dsh-global-todo 0.7.1 → 0.8.0

package/CHANGELOG.md

@@ -1,3 +1,35 @@
+## [0.8.0] — 2026-10-20
+
+A todo can carry its plan, and the plan is what the agent receives.
+
+- **`steps[]` on a todo**: `{ text, done }`, up to 20 steps of 200 characters. Strings are accepted
+  wherever steps are (create, agent tools), a blank line is not a step, and a longer plan is
+  refused rather than truncated — twenty steps means the todo should have been split.
+- **The dispatch prompt numbers them**, marking the ones already done. Handing over "1. 对齐版本号
+  2. 跑 verify 3. 打 tag" is worth more than handing over a paragraph.
+- **The panel shows progress without opening the row** (`步骤 2/4` in the metadata), renders the
+  ticks in the detail, and takes one step per line in the add form.
+- **Agent guidance says so too**: multi-round work should be recorded with 3–6 steps, and a
+  finished step is one `global_todo_update`.
+- Replacement semantics (like `links`): the array travels whole through `applyPatch`, so there is
+  still one validation and one write path.
+
+## [0.7.2] — 2026-10-20
+
+The roadmap audited against the tree, and the review feature brought up to the same standard
+as the rest of the panel.
+
+- **`docs/ROADMAP.md` no longer lies.** Six entries claimed things that already exist (due
+  reminders, batch completion/tagging, archive, cross-machine notices, external ingest) — they
+  moved to *Landed* with the function that proves each one, and *Next* is now ordered by value
+  against effort with a "today" line per item.
+- **`/review` has route tests**: a rejected claim reopens and drops its completion record,
+  answering twice is a 400 rather than a silent success, an unknown id is a 404.
+- **The review state is photographed** — a fifth scenario (`panel-review.png`) in the same
+  harness as the others, asserted by `check:render` and indexed in both READMEs.
+- **Bulk confirm in the review view**: selecting several finished-by-agent rows and confirming
+  them in one go, since assigning is not what that view is for.
+
 ## [0.7.1] — 2026-10-20
 
 Documentation for the one piece of layout that cannot be "cleaned up".

package/README.md

@@ -43,6 +43,7 @@ preview and photographed by the same tool:
 | Empty list | [`panel-empty.png`](docs/screenshots/panel-empty.png) |
 | Filter with no match | [`panel-filtered.png`](docs/screenshots/panel-filtered.png) |
 | Inbox (awaiting confirmation) | [`panel-inbox.png`](docs/screenshots/panel-inbox.png) |
+| Awaiting review (agent finished) | [`panel-review.png`](docs/screenshots/panel-review.png) |
 | Due reminder | [`panel-reminders.png`](docs/screenshots/panel-reminders.png) |
 | Selection mode | [`panel-select.png`](docs/screenshots/panel-select.png) |
 
@@ -202,7 +203,7 @@ Your list is not touched by install or uninstall: it lives outside the plugin, a
 
 | Tool | Purpose |
 |---|---|
-| `global_todo_add` | Record an item — description, attachments, tags, priority, due time |
+| `global_todo_add` | Record an item — description, attachments, steps, tags, priority, due time |
 | `global_todo_note` | Append a progress note — where you are, what blocks you, who must decide |
 | `global_todo_capture` | **Record a batch**: for 「抓一下待办」 or a turn that produced several follow-ups; each entry is validated on its own |
 | `global_todo_list` | Query by state, tag or text; every row carries its creation time |
@@ -263,7 +264,7 @@ fence when that service is present, and by a strict loopback check otherwise.
 | POST | `/api/global-todo/bulk` | `{ ids, status?, addTags?, removeTags? }` — one change across a selection; a stale id lands in `unmatched` instead of failing the batch |
 | POST | `/api/global-todo/ingest` | `{ items: [{ title, source: { kind }, confidence }], dryRun? }` with `Authorization: Bearer <settings.ingestToken>` — external items; below `ingestConfirmBelow` they wait in the inbox |
 | GET | `/api/global-todo/health` | — (store location, counts, dispatch capabilities, plus **tool registration** and **whether the completion watcher attached** — both fail quietly, so both are reported — and `metrics`: dispatch success rate, agent tool calls, list growth; `autoCollect`: why each waiting conversation was or was not asked, counters, and how the settings file loaded) |
-| POST | `/api/global-todo/create` | `{ title, description?, links?, tags?, priority?, dueAt? }` |
+| POST | `/api/global-todo/create` | `{ title, description?, links?, steps?, tags?, priority?, dueAt? }` |
 | POST | `/api/global-todo/update` | `{ id, ...fields, by?: human\|agent }` |
 | POST | `/api/global-todo/status` | `{ id, status, by?: human\|agent }` |
 | POST | `/api/global-todo/remove` | `{ id }` |

package/README.zh.md

@@ -39,6 +39,7 @@ DSH 自带的 `todo_write` 属于**某一个 agent 会话**：整表替换、三
 | 清单为空 | [`panel-empty.png`](docs/screenshots/panel-empty.png) |
 | 筛选无结果 | [`panel-filtered.png`](docs/screenshots/panel-filtered.png) |
 | 收件箱（待确认） | [`panel-inbox.png`](docs/screenshots/panel-inbox.png) |
+| 待确认（Agent 完成） | [`panel-review.png`](docs/screenshots/panel-review.png) |
 | 到点提醒 | [`panel-reminders.png`](docs/screenshots/panel-reminders.png) |
 | 批量选择 | [`panel-select.png`](docs/screenshots/panel-select.png) |
 
