feat(web): list background tasks in the session header

The task registry has run every background bash, pwsh, pty-send, and one-shot subagent since it landed, but only the model could read it: a human at the Web client could not see that a build was running, tell a finished task from a stuck one, or find its outcome anywhere but the `run_in_background` tool card that printed an id and never updated. Task state now reaches the browser as one whole-snapshot `session/tasks` mux frame per session, pushed at every registry commit that changes what that session can see. `TaskService` gains `onTasksChanged`, which is owner-granular because owner-disposal removal is a change no per-task record can express. The carrier reads the exact owner the listener hands it, so a push stays correct while that scope tears down, and reads the baseline through the non-resuming `ctx.agents.get` so listing never revives a cold session. The client keeps a last-wins mirror on `SessionListState`, and a new `dsh-client-ui-task` package renders it beside the subagent catalog — rendering nothing at all until the session has a task, so an ordinary conversation grows no new chrome. Streamed per-task output and human-initiated cancellation are separate phases; the note records why neither has to undo this channel, and why no Web path may call the consuming `ctx.tasks.read()`.
2026-08-08 23:29:41 +08:00
parent 22609ea425
commit eab0aeb9db
93 changed files with 2130 additions and 68 deletions
@@ -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/2026-08-08-web-background-task-display.md
 2026-08-08-web-background-task-display.md: 17ac109082ab3b2afea92194d0d148cf11ba9d0a
 2026-08-08-web-background-task-display.zh.md: 1049218337caae3bd95c6f6ff3183589d0ce9d15
@@ -0,0 +1,136 @@
 # Agent Note: Web background-task display
 Status: implemented
 English | [中文](2026-08-08-web-background-task-display.zh.md)
 ## Problem
 `ctx.tasks` already runs every long-lived piece of work the harness starts in the background — `bash`, `pwsh`, `pty-send`, and one-shot background subagents — but its only reader was the model. [`dsh-tool-tasks`](../../../../packages/tasks/tool-tasks/README.md) exposes `task_list`, `task_output`, and `task_kill`, and nothing else observed the registry.
 A human at the Web client therefore could not see that a build was running, could not distinguish a finished task from a stuck one, and could not stop one. The only trace was the `run_in_background` tool card that printed a task id somewhere earlier in the transcript, and that card never updates again.
 The session header was already the place where per-session background activity lives: [`dsh-client-ui-subagent`](../../../../packages/client/ui-subagent/README.md) contributes the subagent catalog to `conversation.session.header.actions`. Placement was settled. What was missing was any channel at all that carried task state to a browser.
 ## Decision
 Task state reaches the browser as **one whole-snapshot mux frame per session**, pushed at every registry commit point that changes what that session can see. The client keeps a last-wins mirror; a header action renders it. There is no RPC, no polling, and no client-side staleness bookkeeping.
 This ships the list alone. Per-task streamed output and a human-initiated cancellation are separate phases, and the channel is shaped so neither has to undo it.
 ### Wire shape
 One frame in the mux stream:
 ```ts ignore-check
 | { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] }
 ```
 `TaskView` is browser-safe and owned by the carrier at [`packages/host/apiproxy/src/api/tasks.ts`](../../../../packages/host/apiproxy/src/api/tasks.ts), alongside the other domain contracts, with its wire schema beside it in `tasks.schema.ts`:
 ```ts
 import type { TaskId } from '@deepseek-ai/dsh-tasks/brand'
 export interface TaskView {
  id: TaskId
  kind: string
  label: string
  status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed'
  detail?: string
  startedAt: number
  finishedAt?: number
 }
 ```
 `TaskId` comes from the cordis-free [`@deepseek-ai/dsh-tasks/brand`](../../../../packages/tasks/tasks/src/brand.ts) leaf — the same arrangement as the `@deepseek-ai/dsh-llm/brand` import `api/subagents.ts` already uses, because the `dsh-tasks` root reaches `dsh-agent` and is unreachable from a client program even as a type. Like every other non-root subpath in this workspace, it carries an explicit `tsconfig.base.json` `paths` entry; without one the TypeRT analyzer resolves the specifier to `lib/types/` and rejects the reference as unexported.
 `kind` is `string` on the wire rather than `TaskKind`. The kind map is merge-extensible by producer plugins, so a client build cannot enumerate the closed set; presentation falls through a documented default for an unrecognized kind.
 Three `TaskSnapshot` fields are deliberately absent: `ownerSession` (the frame's `sessionId` already carries it), `reported` (an internal notice-delivery bit with no user meaning), and `outputLimitBytes` (producer-owned model-presentation policy).
 The frame carries a whole snapshot rather than a delta for the reason [`session/queue`](../../../../packages/host/apiproxy/src/api/events.ts) states for itself: start, kill, settlement, reconnect, and a second browser tab all converge through one authoritative value. A session's task set is single-digit; the frame is small.
 ### The task-registry change feed
 `TaskService` owns one observation method:
 ```ts ignore-check
 abstract onTasksChanged(listener: TasksChangedListener): () => void
 ```
 It fires **after** every commit that changes what `list(owner)` returns: registration at the end of `start()`, the `stopping` transition in `kill()`, settlement, and the removal `disposeOwner()` performs. An `undefined` owner means an unowned task changed, and therefore every caller's view changed.
 The listener is owner-granular rather than task-granular. The only consumer pushes whole snapshots, so a per-task record would be discarded on arrival — and a per-task feed cannot express the owner-disposal removal at all without inventing a tombstone status nothing else needs.
 `onTaskDone` is not a subset of this. It delivers the terminal record with the exact owner `Agent` under first-wins semantics that `dsh-tool-tasks` couples to `reported`; `onTasksChanged` is pure observation with no delivery meaning and marks nothing reported. Listener throws are contained and never awaited, matching `onTaskDone`, and each registration is an effect on the calling fiber.
 Service disposal deliberately announces nothing. Every `onTasksChanged` registration is an effect on the registry's own fiber, so the listeners are already gone by the time teardown clears the store; an observer learns the registry left through its own disposal, not through a final empty set.
 ### The api-proxy carrier
 `mux()` subscribes `ctx.tasks.onTasksChanged` and pushes `session/tasks`; the subscription baseline rides next to the existing `session/subscribed` control frames, so a reconnecting client is current before it renders.
 Four rules the carrier keeps:
 - **Never resume.** A change push reads `tasks.list(owner)` with the exact `Agent` the listener supplied, which stays correct even while that owner's scope is tearing down and a lookup by id would already miss. The baseline instead reads `ctx.tasks.list(ctx.agents.get(session.id))` — the non-resuming registry read, where a session with no live Agent correctly yields only the unowned tasks. Neither path touches the [`api-remotes` Agent resolver](../../../../packages/api/remotes/src/agent-lookup.ts), which resumes a cold session as a side effect of lookup; listing must never revive a session the user merely scrolled past.
 - **Fan out unowned changes.** An `undefined` owner pushes a fresh snapshot to every subscribed session, because unowned tasks are visible to every caller.
 - **Stay optional.** The carrier reads `ctx.get('tasks')`. A composition without the registry emits no frames, and the client renders no entry point — the posture `sessionProjections` already has in this file.
 - **Say nothing about nothing.** The baseline is pushed only for sessions whose list is non-empty, and an absent key on the client means an empty list. A change that empties a list still pushes `[]`, because that one transition is the only thing the client cannot infer from absence.
 ### The client mirror
 `SessionListState` carries `tasksBySession: Readonly<Record<SessionId, readonly TaskView[]>>`, owned by `SessionManager` and folded from the frame under last-wins, with an emptied set stored as an absent key so absence and `[]` are one representation.
 It lives on the list mirror rather than on `Session` for three reasons: the header action already reads list state through `useSessions`, nothing needs the pre-instantiation buffering `session/queue` requires (no composer behavior depends on tasks), and a later sidebar indicator gets the data without opening a second channel.
 Two clears keep it honest. On re-subscribe the manager drops the session's mirror — the rule `session/queue` already follows, because a fresh baseline is arriving and this generation sends none for an empty set, so a retained list would survive as a phantom. On `host/session-removed` it drops the mirror again: owner disposal already removed the records registry-side, but that lands on the mux stream while the removal frame rides the host stream, so the two have no relative order.
 ### The header action
 [`@deepseek-ai/dsh-client-ui-task`](../../../../packages/client/ui-task/README.md) registers one entry in `conversation.session.header.actions`, ordered after the subagent catalog. Its own README owns the presentation contract; the decisions worth recording here are that the control does not render at all until the session has a task, that the live badge is omitted at zero so a history-only session keeps a quiet entry point, and that settled rows stay visible because a failed task's `detail` is the only place its failure is legible.
 A running one-shot background subagent therefore appears both there and in the subagent catalog. The two answer different questions — the catalog navigates into the child's transcript, this list is the only handle a cancellation can ever attach to — and suppressing `kind: 'subagent'` here would leave the cancellation phase with no entry point for exactly those tasks.
 ### What this deliberately does not do
 **No web path calls `ctx.tasks.read()`.** It consumes the single output cursor, so a browser read would silently take bytes the model's `task_output` will never see. This is an invariant worth a test rather than a convention, because the failure is invisible at the call site.
 **No cancellation.** That phase owes a decision the seam does not currently answer: `kill()` marks terminal delivery reported, so a human interrupt written against today's contract would leave the model believing its task is still running.
 **No output watermark on the frame.** The output phase's delta channel is where an anchor field earns its place; one added now would have no reader.
 ## Alternatives considered
 **Signal frame plus RPC pull, the subagent-catalog shape.** Push a payload-free `tasks-changed` signal, debounce, then re-read authoritative state over a unary RPC. This is what the subagent catalog does, and the cost is visible in [`SessionManager`](../../../../packages/client/runtime/src/client/sessions/manager.ts): `catalogInflight` for single-flight, `catalogStale` for a trailing re-pull when a membership frame lands mid-request, `updateCatalogActivity` patching loaded rows in place *and* writing into the in-flight request so a response older than the frame gets overwritten, `parentAvailableOverride` replaying a stale `false`, and a reconnect path re-pulling every open catalog. That apparatus exists because the catalog's authority is split — durable lineage from a projection, liveness sampled at response time — and tasks have no durable half to justify inheriting it. It also fails specifically at the moment the output phase cares about: a task settles, its output stream closes immediately, but status only arrives after debounce plus round-trip, so the UI shows a running task with a dead stream for that window.
 **Popover-scoped polling with no seam change.** Cheapest to build and the only option that avoids touching `TaskService`. It cannot support a resident count on the trigger without a resident poll, and both later phases need a real change feed anyway, so it buys a week and spends it back.
 **A session-projection unit over durable task events.** Projection units fold over committed session events, so this would first require task lifecycle to become durable — `task/started` … `task/settled` as a standalone open/close bracket, with the last [`session/end-seed`](../../../../packages/core/session/src/types.ts) marking any unmatched opener as dead history, exactly as the compaction bracket already does. It is genuinely cheaper on the client: `dsh-tool-todo` shows the whole pattern in a fifteen-line unit, and the existing `session/projection` frames, history-tail block, and persisted checkpoint cache would have carried the data with no new wire surface, no carrier subscription, and no manager state. It was rejected because it buys that with a durable format change in service of a browser list, and because it does not extend to the phase it would most need to: [`spill/`](../../../../packages/spill/README.md) exists precisely so oversized tool output stays out of the log, so streamed task output cannot ride durable events either way. Nothing here forecloses revisiting it if durable task history becomes valuable on its own merits.
 **Reusing `PublicTaskSnapshot` from `dsh-tool-tasks`.** Nearly the right fields, but it belongs to the model-facing control surface. A wire type a browser program imports from a tool package couples client presentation to prompt-facing decisions and drags a host-only package into a client build.
 **Folding tasks into the subagent catalog as one "activity" panel.** One entry point instead of two. Rejected because `SubagentCatalogAction` is already 605 lines whose subject is a durable session-lineage tree including finished children; process-scoped tasks are a second data model with different identity, lifetime, and affordances, and the catalog's lazily-expanded branch, duration, and token contracts would all need rewriting to host them.
 **A host-global task list across every session.** The literal reading of "show all running tasks". Rejected because the registry's authorization fence is per-owner-session, so a global read needs a new access rule, and a global list has no business in a session's header — it would need its own home in the sidebar. Nothing in this design blocks adding it later; the per-session frames are the same data.
 ## Testing
 The [web e2e scenario](../../../../apps/web/tests/background-task-list.e2e.ts) is the end-to-end proof and runs keyless: a real `run_in_background` bash call registers with `ctx.tasks`, the header count and row appear with no user interaction, and killing the task through the registry flips the open list to its producer detail. It asserts the whole delivery path rather than any single layer.
 Below it, [`tasks-local`](../../../../packages/tasks/tasks-local/tests/tasks.spec.ts) pins the change feed at all four commit points, its containment of a throwing observer, and its removal on both explicit disposal and fiber teardown; [`api-proxy-tasks`](../../../../packages/host/apiproxy/tests/api-proxy-tasks.spec.ts) pins the baseline-only-when-non-empty rule, the three change pushes, the dropped internal fields, the unowned fan-out, the no-resume guarantee, and the registry-absent composition; and the client suites pin the last-wins fold, the absent-key representation, both clears, and the component's ordering, duration, and dismissal behavior.
 ## Consequences
 **A missed commit point leaks rows.** If `disposeOwner()` removal ever stops firing the feed, the client keeps tasks that no longer exist until the session disappears. The whole-snapshot shape makes this recoverable rather than corrupting — the next legitimate change repairs the list — but the disposal path is the one most easily forgotten, so it carries its own test.
 **Unowned-task fan-out is easy to under-implement.** Pushing only to the changed owner's session is correct for owned tasks and silently wrong for unowned ones, which are visible everywhere. The bug would surface only in compositions that create unowned tasks, which is why the carrier suite covers it directly.
 **The UI set is not the registry's set.** An unowned task is invisible in the header while `task_list` still reports it to the model. In practice every tool call carries an agent, so this stays theoretical, but the two surfaces are not interchangeable.
 **Settled rows accumulate.** The registry retains settled tasks until owner disposal, so a long session with many background commands grows a long list. Capping the settled tail is a presentation change, not a protocol one, if it becomes a real complaint.
 **`stopping` is nearly unreachable today.** Only the model's `task_kill` produces it, so the state is rendered but rarely seen until human cancellation lands. It is in the union now because leaving a status out would have made that phase a wire change.
 **Two entry points for one running subagent.** Accepted deliberately, and bounded to one-shot background delegations. If it reads as noise in practice, the fix is presentational — the catalog row can cite the task rather than the task list hiding the kind.
 **A new non-root subpath needs its `paths` entry.** `@deepseek-ai/dsh-tasks/brand` had to be registered in `tsconfig.base.json` before the TypeRT analyzer would accept the reference. The failure mode is a confusing "not exported by" error from a generator far from the edit, so the entry is part of adding a subpath, not an optimization.
