feat: implement todo plan clearance on turn start

This commit is contained in:
07akioni
2026-07-28 17:55:47 +08:00
parent d85fe78f7d
commit 9e94082f4d
28 changed files with 211 additions and 61 deletions

View File

@@ -316,11 +316,16 @@ 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
}

View File

@@ -99,8 +99,9 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
private queueCache: { rev: number; value: QueuedMessage[] } | null = null
private frozenRev = 0
private nodesCache: { folded: readonly ConversationNode[]; frozenRev: number; value: readonly ConversationNode[] } | null = null
/** Current whole-list todo/write projection: each tail history response replaces it (an omitted
* field is the authoritative empty list) and every live write overwrites it. */
/** Current plan strip: the latest `todo/write` not followed by a later `turn/start`. Tail history
* responses replace it (an omitted field is the authoritative empty list); live writes overwrite
* it; each new `turn/start` clears it so a finished plan does not linger into the next turn. */
private todos: readonly TodoItem[] = []
/** `run_code` sub-dispatches by parent callId (window-derived, like openCalls). Appends
* copy-on-write the per-parent array so published snapshot references never mutate. */
@@ -511,13 +512,13 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
this.views = entries.map(e => e.view)
this.baseSeq = this.events[0]?.seq ?? 0
this.hasMore = hasMore
// Session-level projection from the tail page (full-log latest todo/write,
// independent of the window); an in-window write below re-derives the same
// value, and later live events keep overwriting it. Every caller here is a
// tail request (no beforeSeq), 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, not a missing carrier. Assigning
// it clears a plan the log never kept (a write lost to a host crash).
// Tail-page projection (full-log current plan, independent of the window);
// an in-window write or turn/start below re-derives the same value, and later
// live events keep overwriting or clearing it. Every caller here is a tail
// request (no beforeSeq), which the host answers with the projection or omits
// it when the log has no standing plan — so an absent field is the
// authoritative empty list, not a missing carrier. Assigning it clears a plan
// the log never kept (a write lost to a host crash).
this.todos = todos ?? []
this.foldAdapter.reset(this.events, this.baseSeq, this.views)
this.rebuildDerivedFromWindow()
@@ -693,6 +694,13 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
this.todos = event.data.todos
return
}
case 'turn/start': {
// The plan strip is turn-scoped for display: a new turn retires the previous
// list until the model writes again. turn/end keeps it visible so the finished
// checklist remains while the user reads the answer.
this.todos = []
return
}
case 'turn/end': {
// Aborted turns never finalize. The accumulated partial is VALUE, not residue: freeze it
// into an interrupted terminal node (pulse stops, text survives) instead of deleting it.
@@ -738,10 +746,12 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
/** Re-derive state (partial/openCalls/frozenNodes) from raw window events after a rebuild — keeps
* paging/stitching consistent, and makes the live freeze and the history replay converge on the
* same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text).
* todos is deliberately NOT reset: it is session-level (seeded by the tail page's full-log
* projection, not derivable from an arbitrary window). The window always extends to the log
* tail, so an in-window todo/write can only overwrite it with the same latest value. */
* The standing plan starts empty for the sweep; when the window itself never determines it
* (no todo/write and no turn/start — the write still precedes the page), the tail-page seed is
* restored. A contiguous tail window that contains a turn/start after the standing write will
* determine empty, matching the host projection. */
private rebuildDerivedFromWindow(): void {
const seededTodos = this.todos
this.partial = null
this.openCalls.clear()
this.callsRev++
@@ -749,11 +759,16 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
this.frozenRev++
this.codeDispatches = new Map()
this.dispatchesRev++
this.todos = []
let todosDetermined = false
for (let i = 0; i < this.events.length; i++) {
const event = this.events[i]
/* v8 ignore next -- dense-array guard: i stays within events.length, so the undefined arm needs a sparse array no caller builds. */
if (event !== undefined) this.applyEventSideEffects(event, this.views[i])
if (event === undefined) continue
if (event.type === 'todo/write' || event.type === 'turn/start') todosDetermined = true
this.applyEventSideEffects(event, this.views[i])
}
if (!todosDetermined) this.todos = seededTodos
}
private windowTailSeq(): number | null {