@@ -127,7 +128,7 @@ dsh plugin --profile web remove dsh-global-todo
 
 | 工具 | 用途 |
 |---|---|
-| `global_todo_add` | 登记一条：描述、附件、标签、优先级、截止时间；同时记下「在哪个工作目录、哪个会话里写的」 |
+| `global_todo_add` | 登记一条：描述、附件、步骤、标签、优先级、截止时间；同时记下「在哪个工作目录、哪个会话里写的」 |
 | `global_todo_note` | 追加一条**进展记录**（做到哪了、卡在哪、需要谁做什么）；不改写你的描述 |
 | `global_todo_capture` | **一次登记多条**（批量抓取）：用户说「抓一下待办」，或你一轮里发现好几件要跟进的；逐条校验，坏的那条只跳过它自己 |
 | `global_todo_list` | 按状态/标签/关键词查询，每条都带上加入时间 |
@@ -159,7 +160,7 @@ dsh plugin --profile web remove dsh-global-todo
 | POST | `/api/global-todo/bulk` | `{ ids, status?, addTags?, removeTags? }`——一次改一整批；失效的 id 进 `unmatched`，不会让整批失败 |
 | POST | `/api/global-todo/ingest` | `{ items: [{ title, source: { kind }, confidence }], dryRun? }`，带 `Authorization: Bearer <settings.ingestToken>`——外部条目；置信度低于 `ingestConfirmBelow` 的先进收件箱 |
 | GET | `/api/global-todo/health` | —（数据位置、统计、派发能力，以及**工具注册状态**与**自动收尾观察者是否挂上**——这两种失败是静默的，所以必须能查；还有 `metrics`：派发成功率、工具调用次数、清单增长；`autoCollect`：每个候选对话**为什么被问/没被问**、计次，以及设置文件是怎么加载进来的） |
-| POST | `/api/global-todo/create` | `{ title, description?, links?, tags?, priority?, dueAt? }` |
+| POST | `/api/global-todo/create` | `{ title, description?, links?, steps?, tags?, priority?, dueAt? }` |
 | POST | `/api/global-todo/update` | `{ id, ...字段, by?: human\|agent }` |
 | POST | `/api/global-todo/status` | `{ id, status, by?: human\|agent }` |
 | POST | `/api/global-todo/remove` | `{ id }` |

package/docs/DESIGN.md

@@ -57,6 +57,25 @@ $DSH_HOME/global-todo/todos.json     ← { version: 1, todos: [ … ] }
   version, and a future migration step would run before the first write, keeping the old
   file as a backup.
 
+## A plan inside the todo
+
+A todo is one line, but the work behind it is often five steps. Rather than grow a second object
+(a "project", a "plan file"), a todo may carry `steps[]` — text plus a tick, order is the plan.
+
+- **Why inside the todo:** the dispatch prompt is the product here. Handing an agent "ship the
+  plugin" is a paragraph; handing it "1. 对齐版本号 2. 跑 verify 3. 打 tag 4. 补截图" is a plan it
+  can execute and report against. The steps are also what a person reviews afterwards.
+- **Shape:** `{ text, done }`, capped at `LIMITS.steps` (20) and 200 characters per step. Strings
+  are accepted wherever an array of steps is (create, agent tools) so a caller never has to spell
+  out `{ done: false }`; a blank line is a typo, not a step, and a plan longer than the cap is
+  refused rather than truncated — twenty steps means the todo should have been split.
+- **Replacement, not patching:** `steps` travels as a whole array through `applyPatch`, the same
+  rule as `links`. Toggling one tick is a client-side rewrite of the array, which keeps one write
+  path and one validation.
+- **Where it shows:** the row's metadata gets `步骤 2/4` (progress without opening anything), the
+  detail renders the ticks, the panel's add form takes one step per line, and the dispatch prompt
+  numbers them with `[已完成]` on the ones already behind us.
+
 ## On a wide window, the detail stands beside the list
 
 Expanding a row inline is right on a narrow window and wrong on a wide one: the list jumps, the

package/docs/ROADMAP.md

@@ -110,95 +110,129 @@ in `skipped[]`, and archived/cancelled rows deliberately do not block a new one.
 counts a disagreement once (`externalChanges`, `lastExternalAt` in `lib/store.js`; surfaced by
 `/health.store`). The panel shows a one-line notice instead of letting a synced folder change the
 list silently.
-**Side detail on wide windows** — above 1100px the open row's detail becomes a card at the
-panel's right edge instead of pushing the list down (CSS-only over the same markup; one detail
-implementation), while narrow windows keep the inline expansion.
+**Side detail on wide windows** — when the panel itself is at least 960px wide, the open row's
+detail becomes a card at the panel's right edge instead of pushing the list down (CSS-only over
+the same markup; one detail implementation), while narrow windows keep the inline expansion. The
+breakpoint follows the panel's measured width, and the card is `position: fixed` with a measured
+anchor — `DESIGN.md` records the two alternatives that were measured and rejected, so this is not
+re-litigated every time someone tries to "clean it up".
 **External ingest with an inbox** — `POST /ingest` takes source-tagged, confidence-scored items
 behind a Bearer token; low-confidence records wait in an `inbox` tag view with 确认 / 丢弃 and a
 seven-day sweep, so an external source cannot silently fill the list.
+**An agent's "done" is a claim** — finishing as an agent sets `review = { pending }`; a person
+confirms or sends it back through `POST /review` (`reviewTodo()` in `lib/model.js`, `review()` in
+`lib/service.js`). Confirming keeps the record finished; rejecting reopens it and drops the
+completion record, because "not actually done" is the only honest reading. The panel shows a
+待确认 chip, a 待确认 filter and 确认完成 / 退回清单; bulk confirm exists in that view.
+`counts.review` drives the chip. Tests: `test/model.test.mjs`, `test/routes.test.mjs`.
+**A design system with guards** — five type sizes (20/14/13/12/11), four control heights, one
+settings inspector, and no JavaScript layout measurement left in the panel. Three guards keep it
+that way: `test/locale.test.mjs` (duplicate keys, zh/en parity, full-width punctuation in English,
+missing `t()` keys), the scenario table in `tools/preview.mjs` (empty, filtered, inbox, review,
+reminder) photographed into `docs/screenshots/` by `npm run screenshots`, and
+`npm run check:render` asserting each state's marker.
 ### Partly landed
 
