Merge remote-tracking branch 'origin/master' into codex/status-bar-token-metrics

# Conflicts:
#	packages/client/runtime/README.i18n.yaml
#	packages/client/runtime/README.md
#	packages/client/runtime/README.zh.md
#	packages/client/ui-conversation/README.i18n.yaml
#	packages/client/ui-conversation/README.md
#	packages/client/ui-conversation/README.zh.md
#	packages/host/apiproxy/README.i18n.yaml
#	packages/host/apiproxy/README.md
#	packages/host/apiproxy/README.zh.md

.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml

@@ -1,6 +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
-2026-06-29-todo-write-tool.md: 760373d64f462e3717a174d5793e6d47ab76b0b4
-2026-06-29-todo-write-tool.zh.md: fd29e6049e6a729c2c7e78860ad7c065422da60e
+#   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: 03dae6328e5c7f4379694ab01db3434b4469826c

.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md

@@ -18,7 +18,7 @@ The model sends the entire list every call; the new list replaces the old (last-
 
 ### State on the session log, not a service
 
-The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and resume reconstruction for free: a reopened session re-derives the current list from the latest `todo/write`, with no separate persistence backend, in-memory service to rehydrate, or extra wiring. An in-memory `ctx.todos` service would have to reinvent all of that. (Full-log consumers get this reconstruction outright; the web client's paged window gets it from the tail history page's host-computed projection — see the [web todo display note](2026-07-23-web-todo-display.md).)
+The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and resume reconstruction for free: a reopened session re-derives the standing plan from the latest `todo/write` that is not followed by a later `turn/start` ([plan strip lifetime](2026-07-28-todo-plan-clears-on-next-turn.md)), with no separate persistence backend, in-memory service to rehydrate, or extra wiring. An in-memory `ctx.todos` service would have to reinvent all of that. (Full-log consumers get this reconstruction outright; the web client's paged window gets it from the tail history page's host-computed projection — see the [web todo display note](2026-07-23-web-todo-display.md).)
 
 ### NOT a surface event
 

.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md

@@ -18,7 +18,7 @@ harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结
 
 ### 状态在会话日志上，而非服务
 
-列表作为 `todo/write` 事件追加到日志，携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM（大语言模型）历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和恢复重建：重新打开的会话从最新的 `todo/write` 重新推导当前列表，无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。（全量 log 消费者直接获得这份重建；web 客户端的分页窗口则从尾页 history 携带的 host 计算投影获得——见 [web todo 展示 Note](2026-07-23-web-todo-display.md)。）
+列表作为 `todo/write` 事件追加到日志，携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM（大语言模型）历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和恢复重建：重新打开的会话从「其后没有更晚 `turn/start`」的最近一次 `todo/write` 重新推导站立计划（[计划条生命周期](2026-07-28-todo-plan-clears-on-next-turn.md)），无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。（全量 log 消费者直接获得这份重建；web 客户端的分页窗口则从尾页 history 携带的 host 计算投影获得——见 [web todo 展示 Note](2026-07-23-web-todo-display.md)。）
 
 ### 不是 surface 事件
 

.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: 5fe08cc40c1d23ff3a9b8c6d766fea6d3694c30d
-2026-07-23-web-todo-display.zh.md: c121ffc27e3d0a93707c2c22b2f180023ebae5be
+2026-07-23-web-todo-display.md: 7223ff9adbf1fa6dca39c9eb4949b6d3861bdd6d
+2026-07-23-web-todo-display.zh.md: ac773a3c587183aa9a152caff2812686bc79f3c7

.agents/notes/implemented/feature/2026-07-23-web-todo-display.md

@@ -14,7 +14,7 @@ Consume `todo/write` as a Session side effect, not a surface node, and render it
 
 ### Side-effect channel, converging with window replay
 
-`applyEventSideEffects` gains a `todo/write` case (whole list, last write wins). Unlike partial/openCalls, `rebuildDerivedFromWindow` deliberately does NOT reset it: the value is session-level — taken from the tail history page's full-log projection — and an arbitrary window may not contain the latest write, so an older-page prepend keeps it and only an in-window or live write overwrites it. Every `installWindow` caller is a tail request (`doOpen`, its gap re-pull, `repairGap`; `loadOlder` prepends without it), which the host answers with the projection or omits it only when the full log holds no `todo/write` — so an absent field is the authoritative empty list and is assigned as such. That distinction matters on rollback: a live write whose host crashed before persisting leaves the log empty, and preserving the prior value instead would strand the rolled-back plan on screen indefinitely. `ConversationSnapshot.todos` is the read surface. This follows the event's own contract ("log-only UI state; never derived history"): surfacing each write as a conversation node would render superseded lists as if they were still standing.
+`applyEventSideEffects` gains a `todo/write` case (whole list, last write wins) and clears on `turn/start` ([turn-scoped plan lifetime](2026-07-28-todo-plan-clears-on-next-turn.md)). `rebuildDerivedFromWindow` sweeps the window from an empty plan and restores the tail-page seed only when the window never determined the plan (no `todo/write` and no `turn/start`); otherwise the in-window write/`turn/start` fold wins. Every `installWindow` caller is a tail request (`doOpen`, its gap re-pull, `repairGap`; `loadOlder` prepends without reseeding), which the host answers with the projection or omits it when no plan stands — so an absent field is the authoritative empty list and is assigned as such. That distinction matters on rollback: a live write whose host crashed before persisting leaves the log empty, and preserving the prior value instead would strand the rolled-back plan on screen indefinitely. `ConversationSnapshot.todos` is the read surface. This follows the event's own contract ("log-only UI state; never derived history"): surfacing each write as a conversation node would render superseded lists as if they were still standing.
 
 ### TodoPanel: the durable list as a persistent strip
 
@@ -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 is untouched (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 latest `todo/write`, computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan even when the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, 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 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.

