Merge pull request #649 from deepseek-harness/feat/todo-multi-in-progress
feat(todo): allow several in_progress todos at once
This commit is contained in:
Chinesezjc
GitHub
+2
-2
@@ -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/architecture/2026-07-19-package-invariant-runtime-contracts.md
|
||||
2026-07-19-package-invariant-runtime-contracts.md: 40d152b2320ac65f9ea7d8732b1a667236d2780a
|
||||
2026-07-19-package-invariant-runtime-contracts.zh.md: a734b1a3deb739c214d1c4c2565fc697b5e4b89b
|
||||
2026-07-19-package-invariant-runtime-contracts.md: 86d86f69b606c348e85d1ae654b6b35c4326985a
|
||||
2026-07-19-package-invariant-runtime-contracts.zh.md: 386a294b577561d08493a3b2925910ee5ba971b4
|
||||
+1
-1
@@ -50,7 +50,7 @@ The current 103-package workspace has 21 executable companions and 82 justified
|
||||
| `dsh-user-approval` | Approval asked/decided records pair by call and use valid outcomes and policies. |
|
||||
| `dsh-workflow` | Workflow and child-agent start/end events preserve run metadata, identity, outcome, count, and error relations. |
|
||||
| `dsh-tasks` | Current and terminal task snapshots preserve id/kind, owner, status, and timestamp relationships. |
|
||||
| `dsh-tool-todo` | Durable whole-list snapshots use unique trimmed items, closed statuses, and at most one active item. |
|
||||
| `dsh-tool-todo` | Durable whole-list snapshots use unique trimmed items and closed statuses. |
|
||||
| `dsh-time-context` | Plugin-attributed clock readings agree with the session's open turn, next pre-step position, and elapsed baseline; rendered time parses and does not postdate its event. |
|
||||
|
||||
Session-backed companions validate existing durable events when they load, using the prefix preceding each candidate where the relationship depends on event order. Other checks observe the authoritative live event boundary or mutable service result. Validation runs before publication where accepting an invalid event would otherwise commit bad state.
|
||||
|
||||
+1
-1
@@ -50,7 +50,7 @@ Status: implemented
|
||||
| `dsh-user-approval` | approval asked/decided 记录按 call 配对，并使用有效 outcome 和 policy。 |
|
||||
| `dsh-workflow` | 工作流和 child-agent start/end 事件保持 run metadata、身份、outcome、数量和 error 关系。 |
|
||||
| `dsh-tasks` | 当前与终态 task 快照保持 id/kind、owner、status 和 timestamp 关系。 |
|
||||
| `dsh-tool-todo` | 持久化全量快照使用唯一且已 trim 的条目、封闭 status，并且最多有一个活动条目。 |
|
||||
| `dsh-tool-todo` | 持久化全量快照使用唯一且已 trim 的条目和封闭 status。 |
|
||||
| `dsh-time-context` | 标注插件来源的时钟 reading 必须匹配会话当前打开的轮次、下一个步骤开始前的位置和 elapsed baseline；渲染时间必须可解析，且不得晚于对应事件。 |
|
||||
|
||||
基于会话的 companion 在加载时验证已有持久化事件；关系依赖事件顺序时，会使用每个候选事件之前的事件前缀。其他检查观测权威实时事件边界或可变服务结果。如果接受无效事件会提交错误状态，验证就在发布前执行。
|
||||
|
||||
@@ -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/2026-06-29-todo-write-tool.md
|
||||
2026-06-29-todo-write-tool.md: 288932f641a37c13ea6beeb069ac360c4a8447c1
|
||||
2026-06-29-todo-write-tool.zh.md: 2eced2e1670c20726989137d441d1c78df289641
|
||||
2026-06-29-todo-write-tool.md: c4cf64b7876bd8b80df80fe6fc27005715f96b5e
|
||||
2026-06-29-todo-write-tool.zh.md: 1f797c5517df8affd66addecf2a8db43c1da3332
|
||||
@@ -6,7 +6,7 @@ English | [中文](2026-06-29-todo-write-tool.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The harness gives the model bash and subagent tools but no way to record a structured task list. A todo list serves two co-equal purposes: it steers the model to plan multi-step work and keep the active task unambiguous (at most one active, exactly one while work remains), and it gives an interactive host a live progress checklist. Every reference coding agent surveyed (claude-code, opencode, codex, oh-my-pi, pi) ships some form of this; the harness had nothing.
|
||||
The harness gives the model bash and subagent tools but no way to record a structured task list. A todo list serves two co-equal purposes: it steers the model to plan multi-step work and keep the active work unambiguous, and it gives an interactive host a live progress checklist. Every reference coding agent surveyed (claude-code, opencode, codex, oh-my-pi, pi) ships some form of this; the harness had nothing.
|
||||
|
||||
## Decision
|
||||
|
||||
@@ -34,7 +34,7 @@ Each list belongs to the calling agent session, and non-agent calls are rejected
|
||||
|
||||
### Validation: the cheap middle
|
||||
|
||||
The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content` and more than one `in_progress` task. claude-code leaves single-in-progress to the prompt; oh-my-pi enforces it in code. We take the middle: enforce the cheap invariants that make a plan *coherent* (no blank tasks, no dupes, at most one active), but leave ordering and the discipline of keeping the list current to the model via the tool description. A rejected write returns an `isError` result so the model self-corrects.
|
||||
The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content` and, when `allowParallelInProgress` is `false`, more than one active task. Ordering and keeping the list current remain model disciplines expressed in the tool description. A rejected write returns an `isError` result so the model self-corrects. The required deployment policy and the durable invariant's independence from it are owned by the [parallel in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md).
|
||||
|
||||
## Why no cordis-catalog entry / no `@mode`
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ Status: implemented
|
||||
|
||||
## 问题
|
||||
|
||||
harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结构化的任务列表。todo 列表有两个同等重要的用途：引导模型规划多步骤工作并保持当前活跃任务明确（最多一个活跃，有剩余工作时恰好一个）；同时为交互式宿主提供实时进度清单。调研的所有参考编码 agent（智能体），包括 claude-code、opencode、codex、oh-my-pi 和 pi，都提供了某种形式的此功能；本 harness 此前没有。
|
||||
harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结构化的任务列表。todo 列表有两个同等重要的用途：引导模型规划多步骤工作并保持当前活跃任务明确；同时为交互式宿主提供实时进度清单。调研的所有参考编码 agent（智能体），包括 claude-code、opencode、codex、oh-my-pi 和 pi，都提供了某种形式的此功能；本 harness 此前没有。
|
||||
|
||||
## 决策
|
||||
|
||||
@@ -34,7 +34,7 @@ claude-code V1 的条目是 `{ content, status, activeForm }`；后来（V2）
|
||||
|
||||
### 校验：低成本的中间路线
|
||||
|
||||
schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重复的 `content`，以及超过一个 `in_progress` 任务。claude-code 将单一 in_progress 交给提示词约束；oh-my-pi 在代码中强制。我们取中间路线：强制执行使计划*连贯*的低成本不变式（无空任务、无重复、最多一个活跃），但将排序和保持列表最新的纪律通过工具描述交给模型。被拒绝的写入返回 `isError` 结果，使模型自行修正。
|
||||
schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重复的 `content`，并在 `allowParallelInProgress` 为 `false` 时拒绝超过一个活跃任务。排序和保持列表最新仍通过工具描述交给模型。被拒绝的写入返回 `isError` 结果，使模型自行修正。必填的部署策略及持久日志不变式独立于该策略这一约定，由[并行 in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md) 负责。
|
||||
|
||||
## 为何没有 cordis-catalog 条目 / 没有 `@mode`
|
||||
|
||||
|
||||
@@ -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/2026-07-23-web-todo-display.md
|
||||
2026-07-23-web-todo-display.md: d5939c0fa6ab83a61f1932622c4b6a150ccaded7
|
||||
2026-07-23-web-todo-display.zh.md: b1ecf679efe81016e00c5c1221c04730b3ce98bb
|
||||
2026-07-23-web-todo-display.md: 9e6e4914cd24d1db9271baa3d3fb6fdc56a9ac65
|
||||
2026-07-23-web-todo-display.zh.md: 5a5ac554b37c255a7d8c1ce821ebeb1b3f9f091f
|
||||
@@ -18,11 +18,11 @@ Consume `todo/write` as a Session side effect, not a surface node, and render it
|
||||
|
||||
### TodoPanel: the durable list as a persistent strip
|
||||
|
||||
The panel mounts through the `conversation.input.dock` slot (a plain registrant plugin, `todoDockEntry`, using `ctx.slots.inject` with no `ConversationService` edge, `order: -1` above the queue rows), hidden while empty, collapsible to a header of title + `"<done>/<total> tasks · <n> in progress"` (no in-progress content hint when collapsed). Status glyphs are the figma todo set (green check ring / blue fading ring / dashed pending ring) on a tip-surface card (`--dsw-specific-tip`, 14px radius, `width: calc(100% - 88px)` / `max-width: 776px` centered; InputBar top pad 6px is the gap to the composer card). It reads `snapshot.todos` via the standard-kit `useSession` hook the dock entry receives — no store, no service, no ctx. The inner component stays props-complete and framework-free; the dock adapter is a one-line wrapper.
|
||||
The panel mounts through the `conversation.input.dock` slot (a plain registrant plugin, `todoDockEntry`, using `ctx.slots.inject` with no `ConversationService` edge, `order: 0` above the queue rows), hidden while empty, collapsible to a header of title + `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted; no in-progress content hint when collapsed). Status glyphs are the figma todo set (green check ring / blue fading ring / dashed pending ring) on a tip-surface card (`--dsw-specific-tip`, 14px radius, `width: calc(100% - 88px)` / `max-width: 776px` centered; InputBar top pad 6px is the gap to the composer card). It reads the host-computed `todos` projection via the standard-kit `useProjection` hook the dock entry receives — no store, no service, no ctx. The inner component stays props-complete and framework-free; the dock adapter is a one-line wrapper.
|
||||
|
||||
### TodoRow: the per-call row through the keyed toolview slot
|
||||
|
||||
The dedicated `todo_write` chat row is a plain registrant plugin (`todoToolview`, mounted from `apply`) that registers into the keyed `conversation.chat.toolview` slot through `ctx.slots.inject`, the same declaration-lifetime posture as the bash sample but a product registration. The summary derives from call args (`N/M done · active item`); unparseable args fall back to the generic row summary; clicking opens the details column with the raw args. No `ToolEventView` is added for todo — presentation is client-owned, and the durable list renders from the session event, not the tool card.
|
||||
The dedicated `todo_write` chat row is a plain registrant plugin (`todoToolview`, mounted from `apply`) that registers into the keyed `conversation.chat.toolview` slot through `ctx.slots.inject`, the same declaration-lifetime posture as the bash sample but a product registration. The summary derives from call args (`N/M done · first active item`, with a `+<n>` count of the other active ones in `ToolRow`'s non-shrinking `summarySuffix` slot); unparseable args fall back to the generic row summary; clicking opens the details column with the raw args. No `ToolEventView` is added for todo — presentation is client-owned, and the durable list renders from the session event, not the tool card.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
@@ -33,4 +33,4 @@ The dedicated `todo_write` chat row is a plain registrant plugin (`todoToolview`
|
||||
|
||||
## Consequences
|
||||
|
||||
Replay correctness is owned by one code path: any future change to window rebuild keeps todos consistent for free, and the fixture (fx-alpha turn 65) plus the assembled keyless snapshot (`apps/web/tests/todo-display.snapshot.ts`) pin the full chain (row summary and state, dock panel content, collapse round-trip) over the built client graph. `todos` is a required `ConversationSnapshot` field, so scripted fakes in specs must carry it. The TUI panel shares the same turn-scoped lifetime (the automation-only ACP bridge deliberately omits todo presentation); the web surfaces render the same event, adding one wire field and no new event type. That field is how cold-load reconstruction stays host-backed: the tail history page carries `todos` — the full-log standing plan (latest `todo/write` with no later `turn/start`), computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan when it still stands and the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, clears on a later `turn/start`, and resets to empty when a tail response carries no projection.
|
||||
Replay correctness is owned by one code path: any future change to window rebuild keeps todos consistent for free, and the fixture (fx-alpha turn 71) plus `packages/client/ui-conversation/tests/todo-panel.spec.tsx` pin the full chain (row summary and state, dock panel content, collapse round-trip). `todos` is a required `ConversationSnapshot` field, so scripted fakes in specs must carry it. The automation-only ACP bridge deliberately omits todo presentation; the web surfaces render the same event, adding one wire field and no new event type. That field is how cold-load reconstruction stays host-backed: the tail history page carries `todos` — the full-log standing plan (latest `todo/write` with no later `turn/start`), computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan when it still stands and the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, clears on a later `turn/start`, and resets to empty when a tail response carries no projection.
|
||||
@@ -18,11 +18,11 @@ Status: implemented
|
||||
|
||||
### TodoPanel：持久化列表作为一条常驻横条
|
||||
|
||||
面板经 `conversation.input.dock` slot 挂载（普通注册者插件 `todoDockEntry` 使用 `ctx.slots.inject`，不依赖 `ConversationService`，`order: -1` 排在队列条上方），空列表时隐藏，可折叠为标题加 `"<已完成>/<总数> tasks · <n> in progress"` 的表头（折叠态不再附带进行中条目正文）。状态图标为 figma todo 套件（绿色勾选环／蓝色渐隐环／虚线未开始环），卡片使用 tip 表面（`--dsw-specific-tip`、14px 圆角、`width: calc(100% - 88px)`／`max-width: 776px` 居中；InputBar 顶部 6px 内边距是到输入卡的间距）。它经 dock entry 收到的标准件 `useSession` hook 读取 `snapshot.todos`——无 store、无 service、无 ctx。内部组件保持 props 完备且框架无关；dock 适配件只是一行包装。
|
||||
面板经 `conversation.input.dock` slot 挂载（普通注册者插件 `todoDockEntry` 使用 `ctx.slots.inject`，不依赖 `ConversationService`，`order: 0` 排在队列条上方），空列表时隐藏，可折叠为标题加以 `·` 连接的各状态计数的表头（本地化，形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略；折叠态不再附带进行中条目正文）。状态图标为 figma todo 套件（绿色勾选环／蓝色渐隐环／虚线未开始环），卡片使用 tip 表面（`--dsw-specific-tip`、14px 圆角、`width: calc(100% - 88px)`／`max-width: 776px` 居中；InputBar 顶部 6px 内边距是到输入卡的间距）。它经 dock entry 收到的标准件 `useProjection` hook 读取 host 计算的 `todos` 投影——无 store、无 service、无 ctx。内部组件保持 props 完备且框架无关；dock 适配件只是一行包装。
|
||||
|
||||
### TodoRow：经 keyed toolview slot 的逐调用行
|
||||
|
||||
专用的 `todo_write` 对话行是一个普通注册者插件（`todoToolview`，由 `apply` 挂载），经 `ctx.slots.inject` 注册进 keyed 的 `conversation.chat.toolview` slot，遵循与 bash 样例相同的声明生命周期，但属产品级注册。摘要由调用 args 推导（`N/M done · active item`）；无法解析的 args 回退到通用行摘要；点击会以原始 args 打开 details 列。todo 不新增任何 `ToolEventView`——呈现归客户端所有，常驻列表从会话事件渲染，而非工具卡。
|
||||
专用的 `todo_write` 对话行是一个普通注册者插件（`todoToolview`，由 `apply` 挂载），经 `ctx.slots.inject` 注册进 keyed 的 `conversation.chat.toolview` slot，遵循与 bash 样例相同的声明生命周期，但属产品级注册。摘要由调用 args 推导（`N/M done · first active item`，其余活跃项的 `+<n>` 计数放在 `ToolRow` 的不收缩 `summarySuffix` 位里）；无法解析的 args 回退到通用行摘要；点击会以原始 args 打开 details 列。todo 不新增任何 `ToolEventView`——呈现归客户端所有，常驻列表从会话事件渲染，而非工具卡。
|
||||
|
||||
## 考虑过的替代方案
|
||||
|
||||
@@ -33,4 +33,4 @@ Status: implemented
|
||||
|
||||
## 后果
|
||||
|
||||
回放正确性由一条代码路径掌管：未来对窗口重建的任何改动都会自然保持 todos 一致；fx-alpha 第 65 轮的 fixture（测试前置数据）加上组装后的无密钥快照（`apps/web/tests/todo-display.snapshot.ts`）在构建后的完整客户端依赖图中固定整条链（行摘要与状态、dock 面板内容、折叠往返）。`todos` 是 `ConversationSnapshot` 的必填字段，所以 spec 里脚本化的 fake 必须带上它。TUI 面板共用同一按轮次界定的生命周期（自动化专用的 ACP 桥接刻意不做 todo 呈现）；Web 各面渲染同一个事件，只新增一个协议字段，不新增事件类型。这个由 host 提供的字段正是冷加载重建的依据：history 尾页附带 `todos`——全量 log 上当前有效的计划（其后没有更晚 `turn/start` 的最近一次 `todo/write`），独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时若计划仍然有效且最后一次写入落在窗口之前，计划也照常恢复；该值跨往前翻页保留，之后的任何写入照常覆盖，更晚的 `turn/start` 会清空，而尾页响应不带投影时复位为空。
|
||||
回放正确性由一条代码路径掌管：未来对窗口重建的任何改动都会自然保持 todos 一致；fx-alpha 第 71 轮的 fixture（测试前置数据）加上 `packages/client/ui-conversation/tests/todo-panel.spec.tsx` 固定整条链（行摘要与状态、dock 面板内容、折叠往返）。`todos` 是 `ConversationSnapshot` 的必填字段，所以 spec 里脚本化的 fake 必须带上它。自动化专用的 ACP 桥接刻意不做 todo 呈现；Web 各面渲染同一个事件，只新增一个协议字段，不新增事件类型。这个由 host 提供的字段正是冷加载重建的依据：history 尾页附带 `todos`——全量 log 上当前有效的计划（其后没有更晚 `turn/start` 的最近一次 `todo/write`），独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时若计划仍然有效且最后一次写入落在窗口之前，计划也照常恢复；该值跨往前翻页保留，之后的任何写入照常覆盖，更晚的 `turn/start` 会清空，而尾页响应不带投影时复位为空。
|
||||
@@ -0,0 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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/2026-07-26-todo-parallel-in-progress.md
|
||||
2026-07-26-todo-parallel-in-progress.md: 2805ef894050d1b1cffe06fce59a4984d463f8d1
|
||||
2026-07-26-todo-parallel-in-progress.zh.md: 16b32daa05b10f24eacde4cec9622b2159cdef09
|
||||
@@ -0,0 +1,54 @@
|
||||
# Agent Note: Allow several `in_progress` todos at once
|
||||
|
||||
Status: implemented
|
||||
|
||||
English | [中文](2026-07-26-todo-parallel-in-progress.zh.md)
|
||||
|
||||
## Problem
|
||||
|
||||
The [original `todo_write` design](2026-06-29-todo-write-tool.md) enforced at most one `in_progress` task per list, both in `execute` and in the durable-log invariant. That invariant assumes sequential work, but the harness runs genuinely parallel work — concurrent subagents through the delegation tool, background bash commands, workflow fan-out — and a list that can name only one active task cannot represent it. The model was forced to either mislabel parallel tasks as `pending` or merge them into one vague item, and the UI progress checklist under-reported what was actually running.