-- **Batch and multi-select** — the selection mode, its per-row markers and the batch
-  一键分配 are in (`lib/client.js`, `POST /assign` at
-  `lib/routes.js`, `assignMany()` at `lib/dispatch.js`; tests
-  `test/dispatch.test.mjs`). Batch 完成 / 打标签 across a selection do not exist.
-- **Session read-back** — `sessionAlive` is on every listed todo
-  (`lib/routes.js`, `lib/dispatch.js`). Reading what that session last said,
-  and linking to it, is not: `lib/completion.js` reads `assistant/message` only to
-  close a todo this plugin dispatched, and stores one summary in its completion record.
-- **What the agents produced** — the per-todo record with a summary and the changed
-  files landed (`completeTodo()` at `lib/model.js`, 「完成记录」 at
-  `lib/client.js`, the 已完成 filter and group at `lib/client.js`). The
-  cross-todo "what did the sessions finish this week, and what did they touch" view did
-  not.
+- **Session read-back** — `sessionAlive` is on every listed todo (`sessionAlive` in
+  `lib/dispatch.js`, surfaced by `GET /list`). Reading what that session last said, and
+  linking to it, is not: `lib/completion.js` reads `assistant/message` only to close a todo
+  this plugin dispatched, and stores one summary in its completion record.
+- **What the agents produced** — the per-todo record with a summary and the changed files landed
+  (`completeTodo()` in `lib/model.js`, 「完成记录」 in `lib/client.js`, the 已完成 filter and
+  group). The cross-todo "what did the sessions finish this week, and what did they touch" view
+  did not.
+- **Attachment health** — a dead file link is flagged on read, but there is no 「重新挂载」 next
+  to it (`relink` does not exist anywhere in `lib/`), and `annotateLinks()` has no unit test:
+  today the render assertion in `tools/preview.mjs` is the only coverage.
+- **Batch** — selection, 一键分配, 完成 / 归档 / 打标签 and 批量确认（待确认视图）are all in.
+  Nothing here is missing; it is listed because the panel is where the batch surface lives.
 
 ## Next
 
-### 1. Checklist inside a todo
+Ordered by value against effort, and audited against the tree on 2026-10-20 — "today"
+means what the code actually does, not what the last plan hoped.
 
-Large items ("ship the plugin") are really a list of steps. Proposed: an optional
-`steps[]` on a todo, rendered as checkboxes, and shipped to the agent as a numbered
-plan in the dispatch prompt.
+### 1. ~~Checklist inside a todo~~ — landed in 0.8.0
 
-- Effort: medium (model + tools + panel + prompt builder).
-- Today: nothing named `steps` exists anywhere in `lib/`, so this is untouched.
-- Why it matters: it removes the need for a separate "plan" plugin, and the dispatch
-  prompt gets materially better.
+`steps[]` (text + tick) ships on the todo, renders as `步骤 2/4` in the row and as ticks in the
+detail, is editable from the panel's add form, and travels in the dispatch prompt as a numbered
+plan. `normalizeSteps()` in `lib/model.js`, `dispatchPrompt()` in `lib/service.js`; tests in
+`test/model.test.mjs` and `test/service.test.mjs`.
 
-### 2. Session read-back
+What is left of the original idea: making a step addressable on its own (a tool that ticks step 3
+without resending the array) — not worth a tenth tool today.
 
-The panel shows whether the bound session is alive (`sessionAlive`). Next: show what
-that session last said — one line of its latest assistant message, and a link to open it
-— so a dispatched todo reports back where the work is.
+### 2. Session read-back — makes hand-off stop being fire-and-forget
 
-- Effort: medium. Needs a host-side read of the bound session (the `sessions` service
-  exists, but this must stay cheap and failure-tolerant).
-- Why it matters: hand-off stops being fire-and-forget.
+`sessionAlive` says a bound conversation still exists. Next: one line of its latest
+assistant message plus a link to open it.
 
-### 3. Due reminders
+- Today: `lib/completion.js` reads `assistant/message` only to close a todo this plugin
+  dispatched; nothing exposes it to the panel.
+- Effort: medium, and it must stay cheap and failure-tolerant: a missing or huge message is
+  a normal case, not an error.
+- Why second: the panel currently cannot answer "did the thing I handed over get anywhere",
+  which is the question people actually ask.
 
