feat(plan): keep exit_plan_mode declared after the first plan-mode entry
Disclose the exit tool progressively instead of following every plan-mode transition. The plan projection records whether a logged plan/mode ever activated plan mode (stateVersion 4), and the tool's condition admits it for a step whose selected state is active or once the Session has entered plan mode. Leaving plan mode now changes only the guidance section, so an addition-only route no longer drops a declaration from its cached prefix. A call while plan mode is not committed still fails as unavailable outside plan mode, and a Session that never entered plan mode does not list the tool. The Web plan-review fixtures return to master's recording because the request tool lists no longer change on exit.
This commit is contained in:
Yichen Jiang committed
1 parent
85b29bbcea
commit
752cc5c0c0
21 files changed
+98
-67
No files matched your search
@@ -2465,7 +2465,7 @@ export interface Config {
|
||||
## `@deepseek-ai/dsh-plan-mode`
|
||||
|
||||
- `inject`: `tools` · `systemPrompt` · `sessionProjections` · `agents`
|
||||
- `source`: [`packages/plan/plan-mode/src/index.ts:66`](../packages/plan/plan-mode/src/index.ts)
|
||||
- `source`: [`packages/plan/plan-mode/src/index.ts:67`](../packages/plan/plan-mode/src/index.ts)
|
||||
|
||||
```ts config-catalog
|
||||
/** Deployment-owned plan guidance. */
|
||||
|
||||
@@ -2467,7 +2467,7 @@ export interface Config {
|
||||
## `@deepseek-ai/dsh-plan-mode`
|
||||
|
||||
- `inject`: `tools` · `systemPrompt` · `sessionProjections` · `agents`
|
||||
- `source`: [`packages/plan/plan-mode/src/index.ts:66`](../packages/plan/plan-mode/src/index.ts)
|
||||
- `source`: [`packages/plan/plan-mode/src/index.ts:67`](../packages/plan/plan-mode/src/index.ts)
|
||||
|
||||
```ts config-catalog
|
||||
/** Deployment-owned plan guidance. */
|
||||
|
||||
@@ -153,8 +153,8 @@
|
||||
en: 4294f78d26ed985b
|
||||
zh: 4294f78d26ed985b
|
||||
/session-persistence-event-catalog/events/plan/plan-mode-log-only:
|
||||
en: 862175bfe8692ef7
|
||||
zh: a8ab123bf674cf77
|
||||
en: 9ae5537eeae238de
|
||||
zh: 6be761c7fd83fdce
|
||||
/session-persistence-event-catalog/events/request:
|
||||
en: a8df82440ebdf5f8
|
||||
zh: a8df82440ebdf5f8
|
||||
@@ -1398,8 +1398,8 @@
|
||||
en: a74e3dfa51c987af
|
||||
zh: 6c3c87974d7a7260
|
||||
/session-persistence-event-catalog/resolved-persistence-types/active~2:
|
||||
en: a3de6a6fe9672c7a
|
||||
zh: a357481e27b3b81f
|
||||
en: c861888d6239b700
|
||||
zh: a9b2271d3c6b8737
|
||||
/session-persistence-event-catalog/resolved-persistence-types/agentpreset:
|
||||
en: 1afbe8196f161601
|
||||
zh: a320a36a8928817c
|
||||
|
||||
@@ -735,7 +735,7 @@ Source: [`packages/interaction/permission-presets/src/index.ts:52`](../packages/
|
||||
'plan/mode': { active: boolean }
|
||||
```
|
||||
|
||||
Source: [`packages/plan/plan-mode/src/index.ts:52`](../packages/plan/plan-mode/src/index.ts)
|
||||
Source: [`packages/plan/plan-mode/src/index.ts:53`](../packages/plan/plan-mode/src/index.ts)
|
||||
|
||||
### `request/*`
|
||||
|
||||
@@ -5769,7 +5769,7 @@ Array of `unknown` (opaque).
|
||||
|
||||
SHA-256: `20a57544bbf204dacd1ae6beb2ab29444365c3c869f2afdf489dcdcbc3d9c8c5`
|
||||
|
||||
Sources: [`packages/plan/plan-mode/src/index.ts:52`](../packages/plan/plan-mode/src/index.ts)
|
||||
Sources: [`packages/plan/plan-mode/src/index.ts:53`](../packages/plan/plan-mode/src/index.ts)
|
||||
|
||||
| Property | Presence | Type |
|
||||
|---|---|---|
|
||||
|
||||
@@ -737,7 +737,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = {
|
||||
'plan/mode': { active: boolean }
|
||||
```
|
||||
|
||||
来源：[`packages/plan/plan-mode/src/index.ts:52`](../packages/plan/plan-mode/src/index.ts)
|
||||
来源：[`packages/plan/plan-mode/src/index.ts:53`](../packages/plan/plan-mode/src/index.ts)
|
||||
|
||||
### `request/*`
|
||||
|
||||
@@ -5771,7 +5771,7 @@ SHA-256: `b1664fa89f8eab49a14e7e3168d8bc4da4aa9fd76332f6c4a053d839e5276ae7`
|
||||
|
||||
SHA-256: `20a57544bbf204dacd1ae6beb2ab29444365c3c869f2afdf489dcdcbc3d9c8c5`
|
||||
|
||||
来源：[`packages/plan/plan-mode/src/index.ts:52`](../packages/plan/plan-mode/src/index.ts)
|
||||
来源：[`packages/plan/plan-mode/src/index.ts:53`](../packages/plan/plan-mode/src/index.ts)
|
||||
|
||||
| 属性 | 存在性 | 类型 |
|
||||
|---|---|---|
|
||||
|
||||
Generated
+1
-1
@@ -153,7 +153,7 @@
|
||||
{"digest":"1f1385dbc3e875c021e387c7096d671d606f22daec51b25c80348735b6bbfa10","names":[],"sources":[]},
|
||||
{"digest":"1f8c126cfab3df812cd115cfc23e3256f0fa2383400f4ce91ecad313577e59b0","names":["packages/core/session/src/types.ts#TurnEndCancelCause"],"sources":["packages/core/session/src/types.ts:197"]},
|
||||
{"digest":"1fdad624334d354820dfb3a26e28d0bc9fc1b62a33f87bab63f715b3f4391bfd","names":[],"sources":[]},
|
||||
{"digest":"20a57544bbf204dacd1ae6beb2ab29444365c3c869f2afdf489dcdcbc3d9c8c5","names":[],"sources":["packages/plan/plan-mode/src/index.ts:52"]},
|
||||
{"digest":"20a57544bbf204dacd1ae6beb2ab29444365c3c869f2afdf489dcdcbc3d9c8c5","names":[],"sources":["packages/plan/plan-mode/src/index.ts:53"]},
|
||||
{"digest":"2142e391b9ccb60d487afcf373ce74db98d952f69e8289eddb352a7e16e996c5","names":[],"sources":[]},
|
||||
{"digest":"2152caf1a71e588e4df2358a806dea24936c1c47131134f01a12939d12cdc0c0","names":["packages/experimental/agent-team/src/types.ts#TeamMessageSource"],"sources":["packages/experimental/agent-team/src/types.ts:138"]},
|
||||
{"digest":"21fb6a90d5068f6a0003b7ab316ed2f56342477146a65c00db0f13c4d8df667d","names":[],"sources":[]},
|
||||
|
||||
@@ -15,8 +15,8 @@
|
||||
en: ee04468005fae8e1
|
||||
zh: 1347d554102951f2
|
||||
/plan-mode/the-exit-tool-and-the-plan-command:
|