@@ -0,0 +1,136 @@
 # Agent Note: Web 后台任务展示
 Status: implemented
 [English](2026-08-08-web-background-task-display.md) | 中文
 ## 问题
 `ctx.tasks` 已经承载了 harness 在后台启动的全部长时工作——`bash`、`pwsh`、`pty-send`，以及一次性后台 subagent——但它唯一的读者是模型。[`dsh-tool-tasks`](../../../../packages/tasks/tool-tasks/README.md) 暴露了 `task_list`、`task_output` 和 `task_kill`，除此之外没有任何东西观察这个注册表。
 于是 Web 端的人类看不到构建正在跑，分不清一个任务是已经完成还是卡死，也无法把它停掉。唯一的痕迹是 transcript 里更早某处那张打印了 task id 的 `run_in_background` 工具卡片，而那张卡片此后再也不会更新。
 会话 header 本来就是每会话后台活动的落点：[`dsh-client-ui-subagent`](../../../../packages/client/ui-subagent/README.md) 把 subagent 目录贡献到 `conversation.session.header.actions`。位置没有争议。缺的是任何一条把任务状态送到浏览器的通道。
 ## 决策
 任务状态以**每会话一帧的整份快照**到达浏览器，在注册表每一个会改变该会话可见内容的提交点推出。客户端保持一份 last-wins 镜像，由一个 header 入口渲染。没有 RPC，没有轮询，客户端不需要任何过期状态管理。
 本次只交付列表。每个任务的流式输出与人类发起的中断是各自独立的阶段，而通道的形状让两者都不必推翻它。
 ### 线路形状
 mux 流中的一帧：
 ```ts ignore-check
 | { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] }
 ```
 `TaskView` 是浏览器安全类型，由载体在 [`packages/host/apiproxy/src/api/tasks.ts`](../../../../packages/host/apiproxy/src/api/tasks.ts) 里拥有，与其他领域契约并列，线路 schema 就在旁边的 `tasks.schema.ts`：
 ```ts
 import type { TaskId } from '@deepseek-ai/dsh-tasks/brand'
 export interface TaskView {
  id: TaskId
  kind: string
  label: string
  status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed'
  detail?: string
  startedAt: number
  finishedAt?: number
 }
 ```
 `TaskId` 取自不依赖 cordis 的 [`@deepseek-ai/dsh-tasks/brand`](../../../../packages/tasks/tasks/src/brand.ts) 叶子——与 `api/subagents.ts` 已经在用的 `@deepseek-ai/dsh-llm/brand` 导入是同一种安排，因为 `dsh-tasks` 根出口会牵到 `dsh-agent`，即便只作类型也无法被客户端程序触及。和本仓库其他每一个非根子路径一样，它带有显式的 `tsconfig.base.json` `paths` 条目；没有这一条，TypeRT 分析器会把该 specifier 解析到 `lib/types/` 并判定该引用未被导出。
 线路上的 `kind` 是 `string` 而非 `TaskKind`。kind 映射由生产者插件按声明合并扩展，客户端构建无法枚举这个闭集；遇到无法识别的 kind，呈现层走一条有文档的默认分支。
 `TaskSnapshot` 的三个字段被刻意省去：`ownerSession`（帧的 `sessionId` 已经带了）、`reported`（内部的通知投递位，对用户无意义），以及 `outputLimitBytes`（生产者拥有的模型呈现策略）。
 这一帧带整份快照而非增量，理由就是 [`session/queue`](../../../../packages/host/apiproxy/src/api/events.ts) 为自己写下的那条：启动、中断、结算、重连，以及第二个浏览器标签页，全都通过同一个权威值收敛。一个会话的任务集是个位数，帧很小。
 ### 任务注册表变更订阅
 `TaskService` 拥有一个观察方法：
 ```ts ignore-check
 abstract onTasksChanged(listener: TasksChangedListener): () => void
 ```
 它在每一个会改变 `list(owner)` 返回内容的提交点**之后**触发：`start()` 末尾的注册、`kill()` 里转入 `stopping`、结算，以及 `disposeOwner()` 执行的移除。`owner` 为 `undefined` 表示一个无主任务发生了变化，因而每一个调用方的视图都变了。
 监听器按 owner 而非按任务分粒度。唯一的消费方推的是整份快照，逐任务记录到手即弃——而且逐任务的订阅根本无法表达 owner 销毁时的移除，除非发明一个别处都不需要的墓碑状态。
 `onTaskDone` 不是它的子集。后者按 first-wins 语义投递终态记录和确切的 owner `Agent`，`dsh-tool-tasks` 把这套语义与 `reported` 绑在一起；`onTasksChanged` 是纯观察，不含任何投递含义，也不把任何东西标为已上报。监听器抛错被包住且从不 await，与 `onTaskDone` 一致，每次注册都是调用方 fiber 上的 effect。
 服务销毁刻意什么都不通告。每个 `onTasksChanged` 注册都是注册表自身 fiber 上的 effect，等到 teardown 清空 store 时监听器早已消失；观察者通过自己的销毁而不是一份最终空集来得知注册表离开了。
 ### api-proxy 载体
 `mux()` 订阅 `ctx.tasks.onTasksChanged` 并推送 `session/tasks`；订阅 baseline 紧挨着既有的 `session/subscribed` 控制帧发出，让重连的客户端在渲染前就是最新的。
 载体守着四条规则：
 - **绝不 resume。** 变更推送用监听器给出的确切 `Agent` 调 `tasks.list(owner)`，即使该 owner 的 scope 正在拆除、按 id 查找已经查不到，它依然正确。baseline 则读 `ctx.tasks.list(ctx.agents.get(session.id))`——不触发 resume 的注册表读法，没有活体 Agent 的会话正确地只得到无主任务。两条路径都不碰 [`api-remotes` 的 Agent 解析器](../../../../packages/api/remotes/src/agent-lookup.ts)，那个解析器会把查询变成复活冷会话的副作用；列个任务不该让用户随手划过的会话活过来。
 - **无主变更要扇出。** `owner` 为 `undefined` 时向每一个已订阅会话推一份新快照，因为无主任务对所有调用方可见。
 - **保持可选。** 载体读 `ctx.get('tasks')`。没有挂注册表的组合不发任何帧，客户端也就不渲染入口——`sessionProjections` 在这个文件里已经是这个姿态。
 - **没有就不说。** baseline 只为列表非空的会话推送，客户端上键缺失即表示空列表。把列表清空的那次变更仍然推 `[]`，因为这一个转换是客户端唯一无法从「缺失」推断出来的东西。
 ### 客户端镜像
 `SessionListState` 带有 `tasksBySession: Readonly<Record<SessionId, readonly TaskView[]>>`，由 `SessionManager` 拥有，按 last-wins 从帧折叠而来；被清空的集合存为缺失的键，使「缺失」与 `[]` 成为同一种表示。
 它放在列表镜像而不是 `Session` 上，有三个理由：header 入口本来就通过 `useSessions` 读列表状态；没有任何东西需要 `session/queue` 那种实例化前的缓冲（没有 composer 行为依赖任务）；将来侧栏加指示器时不必再开第二条通道。
 两处清理让它保持诚实。重新订阅时 manager 丢弃该会话的镜像——`session/queue` 已经遵循的规则，因为新的 baseline 正在路上，而这一世代对空集不发 baseline，被留下的列表会变成幽灵。`host/session-removed` 时再丢一次：owner 销毁在注册表侧已经移除了记录，但那件事落在 mux 流上而这一帧走 host 流，两者没有相对顺序。
 ### header 入口
 [`@deepseek-ai/dsh-client-ui-task`](../../../../packages/client/ui-task/README.md) 在 `conversation.session.header.actions` 注册一个条目，排在 subagent 目录之后。呈现契约归它自己的 README；值得记在这里的决策是：会话没有任务时控件根本不渲染；活跃角标为零时省略，让只剩历史的会话保留一个安静的入口；终态行保持可见，因为失败任务的 `detail` 是其失败唯一可读之处。
 因此一个运行中的一次性后台 subagent 会同时出现在那里和 subagent 目录里。两者回答不同的问题——目录负责进入子会话的 transcript，而这个列表是中断能力唯一可能附着的句柄——在这里屏蔽 `kind: 'subagent'` 会让中断那一期恰好对这批任务没有入口。
 ### 刻意不做的事
 **没有任何 Web 路径调用 `ctx.tasks.read()`。** 它消费唯一的输出游标，浏览器读一次就悄悄拿走了模型 `task_output` 永远看不到的字节。这该是一条有测试兜底的不变量而不是一条约定，因为它的故障在调用点完全不可见。
 **不做中断。** 那一期欠一个 seam 目前没有回答的决策：`kill()` 会把终态投递标为已上报，所以照今天的契约写出来的人类中断，会让模型一直以为它的任务还在跑。
 **帧上不带输出水位。** 输出那一期的增量通道才是锚点字段该出现的地方；现在加就是一个没有读者的字段。
 ## 备选方案
 **信号帧加 RPC 拉取，即 subagent 目录的形状。** 推一个无 payload 的 `tasks-changed` 信号，防抖后用一元 RPC 重读权威状态。subagent 目录就是这么做的，代价在 [`SessionManager`](../../../../packages/client/runtime/src/client/sessions/manager.ts) 里一览无余：`catalogInflight` 做单飞行、`catalogStale` 在成员帧落于请求中途时补一次尾拉、`updateCatalogActivity` 既就地打补丁又往在途请求里写一份好让比帧更旧的响应被覆盖、`parentAvailableOverride` 重放一个过期的 `false`，还有重连时逐一重拉每个打开的目录。这套装置之所以存在，是因为目录的权威被劈成两半——持久血缘来自投影，活跃度是响应时刻的采样——而任务没有持久的那一半，不该继承这份复杂度。它还恰好在输出那一期最在意的时刻失效：任务结算，输出流立即关闭，状态却要等防抖加一次往返才到，那段窗口里 UI 显示一个流已死的运行中任务。
 **只在弹层打开时轮询，不改 seam。** 最省事，也是唯一不碰 `TaskService` 的选项。它无法在不常驻轮询的前提下支持触发器上的常驻计数，而后面两期反正都需要一条真正的变更订阅，所以它省下一周又还回去。
 **基于持久任务事件的 session-projection 单元。** 投影单元在已提交的会话事件上折叠，所以这条路要先让任务生命周期变持久——`task/started` … `task/settled` 作为一对独立的开合括号，由最后一个 [`session/end-seed`](../../../../packages/core/session/src/types.ts) 把未配对的开括号标为死历史，与 compaction 括号已有的做法完全一致。它在客户端确实更省：`dsh-tool-todo` 用十五行的单元展示了整套模式，而现成的 `session/projection` 帧、history-tail 块和持久化 checkpoint 缓存本可以承载这批数据，无需新线路面、无需载体订阅、无需 manager 状态。否决它，是因为这要拿一次持久格式变更去换一个浏览器列表，而且它并不能延伸到最需要它的那一期：[`spill/`](../../../../packages/spill/README.md) 的存在正是为了让超大工具输出留在日志之外，所以流式任务输出无论如何都不能骑在持久事件上。如果持久任务历史将来凭自身价值站得住，本设计不阻挡重新考虑它。
 **复用 `dsh-tool-tasks` 的 `PublicTaskSnapshot`。** 字段几乎就是对的，但它属于面向模型的控制面。浏览器程序从一个 tool 包导入线路类型，会把客户端呈现耦合到面向 prompt 的决策上，并把一个 host-only 包拖进客户端构建。
 **并进 subagent 目录做成统一的「活动」面板。** 一个入口而不是两个。否决的理由是 `SubagentCatalogAction` 已经 605 行，其主题是含已结束子会话的持久会话血缘树；进程域的任务是第二套数据模型，身份、生命期和可用动作都不同，而目录的懒展开分支、时长与 token 契约全都要重写才能容纳它们。
 **跨全部会话的 host 全局任务列表。**「显示所有运行中任务」的字面读法。否决是因为注册表的鉴权围栏是按 owner 会话的，全局读需要一条新的访问规则，而且全局列表不该出现在某个会话的 header 里——它需要侧栏里自己的位置。本设计没有阻挡后续再加；按会话的帧就是同一批数据。
 ## 测试
 [web e2e 场景](../../../../apps/web/tests/background-task-list.e2e.ts)是端到端的证据，且无需密钥：一次真实的 `run_in_background` bash 调用注册进 `ctx.tasks`，header 的计数与行在没有任何用户操作的情况下出现，通过注册表杀掉该任务后打开着的列表翻到生产者给出的 detail。它断言的是整条投递链路，而不是其中某一层。
 在它之下，[`tasks-local`](../../../../packages/tasks/tasks-local/tests/tasks.spec.ts) 钉住变更订阅的全部四个提交点、对抛错观察者的包容，以及显式销毁与 fiber 拆除两条路径上的注销；[`api-proxy-tasks`](../../../../packages/host/apiproxy/tests/api-proxy-tasks.spec.ts) 钉住「非空才发 baseline」、三次变更推送、被丢弃的内部字段、无主扇出、不 resume 的保证，以及没有注册表的组合；客户端各套件钉住 last-wins 折叠、缺失键表示、两处清理，以及组件的排序、时长与关闭行为。
 ## 影响
 **漏掉一个提交点会漏行。** 如果 `disposeOwner()` 的移除有朝一日不再触发订阅，客户端会一直留着已经不存在的任务，直到会话消失。整份快照的形状让这件事可恢复而非损坏——下一次正当变更就修好了——但销毁路径是最容易被忘掉的一条，所以它自带测试。
 **无主任务的扇出很容易做漏。** 只推给变更 owner 所在的会话，对有主任务是对的，对处处可见的无主任务则是悄悄错的。这个 bug 只会在会创建无主任务的组合里显形，所以载体套件直接覆盖了它。
 **UI 的集合不等于注册表的集合。** 无主任务在 header 里不可见，而 `task_list` 仍会把它报告给模型。实践中每次工具调用都带着 agent，所以这停留在理论层面，但两个界面并不可互换。
 **终态行会堆积。** 注册表把已结算任务留到 owner 销毁，所以一个跑了很多后台命令的长会话会积出长列表。如果真的成为抱怨，给终态尾巴加上限是呈现层改动而非协议改动。
 **`stopping` 今天几乎不可达。** 只有模型的 `task_kill` 会产生它，所以这个状态会被渲染但在人类中断落地之前很少见到。现在就纳入联合类型，是因为把它留在外面会让那一期变成一次线路变更。
 **一个运行中的 subagent 有两个入口。** 这是刻意接受的，且被限制在一次性后台委派这一种情况。如果实际用起来读着像噪声，修法是呈现层的——可以让目录行引用那个任务，而不是让任务列表隐藏这个 kind。
 **新增非根子路径必须补 `paths` 条目。** `@deepseek-ai/dsh-tasks/brand` 得先登记进 `tsconfig.base.json`，TypeRT 分析器才会接受该引用。它的故障表现是一条来自远离改动处的生成器的、令人困惑的「not exported by」错误，所以这个条目是新增子路径的组成部分，而不是优化。
@@ -0,0 +1,130 @@
 // Web e2e scenario: the session-header background-task list over the real
 // host. No model call is involved — a genuine `run_in_background` bash call
 // registers with `ctx.tasks`, and the assertion chain is the whole delivery
 // path: registry change feed → api-proxy `session/tasks` frame → the client's
 // `tasksBySession` mirror → the header action.
 import { readFile } from 'node:fs/promises'
 import { fileURLToPath } from 'node:url'
 import { join } from 'node:path'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { CallId } from '@deepseek-ai/dsh-llm'
 import { SessionId } from '@deepseek-ai/dsh-session'
 import { TaskId } from '@deepseek-ai/dsh-tasks'
 import {
  assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
  launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
 import { newEnglishPage, saveFailureShot } from './support.ts'
 const FIXTURE = fileURLToPath(new URL('./snapshots/fresh-round-trip/session.jsonl', import.meta.url))
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/background-task-list', import.meta.url))
 const RUNNING_EXPECTED = join(SNAPSHOT_DIR, 'running.expected.md')
 const SETTLED_EXPECTED = join(SNAPSHOT_DIR, 'settled.expected.md')
 const MODE = webSnapshotMode()
 const SEED_ID = 'background-task-list-web-e2e'
 // Long enough that the running assertions never race the process exiting on
 // their own; the test kills it explicitly to reach the settled state.
 const COMMAND = 'sleep 45'
 /**
 * Wait for the Host to publish the live Agent that opening a session resumes.
 * @param scaffold - the booted web scaffold.
 * @param sessionId - the opened session's identity.
 * @returns the registered Agent instance.
 */
 async function liveAgent(scaffold: WebScaffold, sessionId: SessionId): Promise<Agent> {
  const deadline = Date.now() + 30_000
  for (;;) {
    const found = scaffold.ctx.agents.get(sessionId)
    if (found !== undefined) return found
    if (Date.now() > deadline) throw new Error(`opening session "${sessionId}" published no live Agent`)
    await new Promise(resolve => setTimeout(resolve, 100))
  }
 }
 describe.skipIf(MODE === 'record')('web e2e: background task list', () => {
  let scaffold: WebScaffold
  let browser: Browser
  let page: Page
  let tripwire: ReturnType<typeof watchConsole>
  let agent: Agent
  let taskId: TaskId
  beforeAll(async () => {
    scaffold = await launchWebScaffold({})
    await seedSession(scaffold, await readFile(FIXTURE, 'utf8'), SEED_ID)
    browser = await chromium.launch()
    page = await newEnglishPage(browser)
    tripwire = watchConsole(page)
    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
    const groupRow = page.locator('[role="treeitem"]').first()
    await groupRow.waitFor({ timeout: 15_000 })
    await groupRow.click()
    const sessionRow = page.locator('[role="treeitem"]').nth(1)
    await sessionRow.waitFor({ timeout: 10_000 })
    await sessionRow.click()
    // Opening the session drives the Host's ordinary Agent resolution; the
    // task owner must be that exact live instance, never a second one.
    // `expect.poll` is test-scoped, so this hook polls by hand.
    agent = await liveAgent(scaffold, SessionId(SEED_ID))
  }, 120_000)
  afterAll(async () => {
    await browser?.close()
    await scaffold?.close()
  })
  it('shows a running background task in the session header without a refresh', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-background-task-running'))
    const trigger = page.getByRole('button', { name: '1 background task running' })
    await expect.poll(() => trigger.count(), { timeout: 5_000 }).toBe(0)
    const started = await scaffold.ctx.tools.execute({
      signal: new AbortController().signal,
      callId: CallId('background-task-list-e2e'),
      name: 'bash',
      arguments: { command: COMMAND, description: 'Hold a background slot open', run_in_background: true },
      agent,
    })
    const reported = started.content.map(block => block.type === 'text' ? block.text : '').join('')
    const matched = /\bbash-\d+\b/.exec(reported)
    if (matched === null) throw new Error(`background bash reported no task id: ${reported}`)
    taskId = TaskId(matched[0])
    await trigger.waitFor({ timeout: 15_000 })
    await trigger.click()
    const row = page.getByRole('list', { name: 'Background tasks' }).getByRole('listitem').first()
    await row.waitFor({ timeout: 10_000 })
    await expect.poll(() => row.textContent()).toContain(COMMAND)
    const snapshot = await captureStableAria(page, '[class*="menu"]', scaffold.workspaceCwd)
    await compareOrRefreshGolden(RUNNING_EXPECTED, snapshot, MODE)
    expect(tripwire.pageErrors).toEqual([])
    expect(tripwire.warnings).toEqual([])
  }, 60_000)
  it('flips the open list to the cancelled outcome when the registry settles it', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-background-task-settled'))
    expect(scaffold.ctx.tasks.kill(taskId, agent, 'web e2e cancellation')).toBe('requested')
    // The trigger drops its live count once the task leaves running/stopping,
    // which is also the proof that settlement reached the browser unprompted.
    const idle = page.getByRole('button', { name: '1 background task' })
    await idle.waitFor({ timeout: 20_000 })
    const snapshot = await captureStableAria(page, '[class*="menu"]', scaffold.workspaceCwd)
    await compareOrRefreshGolden(SETTLED_EXPECTED, snapshot, MODE)
    expect(tripwire.pageErrors).toEqual([])
    expect(tripwire.warnings).toEqual([])
  }, 60_000)
  it('keeps its snapshot inventory closed', async () => {
    await assertFixtureInventory(SNAPSHOT_DIR, ['running.expected.md', 'settled.expected.md'])
  })
 })
@@ -0,0 +1,2 @@
 - list "Background tasks":
  - listitem: bash sleep 45 running {{duration}}
@@ -0,0 +1,2 @@
 - list "Background tasks":
  - listitem: "bash sleep 45 signal: SIGTERM {{duration}}"
@@ -67,6 +67,7 @@
    "tests/goal-bar.e2e.ts",
    "tests/subagent-conversation.e2e.ts",
    "tests/sidebar-subagent-activity.e2e.ts",
    "tests/background-task-list.e2e.ts",
    "tests/bash-abort-row.e2e.ts",
    "tests/skill-tool-row.e2e.ts",
    "tests/turn-tail-actions.e2e.ts",
@@ -2565,6 +2565,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co
 - `@deepseek-ai/dsh-client-ui-skill` ([`packages/client/ui-skill/src/index.ts`](../packages/client/ui-skill/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-slash` ([`packages/client/ui-slash/src/index.ts`](../packages/client/ui-slash/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-subagent` ([`packages/client/ui-subagent/src/index.ts`](../packages/client/ui-subagent/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-task` ([`packages/client/ui-task/src/index.ts`](../packages/client/ui-task/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-tool` ([`packages/client/ui-tool/src/index.ts`](../packages/client/ui-tool/src/index.ts))
 - `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts))
@@ -2338,6 +2338,22 @@ abstract wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSigna
 */
 abstract onTaskDone(listener: TaskDoneListener): () => void
 /**
 * Register an effect-scoped observer of visible-set changes. It fires after
 * every commit that changes what {@link list} returns for that owner —
 * registration, the stopping transition, settlement, and owner-disposal
 * removal — so an observer re-reads rather than accumulating deltas.
