diff --git a/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.i18n.yaml b/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.i18n.yaml index a2f32a437d..fadc63d52e 100644 --- a/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.i18n.yaml @@ -9,8 +9,8 @@ en: de9b76d89795ccec zh: 588d45b7d9ca9582 /agent-note-apply-patch-file-editing/decision: - en: 5215c99707a56350 - zh: 3762956afb5657bd + en: 96c7c9c4d2a6800d + zh: 0618c4eb26378f98 /agent-note-apply-patch-file-editing/alternatives-considered: en: ba041bf84ae114a0 zh: 314c4a01afeaf37e diff --git a/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.md b/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.md index 7b5f80e05a..9ba2131d4e 100644 --- a/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.md +++ b/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.md @@ -20,7 +20,7 @@ Commit reports return `isError: false` so completed diff metadata survives a sto [Review capture](../../../../packages/deliverables/workspace-changes/README.md) uses filesystem intent listeners, not argument parsing. `tools/pre-execute` associates the execution with its turn recorder; prepended write, edit, and delete listeners first await the policy decision, then await capture before provider mutation. Moves capture both endpoints. Each turn retains its first baseline and compares actual final bytes, so repeated edits yield one net diff and reverted changes disappear. Existing size, count, time, location, and Session-lifetime limits remain. -`tool-fs.applyPatch` defaults to `false`; `dsh-base` (headless, SDK, and ACP) and the Web `standard` preset enable it after an evaluation on the shipped compositions, keeping the SDK and Desktop `standard` tool sets equal, while the Web `ptc` and `cordis` presets state `applyPatch: false` on their `tool-fs` rows so each is a one-line change; the SDK/Desktop parity exceptions record that the SDK PTC overlay keeps the base row while the Desktop PTC preset lists its own. The tool consults the `fs/*` intent waterfalls like `write` and `edit`, and `dsh-base` ships the `fs-observation-policy` row `disabled: true`, so every mutating tool runs unconditionally unless a deployment enables that row. Across 2,226 recorded DS-Bench and DeepSWE rollouts with the policy on, 14% of `apply_patch` calls were rejected for sending the Codex parameter name `input` (the schema now uses it), 20–27% of the remaining failures were read-first refusals, and 9–14% stale-version refusals of patches whose hunks matched the current file; hunk context matching already rejects a divergent file, and a follow-up evaluation with the policy off decided its default. The `apply_patch` guidance asks for enough hunk context rather than a prior read; the `write` and `edit` guidance keeps asking for a prior read without naming the policy. The tool registers its schema, guidance, native/PTC execution, and tool presentation through plugin effects; the agent loop is unchanged. +`tool-fs.applyPatch` defaults to `false`, so every shipped composition keeps the model request it had before the tool existed; the `tool-fs` rows that enable `edit` (`dsh-base` and the Web `standard`, `ptc`, and `cordis` presets) state `applyPatch: false`, and a deployment turns the tool on by changing that one line, or by a profile patch on the `tool-fs` id where no preset owns the row. The tool consults the `fs/*` intent waterfalls like `write` and `edit`, so the mounted observation policy requires a prior read and rejects stale versions for every patch operation. The schema names its argument `input` as the Codex tool does: across 2,226 recorded DS-Bench and DeepSWE rollouts, 14% of `apply_patch` calls arrived with that key and were rejected while the argument was named `patch`. The tool registers its schema, guidance, native/PTC execution, and tool presentation through plugin effects; the agent loop is unchanged. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.zh.md b/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.zh.md index 83892825be..c016319cb9 100644 --- a/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.zh.md +++ b/.agents/notes/implemented/feature/2026-09-28-apply-patch-file-editing.zh.md @@ -20,7 +20,7 @@ Status: implemented [Review 采集](../../../../packages/deliverables/workspace-changes/README.zh.md)使用文件系统 intent 监听器,不解析参数。`tools/pre-execute` 将执行关联到轮次记录器;前置的 write、edit 和 delete 监听器先等待策略决策,再等待捕获完成,然后提供方才修改文件。移动捕获两端。每轮保留首次基线,比较实际最终字节,因此重复编辑形成一份净 diff,还原的变化不再显示。现有大小、数量、时间、位置和 Session 生命周期限制保持适用。 -`tool-fs.applyPatch` 默认为 `false`;`dsh-base`(headless、SDK、ACP)与 Web 的 `standard` preset 在对随发行版交付的组合做过评测后开启它,使 SDK 与 Desktop 的 `standard` 工具集保持一致,而 Web 的 `ptc`、`cordis` preset 在各自 `tool-fs` 行上显式写出 `applyPatch: false`,每处都是一行改动;SDK/Desktop 一致性例外记录了 SDK 的 PTC overlay 沿用 base 行而 Desktop 的 PTC preset 自列一行。该工具像 `write` 和 `edit` 一样咨询 `fs/*` intent waterfall,而 `dsh-base` 以 `disabled: true` 交付 `fs-observation-policy` 行,因此除非部署启用该行,所有修改工具都无条件执行。在策略开启下录制的 2,226 条 DS-Bench 与 DeepSWE 轨迹中,14% 的 `apply_patch` 调用因使用 Codex 的参数名 `input` 被拒(schema 现已采用该名),其余失败里 20–27% 是先读拒绝、9–14% 是 hunk 能匹配当前文件却因版本过期被拒;hunk 上下文匹配本身已能拒绝内容偏离的文件,随后一轮关闭策略的评测决定了它的默认值。`apply_patch` 的提示语要求给足 hunk 上下文而非先读;`write` 与 `edit` 的提示语仍要求先读,但不再点名该策略。工具通过插件 effect 注册 schema、指导文本、native/PTC 执行与调用展示;不修改 agent loop(智能体循环)。 +`tool-fs.applyPatch` 默认为 `false`,因此所有随发行版交付的组合保持该工具出现之前的模型请求;启用 `edit` 的 `tool-fs` 行(`dsh-base` 以及 Web 的 `standard`、`ptc`、`cordis` preset)显式写出 `applyPatch: false`,部署只需改这一行即可开启,或在没有 preset 拥有该行时通过针对 `tool-fs` id 的 profile patch 开启。该工具像 `write` 和 `edit` 一样咨询 `fs/*` intent waterfall,因此已挂载的观察策略对每个补丁操作要求先读并拒绝过期版本。schema 沿用 Codex 的参数名 `input`:在 2,226 条 DS-Bench 与 DeepSWE 录制轨迹中,14% 的 `apply_patch` 调用带着这个键发出,而参数名为 `patch` 时它们都被拒绝。工具通过插件 effect 注册 schema、指导文本、native/PTC 执行与调用展示;不修改 agent loop(智能体循环)。 ## 考虑过的替代方案 diff --git a/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl b/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl index b9bee477bd..3f3dee9c95 100644 --- a/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl +++ b/apps/cli/tests/profiles/headless/tests/expected/subagent-inheritance/parent.expected.jsonl @@ -17,8 +17,8 @@ {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[2],"surfaceOp":{"op":"replace","startSeq":2,"endSeq":2}} {"type":"user/message","data":{"content":[{"type":"text","text":"Delegate the write probe to a subagent."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: read-only. Any available operation enforced by the DSH file sandbox cannot modify files in the standing mode. Do not refuse a required modification from this policy alone: try an available tool normally and follow any denial and escalation guidance it returns."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","reasoningEffort":"low"},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"resume","startsSeries":true}} -{"type":"developer/message","data":{"turn":2,"step":1,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"apply_patch"},{"type":"tool-addition","toolName":"bash"},{"type":"tool-addition","toolName":"create_goal"},{"type":"tool-addition","toolName":"edit"},{"type":"tool-addition","toolName":"get_goal"},{"type":"tool-addition","toolName":"glob"},{"type":"tool-addition","toolName":"grep"},{"type":"tool-addition","toolName":"interrupt_agent"},{"type":"tool-addition","toolName":"job_kill"},{"type":"tool-addition","toolName":"job_list"},{"type":"tool-addition","toolName":"job_output"},{"type":"tool-addition","toolName":"list_agents"},{"type":"tool-addition","toolName":"read"},{"type":"tool-addition","toolName":"read_image"},{"type":"tool-addition","toolName":"send_message"},{"type":"tool-addition","toolName":"skill"},{"type":"tool-addition","toolName":"subagent"},{"type":"tool-addition","toolName":"subagent_fork"},{"type":"tool-addition","toolName":"todo_write"},{"type":"tool-addition","toolName":"update_goal"},{"type":"tool-addition","toolName":"web_fetch"},{"type":"tool-addition","toolName":"web_search"},{"type":"tool-addition","toolName":"workflow"},{"type":"tool-addition","toolName":"working_directory"},{"type":"tool-addition","toolName":"write"}],"role":"developer","id":"{{sessionId}}"},"headerSeq":18},"surfaceOp":"append"} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","reasoningEffort":"low"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"resume","startsSeries":true}} +{"type":"developer/message","data":{"turn":2,"step":1,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"bash"},{"type":"tool-addition","toolName":"create_goal"},{"type":"tool-addition","toolName":"edit"},{"type":"tool-addition","toolName":"get_goal"},{"type":"tool-addition","toolName":"glob"},{"type":"tool-addition","toolName":"grep"},{"type":"tool-addition","toolName":"interrupt_agent"},{"type":"tool-addition","toolName":"job_kill"},{"type":"tool-addition","toolName":"job_list"},{"type":"tool-addition","toolName":"job_output"},{"type":"tool-addition","toolName":"list_agents"},{"type":"tool-addition","toolName":"read"},{"type":"tool-addition","toolName":"read_image"},{"type":"tool-addition","toolName":"send_message"},{"type":"tool-addition","toolName":"skill"},{"type":"tool-addition","toolName":"subagent"},{"type":"tool-addition","toolName":"subagent_fork"},{"type":"tool-addition","toolName":"todo_write"},{"type":"tool-addition","toolName":"update_goal"},{"type":"tool-addition","toolName":"web_fetch"},{"type":"tool-addition","toolName":"web_search"},{"type":"tool-addition","toolName":"workflow"},{"type":"tool-addition","toolName":"working_directory"},{"type":"tool-addition","toolName":"write"}],"role":"developer","id":"{{sessionId}}"},"headerSeq":18},"surfaceOp":"append"} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Tighten this session to read-only.","messageSeqs":[3],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"delegate-write","name":"subagent","arguments":"{\"description\": \"Delegated write probe\", \"prompt\": \"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"delegate-write","name":"subagent","args":["{\"description\": \"Delegated write probe\", \"prompt\": \"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE.\"}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"delegate-write","name":"subagent","arguments":"{\"description\": \"Delegated write probe\", \"prompt\": \"Use the write tool exactly once with file_path set to exactly the relative path inherited.txt and content escaped. If the write is denied, reply with the single word CHILD_DENIED and the denial marker line; do not retry and do not request escalation. If it succeeds, reply CHILD_WROTE.\"}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} diff --git a/apps/cli/tests/profiles/sdk/tool-parity.ts b/apps/cli/tests/profiles/sdk/tool-parity.ts index 98164dd9fa..fce089fc02 100644 --- a/apps/cli/tests/profiles/sdk/tool-parity.ts +++ b/apps/cli/tests/profiles/sdk/tool-parity.ts @@ -18,8 +18,6 @@ export const toolParityExceptions: Record = { reason: 'SDK PTC changes are persisted for restart without replacing active bindings because HMR is disabled; Desktop PTC excludes management in its HMR-enabled preset.' }, { tool: 'workflow', side: 'sdk', reason: 'The SDK PTC overlay changes only the executor so existing base workflow callers keep working; Desktop PTC uses run_code orchestration and omits the separate workflow surface.' }, - { tool: 'apply_patch', side: 'sdk', - reason: 'The SDK PTC overlay keeps the base tool-fs row, which ships apply_patch beside edit; the Desktop PTC preset lists its own tool-fs row with applyPatch: false.' }, ], } diff --git a/apps/cli/tests/web-agent-presets.e2e.ts b/apps/cli/tests/web-agent-presets.e2e.ts index 3bba385a43..baac502987 100644 --- a/apps/cli/tests/web-agent-presets.e2e.ts +++ b/apps/cli/tests/web-agent-presets.e2e.ts @@ -300,7 +300,7 @@ describe('the shipped Web composition', () => { // excluded for the reason the TUI composition e2e excludes them — they // depend on ripgrep being present on the machine. expect(toolNames(ctx, handle.agent).filter(name => name !== 'glob' && name !== 'grep')).toEqual([ - 'apply_patch', 'ask_user_question', 'bash', 'create_goal', 'edit', 'exit_plan_mode', + 'ask_user_question', 'bash', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'interrupt_agent', 'job_kill', 'job_list', 'job_output', 'list_agents', 'list_subagent_models', 'plugin_manager', 'present', 'read', 'read_image', 'schedule_create', 'schedule_delete', 'schedule_list', 'schedule_update', 'send_message', 'skill', diff --git a/apps/web/tests/shipped-composition.e2e.ts b/apps/web/tests/shipped-composition.e2e.ts index f676896f34..ceb4b4644b 100644 --- a/apps/web/tests/shipped-composition.e2e.ts +++ b/apps/web/tests/shipped-composition.e2e.ts @@ -473,7 +473,6 @@ function assertLeanChildRecord(agent: Agent): void { * Agent Note owns the rationale and its sources. */ const EXPECTED_TOOLS = [ - 'apply_patch', 'ask_user_question', 'bash', 'create_goal', diff --git a/docs/subsystems/filesystem.i18n.yaml b/docs/subsystems/filesystem.i18n.yaml index b331ce4883..b8eb98d2a0 100644 --- a/docs/subsystems/filesystem.i18n.yaml +++ b/docs/subsystems/filesystem.i18n.yaml @@ -3,8 +3,8 @@ # After editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/subsystems/filesystem.md /filesystem: - en: b700f9ad23d45a4a - zh: 4ab2fecc66704f11 + en: 43c2a032cfbcfb13 + zh: 7781e8b14e143381 /filesystem/target-identity-and-metadata-provider-contract: en: 1e55f1c74f0ade3f zh: faecf389a2fb0a93 diff --git a/docs/subsystems/filesystem.md b/docs/subsystems/filesystem.md index 98ac05100d..db2500ebaf 100644 --- a/docs/subsystems/filesystem.md +++ b/docs/subsystems/filesystem.md @@ -4,7 +4,7 @@ English | [中文](filesystem.zh.md) The optional filesystem capability composes these roles: [dsh-fs](../../packages/fs/fs) owns `ctx.fs` and guarded file mutations, [dsh-fs-local](../../packages/fs/fs-local) implements local disk, [dsh-fs-observation-policy](../../packages/fs/fs-observation-policy) records observed presence or absence and adds freshness rules through events rather than a service, and [dsh-tool-fs](../../packages/fs/tool-fs) directly executes model-facing read/write/edit calls and renders windows. It is outside the agent-loop spine; alternate backends do not change policy or tool schemas. The pure [dsh-fs-patch](../../packages/fs/fs-patch/README.md) library supplies patch parsing and text application. -`dsh-fs-observation-policy` is optional. Without it, the `FileSystem` Service Definition, a provider, and the `dsh-tool-fs` Consumer form the complete, unconstrained filesystem seam: `write` unconditionally creates or overwrites, and `edit` unconditionally replaces literal text. The policy plugin changes these operations by deciding the `fs/*` waterfalls. Removing it does not break the tool because the tool calls `ctx.fs` and dispatches events; it does not call policy methods. The shipped compositions run without it: `dsh-base` lists the `fs-observation-policy` row `disabled: true`, and a deployment that wants read-before-write/edit sets that row to `false`. +`dsh-fs-observation-policy` is optional. Without it, the `FileSystem` Service Definition, a provider, and the `dsh-tool-fs` Consumer form the complete, unconstrained filesystem seam: `write` unconditionally creates or overwrites, and `edit` unconditionally replaces literal text. The policy plugin changes these operations by deciding the `fs/*` waterfalls. Removing it does not break the tool because the tool calls `ctx.fs` and dispatches events; it does not call policy methods. A deployment that loads `dsh-tool-fs` is expected to also load `dsh-fs-observation-policy` so the default behavior is read-before-write/edit. Provider source: [`packages/fs/fs/src/types.ts`](../../packages/fs/fs/src/types.ts) and [`packages/fs/fs/src/index.ts`](../../packages/fs/fs/src/index.ts). Policy source: [`packages/fs/fs-observation-policy/src/types.ts`](../../packages/fs/fs-observation-policy/src/types.ts). Read-rendering source: [`packages/fs/tool-fs/src/read-render.ts`](../../packages/fs/tool-fs/src/read-render.ts). diff --git a/docs/subsystems/filesystem.zh.md b/docs/subsystems/filesystem.zh.md index 915f925c63..a5cc8a9973 100644 --- a/docs/subsystems/filesystem.zh.md +++ b/docs/subsystems/filesystem.zh.md @@ -4,7 +4,7 @@ 可选的文件系统能力由以下角色组成:[dsh-fs](../../packages/fs/fs) 拥有 `ctx.fs` 和受防护的文件变更操作;[dsh-fs-local](../../packages/fs/fs-local) 实现本地磁盘后端;[dsh-fs-observation-policy](../../packages/fs/fs-observation-policy) 记录观测到的存在或缺失状态,并通过事件(而非服务)添加新鲜度规则;[dsh-tool-fs](../../packages/fs/tool-fs) 直接执行面向模型的 read/write/edit 调用并渲染窗口。它位于 agent loop(智能体循环)主干之外;替换后端不会改变策略或工具 schema。纯库 [dsh-fs-patch](../../packages/fs/fs-patch/README.zh.md) 提供补丁解析与文本应用。 -`dsh-fs-observation-policy` 是可选插件。没有该插件时,`FileSystem` 服务定义、一个提供方和 `dsh-tool-fs` 消费方组成完整且不受约束的文件系统 seam:`write` 无条件创建或覆盖,`edit` 无条件替换字面文本。策略插件通过裁决 `fs/*` waterfall(瀑布式事件)来改变这些操作。移除该插件不会破坏工具,因为工具调用 `ctx.fs` 并分发事件,而不调用策略方法。随发行版交付的组合不启用它:`dsh-base` 中的 `fs-observation-policy` 行写着 `disabled: true`,需要「先读后写/编辑」的部署把该行改为 `false`。 +`dsh-fs-observation-policy` 是可选插件。没有该插件时,`FileSystem` 服务定义、一个提供方和 `dsh-tool-fs` 消费方组成完整且不受约束的文件系统 seam:`write` 无条件创建或覆盖,`edit` 无条件替换字面文本。策略插件通过裁决 `fs/*` waterfall(瀑布式事件)来改变这些操作。移除该插件不会破坏工具,因为工具调用 `ctx.fs` 并分发事件,而不调用策略方法。加载了 `dsh-tool-fs` 的部署也应加载 `dsh-fs-observation-policy`,使默认行为为「先读后写/编辑」。 提供方源码:[`packages/fs/fs/src/types.ts`](../../packages/fs/fs/src/types.ts) 与 [`packages/fs/fs/src/index.ts`](../../packages/fs/fs/src/index.ts)。策略源码:[`packages/fs/fs-observation-policy/src/types.ts`](../../packages/fs/fs-observation-policy/src/types.ts)。读取渲染源码:[`packages/fs/tool-fs/src/read-render.ts`](../../packages/fs/tool-fs/src/read-render.ts)。 diff --git a/docs/tool-catalog.i18n.yaml b/docs/tool-catalog.i18n.yaml index 50eb0de62c..d670fbe0f4 100644 --- a/docs/tool-catalog.i18n.yaml +++ b/docs/tool-catalog.i18n.yaml @@ -9,8 +9,8 @@ en: 6cc2cd9ced70bb09 zh: 1c0e6cb4ba2ed637 /tool-schema-catalog/tool-package-map: - en: b44b9a6aad8b74d6 - zh: 455ca9f6b37c7b16 + en: 2615753236eba27b + zh: 79d0231bb539567e /tool-schema-catalog/deepseek-ai-dsh-plugin-manager: en: e0143916bb634762 zh: e0143916bb634762 @@ -141,8 +141,8 @@ en: f6f7a1140066ce04 zh: d528e01a0939795a /tool-schema-catalog/deepseek-ai-dsh-tool-fs/write: - en: d1330f74cbd84a08 - zh: 78affbbeb71e608a + en: af50ae531075cf26 + zh: 974da3c5fbfa5959 /tool-schema-catalog/deepseek-ai-dsh-tool-fs-search: en: 703fea005ce84c50 zh: 703fea005ce84c50 diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index cf3c615b95..e8a18d5919 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -30,7 +30,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.workingDirectory`, `ctx.tools`, `ctx.terminals`, `an owning Agent at execution time` | `tool/call`, `PTY shell state`, `tool/result` | - | One owner-isolated persistent bash tool; deployment composition supplies the PTY backend and may override the model-facing environment description. | | `@deepseek-ai/dsh-tool-pwsh-persistent` | `pwsh` | `ctx.workingDirectory`, `ctx.tools`, `ctx.terminals`, `an owning Agent at execution time` | `tool/call`, `PTY shell state`, `tool/result` | - | One owner-isolated persistent pwsh tool, the Windows counterpart of the persistent bash tool; deployment composition supplies a pwsh-dialect PTY backend and may override the model-facing environment description. | | `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`, `ctx.fs` | `tool/call`, `fs/observed after view presence/absence, edit absence, or successful mutation`, `tool/result` | - | Standalone view/create/unique literal replace/line insert tool over the filesystem seam; it composes with any shell or terminal API. | -| `@deepseek-ai/dsh-tool-fs` | `apply_patch`, `edit`, `read`, `read_image`, `write` | `ctx.workingDirectory`, `ctx.tools`, `ctx.fs`, `ctx.systemPrompt`, `ctx.attachments (image-tool registration)`, `ctx.llm + an image-capable route (image-tool execution)` | `tool/call`, `fs/write-intent, fs/edit-intent, or fs/delete-intent for mutations`, `fs/observed after read presence/absence or successful file operation`, `durable attachment (read_image)`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-observation-policy` (an `fs/*` event-gate plugin, no schema change); the shipped compositions leave its row disabled, so mutations are unconditional unless a deployment enables it. The image tool is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. `apply_patch` registers only with `applyPatch: true`; the catalog sets it so the schema is documented, while shipped compositions keep the switch off on their `tool-fs` rows. | +| `@deepseek-ai/dsh-tool-fs` | `apply_patch`, `edit`, `read`, `read_image`, `write` | `ctx.workingDirectory`, `ctx.tools`, `ctx.fs`, `ctx.systemPrompt`, `ctx.attachments (image-tool registration)`, `ctx.llm + an image-capable route (image-tool execution)` | `tool/call`, `fs/write-intent, fs/edit-intent, or fs/delete-intent for mutations`, `fs/observed after read presence/absence or successful file operation`, `durable attachment (read_image)`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-observation-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The image tool is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. `apply_patch` registers only with `applyPatch: true`; the catalog sets it so the schema is documented, while shipped compositions keep the switch off on their `tool-fs` rows. | | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.workingDirectory`, `ctx.tools`, `ctx.subprocess`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are unconditional discovery tools that spawn the packaged ripgrep binary (`@vscode/ripgrep`) through ctx.subprocess as ordinary foreground calls (never background jobs) — no host `rg` install and no shell layer. The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-terminal` | `terminal_close`, `terminal_list`, `terminal_open`, `terminal_read`, `terminal_send`, `terminal_signal` | `ctx.workingDirectory`, `ctx.tools`, `ctx.terminals`, `ctx.systemPrompt`, `ctx.jobs at call time for run_in_background` | `tool/call`, `tool/result` | - | The six terminal tools are opt-in and complement one-shot shell/filesystem tools. `terminal_send(run_in_background: true)` registers with `ctx.jobs`; TUI, named key sequences, BEL, resize, auto-start, and cross-agent sharing are absent from the schema. | | `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `goal/change for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. | @@ -1053,7 +1053,7 @@ Create, update, delete, or move UTF-8 text files with one Codex-style patch; pre "properties": { "input": { "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." + "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. Read existing files before updating, deleting, or moving them." } }, "required": [ @@ -1175,7 +1175,7 @@ Create or fully replace a UTF-8 text file. Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) -The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-observation-policy` (an `fs/*` event-gate plugin, no schema change); the shipped compositions leave its row disabled, so mutations are unconditional unless a deployment enables it. The image tool is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. `apply_patch` registers only with `applyPatch: true`; the catalog sets it so the schema is documented, while shipped compositions keep the switch off on their `tool-fs` rows. +The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-observation-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The image tool is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. `apply_patch` registers only with `applyPatch: true`; the catalog sets it so the schema is documented, while shipped compositions keep the switch off on their `tool-fs` rows. diff --git a/docs/tool-catalog.zh.md b/docs/tool-catalog.zh.md index be094cdf03..666fc8e0d7 100644 --- a/docs/tool-catalog.zh.md +++ b/docs/tool-catalog.zh.md @@ -34,7 +34,7 @@ | `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.workingDirectory`、`ctx.tools`、`ctx.terminals`、`an owning Agent at execution time` | `tool/call`、`PTY shell state`、`tool/result` | - | 一个按所有者隔离的持久 bash 工具;部署组合提供 PTY 后端,并可覆盖面向模型的环境描述。 | | `@deepseek-ai/dsh-tool-pwsh-persistent` | `pwsh` | `ctx.workingDirectory`、`ctx.tools`、`ctx.terminals`、`an owning Agent at execution time` | `tool/call`、`PTY shell state`、`tool/result` | - | 一个按所有者隔离的持久 pwsh 工具,持久 bash 工具的 Windows 对应物;部署组合提供 pwsh 方言的 PTY 后端,并可覆盖面向模型的环境描述。 | | `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`、`ctx.fs` | `tool/call`、`fs/observed after view presence/absence, edit absence, or successful mutation`、`tool/result` | - | 基于文件系统 seam 的独立查看/创建/唯一字面量替换/按行插入工具;可与任何 shell 或终端接口组合。 | -| `@deepseek-ai/dsh-tool-fs` | `apply_patch`、`edit`、`read`、`read_image`、`write` | `ctx.workingDirectory`、`ctx.tools`、`ctx.fs`、`ctx.systemPrompt`、`ctx.attachments (image-tool registration)`、`ctx.llm + an image-capable route (image-tool execution)` | `tool/call`、`fs/write-intent, fs/edit-intent, or fs/delete-intent for mutations`、`fs/observed after read presence/absence or successful file operation`、`durable attachment (read_image)`、`tool/result` | - | 先读后写/编辑策略由 `@deepseek-ai/dsh-fs-observation-policy` 添加;它是一个 `fs/*` 事件门禁插件,不会改变 schema。随发行版交付的组合保持该行禁用,因此除非部署启用它,修改都是无条件的。没有 `ctx.attachments` 时图片工具不会注册;其 schema 与路由无关,执行时除非确切路由的模型声明图片输入,否则拒绝。`apply_patch` 仅在 `applyPatch: true` 时注册;目录为了记录其 schema 而开启该开关,而随发行版交付的组合在各自的 `tool-fs` 行上保持关闭。 | +| `@deepseek-ai/dsh-tool-fs` | `apply_patch`、`edit`、`read`、`read_image`、`write` | `ctx.workingDirectory`、`ctx.tools`、`ctx.fs`、`ctx.systemPrompt`、`ctx.attachments (image-tool registration)`、`ctx.llm + an image-capable route (image-tool execution)` | `tool/call`、`fs/write-intent, fs/edit-intent, or fs/delete-intent for mutations`、`fs/observed after read presence/absence or successful file operation`、`durable attachment (read_image)`、`tool/result` | - | 先读后写/编辑策略由 `@deepseek-ai/dsh-fs-observation-policy` 添加;它是一个 `fs/*` 事件门禁插件,不会改变 schema。加载这些工具的部署按预期也应加载该插件。没有 `ctx.attachments` 时图片工具不会注册;其 schema 与路由无关,执行时除非确切路由的模型声明图片输入,否则拒绝。`apply_patch` 仅在 `applyPatch: true` 时注册;目录为了记录其 schema 而开启该开关,而随发行版交付的组合在各自的 `tool-fs` 行上保持关闭。 | | `@deepseek-ai/dsh-tool-fs-search` | `glob`、`grep` | `ctx.workingDirectory`、`ctx.tools`、`ctx.subprocess`、`ctx.systemPrompt` | `tool/call`、`tool/result` | - | glob 和 grep 是无条件可用的发现工具,通过 ctx.subprocess spawn 随包提供的 ripgrep 二进制文件(`@vscode/ripgrep`),并作为普通前台调用运行,绝不作为后台任务;无需在宿主机安装 `rg`,也不经过 shell 层。本目录使用 `sampleOverCapGlobResults: true`;部署必须显式选择该行为。结果超过上限时,会通过可选的 ctx.spillStore 后端保存完整的格式化列表;在共置部署中,如果后端公开本地路径,返回的定位信息可供后续读取/搜索。 | | `@deepseek-ai/dsh-tool-terminal` | `terminal_close`、`terminal_list`、`terminal_open`、`terminal_read`、`terminal_send`、`terminal_signal` | `ctx.workingDirectory`、`ctx.tools`、`ctx.terminals`、`ctx.systemPrompt`、`ctx.jobs at call time for run_in_background` | `tool/call`、`tool/result` | - | 这 6 个终端工具需要选择启用,用于补充一次性 bash/文件系统工具。`terminal_send(run_in_background: true)` 会注册到 `ctx.jobs`;schema 不包含 TUI、具名按键序列、BEL、调整尺寸、自动启动和跨 agent 共享。 | | `@deepseek-ai/dsh-tool-goal` | `create_goal`、`get_goal`、`update_goal` | `ctx.tools`、`ctx.agents`、`ctx.goals`、`ctx.systemPrompt`、`a calling Agent in an authorized open turn` | `tool/call`、`goal/change for mutations`、`tool/result` | - | create、edit、pause 和 resume 要求直接来自人类的根权限;complete 和 blocked 也接受确切的当前 Goal Round。blocked 的默认下限是 3 个获准的 Round。 | @@ -1059,7 +1059,7 @@ pwsh 工具是 Windows 组合中 bash 执行器 seam 的 PowerShell 方言消费 "properties": { "input": { "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." + "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. Read existing files before updating, deleting, or moving them." } }, "required": [ @@ -1181,7 +1181,7 @@ pwsh 工具是 Windows 组合中 bash 执行器 seam 的 PowerShell 方言消费 来源:[`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) -先读后写/编辑策略由 `@deepseek-ai/dsh-fs-observation-policy` 添加;它是一个 `fs/*` 事件门禁插件,不会改变 schema。随发行版交付的组合保持该行禁用,因此除非部署启用它,修改都是无条件的。没有 `ctx.attachments` 时图片工具不会注册;其 schema 与路由无关,执行时除非确切路由的模型声明图片输入,否则拒绝。`apply_patch` 仅在 `applyPatch: true` 时注册;目录为了记录其 schema 而开启该开关,而随发行版交付的组合在各自的 `tool-fs` 行上保持关闭。 +先读后写/编辑策略由 `@deepseek-ai/dsh-fs-observation-policy` 添加;它是一个 `fs/*` 事件门禁插件,不会改变 schema。加载这些工具的部署按预期也应加载该插件。没有 `ctx.attachments` 时图片工具不会注册;其 schema 与路由无关,执行时除非确切路由的模型声明图片输入,否则拒绝。`apply_patch` 仅在 `applyPatch: true` 时注册;目录为了记录其 schema 而开启该开关,而随发行版交付的组合在各自的 `tool-fs` 行上保持关闭。 diff --git a/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.i18n.yaml b/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.i18n.yaml deleted file mode 100644 index f8b9475dc6..0000000000 --- a/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.i18n.yaml +++ /dev/null @@ -1,16 +0,0 @@ -# Bilingual-pair consistency record for guide.md (docs/i18n/README.md): per heading -# section, a hash of its English and Chinese blocks outside code blocks and generated regions. -# After editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.md -/: - en: 94b863d7f57ffb37 - zh: 158af8a6f172ee5f -/filesystem-mutations-no-longer-require-a-prior-read-by-default: - en: e6dd0c06f99737e4 - zh: a706b0bbdea94aac -/filesystem-mutations-no-longer-require-a-prior-read-by-default/change: - en: 50d421177ba7d458 - zh: 2190ebc2e146551c -/filesystem-mutations-no-longer-require-a-prior-read-by-default/migration: - en: 2d675e59b9ca21b7 - zh: 455c0af0eb3e80f4 diff --git a/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.md b/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.md deleted file mode 100644 index a66a886ebc..0000000000 --- a/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.md +++ /dev/null @@ -1,29 +0,0 @@ ---- -kind: upgrade-guide -description: "The fs-observation-policy row ships disabled, so write, edit, and apply_patch no longer require a prior read, and dsh-base plus the Web standard preset gain apply_patch." ---- - -# Filesystem mutations no longer require a prior read by default - -English | [中文](guide.zh.md) - -## Change - -In 0.2.2-alpha.2, `dsh-base` mounted `@deepseek-ai/dsh-fs-observation-policy`, so in every shipped profile `write` refused to overwrite a file the model had not read, `edit` refused an unread or externally changed file, and the model's guidance named the policy. The `fs-observation-policy` row now ships `disabled: true`: `write` overwrites, `edit` replaces literal text, and the new `apply_patch` applies hunks on context match alone, each unconditionally. The `write` and `edit` guidance still asks for a prior read but no longer cites the policy. Review capture, sandbox confinement, and `fs/observed` events are unchanged. - -The `dsh-base` `tool-fs` row (headless, SDK, and ACP) and the Web `standard` preset now list `apply_patch` (`applyPatch: true`); the Web `ptc` and `cordis` presets keep `applyPatch: false`. - -Affected: every shipped profile (`headless`, `web`, `sdk`, `sdk-minimal`, `acp`), profile patches that override the `fs-observation-policy` or `tool-fs` rows by id, and recorded expectations that include an `FS_NOT_OBSERVED` or `FS_STALE_VERSION` refusal. - -## Migration - -1. To keep read-before-write behavior, add to the profile's `cordis.patch.yml` (`$DSH_HOME/profiles//cordis.patch.yml`): - - ```yaml - - id: fs-observation-policy - disabled: false - ``` - - A profile patch that already carries this row with `disabled: false` needs no change; one that set `disabled: true` to opt out can drop that override. -2. To run without `apply_patch`, add `- {id: tool-fs, config: {applyPatch: false}}` to the profile's `cordis.patch.yml` for `headless`, `sdk`, and `acp`; for the Web `standard` preset, edit it from the Agent presets settings page or set `applyPatch: false` on its `tool-fs` row in `packages/bundle/web-app/presets/standard.patch.yml`. -3. Confirm with `dsh --profile --dump-config`: the `fs-observation-policy` row shows the intended `disabled` value, and the `tool-fs` rows show the intended `applyPatch` value. In a session, an `edit` of a file that was not read succeeds with the row disabled and fails with `FS_NOT_OBSERVED` with it enabled. diff --git a/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.zh.md b/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.zh.md deleted file mode 100644 index 064c97d6a4..0000000000 --- a/docs/upgrade-guide/v0.2.2-alpha.2/fs-observation-policy-default-off/guide.zh.md +++ /dev/null @@ -1,29 +0,0 @@ ---- -kind: upgrade-guide -description: "fs-observation-policy 行随发行版禁用,write、edit 与 apply_patch 不再要求先读,dsh-base 与 Web standard preset 新增 apply_patch。" ---- - -# 文件系统修改默认不再要求先读 - -[English](guide.md) | 中文 - -## 变更 - -在 0.2.2-alpha.2 中,`dsh-base` 挂载了 `@deepseek-ai/dsh-fs-observation-policy`,因此所有随发行版交付的 profile 中,`write` 拒绝覆盖模型未读过的文件,`edit` 拒绝未读或被外部修改的文件,模型提示语也点名该策略。现在 `fs-observation-policy` 行以 `disabled: true` 交付:`write` 直接覆盖,`edit` 直接替换字面文本,新增的 `apply_patch` 只凭上下文匹配应用 hunk,三者均无条件执行。`write` 与 `edit` 的提示语仍要求先读,但不再引用该策略。Review 采集、沙箱围栏与 `fs/observed` 事件不变。 - -`dsh-base` 的 `tool-fs` 行(headless、SDK、ACP)与 Web 的 `standard` preset 现在列出 `apply_patch`(`applyPatch: true`);Web 的 `ptc`、`cordis` preset 保持 `applyPatch: false`。 - -受影响范围:所有随发行版交付的 profile(`headless`、`web`、`sdk`、`sdk-minimal`、`acp`),按 id 覆盖 `fs-observation-policy` 或 `tool-fs` 行的 profile patch,以及包含 `FS_NOT_OBSERVED` 或 `FS_STALE_VERSION` 拒绝的录制期望。 - -## 迁移 - -1. 要保留先读后写行为,在 profile 的 `cordis.patch.yml`(`$DSH_HOME/profiles//cordis.patch.yml`)中加入: - - ```yaml - - id: fs-observation-policy - disabled: false - ``` - - 已带有该行且 `disabled: false` 的 profile patch 无需改动;为退出策略而写 `disabled: true` 的可以删掉该覆盖。 -2. 要在没有 `apply_patch` 的情况下运行,为 `headless`、`sdk`、`acp` 在 profile 的 `cordis.patch.yml` 中加入 `- {id: tool-fs, config: {applyPatch: false}}`;对 Web `standard` preset,在 Agent presets 设置页编辑它,或在 `packages/bundle/web-app/presets/standard.patch.yml` 的 `tool-fs` 行上设置 `applyPatch: false`。 -3. 用 `dsh --profile --dump-config` 确认:`fs-observation-policy` 行显示预期的 `disabled` 值,`tool-fs` 行显示预期的 `applyPatch` 值。在会话中,行禁用时对未读文件执行 `edit` 成功,启用时以 `FS_NOT_OBSERVED` 失败。 diff --git a/packages/bundle/base/cordis.patch.yml b/packages/bundle/base/cordis.patch.yml index ef931753d9..e37664bb4f 100644 --- a/packages/bundle/base/cordis.patch.yml +++ b/packages/bundle/base/cordis.patch.yml @@ -291,13 +291,12 @@ - id: fs-observation-policy name: '@deepseek-ai/dsh-fs-observation-policy' - disabled: true - id: tool-fs name: '@deepseek-ai/dsh-tool-fs' config: - # Set false to drop the apply_patch tool beside edit. - applyPatch: true + # Set true to add the apply_patch tool beside edit. + applyPatch: false - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' diff --git a/packages/bundle/web-app/presets/standard.patch.yml b/packages/bundle/web-app/presets/standard.patch.yml index a1aff022b0..554c2c9d0e 100644 --- a/packages/bundle/web-app/presets/standard.patch.yml +++ b/packages/bundle/web-app/presets/standard.patch.yml @@ -27,8 +27,8 @@ - id: tool-fs name: '@deepseek-ai/dsh-tool-fs' config: - # Set false to drop the apply_patch tool beside edit. - applyPatch: true + # Set true to add the apply_patch tool beside edit. + applyPatch: false - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' config: diff --git a/packages/fs/fs-observation-policy/README.i18n.yaml b/packages/fs/fs-observation-policy/README.i18n.yaml index 4ef14fa553..52458e6c35 100644 --- a/packages/fs/fs-observation-policy/README.i18n.yaml +++ b/packages/fs/fs-observation-policy/README.i18n.yaml @@ -15,8 +15,8 @@ en: d152484eb41ac6b4 zh: 09388d293f9be9cb /deepseek-ai-dsh-fs-observation-policy/use-this-package: - en: 79359e26da12646b - zh: 78220ab672cf3a7f + en: e45098c59fc9b3ba + zh: 2a12cf800bca1ef6 /deepseek-ai-dsh-fs-observation-policy/use-this-package/minimal-composition: en: d85e3b814b43768e zh: 89d3672dbb2f6d30 diff --git a/packages/fs/fs-observation-policy/README.md b/packages/fs/fs-observation-policy/README.md index ed822e2729..7f76f910b9 100644 --- a/packages/fs/fs-observation-policy/README.md +++ b/packages/fs/fs-observation-policy/README.md @@ -27,7 +27,7 @@ English | [中文](README.zh.md) `fs/delete-intent` requires the same present observation as `fs/edit-intent`: unseen sources fail with `FS_NOT_OBSERVED`, confirmed-absent sources fail with `FS_NOT_FOUND`, and present sources supply their observed version. Patches and move sources reuse `fs/edit-intent`; move destinations reuse `fs/write-intent`. -Load this plugin alongside a `ctx.fs` backend and the `dsh-tool-fs` tools when a deployment wants the model to read a file before it can overwrite or edit it. The plugin needs no configuration and injects no service; it only listens for the `fs/*` events the tools dispatch. The shipped compositions leave it off: [`dsh-base`](../../bundle/base/cordis.patch.yml) lists its `fs-observation-policy` row `disabled: true`, because with the guard on the model spent 20–27% of its `apply_patch` failures on read-first refusals and a further 9–14% on stale-version refusals of patches whose hunks matched, while hunk context already rejects a divergent file; set the row to `false` to restore the guard for every mutating tool. +Load this plugin alongside a `ctx.fs` backend and the `dsh-tool-fs` tools when a deployment wants the model to read a file before it can overwrite or edit it. The plugin needs no configuration and injects no service; it only listens for the `fs/*` events the tools dispatch. ### Minimal composition diff --git a/packages/fs/fs-observation-policy/README.zh.md b/packages/fs/fs-observation-policy/README.zh.md index 52ad60f71e..7c06af8beb 100644 --- a/packages/fs/fs-observation-policy/README.zh.md +++ b/packages/fs/fs-observation-policy/README.zh.md @@ -27,7 +27,7 @@ kind: "package-reference" `fs/delete-intent` 与 `fs/edit-intent` 要求相同的存在观察:未见源以 `FS_NOT_OBSERVED` 失败,确认缺失的源以 `FS_NOT_FOUND` 失败,存在源提供观察到的版本。补丁和移动源复用 `fs/edit-intent`;移动目标复用 `fs/write-intent`。 -当部署希望模型在覆盖或编辑文件之前先读取该文件时,把本插件与 `ctx.fs` 后端及 `dsh-tool-fs` 工具一起加载。插件无需配置,也不注入任何服务;它只监听工具分派的 `fs/*` 事件。随发行版交付的组合默认不启用它:[`dsh-base`](../../bundle/base/cordis.patch.yml) 中的 `fs-observation-policy` 行写着 `disabled: true`,因为开启防护时模型 `apply_patch` 失败里 20–27% 是先读拒绝、另有 9–14% 是 hunk 能匹配却因版本过期被拒,而 hunk 上下文本身已能拒绝内容偏离的文件;把该行改为 `false` 即可为所有修改工具恢复防护。 +当部署希望模型在覆盖或编辑文件之前先读取该文件时,把本插件与 `ctx.fs` 后端及 `dsh-tool-fs` 工具一起加载。插件无需配置,也不注入任何服务;它只监听工具分派的 `fs/*` 事件。 ### 最小组合 diff --git a/packages/fs/tool-fs/README.i18n.yaml b/packages/fs/tool-fs/README.i18n.yaml index 0d2a40c3af..1c5399e50b 100644 --- a/packages/fs/tool-fs/README.i18n.yaml +++ b/packages/fs/tool-fs/README.i18n.yaml @@ -18,14 +18,14 @@ en: c7da73c9e2691ea1 zh: 0eba82c1c3553ab9 /deepseek-ai-dsh-tool-fs/use-this-package/minimal-composition: - en: f0845fd087912fe4 - zh: 4cae06864c73f710 + en: bcd61964469f1a55 + zh: bded1de1c747c641 /deepseek-ai-dsh-tool-fs/use-this-package/the-tools: en: 6e12ea9c79039360 zh: 7230ad3bda4515d5 /deepseek-ai-dsh-tool-fs/use-this-package/configuration: - en: 92b0a816b47159e9 - zh: 1b6ce7b0c7216886 + en: 0a21c4f17d25d1bb + zh: 38b848719f8b9ebf /deepseek-ai-dsh-tool-fs/use-this-package/policy-and-sandbox-behavior: en: 9bddebaf4aff0a8d zh: fea0196162e3fcd1 diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index a7fe94442d..b436f0731c 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -39,7 +39,7 @@ A backend, the policy plugin, then the tools; the attachment store is optional a - name: '@deepseek-ai/dsh-tool-fs' ``` -The policy plugin is optional: without it the tools run against the bare provider (unconditional write, overwrite, edit, and patch with no observed state), which is how the shipped compositions run — [`dsh-base`](../../bundle/base/cordis.patch.yml) lists the `fs-observation-policy` row `disabled: true`; set it to `false` to require prior reads and reject stale versions for every mutating tool. `read_image` registers only while a durable `ctx.attachments` service is mounted; execution additionally refuses on a route whose exact model does not declare image input, so a text route's durable history stays free of image blocks. +The policy plugin is optional: without it the tools run against the bare provider (unconditional write, overwrite, edit, and patch with no observed state). A deployment that loads these tools is expected to also load it, so the behavior is read-before-write/edit/patch. `read_image` registers only while a durable `ctx.attachments` service is mounted; execution additionally refuses on a route whose exact model does not declare image input, so a text route's durable history stays free of image blocks. ### The tools @@ -55,7 +55,7 @@ Field names are snake_case to match Claude Code and existing harness tool schema ### Configuration -All keys are optional. The `read`, `readImage`, `write`, and `edit` switches default to `true`; set a switch to `false` to omit that tool and its guidance. `applyPatch` defaults to `false`; [`dsh-base`](../../bundle/base/cordis.patch.yml) and the Web `standard` preset enable it on their `tool-fs` rows, while the Web `ptc` and `cordis` presets state `applyPatch: false`, and changing that one line adds or drops the tool beside `edit`. All five tools may be disabled. Enabling `readImage` still requires an attachment store and an image-capable model. Read caps remain validated when `read` is disabled. +All keys are optional. The `read`, `readImage`, `write`, and `edit` switches default to `true`; set a switch to `false` to omit that tool and its guidance. `applyPatch` defaults to `false`, so the default composition registers no `apply_patch`; the shipped `tool-fs` rows that enable `edit` ([`dsh-base`](../../bundle/base/cordis.patch.yml) and the Web `standard`, `ptc`, and `cordis` presets) state `applyPatch: false`, and changing that one line to `true` adds the tool beside `edit`. All five tools may be disabled. Enabling `readImage` still requires an attachment store and an image-capable model. Read caps remain validated when `read` is disabled. | Key | Default | Meaning | |---|---|---| @@ -169,13 +169,13 @@ Use the read tool — not shell commands like cat — to inspect text files. Use ##### Write guidance ```markdown -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. ``` ##### Edit guidance ```markdown -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. ``` #### Token effect @@ -265,7 +265,7 @@ The `apply_patch` schema requires one `input` string (the Codex parameter name, ##### System guidance ```markdown -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Prefer apply_patch over separate edit calls for changes across files or separated regions. Read a file before updating, deleting, or moving it (the default fs-observation-policy requires it), unless you just created or edited it in this session. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. ``` ##### Result examples diff --git a/packages/fs/tool-fs/README.zh.md b/packages/fs/tool-fs/README.zh.md index 0b1185a97f..634bdcf692 100644 --- a/packages/fs/tool-fs/README.zh.md +++ b/packages/fs/tool-fs/README.zh.md @@ -39,7 +39,7 @@ kind: "package-reference" - name: '@deepseek-ai/dsh-tool-fs' ``` -策略插件是可选的:省略时,工具直接使用裸提供方(无条件写入、覆盖、编辑与补丁,无已观察状态),随发行版交付的组合就是这样运行的——[`dsh-base`](../../bundle/base/cordis.patch.yml) 中的 `fs-observation-policy` 行写着 `disabled: true`;改为 `false` 即对所有修改工具要求先读并拒绝过期版本。`read_image` 只在持久 `ctx.attachments` 服务已挂载时注册;执行时还拒绝确切模型未声明图像输入的路由,因此文本路由的持久历史不会出现图像块。 +策略插件是可选的:省略时,工具直接使用裸提供方(无条件写入、覆盖、编辑与补丁,无已观察状态)。加载这些工具的部署也应加载该插件,从而提供写入/编辑/补丁前读取行为。`read_image` 只在持久 `ctx.attachments` 服务已挂载时注册;执行时还拒绝确切模型未声明图像输入的路由,因此文本路由的持久历史不会出现图像块。 ### 工具 @@ -55,7 +55,7 @@ kind: "package-reference" ### 配置 -所有键均为可选。`read`、`readImage`、`write` 和 `edit` 开关默认为 `true`;将开关设为 `false` 可省略对应工具及其指导文本。`applyPatch` 默认为 `false`;[`dsh-base`](../../bundle/base/cordis.patch.yml) 与 Web 的 `standard` preset 在各自的 `tool-fs` 行上开启它,而 Web 的 `ptc`、`cordis` preset 显式写出 `applyPatch: false`,改这一行即可在 `edit` 旁加入或去掉该工具。允许关闭全部五个工具。启用 `readImage` 仍需要附件存储和支持图片输入的模型。关闭 `read` 时仍会校验读取上限。 +所有键均为可选。`read`、`readImage`、`write` 和 `edit` 开关默认为 `true`;将开关设为 `false` 可省略对应工具及其指导文本。`applyPatch` 默认为 `false`,因此默认组合不注册 `apply_patch`;启用 `edit` 的随发行版交付的 `tool-fs` 行([`dsh-base`](../../bundle/base/cordis.patch.yml) 以及 Web 的 `standard`、`ptc`、`cordis` preset)显式写出 `applyPatch: false`,把这一行改为 `true` 即在 `edit` 旁加入该工具。允许关闭全部五个工具。启用 `readImage` 仍需要附件存储和支持图片输入的模型。关闭 `read` 时仍会校验读取上限。 | 键 | 默认值 | 含义 | |---|---|---| @@ -169,13 +169,13 @@ Use the read tool — not shell commands like cat — to inspect text files. Use ##### Write 指导 ```markdown -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. ``` ##### Edit 指导 ```markdown -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. ``` #### Token 影响 @@ -265,7 +265,7 @@ Read a file before editing it unless you just created or edited it in this sessi ##### 系统提示 ```markdown -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Prefer apply_patch over separate edit calls for changes across files or separated regions. Read a file before updating, deleting, or moving it (the default fs-observation-policy requires it), unless you just created or edited it in this session. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. ``` ##### 结果示例 diff --git a/packages/fs/tool-fs/src/apply-patch.ts b/packages/fs/tool-fs/src/apply-patch.ts index 93fcd2f410..cdb213e6b8 100644 --- a/packages/fs/tool-fs/src/apply-patch.ts +++ b/packages/fs/tool-fs/src/apply-patch.ts @@ -19,7 +19,7 @@ export function applyApplyPatchTool(ctx: Context, sandbox: FsSandboxController): name: 'tool:apply_patch', order: ctx.systemPrompt.getSectionOrder('TOOL_APPLY_PATCH'), text: ({ scope }) => ctx.tools.get('apply_patch', scope) === undefined ? '' : 'Prefer apply_patch over separate edit calls for changes across files or separated regions. ' - + 'Give every hunk enough surrounding context lines to match one place in the current file. ' + + 'Read a file before updating, deleting, or moving it (the default fs-observation-policy requires it), unless you just created or edited it in this session. ' + 'The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; ' + 'once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed.', }) @@ -34,7 +34,7 @@ export function applyApplyPatchTool(ctx: Context, sandbox: FsSandboxController): + 'Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, ' + 'with @@ or @@ context and space-prefixed context, + added, or - removed lines; ' + '*** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. ' - + 'Paths are relative to the Session working directory.', + + 'Paths are relative to the Session working directory. Read existing files before updating, deleting, or moving them.', }, ...