fix(permission): tighten Auto review validation
This commit is contained in:
1 parent
64b05dacdd
commit
1ec5f21e82
34 files changed
+94
-120
No files matched your search
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-28-auto-review.md
|
||||
2026-08-28-auto-review.md: 1de85c716e2cc16d17a594e48632cbcc4a880173
|
||||
2026-08-28-auto-review.zh.md: dc13c4dde0af9d430cc7e2b55f188e6378bd41c0
|
||||
2026-08-28-auto-review.md: fc27d04acd06912f5eecb22fe2b59d66fcabff50
|
||||
2026-08-28-auto-review.zh.md: a48dfcdf1974a7dff870c31a18119b0b206f8252
|
||||
@@ -10,7 +10,7 @@ The permission preset layer names sandbox and approval-policy combinations, but
|
||||
|
||||
## Decision
|
||||
|
||||
The shipped Web application offers `Auto review` as the fourth complete current-session permission mode. Its durable identity is `permission/preset:auto`, and its execution knobs are exactly `danger-full-access` plus approval policy `never`. [`@deepseek-ai/dsh-auto-review`](../../../../packages/interaction/auto-review/README.md) owns the additional authorization behavior; [`dsh-permission-presets`](../../../../packages/interaction/permission-presets/README.md) owns the fixed Auto identity, bundle, presentation, `registerAuto(admit)` hook, canonical preset write path, and fail-closed admission on selection or restore. It does not expose a generic preset-contribution API.
|
||||
The shipped Web application offers `Auto review` as the fourth complete current-session permission mode. Its durable identity is `permission/preset:auto`, and its execution knobs are exactly `danger-full-access` plus approval policy `never`. [`@deepseek-ai/dsh-auto-review`](../../../../packages/interaction/auto-review/README.md) owns the additional authorization behavior; [`dsh-permission-presets`](../../../../packages/interaction/permission-presets/README.md) owns the fixed Auto identity, bundle, `registerAuto(admit)` hook, canonical preset write path, and fail-closed admission on selection or restore. The shipped Web client locale dictionaries own the fixed Auto label and description. The permission service does not expose a generic preset-contribution API.
|
||||
|
||||
Auto is experimental because an LLM decision is probabilistic. An allowed call starts immediately with full host access and no later human confirmation. A reviewer can therefore allow an action that should have been denied or deny a valid action, and each review adds provider latency and token use.
|
||||
|
||||
|
||||
@@ -10,7 +10,7 @@ Status: implemented
|
||||
|
||||
## 决策
|
||||
|
||||
shipped Web 应用把 `Auto review` 作为第四个完整的当前会话权限模式。它的持久身份是 `permission/preset:auto`,执行旋钮精确等于 `danger-full-access` 加审批策略 `never`。[`@deepseek-ai/dsh-auto-review`](../../../../packages/interaction/auto-review/README.zh.md)拥有额外授权行为;[`dsh-permission-presets`](../../../../packages/interaction/permission-presets/README.zh.md)拥有固定 Auto 身份、组合、展示、`registerAuto(admit)` 钩子、规范预设写入路径,以及在选择或恢复时以拒绝方式关闭的准入。它不暴露通用预设 contribution API。
|
||||
shipped Web 应用把 `Auto review` 作为第四个完整的当前会话权限模式。它的持久身份是 `permission/preset:auto`,执行旋钮精确等于 `danger-full-access` 加审批策略 `never`。[`@deepseek-ai/dsh-auto-review`](../../../../packages/interaction/auto-review/README.zh.md)拥有额外授权行为;[`dsh-permission-presets`](../../../../packages/interaction/permission-presets/README.zh.md)拥有固定 Auto 身份、组合、`registerAuto(admit)` 钩子、规范预设写入路径,以及在选择或恢复时以拒绝方式关闭的准入。shipped Web 客户端的 locale 字典拥有固定的 Auto label 与 description。权限服务不暴露通用预设 contribution API。
|
||||
|
||||
Auto 是实验功能,因为 LLM 决定具有概率性。获准调用会立刻以完整宿主访问权限开始,之后没有人工确认。因此,reviewer 可能放行本应拒绝的动作或拒绝有效动作,而且每次审查都会增加提供方延迟与 token 用量。
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write docs/config-catalog.md
|
||||
config-catalog.md: d45e49e43f6bbc06337baad4d67fe9d1dba74b66
|
||||
config-catalog.zh.md: a089971771e5572d49879d8ac9b8e8bb3892e453
|
||||
config-catalog.md: e7272bbfe0f08314295108eac982d0583b568465
|
||||
config-catalog.zh.md: 78a1a794f902c7222b92f91423737f9fd7d84a5e
|
||||
@@ -1541,7 +1541,7 @@ export interface PresetSpec {
|
||||
|
||||
Depends on: [`ApprovalPolicy`](subsystems/approval.md) · [`SandboxMode`](subsystems/sandbox.md)
|
||||
|
||||
Source: [`packages/interaction/permission-presets/src/index.ts:157`](../packages/interaction/permission-presets/src/index.ts)
|
||||
Source: [`packages/interaction/permission-presets/src/index.ts:155`](../packages/interaction/permission-presets/src/index.ts)
|
||||
|
||||
<a id="deepseek-aidsh-persona"></a>
|
||||
|
||||
|
||||
@@ -1543,7 +1543,7 @@ export interface PresetSpec {
|
||||
|
||||
依赖:[`ApprovalPolicy`](subsystems/approval.zh.md) · [`SandboxMode`](subsystems/sandbox.zh.md)
|
||||
|
||||
来源:[`packages/interaction/permission-presets/src/index.ts:157`](../packages/interaction/permission-presets/src/index.ts)
|
||||
来源:[`packages/interaction/permission-presets/src/index.ts:155`](../packages/interaction/permission-presets/src/index.ts)
|
||||
|
||||
<a id="deepseek-aidsh-persona"></a>
|
||||
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write docs/module-graph.md
|
||||
module-graph.md: ab988c74b02cfe00167d4ce8babd228c0104976e
|
||||
module-graph.zh.md: 0cc05ec82d0c3bc4e3a201221be5201deae46067
|
||||
module-graph.md: 8f29a5de39eb667f78a4833c1962f4d649d1416c
|
||||
module-graph.zh.md: 1054f0f8bef00e820cc3f3675588888b1e4837f6
|
||||
@@ -914,7 +914,6 @@ flowchart TD
|
||||
pkg_host_plugin_inventory --> pkg_typert_protocol
|
||||
pkg_auto_review --> pkg_agent
|
||||
pkg_auto_review --> pkg_agent_instructions
|
||||
pkg_auto_review --> pkg_invariants
|
||||
pkg_auto_review --> pkg_llm
|
||||
pkg_auto_review --> pkg_permission_presets
|
||||
pkg_auto_review --> pkg_session
|
||||
@@ -1368,7 +1367,7 @@ flowchart TD
|
||||
| [`compaction-tool-result-pruner`](../packages/compaction/compaction-tool-result-pruner) | `compaction` | [`compaction`](../packages/compaction/compaction), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) |
|
||||