.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md

@@ -14,7 +14,7 @@ Status: implemented
 
 ### 副作用通道，与窗口回放收敛
 
-`applyEventSideEffects` 新增一个 `todo/write` 分支（整份列表，后写覆盖先写）。与 partial/openCalls 不同，`rebuildDerivedFromWindow` 刻意不重置它：该值是会话级的——取自尾页 history 携带的全量 log 投影——而任意窗口未必包含最近一次写入，因此往前翻页保留它，只有窗口内或实时的写入才会覆盖。`installWindow` 的每个调用方都是尾页请求（`doOpen`、其补洞重拉、`repairGap`；`loadOlder` 只往前拼接、不走它），而 host 对尾页请求要么带上投影、要么仅在全量 log 没有任何 `todo/write` 时省略——因此字段缺失就是权威的空列表，直接照此赋值。这个区分在回滚场景上要紧：实时写入若在 host 持久化前崩溃，log 里就是空的，此时保留旧值会让已回滚的计划永远留在屏幕上。`ConversationSnapshot.todos` 是读取面。这遵循事件自身的契约（「仅日志 UI 状态，绝非派生历史」）：把每次写入作为对话节点呈现，会让已被取代的列表看起来仍然有效。
+`applyEventSideEffects` 新增一个 `todo/write` 分支（整份列表，后写覆盖先写），并在 `turn/start` 清空（[按 turn 界定的计划生命周期](2026-07-28-todo-plan-clears-on-next-turn.md)）。`rebuildDerivedFromWindow` 从空计划扫过窗口，仅当窗口从未判定计划（无 `todo/write` 且无 `turn/start`）时恢复尾页种子；否则以窗口内写入／`turn/start` 折叠为准。`installWindow` 的每个调用方都是尾页请求（`doOpen`、其补洞重拉、`repairGap`；`loadOlder` 只往前拼接、不再播种），而 host 对尾页请求要么带上投影、要么在无站立计划时省略——因此字段缺失就是权威的空列表，直接照此赋值。这个区分在回滚场景上要紧：实时写入若在 host 持久化前崩溃，log 里就是空的，此时保留旧值会让已回滚的计划永远留在屏幕上。`ConversationSnapshot.todos` 是读取面。这遵循事件自身的契约（「仅日志 UI 状态，绝非派生历史」）：把每次写入作为对话节点呈现，会让已被取代的列表看起来仍然有效。
 
 ### TodoPanel：长驻列表作为一条常驻横条
 
@@ -33,4 +33,4 @@ Status: implemented
 
 ## Consequences
 
-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免费保持 todos 一致；fx-alpha 第 65 轮的 fixture（测试前置数据）加 assembled keyless snapshot（`apps/web/tests/todo-display.snapshot.ts`）在构建产物客户端全图上钉住整条链（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 面板未受改动（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。冷加载重建正是靠这个字段由 host 兜底：history 尾页附带 `todos`——全量 log 上最新一次 `todo/write` 的投影，独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时即使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，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免费保持 todos 一致；fx-alpha 第 65 轮的 fixture（测试前置数据）加 assembled keyless snapshot（`apps/web/tests/todo-display.snapshot.ts`）在构建产物客户端全图上钉住整条链（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 turn 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。冷加载重建正是靠这个字段由 host 兜底：history 尾页附带 `todos`——全量 log 上的站立计划（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站立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。

.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.i18n.yaml

@@ -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/2026-07-28-todo-plan-clears-on-next-turn.md
+2026-07-28-todo-plan-clears-on-next-turn.md: 8a2808f5023a0800fbbeb65c5e28b3495e051dbc
+2026-07-28-todo-plan-clears-on-next-turn.zh.md: 6ea6b2b4fafe4b2f695ad2d54561f164747e5694

.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.md

@@ -0,0 +1,31 @@
+# Agent Note: Todo plan strip clears on the next turn
+
+Status: implemented
+
+English | [中文](2026-07-28-todo-plan-clears-on-next-turn.zh.md)
+
+## Problem
+
+`todo_write` stores whole-list snapshots on the session log, and interactive hosts render the latest list as a plan strip (web TodoPanel via the `todos` projection, TUI Plan panel). After a turn finished, that strip stayed on screen into the next user turn — a completed or abandoned checklist from the previous task. Readers treat the strip as "what this turn is doing," so a stale list across the turn boundary is the wrong product lifetime. The [web todo display](2026-07-23-web-todo-display.md) and [`todo_write` tool](2026-06-29-todo-write-tool.md) notes still own event-sourcing and the two render surfaces; they described the standing plan as lasting for the whole session until the next write.
+
+## Decision
+
+The standing plan is the latest `todo/write` that is not followed by a later `turn/start`. `turn/end` keeps the list visible so the finished checklist remains while the user reads the answer; the next `turn/start` clears it until the model writes again.
+
+### Host projection (web)
+
+`dsh-tool-todo`'s `todos` projection unit folds the rule: `apply` takes the whole list from each `todo/write` and returns `null` on each `turn/start` (`stateVersion` 2). Carriers (`dsh-host-apiproxy`) serve that value on the history tail `projections` block and push `session/projection` frames; the web dock reads it through `useProjection('todos')`. The keyless fixture mirrors the same fold for assembled snapshots.
+
+### TUI live path
+
+The TUI `renderEvent` switch still clears its local plan panel on `turn/start` and replaces it on `todo/write` (TUI is not yet a projection carrier). The rebuild path resets the panel before replaying the log so cold resume converges on the same rule.
+
+## Alternatives considered
+
+- **Clear on `turn/end`** — hides the checklist while the user is still reading the just-finished answer; the strip's job at that moment is the completed plan, not an empty dock.
+- **Clear only when every item is `completed`** — leaves abandoned or partial plans across turns; the strip would still show another task's work.
+- **Append an empty `todo/write` on turn start** — mutates the log for a UI lifetime rule and invents a write the model never authored.
+
+## Consequences
+
+The host projection and the TUI panel share one lifetime rule; reopening a session restores a plan only when no later turn has started. Partial supersession of the session-long standing-plan wording in [web todo display](2026-07-23-web-todo-display.md) and [`todo_write` tool](2026-06-29-todo-write-tool.md): event-sourcing, last-write-wins replacement, and the two render surfaces stay there; this note owns turn-boundary clearance. Coverage: tool-todo projection specs for turn/start clear + turn/end keep, fixture push-frame clearance for the assembled web snapshot, plus the TUI snapshot that starts the next turn and pins the strip gone.