|
||||
|
||||
## Decision
|
||||
|
||||
Make the single-`in_progress` cap a deployment policy instead of a fixed rule, requiring every composition to choose:
|
||||
|
||||
- `packages/todo/tool-todo/src/index.ts` gains the required `Config.allowParallelInProgress` field. At `true`, `execute` accepts any number of active items and the description instructs the model to mark every actively-worked task — several during parallel work, one for sequential work — keeping at least one while work remains. At `false`, the description asks for exactly one and `execute` rejects a call marking more.
|
||||
- The durable-log invariant in `packages/todo/tool-todo/src/invariant.ts` no longer rejects snapshots with several active items, and does not follow the config, so previously-persisted logs are unaffected and parallel snapshots replay cleanly under either policy.
|
||||
|
||||
The remaining coded invariants are unchanged: non-empty trimmed unique `content`, valid status enum. This supersedes the "at most one active" clause of the [original design's validation decision](2026-06-29-todo-write-tool.md); the rest of that Agent Note (whole-list replace, log-backed state, single owner) stands.
|
||||
|
||||
## Why guidance, not a parallelism-aware invariant
|
||||
|
||||
A coded invariant can only see the list, not the runtime: whether two `in_progress` items are legitimate depends on whether work is actually running concurrently, which the tool cannot observe. Enforcing a cap was therefore wrong in exactly the cases parallelism made it matter, and any replacement (for example, capping active items at the live subagent count) would couple the tool to runtimes it deliberately knows nothing about. The discipline of matching `in_progress` marks to genuinely concurrent work moves to the tool description, the same place ordering and list freshness already live.
|
||||
|
||||
## The policy is a deployment choice
|
||||
|
||||
Whether concurrent active tasks are legitimate depends on runtime concurrency the tool cannot observe — but whether a deployment's agents ever run work concurrently is knowable at composition time. That makes the policy a required `Config` field rather than a constant or default: every cordis.yml composition sets `allowParallelInProgress` deliberately, choosing `true` for agents that may fan out work or `false` for the single-active discipline.
|
||||
|
||||
The flag moves the model-facing instruction and the accepted input together. Splitting them would be the bug: a description asking for one active task while `execute` accepts several teaches the model a rule the tool does not hold, and the reverse rejects calls the description invited. Only the active-status clause of the description varies, because that is the only instruction the policy changes.
|
||||
|
||||
The durable-log invariant deliberately does NOT follow the flag. A log written while parallel work was allowed must still replay after a deployment tightens the policy, so tying `invariant.ts` to the current config would reject history that was valid when it was written. The invariant stays silent on the active count; the tool is where the policy applies, at the moment of the write.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
- **Keep the cap and add an explicit parallel opt-in flag** — an extra argument on every call to serve the common case; the flag would be noise for sequential work and still unverifiable.
|
||||
- **Cap active items at a configured maximum** — any fixed number is arbitrary. This is why the config field is a boolean policy switch and not a count: "may several tasks be active" is a property of the deployment, while "at most N" invents a threshold nothing can justify.
|
||||
- **Hardcode the parallel policy** — the first revision of this branch did, which is what made `allowParallelInProgress` necessary: a deployment running strictly sequential agents had no way back to the discipline it wanted.
|
||||
|
||||
## The display surfaces are part of the change
|
||||
|
||||
Lifting the cap makes a list shape reachable that no renderer had ever received, so this branch stacks on the [web todo display](2026-07-23-web-todo-display.md) rather than landing beside it: both change `tool-todo`, and the GUI is where a parallel plan becomes visible. Two web sites derived their one-line summary with `todos.find(t => t.status === 'in_progress')` — the collapsed plan-strip header and the `todo_write` row — and under the old cap that `find` was total, since at most one item could match. With several active it silently dropped every active item but the first: a four-item plan with three running tasks collapsed to the name of one, and the row read `1/4 已完成 · <one task>` while two others were in flight. The expanded list was always correct (it maps every item), which is why neither PR's tests caught it — only the collapsed header and the row lost information. The panel redesign in [#740](https://github.com/deepseek-harness/deepseek-harness/pull/740) has since replaced the collapsed header's named hint with `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted), which reports parallel work correctly and needs no name to truncate; the row is the one site this branch still had to fix.
|
||||
|
||||
The row takes `planSummary` in `toolviews/plan-summary.ts`. It names the first active item and counts the rest, so the row reports how many tasks are running instead of implying one. Naming every active item was rejected: the row is a single line, and an unbounded join would overflow it — the count degrades predictably where a list does not. The derivation sits inside the toolviews domain rather than in `contract/`, the inter-domain face: the panel computes its own counts inline and shares nothing with the row, so a contract module would declare a sharing relationship that no longer exists.
|
||||
|
||||
`planSummary` returns the name and the count as separate fields rather than one joined string, because the row truncates its summary with `overflow: hidden` / `text-overflow: ellipsis`. A count appended to the task name sits at the far end of the truncatable text, so exactly the narrow viewports and long task names that make the count informative are the ones that clip it away, leaving a parallel plan indistinguishable from a sequential one. The row therefore hands the count to the shared `ToolRow` as `summarySuffix`, a non-shrinking slot beside the ellipsized summary text; a pre-joined string could not express that split, and pushing the count in front of the name was rejected because the task name is what the reader is looking for first.
|
||||
|
||||
`summarySuffix` is a slot on `ToolRow` rather than markup owned by the todo row: every toolview renders through that shared component, whose `summary` is a plain ellipsized string with no place for a fragment that must survive the clip. Sitting outside the `.summary` rule, the suffix repeats that rule's `font-size` and `line-height` — the web shell leaves body text at the browser default rather than the row's 14px, so an unstyled span renders visibly larger than the text beside it on a 24px row. An error row drops the suffix, because its collapsed summary is the failure line rather than anything derived from the call args.
|
||||
|
||||
## Deferred
|
||||
|
||||
Two review findings are recorded here rather than fixed on this branch. The `summarySuffix` span carries no accessible name, so a screen reader reads the count without its noun (`… 实现 fixture 样本 +1`); naming it introduces localized copy with its own test contract, which belongs to an accessibility pass over the whole `ToolRow` summary line rather than to one row. And when the *first* active item's content is unusable — missing, mistyped, or blank once trimmed — the row drops the active clause and the count with it, so a parallel plan renders as bare counts; skipping forward to the first usable active item was rejected because call args are an explicitly unvalidated boundary where model order is the only ordering the row can honour, and dropping the unusable clause alone keeps the `done`/`total` counts, which are trustworthy regardless.
|
||||
|
||||
## Consequences
|
||||
|
||||
A todo list can now faithfully mirror parallel execution, and every surface renders several active markers at once: the plan strip's header counts the active items, and the row needed the derivation above. A composition that sets `allowParallelInProgress: true` no longer rejects a formerly-invalid snapshot shape; one that sets `false` keeps the old rejection, and the durable-log invariant accepts both. The model-facing description changed, which re-recorded the tool-catalog page and every snapshot sidecar carrying the todo schema. No count is recorded here: the set grows with every pinning scenario that lands, and the two point-in-time censuses this note previously carried were both stale within days. The operative rule is that a branch changing the tool description must refresh whichever sidecars landed after it branched — including the numbered `tool-schemas.<n>.expected.json` files pinning a subagent class, whose schemas the parent scenario does not cover — and `pnpm run test:snapshot:refresh` does it keylessly over the whole corpus. The web fixture's todo sample now runs two items `in_progress`, so both fixture-driven surfaces render a parallel plan. `packages/client/ui-conversation/tests/todo-panel.spec.tsx` pins the row summary and the plan strip over src, the ACP `todo-write` scenario records a three-todo plan with two active, and `apps/web/tests/todo-row.snapshot.ts` pins both surfaces in the assembled application — booted from the built `packages/client/*/lib/client.js` bundles, so it is the one place the keyed registration and the bundled wiring are under test. That last file records `summary`, `suffix`, and the strip's header as separate fields, so folding the `+N` count back into the summary string changes the expected output even though the concatenated text would read the same.
|
||||
@@ -0,0 +1,54 @@
|
||||
# Agent Note: 允许同时存在多个 `in_progress` todo
|
||||
|
||||
Status: implemented
|
||||
|
||||
[English](2026-07-26-todo-parallel-in-progress.md) | 中文
|
||||
|
||||
## 问题
|
||||
|
||||
[原始 `todo_write` 设计](2026-06-29-todo-write-tool.md)在 `execute` 和持久日志不变式中都强制每个列表至多一个 `in_progress` 任务。该不变式假设工作是顺序进行的，但 harness 会运行真正并行的工作（通过委派工具启动的并发 subagent、后台 bash 命令、工作流扇出），而一个只能标出单个活跃任务的列表无法表示这种情况。模型被迫要么把并行任务错误标记为 `pending`，要么把它们合并成一个含糊的条目，导致 UI 进度清单少报了实际正在运行的工作。
|
||||
|
||||
## 决策
|
||||
|
||||
把单一 `in_progress` 上限从固定规则改为部署策略，并要求每个组合都作出选择：
|
||||
|
||||
- `packages/todo/tool-todo/src/index.ts` 新增必填的 `Config.allowParallelInProgress` 字段。为 `true` 时，`execute` 接受任意数量的活跃条目，描述指示模型把每个正在处理的任务标记为 `in_progress`（并行工作时可以有多个，顺序工作时只有一个），并在仍有工作未完成时至少保留一个；为 `false` 时，描述要求恰好一个，`execute` 拒绝标记更多的调用。
|
||||
- `packages/todo/tool-todo/src/invariant.ts` 中的持久日志不变式不再拒绝含多个活跃条目的快照，且不跟随该配置，因此此前持久化的日志不受影响，并行快照在任一策略下都能干净回放。
|
||||
|
||||
其余编码的不变式保持不变：`content` 去除首尾空白后非空且唯一、status 为合法枚举值。本决定取代[原始设计的校验决策](2026-06-29-todo-write-tool.md)中「至多一个活跃」的条款；该 Agent Note 的其余部分（整列表替换、日志支撑的状态、单一所有者）依然成立。
|
||||
|
||||
## 为何用指引而非感知并行的不变式
|
||||
|
||||
编码的不变式只能看到列表，看不到运行时：两个 `in_progress` 条目是否合理，取决于工作是否真的在并发运行，而这一点工具无法观测。因此，恰恰在并行让上限变得重要的场景里，强制上限反而是错的；任何替代方案（例如把活跃条目数限制为在线 subagent 的数量）都会把工具耦合到它有意一无所知的运行时上。把 `in_progress` 标记与真正并发的工作对应起来这一纪律，转移到工具描述中，也就是排序与列表新鲜度已经所在的地方。
|
||||
|
||||
## 该策略是部署层的选择
|
||||
|
||||
并发的活跃任务是否合理，取决于工具无法观测的运行时并发情况——但一个部署的 agent 是否会并发展开工作，在组装期就是可知的。因此该策略是必填的 `Config` 字段，而非常量或默认值：每个 cordis.yml 组合都会有意设置 `allowParallelInProgress`，为可能并行展开工作的 agent 选择 `true`，或为单活跃项纪律选择 `false`。
|
||||
|
||||
该开关会同时改变面向模型的指令与接受的输入。把两者拆开才是 bug：描述要求只保留一个活跃任务、而 `execute` 却接受多个，等于教给模型一条工具并不遵守的规则；反过来则会拒绝描述所邀请的调用。描述中只有活跃状态那一句会变化，因为这是该策略唯一改变的指令。
|
||||
|
||||
持久日志不变式刻意**不**跟随该开关。在允许并行时写下的日志，在部署收紧策略之后仍必须可回放，因此把 `invariant.ts` 绑定到当前配置会拒绝在写入当时合法的历史。不变式对活跃数量保持沉默；策略生效之处是工具，时机是写入的那一刻。
|
||||
|
||||
## 曾考虑的替代方案
|
||||
|
||||
- **保留上限并增加一个显式的并行 opt-in 标志**——为服务常见场景而给每次调用增加一个额外参数；这个标志对顺序工作而言只是噪声，而且仍然无法验证。
|
||||
- **把活跃条目限制在一个可配置的上限内**——任何固定数字都是任意的。这正是该配置字段是布尔策略开关而非数量的原因：「是否允许多个任务同时活跃」是部署的属性，而「最多 N 个」凭空发明了一个无从论证的阈值。
|
||||
- **把并行策略硬编码**——本分支的第一版就是如此，这也是 `allowParallelInProgress` 之所以必要的原因：运行严格顺序 agent 的部署没有任何办法回到它想要的纪律。
|
||||
|
||||
## 展示面是本次改动的一部分
|
||||
|
||||
解除上限使一种此前任何渲染器都不曾收到的列表形状变得可达，因此本分支 stack（栈叠）在 [web todo 展示](2026-07-23-web-todo-display.md)之上，而不是与之并行落地：两者都改 `tool-todo`，而 GUI 正是并行计划变得可见的地方。web 有两处用 `todos.find(t => t.status === 'in_progress')` 推导单行摘要——折叠态的计划横条表头与 `todo_write` 工具行——在旧上限下这个 `find` 是完备的，因为最多只能有一个条目匹配。一旦有多个活跃项，它会静默丢掉除第一个之外的全部活跃条目：一个四条目、三个任务在跑的计划折叠后只显示其中一个的名字，工具行读作 `1/4 已完成 · <一个任务>`，而另外两个仍在进行。展开态的列表始终正确（它遍历每个条目），这也是两个 PR 的测试都没抓到它的原因——只有折叠表头与工具行丢失了信息。其后 [#740](https://github.com/deepseek-harness/deepseek-harness/pull/740) 的面板重做已把折叠表头的具名提示换成以 `·` 连接的各状态计数（本地化后形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略），它能正确报告并行工作，且不需要任何可被截断的名字；工具行才是本分支仍需修的那一处。
|
||||
|
||||
工具行改用 `toolviews/plan-summary.ts` 中的 `planSummary`。它给出第一个活跃条目，并计数其余活跃项，因此工具行报告的是有多少任务在跑，而不是暗示只有一个。列出全部活跃条目被否决了：工具行是单行，无上界的拼接会溢出——在列表做不到的地方，计数能够可预测地降级。该推导放在 toolviews 域内而非 `contract/`（域间共享面）：面板自行内联计算其计数，与工具行不共享任何东西，因此放进 contract 会声明一种已不存在的共享关系。
|
||||
|
||||
`planSummary` 把任务名与计数作为两个独立字段返回，而不是一个拼好的字符串，因为工具行用 `overflow: hidden` / `text-overflow: ellipsis` 截断其摘要文本。计数接在任务名之后时位于可截断文本的末端，于是恰恰是让计数变得有意义的那些场景——窄视口、长任务名——会把它裁掉，让并行计划看起来与顺序计划无异。因此工具行把计数交给共享的 `ToolRow`，作为 `summarySuffix`——一个紧邻被省略号截断的摘要文本、且不会收缩的槽位；一个预先拼好的字符串无法表达这个切分，而把计数放到任务名之前也被否决了：读者首先要找的是任务名。
|
||||
|
||||
`summarySuffix` 是 `ToolRow` 上的槽位，而不是 todo 工具行自有的标记：每个 toolview 都经由这个共享组件渲染，而它的 `summary` 是一个会被省略号截断的普通字符串，容不下一个必须挺过截断的片段。该后缀落在 `.summary` 规则之外，因此重复了该规则的 `font-size` 与 `line-height`——Web 外壳把正文字号留在浏览器默认值而非该行的 14px，所以未加样式的 span 会明显大于同一 24px 行内与之并列的文本。错误行会丢弃该后缀，因为它折叠态的摘要是失败行，而非任何由调用 args 推导出的内容。
|
||||
|
||||
## 暂缓项
|
||||
|
||||
两条 review 结论在此记录而非在本分支修复。`summarySuffix` 这个 span 没有无障碍名称，屏幕阅读器读出的数量缺少它所修饰的名词（`… 实现 fixture 样本 +1`）；为它命名会引入带自身测试契约的本地化文案，这属于对整条 `ToolRow` 摘要行做的无障碍专项，而不属于某一行。以及，当*第一个*活跃条目的 content 不可用时——缺失、类型不对、或 trim 后为空——行会连同数量一起丢掉活跃子句，于是并行计划渲染成裸计数；向后跳到第一个可用活跃条目的方案被否决，因为调用 args 是一处明确未经校验的边界，模型给出的顺序是该行唯一能遵循的顺序，而只丢掉不可用的那个子句可以保住 `done`/`total` 计数——这两个数无论如何都是可信的。
|
||||
|
||||
## 后果
|
||||
|
||||
现在 todo 列表可以忠实反映并行执行，并且每个展示面都能一次渲染多个活跃标记：计划横条的表头会计数活跃条目，工具行则需要上述推导。设置 `allowParallelInProgress: true` 的组合不再拒绝一种此前无效的快照形状；设置为 `false` 的组合仍保留旧的拒绝行为，而持久日志不变式两者都接受。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个带有 todo schema 的快照 sidecar。此处不记录数量：该集合会随每个新落地的 pin 场景增长，而本 Note 先前记过的两次点时刻计数都在几天内失实。有效规则是：改动工具描述的分支必须刷新它分叉之后落地的那些 sidecar —— 包括固定 subagent 类工具的编号文件 `tool-schemas.<n>.expected.json`，其 schema 不被父场景覆盖 —— `pnpm run test:snapshot:refresh` 可以无 key 地对整个语料完成刷新。web fixture 的 todo 样本现在有两个条目处于 `in_progress`，因此两个由 fixture 驱动的展示面渲染的都是并行计划。`packages/client/ui-conversation/tests/todo-panel.spec.tsx` 在 src 上固定工具行摘要与计划横条，ACP `todo-write` 场景录制的是三条目、两个活跃的计划，而 `apps/web/tests/todo-row.snapshot.ts` 在组装后的应用中固定这两个面——它从构建产物 `packages/client/*/lib/client.js` 启动，因此是唯一覆盖 keyed 注册与打包接线的地方。该文件把 `summary`、`suffix` 与横条表头记录为独立字段，因此即便拼接后的文本读起来一样，把 `+N` 计数折回摘要字符串也会改变预期输出。
|
||||
@@ -0,0 +1,133 @@
|
||||
// Shared scaffolding for the assembled-jsdom snapshots: the real built
|
||||
// `packages/client/*/lib/client.js` artifacts booted through AppWebEntry's
|
||||
// ModuleLoader path (loadBundle) against the keyless FixtureApiClient
|
||||
// transport. Every file that mounts this graph needs the same boot entry list,
|
||||
// the same bundle map, the same jsdom globals, and the same mount call, and
|
||||
// differs only in what it asserts afterwards, so the scaffolding lives here.
|
||||
//
|
||||
// Keyless and deterministic: the fixture is the fake server, so nothing here
|
||||
// reaches a model or the network.