| [`tool-cordis`](../packages/extensions/tool-cordis) | `extensions` | [`agent`](../packages/core/agent), [`cordis-host-runner`](../packages/extensions/cordis-host-runner), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`host-plugin-inventory`](../packages/host/plugin-inventory) | `host` | [`agent-presets`](../packages/preset/agent-presets), [`brand`](../packages/util/brand), [`typert-protocol`](../packages/typert/protocol) |
|
||||
| [`auto-review`](../packages/interaction/auto-review) | `interaction` | [`agent`](../packages/core/agent), [`agent-instructions`](../packages/context/agent-instructions), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`permission-presets`](../packages/interaction/permission-presets), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`auto-review`](../packages/interaction/auto-review) | `interaction` | [`agent`](../packages/core/agent), [`agent-instructions`](../packages/context/agent-instructions), [`llm`](../packages/llm/llm), [`permission-presets`](../packages/interaction/permission-presets), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`tool-bash`](../packages/shell/tool-bash) | `shell` | [`agent`](../packages/core/agent), [`jobs`](../packages/jobs/jobs), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`shell`](../packages/shell/shell), [`shell-env`](../packages/shell/shell-env), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) |
|
||||
| [`tool-pwsh`](../packages/shell/tool-pwsh) | `shell` | [`agent`](../packages/core/agent), [`jobs`](../packages/jobs/jobs), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`shell`](../packages/shell/shell), [`shell-env`](../packages/shell/shell-env), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) |
|
||||
| [`webhook`](../packages/webhook/webhook) | `webhook` | [`agent`](../packages/core/agent), [`agent-default-model`](../packages/core/agent-default-model), [`agent-presets`](../packages/preset/agent-presets), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`permission-presets`](../packages/interaction/permission-presets), [`session`](../packages/core/session), [`session-title`](../packages/session/session-title), [`workspace`](../packages/workspace/workspace) |
|
||||
|
||||
@@ -916,7 +916,6 @@ flowchart TD
|
||||
pkg_host_plugin_inventory --> pkg_typert_protocol
|
||||
pkg_auto_review --> pkg_agent
|
||||
pkg_auto_review --> pkg_agent_instructions
|
||||
pkg_auto_review --> pkg_invariants
|
||||
pkg_auto_review --> pkg_llm
|
||||
pkg_auto_review --> pkg_permission_presets
|
||||
pkg_auto_review --> pkg_session
|
||||
@@ -1370,7 +1369,7 @@ flowchart TD
|
||||
| [`compaction-tool-result-pruner`](../packages/compaction/compaction-tool-result-pruner) | `compaction` | [`compaction`](../packages/compaction/compaction), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) |
|
||||
| [`tool-cordis`](../packages/extensions/tool-cordis) | `extensions` | [`agent`](../packages/core/agent), [`cordis-host-runner`](../packages/extensions/cordis-host-runner), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) |
|
||||
| [`host-plugin-inventory`](../packages/host/plugin-inventory) | `host` | [`agent-presets`](../packages/preset/agent-presets), [`brand`](../packages/util/brand), [`typert-protocol`](../packages/typert/protocol) |
|
||||
| [`auto-review`](../packages/interaction/auto-review) | `interaction` | [`agent`](../packages/core/agent), [`agent-instructions`](../packages/context/agent-instructions), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`permission-presets`](../packages/interaction/permission-presets), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`auto-review`](../packages/interaction/auto-review) | `interaction` | [`agent`](../packages/core/agent), [`agent-instructions`](../packages/context/agent-instructions), [`llm`](../packages/llm/llm), [`permission-presets`](../packages/interaction/permission-presets), [`session`](../packages/core/session), [`tools`](../packages/core/tools) |
|
||||
| [`tool-bash`](../packages/shell/tool-bash) | `shell` | [`agent`](../packages/core/agent), [`jobs`](../packages/jobs/jobs), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`shell`](../packages/shell/shell), [`shell-env`](../packages/shell/shell-env), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) |
|
||||
| [`tool-pwsh`](../packages/shell/tool-pwsh) | `shell` | [`agent`](../packages/core/agent), [`jobs`](../packages/jobs/jobs), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`shell`](../packages/shell/shell), [`shell-env`](../packages/shell/shell-env), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) |
|
||||
| [`webhook`](../packages/webhook/webhook) | `webhook` | [`agent`](../packages/core/agent), [`agent-default-model`](../packages/core/agent-default-model), [`agent-presets`](../packages/preset/agent-presets), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`permission-presets`](../packages/interaction/permission-presets), [`session`](../packages/core/session), [`session-title`](../packages/session/session-title), [`workspace`](../packages/workspace/workspace) |
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write docs/subsystems/permission-presets.md
|
||||
permission-presets.md: b9496303dad03401a388814201111971b0f7506a
|
||||
permission-presets.zh.md: 5a528c634a39daca0ea163706e14e5c1025375f1
|
||||
permission-presets.md: e3156e4fd47f8a0f5d5035e6f57ac471ea8c7d0c
|
||||
permission-presets.zh.md: d539cabfc01d9e876fa715a599b948461be59240
|
||||
@@ -46,7 +46,7 @@ The service requires a confining `ctx.shell` executor and `ctx.approval`, and mi
|
||||
|
||||
## Fixed current-session Auto registration
|
||||
|
||||
The Auto integration calls `registerAuto(admit)` for its effect lifetime. This service fixes the `auto` identity, its `danger-full-access` plus `never` bundle, and its client label and description; callers cannot publish another preset through a generic contribution API. Auto appears after configured presets, never enters the `permission.defaultPreset` settings schema, and disappears when the effect is disposed. The synchronous `admit` callback runs before Auto selection mutates the Session and before a stored Auto Session publishes, so a missing or closing integration does not rewrite the durable identity.