.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.zh.md

@@ -0,0 +1,31 @@
+# Agent Note: 下一轮开始时清空 todo 计划条
+
+Status: implemented
+
+[English](2026-07-28-todo-plan-clears-on-next-turn.md) | 中文
+
+## 问题
+
+`todo_write` 在会话日志中存储整表快照，交互式宿主把最新列表渲染为计划条（web TodoPanel 经 `todos` 投影，TUI Plan 面板）。一轮结束后，该条仍留在下一用户轮次的屏幕上——上一任务已完成或已放弃的清单。读者把计划条理解为「本轮正在做什么」，因此跨轮次的陈旧列表是错误的产品生命周期。[web todo 展示](2026-07-23-web-todo-display.md)与 [`todo_write` 工具](2026-06-29-todo-write-tool.md)笔记仍拥有事件溯源与两个渲染面；它们把站立计划描述为持续整段会话直至下一次写入。
+
+## 决策
+
+站立计划是其后没有更晚 `turn/start` 的最近一次 `todo/write`。`turn/end` 保留列表可见，以便用户阅读回答时仍能看到刚完成的清单；下一次 `turn/start` 将其清空，直至模型再次写入。
+
+### Host 投影（web）
+
+`dsh-tool-todo` 的 `todos` 投影单元折叠该规则：`apply` 从每个 `todo/write` 取整表，并在每个 `turn/start` 返回 `null`（`stateVersion` 2）。载体（`dsh-host-apiproxy`）在历史尾页的 `projections` 块与 `session/projection` 推送帧上供给该值；web dock 经 `useProjection('todos')` 读取。无密钥 fixture（测试前置数据）镜像同一折叠，供组装后的 snapshot 使用。
+
+### TUI 实时路径
+
+TUI 的 `renderEvent` 分支仍在 `turn/start` 清空本地计划面板、在 `todo/write` 替换之（TUI 尚非投影载体）。重建路径在回放日志前重置面板，使冷恢复收敛到同一规则。
+
+## 考虑过的替代方案
+
+- **在 `turn/end` 清空**——用户仍在阅读刚完成的回答时就隐藏清单；此时计划条的职责是已完成计划，而非空 dock。
+- **仅在全部项为 `completed` 时清空**——会让放弃或部分完成的计划跨轮残留；计划条仍会显示另一任务的工作。
+- **在 turn start 追加空的 `todo/write`**——为 UI 生命周期规则改写日志，并捏造模型从未写出的写入。
+
+## 后果
+
+Host 投影与 TUI 面板共用同一生命周期规则；重新打开会话仅在其后没有更晚轮次开始时恢复计划。部分取代 [web todo 展示](2026-07-23-web-todo-display.md)与 [`todo_write` 工具](2026-06-29-todo-write-tool.md)中「会话级站立计划」的表述：事件溯源、last-write-wins 替换与两个渲染面仍归那些笔记；本笔记拥有轮次边界清空。覆盖：tool-todo 投影对 turn/start 清空与 turn/end 保留的规格测试、供组装 web snapshot 的 fixture 推送帧清空，以及启动下一轮并钉住计划条消失的 TUI snapshot。

apps/web/tests/todo-display.snapshot.ts

@@ -4,8 +4,9 @@
 // Opens the fixture history session and pins the todo_write turn's two
 // surfaces: the dedicated TodoRow in the chat flow (keyed toolview, summary
 // derived from the call args) and the TodoPanel plan strip riding the
-// 'conversation.input.dock' slot (fed by ConversationSnapshot.todos, seeded
-// by the tail history page), including the collapse interaction.
+// 'conversation.input.dock' slot (fed by the host `todos` projection via
+// useProjection, seeded by the tail history page), including the collapse
+// interaction and the next-turn clearance of the standing plan.
 import { readFileSync } from 'node:fs'
 import { join } from 'node:path'
 import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react'
@@ -189,3 +190,31 @@ it('collapses the plan strip to the count summary and restores it', async () =>
   fireEvent.click(header)
   expect(panel.querySelectorAll('li')).toHaveLength(3)
 })
+
+it('hides the plan strip when the next turn starts', async () => {
+  boot()
+  await openFixtureSession()
+  expect(document.querySelector('[data-testid="todo-panel"]')).not.toBeNull()
+
+  const composer = await screen.findByPlaceholderText('Message the agent', {}, { timeout: 10_000 })
+  fireEvent.change(composer, { target: { value: '下一轮清空计划' } })
+  fireEvent.keyDown(composer, { key: 'Enter' })
+
+  await screen.findByText('下一轮清空计划', { exact: true }, { timeout: 10_000 })
+  await waitFor(() => {
+    expect(document.querySelector('[data-testid="todo-panel"]')).toBeNull()
+  }, { timeout: 10_000 })
+
+  expect({
+    promptVisible: screen.getByText('下一轮清空计划', { exact: true }).textContent,
+    panelGone: document.querySelector('[data-testid="todo-panel"]') === null,
+    // Historical todo_write row stays in the flow; only the dock strip clears.
+    rowStillPresent: document.querySelector('[data-sample="todo-row"]') !== null,
+  }).toMatchInlineSnapshot(`
+    {
+      "panelGone": true,
+      "promptVisible": "下一轮清空计划",
+      "rowStillPresent": true,
+    }
+  `)
+})

packages/client/connection/src/client/fixture.ts

@@ -309,20 +309,31 @@ function projectionValuesOf(log: readonly SessionEvent[]): Record<string, unknow
   if (titleEvent !== undefined) {
     values['title'] = (titleEvent as unknown as { data: { title: string } }).data.title
   }
-  const todos = backscanTodos(log)
-  if (todos !== undefined) values['todos'] = todos
+  // Always present (tool-todo unit composed): null when no plan stands.
+  values['todos'] = backscanTodos(log) ?? null
   return values
 }
 
 /** Host push-frame parallel: emit one session/projection frame per key the given event advanced. */
 function projectionFramesOf(id: SessionId, log: readonly SessionEvent[], event: SessionEvent): Extract<MuxFrame, { type: 'session/projection' }>[] {
   const type = (event as { type: string }).type
-  const key = type === 'session/title' ? 'title' : type === 'todo/write' ? 'todos' : undefined
-  if (key === undefined) return []
-  const values = projectionValuesOf(log)
-  /* v8 ignore next -- the advancing event is in the log, so its key always has a value. */
-  if (!Object.hasOwn(values, key)) return []
-  return [{ type: 'session/projection', sessionId: id, key, value: values[key], seq: event.seq }]
+  if (type === 'session/title') {
+    const values = projectionValuesOf(log)
+    /* v8 ignore next -- the advancing title event is in the log, so the key is present. */
+    if (!Object.hasOwn(values, 'title')) return []
+    return [{ type: 'session/projection', sessionId: id, key: 'title', value: values['title'], seq: event.seq }]
+  }
+  // Standing-plan fold: writes replace the list; turn/start clears it (null).
+  if (type === 'todo/write' || type === 'turn/start') {
+    return [{
+      type: 'session/projection',
+      sessionId: id,
+      key: 'todos',
+      value: backscanTodos(log) ?? null,
+      seq: event.seq,
+    }]
+  }
+  return []
 }
 