 *
 * This is not a superset of {@link onTaskDone}: that one delivers the terminal
 * record under first-wins semantics a control surface couples to notice
 * delivery, while this one carries no delivery meaning and marks nothing
 * reported. Listeners are contained and never awaited.
 * @param listener - receives the owner whose visible set changed, or
 *   `undefined` when an unowned task changed and every caller's set did.
 * @returns disposer that unregisters the listener.
 */
 abstract onTasksChanged(listener: TasksChangedListener): () => void
 /**
 * Attach an effect-scoped surface that can read and stop tasks. {@link start}
 * refuses work while none is attached.
@@ -2347,9 +2363,9 @@ abstract onTaskDone(listener: TaskDoneListener): () => void
 abstract attachSurface(name: string): () => void
 ```
-Types: [Agent](../core-data-structures/core.md) · [TaskDoneListener](../core-data-structures/tasks.md) · [TaskId](../core-data-structures/tasks.md) · [TaskRead](../core-data-structures/tasks.md) · [TaskSnapshot](../core-data-structures/tasks.md) · [TaskStart](../core-data-structures/tasks.md)
+Types: [Agent](../core-data-structures/core.md) · [TaskDoneListener](../core-data-structures/tasks.md) · [TaskId](../core-data-structures/tasks.md) · [TaskRead](../core-data-structures/tasks.md) · [TaskSnapshot](../core-data-structures/tasks.md) · [TaskStart](../core-data-structures/tasks.md) · [TasksChangedListener](../core-data-structures/tasks.md)
-Source: [`packages/tasks/tasks/src/index.ts:50`](../../packages/tasks/tasks/src/index.ts)
+Source: [`packages/tasks/tasks/src/index.ts:53`](../../packages/tasks/tasks/src/index.ts)
 ## `ctx.telemetry` — `Telemetry` (abstract seam)
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write docs/core-data-structures/tasks.md
-tasks.md: a38055d3ef7aa18e62678f92eb5ac5ae2a09c205
+tasks.md: e07fa4798d9d7585fd1036346f8df39068884835
-tasks.zh.md: f34d42e713c3a0c11cbf88d52e573bb100c52493
+tasks.zh.md: d958be308f462db371d10240cfa369a892fe1ce0
@@ -151,4 +151,4 @@ interface TaskRead {
 ## Service behavior
-The abstract [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam defines atomic `start`, caller-scoped `get` and `list`, `read`, `kill`, bounded `wait`, contained `onTaskDone` listeners, and the `attachSurface` availability fence; [`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) is the process-local implementation. Authorization compares owner sessions; owner cleanup selects the exact registered `Agent` instance. See [`dsh-tasks`](../../packages/tasks/tasks/README.md) for the seam contract, [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md) for the registry lifecycle, and [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md) for the model-facing surface.
+The abstract [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam defines atomic `start`, caller-scoped `get` and `list`, `read`, `kill`, bounded `wait`, contained `onTaskDone` and `onTasksChanged` listeners, and the `attachSurface` availability fence; [`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) is the process-local implementation. The two listener kinds are not nested: `onTaskDone` delivers one terminal record under first-wins semantics a control surface couples to notice delivery, while `onTasksChanged` observes every visible-set change — registration, the stopping transition, settlement, and owner-disposal removal — carrying only the owner whose set moved, or `undefined` when an unowned task changed and every caller's set moved with it. Authorization compares owner sessions; owner cleanup selects the exact registered `Agent` instance. See [`dsh-tasks`](../../packages/tasks/tasks/README.md) for the seam contract, [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md) for the registry lifecycle, and [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md) for the model-facing surface.
@@ -151,4 +151,4 @@ interface TaskRead {
 ## 服务行为
-抽象的 [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam 定义原子 `start`、限定调用方作用域的 `get` 和 `list`、`read`、`kill`、有界 `wait`、故障隔离的 `onTaskDone` 监听器，以及 `attachSurface` 可用性防线；[`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) 是其进程局部实现。授权会比较拥有者会话；拥有者清理会选择确切的已注册 `Agent` 实例。seam 契约见 [`dsh-tasks`](../../packages/tasks/tasks/README.md)，注册表生命周期见 [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md)，面向模型的接口见 [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md)。
+抽象的 [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam 定义原子 `start`、限定调用方作用域的 `get` 和 `list`、`read`、`kill`、有界 `wait`、故障隔离的 `onTaskDone` 与 `onTasksChanged` 监听器，以及 `attachSurface` 可用性防线；[`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) 是其进程局部实现。两类监听器不是包含关系：`onTaskDone` 按控制面与通知投递绑定的 first-wins 语义投递唯一一条终态记录，而 `onTasksChanged` 观察每一次可见集合的变化——注册、转入 stopping、结算，以及 owner 销毁时的移除——只携带集合发生变化的那个 owner，或在无主任务变化、因而每个调用方的集合都随之变化时携带 `undefined`。授权会比较拥有者会话；拥有者清理会选择确切的已注册 `Agent` 实例。seam 契约见 [`dsh-tasks`](../../packages/tasks/tasks/README.md)，注册表生命周期见 [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md)，面向模型的接口见 [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md)。
@@ -176,6 +176,10 @@
    - id: ui-subagent
      name: '@deepseek-ai/dsh-client-ui-subagent'
    # Background tasks: the session-header list over the tasksBySession mirror.
    - id: ui-task
      name: '@deepseek-ai/dsh-client-ui-task'
    # Goal surface: GoalBar in the input dock over the goal session projection.
    - id: ui-goal
      name: '@deepseek-ai/dsh-client-ui-goal'
@@ -54,6 +54,7 @@
    "@deepseek-ai/dsh-client-ui-skill": "workspace:^",
    "@deepseek-ai/dsh-client-ui-slash": "workspace:^",
    "@deepseek-ai/dsh-client-ui-subagent": "workspace:^",
    "@deepseek-ai/dsh-client-ui-task": "workspace:^",
    "@deepseek-ai/dsh-client-ui-theme": "workspace:^",
    "@deepseek-ai/dsh-client-ui-tool": "workspace:^",
    "@deepseek-ai/dsh-client-ui-trajectory": "workspace:^",
@@ -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/README.md
-README.md: b6fa426fbe541e2b22d2bf5f19d4397361cf0899
+README.md: 347a42e0671ad0ae1da6c5488f94f387e85fcf99
-README.zh.md: 5a55bb8c2c31b5215fc73e75e1c4f3aca79add64
+README.zh.md: 596ce3910430a183a9750c94b83cb79f43ce037f
@@ -29,6 +29,7 @@ The browser side of the dsh web GUI: shell boot, browser-host communication, sha
 | [`ui-slash/`](ui-slash/README.md) | Coordinates inline command and reference suggestions. |
 | [`ui-skill/`](ui-skill/README.md) | Adds skill references to inline suggestions. |
 | [`ui-subagent/`](ui-subagent/README.md) | Provides subagent navigation, child transcript states, and inline references. |
 | [`ui-task/`](ui-task/README.md) | Lists this session's background tasks in the conversation header. |
 | [`ui-model/`](ui-model/README.md) | Provides model selection in conversation surfaces. |
 | [`ui-permission/`](ui-permission/README.md) | Configures default permissions and switches the current session's access. |
 | [`ui-plan/`](ui-plan/README.md) | Presents active plan-mode status and its exit control. |
@@ -29,6 +29,7 @@ dsh web GUI 的浏览器侧：shell 启动、浏览器与宿主通信、共享 U
 | [`ui-slash/`](ui-slash/README.md) | 协调内联命令和引用建议。 |
 | [`ui-skill/`](ui-skill/README.md) | 向内联建议添加 skill（技能）引用。 |
 | [`ui-subagent/`](ui-subagent/README.md) | 提供 subagent 导航、子会话记录状态和内联引用。 |
 | [`ui-task/`](ui-task/README.md) | 在会话标题栏列出当前会话的后台任务。 |
 | [`ui-model/`](ui-model/README.md) | 在会话界面中提供模型选择。 |
 | [`ui-permission/`](ui-permission/README.md) | 配置默认权限并切换当前会话的访问模式。 |
 | [`ui-plan/`](ui-plan/README.md) | 展示生效中的 plan mode 状态及其退出控件。 |
@@ -17,6 +17,7 @@ export type {
  SettingsApi, SettingsNamespaceView, SettingsPathOpView, SettingsSecretView,
  CredentialsApi, CredentialView, ConfigurableProviderView, DiscoveredModelView, LlmApi,
  SubagentsApi, SubagentAddress, SubagentCatalog, SubagentListEntry, SubagentPromptReceipt,
  TaskView,
 } from '@deepseek-ai/dsh-host-apiproxy/api'
 export type { ToolCallView, ToolResultView } from '@deepseek-ai/dsh-tools/presentation'
 export type {
@@ -22,6 +22,7 @@ export type {
  ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning,
  MessageId, ModelReasoningEffort, ModelTarget, QueueAction, QueuedInboxItem, SessionModels,
  SubagentsApi, SubagentAddress, SubagentCatalog, SubagentListEntry, SubagentPromptReceipt,
  TaskView,
  RpcRequest, RpcResponse, RpcResult, RpcError, RpcErrorCode,
  ClientRequest, ServerResponse, ServerRequest, ClientResponse, RpcMessage, RpcReceipt,
  IApiClient, SessionId, SessionEvent, ContentBlock, StreamChunk,
@@ -16,7 +16,7 @@ const OPTIONS = [{ id: 'zh', label: '中文' }, { id: 'en', label: 'English' }]
 /** Empty global standard-kit hooks (the row reads neither). */
 function emptySessions() {
  const store = createSnapshotStore<SessionListState>(
-    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined })
+    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined })
  return bindSnapshotSelector(store)
 }
 function emptyWorkspaces() {
@@ -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: a9b604974595b1b7856f74b72d36093491ec1bd1
+README.md: 5abe72767aa76d5690b3f287391bc8924bc62d03
-README.zh.md: 6eee14bdbe7a9fb86b0a12355e7d0a45cd500774
+README.zh.md: 78024fa095a5bcddc50ee121eec64e887f241ba7
@@ -24,6 +24,8 @@ SlotsService gives the renderer separate bare observables for `useSessions` and
 `indexSubagentDescendants()` derives per-parent total and running descendant counts from the retained list mirror. It follows only uninterrupted `origin: 'subagent'` ancestry, so an ordinary fork starts a separate ownership subtree; cycles stop without throwing, and a missing parent remains a harmless key until its summary arrives.
 `SessionListState.tasksBySession` mirrors the Host's `session/tasks` frames last-wins, keyed by session and needing no Session instance. An emptied set is stored as an absent key, so absence and `[]` are one representation and consumers never test a sentinel. Two clears keep it from outliving its truth: `session/subscribed` drops the session's mirror, because a fresh generation sends a baseline only for a non-empty set and a retained list would survive as a phantom, and `host/session-removed` drops it again, because owner disposal removed the records on the mux stream while the removal frame rides the host stream, leaving the two with no relative order.
 `SessionsService.search(query, signal)` is a stateless one-shot action over the `session.search` RPC. It returns ranked session/snippet pairs without putting query, loading, or error state into the shared Session list, so each UI owner controls debounce, cancellation, stale-response suppression, and fallback presentation. `searchResultLimit` re-exposes `SESSION_SEARCH_RESULT_LIMIT` — the bound the response schema itself enforces — as injected presentation data, so client plugins do not duplicate it. It is a protocol constant rather than per-connection state, so the connection handle does not carry it.
 ## New Session and the blank mirror
@@ -24,6 +24,8 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸
 `indexSubagentDescendants()` 从保留的列表镜像中派生每个 parent 的后代总数与运行中后代数。它只沿不间断的 `origin: 'subagent'` 祖先链追踪，因此普通 fork 会开启独立的归属子树；遇到环时，追踪会停止但不会抛出异常，缺失的 parent 则会保留为无害的键，直至其摘要到达。
 `SessionListState.tasksBySession` 按 last-wins 镜像宿主的 `session/tasks` 帧，以会话为键，不需要 Session 实例。被清空的集合存为缺失的键，因此「缺失」与 `[]` 是同一种表示，消费方永远不必检测哨兵值。两处清理让它不至于比它所反映的真相活得更久：`session/subscribed` 丢弃该会话的镜像，因为新一代只为非空集合发送 baseline，被留下的列表会变成幽灵；`host/session-removed` 再丢一次，因为 owner 销毁是在 mux 流上移除记录的，而移除帧走 host 流，两者没有相对顺序。
 `SessionsService.search(query, signal)` 是基于 `session.search` RPC 的无状态单次操作。它返回经过排序的会话／snippet 对，但不会将查询条件、加载状态或错误状态写入共享 Session 列表，因此每个 UI 所有者都自行负责防抖、取消、抑制陈旧响应和回退呈现。`searchResultLimit` 将 `SESSION_SEARCH_RESULT_LIMIT`——即响应 schema 自身强制执行的上限——作为注入的呈现数据重新公开，使客户端插件无需复制该值。它是协议常量而非逐连接状态，因此连接 handle 不携带它。
 ## New Session 与 blank 镜像
@@ -36,7 +36,7 @@ export type {
  SessionBinding, SessionListState, SessionProvideContribution, SessionProvideDescriptor, SessionSummary,
 } from './sessions/service.ts'
 export type { SessionListPhase, SessionSearchResultItem, SubagentCatalogSnapshot } from './sessions/manager.ts'
-export type { SubagentAddress } from '@deepseek-ai/dsh-client-connection/client'
+export type { SubagentAddress, TaskView } from '@deepseek-ai/dsh-client-connection/client'
 export type { WorkspaceListPhase } from './workspaces/manager.ts'
 export type { WorkspaceListState } from './workspaces/service.ts'
 export type {
@@ -4,7 +4,7 @@
 import type {
  IApiClient, HostFrame, MuxFrame, RpcError, RpcRequest, RpcResult, SessionId,
-  SessionSummary, SubagentAddress, SubagentCatalog, WorkspaceId,
+  SessionSummary, SubagentAddress, SubagentCatalog, TaskView, WorkspaceId,
 } from '@deepseek-ai/dsh-client-connection/client'
 // Value import from the inline-safe wire layer (not the connection plugin):
 // plugin-to-plugin value imports are a bundle purity error.
@@ -47,6 +47,8 @@ export interface SessionListSnapshot {
  phase: SessionListPhase
  error: RpcError | null
  subagentsByParent: Readonly<Record<SessionId, SubagentCatalogSnapshot>>
  /** Background tasks per session; an absent key is an empty set. */
  tasksBySession: Readonly<Record<SessionId, readonly TaskView[]>>
  currentAddress: SubagentAddress | undefined
 }
@@ -137,6 +139,11 @@ export class SessionManager {
  private readonly catalogStale = new Set<SessionId>()
  private readonly openCatalogs = new Set<SessionId>()
  private readonly catalogDebounce = new Map<SessionId, ReturnType<typeof setTimeout>>()
  /**
   * Background tasks per session, last-wins from `session/tasks`. An empty set
   * is stored as an absent key, so absence and `[]` are one representation.
   */
  private readonly tasksBySession = new Map<SessionId, readonly TaskView[]>()
  private selected: SessionId | undefined
@@ -657,10 +664,23 @@ export class SessionManager {
      this.notifier.markDirty()
      return
    }
    if (frame.type === 'session/tasks') {
      // Whole-set snapshot, so last-wins with no reconciliation. The Host omits
      // the baseline for an empty set, which is the same fact an emptying change
      // reports as `[]` — both land as an absent key.
      if (frame.tasks.length === 0) this.tasksBySession.delete(frame.sessionId)
      else this.tasksBySession.set(frame.sessionId, frame.tasks)
      this.notifier.markDirty()
      return
    }
    if (frame.type === 'session/subscribed') {
      // Rows past the host's durable baseline rode state a restart lost; drop
      // them so last-wins cannot pin a phantom value over recomputed truth.
      this.projectionStores.get(frame.sessionId)?.truncate(frame.lastSeq)
      // Same re-baseline reasoning as the queue below: this generation sends a
      // task baseline only when the set is non-empty, so a mirror kept from the
      // previous generation would survive as a phantom list.
      this.tasksBySession.delete(frame.sessionId)
      this.notifier.markDirty()
      // New mux-generation baseline: discard the previous queue snapshot.
      // The host omits session/queue when the live queue is empty, so retaining
@@ -770,6 +790,11 @@ export class SessionManager {
        }
        this.pendingBuffers.delete(frame.sessionId) // a removed session's buffered frames must not replay on a future instantiation
        this.pendingInteractions.delete(frame.sessionId) // a removed session cannot wait on anyone
        // Owner disposal already dropped these registry-side, but that lands on
        // the mux stream while this frame rides the host stream, so the two have
        // no relative order. Clearing here makes a detached Activation's rows
        // disappear whichever arrives first.
        this.tasksBySession.delete(frame.sessionId)
        if (!durableSubagent) this.projectionStores.delete(frame.sessionId)
        // A pull already in flight was requested before this removal and can
        // carry the pre-removal parentAvailable:true, which would resurrect
@@ -1006,6 +1031,7 @@ export class SessionManager {
      phase: this.listPhase,
      error: this.listError,
      subagentsByParent: Object.fromEntries(this.catalogs),
      tasksBySession: Object.fromEntries(this.tasksBySession),
      currentAddress: current === undefined ? undefined : this.addresses.get(current),
    }
  }
@@ -17,7 +17,7 @@
 */
 import type { Context, Fiber } from 'cordis'
 import type {
-  IApiClient, RpcError, RpcResult, SessionId, SubagentAddress, WorkspaceId,
+  IApiClient, RpcError, RpcResult, SessionId, SubagentAddress, TaskView, WorkspaceId,
 } from '@deepseek-ai/dsh-client-connection/client'
 // Value import from the inline-safe wire layer (not the connection plugin):
 // plugin-to-plugin value imports are a bundle purity error.