-A reminder when a due time passes, in the GUI and optionally to the IM channel this
-deployment already has.
+### 3. Markdown / TaskPaper import and export
 
-- Effort: medium. The plugin has no scheduler today (nothing in `lib/` matches
-  `remind`); the Host's timer service plus a config flag is the smallest version.
-- Careful: **remind only, never auto-dispatch.** The list belongs to the human; starting
-  work stays an explicit act. (Auto-dispatch was rejected in `DESIGN.md` for this
-  reason.)
+JSON round-trips byte for byte; the text formats are what let the list live in a repo and
+diff.
 
-### 4. Batch completion and tagging
+- Today: only `GET /export` / `POST /import` over JSON.
+- Effort: medium — a serializer plus a tolerant parser, both with round-trip tests.
+- Why third: cheap portability, and it is the only way to compare this list with another
+  tool's.
 
-Shift-click to select, then 完成 / 打标签 across the selection — the half of
-multi-select that did not land with batch assignment.
+### 4. The weekly agent report
 
-- Effort: small (one bulk route beside `/assign`, one button beside 一键分配).
+Per-todo completion records already carry a summary and the changed files. A cross-todo
+view — "what did the sessions finish this week, and what did they touch" — turns that into
+something reviewable.
 
-### 5. Import and export beyond JSON
+- Today: the data exists (`completion.artifacts`), the aggregate does not.
+- Effort: small-medium; the honest version is a date-bounded list filtered on
+  `completion.by === 'agent'`, with `review` state beside each row.
 
-Markdown / TaskPaper in and out, so the list can be migrated from (and to) any other
-tool and diffed in a repo.
+### 5. Image attachments
 
-- Effort: medium. JSON is done; the text formats are the remaining work.
+`kind: 'image'` beside `url` / `file`, so a screenshot can be attached instead of a path
+to one.
 
-### 6. What the agents produced
+- Today: `LINK_KINDS = ['url', 'file']` (`lib/links.js`); the link shape is already prepared.
+- Effort: medium — the store must not inline bytes, so this is a path with a preview and a
+  clear "the file is gone" state, which #3-adjacent work already models.
 
-Completions already record a summary and the changed files per todo. A cross-todo view —
-"what did the sessions finish this week, and what did they touch" — would turn that into
-something you can review, and would be the honest way to show that a hand-off did work.
+### 6. Source adapters for the ingest door
+
+`POST /ingest` exists and is fenced by a token; nothing pushes to it.
+
+- Today: the door, the inbox, the confidence threshold and the seven-day sweep are done.
+  There is no mail/notification reader anywhere in the repo.
+- Effort: large, and the mode of the work is different: every adapter is an external
+  dependency with its own failure modes. Do it when a real source exists, not before.
+
+### 7. Small, well-understood items
+
+- `before:` / `after:` date bounds in the search syntax (the parser already walks tokens).
+- 「重新挂载」 next to a dead attachment, plus the `annotateLinks()` unit test it owes.
+- A screen-reader pass over the panel and the group headers; the keyboard path is close.
+
+### Landed after this list was written
+
+Due reminders (0.5.2), batch completion and tagging (`/bulk`), archive instead of
+delete, cross-machine change notices, external ingest with an inbox — all four used to be
+items here. See `Landed since 0.1` above; the entries were removed rather than left to
+mislead.
 
 ## Later
 
 | Idea | Note |
 |---|---|
-| Image attachments | `kind: 'image'` next to `url` / `file`. The shape is already prepared for it, but `LINK_KINDS` is still `['url', 'file']` (`lib/links.js`). |
 | Official `storageDomain` backend | A second store backend behind the same interface; the file stays the default because it is the feature. Today there is one backend and it says so (`kind: 'json'`, `lib/store.js`). |
 | Virtualised list | Only needed past a few hundred rows; measure first. Nothing in `lib/client.js` virtualises today. |
 | Drag to reorder | Manual order is meaningful to some people; it also needs a stable `position` field and a decision about how it interacts with due-date grouping. |
 | Multi-list / projects | A `list` field with one default list; deferred because "global single list" is the current identity. |
-| Archive instead of delete | Keeps history without cluttering. `POST /remove` deletes for real (`lib/routes.js`); only the panel's short undo brings a record back. |
-| Cross-machine conflict notice | The file is portable (NAS, sync folder). Detect "changed underneath me" and offer a reload instead of a silent overwrite — `store.read` still trusts the file whenever it parses. |
-| Capture from outside the chat | Notifications, mail, announcements — the sources `dsh-todo-list` reads. Needs an ingest path and a policy for deduplication; `POST /capture` only asks a conversation to collect (`lib/routes.js`). |
-| Accessible-only sweep | Full keyboard path is close; a screen-reader pass over the panel and the group headers is still owed. |
 
 ## Explicitly not planned
 

package/lib/client.js

@@ -50,7 +50,7 @@ window.__ModuleLoader__.load({
      * different mechanisms (restart vs. hot reload), so "which one am I looking
      * at" needs an answer that the bundle itself carries.
      */
-    const UI_REV = 'ui45'
+    const UI_REV = 'ui47'
     /** Last language resolved for the shell; module-level so a fetch failure can be worded too. */
     let activeLang = 'zh'
 