 /**
@@ -356,11 +367,16 @@ function pageOf(
   return { events, hasMore: start > 0 }
 }
 
-/** Current todo projection over the full log (host parallel: latest todo/write, last write wins). */
+/**
+ * Current plan projection over the full log (host parallel: latest todo/write
+ * with no later turn/start; a new turn retires the previous plan).
+ */
 function backscanTodos(log: readonly SessionEvent[]): TodoItem[] | undefined {
   for (let i = log.length - 1; i >= 0; i--) {
     const event = log[i]
-    if (event !== undefined && event.type === 'todo/write') return event.data.todos
+    if (event === undefined) continue
+    if (event.type === 'turn/start') return undefined
+    if (event.type === 'todo/write') return event.data.todos
   }
   return undefined
 }

packages/client/connection/tests/fixture.spec.ts

@@ -69,7 +69,10 @@ describe('createFixtureApi', () => {
     // tail block still rides it — empty-log cut at -1, the host convention.
     const empty = await api.sessions.history(req({ sessionId: sid('no-such'), maxMessages: 10 }))
     if (!empty.result.ok) throw new Error('empty failed')
-    expect(empty.result.value).toEqual({ events: [], hasMore: false, projections: { asOfSeq: -1, values: {} } })
+    // Fixture composes the todos unit (host parallel when tool-todo is mounted): null before any write.
+    expect(empty.result.value).toEqual({
+      events: [], hasMore: false, projections: { asOfSeq: -1, values: { todos: null } },
+    })
   })
 
   it('serves grouped models and keeps a selected target for later history and fixture requests', async () => {

packages/client/runtime/README.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 packages/client/runtime/README.md
-README.md: 25370844c69aea639c9dca3d5466f5cfd1fc80c0
-README.zh.md: fde649cd2a940dcfad7bd71d9fe2314e6f28466a
+README.md: 879730733f3d89c3962d8c54bcfd53795a980049
+README.zh.md: 1b1d7f03d1f5f03c054dfeaa790a9f6f91e0dca2

packages/client/runtime/README.md

@@ -2,7 +2,7 @@
 
 English | [中文](README.zh.md)
 
-Client cordis boot and React-free object services: SlotsService wraps SlotCore and supplies renderer data sources; SessionsService owns Session objects, list/scope/history state; WorkspacesService depends on SessionsService and owns Workspace objects, list/actions, default-target derivation, and the New Session blank-reuse entry (`connectWorkspace`). The runtime fans the shared Host stream into both managers. Client sessions are always Host-born (Session+Agent+cwd in one `session.create`); the client holds no pre-entity session state — a session's Agent scope (the client mirror of host dsh-scope, keyed by the shared agent/session id) is born when its row enters the list mirror and dies with the prune. Contract: api-contracts v3 §4. Generic full-log domain values such as `todos` and `title` live in the per-session projection store: history-tail `projections` seed it, `session/projection` frames update it under higher-seq-wins, and consumers read keys through `useProjection`. Durable `ConversationSnapshot.metrics` instead comes from the separate history-tail value and live `session/metrics` frames because point-in-time token-meter pressure can advance at the same durable log revision; only nondecreasing log and projection revisions are accepted. `ConversationSnapshot.modelRequestContextWindow` separately retains capacity from the latest `session/model-request` observed on the current mux connection. A later request replaces or clears that value, while `session/subscribed` clears both metrics ordering and capacity; reconnect, restore, and a new subscription therefore show no percentage until another request is observed. Missing metrics remain `null` rather than being inferred from the visible node window.
+Client cordis boot and React-free object services: SlotsService wraps SlotCore and supplies renderer data sources; SessionsService owns Session objects, list/scope/history state; WorkspacesService depends on SessionsService and owns Workspace objects, list/actions, default-target derivation, and the New Session blank-reuse entry (`connectWorkspace`). The runtime fans the shared Host stream into both managers. Client sessions are always Host-born (Session+Agent+cwd in one `session.create`); the client holds no pre-entity session state — a session's Agent scope (the client mirror of host dsh-scope, keyed by the shared agent/session id) is born when its row enters the list mirror and dies with the prune. Contract: api-contracts v3 §4. Each `Session` holds a generic `ProjectionValueStore` seeded from the history-tail `projections` block and updated by `session/projection` frames under higher-seq-wins; domain keys (including `todos` and `title`) are read via `projections.faceOf` / `useProjection`, not via `ConversationSnapshot`. Durable `ConversationSnapshot.metrics` instead comes from the separate history-tail value and live `session/metrics` frames because point-in-time token-meter pressure can advance at the same durable log revision; only nondecreasing log and projection revisions are accepted. `ConversationSnapshot.modelRequestContextWindow` separately retains capacity from the latest `session/model-request` observed on the current mux connection. A later request replaces or clears that value, while `session/subscribed` clears both metrics ordering and capacity; reconnect, restore, and a new subscription therefore show no percentage until another request is observed. Missing metrics remain `null` rather than being inferred from the visible node window.
 