@@ -80,6 +80,12 @@ export interface SessionListState {
  phase: SessionListPhase
  /** Direct durable catalogs keyed by their selected parent address. */
  subagentsByParent: Readonly<Record<SessionId, SubagentCatalogSnapshot>>
  /**
   * Background tasks each session can see, mirrored last-wins from
   * `session/tasks`. A missing key is an empty set — the Host sends no baseline
   * for a session without tasks — so consumers read absence, never a sentinel.
   */
  tasksBySession: Readonly<Record<SessionId, readonly TaskView[]>>
  /** Current session's catalog-derived address, absent on ordinary navigation. */
  currentAddress: SubagentAddress | undefined
 }
@@ -271,7 +277,7 @@ export class SessionsService implements ISessions {
    this.manager = new SessionManager(api, restored.sessionId, restored.subagentAddress)
    this.list = createSnapshotStore<SessionListState>({
      ids: [], byId: {}, current: undefined, phase: 'pending',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })
    // The manager owns wire truth; the store is its projection. Manager
    // notifications are already microtask-batched.
@@ -606,7 +612,7 @@ export class SessionsService implements ISessions {
  /** Project the manager's list snapshot into the store (title derivation is display-only). */
  private projectList(): void {
    const {
-      items, current, phase, subagentsByParent, currentAddress,
+      items, current, phase, subagentsByParent, tasksBySession, currentAddress,
    } = this.manager.getListSnapshot()
    const ids: SessionId[] = []
    const byId: Record<SessionId, SessionSummary> = {}
@@ -675,7 +681,7 @@ export class SessionsService implements ISessions {
        ...(currentAddress === undefined ? {} : { subagentAddress: currentAddress }),
      })
    }
-    this.list.set({ ids, byId, current, phase, subagentsByParent, currentAddress })
+    this.list.set({ ids, byId, current, phase, subagentsByParent, tasksBySession, currentAddress })
    this.pruneScopes()
  }
@@ -1110,3 +1110,60 @@ describe('completed reminder', () => {
    expect(entry(manager, S2)?.completed).toBe(true)
  })
 })
 describe('background-task mirror', () => {
  const view = (over: Partial<{ id: string; status: string; label: string }> = {}) => ({
    id: 'bash-1', kind: 'bash', label: 'pnpm run build', status: 'running', startedAt: 5, ...over,
  })
  const tasksFrame = (sessionId: SessionId, tasks: unknown[]) =>
    ({ rpcId: 't' as never, payload: { type: 'session/tasks', sessionId, tasks } as never })
  it('mirrors the whole set last-wins, keyed per session, with no Session instance needed', () => {
    const manager = new SessionManager(new FakeApiClient())
    manager.handleMuxEnvelope(tasksFrame(S1, [view()]))
    manager.handleMuxEnvelope(tasksFrame(S2, [view({ id: 'pwsh-1', label: 'other' })]))
    const first = manager.getListSnapshot().tasksBySession
    expect(first[S1]).toEqual([view()])
    expect(first[S2]?.[0]?.label).toBe('other')
    // Last-wins: the newer whole set replaces, it does not merge.
    manager.handleMuxEnvelope(tasksFrame(S1, [view({ status: 'completed' })]))
    expect(manager.getListSnapshot().tasksBySession[S1]).toEqual([view({ status: 'completed' })])
  })
  it('stores an emptied set as an absent key so absence and [] read alike', () => {
    const manager = new SessionManager(new FakeApiClient())
    manager.handleMuxEnvelope(tasksFrame(S1, [view()]))
    expect(S1 in manager.getListSnapshot().tasksBySession).toBe(true)
    manager.handleMuxEnvelope(tasksFrame(S1, []))
    expect(S1 in manager.getListSnapshot().tasksBySession).toBe(false)
  })
  it('clears the mirror on re-subscribe, because a task-free generation sends no baseline', () => {
    const manager = new SessionManager(new FakeApiClient())
    manager.handleMuxEnvelope(tasksFrame(S1, [view()]))
    manager.handleMuxEnvelope({
      rpcId: 's' as never,
      payload: { type: 'session/subscribed', sessionId: S1, lastSeq: 3 },
    })
    expect(S1 in manager.getListSnapshot().tasksBySession).toBe(false)
  })
  it('drops the rows when the session is removed, whichever stream lands first', () => {
    const manager = new SessionManager(new FakeApiClient())
    manager.handleHostEnvelope({ rpcId: 'a' as never, payload: { type: 'host/session-added', blank: true, sessionId: S1 } })
    manager.handleMuxEnvelope(tasksFrame(S1, [view()]))
    manager.handleHostEnvelope({ rpcId: 'r' as never, payload: { type: 'host/session-removed', sessionId: S1 } })
    expect(S1 in manager.getListSnapshot().tasksBySession).toBe(false)
  })
  it('notifies list subscribers so an open header re-renders without a poll', async () => {
    const manager = new SessionManager(new FakeApiClient())
    const seen = vi.fn()
    manager.subscribe(seen)
    manager.handleMuxEnvelope(tasksFrame(S1, [view()]))
    // The notifier batches on a microtask; the frame itself is already applied.
    await Promise.resolve()
    expect(seen).toHaveBeenCalled()
  })
 })
@@ -192,7 +192,7 @@ export class TestSessions implements ISessions {
  constructor(private readonly stabilize: Stabilizer, private readonly rootCtx: Context) {
    this.list = createSnapshotStore<SessionListState>({
      ids: [], byId: {}, current: undefined, phase: 'ready',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })
    this.channel = new SessionProvideChannel({
      rebuildBundles: () => {
@@ -110,7 +110,7 @@ const compaction = (over: Partial<CompactionSummaryNode> = {}): CompactionSummar
 /** Empty sessions-list hook for the global standard-kit seat. */
 function emptySessions() {
  const store = createSnapshotStore<SessionListState>(
-    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined })
+    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined })
  return bindSnapshotSelector(store)
 }
@@ -16,7 +16,7 @@ afterEach(() => {
 function emptySessions() {
  return bindSnapshotSelector(createSnapshotStore<SessionListState>({
-    ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined,
+    ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
  }))
 }
@@ -100,7 +100,7 @@ describe('render branch tails', () => {
    const chat = createChatStore().create()
    chat.actions.select({ turnSeq: 1, callId: 'ghost' } satisfies SelectionTarget)
    const emptyList = createSnapshotStore<SessionListState>(
-      { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined })
+      { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined })
    const emptyWorkspaces = createSnapshotStore<WorkspaceListState>({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
      baselinesReady: true, recentWorkspaceId: undefined,
@@ -149,7 +149,7 @@ describe('render branch tails', () => {
    const chat = createChatStore().create()
    chat.actions.select({ turnSeq: 9, callId: 'p1:code:1:code:1', toolName: 'read' } satisfies SelectionTarget)
    const emptyList = createSnapshotStore<SessionListState>(
-      { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined })
+      { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined })
    const emptyWorkspaces = createSnapshotStore<WorkspaceListState>({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
      baselinesReady: true, recentWorkspaceId: undefined,
@@ -109,7 +109,7 @@ function bench(over?: BenchOptions) {
    useSession: bindSnapshotSelector(session),
    useSessions: bindSnapshotSelector(createSnapshotStore({
      ids: [], byId: {}, current: undefined, phase: 'ready',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })),
    useWorkspaces: bindSnapshotSelector(createSnapshotStore({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
@@ -37,7 +37,7 @@ function mountBar(shell: SessionInputShell, over?: { running?: boolean; disabled
    useSession: bindSnapshotSelector(session),
    useSessions: bindSnapshotSelector(createSnapshotStore({
      ids: [], byId: {}, current: undefined, phase: 'ready',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })),
    useWorkspaces: bindSnapshotSelector(createSnapshotStore({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
@@ -123,7 +123,7 @@ async function scopedBench(register?: (slash: SlashService) => void) {
    useSession: bindSnapshotSelector(sessionStore),
    useSessions: bindSnapshotSelector(createSnapshotStore({
      ids: [], byId: {}, current: undefined, phase: 'ready',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })),
    useWorkspaces: bindSnapshotSelector(createSnapshotStore({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
@@ -107,7 +107,7 @@ function mount(
    ids: listed ? [root, SID] : [root],
    byId: { [root]: rootRow, ...listed && { [SID]: childRow } },
    current: SID,
-    phase: 'ready', subagentsByParent: {}, currentAddress: undefined,
+    phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
  })
  const workspaces = createSnapshotStore<WorkspaceListState>(workspaceState(workspaceRows))
  const session = createSnapshotStore<ConversationSnapshot>(snapshot)
@@ -61,6 +61,7 @@ function props(
    },
    current: PARENT, phase: 'ready',
    subagentsByParent: value === undefined ? nested : { [PARENT]: value, ...nested },
    tasksBySession: {},
    currentAddress: undefined,
  } satisfies SessionListState
  function useSessions<T>(select: (snapshot: SessionListState) => T): T {
@@ -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 packages/client/ui-task/README.md
 README.md: 318984808838cb7a336a4c34c95a2f27db578423
 README.zh.md: 7adeb254662fd23cf4bd1efc8618471cf74df7c0
@@ -0,0 +1,24 @@
 # @deepseek-ai/dsh-client-ui-task
 English | [中文](README.zh.md)
 Web background-task feature owner: contributes one entry to `conversation.session.header.actions` listing the `ctx.tasks` records this session can see. The data arrives entirely through the `tasksBySession` list mirror that [`dsh-client-runtime`](../runtime/README.md) folds from `session/tasks` frames, so this package issues no RPC and holds no state beyond popover visibility.
 The trigger renders only when the session has at least one task, so an ordinary conversation never grows a control for a capability it is not using. Its badge counts `running` plus `stopping` and is omitted at zero, leaving a session that holds only finished tasks a quiet entry point into its history rather than one advertising a count of nothing. The popover is a flat list: live rows first by `startedAt` ascending, then settled rows by `finishedAt` descending, with a same-millisecond tie broken on start order so the host's map iteration never decides it. A row shows the producer kind, the label, a status marker, the producer's `detail` in place of the generic status word once it has one, and an elapsed duration. That duration advances once per second while the row is live and freezes at `finishedAt`; the clock runs only while an open list holds something that moves. A settled row missing `finishedAt` reads as zero rather than as a negative figure, and a duration past an hour stays in hours rather than growing a day vocabulary no producer currently reaches.
 Settled rows stay visible and de-emphasized until the registry drops them at owner disposal. They are in the snapshot, a failed task's `detail` is the only place its failure is legible, and filtering them out here is work the output and cancellation phases would undo. A running one-shot background subagent therefore appears both here and in the [subagent catalog](../ui-subagent/README.md): the catalog navigates into the child's transcript, while this list is the only handle a future cancellation can attach to.
 Escape closes the list and returns focus to the trigger, as does a pointer press outside it. The last task disappearing closes the list before the control unmounts, so focus never vanishes from a removed node. Styling uses tokens only; copy goes through the package's own `task` locale namespace. The behavior is specified by the [Web background-task display Agent Note](../../../.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md).
 ## Model Experience
 None, as this package renders host-computed registry state for a human and touches no prompt, message, schema, stream, or tool result. The model's own view of the same tasks stays with [`dsh-tool-tasks`](../../tasks/tool-tasks/README.md).
 #### KV Cache effect
 None; the package never assembles or sends provider requests.
 ## Known Limitations and Deferred Work
 - **Rows are read-only** — a task's streamed output and a human-initiated cancellation are separate phases. Cancellation additionally owes a model-facing decision the seam does not answer today: `kill()` marks terminal delivery reported, so an interrupt written against the current contract would leave the model believing its task is still running.
 - **The list is not the registry's own set** — it shows what the owning session can see through the wire view, so an unowned task (one started without a live `Agent`) is invisible here while `task_list` still reports it to the model.
@@ -0,0 +1,24 @@
 # @deepseek-ai/dsh-client-ui-task
 [English](README.md) | 中文
 Web 后台任务特性的归属方：向 `conversation.session.header.actions` 贡献一个条目，列出当前会话可见的 `ctx.tasks` 记录。数据完全来自 [`dsh-client-runtime`](../runtime/README.md) 从 `session/tasks` 帧折叠出的 `tasksBySession` 列表镜像，因此本包不发任何 RPC，除弹层开合外不持有任何状态。
 只有当会话至少有一个任务时才渲染触发器，普通对话不会因为一项未被使用的能力而长出控件。角标计数为 `running` 加 `stopping`，为零时省略，这样只剩已完成任务的会话保留一个安静的历史入口，而不是宣告一个「零」。弹层是一个扁平列表：活跃行在前按 `startedAt` 升序，随后终态行按 `finishedAt` 降序；毫秒相同的并列按启动顺序打破，宿主的 map 迭代顺序永远不参与决定。一行显示生产者 kind、label、状态标记、生产者一旦给出 `detail` 就取代通用状态词的那段文字，以及已耗时。该耗时在活跃时每秒推进，并在 `finishedAt` 冻结；只有当打开的列表里确实有会动的东西时时钟才运行。缺少 `finishedAt` 的终态行读作零而不是负数，超过一小时的耗时停留在小时单位，不会长出任何生产者目前都到不了的「天」词汇。
 终态行保持可见并弱化，直到注册表在 owner 销毁时把它们丢掉。它们本就在快照里，失败任务的 `detail` 是其失败唯一可读之处，在这里过滤掉它们是输出与中断两期要推翻的工作。因此一个运行中的一次性后台 subagent 会同时出现在这里和 [subagent 目录](../ui-subagent/README.md)里：目录负责进入子会话的 transcript，而这个列表是将来中断能力唯一可能附着的句柄。
 Escape 关闭列表并把焦点交还触发器，在其外部按下指针同理。最后一个任务消失时先关闭列表再卸载控件，焦点因此不会从一个被移除的节点上凭空消失。样式只用 token；文案走本包自己的 `task` locale 命名空间。行为由 [Web 后台任务展示 Agent Note](../../../.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md) 规定。
 ## Model Experience
 无，因为本包为人类渲染宿主计算出的注册表状态，不触及 prompt、消息、schema、流或工具结果。模型对同一批任务的视角仍属于 [`dsh-tool-tasks`](../../tasks/tool-tasks/README.md)。
 #### KV Cache effect
 无；本包从不组装或发送 provider 请求。
 ## Known Limitations and Deferred Work
 - **行是只读的** —— 任务的流式输出与人类发起的中断是各自独立的阶段。中断还额外欠一个 seam 目前没有回答的、面向模型的决策：`kill()` 会把终态投递标为已上报，所以照当前契约写出来的中断会让模型一直以为它的任务还在跑。
 - **列表不等于注册表自己的集合** —— 它展示的是拥有它的会话通过线路视图能看到的东西，因此一个无主任务（在没有活体 `Agent` 时启动的任务）在这里不可见，而 `task_list` 仍会把它报告给模型。
@@ -0,0 +1,68 @@
 {
  "name": "@deepseek-ai/dsh-client-ui-task",
  "description": "Session-header background-task list: live registry state mirrored from session/tasks frames",
  "version": "0.0.1",
  "private": true,
  "type": "module",
  "main": "lib/index.js",
  "types": "lib/types/index.d.ts",
  "exports": {
    ".": {
      "types": "./lib/types/index.d.ts",
      "default": "./lib/index.js"
    },
    "./invariant": {
      "types": "./lib/types/invariant.d.ts",
      "default": "./lib/invariant.js"
    },
    "./client": {
      "types": "./lib/types/client/index.d.ts",
      "default": "./lib/client.js"
    },
    "./src/*": "./src/*",
    "./package.json": "./package.json"
  },
  "dshClient": {
    "inject": [
      "@deepseek-ai/dsh-client-locale",
      "@deepseek-ai/dsh-client-runtime",
      "@deepseek-ai/dsh-client-ui-conversation",
      "@deepseek-ai/dsh-client-ui-primitives"
    ],
    "platform": "web"
  },
  "scripts": {
    "bundle": "tsdown",
    "watch": "tsdown --watch"
  },
  "license": "BSD-3-Clause",
  "dependencies": {
    "react": "^18.2.0"
  },
  "peerDependencies": {
    "@deepseek-ai/dsh-client-locale": "^0.0.1",
    "@deepseek-ai/dsh-client-runtime": "^0.0.1",
    "@deepseek-ai/dsh-client-ui-conversation": "^0.0.1",
    "@deepseek-ai/dsh-client-ui-primitives": "^0.0.1",
    "@deepseek-ai/dsh-client-ui-slots": "^0.0.1",
    "@deepseek-ai/dsh-invariants": "^0.0.1",
    "cordis": "^4.0.0-rc.7"
  },
  "devDependencies": {
    "@deepseek-ai/dsh-client-locale": "workspace:^",
    "@deepseek-ai/dsh-client-runtime": "workspace:^",
    "@deepseek-ai/dsh-client-test-runtime": "workspace:^",
    "@deepseek-ai/dsh-client-ui-conversation": "workspace:^",
    "@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
    "@deepseek-ai/dsh-client-ui-slots": "workspace:^",
    "@deepseek-ai/dsh-invariants": "workspace:^",
    "@types/react": "~18.3.1",
    "cordis": "^4.0.0-rc.7"
  },
  "files": [
    "lib/index.js",
    "lib/invariant.js",
    "lib/client.js",
    "lib/types/**/*.d.ts"
  ]
 }
@@ -0,0 +1,116 @@
 .root {
  position: relative;
 }
 .trigger {
  display: inline-flex;
  align-items: center;
  gap: 3px;
  min-height: 28px;
  padding: 3px 2px;
  border: 0;
  border-radius: 6px;
  background: transparent;
  color: var(--dsw-alias-label-tertiary);
  font-size: 12px;
  line-height: 18px;
  cursor: pointer;
 }
 .trigger:hover,
 .trigger:focus-visible {
  color: var(--dsw-alias-label-secondary);
 }
 .trigger svg {
  transition: transform 120ms ease;
 }
 .triggerOpen {
  transform: rotate(180deg);
 }
 .triggerDot {
  flex: none;
 }
 .count {
  margin: 0 5px;
 }
 .menu {
  position: absolute;
  top: calc(100% + 5px);
  left: 0;
  z-index: 100;
  box-sizing: border-box;
  display: flex;
  flex-direction: column;
  gap: 1px;
  width: 336px;
  max-width: min(400px, calc(100vw - 32px));
  max-height: min(420px, calc(100vh - 140px));
  margin: 0;
  padding: 4px;
  overflow: auto;
  list-style: none;
  border: 1px solid var(--dsw-alias-border-l2);
  border-radius: 12px;
  background: var(--dsw-specific-menu);
  --dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2);
  --dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2);
  box-shadow: var(--dsw-shadow-lv3);
 }
 .row {
  display: flex;
  align-items: center;
  gap: 8px;
  box-sizing: border-box;
  width: 100%;
  min-height: 32px;
  padding: 6px 8px;
  border-radius: 8px;
  color: var(--dsw-alias-label-primary);
  font-size: 13px;
  line-height: 18px;
 }
 .rowSettled {
  color: var(--dsw-alias-label-tertiary);
 }
 .rowDot {
  flex: none;
 }
 .kind {
  flex: none;
  padding: 0 6px;
  border-radius: 5px;
  background: var(--dsw-alias-fill-l2);
  color: var(--dsw-alias-label-secondary);
  font-size: 11px;
  line-height: 18px;
 }
 .label {
  flex: 1;
  min-width: 0;
  overflow: hidden;
  font-family: var(--dsw-font-mono);
  white-space: nowrap;
  text-overflow: ellipsis;
 }
 .status,
 .duration {
  flex: none;
  color: var(--dsw-alias-label-tertiary);
  font-size: 11px;
  line-height: 18px;
 }
 .duration {
  font-variant-numeric: tabular-nums;
 }
@@ -0,0 +1,185 @@
 import { useEffect, useMemo, useRef, useState, type KeyboardEvent } from 'react'
 import type { TaskView } from '@deepseek-ai/dsh-client-runtime/client'
 import { IconChevronDownOutline14, StateDot, type StateDotState } from '@deepseek-ai/dsh-client-ui-primitives'
 import type { PropsLocale, PropsRuntime, TranslateNS } from '@deepseek-ai/dsh-client-ui-slots'
 import { NS } from './locales.ts'
 import type {} from '@deepseek-ai/dsh-client-ui-conversation/client'
 import css from './TaskListAction.module.css'
 /** Full props for the session-header background-task action. */
 export type TaskListActionProps =
  PropsRuntime<'conversation.session.header.actions'> & PropsLocale<typeof NS>
 /** Stable empty list so a session with no tasks keeps one array identity. */
 const NO_TASKS: readonly TaskView[] = []
 /** A task the registry still holds open, and whose duration therefore ticks. */
 function isLive(task: TaskView): boolean {
  return task.status === 'running' || task.status === 'stopping'
 }
 /** Closed-union exhaustiveness fence for the wire status set. */
 /* v8 ignore next 3 -- closed-union backstop; only reached if a status is forged */
 function assertNever(value: never): never {
  throw new Error(`unhandled task status: ${JSON.stringify(value)}`)
 }
 /**
 * Status marker semantics. `stopping` and `killed` share the attention color:
 * both mean the work ended (or is ending) on request rather than on its own.