|
||||
The Auto integration calls `registerAuto(admit)` for its effect lifetime. This service fixes the `auto` identity and its `danger-full-access` plus `never` bundle; the shipped client locale dictionaries own Auto's label and description, while configured preset presentation remains Host-owned. Callers cannot publish another preset through a generic contribution API. Auto appears after configured presets, never enters the `permission.defaultPreset` settings schema, and disappears when the effect is disposed. The synchronous `admit` callback runs before Auto selection mutates the Session and before a stored Auto Session publishes, so a missing or closing integration does not rewrite the durable identity.
|
||||
|
||||
Registering or removing Auto emits the payload-free `permission-presets/catalog-changed` notification. Process consumers subscribe before calling `catalog()`, then re-read the complete selectable catalog after each notification. The `permissions` Session projection contains only `currentValue`, so catalog changes append no Session event, publish no Session projection frame, and leave the Session sequence unchanged.
|
||||
|
||||
|
||||
@@ -46,7 +46,7 @@ interface Config {
|
||||
|
||||
## 固定的当前会话 Auto 注册
|
||||
|
||||
Auto integration 会在自身 effect 生命周期内调用 `registerAuto(admit)`。本服务固定 `auto` 身份、`danger-full-access` 加 `never` 的组合,以及客户端 label 与 description;调用方不能通过通用 contribution API 发布其他预设。Auto 排列在配置预设之后,绝不会进入 `permission.defaultPreset` 设置 schema,并在 effect dispose 时消失。同步 `admit` 回调会在 Auto 选择修改 Session 前,以及存储的 Auto Session 发布前运行,因此 integration 缺失或正在关闭时不会改写持久身份。
|
||||
Auto integration 会在自身 effect 生命周期内调用 `registerAuto(admit)`。本服务固定 `auto` 身份以及 `danger-full-access` 加 `never` 的组合;shipped 客户端的 locale 字典拥有 Auto 的 label 与 description,而配置预设的展示信息仍归 Host 所有。调用方不能通过通用 contribution API 发布其他预设。Auto 排列在配置预设之后,绝不会进入 `permission.defaultPreset` 设置 schema,并在 effect dispose 时消失。同步 `admit` 回调会在 Auto 选择修改 Session 前,以及存储的 Auto Session 发布前运行,因此 integration 缺失或正在关闭时不会改写持久身份。
|
||||
|
||||
注册或移除 Auto 会发出无 payload 的 `permission-presets/catalog-changed` 通知。进程级消费方先订阅,再调用 `catalog()`;每次收到通知后重新读取完整的可选目录。`permissions` Session 投影只包含 `currentValue`,因此目录变化不会追加 Session 事件、发布 Session 投影帧或改变 Session 序列。
|
||||
|
||||
|
||||
@@ -80,9 +80,6 @@
|
||||
{
|
||||
"path": "../../settings/settings"
|
||||
},
|
||||
{
|
||||
"path": "../../runtime-diagnostics/invariants"
|
||||
},
|
||||
{
|
||||
"path": "../ui-settings"
|
||||
},
|
||||
|
||||
@@ -5,12 +5,10 @@ import type { ConnectionHandle } from '@deepseek-ai/dsh-client-connection/client
|
||||
import { createSnapshotStore, type SnapshotStore } from '@deepseek-ai/dsh-client-store'
|
||||
import type { PermissionCatalog } from '@deepseek-ai/dsh-permission-presets/client'
|
||||
|
||||
/** Observable lifecycle of the current Host generation's complete catalog. */
|
||||
/** Observable value and latest read error for the current Host generation. */
|
||||
export interface PermissionCatalogState {
|
||||
/** Last complete catalog for this generation, or null before one succeeds. */
|
||||
value: PermissionCatalog | null
|
||||
/** Current read lifecycle; error may coexist with a retained complete value. */
|
||||
status: 'idle' | 'loading' | 'ready' | 'error'
|
||||
/** Current-generation read failure text, when present. */
|
||||
error: string | null
|
||||
}
|
||||
@@ -20,7 +18,6 @@ export class PermissionCatalogDirectory {
|
||||
/** Complete snapshot consumed by both the slash popup and composer seat. */
|
||||
readonly store: SnapshotStore<PermissionCatalogState> = createSnapshotStore({
|
||||
value: null,
|
||||
status: 'idle',
|
||||
error: null,
|
||||
})
|
||||
|
||||
@@ -104,7 +101,7 @@ export class PermissionCatalogDirectory {
|
||||
this.generationId = generationId
|
||||
++this.epoch
|
||||
this.pending = undefined
|
||||
this.store.set({ value: null, status: 'idle', error: null })
|
||||
this.store.set({ value: null, error: null })
|
||||
if (generationId !== undefined) this.startRead(generationId)
|
||||
}
|
||||
|
||||
@@ -112,18 +109,17 @@ export class PermissionCatalogDirectory {
|
||||
private startRead(generationId: number): void {
|
||||
const epoch = ++this.epoch
|
||||
const retained = this.store.getSnapshot().value
|
||||
this.store.set({ value: retained, status: 'loading', error: null })
|
||||
this.store.set({ value: retained, error: null })
|
||||
const operation = this.ctx.remote.permissionPresets.catalog()
|
||||
.then((result) => {
|
||||
if (!result.ok) throw new Error(`${result.error.code}: ${result.error.message}`)
|
||||