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { join } from 'node:path'
|
||||
import { act, cleanup } from '@testing-library/react'
|
||||
import { afterEach, beforeEach, vi } from 'vitest'
|
||||
import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client'
|
||||
import { AppWebEntry } from '@deepseek-ai/dsh-client-web'
|
||||
|
||||
/** Boot entries for the minimal assembled graph, each carrying the workspace directory its bundle is read from. */
|
||||
const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
|
||||
{ id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{
|
||||
id: '@deepseek-ai/dsh-client-ui-workspace',
|
||||
dir: 'ui-workspace',
|
||||
url: '/plugins/ui-workspace.js',
|
||||
rev: 'fx',
|
||||
inject: [
|
||||
'@deepseek-ai/dsh-client-runtime',
|
||||
'@deepseek-ai/dsh-client-ui-conversation',
|
||||
'@deepseek-ai/dsh-client-ui-sidebar',
|
||||
],
|
||||
},
|
||||
{ id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', url: '/plugins/ui-trajectory.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
|
||||
]
|
||||
|
||||
const bundles = new Map(PLUGINS.map(plugin => [
|
||||
plugin.url,
|
||||
readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
|
||||
]))
|
||||
|
||||
interface FixtureWindow extends Window {
|
||||
__DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
|
||||
__ModuleLoader__?: unknown
|
||||
}
|
||||
|
||||
class ResizeObserverStub {
|
||||
observe(): void {}
|
||||
disconnect(): void {}
|
||||
unobserve(): void {}
|
||||
}
|
||||
|
||||
const win = window as FixtureWindow
|
||||
let unmount: (() => void) | undefined
|
||||
|
||||
/**
|
||||
* Register the per-test jsdom setup and teardown the assembled boot needs:
|
||||
* English pinned before boot so role/text locators stay deterministic across
|
||||
* localized component migrations (the newEnglishPage e2e convention), the
|
||||
* observers and frame callbacks jsdom lacks, and a full reset of the document,
|
||||
* the boot globals, and the injected plugin styles afterwards.
|
||||
*/
|
||||
export function installAssembledBootEnv(): void {
|
||||
beforeEach(() => {
|
||||
localStorage.clear()
|
||||
localStorage.setItem('dsh.locale', 'en')
|
||||
document.title = 'DeepSeek Harness'
|
||||
vi.stubGlobal('ResizeObserver', ResizeObserverStub)
|
||||
vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
|
||||
setTimeout(() => { callback(0) }, 0) as unknown as number)
|
||||
vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
act(() => { unmount?.() })
|
||||
unmount = undefined
|
||||
cleanup()
|
||||
delete win.__DSH_BOOT__
|
||||
delete win.__ModuleLoader__
|
||||
document.body.innerHTML = ''
|
||||
document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
|
||||
document.title = ''
|
||||
history.replaceState(null, '', '/')
|
||||
vi.unstubAllGlobals()
|
||||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* Mount the assembled application on the fixture transport; the teardown
|
||||
* registered by installAssembledBootEnv disposes it.
|
||||
*/
|
||||
export function mountAssembledApp(): void {
|
||||
history.replaceState(null, '', '/?fixture')
|
||||
const root = document.createElement('div')
|
||||
root.id = 'root'
|
||||
document.body.appendChild(root)
|
||||
win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
|
||||
act(() => {
|
||||
const entry = new AppWebEntry(root, {
|
||||
loadBundle: async (url) => {
|
||||
const code = bundles.get(url)
|
||||
if (code === undefined) throw new Error(`missing built bundle ${url}`)
|
||||
;(0, eval)(code)
|
||||
},
|
||||
})
|
||||
void entry.run()
|
||||
unmount = () => { entry.dispose() }
|
||||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* Match a CSS-module class by its logical name.
|
||||
* Module class names carry a per-build hash in one of two schemes —
|
||||
* ui-primitives emits `_<name>_<hash>` (name bounded by underscores),
|
||||
* ui-conversation emits `<hash>_<name>` (name at the end) — and a longer name
|
||||
* containing this one must not match (`line` must not hit `lineNumber`).
|
||||
* @param el - element whose class list is inspected.
|
||||
* @param name - logical (unhashed) module class name.
|
||||
* @returns whether the element carries that module class.
|
||||
*/
|
||||
export function hasClass(el: Element, name: string): boolean {
|
||||
return [...el.classList].some(cls => cls === name || cls.endsWith(`_${name}`) || cls.startsWith(`_${name}_`) || cls.includes(`_${name}_`))
|
||||
}
|
||||
|
||||
/**
|
||||
* Whether this run rewrites its golden instead of comparing against it, set by
|
||||
* the snapshot gate's `DSH_SNAPSHOT` mode (`record` re-runs the scenarios from
|
||||
* scratch, `refresh` re-derives the expected text from the existing ones).
|
||||
*/
|
||||
export const REFRESHING_GOLDEN = process.env.DSH_SNAPSHOT === 'record' || process.env.DSH_SNAPSHOT === 'refresh'
|
||||
@@ -1,105 +1,23 @@
|
||||
// @vitest-environment jsdom
|
||||
// The built-bundle boot smoke: the ONE assembled-jsdom test that loads the
|
||||
// real `packages/client/*/lib/client.js` artifacts through AppWebEntry's
|
||||
// ModuleLoader path (loadBundle) and proves the boot graph
|
||||
// assembles — staged activation across the immediately tier and the inject
|
||||
// layers, per-plugin CSS injection, and a rendered journey reaching chat
|
||||
// content from the keyless FixtureApiClient transport.
|
||||
// The built-bundle boot smoke: the assembled-jsdom test that owns the boot
|
||||
// graph itself. Other files share the same scaffolding (assembled-boot.ts) to
|
||||
// reach a surface only the built bundles expose; this one asserts that the
|
||||
// graph assembles at all — staged activation across the immediately tier and
|
||||
// the inject layers, per-plugin CSS injection, and a rendered journey reaching
|
||||
// chat content from the keyless FixtureApiClient transport.
|
||||
//
|
||||
// Component behavior remains owned by per-package suites (SlotTestRuntime
|
||||
// benches over src). This smoke additionally pins the resident interaction
|
||||
// fixture's cross-plugin projection because only the built connection/runtime/
|
||||
// workspace graph can prove that transport-to-row path end to end.
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { join } from 'node:path'
|
||||
import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
|
||||
import { afterEach, beforeEach, expect, it, vi } from 'vitest'
|
||||
import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client'
|
||||
import { AppWebEntry } from '@deepseek-ai/dsh-client-web'
|
||||
import { act, fireEvent, screen, waitFor, within } from '@testing-library/react'
|
||||
import { expect, it } from 'vitest'
|
||||
import { installAssembledBootEnv, mountAssembledApp } from './assembled-boot.ts'
|
||||
|
||||
const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
|
||||
{ id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{
|
||||
id: '@deepseek-ai/dsh-client-ui-workspace',
|
||||
dir: 'ui-workspace',
|
||||
url: '/plugins/ui-workspace.js',
|
||||
rev: 'fx',
|
||||
inject: [
|
||||
'@deepseek-ai/dsh-client-runtime',
|
||||
'@deepseek-ai/dsh-client-ui-conversation',
|
||||
'@deepseek-ai/dsh-client-ui-sidebar',
|
||||
],
|
||||
},
|
||||
{ id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', url: '/plugins/ui-trajectory.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
|
||||
]
|
||||
|
||||
const bundles = new Map(PLUGINS.map(plugin => [
|
||||
plugin.url,
|
||||
readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
|
||||
]))
|
||||
|
||||
interface FixtureWindow extends Window {
|
||||
__DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
|
||||
__ModuleLoader__?: unknown
|
||||
}
|
||||
|
||||
class ResizeObserverStub {
|
||||
observe(): void {}
|
||||
disconnect(): void {}
|
||||
unobserve(): void {}
|
||||
}
|
||||
|
||||
const win = window as FixtureWindow
|
||||
let unmount: (() => void) | undefined
|
||||
|
||||
beforeEach(() => {
|
||||
localStorage.clear()
|
||||
// English pinned before boot: role/text locators stay deterministic across
|
||||
// localized component migrations (the newEnglishPage e2e convention).
|
||||
localStorage.setItem('dsh.locale', 'en')
|
||||
document.title = 'DeepSeek Harness'
|
||||
vi.stubGlobal('ResizeObserver', ResizeObserverStub)
|
||||
vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
|
||||
setTimeout(() => { callback(0) }, 0) as unknown as number)
|
||||
vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
act(() => { unmount?.() })
|
||||
unmount = undefined
|
||||
cleanup()
|
||||
delete win.__DSH_BOOT__
|
||||
delete win.__ModuleLoader__
|
||||
document.body.innerHTML = ''
|
||||
document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
|
||||
document.title = ''
|
||||
history.replaceState(null, '', '/')
|
||||
vi.unstubAllGlobals()
|
||||
})
|
||||
installAssembledBootEnv()
|
||||
|
||||
it('boots the built plugin graph and renders a fixture session end to end', async () => {
|
||||
history.replaceState(null, '', '/?fixture')
|
||||
const root = document.createElement('div')
|
||||
root.id = 'root'
|
||||
document.body.appendChild(root)
|
||||
win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
|
||||
act(() => {
|
||||
const entry = new AppWebEntry(root, {
|
||||
loadBundle: async (url) => {
|
||||
const code = bundles.get(url)
|
||||
if (code === undefined) throw new Error(`missing built bundle ${url}`)
|
||||
;(0, eval)(code)
|
||||
},
|
||||
})
|
||||
void entry.run()
|
||||
unmount = () => { entry.dispose() }
|
||||
})
|
||||
mountAssembledApp()
|
||||
|
||||
// The sidebar renders from the boot graph: every inject layer activated.
|
||||
const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
|
||||
|
||||
@@ -14,69 +14,19 @@
|
||||
// derivation over the result view, pinned at every render site by the
|
||||
// ui-conversation suite; here the fixture turn exercises the assembled card
|
||||
// shape and its cap.
|
||||
import { mkdirSync, readFileSync, writeFileSync } from 'node:fs'
|
||||
import { mkdirSync, writeFileSync } from 'node:fs'
|
||||
import { dirname, join } from 'node:path'
|
||||
import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
|
||||
import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client'
|
||||
import { AppWebEntry } from '@deepseek-ai/dsh-client-web'
|
||||
import { act, fireEvent, screen, waitFor, within } from '@testing-library/react'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { hasClass, installAssembledBootEnv, mountAssembledApp, REFRESHING_GOLDEN } from './assembled-boot.ts'
|
||||
|
||||
const EXPECTED = join(process.cwd(), 'apps/web/tests/snapshots/search-card/grep-card.expected.txt')
|
||||
const refreshing = process.env.DSH_SNAPSHOT === 'record' || process.env.DSH_SNAPSHOT === 'refresh'
|
||||
|
||||
const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [
|
||||
{ id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{ id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] },
|
||||
{
|
||||
id: '@deepseek-ai/dsh-client-ui-workspace',
|
||||
dir: 'ui-workspace',
|
||||
url: '/plugins/ui-workspace.js',
|
||||
rev: 'fx',
|
||||
inject: [
|
||||
'@deepseek-ai/dsh-client-runtime',
|
||||
'@deepseek-ai/dsh-client-ui-conversation',
|
||||
'@deepseek-ai/dsh-client-ui-sidebar',
|
||||
],
|
||||
},
|
||||
{ id: '@deepseek-ai/dsh-client-ui-trajectory', dir: 'ui-trajectory', url: '/plugins/ui-trajectory.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-conversation'] },
|
||||
]
|
||||
|
||||
const bundles = new Map(PLUGINS.map(plugin => [
|
||||
plugin.url,
|
||||
readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'),
|
||||
]))
|
||||
|
||||
interface FixtureWindow extends Window {
|
||||
__DSH_BOOT__?: { rev: string; entries: WebBootEntry[] }
|
||||
__ModuleLoader__?: unknown
|
||||
}
|
||||
|
||||
class ResizeObserverStub {
|
||||
observe(): void {}
|
||||
disconnect(): void {}
|
||||
unobserve(): void {}
|
||||
}
|
||||
|
||||
const win = window as FixtureWindow
|
||||
let unmount: (() => void) | undefined
|
||||
installAssembledBootEnv()
|
||||
|
||||
/** Normalize a rendered search card to a stable text shape: the kind, the banner
|
||||
* summary, each file header (path + count), each visible match line, the expand
|
||||
* control label, and the recovery footer. CSS-module class names carry a
|
||||
* per-build hash in one of two schemes — ui-primitives emits `_<name>_<hash>`
|
||||
* (name bounded by underscores), ui-conversation emits `<hash>_<name>` (name at
|
||||
* the end). `hasClass` matches a module class by its logical name under either,
|
||||
* without matching a longer name that contains it (`line` must not hit
|
||||
* `lineNumber`). */
|
||||
function hasClass(el: Element, name: string): boolean {
|
||||
return [...el.classList].some(cls => cls === name || cls.endsWith(`_${name}`) || cls.startsWith(`_${name}_`) || cls.includes(`_${name}_`))
|
||||
}
|
||||
|
||||
* control label, and the recovery footer. */
|
||||
function cardShape(root: Element): string {
|
||||
const card = root.querySelector('[data-search]')
|
||||
if (card === null) return '<no search card>'
|
||||
@@ -94,49 +44,9 @@ function cardShape(root: Element): string {
|
||||
return lines.join('\n')
|
||||
}
|
||||
|
||||
beforeEach(() => {
|
||||
localStorage.clear()
|
||||
// English pinned before boot so the sidebar's role/text locators stay
|
||||
// deterministic (the built-boot smoke's convention).
|
||||
localStorage.setItem('dsh.locale', 'en')
|
||||
document.title = 'DeepSeek Harness'
|
||||
vi.stubGlobal('ResizeObserver', ResizeObserverStub)
|
||||
vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) =>
|
||||
setTimeout(() => { callback(0) }, 0) as unknown as number)
|
||||
vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) })
|
||||
})
|
||||
|
||||
afterEach(() => {
|
||||
act(() => { unmount?.() })
|
||||
unmount = undefined
|
||||
cleanup()
|
||||
delete win.__DSH_BOOT__
|
||||
delete win.__ModuleLoader__
|
||||
document.body.innerHTML = ''
|
||||
document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() })
|
||||
document.title = ''
|
||||
history.replaceState(null, '', '/')
|
||||
vi.unstubAllGlobals()
|
||||
})
|
||||
|
||||
describe('assembled search card', () => {
|
||||
it('renders the grep card, its truncation summary, and its capped head/tail slice from the built bundles', async () => {
|
||||
history.replaceState(null, '', '/?fixture')
|
||||
const root = document.createElement('div')
|
||||
root.id = 'root'
|
||||
document.body.appendChild(root)
|
||||
win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) }
|
||||
act(() => {
|
||||
const entry = new AppWebEntry(root, {
|
||||
loadBundle: async (url) => {
|
||||
const code = bundles.get(url)
|
||||
if (code === undefined) throw new Error(`missing built bundle ${url}`)
|
||||
;(0, eval)(code)
|
||||
},
|
||||
})
|
||||
void entry.run()
|
||||
unmount = () => { entry.dispose() }
|
||||
})
|
||||
mountAssembledApp()
|
||||
|
||||
const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
|
||||
fireEvent.click(await within(tree).findByText('Fixture 历史会话'))
|
||||
@@ -161,7 +71,7 @@ describe('assembled search card', () => {
|
||||
expect(grepRow.querySelector('[data-search]')).not.toBeNull()
|
||||
}, { timeout: 10_000 })
|
||||
const shape = cardShape(grepRow)
|
||||
if (refreshing) {
|
||||
if (REFRESHING_GOLDEN) {
|
||||
mkdirSync(dirname(EXPECTED), { recursive: true })
|
||||
writeFileSync(EXPECTED, shape)
|
||||
}
|
||||
|
||||
@@ -0,0 +1,9 @@
|
||||
row=todo_write
|
||||
title=Update to-do list
|
||||
summary=1/4 completed · 实现 fixture 样本
|
||||
suffix=+1
|
||||
panel=1 completed · 2 in progress · 1 pending
|
||||
item=completed 梳理需求
|
||||
item=in_progress 实现 fixture 样本
|
||||
item=in_progress 跑后台构建
|
||||
item=pending 浏览器验收
|
||||
@@ -0,0 +1,71 @@
|
||||
// @vitest-environment jsdom
|
||||
// Assembled todo snapshot: boots the real built `packages/client/*/lib/
|
||||
// client.js` bundles through AppWebEntry's ModuleLoader path against the
|
||||
// keyless FixtureApiClient transport, opens the fixture session, and pins the
|
||||
// two surfaces the fixture's parallel plan (turn 71, two items `in_progress`)
|
||||
// reaches — the `todo_write` tool row and the dock's plan strip.
|
||||
//
|
||||
// The row is pinned as three separate fields on purpose. `summary=` is the
|
||||
// ellipsized text and `suffix=` is ToolRow's non-shrinking `summarySuffix`
|
||||
// slot, so a regression that folds the `+N` count back into the summary string
|
||||
// changes this file even though the concatenated text would read the same; the
|
||||
// jsdom package suites bench over src and cannot see the bundled registration.
|
||||
import { mkdirSync, writeFileSync } from 'node:fs'
|
||||
import { dirname, join } from 'node:path'
|
||||
import { fireEvent, screen, waitFor, within } from '@testing-library/react'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { hasClass, installAssembledBootEnv, mountAssembledApp, REFRESHING_GOLDEN } from './assembled-boot.ts'
|
||||
|
||||
const EXPECTED = join(process.cwd(), 'apps/web/tests/snapshots/todo-row/parallel-plan.expected.txt')
|
||||
|
||||
installAssembledBootEnv()
|
||||
|
||||
/** Normalize the todo row and the plan strip to a stable text shape: the row's
|
||||
* title, its truncatable summary, its non-shrinking suffix, then the panel's
|
||||
* per-status header and every list item with its status. */
|
||||
function todoShape(row: Element, panel: Element): string {
|
||||
const pick = (from: Element, name: string): Element[] =>
|
||||
[...from.querySelectorAll('*')].filter(el => hasClass(el, name))
|
||||
const first = (from: Element, name: string): string =>
|
||||
pick(from, name)[0]?.textContent?.trim() ?? '<absent>'
|
||||
const items = [...panel.querySelectorAll('[data-status]')]
|
||||
.map(item => `item=${item.getAttribute('data-status')} ${item.textContent?.trim() ?? ''}`)
|
||||
return [
|
||||
`row=${row.getAttribute('data-tool')}`,
|
||||
`title=${first(row, 'title')}`,
|
||||
`summary=${first(row, 'summary')}`,
|
||||
`suffix=${first(row, 'summarySuffix')}`,
|
||||
`panel=${first(panel, 'progress')}`,
|
||||
...items,
|
||||
].join('\n')
|
||||
}
|
||||
|
||||
describe('assembled todo surfaces', () => {
|
||||
it('renders the parallel plan as a row summary, a separate active count, and the dock plan strip', async () => {
|
||||
mountAssembledApp()
|
||||
|
||||
const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
|
||||
fireEvent.click(await within(tree).findByText('Fixture 历史会话'))
|
||||
// The todo turn is the fixture's last, so wait for its keyed row rather
|
||||
// than for chat content in general.