||||
en: 9f2a549447f8d374
|
||||
zh: 8f3064e31d514702
|
||||
en: 32ecfb7086dd1578
|
||||
zh: 0aaeaa69bb63f255
|
||||
/plan-mode/the-service:
|
||||
en: f3e6d5a7fe0b67f0
|
||||
zh: 774cc97e493991fa
|
||||
@@ -30,7 +30,7 @@ A missing, blank, or non-string `section` and any unknown key fail at plugin loa
|
||||
|
||||
## The exit tool and the `/plan` command
|
||||
|
||||
[`exit_plan_mode`](../tool-catalog.md#deepseek-aidsh-plan-mode) is admitted only for steps whose selected plan state is active, so entering or leaving plan mode changes the request tool declarations and the plan guidance together; Native and PTC execution use the same admitted set, and a call outside plan mode returns `UNKNOWN_TOOL`. In plan mode it requires a complete markdown plan starting with a `#` heading and presents it for review through the [user-questions seam](user-questions.md). Approval returns `{ approved: true }` and records a silent (non-narrated) pending exit that is appended at the next accepted in-turn pre-step. Plan guidance therefore remains active for the rest of the assistant's current tool batch, and the tool result itself reports the transition. Keep-planning is a failed call carrying the user's feedback, so the model revises and presents again. A dismissed review returns `{ approved: false }` and concludes the turn, so plan mode stays active until the user's next message. A missing interaction channel and a service reload during review also fail the call rather than silently leaving plan mode.
|
||||
[`exit_plan_mode`](../tool-catalog.md#deepseek-aidsh-plan-mode) is disclosed progressively: it is admitted from the first step whose selected plan state is active and stays admitted for the rest of the Session, so the first plan-mode entry adds it to the request tool declarations and later transitions change only the plan guidance. Native and PTC execution use the same admitted set; a call before the first entry returns `UNKNOWN_TOOL`, and a call while plan mode is not committed fails. In plan mode it requires a complete markdown plan starting with a `#` heading and presents it for review through the [user-questions seam](user-questions.md). Approval returns `{ approved: true }` and records a silent (non-narrated) pending exit that is appended at the next accepted in-turn pre-step. Plan guidance therefore remains active for the rest of the assistant's current tool batch, and the tool result itself reports the transition. Keep-planning is a failed call carrying the user's feedback, so the model revises and presents again. A dismissed review returns `{ approved: false }` and concludes the turn, so plan mode stays active until the user's next message. A missing interaction channel and a service reload during review also fail the call rather than silently leaving plan mode.
|
||||
|
||||
When [`ctx.commands`](commands.md) is composed, the plugin registers `/plan [off|message]`: bare `/plan` selects plan mode, any other non-empty message selects it and then submits the text through `agent.steer()` so it becomes the next step's ordinary logged user message under plan guidance, and the exact argument `off` selects inactive, which also cancels a pending entry before it is appended and becomes visible to a request.
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ interface PlanModeConfig {
|
||||
|
||||
## 退出工具与 `/plan` 命令
|
||||
|
||||
[`exit_plan_mode`](../tool-catalog.zh.md#deepseek-aidsh-plan-mode) 只在已选计划状态为激活的步骤中准入，因此进入或离开计划模式会同时改变请求的工具声明与计划指引；原生与 PTC 执行使用同一准入集合，在计划模式之外调用会返回 `UNKNOWN_TOOL`。在计划模式中，它要求一份以 `#` 标题开头的完整 markdown 计划，并通过[用户交互 seam](user-questions.zh.md) 呈交评审。批准返回 `{ approved: true }`，并记录一个静默（不叙述）的待生效退出，由下一个被接受的轮内 pre-step 追加。因此，计划指引在 assistant 当前这批工具调用的剩余部分继续生效，而工具结果本身会报告这次转换。「继续规划」则是一次携带用户反馈的失败调用，模型据此修订并再次呈交。放弃评审返回 `{ approved: false }` 并结束当前轮次，计划模式保持激活，直到用户发出下一条消息。评审期间交互通道缺失或服务重载同样使调用失败，而不是静默离开计划模式。
|
||||
[`exit_plan_mode`](../tool-catalog.zh.md#deepseek-aidsh-plan-mode) 采用渐进式披露：从已选计划状态首次为激活的步骤起准入，并在会话剩余部分保持准入，因此首次进入计划模式时它进入请求的工具声明，之后的切换只改变计划指引。原生与 PTC 执行使用同一准入集合；首次进入之前调用返回 `UNKNOWN_TOOL`，计划模式未提交时调用会失败。在计划模式中，它要求一份以 `#` 标题开头的完整 markdown 计划，并通过[用户交互 seam](user-questions.zh.md) 呈交评审。批准返回 `{ approved: true }`，并记录一个静默（不叙述）的待生效退出，由下一个被接受的轮内 pre-step 追加。因此，计划指引在 assistant 当前这批工具调用的剩余部分继续生效，而工具结果本身会报告这次转换。「继续规划」则是一次携带用户反馈的失败调用，模型据此修订并再次呈交。放弃评审返回 `{ approved: false }` 并结束当前轮次，计划模式保持激活，直到用户发出下一条消息。评审期间交互通道缺失或服务重载同样使调用失败，而不是静默离开计划模式。
|
||||
|
||||
当 [`ctx.commands`](commands.zh.md) 被组合时，插件注册 `/plan [off|message]`：单独的 `/plan` 选择计划模式；任何其他非空消息先选择计划模式，再通过 `agent.steer()` 提交该文本，使其在计划指引下成为下一步骤的普通已记录用户消息；确切参数 `off` 选择未激活，这还会在待生效条目被追加并对请求可见之前将其取消。
|
||||
|
||||
|
||||
@@ -3,14 +3,14 @@
|
||||
# After editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write docs/upgrade-guide/v0.2.1-rc.2/conditional-tools/guide.md
|
||||
/:
|
||||
en: 759962a4bf2e454f
|
||||
zh: df802b222d1a46f3
|
||||
en: 1dc343c5aa10de02
|
||||
zh: 59ac1c2052255919
|
||||
/declare-conditional-tools-through-step-admission:
|
||||
en: 4edb4c80b402de77
|
||||
zh: 856160ec69c515ea
|
||||
/declare-conditional-tools-through-step-admission/change:
|
||||
en: ba47cb460364f666
|
||||
zh: 1b5db25e4fb99ac2
|
||||
en: 71aba6399833cd1d
|
||||
zh: b820e301baf72e4e
|
||||
/declare-conditional-tools-through-step-admission/migration:
|
||||
en: 676839aab96dcd2d
|
||||
zh: eae3c9a6795f8d6e
|
||||
en: 943671c4348031bb
|
||||
zh: 0e44d7b29eab0168
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
kind: upgrade-guide
|
||||
description: "Tool declarations come only from step-admitted registrations: `system-prompt/assemble` no longer carries tools, conditional tools need a resolved step set, and `exit_plan_mode` is declared only in plan mode."