 */
 function dotState(status: TaskView['status']): StateDotState {
  switch (status) {
    case 'running': return 'ongoing'
    case 'stopping': return 'warning'
    case 'completed': return 'done'
    case 'killed': return 'warning'
    case 'failed': return 'error'
    /* v8 ignore next -- closed wire status union */
    default: return assertNever(status)
  }
 }
 /** Human status word for the row and its accessible name. */
 function statusLabel(status: TaskView['status'], t: TranslateNS<typeof NS>): string {
  switch (status) {
    case 'running': return t('status.running')
    case 'stopping': return t('status.stopping')
    case 'completed': return t('status.completed')
    case 'killed': return t('status.killed')
    case 'failed': return t('status.failed')
    /* v8 ignore next -- closed wire status union */
    default: return assertNever(status)
  }
 }
 /**
 * Elapsed time in at most two adjacent units. A background task that outlives
 * an hour is already exceptional, so hours is the widest unit — beyond that the
 * figure stays in hours rather than growing a day/month vocabulary no producer
 * currently reaches.
 */
 function formatDuration(elapsedMs: number, t: TranslateNS<typeof NS>): string {
  const total = Math.max(0, Math.floor(elapsedMs / 1_000))
  const seconds = total % 60
  const minutes = Math.floor(total / 60) % 60
  const hours = Math.floor(total / 3_600)
  if (hours > 0) return t('duration.hours', { hours, minutes })
  if (minutes > 0) return t('duration.minutes', { minutes, seconds })
  return t('duration.seconds', { seconds })
 }
 /**
 * Live rows first in start order, then settled rows newest-first. Two tasks
 * that settled in the same millisecond fall back to start order, so the sort
 * never depends on the host's map iteration.
 */
 function ordered(tasks: readonly TaskView[]): TaskView[] {
  return [...tasks].sort((left, right) => {
    const liveLeft = isLive(left)
    if (liveLeft !== isLive(right)) return liveLeft ? -1 : 1
    if (liveLeft) return left.startedAt - right.startedAt
    const finished = (right.finishedAt ?? right.startedAt) - (left.finishedAt ?? left.startedAt)
    return finished !== 0 ? finished : left.startedAt - right.startedAt
  })
 }
 /**
 * Session-header entry point for this session's background tasks. It renders
 * nothing at all until the session has at least one task, so an ordinary
 * conversation never grows a control for a capability it is not using.
 * @param props - runtime slot currency plus the namespace translator.
 * @returns the trigger and its popover list, or null when there is nothing to show.
 */
 export function TaskListAction({ sessionId, useSessions, t }: TaskListActionProps) {
  const tasks = useSessions(state => state.tasksBySession[sessionId]) ?? NO_TASKS
  const [open, setOpen] = useState(false)
  const [now, setNow] = useState(() => Date.now())
  const rootRef = useRef<HTMLDivElement>(null)
  const triggerRef = useRef<HTMLButtonElement>(null)
  const rows = useMemo(() => ordered(tasks), [tasks])
  const liveCount = useMemo(() => tasks.filter(isLive).length, [tasks])
  useEffect(() => {
    if (!open) return
    const closeOutside = (event: PointerEvent): void => {
      if (event.target instanceof Node && !rootRef.current?.contains(event.target)) {
        setOpen(false)
      }
    }
    document.addEventListener('pointerdown', closeOutside)
    return () => { document.removeEventListener('pointerdown', closeOutside) }
  }, [open])
  // The clock only runs while an open list is showing something that moves.
  useEffect(() => {
    if (!open || liveCount === 0) return
    setNow(Date.now())
    const timer = setInterval(() => { setNow(Date.now()) }, 1_000)
    return () => { clearInterval(timer) }
  }, [open, liveCount])
  // The last task disappearing removes this control; close first so focus does
  // not vanish from an unmounting node.
  useEffect(() => {
    if (tasks.length === 0 && open) setOpen(false)
  }, [tasks.length, open])
  if (tasks.length === 0) return null
  const countKey = liveCount > 0
    ? (liveCount === 1 ? 'count.live.one' : 'count.live.other')
    : (tasks.length === 1 ? 'count.idle.one' : 'count.idle.other')
  const countLabel = t(countKey, { count: liveCount > 0 ? liveCount : tasks.length })
  const onKeyDown = (event: KeyboardEvent<HTMLDivElement>): void => {
    if (event.key !== 'Escape' || !open) return
    event.preventDefault()
    setOpen(false)
    triggerRef.current?.focus()
  }
  return (
    <div ref={rootRef} className={css.root} onKeyDown={onKeyDown}>
      <button
        ref={triggerRef}
        type="button"
        className={css.trigger}
        aria-expanded={open}
        aria-label={countLabel}
        onClick={() => { setOpen(current => !current) }}
      >
        {liveCount > 0 ? <StateDot state="ongoing" className={css.triggerDot} /> : null}
        <span className={css.count}>{countLabel}</span>
        <IconChevronDownOutline14 className={open ? css.triggerOpen : undefined} />
      </button>
      {open
        ? (
          <ul className={css.menu} aria-label={t('list.aria')}>
            {rows.map((task) => {
              const live = isLive(task)
              const elapsed = live ? now - task.startedAt : (task.finishedAt ?? task.startedAt) - task.startedAt
              const duration = formatDuration(elapsed, t)
              const status = statusLabel(task.status, t)
              return (
                <li key={task.id} className={live ? css.row : `${css.row} ${css.rowSettled}`}>
                  <StateDot state={dotState(task.status)} className={css.rowDot} />
                  <span className={css.kind}>{task.kind}</span>
                  <span className={css.label} title={task.label}>{task.label}</span>
                  <span className={css.status}>{task.detail ?? status}</span>
                  <span
                    className={css.duration}
                    title={t(live ? 'duration.title.live' : 'duration.title.done', { duration })}
                  >
                    {duration}
                  </span>
                </li>
              )
            })}
          </ul>
        )
        : null}
    </div>
  )
 }
@@ -0,0 +1,40 @@
 /**
 * Background-task plugin, browser half: contributes one session-header action
 * that renders this session's `ctx.tasks` records. The data arrives entirely
 * through the `tasksBySession` list mirror, so the plugin issues no RPC and
 * holds no state of its own beyond popover visibility.
 */
 import type { ClientContext } from '@deepseek-ai/dsh-client-runtime/client'
 import { TaskListAction } from './TaskListAction.tsx'
 import type {} from '@deepseek-ai/dsh-client-locale/client'
 import { en, NS, zh, type TaskKey } from './locales.ts'
 declare module '@deepseek-ai/dsh-client-ui-slots' {
  interface LocaleNamespaceMap {
    /** Background-task list copy. */
    'task': TaskKey
  }
 }
 export type { TaskListActionProps } from './TaskListAction.tsx'
 /** Required services for locale registration and header-slot contribution. */
 export const inject = ['sessions', 'slots', 'locale']
 /**
 * Client plugin body: register the dictionaries and the header action.
 * @param ctx - client root context.
 */
 export function apply(ctx: ClientContext): void {
  ctx.effect(() => ctx.locale.register(NS, { zh, en }), 'ui-task: dictionaries')
  ctx.slots.inject(
    'conversation.session.header.actions',
    () => ctx.slots.register({
      name: 'conversation.session.header.actions',
      id: 'task-list',
      // After the subagent catalog: session lineage reads before process work.
      order: 20,
      locale: NS,
    }, TaskListAction),
  )
 }
@@ -0,0 +1,45 @@
 /** `task` namespace dictionaries. */
 /** Dictionary namespace owned by this plugin. */
 export const NS = 'task'
 /** Simplified Chinese dictionary (the key-set source of truth). */
 export const zh = {
  'count.live.one': '{count} 个后台任务运行中',
  'count.live.other': '{count} 个后台任务运行中',
  'count.idle.one': '{count} 个后台任务',
  'count.idle.other': '{count} 个后台任务',
  'list.aria': '后台任务',
  'status.running': '运行中',
  'status.stopping': '正在停止',
  'status.completed': '已完成',
  'status.killed': '已取消',
  'status.failed': '已失败',
  'duration.seconds': '{seconds}秒',
  'duration.minutes': '{minutes}分{seconds}秒',
  'duration.hours': '{hours}小时{minutes}分',
  'duration.title.live': '已运行 {duration}',
  'duration.title.done': '耗时 {duration}',
 } as const
 /** English dictionary, key-identical to the Chinese source of truth. */
 export const en: Record<TaskKey, string> = {
  'count.live.one': '{count} background task running',
  'count.live.other': '{count} background tasks running',
  'count.idle.one': '{count} background task',
  'count.idle.other': '{count} background tasks',
  'list.aria': 'Background tasks',
  'status.running': 'running',
  'status.stopping': 'stopping',
  'status.completed': 'completed',
  'status.killed': 'cancelled',
  'status.failed': 'failed',
  'duration.seconds': '{seconds}s',
  'duration.minutes': '{minutes}m {seconds}s',
  'duration.hours': '{hours}h {minutes}m',
  'duration.title.live': 'Running for {duration}',
  'duration.title.done': 'Took {duration}',
 }
 /** Key domain of the `task` namespace (zh is the source of truth). */
 export type TaskKey = keyof typeof zh
@@ -0,0 +1,6 @@
 declare module '*.module.css' {
  const classes: Record<string, string>
  export default classes
 }
 declare module '*.css'
@@ -0,0 +1,9 @@
 /**
 * Background-task list plugin, node half. Pure UI plugin: the empty apply
 * exists so the plugin appears in the host cordis.yml / Loader; the browser
 * half ships via exports["./client"], discovered through the package.json
 * dshClient declaration.
 */
 /** Host plugin body — no host-side behavior for this source plugin. */
 export function apply(): void {}
@@ -0,0 +1,32 @@
 /**
 * Package-owned invariant companion for `@deepseek-ai/dsh-client-ui-task`.
 * @module @deepseek-ai/dsh-client-ui-task/invariant
 */
 /* jscpd:ignore-start */
 import type { Context } from 'cordis'
 import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
 const PACKAGE_NAME = '@deepseek-ai/dsh-client-ui-task'
 /** Cordis companion plugin name. */
 export const name = 'client-ui-task-invariant'
 /** Service required before the companion can reserve package ownership. */
 export const inject = ['invariants']
 /**
 * No runtime invariant: this package is a read-only projection of the
 * `tasksBySession` mirror onto one header slot entry. It emits no cordis
 * events, owns no cross-plugin mutable state, and its single slot registration
 * proves disposal through the HMR-safety spec.
 */
 const install: InvariantInstaller = () => {}
 /**
 * Register this package's invariant companion.
 * @param ctx - Cordis context carrying the invariant service.
 * @returns the installed registration's disposer after setup succeeds.
 */
 export const apply = (ctx: Context): Promise<() => void> =>
  Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
 /* jscpd:ignore-end */
@@ -0,0 +1,89 @@
 /**
 * ui-task plugin halves: the browser entry's dictionary and header-slot
 * registrations against the real SlotsService (with fiber teardown proving
 * removal — HMR safety), the inert node entry, and the invariant companion's
 * ownership reservation.
 */
 import { Context } from 'cordis'
 import { describe, expect, it } from 'vitest'
 import InvariantService from '@deepseek-ai/dsh-invariants'
 import { SlotsService } from '@deepseek-ai/dsh-client-runtime/client'
 import { apply as applyLocale } from '@deepseek-ai/dsh-client-locale/client'
 import { apply, inject } from '../src/client/index.ts'
 import { apply as applyNode } from '../src/index.ts'
 import * as TaskInvariant from '../src/invariant.ts'
 import { en, NS, zh } from '../src/client/locales.ts'
 /** Slot ledger reader: entry ids currently registered in the header list. */
 function headerEntryIds(ctx: Context): (string | undefined)[] {
  return ctx.slots
    .entries('conversation.session.header.actions')
    .map(entry => entry.options.id)
 }
 /** Boot the browser half over a real slot tree that declares the header list. */
 async function bench(): Promise<{ ctx: Context; fiber: ReturnType<Context['plugin']> }> {
  const ctx = new Context()
  await ctx.plugin(SlotsService).await()
  ctx.slots.register({
    name: 'root',
    children: {
      'conversation.session.header.actions': { kind: 'list', scope: 'session' },
    },
  } as never, () => null)
  ctx.provide('sessions', {})
  await ctx.plugin({ inject: ['slots'], apply: applyLocale }).await()
  const fiber = ctx.plugin({ inject: [...inject], apply })
  await fiber.await()
  return { ctx, fiber }
 }
 describe('ui-task browser half', () => {
  it('declares the services it binds', () => {
    expect(inject).toEqual(['sessions', 'slots', 'locale'])
  })
  it('registers the header action, and fiber teardown removes it (HMR safety)', async () => {
    const { ctx, fiber } = await bench()
    expect(headerEntryIds(ctx)).toContain('task-list')
    await fiber.dispose()
    expect(headerEntryIds(ctx)).not.toContain('task-list')
  })
  it('registers both dictionaries under its own namespace and releases them with the fiber', async () => {
    const { ctx, fiber } = await bench()
    const translate = ctx.locale.bind(NS)
    expect(translate('list.aria')).toBe(zh['list.aria'])
    ctx.locale.setLocale('en')
    expect(translate('list.aria')).toBe(en['list.aria'])
    // Withdrawn dictionaries leave the key unresolved rather than translated.
    await fiber.dispose()
    expect(translate('list.aria')).not.toBe(en['list.aria'])
  })
  it('keeps the English dictionary key-identical to the Chinese source of truth', () => {
    expect(Object.keys(en).sort()).toEqual(Object.keys(zh).sort())
  })
 })
 describe('ui-task node half', () => {
  it('contributes no host behavior', () => {
    // The node half exists only so the plugin appears in the Loader tree.
    expect(applyNode).not.toThrow()
  })
 })
 describe('ui-task invariant companion', () => {
  it('reserves package ownership under its declared companion name', async () => {
    const ctx = new Context()
    await ctx.plugin(InvariantService, { enabled: true })
    const fiber = ctx.plugin(TaskInvariant)
    await fiber.await()
    expect(TaskInvariant.name).toBe('client-ui-task-invariant')
    expect(TaskInvariant.inject).toEqual(['invariants'])
    // Emitting an unrelated event proves the companion installed no audit.
    expect(() => { (ctx.emit as (event: string) => void)('slots/changed') }).not.toThrow()
    await fiber.dispose()
  })
 })
@@ -0,0 +1,239 @@
 // @vitest-environment jsdom
 import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
 import { act, cleanup, fireEvent, render, screen, within } from '@testing-library/react'
 import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime'
 import type { SessionId, SessionListState, TaskView } from '@deepseek-ai/dsh-client-runtime/client'
 import { TaskListAction, type TaskListActionProps } from '../src/client/TaskListAction.tsx'
 import { zh } from '../src/client/locales.ts'
 // Live rows render `now - startedAt`, so every assertion needs a pinned clock.
 beforeEach(() => {
  vi.useFakeTimers()
  vi.setSystemTime(START)
 })
 afterEach(() => {
  cleanup()
  vi.useRealTimers()
  vi.restoreAllMocks()
 })
 const SESSION = 'session' as SessionId
 const START = 1_700_000_000_000
 const t: TaskListActionProps['t'] = makeTranslate(zh)
 function task(over: Partial<TaskView> = {}): TaskView {
  return {
    id: 'bash-1' as TaskView['id'],
    kind: 'bash',
    label: 'pnpm run build',
    status: 'running',
    startedAt: START,
    ...over,
  }
 }
 function props(tasks: readonly TaskView[] | undefined): TaskListActionProps {
  const state = {
    ids: [SESSION],
    byId: {},
    current: SESSION,
    phase: 'ready',
    subagentsByParent: {},
    tasksBySession: tasks === undefined ? {} : { [SESSION]: tasks },
    currentAddress: undefined,
  } satisfies SessionListState
  function useSessions<T>(select: (snapshot: SessionListState) => T): T {
    return select(state)
  }
  return { sessionId: SESSION, useSessions, t } as unknown as TaskListActionProps
 }
 /**
 * Rows in render order as `[kind, label, status, duration]`. Adjacent spans
 * carry no whitespace between them, so the cells are read one element at a
 * time rather than split out of a flattened string.