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {}, }, diff --git a/packages/fs/tool-fs/src/edit.ts b/packages/fs/tool-fs/src/edit.ts index f927ccb1cb..2dd594a37d 100644 --- a/packages/fs/tool-fs/src/edit.ts +++ b/packages/fs/tool-fs/src/edit.ts @@ -79,7 +79,7 @@ export function applyEditTool(ctx: Context, sandbox: FsSandboxController): void order: ctx.systemPrompt.getSectionOrder('TOOL_EDIT'), text: ({ scope }) => ctx.tools.get('edit', scope) === undefined ? '' - : 'Read a file before editing it unless you just created or edited it in this session.', + : 'Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session.', }) ctx.tools.register(defineTool({ diff --git a/packages/fs/tool-fs/src/write.ts b/packages/fs/tool-fs/src/write.ts index 0745ffc98d..1068cd9644 100644 --- a/packages/fs/tool-fs/src/write.ts +++ b/packages/fs/tool-fs/src/write.ts @@ -65,7 +65,7 @@ export function applyWriteTool(ctx: Context, sandbox: FsSandboxController): void order: ctx.systemPrompt.getSectionOrder('TOOL_WRITE'), text: ({ scope }) => ctx.tools.get('write', scope) === undefined ? '' - : 'Read an existing file before overwriting it with write' + : 'Read an existing file before overwriting it with write (the default fs-observation-policy requires it)' + (ctx.tools.get('edit', scope) === undefined ? '' : ' and prefer edit for targeted changes') + '.', }) diff --git a/packages/fs/tool-fs/tests/apply-patch.spec.ts b/packages/fs/tool-fs/tests/apply-patch.spec.ts index 18e84ee5f3..5dfeb725ae 100644 --- a/packages/fs/tool-fs/tests/apply-patch.spec.ts +++ b/packages/fs/tool-fs/tests/apply-patch.spec.ts @@ -11,7 +11,7 @@ import type { PtcRunRequest, PtcRunSpec } from '@deepseek-ai/dsh-ptc-runtime' import { add, move, patch, remove, setup, update } from './patch/harness.ts' const guidance = 'Prefer apply_patch over separate edit calls for changes across files or separated regions. ' - + 'Give every hunk enough surrounding context lines to match one place in the current file. ' + + 'Read a file before updating, deleting, or moving it (the default fs-observation-policy requires it), unless you just created or edited it in this session. ' + 'The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed.' type Fixture = Awaited> diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 08e4800285..94b80c86bd 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -1155,8 +1155,8 @@ async function guidanceScope(ctx: Context) { const originalGuidance = { read: 'Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files.', - write: 'Read an existing file before overwriting it with write and prefer edit for targeted changes.', - edit: 'Read a file before editing it unless you just created or edited it in this session.', + write: 'Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes.', + edit: 'Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session.', } describe('scope-aware filesystem guidance', () => { diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 09f64a6095..5a67ca2fbf 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -410,7 +410,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolFs, { applyPatch: true }) }, note: - 'The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-observation-policy` (an `fs/*` event-gate plugin, no schema change); the shipped compositions leave its row disabled, so mutations are unconditional unless a deployment enables it. The image tool is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. `apply_patch` registers only with `applyPatch: true`; the catalog sets it so the schema is documented, while shipped compositions keep the switch off on their `tool-fs` rows.', + 'The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-observation-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The image tool is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. `apply_patch` registers only with `applyPatch: true`; the catalog sets it so the schema is documented, while shipped compositions keep the switch off on their `tool-fs` rows.', }, { pkg: '@deepseek-ai/dsh-tool-fs-search', diff --git a/scripts/product-package-policy.ts b/scripts/product-package-policy.ts index 9568a91285..08171b05b8 100644 --- a/scripts/product-package-policy.ts +++ b/scripts/product-package-policy.ts @@ -36,7 +36,6 @@ export const PRODUCT_PACKAGE_POLICY: Readonly mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/command-attachments/system-prompt.expected.md b/snapshots/sdk/command-attachments/system-prompt.expected.md index 12f73e9afe..87c8754913 100644 --- a/snapshots/sdk/command-attachments/system-prompt.expected.md +++ b/snapshots/sdk/command-attachments/system-prompt.expected.md @@ -21,11 +21,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/command-attachments/tool-schemas.expected.json b/snapshots/sdk/command-attachments/tool-schemas.expected.json index 6864c8cfc9..0694559141 100644 --- a/snapshots/sdk/command-attachments/tool-schemas.expected.json +++ b/snapshots/sdk/command-attachments/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/sdk/desktop-context/system-prompt.expected.md b/snapshots/sdk/desktop-context/system-prompt.expected.md index f25ecb8425..86a2cff4e4 100644 --- a/snapshots/sdk/desktop-context/system-prompt.expected.md +++ b/snapshots/sdk/desktop-context/system-prompt.expected.md @@ -8,11 +8,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/desktop-context/tool-schemas.expected.json b/snapshots/sdk/desktop-context/tool-schemas.expected.json index 2f3046157b..6970ffe46f 100644 --- a/snapshots/sdk/desktop-context/tool-schemas.expected.json +++ b/snapshots/sdk/desktop-context/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/sdk/desktop-ptc-context/system-prompt.expected.md b/snapshots/sdk/desktop-ptc-context/system-prompt.expected.md index c0cdcf7b20..3831cfe891 100644 --- a/snapshots/sdk/desktop-ptc-context/system-prompt.expected.md +++ b/snapshots/sdk/desktop-ptc-context/system-prompt.expected.md @@ -10,11 +10,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -51,15 +49,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission. */ ask_user_question: { /** Questions to ask the user before continuing. */ @@ -411,27 +400,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; ask_user_question: { answers: { id: string; diff --git a/snapshots/sdk/dynamic-tool-updates/notifications.expected.jsonl b/snapshots/sdk/dynamic-tool-updates/notifications.expected.jsonl index a30d0584b2..cca4e59344 100644 --- a/snapshots/sdk/dynamic-tool-updates/notifications.expected.jsonl +++ b/snapshots/sdk/dynamic-tool-updates/notifications.expected.jsonl @@ -6,7 +6,7 @@ {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Read task.txt, call the newly available snapshot_ping tool once, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} -{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}}} +{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"Read task.txt, call the newly","messageSeqs":[8],"source":{"kind":"fallback"}}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":13,"time":0,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"call_task_read","name":"read","args":["{\"file_path\":\"task.txt\"}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}}} @@ -14,14 +14,14 @@ {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":15,"time":0,"data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_task_read"},"toolCallId":"call_task_read","content":[{"type":"text","text":"{{cwd}}/task.txt\nfile\n\n1: Reply with the single word DONE after reading this file.\n\n(End of file - total 1 lines)\n"}],"isError":false,"id":"{{sessionId}}"},"meta":{"path":"{{cwd}}/task.txt","offset":1,"lines":[{"number":1,"text":"Reply with the single word DONE after reading this file."}],"totalLines":1}},"sourceEventSeqs":[14],"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/end","seq":16,"time":0,"data":{"turn":1,"step":1}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/start","seq":17,"time":0,"data":{"turn":1,"step":2}}}} -{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":18,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}}} +{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":18,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"developer/message","seq":19,"time":0,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"snapshot_ping"}],"role":"developer","id":"{{sessionId}}"},"headerSeq":18},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"call_dynamic_ping","name":"snapshot_ping","args":["{}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_dynamic_ping"},"toolCallId":"call_dynamic_ping","content":[{"type":"text","text":"pong"}],"isError":false,"id":"{{sessionId}}"}},"sourceEventSeqs":[21],"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}}} -{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":25,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}}} +{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":25,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"developer/message","seq":26,"time":0,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"snapshot_ping"}],"role":"developer","id":"{{sessionId}}"}},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":27,"time":0,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":0,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":0,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/end","seq":28,"time":0,"data":{"turn":1,"step":3}}}} diff --git a/snapshots/sdk/dynamic-tool-updates/session.v4.jsonl b/snapshots/sdk/dynamic-tool-updates/session.v4.jsonl index b4d667d653..03befefbea 100644 --- a/snapshots/sdk/dynamic-tool-updates/session.v4.jsonl +++ b/snapshots/sdk/dynamic-tool-updates/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Read task.txt, call the newly available snapshot_ping tool once, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Read task.txt, call the newly","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":1790049391235,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790049391235,"index":0,"dt":[],"id":"call_task_read","name":"read","args":["{\"file_path\":\"task.txt\"}"]},{"type":"chunk","time":1790049391235,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}}},{"type":"chunk","time":1790049391235,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":1790049391235,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -17,14 +17,14 @@ {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_task_read"},"toolCallId":"call_task_read","content":[{"type":"text","text":"{{cwd}}/task.txt\nfile\n\n1: Reply with the single word DONE after reading this file.\n\n(End of file - total 1 lines)\n"}],"isError":false,"id":"{{message:5}}"},"meta":{"path":"{{cwd}}/task.txt","offset":1,"lines":[{"number":1,"text":"Reply with the single word DONE after reading this file."}],"totalLines":1}},"sourceEventSeqs":[14],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:6}}"},"headerSeq":18},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:7}}"},"stream":[{"type":"chunk","time":1790049391255,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790049391255,"index":0,"dt":[],"id":"call_dynamic_ping","name":"snapshot_ping","args":["{}"]},{"type":"chunk","time":1790049391255,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}},{"type":"chunk","time":1790049391255,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_dynamic_ping"},"toolCallId":"call_dynamic_ping","content":[{"type":"text","text":"pong"}],"isError":false,"id":"{{message:8}}"}},"sourceEventSeqs":[21],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:9}}"}},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1790049391270,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1790049391270,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1790049391270,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1790049391270,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1790049391270,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} diff --git a/snapshots/sdk/multi-turn/writer.expected.jsonl b/snapshots/sdk/multi-turn/writer.expected.jsonl index 93c22b5785..fc36064687 100644 --- a/snapshots/sdk/multi-turn/writer.expected.jsonl +++ b/snapshots/sdk/multi-turn/writer.expected.jsonl @@ -12,7 +12,7 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Reply with exactly the word:","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18},"stream":[{"type":"chunk","time":1793265605462,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265605462,"index":0,"dt":[0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","ONE","\""," and"," use"," no"," tools","."]},{"type":"chunk","time":1793265605463,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265605463,"index":1,"dt":[],"texts":["ONE"]},{"type":"chunk","time":1793265605463,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."}}},{"type":"chunk","time":1793265605463,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ONE"}}},{"type":"chunk","time":1793265605463,"chunk":{"type":"usage","usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}}},{"type":"chunk","time":1793265605463,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18},"stream":[{"type":"chunk","time":1791444991204,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444991204,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","ONE","\""," and"," use"," no"," tools","."]},{"type":"chunk","time":1791444991204,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791444991204,"index":1,"dt":[],"texts":["ONE"]},{"type":"chunk","time":1791444991204,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."}}},{"type":"chunk","time":1791444991204,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ONE"}}},{"type":"chunk","time":1791444991204,"chunk":{"type":"usage","usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}}},{"type":"chunk","time":1791444991204,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Reply with exactly the word: TWO. No tools."}],"source":{"kind":"user"},"role":"user","id":"{{message:5}}"}]}} @@ -20,6 +20,6 @@ {"type":"agent/inbox/spliced","data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","data":{"turn":2,"step":1}} {"type":"user/message","data":{"content":[{"type":"text","text":"Reply with exactly the word: TWO. No tools."}],"source":{"kind":"user"},"role":"user","id":"{{message:5}}"},"surfaceOp":"append"} -{"type":"assistant/message","data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18},"stream":[{"type":"chunk","time":1793265605480,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265605480,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","T","WO","\""," and"," no"," tools","."]},{"type":"chunk","time":1793265605480,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265605480,"index":1,"dt":[0],"texts":["T","WO"]},{"type":"chunk","time":1793265605480,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."}}},{"type":"chunk","time":1793265605480,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"TWO"}}},{"type":"chunk","time":1793265605480,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}},{"type":"chunk","time":1793265605480,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18},"stream":[{"type":"chunk","time":1791444991222,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444991222,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","T","WO","\""," and"," no"," tools","."]},{"type":"chunk","time":1791444991222,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791444991222,"index":1,"dt":[0],"texts":["T","WO"]},{"type":"chunk","time":1791444991222,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."}}},{"type":"chunk","time":1791444991222,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"TWO"}}},{"type":"chunk","time":1791444991222,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}},{"type":"chunk","time":1791444991222,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":2,"step":1}} {"type":"turn/end","data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/snapshots/sdk/plan-review/session.v4.jsonl b/snapshots/sdk/plan-review/session.v4.jsonl index 50393dd119..d7500984a2 100644 --- a/snapshots/sdk/plan-review/session.v4.jsonl +++ b/snapshots/sdk/plan-review/session.v4.jsonl @@ -10,7 +10,7 @@ {"type":"user/message","data":{"content":[{"type":"text","text":"Reply SDK_PLAN_INITIAL without tools."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Time sampled while preparing turn 1, step 1: 2026-10-16T00:00:00+00:00[UTC]\nBrowser time zone for this request: unavailable. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: unavailable."}],"source":{"kind":"time-context","form":"snapshot","sections":[{"name":"time-context","text":"Time sampled while preparing turn 1, step 1: 2026-10-16T00:00:00+00:00[UTC]\nBrowser time zone for this request: unavailable. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: unavailable."}]},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Reply SDK_PLAN_INITIAL without tools.","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session:1}}","sessionFormatVersion":4,"throughSeq":13}} @@ -28,7 +28,7 @@ {"type":"system/message","data":{"turn":2,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:8}}"}},"sourceEventSeqs":[7],"surfaceOp":{"op":"replace","startSeq":7,"endSeq":7}} {"type":"user/message","data":{"content":[{"type":"text","text":"The user switched this session to plan mode."}],"source":{"kind":"plan-mode","form":"notice","summary":"The user switched this session to plan mode."},"role":"user","id":"{{message:6}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Prepare a plan through exit_plan_mode; revise after feedback and acknowledge approval."}],"source":{"kind":"user"},"role":"user","id":"{{message:7}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} {"type":"developer/message","data":{"turn":2,"step":1,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"exit_plan_mode"}],"role":"developer","id":"{{message:9}}"},"headerSeq":29},"surfaceOp":"append"} {"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session:1}}","sessionFormatVersion":4,"throughSeq":30}} {"type":"assistant/message","data":{"turn":2,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"commands-tool-1","name":"exit_plan_mode","arguments":"{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"tool-call"}]}},"id":"{{message:10}}"},"usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032},"stream":[{"type":"chunk","time":1792108800000,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792108800000,"index":0,"dt":[],"id":"commands-tool-1","name":"exit_plan_mode","args":[""]},{"type":"tool-call-chunks","time0":1792108800000,"index":0,"dt":[],"id":"commands-tool-1","args":["{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"]},{"type":"chunk","time":1792108800000,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"commands-tool-1","name":"exit_plan_mode","arguments":"{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"usage","usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"} @@ -44,7 +44,7 @@ {"type":"plan/mode","data":{"active":false}} {"type":"step/start","data":{"turn":2,"step":3}} {"type":"system/message","data":{"turn":2,"step":3,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:14}}"}},"sourceEventSeqs":[26],"surfaceOp":{"op":"replace","startSeq":26,"endSeq":26}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"series"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"series"}} {"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session:1}}","sessionFormatVersion":4,"throughSeq":45}} {"type":"assistant/message","data":{"turn":2,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"SDK_PLAN_APPROVED"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"text"}]}},"id":"{{message:15}}"},"usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032},"stream":[{"type":"chunk","time":1792108800000,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1792108800000,"index":0,"dt":[],"texts":["SDK_PLAN_APPROVED"]},{"type":"chunk","time":1792108800000,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SDK_PLAN_APPROVED"}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"usage","usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":2,"step":3}} @@ -61,7 +61,7 @@ {"type":"system/message","data":{"turn":3,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:18}}"}},"sourceEventSeqs":[44],"surfaceOp":{"op":"replace","startSeq":44,"endSeq":44}} {"type":"user/message","data":{"content":[{"type":"text","text":"The user switched this session to plan mode."}],"source":{"kind":"plan-mode","form":"notice","summary":"The user switched this session to plan mode."},"role":"user","id":"{{message:16}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Present another plan for review."}],"source":{"kind":"user"},"role":"user","id":"{{message:17}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"series"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"series"}} {"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session:1}}","sessionFormatVersion":4,"throughSeq":62}} {"type":"assistant/message","data":{"turn":3,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"commands-tool-4","name":"exit_plan_mode","arguments":"{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"tool-call"}]}},"id":"{{message:19}}"},"usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032},"stream":[{"type":"chunk","time":1792108800000,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792108800000,"index":0,"dt":[],"id":"commands-tool-4","name":"exit_plan_mode","args":[""]},{"type":"tool-call-chunks","time0":1792108800000,"index":0,"dt":[],"id":"commands-tool-4","args":["{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"]},{"type":"chunk","time":1792108800000,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"commands-tool-4","name":"exit_plan_mode","arguments":"{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"usage","usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"tool-call"}]}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":3,"step":1,"callId":"commands-tool-4","name":"exit_plan_mode","arguments":"{\"plan\": \"# Implement the change\\n\\n- Inspect existing code.\\n- Make the smallest change.\\n- Run focused tests.\"}"}} @@ -80,7 +80,7 @@ {"type":"system/message","data":{"turn":4,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:23}}"}},"sourceEventSeqs":[59],"surfaceOp":{"op":"replace","startSeq":59,"endSeq":59}} {"type":"user/message","data":{"content":[{"type":"text","text":"The user switched this session back to the default mode."}],"source":{"kind":"plan-mode","form":"notice","summary":"The user switched this session back to the default mode."},"role":"user","id":"{{message:21}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Reply SDK_PLAN_OK without tools."}],"source":{"kind":"user"},"role":"user","id":"{{message:22}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"series"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","exit_plan_mode","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"series"}} {"type":"session-log-deepseek/delivery-accepted","data":{"sessionId":"{{session:1}}","sessionFormatVersion":4,"throughSeq":81}} {"type":"assistant/message","data":{"turn":4,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"SDK_PLAN_OK"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"text"}]}},"id":"{{message:24}}"},"usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032},"stream":[{"type":"chunk","time":1792108800000,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1792108800000,"index":0,"dt":[],"texts":["SDK_PLAN_OK"]},{"type":"chunk","time":1792108800000,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SDK_PLAN_OK"}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"usage","usage":{"inputTokens":10000,"outputTokens":32,"totalTokens":10032}}},{"type":"chunk","time":1792108800000,"chunk":{"type":"finish","reason":{"kind":"stop"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"text"}]}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":4,"step":1}} diff --git a/snapshots/sdk/plan-review/system-prompt.expected.md b/snapshots/sdk/plan-review/system-prompt.expected.md index 5d853c2010..d76bb0ad7b 100644 --- a/snapshots/sdk/plan-review/system-prompt.expected.md +++ b/snapshots/sdk/plan-review/system-prompt.expected.md @@ -8,11 +8,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -57,11 +55,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -93,11 +89,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -142,11 +136,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -178,11 +170,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/plan-review/tool-schemas.expected.json b/snapshots/sdk/plan-review/tool-schemas.expected.json index 44997dd78c..71459a7f86 100644 --- a/snapshots/sdk/plan-review/tool-schemas.expected.json +++ b/snapshots/sdk/plan-review/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", @@ -1070,14 +1042,154 @@ "changes": [ [ { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", + "name": "ask_user_question", + "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", "parameters": { "type": "object", "properties": { - "input": { + "questions": { + "type": "array", + "description": "Questions to ask the user before continuing.", + "items": { + "type": "object", + "additionalProperties": true, + "properties": { + "id": { + "type": "string", + "description": "Stable id for this question; echoed in the answer." + }, + "question": { + "type": "string", + "description": "The specific question to ask the user." + }, + "header": { + "type": "string", + "description": "Optional short heading for the question, such as \"Confirm\" or \"Choose Mode\"." + }, + "options": { + "type": "array", + "description": "Optional choices to show the user. If you recommend one, put it first and append \"(Recommended)\" to that label.", + "items": { + "type": "object", + "additionalProperties": true, + "properties": { + "label": { + "type": "string", + "description": "Short user-facing option label." + }, + "description": { + "type": "string", + "description": "One sentence explaining the tradeoff or impact." + } + }, + "required": [ + "label" + ] + } + }, + "multi_select": { + "type": "boolean", + "description": "Whether the user may select more than one option. Defaults to false." + } + }, + "required": [ + "id", + "question" + ] + } + } + }, + "required": [ + "questions" + ] + } + }, + { + "name": "bash", + "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", + "parameters": { + "type": "object", + "properties": { + "description": { "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." + "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." + }, + "command": { + "type": "string", + "description": "The bash command to execute." + }, + "timeoutMs": { + "type": "number", + "description": "Timeout in milliseconds. The executor applies its configured default and cap; on expiry the command moves to the background as a job instead of being killed." + }, + "workdir": { + "type": "string", + "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." + }, + "run_in_background": { + "type": "boolean", + "description": "Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies." + }, + "sandbox_permissions": { + "type": "string", + "description": "The narrowest wider sandbox mode for a one-shot retry of the exact command the sandbox just denied; the retry asks the user for approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. Use the language of the user’s current request." + } + }, + "required": [ + "description", + "command" + ] + } + }, + { + "name": "create_goal", + "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer limit on automatic continuation rounds." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "edit", + "description": "Edit an existing UTF-8 text file by replacing literal text.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to edit, resolved by the filesystem backend. Provide `file_path` before `old_string` and `new_string` in the arguments." + }, + "old_string": { + "type": "string", + "description": "Literal text to replace." + }, + "new_string": { + "type": "string", + "description": "Literal replacement text. Use an empty string to delete the match." + }, + "replace_all": { + "type": "boolean", + "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." }, "sandbox_permissions": { "type": "string", @@ -1093,10 +1205,898 @@ } }, "required": [ - "input" + "file_path", + "old_string", + "new_string" ] } }, + { + "name": "exit_plan_mode", + "description": "Use only in plan mode. Present your plan for the user's review and, on approval, leave plan mode. The user may approve (carry out the plan from your next step) or keep planning — their feedback comes back in the tool result; revise and present again.", + "parameters": { + "type": "object", + "properties": { + "plan": { + "type": "string", + "description": "The complete plan, as markdown, starting with a # heading that names it." + } + }, + "required": [ + "plan" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current session goal, including the id and revision that update_goal requires.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "glob", + "description": "Find files, not directories, whose paths match a glob pattern, including hidden and ignored files. Returns up to 100 paths in modification-time order; a larger result keeps the first paths and reports where the complete list was saved.", + "parameters": { + "type": "object", + "properties": { + "pattern": { + "type": "string", + "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." + }, + "path": { + "type": "string", + "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." + } + }, + "required": [ + "pattern" + ] + } + }, + { + "name": "grep", + "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns up to 250 matches; a larger result reports where the complete match list was saved.", + "parameters": { + "type": "object", + "properties": { + "pattern": { + "type": "string", + "description": "Regular expression to search for (ripgrep syntax)." + }, + "path": { + "type": "string", + "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." + }, + "include": { + "type": "string", + "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." + } + }, + "required": [ + "pattern" + ] + } + }, + { + "name": "interrupt_agent", + "description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.", + "parameters": { + "type": "object", + "properties": { + "agent_id": { + "type": "string", + "description": "The id of an agent created under you: your direct child or a deeper descendant." + } + }, + "required": [ + "agent_id" + ] + } + }, + { + "name": "job_kill", + "description": "Request cancellation of a running background job.", + "parameters": { + "type": "object", + "properties": { + "job_id": { + "type": "string", + "description": "Job id returned by the tool that started the background work." + }, + "reason": { + "type": "string", + "description": "Optional short reason, recorded in the log and forwarded to the job." + } + }, + "required": [ + "job_id" + ] + } + }, + { + "name": "job_list", + "description": "List your background jobs (running and finished) with their ids, kinds, and statuses.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "job_output", + "description": "Read a background job: output since the previous read for stream jobs, or the result of a finished final-output job.", + "parameters": { + "type": "object", + "properties": { + "job_id": { + "type": "string", + "description": "Job id returned by the tool that started the background work." + }, + "wait": { + "type": "boolean", + "description": "Block until the job finishes or the timeout expires; a timed-out wait leaves the job running. Defaults to false." + }, + "timeout_ms": { + "type": "number", + "description": "Max wait in milliseconds with wait: true. Defaults to and is capped by configuration." + } + }, + "required": [ + "job_id" + ] + } + }, + { + "name": "list_agents", + "description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.", + "parameters": { + "type": "object", + "properties": { + "scope": { + "type": "string", + "description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.", + "enum": [ + "children", + "descendants" + ] + } + } + } + }, + { + "name": "plugin_manager", + "description": "List plugins or bundles in the current profile, enable or disable them, install a bundle, or remove an installed bundle. Every action requires danger-full-access permission or approval for this call. Approval does not change the session permission mode. Changes affect every session in this profile. List first to obtain exact identifiers. Package installation can execute allowed build scripts. Live profiles apply changes immediately, including upgrades of installed packages; a change result that is not applied carries nextStep, which says what to do or tell the user. Unmet DSH version requirements (engines.dsh, else DSH peer dependencies) block installation and activation. Version exemptions risk crashes and data loss: warn the user and obtain explicit permission for the exact plugin and runtime versions before granting one.", + "parameters": { + "type": "object", + "properties": { + "action": { + "type": "string", + "description": "Management operation.", + "enum": [ + "list_plugins", + "list_bundles", + "set_plugin", + "set_bundle", + "install_bundle", + "remove_bundle", + "list_version_exemptions", + "set_version_exemption" + ] + }, + "target": { + "type": "string", + "description": "Plugin entry id, bundle package name, or installation spec, according to action. For an Official catalog entry, pass list_bundles installTarget.spec to install_bundle." + }, + "enabled": { + "type": "boolean", + "description": "Required for set operations; defaults to true for installation. For set_version_exemption, true grants and false revokes." + }, + "runtimeVersion": { + "type": "string", + "description": "For set_version_exemption: exact DSH version from list_version_exemptions. Target must be the manifest package-name@version, not an alias or version range." + }, + "acceptRisk": { + "type": "boolean", + "description": "For granting an exemption: true only after warning the user about possible crashes and data loss and receiving explicit permission for this exact plugin/runtime pair. General installation permission is not enough." + }, + "approvedBuilds": { + "type": "array", + "description": "For install_bundle: pass names from pendingBuilds only after the user explicitly approves running their install scripts in the conversation. This grants persistent permission for this profile.", + "items": { + "type": "string" + } + }, + "registry": { + "type": "string", + "description": "For install_bundle: the npm registry URL asked first, when the user names one; otherwise the configured registry is asked, and its configured fallbacks while a registry is unreachable." + }, + "offset": { + "type": "number", + "description": "Zero-based list offset; defaults to 0." + }, + "limit": { + "type": "number", + "description": "List page size, from 1 to 100; defaults to 25." + } + }, + "required": [ + "action" + ] + } + }, + { + "name": "present", + "description": "Declare existing files as final deliverables for the user. Hosts may show presented files only after your turn ends, so call it once the files are final. If the user needs to review files earlier, such as before a tool call that waits for their answer, link them in your message instead. Use it when the user needs a separate file, especially Office documents, spreadsheets, and slide decks; prefer your final response when that suffices. The user opens the current files; their contents are not copied.", + "parameters": { + "type": "object", + "properties": { + "files": { + "type": "array", + "description": "Usually the 1-2 most important deliverables; at most 4 per call.", + "items": { + "type": "object", + "additionalProperties": false, + "properties": { + "path": { + "type": "string", + "description": "Path of an existing regular file. Relative paths use the Session working directory." + }, + "description": { + "type": "string", + "description": "Brief description for the user." + } + }, + "required": [ + "path" + ] + } + } + }, + "required": [ + "files" + ] + } + }, + { + "name": "read", + "description": "Read a UTF-8 text file and return line-numbered content.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to read, resolved by the filesystem backend." + }, + "offset": { + "type": "number", + "description": "1-based first line to return. Defaults to 1." + }, + "limit": { + "type": "number", + "description": "Maximum number of lines to return. Defaults to 2000." + } + }, + "required": [ + "file_path" + ] + } + }, + { + "name": "read_image", + "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Large images are downscaled automatically; do not install image libraries or create thumbnails to inspect an image.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to the image file, resolved by the filesystem backend." + } + }, + "required": [ + "file_path" + ] + } + }, + { + "name": "schedule_create", + "description": "Create a reminder in the current session that delivers prompt when it becomes due. Supply exactly one timing parameter: after_seconds, at, every_seconds, daily, weekly, or cron. Local times that do not exist in the zone are skipped; repeated local times fire once, at the earlier instant. After downtime, a recurring reminder delivers only its latest missed occurrence. Delivery can repeat after a crash.", + "parameters": { + "type": "object", + "properties": { + "prompt": { + "type": "string", + "description": "Reminder content to present when the target becomes due." + }, + "title": { + "type": "string", + "description": "Concise task name in the user's language, at most 120 characters. Name only the core action and subject; keep essential target identifiers such as PR numbers and branch names. Do not include execution frequency (e.g. daily, hourly), scheduled dates/times, time zones, task status, or configuration and execution details (e.g. read-only mode, profile-tag filters), even when embedded in the requested or existing title. Do not append parenthetical notes. Put scheduling information in the timing parameters and execution instructions in prompt." + }, + "after_seconds": { + "type": "number", + "description": "Delay in whole seconds." + }, + "every_seconds": { + "type": "number", + "description": "Fixed-rate interval in whole seconds, at least 60, aligned to the creation time; changing it with schedule_update re-aligns it to the save time." + }, + "daily": { + "type": "object", + "description": "Every day at a local time.", + "additionalProperties": false, + "properties": { + "time": { + "type": "string", + "description": "HH:mm:ss with optional 1-3 fractional digits, for example 23:00:00." + }, + "time_zone": { + "type": "string", + "description": "UTC or IANA Area/Location, for example Asia/Shanghai." + } + }, + "required": [ + "time", + "time_zone" + ] + }, + "weekly": { + "type": "object", + "description": "On the given weekdays at a local time.", + "additionalProperties": false, + "properties": { + "time": { + "type": "string", + "description": "HH:mm:ss with optional 1-3 fractional digits, for example 09:00:00." + }, + "time_zone": { + "type": "string", + "description": "UTC or IANA Area/Location, for example Asia/Shanghai." + }, + "weekdays": { + "type": "array", + "description": "ISO weekdays, Monday 1 through Sunday 7, without repetitions.", + "items": { + "type": "integer" + } + } + }, + "required": [ + "time", + "time_zone", + "weekdays" + ] + }, + "cron": { + "type": "object", + "description": "Five-field Vixie cron expression in a time zone.", + "additionalProperties": false, + "properties": { + "expression": { + "type": "string", + "description": "minute hour day-of-month month day-of-week, for example \"*/15 9-17 * * 1-5\". When both day fields are restricted, a date matches if either one matches." + }, + "time_zone": { + "type": "string", + "description": "UTC or IANA Area/Location, for example Asia/Shanghai." + } + }, + "required": [ + "expression", + "time_zone" + ] + }, + "at": { + "oneOf": [ + { + "type": "string" + }, + { + "type": "object", + "additionalProperties": false, + "properties": { + "date": { + "type": "string" + }, + "time": { + "type": "string" + }, + "time_zone": { + "type": "string" + } + }, + "required": [ + "date", + "time", + "time_zone" + ] + } + ], + "description": "Absolute target: an RFC 3339 date-time with offset, or a local date, time, and IANA time_zone." + } + }, + "required": [ + "prompt", + "title" + ] + } + }, + { + "name": "schedule_delete", + "description": "Delete a reminder in the current session, active or inactive. Deletion does not retract a reminder message that is already queued.", + "parameters": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "Exact schedule id." + } + }, + "required": [ + "id" + ] + } + }, + { + "name": "schedule_list", + "description": "List the active reminders in the current session.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "schedule_update", + "description": "Change a reminder in place, keeping its id. Supply a new title, prompt, or at most one timing parameter; omitted fields keep their stored values. To change a relative delay, create a new reminder.", + "parameters": { + "type": "object", + "properties": { + "id": { + "type": "string", + "description": "Schedule id returned by schedule_list." + }, + "title": { + "type": "string", + "description": "New task name; follow the schedule_create title rules." + }, + "prompt": { + "type": "string", + "description": "New reminder content." + }, + "every_seconds": { + "type": "number", + "description": "Fixed-rate interval in whole seconds, at least 60, aligned to the creation time; changing it with schedule_update re-aligns it to the save time." + }, + "daily": { + "type": "object", + "description": "Every day at a local time.", + "additionalProperties": false, + "properties": { + "time": { + "type": "string", + "description": "HH:mm:ss with optional 1-3 fractional digits, for example 23:00:00." + }, + "time_zone": { + "type": "string", + "description": "UTC or IANA Area/Location, for example Asia/Shanghai." + } + }, + "required": [ + "time", + "time_zone" + ] + }, + "weekly": { + "type": "object", + "description": "On the given weekdays at a local time.", + "additionalProperties": false, + "properties": { + "time": { + "type": "string", + "description": "HH:mm:ss with optional 1-3 fractional digits, for example 09:00:00." + }, + "time_zone": { + "type": "string", + "description": "UTC or IANA Area/Location, for example Asia/Shanghai." + }, + "weekdays": { + "type": "array", + "description": "ISO weekdays, Monday 1 through Sunday 7, without repetitions.", + "items": { + "type": "integer" + } + } + }, + "required": [ + "time", + "time_zone", + "weekdays" + ] + }, + "cron": { + "type": "object", + "description": "Five-field Vixie cron expression in a time zone.", + "additionalProperties": false, + "properties": { + "expression": { + "type": "string", + "description": "minute hour day-of-month month day-of-week, for example \"*/15 9-17 * * 1-5\". When both day fields are restricted, a date matches if either one matches." + }, + "time_zone": { + "type": "string", + "description": "UTC or IANA Area/Location, for example Asia/Shanghai." + } + }, + "required": [ + "expression", + "time_zone" + ] + }, + "at": { + "oneOf": [ + { + "type": "string" + }, + { + "type": "object", + "additionalProperties": false, + "properties": { + "date": { + "type": "string" + }, + "time": { + "type": "string" + }, + "time_zone": { + "type": "string" + } + }, + "required": [ + "date", + "time", + "time_zone" + ] + } + ], + "description": "Absolute target: an RFC 3339 date-time with offset, or a local date, time, and IANA time_zone." + } + }, + "required": [ + "id" + ] + } + }, + { + "name": "send_message", + "description": "Send a message to an agent. A working agent receives it at its next step; an idle agent starts a new turn with it. Returns delivery confirmation, not the agent's answer.", + "parameters": { + "type": "object", + "properties": { + "agent_id": { + "type": "string", + "description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child." + }, + "message": { + "type": "string", + "description": "The message to deliver to the agent." + } + }, + "required": [ + "agent_id", + "message" + ] + } + }, + { + "name": "skill", + "description": "Load the full instructions for a skill. Call it before acting on a task that names or clearly matches a skill in the session skill catalog.", + "parameters": { + "type": "object", + "properties": { + "name": { + "type": "string", + "description": "The exact skill name from the available skills list." + } + }, + "required": [ + "name" + ] + } + }, + { + "name": "subagent", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", + "parameters": { + "type": "object", + "properties": { + "cwd": { + "type": "string", + "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." + }, + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "subagent_fork", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", + "parameters": { + "type": "object", + "properties": { + "cwd": { + "type": "string", + "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." + }, + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "todo_write", + "description": "Record and update a task list to plan multi-step work and show progress; skip it for trivial single-step tasks. Add one todo per concrete step before you start. While work remains, keep the todos being worked on `in_progress`, several only when work runs in parallel. Mark each todo `completed` as soon as it is done.", + "parameters": { + "type": "object", + "properties": { + "todos": { + "type": "array", + "description": "The COMPLETE task list, replacing any previous list.", + "items": { + "type": "object", + "additionalProperties": false, + "properties": { + "content": { + "type": "string", + "description": "What the task is — a short imperative line." + }, + "status": { + "type": "string", + "description": "pending (not started) | in_progress (now) | completed (done).", + "enum": [ + "pending", + "in_progress", + "completed" + ] + } + }, + "required": [ + "content", + "status" + ] + } + } + }, + "required": [ + "todos" + ] + } + }, + { + "name": "update_goal", + "description": "Update the current goal.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit, pause, and resume require a direct top-level human request. complete and blocked are also allowed during an automatic continuation of this goal; blocked is rejected before the configured minimum round count.", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Required only with action blocked: the concrete condition that persisted across rounds and blocks progress." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, + { + "name": "web_fetch", + "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", + "parameters": { + "type": "object", + "properties": { + "url": { + "type": "string", + "description": "The HTTP(S) URL to fetch." + } + }, + "required": [ + "url" + ] + } + }, + { + "name": "web_search", + "description": "Search the web for current information. Returns an optional summary answer and a list of source URLs.", + "parameters": { + "type": "object", + "properties": { + "queries": { + "type": "array", + "description": "1–4 search queries; their results are merged.", + "items": { + "type": "string" + } + } + }, + "required": [ + "queries" + ] + } + }, + { + "name": "workflow", + "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. A stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) end the whole script instead of producing `null`. The script has no filesystem, network, timer, or Node.js APIs; the agents do the work.", + "parameters": { + "type": "object", + "properties": { + "script": { + "type": "string", + "description": "The plain JavaScript body, not TypeScript and without an `export const meta` statement; top-level await is allowed. End with `return `; the JSON-serializable value is this tool's result." + }, + "meta": { + "type": "object", + "description": "The workflow identity as plain JSON, not code.", + "additionalProperties": true, + "properties": { + "name": { + "type": "string", + "description": "Short kebab-case workflow name." + }, + "description": { + "type": "string", + "description": "One-line description of what the workflow does." + }, + "whenToUse": { + "type": "string", + "description": "Optional guidance on when this workflow applies." + }, + "phases": { + "type": "array", + "description": "Optional phase declarations matched by phase() calls.", + "items": { + "type": "object", + "additionalProperties": true, + "properties": { + "title": { + "type": "string", + "description": "The phase title phase() calls match by exact string." + }, + "detail": { + "type": "string", + "description": "Optional one-line description of the phase." + }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, + "model": { + "type": "string", + "description": "Optional model override this phase is expected to use." + } + }, + "required": [ + "title" + ] + } + } + }, + "required": [ + "name", + "description" + ] + }, + "args": { + "type": "object", + "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", + "additionalProperties": true + }, + "run_in_background": { + "type": "boolean", + "description": "Run as a background job: return a job id immediately instead of waiting; the return value arrives with the completion notice." + } + }, + "required": [ + "script", + "meta" + ] + } + }, + { + "name": "working_directory", + "description": "Read the current working directory, or change it with cd. Relative paths use the current directory. Existing shells and running processes keep their own directories.", + "parameters": { + "type": "object", + "properties": { + "cd": { + "type": "string", + "description": "Existing directory to enter. Omit to read the current directory." + } + } + } + }, + { + "name": "write", + "description": "Create or fully replace a UTF-8 text file.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to write, resolved by the filesystem backend. Provide `file_path` before `content` in the arguments." + }, + "content": { + "type": "string", + "description": "Full UTF-8 text content to write." + }, + "sandbox_permissions": { + "type": "string", + "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." + } + }, + "required": [ + "file_path", + "content" + ] + } + } + ], + [ { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", @@ -2153,34 +3153,6 @@ } ], [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", @@ -3237,1118 +4209,6 @@ } ], [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, - { - "name": "ask_user_question", - "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", - "parameters": { - "type": "object", - "properties": { - "questions": { - "type": "array", - "description": "Questions to ask the user before continuing.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "id": { - "type": "string", - "description": "Stable id for this question; echoed in the answer." - }, - "question": { - "type": "string", - "description": "The specific question to ask the user." - }, - "header": { - "type": "string", - "description": "Optional short heading for the question, such as \"Confirm\" or \"Choose Mode\"." - }, - "options": { - "type": "array", - "description": "Optional choices to show the user. If you recommend one, put it first and append \"(Recommended)\" to that label.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "label": { - "type": "string", - "description": "Short user-facing option label." - }, - "description": { - "type": "string", - "description": "One sentence explaining the tradeoff or impact." - } - }, - "required": [ - "label" - ] - } - }, - "multi_select": { - "type": "boolean", - "description": "Whether the user may select more than one option. Defaults to false." - } - }, - "required": [ - "id", - "question" - ] - } - } - }, - "required": [ - "questions" - ] - } - }, - { - "name": "bash", - "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." - }, - "command": { - "type": "string", - "description": "The bash command to execute." - }, - "timeoutMs": { - "type": "number", - "description": "Timeout in milliseconds. The executor applies its configured default and cap; on expiry the command moves to the background as a job instead of being killed." - }, - "workdir": { - "type": "string", - "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." - }, - "run_in_background": { - "type": "boolean", - "description": "Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact command the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "description", - "command" - ] - } - }, - { - "name": "create_goal", - "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend. Provide `file_path` before `old_string` and `new_string` in the arguments." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "exit_plan_mode", - "description": "Use only in plan mode. Present your plan for the user's review and, on approval, leave plan mode. The user may approve (carry out the plan from your next step) or keep planning — their feedback comes back in the tool result; revise and present again.", - "parameters": { - "type": "object", - "properties": { - "plan": { - "type": "string", - "description": "The complete plan, as markdown, starting with a # heading that names it." - } - }, - "required": [ - "plan" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current session goal, including the id and revision that update_goal requires.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "glob", - "description": "Find files, not directories, whose paths match a glob pattern, including hidden and ignored files. Returns up to 100 paths in modification-time order; a larger result keeps the first paths and reports where the complete list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." - }, - "path": { - "type": "string", - "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "grep", - "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns up to 250 matches; a larger result reports where the complete match list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Regular expression to search for (ripgrep syntax)." - }, - "path": { - "type": "string", - "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." - }, - "include": { - "type": "string", - "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "interrupt_agent", - "description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The id of an agent created under you: your direct child or a deeper descendant." - } - }, - "required": [ - "agent_id" - ] - } - }, - { - "name": "job_kill", - "description": "Request cancellation of a running background job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the job." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "job_list", - "description": "List your background jobs (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "job_output", - "description": "Read a background job: output since the previous read for stream jobs, or the result of a finished final-output job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the job finishes or the timeout expires; a timed-out wait leaves the job running. Defaults to false." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds with wait: true. Defaults to and is capped by configuration." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "list_agents", - "description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.", - "parameters": { - "type": "object", - "properties": { - "scope": { - "type": "string", - "description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.", - "enum": [ - "children", - "descendants" - ] - } - } - } - }, - { - "name": "plugin_manager", - "description": "List plugins or bundles in the current profile, enable or disable them, install a bundle, or remove an installed bundle. Every action requires danger-full-access permission or approval for this call. Approval does not change the session permission mode. Changes affect every session in this profile. List first to obtain exact identifiers. Package installation can execute allowed build scripts. Live profiles apply changes immediately, including upgrades of installed packages; a change result that is not applied carries nextStep, which says what to do or tell the user. Unmet DSH version requirements (engines.dsh, else DSH peer dependencies) block installation and activation. Version exemptions risk crashes and data loss: warn the user and obtain explicit permission for the exact plugin and runtime versions before granting one.", - "parameters": { - "type": "object", - "properties": { - "action": { - "type": "string", - "description": "Management operation.", - "enum": [ - "list_plugins", - "list_bundles", - "set_plugin", - "set_bundle", - "install_bundle", - "remove_bundle", - "list_version_exemptions", - "set_version_exemption" - ] - }, - "target": { - "type": "string", - "description": "Plugin entry id, bundle package name, or installation spec, according to action. For an Official catalog entry, pass list_bundles installTarget.spec to install_bundle." - }, - "enabled": { - "type": "boolean", - "description": "Required for set operations; defaults to true for installation. For set_version_exemption, true grants and false revokes." - }, - "runtimeVersion": { - "type": "string", - "description": "For set_version_exemption: exact DSH version from list_version_exemptions. Target must be the manifest package-name@version, not an alias or version range." - }, - "acceptRisk": { - "type": "boolean", - "description": "For granting an exemption: true only after warning the user about possible crashes and data loss and receiving explicit permission for this exact plugin/runtime pair. General installation permission is not enough." - }, - "approvedBuilds": { - "type": "array", - "description": "For install_bundle: pass names from pendingBuilds only after the user explicitly approves running their install scripts in the conversation. This grants persistent permission for this profile.", - "items": { - "type": "string" - } - }, - "registry": { - "type": "string", - "description": "For install_bundle: the npm registry URL asked first, when the user names one; otherwise the configured registry is asked, and its configured fallbacks while a registry is unreachable." - }, - "offset": { - "type": "number", - "description": "Zero-based list offset; defaults to 0." - }, - "limit": { - "type": "number", - "description": "List page size, from 1 to 100; defaults to 25." - } - }, - "required": [ - "action" - ] - } - }, - { - "name": "present", - "description": "Declare existing files as final deliverables for the user. Hosts may show presented files only after your turn ends, so call it once the files are final. If the user needs to review files earlier, such as before a tool call that waits for their answer, link them in your message instead. Use it when the user needs a separate file, especially Office documents, spreadsheets, and slide decks; prefer your final response when that suffices. The user opens the current files; their contents are not copied.", - "parameters": { - "type": "object", - "properties": { - "files": { - "type": "array", - "description": "Usually the 1-2 most important deliverables; at most 4 per call.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "path": { - "type": "string", - "description": "Path of an existing regular file. Relative paths use the Session working directory." - }, - "description": { - "type": "string", - "description": "Brief description for the user." - } - }, - "required": [ - "path" - ] - } - } - }, - "required": [ - "files" - ] - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "read_image", - "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Large images are downscaled automatically; do not install image libraries or create thumbnails to inspect an image.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to the image file, resolved by the filesystem backend." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "schedule_create", - "description": "Create a reminder in the current session that delivers prompt when it becomes due. Supply exactly one timing parameter: after_seconds, at, every_seconds, daily, weekly, or cron. Local times that do not exist in the zone are skipped; repeated local times fire once, at the earlier instant. After downtime, a recurring reminder delivers only its latest missed occurrence. Delivery can repeat after a crash.", - "parameters": { - "type": "object", - "properties": { - "prompt": { - "type": "string", - "description": "Reminder content to present when the target becomes due." - }, - "title": { - "type": "string", - "description": "Concise task name in the user's language, at most 120 characters. Name only the core action and subject; keep essential target identifiers such as PR numbers and branch names. Do not include execution frequency (e.g. daily, hourly), scheduled dates/times, time zones, task status, or configuration and execution details (e.g. read-only mode, profile-tag filters), even when embedded in the requested or existing title. Do not append parenthetical notes. Put scheduling information in the timing parameters and execution instructions in prompt." - }, - "after_seconds": { - "type": "number", - "description": "Delay in whole seconds." - }, - "every_seconds": { - "type": "number", - "description": "Fixed-rate interval in whole seconds, at least 60, aligned to the creation time; changing it with schedule_update re-aligns it to the save time." - }, - "daily": { - "type": "object", - "description": "Every day at a local time.", - "additionalProperties": false, - "properties": { - "time": { - "type": "string", - "description": "HH:mm:ss with optional 1-3 fractional digits, for example 23:00:00." - }, - "time_zone": { - "type": "string", - "description": "UTC or IANA Area/Location, for example Asia/Shanghai." - } - }, - "required": [ - "time", - "time_zone" - ] - }, - "weekly": { - "type": "object", - "description": "On the given weekdays at a local time.", - "additionalProperties": false, - "properties": { - "time": { - "type": "string", - "description": "HH:mm:ss with optional 1-3 fractional digits, for example 09:00:00." - }, - "time_zone": { - "type": "string", - "description": "UTC or IANA Area/Location, for example Asia/Shanghai." - }, - "weekdays": { - "type": "array", - "description": "ISO weekdays, Monday 1 through Sunday 7, without repetitions.", - "items": { - "type": "integer" - } - } - }, - "required": [ - "time", - "time_zone", - "weekdays" - ] - }, - "cron": { - "type": "object", - "description": "Five-field Vixie cron expression in a time zone.", - "additionalProperties": false, - "properties": { - "expression": { - "type": "string", - "description": "minute hour day-of-month month day-of-week, for example \"*/15 9-17 * * 1-5\". When both day fields are restricted, a date matches if either one matches." - }, - "time_zone": { - "type": "string", - "description": "UTC or IANA Area/Location, for example Asia/Shanghai." - } - }, - "required": [ - "expression", - "time_zone" - ] - }, - "at": { - "oneOf": [ - { - "type": "string" - }, - { - "type": "object", - "additionalProperties": false, - "properties": { - "date": { - "type": "string" - }, - "time": { - "type": "string" - }, - "time_zone": { - "type": "string" - } - }, - "required": [ - "date", - "time", - "time_zone" - ] - } - ], - "description": "Absolute target: an RFC 3339 date-time with offset, or a local date, time, and IANA time_zone." - } - }, - "required": [ - "prompt", - "title" - ] - } - }, - { - "name": "schedule_delete", - "description": "Delete a reminder in the current session, active or inactive. Deletion does not retract a reminder message that is already queued.", - "parameters": { - "type": "object", - "properties": { - "id": { - "type": "string", - "description": "Exact schedule id." - } - }, - "required": [ - "id" - ] - } - }, - { - "name": "schedule_list", - "description": "List the active reminders in the current session.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "schedule_update", - "description": "Change a reminder in place, keeping its id. Supply a new title, prompt, or at most one timing parameter; omitted fields keep their stored values. To change a relative delay, create a new reminder.", - "parameters": { - "type": "object", - "properties": { - "id": { - "type": "string", - "description": "Schedule id returned by schedule_list." - }, - "title": { - "type": "string", - "description": "New task name; follow the schedule_create title rules." - }, - "prompt": { - "type": "string", - "description": "New reminder content." - }, - "every_seconds": { - "type": "number", - "description": "Fixed-rate interval in whole seconds, at least 60, aligned to the creation time; changing it with schedule_update re-aligns it to the save time." - }, - "daily": { - "type": "object", - "description": "Every day at a local time.", - "additionalProperties": false, - "properties": { - "time": { - "type": "string", - "description": "HH:mm:ss with optional 1-3 fractional digits, for example 23:00:00." - }, - "time_zone": { - "type": "string", - "description": "UTC or IANA Area/Location, for example Asia/Shanghai." - } - }, - "required": [ - "time", - "time_zone" - ] - }, - "weekly": { - "type": "object", - "description": "On the given weekdays at a local time.", - "additionalProperties": false, - "properties": { - "time": { - "type": "string", - "description": "HH:mm:ss with optional 1-3 fractional digits, for example 09:00:00." - }, - "time_zone": { - "type": "string", - "description": "UTC or IANA Area/Location, for example Asia/Shanghai." - }, - "weekdays": { - "type": "array", - "description": "ISO weekdays, Monday 1 through Sunday 7, without repetitions.", - "items": { - "type": "integer" - } - } - }, - "required": [ - "time", - "time_zone", - "weekdays" - ] - }, - "cron": { - "type": "object", - "description": "Five-field Vixie cron expression in a time zone.", - "additionalProperties": false, - "properties": { - "expression": { - "type": "string", - "description": "minute hour day-of-month month day-of-week, for example \"*/15 9-17 * * 1-5\". When both day fields are restricted, a date matches if either one matches." - }, - "time_zone": { - "type": "string", - "description": "UTC or IANA Area/Location, for example Asia/Shanghai." - } - }, - "required": [ - "expression", - "time_zone" - ] - }, - "at": { - "oneOf": [ - { - "type": "string" - }, - { - "type": "object", - "additionalProperties": false, - "properties": { - "date": { - "type": "string" - }, - "time": { - "type": "string" - }, - "time_zone": { - "type": "string" - } - }, - "required": [ - "date", - "time", - "time_zone" - ] - } - ], - "description": "Absolute target: an RFC 3339 date-time with offset, or a local date, time, and IANA time_zone." - } - }, - "required": [ - "id" - ] - } - }, - { - "name": "send_message", - "description": "Send a message to an agent. A working agent receives it at its next step; an idle agent starts a new turn with it. Returns delivery confirmation, not the agent's answer.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child." - }, - "message": { - "type": "string", - "description": "The message to deliver to the agent." - } - }, - "required": [ - "agent_id", - "message" - ] - } - }, - { - "name": "skill", - "description": "Load the full instructions for a skill. Call it before acting on a task that names or clearly matches a skill in the session skill catalog.", - "parameters": { - "type": "object", - "properties": { - "name": { - "type": "string", - "description": "The exact skill name from the available skills list." - } - }, - "required": [ - "name" - ] - } - }, - { - "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "todo_write", - "description": "Record and update a task list to plan multi-step work and show progress; skip it for trivial single-step tasks. Add one todo per concrete step before you start. While work remains, keep the todos being worked on `in_progress`, several only when work runs in parallel. Mark each todo `completed` as soon as it is done.", - "parameters": { - "type": "object", - "properties": { - "todos": { - "type": "array", - "description": "The COMPLETE task list, replacing any previous list.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "content": { - "type": "string", - "description": "What the task is — a short imperative line." - }, - "status": { - "type": "string", - "description": "pending (not started) | in_progress (now) | completed (done).", - "enum": [ - "pending", - "in_progress", - "completed" - ] - } - }, - "required": [ - "content", - "status" - ] - } - } - }, - "required": [ - "todos" - ] - } - }, - { - "name": "update_goal", - "description": "Update the current goal.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit, pause, and resume require a direct top-level human request. complete and blocked are also allowed during an automatic continuation of this goal; blocked is rejected before the configured minimum round count.", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Required only with action blocked: the concrete condition that persisted across rounds and blocks progress." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "name": "web_fetch", - "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", - "parameters": { - "type": "object", - "properties": { - "url": { - "type": "string", - "description": "The HTTP(S) URL to fetch." - } - }, - "required": [ - "url" - ] - } - }, - { - "name": "web_search", - "description": "Search the web for current information. Returns an optional summary answer and a list of source URLs.", - "parameters": { - "type": "object", - "properties": { - "queries": { - "type": "array", - "description": "1–4 search queries; their results are merged.", - "items": { - "type": "string" - } - } - }, - "required": [ - "queries" - ] - } - }, - { - "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. A stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) end the whole script instead of producing `null`. The script has no filesystem, network, timer, or Node.js APIs; the agents do the work.", - "parameters": { - "type": "object", - "properties": { - "script": { - "type": "string", - "description": "The plain JavaScript body, not TypeScript and without an `export const meta` statement; top-level await is allowed. End with `return `; the JSON-serializable value is this tool's result." - }, - "meta": { - "type": "object", - "description": "The workflow identity as plain JSON, not code.", - "additionalProperties": true, - "properties": { - "name": { - "type": "string", - "description": "Short kebab-case workflow name." - }, - "description": { - "type": "string", - "description": "One-line description of what the workflow does." - }, - "whenToUse": { - "type": "string", - "description": "Optional guidance on when this workflow applies." - }, - "phases": { - "type": "array", - "description": "Optional phase declarations matched by phase() calls.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "title": { - "type": "string", - "description": "The phase title phase() calls match by exact string." - }, - "detail": { - "type": "string", - "description": "Optional one-line description of the phase." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "model": { - "type": "string", - "description": "Optional model override this phase is expected to use." - } - }, - "required": [ - "title" - ] - } - } - }, - "required": [ - "name", - "description" - ] - }, - "args": { - "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", - "additionalProperties": true - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background job: return a job id immediately instead of waiting; the return value arrives with the completion notice." - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "working_directory", - "description": "Read the current working directory, or change it with cd. Relative paths use the current directory. Existing shells and running processes keep their own directories.", - "parameters": { - "type": "object", - "properties": { - "cd": { - "type": "string", - "description": "Existing directory to enter. Omit to read the current directory." - } - } - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend. Provide `file_path` before `content` in the arguments." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ], - [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/sdk/session-resume/snapshot.yml b/snapshots/sdk/session-resume/snapshot.yml index 4462b95446..d99cd57cde 100644 --- a/snapshots/sdk/session-resume/snapshot.yml +++ b/snapshots/sdk/session-resume/snapshot.yml @@ -8,3 +8,4 @@ header: pin: true changes: 1 promptChanges: 1 + toolSchemasSource: session/compaction-recovery diff --git a/snapshots/sdk/session-resume/system-prompt.expected.md b/snapshots/sdk/session-resume/system-prompt.expected.md index f6e947cf8e..edee628694 100644 --- a/snapshots/sdk/session-resume/system-prompt.expected.md +++ b/snapshots/sdk/session-resume/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -44,11 +42,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/session-resume/tool-schemas.expected.json b/snapshots/sdk/session-resume/tool-schemas.expected.json deleted file mode 100644 index 42b0e228ce..0000000000 --- a/snapshots/sdk/session-resume/tool-schemas.expected.json +++ /dev/null @@ -1,1292 +0,0 @@ -{ - "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, - { - "name": "bash", - "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." - }, - "command": { - "type": "string", - "description": "The bash command to execute." - }, - "timeoutMs": { - "type": "number", - "description": "Timeout in milliseconds. The executor applies its configured default and cap; on expiry the command moves to the background as a job instead of being killed." - }, - "workdir": { - "type": "string", - "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." - }, - "run_in_background": { - "type": "boolean", - "description": "Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact command the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "description", - "command" - ] - } - }, - { - "name": "create_goal", - "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend. Provide `file_path` before `old_string` and `new_string` in the arguments." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current session goal, including the id and revision that update_goal requires.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "glob", - "description": "Find files, not directories, whose paths match a glob pattern, including hidden and ignored files. Returns up to 100 paths in modification-time order; a larger result keeps the first paths and reports where the complete list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." - }, - "path": { - "type": "string", - "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "grep", - "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns up to 250 matches; a larger result reports where the complete match list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Regular expression to search for (ripgrep syntax)." - }, - "path": { - "type": "string", - "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." - }, - "include": { - "type": "string", - "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "interrupt_agent", - "description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The id of an agent created under you: your direct child or a deeper descendant." - } - }, - "required": [ - "agent_id" - ] - } - }, - { - "name": "job_kill", - "description": "Request cancellation of a running background job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the job." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "job_list", - "description": "List your background jobs (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "job_output", - "description": "Read a background job: output since the previous read for stream jobs, or the result of a finished final-output job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the job finishes or the timeout expires; a timed-out wait leaves the job running. Defaults to false." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds with wait: true. Defaults to and is capped by configuration." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "list_agents", - "description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.", - "parameters": { - "type": "object", - "properties": { - "scope": { - "type": "string", - "description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.", - "enum": [ - "children", - "descendants" - ] - } - } - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "read_image", - "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Large images are downscaled automatically; do not install image libraries or create thumbnails to inspect an image.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to the image file, resolved by the filesystem backend." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "send_message", - "description": "Send a message to an agent. A working agent receives it at its next step; an idle agent starts a new turn with it. Returns delivery confirmation, not the agent's answer.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child." - }, - "message": { - "type": "string", - "description": "The message to deliver to the agent." - } - }, - "required": [ - "agent_id", - "message" - ] - } - }, - { - "name": "skill", - "description": "Load the full instructions for a skill. Call it before acting on a task that names or clearly matches a skill in the session skill catalog.", - "parameters": { - "type": "object", - "properties": { - "name": { - "type": "string", - "description": "The exact skill name from the available skills list." - } - }, - "required": [ - "name" - ] - } - }, - { - "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "todo_write", - "description": "Record and update a task list to plan multi-step work and show progress; skip it for trivial single-step tasks. Add one todo per concrete step before you start. While work remains, keep the todos being worked on `in_progress`, several only when work runs in parallel. Mark each todo `completed` as soon as it is done.", - "parameters": { - "type": "object", - "properties": { - "todos": { - "type": "array", - "description": "The COMPLETE task list, replacing any previous list.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "content": { - "type": "string", - "description": "What the task is — a short imperative line." - }, - "status": { - "type": "string", - "description": "pending (not started) | in_progress (now) | completed (done).", - "enum": [ - "pending", - "in_progress", - "completed" - ] - } - }, - "required": [ - "content", - "status" - ] - } - } - }, - "required": [ - "todos" - ] - } - }, - { - "name": "update_goal", - "description": "Update the current goal.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit, pause, and resume require a direct top-level human request. complete and blocked are also allowed during an automatic continuation of this goal; blocked is rejected before the configured minimum round count.", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Required only with action blocked: the concrete condition that persisted across rounds and blocks progress." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "name": "web_fetch", - "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", - "parameters": { - "type": "object", - "properties": { - "url": { - "type": "string", - "description": "The HTTP(S) URL to fetch." - } - }, - "required": [ - "url" - ] - } - }, - { - "name": "web_search", - "description": "Search the web for current information. Returns an optional summary answer and a list of source URLs.", - "parameters": { - "type": "object", - "properties": { - "queries": { - "type": "array", - "description": "1–4 search queries; their results are merged.", - "items": { - "type": "string" - } - } - }, - "required": [ - "queries" - ] - } - }, - { - "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. A stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) end the whole script instead of producing `null`. The script has no filesystem, network, timer, or Node.js APIs; the agents do the work.", - "parameters": { - "type": "object", - "properties": { - "script": { - "type": "string", - "description": "The plain JavaScript body, not TypeScript and without an `export const meta` statement; top-level await is allowed. End with `return `; the JSON-serializable value is this tool's result." - }, - "meta": { - "type": "object", - "description": "The workflow identity as plain JSON, not code.", - "additionalProperties": true, - "properties": { - "name": { - "type": "string", - "description": "Short kebab-case workflow name." - }, - "description": { - "type": "string", - "description": "One-line description of what the workflow does." - }, - "whenToUse": { - "type": "string", - "description": "Optional guidance on when this workflow applies." - }, - "phases": { - "type": "array", - "description": "Optional phase declarations matched by phase() calls.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "title": { - "type": "string", - "description": "The phase title phase() calls match by exact string." - }, - "detail": { - "type": "string", - "description": "Optional one-line description of the phase." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "model": { - "type": "string", - "description": "Optional model override this phase is expected to use." - } - }, - "required": [ - "title" - ] - } - } - }, - "required": [ - "name", - "description" - ] - }, - "args": { - "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", - "additionalProperties": true - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background job: return a job id immediately instead of waiting; the return value arrives with the completion notice." - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "working_directory", - "description": "Read the current working directory, or change it with cd. Relative paths use the current directory. Existing shells and running processes keep their own directories.", - "parameters": { - "type": "object", - "properties": { - "cd": { - "type": "string", - "description": "Existing directory to enter. Omit to read the current directory." - } - } - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend. Provide `file_path` before `content` in the arguments." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ], - "changes": [ - [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, - { - "name": "bash", - "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." - }, - "command": { - "type": "string", - "description": "The bash command to execute." - }, - "timeoutMs": { - "type": "number", - "description": "Timeout in milliseconds. The executor applies its configured default and cap; on expiry the command moves to the background as a job instead of being killed." - }, - "workdir": { - "type": "string", - "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." - }, - "run_in_background": { - "type": "boolean", - "description": "Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact command the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "description", - "command" - ] - } - }, - { - "name": "create_goal", - "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend. Provide `file_path` before `old_string` and `new_string` in the arguments." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current session goal, including the id and revision that update_goal requires.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "glob", - "description": "Find files, not directories, whose paths match a glob pattern, including hidden and ignored files. Returns up to 100 paths in modification-time order; a larger result keeps the first paths and reports where the complete list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." - }, - "path": { - "type": "string", - "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "grep", - "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns up to 250 matches; a larger result reports where the complete match list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Regular expression to search for (ripgrep syntax)." - }, - "path": { - "type": "string", - "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." - }, - "include": { - "type": "string", - "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "interrupt_agent", - "description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The id of an agent created under you: your direct child or a deeper descendant." - } - }, - "required": [ - "agent_id" - ] - } - }, - { - "name": "job_kill", - "description": "Request cancellation of a running background job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the job." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "job_list", - "description": "List your background jobs (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "job_output", - "description": "Read a background job: output since the previous read for stream jobs, or the result of a finished final-output job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the job finishes or the timeout expires; a timed-out wait leaves the job running. Defaults to false." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds with wait: true. Defaults to and is capped by configuration." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "list_agents", - "description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.", - "parameters": { - "type": "object", - "properties": { - "scope": { - "type": "string", - "description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.", - "enum": [ - "children", - "descendants" - ] - } - } - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "read_image", - "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Large images are downscaled automatically; do not install image libraries or create thumbnails to inspect an image.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to the image file, resolved by the filesystem backend." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "send_message", - "description": "Send a message to an agent. A working agent receives it at its next step; an idle agent starts a new turn with it. Returns delivery confirmation, not the agent's answer.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child." - }, - "message": { - "type": "string", - "description": "The message to deliver to the agent." - } - }, - "required": [ - "agent_id", - "message" - ] - } - }, - { - "name": "skill", - "description": "Load the full instructions for a skill. Call it before acting on a task that names or clearly matches a skill in the session skill catalog.", - "parameters": { - "type": "object", - "properties": { - "name": { - "type": "string", - "description": "The exact skill name from the available skills list." - } - }, - "required": [ - "name" - ] - } - }, - { - "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "todo_write", - "description": "Record and update a task list to plan multi-step work and show progress; skip it for trivial single-step tasks. Add one todo per concrete step before you start. While work remains, keep the todos being worked on `in_progress`, several only when work runs in parallel. Mark each todo `completed` as soon as it is done.", - "parameters": { - "type": "object", - "properties": { - "todos": { - "type": "array", - "description": "The COMPLETE task list, replacing any previous list.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "content": { - "type": "string", - "description": "What the task is — a short imperative line." - }, - "status": { - "type": "string", - "description": "pending (not started) | in_progress (now) | completed (done).", - "enum": [ - "pending", - "in_progress", - "completed" - ] - } - }, - "required": [ - "content", - "status" - ] - } - } - }, - "required": [ - "todos" - ] - } - }, - { - "name": "update_goal", - "description": "Update the current goal.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit, pause, and resume require a direct top-level human request. complete and blocked are also allowed during an automatic continuation of this goal; blocked is rejected before the configured minimum round count.", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Required only with action blocked: the concrete condition that persisted across rounds and blocks progress." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "name": "web_fetch", - "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", - "parameters": { - "type": "object", - "properties": { - "url": { - "type": "string", - "description": "The HTTP(S) URL to fetch." - } - }, - "required": [ - "url" - ] - } - }, - { - "name": "web_search", - "description": "Search the web for current information. Returns an optional summary answer and a list of source URLs.", - "parameters": { - "type": "object", - "properties": { - "queries": { - "type": "array", - "description": "1–4 search queries; their results are merged.", - "items": { - "type": "string" - } - } - }, - "required": [ - "queries" - ] - } - }, - { - "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. A stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) end the whole script instead of producing `null`. The script has no filesystem, network, timer, or Node.js APIs; the agents do the work.", - "parameters": { - "type": "object", - "properties": { - "script": { - "type": "string", - "description": "The plain JavaScript body, not TypeScript and without an `export const meta` statement; top-level await is allowed. End with `return `; the JSON-serializable value is this tool's result." - }, - "meta": { - "type": "object", - "description": "The workflow identity as plain JSON, not code.", - "additionalProperties": true, - "properties": { - "name": { - "type": "string", - "description": "Short kebab-case workflow name." - }, - "description": { - "type": "string", - "description": "One-line description of what the workflow does." - }, - "whenToUse": { - "type": "string", - "description": "Optional guidance on when this workflow applies." - }, - "phases": { - "type": "array", - "description": "Optional phase declarations matched by phase() calls.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "title": { - "type": "string", - "description": "The phase title phase() calls match by exact string." - }, - "detail": { - "type": "string", - "description": "Optional one-line description of the phase." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "model": { - "type": "string", - "description": "Optional model override this phase is expected to use." - } - }, - "required": [ - "title" - ] - } - } - }, - "required": [ - "name", - "description" - ] - }, - "args": { - "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", - "additionalProperties": true - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background job: return a job id immediately instead of waiting; the return value arrives with the completion notice." - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "working_directory", - "description": "Read the current working directory, or change it with cd. Relative paths use the current directory. Existing shells and running processes keep their own directories.", - "parameters": { - "type": "object", - "properties": { - "cd": { - "type": "string", - "description": "Existing directory to enter. Omit to read the current directory." - } - } - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend. Provide `file_path` before `content` in the arguments." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ] - ] -} diff --git a/snapshots/sdk/subagent-activation-limit/system-prompt.1.expected.md b/snapshots/sdk/subagent-activation-limit/system-prompt.1.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/sdk/subagent-activation-limit/system-prompt.1.expected.md +++ b/snapshots/sdk/subagent-activation-limit/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-activation-limit/tool-schemas.1.expected.json b/snapshots/sdk/subagent-activation-limit/tool-schemas.1.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/sdk/subagent-activation-limit/tool-schemas.1.expected.json +++ b/snapshots/sdk/subagent-activation-limit/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-continuable-inheritance/system-prompt.1.expected.md b/snapshots/sdk/subagent-continuable-inheritance/system-prompt.1.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/sdk/subagent-continuable-inheritance/system-prompt.1.expected.md +++ b/snapshots/sdk/subagent-continuable-inheritance/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-continuable-inheritance/tool-schemas.1.expected.json b/snapshots/sdk/subagent-continuable-inheritance/tool-schemas.1.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/sdk/subagent-continuable-inheritance/tool-schemas.1.expected.json +++ b/snapshots/sdk/subagent-continuable-inheritance/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-continuable/system-prompt.1.expected.md b/snapshots/sdk/subagent-continuable/system-prompt.1.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/sdk/subagent-continuable/system-prompt.1.expected.md +++ b/snapshots/sdk/subagent-continuable/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-continuable/tool-schemas.1.expected.json b/snapshots/sdk/subagent-continuable/tool-schemas.1.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/sdk/subagent-continuable/tool-schemas.1.expected.json +++ b/snapshots/sdk/subagent-continuable/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-dsh-sdk-diagnostic/system-prompt.expected.md b/snapshots/sdk/subagent-dsh-sdk-diagnostic/system-prompt.expected.md index 5f1e311730..557223b560 100644 --- a/snapshots/sdk/subagent-dsh-sdk-diagnostic/system-prompt.expected.md +++ b/snapshots/sdk/subagent-dsh-sdk-diagnostic/system-prompt.expected.md @@ -6,11 +6,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-dsh-sdk-diagnostic/tool-schemas.expected.json b/snapshots/sdk/subagent-dsh-sdk-diagnostic/tool-schemas.expected.json index a392470765..e21bdfc94e 100644 --- a/snapshots/sdk/subagent-dsh-sdk-diagnostic/tool-schemas.expected.json +++ b/snapshots/sdk/subagent-dsh-sdk-diagnostic/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.1.expected.md b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.1.expected.md index 23774a47e5..88216ca091 100644 --- a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.1.expected.md +++ b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.1.expected.md @@ -6,11 +6,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.expected.md b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.expected.md index e09093bb78..312d216243 100644 --- a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.expected.md +++ b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/system-prompt.expected.md @@ -6,11 +6,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.1.expected.json b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.1.expected.json index 0482c38361..ef6c62a3fb 100644 --- a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.1.expected.json +++ b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.expected.json b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.expected.json index 4f6c3f2b5e..02b43f6d74 100644 --- a/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.expected.json +++ b/snapshots/sdk/subagent-dsh-sdk-dynamic-route/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-list-agents/system-prompt.1.expected.md b/snapshots/sdk/subagent-list-agents/system-prompt.1.