|
||||
description: "Tool declarations come only from step-admitted registrations: `system-prompt/assemble` no longer carries tools, conditional tools need a resolved step set, and `exit_plan_mode` is declared only after a Session first enters plan mode."
|
||||
---
|
||||
|
||||
# Declare conditional tools through step admission
|
||||
@@ -15,11 +15,11 @@ The `system-prompt/assemble` waterfall now receives sections, contexts, and vari
|
||||
|
||||
Model tool calls run only through their step's admitted set. A call to a conditional tool without a resolved set, a call after the set is disposed, and a pending call whose registration was replaced or removed during the step return `UNKNOWN_TOOL` instead of running.
|
||||
|
||||
`exit_plan_mode` is declared only for steps whose selected plan state is active, so the request tool list changes when plan mode starts or ends. Existing Sessions require no format migration.
|
||||
`exit_plan_mode` is declared from the first step whose selected plan state is active and stays declared for the rest of the Session, so requests of a Session that never entered plan mode no longer list it. Existing Sessions require no format migration.
|
||||
|
||||
## Migration
|
||||
|
||||
1. Replace tool filtering in `system-prompt/assemble` listeners with a `when` condition on the registration; read the step's provider, model, and reasoning effort from the condition's `modelSelection`. Keep only section, context, and variable changes in the waterfall.
|
||||
2. Make tool guidance follow the same admission: section callbacks pass `context.toolSet` to `ctx.tools.get()` or `ctx.tools.schemas()`.
|
||||
3. For programmatic calls of conditional tools, call `ctx.tools.resolve({ agent, modelSelection, signal })`, pass the returned `toolSet` to `assemble()` and `ctx.tools.execute()`, and dispose it after the batch settles.
|
||||
4. Update expectations that listed `exit_plan_mode` outside plan mode. Verify that a disabled tool is absent from the request, that calling its name returns `UNKNOWN_TOOL` without reaching the implementation, and that a failing condition ends the turn with `TOOL_ACTIVATION_FAILED`.
|
||||
4. Update expectations that listed `exit_plan_mode` before a Session entered plan mode. Verify that a disabled tool is absent from the request, that calling its name returns `UNKNOWN_TOOL` without reaching the implementation, and that a failing condition ends the turn with `TOOL_ACTIVATION_FAILED`.
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
kind: upgrade-guide
|
||||
description: "工具声明只来自步骤准入的注册：`system-prompt/assemble` 不再携带工具，条件工具需要已解析的步骤集合，`exit_plan_mode` 只在计划模式下声明。"
|
||||
description: "工具声明只来自步骤准入的注册：`system-prompt/assemble` 不再携带工具，条件工具需要已解析的步骤集合，`exit_plan_mode` 只在会话首次进入计划模式后声明。"
|
||||
---
|
||||
|
||||
# 通过步骤准入声明条件工具
|
||||
@@ -15,11 +15,11 @@ description: "工具声明只来自步骤准入的注册：`system-prompt/assemb
|
||||
|
||||
模型的工具调用只通过所属步骤的准入集合执行。没有已解析集合的条件工具调用、集合释放之后的调用，以及注册在步骤内被替换或移除时尚未开始的调用，都会返回 `UNKNOWN_TOOL`，不会执行。
|
||||
|
||||
`exit_plan_mode` 只在已选计划状态为激活的步骤中声明，因此进入或离开计划模式时请求的工具列表会变化。现有 Session 无需格式迁移。
|
||||
`exit_plan_mode` 从已选计划状态首次为激活的步骤起声明，并在会话剩余部分保持声明，因此从未进入计划模式的会话，其请求不再列出它。现有 Session 无需格式迁移。
|
||||
|
||||
## 迁移
|
||||
|
||||
1. 把 `system-prompt/assemble` 监听器中的工具过滤改为注册时的 `when` 条件；从条件的 `modelSelection` 读取该步骤的提供方、模型与推理强度。waterfall 中只保留段落、上下文与变量的修改。
|
||||
2. 让工具指引跟随同一准入：段落回调把 `context.toolSet` 传给 `ctx.tools.get()` 或 `ctx.tools.schemas()`。
|
||||
3. 程序化调用条件工具时，调用 `ctx.tools.resolve({ agent, modelSelection, signal })`，把返回的 `toolSet` 传给 `assemble()` 与 `ctx.tools.execute()`，并在批次结束后释放。
|
||||
4. 更新在计划模式之外仍列出 `exit_plan_mode` 的期望。验证被禁用的工具不出现在请求中，用其名称调用会返回 `UNKNOWN_TOOL` 且不进入实现，条件失败时轮次以 `TOOL_ACTIVATION_FAILED` 结束。
|
||||
4. 更新在会话进入计划模式之前仍列出 `exit_plan_mode` 的期望。验证被禁用的工具不出现在请求中，用其名称调用会返回 `UNKNOWN_TOOL` 且不进入实现，条件失败时轮次以 `TOOL_ACTIVATION_FAILED` 结束。
|
||||
@@ -45,8 +45,8 @@
|
||||
en: a7bf35c2a9da52bc
|
||||
zh: dea9f4b3a41f1a6d
|
||||
/deepseek-ai-dsh-plan-mode/understand-the-implementation/the-exit-tool:
|
||||
en: ad84b4025d8ea536
|
||||
zh: 683b3f56b0b6b368
|
||||
en: 7736aea9e4934fa8
|
||||
zh: a595e477f54a199e
|
||||
/deepseek-ai-dsh-plan-mode/understand-the-implementation/session-projection-unit:
|
||||
en: 396d66816890f715
|
||||
zh: fab5d67c027b33f5
|
||||
@@ -90,14 +90,14 @@
|
||||
en: 9622e96bdc01276d
|
||||
zh: 53801e68a49f3d1d
|
||||
/deepseek-ai-dsh-plan-mode/model-experience/exit-tool-schema-and-review-exchange/what-the-model-sees:
|
||||
en: b0b53f72b11d634b
|
||||
zh: c7bc8a10a90f7fa3
|
||||
en: 1b978a7b6eecdffe
|
||||
zh: 338000d1bf8dd4a9
|
||||