@@ -288,6 +288,13 @@ window.__ModuleLoader__.load({
       'meta.session.noDirHint': '这个会话没有工作目录，agent 在里面做不了事；用「派发：开新会话」重派一次',
       'meta.dispatchFailed': '上次派发失败',
       'detail.description': '描述',
+      'meta.steps': '步骤 {done}/{total}',
+      'detail.steps': '步骤',
+      'steps.none': '还没有步骤。',
+      'field.steps': '第一步…（一行一步）',
+      'field.stepsHint': '一行一步；派发时会作为编号计划交给 Agent。',
+      'step.done': '标记这一步完成',
+      'step.undo': '取消这一步的完成标记',
       'detail.noDescription': '没有描述。',
       'detail.links': '相关文档与地址',
       'detail.completion': '完成记录',
@@ -561,6 +568,13 @@ window.__ModuleLoader__.load({
       'meta.session.noDirHint': 'This conversation has no working directory, so an agent cannot do anything in it; hand it off again with a new conversation.',
       'meta.dispatchFailed': 'last hand-off failed',
       'detail.description': 'Description',
+      'meta.steps': 'steps {done}/{total}',
+      'detail.steps': 'Steps',
+      'steps.none': 'No steps yet.',
+      'field.steps': 'First step… (one per line)',
+      'field.stepsHint': 'One per line; they ship to the agent as a numbered plan.',
+      'step.done': 'Mark this step done',
+      'step.undo': 'Clear this step',
       'detail.noDescription': 'No description.',
       'detail.links': 'Documents and links',
       'detail.noLinks': 'No attachments. Attach an absolute document path, or a URL.',
@@ -1281,6 +1295,16 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
 .gt-links { display: flex; flex-direction: column; gap: 4px; margin: 0; padding: 0; list-style: none; }
 .gt-link { display: flex; gap: 8px; align-items: center; padding: 4px 0; min-width: 0; }
 .gt-link-main { display: flex; align-items: center; gap: 6px; min-width: 0; flex: 1; }
+.gt-textarea-steps { min-height: 76px; }
+.gt-steps { display: flex; flex-direction: column; gap: 2px; margin: 0; padding: 0; list-style: none; }
+.gt-step { display: flex; align-items: flex-start; gap: 8px; padding: 3px 0; }
+.gt-step-check { flex: 0 0 auto; width: 18px; height: 18px; margin-top: 2px; padding: 0; cursor: pointer;
+  border-radius: 5px; border: 1.4px solid var(--dsw-alias-border-l2); background: transparent;
+  color: transparent; display: inline-flex; align-items: center; justify-content: center; }
+.gt-step[data-done="1"] .gt-step-check { border-color: var(--dsw-alias-state-success-primary);
+  background: var(--dsw-alias-state-success-primary); color: var(--dsw-alias-bg-base); }
+.gt-step-text { font-size: 13px; line-height: 20px; word-break: break-word; }
+.gt-step[data-done="1"] .gt-step-text { color: var(--dsw-alias-label-secondary); text-decoration: line-through; }
 .gt-note-item { display: flex; flex-direction: column; gap: 4px; padding: 8px 0; }
 .gt-note-item + .gt-note-item { border-top: 1px solid var(--dsw-alias-border-l1); }
 .gt-note-meta { display: flex; align-items: center; gap: 6px; font-size: 12px; color: var(--dsw-alias-label-secondary);
@@ -1671,6 +1695,12 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
         )
       }
       meta.push(h('span', { key: 'added', title: new Date(todo.createdAt).toLocaleString() }, ageText(lang, todo.createdAt, now)))
+      // Progress on the plan, when there is one: the row shows where it stands without
+      // opening the detail.
+      if (Array.isArray(todo.steps) && todo.steps.length > 0) {
+        const done = todo.steps.filter((step) => step.done === true).length
+        meta.push(h('span', { key: 'steps' }, t('meta.steps', { done, total: todo.steps.length })))
+      }
       if (todo.tags.length > 0) {
         const shown = todo.tags.slice(0, 4)
         meta.push(
@@ -2155,6 +2185,40 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
                           ),
                         ),
                   ),
+              h(
+                'div',
+                { className: 'gt-section' },
+                h('div', { className: 'gt-section-title' }, t('detail.steps')),
+                (todo.steps ?? []).length === 0
+                  ? h('div', { className: 'gt-muted' }, t('steps.none'))
+                  : h(
+                      'ul',
+                      { className: 'gt-steps' },
+                      todo.steps.map((step, index) =>
+                        h(
+                          'li',
+                          { key: `${index}:${step.text}`, className: 'gt-step', 'data-done': step.done === true ? '1' : '0' },
+                          h(
+                            'button',
+                            {
+                              type: 'button',
+                              className: 'gt-step-check',
+                              'aria-pressed': step.done === true,
+                              title: step.done === true ? t('step.undo') : t('step.done'),
+                              'aria-label': step.done === true ? t('step.undo') : t('step.done'),
+                              disabled: busy,
+                              onClick: () =>
+                                onAction('steps', todo, {
+                                  steps: todo.steps.map((item, i) => (i === index ? { text: item.text, done: item.done !== true } : { text: item.text, done: item.done === true })),
+                                }),
+                            },
+                            step.done === true ? h(Icon, { name: 'check', size: 11 }) : null,
+                          ),
+                          h('span', { className: 'gt-step-text' }, step.text),
+                        ),
+                      ),
+                    ),
+              ),
               h(
                 'div',
                 { className: 'gt-section' },
@@ -2349,7 +2413,7 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
       const [more, setMore] = useState(false)
       const [collapsed, setCollapsed] = useState({})
       const [undo, setUndo] = useState(null)
-      const [draft, setDraft] = useState({ title: '', description: '', links: '', tags: '', priority: 'normal', due: '' })
+      const [draft, setDraft] = useState({ title: '', description: '', links: '', steps: '', tags: '', priority: 'normal', due: '' })
       // Conversations come from the shell's own sessions service, declared in this
       // plugin's `inject` list the way the shipped panels do it
       // (`ui-subagent` / `agent-team`: ["sessions", "uiWorkspace", "slots", "locale"]).
@@ -2750,6 +2814,11 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
           .split(',')
           .map((part) => part.trim())
           .filter((part) => part !== '')
+        // One step per line: the shape a person already writes a plan in.
+        const steps = (draft.steps ?? '')
+          .split('\n')
+          .map((line) => line.trim())
+          .filter((line) => line !== '')
         await run('__new__', () =>
           call('create', {
             method: 'POST',
@@ -2757,13 +2826,14 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
               title,
               ...(draft.description.trim() === '' ? {} : { description: draft.description.trim() }),
               ...(links.length === 0 ? {} : { links }),
+              ...(steps.length === 0 ? {} : { steps }),
               ...(tags.length === 0 ? {} : { tags }),
               ...(draft.priority === 'normal' ? {} : { priority: draft.priority }),
               ...(draft.due === '' ? {} : { dueAt: new Date(draft.due).toISOString() }),
             },
           }),
         )
-        setDraft({ title: '', description: '', links: '', tags: '', priority: 'normal', due: '' })
+        setDraft({ title: '', description: '', links: '', steps: '', tags: '', priority: 'normal', due: '' })
         setMore(false)
       }
 