View File

@@ -177,23 +177,62 @@ describe('live event path', () => {
it('seeds todos from the tail page projection when the last write precedes the window', async () => {
const list = [{ content: '窗口外的计划', status: 'in_progress' as const }]
// Cold open: the page window carries NO todo/write; the projection rides the response.
// Cold open: same-turn page with no todo/write and no turn/start (a later turn/start
// would mean the host projection is empty). The standing plan rides the response.
const tailPage = [
ev.user(100, '问'),
ev.stepStart(101, 9),
ev.assistant(102, 9, '答'),
ev.stepEnd(103, 9),
ev.turnEnd(104, 9),
]
const { api, session } = makeSession()
api.onHistory = () => histResponse(plainTurn(100, 9, '问', '答'), true, list)
api.onHistory = () => histResponse(tailPage, true, list)
await session.open()
expect(session.getSnapshot().todos).toEqual(list)
// Paging an older window in must not clear the session-level projection.
api.onHistory = () => histResponse(plainTurn(94, 8, '旧问', '旧答'), false)
// Older same-turn slice (still no determiner) must keep the seeded plan.
api.onHistory = () => histResponse([
ev.user(95, '旧问'),
ev.stepStart(96, 9),
ev.assistant(97, 9, '旧答'),
ev.stepEnd(98, 9),
ev.turnEnd(99, 9),
], false)
await session.loadOlder()
expect(session.getSnapshot().todos).toEqual(list)
// A later live write still overrides the seeded projection.
// Contiguous live write (tail is 104) still overrides the seeded projection.
session.handleMuxEnvelope('r' as never, {
type: 'session/event', sessionId: SID,
event: ev.todoWrite(106, [{ content: '新计划', status: 'pending' as const }]),
event: ev.todoWrite(105, [{ content: '新计划', status: 'pending' as const }]),
})
expect(session.getSnapshot().todos).toEqual([{ content: '新计划', status: 'pending' }])
})
it('clears the plan on turn/start (live and on window replay)', async () => {
const list = [{ content: '上一轮计划', status: 'completed' as const }]
const { session } = await opened()
const feed = (event: SessionEvent) => {
session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event })
}
feed(ev.todoWrite(6, list))
expect(session.getSnapshot().todos).toEqual(list)
// turn/end keeps the finished checklist visible while the user reads.
feed(ev.turnEnd(7, 0))
expect(session.getSnapshot().todos).toEqual(list)
feed(ev.turnStart(8, 1))
expect(session.getSnapshot().todos).toEqual([])
// Replay converges: a turn/start after the latest write yields an empty plan.
const replayed = makeSession()
replayed.api.onHistory = () => histResponse([
...plainTurn(0, 0, 'a', 'b'),
ev.todoWrite(6, list),
ev.turnStart(7, 1),
ev.user(8, '下一问'),
])
await replayed.session.open()
expect(replayed.session.getSnapshot().todos).toEqual([])
})
it('repairs a seq gap by repulling the tail page instead of appending a hole', async () => {
const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) // tail seq = 5
const repaired = [...plainTurn(0, 0, 'a', 'b'), ...plainTurn(6, 1, 'c', 'd')]
@@ -211,11 +250,18 @@ describe('live event path', () => {
it('gap repair adopts the repull response projection (a missed todo/write outside the new tail page)', async () => {
const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) // tail seq = 5
expect(session.getSnapshot().todos).toEqual([])
// The missed range contained a todo/write that the repulled page no longer
// covers; the response's session-level projection is the only carrier.
// Missed todo/write still stands (no later turn/start); the repulled tail page
// omits that write and any determiner, so the response projection is the carrier.
const current = [{ content: '断线期间写的', status: 'in_progress' as const }]
api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ...plainTurn(8, 1, 'c', 'd')], false, current)
session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event: ev.assistant(11, 1, 'd') })
const tailPage = [
ev.user(8, 'c'),
ev.stepStart(9, 1),
ev.assistant(10, 1, 'd'),
ev.stepEnd(11, 1),
ev.turnEnd(12, 1),
]
api.onHistory = () => histResponse(tailPage, false, current)
session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event: ev.assistant(10, 1, 'd') })
await vi.waitFor(() => {
expect(api.callsOf('session.history').length).toBe(2)
})

View File

@@ -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: a04c20f225c731581accbe8c12c52a5e7597029a
README.zh.md: f9e6a635ea6090c87a66f029785af214025b9bda
README.md: f343691d27993791f2264c4335c5cfa6a620851a
README.zh.md: aebac5ca78da914af61f4be8001b47cd01628e1e

View File

@@ -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 selects `todos` off the session snapshot 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 selects `todos` off the session snapshot (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.

View File

@@ -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:它从会话快照中选取 `todos` 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:它从会话快照中选取 `todos`(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。

View File

@@ -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'

View File

@@ -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/host/apiproxy/README.md
README.md: 33a4752f97c17e7879dff11a33acc93e335496b7
README.zh.md: 45aee0225717ad8a4d9b923067f196535c7ab3f9
README.md: c1a4bb9aa08119dc0edb783fad22a758410e18d8
README.zh.md: 8ba835751771d38b9b5e192b48bd64b1e347b49f