if (!this.accepts(epoch, generationId)) return
|
||||
this.store.set({ value: result.value, status: 'ready', error: null })
|
||||
this.store.set({ value: result.value, error: null })
|
||||
})
|
||||
.catch((error: unknown) => {
|
||||
if (!this.accepts(epoch, generationId)) return
|
||||
this.store.set({
|
||||
value: this.store.getSnapshot().value,
|
||||
status: 'error',
|
||||
error: error instanceof Error ? error.message : String(error),
|
||||
})
|
||||
})
|
||||
|
||||
@@ -86,7 +86,7 @@ describe('PermissionCatalogDirectory', () => {
|
||||
first.resolve({ ok: true, value: FIRST })
|
||||
await first.promise
|
||||
await Promise.resolve()
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: SECOND, status: 'ready', error: null })
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: SECOND, error: null })
|
||||
directory.dispose()
|
||||
})
|
||||
|
||||
@@ -114,10 +114,9 @@ describe('PermissionCatalogDirectory', () => {
|
||||
|
||||
response = 'rpc-failure'
|
||||
remote.emit('permission-presets/catalog-changed', [])
|
||||
await vi.waitFor(() => { expect(directory.store.getSnapshot().status).toBe('error') })
|
||||
await vi.waitFor(() => { expect(directory.store.getSnapshot().error).not.toBeNull() })
|
||||
expect(directory.store.getSnapshot()).toEqual({
|
||||
value: FIRST,
|
||||
status: 'error',
|
||||
error: 'catalog/unavailable: catalog unavailable',
|
||||
})
|
||||
|
||||
@@ -175,16 +174,16 @@ describe('PermissionCatalogDirectory', () => {
|
||||
const directory = new PermissionCatalogDirectory(ctx)
|
||||
|
||||
generation.set(undefined)
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: null, status: 'idle', error: null })
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: null, error: null })
|
||||
directory.refresh()
|
||||
await expect(directory.load()).rejects.toThrow(/no active Host connection/)
|
||||
oldRead.reject(new Error('old Host failed'))
|
||||
await expect(oldRead.promise).rejects.toThrow('old Host failed')
|
||||
await Promise.resolve()
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: null, status: 'idle', error: null })
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: null, error: null })
|
||||
|
||||
generation.set(2)
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: null, status: 'loading', error: null })
|
||||
expect(directory.store.getSnapshot()).toEqual({ value: null, error: null })
|
||||
newRead.resolve({ ok: true, value: SECOND })
|
||||
await expect(directory.load()).resolves.toEqual(SECOND)
|
||||
expect(calls).toBe(2)
|
||||
|
||||
@@ -40,7 +40,6 @@ function setup(options: {
|
||||
})
|
||||
const catalog = createSnapshotStore<PermissionCatalogState>({
|
||||
value: options.catalog === undefined ? CATALOG : options.catalog,
|
||||
status: 'ready',
|
||||
error: null,
|
||||
})
|
||||
const useProjection = (_key: string, selector?: (value: unknown) => unknown) =>
|
||||
@@ -170,7 +169,7 @@ describe('PermissionSelect', () => {
|
||||
cleanup()
|
||||
const vanished = setup()
|
||||
fireEvent.click(trigger())
|
||||
act(() => { vanished.catalog.set({ value: null, status: 'idle', error: null }) })
|
||||
act(() => { vanished.catalog.set({ value: null, error: null }) })
|
||||
expect(vanished.view.container.innerHTML).toBe('')
|
||||
|
||||
cleanup()
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/interaction/auto-review/README.md
|
||||
README.md: 1c65bb2b9f7bb1649e2784d381dad521e34628f7
|
||||
README.zh.md: c13c8eb352bdec66db82c2070bd0438d86061130
|
||||
README.md: f205c631416a789b18b2a649106ed26f4116e84a
|
||||
README.zh.md: 157c105b5bd59f01627c4aafc062fee51d777aa2
|
||||
@@ -37,7 +37,9 @@ The shipped Web bundle mounts the integration as one ordinary Cordis row after t
|
||||
name: '@deepseek-ai/dsh-auto-review'
|
||||
```
|
||||
|
||||
The plugin calls the permission service's fixed `registerAuto(admit)` hook for its effect lifetime. The permission service owns the reserved identity, Full access knob bundle, and presentation; users can select Auto for the current session through the Web picker or `/permission auto`, and it never enters `permission.defaultPreset` choices.
|
||||
The plugin calls the permission service's fixed `registerAuto(admit)` hook for its effect lifetime. The permission service owns the reserved identity and Full access knob bundle, while the shipped Web client locale dictionaries own the fixed Auto label and description. Users can select Auto for the current session through the Web picker or `/permission auto`, and it never enters `permission.defaultPreset` choices.