@@ -3197,6 +3267,7 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
         if (kind === 'archive') return run(todo.id, () => call('status', { method: 'POST', body: { id: todo.id, status: 'archived' } }))
         if (kind === 'unarchive') return run(todo.id, () => call('status', { method: 'POST', body: { id: todo.id, status: 'open' } }))
         if (kind === 'save') return run(todo.id, () => call('update', { method: 'POST', body: { id: todo.id, ...payload } }))
+        if (kind === 'steps') return run(todo.id, () => call('update', { method: 'POST', body: { id: todo.id, steps: payload.steps } }))
         if (kind === 'note') return run(todo.id, () => call('note', { method: 'POST', body: { id: todo.id, ...payload } }))
         if (kind === 'link') return run(todo.id, () => call('link', { method: 'POST', body: { id: todo.id, ...payload } }))
         if (kind === 'unlink') return run(todo.id, () => call('link', { method: 'POST', body: { id: todo.id, remove: [payload.index] } }))
@@ -3320,6 +3391,39 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
         }
       }
 
+      // Reviewing is a per-record decision, so it cannot ride on /bulk: answering is not a
+      // status change, and a rejected claim has to clean up its completion record.
+      const runBulkReview = async () => {
+        const ids = Object.keys(selected)
+        if (ids.length === 0) return
+        try {
+          const results = await Promise.all(
+            ids.map((id) =>
+              call('review', { method: 'POST', body: { id, decision: 'confirm' } }).then(
+                () => true,
+                () => false,
+              ),
+            ),
+          )
+          const done = results.filter(Boolean).length
+          setNotice({
+            text:
+              done === ids.length
+                ? t('notice.bulk', { n: done })
+                : t('notice.bulkPartial', { n: done, m: ids.length - done }),
+            sessionId: '',
+          })
+          setTimeout(() => setNotice(null), 6000)
+          setSelected({})
+          setError(null)
+          void reload()
+          void refreshHealth()
+        } catch (failure) {
+          reportFailure('bulk-review', { message: failure?.message })
+          setError(failure)
+        }
+      }
+
       const counts = state.counts ?? { total: 0, open: 0, doing: 0, done: 0, cancelled: 0, archived: 0, overdue: 0, inbox: 0 }
       const remindersDue = Array.isArray(state.health?.reminders?.due) ? state.health.reminders.due : []
       const dueKey = remindersDue.map((item) => `${item.id}:${item.dueAt}`).join('|')
@@ -3737,6 +3841,19 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
                     }),
                     h('span', { className: 'gt-hint' }, t('field.linksHint')),
                   ),
+                  h(
+                    'div',
+                    { className: 'gt-field' },
+                    h('label', { className: 'gt-field-label', htmlFor: 'gt-new-steps' }, t('detail.steps')),
+                    h('textarea', {
+                      id: 'gt-new-steps',
+                      className: 'gt-textarea gt-textarea-steps',
+                      placeholder: t('field.steps'),
+                      value: draft.steps,
+                      onChange: (event) => setDraft({ ...draft, steps: event.target.value }),
+                    }),
+                    h('span', { className: 'gt-hint' }, t('field.stepsHint')),
+                  ),
                   h(
                     'div',
                     { className: 'gt-field-row' },
@@ -4062,11 +4179,25 @@ button.gt-chip[data-on="1"] { color: var(--dsw-alias-label-primary); border-colo
                   t('select.clearAll'),
                 ),
                 h('span', { className: 'gt-spacer' }),
+                // In the review view the batch action is confirming, not assigning: every
+                // record on screen is finished and waiting for a word.
+                filter === 'review'
+                  ? h(
+                      'button',
+                      {
+                        type: 'button',
+                        className: 'gt-btn gt-btn-primary',
+                        disabled: Object.keys(selected).length === 0,
+                        onClick: () => void runBulkReview(),
+                      },
+                      t('review.confirm'),
+                    )
+                  : null,
                 h(
                   'button',
                   {
                     type: 'button',
-                    className: 'gt-btn gt-btn-primary',
+                    className: filter === 'review' ? 'gt-btn gt-btn-quiet' : 'gt-btn gt-btn-primary',
                     disabled: assignBusy || Object.keys(selected).length === 0,
                     onClick: () => void runAssign(Object.keys(selected)),
                   },

package/lib/index.js

@@ -36,7 +36,7 @@ import { createStore, resolveStorePath } from './store.js'
 import { createTools } from './tools.js'
 