|
||||
const row = await waitFor(() => {
|
||||
const found = document.querySelector('[data-tool="todo_write"]')
|
||||
expect(found).not.toBeNull()
|
||||
return found!
|
||||
}, { timeout: 10_000 })
|
||||
// The panel is the standing plan the turn's `todo/write` event feeds; it
|
||||
// mounts above the composer, outside the row, and starts collapsed — its
|
||||
// list only exists once expanded.
|
||||
const panel = await screen.findByTestId('todo-panel', undefined, { timeout: 10_000 })
|
||||
const toggle = panel.querySelector('button[aria-expanded]')
|
||||
if (toggle === null) throw new Error('the plan strip must expose its expand toggle')
|
||||
if (toggle.getAttribute('aria-expanded') === 'false') fireEvent.click(toggle)
|
||||
|
||||
const shape = todoShape(row, panel)
|
||||
if (REFRESHING_GOLDEN) {
|
||||
mkdirSync(dirname(EXPECTED), { recursive: true })
|
||||
writeFileSync(EXPECTED, shape)
|
||||
}
|
||||
await expect(shape).toMatchFileSnapshot(EXPECTED)
|
||||
})
|
||||
})
|
||||
+20
-1
@@ -2148,6 +2148,26 @@ export interface Config {
|
||||
|
||||
Source: [`packages/tasks/tool-tasks/src/index.ts:23`](../packages/tasks/tool-tasks/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-todo`
|
||||
|
||||
Requires: `tools`
|
||||
|
||||
```ts config-catalog
|
||||
/** Model-facing todo tool configuration. */
|
||||
export interface Config {
|
||||
/**
|
||||
* Required deployment choice for whether several todos may be `in_progress` at once. True suits
|
||||
* agents that run work concurrently — subagents, background commands, workflow fan-out — and the
|
||||
* description then instructs the model to mark every actively worked task. False restores the
|
||||
* single-active discipline: the description asks for exactly one, and a call marking more is
|
||||
* rejected.
|
||||
*/
|
||||
allowParallelInProgress: boolean
|
||||
}
|
||||
```
|
||||
|
||||
Source: [`packages/todo/tool-todo/src/index.ts:29`](../packages/todo/tool-todo/src/index.ts)
|
||||
|
||||
## `@deepseek-ai/dsh-tool-web`
|
||||
|
||||
Requires: `tools` · `web` · `systemPrompt`
|
||||
@@ -2510,7 +2530,6 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
|
||||
- `@deepseek-ai/dsh-timeout-policy` — requires `tools` ([`packages/timeout/timeout-policy/src/index.ts`](../packages/timeout/timeout-policy/src/index.ts))
|
||||
- `@deepseek-ai/dsh-tool-ask-user` — requires `tools` · `userInteraction` ([`packages/ui/tool-ask-user/src/index.ts`](../packages/ui/tool-ask-user/src/index.ts))
|
||||
- `@deepseek-ai/dsh-tool-subagent-control` — requires `tools` · `subagents` ([`packages/subagent/tool-subagent-control/src/index.ts`](../packages/subagent/tool-subagent-control/src/index.ts))
|
||||
- `@deepseek-ai/dsh-tool-todo` — requires `tools` ([`packages/todo/tool-todo/src/index.ts`](../packages/todo/tool-todo/src/index.ts))
|
||||
- `@deepseek-ai/dsh-typert-registry` ([`packages/typert/registry/src/index.ts`](../packages/typert/registry/src/index.ts))
|
||||
- `@deepseek-ai/dsh-user-interaction` ([`packages/ui/user-interaction/src/index.ts`](../packages/ui/user-interaction/src/index.ts))
|
||||
- `@deepseek-ai/dsh-workspace` — requires `storageDomain` · `sessionPersistence` ([`packages/workspace/workspace/src/index.ts`](../packages/workspace/workspace/src/index.ts))
|
||||
|
||||
@@ -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/core-data-structures/session.md
|
||||
session.md: fac201b581e395865fd46d51bca1350cbbc46e8e
|
||||
session.zh.md: 53dc9d11de895deec72aaf5ea81c70ba87c9c6bd
|
||||
session.md: fb04ff3eb3c15d1f3c923ee73d4ba19537d36f11
|
||||
session.zh.md: 138159d97a5c368f28821715512632e0ca95b29e
|
||||
@@ -144,7 +144,7 @@ The unit of the `todo/write` event's whole-list snapshot. Deliberately minimal
|
||||
interface TodoItem {
|
||||
/** What this task is — a short imperative line shown in the UI. */
|
||||
content: string
|
||||
/** Lifecycle state. `in_progress` marks the single task being worked now. */
|
||||
/** Lifecycle state. `in_progress` marks a task being worked now; parallel work may mark several. */
|
||||
status: 'pending' | 'in_progress' | 'completed'
|
||||
}
|
||||
```
|
||||
|
||||
@@ -144,7 +144,7 @@ interface SessionEventMap {
|
||||
interface TodoItem {
|
||||
/** What this task is — a short imperative line shown in the UI. */
|
||||
content: string
|
||||
/** Lifecycle state. `in_progress` marks the single task being worked now. */
|
||||
/** Lifecycle state. `in_progress` marks a task being worked now; parallel work may mark several. */
|
||||
status: 'pending' | 'in_progress' | 'completed'
|
||||
}
|
||||
```
|
||||
|
||||
@@ -7,7 +7,7 @@ Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`,
|
||||
|
||||
This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator's boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog Agent Note](../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md).
|
||||
|
||||
Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope.
|
||||
Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config, except where a Config field is REQUIRED with no default — there the generator must choose, and the per-package note records which branch this page shows. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope.
|
||||
|
||||
## Tool Package Map
|
||||
|
||||
@@ -35,7 +35,7 @@ This table connects model-visible tool names to the plugin package and service s
|
||||
| `@deepseek-ai/dsh-tool-subagent-control` | `list_agents`, `send_message` | `ctx.tools`, `ctx.subagents`, `ctx.sessionProjections (list_agents catalog rows)` | `tool/call`, `tool/result`, `child session events through ctx.subagents` | - | The globally named control tools over continuable background subagents: provider-bound `tool-subagent` instances register distinct delegation tools, while this package registers `send_message` once, plus `list_agents` from its separately loaded `/list-agents` plugin (whose catalog rows are served through the sessionProjections registry). |
|
||||
| `@deepseek-ai/dsh-tool-subagent-report` | `report` | `ctx.subagents`, `a live continuable in-process child Agent` | `tool/call`, `tool/result`, `a user-role message in the direct parent session` | - | Registered per continuable in-process child rather than globally, so this schema is visible only inside such a child and survives its global `toolFilter`. The parent-facing `send_message` tool is installed independently. |
|
||||
| `@deepseek-ai/dsh-tool-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `user/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: background bash commands, PTY sends, and subagents are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. |
|
||||
| `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist. |
|
||||
| `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist. `allowParallelInProgress` is required with no default, so the catalog states its choice: `true`, whose description invites several `in_progress` items. A deployment choosing `false` receives the same tool with a description asking for exactly one active task. |
|
||||
| `@deepseek-ai/dsh-tool-workflow` | `workflow` | `ctx.tools`, `ctx.workflows`, `ctx.systemPrompt`, `a calling Agent (exec.agent parents the script children)` | `tool/call`, `tool/result` | - | - |
|
||||
| `@deepseek-ai/dsh-tool-web` | `web_fetch`, `web_search` | `ctx.tools`, `ctx.web`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | web_search and web_fetch keep provider selection behind ctx.web so model-visible schemas stay stable across backend swaps. |
|
||||
|
||||
@@ -1334,7 +1334,7 @@ The kind-agnostic background-task control surface: background bash commands, PTY
|
||||
|
||||
### `todo_write`
|
||||
|
||||
Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).
|
||||
Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).
|
||||
|
||||
```json
|
||||
{
|
||||
@@ -1376,7 +1376,7 @@ Record and update a structured task list for the current work. Send the ENTIRE l
|
||||
|
||||
Source: [`packages/todo/tool-todo/src/index.ts`](../packages/todo/tool-todo/src/index.ts)
|
||||
|
||||
todo_write is session-owned state; UIs render the latest todo/write event as a checklist.
|
||||
todo_write is session-owned state; UIs render the latest todo/write event as a checklist. `allowParallelInProgress` is required with no default, so the catalog states its choice: `true`, whose description invites several `in_progress` items. A deployment choosing `false` receives the same tool with a description asking for exactly one active task.
|
||||
|
||||
## `@deepseek-ai/dsh-tool-workflow`
|
||||
|
||||
|
||||
@@ -147,6 +147,8 @@
|
||||
# `todo_write` replaces the logged whole list for later model requests.
|
||||
- id: tool-todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
config:
|
||||
allowParallelInProgress: true
|
||||
|
||||
# Identical repeat calls trigger advisory context, never a block, at the default
|
||||
# thresholds [3, 5, 8]. Only the repeat-tool-guard snapshot scenario reaches them.
|
||||
|
||||
@@ -160,7 +160,7 @@ interface ToolArgsMap {
|
||||
/** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */
|
||||
timeout_ms?: number;
|
||||
} & Record<string, JsonValue>;
|
||||
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
|
||||
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
|
||||
todo_write: {
|
||||
/** The COMPLETE task list, replacing any previous list. */
|
||||
todos: ({
|
||||
|
||||
@@ -386,7 +386,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -329,7 +329,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -143,7 +143,7 @@ interface ToolArgsMap {
|
||||
/** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */
|
||||
timeout_ms?: number;
|
||||
} & Record<string, JsonValue>;
|
||||
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
|
||||
/** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */
|
||||
todo_write: {
|
||||
/** The COMPLETE task list, replacing any previous list. */
|
||||
todos: ({
|
||||
|
||||
@@ -345,7 +345,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -437,7 +437,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -512,7 +512,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
+1
-1
@@ -324,7 +324,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
+1
-1
@@ -324,7 +324,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -324,7 +324,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -308,7 +308,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -2,6 +2,6 @@
|
||||
"steps": [
|
||||
{ "op": "initialize" },
|
||||
{ "op": "newSession" },
|
||||
{ "op": "prompt", "text": "Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop." }
|
||||
{ "op": "prompt", "text": "Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop." }
|
||||
]
|
||||
}
|
||||
@@ -1,36 +1,37 @@
|
||||
{"type":"session","version":0,"id":"b0f1f758-dcf0-474e-851d-e62c11ec0a09","createdAt":1783352057652,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"agent/inbox/spliced","seq":0,"time":1785498772484,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"5ecf5e4b-6a18-447d-9341-48f38afdd12e"}]}}
|
||||
{"type":"turn/start","seq":1,"time":1785821376741,"data":{"turn":1}}
|
||||
{"type":"agent/inbox/spliced","seq":2,"time":1785821376741,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
|
||||
{"type":"step/start","seq":3,"time":1783352057657,"data":{"turn":1,"step":1}}
|
||||
{"type":"user/message","seq":4,"time":1785498772510,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"5ecf5e4b-6a18-447d-9341-48f38afdd12e"},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":5,"time":1785730425725,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"8d4ac045-8016-4cec-8b12-91d9459231e1"},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":6,"time":1785730425725,"data":{"title":"Use the todo_write tool to","messageSeqs":[4],"source":{"kind":"fallback"}}}
|
||||
{"type":"request/header","seq":7,"time":1785498772511,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"request/context","seq":8,"time":1785730425726,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1783352058426,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":10,"time0":1783352058466,"data":{"turn":1,"step":1,"index":0,"dt":[1,0,0,0,17,0,0,0,1,26,1,1,0,0,1,26,0,31,1,25,0,0,0,29,0,0,0,0,91,0],"texts":["The"," user"," wants"," me"," to"," use"," the"," todo","_write"," tool"," to"," record"," a"," plan"," with"," exactly"," three"," todos"," in"," the"," specified"," status","es",","," then"," reply"," with"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":41,"time":1783352058746,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":42,"time0":1783352058747,"data":{"turn":1,"step":1,"index":1,"dt":[0,0,28,0,1,29,1,0,0,0,0,26,0,0,0,0,0,30,1,0,0,0,0,26,1,0,0,0,0,28,0,0,0,0,0,29,0,0,0,0,1,28,0,0,0,1,0,27,1,0,28,62,1],"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","args":["","{","\"","t","odos","\"",": ","[","{\"","content","\":"," \"","read"," the"," code","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","write"," the"," fix","\","," \"","status","\":"," \"","pending","\"},"," {\"","content","\":"," \"","run"," the"," tests","\","," \"","status","\":"," \"","pending","\"","}]","}"]}}
|
||||
{"type":"assistant/chunk","seq":96,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."}}}}
|
||||
{"type":"assistant/chunk","seq":97,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}}
|
||||
{"type":"assistant/chunk","seq":98,"time":1785498772522,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}}}}
|
||||
{"type":"assistant/chunk","seq":99,"time":1785730425738,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":100,"time":1785730425738,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"08141496-5477-4d05-b2c7-414865ea9a17"},"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":101,"time":1785730425739,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}
|
||||
{"type":"todo/write","seq":102,"time":1785730425747,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}}
|
||||
{"type":"tool/result","seq":103,"time":1785730425748,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_fjAnBThbDjxepBtp3hDt3264"},"content":[{"type":"tool-result","toolCallId":"call_00_fjAnBThbDjxepBtp3hDt3264","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false}],"role":"user","id":"c178ad5b-7c1f-4239-9aa6-20d1c6b00a82"}},"sourceEventSeqs":[101],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":104,"time":1785730425748,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":105,"time":1785730425759,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":106,"time":1783352059835,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":107,"time0":1783352059863,"data":{"turn":1,"step":2,"index":0,"dt":[0,1,0,28,0,1,0,27,0,1,0,0,29,0,0,0,1,0,28,0],"texts":["The"," todos"," have"," been"," written"," successfully","."," Now"," I"," just"," need"," to"," reply"," with"," the"," single"," word"," \"","D","ONE","\"."]}}
|
||||
{"type":"assistant/chunk","seq":128,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":129,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
|
||||
{"type":"assistant/chunk","seq":130,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
|
||||
{"type":"assistant/chunk","seq":131,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."}}}}
|
||||
{"type":"assistant/chunk","seq":132,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":133,"time":1785498772545,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}}}}
|
||||
{"type":"assistant/chunk","seq":134,"time":1785730425764,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":135,"time":1785730425764,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"c4e454ce-14cc-4030-be47-0395ac9f12fb"},"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[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],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":136,"time":1785730425764,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":137,"time":1785730425764,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
{"type":"session","version":0,"id":"d9d967e8-0112-471c-a3b5-dfdc171aba61","createdAt":1785987077399,"cwd":"{{cwd}}","delegationDepth":0}
|
||||
{"type":"agent/inbox/spliced","seq":0,"time":1785987077401,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"befb10e9-f992-4a19-9e1b-333ad7fd72f8"}]}}
|
||||
{"type":"turn/start","seq":1,"time":1785987077401,"data":{"turn":1}}
|
||||
{"type":"agent/inbox/spliced","seq":2,"time":1785987077401,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
|
||||
{"type":"step/start","seq":3,"time":1785987077430,"data":{"turn":1,"step":1}}
|
||||
{"type":"user/message","seq":4,"time":1785987077430,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos for work running in parallel: \"read the code\" (in_progress), \"watch the background build\" (in_progress), \"write the fix\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"},"role":"user","id":"befb10e9-f992-4a19-9e1b-333ad7fd72f8"},"surfaceOp":"append"}
|
||||
{"type":"user/message","seq":5,"time":1785987077430,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"3893b488-4678-4b29-be9f-6365854b0ddc"},"surfaceOp":"append"}
|
||||
{"type":"session/title","seq":6,"time":1785987077430,"data":{"title":"Use the todo_write tool to","messageSeqs":[4],"source":{"kind":"fallback"}}}
|
||||
{"type":"request/header","seq":7,"time":1785987077431,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
|
||||
{"type":"request/context","seq":8,"time":1785987077431,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1785987079233,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"reasoning-chunks","seq0":10,"time0":1785987079233,"data":{"turn":1,"step":1,"index":0,"dt":[152,51,2,0,0,61,55,0,1,0,47,53,0,1,0,46,1,0,0,1,45,1,0],"texts":["The"," user"," wants"," me"," to"," use"," todo","_write"," to"," create"," exactly"," three"," todos",","," then"," reply"," with"," \"","D","ONE","\""," and"," stop","."]}}
|
||||
{"type":"assistant/chunk","seq":34,"time":1785987079909,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
|
||||
{"type":"tool-call-chunks","seq0":35,"time0":1785987079910,"data":{"turn":1,"step":1,"index":1,"dt":[52,0,1,0,0,0,55,1,0,0,50,1,0,0,0,0,52,0,0,0,0,1,52,1,0,0,0,0,59,0,0,0,0,0,57,0,0,0,0,0,54,0,0,0,0,0,45,1,0,0,0,0,67,0,0,46],"id":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","args":["","{","\"","t","odos","\"",": ","[","{\"","content","\":"," \"","read"," the"," code","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","watch"," the"," background"," build","\","," \"","status","\":"," \"","in","_pro","gress","\"},"," {\"","content","\":"," \"","write"," the"," fix","\","," \"","status","\":"," \"","pending","\"","}]","}"]}}
|
||||
{"type":"assistant/chunk","seq":92,"time":1785987080614,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use todo_write to create exactly three todos, then reply with \"DONE\" and stop."}}}}
|
||||
{"type":"assistant/chunk","seq":93,"time":1785987080614,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"watch the background build\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}]}"}}}}
|
||||
{"type":"assistant/chunk","seq":94,"time":1785987080615,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5778,"outputTokens":117,"cacheReadTokens":0,"reasoningTokens":24}}}}
|
||||
{"type":"assistant/chunk","seq":95,"time":1785987080615,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/message","seq":96,"time":1785987080618,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"reasoning","text":"The user wants me to use todo_write to create exactly three todos, then reply with \"DONE\" and stop."},{"type":"tool-call","id":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"watch the background build\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}]}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"600b618f-2403-4584-b7aa-84b474e7ef08"},"usage":{"inputTokens":5778,"outputTokens":117,"cacheReadTokens":0,"reasoningTokens":24}},"sourceEventSeqs":[9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"surfaceOp":"append"}
|
||||
{"type":"tool/call","seq":97,"time":1785987080619,"data":{"turn":1,"step":1,"callId":"call_00_UHvM5RrwIkjNJ9xh3S735164","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"watch the background build\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}]}"}}
|
||||
{"type":"todo/write","seq":98,"time":1785987080632,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"watch the background build","status":"in_progress"},{"content":"write the fix","status":"pending"}]}}
|
||||
{"type":"tool/result","seq":99,"time":1785987080633,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_00_UHvM5RrwIkjNJ9xh3S735164"},"content":[{"type":"tool-result","toolCallId":"call_00_UHvM5RrwIkjNJ9xh3S735164","content":[{"type":"text","text":"Updated todo list: 1 pending, 2 in progress, 0 completed."}],"isError":false}],"role":"user","id":"65e181f3-565f-4be4-9ffe-9d59c808f7f8"}},"sourceEventSeqs":[97],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":100,"time":1785987080633,"data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","seq":101,"time":1785987080647,"data":{"turn":1,"step":2}}
|
||||
{"type":"assistant/chunk","seq":102,"time":1785987081239,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
|
||||
{"type":"assistant/chunk","seq":103,"time":1785987081239,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Done"}}}
|
||||
{"type":"assistant/chunk","seq":104,"time":1785987081391,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}}
|
||||
{"type":"assistant/chunk","seq":105,"time":1785987081451,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":106,"time":1785987081452,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}}
|
||||
{"type":"assistant/chunk","seq":107,"time":1785987081452,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}}
|
||||
{"type":"assistant/chunk","seq":108,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Done."}}}}
|
||||
{"type":"assistant/chunk","seq":109,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":110,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":154,"outputTokens":5,"cacheReadTokens":5760,"reasoningTokens":2}}}}
|
||||
{"type":"assistant/chunk","seq":111,"time":1785987081453,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
{"type":"assistant/message","seq":112,"time":1785987081454,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"reasoning","text":"Done."},{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"e4db2f4e-732f-4b58-a44f-5d08b50ce234"},"usage":{"inputTokens":154,"outputTokens":5,"cacheReadTokens":5760,"reasoningTokens":2}},"sourceEventSeqs":[102,103,104,105,106,107,108,109,110,111],"surfaceOp":"append"}
|
||||
{"type":"step/end","seq":113,"time":1785987081455,"data":{"turn":1,"step":2}}
|
||||
{"type":"turn/end","seq":114,"time":1785987081455,"data":{"turn":1,"reason":{"kind":"completed"}}}