/deepseek-ai-dsh-plan-mode/model-experience/exit-tool-schema-and-review-exchange/token-effect:
|
||||
en: a1a020eb7ba26e7c
|
||||
zh: a99208693d331a31
|
||||
en: 5ef9db72f91e4a8c
|
||||
zh: 6e96335cc3eb5976
|
||||
/deepseek-ai-dsh-plan-mode/model-experience/exit-tool-schema-and-review-exchange/kv-cache-effect:
|
||||
en: 9d9626fbf4cdc8de
|
||||
zh: 8237cbc3ca048024
|
||||
en: a9eb70ad541fcfd7
|
||||
zh: 9c06d39341fc52b1
|
||||
/deepseek-ai-dsh-plan-mode/known-limitations-and-deferred-work:
|
||||
en: a87aabfede0087fd
|
||||
zh: 201e9b3766980005
|
||||
|
||||
@@ -90,7 +90,7 @@ The command child activates only when a commands service is composed. It maps ba
|
||||
|
||||
### The exit tool
|
||||
|
||||
`exit_plan_mode` is admitted only for steps whose selected plan state is active, the same state that renders plan guidance, so entering or leaving changes the tool declarations and the guidance together; Native and PTC execution use the same admitted set. An approved review records a silent pending exit that the next accepted in-turn pre-step appends, keeping plan guidance for the rest of the current tool batch. Without a user-questions channel, or after a service reload while the review is pending, the call fails closed and `/plan off` remains the manual escape.
|
||||
`exit_plan_mode` is disclosed progressively: it is admitted from the first step whose selected plan state is active and stays admitted for the rest of the Session, so entering plan mode the first time adds it together with the guidance, and later transitions change only the guidance; Native and PTC execution use the same admitted set. A call while plan mode is not committed fails. An approved review records a silent pending exit that the next accepted in-turn pre-step appends, keeping plan guidance for the rest of the current tool batch. Without a user-questions channel, or after a service reload while the review is pending, the call fails closed and `/plan off` remains the manual escape.
|
||||
|
||||
### Session projection unit
|
||||
|
||||
@@ -166,15 +166,15 @@ The user block is append-only conversation growth. Entering or leaving plan mode
|
||||
|
||||
#### What the model sees
|
||||
|
||||
The [`exit_plan_mode` schema](../../../docs/tool-catalog.md#deepseek-aidsh-plan-mode) is offered only in plan mode; calls outside its admitted set return `UNKNOWN_TOOL`, while an approved in-mode review returns the canonical `{ approved: true }` value and renders the existing confirmation text. Rejection remains a failed call carrying review feedback. A dismissed review returns `{ approved: false }`, renders a note that the user will reply, and concludes the turn without another model request.
|
||||
The [`exit_plan_mode` schema](../../../docs/tool-catalog.md#deepseek-aidsh-plan-mode) is offered from the first plan-mode entry in a Session; earlier calls return `UNKNOWN_TOOL`, calls after leaving plan mode fail as unavailable outside plan mode, and an approved in-mode review returns the canonical `{ approved: true }` value and renders the existing confirmation text. Rejection remains a failed call carrying review feedback. A dismissed review returns `{ approved: false }`, renders a note that the user will reply, and concludes the turn without another model request.
|
||||
|
||||
#### Token effect
|
||||
|
||||
The schema is paid only while active, according to ToolRuntime mode, and each plan argument and review result remains in conversation history.
|
||||
The schema is paid from the first entry on, according to ToolRuntime mode, and each plan argument and review result remains in conversation history.
|
||||
|
||||
#### KV Cache effect
|
||||
|
||||
Entering plan mode adds the exit tool through the route’s tool-update protocol, and leaving removes it. An `in-history` route records both changes after cached history. An `addition-only` route, such as the default catalog’s `deepseek-flash`, cannot record the removal and drops the tool from later requests, so the first request after leaving can miss part of the cached prefix; a route without tool updates resends its changed declaration list after either transition. Plan arguments and review results extend the conversation normally.
|
||||
The first entry into plan mode adds the exit tool through the route’s tool-update protocol; `in-history` and `addition-only` routes record the addition after cached history, while a route without tool updates resends its changed declaration list once. Later transitions leave the tool list unchanged. Plan arguments and review results extend the conversation normally.