 */
 function rowCells(): string[][] {
  return within(screen.getByRole('list', { name: zh['list.aria'] }))
    .getAllByRole('listitem')
    .map(row => [...row.children]
      .map(cell => cell.textContent ?? '')
      .filter(text => text !== ''))
 }
 describe('TaskListAction visibility', () => {
  it('renders nothing while the session has no tasks', () => {
    const { container } = render(<TaskListAction {...props(undefined)} />)
    expect(container.innerHTML).toBe('')
  })
  it('counts only live tasks, and falls back to the total when none are live', () => {
    const { rerender } = render(<TaskListAction {...props([task(), task({ id: 'bash-2' as TaskView['id'] })])} />)
    expect(screen.getByRole('button', { name: '2 个后台任务运行中' })).toBeDefined()
    rerender(<TaskListAction {...props([task({ status: 'completed', finishedAt: START + 3_000 })])} />)
    expect(screen.getByRole('button', { name: '1 个后台任务' })).toBeDefined()
  })
  it('closes and unmounts when the last task disappears while the list is open', () => {
    const { container, rerender } = render(<TaskListAction {...props([task()])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(screen.getByRole('list', { name: zh['list.aria'] })).toBeDefined()
    rerender(<TaskListAction {...props([])} />)
    expect(container.innerHTML).toBe('')
  })
 })
 describe('TaskListAction rows', () => {
  it('orders live tasks by start, then settled tasks newest-first', () => {
    render(<TaskListAction {...props([
      task({ id: 'bash-3' as TaskView['id'], label: 'old done', status: 'completed', startedAt: START, finishedAt: START + 1_000 }),
      task({ id: 'bash-4' as TaskView['id'], label: 'new done', status: 'failed', startedAt: START, finishedAt: START + 9_000 }),
      task({ id: 'bash-2' as TaskView['id'], label: 'later live', startedAt: START + 5_000 }),
      task({ id: 'bash-1' as TaskView['id'], label: 'earlier live', startedAt: START }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells()).toEqual([
      ['bash', 'earlier live', '运行中', '0秒'],
      ['bash', 'later live', '运行中', '0秒'],
      ['bash', 'new done', '已失败', '9秒'],
      ['bash', 'old done', '已完成', '1秒'],
    ])
  })
  it('breaks a settled tie on start order so map iteration never decides it', () => {
    render(<TaskListAction {...props([
      task({ id: 'bash-2' as TaskView['id'], label: 'second', status: 'completed', startedAt: START + 10, finishedAt: START + 100 }),
      task({ id: 'bash-1' as TaskView['id'], label: 'first', status: 'completed', startedAt: START, finishedAt: START + 100 }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells().map(cells => cells[1])).toEqual(['first', 'second'])
  })
  it('prefers the producer detail over the generic status word', () => {
    render(<TaskListAction {...props([
      task({ status: 'killed', detail: 'signal: SIGTERM', finishedAt: START + 2_000 }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells()[0]).toContain('signal: SIGTERM')
  })
  it('renders every status word, including the stopping transition', () => {
    render(<TaskListAction {...props([
      task({ id: 'bash-1' as TaskView['id'], label: 'a', status: 'running' }),
      task({ id: 'bash-2' as TaskView['id'], label: 'b', status: 'stopping' }),
      task({ id: 'bash-3' as TaskView['id'], label: 'c', status: 'completed', finishedAt: START }),
      task({ id: 'bash-4' as TaskView['id'], label: 'd', status: 'killed', finishedAt: START }),
      task({ id: 'bash-5' as TaskView['id'], label: 'e', status: 'failed', finishedAt: START }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    const words = rowCells().map(cells => cells[2])
    expect(new Set(words)).toEqual(new Set(['运行中', '正在停止', '已完成', '已取消', '已失败']))
  })
 })
 describe('TaskListAction duration', () => {
  it('advances a live row once per second and freezes a settled one', () => {
    vi.setSystemTime(START + 1_000)
    render(<TaskListAction {...props([
      task({ id: 'bash-1' as TaskView['id'], label: 'live' }),
      task({ id: 'bash-2' as TaskView['id'], label: 'done', status: 'completed', finishedAt: START + 4_000 }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells()[0]).toContain('1秒')
    expect(rowCells()[1]).toContain('4秒')
    act(() => { vi.advanceTimersByTime(2_000) })
    expect(rowCells()[0]).toContain('3秒')
    expect(rowCells()[1]).toContain('4秒')
  })
  it('widens to minutes and then hours, and never shows a negative figure', () => {
    render(<TaskListAction {...props([
      task({ id: 'bash-1' as TaskView['id'], label: 'm', status: 'completed', finishedAt: START + 125_000 }),
      task({ id: 'bash-2' as TaskView['id'], label: 'h', status: 'completed', finishedAt: START + 7_380_000 }),
      // A clock that moved backwards must not render a negative duration.
      task({ id: 'bash-3' as TaskView['id'], label: 'skew', status: 'completed', startedAt: START + 5_000, finishedAt: START }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells().map(cells => cells[3])).toEqual(['2小时3分', '2分5秒', '0秒'])
  })
  it('runs no clock while the list is closed', () => {
    const interval = vi.spyOn(globalThis, 'setInterval')
    render(<TaskListAction {...props([task()])} />)
    expect(interval).not.toHaveBeenCalled()
    fireEvent.click(screen.getByRole('button'))
    expect(interval).toHaveBeenCalledTimes(1)
  })
  it('runs no clock for an open list holding only settled tasks', () => {
    const interval = vi.spyOn(globalThis, 'setInterval')
    render(<TaskListAction {...props([task({ status: 'completed', finishedAt: START })])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(interval).not.toHaveBeenCalled()
  })
 })
 describe('TaskListAction dismissal', () => {
  it('closes on Escape and returns focus to the trigger', () => {
    render(<TaskListAction {...props([task()])} />)
    const trigger = screen.getByRole('button')
    fireEvent.click(trigger)
    expect(trigger.getAttribute('aria-expanded')).toBe('true')
    fireEvent.keyDown(trigger, { key: 'Escape' })
    expect(trigger.getAttribute('aria-expanded')).toBe('false')
    expect(document.activeElement).toBe(trigger)
  })
  it('ignores other keys and a closed-list Escape', () => {
    render(<TaskListAction {...props([task()])} />)
    const trigger = screen.getByRole('button')
    fireEvent.keyDown(trigger, { key: 'Escape' })
    expect(trigger.getAttribute('aria-expanded')).toBe('false')
    fireEvent.click(trigger)
    fireEvent.keyDown(trigger, { key: 'ArrowDown' })
    expect(trigger.getAttribute('aria-expanded')).toBe('true')
  })
  it('closes on an outside pointer press but not on one inside', () => {
    render(<TaskListAction {...props([task()])} />)
    const trigger = screen.getByRole('button')
    fireEvent.click(trigger)
    fireEvent.pointerDown(screen.getByRole('list', { name: zh['list.aria'] }))
    expect(trigger.getAttribute('aria-expanded')).toBe('true')
    fireEvent.pointerDown(document.body)
    expect(trigger.getAttribute('aria-expanded')).toBe('false')
  })
 })
 describe('TaskListAction wire tolerance', () => {
  it('treats a settled task with no finishedAt as zero-duration and sorts it by start', () => {
    // `finishedAt` is optional on the wire; the Host always sets it, so this
    // covers a producer or carrier that ever stops doing so.
    render(<TaskListAction {...props([
      task({ id: 'bash-1' as TaskView['id'], label: 'no finish', status: 'completed' }),
      task({ id: 'bash-2' as TaskView['id'], label: 'finished', status: 'completed', startedAt: START - 1_000, finishedAt: START + 2_000 }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells().map(cells => [cells[1], cells[3]])).toEqual([
      ['finished', '3秒'],
      ['no finish', '0秒'],
    ])
  })
  it('falls back to start order when neither settled task carries a finish time', () => {
    render(<TaskListAction {...props([
      task({ id: 'bash-2' as TaskView['id'], label: 'later', status: 'failed', startedAt: START + 1_000 }),
      task({ id: 'bash-1' as TaskView['id'], label: 'earlier', status: 'failed', startedAt: START }),
    ])} />)
    fireEvent.click(screen.getByRole('button'))
    expect(rowCells().map(cells => cells[1])).toEqual(['later', 'earlier'])
  })
 })
@@ -0,0 +1,33 @@
 {
  "extends": "../../../tsconfig.base.client.json",
  "compilerOptions": {
    "rootDir": "src",
    "outDir": "lib/types"
  },
  "include": [
    "src"
  ],
  "references": [
    {
      "path": "../../../vendor/cordis"
    },
    {
      "path": "../locale"
    },
    {
      "path": "../runtime"
    },
    {
      "path": "../ui-conversation"
    },
    {
      "path": "../ui-primitives"
    },
    {
      "path": "../ui-slots"
    },
    {
      "path": "../../support/invariants"
    }
  ]
 }
@@ -0,0 +1,3 @@
 import { clientBundle } from '../tsdown.client.ts'
 export default clientBundle('@deepseek-ai/dsh-client-ui-task', ['lib/types/index.js', 'lib/types/invariant.js'])
@@ -22,7 +22,7 @@ const COPY: Record<string, string> = {
 /** Empty global standard-kit hooks (the row reads neither). */
 function emptySessions() {
  const store = createSnapshotStore<SessionListState>(
-    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined })
+    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined })
  return bindSnapshotSelector(store)
 }
 function emptyWorkspaces() {
@@ -101,7 +101,7 @@ async function bench(snapshot: ConversationSnapshot) {
    ids: [SID],
    byId: { [SID]: { id: SID, title: 'S', displayTitle: 'S', running: false, blank: false, updatedAt: 1 } },
    current: SID,
-    phase: 'ready', subagentsByParent: {}, currentAddress: undefined,
+    phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
  })
  const scoped = { send: vi.fn(async () => {}), cancel: vi.fn(async () => {}) }
  const layout = { openDetails: vi.fn(), closeDetails: vi.fn() }
@@ -30,7 +30,7 @@ function listStore() {
    },
    current: undefined,
    phase: 'ready',
-    subagentsByParent: {},
+    subagentsByParent: {}, tasksBySession: {},
    currentAddress: undefined,
  })
 }
@@ -157,7 +157,7 @@ describe('FileMutationRow diff card', () => {
    byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd: '/w/app' } },
    current: SID,
    phase: 'ready',
-    subagentsByParent: {},
+    subagentsByParent: {}, tasksBySession: {},
    currentAddress: undefined,
  })
@@ -309,13 +309,13 @@ describe('DetailsPanel diff Output section', () => {
    const chat = createChatStore().create()
    if (selection !== null) chat.actions.select(selection)
    const sessions = createSnapshotStore<SessionListState>(cwd === undefined
-      ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }
+      ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }
      : {
        ids: [SID],
        byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd } },
        current: SID,
        phase: 'ready',
-        subagentsByParent: {},
+        subagentsByParent: {}, tasksBySession: {},
        currentAddress: undefined,
      })
    const workspaces = createSnapshotStore<WorkspaceListState>({
@@ -171,7 +171,7 @@ describe('ReadRow keyed toolview', () => {
    byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd: '/w/app' } },
    current: SID,
    phase: 'ready',
-    subagentsByParent: {},
+    subagentsByParent: {}, tasksBySession: {},
    currentAddress: undefined,
  })
@@ -255,13 +255,13 @@ describe('DetailsPanel Output section (read)', () => {
    const chat = createChatStore().create()
    if (selection !== null) chat.actions.select(selection)
    const sessions = createSnapshotStore<SessionListState>(cwd === undefined
-      ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }
+      ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }
      : {
        ids: [SID],
        byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd } },
        current: SID,
        phase: 'ready',
-        subagentsByParent: {},
+        subagentsByParent: {}, tasksBySession: {},
        currentAddress: undefined,
      })
    const workspaces = createSnapshotStore<WorkspaceListState>({
@@ -378,7 +378,7 @@ describe('DetailsPanel Output section (search)', () => {
    if (selection !== null) chat.actions.select(selection)
    const sessions = createSnapshotStore<SessionListState>({
      ids: [], byId: {}, current: undefined, phase: 'ready',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })
    const workspaces = createSnapshotStore<WorkspaceListState>({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
@@ -346,7 +346,7 @@ describe('BashRow terminal card', () => {
    byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0 } },
    current: undefined,
    phase: 'ready',
-    subagentsByParent: {},
+    subagentsByParent: {}, tasksBySession: {},
    currentAddress: undefined,
  })
@@ -446,13 +446,13 @@ describe('DetailsPanel Output section', () => {
    const chat = createChatStore().create()
    if (selection !== null) chat.actions.select(selection)
    const sessions = createSnapshotStore<SessionListState>(cwd === undefined
-      ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }
+      ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }
      : {
        ids: [SID],
        byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd } },
        current: SID,
        phase: 'ready',
-        subagentsByParent: {},
+        subagentsByParent: {}, tasksBySession: {},
        currentAddress: undefined,
      })
    const workspaces = createSnapshotStore<WorkspaceListState>({
@@ -643,7 +643,7 @@ describe('DetailsPanel Output section', () => {
        useSessions={bindSnapshotSelector(createSnapshotStore<SessionListState>(
          {
            ids: [], byId: {}, current: undefined, phase: 'ready',
-            subagentsByParent: {}, currentAddress: undefined,
+            subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
          }))}
        useWorkspaces={bindSnapshotSelector(createSnapshotStore<WorkspaceListState>({
          items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
@@ -208,7 +208,7 @@ describe('DetailsPanel web Output section', () => {
    if (selection !== null) chat.actions.select(selection)
    const sessions = createSnapshotStore<SessionListState>({
      ids: [], byId: {}, current: undefined, phase: 'ready',
-      subagentsByParent: {}, currentAddress: undefined,
+      subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
    })
    const workspaces = createSnapshotStore<WorkspaceListState>({
      items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null,
@@ -122,7 +122,7 @@ function fakeSession(nodes: ConversationSnapshot['nodes']) {
 /** Empty sessions-list hook; breadcrumbs therefore fall back to the raw id. */
 function emptySessions() {
  const store = createSnapshotStore<SessionListState>(
-    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined })
+    { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined })
  return bindSnapshotSelector(store)
 }
@@ -17,7 +17,7 @@ const list = (...items: SessionSummary[]): SessionListState => ({
  ids: items.map(item => item.id),
  byId: Object.fromEntries(items.map(item => [item.id, item])),
  current: undefined,
-  phase: 'ready', subagentsByParent: {}, currentAddress: undefined,
+  phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
 })
 const workspace = (id: string, sessionIds: string[], title = id): WorkspaceView => ({
  workspaceId: wid(id), path: `/projects/${id}`, title,
@@ -29,7 +29,7 @@ const sessionState = (items: readonly SessionSummary[], overrides: Partial<Sessi
  byId: Object.fromEntries(items.map(item => [item.id, item])),
  current: undefined,
  phase: 'ready',
-  subagentsByParent: {},
+  subagentsByParent: {}, tasksBySession: {},
  currentAddress: undefined,
  ...overrides,
 })
@@ -28,7 +28,7 @@ function hook<T>(snapshot: T) {
  return function select<S>(selector: (state: T) => S): S { return selector(snapshot) }
 }
 const sessions: SessionListState = {
-  ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined,
+  ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined,
 }
 const workspaceState = (items: readonly WorkspaceView[]): WorkspaceListState => ({
  items, archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, baselinesReady: true,
@@ -1030,6 +1030,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [
        signature: 'abstract onTaskDone(listener: TaskDoneListener): () => void',
        jsDoc: '/**\n * Register an effect-scoped completion listener. Each listener is contained;\n * returned promises are observed but not awaited. No listener runs after\n * service disposal.\n * @param listener - receives each terminal snapshot and its exact owner.\n * @returns disposer that unregisters the listener.\n */',
      },
      {
        signature: 'abstract onTasksChanged(listener: TasksChangedListener): () => void',
        jsDoc: '/**\n * Register an effect-scoped observer of visible-set changes. It fires after\n * every commit that changes what {@link list} returns for that owner —\n * registration, the stopping transition, settlement, and owner-disposal\n * removal — so an observer re-reads rather than accumulating deltas.\n *\n * This is not a superset of {@link onTaskDone}: that one delivers the terminal\n * record under first-wins semantics a control surface couples to notice\n * delivery, while this one carries no delivery meaning and marks nothing\n * reported. Listeners are contained and never awaited.\n * @param listener - receives the owner whose visible set changed, or\n *   `undefined` when an unowned task changed and every caller\'s set did.\n * @returns disposer that unregisters the listener.\n */',
      },
      {
        signature: 'abstract attachSurface(name: string): () => void',
        jsDoc: '/**\n * Attach an effect-scoped surface that can read and stop tasks. {@link start}\n * refuses work while none is attached.\n * @param name - diagnostic label; duplicate names remain independent.\n * @returns disposer that detaches this surface.\n */',
@@ -2915,6 +2919,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [
    name: 'TaskRead',
    declaration: 'export interface TaskRead {\n    text: string;\n    snapshot: TaskSnapshot;\n}',
  },
  {
    name: 'TasksChangedListener',
    declaration: 'export type TasksChangedListener = (owner: Agent | undefined) => void;',
  },
  {
    name: 'TaskSnapshot',
    declaration: 'export interface TaskSnapshot {\n    id: TaskId;\n    kind: TaskKind;\n    label: string;\n    outputLimitBytes?: number;\n    ownerSession?: SessionId;\n    status: TaskStatus;\n    detail?: string;\n    startedAt: number;\n    finishedAt?: number;\n    reported: boolean;\n}',
@@ -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: a3c9f214690144ec0f39a8690e4fd346f5e315e2
+README.md: edf51dd1c15c61a03102003eb921a0e21b1f0fa8
-README.zh.md: aeaf1b29e5a71674c9feedb30b67f9ce11c47340
+README.zh.md: 6b8bfa0459167b87c5b2848eb683cabf7ce91444
@@ -36,6 +36,8 @@ Session model routing is a session-domain contract. `session.models` returns the
 Pending queued input is a live control-plane contract, not conversation history. The gateway derives the complete `next-turn` queue from durable `agent/inbox/spliced` mutations and broadcasts authoritative `session/queue` snapshots after each change and on reconnect; pending `next-step` steering stays outside this Web projection. Within `next-step`, user-origin messages carry the `steering` placement while injected context (approval notices, task completion, attached snapshots) carries `context` and is not surfaced until claimed. The message-local `agent/inbox/inserted`, `claimed`, and `discarded` notifications remain available to lifecycle observers but do not build the queue view. `session.updateQueue` addresses one `MessageId`; edit and remove mutate the attached Agent through `Inbox.splice()`. A claim's pure deletion splice wins races before pre-step admission, so a later operation returns `queue-item-not-found`. `session.cancel` aborts only the active turn and preserves pending inbox work; after cancellation reaches quiescence and the closing turn flushes, AgentLoop claims the next waking message in FIFO order, and the browser never resends or promotes it. Queue operations never resume a cold session, and the client never infers retirement from turn or status events.