|
||||
|
||||
No runtime invariant companion is published because the root plugin's single effect owns authorization and teardown, leaving no independent observation that can diverge from that lifecycle.
|
||||
|
||||
### Review and failure behavior
|
||||
|
||||
@@ -75,7 +77,6 @@ Publication and teardown are fail-closed. A persisted Auto session cannot publis
|
||||
| File | Role |
|
||||
|---|---|
|
||||
| [`src/index.ts`](src/index.ts) | Fixed Auto registration, five-section request, strict decision parser, pre-execute listener, and teardown |
|
||||
| [`src/invariant.ts`](src/invariant.ts) | Invariant companion for this stateless integration |
|
||||
| [`tests/auto-review.spec.ts`](tests/auto-review.spec.ts) | Logged-input, decision, cancellation, native/PTC, restore, and disposal behavior |
|
||||
| [`tests/auto-review.e2e.ts`](tests/auto-review.e2e.ts) | Opt-in 22-call real-model certification across eight semantic pairs, both execution paths, and all shipped models |
|
||||
|
||||
|
||||
@@ -37,7 +37,9 @@ shipped Web 组合包会在基础权限、Session、LLM 与 Tool 服务可用后
|
||||
name: '@deepseek-ai/dsh-auto-review'
|
||||
```
|
||||
|
||||
插件会在自身 effect 生命周期内调用权限服务固定的 `registerAuto(admit)` 钩子。权限服务拥有保留身份、Full access 旋钮组合与展示信息;用户可以通过 Web 选择器或 `/permission auto` 为当前会话选择 Auto,而它绝不会进入 `permission.defaultPreset` 的候选项。
|
||||
插件会在自身 effect 生命周期内调用权限服务固定的 `registerAuto(admit)` 钩子。权限服务拥有保留身份与 Full access 旋钮组合,而 shipped Web 客户端的 locale 字典拥有固定的 Auto label 与 description。用户可以通过 Web 选择器或 `/permission auto` 为当前会话选择 Auto,而它绝不会进入 `permission.defaultPreset` 的候选项。
|
||||
|
||||
本包不发布 runtime invariant 伴生插件,因为根插件的单个 effect 共同拥有授权与资源释放,不存在会与该生命周期发生分歧的独立观测。
|
||||
|
||||
### 审查与故障行为
|
||||
|
||||
@@ -75,7 +77,6 @@ Auto 拒绝使用固定模型可见消息,其中会指明被拒绝的工具并
|
||||
| 文件 | 职责 |
|
||||
|---|---|
|
||||
| [`src/index.ts`](src/index.ts) | 固定 Auto 注册、五分区请求、严格决定解析器、pre-execute 监听器与资源释放 |
|
||||
| [`src/invariant.ts`](src/invariant.ts) | 这一无状态集成的不变式伴生插件 |
|
||||
| [`tests/auto-review.spec.ts`](tests/auto-review.spec.ts) | 日志输入、决定、取消、原生/PTC、恢复与资源释放行为 |
|
||||
| [`tests/auto-review.e2e.ts`](tests/auto-review.e2e.ts) | 显式启用的 22-call 真实模型认证,覆盖八组语义配对、两条执行路径与全部 shipped 模型 |
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@deepseek-ai/dsh-auto-review",
|
||||
"description": "Per-tool LLM authorization review for the DeepSeek Harness Auto permission preset",
|
||||
"version": "0.1.2-alpha.2",
|
||||
"version": "0.1.2-alpha.5",
|
||||
"publishConfig": {
|
||||
"access": "public"
|
||||
},
|
||||
@@ -18,23 +18,17 @@
|
||||
"types": "./lib/types/index.d.ts",
|
||||
"default": "./lib/index.js"
|
||||
},
|
||||
"./invariant": {
|
||||
"types": "./lib/types/invariant.d.ts",
|
||||
"default": "./lib/invariant.js"
|
||||
},
|
||||
"./src/*": "./src/*",
|
||||
"./package.json": "./package.json"
|
||||
},
|
||||
"files": [
|
||||
"lib/index.js",
|
||||
"lib/invariant.js",
|
||||
"lib/types/**/*.d.ts"
|
||||
],
|
||||
"license": "MIT",
|
||||
"peerDependencies": {
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-instructions": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-permission-presets": "workspace:^",
|
||||
"@deepseek-ai/dsh-session": "workspace:^",
|
||||
@@ -55,7 +49,6 @@
|
||||
"@deepseek-ai/dsh-fs-local": "workspace:^",
|
||||
"@deepseek-ai/dsh-fs-observation-policy": "workspace:^",
|
||||
"@deepseek-ai/dsh-fs-sandbox": "workspace:^",
|
||||
"@deepseek-ai/dsh-invariants": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm": "workspace:^",
|
||||
"@deepseek-ai/dsh-llm-deepseek": "workspace:^",
|
||||
"@deepseek-ai/dsh-permission-presets": "workspace:^",
|
||||
|
||||
@@ -395,6 +395,28 @@ function reviewUserText(snapshot: ReviewSnapshot): string {
|
||||
].join('\n\n')
|
||||
}
|
||||
|
||||
/** Count members in the raw top-level JSON object. */
|
||||
function topLevelMemberCount(text: string): number {
|
||||
const syntax = text.replace(/"(?:\\.|[^"\\])*"/gs, '')
|
||||
let depth = 0
|
||||
let count = 0
|
||||
for (const char of syntax) {
|
||||
switch (char) {
|
||||
case '{':
|
||||
case '[':
|
||||
depth += 1
|
||||
break
|
||||
case '}':
|
||||
case ']':
|
||||
depth -= 1
|
||||
break
|
||||
case ':':
|
||||
if (depth === 1) count += 1
|
||||
}
|
||||
}
|
||||
return count
|
||||
}
|
||||
|
||||
/** Parse the only three accepted reviewer JSON objects. */
|
||||
function parseDecision(text: string): AutoReviewDecision {
|
||||
const value: unknown = JSON.parse(text)
|
||||
@@ -403,6 +425,9 @@ function parseDecision(text: string): AutoReviewDecision {
|
||||
}
|
||||
const record = value as Record<string, unknown>
|
||||
const keys = Object.keys(record)
|
||||
if (topLevelMemberCount(text) !== keys.length) {
|
||||
throw new Error('auto-review: reviewer output repeats a JSON member')
|
||||
}
|
||||
if (record['decision'] === 'allow' && keys.length === 1) return { decision: 'allow' }
|
||||
if (record['decision'] === 'deny' && keys.length === 1) return { decision: 'deny' }
|
||||
if (record['decision'] === 'deny'
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
/** Package-owned invariant companion for `@deepseek-ai/dsh-auto-review`.