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/sdk/subagent-list-agents/system-prompt.1.expected.md +++ b/snapshots/sdk/subagent-list-agents/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-list-agents/tool-schemas.1.expected.json b/snapshots/sdk/subagent-list-agents/tool-schemas.1.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/sdk/subagent-list-agents/tool-schemas.1.expected.json +++ b/snapshots/sdk/subagent-list-agents/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/subagent-send-message/system-prompt.1.expected.md b/snapshots/sdk/subagent-send-message/system-prompt.1.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/sdk/subagent-send-message/system-prompt.1.expected.md +++ b/snapshots/sdk/subagent-send-message/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/subagent-send-message/tool-schemas.1.expected.json b/snapshots/sdk/subagent-send-message/tool-schemas.1.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/sdk/subagent-send-message/tool-schemas.1.expected.json +++ b/snapshots/sdk/subagent-send-message/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/text-turn/system-prompt.expected.md b/snapshots/sdk/text-turn/system-prompt.expected.md index 77fe3f35ef..6288c22387 100644 --- a/snapshots/sdk/text-turn/system-prompt.expected.md +++ b/snapshots/sdk/text-turn/system-prompt.expected.md @@ -6,11 +6,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/sdk/text-turn/tool-schemas.expected.json b/snapshots/sdk/text-turn/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/sdk/text-turn/tool-schemas.expected.json +++ b/snapshots/sdk/text-turn/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/sdk/tool-error-details/notifications.expected.jsonl b/snapshots/sdk/tool-error-details/notifications.expected.jsonl index 1e7915e511..255a064363 100644 --- a/snapshots/sdk/tool-error-details/notifications.expected.jsonl +++ b/snapshots/sdk/tool-error-details/notifications.expected.jsonl @@ -6,7 +6,7 @@ {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"system/message","seq":7,"time":0,"data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":8,"time":0,"data":{"content":[{"type":"text","text":"Exercise a native denial and a caught PTC inner denial, then reply ERROR_DETAILS_OK."}],"source":{"kind":"user"},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"user/message","seq":9,"time":0,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{sessionId}}"},"surfaceOp":"append"}}} -{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}}} +{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":10,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/context","seq":11,"time":0,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"session/title","seq":12,"time":0,"data":{"title":"Exercise a native denial and","messageSeqs":[8],"source":{"kind":"fallback"}}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":13,"time":0,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"denied-native","name":"bash","arguments":"{\"command\":\"echo AUTO_DENIED\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"denied-native","name":"bash","args":["{\"command\":\"echo AUTO_DENIED\"}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"denied-native","name":"bash","arguments":"{\"command\":\"echo AUTO_DENIED\"}"}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}}} @@ -16,7 +16,7 @@ {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"step/start","seq":17,"time":0,"data":{"turn":1,"step":2}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"system/message","seq":18,"time":0,"data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{sessionId}}"}},"sourceEventSeqs":[7],"surfaceOp":{"op":"replace","startSeq":7,"endSeq":7}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"request/header","seq":19,"time":0,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["run_code"]},"reason":"change","startsSeries":true}}}} -{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"developer/message","seq":20,"time":0,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"run_code"},{"type":"tool-removal","toolName":"apply_patch"},{"type":"tool-removal","toolName":"bash"},{"type":"tool-removal","toolName":"create_goal"},{"type":"tool-removal","toolName":"edit"},{"type":"tool-removal","toolName":"get_goal"},{"type":"tool-removal","toolName":"glob"},{"type":"tool-removal","toolName":"grep"},{"type":"tool-removal","toolName":"interrupt_agent"},{"type":"tool-removal","toolName":"job_kill"},{"type":"tool-removal","toolName":"job_list"},{"type":"tool-removal","toolName":"job_output"},{"type":"tool-removal","toolName":"list_agents"},{"type":"tool-removal","toolName":"read"},{"type":"tool-removal","toolName":"read_image"},{"type":"tool-removal","toolName":"send_message"},{"type":"tool-removal","toolName":"skill"},{"type":"tool-removal","toolName":"subagent"},{"type":"tool-removal","toolName":"subagent_fork"},{"type":"tool-removal","toolName":"todo_write"},{"type":"tool-removal","toolName":"update_goal"},{"type":"tool-removal","toolName":"web_fetch"},{"type":"tool-removal","toolName":"web_search"},{"type":"tool-removal","toolName":"workflow"},{"type":"tool-removal","toolName":"working_directory"},{"type":"tool-removal","toolName":"write"}],"role":"developer","id":"{{sessionId}}"},"headerSeq":19},"surfaceOp":"append"}}} +{"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"developer/message","seq":20,"time":0,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"run_code"},{"type":"tool-removal","toolName":"bash"},{"type":"tool-removal","toolName":"create_goal"},{"type":"tool-removal","toolName":"edit"},{"type":"tool-removal","toolName":"get_goal"},{"type":"tool-removal","toolName":"glob"},{"type":"tool-removal","toolName":"grep"},{"type":"tool-removal","toolName":"interrupt_agent"},{"type":"tool-removal","toolName":"job_kill"},{"type":"tool-removal","toolName":"job_list"},{"type":"tool-removal","toolName":"job_output"},{"type":"tool-removal","toolName":"list_agents"},{"type":"tool-removal","toolName":"read"},{"type":"tool-removal","toolName":"read_image"},{"type":"tool-removal","toolName":"send_message"},{"type":"tool-removal","toolName":"skill"},{"type":"tool-removal","toolName":"subagent"},{"type":"tool-removal","toolName":"subagent_fork"},{"type":"tool-removal","toolName":"todo_write"},{"type":"tool-removal","toolName":"update_goal"},{"type":"tool-removal","toolName":"web_fetch"},{"type":"tool-removal","toolName":"web_search"},{"type":"tool-removal","toolName":"workflow"},{"type":"tool-removal","toolName":"working_directory"},{"type":"tool-removal","toolName":"write"}],"role":"developer","id":"{{sessionId}}"},"headerSeq":19},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":21,"time":0,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"denied-code","name":"run_code","arguments":"{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{sessionId}}"},"stream":[{"type":"chunk","time":0,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":0,"index":0,"dt":[],"id":"denied-code","name":"run_code","args":["{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"]},{"type":"chunk","time":0,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"denied-code","name":"run_code","arguments":"{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"}}},{"type":"chunk","time":0,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"denied-code","name":"run_code","arguments":"{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"}}}} {"method":"session.event","params":{"sessionId":"{{sessionId}}","event":{"type":"tool/ptc-dispatch-start","seq":23,"time":0,"data":{"rootCallId":"denied-code","parentCallId":"denied-code","subCallId":"denied-code:ptc:1","name":"bash","arguments":{"command":"echo AUTO_DENIED"}}}}} diff --git a/snapshots/sdk/tool-error-details/session.v4.jsonl b/snapshots/sdk/tool-error-details/session.v4.jsonl index d6a766da69..e88e55d31a 100644 --- a/snapshots/sdk/tool-error-details/session.v4.jsonl +++ b/snapshots/sdk/tool-error-details/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Exercise a native denial and a caught PTC inner denial, then reply ERROR_DETAILS_OK."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Exercise a native denial and","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"denied-native","name":"bash","arguments":"{\"command\":\"echo AUTO_DENIED\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"stream":[{"type":"chunk","time":1791315723125,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791315723125,"index":0,"dt":[],"id":"denied-native","name":"bash","args":["{\"command\":\"echo AUTO_DENIED\"}"]},{"type":"chunk","time":1791315723125,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"denied-native","name":"bash","arguments":"{\"command\":\"echo AUTO_DENIED\"}"}}},{"type":"chunk","time":1791315723125,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -19,7 +19,7 @@ {"type":"step/start","data":{"turn":1,"step":2}} {"type":"system/message","data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:6}}"}},"sourceEventSeqs":[7],"surfaceOp":{"op":"replace","startSeq":7,"endSeq":7}} {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["run_code"]},"reason":"change","startsSeries":true}} -{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"run_code"},{"type":"tool-removal","toolName":"apply_patch"},{"type":"tool-removal","toolName":"bash"},{"type":"tool-removal","toolName":"create_goal"},{"type":"tool-removal","toolName":"edit"},{"type":"tool-removal","toolName":"get_goal"},{"type":"tool-removal","toolName":"glob"},{"type":"tool-removal","toolName":"grep"},{"type":"tool-removal","toolName":"interrupt_agent"},{"type":"tool-removal","toolName":"job_kill"},{"type":"tool-removal","toolName":"job_list"},{"type":"tool-removal","toolName":"job_output"},{"type":"tool-removal","toolName":"list_agents"},{"type":"tool-removal","toolName":"read"},{"type":"tool-removal","toolName":"read_image"},{"type":"tool-removal","toolName":"send_message"},{"type":"tool-removal","toolName":"skill"},{"type":"tool-removal","toolName":"subagent"},{"type":"tool-removal","toolName":"subagent_fork"},{"type":"tool-removal","toolName":"todo_write"},{"type":"tool-removal","toolName":"update_goal"},{"type":"tool-removal","toolName":"web_fetch"},{"type":"tool-removal","toolName":"web_search"},{"type":"tool-removal","toolName":"workflow"},{"type":"tool-removal","toolName":"working_directory"},{"type":"tool-removal","toolName":"write"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} +{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"run_code"},{"type":"tool-removal","toolName":"bash"},{"type":"tool-removal","toolName":"create_goal"},{"type":"tool-removal","toolName":"edit"},{"type":"tool-removal","toolName":"get_goal"},{"type":"tool-removal","toolName":"glob"},{"type":"tool-removal","toolName":"grep"},{"type":"tool-removal","toolName":"interrupt_agent"},{"type":"tool-removal","toolName":"job_kill"},{"type":"tool-removal","toolName":"job_list"},{"type":"tool-removal","toolName":"job_output"},{"type":"tool-removal","toolName":"list_agents"},{"type":"tool-removal","toolName":"read"},{"type":"tool-removal","toolName":"read_image"},{"type":"tool-removal","toolName":"send_message"},{"type":"tool-removal","toolName":"skill"},{"type":"tool-removal","toolName":"subagent"},{"type":"tool-removal","toolName":"subagent_fork"},{"type":"tool-removal","toolName":"todo_write"},{"type":"tool-removal","toolName":"update_goal"},{"type":"tool-removal","toolName":"web_fetch"},{"type":"tool-removal","toolName":"web_search"},{"type":"tool-removal","toolName":"workflow"},{"type":"tool-removal","toolName":"working_directory"},{"type":"tool-removal","toolName":"write"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"denied-code","name":"run_code","arguments":"{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1791315723151,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791315723151,"index":0,"dt":[],"id":"denied-code","name":"run_code","args":["{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"]},{"type":"chunk","time":1791315723151,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"denied-code","name":"run_code","arguments":"{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"}}},{"type":"chunk","time":1791315723151,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"denied-code","name":"run_code","arguments":"{\"code\":\"try { await tools.bash({command: \\\"echo AUTO_DENIED\\\"}) } catch (error) { return error.message }\",\"description\":\"Catch one denied inner call\"}"}} {"type":"tool/ptc-dispatch-start","data":{"rootCallId":"denied-code","parentCallId":"denied-code","subCallId":"denied-code:ptc:1","name":"bash","arguments":{"command":"echo AUTO_DENIED"}}} diff --git a/snapshots/sdk/tool-error-details/system-prompt.expected.md b/snapshots/sdk/tool-error-details/system-prompt.expected.md index 665f4fa8de..aca0bd51a7 100644 --- a/snapshots/sdk/tool-error-details/system-prompt.expected.md +++ b/snapshots/sdk/tool-error-details/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -87,15 +83,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -308,27 +295,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/sdk/tool-error-details/tool-schemas.expected.json b/snapshots/sdk/tool-error-details/tool-schemas.expected.json index 4d855f5c09..6edd4627f4 100644 --- a/snapshots/sdk/tool-error-details/tool-schemas.expected.json +++ b/snapshots/sdk/tool-error-details/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/advanced-toolchain/session.v4.jsonl b/snapshots/session/advanced-toolchain/session.v4.jsonl index 0a8802a496..add1f65e1f 100644 --- a/snapshots/session/advanced-toolchain/session.v4.jsonl +++ b/snapshots/session/advanced-toolchain/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: list runtime inspect providers; discover providers through run_code when available; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; list providers again; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","bash","cordis_inspect_list","cordis_inspect_query","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["bash","cordis_inspect_list","cordis_inspect_query","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Run this advanced flow exactly","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-inspect-before","name":"cordis_inspect_list","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":3,"outputTokens":3},"stream":[{"type":"chunk","time":1791315715021,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791315715022,"index":0,"dt":[],"id":"advanced-inspect-before","name":"cordis_inspect_list","args":["{}"]},{"type":"chunk","time":1791315715022,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-inspect-before","name":"cordis_inspect_list","arguments":"{}"}}},{"type":"chunk","time":1791315715022,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}},{"type":"chunk","time":1791315715022,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -19,7 +19,7 @@ {"type":"step/start","data":{"turn":1,"step":2}} {"type":"system/message","data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:6}}"}},"sourceEventSeqs":[7],"surfaceOp":{"op":"replace","startSeq":7,"endSeq":7}} {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["run_code"]},"reason":"change","startsSeries":true}} -{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"run_code"},{"type":"tool-removal","toolName":"apply_patch"},{"type":"tool-removal","toolName":"bash"},{"type":"tool-removal","toolName":"cordis_inspect_list"},{"type":"tool-removal","toolName":"cordis_inspect_query"},{"type":"tool-removal","toolName":"create_goal"},{"type":"tool-removal","toolName":"edit"},{"type":"tool-removal","toolName":"get_goal"},{"type":"tool-removal","toolName":"glob"},{"type":"tool-removal","toolName":"grep"},{"type":"tool-removal","toolName":"interrupt_agent"},{"type":"tool-removal","toolName":"job_kill"},{"type":"tool-removal","toolName":"job_list"},{"type":"tool-removal","toolName":"job_output"},{"type":"tool-removal","toolName":"list_agents"},{"type":"tool-removal","toolName":"read"},{"type":"tool-removal","toolName":"read_image"},{"type":"tool-removal","toolName":"send_message"},{"type":"tool-removal","toolName":"skill"},{"type":"tool-removal","toolName":"subagent"},{"type":"tool-removal","toolName":"subagent_fork"},{"type":"tool-removal","toolName":"todo_write"},{"type":"tool-removal","toolName":"update_goal"},{"type":"tool-removal","toolName":"web_fetch"},{"type":"tool-removal","toolName":"web_search"},{"type":"tool-removal","toolName":"workflow"},{"type":"tool-removal","toolName":"working_directory"},{"type":"tool-removal","toolName":"write"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} +{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"run_code"},{"type":"tool-removal","toolName":"bash"},{"type":"tool-removal","toolName":"cordis_inspect_list"},{"type":"tool-removal","toolName":"cordis_inspect_query"},{"type":"tool-removal","toolName":"create_goal"},{"type":"tool-removal","toolName":"edit"},{"type":"tool-removal","toolName":"get_goal"},{"type":"tool-removal","toolName":"glob"},{"type":"tool-removal","toolName":"grep"},{"type":"tool-removal","toolName":"interrupt_agent"},{"type":"tool-removal","toolName":"job_kill"},{"type":"tool-removal","toolName":"job_list"},{"type":"tool-removal","toolName":"job_output"},{"type":"tool-removal","toolName":"list_agents"},{"type":"tool-removal","toolName":"read"},{"type":"tool-removal","toolName":"read_image"},{"type":"tool-removal","toolName":"send_message"},{"type":"tool-removal","toolName":"skill"},{"type":"tool-removal","toolName":"subagent"},{"type":"tool-removal","toolName":"subagent_fork"},{"type":"tool-removal","toolName":"todo_write"},{"type":"tool-removal","toolName":"update_goal"},{"type":"tool-removal","toolName":"web_fetch"},{"type":"tool-removal","toolName":"web_search"},{"type":"tool-removal","toolName":"workflow"},{"type":"tool-removal","toolName":"working_directory"},{"type":"tool-removal","toolName":"write"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"const inspected = await tools.cordis_inspect_list({}); return inspected.providers.map(provider => provider.id);\",\"description\":\"Discover runtime APIs through PTC\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"usage":{"inputTokens":3,"outputTokens":3},"stream":[{"type":"chunk","time":1791315715055,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791315715055,"index":0,"dt":[],"id":"advanced-code","name":"run_code","args":["{\"code\":\"const inspected = await tools.cordis_inspect_list({}); return inspected.providers.map(provider => provider.id);\",\"description\":\"Discover runtime APIs through PTC\"}"]},{"type":"chunk","time":1791315715055,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"const inspected = await tools.cordis_inspect_list({}); return inspected.providers.map(provider => provider.id);\",\"description\":\"Discover runtime APIs through PTC\"}"}}},{"type":"chunk","time":1791315715055,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}},{"type":"chunk","time":1791315715055,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"const inspected = await tools.cordis_inspect_list({}); return inspected.providers.map(provider => provider.id);\",\"description\":\"Discover runtime APIs through PTC\"}"}} {"type":"tool/ptc-dispatch-start","data":{"rootCallId":"advanced-code","parentCallId":"advanced-code","subCallId":"advanced-code:ptc:1","name":"cordis_inspect_list","arguments":{}}} @@ -28,8 +28,8 @@ {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} {"type":"system/message","data":{"turn":1,"step":3,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:10}}"}},"sourceEventSeqs":[18],"surfaceOp":{"op":"replace","startSeq":18,"endSeq":18}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","bash","cordis_inspect_list","cordis_inspect_query","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} -{"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"apply_patch"},{"type":"tool-addition","toolName":"bash"},{"type":"tool-addition","toolName":"cordis_inspect_list"},{"type":"tool-addition","toolName":"cordis_inspect_query"},{"type":"tool-addition","toolName":"create_goal"},{"type":"tool-addition","toolName":"edit"},{"type":"tool-addition","toolName":"get_goal"},{"type":"tool-addition","toolName":"glob"},{"type":"tool-addition","toolName":"grep"},{"type":"tool-addition","toolName":"interrupt_agent"},{"type":"tool-addition","toolName":"job_kill"},{"type":"tool-addition","toolName":"job_list"},{"type":"tool-addition","toolName":"job_output"},{"type":"tool-addition","toolName":"list_agents"},{"type":"tool-addition","toolName":"read"},{"type":"tool-addition","toolName":"read_image"},{"type":"tool-addition","toolName":"send_message"},{"type":"tool-addition","toolName":"skill"},{"type":"tool-addition","toolName":"subagent"},{"type":"tool-addition","toolName":"subagent_fork"},{"type":"tool-addition","toolName":"todo_write"},{"type":"tool-addition","toolName":"update_goal"},{"type":"tool-addition","toolName":"web_fetch"},{"type":"tool-addition","toolName":"web_search"},{"type":"tool-addition","toolName":"workflow"},{"type":"tool-addition","toolName":"working_directory"},{"type":"tool-addition","toolName":"write"},{"type":"tool-removal","toolName":"run_code"}],"role":"developer","id":"{{message:11}}"},"headerSeq":29},"surfaceOp":"append"} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["bash","cordis_inspect_list","cordis_inspect_query","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} +{"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"bash"},{"type":"tool-addition","toolName":"cordis_inspect_list"},{"type":"tool-addition","toolName":"cordis_inspect_query"},{"type":"tool-addition","toolName":"create_goal"},{"type":"tool-addition","toolName":"edit"},{"type":"tool-addition","toolName":"get_goal"},{"type":"tool-addition","toolName":"glob"},{"type":"tool-addition","toolName":"grep"},{"type":"tool-addition","toolName":"interrupt_agent"},{"type":"tool-addition","toolName":"job_kill"},{"type":"tool-addition","toolName":"job_list"},{"type":"tool-addition","toolName":"job_output"},{"type":"tool-addition","toolName":"list_agents"},{"type":"tool-addition","toolName":"read"},{"type":"tool-addition","toolName":"read_image"},{"type":"tool-addition","toolName":"send_message"},{"type":"tool-addition","toolName":"skill"},{"type":"tool-addition","toolName":"subagent"},{"type":"tool-addition","toolName":"subagent_fork"},{"type":"tool-addition","toolName":"todo_write"},{"type":"tool-addition","toolName":"update_goal"},{"type":"tool-addition","toolName":"web_fetch"},{"type":"tool-addition","toolName":"web_search"},{"type":"tool-addition","toolName":"workflow"},{"type":"tool-addition","toolName":"working_directory"},{"type":"tool-addition","toolName":"write"},{"type":"tool-removal","toolName":"run_code"}],"role":"developer","id":"{{message:11}}"},"headerSeq":29},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\",\"run_in_background\":false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:12}}"},"usage":{"inputTokens":3,"outputTokens":3},"stream":[{"type":"chunk","time":1791315715200,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791315715200,"index":0,"dt":[],"id":"advanced-direct-child","name":"subagent","args":["{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\",\"run_in_background\":false}"]},{"type":"chunk","time":1791315715200,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\",\"run_in_background\":false}"}}},{"type":"chunk","time":1791315715200,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}},{"type":"chunk","time":1791315715200,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\",\"run_in_background\":false}"}} {"type":"subagent/catalog","data":{"version":0,"childId":"{{session:2}}","childCreatedAt":1791315715221,"mode":"continuable","label":"Check direct child"}} diff --git a/snapshots/session/advanced-toolchain/system-prompt.1.expected.md b/snapshots/session/advanced-toolchain/system-prompt.1.expected.md index bdf2a8dfc7..c776c30451 100644 --- a/snapshots/session/advanced-toolchain/system-prompt.1.expected.md +++ b/snapshots/session/advanced-toolchain/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/advanced-toolchain/system-prompt.2.expected.md b/snapshots/session/advanced-toolchain/system-prompt.2.expected.md index bdf2a8dfc7..c776c30451 100644 --- a/snapshots/session/advanced-toolchain/system-prompt.2.expected.md +++ b/snapshots/session/advanced-toolchain/system-prompt.2.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/advanced-toolchain/system-prompt.expected.md b/snapshots/session/advanced-toolchain/system-prompt.expected.md index b9cc40cd1b..46dd5fe0a4 100644 --- a/snapshots/session/advanced-toolchain/system-prompt.expected.md +++ b/snapshots/session/advanced-toolchain/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -87,15 +83,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -321,27 +308,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; @@ -632,11 +598,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/advanced-toolchain/tool-schemas.expected.json b/snapshots/session/advanced-toolchain/tool-schemas.expected.json index d21ee259a9..b2911c0f2d 100644 --- a/snapshots/session/advanced-toolchain/tool-schemas.expected.json +++ b/snapshots/session/advanced-toolchain/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", @@ -725,34 +697,6 @@ } ], [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/agent-instructions/system-prompt.expected.md b/snapshots/session/agent-instructions/system-prompt.expected.md index bdf2a8dfc7..c776c30451 100644 --- a/snapshots/session/agent-instructions/system-prompt.expected.md +++ b/snapshots/session/agent-instructions/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/agent-instructions/tool-schemas.expected.json b/snapshots/session/agent-instructions/tool-schemas.expected.json index 42b0e228ce..f6aebf6daf 100644 --- a/snapshots/session/agent-instructions/tool-schemas.expected.json +++ b/snapshots/session/agent-instructions/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", @@ -645,34 +617,6 @@ ], "changes": [ [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/apply-patch-rejected/runtime.cordis.yml b/snapshots/session/apply-patch-rejected/runtime.cordis.yml deleted file mode 100644 index c442bc8348..0000000000 --- a/snapshots/session/apply-patch-rejected/runtime.cordis.yml +++ /dev/null @@ -1,3 +0,0 @@ -# Recorded with the observation policy on: the read-first refusal and retry are the scenario. -- id: fs-observation-policy - disabled: false diff --git a/snapshots/session/apply-patch-update/system-prompt.expected.md b/snapshots/session/apply-patch-update/system-prompt.expected.md index d197219bc4..ac5171f2f3 100644 --- a/snapshots/session/apply-patch-update/system-prompt.expected.md +++ b/snapshots/session/apply-patch-update/system-prompt.expected.md @@ -6,11 +6,11 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Prefer apply_patch over separate edit calls for changes across files or separated regions. Read a file before updating, deleting, or moving it (the default fs-observation-policy requires it), unless you just created or edited it in this session. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/apply-patch-update/tool-schemas.expected.json b/snapshots/session/apply-patch-update/tool-schemas.expected.json index 80440d8e35..cea14368fb 100644 --- a/snapshots/session/apply-patch-update/tool-schemas.expected.json +++ b/snapshots/session/apply-patch-update/tool-schemas.expected.json @@ -8,7 +8,7 @@ "properties": { "input": { "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." + "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. Read existing files before updating, deleting, or moving them." }, "sandbox_permissions": { "type": "string", diff --git a/snapshots/session/background-confinement-failure/system-prompt.expected.md b/snapshots/session/background-confinement-failure/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/background-confinement-failure/system-prompt.expected.md +++ b/snapshots/session/background-confinement-failure/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/background-confinement-failure/tool-schemas.expected.json b/snapshots/session/background-confinement-failure/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/background-confinement-failure/tool-schemas.expected.json +++ b/snapshots/session/background-confinement-failure/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/both-mode-turn/system-prompt.expected.md b/snapshots/session/both-mode-turn/system-prompt.expected.md index dda7281f59..ed5922ee4f 100644 --- a/snapshots/session/both-mode-turn/system-prompt.expected.md +++ b/snapshots/session/both-mode-turn/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -273,27 +262,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/browser-use-chrome-devtools-mcp/system-prompt.expected.md b/snapshots/session/browser-use-chrome-devtools-mcp/system-prompt.expected.md index c3272dfe99..c07f1a39fe 100644 --- a/snapshots/session/browser-use-chrome-devtools-mcp/system-prompt.expected.md +++ b/snapshots/session/browser-use-chrome-devtools-mcp/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/browser-use-chrome-devtools-mcp/tool-schemas.expected.json b/snapshots/session/browser-use-chrome-devtools-mcp/tool-schemas.expected.json index ae3310a81e..cc51623a5b 100644 --- a/snapshots/session/browser-use-chrome-devtools-mcp/tool-schemas.expected.json +++ b/snapshots/session/browser-use-chrome-devtools-mcp/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/browser-use-playwright-mcp/system-prompt.expected.md b/snapshots/session/browser-use-playwright-mcp/system-prompt.expected.md index eca109335c..63b5fb94fa 100644 --- a/snapshots/session/browser-use-playwright-mcp/system-prompt.expected.md +++ b/snapshots/session/browser-use-playwright-mcp/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/browser-use-playwright-mcp/tool-schemas.expected.json b/snapshots/session/browser-use-playwright-mcp/tool-schemas.expected.json index d5b383effb..43d2d085bd 100644 --- a/snapshots/session/browser-use-playwright-mcp/tool-schemas.expected.json +++ b/snapshots/session/browser-use-playwright-mcp/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/browser-use-stagehand-native/system-prompt.expected.md b/snapshots/session/browser-use-stagehand-native/system-prompt.expected.md index 64bde8515e..2958e580fc 100644 --- a/snapshots/session/browser-use-stagehand-native/system-prompt.expected.md +++ b/snapshots/session/browser-use-stagehand-native/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/browser-use-stagehand-native/tool-schemas.expected.json b/snapshots/session/browser-use-stagehand-native/tool-schemas.expected.json index 019528e195..b4bd87c655 100644 --- a/snapshots/session/browser-use-stagehand-native/tool-schemas.expected.json +++ b/snapshots/session/browser-use-stagehand-native/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/claude-code-mods/system-prompt.expected.md b/snapshots/session/claude-code-mods/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/claude-code-mods/system-prompt.expected.md +++ b/snapshots/session/claude-code-mods/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/claude-code-mods/tool-schemas.expected.json b/snapshots/session/claude-code-mods/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/claude-code-mods/tool-schemas.expected.json +++ b/snapshots/session/claude-code-mods/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/compaction-output-reserve/cordis.snapshot.yml b/snapshots/session/compaction-output-reserve/cordis.snapshot.yml index 98ee410af1..09b732a14a 100644 --- a/snapshots/session/compaction-output-reserve/cordis.snapshot.yml +++ b/snapshots/session/compaction-output-reserve/cordis.snapshot.yml @@ -1,11 +1,6 @@ # With 1,800 tokens of headroom, a 1,000-token output reservation lowers the # trigger from 6,822 to 5,822, between the history and its condensed replacement. -# Keep the recorded tool set for the fixed compaction thresholds. -- id: tool-fs - config: - applyPatch: false - - id: agent-instructions disabled: true diff --git a/snapshots/session/compaction-recovery/cordis.snapshot.yml b/snapshots/session/compaction-recovery/cordis.snapshot.yml index dccb8a0242..f389be6b5e 100644 --- a/snapshots/session/compaction-recovery/cordis.snapshot.yml +++ b/snapshots/session/compaction-recovery/cordis.snapshot.yml @@ -27,8 +27,3 @@ models: - id: deepseek-v4-flash contextWindow: 128000 - -# Keep the recorded tool set shared by the fixed-budget compaction scenarios. -- id: tool-fs - config: - applyPatch: false diff --git a/snapshots/session/compaction-recovery/system-prompt.expected.md b/snapshots/session/compaction-recovery/system-prompt.expected.md index b4373cffd9..4129b103da 100644 --- a/snapshots/session/compaction-recovery/system-prompt.expected.md +++ b/snapshots/session/compaction-recovery/system-prompt.expected.md @@ -9,9 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/compaction-summary-headroom/cordis.snapshot.yml b/snapshots/session/compaction-summary-headroom/cordis.snapshot.yml index 4593e4f50a..2c6f7de38e 100644 --- a/snapshots/session/compaction-summary-headroom/cordis.snapshot.yml +++ b/snapshots/session/compaction-summary-headroom/cordis.snapshot.yml @@ -1,11 +1,6 @@ # The summary output cap inherits the 1,800-token headroom. A 1,000-token # request output reservation lowers the proactive trigger to 5,822 tokens. -# Keep the recorded tool set for the fixed compaction thresholds. -- id: tool-fs - config: - applyPatch: false - - id: agent-instructions disabled: true diff --git a/snapshots/session/computer-use-cua-driver-mcp/system-prompt.expected.md b/snapshots/session/computer-use-cua-driver-mcp/system-prompt.expected.md index d0b8f7b297..ec0feaa6d1 100644 --- a/snapshots/session/computer-use-cua-driver-mcp/system-prompt.expected.md +++ b/snapshots/session/computer-use-cua-driver-mcp/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/computer-use-cua-driver-mcp/tool-schemas.expected.json b/snapshots/session/computer-use-cua-driver-mcp/tool-schemas.expected.json index 7f5b451b53..e1d4a256e3 100644 --- a/snapshots/session/computer-use-cua-driver-mcp/tool-schemas.expected.json +++ b/snapshots/session/computer-use-cua-driver-mcp/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/computer-use-cua-driver-native/system-prompt.expected.md b/snapshots/session/computer-use-cua-driver-native/system-prompt.expected.md index bda6178a25..b80574dac4 100644 --- a/snapshots/session/computer-use-cua-driver-native/system-prompt.expected.md +++ b/snapshots/session/computer-use-cua-driver-native/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/computer-use-cua-driver-native/tool-schemas.expected.json b/snapshots/session/computer-use-cua-driver-native/tool-schemas.expected.json index 8e11b504a1..078ba05d26 100644 --- a/snapshots/session/computer-use-cua-driver-native/tool-schemas.expected.json +++ b/snapshots/session/computer-use-cua-driver-native/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/cordis-inspect-jsdoc/system-prompt.expected.md b/snapshots/session/cordis-inspect-jsdoc/system-prompt.expected.md index bdf2a8dfc7..c776c30451 100644 --- a/snapshots/session/cordis-inspect-jsdoc/system-prompt.expected.md +++ b/snapshots/session/cordis-inspect-jsdoc/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/cordis-inspect-jsdoc/tool-schemas.expected.json b/snapshots/session/cordis-inspect-jsdoc/tool-schemas.expected.json index c94322a8cd..f33d4e7c51 100644 --- a/snapshots/session/cordis-inspect-jsdoc/tool-schemas.expected.json +++ b/snapshots/session/cordis-inspect-jsdoc/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/cua-native/system-prompt.expected.md b/snapshots/session/cua-native/system-prompt.expected.md index 05c4c14d90..c842954b3b 100644 --- a/snapshots/session/cua-native/system-prompt.expected.md +++ b/snapshots/session/cua-native/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/cua-native/tool-schemas.expected.json b/snapshots/session/cua-native/tool-schemas.expected.json index a5d36955d7..8fd3a17423 100644 --- a/snapshots/session/cua-native/tool-schemas.expected.json +++ b/snapshots/session/cua-native/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/cua-ptc/system-prompt.expected.md b/snapshots/session/cua-ptc/system-prompt.expected.md index 681b4a55a2..55611ceb34 100644 --- a/snapshots/session/cua-ptc/system-prompt.expected.md +++ b/snapshots/session/cua-ptc/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -97,15 +95,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -320,27 +309,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/deepseek-messages-system-prompt/system-prompt.expected.md b/snapshots/session/deepseek-messages-system-prompt/system-prompt.expected.md index 1d3b3bee67..0296cb556a 100644 --- a/snapshots/session/deepseek-messages-system-prompt/system-prompt.expected.md +++ b/snapshots/session/deepseek-messages-system-prompt/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/deepseek-messages-system-prompt/tool-schemas.expected.json b/snapshots/session/deepseek-messages-system-prompt/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/deepseek-messages-system-prompt/tool-schemas.expected.json +++ b/snapshots/session/deepseek-messages-system-prompt/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/deepseek-protocol-system-prompt/system-prompt.expected.md b/snapshots/session/deepseek-protocol-system-prompt/system-prompt.expected.md index 1d3b3bee67..0296cb556a 100644 --- a/snapshots/session/deepseek-protocol-system-prompt/system-prompt.expected.md +++ b/snapshots/session/deepseek-protocol-system-prompt/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/deepseek-protocol-system-prompt/tool-schemas.expected.json b/snapshots/session/deepseek-protocol-system-prompt/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/deepseek-protocol-system-prompt/tool-schemas.expected.json +++ b/snapshots/session/deepseek-protocol-system-prompt/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/dynamic-tool-prompt-updates/session.v4.jsonl b/snapshots/session/dynamic-tool-prompt-updates/session.v4.jsonl index 9bbfbca31e..7532f7f79d 100644 --- a/snapshots/session/dynamic-tool-prompt-updates/session.v4.jsonl +++ b/snapshots/session/dynamic-tool-prompt-updates/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Read task.txt, call the newly available snapshot_ping tool once, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","systemPromptUpdate":"in-history"}} {"type":"session/title","data":{"title":"Read task.txt, call the newly","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":1790149644504,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790149644504,"index":0,"dt":[],"id":"call_task_read","name":"read","args":["{\"file_path\":\"task.txt\"}"]},{"type":"chunk","time":1790149644504,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}}},{"type":"chunk","time":1790149644504,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":1790149644504,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -18,14 +18,14 @@ {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} {"type":"system/message","data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:6}}"}},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1790149644534,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790149644534,"index":0,"dt":[],"id":"call_dynamic_ping","name":"snapshot_ping","args":["{}"]},{"type":"chunk","time":1790149644534,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}},{"type":"chunk","time":1790149644535,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_dynamic_ping"},"toolCallId":"call_dynamic_ping","content":[{"type":"text","text":"pong"}],"isError":false,"id":"{{message:9}}"}},"sourceEventSeqs":[22],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:10}}"}},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:11}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1790149644557,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1790149644557,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1790149644557,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1790149644557,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1790149644557,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} diff --git a/snapshots/session/dynamic-tool-prompt-updates/system-prompt.expected.md b/snapshots/session/dynamic-tool-prompt-updates/system-prompt.expected.md index f33b3d64fd..86d12ea329 100644 --- a/snapshots/session/dynamic-tool-prompt-updates/system-prompt.expected.md +++ b/snapshots/session/dynamic-tool-prompt-updates/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/dynamic-tool-updates/session.v4.jsonl b/snapshots/session/dynamic-tool-updates/session.v4.jsonl index b4d667d653..03befefbea 100644 --- a/snapshots/session/dynamic-tool-updates/session.v4.jsonl +++ b/snapshots/session/dynamic-tool-updates/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Read task.txt, call the newly available snapshot_ping tool once, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Read task.txt, call the newly","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":1790049391235,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790049391235,"index":0,"dt":[],"id":"call_task_read","name":"read","args":["{\"file_path\":\"task.txt\"}"]},{"type":"chunk","time":1790049391235,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}}},{"type":"chunk","time":1790049391235,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":1790049391235,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -17,14 +17,14 @@ {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_task_read"},"toolCallId":"call_task_read","content":[{"type":"text","text":"{{cwd}}/task.txt\nfile\n\n1: Reply with the single word DONE after reading this file.\n\n(End of file - total 1 lines)\n"}],"isError":false,"id":"{{message:5}}"},"meta":{"path":"{{cwd}}/task.txt","offset":1,"lines":[{"number":1,"text":"Reply with the single word DONE after reading this file."}],"totalLines":1}},"sourceEventSeqs":[14],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:6}}"},"headerSeq":18},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:7}}"},"stream":[{"type":"chunk","time":1790049391255,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790049391255,"index":0,"dt":[],"id":"call_dynamic_ping","name":"snapshot_ping","args":["{}"]},{"type":"chunk","time":1790049391255,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}},{"type":"chunk","time":1790049391255,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_dynamic_ping"},"toolCallId":"call_dynamic_ping","content":[{"type":"text","text":"pong"}],"isError":false,"id":"{{message:8}}"}},"sourceEventSeqs":[21],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:9}}"}},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1790049391270,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1790049391270,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1790049391270,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1790049391270,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1790049391270,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} diff --git a/snapshots/session/dynamic-tool-updates/system-prompt.expected.md b/snapshots/session/dynamic-tool-updates/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/dynamic-tool-updates/system-prompt.expected.md +++ b/snapshots/session/dynamic-tool-updates/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/dynamic-tool-updates/tool-schemas.expected.json b/snapshots/session/dynamic-tool-updates/tool-schemas.expected.json index f7fc1e4ed7..6a6b432083 100644 --- a/snapshots/session/dynamic-tool-updates/tool-schemas.expected.json +++ b/snapshots/session/dynamic-tool-updates/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", @@ -645,34 +617,6 @@ ], "changes": [ [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", @@ -1297,34 +1241,6 @@ } ], [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/empty-response-retry/writer.expected.jsonl b/snapshots/session/empty-response-retry/writer.expected.jsonl index aafd4d7d0a..30c479ce67 100644 --- a/snapshots/session/empty-response-retry/writer.expected.jsonl +++ b/snapshots/session/empty-response-retry/writer.expected.jsonl @@ -12,9 +12,9 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"This prompt first receives an","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/attempt","data":{"turn":1,"step":1,"stream":[{"type":"chunk","time":1793265494563,"chunk":{"type":"usage","usage":{"inputTokens":0,"outputTokens":0}}},{"type":"chunk","time":1793265494563,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}}]}} +{"type":"assistant/attempt","data":{"turn":1,"step":1,"stream":[{"type":"chunk","time":1791444890557,"chunk":{"type":"usage","usage":{"inputTokens":0,"outputTokens":0}}},{"type":"chunk","time":1791444890557,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}}}]}} {"type":"llm/retry","data":{"retryId":"{{retry:1}}","turn":1,"step":1,"provider":"deepseek-official","mode":"normal","policyKey":"[\"normal\",2,[\"EMPTY_RESPONSE\",\"RATE_LIMIT\",\"SERVER\",\"TIMEOUT\",\"TRANSPORT\"],1,1,0]","retry":1,"maxRetries":2,"delayMs":1,"failure":{"message":"model returned a completed response with no content","code":"EMPTY_RESPONSE"}}} {"type":"llm/retry-started","data":{"retryId":"{{retry:1}}","turn":1,"step":1,"retry":1}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"Recovered."}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":12,"outputTokens":3},"stream":[{"type":"chunk","time":1793265494568,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1793265494569,"index":0,"dt":[],"texts":["Recovered."]},{"type":"chunk","time":1793265494569,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"Recovered."}}},{"type":"chunk","time":1793265494569,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":3}}},{"type":"chunk","time":1793265494569,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"Recovered."}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":12,"outputTokens":3},"stream":[{"type":"chunk","time":1791444890563,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1791444890564,"index":0,"dt":[],"texts":["Recovered."]},{"type":"chunk","time":1791444890564,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"Recovered."