 /** Must equal `package.json`'s version; `npm run check` enforces that. */
-export const VERSION = '0.7.1'
+export const VERSION = '0.8.0'
 
 /** Plugin id. Also the Loader row id in `cordis.patch.yml`. */
 export const name = 'dsh-global-todo'
@@ -74,6 +74,7 @@ const GUIDANCE = [
   '- 用户说「记一下 / 别忘了 / 回头办」。',
   '**不要记**：你这一步就能做完的、本会话内的执行计划、纯闲聊。宁可少记。',
   '记的时候：标题一句话说清要做什么；把相关文档**绝对路径**或网址挂进 `links`（接手时会作为上下文一起交出去）；需要精确时间的写 `dueAt`。',
+  '**大活拆步骤**：一件需要多轮才能做完的事，用 `steps` 记下 3–6 步（`global_todo_add` 的 `steps` 参数）——派发时这些步骤会作为编号计划原样交给接手的 Agent，比一段散文有用得多；做完一步就用 `global_todo_update` 把该步的 `done` 置为 true。',
   '记完用一句话说明记了什么（别复述整条描述）。做完用 `global_todo_done` 留痕，**不要删**。',
   '**一轮收尾时顺手划掉**：如果清单里某条就是你刚做完的事，直接 `global_todo_done` 结束它，别留着占地方（插件也会在你安静下来后自动划掉，但你先划更准）。',
   '做不到 / 卡住了：用 `global_todo_note` 追加一条进展，说明卡在哪、需要用户做什么——**不要**改写待办的 description（那是用户自己的文字）。',

package/lib/model.js

@@ -52,6 +52,10 @@ export const LIMITS = Object.freeze({
   activity: 50,
   note: 2000,
   notes: 50,
+  // A todo is a unit of work, not a project plan: a list longer than this is a sign the
+  // item should be split, and a cap keeps the dispatch prompt from becoming a document.
+  steps: 20,
+  step: 200,
 })
 
 /**
@@ -201,6 +205,9 @@ export function createTodo(input, options = {}) {
     dueAt: normalizeDue(raw.dueAt ?? raw.due),
     tags: normalizeTags(raw.tags),
     links,
+    // An optional plan inside the todo: the steps a person or an agent broke it into.
+    // Shipped to the agent as a numbered list, so hand-off stops being one paragraph.
+    steps: normalizeSteps(raw.steps),
     createdAt: now,
     updatedAt: now,
     createdBy: by,
@@ -305,6 +312,13 @@ export function normalizeStored(raw, options = {}) {
       }
     })(),
     links,
+    steps: (() => {
+      try {
+        return normalizeSteps(raw.steps)
+      } catch {
+        return []
+      }
+    })(),
     createdAt,
     updatedAt: Number.isFinite(raw.updatedAt) ? Number(raw.updatedAt) : createdAt,
     createdBy: normalizeActor(raw.createdBy),
@@ -563,11 +577,23 @@ export function applyPatch(todo, patch, options = {}) {
       changed.push('tags')
     }
   }
+  if (patch.steps !== undefined) {
+    const steps = normalizeSteps(patch.steps)
+    const same =
+      steps.length === todo.steps.length && steps.every((step, index) => step.text === todo.steps[index].text && step.done === todo.steps[index].done)
+    if (!same) {
+      todo.steps = steps
+      changed.push('steps')
+    }
+  }
   if (patch.status !== undefined) {
     const status = normalizeEnum(patch.status, STATUSES, 'invalid-status', '状态', todo.status)
     if (status !== todo.status) {
       todo.status = status
       todo.doneAt = status === 'done' ? now : null
+      // Reaching done through a patch carries the same review rule as the dedicated
+      // status path: an agent's "done" is a claim, a person's is a decision.
+      todo.review = status === 'done' && by === 'agent' ? { pending: true, at: now, by } : null
       changed.push('status')
     }
   }
@@ -626,6 +652,40 @@ export function setStatus(todo, status, options = {}) {
   return true
 }
 
+/**
+ * An optional plan inside a todo.
+ *
+ * A step is text plus a tick, and the order is the plan. Strings are accepted for the
+ * common case (create, or an agent rewriting the plan) so a caller never has to spell out
+ * `{ done: false }` for every line.
+ *
+ * @param {unknown} value
+ * @returns {Array<{ text: string, done: boolean }>}
+ */
+export function normalizeSteps(value) {
+  if (value === null || value === undefined) return []
+  if (!Array.isArray(value)) throw new TodoError('invalid-steps', '步骤必须是数组')
+  if (value.length > LIMITS.steps) {
+    throw new TodoError('invalid-steps', `步骤最多 ${LIMITS.steps} 条，收到 ${value.length} 条`)
+  }
+  const out = []
+  for (const item of value) {
+    if (typeof item === 'string') {
+      const text = item.trim().slice(0, LIMITS.step)
+      // A blank line in a textarea is a typo, not a step.
+      if (text !== '') out.push({ text, done: false })
+      continue
+    }
+    if (item === null || typeof item !== 'object' || Array.isArray(item)) {
+      throw new TodoError('invalid-steps', '步骤必须是字符串或 { text, done }')
+    }
+    const text = typeof item.text === 'string' ? item.text.trim().slice(0, LIMITS.step) : ''
+    if (text === '') continue
+    out.push({ text, done: item.done === true })
+  }
+  return out
+}
+
 /**
  * @param {object} todo
  * @param {unknown} link