|
||||
@@ -308,7 +308,7 @@
|
||||
},
|
||||
{
|
||||
"name": "todo_write",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
||||
@@ -134,6 +134,8 @@
|
||||
# `todo_write` replaces the logged whole list.
|
||||
- id: tool-todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
config:
|
||||
allowParallelInProgress: true
|
||||
|
||||
# Policy loads before the model-facing filesystem tools so writes and edits
|
||||
# require an observed file. Relative paths resolve from the process cwd.
|
||||
|
||||
@@ -30,8 +30,9 @@ export const SYSTEM_PROMPT = 'You are a coding agent. Use bash for file operatio
|
||||
/** System prompt for the todo_write e2e: nudges the model to plan with the tool. */
|
||||
export const TODO_SYSTEM_PROMPT = 'You are a coding agent. For multi-step work, '
|
||||
+ 'use the todo_write tool to track a task list: send the WHOLE list each call, '
|
||||
+ 'keep at most one task in_progress (exactly one while work remains), and mark '
|
||||
+ 'a task completed as soon as it is done.'
|
||||
+ 'mark every task being actively worked on in_progress (several at once when '
|
||||
+ 'work runs in parallel, at least one while work remains), and mark a task '
|
||||
+ 'completed as soon as it is done.'
|
||||
|
||||
/** Options for {@link codingHarness}. */
|
||||
export interface CodingHarnessOptions {
|
||||
@@ -65,7 +66,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio
|
||||
await ctx.plugin(BashEnvPlugin)
|
||||
await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 })
|
||||
await ctx.plugin(ToolBash)
|
||||
await ctx.plugin(ToolTodo)
|
||||
await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
// Compaction is opt-in: only the compaction e2e loads the reusable meter and backend.
|
||||
if (options.compact !== undefined) {
|
||||
await ctx.plugin(TokenMeterService)
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -31,9 +31,10 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
|
||||
|
||||
agent.followup(createUserMessage({
|
||||
content: [{ type: 'text', text:
|
||||
'Use the todo_write tool to record a plan of exactly two steps: first '
|
||||
+ '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
|
||||
+ 'Send both in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } }))
|
||||
'Use the todo_write tool to record a plan of exactly three steps for work '
|
||||
+ 'running in parallel: "inspect the failing test" (in_progress), '
|
||||
+ '"watch the background build" (in_progress), then "apply the fix" (pending). '
|
||||
+ 'Send all three in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } }))
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const events = [...agent.session.events]
|
||||
@@ -42,13 +43,15 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a
|
||||
const calls = events.filter(event => event.type === 'tool/call')
|
||||
expect(calls.some(event => event.data.name === 'todo_write')).toBe(true)
|
||||
|
||||
// And the tool wrote a todo/write event to the log — verify the WORLD.
|
||||
// And the tool wrote a todo/write event to the log — verify the WORLD,
|
||||
// including two simultaneously in_progress tasks (the parallel contract).
|
||||
const todoEvents = events.filter(event => event.type === 'todo/write')
|
||||
expect(todoEvents.length).toBeGreaterThan(0)
|
||||
|
||||
const todos = (todoEvents.at(-1)!).data.todos
|
||||
expect(todos).toEqual([
|
||||
{ content: 'inspect the failing test', status: 'in_progress' },
|
||||
{ content: 'watch the background build', status: 'in_progress' },
|
||||
{ content: 'apply the fix', status: 'pending' },
|
||||
])
|
||||
}, 120_000)
|
||||
|
||||
@@ -65,6 +65,8 @@
|
||||
|
||||
- id: tool-todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
config:
|
||||
allowParallelInProgress: true
|
||||
|
||||
- id: fs-local
|
||||
name: '@deepseek-ai/dsh-fs-local'
|
||||
|
||||
@@ -326,6 +326,8 @@
|
||||
|
||||
- id: tool-todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
config:
|
||||
allowParallelInProgress: true
|
||||
|
||||
# Persisted same-session goals reach the model and the slash menu here; the
|
||||
# domain, driver, and `/goal` command are above.
|
||||
|
||||
@@ -474,11 +474,14 @@ function buildAlphaLog(): SessionEvent[] {
|
||||
push({ type: 'step/end', data: { turn, step: 0 } })
|
||||
push({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } })
|
||||
}
|
||||
// Turn 67: todo_write sample — the TodoRow toolview in the flow plus the
|
||||
// todo/write snapshot event feeding the TodoPanel plan strip.
|
||||
// Turn 71: todo_write sample — the TodoRow toolview in the flow plus the
|
||||
// todo/write snapshot event feeding the TodoPanel plan strip. Two items are
|
||||
// in_progress: this fixture chooses the parallel policy, so both surfaces
|
||||
// must render a parallel plan rather than the first active item alone.
|
||||
const fixtureTodos = [
|
||||
{ content: '梳理需求', status: 'completed' },
|
||||
{ content: '实现 fixture 样本', status: 'in_progress' },
|
||||
{ content: '跑后台构建', status: 'in_progress' },
|
||||
{ content: '浏览器验收', status: 'pending' },
|
||||
]
|
||||
// Turn 65: the terminal sample turn 60's two clean prompt rows cannot cover —
|
||||
@@ -531,7 +534,7 @@ function buildAlphaLog(): SessionEvent[] {
|
||||
toolTurn(70, 'web_fetch', '{"url":"https://www.deepseek.com/blog/harness-architecture"}', '# Harness architecture\n\nEverything is a plugin.')
|
||||
|
||||
const todoArgs = JSON.stringify({ todos: fixtureTodos })
|
||||
toolTurn(71, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 1 in progress, 1 completed.')
|
||||
toolTurn(71, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 2 in progress, 1 completed.')
|
||||
// The real tool appends the snapshot mid-execution — between tool/call and
|
||||
// tool/result — so the fixture reproduces that exact ordering (the last
|
||||
// toolTurn events run ... tool/call, tool/result, step/end, turn/end).
|
||||
|
||||
@@ -242,6 +242,10 @@ describe('createFixtureApi', () => {
|
||||
const times = events.slice(todoAt - 1, todoAt + 2).map(e => e.time)
|
||||
expect(times[0]).toBeLessThanOrEqual(times[1] ?? 0)
|
||||
expect(times[1]).toBeLessThanOrEqual(times[2] ?? 0)
|
||||
// The sample is a parallel plan: this fixture chooses the parallel policy,
|
||||
// so the surfaces fed from here face more than one active item.
|
||||
const snapshot = events[todoAt] as { data: { todos: { status: string }[] } }
|
||||
expect(snapshot.data.todos.filter(t => t.status === 'in_progress')).toHaveLength(2)
|
||||
})
|
||||
|
||||
it('create adds a session and pushes host/session-added to open host streams', async () => {
|
||||
|
||||
@@ -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/client/ui-conversation/README.md
|
||||
README.md: bbd115eac0eb914914dc11e504639633c801abdd
|
||||
README.zh.md: 843b49e311fbf1a9157413c42a0ef3e9828284bc
|
||||
README.md: 8d6c26f67916f043251c58a3283542bd58a08666
|
||||
README.zh.md: 8dd43cca59f8dfda18ce036b5d8c6f948306c947
|
||||
@@ -34,7 +34,7 @@ A `grep`/`glob` call declaring the `search` render intent renders its result inl
|
||||
|
||||
Tool rows use the keyed, session-scoped `'conversation.chat.toolview'` slot; its render site dispatches via `entryKey: toolName` with `GenericToolCard` as the call-site fallback. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openFile`), and `ToolRowProps` composes it with the session standard kit. A registrant is a plain plugin with only the slot service edge: `ctx.slots.inject('conversation.chat.toolview', () => ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row))`. The declaration is the activation and reload dependency; `ConversationService` is required only by registrations that call its actions. Trajectory and waterfall toolview slots share this shape and use their own render sites; RendersCheck rejects a declaration nobody renders.
|
||||
|
||||
The todo surfaces are two registrations over that shape, both using slot declaration injection without a `ConversationService` edge. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`<done>/<total> 已完成 · <active item>` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: 0` — before Goal and Queue — and is the plan strip: it reads the host-computed `todos` projection via `useProjection` (standing plan: latest `todo/write` with no later `turn/start`) and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and starts collapsed as a header of title plus `"<done>/<total> tasks · <n> in progress"` (status glyphs are the figma check / progress / dashed-pending set). The dock adapter owns the selection so the panel stays a pure function of its props; the standing list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included.
|
||||
The todo surfaces are two registrations over that shape, both using slot declaration injection without a `ConversationService` edge. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`<done>/<total> completed · <active item>` plus a `+<n>` count of the other active ones, parsed from its args through `toolviews/plan-summary.ts` `planSummary`, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). When the deployment permits parallel work, several items may be `in_progress` at once, so `planSummary` names the first and counts the rest, and deliberately returns the two unjoined: the row ellipsizes its summary text, so a count concatenated onto the end of the task name would be the first thing a narrow row clips. The row hands the count to `ToolRow`'s `summarySuffix`, the shared row's non-shrinking slot beside that ellipsized text (an error row drops it, since its collapsed summary is the failure line). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: 0` — before Goal and Queue — and is the plan strip: it reads the host-computed `todos` projection via `useProjection` (standing plan: latest `todo/write` with no later `turn/start`) and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and starts collapsed as a header of title plus its own `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted; status glyphs are the figma check / progress / dashed-pending set), so it reports the parallel count without needing a name to truncate. The dock adapter owns the selection so the panel stays a pure function of its props; the standing list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included.
|
||||
|
||||
`QueueDock` is the terminal input-dock entry at `order: 20`. It hides while empty, renders one pending row directly, and defaults two or more rows to a collapsed `"<n> 条排队消息"` header whose button expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Each visible ordinary-session row remains a single-line preview with its exact-occurrence edit, delete, and strict-steer actions; addressed subagents retain the rows as a read-only projection because their continuation transport does not expose queue mutation. If strict steer loses to a closed window, the original occurrence remains queued for normal delivery; if the driver already claimed it, normal delivery is already underway. Neither converged race displays a failure, while transport and unknown failures do.
|
||||
|
||||
|
||||
@@ -34,7 +34,7 @@ Think 行默认保持折叠，并在不展开思维链的情况下暴露实时
|
||||
|
||||
审批经由本包声明的链接管编辑器：`ApprovalPanel` 注册为按选择器路由的 `'conversation.composer'` 配置项（ui-question 模式），在审批等待未决期间取代 InputBar 占据编辑器（琥珀色条、理由标题、来自运行中调用参数的配对命令行、一次性的拒绝／允许）。`contract/slots.ts` 中的 `PendingApproval` 领域面在运行时 `PendingWait` 载体之上拥有 wire 编码——带审计关联的 `ApprovalResponsePayload` 值；广播的 `approval/resolved` 帧使等待落定并恢复编辑器。运行时 manager 会将所有审批或问题等待通过 `SessionSummary.pendingInteraction` 投影出来，未实例化的 Session 也不例外；`ui-workspace` 负责其侧边栏呈现。未决等待完全离开消息流：问题（ui-question）与审批（ApprovalPanel）都经编辑器接管作答，不再保留只读占位卡。编辑器底行的 Access 席位挂载 `PermissionSelect`，由 host 计算的 `permissions` 投影经标准工具包 `useProjection` 供数（key 缺席即隐藏 chip）；chip 打开 Menu 原语下拉，其中 kebab-case 预设名渲染为 Title Case 标签；普通安全预设会立即经输入栏注入的 `command` 回调提交 `/permission <preset>`，而 `danger-full-access` 在界面中显示为 `Full access`，选择后先打开页面内的 Modal 风险确认。用户勾选确认项前启用按钮始终不可用；取消、Escape、关闭按钮与点击遮罩都不会提交命令。
|
||||
|
||||
todo 两个面就是在该形状上的两个注册项，都使用 slot 声明注入，不依赖 `ConversationService`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。`TodoDock` 以 `order: 0` 占用 `'conversation.input.dock'` 列表 slot（位于 Goal 与 Queue 之前），是计划条：它经 `useProjection` 读取 host 计算的 `todos` 投影（站立计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏；列表非空时面板初始折叠，表头显示标题加 `"<已完成>/<总数> tasks · <n> in progress"`（状态图标为 figma 的勾选／进行中／虚线未开始一组）。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；站立列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。
|
||||
todo 两个面就是在该形状上的两个注册项，都使用 slot 声明注入，不依赖 `ConversationService`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 经 `toolviews/plan-summary.ts` 的 `planSummary` 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`，以及「其余活跃项的数量」`+<n>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。部署允许并行工作时，可以有多个条目同时处于 `in_progress`，因此 `planSummary` 给出第一个活跃条目并计数其余，且刻意不把两者拼成一个字符串：行会对摘要文本做省略号截断，把数量接在任务名末尾时，窄行最先裁掉的正是这个数量。该行把数量交给 `ToolRow` 的 `summarySuffix`——共享行在被截断文本旁的不收缩位（出错的行会丢弃它，因为其折叠摘要是失败首行）。`TodoDock` 以 `order: 0` 占用 `'conversation.input.dock'` 列表 slot（位于 Goal 与 Queue 之前），是计划条：它经 `useProjection` 读取 host 计算的 `todos` 投影（站立计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏；列表非空时面板初始折叠，表头显示标题加它自行计算的、以 `·` 连接的各状态计数（本地化，形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略；状态图标为 figma 的勾选／进行中／虚线未开始一组），因此它无需一个可被截断的任务名即可报告并行数量。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；站立列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。
|
||||
|
||||
`QueueDock` 是 `order: 20` 的末端 input-dock 条目。队列为空时隐藏；只有一个待处理项时直接渲染该行；存在两个或更多待处理项时，默认收起为 `"<n> 条排队消息"` 表头，其按钮可展开或收起完整列表。表头暴露 `aria-expanded` 和 `aria-controls`；展开后的列表以 180px 为高度上限，并可滚动。存在进行中的编辑或变更时，列表行会保持可见；队列清空后，下一次出现队列时会恢复默认收起状态。普通会话中的每条可见行仍是单行预览，并提供针对精确单次入队项的编辑、删除和严格 steering 操作；已寻址 subagent 则保留只读行，因为其继续执行传输不提供 Queue 变更。如果严格 steering 输给已关闭的窗口，原单次入队项会留在 Queue 中正常投递；如果驱动器已经认领该项，正常投递就已开始。这两种已收敛的竞态都不显示失败，传输和未知错误仍会显示。
|
||||
|
||||
|
||||
@@ -89,6 +89,20 @@
|
||||
text-overflow: clip;
|
||||
}
|
||||
|
||||
/* Trailing summary fragment kept out of .summary's ellipsis, for a count whose
|
||||
whole value is that it survives a narrow row (the todo row's parallel-active
|
||||
`+n`). Repeats .summary's type because it sits beside that text, and its
|
||||
`nowrap` too: `flex: none` stops the box shrinking but not the text wrapping,
|
||||
which would break the one-line row in the narrow case the slot exists for. */
|
||||
.summarySuffix {
|
||||
flex: none;
|
||||
margin-left: 4px;
|
||||
white-space: nowrap;
|
||||
font-size: 14px;
|
||||
line-height: 24px;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
}
|
||||
|
||||
/* File-tool path: same geometry as .summary; hover underline + pointer. */
|
||||
.fileLink {
|
||||
flex: 1 1 auto;
|
||||
|
||||
@@ -46,6 +46,14 @@ export interface ToolRowProps {
|
||||
icon: ReactNode
|
||||
title: string
|
||||
summary: string
|
||||
/**
|
||||
* Trailing summary fragment rendered outside the ellipsized summary text, so
|
||||
* a narrow row clips the summary before this. For a fragment whose whole
|
||||
* value is surviving that clip — the todo row's parallel-active count.
|
||||
* null/absent = the summary is the whole collapsed content. Dropped on an
|
||||
* error row, whose collapsed summary is the failure line instead.
|
||||
*/
|
||||
summarySuffix?: string | null | undefined
|
||||
/** Expanded-body input text; null = no input section. */
|
||||
body: string | null
|
||||
/** Flattened result text for the expanded Output section; null/absent = no output section. */
|
||||
@@ -139,6 +147,7 @@ export function ToolRow({
|
||||
icon,
|
||||
title,
|
||||
summary,
|
||||
summarySuffix,
|
||||
body,
|
||||
output,
|
||||
errorSummary,
|
||||
@@ -173,6 +182,9 @@ export function ToolRow({
|
||||
// the error color outranks both the args summary and a terminal description.
|
||||
const failureLine = state === 'error' ? errorSummary ?? null : null
|
||||
const summaryText = failureLine ?? summary
|
||||
// The failure line replaces the summary wholesale, so a suffix derived from
|
||||
// the call args has nothing left to sit beside.
|
||||
const suffix = failureLine === null ? summarySuffix ?? null : null
|
||||
// The failure line is error prose, not the path: no open-file affordance.