}}},{"type":"chunk","time":1791444890564,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":3}}},{"type":"chunk","time":1791444890564,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/error-finish/writer.expected.jsonl b/snapshots/session/error-finish/writer.expected.jsonl index eb6b421839..7a944ad039 100644 --- a/snapshots/session/error-finish/writer.expected.jsonl +++ b/snapshots/session/error-finish/writer.expected.jsonl @@ -12,6 +12,6 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"This prompt triggers a recorded","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/attempt","data":{"turn":1,"step":1,"stream":[{"type":"chunk","time":1793265496026,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"simulated provider error (HTTP 401)","code":"AUTH"}}}}]}} +{"type":"assistant/attempt","data":{"turn":1,"step":1,"stream":[{"type":"chunk","time":1791444892025,"chunk":{"type":"finish","reason":{"kind":"error","failure":{"message":"simulated provider error (HTTP 401)","code":"AUTH"}}}}]}} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"error","error":{"message":"simulated provider error (HTTP 401)","code":"AUTH"}}}} diff --git a/snapshots/session/foreground-confinement-timeout/system-prompt.expected.md b/snapshots/session/foreground-confinement-timeout/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/foreground-confinement-timeout/system-prompt.expected.md +++ b/snapshots/session/foreground-confinement-timeout/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/foreground-confinement-timeout/tool-schemas.expected.json b/snapshots/session/foreground-confinement-timeout/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/foreground-confinement-timeout/tool-schemas.expected.json +++ b/snapshots/session/foreground-confinement-timeout/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/fs-glob-sampling/system-prompt.expected.md b/snapshots/session/fs-glob-sampling/system-prompt.expected.md index d197219bc4..1b805eaf0c 100644 --- a/snapshots/session/fs-glob-sampling/system-prompt.expected.md +++ b/snapshots/session/fs-glob-sampling/system-prompt.expected.md @@ -6,11 +6,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/fs-glob-sampling/tool-schemas.expected.json b/snapshots/session/fs-glob-sampling/tool-schemas.expected.json index aef09f80ef..5b4d780009 100644 --- a/snapshots/session/fs-glob-sampling/tool-schemas.expected.json +++ b/snapshots/session/fs-glob-sampling/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/fs-policy-reject/runtime.cordis.yml b/snapshots/session/fs-policy-reject/runtime.cordis.yml deleted file mode 100644 index 2818054948..0000000000 --- a/snapshots/session/fs-policy-reject/runtime.cordis.yml +++ /dev/null @@ -1,3 +0,0 @@ -# Recorded with the observation policy on: the edit refusal is the scenario. -- id: fs-observation-policy - disabled: false diff --git a/snapshots/session/in-history-series-start/session.v4.jsonl b/snapshots/session/in-history-series-start/session.v4.jsonl index 1c8246132e..91a6e4003d 100644 --- a/snapshots/session/in-history-series-start/session.v4.jsonl +++ b/snapshots/session/in-history-series-start/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Read task.txt, call the newly available snapshot_ping tool once, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","systemPromptUpdate":"in-history"}} {"type":"session/title","data":{"title":"Read task.txt, call the newly","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":1792735518085,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792735518085,"index":0,"dt":[],"id":"call_task_read","name":"read","args":["{\"file_path\":\"task.txt\"}"]},{"type":"chunk","time":1792735518085,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}}},{"type":"chunk","time":1792735518085,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":1792735518085,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -18,7 +18,7 @@ {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} {"type":"system/message","data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:6}}"}},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1792735518105,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792735518105,"index":0,"dt":[],"id":"call_dynamic_ping","name":"snapshot_ping","args":["{}"]},{"type":"chunk","time":1792735518105,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}},{"type":"chunk","time":1792735518105,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}} @@ -26,7 +26,7 @@ {"type":"step/end","data":{"turn":1,"step":2}} {"type":"user/message","data":{"content":[{"type":"text","text":"Snapshot checkpoint replacing the first admitted user message."}],"source":{"kind":"test-compaction"},"role":"user","id":"{{message:10}}"},"sourceEventSeqs":[8],"surfaceOp":{"op":"replace","startSeq":8,"endSeq":8}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"high"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} {"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:11}}"}},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:12}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1792735518120,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1792735518120,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1792735518120,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1792735518120,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1792735518120,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} diff --git a/snapshots/session/in-history-series-start/system-prompt.expected.md b/snapshots/session/in-history-series-start/system-prompt.expected.md index dee1761981..560982974b 100644 --- a/snapshots/session/in-history-series-start/system-prompt.expected.md +++ b/snapshots/session/in-history-series-start/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/lsp-definition/system-prompt.expected.md b/snapshots/session/lsp-definition/system-prompt.expected.md index 0348eab83f..0283ccaab4 100644 --- a/snapshots/session/lsp-definition/system-prompt.expected.md +++ b/snapshots/session/lsp-definition/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/lsp-definition/tool-schemas.expected.json b/snapshots/session/lsp-definition/tool-schemas.expected.json index c6e4719079..9b31b5eb2c 100644 --- a/snapshots/session/lsp-definition/tool-schemas.expected.json +++ b/snapshots/session/lsp-definition/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/mcp-resources-ptc/system-prompt.expected.md b/snapshots/session/mcp-resources-ptc/system-prompt.expected.md index 256d0920f3..47af8cdc91 100644 --- a/snapshots/session/mcp-resources-ptc/system-prompt.expected.md +++ b/snapshots/session/mcp-resources-ptc/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -60,15 +58,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -302,27 +291,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/mcp-resources/system-prompt.expected.md b/snapshots/session/mcp-resources/system-prompt.expected.md index 97f5ef71e1..275f98c89b 100644 --- a/snapshots/session/mcp-resources/system-prompt.expected.md +++ b/snapshots/session/mcp-resources/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/mcp-resources/tool-schemas.expected.json b/snapshots/session/mcp-resources/tool-schemas.expected.json index 3b6cf21edd..f47e927b07 100644 --- a/snapshots/session/mcp-resources/tool-schemas.expected.json +++ b/snapshots/session/mcp-resources/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/model-switch-compaction/cordis.snapshot.yml b/snapshots/session/model-switch-compaction/cordis.snapshot.yml index 2f1dd56a9e..660396f13c 100644 --- a/snapshots/session/model-switch-compaction/cordis.snapshot.yml +++ b/snapshots/session/model-switch-compaction/cordis.snapshot.yml @@ -39,8 +39,3 @@ name: '../../../packages/test-support/session-snapshot/tests/fixtures/compaction-working-directory.ts' - id: model-switch-compaction-driver name: './driver.mjs' - -# Keep the recorded tool set shared by the fixed-budget compaction scenarios. -- id: tool-fs - config: - applyPatch: false diff --git a/snapshots/session/model-switch-compaction/system-prompt.expected.md b/snapshots/session/model-switch-compaction/system-prompt.expected.md index 314322822a..edee628694 100644 --- a/snapshots/session/model-switch-compaction/system-prompt.expected.md +++ b/snapshots/session/model-switch-compaction/system-prompt.expected.md @@ -9,9 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -42,9 +42,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/model-switch-notice/snapshot.yml b/snapshots/session/model-switch-notice/snapshot.yml index e327d306c5..ebb028b2bd 100644 --- a/snapshots/session/model-switch-notice/snapshot.yml +++ b/snapshots/session/model-switch-notice/snapshot.yml @@ -8,3 +8,4 @@ header: pin: true changes: 1 promptChanges: 1 + toolSchemasSource: compaction-recovery diff --git a/snapshots/session/model-switch-notice/system-prompt.expected.md b/snapshots/session/model-switch-notice/system-prompt.expected.md index f6e947cf8e..edee628694 100644 --- a/snapshots/session/model-switch-notice/system-prompt.expected.md +++ b/snapshots/session/model-switch-notice/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -44,11 +42,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/model-switch-notice/tool-schemas.expected.json b/snapshots/session/model-switch-notice/tool-schemas.expected.json deleted file mode 100644 index 42b0e228ce..0000000000 --- a/snapshots/session/model-switch-notice/tool-schemas.expected.json +++ /dev/null @@ -1,1292 +0,0 @@ -{ - "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, - { - "name": "bash", - "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." - }, - "command": { - "type": "string", - "description": "The bash command to execute." - }, - "timeoutMs": { - "type": "number", - "description": "Timeout in milliseconds. The executor applies its configured default and cap; on expiry the command moves to the background as a job instead of being killed." - }, - "workdir": { - "type": "string", - "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." - }, - "run_in_background": { - "type": "boolean", - "description": "Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact command the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "description", - "command" - ] - } - }, - { - "name": "create_goal", - "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend. Provide `file_path` before `old_string` and `new_string` in the arguments." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current session goal, including the id and revision that update_goal requires.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "glob", - "description": "Find files, not directories, whose paths match a glob pattern, including hidden and ignored files. Returns up to 100 paths in modification-time order; a larger result keeps the first paths and reports where the complete list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." - }, - "path": { - "type": "string", - "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "grep", - "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns up to 250 matches; a larger result reports where the complete match list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Regular expression to search for (ripgrep syntax)." - }, - "path": { - "type": "string", - "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." - }, - "include": { - "type": "string", - "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "interrupt_agent", - "description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The id of an agent created under you: your direct child or a deeper descendant." - } - }, - "required": [ - "agent_id" - ] - } - }, - { - "name": "job_kill", - "description": "Request cancellation of a running background job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the job." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "job_list", - "description": "List your background jobs (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "job_output", - "description": "Read a background job: output since the previous read for stream jobs, or the result of a finished final-output job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the job finishes or the timeout expires; a timed-out wait leaves the job running. Defaults to false." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds with wait: true. Defaults to and is capped by configuration." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "list_agents", - "description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.", - "parameters": { - "type": "object", - "properties": { - "scope": { - "type": "string", - "description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.", - "enum": [ - "children", - "descendants" - ] - } - } - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "read_image", - "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Large images are downscaled automatically; do not install image libraries or create thumbnails to inspect an image.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to the image file, resolved by the filesystem backend." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "send_message", - "description": "Send a message to an agent. A working agent receives it at its next step; an idle agent starts a new turn with it. Returns delivery confirmation, not the agent's answer.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child." - }, - "message": { - "type": "string", - "description": "The message to deliver to the agent." - } - }, - "required": [ - "agent_id", - "message" - ] - } - }, - { - "name": "skill", - "description": "Load the full instructions for a skill. Call it before acting on a task that names or clearly matches a skill in the session skill catalog.", - "parameters": { - "type": "object", - "properties": { - "name": { - "type": "string", - "description": "The exact skill name from the available skills list." - } - }, - "required": [ - "name" - ] - } - }, - { - "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "todo_write", - "description": "Record and update a task list to plan multi-step work and show progress; skip it for trivial single-step tasks. Add one todo per concrete step before you start. While work remains, keep the todos being worked on `in_progress`, several only when work runs in parallel. Mark each todo `completed` as soon as it is done.", - "parameters": { - "type": "object", - "properties": { - "todos": { - "type": "array", - "description": "The COMPLETE task list, replacing any previous list.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "content": { - "type": "string", - "description": "What the task is — a short imperative line." - }, - "status": { - "type": "string", - "description": "pending (not started) | in_progress (now) | completed (done).", - "enum": [ - "pending", - "in_progress", - "completed" - ] - } - }, - "required": [ - "content", - "status" - ] - } - } - }, - "required": [ - "todos" - ] - } - }, - { - "name": "update_goal", - "description": "Update the current goal.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit, pause, and resume require a direct top-level human request. complete and blocked are also allowed during an automatic continuation of this goal; blocked is rejected before the configured minimum round count.", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Required only with action blocked: the concrete condition that persisted across rounds and blocks progress." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "name": "web_fetch", - "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", - "parameters": { - "type": "object", - "properties": { - "url": { - "type": "string", - "description": "The HTTP(S) URL to fetch." - } - }, - "required": [ - "url" - ] - } - }, - { - "name": "web_search", - "description": "Search the web for current information. Returns an optional summary answer and a list of source URLs.", - "parameters": { - "type": "object", - "properties": { - "queries": { - "type": "array", - "description": "1–4 search queries; their results are merged.", - "items": { - "type": "string" - } - } - }, - "required": [ - "queries" - ] - } - }, - { - "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. A stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) end the whole script instead of producing `null`. The script has no filesystem, network, timer, or Node.js APIs; the agents do the work.", - "parameters": { - "type": "object", - "properties": { - "script": { - "type": "string", - "description": "The plain JavaScript body, not TypeScript and without an `export const meta` statement; top-level await is allowed. End with `return `; the JSON-serializable value is this tool's result." - }, - "meta": { - "type": "object", - "description": "The workflow identity as plain JSON, not code.", - "additionalProperties": true, - "properties": { - "name": { - "type": "string", - "description": "Short kebab-case workflow name." - }, - "description": { - "type": "string", - "description": "One-line description of what the workflow does." - }, - "whenToUse": { - "type": "string", - "description": "Optional guidance on when this workflow applies." - }, - "phases": { - "type": "array", - "description": "Optional phase declarations matched by phase() calls.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "title": { - "type": "string", - "description": "The phase title phase() calls match by exact string." - }, - "detail": { - "type": "string", - "description": "Optional one-line description of the phase." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "model": { - "type": "string", - "description": "Optional model override this phase is expected to use." - } - }, - "required": [ - "title" - ] - } - } - }, - "required": [ - "name", - "description" - ] - }, - "args": { - "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", - "additionalProperties": true - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background job: return a job id immediately instead of waiting; the return value arrives with the completion notice." - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "working_directory", - "description": "Read the current working directory, or change it with cd. Relative paths use the current directory. Existing shells and running processes keep their own directories.", - "parameters": { - "type": "object", - "properties": { - "cd": { - "type": "string", - "description": "Existing directory to enter. Omit to read the current directory." - } - } - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend. Provide `file_path` before `content` in the arguments." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ], - "changes": [ - [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, - { - "name": "bash", - "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", - "parameters": { - "type": "object", - "properties": { - "description": { - "type": "string", - "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." - }, - "command": { - "type": "string", - "description": "The bash command to execute." - }, - "timeoutMs": { - "type": "number", - "description": "Timeout in milliseconds. The executor applies its configured default and cap; on expiry the command moves to the background as a job instead of being killed." - }, - "workdir": { - "type": "string", - "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." - }, - "run_in_background": { - "type": "boolean", - "description": "Run in the background and return a job id immediately (collect with job_output, stop with job_kill). No timeout applies." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact command the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "description", - "command" - ] - } - }, - { - "name": "create_goal", - "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", - "parameters": { - "type": "object", - "properties": { - "objective": { - "type": "string", - "description": "The concrete completion objective inferred from the direct human request." - }, - "max_goal_rounds": { - "type": "number", - "description": "Optional positive safe-integer limit on automatic continuation rounds." - } - }, - "required": [ - "objective" - ] - } - }, - { - "name": "edit", - "description": "Edit an existing UTF-8 text file by replacing literal text.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to edit, resolved by the filesystem backend. Provide `file_path` before `old_string` and `new_string` in the arguments." - }, - "old_string": { - "type": "string", - "description": "Literal text to replace." - }, - "new_string": { - "type": "string", - "description": "Literal replacement text. Use an empty string to delete the match." - }, - "replace_all": { - "type": "boolean", - "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "old_string", - "new_string" - ] - } - }, - { - "name": "get_goal", - "description": "Read the current session goal, including the id and revision that update_goal requires.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "glob", - "description": "Find files, not directories, whose paths match a glob pattern, including hidden and ignored files. Returns up to 100 paths in modification-time order; a larger result keeps the first paths and reports where the complete list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Glob pattern to match file paths against (e.g. \"**/*.ts\", \"src/**/*.test.js\"). A pattern with no \"/\" matches the basename at any depth, so \"*\" and \"*.ts\" both search the whole tree; include a separator to anchor the depth." - }, - "path": { - "type": "string", - "description": "Directory to search in. Defaults to the session workspace; a relative path resolves against it." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "grep", - "description": "Search file contents with a ripgrep regular expression. Returns matching lines with line numbers, grouped by file. Returns up to 250 matches; a larger result reports where the complete match list was saved.", - "parameters": { - "type": "object", - "properties": { - "pattern": { - "type": "string", - "description": "Regular expression to search for (ripgrep syntax)." - }, - "path": { - "type": "string", - "description": "File or directory to search. Defaults to the session workspace; a relative path resolves against it." - }, - "include": { - "type": "string", - "description": "One glob filter for which files to search (e.g. \"*.ts\", \"*.{js,jsx}\"). Not a list; negation is not supported." - } - }, - "required": [ - "pattern" - ] - } - }, - { - "name": "interrupt_agent", - "description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The id of an agent created under you: your direct child or a deeper descendant." - } - }, - "required": [ - "agent_id" - ] - } - }, - { - "name": "job_kill", - "description": "Request cancellation of a running background job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "reason": { - "type": "string", - "description": "Optional short reason, recorded in the log and forwarded to the job." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "job_list", - "description": "List your background jobs (running and finished) with their ids, kinds, and statuses.", - "parameters": { - "type": "object", - "properties": {} - } - }, - { - "name": "job_output", - "description": "Read a background job: output since the previous read for stream jobs, or the result of a finished final-output job.", - "parameters": { - "type": "object", - "properties": { - "job_id": { - "type": "string", - "description": "Job id returned by the tool that started the background work." - }, - "wait": { - "type": "boolean", - "description": "Block until the job finishes or the timeout expires; a timed-out wait leaves the job running. Defaults to false." - }, - "timeout_ms": { - "type": "number", - "description": "Max wait in milliseconds with wait: true. Defaults to and is capped by configuration." - } - }, - "required": [ - "job_id" - ] - } - }, - { - "name": "list_agents", - "description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.", - "parameters": { - "type": "object", - "properties": { - "scope": { - "type": "string", - "description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.", - "enum": [ - "children", - "descendants" - ] - } - } - } - }, - { - "name": "read", - "description": "Read a UTF-8 text file and return line-numbered content.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to read, resolved by the filesystem backend." - }, - "offset": { - "type": "number", - "description": "1-based first line to return. Defaults to 1." - }, - "limit": { - "type": "number", - "description": "Maximum number of lines to return. Defaults to 2000." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "read_image", - "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Large images are downscaled automatically; do not install image libraries or create thumbnails to inspect an image.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to the image file, resolved by the filesystem backend." - } - }, - "required": [ - "file_path" - ] - } - }, - { - "name": "send_message", - "description": "Send a message to an agent. A working agent receives it at its next step; an idle agent starts a new turn with it. Returns delivery confirmation, not the agent's answer.", - "parameters": { - "type": "object", - "properties": { - "agent_id": { - "type": "string", - "description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child." - }, - "message": { - "type": "string", - "description": "The message to deliver to the agent." - } - }, - "required": [ - "agent_id", - "message" - ] - } - }, - { - "name": "skill", - "description": "Load the full instructions for a skill. Call it before acting on a task that names or clearly matches a skill in the session skill catalog.", - "parameters": { - "type": "object", - "properties": { - "name": { - "type": "string", - "description": "The exact skill name from the available skills list." - } - }, - "required": [ - "name" - ] - } - }, - { - "name": "subagent", - "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "subagent_fork", - "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.", - "parameters": { - "type": "object", - "properties": { - "cwd": { - "type": "string", - "description": "Initial child working directory. Relative paths use your current directory; omitted inherits it. Later directory changes in either agent are independent." - }, - "description": { - "type": "string", - "description": "A short (3-5 word) description of the delegated task, for display." - }, - "prompt": { - "type": "string", - "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." - } - }, - "required": [ - "description", - "prompt" - ] - } - }, - { - "name": "todo_write", - "description": "Record and update a task list to plan multi-step work and show progress; skip it for trivial single-step tasks. Add one todo per concrete step before you start. While work remains, keep the todos being worked on `in_progress`, several only when work runs in parallel. Mark each todo `completed` as soon as it is done.", - "parameters": { - "type": "object", - "properties": { - "todos": { - "type": "array", - "description": "The COMPLETE task list, replacing any previous list.", - "items": { - "type": "object", - "additionalProperties": false, - "properties": { - "content": { - "type": "string", - "description": "What the task is — a short imperative line." - }, - "status": { - "type": "string", - "description": "pending (not started) | in_progress (now) | completed (done).", - "enum": [ - "pending", - "in_progress", - "completed" - ] - } - }, - "required": [ - "content", - "status" - ] - } - } - }, - "required": [ - "todos" - ] - } - }, - { - "name": "update_goal", - "description": "Update the current goal.", - "parameters": { - "type": "object", - "properties": { - "goal_id": { - "type": "string", - "description": "Exact id returned by get_goal." - }, - "revision": { - "type": "number", - "description": "Exact positive revision returned by get_goal." - }, - "action": { - "type": "string", - "description": "edit, pause, and resume require a direct top-level human request. complete and blocked are also allowed during an automatic continuation of this goal; blocked is rejected before the configured minimum round count.", - "enum": [ - "edit", - "pause", - "resume", - "complete", - "blocked" - ] - }, - "objective": { - "type": "string", - "description": "Replacement objective; valid only with action edit." - }, - "max_goal_rounds": { - "type": "number", - "description": "Replacement cap; valid only with action edit." - }, - "blocked_reason": { - "type": "string", - "description": "Required only with action blocked: the concrete condition that persisted across rounds and blocks progress." - } - }, - "required": [ - "goal_id", - "revision", - "action" - ] - } - }, - { - "name": "web_fetch", - "description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.", - "parameters": { - "type": "object", - "properties": { - "url": { - "type": "string", - "description": "The HTTP(S) URL to fetch." - } - }, - "required": [ - "url" - ] - } - }, - { - "name": "web_search", - "description": "Search the web for current information. Returns an optional summary answer and a list of source URLs.", - "parameters": { - "type": "object", - "properties": { - "queries": { - "type": "array", - "description": "1–4 search queries; their results are merged.", - "items": { - "type": "string" - } - } - }, - "required": [ - "queries" - ] - } - }, - { - "name": "workflow", - "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. A stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) end the whole script instead of producing `null`. The script has no filesystem, network, timer, or Node.js APIs; the agents do the work.", - "parameters": { - "type": "object", - "properties": { - "script": { - "type": "string", - "description": "The plain JavaScript body, not TypeScript and without an `export const meta` statement; top-level await is allowed. End with `return `; the JSON-serializable value is this tool's result." - }, - "meta": { - "type": "object", - "description": "The workflow identity as plain JSON, not code.", - "additionalProperties": true, - "properties": { - "name": { - "type": "string", - "description": "Short kebab-case workflow name." - }, - "description": { - "type": "string", - "description": "One-line description of what the workflow does." - }, - "whenToUse": { - "type": "string", - "description": "Optional guidance on when this workflow applies." - }, - "phases": { - "type": "array", - "description": "Optional phase declarations matched by phase() calls.", - "items": { - "type": "object", - "additionalProperties": true, - "properties": { - "title": { - "type": "string", - "description": "The phase title phase() calls match by exact string." - }, - "detail": { - "type": "string", - "description": "Optional one-line description of the phase." - }, - "provider": { - "type": "string", - "description": "Optional provider override this phase is expected to use." - }, - "model": { - "type": "string", - "description": "Optional model override this phase is expected to use." - } - }, - "required": [ - "title" - ] - } - } - }, - "required": [ - "name", - "description" - ] - }, - "args": { - "type": "object", - "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", - "additionalProperties": true - }, - "run_in_background": { - "type": "boolean", - "description": "Run as a background job: return a job id immediately instead of waiting; the return value arrives with the completion notice." - } - }, - "required": [ - "script", - "meta" - ] - } - }, - { - "name": "working_directory", - "description": "Read the current working directory, or change it with cd. Relative paths use the current directory. Existing shells and running processes keep their own directories.", - "parameters": { - "type": "object", - "properties": { - "cd": { - "type": "string", - "description": "Existing directory to enter. Omit to read the current directory." - } - } - } - }, - { - "name": "write", - "description": "Create or fully replace a UTF-8 text file.", - "parameters": { - "type": "object", - "properties": { - "file_path": { - "type": "string", - "description": "Path to write, resolved by the filesystem backend. Provide `file_path` before `content` in the arguments." - }, - "content": { - "type": "string", - "description": "Full UTF-8 text content to write." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "file_path", - "content" - ] - } - } - ] - ] -} diff --git a/snapshots/session/multimodal-spill-ends/system-prompt.expected.md b/snapshots/session/multimodal-spill-ends/system-prompt.expected.md index d2e726f28b..4956076bc6 100644 --- a/snapshots/session/multimodal-spill-ends/system-prompt.expected.md +++ b/snapshots/session/multimodal-spill-ends/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/multimodal-spill-ends/tool-schemas.expected.json b/snapshots/session/multimodal-spill-ends/tool-schemas.expected.json index 1c5f13e197..3a003efa6c 100644 --- a/snapshots/session/multimodal-spill-ends/tool-schemas.expected.json +++ b/snapshots/session/multimodal-spill-ends/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/office-authoring-checker/system-prompt.expected.md b/snapshots/session/office-authoring-checker/system-prompt.expected.md index af4124eff6..fb8a26b762 100644 --- a/snapshots/session/office-authoring-checker/system-prompt.expected.md +++ b/snapshots/session/office-authoring-checker/system-prompt.expected.md @@ -7,11 +7,9 @@ Verify your work by running the code or tests. Keep answers brief and factual. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/office-progressive-native/system-prompt.expected.md b/snapshots/session/office-progressive-native/system-prompt.expected.md index af4124eff6..fb8a26b762 100644 --- a/snapshots/session/office-progressive-native/system-prompt.expected.md +++ b/snapshots/session/office-progressive-native/system-prompt.expected.md @@ -7,11 +7,9 @@ Verify your work by running the code or tests. Keep answers brief and factual. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/office-progressive-native/tool-schemas.expected.json b/snapshots/session/office-progressive-native/tool-schemas.expected.json index 8606601075..b9c653bab9 100644 --- a/snapshots/session/office-progressive-native/tool-schemas.expected.json +++ b/snapshots/session/office-progressive-native/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "create_goal", "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", diff --git a/snapshots/session/office-progressive-ptc/system-prompt.expected.md b/snapshots/session/office-progressive-ptc/system-prompt.expected.md index f13d31e3bd..5a735d0ba4 100644 --- a/snapshots/session/office-progressive-ptc/system-prompt.expected.md +++ b/snapshots/session/office-progressive-ptc/system-prompt.expected.md @@ -9,11 +9,9 @@ Verify your work by running the code or tests. Keep answers brief and factual. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -48,15 +46,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say "goal"; not for single-turn work. */ create_goal: { /** The concrete completion objective inferred from the direct human request. */ @@ -252,27 +241,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; create_goal: { goal: null; } | { diff --git a/snapshots/session/office-render-tools-ptc/writer.expected.jsonl b/snapshots/session/office-render-tools-ptc/writer.expected.jsonl index e752378b83..72d70aa18c 100644 --- a/snapshots/session/office-render-tools-ptc/writer.expected.jsonl +++ b/snapshots/session/office-render-tools-ptc/writer.expected.jsonl @@ -14,28 +14,28 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"/office-docx Load the Office rendering","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_skill","name":"run_code","arguments":"{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1793265530874,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265530875,"index":0,"dt":[],"id":"call_office_skill","name":"run_code","args":["{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1793265530875,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_skill","name":"run_code","arguments":"{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1793265530875,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_skill","name":"run_code","arguments":"{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1792238445884,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238445885,"index":0,"dt":[],"id":"call_office_skill","name":"run_code","args":["{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1792238445885,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_skill","name":"run_code","arguments":"{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1792238445885,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_office_skill","name":"run_code","arguments":"{\"code\":\"console.log(await tools.skill({\\\"name\\\":\\\"office-xlsx\\\"}));\",\"description\":\"Use the Office workflow\"}"}} {"type":"tool/ptc-dispatch-start","data":{"rootCallId":"call_office_skill","parentCallId":"call_office_skill","subCallId":"call_office_skill:ptc:1","name":"skill","arguments":{"name":"office-xlsx"}}} {"type":"tool/ptc-dispatch","data":{"rootCallId":"call_office_skill","parentCallId":"call_office_skill","subCallId":"call_office_skill:ptc:1","name":"skill","arguments":{"name":"office-xlsx"},"isError":false,"content":[{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/office-skills/office-xlsx\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\n# Excel workbooks\n\nFollow an explicit user or applicable AGENTS.md requirement for an environment or library. Otherwise call `load_workspace_dependencies` and run its Python executable with bundled `openpyxl` and `pandas`. Do not install packages or search for a system Python for the default workflow. If the tool is unavailable, use an already configured environment and report a missing dependency only when it prevents the requested operation.\n\nKeep scripts, working files, and outputs in the task workspace. The runtime and skill directory are shared read-only resources. Save to a new workbook unless the user requests an in-place edit.\n\nName Python scripts for their task, such as `edit_xlsx.py`; avoid module names such as `inspect.py`, `openpyxl.py`, or `pandas.py` that shadow imported libraries.\n\n## Read and modify\n\nUse `openpyxl` for existing XLSX workbooks and targeted cell or style changes. Load with `data_only=False` when formulas must survive. Inspect sheet names, the affected cell types, formulas, styles, merged ranges, and referenced ranges before editing. Check the saved file by reopening it, including unchanged content that the request requires preserving.\n\nUse pandas for data analysis and transformations. A DataFrame is not the workbook: exporting it over an existing file can lose sheets, formulas, charts, and formatting. Write analysis results back to the intended ranges with openpyxl. `XlsxWriter` can create new workbooks, but cannot read or modify existing ones.\n\nFor a new workbook, the selected Python environment can write editable values, styles, and formulas directly:\n\n```python\nfrom openpyxl import Workbook\nfrom openpyxl.styles import Font\n\nworkbook = Workbook()\nsheet = workbook.active\nsheet.title = \"Revenue\"\nfor row in [(\"Quarter\", \"Revenue\"), (\"Q1\", 12), (\"Q2\", 18), (\"Total\", \"=SUM(B2:B3)\")]:\n sheet.append(row)\nfor cell in sheet[1]:\n cell.font = Font(bold=True)\nsheet.column_dimensions[\"A\"].width = 18\nsheet.column_dimensions[\"B\"].width = 18\nworkbook.save(\"report.xlsx\")\n```\n\nPreserve numbers, dates, booleans, and identifiers as the intended cell types; formatting is not a type conversion. For modifications, load the existing file with `openpyxl.load_workbook(\"input.xlsx\", data_only=False)`, change the requested ranges, and save a separate result. Avoid a DataFrame round trip when workbook features must survive.\n\nWriting a formula does not calculate its result. openpyxl and XlsxWriter do not evaluate formulas; `data_only=True` returns cached values that may be absent or stale. When calculated results must be refreshed, load `office-recalculate`. Do not replace requested formulas with constants or report stale values as newly calculated results.\n\nDo not rename `.xls`, `.xlsb`, encrypted files, or macro-enabled files to `.xlsx`. They need an appropriate supported operation. `keep_vba=True` can preserve VBA package content in an XLSM workflow, but does not execute or edit macros and does not guarantee every advanced workbook feature survives. Preserve the original and verify such requirements explicitly.\n\n## Check and deliver\n\nReopen the saved workbook with openpyxl and verify the requested sheet names, values, types, formulas, styles, and totals against the source data, including unchanged content that must be preserved. These checks do not calculate formulas or judge workbook appearance.\n\nLoad `office-render` for requested images or visual inspection and whenever the user's primary task targets appearance, including cell fill colors, text alignment, spacing, or sizing. These appearance changes require rendering even without a separate visual-check request, unless the user explicitly skips it. New workbooks and data or formula edits do not require rendering solely because they include incidental basic formatting. In particular, bold headers and number formats accompanying data edits do not require loading `office-render` or running its commands.\n\nLoad `office-recalculate` when refreshed calculated values are needed and `office-export-pdf` for PDF output. Deliver after the requested data checks pass and the required operations finish.\n\nCall `present({\"files\":[{\"path\":\"report.xlsx\"}]})` with the actual final workbook path. It exposes the current source file without copying or preserving its bytes, so keep that file in place and omit intermediate scripts and reports unless requested. If `present` is unavailable, use the session's supported file delivery method.\n\n"}]}} {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_skill"},"toolCallId":"call_office_skill","content":[{"type":"text","text":"{\n name: 'office-xlsx',\n provider: 'dsh-office',\n resourceBase: {\n kind: 'directory',\n path: '{{cwd}}/office-skills/office-xlsx'\n },\n content: '# Excel workbooks\\n' +\n '\\n' +\n 'Follow an explicit user or applicable AGENTS.md requirement for an environment or library. Otherwise call `load_workspace_dependencies` and run its Python executable with bundled `openpyxl` and `pandas`. Do not install packages or search for a system Python for the default workflow. If the tool is unavailable, use an already configured environment and report a missing dependency only when it prevents the requested operation.\\n' +\n '\\n' +\n 'Keep scripts, working files, and outputs in the task workspace. The runtime and skill directory are shared read-only resources. Save to a new workbook unless the user requests an in-place edit.\\n' +\n '\\n' +\n 'Name Python scripts for their task, such as `edit_xlsx.py`; avoid module names such as `inspect.py`, `openpyxl.py`, or `pandas.py` that shadow imported libraries.\\n' +\n '\\n' +\n '## Read and modify\\n' +\n '\\n' +\n 'Use `openpyxl` for existing XLSX workbooks and targeted cell or style changes. Load with `data_only=False` when formulas must survive. Inspect sheet names, the affected cell types, formulas, styles, merged ranges, and referenced ranges before editing. Check the saved file by reopening it, including unchanged content that the request requires preserving.\\n' +\n '\\n' +\n 'Use pandas for data analysis and transformations. A DataFrame is not the workbook: exporting it over an existing file can lose sheets, formulas, charts, and formatting. Write analysis results back to the intended ranges with openpyxl. `XlsxWriter` can create new workbooks, but cannot read or modify existing ones.\\n' +\n '\\n' +\n 'For a new workbook, the selected Python environment can write editable values, styles, and formulas directly:\\n' +\n '\\n' +\n '```python\\n' +\n 'from openpyxl import Workbook\\n' +\n 'from openpyxl.styles import Font\\n' +\n '\\n' +\n 'workbook = Workbook()\\n' +\n 'sheet = workbook.active\\n' +\n 'sheet.title = \"Revenue\"\\n' +\n 'for row in [(\"Quarter\", \"Revenue\"), (\"Q1\", 12), (\"Q2\", 18), (\"Total\", \"=SUM(B2:B3)\")]:\\n' +\n ' sheet.append(row)\\n' +\n 'for cell in sheet[1]:\\n' +\n ' cell.font = Font(bold=True)\\n' +\n 'sheet.column_dimensions[\"A\"].width = 18\\n' +\n 'sheet.column_dimensions[\"B\"].width = 18\\n' +\n 'workbook.save(\"report.xlsx\")\\n' +\n '```\\n' +\n '\\n' +\n 'Preserve numbers, dates, booleans, and identifiers as the intended cell types; formatting is not a type conversion. For modifications, load the existing file with `openpyxl.load_workbook(\"input.xlsx\", data_only=False)`, change the requested ranges, and save a separate result. Avoid a DataFrame round trip when workbook features must survive.\\n' +\n '\\n' +\n 'Writing a formula does not calculate its result. openpyxl and XlsxWriter do not evaluate formulas; `data_only=True` returns cached values that may be absent or stale. When calculated results must be refreshed, load `office-recalculate`. Do not replace requested formulas with constants or report stale values as newly calculated results.\\n' +\n '\\n' +\n 'Do not rename `.xls`, `.xlsb`, encrypted files, or macro-enabled files to `.xlsx`. They need an appropriate supported operation. `keep_vba=True` can preserve VBA package content in an XLSM workflow, but does not execute or edit macros and does not guarantee every advanced workbook feature survives. Preserve the original and verify such requirements explicitly.\\n' +\n '\\n' +\n '## Check and deliver\\n' +\n '\\n' +\n 'Reopen the saved workbook with openpyxl and verify the requested sheet names, values, types, formulas, styles, and totals against the source data, including unchanged content that must be preserved. These checks do not calculate formulas or judge workbook appearance.\\n' +\n '\\n' +\n \"Load `office-render` for requested images or visual inspection and whenever the user's primary task targets appearance, including cell fill colors, text alignment, spacing, or sizing. These appearance changes require rendering even without a separate visual-check request, unless the user explicitly skips it. New workbooks and data or formula edits do not require rendering solely because they include incidental basic formatting. In particular, bold headers and number formats accompanying data edits do not require loading `office-render` or running its commands.\\n\" +\n '\\n' +\n 'Load `office-recalculate` when refreshed calculated values are needed and `office-export-pdf` for PDF output. Deliver after the requested data checks pass and the required operations finish.\\n' +\n '\\n' +\n 'Call `present({\"files\":[{\"path\":\"report.xlsx\"}]})` with the actual final workbook path. It exposes the current source file without copying or preserving its bytes, so keep that file in place and omit intermediate scripts and reports unless requested. If `present` is unavailable, use the session\\'s supported file delivery method.'