|
||||
|
||||
## Known Limitations and Deferred Work
|
||||
|
||||
|
||||
@@ -90,7 +90,7 @@ agent 完成计划后，会以 markdown 形式、从标题开头书写计划并
|
||||
|
||||
### 退出工具
|
||||
|
||||
`exit_plan_mode` 只在已选计划状态为激活的步骤中准入，这一状态也决定是否渲染计划指引，因此进入或离开会同时改变工具声明与指引；原生与 PTC 执行使用同一准入集合。经批准的评审会记录一个静默的待生效退出，由下一个被接受的轮内 pre-step 追加，当前这批工具调用剩余部分仍保留计划引导。缺少用户交互通道，或评审等待期间服务重载，调用都会以拒绝方式失败，`/plan off` 仍是手动退路。
|
||||
`exit_plan_mode` 采用渐进式披露：从已选计划状态首次为激活的步骤起准入，并在会话剩余部分保持准入，因此首次进入计划模式时它与指引一起出现，之后的切换只改变指引；原生与 PTC 执行使用同一准入集合。计划模式未提交时调用会失败。经批准的评审会记录一个静默的待生效退出，由下一个被接受的轮内 pre-step 追加，当前这批工具调用剩余部分仍保留计划引导。缺少用户交互通道，或评审等待期间服务重载，调用都会以拒绝方式失败，`/plan off` 仍是手动退路。
|
||||
|
||||
### 会话投影单元
|
||||
|
||||
@@ -166,15 +166,15 @@ You are in plan mode. Explore and design before presenting the complete plan thr
|
||||
|
||||
#### 模型看到什么
|
||||
|
||||
[`exit_plan_mode` schema](../../../docs/tool-catalog.zh.md#deepseek-aidsh-plan-mode) 只在计划模式中提供；不在准入集合中的调用返回 `UNKNOWN_TOOL`。模式内获批的评审返回规范值 `{ approved: true }` 并渲染现有确认文本。拒绝仍是携带评审反馈的失败调用。放弃评审返回 `{ approved: false }`，渲染一条说明用户将自行回复的文本，并结束当前轮次，不再发起模型请求。
|
||||
[`exit_plan_mode` schema](../../../docs/tool-catalog.zh.md#deepseek-aidsh-plan-mode) 从会话首次进入计划模式起提供；此前的调用返回 `UNKNOWN_TOOL`，离开计划模式后的调用会以计划模式之外不可用而失败。模式内获批的评审返回规范值 `{ approved: true }` 并渲染现有确认文本。拒绝仍是携带评审反馈的失败调用。放弃评审返回 `{ approved: false }`，渲染一条说明用户将自行回复的文本，并结束当前轮次，不再发起模型请求。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
schema 仅在启用时按 ToolRuntime 模式计入开销；每份计划参数与评审结果保留在对话历史中。
|
||||
schema 从首次进入计划模式起按 ToolRuntime 模式计入开销；每份计划参数与评审结果保留在对话历史中。
|
||||
|
||||
#### KV Cache 影响
|
||||
|
||||
进入计划模式时，退出工具通过路由的工具更新协议新增，离开时则移除。`in-history` 路由会在已缓存历史之后记录这两种变化。`addition-only` 路由（例如默认目录中的 `deepseek-flash`）无法记录移除，只能在之后的请求中去掉该工具，因此离开后的首个请求可能无法命中部分已缓存前缀；不支持工具更新的路由在任一方向转换后都会重新发送变化后的声明列表。计划参数与评审结果正常扩展对话。
|
||||
首次进入计划模式时，退出工具通过路由的工具更新协议新增；`in-history` 与 `addition-only` 路由在已缓存历史之后记录这次新增，不支持工具更新的路由会重新发送一次变化后的声明列表。之后的模式切换不改变工具列表。计划参数与评审结果正常扩展对话。
|
||||
|
||||
## 已知限制与延期工作
|
||||
|
||||
|
||||
@@ -12,9 +12,10 @@
|
||||
* assembly, then appends `plan/mode` from `agent/pre-step` only when the step
|
||||
* is accepted. Same-step request retries reuse their assembly.
|
||||
*
|
||||
* The exit tool is admitted only for steps whose selected state is active,
|
||||
* the same state that renders the guidance section. Native declarations, PTC
|
||||
* bindings, and execution share that admission.
|
||||
* The exit tool is disclosed progressively: it is admitted from the first step
|
||||
* whose selected state is active and stays admitted for the rest of the
|
||||
* Session, so leaving plan mode changes only the guidance section. Native
|
||||
* declarations, PTC bindings, and execution share that admission.
|
||||
*
|
||||
* See packages/plan/plan-mode/README.md.
|
||||
*
|
||||
@@ -59,7 +60,7 @@ declare module '@deepseek-ai/cordis' {
|
||||
}
|
||||
}
|
||||
|
||||
/** The model-facing exit tool's name, admitted only for steps in plan mode. */
|
||||
/** The model-facing exit tool's name, admitted once the Session enters plan mode. */
|
||||
export const EXIT_PLAN_MODE = 'exit_plan_mode'
|
||||
|
||||
/** Deployment-owned plan guidance. */
|
||||
@@ -121,6 +122,7 @@ const planUnitStateSchema: ZodType<PlanUnitState> = zod.object({
|
||||
wanted: zod.boolean(),
|
||||
}).strict().nullable(),
|
||||
activeAtLastHeader: zod.boolean().nullable(),
|
||||
entered: zod.boolean(),
|
||||
}).strict()
|
||||
|
||||
/** Wire payload schema of the `plan` projection. */
|
||||
@@ -132,9 +134,9 @@ const planProjectionSchema: ZodType<PlanProjection> = zod.object({
|
||||
/** Projection of logged plan selections and committed mode. */
|
||||
export const planProjectionDefinition = {
|
||||
key: 'plan',
|
||||
stateVersion: 3,
|
||||
stateVersion: 4,
|
||||
stateSchema: planUnitStateSchema,
|
||||
init: () => ({ active: false, wanted: null, running: null, activeAtLastHeader: null }),
|
||||
init: () => ({ active: false, wanted: null, running: null, activeAtLastHeader: null, entered: false }),
|
||||
apply: (state, event) => {
|
||||
if (event.type === 'command/run' && event.data.name === 'plan') {
|
||||
if (event.data.args === undefined) return state
|
||||
@@ -148,7 +150,7 @@ export const planProjectionDefinition = {
|
||||
return { ...state, wanted, running: null }
|
||||
}
|
||||
if (event.type === 'plan/mode') {
|
||||
return { ...state, active: event.data.active, wanted: null }
|
||||
return { ...state, active: event.data.active, wanted: null, entered: state.entered || event.data.active }
|
||||
}
|
||||
if (event.type === 'request/header') {
|
||||
return { ...state, activeAtLastHeader: state.active }
|
||||
@@ -299,7 +301,7 @@ export class PlanModeController extends Service {
|
||||
execute: async (args, exec) => {
|
||||
// oxlint-disable-next-line typescript/no-non-null-assertion -- conditional admission requires the step's Agent
|
||||
const agent = exec.agent!
|
||||
// Admission follows the selected state; a failed pre-step append can leave it uncommitted.
|
||||
// Admission outlives plan mode and follows the selected state, so check the committed state.