|
||||
const fileLink = filePath !== undefined && onOpenFile !== undefined && failureLine === null
|
||||
const isThink = variant === 'think'
|
||||
@@ -249,6 +261,7 @@ export function ToolRow({
|
||||
{summaryText}
|
||||
</span>
|
||||
)}
|
||||
{suffix !== null && <span className={css.summarySuffix}>{suffix}</span>}
|
||||
</>
|
||||
)}
|
||||
>
|
||||
|
||||
@@ -0,0 +1,60 @@
|
||||
/**
|
||||
* Pure plan derivation for the todo_write row's one-line summary. Several items
|
||||
* may be `in_progress` at once — parallel work runs concurrent tasks, so a
|
||||
* summary built from one active item would silently drop the rest. The plan
|
||||
* strip header derives its own counts inline and shares nothing with this, so
|
||||
* this stays inside the toolviews domain rather than in `contract/` (the
|
||||
* inter-domain face).
|
||||
* @module
|
||||
*/
|
||||
|
||||
/**
|
||||
* One list item as the row sees it: unvalidated model JSON parsed from a call's
|
||||
* args, so any field may be missing or mistyped.
|
||||
*/
|
||||
export interface PlanItemLike {
|
||||
content?: unknown
|
||||
status?: unknown
|
||||
}
|
||||
|
||||
/**
|
||||
* Counts plus the two halves of the summary, deliberately NOT pre-joined: the
|
||||
* row ellipsizes its summary text, and a count concatenated onto the end of the
|
||||
* task name is the first thing a narrow row clips — exactly when it carries
|
||||
* information. The row renders `activeExtra` in its own non-shrinking span
|
||||
* beside the truncatable text.
|
||||
*/
|
||||
export interface PlanSummary {
|
||||
done: number
|
||||
total: number
|
||||
/** First `in_progress` content, or null when that first item is unusable. */
|
||||
activeContent: string | null
|
||||
/** Active items beyond the first; 0 whenever there is no `activeContent` to sit beside. */
|
||||
activeExtra: number
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive the counts and the active summary from a whole-list snapshot. It names
|
||||
* the first `in_progress` item and counts the remaining active ones, so a
|
||||
* parallel plan reports how many tasks are running rather than naming one and
|
||||
* hiding the others. `activeContent` is null when nothing is in progress, or
|
||||
* when the first active item's content is missing, mistyped, or blank once
|
||||
* trimmed — the tool's own rule for usable content, applied here because a
|
||||
* rejected call keeps its args verbatim. The row then renders the counts alone
|
||||
* rather than falling back to the generic tool summary: the counts are already
|
||||
* known to be good, and the active-item clause is the only part an unusable
|
||||
* name costs.
|
||||
* @param todos - the whole list, in model order.
|
||||
* @returns the done/total counts and the two summary halves.
|
||||
*/
|
||||
export function planSummary(todos: readonly PlanItemLike[]): PlanSummary {
|
||||
const active = todos.filter(t => t.status === 'in_progress')
|
||||
const first = active[0]?.content
|
||||
const named = typeof first === 'string' && first.trim() !== ''
|
||||
return {
|
||||
done: todos.filter(t => t.status === 'completed').length,
|
||||
total: todos.length,
|
||||
activeContent: named ? first : null,
|
||||
activeExtra: named ? active.length - 1 : 0,
|
||||
}
|
||||
}
|
||||
@@ -2,9 +2,10 @@
|
||||
// "Tool call" card, registered into the keyed 'conversation.chat.toolview'
|
||||
// hole like the bash sample (a product registration, not a sample). The row
|
||||
// composes ToolRow (chrome, running sweep, whole-row expand) and swaps in a
|
||||
// summary of the written list (counts + active item) from the call args; the
|
||||
// durable list itself renders in the TodoPanel above the composer, so the
|
||||
// row stays one line until expanded.
|
||||
// summary of the written list (counts + active items) from the call args, with
|
||||
// the parallel-active count riding ToolRow's non-shrinking summary suffix so a
|
||||
// narrow row never clips it; the durable list itself renders in the TodoPanel
|
||||
// above the composer, so the row stays one line until expanded.
|
||||
|
||||
import { IconChecklistOutline14 } from '@deepseek-ai/dsh-client-ui-primitives'
|
||||
import type { Context } from 'cordis'
|
||||
@@ -13,18 +14,26 @@ import type { ToolRowProps } from '../contract/slots.ts'
|
||||
import { toolRowModel } from '../contract/tool-call-model.ts'
|
||||
import { ToolRow } from '../chat/ToolRow.tsx'
|
||||
import { NS } from '../locales.ts'
|
||||
import { planSummary, type PlanItemLike } from './plan-summary.ts'
|
||||
|
||||
/** Todo row props: the toolview runtime share plus the standard locale seat. */
|
||||
type TodoRowProps = ToolRowProps & PropsLocale<'conversation'>
|
||||
|
||||
/** One parsed args item, shape-checked (model JSON: any field may be missing or mistyped). */
|
||||
interface TodoWriteItem { content?: unknown; status?: unknown }
|
||||
|
||||
function isItem(value: unknown): value is TodoWriteItem {
|
||||
function isItem(value: unknown): value is PlanItemLike {
|
||||
return typeof value === 'object' && value !== null
|
||||
}
|
||||
|
||||
function summarize(argsRaw: string, t: TodoRowProps['t']): string | null {
|
||||
/**
|
||||
* The row's summary split at the ellipsis boundary: `text` truncates, `extra`
|
||||
* is the parallel-active count that must not, so a narrow row never clips the
|
||||
* one part that says several tasks are running.
|
||||
*/
|
||||
interface RowSummary {
|
||||
text: string
|
||||
extra: number
|
||||
}
|
||||
|
||||
function summarize(argsRaw: string, t: TodoRowProps['t']): RowSummary | null {
|
||||
let parsed: unknown
|
||||
try {
|
||||
parsed = JSON.parse(argsRaw)
|
||||
@@ -37,12 +46,12 @@ function summarize(argsRaw: string, t: TodoRowProps['t']): string | null {
|
||||
if (typeof parsed !== 'object' || parsed === null) return null
|
||||
const todos = (parsed as { todos?: unknown }).todos
|
||||
if (!Array.isArray(todos) || !todos.every(isItem)) return null
|
||||
const done = todos.filter(item => item.status === 'completed').length
|
||||
const active = todos.find(item => item.status === 'in_progress')
|
||||
const head = t('todo.completed', { done, total: todos.length })
|
||||
return typeof active?.content === 'string' && active.content !== ''
|
||||
? `${head} · ${active.content}`
|
||||
: head
|
||||
const { done, total, activeContent, activeExtra } = planSummary(todos)
|
||||
const head = t('todo.completed', { done, total })
|
||||
return {
|
||||
text: activeContent === null ? head : `${head} · ${activeContent}`,
|
||||
extra: activeExtra,
|
||||
}
|
||||
}
|
||||
|
||||
/** One-line plan update row (the whole row toggles the call's Input/Output
|
||||
@@ -52,7 +61,7 @@ function summarize(argsRaw: string, t: TodoRowProps['t']): string | null {
|
||||
export function TodoRow({ toolName, block, inspect, t }: TodoRowProps) {
|
||||
const model = toolRowModel(toolName, block)
|
||||
const argsRaw = ('kind' in block ? block.call?.argsRaw : block.argsRaw) ?? ''
|
||||
const summary = summarize(argsRaw, t) ?? model.summary
|
||||
const summary = summarize(argsRaw, t) ?? { text: model.summary, extra: 0 }
|
||||
return (
|
||||
<ToolRow
|
||||
t={t}
|
||||
@@ -60,7 +69,8 @@ export function TodoRow({ toolName, block, inspect, t }: TodoRowProps) {
|
||||
toolName={toolName}
|
||||
icon={<IconChecklistOutline14 />}
|
||||
title={t('todo.rowTitle')}
|
||||
summary={summary}
|
||||
summary={summary.text}
|
||||
summarySuffix={summary.extra > 0 ? `+${summary.extra}` : null}
|
||||
body={model.body}
|
||||
output={model.output}
|
||||
errorSummary={model.errorSummary}
|
||||
|
||||
@@ -301,6 +301,20 @@ describe('ToolRow', () => {
|
||||
expect(view.getByText('List files')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('renders summarySuffix outside the ellipsized summary span, and drops it on a failure line', () => {
|
||||
const view = render(<ToolRow {...rowProps} summarySuffix="+2" />)
|
||||
const summary = view.getByText('List files')
|
||||
const suffix = view.getByText('+2')
|
||||
// Separate spans: .summary truncates, the suffix must not travel inside it.
|
||||
expect(summary.contains(suffix)).toBe(false)
|
||||
view.unmount()
|
||||
// The failure line replaces the summary wholesale, so the suffix goes with it.
|
||||
const failed = render(
|
||||
<ToolRow {...rowProps} state="error" errorSummary="boom" summarySuffix="+2" />,
|
||||
)
|
||||
expect(failed.queryByText('+2')).toBeNull()
|
||||
})
|
||||
|
||||
it('an error file row drops the open-file link (the summary is failure prose, not the path)', () => {
|
||||
const open = vi.fn()
|
||||
const view = render(
|
||||
|
||||
@@ -1,10 +1,13 @@
|
||||
// @vitest-environment jsdom
|
||||
/**
|
||||
* Todo display acceptance: the TodoPanel plan strip (empty-hidden, status
|
||||
* rows, collapse), its TodoDock adapter (selects the plan off the session
|
||||
* snapshot and follows changes), and the todo_write toolview row (progress
|
||||
* summary from args, generic fallback on malformed JSON, shared ToolRow
|
||||
* state dots and leading expansion).
|
||||
* Todo display acceptance: the TodoPanel plan strip (empty-hidden, status rows
|
||||
* including several `in_progress` at once, collapse), its TodoDock adapter
|
||||
* (selects the plan off the session snapshot and follows changes), the row's
|
||||
* plan summary (counts plus the two halves of the active summary — the named
|
||||
* task and the `+N` count that parallel work adds, kept apart so the row never
|
||||
* ellipsizes the count away), and the todo_write toolview row (progress summary
|
||||
* from args, generic fallback on malformed JSON, shared ToolRow state dots and
|
||||
* leading expansion).
|
||||
*/
|
||||
import { act, cleanup, fireEvent, render, screen } from '@testing-library/react'
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
@@ -17,6 +20,7 @@ import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts
|
||||
import { TodoRow, todoToolview } from '../src/client/toolviews/todo-row.tsx'
|
||||
import type { TodoDockProps } from '../src/client/skeleton/TodoPanel.tsx'
|
||||
import { TodoDock, TodoPanel, todoDockEntry } from '../src/client/skeleton/TodoPanel.tsx'
|
||||
import { planSummary } from '../src/client/toolviews/plan-summary.ts'
|
||||
import { NS, zh } from '../src/client/locales.ts'
|
||||
|
||||
type TodoRowProps = Parameters<typeof TodoRow>[0]
|
||||
@@ -32,6 +36,49 @@ const LIST: TodoItem[] = [
|
||||
{ content: '补测试', status: 'pending' },
|
||||
]
|
||||
|
||||
/** A parallel plan: three tasks running at once (concurrent subagents). */
|
||||
const PARALLEL: TodoItem[] = [
|
||||
{ content: '搭骨架', status: 'completed' },
|
||||
{ content: '写组件', status: 'in_progress' },
|
||||
{ content: '跑后台构建', status: 'in_progress' },
|
||||
{ content: '读源码', status: 'in_progress' },
|
||||
{ content: '补测试', status: 'pending' },
|
||||
]
|
||||
|
||||
describe('planSummary', () => {
|
||||
it('counts done/total and names the single active item with no extra count', () => {
|
||||
expect(planSummary(LIST)).toEqual({ done: 1, total: 3, activeContent: '写组件', activeExtra: 0 })
|
||||
})
|
||||
|
||||
it('reports the extra active count separately when several items are in progress', () => {
|
||||
// Parallel work marks several: naming one and hiding the rest would lose
|
||||
// them, and the count stays unjoined so the row cannot ellipsize it.
|
||||
expect(planSummary(PARALLEL)).toEqual({ done: 1, total: 5, activeContent: '写组件', activeExtra: 2 })
|
||||
})
|
||||
|
||||
it('has no hint when nothing is in progress', () => {
|
||||
expect(planSummary([{ content: '都完了', status: 'completed' }]))
|
||||
.toEqual({ done: 1, total: 1, activeContent: null, activeExtra: 0 })
|
||||
})
|
||||
|
||||
it('has no hint when the first active item carries no usable content (model JSON)', () => {
|
||||
// Unvalidated args: a missing, mistyped, empty, or whitespace-only content
|
||||
// yields no hint — and no orphan count, even with a second active item to
|
||||
// count. Whitespace-only is the tool's own rejection rule (trimmed
|
||||
// non-empty), and a rejected call keeps its args verbatim.
|
||||
expect(planSummary([{ status: 'in_progress' }, { content: 'x', status: 'in_progress' }]))
|
||||
.toMatchObject({ activeContent: null, activeExtra: 0 })
|
||||
expect(planSummary([{ content: 42, status: 'in_progress' }]).activeContent).toBeNull()
|
||||
expect(planSummary([{ content: '', status: 'in_progress' }]).activeContent).toBeNull()
|
||||
expect(planSummary([{ content: ' ', status: 'in_progress' }, { content: 'x', status: 'in_progress' }]))
|
||||
.toMatchObject({ activeContent: null, activeExtra: 0 })
|
||||
})
|
||||
|
||||
it('is empty-safe', () => {
|
||||
expect(planSummary([])).toEqual({ done: 0, total: 0, activeContent: null, activeExtra: 0 })
|
||||
})
|
||||
})
|
||||
|
||||
describe('TodoPanel', () => {
|
||||
it('renders nothing while the list is empty', () => {
|
||||
const { container } = render(<TodoPanel todos={[]} t={t} />)
|
||||
@@ -80,6 +127,18 @@ describe('TodoPanel', () => {
|
||||
expect(screen.getAllByRole('listitem')).toHaveLength(3)
|
||||
})
|
||||
|
||||
it('marks every parallel active item, and counts them all in the header', () => {
|
||||
render(<TodoPanel todos={PARALLEL} t={t} />)
|
||||
fireEvent.click(screen.getByRole('button', { expanded: false }))
|
||||
// The old unconditional cap made this list unreachable: three items carry
|
||||
// the in-progress glyph at once, and the header counts all three.
|
||||
const statuses = screen.getAllByRole('listitem').map(li => li.getAttribute('data-status'))
|
||||
expect(statuses.filter(s => s === 'in_progress')).toHaveLength(3)
|
||||
expect(screen.getByText('跑后台构建')).toBeTruthy()
|
||||
expect(screen.getByText('读源码')).toBeTruthy()
|
||||
expect(screen.getByText('1 已完成 · 3 进行中 · 1 待处理')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('an all-completed list collapses the summary to the done count alone', () => {
|
||||
render(<TodoPanel todos={[{ content: '都完了', status: 'completed' }]} t={t} />)
|
||||
expect(screen.getByRole('button', { expanded: false })).toBeTruthy()
|
||||
@@ -145,12 +204,30 @@ describe('TodoRow', () => {
|
||||
expect(screen.getByText('1/3 已完成 · 写组件')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('reports the extra active count outside the ellipsized summary text', () => {
|
||||
const { container } = render(<TodoRow {...rowProps(resultNode(JSON.stringify({ todos: PARALLEL })))} />)
|
||||
const text = screen.getByText('1/5 已完成 · 写组件')
|
||||
const extra = screen.getByText('+2')
|
||||
// Separate spans: .summary truncates, the count must not travel inside it.
|
||||
expect(text.contains(extra)).toBe(false)
|
||||
expect(container.textContent).toContain('1/5 已完成 · 写组件+2')
|
||||
})
|
||||
|
||||
it('omits the active clause when no item is in progress and reads running-call args', () => {
|
||||
const args = JSON.stringify({ todos: [{ content: 'x', status: 'completed' }] })
|
||||
render(<TodoRow {...rowProps({ callId: 'c1', name: 'todo_write', argsRaw: args, turn: 1, step: 1, time: 1_000, callView: null })} />)
|
||||
expect(screen.getByText('1/1 已完成')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('keeps the counts when an active item has unusable content, instead of the generic summary', () => {
|
||||
// planSummary yields activeContent null here, but the counts are known good,
|
||||
// so the row drops only the active clause — `?? model.summary` never runs.
|
||||
const args = JSON.stringify({ todos: [{ content: 'done', status: 'completed' }, { content: 42, status: 'in_progress' }] })
|
||||
const { container } = render(<TodoRow {...rowProps(resultNode(args))} />)
|
||||
expect(screen.getByText('1/2 已完成')).toBeTruthy()
|
||||
expect(container.textContent).not.toContain('+')
|
||||
})
|
||||
|
||||
it('keeps the non-ok execution states visible through the shared row states', () => {
|
||||
// A running call (no result yet) carries the running state (row sweep).
|
||||
const args = JSON.stringify({ todos: LIST })
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
/**
|
||||
* The one-line contract of the ToolRow summary line as CSS text. jsdom has no
|
||||
* layout, so the rendering specs (chat-tool-row.spec.tsx) can pin which spans
|
||||
* exist but not whether a narrow row still fits on one line; these read the
|
||||
* declarations the layout depends on.
|
||||
*/
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
|
||||
const css = readFileSync(fileURLToPath(new URL('../src/client/chat/ToolRow.module.css', import.meta.url)), 'utf8')
|
||||
/** Declarations only: the sheet's prose names the properties it explains. */
|
||||
const declarationText = css.replace(/\/\*[\s\S]*?\*\//g, ' ')
|
||||
|
||||
function declarations(selector: string): string[] {
|
||||
// Anchored at a rule boundary: an unanchored match would silently read a
|
||||
// compound rule that merely contains the selector (`.root:hover .summarySuffix`)
|
||||
// if one ever lands above the base rule.
|
||||
const rule = new RegExp(`(?:^|\\})\\s*\\${selector}\\s*\\{([^{}]*)\\}`).exec(declarationText)
|
||||
if (rule === null) throw new Error(`ToolRow.module.css has no \`${selector}\` rule`)
|
||||
return (rule[1] ?? '').split(';').map(part => part.trim()).filter(Boolean)
|
||||
}
|
||||
|
||||
describe('ToolRow.module.css summary line', () => {
|
||||
it('keeps the summary suffix on one line and unshrunk', () => {
|
||||
// `flex: none` stops the box shrinking, not the text wrapping: without
|
||||
// `nowrap`, a row too narrow for title + separator + suffix wraps the `+n`
|
||||
// onto a second line — the exact case the slot exists to survive.
|
||||
expect(declarations('.summarySuffix')).toEqual(expect.arrayContaining([
|
||||
'flex: none',
|
||||
'white-space: nowrap',
|
||||
]))
|
||||
})
|
||||
|
||||
it('leaves the truncation to the summary text alone', () => {
|
||||
// The suffix must never ellipsize: a clipped count reads as a smaller
|
||||
// number rather than as missing information.