\n}"}],"isError":false,"id":"{{message:7}}"}},"sourceEventSeqs":[16],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_2","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1793265531412,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265531412,"index":0,"dt":[],"id":"call_office_2","name":"run_code","args":["{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1793265531412,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_2","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1793265531412,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_2","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1792238446419,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238446419,"index":0,"dt":[],"id":"call_office_2","name":"run_code","args":["{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1792238446419,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_2","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1792238446419,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_office_2","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"load\\\"}));\",\"description\":\"Use the Office workflow\"}"}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_2"},"toolCallId":"call_office_2","content":[{"type":"text","text":"Error: code run failed (exception): TypeError: tools.office_tools is not a function\nFile sandbox: danger-full-access."}],"isError":true,"id":"{{message:9}}"},"error":{"name":"CodeRunFailedError","code":"CODE_RUN_FAILED"}},"sourceEventSeqs":[23],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_3","name":"run_code","arguments":"{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"stream":[{"type":"chunk","time":1793265531524,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265531524,"index":0,"dt":[],"id":"call_office_3","name":"run_code","args":["{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1793265531524,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_3","name":"run_code","arguments":"{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1793265531524,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_3","name":"run_code","arguments":"{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"stream":[{"type":"chunk","time":1792238446498,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238446498,"index":0,"dt":[],"id":"call_office_3","name":"run_code","args":["{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1792238446498,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_3","name":"run_code","arguments":"{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1792238446498,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":3,"callId":"call_office_3","name":"run_code","arguments":"{\"code\":\"console.log(await tools.render_document({\\\"input\\\":\\\"report.docx\\\",\\\"outputDirectory\\\":\\\"preview\\\",\\\"pages\\\":[1]}));\",\"description\":\"Use the Office workflow\"}"}} {"type":"tool/result","data":{"turn":1,"step":3,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_3"},"toolCallId":"call_office_3","content":[{"type":"text","text":"Error: code run failed (exception): TypeError: tools.render_document is not a function\nFile sandbox: danger-full-access."}],"isError":true,"id":"{{message:11}}"},"error":{"name":"CodeRunFailedError","code":"CODE_RUN_FAILED"}},"sourceEventSeqs":[28],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} {"type":"step/start","data":{"turn":1,"step":4}} -{"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_4","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:12}}"},"stream":[{"type":"chunk","time":1793265531638,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265531638,"index":0,"dt":[],"id":"call_office_4","name":"run_code","args":["{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1793265531638,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_4","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1793265531638,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_4","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:12}}"},"stream":[{"type":"chunk","time":1792238446579,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238446579,"index":0,"dt":[],"id":"call_office_4","name":"run_code","args":["{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"]},{"type":"chunk","time":1792238446579,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_4","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"}}},{"type":"chunk","time":1792238446579,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":4,"callId":"call_office_4","name":"run_code","arguments":"{\"code\":\"console.log(await tools.office_tools({\\\"action\\\":\\\"remove\\\"}));\",\"description\":\"Use the Office workflow\"}"}} {"type":"tool/result","data":{"turn":1,"step":4,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_4"},"toolCallId":"call_office_4","content":[{"type":"text","text":"Error: code run failed (exception): TypeError: tools.office_tools is not a function\nFile sandbox: danger-full-access."}],"isError":true,"id":"{{message:13}}"},"error":{"name":"CodeRunFailedError","code":"CODE_RUN_FAILED"}},"sourceEventSeqs":[33],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":4}} {"type":"step/start","data":{"turn":1,"step":5}} -{"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:14}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1793265531750,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1793265531750,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1793265531750,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1793265531750,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1793265531750,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:14}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1792238446660,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1792238446660,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1792238446660,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1792238446660,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1792238446660,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":5}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/office-render-tools/writer.expected.jsonl b/snapshots/session/office-render-tools/writer.expected.jsonl index 0999771798..017eec744b 100644 --- a/snapshots/session/office-render-tools/writer.expected.jsonl +++ b/snapshots/session/office-render-tools/writer.expected.jsonl @@ -14,26 +14,26 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"/office-docx Load the Office rendering","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_skill","name":"skill","arguments":"{\"name\":\"office-xlsx\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1793265530082,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265530082,"index":0,"dt":[],"id":"call_office_skill","name":"skill","args":["{\"name\":\"office-xlsx\"}"]},{"type":"chunk","time":1793265530082,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_skill","name":"skill","arguments":"{\"name\":\"office-xlsx\"}"}}},{"type":"chunk","time":1793265530082,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_skill","name":"skill","arguments":"{\"name\":\"office-xlsx\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1792238445064,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238445064,"index":0,"dt":[],"id":"call_office_skill","name":"skill","args":["{\"name\":\"office-xlsx\"}"]},{"type":"chunk","time":1792238445064,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_skill","name":"skill","arguments":"{\"name\":\"office-xlsx\"}"}}},{"type":"chunk","time":1792238445064,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_office_skill","name":"skill","arguments":"{\"name\":\"office-xlsx\"}"}} {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_skill"},"toolCallId":"call_office_skill","content":[{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/office-skills/office-xlsx\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\n# Excel workbooks\n\nFollow an explicit user or applicable AGENTS.md requirement for an environment or library. Otherwise call `load_workspace_dependencies` and run its Python executable with bundled `openpyxl` and `pandas`. Do not install packages or search for a system Python for the default workflow. If the tool is unavailable, use an already configured environment and report a missing dependency only when it prevents the requested operation.\n\nKeep scripts, working files, and outputs in the task workspace. The runtime and skill directory are shared read-only resources. Save to a new workbook unless the user requests an in-place edit.\n\nName Python scripts for their task, such as `edit_xlsx.py`; avoid module names such as `inspect.py`, `openpyxl.py`, or `pandas.py` that shadow imported libraries.\n\n## Read and modify\n\nUse `openpyxl` for existing XLSX workbooks and targeted cell or style changes. Load with `data_only=False` when formulas must survive. Inspect sheet names, the affected cell types, formulas, styles, merged ranges, and referenced ranges before editing. Check the saved file by reopening it, including unchanged content that the request requires preserving.\n\nUse pandas for data analysis and transformations. A DataFrame is not the workbook: exporting it over an existing file can lose sheets, formulas, charts, and formatting. Write analysis results back to the intended ranges with openpyxl. `XlsxWriter` can create new workbooks, but cannot read or modify existing ones.\n\nFor a new workbook, the selected Python environment can write editable values, styles, and formulas directly:\n\n```python\nfrom openpyxl import Workbook\nfrom openpyxl.styles import Font\n\nworkbook = Workbook()\nsheet = workbook.active\nsheet.title = \"Revenue\"\nfor row in [(\"Quarter\", \"Revenue\"), (\"Q1\", 12), (\"Q2\", 18), (\"Total\", \"=SUM(B2:B3)\")]:\n sheet.append(row)\nfor cell in sheet[1]:\n cell.font = Font(bold=True)\nsheet.column_dimensions[\"A\"].width = 18\nsheet.column_dimensions[\"B\"].width = 18\nworkbook.save(\"report.xlsx\")\n```\n\nPreserve numbers, dates, booleans, and identifiers as the intended cell types; formatting is not a type conversion. For modifications, load the existing file with `openpyxl.load_workbook(\"input.xlsx\", data_only=False)`, change the requested ranges, and save a separate result. Avoid a DataFrame round trip when workbook features must survive.\n\nWriting a formula does not calculate its result. openpyxl and XlsxWriter do not evaluate formulas; `data_only=True` returns cached values that may be absent or stale. When calculated results must be refreshed, load `office-recalculate`. Do not replace requested formulas with constants or report stale values as newly calculated results.\n\nDo not rename `.xls`, `.xlsb`, encrypted files, or macro-enabled files to `.xlsx`. They need an appropriate supported operation. `keep_vba=True` can preserve VBA package content in an XLSM workflow, but does not execute or edit macros and does not guarantee every advanced workbook feature survives. Preserve the original and verify such requirements explicitly.\n\n## Check and deliver\n\nReopen the saved workbook with openpyxl and verify the requested sheet names, values, types, formulas, styles, and totals against the source data, including unchanged content that must be preserved. These checks do not calculate formulas or judge workbook appearance.\n\nLoad `office-render` for requested images or visual inspection and whenever the user's primary task targets appearance, including cell fill colors, text alignment, spacing, or sizing. These appearance changes require rendering even without a separate visual-check request, unless the user explicitly skips it. New workbooks and data or formula edits do not require rendering solely because they include incidental basic formatting. In particular, bold headers and number formats accompanying data edits do not require loading `office-render` or running its commands.\n\nLoad `office-recalculate` when refreshed calculated values are needed and `office-export-pdf` for PDF output. Deliver after the requested data checks pass and the required operations finish.\n\nCall `present({\"files\":[{\"path\":\"report.xlsx\"}]})` with the actual final workbook path. It exposes the current source file without copying or preserving its bytes, so keep that file in place and omit intermediate scripts and reports unless requested. If `present` is unavailable, use the session's supported file delivery method.\n\n"}],"isError":false,"id":"{{message:7}}"}},"sourceEventSeqs":[16],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_2","name":"office_tools","arguments":"{\"action\":\"load\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1793265530099,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265530099,"index":0,"dt":[],"id":"call_office_2","name":"office_tools","args":["{\"action\":\"load\"}"]},{"type":"chunk","time":1793265530099,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_2","name":"office_tools","arguments":"{\"action\":\"load\"}"}}},{"type":"chunk","time":1793265530099,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_2","name":"office_tools","arguments":"{\"action\":\"load\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1792238445088,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238445088,"index":0,"dt":[],"id":"call_office_2","name":"office_tools","args":["{\"action\":\"load\"}"]},{"type":"chunk","time":1792238445088,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_2","name":"office_tools","arguments":"{\"action\":\"load\"}"}}},{"type":"chunk","time":1792238445088,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_office_2","name":"office_tools","arguments":"{\"action\":\"load\"}"}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_2"},"toolCallId":"call_office_2","content":[{"type":"text","text":"Error: unknown tool \"office_tools\""}],"isError":true,"id":"{{message:9}}"},"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[21],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_3","name":"render_document","arguments":"{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"stream":[{"type":"chunk","time":1793265530114,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265530114,"index":0,"dt":[],"id":"call_office_3","name":"render_document","args":["{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"]},{"type":"chunk","time":1793265530114,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_3","name":"render_document","arguments":"{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"}}},{"type":"chunk","time":1793265530114,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_3","name":"render_document","arguments":"{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"stream":[{"type":"chunk","time":1792238445107,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238445107,"index":0,"dt":[],"id":"call_office_3","name":"render_document","args":["{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"]},{"type":"chunk","time":1792238445107,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_3","name":"render_document","arguments":"{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"}}},{"type":"chunk","time":1792238445107,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":3,"callId":"call_office_3","name":"render_document","arguments":"{\"input\":\"report.docx\",\"outputDirectory\":\"preview\",\"pages\":[1]}"}} {"type":"tool/result","data":{"turn":1,"step":3,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_3"},"toolCallId":"call_office_3","content":[{"type":"text","text":"Error: unknown tool \"render_document\""}],"isError":true,"id":"{{message:11}}"},"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[26],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} {"type":"step/start","data":{"turn":1,"step":4}} -{"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_4","name":"office_tools","arguments":"{\"action\":\"remove\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:12}}"},"stream":[{"type":"chunk","time":1793265530129,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265530129,"index":0,"dt":[],"id":"call_office_4","name":"office_tools","args":["{\"action\":\"remove\"}"]},{"type":"chunk","time":1793265530129,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_4","name":"office_tools","arguments":"{\"action\":\"remove\"}"}}},{"type":"chunk","time":1793265530129,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_office_4","name":"office_tools","arguments":"{\"action\":\"remove\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:12}}"},"stream":[{"type":"chunk","time":1792238445129,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792238445129,"index":0,"dt":[],"id":"call_office_4","name":"office_tools","args":["{\"action\":\"remove\"}"]},{"type":"chunk","time":1792238445129,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_office_4","name":"office_tools","arguments":"{\"action\":\"remove\"}"}}},{"type":"chunk","time":1792238445129,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":4,"callId":"call_office_4","name":"office_tools","arguments":"{\"action\":\"remove\"}"}} {"type":"tool/result","data":{"turn":1,"step":4,"message":{"role":"tool","source":{"kind":"tool","callId":"call_office_4"},"toolCallId":"call_office_4","content":[{"type":"text","text":"Error: unknown tool \"office_tools\""}],"isError":true,"id":"{{message:13}}"},"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[31],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":4}} {"type":"step/start","data":{"turn":1,"step":5}} -{"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:14}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1793265530144,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1793265530144,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1793265530144,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1793265530144,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1793265530144,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:14}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1792238445149,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1792238445149,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1792238445149,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1792238445149,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1792238445149,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":5}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/office-sidecar-instructions/system-prompt.expected.md b/snapshots/session/office-sidecar-instructions/system-prompt.expected.md index af4124eff6..fb8a26b762 100644 --- a/snapshots/session/office-sidecar-instructions/system-prompt.expected.md +++ b/snapshots/session/office-sidecar-instructions/system-prompt.expected.md @@ -7,11 +7,9 @@ Verify your work by running the code or tests. Keep answers brief and factual. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/office-skills/system-prompt.expected.md b/snapshots/session/office-skills/system-prompt.expected.md index af4124eff6..fb8a26b762 100644 --- a/snapshots/session/office-skills/system-prompt.expected.md +++ b/snapshots/session/office-skills/system-prompt.expected.md @@ -7,11 +7,9 @@ Verify your work by running the code or tests. Keep answers brief and factual. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/office-skills/tool-schemas.expected.json b/snapshots/session/office-skills/tool-schemas.expected.json index 8606601075..b9c653bab9 100644 --- a/snapshots/session/office-skills/tool-schemas.expected.json +++ b/snapshots/session/office-skills/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "create_goal", "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", diff --git a/snapshots/session/packed-chunks/writer.expected.jsonl b/snapshots/session/packed-chunks/writer.expected.jsonl index bfacb0cb39..36e45ee89c 100644 --- a/snapshots/session/packed-chunks/writer.expected.jsonl +++ b/snapshots/session/packed-chunks/writer.expected.jsonl @@ -12,13 +12,13 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Use the bash tool to","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17},"stream":[{"type":"chunk","time":1793265534769,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265534769,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," run"," a"," simple"," bash"," command"," and"," report"," the"," result"," verb","atim","."]},{"type":"chunk","time":1793265534769,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265534769,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","args":["","{","\"","command","\"",": ","\"","echo"," HE","LL","O","\"",", ","\"","description","\"",": ","\"","Run"," echo"," HE","LL","O","\"","}"]},{"type":"chunk","time":1793265534769,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."}}},{"type":"chunk","time":1793265534769,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}},{"type":"chunk","time":1793265534769,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}},{"type":"chunk","time":1793265534770,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17},"stream":[{"type":"chunk","time":1791444921353,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444921353,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," run"," a"," simple"," bash"," command"," and"," report"," the"," result"," verb","atim","."]},{"type":"chunk","time":1791444921353,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791444921353,"index":1,"dt":[0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","args":["","{","\"","command","\"",": ","\"","echo"," HE","LL","O","\"",", ","\"","description","\"",": ","\"","Run"," echo"," HE","LL","O","\"","}"]},{"type":"chunk","time":1791444921354,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."}}},{"type":"chunk","time":1791444921354,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}},{"type":"chunk","time":1791444921354,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}},{"type":"chunk","time":1791444921354,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","data":{"turn":1,"point":"PreToolUse","dialect":"claude-code","handlerId":"claude-code:PreToolUse:1","matcher":"bash"}} -{"type":"hook/result","data":{"turn":1,"point":"PreToolUse","handlerId":"claude-code:PreToolUse:1","decision":"block","exitCode":2,"stderrSummary":"bash is disabled by policy in this session","durationMs":4.173416999999972}} +{"type":"hook/result","data":{"turn":1,"point":"PreToolUse","handlerId":"claude-code:PreToolUse:1","decision":"block","exitCode":2,"stderrSummary":"bash is disabled by policy in this session","durationMs":4.37179100000003}} {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_00_JliP571Bh0QQ8QExbSPk0080"},"toolCallId":"call_00_JliP571Bh0QQ8QExbSPk0080","content":[{"type":"text","text":"Error: bash is disabled by policy in this session"}],"isError":true,"id":"{{message:5}}"}},"sourceEventSeqs":[14],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."},{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21},"stream":[{"type":"chunk","time":1793265534787,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265534787,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0],"texts":["The"," bash"," tool"," is"," disabled"," by"," policy","."," I"," need"," to"," report"," this"," error"," verb","atim"," back"," to"," the"," user","."]},{"type":"chunk","time":1793265534788,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265534788,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," tool"," returned",":\n\n",">"," Error",":"," bash"," is"," disabled"," by"," policy"," in"," this"," session","\n\n","I"," cannot"," run"," the"," command"," because"," the"," bash"," tool"," is"," disabled"," by"," policy","."]},{"type":"chunk","time":1793265534788,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."}}},{"type":"chunk","time":1793265534788,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}}},{"type":"chunk","time":1793265534788,"chunk":{"type":"usage","usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}}},{"type":"chunk","time":1793265534788,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."},{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21},"stream":[{"type":"chunk","time":1791444921374,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444921374,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," bash"," tool"," is"," disabled"," by"," policy","."," I"," need"," to"," report"," this"," error"," verb","atim"," back"," to"," the"," user","."]},{"type":"chunk","time":1791444921374,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791444921374,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0],"texts":["The"," tool"," returned",":\n\n",">"," Error",":"," bash"," is"," disabled"," by"," policy"," in"," this"," session","\n\n","I"," cannot"," run"," the"," command"," because"," the"," bash"," tool"," is"," disabled"," by"," policy","."]},{"type":"chunk","time":1791444921375,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."}}},{"type":"chunk","time":1791444921375,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}}},{"type":"chunk","time":1791444921375,"chunk":{"type":"usage","usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}}},{"type":"chunk","time":1791444921375,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/persistent-pwsh-tool-turn/system-prompt.expected.md b/snapshots/session/persistent-pwsh-tool-turn/system-prompt.expected.md index fea8378aec..842c2d65fe 100644 --- a/snapshots/session/persistent-pwsh-tool-turn/system-prompt.expected.md +++ b/snapshots/session/persistent-pwsh-tool-turn/system-prompt.expected.md @@ -4,11 +4,9 @@ You are a concise snapshot agent. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/persistent-pwsh-tool-turn/tool-schemas.expected.json b/snapshots/session/persistent-pwsh-tool-turn/tool-schemas.expected.json index 00f9f16fec..925f644478 100644 --- a/snapshots/session/persistent-pwsh-tool-turn/tool-schemas.expected.json +++ b/snapshots/session/persistent-pwsh-tool-turn/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "edit", "description": "Edit an existing UTF-8 text file by replacing literal text.", diff --git a/snapshots/session/pi-ai-conversation-updates/session.v4.jsonl b/snapshots/session/pi-ai-conversation-updates/session.v4.jsonl index d29f199056..3c238c7228 100644 --- a/snapshots/session/pi-ai-conversation-updates/session.v4.jsonl +++ b/snapshots/session/pi-ai-conversation-updates/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Read task.txt, call the newly available snapshot_ping tool once, then reply DONE."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"moonshotai","model":"kimi-k3"},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"moonshotai","model":"kimi-k3"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"moonshotai","model":"kimi-k3","contextWindow":1048576,"systemPromptUpdate":"in-history"}} {"type":"session/title","data":{"title":"Read task.txt, call the newly","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}],"source":{"kind":"model","provider":"moonshotai","model":"kimi-k3"},"id":"{{message:4}}"},"usage":{"inputTokens":10,"outputTokens":5},"stream":[{"type":"chunk","time":1790149644504,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790149644504,"index":0,"dt":[],"id":"call_task_read","name":"read","args":["{\"file_path\":\"task.txt\"}"]},{"type":"chunk","time":1790149644504,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_task_read","name":"read","arguments":"{\"file_path\":\"task.txt\"}"}}},{"type":"chunk","time":1790149644504,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}},{"type":"chunk","time":1790149644504,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -18,14 +18,14 @@ {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} {"type":"system/message","data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:6}}"}},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"moonshotai","model":"kimi-k3"},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"moonshotai","model":"kimi-k3"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","snapshot_ping","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}],"source":{"kind":"model","provider":"moonshotai","model":"kimi-k3"},"id":"{{message:8}}"},"stream":[{"type":"chunk","time":1790149644534,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790149644534,"index":0,"dt":[],"id":"call_dynamic_ping","name":"snapshot_ping","args":["{}"]},{"type":"chunk","time":1790149644534,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}}},{"type":"chunk","time":1790149644535,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_dynamic_ping","name":"snapshot_ping","arguments":"{}"}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_dynamic_ping"},"toolCallId":"call_dynamic_ping","content":[{"type":"text","text":"pong"}],"isError":false,"id":"{{message:9}}"}},"sourceEventSeqs":[22],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"step/start","data":{"turn":1,"step":3}} -{"type":"request/header","data":{"header":{"config":{"provider":"moonshotai","model":"kimi-k3"},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"moonshotai","model":"kimi-k3"},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":3,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"snapshot_ping"}],"role":"developer","id":"{{message:10}}"}},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"moonshotai","model":"kimi-k3"},"id":"{{message:11}}"},"usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10},"stream":[{"type":"chunk","time":1790149644557,"chunk":{"type":"block-start","index":0,"blockType":"text"}},{"type":"text-chunks","time0":1790149644557,"index":0,"dt":[],"texts":["DONE"]},{"type":"chunk","time":1790149644557,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1790149644557,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2,"cacheReadTokens":10}}},{"type":"chunk","time":1790149644557,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} diff --git a/snapshots/session/pi-ai-conversation-updates/system-prompt.expected.md b/snapshots/session/pi-ai-conversation-updates/system-prompt.expected.md index 22f72af1c1..ae076cd46e 100644 --- a/snapshots/session/pi-ai-conversation-updates/system-prompt.expected.md +++ b/snapshots/session/pi-ai-conversation-updates/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/plugin-manager-mcp/session.v4.jsonl b/snapshots/session/plugin-manager-mcp/session.v4.jsonl index ac4fbcaf96..af8d95fc88 100644 --- a/snapshots/session/plugin-manager-mcp/session.v4.jsonl +++ b/snapshots/session/plugin-manager-mcp/session.v4.jsonl @@ -9,7 +9,7 @@ {"type":"system/message","data":{"turn":1,"step":1,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:2}}"}},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Use plugin_manager with action set_plugin, target include:demo, enabled true to activate the configured MCP entry. Then call its newly discovered mcp__demo__ping tool and report the result. Do not use other tools."}],"source":{"kind":"user"},"role":"user","id":"{{message:1}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"max"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"max"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","plugin_manager","read","read_image","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":1000000}} {"type":"session/title","data":{"title":"Use plugin_manager with action set_plugi","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to activate a plugin via plugin_manager, then call an MCP tool. Let me do the plugin_manager call first.\n\nNote: they say \"Do not use other tools\" other than plugin_manager and the mcp tool. But I need to first enable it. Let's call plugin_manager set_plugin.\n\nLet me also list plugins first? The instruction says use plugin_manager with action set_plugin, target include:demo, enabled true. Let's just do that."},{"type":"tool-call","id":"call_00_xLhr9wia3A5m7wuSRWwD0436","name":"plugin_manager","arguments":"{\"action\": \"set_plugin\", \"target\": \"include:demo\", \"enabled\": true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"reasoning","signature":"75d99e21-1d47-4a33-bb88-340a1e84b749"},{"type":"tool-call"}]}},"id":"{{message:4}}"},"usage":{"inputTokens":7220,"outputTokens":174,"cacheReadTokens":0,"cacheWriteTokens":0,"totalTokens":7394},"stream":[{"type":"chunk","time":1789984418848,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1789984418848,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," activate"," a"," plugin"," via"," plugin","_manager",","," then"," call"," an"," M","CP"," tool","."," Let"," me"," do"," the"," plugin","_manager"," call"," first",".\n\n","Note",":"," they"," say"," \"","Do"," not"," use"," other"," tools","\""," other"," than"," plugin","_manager"," and"," the"," m","cp"," tool","."," But"," I"," need"," to"," first"," enable"," it","."," Let","'s"," call"," plugin","_manager"," set","_","plugin",".\n\n","Let"," me"," also"," list"," plugins"," first","?"," The"," instruction"," says"," use"," plugin","_manager"," with"," action"," set","_","plugin",","," target"," include",":","demo",","," enabled"," true","."," Let","'s"," just"," do"," that","."]},{"type":"chunk","time":1789984418849,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to activate a plugin via plugin_manager, then call an MCP tool. Let me do the plugin_manager call first.\n\nNote: they say \"Do not use other tools\" other than plugin_manager and the mcp tool. But I need to first enable it. Let's call plugin_manager set_plugin.\n\nLet me also list plugins first? The instruction says use plugin_manager with action set_plugin, target include:demo, enabled true. Let's just do that."}}},{"type":"chunk","time":1789984418849,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1789984418849,"index":1,"dt":[],"id":"call_00_xLhr9wia3A5m7wuSRWwD0436","name":"plugin_manager","args":[""]},{"type":"tool-call-chunks","time0":1789984418849,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_xLhr9wia3A5m7wuSRWwD0436","args":["{","\"","action","\"",": ","\"","set","_","plugin","\"",", ","\"","target","\"",": ","\"","include",":","demo","\"",", ","\"","en","abled","\"",": ","true","}"]},{"type":"chunk","time":1789984418849,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_xLhr9wia3A5m7wuSRWwD0436","name":"plugin_manager","arguments":"{\"action\": \"set_plugin\", \"target\": \"include:demo\", \"enabled\": true}"}}},{"type":"chunk","time":1789984418849,"chunk":{"type":"usage","usage":{"inputTokens":7220,"outputTokens":174,"cacheReadTokens":0,"cacheWriteTokens":0,"totalTokens":7394}}},{"type":"chunk","time":1789984418849,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"reasoning","signature":"75d99e21-1d47-4a33-bb88-340a1e84b749"},{"type":"tool-call"}]}}}]},"surfaceOp":"append"} @@ -18,7 +18,7 @@ {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} {"type":"system/message","data":{"turn":1,"step":2,"message":{"role":"system","content":[{"type":"text","text":"{{system}}"}],"source":{"kind":"system-prompt"},"id":"{{message:6}}"}},"sourceEventSeqs":[7],"surfaceOp":{"op":"replace","startSeq":7,"endSeq":7}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"max"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["apply_patch","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_mcp_resource_templates","list_mcp_resources","mcp__demo__ping","plugin_manager","read","read_image","read_mcp_resource","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash","maxTokens":256000,"reasoningEffort":"max"},"adapterDefaults":{"reasoningEffort":true,"maxTokens":true},"tools":["bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_mcp_resource_templates","list_mcp_resources","mcp__demo__ping","plugin_manager","read","read_image","read_mcp_resource","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change","startsSeries":true}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"list_mcp_resource_templates"},{"type":"tool-addition","toolName":"list_mcp_resources"},{"type":"tool-addition","toolName":"mcp__demo__ping"},{"type":"tool-addition","toolName":"read_mcp_resource"}],"role":"developer","id":"{{message:7}}"},"headerSeq":19},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plugin was enabled. Now call mcp__demo__ping.\n\nWait — the tool was already listed in my tools before enabling. Let's call it anyway."},{"type":"tool-call","id":"call_00_miuKfLCTz5Cb38gdp8kK5186","name":"mcp__demo__ping","arguments":"{}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash","replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"reasoning","signature":"b1ec1efe-4be6-4836-a10c-e5d6bfdce520"},{"type":"tool-call"}]}},"id":"{{message:8}}"},"usage":{"inputTokens":7035,"outputTokens":59,"cacheReadTokens":768,"cacheWriteTokens":0,"totalTokens":7862},"stream":[{"type":"chunk","time":1789984418998,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1789984418998,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," plugin"," was"," enabled","."," Now"," call"," m","cp","__","demo","__","ping",".\n\n","Wait"," —"," the"," tool"," was"," already"," listed"," in"," my"," tools"," before"," enabling","."," Let","'s"," call"," it"," anyway","."]},{"type":"chunk","time":1789984418998,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plugin was enabled. Now call mcp__demo__ping.\n\nWait — the tool was already listed in my tools before enabling. Let's call it anyway."}}},{"type":"chunk","time":1789984418998,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1789984418998,"index":1,"dt":[],"id":"call_00_miuKfLCTz5Cb38gdp8kK5186","name":"mcp__demo__ping","args":[""]},{"type":"tool-call-chunks","time0":1789984418998,"index":1,"dt":[],"id":"call_00_miuKfLCTz5Cb38gdp8kK5186","args":["{}"]},{"type":"chunk","time":1789984418998,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_miuKfLCTz5Cb38gdp8kK5186","name":"mcp__demo__ping","arguments":"{}"}}},{"type":"chunk","time":1789984418998,"chunk":{"type":"usage","usage":{"inputTokens":7035,"outputTokens":59,"cacheReadTokens":768,"cacheWriteTokens":0,"totalTokens":7862}}},{"type":"chunk","time":1789984418998,"chunk":{"type":"finish","reason":{"kind":"tool-calls"},"replayState":{"response":{"kind":"deepseek-messages","version":1,"model":"deepseek-v4-flash"},"blocks":[{"type":"reasoning","signature":"b1ec1efe-4be6-4836-a10c-e5d6bfdce520"},{"type":"tool-call"}]}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_00_miuKfLCTz5Cb38gdp8kK5186","name":"mcp__demo__ping","arguments":"{}"}} diff --git a/snapshots/session/plugin-manager-mcp/system-prompt.expected.md b/snapshots/session/plugin-manager-mcp/system-prompt.expected.md index a5fbfd46c3..738714e849 100644 --- a/snapshots/session/plugin-manager-mcp/system-prompt.expected.md +++ b/snapshots/session/plugin-manager-mcp/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -44,11 +42,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/plugin-manager-mcp/tool-schemas.expected.json b/snapshots/session/plugin-manager-mcp/tool-schemas.expected.json index 6ae7f2fbff..b59709bee7 100644 --- a/snapshots/session/plugin-manager-mcp/tool-schemas.expected.json +++ b/snapshots/session/plugin-manager-mcp/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", @@ -706,34 +678,6 @@ ], "changes": [ [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/plugin-manager/system-prompt.expected.md b/snapshots/session/plugin-manager/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/plugin-manager/system-prompt.expected.md +++ b/snapshots/session/plugin-manager/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/plugin-manager/tool-schemas.expected.json b/snapshots/session/plugin-manager/tool-schemas.expected.json index 8ec77ee2a1..290f04d13a 100644 --- a/snapshots/session/plugin-manager/tool-schemas.expected.json +++ b/snapshots/session/plugin-manager/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/product-subagent-both/system-prompt.expected.md b/snapshots/session/product-subagent-both/system-prompt.expected.md index f838fbc059..c56d93da7d 100644 --- a/snapshots/session/product-subagent-both/system-prompt.expected.md +++ b/snapshots/session/product-subagent-both/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/product-subagent-both/tool-schemas.expected.json b/snapshots/session/product-subagent-both/tool-schemas.expected.json index 0e2d68f4b8..1b05d09fe2 100644 --- a/snapshots/session/product-subagent-both/tool-schemas.expected.json +++ b/snapshots/session/product-subagent-both/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/product-subagent-codex/system-prompt.expected.md b/snapshots/session/product-subagent-codex/system-prompt.expected.md index 77e4259ced..1d102aa047 100644 --- a/snapshots/session/product-subagent-codex/system-prompt.expected.md +++ b/snapshots/session/product-subagent-codex/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/product-subagent-codex/tool-schemas.expected.json b/snapshots/session/product-subagent-codex/tool-schemas.expected.json index acc7319e7a..1c48e82c80 100644 --- a/snapshots/session/product-subagent-codex/tool-schemas.expected.json +++ b/snapshots/session/product-subagent-codex/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/product-subagent-oar/system-prompt.expected.md b/snapshots/session/product-subagent-oar/system-prompt.expected.md index 9e1cfe2ecd..1602145e6e 100644 --- a/snapshots/session/product-subagent-oar/system-prompt.expected.md +++ b/snapshots/session/product-subagent-oar/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/product-subagent-oar/tool-schemas.expected.json b/snapshots/session/product-subagent-oar/tool-schemas.expected.json index 0f60889597..24b40899a7 100644 --- a/snapshots/session/product-subagent-oar/tool-schemas.expected.json +++ b/snapshots/session/product-subagent-oar/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/product-subagent-result-diagnostic/system-prompt.expected.md b/snapshots/session/product-subagent-result-diagnostic/system-prompt.expected.md index 1db919c395..f99fb3e50f 100644 --- a/snapshots/session/product-subagent-result-diagnostic/system-prompt.expected.md +++ b/snapshots/session/product-subagent-result-diagnostic/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/product-subagent-result-diagnostic/tool-schemas.expected.json b/snapshots/session/product-subagent-result-diagnostic/tool-schemas.expected.json index d2c17f6f0c..da2d9314ae 100644 --- a/snapshots/session/product-subagent-result-diagnostic/tool-schemas.expected.json +++ b/snapshots/session/product-subagent-result-diagnostic/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/provider-cwd/system-prompt.expected.md b/snapshots/session/provider-cwd/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/provider-cwd/system-prompt.expected.md +++ b/snapshots/session/provider-cwd/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/provider-cwd/tool-schemas.expected.json b/snapshots/session/provider-cwd/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/provider-cwd/tool-schemas.expected.json +++ b/snapshots/session/provider-cwd/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/ptc-node-read-only/system-prompt.expected.md b/snapshots/session/ptc-node-read-only/system-prompt.expected.md index 5f0b102350..792433868b 100644 --- a/snapshots/session/ptc-node-read-only/system-prompt.expected.md +++ b/snapshots/session/ptc-node-read-only/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -277,27 +266,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-node-workspace/system-prompt.expected.md b/snapshots/session/ptc-node-workspace/system-prompt.expected.md index 5f0b102350..792433868b 100644 --- a/snapshots/session/ptc-node-workspace/system-prompt.expected.md +++ b/snapshots/session/ptc-node-workspace/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -277,27 +266,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-persistent/system-prompt.expected.md b/snapshots/session/ptc-persistent/system-prompt.expected.md index 2974bb8a57..cee1d38ca1 100644 --- a/snapshots/session/ptc-persistent/system-prompt.expected.md +++ b/snapshots/session/ptc-persistent/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -277,27 +266,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-policy-change/system-prompt.expected.md b/snapshots/session/ptc-policy-change/system-prompt.expected.md index b0c19ef0ba..0299ece58d 100644 --- a/snapshots/session/ptc-policy-change/system-prompt.expected.md +++ b/snapshots/session/ptc-policy-change/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -275,27 +264,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-python-turn/system-prompt.expected.md b/snapshots/session/ptc-python-turn/system-prompt.expected.md index a8bed255ba..30de551e71 100644 --- a/snapshots/session/ptc-python-turn/system-prompt.expected.md +++ b/snapshots/session/ptc-python-turn/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -48,38 +46,6 @@ from typing import Any, Literal, NotRequired, Protocol, TypedDict class ToolCallError(Exception): toolName: str -class ApplyPatchArgs(TypedDict): - # Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. - input: str - # The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. - sandbox_permissions: NotRequired[Literal["workspace-write", "danger-full-access"]] - # Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. - justification: NotRequired[str] - # Additional keys beyond those declared are allowed. - -class ApplyPatchOutputOperationsChanges(TypedDict): - path: str - before: str | None - after: str | None - -class ApplyPatchOutputOperations(TypedDict): - index: int - kind: Literal["add", "update", "delete", "move"] - path: str - destination: NotRequired[str] - patchLine: int - status: Literal["completed", "failed", "unknown", "skipped"] - code: NotRequired[str] - message: NotRequired[str] - hunkLine: NotRequired[int] - changes: NotRequired[list[ApplyPatchOutputOperationsChanges]] - -class ApplyPatchOutput(TypedDict): - phase: Literal["commit"] - cancelled: bool - operations: list[ApplyPatchOutputOperations] - affectedPaths: list[str] - class BashArgs(TypedDict): # Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". description: str @@ -538,8 +504,6 @@ class WriteOutput(TypedDict): after: str class Tools(Protocol): - async def apply_patch(self, args: ApplyPatchArgs) -> ApplyPatchOutput: - """Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.""" async def bash(self, args: BashArgs) -> BashOutput1 | BashOutput2 | BashOutput3: """Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.""" async def create_goal(self, args: CreateGoalArgs) -> CreateGoalOutput1 | CreateGoalOutput2: diff --git a/snapshots/session/ptc-read-image/system-prompt.expected.md b/snapshots/session/ptc-read-image/system-prompt.expected.md index 42801f3864..24a8c6d038 100644 --- a/snapshots/session/ptc-read-image/system-prompt.expected.md +++ b/snapshots/session/ptc-read-image/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -273,27 +262,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-script-fresh/system-prompt.expected.md b/snapshots/session/ptc-script-fresh/system-prompt.expected.md index 2974bb8a57..cee1d38ca1 100644 --- a/snapshots/session/ptc-script-fresh/system-prompt.expected.md +++ b/snapshots/session/ptc-script-fresh/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -277,27 +266,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-script-retained/system-prompt.expected.md b/snapshots/session/ptc-script-retained/system-prompt.expected.md index 363bf7bea7..8b1fb247db 100644 --- a/snapshots/session/ptc-script-retained/system-prompt.expected.md +++ b/snapshots/session/ptc-script-retained/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -104,15 +102,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -331,27 +320,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/ptc-turn/system-prompt.expected.md b/snapshots/session/ptc-turn/system-prompt.expected.md index 5f0b102350..792433868b 100644 --- a/snapshots/session/ptc-turn/system-prompt.expected.md +++ b/snapshots/session/ptc-turn/system-prompt.expected.md @@ -11,11 +11,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -52,15 +50,6 @@ Program-only SDK bindings: type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue } interface ToolArgsMap { - /** Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions. */ - apply_patch: { - /** Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory. */ - input: string; - /** The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval. */ - sandbox_permissions?: "workspace-write" | "danger-full-access"; - /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request. */ - justification?: string; - } & Record; /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way. */ bash: { /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: "ls" → "List files in current directory"; "git status" → "Show working tree status"; "npm install" → "Install package dependencies". */ @@ -277,27 +266,6 @@ interface ToolArgsMap { } interface ToolOutputMap { - apply_patch: { - phase: "commit"; - cancelled: boolean; - operations: ({ - index: number; - kind: "add" | "update" | "delete" | "move"; - path: string; - destination?: string; - patchLine: number; - status: "completed" | "failed" | "unknown" | "skipped"; - code?: string; - message?: string; - hunkLine?: number; - changes?: ({ - path: string; - before: string | null; - after: string | null; - })[]; - })[]; - affectedPaths: string[]; - }; bash: { kind: "background"; jobId: string; diff --git a/snapshots/session/pty-tools-sandbox-backend/system-prompt.expected.md b/snapshots/session/pty-tools-sandbox-backend/system-prompt.expected.md index 64733380f0..20152fd0c0 100644 --- a/snapshots/session/pty-tools-sandbox-backend/system-prompt.expected.md +++ b/snapshots/session/pty-tools-sandbox-backend/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/pty-tools-sandbox-backend/tool-schemas.expected.json b/snapshots/session/pty-tools-sandbox-backend/tool-schemas.expected.json index 72985255e3..bf0cb36d10 100644 --- a/snapshots/session/pty-tools-sandbox-backend/tool-schemas.expected.json +++ b/snapshots/session/pty-tools-sandbox-backend/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/pwsh-tool-turn/system-prompt.expected.md b/snapshots/session/pwsh-tool-turn/system-prompt.expected.md index ea6aefddf9..d8b177d881 100644 --- a/snapshots/session/pwsh-tool-turn/system-prompt.expected.md +++ b/snapshots/session/pwsh-tool-turn/system-prompt.expected.md @@ -6,11 +6,9 @@ Non-zero exits are reported as `[exit code: N]` markers; investigate failures be Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/pwsh-tool-turn/tool-schemas.expected.json b/snapshots/session/pwsh-tool-turn/tool-schemas.expected.json index e3b371cc9c..95be0857e0 100644 --- a/snapshots/session/pwsh-tool-turn/tool-schemas.expected.json +++ b/snapshots/session/pwsh-tool-turn/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "edit", "description": "Edit an existing UTF-8 text file by replacing literal text.", diff --git a/snapshots/session/ralph-loop/system-prompt.1.expected.md b/snapshots/session/ralph-loop/system-prompt.1.expected.md index 400faa77be..5fbb332b1a 100644 --- a/snapshots/session/ralph-loop/system-prompt.1.expected.md +++ b/snapshots/session/ralph-loop/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/ralph-loop/system-prompt.2.expected.md b/snapshots/session/ralph-loop/system-prompt.2.expected.md index 400faa77be..5fbb332b1a 100644 --- a/snapshots/session/ralph-loop/system-prompt.2.expected.md +++ b/snapshots/session/ralph-loop/system-prompt.2.