|
||||
if (!this.loggedActive(agent.session)) {
|
||||
throw new Error(`${EXIT_PLAN_MODE} is only available in plan mode`)
|
||||
}
|
||||
@@ -371,7 +373,7 @@ export class PlanModeController extends Service {
|
||||
title: 'Plan review',
|
||||
content: result.content,
|
||||
}),
|
||||
}), { when: ({ agent }) => this.selectedActive(agent.session) })
|
||||
}), { when: ({ agent }) => this.selectedActive(agent.session) || this.planState(agent.session).entered })
|
||||
}
|
||||
|
||||
private loggedActive(session: Session): boolean {
|
||||
|
||||
@@ -33,6 +33,8 @@ export interface PlanUnitState {
|
||||
running: { commandId: CommandId; wanted: boolean } | null
|
||||
/** Active state recorded by the latest `request/header`, or null. */
|
||||
activeAtLastHeader: boolean | null
|
||||
/** Whether a logged `plan/mode` has ever activated plan mode in this Session. */
|
||||
entered: boolean
|
||||
}
|
||||
|
||||
declare module '@deepseek-ai/dsh-session-projection/types' {
|
||||
|
||||
@@ -438,7 +438,7 @@ describe('the boundary flush', () => {
|
||||
})
|
||||
|
||||
describe('the soft layer', () => {
|
||||
it('adds the exit schema together with plan guidance', async () => {
|
||||
it('adds the exit schema with the first plan guidance and keeps it after leaving plan mode', async () => {
|
||||
const ctx = await setup()
|
||||
registerNamedTools(ctx, ['read', 'write'])
|
||||
const agent = await agentWithSession(ctx)
|
||||
@@ -450,6 +450,11 @@ describe('the soft layer', () => {
|
||||
const planAssembly = await assembleFor(ctx, agent)
|
||||
expect(planAssembly.tools.map(tool => tool.name)).toEqual([EXIT_PLAN_MODE, 'read', 'write'])
|
||||
expect(planAssembly.sections.find(section => section.name === 'plan:policy')?.text).toBe(TEST_PLAN_SECTION)
|
||||
|
||||
agent.session.append('plan/mode', { active: false })
|
||||
const leftAssembly = await assembleFor(ctx, agent)
|
||||
expect(leftAssembly.tools).toEqual(planAssembly.tools)
|
||||
expect(leftAssembly.sections.find(section => section.name === 'plan:policy')?.text).toBe('')
|
||||
})
|
||||
|
||||
it('leaves an agent-less assembly untouched', async () => {
|
||||
@@ -506,7 +511,7 @@ describe('the soft layer', () => {
|
||||
expectPlanPtcSdkBindings(sdk)
|
||||
})
|
||||
|
||||
it('includes the PTC exit binding only while plan mode is active', async () => {
|
||||
it('includes the PTC exit binding from the first plan-mode entry', async () => {
|
||||
class FakeRuntime extends PtcRuntime {
|
||||
resolve(request: import('@deepseek-ai/dsh-ptc-runtime').PtcRunRequest): import('@deepseek-ai/dsh-ptc-runtime').PtcRunSpec { return { ...request, cwd: request.cwd ?? process.cwd(), timeoutMs: request.timeoutMs ?? 120_000 } }
|
||||
|
||||
@@ -527,6 +532,9 @@ describe('the soft layer', () => {
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
const planSdk = (await assembleFor(withPlanMode, agent)).sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expectPlanPtcSdkBindings(planSdk)
|
||||
agent.session.append('plan/mode', { active: false })
|
||||
const leftSdk = (await assembleFor(withPlanMode, agent)).sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expect(leftSdk).toBe(planSdk)
|
||||
|
||||
const bare = new Context()
|
||||
await bare.plugin(SystemPrompt)
|
||||
@@ -804,7 +812,7 @@ describe('exit_plan_mode', () => {
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: unknown tool "exit_plan_mode"' }])
|
||||
})
|
||||
|
||||
it('omits and rejects the exit tool outside plan mode', async () => {
|
||||
it('omits and rejects the exit tool before the Session enters plan mode', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
expect((await assembleFor(ctx, agent)).tools.map(tool => tool.name)).not.toContain(EXIT_PLAN_MODE)
|
||||
@@ -813,6 +821,16 @@ describe('exit_plan_mode', () => {
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: unknown tool "exit_plan_mode"' }])
|
||||
})
|
||||
|
||||
it('keeps the exit tool after leaving plan mode and rejects a call outside it', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx, 'left-plan', { active: true })
|
||||
agent.session.append('plan/mode', { active: false })
|
||||
expect((await assembleFor(ctx, agent)).tools.map(tool => tool.name)).toContain(EXIT_PLAN_MODE)
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: exit_plan_mode is only available in plan mode' }])
|
||||
})
|
||||
|
||||
it('admits the exit tool for a selected entry but rejects a call before the entry is logged', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
@@ -944,22 +962,22 @@ describe('exit_plan_mode', () => {
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true, pending: false })
|
||||
})
|
||||
|
||||
it('an approved exit removes the tool and guidance from the next proposed assembly', async () => {
|
||||
it('an approved exit removes the guidance from the next proposed assembly and keeps the tool', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Approve'] })
|
||||
const approved = await callExit(ctx, agent)
|
||||
expect(approved.isError).toBe(false)
|
||||
// Calls of the SAME assistant response were requested under the existing
|
||||
// plan-shaped header. Pending state shapes the proposed next assembly,
|
||||
// tool declarations included; the accepted boundary then commits the
|
||||
// matching durable fold.
|
||||
// plan-shaped header. Pending state shapes the proposed next assembly;
|
||||
// the accepted boundary then commits the matching durable fold. The tool
|
||||
// stays declared because the Session has entered plan mode.
|
||||
expect(foldPlanMode(agent.session.snapshotEvents())).toBe(true)
|
||||
const assembly = await assembleFor(ctx, agent)
|
||||
expect(assembly.tools.some(tool => tool.name === EXIT_PLAN_MODE)).toBe(false)
|
||||
expect(assembly.tools.some(tool => tool.name === EXIT_PLAN_MODE)).toBe(true)
|
||||
expect(assembly.sections.find(section => section.name === 'plan:policy')?.text).toBe('')
|
||||
await boundary(ctx, agent, 'step-start')
|
||||
expect(foldPlanMode(agent.session.snapshotEvents())).toBe(false)
|
||||
const afterExit = await assembleFor(ctx, agent)
|
||||
expect(afterExit.tools.some(tool => tool.name === EXIT_PLAN_MODE)).toBe(false)
|
||||
expect(afterExit.tools).toEqual(assembly.tools)
|
||||
expect(afterExit.sections.find(section => section.name === 'plan:policy')?.text).toBe('')
|
||||
})
|
||||
|
||||
|
||||
@@ -114,6 +114,17 @@ describe('plan projection unit', () => {
|
||||
expect(bench.values().plan).toEqual({ active: false, pending: true })
|
||||
})
|
||||
|
||||
it('records that plan mode was entered and keeps the record after leaving', async () => {
|
||||
const bench = await harness(true)
|
||||
expect(bench.ctx.sessionProjections.checkpoint(bench.session).plan?.val).toMatchObject({ entered: false })
|
||||
commitPlanMode(bench.session, false, 0)
|
||||
expect(bench.ctx.sessionProjections.checkpoint(bench.session).plan?.val).toMatchObject({ entered: false })
|
||||
commitPlanMode(bench.session, true, 1)
|
||||
expect(bench.ctx.sessionProjections.checkpoint(bench.session).plan?.val).toMatchObject({ active: true, entered: true })
|
||||
commitPlanMode(bench.session, false, 2)
|
||||
expect(bench.ctx.sessionProjections.checkpoint(bench.session).plan?.val).toMatchObject({ active: false, entered: true })
|
||||
})
|
||||
|
||||
it('freezes the active state across a request/header into activeAtLastHeader', async () => {
|
||||
const bench = await harness(true)
|
||||
commitPlanMode(bench.session, true, 0)
|
||||
|
||||
@@ -18,7 +18,6 @@
|
||||
- text: .