|
||||
expect(declarations('.summary')).toEqual(expect.arrayContaining([
|
||||
'overflow: hidden',
|
||||
'text-overflow: ellipsis',
|
||||
'white-space: nowrap',
|
||||
]))
|
||||
expect(declarations('.summarySuffix')).not.toEqual(expect.arrayContaining(['text-overflow: ellipsis']))
|
||||
})
|
||||
})
|
||||
@@ -161,7 +161,7 @@ export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap]
|
||||
export interface TodoItem {
|
||||
/** What this task is — a short imperative line shown in the UI. */
|
||||
content: string
|
||||
/** Lifecycle state. `in_progress` marks the single task being worked now. */
|
||||
/** Lifecycle state. `in_progress` marks a task being worked now; parallel work may mark several. */
|
||||
status: 'pending' | 'in_progress' | 'completed'
|
||||
}
|
||||
|
||||
|
||||
@@ -45,6 +45,7 @@
|
||||
"@deepseek-ai/dsh-session-persistence-sqlite": "workspace:^",
|
||||
"@deepseek-ai/dsh-subprocess": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-subagent": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-todo": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-web": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
|
||||
@@ -10,6 +10,7 @@ import type { Config as CodexHooksConfig } from '@deepseek-ai/dsh-hooks-codex'
|
||||
import type { Config as JsonlConfig } from '@deepseek-ai/dsh-session-persistence-jsonl'
|
||||
import type { Config as SqliteConfig } from '@deepseek-ai/dsh-session-persistence-sqlite'
|
||||
import type { Config as ToolSubagentConfig } from '@deepseek-ai/dsh-tool-subagent'
|
||||
import type { Config as ToolTodoConfig } from '@deepseek-ai/dsh-tool-todo'
|
||||
import type { Config as ToolWebConfig } from '@deepseek-ai/dsh-tool-web'
|
||||
import type { ProjectProfile } from '../../project/types.ts'
|
||||
import { defineFeatures } from '../define-feature.ts'
|
||||
@@ -126,7 +127,12 @@ config:
|
||||
id: 'default',
|
||||
label: 'todo_write tool',
|
||||
default: true,
|
||||
resources: [{ kind: 'npm-cordis-config-entry', id: 'tool-todo', package: '@deepseek-ai/dsh-tool-todo' }],
|
||||
resources: [{
|
||||
kind: 'npm-cordis-config-entry',
|
||||
id: 'tool-todo',
|
||||
package: '@deepseek-ai/dsh-tool-todo',
|
||||
config: { allowParallelInProgress: true } satisfies ToolTodoConfig,
|
||||
}],
|
||||
}],
|
||||
},
|
||||
{
|
||||
|
||||
@@ -27,6 +27,9 @@
|
||||
{
|
||||
"path": "../../subagent/tool-subagent"
|
||||
},
|
||||
{
|
||||
"path": "../../todo/tool-todo"
|
||||
},
|
||||
{
|
||||
"path": "../../web/tool-web"
|
||||
},
|
||||
|
||||
@@ -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/todo/tool-todo/README.md
|
||||
README.md: 456d4a08d88b145d574362ffa0874faef9167b22
|
||||
README.zh.md: ec37682773e50c3f153525f6c2b6b6cce583144f
|
||||
README.md: 914e89a000e4bb87ebd7844f05db3809c6726528
|
||||
README.zh.md: c88dbf976fa5110028fcc964ab9aa8efcc3244d3
|
||||
@@ -14,9 +14,15 @@ Registers one tool, `todo_write(todos: [{ content, status }])`, on `ctx.tools`.
|
||||
|
||||
The list belongs to the ONE agent session that called the tool. There is no subagent/shared/swarm scope: a non-agent caller (no `exec.agent`) has nowhere to write the list and is rejected. This is a deliberate scope limit — see the Agent Note.
|
||||
|
||||
## Configuration
|
||||
|
||||
`allowParallelInProgress` is required: every composition must choose whether several todos may be `in_progress` at once. It is a deployment choice, not a fixed rule: whether concurrent active tasks are legitimate depends on runtime concurrency the tool cannot observe. Use `true` for agents that may fan out work and `false` to enforce the single-active discipline.
|
||||
|
||||
The flag moves the model-facing instruction and the accepted input together — `true` asks the model to mark every actively worked task and accepts any number, `false` asks for exactly one and rejects a call marking more with `Error: invalid todos: at most one task may be in_progress (got <n>)`. The durable-log invariant does NOT follow it: a log written while parallel work was allowed must still replay after a deployment tightens the policy, so the invariant stays silent on the active count.
|
||||
|
||||
## Validation
|
||||
|
||||
Beyond the schema's type/required/enum checks, `execute` rejects an empty or duplicate `content`, more than one `in_progress` task (a coherent plan has at most one task active), and any item key beyond `content`/`status` — an extended item shape (ids, nesting) fails loud instead of silently flattening, keeping the logged snapshot equal to what the model believes it wrote. Ordering and the discipline of keeping the list current are left to the model via the tool description.
|
||||
Beyond the schema's type/required/enum checks, `execute` rejects an empty or duplicate `content`, and any item key beyond `content`/`status` — an extended item shape (ids, nesting) fails loud instead of silently flattening, keeping the logged snapshot equal to what the model believes it wrote. How many tasks may be `in_progress` at once is the deployment's call (§ Configuration): a composition that chooses `true` permits parallel work (concurrent subagents, background commands) to mark several tasks simultaneously. Ordering and the discipline of keeping the list current are left to the model via the tool description.
|
||||
|
||||
## Rendering
|
||||
|
||||
@@ -50,7 +56,7 @@ Prefix-stable while the definition and visibility are unchanged. Plugin lifecycl
|
||||
|
||||
#### What the model sees
|
||||
|
||||
Each assistant tool call retains the entire replacement list in its arguments. Success returns exactly `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.` Stable failures are ``Error: invalid todo: `content` must be a non-empty string``, `Error: invalid todos: duplicate content "<content>"`, `Error: invalid todos: at most one task may be in_progress, got <count>`, and `Error: todo_write requires an owning agent session`. The full `todo/write` session event is UI and replay state, not a second model message.
|
||||
Each assistant tool call retains the entire replacement list in its arguments. Success returns exactly `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.` Stable failures are ``Error: invalid todo: `content` must be a non-empty string``, `Error: invalid todos: duplicate content "<content>"`, `Error: todo_write requires an owning agent session`, and — only where the deployment set `allowParallelInProgress: false` — `Error: invalid todos: at most one task may be in_progress (got <n>)`. The full `todo/write` session event is UI and replay state, not a second model message.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -14,9 +14,15 @@
|
||||
|
||||
该列表属于调用工具的唯一 agent 会话。不存在 subagent／共享／swarm scope：非 agent 调用方（没有 `exec.agent`）无处写入列表，因此会被拒绝。这是有意设置的 scope 限制，详见 Agent Note（agent 决策记录）。
|
||||
|
||||
## 配置
|
||||
|
||||
`allowParallelInProgress` 是必填项：每个组合都必须选择是否允许多个 todo 同时处于 `in_progress`。这是部署层的选择而非固定规则：并发的活跃任务是否合理，取决于工具无法观测的运行时并发情况。可能并行展开工作的 agent 使用 `true`，`false` 则强制执行单活跃项纪律。
|
||||
|
||||
该开关会同时改变面向模型的指令与接受的输入——`true` 要求模型标记每个正在推进的任务并接受任意数量；`false` 要求恰好一个，并以 `Error: invalid todos: at most one task may be in_progress (got <n>)` 拒绝标记更多的调用。持久日志不变式**不**跟随它：在允许并行时写下的日志，在部署收紧策略之后仍必须可回放，因此不变式对活跃数量保持沉默。
|
||||
|
||||
## 验证
|
||||
|
||||
除 schema 的类型／必填／枚举检查外，`execute` 还会拒绝空或重复的 `content`、同时存在多个 `in_progress` 任务的情况（连贯计划最多只有一个活跃任务），以及 `content`/`status` 之外的任何条目键——扩展条目形状（id、嵌套）会明确报错而不是被静默压平，保证落日志的快照与模型自认为写入的内容一致。列表的顺序及及时更新由模型依照工具描述负责。
|
||||
除 schema 的类型／必填／枚举检查外，`execute` 还会拒绝空或重复的 `content`，以及 `content`/`status` 之外的任何条目键——扩展条目形状（id、嵌套）会明确报错而不是被静默压平，保证落日志的快照与模型自认为写入的内容一致。同时可以有多少任务处于 `in_progress` 由部署决定（见 § 配置）：选择 `true` 的组合允许并行工作（并发 subagent、后台命令）同时将多个任务标记为 `in_progress`。列表的顺序及及时更新由模型依照工具描述负责。
|
||||
|
||||
## 渲染
|
||||
|
||||
@@ -50,7 +56,7 @@
|
||||
|
||||
#### 模型看到的内容
|
||||
|
||||
每个 assistant 工具调用都会在参数中保留整个替换列表。成功时原样返回 `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.`。稳定失败文本为 ``Error: invalid todo: `content` must be a non-empty string``、`Error: invalid todos: duplicate content "<content>"`、`Error: invalid todos: at most one task may be in_progress, got <count>` 和 `Error: todo_write requires an owning agent session`。完整 `todo/write` 会话事件是 UI 与回放状态，而非第二条模型消息。
|
||||
每个 assistant 工具调用都会在参数中保留整个替换列表。成功时原样返回 `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.`。稳定失败文本为 ``Error: invalid todo: `content` must be a non-empty string``、`Error: invalid todos: duplicate content "<content>"`、`Error: todo_write requires an owning agent session`，以及——仅在部署设置了 `allowParallelInProgress: false` 时——`Error: invalid todos: at most one task may be in_progress (got <n>)`。完整 `todo/write` 会话事件是 UI 与回放状态，而非第二条模型消息。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
|
||||
@@ -30,6 +30,7 @@
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0",
|
||||
"zod": "^4.4.3"
|
||||
},
|
||||
"peerDependencies": {
|
||||
@@ -41,6 +42,8 @@
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@cordisjs/plugin-include": "workspace:^",
|
||||
"@cordisjs/plugin-loader": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
|
||||
|
||||
@@ -6,7 +6,8 @@
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import { z } from 'zod'
|
||||
import z from 'schemastery'
|
||||
import { z as zod } from 'zod'
|
||||
import type { ZodType } from 'zod'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { TodoItem } from '@deepseek-ai/dsh-session'
|
||||
@@ -24,29 +25,73 @@ export const inject = ['tools']
|
||||
/** The valid {@link TodoItem} statuses, as a runtime set for input narrowing. */
|
||||
const STATUSES = ['pending', 'in_progress', 'completed'] as const
|
||||
|
||||
const DESCRIPTION =
|
||||
/** Model-facing todo tool configuration. */
|
||||
export interface Config {
|
||||
/**
|
||||
* Required deployment choice for whether several todos may be `in_progress` at once. True suits
|
||||
* agents that run work concurrently — subagents, background commands, workflow fan-out — and the
|
||||
* description then instructs the model to mark every actively worked task. False restores the
|
||||
* single-active discipline: the description asks for exactly one, and a call marking more is
|
||||
* rejected.
|
||||
*/
|
||||
allowParallelInProgress: boolean
|
||||
}
|
||||
|
||||
/** Schemastery configuration for the todo tool consumer. */
|
||||
export const Config: z<Config> = z.object({
|
||||
allowParallelInProgress: z.boolean().required(),
|
||||
})
|
||||
|
||||
const DESCRIPTION_HEAD =
|
||||
'Record and update a structured task list for the current work. Send the ENTIRE '
|
||||
+ 'list every call — it REPLACES the previous list (there are no partial updates, '
|
||||
+ 'no per-item edits). Use it to plan multi-step work and show progress: add one '
|
||||
+ 'todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` '
|
||||
+ 'at a time; while work remains, exactly one active task should be '
|
||||
+ '`in_progress`. Mark a todo `completed` the moment it is done (do not batch '
|
||||
+ 'completions), and allow no `in_progress` item only once all work is complete. '
|
||||
+ 'Skip the list for trivial single-step tasks. Statuses: `pending` '
|
||||
+ '(not started), `in_progress` (being worked on now), `completed` (finished).'
|
||||
+ 'todo per concrete step before you start. '
|
||||
|
||||
const DESCRIPTION_PARALLEL =
|
||||
'Mark every todo being actively worked '
|
||||
+ 'on `in_progress` — several at once when work genuinely runs in parallel (e.g. '
|
||||
+ 'concurrent subagents or background commands), one for sequential work; while '
|
||||
+ 'work remains, at least one task should be `in_progress`. '
|
||||
|
||||
const DESCRIPTION_SINGLE =
|
||||
'Keep AT MOST ONE todo `in_progress` at a '
|
||||
+ 'time; while work remains, exactly one active task should be `in_progress`. '
|
||||
|
||||
const DESCRIPTION_TAIL =
|
||||
'Mark a todo '
|
||||
+ '`completed` the moment it is done (do not batch completions), and allow no '
|
||||
+ '`in_progress` item only once all work is complete. Skip the list for trivial '
|
||||
+ 'single-step tasks. Statuses: `pending` (not started), `in_progress` (being '
|
||||
+ 'worked on now), `completed` (finished).'
|
||||
|
||||
/**
|
||||
* The model-facing description for one activation. The active-status clause is the only part that
|
||||
* varies, because it is the only instruction the parallel policy changes.
|
||||
* @param allowParallel - whether several todos may be `in_progress` at once.
|
||||
* @returns the composed tool description.
|
||||
*/
|
||||
function describe(allowParallel: boolean): string {
|
||||
return DESCRIPTION_HEAD
|
||||
+ (allowParallel ? DESCRIPTION_PARALLEL : DESCRIPTION_SINGLE)
|
||||
+ DESCRIPTION_TAIL
|
||||
}
|
||||
|
||||
/**
|
||||
* Validate the value constraints the ParameterSchemaSpec can't express and build the canonical {@link
|
||||
* TodoItem}[]: trimmed non-empty unique content and at most one in-progress item. The registry
|
||||
* has already enforced the status enum and rejected unknown item keys (`additionalProperties:
|
||||
* false` — the logged snapshot must equal what the model believes it wrote, so a nested/extended
|
||||
* item shape fails loud at the schema boundary instead of silently flattening); the cast below
|
||||
* records that guarantee.
|
||||
* TodoItem}[]: trimmed non-empty unique content, and at most one `in_progress` item unless the
|
||||
* deployment allows parallel work. The registry has already enforced the status enum and rejected
|
||||
* unknown item keys (`additionalProperties: false` — the logged snapshot must equal what the model
|
||||
* believes it wrote, so a nested/extended item shape fails loud at the schema boundary instead of
|
||||
* silently flattening); the cast below records that guarantee.
|
||||
* @param raw - the model-supplied list, already schema-checked.
|
||||
* @param allowParallel - whether several items may be `in_progress` at once.
|
||||
* @returns the canonical list.
|
||||
*/
|
||||
function toTodoList(raw: { content: string; status: string }[]): TodoItem[] {
|
||||
function toTodoList(raw: { content: string; status: string }[], allowParallel: boolean): TodoItem[] {
|
||||
const todos: TodoItem[] = []
|
||||
const seen = new Set<string>()
|
||||
let inProgress = 0
|
||||
let active = 0
|
||||
for (const item of raw) {
|
||||
const content = item.content.trim()
|
||||
if (content.length === 0) {
|
||||
@@ -56,27 +101,32 @@ function toTodoList(raw: { content: string; status: string }[]): TodoItem[] {
|
||||
throw new Error(`invalid todos: duplicate content ${JSON.stringify(content)}`)
|
||||
}
|
||||
seen.add(content)
|
||||
const status = item.status as TodoItem['status']
|
||||
if (status === 'in_progress') inProgress++
|
||||
todos.push({ content, status })
|
||||
if (item.status === 'in_progress') active++
|
||||
todos.push({ content, status: item.status as TodoItem['status'] })
|
||||
}
|
||||
if (inProgress > 1) {
|
||||
throw new Error(`invalid todos: at most one task may be in_progress, got ${inProgress}`)
|
||||
if (!allowParallel && active > 1) {
|
||||
throw new Error(`invalid todos: at most one task may be in_progress (got ${active})`)
|
||||
}
|
||||
return todos
|
||||
}
|
||||
|
||||
/** Wire payload schema of the `todos` projection (whole list or pre-first-write null). */
|
||||
const todosProjectionSchema: ZodType<TodoItem[] | null> = z.union([
|
||||
z.array(z.object({
|
||||
content: z.string(),
|
||||
status: z.union([z.literal('pending'), z.literal('in_progress'), z.literal('completed')]),
|
||||
const todosProjectionSchema: ZodType<TodoItem[] | null> = zod.union([
|
||||
zod.array(zod.object({
|
||||
content: zod.string(),
|
||||
status: zod.union([zod.literal('pending'), zod.literal('in_progress'), zod.literal('completed')]),
|
||||
})),
|
||||
z.null(),
|
||||
zod.null(),
|
||||
])
|
||||
|
||||
/** Register the `todo_write` tool on `ctx.tools` and, when the session-projection seam is composed, the `todos` unit. */
|
||||
export function apply(ctx: Context): void {
|
||||
/**
|
||||
* Register the `todo_write` tool on `ctx.tools` and, when the session-projection seam is composed,
|
||||
* the `todos` unit.
|
||||
* @param ctx - registrant context carrying the tool registry.
|
||||
* @param config - deployment's explicit todo policy.
|
||||
*/
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
const allowParallel = config.allowParallelInProgress
|
||||
// The unit child activates only when a projection registry is composed
|
||||
// (headless assemblies without the seam stay unaffected). Standing-plan fold:
|
||||
// latest whole todo/write list, cleared by the next turn/start (turn/end keeps
|
||||
@@ -99,7 +149,7 @@ export function apply(ctx: Context): void {
|
||||
})
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'todo_write',
|
||||
description: DESCRIPTION,
|
||||
description: describe(allowParallel),
|
||||
parameters: {
|
||||
todos: {
|
||||
type: 'array',
|
||||
@@ -155,7 +205,7 @@ export function apply(ctx: Context): void {
|
||||
}],
|
||||
},
|
||||
execute(args, exec) {
|
||||
const todos = toTodoList(args.todos)
|
||||
const todos = toTodoList(args.todos, allowParallel)
|
||||
if (!exec.agent) {
|
||||
// The list is per-agent-session state; a non-agent caller (no owning
|
||||
// session) has nowhere to write it. Reject rather than silently no-op.
|
||||
|
||||
@@ -12,11 +12,18 @@ export const name = 'tool-todo-invariant'
|
||||
/** Service required before the companion can reserve package ownership. */
|
||||
export const inject = ['invariants']
|
||||
|
||||
/** Validate one whole-list todo snapshot before it reaches the durable log. */
|
||||
/**
|
||||
* Validate one whole-list todo snapshot before it reaches the durable log.
|
||||
*
|
||||
* Deliberately silent on how many items are `in_progress`. That is the tool's
|
||||
* per-deployment policy (`Config.allowParallelInProgress`), not a durable-shape
|
||||
* rule: a log written while parallel work was allowed must still replay after a
|
||||
* deployment tightens the policy, so tying the invariant to the current config
|
||||
* would reject history that was valid when it was written.