 ## Workspace and Session lists
 

packages/client/runtime/README.zh.md

@@ -2,7 +2,7 @@
 
 [English](README.md) | 中文
 
-客户端 cordis 启动与不依赖 React 的对象服务：SlotsService 包装 SlotCore 并提供 renderer 数据源；SessionsService 拥有 Session 对象、列表／scope／history 状态；WorkspacesService 依赖 SessionsService，拥有 Workspace 对象、列表／操作、默认目标派生，以及 New Session 空会话复用入口（`connectWorkspace`）。运行时把共享 Host 流分发给两个 manager。客户端 Session 一律由 Host 出生（一次 `session.create` 同瞬产出 Session+Agent+cwd）；客户端不持有任何实体化之前的会话状态——Agent scope（host dsh-scope 的客户端镜像，以 agent/session 共用 id 为键）在会话行进入列表镜像时出生，随 prune 死亡。契约：api-contracts v3 §4。`todos` 与 `title` 等通用完整日志领域值存放在逐会话投影值仓中：history 尾页的 `projections` 为其播种，`session/projection` 帧按较高 seq 优先更新，消费方通过 `useProjection` 按 key 读取。持久的 `ConversationSnapshot.metrics` 则来自独立的 history 尾页值与实时 `session/metrics` 帧，因为即时 token-meter 压力可以在相同持久日志修订号上继续变化；客户端只接受日志修订号与投影修订号均不减小的数据。`ConversationSnapshot.modelRequestContextWindow` 另行保留当前 mux 连接观察到的最新 `session/model-request` 容量。后续请求会替换或清除该值，`session/subscribed` 则同时清除指标顺序状态与容量；因此，重连、恢复和新订阅都不会显示百分比，直到观察到另一次请求。缺失的 metrics 保持为 `null`，而不是根据可见节点窗口推断。
+客户端 cordis 启动与不依赖 React 的对象服务：SlotsService 包装 SlotCore 并提供 renderer 数据源；SessionsService 拥有 Session 对象、列表／scope／history 状态；WorkspacesService 依赖 SessionsService，拥有 Workspace 对象、列表／操作、默认目标派生，以及 New Session 空会话复用入口（`connectWorkspace`）。运行时把共享 Host 流分发给两个 manager。客户端 Session 一律由 Host 出生（一次 `session.create` 同瞬产出 Session+Agent+cwd）；客户端不持有任何实体化之前的会话状态——Agent scope（host dsh-scope 的客户端镜像，以 agent/session 共用 id 为键）在会话行进入列表镜像时出生，随 prune 死亡。契约：api-contracts v3 §4。每个 `Session` 持有一个通用的 `ProjectionValueStore`，由历史尾页的 `projections` 块播种，并经 `session/projection` 帧按 seq 高者胜更新；领域键（含 `todos` 与 `title`）经 `projections.faceOf`／`useProjection` 读取，不经 `ConversationSnapshot`。持久的 `ConversationSnapshot.metrics` 则来自独立的 history 尾页值与实时 `session/metrics` 帧，因为即时 token-meter 压力可以在相同持久日志修订号上继续变化；客户端只接受日志修订号与投影修订号均不减小的数据。`ConversationSnapshot.modelRequestContextWindow` 另行保留当前 mux 连接观察到的最新 `session/model-request` 容量。后续请求会替换或清除该值，`session/subscribed` 则同时清除指标顺序状态与容量；因此，重连、恢复和新订阅都不会显示百分比，直到观察到另一次请求。缺失的 metrics 保持为 `null`，而不是根据可见节点窗口推断。
 
 ## Workspace 与 Session 列表
 

packages/client/ui-conversation/README.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 packages/client/ui-conversation/README.md
-README.md: 15bc7c8e18f9992d6c2f0e9770ae33504399266d
-README.zh.md: 1775990359db16adfdd087363bc265aac569799f
+README.md: 4ffa0538cfc29fc1ddfc2cbb6f2c4933da0ac5fa
+README.zh.md: 83678d1474d738a9df2b560ec9890131ba35f673

packages/client/ui-conversation/README.md

@@ -12,7 +12,7 @@ Generic tool rows classify the built-in bash, read, search, write, edit, and run
 
 Tool rows are slots too — the standalone tool ring (`ToolViewRegistry`/`ctx.toolviews`/outlet) is retired. The chat entry declares the keyed `'conversation.chat.toolview'` hole (session scope; the key space is runtime-open); its render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openFile`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam (apply mounts ConversationService after the chat registration, so the service being present guarantees the slot is declared); session differentiation happens inside the component (`useSessions` reading `parentId` — the bash sample is the third-party-posture exemplar). Trajectory/waterfall toolview slots share this shape and land with their own render sites (RendersCheck rejects a declaration nobody renders).
 
-The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `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: -1` — above the queue rows — and is the durable plan strip: it reads the Host-computed `todos` key through `useProjection` and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and collapses to 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 persistent 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 plain registrant plugins with `inject: ['slots', 'conversation']`. `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: -1` — above the queue rows — 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 collapses to 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.
 
 Per-session UI state for selection and the active view lives in the declared chat store (`stores.ts` `createChatStore`); the InputHub owns the composer state machine and mirrors its draft into that store for persistence. Apply passes one store handle to the strict session subtree, chat view, and details registrations, so each session shares one instance and the framework owns its lifecycle. Components are pure: the framework standard kit supplies `useSession`/`sessionId`, global `useSessions`/`useWorkspaces`, and the input machine's `useInput`/`inputActions`; store faces and inject factories supply the remaining state and callbacks.
 

packages/client/ui-conversation/README.zh.md

@@ -12,7 +12,7 @@
 
 工具行同样是 slot：独立工具环（`ToolViewRegistry`／`ctx.toolviews`／outlet）已经退役。聊天配置项声明键控的 `'conversation.chat.toolview'` 空位（Session scope；key 空间在运行时开放）；其渲染点逐行通过 `entryKey: toolName` 分发，并以 `GenericToolCard` 作为调用点 `fallback`。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`／`toolName`／`block`／`openFile`），`ToolRowProps` 则预先将其与 Session 标准工具包组合。注册方只是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作为加载顺序 seam（apply 在聊天注册后挂载 ConversationService，因此服务存在即可保证 slot 已声明）；Session 区分在组件内部完成（`useSessions` 读取 `parentId`，bash 示例是第三方姿态的范例）。Trajectory/waterfall 工具视图 slot 共享此形状，并随各自的渲染点落地（RendersCheck 会拒绝没有任何渲染方的声明）。
 
-todo 两个面就是在该形状上的两个注册项，都是普通注册方插件，`inject: ['slots', 'conversation']`。`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: -1` 占用 `'conversation.input.dock'` 列表 slot（位于队列行之上），是常驻的计划条：它通过 `useProjection` 读取由 Host 计算的 `todos` key 并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏，折叠时收成标题加 `"<已完成>/<总数> tasks · <n> in progress"` 的表头（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；常驻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，都是普通注册方插件，`inject: ['slots', 'conversation']`。`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: -1` 占用 `'conversation.input.dock'` 列表 slot（位于队列行之上），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，折叠时收成标题加 `"<已完成>/<总数> tasks · <n> in progress"` 的表头（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。
 