|
||||
- button "Called tools" [expanded]
|
||||
- 'button "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"'
|
||||
- text: "Tool removed: exit_plan_mode"
|
||||
- 'button "Think The plan was approved. The user''s last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."'
|
||||
- paragraph: DONE
|
||||
- 'button "Open plan: Add `--greeting` flag to CLI"': "Add `--greeting` flag to CLI Plan · Markdown Open"
|
||||
|
||||
@@ -13,18 +13,17 @@
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop."}],"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 policy: ask. 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 policy: ask. 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":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Ask the user to clarify otherwise-unqualified dates and times.\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}}. Ask the user to clarify otherwise-unqualified dates and times.\nElapsed since the preceding model-visible message: {{elapsed}}"}]},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"}
|
||||
{"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","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":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":128000}}
|
||||
{"type":"session/title","data":{"title":"Plan a small change: add","messageSeqs":[11],"source":{"kind":"fallback"}}}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."},{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."},{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:5}}"},"usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52},"stream":[{"type":"chunk","time":1792565774238,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1792565774255,"index":0,"dt":[15,16,15,16,17,15,15,17,16,15,17,15,17,15,17,15,16,15,16,15,16,17,15,15,17,15,17,15,17,16,15,16,17,16,17,16,17,16,16,16,16,15,17,15,15,16,15,16,16,16,16],"texts":["The"," user"," wants"," me"," to"," plan"," a"," small"," change"," to"," add"," a"," `","--","gre","eting","`"," flag"," to"," a"," CLI","."," They"," explicitly"," told"," me"," not"," to"," read"," or"," write"," any"," files",","," and"," to"," call"," exit","_","plan","_mode"," with"," a"," short"," plan","."," Let"," me"," do"," that"," directly","."]},{"type":"chunk","time":1792565775080,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1792565775097,"index":1,"dt":[16,15,16,16,16,16,16,16,15,17,16,16,17,16,15,16,16,17,16,16,15,16,84,16,16,17,16,16,16,17],"texts":["Since"," the"," user"," has"," explicitly"," asked"," me"," not"," to"," read"," or"," write"," any"," files"," and"," to"," go"," straight"," to"," planning",","," I","'ll"," proceed"," with"," `","exit","_","plan","_mode","`."]},{"type":"chunk","time":1792565775661,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1792565775678,"index":2,"dt":[16,17,15,17,15,16,15,15,16,16,15,17,16,15,16,16,16,16,17,15,17,16,16,16,16,15,16,16,16,16,17,16,16,15,16,16,16,16,15,16,16,16,16,16,16,17,16,16,16,15,15,17,17,14,16,17,16,16,17,16,15,16,16,17,16,16,16,16,15,15,17,17,15,16,16,15,17,16,15,17,16,16,15,17,16,15,17,16,16,16,16,16,16,15,17,16,16,15,17,16,15,17,15,16,16,16,16,16,17,16,15,16,16,15,17,16,14,16,16,16,16,15,17,15,16,17,15,16,17,15,16,17,16,16,14,17,16,16,15,17,16,15,17,15,16,17,15,15,16,16,16,17,16,16,16,16,16,15,17,16,16,17,15,15,16,15,16,17,16,16,17,16,16,16,16,15,16,17,16,15,17,16,16,16,16],"id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","args":["","{","\"","plan","\"",": ","\"","#"," Add"," `","--","gre","eting","`"," flag"," to"," CLI","\\n\\n","-"," **","Loc","ate"," the"," CLI"," entry"," point","**"," (","e",".g",".,"," `","cli",".py","`,"," `","main",".go","`,"," `","index",".js","`"," etc",".)"," and"," find"," the"," argument"," parser"," definition"," (","arg","parse",","," click",","," cob","ra",","," y","args",","," or"," similar",").\\n","-"," **","Register"," a"," new"," optional"," string"," argument","**"," named"," `","--","gre","eting","`"," with"," a"," short"," alias"," (`","-","g","`"," if"," available",")"," and"," a"," sensible"," default"," value"," (","e",".g",".,"," `","\\\"","Hello","\\\"","`",").\\n","-"," **","Thread"," the"," parsed"," value","**"," through"," the"," main"," handler"," function"," so"," it"," is"," passed"," where"," the"," greeting"," string"," is"," used"," (","e",".g",".,"," the"," welcome","/","response"," message",").\\n","-"," **","Update"," the"," help"," text","**"," so"," `","--","help","`"," or"," `","-","h","`"," shows"," the"," new"," flag"," with"," its"," description",".\\n","-"," **","No"," tests"," or"," config"," changes","**"," unless"," they"," already"," exist"," and"," directly"," validate"," the"," flag","'s"," presence",".","\"","}"]},{"type":"chunk","time":1792565778646,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me nLine truncated
|
||||
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me not to read or write any files, and to call exit_plan_mode with a short plan. Let me do that directly."},{"type":"text","text":"Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with `exit_plan_mode`."},{"type":"tool-call","id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:5}}"},"usage":{"inputTokens":4529,"outputTokens":303,"cacheReadTokens":640,"reasoningTokens":52},"stream":[{"type":"chunk","time":1790389349382,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1790389349399,"index":0,"dt":[17,15,17,17,17,16,17,16,16,16,16,16,16,15,17,18,14,17,17,15,16,17,16,16,17,16,16,17,14,16,16,16,17,16,16,16,16,16,17,98,16,17,17,16,16,17,17,16,15,16,18],"texts":["The"," user"," wants"," me"," to"," plan"," a"," small"," change"," to"," add"," a"," `","--","gre","eting","`"," flag"," to"," a"," CLI","."," They"," explicitly"," told"," me"," not"," to"," read"," or"," write"," any"," files",","," and"," to"," call"," exit","_","plan","_mode"," with"," a"," short"," plan","."," Let"," me"," do"," that"," directly","."]},{"type":"chunk","time":1790389350326,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1790389350341,"index":1,"dt":[16,16,16,15,17,16,16,16,17,16,17,16,16,16,17,15,17,17,15,17,15,15,16,16,16,17,16,16,15,16],"texts":["Since"," the"," user"," has"," explicitly"," asked"," me"," not"," to"," read"," or"," write"," any"," files"," and"," to"," go"," straight"," to"," planning",","," I","'ll"," proceed"," with"," `","exit","_","plan","_mode","`."]