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/ralph-loop/system-prompt.expected.md b/snapshots/session/ralph-loop/system-prompt.expected.md index b4f21a40f0..c660db009c 100644 --- a/snapshots/session/ralph-loop/system-prompt.expected.md +++ b/snapshots/session/ralph-loop/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/ralph-loop/tool-schemas.1.expected.json b/snapshots/session/ralph-loop/tool-schemas.1.expected.json index fc9bddf0c6..404eb6dc87 100644 --- a/snapshots/session/ralph-loop/tool-schemas.1.expected.json +++ b/snapshots/session/ralph-loop/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/ralph-loop/tool-schemas.2.expected.json b/snapshots/session/ralph-loop/tool-schemas.2.expected.json index fc9bddf0c6..404eb6dc87 100644 --- a/snapshots/session/ralph-loop/tool-schemas.2.expected.json +++ b/snapshots/session/ralph-loop/tool-schemas.2.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/ralph-loop/tool-schemas.expected.json b/snapshots/session/ralph-loop/tool-schemas.expected.json index a73a27faf0..49057f142e 100644 --- a/snapshots/session/ralph-loop/tool-schemas.expected.json +++ b/snapshots/session/ralph-loop/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/read-image/system-prompt.expected.md b/snapshots/session/read-image/system-prompt.expected.md index d2e726f28b..4956076bc6 100644 --- a/snapshots/session/read-image/system-prompt.expected.md +++ b/snapshots/session/read-image/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/session-query-spill/system-prompt.expected.md b/snapshots/session/session-query-spill/system-prompt.expected.md index bf24f48863..11134b52b8 100644 --- a/snapshots/session/session-query-spill/system-prompt.expected.md +++ b/snapshots/session/session-query-spill/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/session-query-spill/tool-schemas.expected.json b/snapshots/session/session-query-spill/tool-schemas.expected.json index cc8ceba981..986c2c612b 100644 --- a/snapshots/session/session-query-spill/tool-schemas.expected.json +++ b/snapshots/session/session-query-spill/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/subagent-acp-diagnostic/system-prompt.expected.md b/snapshots/session/subagent-acp-diagnostic/system-prompt.expected.md index 1d3995e811..e4447fa937 100644 --- a/snapshots/session/subagent-acp-diagnostic/system-prompt.expected.md +++ b/snapshots/session/subagent-acp-diagnostic/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/subagent-acp-diagnostic/tool-schemas.expected.json b/snapshots/session/subagent-acp-diagnostic/tool-schemas.expected.json index aadba63780..9b0246b8c1 100644 --- a/snapshots/session/subagent-acp-diagnostic/tool-schemas.expected.json +++ b/snapshots/session/subagent-acp-diagnostic/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/subagent-agent-preset/system-prompt.1.expected.md b/snapshots/session/subagent-agent-preset/system-prompt.1.expected.md index 34ccbcb0d7..21ed8bf9ad 100644 --- a/snapshots/session/subagent-agent-preset/system-prompt.1.expected.md +++ b/snapshots/session/subagent-agent-preset/system-prompt.1.expected.md @@ -6,11 +6,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/subagent-agent-preset/tool-schemas.1.expected.json b/snapshots/session/subagent-agent-preset/tool-schemas.1.expected.json index 57300e6608..1b56484211 100644 --- a/snapshots/session/subagent-agent-preset/tool-schemas.1.expected.json +++ b/snapshots/session/subagent-agent-preset/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/subagent-agent-preset/tool-schemas.expected.json b/snapshots/session/subagent-agent-preset/tool-schemas.expected.json index 4e4584b509..2a7c449b6b 100644 --- a/snapshots/session/subagent-agent-preset/tool-schemas.expected.json +++ b/snapshots/session/subagent-agent-preset/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/subagent-child-question-rejection/tool-schemas.expected.json b/snapshots/session/subagent-child-question-rejection/tool-schemas.expected.json index c0b1244500..1d2032fd9e 100644 --- a/snapshots/session/subagent-child-question-rejection/tool-schemas.expected.json +++ b/snapshots/session/subagent-child-question-rejection/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/session/subagent-multi/writer.1.expected.jsonl b/snapshots/session/subagent-multi/writer.1.expected.jsonl index b60bee6b99..9666f25ef7 100644 --- a/snapshots/session/subagent-multi/writer.1.expected.jsonl +++ b/snapshots/session/subagent-multi/writer.1.expected.jsonl @@ -13,6 +13,6 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Reply with exactly the word","messageSeqs":[9],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:14}}"},"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19},"stream":[{"type":"chunk","time":1793265576958,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265576958,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","AL","P","HA","\""," and"," nothing"," else","."]},{"type":"chunk","time":1793265576958,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265576958,"index":1,"dt":[0,0],"texts":["AL","P","HA"]},{"type":"chunk","time":1793265576958,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."}}},{"type":"chunk","time":1793265576958,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}},{"type":"chunk","time":1793265576958,"chunk":{"type":"usage","usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}},{"type":"chunk","time":1793265576958,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:14}}"},"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19},"stream":[{"type":"chunk","time":1791789326845,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791789326846,"index":0,"dt":[1,0,0,0,0,0,0,0,0,0,0,0,1,0,1,0,4,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","AL","P","HA","\""," and"," nothing"," else","."]},{"type":"chunk","time":1791789326853,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791789326853,"index":1,"dt":[0,0],"texts":["AL","P","HA"]},{"type":"chunk","time":1791789326854,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."}}},{"type":"chunk","time":1791789326854,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}},{"type":"chunk","time":1791789326854,"chunk":{"type":"usage","usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}},{"type":"chunk","time":1791789326854,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/subagent-multi/writer.2.expected.jsonl b/snapshots/session/subagent-multi/writer.2.expected.jsonl index 206e8128eb..674fa2ce2e 100644 --- a/snapshots/session/subagent-multi/writer.2.expected.jsonl +++ b/snapshots/session/subagent-multi/writer.2.expected.jsonl @@ -13,6 +13,6 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Reply with exactly the word","messageSeqs":[9],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:18}}"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18},"stream":[{"type":"chunk","time":1793265577022,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265577022,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","B","ETA","\""," and"," nothing"," else","."]},{"type":"chunk","time":1793265577022,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265577022,"index":1,"dt":[0],"texts":["B","ETA"]},{"type":"chunk","time":1793265577022,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."}}},{"type":"chunk","time":1793265577022,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BETA"}}},{"type":"chunk","time":1793265577022,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}},{"type":"chunk","time":1793265577022,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:18}}"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18},"stream":[{"type":"chunk","time":1791789328017,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791789328018,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","B","ETA","\""," and"," nothing"," else","."]},{"type":"chunk","time":1791789328019,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791789328019,"index":1,"dt":[0],"texts":["B","ETA"]},{"type":"chunk","time":1791789328019,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."}}},{"type":"chunk","time":1791789328019,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BETA"}}},{"type":"chunk","time":1791789328019,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}},{"type":"chunk","time":1791789328019,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/subagent-multi/writer.expected.jsonl b/snapshots/session/subagent-multi/writer.expected.jsonl index 8ea01332e9..519727be11 100644 --- a/snapshots/session/subagent-multi/writer.expected.jsonl +++ b/snapshots/session/subagent-multi/writer.expected.jsonl @@ -12,24 +12,24 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Use the subagent tool TWICE,","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\", \"run_in_background\": false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49},"stream":[{"type":"chunk","time":1793265576916,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265576916,"index":0,"dt":[1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," sub","agent"," tool"," twice",","," sequentially"," (","one"," at"," a"," time",")."," First"," sub","agent"," should"," reply"," with"," \"","AL","P","HA","\","," second"," with"," \"","B","ETA","\"."," After"," both"," return",","," I"," reply"," with"," \"","PAR","ENT","_D","ONE","\"."]},{"type":"chunk","time":1793265576917,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265576917,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","args":["","{","\"","description","\"",": ","\"","Return"," AL","P","HA"," only","\"",", ","\"","prom","pt","\"",": ","\"","Reply"," with"," exactly"," the"," word"," AL","P","HA"," and"," nothing"," else",".","\"",", \"run_in_background\": false}"]},{"type":"chunk","time":1793265576917,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."}}},{"type":"chunk","time":1793265576917,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\", \"run_in_background\": false}"}}},{"type":"chunk","time":1793265576917,"chunk":{"type":"usage","usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}}},{"type":"chunk","time":1793265576917,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\", \"run_in_background\": false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49},"stream":[{"type":"chunk","time":1791444968802,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444968803,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," sub","agent"," tool"," twice",","," sequentially"," (","one"," at"," a"," time",")."," First"," sub","agent"," should"," reply"," with"," \"","AL","P","HA","\","," second"," with"," \"","B","ETA","\"."," After"," both"," return",","," I"," reply"," with"," \"","PAR","ENT","_D","ONE","\"."]},{"type":"chunk","time":1791444968804,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791444968804,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","args":["","{","\"","description","\"",": ","\"","Return"," AL","P","HA"," only","\"",", ","\"","prom","pt","\"",": ","\"","Reply"," with"," exactly"," the"," word"," AL","P","HA"," and"," nothing"," else",".","\"",", \"run_in_background\": false}"]},{"type":"chunk","time":1791444968804,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."}}},{"type":"chunk","time":1791444968804,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\", \"run_in_background\": false}"}}},{"type":"chunk","time":1791444968804,"chunk":{"type":"usage","usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}}},{"type":"chunk","time":1791444968804,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\", \"run_in_background\": false}"}} -{"type":"subagent/catalog","data":{"version":0,"childId":"{{session:2}}","childCreatedAt":1793265576924,"mode":"continuable","label":"Return ALPHA only"}} +{"type":"subagent/catalog","data":{"version":0,"childId":"{{session:2}}","childCreatedAt":1791444968811,"mode":"continuable","label":"Return ALPHA only"}} {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{session:2}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"ALPHA"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{session:2}} finished and will do no further work unless you send it more.","senderSessionId":"{{session:2}}"},"role":"user","id":"{{message:5}}"}]}} {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010"},"toolCallId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","content":[{"type":"text","text":"started subagent {{session:2}}"}],"isError":false,"id":"{{message:6}}"}},"sourceEventSeqs":[14],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","data":{"turn":1,"step":2}} {"type":"user/message","data":{"content":[{"type":"text","text":"Background subagent {{session:2}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"ALPHA"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{session:2}} finished and will do no further work unless you send it more.","senderSessionId":"{{session:2}}"},"role":"user","id":"{{message:5}}"},"surfaceOp":"append"} -{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\", \"run_in_background\": false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:7}}"},"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23},"stream":[{"type":"chunk","time":1793265576980,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265576980,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["First"," sub","agent"," returned"," \"","AL","P","HA","\"."," Now"," I","'ll"," call"," the"," second"," sub","agent"," to"," return"," \"","B","ETA","\"."]},{"type":"chunk","time":1793265576980,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1793265576980,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","args":["","{","\"","description","\"",": ","\"","Return"," B","ETA"," only","\"",", ","\"","prom","pt","\"",": ","\"","Reply"," with"," exactly"," the"," word"," B","ETA"," and"," nothing"," else",".","\"",", \"run_in_background\": false}"]},{"type":"chunk","time":1793265576980,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."}}},{"type":"chunk","time":1793265576980,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\", \"run_in_background\": false}"}}},{"type":"chunk","time":1793265576980,"chunk":{"type":"usage","usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}}},{"type":"chunk","time":1793265576980,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\", \"run_in_background\": false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:7}}"},"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23},"stream":[{"type":"chunk","time":1791444968872,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444968872,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["First"," sub","agent"," returned"," \"","AL","P","HA","\"."," Now"," I","'ll"," call"," the"," second"," sub","agent"," to"," return"," \"","B","ETA","\"."]},{"type":"chunk","time":1791444968872,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1791444968872,"index":1,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","args":["","{","\"","description","\"",": ","\"","Return"," B","ETA"," only","\"",", ","\"","prom","pt","\"",": ","\"","Reply"," with"," exactly"," the"," word"," B","ETA"," and"," nothing"," else",".","\"",", \"run_in_background\": false}"]},{"type":"chunk","time":1791444968872,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."}}},{"type":"chunk","time":1791444968872,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\", \"run_in_background\": false}"}}},{"type":"chunk","time":1791444968872,"chunk":{"type":"usage","usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}}},{"type":"chunk","time":1791444968872,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\", \"run_in_background\": false}"}} -{"type":"subagent/catalog","data":{"version":0,"childId":"{{session:3}}","childCreatedAt":1793265576987,"mode":"continuable","label":"Return BETA only"}} +{"type":"subagent/catalog","data":{"version":0,"childId":"{{session:3}}","childCreatedAt":1791444968878,"mode":"continuable","label":"Return BETA only"}} {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"Background subagent {{session:3}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"BETA"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{session:3}} finished and will do no further work unless you send it more.","senderSessionId":"{{session:3}}"},"role":"user","id":"{{message:8}}"}]}} {"type":"tool/result","data":{"turn":1,"step":2,"message":{"role":"tool","source":{"kind":"tool","callId":"call_00_FudNKuJ0fchSptGy3Scw1411"},"toolCallId":"call_00_FudNKuJ0fchSptGy3Scw1411","content":[{"type":"text","text":"started subagent {{session:3}}"}],"isError":false,"id":"{{message:9}}"}},"sourceEventSeqs":[23],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":2}} {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","data":{"turn":1,"step":3}} {"type":"user/message","data":{"content":[{"type":"text","text":"Background subagent {{session:3}} finished and will do no further work unless you send it more."},{"type":"text","text":"Its closing message:"},{"type":"text","text":"BETA"}],"source":{"kind":"subagent-settled","form":"notice","summary":"Background subagent {{session:3}} finished and will do no further work unless you send it more.","senderSessionId":"{{session:3}}"},"role":"user","id":"{{message:8}}"},"surfaceOp":"append"} -{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30},"stream":[{"type":"chunk","time":1793265577045,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265577045,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["Both"," sub","agents"," have"," returned",":"," first"," with"," \"","AL","P","HA","\","," second"," with"," \"","B","ETA","\"."," Now"," I"," should"," reply"," with"," \"","PAR","ENT","_D","ONE","\"."]},{"type":"chunk","time":1793265577045,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265577045,"index":1,"dt":[0,0,0],"texts":["PAR","ENT","_D","ONE"]},{"type":"chunk","time":1793265577045,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."}}},{"type":"chunk","time":1793265577045,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}},{"type":"chunk","time":1793265577045,"chunk":{"type":"usage","usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}}},{"type":"chunk","time":1793265577045,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:10}}"},"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30},"stream":[{"type":"chunk","time":1791444968937,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444968937,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["Both"," sub","agents"," have"," returned",":"," first"," with"," \"","AL","P","HA","\","," second"," with"," \"","B","ETA","\"."," Now"," I"," should"," reply"," with"," \"","PAR","ENT","_D","ONE","\"."]},{"type":"chunk","time":1791444968937,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791444968937,"index":1,"dt":[0,0,0],"texts":["PAR","ENT","_D","ONE"]},{"type":"chunk","time":1791444968937,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."}}},{"type":"chunk","time":1791444968937,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}},{"type":"chunk","time":1791444968937,"chunk":{"type":"usage","usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}}},{"type":"chunk","time":1791444968937,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":3}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/subagent-no-message-tool/cordis.snapshot.yml b/snapshots/session/subagent-no-message-tool/cordis.snapshot.yml index 3cbd35c106..83dad82c05 100644 --- a/snapshots/session/subagent-no-message-tool/cordis.snapshot.yml +++ b/snapshots/session/subagent-no-message-tool/cordis.snapshot.yml @@ -63,8 +63,6 @@ id: parent plugins: - name: '@deepseek-ai/dsh-tool-fs' - config: - applyPatch: true - name: '@deepseek-ai/dsh-tool-fs-search' config: sampleOverCapGlobResults: false diff --git a/snapshots/session/subagent-no-message-tool/cordis.yml b/snapshots/session/subagent-no-message-tool/cordis.yml index 0f15062ac9..52de5ec257 100644 --- a/snapshots/session/subagent-no-message-tool/cordis.yml +++ b/snapshots/session/subagent-no-message-tool/cordis.yml @@ -22,8 +22,6 @@ id: parent plugins: - name: '@deepseek-ai/dsh-tool-fs' - config: - applyPatch: true - name: '@deepseek-ai/dsh-tool-fs-search' config: sampleOverCapGlobResults: false diff --git a/snapshots/session/subagent-structured-parent/system-prompt.1.expected.md b/snapshots/session/subagent-structured-parent/system-prompt.1.expected.md index a67420a02e..7cbbfb55ef 100644 --- a/snapshots/session/subagent-structured-parent/system-prompt.1.expected.md +++ b/snapshots/session/subagent-structured-parent/system-prompt.1.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/subagent-structured-parent/tool-schemas.1.expected.json b/snapshots/session/subagent-structured-parent/tool-schemas.1.expected.json index 718fc518c2..fd65fad3b9 100644 --- a/snapshots/session/subagent-structured-parent/tool-schemas.1.expected.json +++ b/snapshots/session/subagent-structured-parent/tool-schemas.1.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/subagent-structured-parent/tool-schemas.expected.json b/snapshots/session/subagent-structured-parent/tool-schemas.expected.json index d9c2c7941e..32e1b67539 100644 --- a/snapshots/session/subagent-structured-parent/tool-schemas.expected.json +++ b/snapshots/session/subagent-structured-parent/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/subagent-tool-filter/cordis.snapshot.yml b/snapshots/session/subagent-tool-filter/cordis.snapshot.yml index 95a4704dda..d8e94149f0 100644 --- a/snapshots/session/subagent-tool-filter/cordis.snapshot.yml +++ b/snapshots/session/subagent-tool-filter/cordis.snapshot.yml @@ -60,8 +60,6 @@ id: parent plugins: - name: '@deepseek-ai/dsh-tool-fs' - config: - applyPatch: true - name: '@deepseek-ai/dsh-tool-fs-search' config: sampleOverCapGlobResults: false diff --git a/snapshots/session/subagent-tool-filter/cordis.yml b/snapshots/session/subagent-tool-filter/cordis.yml index 89d231bedd..d879f555f8 100644 --- a/snapshots/session/subagent-tool-filter/cordis.yml +++ b/snapshots/session/subagent-tool-filter/cordis.yml @@ -19,8 +19,6 @@ id: parent plugins: - name: '@deepseek-ai/dsh-tool-fs' - config: - applyPatch: true - name: '@deepseek-ai/dsh-tool-fs-search' config: sampleOverCapGlobResults: false diff --git a/snapshots/session/system-prompt-in-history/system-prompt.expected.md b/snapshots/session/system-prompt-in-history/system-prompt.expected.md index c5487b183d..95c410e8ec 100644 --- a/snapshots/session/system-prompt-in-history/system-prompt.expected.md +++ b/snapshots/session/system-prompt-in-history/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. @@ -46,11 +44,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/system-prompt-in-history/tool-schemas.expected.json b/snapshots/session/system-prompt-in-history/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/system-prompt-in-history/tool-schemas.expected.json +++ b/snapshots/session/system-prompt-in-history/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/team-targets/system-prompt.expected.md b/snapshots/session/team-targets/system-prompt.expected.md index ae3374721e..ff7929a66a 100644 --- a/snapshots/session/team-targets/system-prompt.expected.md +++ b/snapshots/session/team-targets/system-prompt.expected.md @@ -17,11 +17,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/team-targets/tool-schemas.expected.json b/snapshots/session/team-targets/tool-schemas.expected.json index 598e869853..d33b95f8d9 100644 --- a/snapshots/session/team-targets/tool-schemas.expected.json +++ b/snapshots/session/team-targets/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/text-turn/system-prompt.expected.md b/snapshots/session/text-turn/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/text-turn/system-prompt.expected.md +++ b/snapshots/session/text-turn/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/text-turn/tool-schemas.expected.json b/snapshots/session/text-turn/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/text-turn/tool-schemas.expected.json +++ b/snapshots/session/text-turn/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/text-turn/writer.expected.jsonl b/snapshots/session/text-turn/writer.expected.jsonl index 3e1e46816a..baab2ac720 100644 --- a/snapshots/session/text-turn/writer.expected.jsonl +++ b/snapshots/session/text-turn/writer.expected.jsonl @@ -12,6 +12,6 @@ {"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} {"type":"session/title","data":{"title":"Reply with exactly the word:","messageSeqs":[8],"source":{"kind":"fallback"}}} -{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."},{"type":"text","text":"PONG"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20},"stream":[{"type":"chunk","time":1793265585145,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1793265585145,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","P","ONG","\""," and"," not"," use"," any"," tools","."]},{"type":"chunk","time":1793265585146,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1793265585146,"index":1,"dt":[0],"texts":["P","ONG"]},{"type":"chunk","time":1793265585146,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."}}},{"type":"chunk","time":1793265585146,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PONG"}}},{"type":"chunk","time":1793265585146,"chunk":{"type":"usage","usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}}},{"type":"chunk","time":1793265585146,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} +{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."},{"type":"text","text":"PONG"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:4}}"},"usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20},"stream":[{"type":"chunk","time":1791444976519,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1791444976519,"index":0,"dt":[1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],"texts":["The"," user"," wants"," me"," to"," reply"," with"," exactly"," the"," word"," \"","P","ONG","\""," and"," not"," use"," any"," tools","."]},{"type":"chunk","time":1791444976520,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1791444976520,"index":1,"dt":[0],"texts":["P","ONG"]},{"type":"chunk","time":1791444976520,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."}}},{"type":"chunk","time":1791444976520,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PONG"}}},{"type":"chunk","time":1791444976520,"chunk":{"type":"usage","usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}}},{"type":"chunk","time":1791444976520,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/snapshots/session/web-fetch/system-prompt.expected.md b/snapshots/session/web-fetch/system-prompt.expected.md index d87b33da03..f8ff1ad2b1 100644 --- a/snapshots/session/web-fetch/system-prompt.expected.md +++ b/snapshots/session/web-fetch/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/web-fetch/tool-schemas.expected.json b/snapshots/session/web-fetch/tool-schemas.expected.json index 0482c38361..ef6c62a3fb 100644 --- a/snapshots/session/web-fetch/tool-schemas.expected.json +++ b/snapshots/session/web-fetch/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/web-search-unconfigured/system-prompt.expected.md b/snapshots/session/web-search-unconfigured/system-prompt.expected.md index b22c4a01d9..a839f0d76d 100644 --- a/snapshots/session/web-search-unconfigured/system-prompt.expected.md +++ b/snapshots/session/web-search-unconfigured/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/workflow-confinement/system-prompt.expected.md b/snapshots/session/workflow-confinement/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/workflow-confinement/system-prompt.expected.md +++ b/snapshots/session/workflow-confinement/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/workflow-confinement/tool-schemas.expected.json b/snapshots/session/workflow-confinement/tool-schemas.expected.json index 2274a83d07..1949c7d605 100644 --- a/snapshots/session/workflow-confinement/tool-schemas.expected.json +++ b/snapshots/session/workflow-confinement/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/session/workspace-dependencies/system-prompt.expected.md b/snapshots/session/workspace-dependencies/system-prompt.expected.md index af4124eff6..fb8a26b762 100644 --- a/snapshots/session/workspace-dependencies/system-prompt.expected.md +++ b/snapshots/session/workspace-dependencies/system-prompt.expected.md @@ -7,11 +7,9 @@ Verify your work by running the code or tests. Keep answers brief and factual. Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/workspace-dependencies/tool-schemas.expected.json b/snapshots/session/workspace-dependencies/tool-schemas.expected.json index 6c3e1a7e5e..c930eafbdc 100644 --- a/snapshots/session/workspace-dependencies/tool-schemas.expected.json +++ b/snapshots/session/workspace-dependencies/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "create_goal", "description": "Create a persisted goal that keeps this session working across automatic continuation rounds. Use it when the direct human request is a long-running objective, even if the user did not say \"goal\"; not for single-turn work.", diff --git a/snapshots/session/worktree/system-prompt.expected.md b/snapshots/session/worktree/system-prompt.expected.md index 0cbe8b7159..4129b103da 100644 --- a/snapshots/session/worktree/system-prompt.expected.md +++ b/snapshots/session/worktree/system-prompt.expected.md @@ -9,11 +9,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/session/worktree/tool-schemas.expected.json b/snapshots/session/worktree/tool-schemas.expected.json index 86861240b0..5602d37fda 100644 --- a/snapshots/session/worktree/tool-schemas.expected.json +++ b/snapshots/session/worktree/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "bash", "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell; pass `workdir` instead of using `cd`. Managed `$DSH_*` variables expose current harness environment facts. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Provide `description` before `command` in the arguments. Before any delete or move, verify that the resolved absolute target path is the intended one; never run it against a computed path you have not checked. An unset variable expands to an empty string, so guard variables in such paths with `${VAR:?}`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]`, a policy denial: do not retry another way.", diff --git a/snapshots/web/collapse-timing/next-message.expected.md b/snapshots/web/collapse-timing/next-message.expected.md index b8e9c993c2..8968e9991c 100644 --- a/snapshots/web/collapse-timing/next-message.expected.md +++ b/snapshots/web/collapse-timing/next-message.expected.md @@ -11,7 +11,7 @@ - button "Copy" - status: Completed - button "Completed in {{duration}}" [expanded] -- button "Tools updated 33 added" +- button "Tools updated 32 added" - button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed." - paragraph: DONE - button "Copy" diff --git a/snapshots/web/collapse-timing/verbose.expected.md b/snapshots/web/collapse-timing/verbose.expected.md index de9e56b3e8..272ff8345d 100644 --- a/snapshots/web/collapse-timing/verbose.expected.md +++ b/snapshots/web/collapse-timing/verbose.expected.md @@ -19,7 +19,7 @@ - button "Copy" - status: Completed - button "Completed in {{duration}}" [disabled] [expanded] -- button "Tools updated 33 added" +- button "Tools updated 32 added" - button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed." - paragraph: DONE - button "Copy" diff --git a/snapshots/web/creation-recommendations/session.v4.jsonl b/snapshots/web/creation-recommendations/session.v4.jsonl index 23f28abe00..9cfead0a39 100644 --- a/snapshots/web/creation-recommendations/session.v4.jsonl +++ b/snapshots/web/creation-recommendations/session.v4.jsonl @@ -11,7 +11,7 @@ {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nCurrent DeepSeek Harness implementation checkout: \"{{sourceRoot}}\".\n\nCurrent DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"harness:source","text":"Current DeepSeek Harness implementation checkout: \"{{sourceRoot}}\"."},{"name":"app:web-surface","text":"Current DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `official-plugins`: Check DSH’s optional plugins when the user asks how to do or use something in this app, whether it can, or says a capability is missing or should change: tools, input, thinking or title display, session search, terminals, worktrees, agent teams, desktop control, automation, access, approvals, badges or signatures, plugins or plugin sources. Not a request to develop DSH, even in its own repository: load before reading files or source. Not for ordinary tasks, quoted wishes or declined offers.\n- `personalized-pages`: Plan an optional page or small tool when the user asks for a page, tab, panel, tool or interface in this app (even for one-off use), wants something to keep, revisit or update later, will keep changing data in your answer, or wants a live view of this app’s own data (Sessions, tasks, logs, workspace). Load this before reading any files or source; it says how to submit the proposal. Not for requested files or code, ordinary answers, existing-feature questions, quoted wishes or declined offers.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"official-plugins","description":"Check DSH’s optional plugins when the user asks how to do or use something in this app, whether it can, or says a capability is missing or should change: tools, input, thinking or title display, session search, terminals, worktrees, agent teams, desktop control, automation, access, approvals, badges or signatures, plugins or plugin sources. Not a request to develop DSH, even in its own repository: load before reading files or source. Not for ordinary tasks, quoted wishes or declined offers."},{"name":"personalized-pages","description":"Plan an optional page or small tool when the user asks for a page, tab, panel, tool or interface in this app (even for one-off use), wants something to keep, revisit or update later, will keep changing data in your answer, or wants a live view of this app’s own data (Sessions, tasks, logs, workspace). Load this before reading any files or source; it says how to submit the proposal. Not for requested files or code, ordinary answers, existing-feature questions, quoted wishes or declined offers."}]},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}],"source":{"kind":"time-context","form":"snapshot","sections":[{"name":"time-context","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}]},"role":"user","id":"{{message:5}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":128000}} {"type":"session/title","data":{"title":"I wish I had a","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_creation_skill","name":"skill","arguments":"{\"name\":\"personalized-pages\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1792674450282,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792674450282,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_creation_skill","name":"skill","arguments":"{\"name\":\"personalized-pages\"}"}}},{"type":"chunk","time":1792674450283,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -19,7 +19,7 @@ {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_creation_skill"},"toolCallId":"call_creation_skill","content":[{"type":"text","text":"\n\nResources for this skill are managed by provider \"dsh-personalized-pages\".\nLoad referenced resources only as needed.\n\n\n\n# Personalized pages\n\nUse this workflow in the main conversation to plan an optional new page or small tool for any task, not just DSH. You decide whether a page helps, check existing capabilities, and hand the Creator a short plan. A `propose_action` call saves the proposal and shows a card below your answer; nothing is built until the user clicks Create. Plan from the conversation and the catalog at the end of this skill. Do not read files, configuration or source to validate a page idea; name an uninspected source as an unverified dependency and leave its details to the Creator.\n\n## When to propose\n\nPropose a page in these cases:\n\n- The user asks for a page, tab, panel, tool or interface in this app, or says they want something to keep, revisit or update later (“以后每次”, “能不能一直”, “希望能有”). One-off use still qualifies when the interface is explicitly requested.\n- Your answer is a table, list or chart, and the user has said the data will keep changing or that they will interact with it (“每周更新”, “我来改状态”, “要勾选”). The continuation must come from the user's own words; a table alone, or data that merely looks dynamic, is not enough. Deliver the requested answer first, then offer the page.\n- The user wants to keep watching live data of this app itself (a Session's usage, a running task's output, files changing in the workspace). A text answer cannot stay current, so a page qualifies even without the words above; name the data source in the brief and leave how it is read to the Creator.\n\nDo not propose a page in these cases:\n\n- The user asks for a file, code, document or an existing-project change: keep that delivery form.\n- The wish appears inside quoted text, pasted content, a web page or a tool result rather than the user's own request.\n- The user only wants to discuss, asks how an existing feature works, or has declined recommendations or asked for text only: stay silent on pages for the rest of this conversation.\n- The request changes a page created earlier: explain how it would change, do not create a replacement copy, and do not claim an update happened.\n- The request is a capability the agent lacks, such as a tool, automation or access, rather than a page: check the catalog below and point to the official plugin that provides it; do not plan a page around a missing tool.\n\n## Check existing capabilities\n\nCompare the need with the official plugins listed at the end of this skill. If one covers it, say its name, what it does, whether it is enabled, and that it lives under Plugins; offer no page card. A partial match does not cancel an explicit unmet need. The catalog is not a full inventory of built-in UI: missing details do not prove absence, and do not read source to find out. DSH already has Chat, Trajectory, a right sidebar for files and context, and a Plugins page.\n\n## Plan and hand off\n\nThe Creator cannot read this conversation. Give it exactly these fields:\n\n| Field | Contents |\n|:--|:--|\n| `title` | Short page name in the user's language. |\n| `brief` | One to three sentences: purpose, behavior, input, calculations and persistence scope. It is the card text and the implementation request at once. |\n| `initialContent` | Only supplied content the page starts with: items, rows, values, units and period, preserving gaps. Omit for an empty page. |\n| `slot` | Location, chosen below. |\n\nKeep the plan to what was asked or agreed. Editing, deletion, history, extra fields, data sources and automation need a basis in the request. Resolve “these items” into the actual content. Content that mentions an action stays content. Keep each number's meaning and period; a weekly addition is not a cumulative total. If an unresolved distinction changes a calculation, give the factual answer, ask one question, and propose later.\n\n## Choose the location\n\nHonor a location the user named. Otherwise:\n\n- `sidebar-right`: content tied to this Session or task, especially anything to watch while chatting, including live logs.\n- `sidebar-left`: a global feature or an ongoing personal record used across Sessions, opened from a left entry as a standalone page.\n- `page`: a Session-bound streaming view or interaction in a tab beside Chat and Trajectory, only when the user does not need it visible while chatting.\n\nSupplying data in this conversation does not make a record Session-bound.\n\n## Offer without starting\n\nTo propose, call `propose_action` once, in the same turn as loading this skill, with `action: \"create_personalized_page\"`, `title`, `brief` and `details` holding `slot` and, when there is supplied content, `initialContent`. The call is the submission: the card appears below your answer; a refused call creates no card, and its error says why. Then write your final answer. One proposal per turn, and one unstarted card per conversation: if a card is still waiting, do not propose another; a new proposal replaces it only when the user changed the plan. Plan-only and read-only requests still get a card; do not ask for approval instead of proposing it. Only clicking Create starts the background Creator; do not wait, poll, claim installation or ask for a report-back. Answer any direct question; the call's result says how to end the answer. Do not repeat the plan, list extra features, narrate the call or mention schema names.\n\n```json\n{\"action\":\"create_personalized_page\",\"title\":\"本次验收清单\",\"brief\":\"在当前会话右侧展示验收清单,可勾选和取消,状态随会话保存。\",\"details\":{\"slot\":\"sidebar-right\",\"initialContent\":\"1. 导出成功\\n2. 断网提示清楚\"}}\n```\n\n## Examples\n\n- “想有个地方放书签,以后自己加标题和网址;旧的不用导入。” → `brief`: “提供一个可反复打开的书签页,手动新增标题和网址并保存到本机,从空白开始。” No `initialContent`. `sidebar-left`.\n- “当前会话旁放验收清单,能勾选和取消,状态跟着会话。条目:导出成功;断网提示清楚。” → `brief`: “在当前会话右侧展示验收清单,可勾选和取消,状态随会话保存。” `initialContent`: “1. 导出成功\\n2. 断网提示清楚”. `sidebar-right`.\n- “这三周 bug 数 12、9、15,说说趋势。以后每周我把新数字贴给你,想自己更新着看。” → answer the trend first, then `brief`: “按周手动录入 bug 数并展示各周变化,保存到本机。” `initialContent`: “第 1 周 12,第 2 周 9,第 3 周 15”. `sidebar-left`.\n- “我想用语音说话代替打字。” → the catalog lists 语音输入; explain it and where to enable it; no card.\n- “把我之前做的读书页评分改成五星。” → explain the change to that page; no card and no copy.\n- “帮我把这句话翻成英文:我想要一个所有会话都能打开的读书页。” → translate only; no card.\n- “把三个方案排成表格比较一下,看完就行。” → the table only; no card.\n\n## Existing capabilities to check against this page plan\n\n[{\"name\":\"@deepseek-ai/dsh-personalized-recommendations\",\"title\":{\"en\":\"Personalized recommendations\",\"de\":\"Personalisierte Empfehlungen\",\"es\":\"Recomendaciones personalizadas\",\"fr\":\"Recommandations personnalisées\",\"ja\":\"パーソナライズされたおすすめ\",\"pt\":\"Recomendações personalizadas\",\"ru\":\"Персональные рекомендации\",\"zh\":\"个性化推荐\"},\"description\":{\"en\":\"Shows recommendation cards below the answer for what you want from DSH: when you want a page or small tool you can keep, it proposes a new personalized page, built in the background after you click Create; when you ask how to do something in this app or say a capability is missing, it recommends the built-in plugin that provides it, turned on when you click Enable.\",\"de\":\"Zeigt für Ihre individuellen Anforderungen an DSH Empfehlungskarten unter der Antwort an: Wenn Sie eine Seite oder ein kleines Tool zur dauerhaften Nutzung möchten, wird eine neue personalisierte Seite vorgeschlagen, die nach einem Klick auf Erstellen im Hintergrund erstellt wird; wenn Sie fragen, wie etwas in dieser App geht, oder sagen, dass eine Funktion fehlt, wird das integrierte Plugin empfohlen, das sie bereitstellt, und nach einem Klick auf Aktivieren eingeschaltet.