View File

@@ -20,7 +20,7 @@ Workspace and Session lists are separate reconnect baselines. `workspace.create`
`host.openPath` opens a filesystem path with the operating system's default application (`open` on macOS, `Invoke-Item` on Windows, `xdg-open` on Linux). The opener is injectable for tests. The browser carrier applies the same loopback, same-origin restriction as `host.pickDirectory`.
`session.history` pages on message boundaries, and its tail page (no `beforeSeq`) carries two session-level extras the page window cannot supply: the in-flight partial's chunk events, and `todos` — the latest `todo/write` whole-list projection over the full log. Older pages omit `todos` because the projection is session-level, not per-page; a tail response that omits it means the whole log holds no `todo/write`, so clients read the absent field as the empty plan rather than as unchanged state.
`session.history` pages on message boundaries, and its tail page (no `beforeSeq`) carries two session-level extras the page window cannot supply: the in-flight partial's chunk events, and `todos` — the standing plan over the full log (latest `todo/write` with no later `turn/start`). Older pages omit `todos` because the projection is session-level, not per-page; a tail response that omits it means no plan stands, so clients read the absent field as the empty plan rather than as unchanged state.
The `command.*` and `skill.*` domains expose the host command registry and skill catalog to clients. Every method addresses one session's agent by `sessionId` (a served session always has an Agent; `command.*` resumes cold sessions through the same path as `session.*`, while `skill.list` resolves the project root from the session header without touching the Agent registry). `command.execute` runs a slash-command line host-side and returns a detached result; the carrier's request signal cancels the running handler. `host/commands-changed` is the catalog invalidation frame: clients refetch `command.list` instead of diffing.

View File

@@ -20,7 +20,7 @@ Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.cr
`host.openPath` 会用操作系统的默认应用打开一个文件系统路径(macOS 为 `open`,Windows 为 `Invoke-Item`,Linux 为 `xdg-open`)。打开器可在测试中注入。浏览器载体对其施加与 `host.pickDirectory` 相同的回环、同源限制。
`session.history` 按消息边界分页,其尾页(不带 `beforeSeq`)额外携带两项页窗口本身无法提供的会话级数据:进行中局部消息的 chunk 事件,以及 `todos`——整份日志上最后一次 `todo/write` 的整表投影。较早的页面不带 `todos`,因为该投影是会话级而非分页级的;尾页响应缺少该字段意味着整份日志中没有任何 `todo/write`,因此客户端要把缺失字段读作空计划,而不是读作「状态未变」。
`session.history` 按消息边界分页,其尾页(不带 `beforeSeq`)额外携带两项页窗口本身无法提供的会话级数据:进行中局部消息的 chunk 事件,以及 `todos`——整份日志上的站立计划(其后没有更晚 `turn/start` 的最近一次 `todo/write`)。较早的页面不带 `todos`,因为该投影是会话级而非分页级的;尾页响应缺少该字段意味着当前没有站立计划,因此客户端要把缺失字段读作空计划,而不是读作「状态未变」。
`command.*` 与 `skill.*` 领域向客户端暴露宿主命令注册表和技能目录。每个方法都通过 `sessionId` 寻址一个会话的 Agent(被服务的会话必有 Agent;`command.*` 经由与 `session.*` 相同的路径恢复冷会话,而 `skill.list` 从会话头解析项目根目录,不触碰 Agent 注册表)。`command.execute` 在宿主侧运行一条斜杠命令行并返回脱耦结果;载体的请求信号可取消正在运行的处理器。`host/commands-changed` 是目录失效帧:客户端重新拉取 `command.list` 而不是做差分。

View File

@@ -295,11 +295,17 @@ function backscanArgs(events: readonly SessionEvent[], callId: string): { name:
return undefined
}
/** Current todo projection: the latest `todo/write` over the full log (whole-list replace ⇒ last write wins); undefined when none. */
/**
* Current plan projection over the full log: the latest `todo/write` that is not
* followed by a later `turn/start` (whole-list replace ⇒ last write wins; a new
* turn retires the previous plan). Undefined when none stands.
*/
function backscanTodos(events: readonly SessionEvent[]): TodoItem[] | undefined {
for (let i = events.length - 1; i >= 0; i--) {
const event = events[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
}

View File

@@ -179,6 +179,11 @@ describe('mux live view computation', () => {
const older = await api.sessions.history({ rpcId: RpcId('t-todos-2'), payload: { sessionId: session.id, beforeSeq: boundary, maxMessages: 2 } })
if (!older.result.ok) throw new Error('older failed')
expect('todos' in older.result.value).toBe(false)
// A later turn/start retires the standing plan (omit the field = empty).
session.append('turn/start', { turn: 6, trigger: { kind: 'message', source: { kind: 'user' } } })
const cleared = await api.sessions.history({ rpcId: RpcId('t-todos-cleared'), payload: { sessionId: session.id, maxMessages: 2 } })
if (!cleared.result.ok) throw new Error('cleared failed')
expect('todos' in cleared.result.value).toBe(false)
// A session with no todo/write anywhere omits the field.
const bare = ctx.sessions.create()
ctx.agents.register({ id: bare.id, session: bare, status: 'idle', ctx } as Agent)

View File

@@ -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
README.md: 3615f68953cfe6cdc0e6fc41bf75b8dfdf90a310
README.zh.md: c4a7d829cc1583b65d2c8afa1683d957f68722e9
# pnpm run verify-translation-pairing --write packages/todo/tool-todo/README.md
README.md: 96675539acde5e5b8d0ced32a895473d832f7dd8
README.zh.md: 9a00ecf0cd85fff5ba3a3327252d437687a67f55

View File

@@ -20,7 +20,7 @@ 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)).
## Export shape

View File

@@ -20,7 +20,7 @@
## 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))。
## 导出形状

View File

@@ -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

View File

@@ -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`.

View File

@@ -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`。

View File

@@ -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) {