 逐 Session UI 状态中的选择与活跃视图位于已声明的聊天 store（`stores.ts` `createChatStore`）中；InputHub 拥有输入区状态机，并将草稿镜像到该 store 以便持久化。apply 将同一个 store handle 传给严格限定于会话的子树、聊天视图和详情注册，因此每个会话内共享一个实例，框架拥有其生命周期。组件保持纯粹：框架标准工具包提供 `useSession`／`sessionId`、全局 `useSessions`／`useWorkspaces`，以及输入状态机的 `useInput`／`inputActions`；store 表层与 inject factory 提供其余状态和回调。
 

packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx

@@ -1,9 +1,9 @@
-// TodoPanel: persistent plan strip above the composer (the web counterpart
-// of the TUI plan panel). Renders the latest todo/write whole-list snapshot —
-// no data of its own, hidden while the list is empty. Mounted through the
-// 'conversation.input.dock' slot (QueueDock posture): the dock adapter does
-// the selecting, so the panel takes the plain list and stays framework-free.
-// Visual: figma 772:51905 (states) / 772:52972 (collapsed) / 772:53419 (expanded).
+// TodoPanel: plan strip above the composer (the web counterpart of the TUI
+// plan panel). Renders the standing todo/write whole-list snapshot (cleared on
+// the next turn/start) — no data of its own, hidden while the list is empty.
+// Mounted through the 'conversation.input.dock' slot (QueueDock posture): the
+// dock adapter does the selecting, so the panel takes the plain list and stays
+// framework-free. Visual: figma 772:51905 / 772:52972 / 772:53419.
 
 import { useId, useState } from 'react'
 import type { Context } from 'cordis'

packages/todo/tool-todo/README.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 packages/todo/tool-todo/README.md
-README.md: 5d748e981e8cc75a189916ab87e5d486ba916603
-README.zh.md: ddd22eb13fde81ddd05465ca789b302bb33bb8d9
+README.md: b05ef43e7137dcf5678b1f1ad6d8c00b8a43baef
+README.zh.md: 5bc54c7cdf04f9bd77b385119bb88b2bb6ca43a3

packages/todo/tool-todo/README.md

@@ -20,11 +20,11 @@ Beyond the schema's type/required/enum checks, `execute` rejects an empty or dup
 
 ## Rendering
 
-The canonical result is `{ todos, counts: { pending, inProgress, completed } }`; its Native renderer returns the compact update acknowledgement. The tool also writes the full `todo/write` session event. UIs subscribe to the event stream and render that durable list themselves: the [TUI app](../../examples/tui-demo) shows it as a persistent plan, and the [web client](../../client/ui-conversation) renders a plan strip plus a dedicated tool row off `ConversationSnapshot.todos` ([Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-web-todo-display.md)).
+The canonical result is `{ todos, counts: { pending, inProgress, completed } }`; its Native renderer returns the compact update acknowledgement. The tool also writes the full `todo/write` session event. UIs subscribe to the event stream and render that durable list themselves: the [TUI app](../../examples/tui-demo) and the [web client](../../client/ui-conversation) show a plan strip (plus a dedicated web tool row) off the standing plan — latest `todo/write` with no later `turn/start` ([display](../../../.agents/notes/implemented/feature/2026-07-23-web-todo-display.md), [lifetime](../../../.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.md)).
 
 ## Session projection
 
-When the composition mounts `ctx.sessionProjections` ([`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)), this package registers the `todos` projection unit under an injected child: `init` = `null` (no write yet), `apply` = take the whole list from each `todo/write` (last-wins; every other event returns the same state reference), `view` = identity, `stateVersion` = 1. The key merges into `SessionProjectionMap` here (via the interface package's `/types` outlet); the framework drives the unit and carriers serve the value on the history tail page and the `session/projection` push frame. Compositions without the registry are unaffected.
+When the composition mounts `ctx.sessionProjections` ([`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)), this package registers the `todos` projection unit under an injected child: `init` = `null` (no write yet), `apply` = take the whole list from each `todo/write` and clear to `null` on each `turn/start` (standing plan; `turn/end` keeps the finished checklist; every other event returns the same state reference), `view` = identity, `stateVersion` = 2. The key merges into `SessionProjectionMap` here (via the interface package's `/types` outlet); the framework drives the unit and carriers serve the value on the history tail page and the `session/projection` push frame. Compositions without the registry are unaffected. Lifetime rationale: [todo plan clears on next turn](../../../.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.md).
 
 ## Export shape
 

packages/todo/tool-todo/README.zh.md

@@ -20,11 +20,11 @@
 
 ## 渲染
 
-规范结果为 `{ todos, counts: { pending, inProgress, completed } }`；其 Native 渲染器返回精简的更新确认。工具还会写入完整 `todo/write` 会话事件。UI 订阅事件流，并自行渲染该持久列表：[TUI 应用](../../examples/tui-demo)将其显示为持久计划，[web 客户端](../../client/ui-conversation)则基于 `ConversationSnapshot.todos` 渲染计划横条与专属工具行（[Agent Note](../../../.agents/notes/implemented/feature/2026-07-23-web-todo-display.md)）。
+规范结果为 `{ todos, counts: { pending, inProgress, completed } }`；其 Native 渲染器返回精简的更新确认。工具还会写入完整 `todo/write` 会话事件。UI 订阅事件流，并自行渲染该持久列表：[TUI 应用](../../examples/tui-demo)与 [web 客户端](../../client/ui-conversation)基于站立计划（其后没有更晚 `turn/start` 的最近一次 `todo/write`）显示计划条（web 另有专属工具行）（[展示](../../../.agents/notes/implemented/feature/2026-07-23-web-todo-display.md)、[生命周期](../../../.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.md)）。
 
 ## 会话投影
 
-当组合挂载了 `ctx.sessionProjections`（[`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)）时，本包在一个注入式子插件下注册 `todos` 投影单元：`init` = `null`（尚无写入）、`apply` = 从每个 `todo/write` 取整表（last-wins；其余事件都返回同一个状态引用）、`view` = 恒等、`stateVersion` = 1。key 在本包合并进 `SessionProjectionMap`（经接口包的 `/types` 出口）；框架驱动该单元，载体在历史尾页与 `session/projection` 推送帧上供给该值。未装注册表的组合不受影响。
+当组合挂载了 `ctx.sessionProjections`（[`@deepseek-ai/dsh-session-projection`](../../session-projection/session-projection/README.md)）时，本包在一个注入式子插件下注册 `todos` 投影单元：`init` = `null`（尚无写入）、`apply` = 从每个 `todo/write` 取整表，并在每个 `turn/start` 清为 `null`（站立计划；`turn/end` 保留刚完成的清单；其余事件都返回同一个状态引用）、`view` = 恒等、`stateVersion` = 2。key 在本包合并进 `SessionProjectionMap`（经接口包的 `/types` 出口）；框架驱动该单元，载体在历史尾页与 `session/projection` 推送帧上供给该值。未装注册表的组合不受影响。生命周期理由见 [下一轮清空 todo 计划条](../../../.agents/notes/implemented/feature/2026-07-28-todo-plan-clears-on-next-turn.md)。
 