package/lib/service.js

@@ -555,6 +555,15 @@ export function createService(options) {
     if (todo.description !== '') {
       lines.push('', '描述：', todo.description)
     }
+    // The plan, if there is one: a numbered list is what makes a hand-off concrete, and
+    // the ticks say which parts are already behind us.
+    const steps = Array.isArray(todo.steps) ? todo.steps : []
+    if (steps.length > 0) {
+      lines.push('', `步骤（共 ${steps.length} 步）：`)
+      steps.forEach((step, index) => {
+        lines.push(`${index + 1}. ${step.done === true ? '[已完成] ' : ''}${step.text}`)
+      })
+    }
     if (todo.links.length > 0) {
       lines.push('', '相关文档与地址：')
       for (const link of todo.links) {

package/lib/tools.js

@@ -20,6 +20,34 @@ import { LIMITS, PRIORITIES, PRIORITY_LABELS, STATUSES } from './model.js'
 
 const text = (value) => [{ type: 'text', text: value }]
 
+const STEPS_INPUT = {
+  type: 'array',
+  description:
+    '要做成的几步（可选，最多 ' + LIMITS.steps + ' 条）。每步一句话；已完成的写 { text, done: true }。'
+    + '派发时会把它们作为编号计划交给 Agent。',
+  items: {
+    oneOf: [
+      { type: 'string' },
+      {
+        type: 'object',
+        properties: { text: { type: 'string' }, done: { type: 'boolean' } },
+        required: ['text'],
+        additionalProperties: false,
+      },
+    ],
+  },
+}
+
+const STEPS_SHAPE = {
+  type: 'array',
+  items: {
+    type: 'object',
+    properties: { text: { type: 'string' }, done: { type: 'boolean' } },
+    required: ['text'],
+    additionalProperties: false,
+  },
+}
+
 const LINKS_INPUT = {
   type: 'array',
   description:
@@ -92,6 +120,7 @@ const TODO_SHAPE = {  type: 'object',
     priority: { type: 'string', enum: [...PRIORITIES] },
     dueAt: { oneOf: [{ type: 'string' }, { type: 'null' }] },
     tags: { type: 'array', items: { type: 'string' } },
+    steps: STEPS_SHAPE,
     links: {
       type: 'array',
       items: {
@@ -152,6 +181,7 @@ export function presentTodo(todo, now = Date.now()) {
     priority: todo.priority,
     dueAt: todo.dueAt,
     tags: [...todo.tags],
+    steps: (todo.steps ?? []).map((step) => ({ text: step.text, done: step.done === true })),
     links: todo.links.map((link) => ({ ...link })),
     createdAt: todo.createdAt,
     createdAtIso: new Date(todo.createdAt).toISOString(),
@@ -301,6 +331,7 @@ export function createTools(service, options = {}) {
           title: { type: 'string', description: `一句话说清要做什么（最多 ${LIMITS.title} 字）` },
           description: { type: 'string', description: '补充说明、验收标准、已知的坑' },
           links: LINKS_INPUT,
+          steps: STEPS_INPUT,
           tags: { type: 'array', items: { type: 'string' }, description: `标签，最多 ${LIMITS.tags} 个` },
           priority: { type: 'string', enum: [...PRIORITIES], description: 'P0 紧急 / P1 高 / P2 常规（缺省）/ P3 低' },
           dueAt: { type: 'string', description: 'ISO-8601 截止时间，例如 2026-10-20T10:00 或 2026-10-20' },
@@ -528,7 +559,7 @@ export function createTools(service, options = {}) {
     {
       name: 'global_todo_update',
       description:
-        '改一条全局待办。只传要改的字段；`dueAt: ""` 清空截止时间，`tags: []` 清空标签，`links` 是整体替换（要单独加附件请用 global_todo_link），`status` 可以设为 archived（归档，不删除）。',
+        '改一条全局待办。只传要改的字段；`dueAt: ""` 清空截止时间，`tags: []` 清空标签，`links` / `steps` 是整体替换（要单独加附件请用 global_todo_link），`status` 可以设为 archived（归档，不删除）。',
       parameters: {
         type: 'object',
         properties: {
@@ -542,6 +573,7 @@ export function createTools(service, options = {}) {
           dueAt: { oneOf: [{ type: 'string' }, { type: 'null' }], description: '空串或 null 表示清空' },
           tags: { type: 'array', items: { type: 'string' } },
           links: LINKS_INPUT,
+          steps: STEPS_INPUT,
         },
         required: ['id'],
         additionalProperties: false,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-global-todo",
-  "version": "0.7.1",
+  "version": "0.8.0",
   "icon": "./docs/icon.svg",
   "description": "Global, cross-session todos for DeepSeek Harness: one list owned by the human and the agent together, with creation time, attached documents and links, and one-click hand-off to an agent session. 全局待办：跨会话一份清单，记录加入时间，可挂文档与地址，可一键交给 Agent 继续干。",
   "type": "module",