|
||||
*/
|
||||
function validateTodos(value: unknown, fail: InvariantFailure): void {
|
||||
if (!Array.isArray(value)) fail('todo/write todos must be an array')
|
||||
const seen = new Set<string>()
|
||||
let active = 0
|
||||
for (const item of value) {
|
||||
if (typeof item !== 'object' || item === null) fail('todo/write entries must be objects')
|
||||
const { content, status } = item as Record<string, unknown>
|
||||
@@ -28,9 +35,7 @@ function validateTodos(value: unknown, fail: InvariantFailure): void {
|
||||
if (typeof status !== 'string' || !TODO_STATUSES.has(status)) {
|
||||
fail(`todo/write carries unknown status ${JSON.stringify(status)}`)
|
||||
}
|
||||
if (status === 'in_progress') active += 1
|
||||
}
|
||||
if (active > 1) fail(`todo/write contains ${active} in-progress entries; at most one is allowed`)
|
||||
}
|
||||
|
||||
/* jscpd:ignore-start -- package companions share replay and dispatch plumbing */
|
||||
|
||||
@@ -18,7 +18,7 @@ async function harness(adapter: MockAdapter): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await mountAgentLoopTestDependencies(ctx)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(ToolTodo)
|
||||
await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
return ctx
|
||||
}
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import SessionStore, { type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
import * as TodoInvariant from '@deepseek-ai/dsh-tool-todo/invariant'
|
||||
import InvariantService from '@deepseek-ai/dsh-invariants'
|
||||
|
||||
@@ -17,13 +19,22 @@ function event(todos: unknown): SessionEvent {
|
||||
}
|
||||
|
||||
describe('todo snapshot invariants', () => {
|
||||
it('accepts a unique whole-list snapshot with one active item', async () => {
|
||||
const ctx = await setup()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event([
|
||||
it('accepts historical and live parallel snapshots under the single-active tool policy', async () => {
|
||||
const todos = [
|
||||
{ content: 'Inspect state', status: 'completed' },
|
||||
{ content: 'Apply fix', status: 'in_progress' },
|
||||
{ content: 'Watch background build', status: 'in_progress' },
|
||||
{ content: 'Run checks', status: 'pending' },
|
||||
])) }).not.toThrow()
|
||||
] as const
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(ToolTodo, { allowParallelInProgress: false })
|
||||
ctx.sessions.create().append('todo/write', { todos: [...todos] })
|
||||
await ctx.plugin(InvariantService, { enabled: true })
|
||||
|
||||
await expect(ctx.plugin(TodoInvariant).then(() => undefined)).resolves.toBeUndefined()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(todos)) }).not.toThrow()
|
||||
})
|
||||
|
||||
it.each([
|
||||
@@ -36,7 +47,6 @@ describe('todo snapshot invariants', () => {
|
||||
[[{ content: 'same', status: 'pending' }, { content: 'same', status: 'completed' }], /repeats content/],
|
||||
[[{ content: 'task', status: 42 }], /unknown status/],
|
||||
[[{ content: 'task', status: 'paused' }], /unknown status/],
|
||||
[[{ content: 'one', status: 'in_progress' }, { content: 'two', status: 'in_progress' }], /at most one/],
|
||||
])('rejects an incoherent durable todo snapshot', async (todos, message) => {
|
||||
const ctx = await setup()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(todos)) }).toThrow(message)
|
||||
|
||||
@@ -0,0 +1,139 @@
|
||||
// Proves `allowParallelInProgress` is real configurability and not a constant:
|
||||
// the flag is set in a cordis.yml booted through the real Loader, and both faces
|
||||
// it controls — the model-facing description and the accepted input — follow it.
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { pathToFileURL } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import Include from '@cordisjs/plugin-include'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import AgentRegistry, { Inbox } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
|
||||
let root: string | undefined
|
||||
let context: Context | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
await context?.fiber.dispose()
|
||||
context = undefined
|
||||
if (root !== undefined) await rm(root, { recursive: true, force: true })
|
||||
root = undefined
|
||||
})
|
||||
|
||||
function agent(ctx: Context): Agent {
|
||||
const scope = ctx.plugin(() => {})
|
||||
const id = SessionId('todo-loader-agent')
|
||||
const session = Session.create(id)
|
||||
const value: Agent = {
|
||||
id, options: {}, session, inbox: new Inbox(session, { inserted: () => {}, discarded: () => {}, claimed: () => {} }),
|
||||
status: 'idle', ctx: scope.ctx,
|
||||
followup: () => {}, steer: () => {}, inject: () => {}, send: () => {}, cancel() {},
|
||||
runMaintenance: task => task(new AbortController().signal),
|
||||
whenIdle: () => Promise.resolve(),
|
||||
}
|
||||
ctx.agents.register(value)
|
||||
return value
|
||||
}
|
||||
|
||||
function resultText(result: { content: { type: string; text?: string }[] }): string {
|
||||
return result.content.filter(block => block.type === 'text').map(block => block.text).join('')
|
||||
}
|
||||
|
||||
/**
|
||||
* Boot a cordis.yml carrying the given tool-todo config block.
|
||||
* @param configLines - YAML lines nested under the tool's `config:` key.
|
||||
* @returns the booted context.
|
||||
*/
|
||||
async function boot(configLines: readonly string[]): Promise<Context> {
|
||||
root = await mkdtemp(join(tmpdir(), 'dsh-todo-loader-'))
|
||||
const configPath = join(root, 'cordis.yml')
|
||||
await writeFile(configPath, [
|
||||
"- name: '@deepseek-ai/dsh-agent'",
|
||||
"- name: '@deepseek-ai/dsh-system-prompt'",
|
||||
"- name: '@deepseek-ai/dsh-tools'",
|
||||
"- name: '@deepseek-ai/dsh-tool-todo'",
|
||||
...configLines.length > 0 ? [' config:', ...configLines] : [],
|
||||
'',
|
||||
].join('\n'))
|
||||
|
||||
const ctx = new Context()
|
||||
context = ctx
|
||||
ctx.baseUrl = pathToFileURL(root).href + '/'
|
||||
await ctx.plugin(Loader)
|
||||
ctx.loader.builtins.include = Include
|
||||
const modules = new Map<string, unknown>([
|
||||
['@deepseek-ai/dsh-agent', AgentRegistry],
|
||||
['@deepseek-ai/dsh-system-prompt', SystemPrompt],
|
||||
['@deepseek-ai/dsh-tools', ToolRegistry],
|
||||
['@deepseek-ai/dsh-tool-todo', ToolTodo],
|
||||
])
|
||||
ctx.loader.internal = {
|
||||
version: 'v2',
|
||||
async import(specifier: string) {
|
||||
if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`)
|
||||
return modules.get(specifier)
|
||||
},
|
||||
} as unknown as NonNullable<typeof ctx.loader.internal>
|
||||
await ctx.loader.create({ name: 'cordis:include', config: { path: pathToFileURL(configPath).href } })
|
||||
await ctx.loader.await()
|
||||
return ctx
|
||||
}
|
||||
|
||||
const PARALLEL_TODOS = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'in_progress' },
|
||||
]
|
||||
|
||||
describe('tool-todo real Loader composition through cordis.yml', () => {
|
||||
it('allowParallelInProgress: false narrows the description and rejects a parallel write', async () => {
|
||||
const ctx = await boot([' allowParallelInProgress: false'])
|
||||
const description = ctx.tools.schemas().find(s => s.name === 'todo_write')?.description ?? ''
|
||||
expect(description).toContain('Keep AT MOST ONE todo `in_progress`')
|
||||
expect(description).not.toContain('several at once')
|
||||
|
||||
const owner = agent(ctx)
|
||||
const result = await ctx.tools.execute({
|
||||
signal: new AbortController().signal,
|
||||
callId: CallId('parallel'),
|
||||
name: 'todo_write',
|
||||
arguments: { todos: PARALLEL_TODOS },
|
||||
agent: owner,
|
||||
})
|
||||
expect(result.isError).toBe(true)
|
||||
expect(resultText(result)).toContain('at most one task may be in_progress')
|
||||
expect(owner.session.events.some(e => e.type === 'todo/write')).toBe(false)
|
||||
}, 30_000)
|
||||
|
||||
it('allowParallelInProgress: true permits a parallel write end to end', async () => {
|
||||
const ctx = await boot([' allowParallelInProgress: true'])
|
||||
const description = ctx.tools.schemas().find(s => s.name === 'todo_write')?.description ?? ''
|
||||
expect(description).toContain('several at once when work genuinely runs in parallel')
|
||||
|
||||
const owner = agent(ctx)
|
||||
const result = await ctx.tools.execute({
|
||||
signal: new AbortController().signal,
|
||||
callId: CallId('parallel-enabled'),
|
||||
name: 'todo_write',
|
||||
arguments: { todos: PARALLEL_TODOS },
|
||||
agent: owner,
|
||||
})
|
||||
expect(result.isError).toBe(false)
|
||||
expect(owner.session.events.findLast(e => e.type === 'todo/write')?.data.todos).toEqual(PARALLEL_TODOS)
|
||||
}, 30_000)
|
||||
|
||||
it.each([
|
||||
{ label: 'is omitted', configLines: [], failure: '$.allowParallelInProgress missing required value' },
|
||||
{ label: 'is not boolean', configLines: [' allowParallelInProgress: "no"'], failure: '$.allowParallelInProgress expected boolean' },
|
||||
])('fails loading when allowParallelInProgress $label', async ({ configLines, failure }) => {
|
||||
// The policy is self-contained, so misconfiguration fails at load: the
|
||||
// entry's apply rejects and boot never reaches a running tool.
|
||||
await expect(boot(configLines)).rejects.toThrow(failure)
|
||||
}, 30_000)
|
||||
})
|
||||
@@ -42,7 +42,7 @@ async function harness(withTodoTool: boolean): Promise<Bench> {
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(SessionProjectionRegistry)
|
||||
if (withTodoTool) await ctx.plugin(ToolTodo)
|
||||
if (withTodoTool) await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
const session = ctx.sessions.create()
|
||||
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
|
||||
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
@@ -116,7 +116,7 @@ describe('todos projection provider', () => {
|
||||
it('drops the key when the tool-todo fiber unloads (HMR safety)', async () => {
|
||||
const bench = await harness(false)
|
||||
seedMessage(bench.session)
|
||||
const fiber = await bench.ctx.plugin(ToolTodo)
|
||||
const fiber = await bench.ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
expect((await bench.tailProjections())?.values).toEqual({ todos: null })
|
||||
await fiber.dispose()
|
||||
expect('todos' in ((await bench.tailProjections())?.values ?? {})).toBe(false)
|
||||
|
||||
@@ -26,11 +26,11 @@ function agentWithSession(id = 'parent-1'): Agent & { session: Session } {
|
||||
return { id: SessionId(id), session } as unknown as Agent & { session: Session }
|
||||
}
|
||||
|
||||
async function setup(): Promise<Context> {
|
||||
async function setup(allowParallelInProgress: boolean): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(tool)
|
||||
await ctx.plugin(tool, { allowParallelInProgress })
|
||||
return ctx
|
||||
}
|
||||
|
||||
@@ -52,7 +52,7 @@ function text(result: { content: { type: string; text?: string }[] }): string {
|
||||
|
||||
describe('dsh-tool-todo', () => {
|
||||
it('registers a `todo_write` tool whose schema is an array of {content,status}', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const schema = ctx.tools.schemas().find(s => s.name === 'todo_write')
|
||||
expect(schema).toBeDefined()
|
||||
const props = (schema!.parameters as { properties?: Record<string, unknown> }).properties ?? {}
|
||||
@@ -65,7 +65,7 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('appends a todo/write event carrying the whole list to the calling session', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('writer')
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'plan', status: 'in_progress' },
|
||||
@@ -85,7 +85,7 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('stores the trimmed content (the dedupe/length key), not the raw input', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('trim')
|
||||
const result = await callTodo(ctx, { todos: [{ content: ' plan the work ', status: 'pending' }] }, { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
@@ -95,7 +95,7 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('replaces the list on a second call (last-write-wins on the log)', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('writer-2')
|
||||
await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent })
|
||||
await callTodo(ctx, { todos: [
|
||||
@@ -111,38 +111,99 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('rejects a malformed status before execute runs (registry arg-validation)', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: [{ content: 'x', status: 'doing' }] })
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it('rejects a non-array todos argument', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: 'nope' })
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it('accepts several in_progress items at once (parallel work)', async () => {
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('parallel')
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'in_progress' },
|
||||
{ content: 'merge results', status: 'pending' },
|
||||
]
|
||||
const result = await callTodo(ctx, { todos }, { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
if (result.isError) throw new Error('expected todo_write success')
|
||||
expect(result.value).toEqual({
|
||||
todos,
|
||||
counts: { pending: 1, inProgress: 2, completed: 0 },
|
||||
})
|
||||
expect(agent.session.events.findLast(e => e.type === 'todo/write')!.data.todos).toEqual(todos)
|
||||
})
|
||||
|
||||
describe('allowParallelInProgress', () => {
|
||||
const parallel = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'in_progress' },
|
||||
]
|
||||
|
||||
it('false rejects a call marking several items in_progress', async () => {
|
||||
const ctx = await setup(false)
|
||||
const agent = agentWithSession('single-active')
|
||||
const result = await callTodo(ctx, { todos: parallel }, { agent })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('at most one task may be in_progress')
|
||||
// A rejected call must not reach the durable log.
|
||||
expect(agent.session.events.some(e => e.type === 'todo/write')).toBe(false)
|
||||
})
|
||||
|
||||
it('false still accepts one active item', async () => {
|
||||
const ctx = await setup(false)
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'pending' },
|
||||
]
|
||||
const result = await callTodo(ctx, { todos })
|
||||
expect(result.isError).toBe(false)
|
||||
})
|
||||
|
||||
it('true accepts the very list false rejects', async () => {
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: parallel })
|
||||
expect(result.isError).toBe(false)
|
||||
})
|
||||
|
||||
it('instructs the model to keep at most one active, while true instructs parallel', async () => {
|
||||
const single = await setup(false)
|
||||
const singleDesc = single.tools.schemas().find(s => s.name === 'todo_write')!.description
|
||||
expect(singleDesc).toContain('Keep AT MOST ONE todo `in_progress`')
|
||||
expect(singleDesc).not.toContain('several at once')
|
||||
|
||||
const parallelDesc = (await setup(true)).tools.schemas().find(s => s.name === 'todo_write')!.description
|
||||
expect(parallelDesc).toContain('several at once when work genuinely runs in parallel')
|
||||
expect(parallelDesc).not.toContain('AT MOST ONE')
|
||||
})
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ label: 'empty content', todos: [{ content: ' ', status: 'pending' }], fragment: 'non-empty' },
|
||||
{ label: 'duplicate content', todos: [{ content: 'dup', status: 'pending' }, { content: 'dup', status: 'completed' }], fragment: 'duplicate' },
|
||||
{ label: 'two in_progress', todos: [{ content: 'a', status: 'in_progress' }, { content: 'b', status: 'in_progress' }], fragment: 'in_progress' },
|
||||
{ label: 'unknown item keys', todos: [{ content: 'a', status: 'pending', children: [] }], fragment: 'not a declared property' },
|
||||
])('rejects $label as an isError result', async ({ todos, fragment }) => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain(fragment)
|
||||
})
|
||||
|
||||
it('rejects a non-agent caller (the list has no owning session)', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent: undefined })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('owning agent session')
|
||||
})
|
||||
|
||||
it('presents the call with a stable title and the list as raw input', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const def = ctx.tools.get('todo_write')!
|
||||
const todos = [{ content: 'a', status: 'pending' }]
|
||||
expect(def.presentCall?.({ todos })).toEqual({ card: 'generic', title: 'Update todo list', kind: 'other', rawInput: todos })
|
||||
@@ -152,7 +213,7 @@ describe('dsh-tool-todo', () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(tool)
|
||||
const fiber = await ctx.plugin(tool, { allowParallelInProgress: true })
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(true)
|
||||
await fiber.dispose()
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(false)
|
||||
|
||||
Generated
+12
@@ -4451,6 +4451,9 @@ importers:
|
||||
'@deepseek-ai/dsh-tool-subagent':
|
||||
specifier: workspace:^
|
||||
version: link:../../subagent/tool-subagent
|
||||
'@deepseek-ai/dsh-tool-todo':
|
||||
specifier: workspace:^
|
||||
version: link:../../todo/tool-todo
|
||||
'@deepseek-ai/dsh-tool-web':
|
||||
specifier: workspace:^
|
||||
version: link:../../web/tool-web
|
||||
@@ -5944,10 +5947,19 @@ importers:
|
||||
|
||||
packages/todo/tool-todo:
|
||||
dependencies:
|
||||
schemastery:
|
||||
specifier: ^3.18.0
|
||||
version: link:../../../vendor/schemastery
|
||||
zod:
|
||||
specifier: ^4.4.3
|
||||
version: 4.4.3
|
||||
devDependencies:
|
||||
'@cordisjs/plugin-include':
|
||||
specifier: workspace:^
|
||||
version: link:../../../vendor/include
|
||||
'@cordisjs/plugin-loader':
|
||||
specifier: workspace:^
|
||||
version: link:../../../vendor/loader
|
||||
'@deepseek-ai/dsh-agent':
|
||||
specifier: workspace:^
|
||||
version: link:../../core/agent
|
||||
|
||||
@@ -38,6 +38,8 @@ _CORDIS_YML = """\
|
||||
cwd: '.'
|
||||
- id: todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
config:
|
||||
allowParallelInProgress: true
|
||||
"""
|
||||
|
||||
|
||||
|
||||
@@ -455,10 +455,10 @@ const TOOL_PACKAGES: ToolPackage[] = [
|
||||
requires: ['ctx.tools', 'owning Agent session'],
|
||||
writes: ['tool/call', 'todo/write', 'tool/result'],
|
||||
async mount(ctx) {
|
||||
await ctx.plugin(ToolTodo)
|
||||
await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
},
|
||||
note:
|
||||
'todo_write is session-owned state; UIs render the latest todo/write event as a checklist.',
|
||||
'todo_write is session-owned state; UIs render the latest todo/write event as a checklist. `allowParallelInProgress` is required with no default, so the catalog states its choice: `true`, whose description invites several `in_progress` items. A deployment choosing `false` receives the same tool with a description asking for exactly one active task.',
|
||||
},
|
||||
{
|
||||
pkg: '@deepseek-ai/dsh-tool-workflow',
|
||||
@@ -611,7 +611,7 @@ export function render(catalog: ToolCatalog): string {
|
||||
'',
|
||||
'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator\'s boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog Agent Note](../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md).',
|
||||
'',
|
||||
'Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.',
|
||||
'Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config, except where a Config field is REQUIRED with no default — there the generator must choose, and the per-package note records which branch this page shows. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.',
|
||||
'',
|
||||
'## Tool Package Map',
|
||||
'',
|
||||
|
||||
Reference in New Issue
Block a user