 ## 导出形状
 

packages/todo/tool-todo/src/index.ts

@@ -78,17 +78,23 @@ const todosProjectionSchema: ZodType<TodoItem[] | null> = z.union([
 /** 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 {
   // The unit child activates only when a projection registry is composed
-  // (headless assemblies without the seam stay unaffected). Pure last-wins
-  // fold: state is the latest whole todo/write list, null before the first
-  // write; every other event returns the same reference (no downstream work).
+  // (headless assemblies without the seam stay unaffected). Standing-plan fold:
+  // latest whole todo/write list, cleared by the next turn/start (turn/end keeps
+  // the finished checklist visible); null before the first write or after a
+  // later turn begins; every other event returns the same state reference.
   ctx.inject(['sessionProjections'], (projectionCtx) => {
     projectionCtx.sessionProjections.register<'todos', TodoItem[] | null>({
       key: 'todos',
       schema: todosProjectionSchema,
       init: () => null,
-      apply: (state, event) => (event.type === 'todo/write' ? event.data.todos : state),
+      apply: (state, event) => {
+        if (event.type === 'todo/write') return event.data.todos
+        if (event.type === 'turn/start') return null
+        return state
+      },
       view: state => state,
-      stateVersion: 1,
+      // Fold semantics changed: turn/start clears the standing plan (was last-write-wins only).
+      stateVersion: 2,
     })
   })
   ctx.tools.register(defineTool({

packages/todo/tool-todo/tests/projection.spec.ts

@@ -91,6 +91,20 @@ describe('todos projection provider', () => {
     expect(projections?.asOfSeq).toBe(session.seq - 1)
   })
 
+  it('clears the standing plan on the next turn/start (turn/end keeps it)', async () => {
+    const bench = await harness(true)
+    const session = bench.session
+    seedMessage(session)
+    const list: TodoItem[] = [{ content: 'done', status: 'completed' }]
+    session.append('todo/write', { todos: list })
+    session.append('turn/end', { turn: 0, reason: { kind: 'completed' } })
+    expect((await bench.tailProjections())?.values.todos).toEqual(list)
+    session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
+    const cleared = await bench.tailProjections()
+    expect(cleared?.values.todos).toBeNull()
+    expect(cleared?.asOfSeq).toBe(session.seq - 1)
+  })
+
   it('has no todos key when tool-todo is not composed', async () => {
     const bench = await harness(false)
     seedMessage(bench.session)

packages/ui/tui/README.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 packages/ui/tui/README.md
-README.md: 528daef773635451ceb198ab3231c2dd87cb9413
-README.zh.md: ed19023334389e3f64b8a2f3821307f1540876f2
+README.md: 5aafd6f5207320bf273c96a04f2d606577ca2da0
+README.zh.md: 1901faeb26c65126bc5475a991fedecd39a88ba5

packages/ui/tui/README.md

@@ -12,7 +12,7 @@ This package owns interactive terminal presentation and input only. It injects `
 
 After terminal startup succeeds, the package provides the terminal-local `ctx.tui` extension service. A plugin that injects it can call `openOverlay()` with a component factory and constrained layout options; the host exposes the viewport, semantic theme, display-text escaping, redraw, close, and a lifetime signal, but not the pi-tui tree, terminal, focus controller, or overlay handle. Plugin overlays, the model selector, and user questions share one FIFO modal queue. Each request is an effect of the calling plugin fiber, so unload removes queued work or closes visible work before cleanup settles; terminal shutdown unloads dependents before stopping pi-tui. Overlay state is not logged or replayed. Component code is trusted and may render ANSI styling, but must pass untrusted text through `host.display()`. The [interactive-extension Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md) owns the boundary and rejected alternatives.
 
-The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. Surface replacement events rebuild the transcript so compacted history does not reappear.
+The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the standing `todo/write` plan above the editor (cleared on the next `turn/start`), and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. Surface replacement events rebuild the transcript so compacted history does not reappear.
 
 An embedding may provide `TuiRuntime.formatCwd` when its logical workspace label differs from the session's host directory. The override changes only the footer label; tools continue to use the session `cwd`.
 

packages/ui/tui/README.zh.md

@@ -12,7 +12,7 @@ DeepSeek Harness agent（智能体）的交互式终端入口，基于 [`@earend
 
 终端成功启动后，本包会提供终端本地的 `ctx.tui` 扩展服务。注入该服务的插件可以使用组件工厂和受限布局选项调用 `openOverlay()`；宿主会公开 viewport、语义化主题、显示文本转义、重绘、关闭和生命周期信号，但不公开 pi-tui 树、终端、焦点控制器或 overlay 句柄。插件 overlay、模型选择器和用户问题共用一个 FIFO 模态队列。每个请求都是调用方插件 fiber 的 effect，因此卸载会移除排队工作，或在清理结算前关闭可见工作；终端关闭会先卸载依赖项，再停止 pi-tui。Overlay 状态不会记录或回放。组件代码受信任，可以渲染 ANSI 样式，但必须通过 `host.display()` 处理不受信任文本。[交互式扩展 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md)持有该边界和未采用的替代方案。
 
