diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml index 3f2ed47be7..2a32b80867 100644 --- a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml @@ -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: b9782d2946086feac3bac4f4361de543b5e93e69 -2026-07-23-web-todo-display.zh.md: e2311d40c8b246add39657162d2fcf3206da24b1 +2026-07-23-web-todo-display.md: 338534d2d2eeb4b1d6df79b32f0d4ec5b6695d39 +2026-07-23-web-todo-display.zh.md: d6e3c2f56ac0251e59a434cd76c198b0434991be diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md index b9782d2946..338534d2d2 100644 --- a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md @@ -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 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. diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md index e2311d40c8..d6e3c2f56a 100644 --- a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md @@ -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。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。 diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml index 65deab6f74..5efe7a5816 100644 --- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml @@ -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/2026-07-26-todo-parallel-in-progress.md -2026-07-26-todo-parallel-in-progress.md: 170c0d205a95b0668e8da0997a04849aae2bd59e -2026-07-26-todo-parallel-in-progress.zh.md: 2ff13750bb2f19acccd09ffdd6d4937729e63803 +2026-07-26-todo-parallel-in-progress.md: 310763977862cf7b170a8901d636ce824fca304d +2026-07-26-todo-parallel-in-progress.zh.md: e00c8357cac1dbc9bb82388b3e25304f96e80b3b diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md index 170c0d205a..3107639778 100644 --- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md +++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md @@ -47,4 +47,4 @@ The row takes `planSummary` in `toolviews/plan-summary.ts`. It names the first a ## Consequences -A todo list can now faithfully mirror parallel execution, and every UI renders several active markers at once: the TUI's per-status prefix needed no change, 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 `tool-schemas.expected.json` sidecar carrying the todo schema (seven of the eight in the tree). Scenarios composing an identical header share one sidecar through `toolSchemasSource` rather than each keeping a copy, so the count tracks distinct header compositions, not scenarios; a branch changing the tool description still has to refresh whichever sidecars landed after it branched — `pnpm run test:snapshot:refresh` does it keylessly. 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, and the ACP `todo-write` scenario records a three-todo plan with two active — and each would fail again if its derivation returned to single-active. +A todo list can now faithfully mirror parallel execution, and every UI renders several active markers at once: the TUI's per-status prefix needed no change, 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..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, and the ACP `todo-write` scenario records a three-todo plan with two active — and each would fail again if its derivation returned to single-active. diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md index 2ff13750bb..e00c8357ca 100644 --- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md +++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md @@ -47,4 +47,4 @@ Status: implemented ## 后果 -现在 todo 列表可以忠实反映并行执行，并且每个 UI 都能一次渲染多个活跃标记：TUI 按状态区分的前缀无需改动，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 `tool-schemas.expected.json` sidecar（树中八个里有七个）。组合出相同 header 的场景通过 `toolSchemasSource` 共用同一份 sidecar，而非各自保留副本，因此这个数量对应的是不同的 header 组合，而不是场景数；改动工具描述的分支仍须刷新它分叉之后落地的那些 sidecar —— `pnpm run test:snapshot:refresh` 可以无 key 完成。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` 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——任一推导退回单活跃项，对应的测试都会失败。 +现在 todo 列表可以忠实反映并行执行，并且每个 UI 都能一次渲染多个活跃标记：TUI 按状态区分的前缀无需改动，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..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` 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——任一推导退回单活跃项，对应的测试都会失败。 diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index c177a4984a..57af22435f 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -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.sessionQuery (list_agents only)` | `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 (which additionally requires session query). | | `@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. | @@ -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` diff --git a/packages/client/connection/tests/fixture.spec.ts b/packages/client/connection/tests/fixture.spec.ts index 0e6b2fbf3d..f608190936 100644 --- a/packages/client/connection/tests/fixture.spec.ts +++ b/packages/client/connection/tests/fixture.spec.ts @@ -242,8 +242,8 @@ 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: the tool permits several in_progress, so - // the surfaces fed from here are exercised against more than one active item. + // 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) }) diff --git a/packages/sdk/helper/package.json b/packages/sdk/helper/package.json index bf9eacb813..bed70dbbda 100644 --- a/packages/sdk/helper/package.json +++ b/packages/sdk/helper/package.json @@ -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" } diff --git a/packages/sdk/helper/src/features/builtin/index.ts b/packages/sdk/helper/src/features/builtin/index.ts index 5022c063d5..abdcc35dd5 100644 --- a/packages/sdk/helper/src/features/builtin/index.ts +++ b/packages/sdk/helper/src/features/builtin/index.ts @@ -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' @@ -130,7 +131,7 @@ config: kind: 'npm-cordis-config-entry', id: 'tool-todo', package: '@deepseek-ai/dsh-tool-todo', - config: { allowParallelInProgress: true }, + config: { allowParallelInProgress: true } satisfies ToolTodoConfig, }], }], }, diff --git a/packages/sdk/helper/tsconfig.json b/packages/sdk/helper/tsconfig.json index b1a3b7a61a..528b370a5c 100644 --- a/packages/sdk/helper/tsconfig.json +++ b/packages/sdk/helper/tsconfig.json @@ -27,6 +27,9 @@ { "path": "../../subagent/tool-subagent" }, + { + "path": "../../todo/tool-todo" + }, { "path": "../../web/tool-web" }, diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index c194d675e7..1cf1c8d902 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -4330,6 +4330,9 @@ 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 diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 0fcd202198..b2c9204444 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -457,7 +457,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ 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', @@ -610,7 +610,7 @@ 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', '',