 Background tasks ride the same live-push posture. When `ctx.tasks` is composed, the gateway subscribes to its change feed and broadcasts a whole `session/tasks` snapshot after every registry commit that alters what a session can see — registration, the stopping transition, settlement, and owner-disposal removal — plus a subscription baseline for each session that already has tasks (an absent baseline is the empty set; a change that empties a set still sends `[]`). A change carrying an owner reads through that exact `Agent`, so a push stays correct while its scope tears down; the baseline reads `ctx.agents.get(sessionId)`, which yields only unowned tasks for a session with no live Agent and never resumes a cold one. An unowned change fans out to every subscribed session, because unowned tasks are visible to every caller. The wire `TaskView` drops `ownerSession`, `reported`, and `outputLimitBytes`: the frame's own `sessionId` carries the first, and the other two are internal notice and model-presentation policy. A composition without the registry emits no such frames.
 Workspace and Session lists are separate reconnect baselines. `workspace.create({ name })` creates a uniquely titled directory under the configured root, while `workspace.create({ path })` adopts an existing canonical directory and permits basename-derived titles to repeat. `workspace.delete` removes only the Workspace registration, `session.create` accepts an optional preallocated Session id, and `host/workspace-changed`, `host/workspace-removed`, plus `host/session-added` carry committed increments in either arrival order. `workspace.archiveSession` adds one session to the registry-global archive set and answers the full updated set; `workspace.list` carries that set as the reconnect baseline and `host/archived-sessions-changed` pushes the full snapshot after every durable change. Archiving hides the session from grouping surfaces without touching its log or its workspace account; a session neither live nor persisted fails with `session-not-found`. Registration deletion preserves the directory and session logs; its Sessions remain in `session.list` and become Ungrouped. `SessionSummary.blank` and the `host/session-added` frame carry the derived zero-events bit: clients hide blank sessions and reuse them per workspace, flip blank on the first `host/session-status(running:true)`, and treat `session.list` as the reconnect authority; cold summaries are never blank because lazy persistence keeps never-appended sessions out of `list()`.
 `session.search` is a bounded content-search projection over the sessions visible through `session.list`. The gateway asks the optional `ctx.sessionQuery` service for globally ranked current-surface user, assistant, and steering matches, consumes that stream until it has at most 20 visible session/snippet pairs plus one lookahead, and revalidates every hit against the list-derived authorization set before returning it. Provider pages start at 20 hits; when a first-page request rejects that limit, the gateway probes 10, 5, 2, then 1 and retains the learned size for continuation and stale-generation restarts. Returned snippets contain at most 240 Unicode code points, and the response schema independently enforces that bound at each client boundary. Keeping the authorization set in Host memory avoids SQLite's variable ceiling for large valid corpora without weakening visibility or ranking.
@@ -36,6 +36,8 @@
 待处理的 queued 输入属于实时控制平面契约，而非对话历史。网关根据持久 `agent/inbox/spliced` 变更派生完整的 `next-turn` 队列，并在每次变更后及重连时广播权威 `session/queue` 快照；待处理的 `next-step` steering（中途引导）不进入此 Web 投影。在 `next-step` 内，用户来源的消息携带 `steering` placement，而注入上下文（审批通知、任务完成、附加快照）携带 `context`，领取前不对外呈现。面向单条消息的 `agent/inbox/inserted`、`claimed` 与 `discarded` 通知仍供生命周期观察方使用，但不用于构建队列视图。`session.updateQueue` 通过 `MessageId` 寻址单个项；编辑和移除经已挂载 Agent 的 `Inbox.splice()` 修改队列。claim 的纯删除 splice 会在 pre-step 准入前赢得竞态，因此之后的操作返回 `queue-item-not-found`。`session.cancel` 仅中止活动轮次并保留待处理 inbox 工作；取消达到完全停稳且结束中的轮次完成 flush 后，AgentLoop 按 FIFO 顺序认领下一条可唤醒消息，浏览器绝不重发或提升它。队列操作绝不恢复冷会话，客户端也绝不根据轮次或状态事件推断某项已退出队列。
 后台任务沿用同一种实时推送姿态。当组合中有 `ctx.tasks` 时，网关订阅它的变更订阅，并在注册表每一次改变某个会话可见内容的提交后——注册、转入 stopping、结算，以及 owner 销毁时的移除——广播一份完整的 `session/tasks` 快照，另外为每个已经有任务的会话发送订阅 baseline（没有 baseline 即表示空集；把集合清空的那次变更仍然发送 `[]`）。带 owner 的变更通过那个确切的 `Agent` 读取，因此推送在其 scope 拆除期间依然正确；baseline 读 `ctx.agents.get(sessionId)`，对没有活体 Agent 的会话只得到无主任务，且绝不恢复冷会话。无主变更向每一个已订阅会话扇出，因为无主任务对所有调用方可见。线路上的 `TaskView` 丢弃 `ownerSession`、`reported` 和 `outputLimitBytes`：第一个由帧自身的 `sessionId` 携带，另外两个分别是内部通知位和模型呈现策略。没有该注册表的组合不发出这类帧。
 Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.create({ name })` 会在配置根目录下创建显示标题唯一的目录，而 `workspace.create({ path })` 会接纳已有的规范目录，并允许由 basename 派生的标题重复。`workspace.delete` 只移除 Workspace 注册记录，`session.create` 接受可选的预分配 Session id，`host/workspace-changed`、`host/workspace-removed` 与 `host/session-added` 则以任意到达顺序携带已提交的增量。`workspace.archiveSession` 向注册表级全局归档集合添加一个会话，并应答完整的更新后集合；`workspace.list` 携带该集合作为重连基线，`host/archived-sessions-changed` 在每次持久变更后推送完整快照。归档只把会话从各分组视图中隐藏，不触碰其日志和 workspace 记账；既非实时也未持久化的会话以 `session-not-found` 失败。删除注册记录会保留目录和会话日志；相关 Session 仍留在 `session.list` 中，并进入 Ungrouped。`SessionSummary.blank` 与 `host/session-added` 帧携带派生的零事件位：客户端隐藏空白会话并按 workspace 复用它们，在首个 `host/session-status(running:true)` 时翻转 blank，并以 `session.list` 作为重连权威；冷会话摘要永远不是空白：惰性持久化让从未追加过事件的会话根本不出现在 `list()` 中。
 `session.search` 是以 `session.list` 所列会话为范围的有界内容搜索投影。网关向可选的 `ctx.sessionQuery` 服务请求全局排序后的当前内容视图中的 user、assistant 和 steering 匹配项，并持续消费该结果流，直到获得至多 20 个可见会话／snippet 对及一个前瞻项；返回前仍会依据从列表推导的授权集合重新校验每个命中。提供方分页初始请求 20 个命中；如果第一页请求因这一上限被拒绝，网关会依次探测 10、5、2、1，并在续传和陈旧世代重启中沿用探测所得的页面大小。返回的 snippet 最多包含 240 个 Unicode 码点，响应 schema 则会在每个客户端边界独立强制执行该上限。将授权集合保留在宿主内存中，可在不削弱可见性或排序的前提下避开有效大型语料库的 SQLite 变量上限。
@@ -56,6 +56,7 @@
    "@deepseek-ai/dsh-settings": "workspace:^",
    "@deepseek-ai/dsh-skill": "workspace:^",
    "@deepseek-ai/dsh-subagent": "workspace:^",
    "@deepseek-ai/dsh-tasks": "workspace:^",
    "@deepseek-ai/dsh-tools": "workspace:^",
    "@deepseek-ai/dsh-user-approval": "workspace:^",
    "@deepseek-ai/dsh-user-interaction": "workspace:^",
@@ -30,7 +30,7 @@ import type {
  ApiProxy, ConfigurableProviderView, CredentialView, GoalRef, HistoryEntry, HostFrame,
  ModelCatalogFailure, ModelProviderGroup,
  ModelReasoning, MuxFrame, QuestionResponsePayload, SessionProjectionsBlock, SessionSearchItem,
-  QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, ToolEventView,
+  QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, TaskView, ToolEventView,
  WorkspaceId, WorkspaceView,
 } from './api/index.ts'
 import {
@@ -40,6 +40,9 @@ import {
 } from './api/session-search.ts'
 // Type-only: resolves `ctx.get('sessionProjections')` to the projection registry.
 import type {} from '@deepseek-ai/dsh-session-projection'
 // Type-only: resolves `ctx.get('tasks')` to the background task registry.
 import type {} from '@deepseek-ai/dsh-tasks'
 import type { TaskSnapshot } from '@deepseek-ai/dsh-tasks'
 // Type-only: resolves `ctx.get('sessionProjectionCache')` (the cold listing column).
 import type {} from '@deepseek-ai/dsh-session-projection-cache'
 // GoalError narrows domain rejections to their stable codes at the wire boundary.
@@ -261,6 +264,22 @@ function subscribeSession(queue: FrameQueue<RpcRequest<MuxFrame>>, session: Sess
  queue.push(frame({ type: 'session/subscribed', sessionId: session.id, lastSeq: session.seq - 1 }))
 }
 /**
 * Project registry snapshots onto the wire view, dropping the three internal
 * fields {@link TaskView} documents as absent.
 */
 function taskViews(snapshots: readonly TaskSnapshot[]): TaskView[] {
  return snapshots.map(task => ({
    id: task.id,
    kind: task.kind,
    label: task.label,
    status: task.status,
    ...task.detail === undefined ? {} : { detail: task.detail },
    startedAt: task.startedAt,
    ...task.finishedAt === undefined ? {} : { finishedAt: task.finishedAt },
  }))
 }
 /**
 * Whether the session's conversation has started: no turn has run yet (a
 * turn is one model-loop execution). Standalone plugin events — command
@@ -2586,6 +2605,19 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
            queue.push(frame({ type: 'session/queue', sessionId: session.id, items: queueItems(agent) }))
          }
        }
        // Background-task baseline. `ctx.agents.get` is the non-resuming read:
        // a session with no live Agent owns no tasks, so it correctly sees only
        // the unowned ones, and listing never revives a cold session. An empty
        // set sends nothing — absence is how the client reads "no tasks".
        const tasks = ctx.get('tasks')
        if (tasks !== undefined) {
          for (const session of ctx.sessions.list()) {
            const views = taskViews(tasks.list(ctx.agents.get(session.id)))
            if (views.length > 0) {
              queue.push(frame({ type: 'session/tasks', sessionId: session.id, tasks: views }))
            }
          }
        }
        // Per-session open-call table for result-view pairing. Bounded by the
        // per-turn call count: entries clear on turn/end; a table miss (stream
        // opened mid-turn) backscans the session's in-memory events instead.
@@ -2614,6 +2646,24 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
          ctx.on('session/disposed', (session: Session) => {
            openCalls.delete(session.id)
          }),
          ...tasks === undefined ? [] : [tasks.onTasksChanged((owner) => {
            if (owner !== undefined) {
              // The exact owner instance the fence compares against, so the
              // push stays correct even while that Agent's scope is tearing
              // down and a lookup by id would already miss.
              queue.push(frame({ type: 'session/tasks', sessionId: owner.id, tasks: taskViews(tasks.list(owner)) }))
              return
            }
            // An unowned task is visible to every caller, so every subscribed
            // session's set changed with it.
            for (const session of ctx.sessions.list()) {
              queue.push(frame({
                type: 'session/tasks',
                sessionId: session.id,
                tasks: taskViews(tasks.list(ctx.agents.get(session.id))),
              }))
            }
          })],
        ]
        return queue.iterate(signal, () => {
          muxQueues.delete(queue)
@@ -13,6 +13,7 @@ import { approvalRequestIdSchema } from './approvals.schema.ts'
 import {
  contentBlockSchema, messageIdSchema, sessionEventSchema, sessionIdSchema, toolEventViewSchema,
 } from './sessions.schema.ts'
 import { taskViewSchema } from './tasks.schema.ts'
 import { workspaceIdSchema, workspaceViewSchema } from './workspace.schema.ts'
 /** Question shape validated strictly against core dsh-user-interaction. */
@@ -58,6 +59,7 @@ export const muxFrameSchema = z.discriminatedUnion('type', [
      message: messageSchema,
    })),
  }),
  z.object({ type: z.literal('session/tasks'), sessionId: sessionIdSchema, tasks: z.array(taskViewSchema) }),
  // value stays wide: it already passed its unit's own schema on the host,
  // and deep-validating here would import every domain's schema into the carrier.
  z.object({ type: z.literal('session/projection'), sessionId: sessionIdSchema, key: z.string().min(1), value: z.unknown(), seq: z.number().int().nonnegative() }),
@@ -14,6 +14,7 @@ import type { CallId } from '@deepseek-ai/dsh-llm/brand'
 import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types'
 import type { ToolCallView, ToolResultView } from '@deepseek-ai/dsh-tools/presentation'
 import type { RpcError, RpcId, RpcRequest } from './rpc.ts'
 import type { TaskView } from './tasks.ts'
 import type { WorkspaceView } from './workspace.ts'
 // Client-side consumers take the render-intent vocabulary from the contract;
@@ -81,6 +82,20 @@ export type MuxFrame =
   * in QueueDock, while pending steering renders at the conversation tail.
   */
  | { type: 'session/queue'; sessionId: SessionId; items: QueuedInboxItem[] }
  /**
   * Complete set of background tasks this session can see, after every registry
   * commit that changes it: registration, the stopping transition, settlement,
   * and owner-disposal removal. The registry is process-local and holds no
   * durable event, so — exactly like `session/queue` — the whole snapshot is
   * what makes a start, a kill, a reconnect, and a second tab converge on one
   * authoritative value.
   *
   * Sent as a subscription baseline only for a session that currently has
   * tasks; an absent key means an empty set. A change that empties the set
   * still sends `[]`, since that transition is the only one absence cannot
   * express.
   */
  | { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] }
  /**
   * One projection unit's finished value changed (session-projection RFC).
   * Live push state, never logged — replay recomputes on the host (the
@@ -44,6 +44,7 @@ export type { DirectoryEntry, DirectoryListing, HostApi } from './host.ts'
 export type {
  SubagentAddress, SubagentCatalog, SubagentListEntry, SubagentPromptReceipt, SubagentsApi,
 } from './subagents.ts'
 export type { TaskView } from './tasks.ts'
 export type { WorkspaceApi, WorkspaceId, WorkspaceView } from './workspace.ts'
 export type { CommandsApi, CommandDescriptor } from './commands.ts'
 export type { SkillsApi, SkillEntry } from './skills.ts'
@@ -0,0 +1,33 @@
 /**
 * tasks domain zod schemas: the branded task id and the wire view carried by
 * `session/tasks` frames.
 */
 import { z } from 'zod'
 import type { TaskId } from '@deepseek-ai/dsh-tasks/brand'
 import type { TaskView } from './tasks.ts'
 import type { Wire } from './rpc.schema.ts'
 /** TaskId: one brand cast after non-empty string validation. */
 export const taskIdSchema = z.string().min(1) as unknown as z.ZodType<TaskId>
 /**
 * One wire task view. `kind` stays an open string because producer plugins
 * extend the registry's kind map by declaration merging, so the closed set is
 * not knowable at this boundary.
 */
 export const taskViewSchema = z.object({
  id: taskIdSchema,
  kind: z.string().min(1),
  label: z.string().min(1),
  status: z.union([
    z.literal('running'),
    z.literal('stopping'),
    z.literal('completed'),
    z.literal('killed'),
    z.literal('failed'),
  ]),
  detail: z.string().optional(),
  startedAt: z.number().int().nonnegative(),
  finishedAt: z.number().int().nonnegative().optional(),
 }) satisfies z.ZodType<Wire<TaskView>>
@@ -0,0 +1,36 @@
 /**
 * Browser-safe background-task domain contract. The registry's live records
 * never cross the wire; a view is the subset a human list needs, minted fresh
 * per push.
 */
 import type { TaskId } from '@deepseek-ai/dsh-tasks/brand'
 /**
 * One background task as the client sees it.