|
||||
* @module @deepseek-ai/dsh-auto-review/invariant
|
||||
*/
|
||||
|
||||
/* jscpd:ignore-start */
|
||||
import type { Context } from '@deepseek-ai/cordis'
|
||||
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
|
||||
|
||||
const PACKAGE_NAME = '@deepseek-ai/dsh-auto-review'
|
||||
|
||||
/** Cordis companion plugin name. */
|
||||
export const name = 'auto-review-invariant'
|
||||
/** Service required before the companion can reserve package ownership. */
|
||||
export const inject = ['invariants']
|
||||
|
||||
/**
|
||||
* No runtime invariant: the package owns no durable state; its effect closes
|
||||
* admission and drains every operation before its registrations disappear.
|
||||
*/
|
||||
const install: InvariantInstaller = () => {}
|
||||
|
||||
/**
|
||||
* Register this package's invariant companion.
|
||||
* @param ctx - Cordis context carrying the invariant service.
|
||||
* @returns the installed registration's disposer after setup succeeds.
|
||||
*/
|
||||
export const apply = (ctx: Context): Promise<() => void> =>
|
||||
Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
|
||||
/* jscpd:ignore-end */
|
||||
@@ -336,6 +336,22 @@ function reviewerRequest(options: GenerateOptions): boolean {
|
||||
&& source.plugin === 'dsh-auto-review'
|
||||
}
|
||||
|
||||
function topLevelMemberCount(text: string): number {
|
||||
const syntax = text.replace(/"(?:\\.|[^"\\])*"/gs, '')
|
||||
let depth = 0
|
||||
let count = 0
|
||||
for (const char of syntax) {
|
||||
if (char === '{' || char === '[') {
|
||||
depth += 1
|
||||
} else if (char === '}' || char === ']') {
|
||||
depth -= 1
|
||||
} else if (char === ':' && depth === 1) {
|
||||
count += 1
|
||||
}
|
||||
}
|
||||
return count
|
||||
}
|
||||
|
||||
function decisionFromText(text: string | undefined, textBlocks: number): Decision | 'invalid' {
|
||||
if (text === undefined || textBlocks !== 1) return 'invalid'
|
||||
try {
|
||||
@@ -343,6 +359,7 @@ function decisionFromText(text: string | undefined, textBlocks: number): Decisio
|
||||
if (parsed === null || typeof parsed !== 'object' || Array.isArray(parsed)) return 'invalid'
|
||||
const record = parsed as Record<string, unknown>
|
||||
const keys = Object.keys(record)
|
||||
if (topLevelMemberCount(text) !== keys.length) return 'invalid'
|
||||
if (record.decision === 'allow' && keys.length === 1) return 'allow'
|
||||
if (record.decision === 'deny' && keys.length === 1) return 'deny'
|
||||
if (record.decision === 'deny' && keys.length === 2
|
||||
|
||||
@@ -597,6 +597,8 @@ describe('native review request', () => {
|
||||
decisionChunks('{"decision":"allow","reason":"not allowed"}'),
|
||||
decisionChunks('{"decision":"deny","reason":1}'),
|
||||
decisionChunks('{"decision":"deny","extra":true}'),
|
||||
decisionChunks('{"decision":"deny","extra":[{"nested":true}]}'),
|
||||
decisionChunks('{"decision":"deny","decision":"allow"}'),
|
||||
decisionChunks('not json'),
|
||||
[
|
||||
{ type: 'block-start', index: 0, blockType: 'reasoning' },
|
||||
@@ -696,7 +698,7 @@ describe('native review request', () => {
|
||||
|
||||
describe('PTC and bypass semantics', () => {
|
||||
it('reviews one started inner call from its logged schema and preserves the raw deny reason', async () => {
|
||||
const rawReason = ' exact scope was not authorized\nretry with a narrower target '
|
||||
const rawReason = ' exact "scope" was not authorized\nretry with a narrower target '
|
||||
const { ctx, adapter } = await harness([
|
||||
decisionChunks(JSON.stringify({ decision: 'deny', reason: rawReason })),
|
||||
])
|
||||
|
||||
@@ -1,18 +0,0 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from '@deepseek-ai/cordis'
|
||||
import InvariantRegistry from '@deepseek-ai/dsh-invariants'
|
||||
import * as AutoReviewInvariant from '@deepseek-ai/dsh-auto-review/invariant'
|
||||
|
||||
describe('auto-review invariant companion', () => {
|
||||
it('reserves and releases the package registration without runtime state', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(InvariantRegistry)
|
||||
const fiber = await ctx.plugin(AutoReviewInvariant)
|
||||
expect(() => ctx.invariants.register('@deepseek-ai/dsh-auto-review', () => {}))
|
||||
.toThrow(/already registered/)
|
||||
await fiber.dispose()
|
||||
const dispose = ctx.invariants.register('@deepseek-ai/dsh-auto-review', () => {})
|
||||
dispose()
|
||||
await ctx.fiber.dispose()
|
||||
})
|
||||
})
|
||||
@@ -11,7 +11,6 @@
|
||||
{ "path": "../../core/agent" },
|
||||
{ "path": "../../context/agent-instructions" },
|
||||
{ "path": "../../compaction/compaction" },
|
||||
{ "path": "../../runtime-diagnostics/invariants" },
|
||||
{ "path": "../../llm/llm" },
|
||||
{ "path": "../../core/session" },
|
||||
{ "path": "../permission-presets" },
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/interaction/permission-presets/README.md
|
||||
README.md: e6bd7c50b9e28f0ac61e0503e4c948155cfa8c57
|
||||
README.zh.md: 9ced957166662404665adfae36244e151c62863e
|
||||
README.md: 434522d2a149c7278971f9d53b26e5762bad229e
|
||||
README.zh.md: ae0faa91b49293e5975fb215c515fd8f06990d94
|
||||
@@ -57,7 +57,7 @@ Switching to Auto first runs its synchronous admission check; every preset switc
|
||||
|
||||
### What users see
|
||||
|
||||
Clients render selectable entries from the process catalog: configured presets in table order followed by Auto while its integration is live. They join that snapshot with the Session's current value; an unmatched `custom` value may label the current control but never appears as a selectable catalog row. Auto's identity, Full access knob bundle, label, and description are fixed inside this service rather than supplied by a generic contribution API. Callers can switch away from `custom` but cannot select or persist a named custom preset through this service.