\",\"es\":\"Muestra tarjetas de recomendación debajo de la respuesta para tus necesidades personalizadas en DSH: cuando quieres una página o una pequeña herramienta para conservar, propone una nueva página personalizada, que se genera en segundo plano al hacer clic en Crear; cuando preguntas cómo hacer algo en esta aplicación o dices que falta una función, recomienda el complemento integrado que la ofrece, que se activa al hacer clic en Habilitar.\",\"fr\":\"Affiche des cartes de recommandation sous la réponse pour vos besoins personnalisés dans DSH : lorsque vous voulez une page ou un petit outil à conserver, propose une nouvelle page personnalisée, générée en arrière-plan après un clic sur Créer ; lorsque vous demandez comment faire quelque chose dans cette application ou signalez qu’une fonctionnalité manque, recommande le plugin intégré qui la fournit, activé lorsque vous cliquez sur Activer.\",\"ja\":\"DSH に対するあなた個人のニーズに合わせて、回答の下におすすめカードを表示します。長く使えるページや小さなツールが欲しいときは新しいパーソナルページを提案し、「作成」をクリックするとバックグラウンドで生成します。このアプリで何かをする方法を尋ねたときや機能が足りないと言ったときは、それを提供する内蔵プラグインを推薦し、「有効にする」をクリックすると有効になります。\",\"pt\":\"Mostra cartões de recomendação abaixo da resposta para suas necessidades personalizadas no DSH: quando você quer uma página ou uma pequena ferramenta para manter, propõe uma nova página personalizada, gerada em segundo plano depois que você clica em Criar; quando você pergunta como fazer algo neste aplicativo ou diz que falta um recurso, recomenda o plug-in integrado que o oferece, ativado quando você clica em Ativar.\",\"ru\":\"Показывает карточки рекомендаций под ответом с учетом ваших индивидуальных потребностей в DSH: когда вам нужна страница или небольшой инструмент для постоянного использования, предлагает новую персональную страницу, которая создается в фоне после нажатия «Создать»; когда вы спрашиваете, как что-то сделать в этом приложении, или говорите, что не хватает какой-то возможности, рекомендует встроенный плагин, который ее предоставляет, и включает его после нажатия «Включить».\",\"zh\":\"针对你对 DSH 的个性化需求,在回答下方展示推荐卡片:想要能长期使用的页面或小工具时,提议新增个性化页面,点击创建后在后台生成;问到本应用怎么做某件事或缺少某项能力时,推荐对应的内置插件,点击启用后开启。\"},\"enabled\":true},{\"name\":\"@deepseek-ai/dsh-experimental-agent-team-profile\",\"title\":{\"en\":\"Agent teams\",\"de\":\"Agententeams\",\"es\":\"Equipos de agentes\",\"fr\":\"Équipes d'agents\",\"ja\":\"エージェントチーム\",\"pt\":\"Equipes de agentes\",\"ru\":\"Команды агентов\",\"zh\":\"智能体团队\"},\"description\":{\"en\":\"Lets the agent you talk to split a job among named teammates, track it on a shared task board, and report back with their results.\",\"de\":\"Ermöglicht dem Agenten, mit dem Sie sprechen, eine Aufgabe auf benannte Teammitglieder aufzuteilen, sie auf einem gemeinsamen Aufgabenboard zu verfolgen und Ihnen mit deren Ergebnissen zu berichten.\",\"es\":\"Permite que el agente con el que habla reparta un trabajo entre compañeros con nombre, lo siga en un tablero de tareas compartido y le informe con sus resultados.\",\"fr\":\"Permet à l'agent avec lequel vous parlez de répartir un travail entre des coéquipiers nommés, de le suivre sur un tableau de tâches partagé et de vous rendre compte de leurs résultats.\",\"ja\":\"対話しているエージェントが、仕事を名前付きのチームメイトに分担させ、共有タスクボードで進捗を追跡し、チームメイトの結果をまとめて報告します。\",\"pt\":\"Permite que o agente com quem você conversa divida um trabalho entre colegas de equipe nomeados, acompanhe-o em um quadro de tarefas compartilhado e informe você com os resultados deles.\",\"ru\":\"Позволяет агенту, с которым вы общаетесь, распределить работу между именованными участниками команды, отслеживать её на общей доске задач и отчитываться перед вами об их результатах.\",\"zh\":\"让与你对话的智能体把工作分给有名字的队友,在共享任务看板上跟踪进度,并汇总队友的结果向你汇报。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-inspector-profile\",\"title\":{\"en\":\"Developer tools\",\"de\":\"Entwicklertools\",\"es\":\"Herramientas de desarrollador\",\"fr\":\"Outils de développement\",\"ja\":\"開発者ツール\",\"pt\":\"Ferramentas de desenvolvedor\",\"ru\":\"Инструменты разработчика\",\"zh\":\"开发者工具\"},\"description\":{\"en\":\"For troubleshooting: view what DSH recorded for a session in Session log, inspect per-turn and per-step statistics in the Statistics tab, and debug the DSH backend in Chrome DevTools.\",\"de\":\"Zur Fehlersuche: Sehen Sie in „Sitzungsprotokoll“, was DSH für eine Sitzung aufgezeichnet hat, prüfen Sie im Tab „Statistik“ Kontext, Dauer, Cache und Werkzeugkosten pro Runde und Schritt und debuggen Sie das DSH-Backend in Chrome DevTools.\",\"es\":\"Para solucionar problemas: vea en «Registro de sesión» lo que DSH registró de una sesión, consulte el contexto, los tiempos, la caché y el coste de herramientas por turno y paso en la pestaña «Estadísticas», y depure el backend de DSH en Chrome DevTools.\",\"fr\":\"Pour le dépannage : consultez dans « Journal de session » ce que DSH a enregistré pour une session, examinez le contexte, les durées, le cache et le coût des outils par tour et étape dans l’onglet « Statistiques », et déboguez le backend de DSH dans Chrome DevTools.\",\"ja\":\"トラブルシューティング用です。「セッションログ」で DSH がセッションについて記録した内容を確認し、「統計」タブでターン/ステップごとのコンテキスト、時間、キャッシュ、ツールコストを確認し、Chrome DevTools で DSH バックエンドをデバッグできます。\",\"pt\":\"Para solução de problemas: veja em «Registro da sessão» o que o DSH registrou de uma sessão, consulte contexto, tempos, cache e custo de ferramentas por turno e etapa na aba «Estatísticas» e depure o backend do DSH no Chrome DevTools.\",\"ru\":\"Для диагностики: просматривайте в «Журнале сеанса», что DSH записал для сеанса, смотрите контекст, время, кэш и стоимость инструментов по ходам и шагам на вкладке «Статистика» и отлаживайте бэкенд DSH в Chrome DevTools.\",\"zh\":\"用于排查问题:在「会话数据诊断」中查看 DSH 为会话记录的内容,在「统计」页签查看每轮/每步的上下文、耗时、缓存和工具成本,并在 Chrome DevTools 中调试 DSH 后端。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\",\"title\":{\"en\":\"Voice input\",\"de\":\"Spracheingabe\",\"es\":\"Entrada de voz\",\"fr\":\"Saisie vocale\",\"ja\":\"音声入力\",\"pt\":\"Entrada de voz\",\"ru\":\"Голосовой ввод\",\"zh\":\"语音输入\"},\"description\":{\"en\":\"Transcribe recordings locally with SenseVoice; first use requires installing dependencies.\",\"de\":\"Transkribieren Sie Aufnahmen lokal mit SenseVoice; Für die erste Verwendung müssen Abhängigkeiten installiert werden.\",\"es\":\"Transcribe grabaciones localmente con SenseVoice; El primer uso requiere instalar dependencias.\",\"fr\":\"Transcrivez les enregistrements localement avec SenseVoice ; la première utilisation nécessite l'installation de dépendances.\",\"ja\":\"ローカルの SenseVoice で録音を文字に起こします。初回利用時には依存関係のインストールが必要です。\",\"pt\":\"Transcreva gravações localmente com SenseVoice; o primeiro uso requer a instalação de dependências.\",\"ru\":\"Транскрибируйте записи локально с помощью SenseVoice; при первом использовании требуется установка зависимостей.\",\"zh\":\"在本机使用 SenseVoice 转写录音,首次使用需安装依赖。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-auto-review\",\"title\":{\"en\":\"Auto authorization review\",\"de\":\"Automatische Autorisierungsüberprüfung\",\"es\":\"Revisión de autorización automática\",\"fr\":\"Examen des autorisations automatiques\",\"ja\":\"自動認可レビュー\",\"pt\":\"Revisão de autorização automática\",\"ru\":\"Проверка автоматической авторизации\",\"zh\":\"自动授权审查\"},\"description\":{\"en\":\"Adds an Auto review access mode: before each tool call, a model checks it against what you asked for, runs allowed calls at once, and holds denied calls for your approval.\",\"de\":\"Fügt den Zugriffsmodus „Auto review“ hinzu: Vor jedem Tool-Aufruf prüft ein Modell den Aufruf anhand Ihrer Anforderung; zugelassene Aufrufe laufen sofort, abgelehnte Aufrufe warten auf Ihre Genehmigung.\",\"es\":\"Añade el modo de acceso “Auto review”: antes de cada llamada a una herramienta, un modelo comprueba la llamada frente a lo que usted pidió; las llamadas permitidas se ejecutan de inmediato y las denegadas esperan su aprobación.\",\"fr\":\"Ajoute le mode d'accès « Auto review » : avant chaque appel d'outil, un modèle vérifie l'appel par rapport à ce que vous avez demandé ; les appels autorisés s'exécutent immédiatement et les appels refusés attendent votre approbation.\",\"ja\":\"「自動認可レビュー」アクセスモードを追加します。各ツール呼び出しの前に、モデルがその呼び出しをあなたの依頼内容と照らし合わせて確認し、許可された呼び出しは即座に実行され、拒否された呼び出しはあなたの承認を待ちます。\",\"pt\":\"Adiciona o modo de acesso “Auto review”: antes de cada chamada de ferramenta, um modelo verifica a chamada em relação ao que você pediu; as chamadas permitidas são executadas imediatamente e as negadas aguardam sua aprovação.\",\"ru\":\"Добавляет режим доступа «Auto review»: перед каждым вызовом инструмента модель сверяет вызов с вашей просьбой; разрешённые вызовы выполняются сразу, а отклонённые ждут вашего одобрения.\",\"zh\":\"提供“自动审查”访问模式:每次工具调用前,由模型对照你的要求检查,获准的调用立即运行,被拒绝的调用等你审批。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-cot-translation-bundle\",\"title\":{\"en\":\"Machine translation of reasoning\",\"de\":\"Maschinelle Übersetzung der Argumentation\",\"es\":\"Traducción automática de razonamiento\",\"fr\":\"Traduction automatique du raisonnement\",\"ja\":\"思考内容の機械翻訳\",\"pt\":\"Tradução automática de raciocínio\",\"ru\":\"Машинный перевод рассуждений\",\"zh\":\"思考过程机器翻译\"},\"description\":{\"en\":\"Translates expanded Think rows into your chosen language as the agent writes them, and View original switches back.\",\"de\":\"Übersetzt aufgeklappte „Denken Sie nach“-Zeilen, während der Agent sie schreibt, in die von Ihnen gewählte Sprache, und „Original ansehen“ wechselt zurück.\",\"es\":\"Traduce las filas “pensar” expandidas al idioma que elija mientras el agente las escribe, y “Ver original” vuelve al texto original.\",\"fr\":\"Traduit les lignes « Pensez » développées dans la langue de votre choix pendant que l'agent les écrit, et « Voir l'original » permet de revenir au texte d'origine.\",\"ja\":\"エージェントが書き出すのと同時に、展開された「思考」行を選択した言語に翻訳します。「原文を表示」で原文に戻せます。\",\"pt\":\"Traduz as linhas “Pense” expandidas para o idioma que você escolher enquanto o agente as escreve, e “Ver original” volta ao texto original.\",\"ru\":\"Переводит развёрнутые строки «Подумайте» на выбранный вами язык по мере того, как агент их пишет, а «Посмотреть оригинал» возвращает исходный текст.\",\"zh\":\"智能体输出时,把展开的“思考”行翻译成你选择的语言,点击“查看原文”可切换回原文。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-badge-skill-bundle\",\"title\":{\"en\":\"DSH badge skill\",\"de\":\"DSH-Abzeichen-Fertigkeit\",\"es\":\"Habilidad de insignia DSH\",\"fr\":\"Compétence du badge DSH\",\"ja\":\"DSH バッジスキル\",\"pt\":\"DSH habilidade de distintivo\",\"ru\":\"DSH значок навыка\",\"zh\":\"DSH 徽章技能\"},\"description\":{\"en\":\"Let agents add a “powered by dsh” badge to documents, pull requests, and other outputs.\",\"de\":\"Lassen Sie Agenten Dokumente, Pull-Requests und andere Ausgaben mit einem „powered by dsh“-Badge versehen.\",\"es\":\"Permita que los agentes agreguen una insignia \\\"con tecnología de dsh\\\" a documentos, solicitudes de extracción y otros resultados.\",\"fr\":\"Laissez les agents ajouter un badge « propulsé par dsh » aux documents, demandes d'extraction et autres sorties.\",\"ja\":\"エージェントが文書や PR などの成果物に「powered by dsh」バッジを追加できます。\",\"pt\":\"Permita que os agentes adicionem um selo “powered by dsh” a documentos, pull requests e outros resultados.\",\"ru\":\"Позвольте агентам добавлять значок «Powered by dsh» к документам, запросам на включение и другим результатам.\",\"zh\":\"让 Agent 为文档、PR 等产出添加「powered by dsh」徽章。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-ralph-bundle\",\"title\":{\"en\":\"Ralph loops\",\"de\":\"Ralph-Loops\",\"es\":\"Bucles de Ralph\",\"fr\":\"Boucles Ralph\",\"ja\":\"Ralph ループ\",\"pt\":\"Loops de Ralph\",\"ru\":\"Ральф петли\",\"zh\":\"Ralph 循环\"},\"description\":{\"en\":\"Ask for a Ralph loop with a goal, and the agent starts a fresh agent on it round after round until the goal is met, a blocker is reported, or the round limit is reached.\",\"de\":\"Bitten Sie um eine Ralph-Schleife mit einem Ziel, und der Agent startet Runde um Runde einen neuen Agenten darauf, bis das Ziel erreicht ist, ein Hindernis gemeldet wird oder das Rundenlimit erreicht ist.\",\"es\":\"Pida un bucle Ralph con un objetivo, y el agente inicia un agente nuevo sobre él ronda tras ronda hasta que se cumpla el objetivo, se informe de un bloqueo o se alcance el límite de rondas.\",\"fr\":\"Demandez une boucle Ralph avec un objectif, et l'agent lance un nouvel agent dessus, tour après tour, jusqu'à ce que l'objectif soit atteint, qu'un blocage soit signalé ou que la limite de tours soit atteinte.\",\"ja\":\"目標を指定して Ralph ループを依頼すると、エージェントは、目標が達成されるか、阻害要因が報告されるか、ラウンド数の上限に達するまで、ラウンドごとに新しいエージェントを起動してその目標に取り組ませます。\",\"pt\":\"Peça um loop Ralph com um objetivo, e o agente inicia um novo agente nele rodada após rodada até que o objetivo seja atingido, um bloqueio seja informado ou o limite de rodadas seja alcançado.\",\"ru\":\"Попросите запустить цикл Ralph с целью, и агент будет раунд за раундом запускать для неё нового агента, пока цель не будет достигнута, не будет сообщено о препятствии или не будет достигнут лимит раундов.\",\"zh\":\"要求用 Ralph 循环完成一个目标后,智能体会一轮接一轮地启动新的智能体处理它,直到目标达成、报告受阻或达到轮次上限。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-session-titles-bundle\",\"title\":{\"en\":\"Conversation-following titles\",\"de\":\"Konversationsfolgende Titel\",\"es\":\"Títulos que siguen la conversación\",\"fr\":\"Titres de suivi de conversation\",\"ja\":\"会話に追従するタイトル\",\"pt\":\"Títulos que acompanham conversas\",\"ru\":\"Заголовки, следующие за разговором\",\"zh\":\"随对话更新的标题\"},\"description\":{\"en\":\"Writes a session's title from all of your messages and updates it when the main task changes, instead of only from the first message.\",\"de\":\"Erstellt den Titel einer Sitzung aus all Ihren Nachrichten und aktualisiert ihn, wenn sich die Hauptaufgabe ändert, statt ihn nur aus der ersten Nachricht zu bilden.\",\"es\":\"Escribe el título de una sesión a partir de todos sus mensajes y lo actualiza cuando cambia la tarea principal, en lugar de basarse solo en el primer mensaje.\",\"fr\":\"Rédige le titre d'une session à partir de tous vos messages et le met à jour lorsque la tâche principale change, au lieu de se baser uniquement sur le premier message.\",\"ja\":\"最初のメッセージだけでなく、あなたのすべてのメッセージからセッションのタイトルを作成し、主なタスクが変わったときに更新します。\",\"pt\":\"Escreve o título de uma sessão a partir de todas as suas mensagens e o atualiza quando a tarefa principal muda, em vez de usar apenas a primeira mensagem.\",\"ru\":\"Составляет заголовок сеанса по всем вашим сообщениям и обновляет его при смене основной задачи, а не только по первому сообщению.\",\"zh\":\"根据你的所有消息生成会话标题,并在主要任务变化时更新,而不是只根据第一条消息生成。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-terminal-bundle\",\"title\":{\"en\":\"Persistent terminals\",\"de\":\"Persistente Terminals\",\"es\":\"Terminales persistentes\",\"fr\":\"Terminaux persistants\",\"ja\":\"永続ターミナル\",\"pt\":\"Terminais persistentes\",\"ru\":\"Постоянные терминалы\",\"zh\":\"持久终端\"},\"description\":{\"en\":\"Gives the agent terminals whose processes keep running in the background between tool calls, so it can start a dev server or REPL and come back later to read output or type input.\",\"de\":\"Stellt dem Agenten Terminals bereit, deren Prozesse zwischen Tool-Aufrufen im Hintergrund weiterlaufen, sodass er einen Entwicklungsserver oder eine REPL starten und später zurückkehren kann, um Ausgaben zu lesen oder Eingaben zu tippen.\",\"es\":\"Proporciona al agente terminales cuyos procesos siguen ejecutándose en segundo plano entre llamadas a herramientas, de modo que puede iniciar un servidor de desarrollo o un REPL y volver más tarde para leer la salida o escribir entradas.\",\"fr\":\"Fournit à l'agent des terminaux dont les processus continuent de s'exécuter en arrière-plan d'un appel d'outil à l'autre, afin qu'il puisse lancer un serveur de développement ou un REPL et revenir plus tard lire la sortie ou saisir des entrées.\",\"ja\":\"エージェントにターミナルを提供します。プロセスはツール呼び出し間もバックグラウンドで実行され続けるため、エージェントは開発サーバーや REPL を起動し、後から出力を読んだり入力したりできます。\",\"pt\":\"Fornece ao agente terminais cujos processos continuam em execução em segundo plano entre chamadas de ferramentas, para que ele possa iniciar um servidor de desenvolvimento ou um REPL e voltar depois para ler a saída ou digitar entradas.\",\"ru\":\"Предоставляет агенту терминалы, процессы которых продолжают работать в фоне между вызовами инструментов, поэтому агент может запустить сервер разработки или REPL и позже вернуться, чтобы прочитать вывод или ввести данные.\",\"zh\":\"为智能体提供终端,进程在多次工具调用之间持续在后台运行,因此它可以启动开发服务器或 REPL,稍后再读取输出或继续输入。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-liveshare\",\"title\":{\"en\":\"LiveShare Session Sharing\",\"de\":\"LiveShare-Sitzungsfreigabe\",\"es\":\"Compartir sesión de LiveShare\",\"fr\":\"Partage de session LiveShare\",\"ja\":\"LiveShare セッション共有\",\"pt\":\"Compartilhamento de sessão do LiveShare\",\"ru\":\"Совместный доступ к сеансу LiveShare\",\"zh\":\"LiveShare 会话分享\"},\"description\":{\"en\":\"Share the current Session with a colleague, who can drive it in a browser, edit files inside the granted workspace when the share allows writes, or branch their own Session from the completed history.\",\"de\":\"Teilt die aktuelle Sitzung mit einer Kollegin oder einem Kollegen, die oder der sie im Browser bedienen, bei erlaubten Schreibzugriffen Dateien im freigegebenen Arbeitsbereich bearbeiten oder aus der abgeschlossenen Historie eine eigene Sitzung abzweigen kann.\",\"es\":\"Comparte la sesión actual con un compañero, que puede dirigirla en un navegador, editar archivos dentro del espacio de trabajo concedido cuando el recurso compartido permite escritura, o crear su propia sesión a partir del historial completado.\",\"fr\":\"Partagez la session en cours avec un collègue, qui peut la piloter dans un navigateur, modifier des fichiers dans l'espace de travail accordé lorsque le partage autorise l'écriture, ou créer sa propre session à partir de l'historique terminé.\",\"ja\":\"現在のセッションを同僚と共有し、ブラウザから操作してもらう、共有が書き込みを許可する場合は付与されたワークスペース内のファイルを編集してもらう、または完了した履歴から自分のセッションを分岐してもらえます。\",\"pt\":\"Compartilhe a sessão atual com um colega, que pode conduzi-la no navegador, editar arquivos dentro do espaço de trabalho concedido quando o compartilhamento permite escrita, ou ramificar a própria sessão a partir do histórico concluído.\",\"ru\":\"Поделитесь текущим сеансом с коллегой: он сможет управлять им в браузере, редактировать файлы в предоставленном рабочем пространстве, если общий доступ разрешает запись, или ответвить собственный сеанс из завершённой истории.\",\"zh\":\"把当前会话分享给同事,对方可在浏览器中驱动该会话、在分享允许写入时修改授权工作区内的文件,或从已完成历史分支出自己的会话。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-session-search\",\"title\":{\"en\":\"Session search\",\"de\":\"Sitzungssuche\",\"es\":\"búsqueda de sesión\",\"fr\":\"Recherche de sessions\",\"ja\":\"セッション検索\",\"pt\":\"Pesquisa de sessão\",\"ru\":\"Поиск сеанса\",\"zh\":\"会话搜索\"},\"description\":{\"en\":\"Ask about earlier work, such as “How did we fix the pool leak last week?”, and the agent searches your earlier sessions in the same workspace to answer.\",\"de\":\"Fragen Sie nach früherer Arbeit, etwa „Wie haben wir letzte Woche das Pool-Leck behoben?“, und der Agent durchsucht Ihre früheren Sitzungen aus demselben Arbeitsverzeichnis, um zu antworten.\",\"es\":\"Pregunte por trabajo anterior, como “¿Cómo arreglamos la fuga del pool la semana pasada?”, y el agente busca en sus sesiones anteriores del mismo directorio de trabajo para responder.\",\"fr\":\"Posez une question sur un travail antérieur, par exemple « Comment avons-nous corrigé la fuite du pool la semaine dernière ? », et l'agent recherche dans vos sessions antérieures du même répertoire de travail pour répondre.\",\"ja\":\"「先週プールのリークをどう直した?」のように以前の作業について尋ねると、エージェントは同じ作業ディレクトリの過去のセッションを検索して回答します。\",\"pt\":\"Pergunte sobre trabalhos anteriores, como “Como corrigimos o vazamento do pool na semana passada?”, e o agente pesquisa suas sessões anteriores do mesmo diretório de trabalho para responder.\",\"ru\":\"Спросите о прошлой работе, например «Как мы исправили утечку в пуле на прошлой неделе?», и агент выполнит поиск по вашим прошлым сеансам из того же рабочего каталога, чтобы ответить.\",\"zh\":\"询问以往的工作,例如“上周我们是怎么修好连接池泄漏的?”,智能体会搜索同一工作区的历史会话来回答。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-tool-worktree\",\"title\":{\"en\":\"Git worktrees\",\"de\":\"Git-Arbeitsbäume\",\"es\":\"árboles de trabajo de git\",\"fr\":\"Arbres de travail Git\",\"ja\":\"Git ワークツリー\",\"pt\":\"Árvores de trabalho Git\",\"ru\":\"Рабочие деревья Git\",\"zh\":\"Git 工作树\"},\"description\":{\"en\":\"Ask for work on a new branch, and the agent creates a separate Git worktree and continues there, leaving your current checkout as it is.\",\"de\":\"Bitten Sie um Arbeit auf einem neuen Branch, und der Agent erstellt einen separaten Git-Worktree und arbeitet dort weiter, während Ihr aktueller Checkout unverändert bleibt.\",\"es\":\"Pida trabajar en una rama nueva, y el agente crea un worktree de Git independiente y continúa allí, dejando su checkout actual tal como está.\",\"fr\":\"Demandez à travailler sur une nouvelle branche, et l'agent crée un worktree Git distinct et y poursuit le travail, en laissant votre copie de travail actuelle telle quelle.\",\"ja\":\"新しいブランチでの作業を依頼すると、エージェントは別の Git ワークツリーを作成してそこで作業を続け、現在のチェックアウトはそのまま残します。\",\"pt\":\"Peça para trabalhar em um novo branch, e o agente cria um worktree do Git separado e continua lá, deixando seu checkout atual como está.\",\"ru\":\"Попросите поработать в новой ветке, и агент создаст отдельное рабочее дерево Git и продолжит работу там, оставив вашу текущую рабочую копию как есть.\",\"zh\":\"要求在新分支上工作时,智能体会创建单独的 Git 工作树并在其中继续,你当前的工作树保持原样。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-plugin-market-bundle\",\"title\":{\"en\":\"Custom plugin indexes\",\"de\":\"Benutzerdefinierte Plugin-Indizes\",\"es\":\"Índices de complementos personalizados\",\"fr\":\"Index de plugins personnalisés\",\"ja\":\"カスタムプラグインインデックス\",\"pt\":\"Índices de plug-ins personalizados\",\"ru\":\"Пользовательские индексы плагинов\",\"zh\":\"自定义插件索引\"},\"description\":{\"en\":\"Adds a Discover tab to Plugins, where you browse and install plugins from plugin indexes you add.\",\"de\":\"Fügt unter „Plugins“ den Tab „Entdecken“ hinzu, in dem Sie Plugins aus von Ihnen hinzugefügten Plugin-Indizes durchsuchen und installieren.\",\"es\":\"Añade la pestaña “Descubrir” a “Complementos”, donde puede explorar e instalar complementos de los índices de complementos que agregue.\",\"fr\":\"Ajoute à « Plugins » un onglet « Découvrez » où vous parcourez et installez des plugins provenant des index de plugins que vous ajoutez.\",\"ja\":\"「プラグイン」に「見つける」タブを追加し、追加したプラグインインデックスからプラグインを閲覧・インストールできるようにします。\",\"pt\":\"Adiciona a guia “Descubra” a “Plug-ins”, onde você navega e instala plug-ins dos índices de plug-ins que adiciona.\",\"ru\":\"Добавляет в «Плагины» вкладку «Откройте для себя», где можно просматривать и устанавливать плагины из добавленных вами индексов плагинов.\",\"zh\":\"在插件页添加“发现”标签页,从你添加的插件索引中浏览和安装插件。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-experimental-forge-bundle\",\"title\":{\"en\":\"Change requests & worktrees\",\"de\":\"Änderungsanfragen und Arbeitsbäume\",\"es\":\"Solicitudes de cambio y árboles de trabajo\",\"fr\":\"Demandes de modification et arbres de travail\",\"ja\":\"変更リクエストとワークツリー\",\"pt\":\"Solicitações de alteração e árvores de trabalho\",\"ru\":\"Запросы на изменение и рабочие деревья\",\"zh\":\"变更请求与工作树\"},\"description\":{\"en\":\"Track each Session's change requests with their checks and reviews, and start new Sessions in a Git worktree; uses the gh CLI for GitHub.\",\"de\":\"Verfolgen Sie die Änderungsanfragen jeder Sitzung mit ihren Prüfungen und Reviews und starten Sie neue Sitzungen in einem Git-Arbeitsbaum; nutzt die gh CLI für GitHub.\",\"es\":\"Siga las solicitudes de cambio de cada sesión con sus comprobaciones y revisiones, e inicie nuevas sesiones en un árbol de trabajo de Git; usa la CLI gh para GitHub.\",\"fr\":\"Suivez les demandes de modification de chaque session avec leurs vérifications et revues, et démarrez de nouvelles sessions dans un arbre de travail Git ; utilise la CLI gh pour GitHub.\",\"ja\":\"各セッションの変更リクエストとそのチェックやレビューを追跡し、新しいセッションを Git ワークツリーで開始できます。GitHub には gh CLI を使用します。\",\"pt\":\"Acompanhe as solicitações de alteração de cada sessão com suas verificações e revisões e inicie novas sessões em uma árvore de trabalho Git; usa a CLI gh para o GitHub.\",\"ru\":\"Отслеживайте запросы на изменение каждого сеанса вместе с их проверками и ревью и начинайте новые сеансы в рабочем дереве Git; для GitHub используется gh CLI.\",\"zh\":\"跟踪每个会话的变更请求及其检查与评审,新会话也可以在 Git 工作树中开始;GitHub 通过 gh 命令行访问。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-subagent-claude-code\",\"title\":{\"de\":\"Claude Code-Subagent\",\"en\":\"Claude Code subagent\",\"es\":\"Subagente Claude Code\",\"fr\":\"Sous-agent Claude Code\",\"ja\":\"Claude Code サブエージェント\",\"pt\":\"Claude Code subagente\",\"ru\":\"Субагент Claude Code\",\"zh\":\"Claude Code 子智能体\"},\"description\":{\"de\":\"Delegieren Sie eine Aufgabe an Claude Code, indem Sie dessen native Authentifizierung und Einstellungen verwenden.\",\"en\":\"Delegate one task to Claude Code using its native authentication and settings.\",\"es\":\"Delegue una tarea a Claude Code utilizando su autenticación y configuración nativas.\",\"fr\":\"Déléguez une tâche à Claude Code à l’aide de son authentification et de ses paramètres natifs.\",\"ja\":\"Claude Code のネイティブの認証と設定を使用して、単独のタスクを委派します。\",\"pt\":\"Delegue uma tarefa a Claude Code usando sua autenticação e configurações nativas.\",\"ru\":\"Делегируйте одну задачу Claude Code, используя его встроенную аутентификацию и настройки.\",\"zh\":\"使用 Claude Code 原生认证和设置委派单个任务。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-subagent-codex\",\"title\":{\"de\":\"Codex-Subagent\",\"en\":\"Codex subagent\",\"es\":\"Subagente Codex\",\"fr\":\"Sous-agent Codex\",\"ja\":\"Codex サブエージェント\",\"pt\":\"Codex subagente\",\"ru\":\"Субагент Codex\",\"zh\":\"Codex 子智能体\"},\"description\":{\"de\":\"Delegieren Sie eine Aufgabe an Codex, indem Sie dessen native Authentifizierung und Einstellungen verwenden.\",\"en\":\"Delegate one task to Codex using its native authentication and settings.\",\"es\":\"Delegue una tarea a Codex utilizando su autenticación y configuración nativas.\",\"fr\":\"Déléguez une tâche à Codex à l’aide de son authentification et de ses paramètres natifs.\",\"ja\":\"Codex のネイティブの認証と設定を使用して、単独のタスクを委派します。\",\"pt\":\"Delegue uma tarefa a Codex usando sua autenticação e configurações nativas.\",\"ru\":\"Делегируйте одну задачу Codex, используя его встроенную аутентификацию и настройки.\",\"zh\":\"使用 Codex 原生认证和设置委派单个任务。\"},\"enabled\":false},{\"name\":\"@deepseek-ai/dsh-cua-bundle\",\"title\":{\"de\":\"Computernutzung\",\"en\":\"Computer use\",\"es\":\"Uso de la computadora\",\"fr\":\"Utilisation de l'ordinateur\",\"ja\":\"Computer Use\",\"pt\":\"Uso do computador\",\"ru\":\"Использование компьютера\",\"zh\":\"Computer Use\"},\"description\":{\"de\":\"Unterstützt derzeit macOS; Die Windows-Unterstützung befindet sich in der Entwicklung. Lädt die Computernutzung für bestehende und neue PTC-Sitzungen. Wechseln Sie in den PTC-Modus und erteilen Sie die Berechtigungen für Barrierefreiheit und Bildschirmaufzeichnung, um ihn zu verwenden.\",\"en\":\"Currently supports macOS; Windows support is in development. Loads computer use for existing and new PTC sessions. Switch to PTC mode and grant Accessibility and Screen Recording permissions to use it.\",\"es\":\"Actualmente es compatible con macOS; El soporte para Windows está en desarrollo. Carga el uso de la computadora para sesiones PTC nuevas y existentes. Cambie al modo PTC y otorgue permisos de Accesibilidad y Grabación de pantalla para usarlo.\",\"fr\":\"Prend actuellement en charge macOS ; La prise en charge de Windows est en cours de développement. Charge l'utilisation de l'ordinateur pour les sessions PTC existantes et nouvelles. Passez en mode PTC et accordez les autorisations d’accessibilité et d’enregistrement d’écran pour l’utiliser.\",\"ja\":\"現在は macOS のみ対応し、Windows 対応は開発中です。既存および新規の PTC セッションに Computer Use を読み込みます。PTC モードに切り替え、アクセシビリティと画面収録の権限を許可して使用してください。\",\"pt\":\"Atualmente suporta macOS; O suporte Windows está em desenvolvimento. Carrega o uso do computador para sessões PTC novas e existentes. Mude para o modo PTC e conceda permissões de acessibilidade e gravação de tela para usá-lo.\",\"ru\":\"В настоящее время поддерживается macOS; Поддержка Windows находится в разработке. Загружает использование компьютера для существующих и новых сеансов PTC. Переключитесь в режим PTC и предоставьте разрешения на доступность и запись экрана для его использования.\",\"zh\":\"目前仅支持 macOS,Windows 支持正在开发中。为已有及新建 PTC 会话加载 Computer Use。请切换到 PTC 模式来使用,并授予辅助功能和屏幕录制权限。\"},\"enabled\":false}]\n\n"}],"isError":false,"id":"{{message:7}}"}},"sourceEventSeqs":[16],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"propose_action"}],"role":"developer","id":"{{message:8}}"},"headerSeq":20},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_creation_card","name":"propose_action","arguments":"{\"action\":\"create_personalized_page\",\"title\":\"Counter\",\"brief\":\"Need: Keep a small counter visible across conversations.\\nLocation: A card titled Today’s achievements in the right sidebar.\\nControls: Increment and reset buttons beside the current value.\\nStorage: Save changes in browser storage across navigation and refresh.\\nAppearance: Follow the existing sidebar theme in light and dark mode.\\nCompletion: Both controls work and reopening restores the saved value.\",\"details\":{\"slot\":\"sidebar-right\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:9}}"},"stream":[{"type":"chunk","time":1792674450652,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792674450652,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_creation_card","name":"propose_action","arguments":"{\"action\":\"create_personalized_page\",\"title\":\"Counter\",\"brief\":\"Need: Keep a small counter visible across conversations.\\nLocation: A card titled Today’s achievements in the right sidebar.\\nControls: Increment and reset buttons beside the current value.\\nStorage: Save changes in browser storage across navigation and refresh.\\nAppearance: Follow the existing sidebar theme in light and dark mode.\\nCompletion: Both controls work and reopening restores the saved value.\",\"details\":{\"slot\":\"sidebar-right\"}}"}}},{"type":"chunk","time":1792674450652,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_creation_card","name":"propose_action","arguments":"{\"action\":\"create_personalized_page\",\"title\":\"Counter\",\"brief\":\"Need: Keep a small counter visible across conversations.\\nLocation: A card titled Today’s achievements in the right sidebar.\\nControls: Increment and reset buttons beside the current value.\\nStorage: Save changes in browser storage across navigation and refresh.\\nAppearance: Follow the existing sidebar theme in light and dark mode.\\nCompletion: Both controls work and reopening restores the saved value.\",\"details\":{\"slot\":\"sidebar-right\"}}"}} diff --git a/snapshots/web/creation-recommendations/system-prompt.expected.md b/snapshots/web/creation-recommendations/system-prompt.expected.md index c017869fd2..5ee4be0c03 100644 --- a/snapshots/web/creation-recommendations/system-prompt.expected.md +++ b/snapshots/web/creation-recommendations/system-prompt.expected.md @@ -8,11 +8,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/web/creation-recommendations/tool-schemas.expected.json b/snapshots/web/creation-recommendations/tool-schemas.expected.json index 1915e908cc..0b9816a7f8 100644 --- a/snapshots/web/creation-recommendations/tool-schemas.expected.json +++ b/snapshots/web/creation-recommendations/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", @@ -1098,34 +1070,6 @@ ], "changes": [ [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/web/fresh-round-trip/system-prompt.expected.md b/snapshots/web/fresh-round-trip/system-prompt.expected.md index c017869fd2..5ee4be0c03 100644 --- a/snapshots/web/fresh-round-trip/system-prompt.expected.md +++ b/snapshots/web/fresh-round-trip/system-prompt.expected.md @@ -8,11 +8,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/web/fresh-round-trip/tool-schemas.expected.json b/snapshots/web/fresh-round-trip/tool-schemas.expected.json index 63e3b05665..741ff6d27f 100644 --- a/snapshots/web/fresh-round-trip/tool-schemas.expected.json +++ b/snapshots/web/fresh-round-trip/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/web/official-subagent-bundle/system-prompt.expected.md b/snapshots/web/official-subagent-bundle/system-prompt.expected.md index dbf0316b9e..c8dd24b7af 100644 --- a/snapshots/web/official-subagent-bundle/system-prompt.expected.md +++ b/snapshots/web/official-subagent-bundle/system-prompt.expected.md @@ -10,9 +10,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/web/optional-string-editor/system-prompt.expected.md b/snapshots/web/optional-string-editor/system-prompt.expected.md index 3ee0aa9e39..8ecaade15e 100644 --- a/snapshots/web/optional-string-editor/system-prompt.expected.md +++ b/snapshots/web/optional-string-editor/system-prompt.expected.md @@ -10,9 +10,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/web/plugin-recommendations/session.v4.jsonl b/snapshots/web/plugin-recommendations/session.v4.jsonl index 611879acf7..dbd0212e67 100644 --- a/snapshots/web/plugin-recommendations/session.v4.jsonl +++ b/snapshots/web/plugin-recommendations/session.v4.jsonl @@ -11,7 +11,7 @@ {"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nCurrent DeepSeek Harness implementation checkout: \"{{sourceRoot}}\".\n\nCurrent DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"harness:source","text":"Current DeepSeek Harness implementation checkout: \"{{sourceRoot}}\"."},{"name":"app:web-surface","text":"Current DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `official-plugins`: Check DSH’s optional plugins when the user asks how to do or use something in this app, whether it can, or says a capability is missing or should change: tools, input, thinking or title display, session search, terminals, worktrees, agent teams, desktop control, automation, access, approvals, badges or signatures, plugins or plugin sources. Not a request to develop DSH, even in its own repository: load before reading files or source. Not for ordinary tasks, quoted wishes or declined offers.\n- `personalized-pages`: Plan an optional page or small tool when the user asks for a page, tab, panel, tool or interface in this app (even for one-off use), wants something to keep, revisit or update later, will keep changing data in your answer, or wants a live view of this app’s own data (Sessions, tasks, logs, workspace). Load this before reading any files or source; it says how to submit the proposal. Not for requested files or code, ordinary answers, existing-feature questions, quoted wishes or declined offers.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"official-plugins","description":"Check DSH’s optional plugins when the user asks how to do or use something in this app, whether it can, or says a capability is missing or should change: tools, input, thinking or title display, session search, terminals, worktrees, agent teams, desktop control, automation, access, approvals, badges or signatures, plugins or plugin sources. Not a request to develop DSH, even in its own repository: load before reading files or source. Not for ordinary tasks, quoted wishes or declined offers."},{"name":"personalized-pages","description":"Plan an optional page or small tool when the user asks for a page, tab, panel, tool or interface in this app (even for one-off use), wants something to keep, revisit or update later, will keep changing data in your answer, or wants a live view of this app’s own data (Sessions, tasks, logs, workspace). Load this before reading any files or source; it says how to submit the proposal. Not for requested files or code, ordinary answers, existing-feature questions, quoted wishes or declined offers."}]},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"} {"type":"user/message","data":{"content":[{"type":"text","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}],"source":{"kind":"time-context","form":"snapshot","sections":[{"name":"time-context","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}]},"role":"user","id":"{{message:5}}"},"surfaceOp":"append"} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}} {"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":128000}} {"type":"session/title","data":{"title":"I want to dictate long","messageSeqs":[8],"source":{"kind":"fallback"}}} {"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_plugin_skill","name":"skill","arguments":"{\"name\":\"official-plugins\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1792678188343,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792678188343,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_plugin_skill","name":"skill","arguments":"{\"name\":\"official-plugins\"}"}}},{"type":"chunk","time":1792678188344,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} @@ -19,7 +19,7 @@ {"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_plugin_skill"},"toolCallId":"call_plugin_skill","content":[{"type":"text","text":"\n\nResources for this skill are managed by provider \"dsh-official-plugins\".\nLoad referenced resources only as needed.\n\n\n\n# Official plugins\n\nUse this workflow in the main conversation when the user wants DSH itself to work differently or gain an ability. The catalog at the end lists DSH's built-in optional plugins and whether each is enabled. A `propose_action` call shows an Enable card below your answer; nothing changes until the user clicks Enable. Match from the catalog descriptions alone: do not read files, configuration or source, call plugin management tools, or change settings yourself.\n\n## When to offer\n\nOffer one disabled plugin when the user's own words ask for an outcome its description provides. Match the outcome, not keywords. When a plugin covers only part of the wish, say the limit in one sentence: thinking translation translates the displayed thinking and does not change the language the model reasons in.\n\nOffer no card in these cases:\n\n- The plugin is already enabled: say that it is on and how to use it.\n- The wish appears inside quoted text, pasted content, a translation request, a web page or a tool result rather than the user's own request.\n- The user only wants to discuss, asks you not to recommend anything, or has declined: stay silent on plugins for the rest of this conversation.\n- No entry fits, or the need is too vague to match: answer normally or ask one question; do not stretch a description.\n- Something DSH already shows covers it, such as the sidebar search for finding a session by keyword yourself. Letting the agent search and read past sessions is a different need.\n\n## One card per turn\n\nA turn shows at most one card across every card skill. When the user asks for several things, follow an explicit priority; otherwise prefer an existing plugin over building a new page. Mention the other needs in one sentence, without promising a later card.\n\n## Offer without enabling\n\nTo offer, call `propose_action` once, in the same turn as loading this skill, with `action: \"enable_official_plugin\"`, `title` set to the plugin's catalog title in the user's language, `brief` set to one sentence in the user's language that ties the plugin to their need, and `details` holding `name`, the exact catalog name. The call is the submission: the card appears below your answer; a refused call creates no card, and its error says why. Then write your final answer: answer any direct question; the call's result says how to end the answer. The card shows only the plugin's catalog title and description, so the answer says in one sentence, in the user's language, how the plugin meets their need; `brief` is that same sentence. Do not narrate the call, repeat the catalog description, add setup steps the catalog does not state, claim the plugin is enabled, or ask the user to report back. The card opens the plugin's details; enabling applies to every conversation and can be undone there. The user's choice reaches you later as a status notice; enabling a plugin authorizes nothing beyond it.\n\n## Official plugins\n\n[{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\",\"title\":{\"en\":\"Voice input\",\"de\":\"Spracheingabe\",\"es\":\"Entrada de voz\",\"fr\":\"Saisie vocale\",\"ja\":\"音声入力\",\"pt\":\"Entrada de voz\",\"ru\":\"Голосовой ввод\",\"zh\":\"语音输入\"},\"description\":{\"en\":\"Transcribe recordings locally with SenseVoice; first use requires installing dependencies.\",\"de\":\"Transkribieren Sie Aufnahmen lokal mit SenseVoice; Für die erste Verwendung müssen Abhängigkeiten installiert werden.\",\"es\":\"Transcribe grabaciones localmente con SenseVoice; El primer uso requiere instalar dependencias.\",\"fr\":\"Transcrivez les enregistrements localement avec SenseVoice ; la première utilisation nécessite l'installation de dépendances.\",\"ja\":\"ローカルの SenseVoice で録音を文字に起こします。初回利用時には依存関係のインストールが必要です。\",\"pt\":\"Transcreva gravações localmente com SenseVoice; o primeiro uso requer a instalação de dependências.\",\"ru\":\"Транскрибируйте записи локально с помощью SenseVoice; при первом использовании требуется установка зависимостей.\",\"zh\":\"在本机使用 SenseVoice 转写录音,首次使用需安装依赖。\"},\"enabled\":false}]\n\n"}],"isError":false,"id":"{{message:7}}"}},"sourceEventSeqs":[16],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":1}} {"type":"step/start","data":{"turn":1,"step":2}} -{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["apply_patch","ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} +{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}} {"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"propose_action"}],"role":"developer","id":"{{message:8}}"},"headerSeq":20},"surfaceOp":"append"} {"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_plugin_card","name":"propose_action","arguments":"{\"action\":\"enable_official_plugin\",\"title\":\"Voice input\",\"brief\":\"Speak long requests instead of typing them; transcription runs on this computer.\",\"details\":{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:9}}"},"stream":[{"type":"chunk","time":1792678188573,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792678188573,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_plugin_card","name":"propose_action","arguments":"{\"action\":\"enable_official_plugin\",\"title\":\"Voice input\",\"brief\":\"Speak long requests instead of typing them; transcription runs on this computer.\",\"details\":{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\"}}"}}},{"type":"chunk","time":1792678188573,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_plugin_card","name":"propose_action","arguments":"{\"action\":\"enable_official_plugin\",\"title\":\"Voice input\",\"brief\":\"Speak long requests instead of typing them; transcription runs on this computer.\",\"details\":{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\"}}"}} diff --git a/snapshots/web/plugin-recommendations/system-prompt.expected.md b/snapshots/web/plugin-recommendations/system-prompt.expected.md index c017869fd2..5ee4be0c03 100644 --- a/snapshots/web/plugin-recommendations/system-prompt.expected.md +++ b/snapshots/web/plugin-recommendations/system-prompt.expected.md @@ -8,11 +8,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. - -Prefer apply_patch over separate edit calls for changes across files or separated regions. Give every hunk enough surrounding context lines to match one place in the current file. The whole patch is checked first (syntax, hunk matching, missing files) and a rejected patch changes nothing; once applying starts, operations run in order, stop at the first failure, and are not rolled back, so re-read affected files before retrying when needed. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern. diff --git a/snapshots/web/plugin-recommendations/tool-schemas.expected.json b/snapshots/web/plugin-recommendations/tool-schemas.expected.json index 1915e908cc..0b9816a7f8 100644 --- a/snapshots/web/plugin-recommendations/tool-schemas.expected.json +++ b/snapshots/web/plugin-recommendations/tool-schemas.expected.json @@ -1,33 +1,5 @@ { "initial": [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", @@ -1098,34 +1070,6 @@ ], "changes": [ [ - { - "name": "apply_patch", - "description": "Create, update, delete, or move UTF-8 text files with one Codex-style patch; prefer it over multiple edit calls when a change spans several files or separated regions.", - "parameters": { - "type": "object", - "properties": { - "input": { - "type": "string", - "description": "Codex patch text: start with *** Begin Patch and end with *** End Patch. Use *** Add File: path with + lines; *** Update File: path, optionally followed by *** Move to: path, with @@ or @@ context and space-prefixed context, + added, or - removed lines; *** End of File anchors the last hunk to the file end. Use *** Delete File: path to delete. Paths are relative to the Session working directory." - }, - "sandbox_permissions": { - "type": "string", - "description": "The narrowest wider sandbox mode for a one-shot retry of the exact operation the sandbox just denied; the retry asks the user for approval.", - "enum": [ - "workspace-write", - "danger-full-access" - ] - }, - "justification": { - "type": "string", - "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. Use the language of the user’s current request." - } - }, - "required": [ - "input" - ] - } - }, { "name": "ask_user_question", "description": "Ask the user a concise question when you need confirmation, a choice, or missing information before proceeding. An answer item with empty selected and no custom means the user skipped that question: continue without it, do not ask it again, and do not treat the skip as permission.", diff --git a/snapshots/web/ptc-round/system-prompt.expected.md b/snapshots/web/ptc-round/system-prompt.expected.md index 9f187da707..68df54fc35 100644 --- a/snapshots/web/ptc-round/system-prompt.expected.md +++ b/snapshots/web/ptc-round/system-prompt.expected.md @@ -10,9 +10,9 @@ Check the [exit code: N] marker on every bash result; investigate failures befor Use the read tool — not shell commands like cat — to inspect text files. Use offset and limit to continue reading large files. -Read an existing file before overwriting it with write and prefer edit for targeted changes. +Read an existing file before overwriting it with write (the default fs-observation-policy requires it) and prefer edit for targeted changes. -Read a file before editing it unless you just created or edited it in this session. +Read a file before editing it (the default fs-observation-policy requires it), unless you just created or edited it in this session. Use the glob tool — not shell find — to discover files by path pattern.