-TUI 从活跃会话表层重建已恢复历史，渲染 Markdown 响应与 reasoning，将每个工具的 `presentCall` / `presentResult` 意图应用到终端、diff 或通用卡片，把最新的 `todo/write` 计划保留在编辑器上方，并在左下方宽键盘面板中展示 `ctx.userInteraction` 问题，包含进度、编号选项和对齐说明。最新记录的会话标题成为 header 副标题；标题不存在时使用 `welcome`，终端窗口标题则变为 `<session title> — <configured title>`。持久 `llm/retry` 事件会撤回失败步骤的实时 chunk，并在 transcript（文本记录）中渲染计划重试次数、延迟和失败；成功、耗尽与取消随后通过普通会话事件结算。Footer 会对每个已记录模型步骤的用量只计一次，包括失败尝试；对于没有用量 chunk 的日志，以已提交消息的用量回退。其空闲视图会将 token-meter 压力与 `ctx.llm.resolveModelInfo()` 为当前路由返回的上下文容量进行比较；适配器没有容量元数据时显示 `context unknown`，并显示工具卡片模式、当前模型，以及任何显式选择的推理强度。Agent 运行时，这些摘要会替换为已经过工作时间指示器和 `esc interrupt`。表层替换事件会重建 transcript，使经过压缩（compaction）的历史不会再次出现。
+TUI 从活跃会话表层重建已恢复历史，渲染 Markdown 响应与 reasoning，将每个工具的 `presentCall` / `presentResult` 意图应用到终端、diff 或通用卡片，把站立的 `todo/write` 计划保留在编辑器上方（下一个 `turn/start` 时清空），并在左下方宽键盘面板中展示 `ctx.userInteraction` 问题，包含进度、编号选项和对齐说明。最新记录的会话标题成为 header 副标题；标题不存在时使用 `welcome`，终端窗口标题则变为 `<session title> — <configured title>`。持久 `llm/retry` 事件会撤回失败步骤的实时 chunk，并在 transcript（文本记录）中渲染计划重试次数、延迟和失败；成功、耗尽与取消随后通过普通会话事件结算。Footer 会对每个已记录模型步骤的用量只计一次，包括失败尝试；对于没有用量 chunk 的日志，以已提交消息的用量回退。其空闲视图会将 token-meter 压力与 `ctx.llm.resolveModelInfo()` 为当前路由返回的上下文容量进行比较；适配器没有容量元数据时显示 `context unknown`，并显示工具卡片模式、当前模型，以及任何显式选择的推理强度。Agent 运行时，这些摘要会替换为已经过工作时间指示器和 `esc interrupt`。表层替换事件会重建 transcript，使经过压缩（compaction）的历史不会再次出现。
 
 如果逻辑工作区标签与会话宿主目录不同，嵌入方可以提供 `TuiRuntime.formatCwd`。该覆盖只改变 footer 标签；工具仍使用会话 `cwd`。
 

packages/ui/tui/src/index.ts

@@ -703,6 +703,10 @@ export function createTuiChat(
       case 'todo/write':
         todo.update(event.data.todos)
         break
+      case 'turn/start':
+        // Plan strip is turn-scoped: keep it after turn/end for reading, clear on the next turn.
+        todo.update([])
+        break
       case 'session/title':
         sessionTitle = event.data.title
         header.invalidate()
@@ -759,6 +763,7 @@ export function createTuiChat(
     toolCards.clear()
     allToolCards.clear()
     streaming = undefined
+    todo.update([])
     const active = activeSurfaceSeqs(agent.session)
     const activeCalls = activeToolCallIds(agent.session, active)
     for (const event of agent.session.events) {

packages/ui/tui/tests/snapshots/todo-plan-cleared.expected.txt

@@ -0,0 +1,38 @@
+terminal 96x36 buffer=normal length=36 base=0 viewport=0
+lifecycle started=1 stopped=0 progress=inactive
+title "DSH snapshot"
+cursor hidden column=7 viewportRow=15 bufferRow=15
+viewport
+0| " DEEPSEEK HARNESS"
+  style 1-8 fg=bright-blue bold
+  style 10-16 bold
+1| " Snapshot agent ready."
+  style 1-21 fg=bright-black
+2| " main-session"
+  style 1-12 dim
+3| <blank>
+4| "Assistant                                                                                       "
+  style 0-8 fg=bright-magenta bold underline
+5| "Tracking the steps.                                                                             "
+6| "Model wait 0.0s · Completed 2026-07-21 14:45:00                                                 "
+  style 0-46 dim
+7| <blank>
+8| "You                                                                                             "
+  style 0-2 fg=bright-blue bold underline
+9| "Plan the work.                                                                                  "
+10| <blank>
+11| "You                                                                                             "
+  style 0-2 fg=bright-blue bold underline
+12| "Next question.                                                                                  "
+13| <blank>
+14| "/workspace/project (tui-staging)  deepseek-v4-flash  ↑0 ↓0  0% context"
+  style 0-17 fg=bright-blue bold
+  style 18-31 fg=bright-black
+  style 34-50 fg=bright-black
+  style 53-57 fg=bright-black
+  style 60-69 fg=bright-black
+15| " dsh >                                                                                          "
+  style 1-3 fg=bright-blue bold
+  style 5-6 fg=bright-black
+  style 7-7 inverse
+16-35| <blank>

packages/ui/tui/tests/tui.snapshot.ts

@@ -57,6 +57,7 @@ const CHECKPOINTS = [
   'resume-sessions',
   'status-diagnostics',
   'status-diagnostics-narrow',
+  'todo-plan-cleared',
 ] as const
 
 // Real-loop scenarios own their assertions in separate snapshot suites but
@@ -301,6 +302,34 @@ describe('TUI terminal-state snapshots', () => {
     await disposeSnapshot(harness)
   })
 
+  it('clears the plan strip when the next turn starts', async () => {
+    // Freeze Completed-at formatting: the first turn ends before the next starts,
+    // so the assistant timing line still appears without a Plan strip below it.
+    const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 14, 45, 0).getTime())
+    const harness = await setupSnapshot({
+      beforeMount(session) {
+        appendUser(session, 'Plan the work.')
+        appendAssistant(session, [{ type: 'text', text: 'Tracking the steps.' }])
+        session.append('todo/write', {
+          todos: [
+            { content: 'read code', status: 'completed' },
+            { content: 'write tests', status: 'in_progress' },
+          ],
+        })
+        session.append('step/end', { turn: 1, step: 1 })
+        session.append('turn/end', { turn: 1, reason: { kind: 'completed' } })
+        session.append('turn/start', {
+          turn: 2,
+          trigger: { kind: 'message', source: { kind: 'user' } },
+        })
+        appendUser(session, 'Next question.')
+      },
+    })
+    await checkpoint('todo-plan-cleared', harness.terminal)
+    nowSpy.mockRestore()
+    await disposeSnapshot(harness)
+  })
+
   it('pins failed-stream retraction, scheduled retry, and eventual success', async () => {
     const harness = await setupSnapshot()
     await renderAfter(harness, () => {