|
||||
Clients render selectable entries from the process catalog: configured presets in table order followed by Auto while its integration is live. They join that snapshot with the Session's current value; an unmatched `custom` value may label the current control but never appears as a selectable catalog row. Auto's identity and Full access knob bundle are fixed inside this service. The shipped client locale dictionaries own Auto's label and description, while configured presets retain Host-supplied presentation. Callers cannot publish another preset through a generic contribution API, and they can switch away from `custom` but cannot select or persist a named custom preset through this service.
|
||||
|
||||
### Session defaults
|
||||
|
||||
|
||||
@@ -57,7 +57,7 @@ kind: "package-reference"
|
||||
|
||||
### 用户看到什么
|
||||
|
||||
客户端从进程级目录渲染可选条目:先按表顺序列出配置预设,再在 Auto integration 存活时列出 Auto。客户端把这份快照与 Session 当前值合并;不匹配的 `custom` 值可以标记当前控件,但绝不会成为可选目录行。Auto 的身份、Full access 旋钮组合、label 与 description 固定在本服务内部,而不是由通用 contribution API 提供。调用方可以从 `custom` 切换出去,但不能通过此服务选中或持久化一个具名 custom 预设。
|
||||
客户端从进程级目录渲染可选条目:先按表顺序列出配置预设,再在 Auto integration 存活时列出 Auto。客户端把这份快照与 Session 当前值合并;不匹配的 `custom` 值可以标记当前控件,但绝不会成为可选目录行。Auto 的身份与 Full access 旋钮组合固定在本服务内部。shipped 客户端的 locale 字典拥有 Auto 的 label 与 description,而配置预设保留 Host 提供的展示信息。调用方不能通过通用 contribution API 发布其他预设;他们可以从 `custom` 切换出去,但不能通过此服务选中或持久化一个具名 custom 预设。
|
||||
|
||||
### 会话默认值
|
||||
|
||||
|
||||
@@ -78,12 +78,10 @@ export const CUSTOM_PRESET = 'custom'
|
||||
/** Canonical identity of the experimental per-call review preset. */
|
||||
export const AUTO_PRESET = 'auto'
|
||||
|
||||
/** Fixed execution bundle and current-session presentation owned by this service. */
|
||||
/** Fixed execution bundle for the live Auto integration. */
|
||||
const AUTO_PRESET_SPEC: PresetSpec = {
|
||||
sandbox: 'danger-full-access',
|
||||
approval: 'never',
|
||||
name: 'Auto review',
|
||||
description: 'Run without a sandbox after an experimental same-model review of every tool call.',
|
||||
}
|
||||
|
||||
/** Settings namespace carrying the default for future sessions. */
|
||||
|
||||
@@ -117,13 +117,11 @@ describe('PermissionPresetService', () => {
|
||||
const fiber = await mountAuto(ctx)
|
||||
expect(ctx.permissionPresets.names).toEqual(['workspace-write', 'danger-full-access', AUTO_PRESET])
|
||||
expect(ctx.permissionPresets.resolve(AUTO_PRESET)).toEqual({
|
||||
sandbox: 'danger-full-access', approval: 'never', name: 'Auto review',
|
||||
description: 'Run without a sandbox after an experimental same-model review of every tool call.',
|
||||
sandbox: 'danger-full-access', approval: 'never',
|
||||
})
|
||||
expect(ctx.permissionPresets.optionOf(AUTO_PRESET)).toEqual({
|
||||
value: AUTO_PRESET,
|
||||
name: 'Auto review',
|
||||
description: 'Run without a sandbox after an experimental same-model review of every tool call.',
|
||||
name: AUTO_PRESET,
|
||||
})
|
||||
|
||||
await fiber.dispose()
|
||||
|
||||
Generated
-3
@@ -5873,9 +5873,6 @@ importers:
|
||||
'@deepseek-ai/dsh-fs-sandbox':
|
||||
specifier: workspace:^
|
||||
version: link:../../fs/fs-sandbox
|
||||
'@deepseek-ai/dsh-invariants':
|
||||
specifier: workspace:^
|
||||
version: link:../../runtime-diagnostics/invariants
|
||||
'@deepseek-ai/dsh-llm':
|
||||
specifier: workspace:^
|
||||
version: link:../../llm/llm
|
||||
|
||||
@@ -19,23 +19,25 @@
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}}}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":6152,"outputTokens":214,"cacheReadTokens":0,"reasoningTokens":60}}}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to write a single Python run_code program that:\n1. Calls bash tool twice: `echo CODE_ONE` and `echo CODE_TWO`\n2. print exactly `captured output`\n3. Return the two outputs joined with a plus sign\n\nLet me write this."},{"type":"tool-call","id":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:3}}"},"usage":{"inputTokens":6152,"outputTokens":214,"cacheReadTokens":0,"reasoningTokens":60}},"sourceEventSeqs":[12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to write a single Python run_code program that:\n1. Calls bash tool twice: `echo CODE_ONE` and `echo CODE_TWO`\n2. print exactly `captured output`\n3. Return the two outputs joined with a plus sign\n\nLet me write this."},{"type":"tool-call","id":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:3}}"},"usage":{"inputTokens":6152,"outputTokens":214,"cacheReadTokens":0,"reasoningTokens":60}},"sourceEventSeqs":[[12,190]],"surfaceOp":"append"}
|
||||
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_00_UiQPVqoELyzBZCY5pm1z7875","name":"run_code","arguments":"{\"code\":\"out1 = await tools.bash({\\\"command\\\": \\\"echo CODE_ONE\\\", \\\"description\\\": \\\"Print CODE_ONE\\\"})\\nout2 = await tools.bash({\\\"command\\\": \\\"echo CODE_TWO\\\", \\\"description\\\": \\\"Print CODE_TWO\\\"})\\nprint(\\\"captured output\\\")\\ntext1 = out1[\\\"stdout\\\"][\\\"text\\\"].strip()\\ntext2 = out2[\\\"stdout\\\"][\\\"text\\\"].strip()\\nreturn text1 + \\\"+\\\" + text2\",\"description\":\"Run two echo commands and join outputs\"}"}}