},{"type":"chunk","time":1790389350839,"chunk":{"type":"block-start","index":2,"blockType":"tool-call"}},{"type":"tool-call-chunks","time0":1790389350855,"index":2,"dt":[17,17,15,16,15,17,16,16,17,17,15,16,16,17,17,16,16,17,16,15,16,17,17,16,16,17,16,16,16,15,16,16,17,16,17,16,16,15,16,16,17,16,15,16,16,16,17,16,16,16,17,15,16,16,16,17,16,16,17,17,17,15,17,17,17,16,17,16,17,15,16,16,14,16,16,17,16,16,17,15,16,16,16,16,16,16,15,17,15,16,16,16,16,16,17,17,15,17,16,17,16,16,14,15,16,16,15,17,16,16,16,16,16,16,15,16,16,16,15,16,16,16,16,15,15,17,16,16,16,17,15,17,16,15,16,16,17,15,17,16,17,17,15,17,15,17,14,17,16,16,17,17,15,16,16,17,16,16,16,17,15,16,17,15,17,16,16,16,16,16,17,16,16,16,16,15,17,15,16,16,17,17,16,16,17],"id":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","args":["","{","\"","plan","\"",": ","\"","#"," Add"," `","--","gre","eting","`"," flag"," to"," CLI","\\n\\n","-"," **","Loc","ate"," the"," CLI"," entry"," point","**"," (","e",".g",".,"," `","cli",".py","`,"," `","main",".go","`,"," `","index",".js","`"," etc",".)"," and"," find"," the"," argument"," parser"," definition"," (","arg","parse",","," click",","," cob","ra",","," y","args",","," or"," similar",").\\n","-"," **","Register"," a"," new"," optional"," string"," argument","**"," named"," `","--","gre","eting","`"," with"," a"," short"," alias"," (`","-","g","`"," if"," available",")"," and"," a"," sensible"," default"," value"," (","e",".g",".,"," `","\\\"","Hello","\\\"","`",").\\n","-"," **","Thread"," the"," parsed"," value","**"," through"," the"," main"," handler"," function"," so"," it"," is"," passed"," where"," the"," greeting"," string"," is"," used"," (","e",".g",".,"," the"," welcome","/","response"," message",").\\n","-"," **","Update"," the"," help"," text","**"," so"," `","--","help","`"," or"," `","-","h","`"," shows"," the"," new"," flag"," with"," its"," description",".\\n","-"," **","No"," tests"," or"," config"," changes","**"," unless"," they"," already"," exist"," and"," directly"," validate"," the"," flag","'s"," presence",".","\"","}"]},{"type":"chunk","time":1790389353849,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to plan a small change to add a `--greeting` flag to a CLI. They explicitly told me nLine truncated
|
||||
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_00_TPh5fH8x5kRezK115kgx8155","name":"exit_plan_mode","arguments":"{\"plan\": \"# Add `--greeting` flag to CLI\\n\\n- **Locate the CLI entry point** (e.g., `cli.py`, `main.go`, `index.js` etc.) and find the argument parser definition (argparse, click, cobra, yargs, or similar).\\n- **Register a new optional string argument** named `--greeting` with a short alias (`-g` if available) and a sensible default value (e.g., `\\\"Hello\\\"`).\\n- **Thread the parsed value** through the main handler function so it is passed where the greeting string is used (e.g., the welcome/response message).\\n- **Update the help text** so `--help` or `-h` shows the new flag with its description.\\n- **No tests or config changes** unless they already exist and directly validate the flag's presence.\"}"}}
|
||||
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_00_TPh5fH8x5kRezK115kgx8155"},"toolCallId":"call_00_TPh5fH8x5kRezK115kgx8155","content":[{"type":"text","text":"Plan approved — plan mode exited; carry out the plan starting with your next step."}],"isError":false,"id":"{{message:6}}"}},"sourceEventSeqs":[18],"surfaceOp":"append"}
|
||||
{"type":"step/end","data":{"turn":1,"step":1}}
|
||||
{"type":"plan/mode","data":{"active":false}}
|
||||
{"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:7}}"}},"sourceEventSeqs":[10],"surfaceOp":{"op":"replace","startSeq":10,"endSeq":10}}
|
||||
{"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":"change","startsSeries":true}}
|
||||
{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-removal","toolName":"exit_plan_mode"}],"role":"developer","id":"{{message:8}}"}},"surfaceOp":"append"}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:9}}"},"usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40},"stream":[{"type":"chunk","time":1792565779968,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1792565779984,"index":0,"dt":[16,17,16,16,16,15,17,16,16,16,16,16,16,17,16,17,16,16,16,17,16,16,15,17,16,17,16,16,16,17,16,16,16,16,15,16,16,16,16],"texts":["The"," plan"," was"," approved","."," The"," user","'s"," last"," instruction"," says",":"," \"","Once"," the"," plan"," is"," approved",","," reply"," with"," the"," single"," word"," D","ONE"," and"," stop",".\""," So"," I"," should"," just"," reply"," with"," D","ONE"," and"," stop","."]},{"type":"chunk","time":1792565780629,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1792565780646,"index":1,"dt":[16],"texts":["D","ONE"]},{"type":"chunk","time":1792565780678,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."}}},{"type":"chunk","time":1792565780694,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1792565780710,"chunk":{"type":"usage","usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}}},{"type":"chunk","time":1792565780726,"chunk":{"type":"finish","reason":{"kind":"stop"}}}]},"surfaceOp":"append"}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":"{{tools}}"},"reason":"series"}}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:8}}"},"usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40},"stream":[{"type":"chunk","time":1790389355144,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}},{"type":"reasoning-chunks","time0":1790389355159,"index":0,"dt":[16,16,17,16,17,16,16,16,16,17,15,17,15,16,17,17,16,14,16,16,17,16,16,16,17,15,16,16,19,16,16,17,15,16,16,16,16,16,15],"texts":["The"," plan"," was"," approved","."," The"," user","'s"," last"," instruction"," says",":"," \"","Once"," the"," plan"," is"," approved",","," reply"," with"," the"," single"," word"," D","ONE"," and"," stop",".\""," So"," I"," should"," just"," reply"," with"," D","ONE"," and"," stop","."]},{"type":"chunk","time":1790389355805,"chunk":{"type":"block-start","index":1,"blockType":"text"}},{"type":"text-chunks","time0":1790389355821,"index":1,"dt":[16],"texts":["D","ONE"]},{"type":"chunk","time":1790389355854,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The plan was approved. The user's last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."}}},{"type":"chunk","time":1790389355870,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}},{"type":"chunk","time":1790389355887,"chunk":{"type":"usage","usage":{"inputTokens":441,"outputTokens":43,"cacheReadTokens":4608,"reasoningTokens":40}}},{"type":"chunk","time":1790389355904,"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"}}}
|
||||
Reference in new issue
Block a user