|
||||
{"type":"tool/code-dispatch-start","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"Print CODE_ONE"}}}
|
||||
{"type":"tool/code-dispatch-start","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:1","name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a job id immediately; read its output with `job_output` and stop it with `job_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"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\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"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 wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user 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."}},"required":["command","description"]},"arguments":{"command":"echo CODE_ONE","description":"Print CODE_ONE"}}}
|
||||
{"type":"tool/code-dispatch","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"Print CODE_ONE"},"isError":false,"content":[{"type":"text","text":"CODE_ONE\n"}]}}
|
||||
{"type":"tool/code-dispatch-start","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Print CODE_TWO"}}}
|
||||
{"type":"tool/code-dispatch-start","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:2","name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under <mode> mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a job id immediately; read its output with `job_output` and stop it with `job_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"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\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"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 wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user 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."}},"required":["command","description"]},"arguments":{"command":"echo CODE_TWO","description":"Print CODE_TWO"}}}
|
||||
{"type":"tool/code-dispatch","data":{"rootCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","parentCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","subCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Print CODE_TWO"},"isError":false,"content":[{"type":"text","text":"CODE_TWO\n"}]}}
|
||||
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_UiQPVqoELyzBZCY5pm1z7875"},"content":[{"type":"tool-result","toolCallId":"call_00_UiQPVqoELyzBZCY5pm1z7875","content":[{"type":"text","text":"captured output\nCODE_ONE+CODE_TWO"}],"isError":false}],"role":"user","id":"{{message:4}}"}},"sourceEventSeqs":[192],"surfaceOp":"append"}
|
||||
{"type":"step/end","data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","data":{"turn":1,"step":2,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0],"texts":["The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only.","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","",""]}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."}}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":""}}}
|
||||
{"type":"reasoning-chunks","data":{"turn":1,"step":2,"index":0,"dt":[0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0,0,0],"texts":["","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","",""]}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"text-chunks","data":{"turn":1,"step":2,"index":1,"dt":[0,0,0,0,0,0],"texts":["CODE","_","ONE","+","CODE","_T","WO"]}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."}}}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CODE_ONE+CODE_TWO"}}}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":117,"outputTokens":50,"cacheReadTokens":6272,"reasoningTokens":42}}}}
|
||||
{"type":"assistant/chunk","data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:5}}"},"usage":{"inputTokens":117,"outputTokens":50,"cacheReadTokens":6272,"reasoningTokens":42}},"sourceEventSeqs":[200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254],"surfaceOp":"append"}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The Python program ran successfully. The print output \"captured output\" appeared, and the return value is \"CODE_ONE+CODE_TWO\". The user asked me to reply with that joined string only."},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:5}}"},"usage":{"inputTokens":117,"outputTokens":50,"cacheReadTokens":6272,"reasoningTokens":42}},"sourceEventSeqs":[[200,254]],"surfaceOp":"append"}
|
||||
{"type":"step/end","data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -148,7 +148,6 @@
|
||||
"@deepseek-ai/dsh-host-plugin-inventory": ["./packages/host/plugin-inventory/src"],
|
||||
"@deepseek-ai/dsh-host-plugin-inventory/types": ["./packages/host/plugin-inventory/src/types.ts"],
|
||||
"@deepseek-ai/dsh-auto-review": ["./packages/interaction/auto-review/src"],
|
||||
"@deepseek-ai/dsh-auto-review/invariant": ["./packages/interaction/auto-review/src/invariant.ts"],
|
||||
"@deepseek-ai/dsh-client-ui-slots": ["./packages/client/ui-slots/src"],
|
||||
"@deepseek-ai/dsh-client-ui-attachment": ["./packages/client/ui-attachment/src"],
|
||||
"@deepseek-ai/dsh-client-ui-primitives": ["./packages/client/ui-primitives/src"],
|
||||
|
||||
Reference in new issue
Block a user