 *
 * Three registry fields are deliberately absent. `ownerSession` is redundant
 * beside the frame's own `sessionId`; `reported` is an internal notice-delivery
 * bit with no user meaning; `outputLimitBytes` is producer-owned model
 * presentation policy that never reaches a human surface.
 */
 export interface TaskView {
  /** Registry-issued `<kind>-N` identity, stable for the task's whole life. */
  id: TaskId
  /**
   * Producer kind (`bash`, `pwsh`, `pty-send`, `subagent`, …). Kept as a bare
   * string because producer plugins extend the kind map by declaration merging,
   * so no client build can enumerate the closed set.
   */
  kind: string
  /** Producer-supplied one-line label: the command, or the delegation description. */
  label: string
  /** Current lifecycle state. */
  status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed'
  /** Kind-specific status detail ('exit code: 3'), present once the producer supplied one. */
  detail?: string
  /** Epoch ms when the task was registered. */
  startedAt: number
  /** Epoch ms when the task settled; absent while live. */
  finishedAt?: number
 }
@@ -0,0 +1,206 @@
 /**
 * Background-task carrier paths of the host ApiProxy: the subscription
 * baseline is sent only for a session that has tasks, every registry change
 * pushes that owner's whole set, an unowned change fans out to every
 * subscribed session, the projection drops the three internal snapshot
 * fields, a composition without `ctx.tasks` emits nothing, and listing never
 * resumes a cold session.
 */
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import AgentRegistry, { Inbox } from '@deepseek-ai/dsh-agent'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
 import type { Session } from '@deepseek-ai/dsh-session'
 import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
 import LocalTaskService from '@deepseek-ai/dsh-tasks-local'
 import type { TaskOutcome } from '@deepseek-ai/dsh-tasks'
 import type { MuxFrame, RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api'
 import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
 import { createApiProxy } from '@deepseek-ai/dsh-host-apiproxy'
 type TaskFrame = Extract<MuxFrame, { type: 'session/tasks' }>
 /**
 * A producer whose settlement the test drives. `cancel` deliberately does not
 * settle, so a kill is observable as the distinct `stopping` step before the
 * test supplies the terminal outcome and its detail.
 */
 function producer(label = 'sleep 60') {
  let settle!: (outcome: TaskOutcome) => void
  const spec = {
    kind: 'bash' as const,
    label,
    run: () => ({
      cancel: () => {},
      done: new Promise<TaskOutcome>((resolve) => { settle = resolve }),
    }),
  }
  return { spec, settle: (outcome: TaskOutcome) => { settle(outcome) } }
 }
 async function harness(withRegistry: boolean): Promise<{ ctx: Context; session: Session; agent: Agent }> {
  const ctx = new Context()
  await ctx.plugin(SessionStore)
  await ctx.plugin(UserInteractionService)
  await ctx.plugin(AgentRegistry)
  if (withRegistry) {
    await ctx.plugin(LocalTaskService)
    ctx.tasks.attachSurface('api-proxy-test')
  }
  const session = ctx.sessions.create()
  const agent = {
    id: session.id,
    session,
    inbox: new Inbox(session, { inserted: () => {}, discarded: () => {}, claimed: () => {} }),
    status: 'idle',
    ctx,
  } as Agent
  ctx.agents.register(agent)
  return { ctx, session, agent }
 }
 const api = (ctx: Context) => createApiProxy(ctx, { defaultTarget: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp', workspaceRoot: '/tmp' })
 /** Drain the mux until `count` session/tasks frames arrived, then abort. */
 async function collect(
  iterable: AsyncIterable<RpcRequest<MuxFrame>>,
  count: number,
  abort: AbortController,
 ): Promise<TaskFrame[]> {
  const frames: MuxFrame[] = []
  for await (const envelope of iterable) {
    frames.push(envelope.payload)
    if (frames.filter(frame => frame.type === 'session/tasks').length >= count) abort.abort()
  }
  return frames.filter((frame): frame is TaskFrame => frame.type === 'session/tasks')
 }
 describe('session/tasks subscription baseline', () => {
  it('is omitted for a session with no tasks — absence is the empty set', async () => {
    const { ctx, session } = await harness(true)
    const abort = new AbortController()
    const stream = api(ctx).events.mux({ rpcId: RpcId('t-tasks-empty'), payload: {} }, abort.signal)
    const frames: MuxFrame[] = []
    const drained = (async () => {
      for await (const envelope of stream) {
        frames.push(envelope.payload)
        if (frames.some(frame => frame.type === 'session/subscribed')) abort.abort()
      }
    })()
    await drained
    expect(frames.some(frame => frame.type === 'session/tasks')).toBe(false)
    expect(frames.some(frame => frame.type === 'session/subscribed')).toBe(true)
    void session
  })
  it('carries the live set for a session that already has tasks when the stream opens', async () => {
    const { ctx, session, agent } = await harness(true)
    ctx.tasks.start({ ...producer('pnpm run build').spec, owner: agent })
    const abort = new AbortController()
    const stream = api(ctx).events.mux({ rpcId: RpcId('t-tasks-baseline'), payload: {} }, abort.signal)
    const [baseline] = await collect(stream, 1, abort)
    expect(baseline?.sessionId).toBe(session.id)
    expect(baseline?.tasks).toHaveLength(1)
    const [task] = baseline?.tasks ?? []
    expect(task?.startedAt).toBeTypeOf('number')
    expect({ ...task, startedAt: 0 }).toEqual({
      id: 'bash-1',
      kind: 'bash',
      label: 'pnpm run build',
      status: 'running',
      startedAt: 0,
    })
  })
 })
 describe('session/tasks change pushes', () => {
  it('pushes the owner\'s whole set on registration, stopping, and settlement', async () => {
    const { ctx, session, agent } = await harness(true)
    const proxy = api(ctx)
    const abort = new AbortController()
    const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-changes'), payload: {} }, abort.signal)
    const collected = collect(stream, 3, abort)
    const p = producer()
    const id = ctx.tasks.start({ ...p.spec, owner: agent })
    ctx.tasks.kill(id, agent, 'test')
    p.settle({ status: 'killed', detail: 'signal: SIGTERM' })
    const frames = await collected
    expect(frames.map(frame => frame.sessionId)).toEqual([session.id, session.id, session.id])
    expect(frames.map(frame => frame.tasks[0]?.status)).toEqual(['running', 'stopping', 'killed'])
    // Terminal detail rides the same whole-set push; no separate signal.
    expect(frames[2]?.tasks[0]?.detail).toBe('signal: SIGTERM')
    expect(frames[2]?.tasks[0]?.finishedAt).toBeTypeOf('number')
  })
  it('drops ownerSession, reported, and outputLimitBytes from the wire view', async () => {
    const { ctx, agent } = await harness(true)
    const proxy = api(ctx)
    const abort = new AbortController()
    const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-fields'), payload: {} }, abort.signal)
    const collected = collect(stream, 1, abort)
    ctx.tasks.start({ ...producer().spec, owner: agent, outputLimitBytes: 1_024 })
    const [frame] = await collected
    const fields: readonly string[] = Object.keys(frame?.tasks[0] ?? {})
    expect([...fields].sort()).toEqual(['id', 'kind', 'label', 'startedAt', 'status'])
  })
  it('fans an unowned change out to every subscribed session', async () => {
    const { ctx } = await harness(true)
    const second = ctx.sessions.create()
    const proxy = api(ctx)
    const abort = new AbortController()
    const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-unowned'), payload: {} }, abort.signal)
    const collected = collect(stream, 2, abort)
    ctx.tasks.start(producer('open to every caller').spec)
    const frames = await collected
    expect(new Set(frames.map(frame => frame.sessionId)).size).toBe(2)
    expect(frames.some(frame => frame.sessionId === second.id)).toBe(true)
    for (const frame of frames) expect(frame.tasks[0]?.label).toBe('open to every caller')
  })
  it('serves a cold session the unowned set without resuming it', async () => {
    const { ctx } = await harness(true)
    const coldId = SessionId('session-cold-tasks')
    let loaded = false
    ctx.provide('sessionPersistence', {
      list: async () => [{ version: 0, id: coldId, createdAt: 5, cwd: '/tmp' }],
      locate: () => undefined,
      load: () => { loaded = true; throw new Error('task listing must not load a cold log') },
    } as never)
    const proxy = api(ctx)
    const abort = new AbortController()
    const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-cold'), payload: {} }, abort.signal)
    const collected = collect(stream, 1, abort)
    ctx.tasks.start(producer().spec)
    await collected
    expect(loaded).toBe(false)
    expect(ctx.agents.get(coldId)).toBeUndefined()
  })
 })
 describe('session/tasks without the registry', () => {
  it('emits no frames at all, so the client renders no entry point', async () => {
    const { ctx, session } = await harness(false)
    const proxy = api(ctx)
    const abort = new AbortController()
    const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-absent'), payload: {} }, abort.signal)
    const frames: MuxFrame[] = []
    const drained = (async () => {
      for await (const envelope of stream) {
        frames.push(envelope.payload)
        if (frames.filter(frame => frame.type === 'session/event').length >= 1) abort.abort()
      }
    })()
    session.append('turn/start', { turn: 1 })
    await drained
    expect(frames.some(frame => frame.type === 'session/tasks')).toBe(false)
  })
 })
@@ -433,6 +433,11 @@ describe('events frame schemas', () => {
        },
      ] },
      { type: 'session/projection', sessionId: 's', key: 'todos', value: [{ content: 'x', status: 'pending' }], seq: 7 },
      { type: 'session/tasks', sessionId: 's', tasks: [] },
      { type: 'session/tasks', sessionId: 's', tasks: [
        { id: 'bash-1', kind: 'bash', label: 'pnpm run build', status: 'running', startedAt: 5 },
        { id: 'pty-send-2', kind: 'pty-send', label: 'send keys', status: 'failed', detail: 'exit code: 3', startedAt: 5, finishedAt: 9 },
      ] },
      { type: 'stream/error', error: { code: 'internal', message: 'm', details: {} } },
    ]
    for (const frame of frames) expect(muxFrameSchema.parse(frame)).toMatchObject({ type: frame.type })
@@ -441,6 +446,14 @@ describe('events frame schemas', () => {
      { type: 'session/projection', sessionId: 's', key: '', value: null, seq: 0 },
      { type: 'session/projection', sessionId: 's', key: 'todos', value: null, seq: -1 },
      { type: 'session/projection', sessionId: 's', key: 'todos', value: null, seq: 0.5 },
      // A producer kind stays an open string, but the closed status set and
      // the identity/label bounds are the carrier's own wire contract.
      { type: 'session/tasks', sessionId: 's', tasks: [{ id: '', kind: 'bash', label: 'l', status: 'running', startedAt: 0 }] },
      { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: '', label: 'l', status: 'running', startedAt: 0 }] },
      { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: '', status: 'running', startedAt: 0 }] },
      { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: 'l', status: 'pending', startedAt: 0 }] },
      { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: 'l', status: 'running', startedAt: -1 }] },
      { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: 'l', status: 'completed', startedAt: 0, finishedAt: 0.5 }] },
    ]) expect(() => muxFrameSchema.parse(invalid)).toThrow()
    expect(askUserQuestionItemSchema.parse({ id: 'q', question: 'Q?' }).id).toBe('q')
  })
@@ -65,6 +65,9 @@
    {
      "path": "../../skill/skill"
    },
    {
      "path": "../../tasks/tasks"
    },
    {
      "path": "../../ui/commands"
    },
@@ -13,7 +13,10 @@ import { Context } from 'cordis'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { deadline, timeoutOf } from '@deepseek-ai/dsh-timeout'
 import { TaskService, TaskId } from '@deepseek-ai/dsh-tasks'
-import type { TaskDoneListener, TaskKind, TaskOutcome, TaskRead, TaskSnapshot, TaskStart, TaskStatus } from '@deepseek-ai/dsh-tasks'
+import type {
  TaskDoneListener, TaskKind, TaskOutcome, TaskRead, TaskSnapshot, TaskStart, TaskStatus,
  TasksChangedListener,
 } from '@deepseek-ai/dsh-tasks'
 /** Timeout code that distinguishes a bounded wait from caller cancellation. */
 export const TASK_WAIT_TIMEOUT = 'TASK_WAIT_TIMEOUT'
@@ -59,6 +62,7 @@ export class LocalTaskService extends TaskService {
  private counters = new Map<string, number>()
  private surfaces = new Set<symbol>()
  private listeners = new Set<TaskDoneListener>()
  private changeListeners = new Set<TasksChangedListener>()
  private listenersClosed = false
  /** Owner agents with attached scope cleanup, mapped to the exact disposer. */
  private ownerCleanups = new Map<Agent, () => Promise<void> | void>()
@@ -119,6 +123,9 @@ export class LocalTaskService extends TaskService {
        this.settle(task, { status: 'failed', detail: String(error) })
      },
    )
    // Registration is complete and cannot fail from here, so the visible set
    // has genuinely changed.
    this.notifyChanged(task.owner)
    return id
  }
@@ -156,6 +163,7 @@ export class LocalTaskService extends TaskService {
    task.cancel(reason)
    task.status = 'stopping'
    task.reported = true
    this.notifyChanged(task.owner)
    return 'requested'
  }
@@ -217,6 +225,14 @@ export class LocalTaskService extends TaskService {
    return () => void dispose()
  }
  onTasksChanged(listener: TasksChangedListener): () => void {
    const dispose = this.ctx.effect(() => {
      this.changeListeners.add(listener)
      return () => this.changeListeners.delete(listener)
    }, 'tasks.onTasksChanged()')
    return () => void dispose()
  }
  attachSurface(name: string): () => void {
    // One token per call keeps duplicate labels independently disposable.
    const token = Symbol(name)
@@ -262,6 +278,20 @@ export class LocalTaskService extends TaskService {
    }
  }
  /**
   * Announce that one owner's visible set changed. Each listener is contained
   * so an observer cannot break a lifecycle commit that already happened.
   */
  private notifyChanged(owner: Agent | undefined): void {
    for (const listener of this.changeListeners) {
      try {
        listener(owner)
      } catch (error: unknown) {
        this.selfCtx.logger.warn(`tasks: onTasksChanged listener threw: ${String(error)}`)
      }
    }
  }
  /**
   * Record the first terminal outcome, notify contained listeners, and release
   * waiters. First-wins preserves a teardown force-failure against late producer
@@ -291,6 +321,7 @@ export class LocalTaskService extends TaskService {
    task.waitResolvers.clear()
    for (const resolveWait of waitResolvers) resolveWait()
    task.markSettled()
    this.notifyChanged(task.owner)
  }
  /**
@@ -323,6 +354,9 @@ export class LocalTaskService extends TaskService {
    this.cancelForTeardown(owned, 'owner disposed')
    await Promise.all(owned.map(task => task.settled))
    for (const task of owned) this.store.delete(task.id)
    // Removal is the one visible-set change no per-task record carries, so it
    // must be announced here or an observer keeps the dropped rows forever.
    if (owned.length > 0) this.notifyChanged(owner)
  }
  /**
@@ -336,6 +370,11 @@ export class LocalTaskService extends TaskService {
    this.cancelForTeardown(all, 'tasks service disposed')
    await Promise.all(all.map(task => task.settled))
    this.store.clear()
    // No change notification here: every `onTasksChanged` registration is an
    // effect on this service's own fiber, so the listeners are already gone by
    // the time service teardown reaches this line. An observer learns the
    // registry left through its own disposal, not through a final empty set.
    this.changeListeners.clear()
    // Detach cross-fiber owner effects after the shared store is quiescent.
    const ownerCleanups = [...this.ownerCleanups.values()]
    this.ownerCleanups.clear()
@@ -760,3 +760,96 @@ describe('LocalTaskService disposal', () => {
    expect(() => ctx.tasks.start(producer().spec)).toThrow('no control surface is attached')
  })
 })
 describe('LocalTaskService.onTasksChanged', () => {
  it('fires after registration, the stopping transition, and settlement', async () => {
    const ctx = await harness()
    const owner = stubAgent(ctx, 'alice')
    ctx.agents.register(owner)
    const seen: (string | undefined)[] = []
    ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id))
    const p = producer({ owner })
    const id = ctx.tasks.start(p.spec)
    // Registration is announced only once the record is readable.
    expect(seen).toEqual(['alice'])
    expect(ctx.tasks.list(owner)).toHaveLength(1)
    expect(ctx.tasks.kill(id, owner)).toBe('requested')
    expect(seen).toEqual(['alice', 'alice'])
    expect(ctx.tasks.get(id, owner).status).toBe('stopping')
    p.settle({ status: 'killed' })
    await tick()
    expect(seen).toEqual(['alice', 'alice', 'alice'])
    expect(ctx.tasks.get(id, owner).status).toBe('killed')
    await disposeAgentScope(owner)
  })
  it('reports an unowned change as undefined, since every caller can see it', async () => {
    const ctx = await harness()
    const seen: (string | undefined)[] = []
    ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id))
    ctx.tasks.start(producer().spec)
    expect(seen).toEqual([undefined])
  })
  it('announces the owner-disposal removal, and stays silent when that owner had none', async () => {
    const ctx = await harness()
    const owner = stubAgent(ctx, 'alice')
    const bystander = stubAgent(ctx, 'bob')
    ctx.agents.register(owner)
    ctx.agents.register(bystander)
    const p = producer({ owner })
    ctx.tasks.start(p.spec)
    const seen: (string | undefined)[] = []
    ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id))
    p.settle({ status: 'completed' })
    await tick()
    expect(seen).toEqual(['alice'])
    // Disposing an owner with no records changes no visible set.
    await disposeAgentScope(bystander)
    expect(seen).toEqual(['alice'])
    await disposeAgentScope(owner)
    expect(seen).toEqual(['alice', 'alice'])
    expect(ctx.tasks.list(owner)).toEqual([])
  })
  it('contains a throwing listener so the lifecycle commit still stands', async () => {
    const ctx = await harness()
    const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {})
    const seen: (string | undefined)[] = []
    ctx.tasks.onTasksChanged(() => { throw new Error('observer boom') })
    ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id))
    const id = ctx.tasks.start(producer().spec)
    expect(id).toBe('bash-1')
    expect(seen).toEqual([undefined])
    expect(warn).toHaveBeenCalledWith(expect.stringContaining('onTasksChanged listener threw'))
  })
  it('unregisters through its disposer and with its fiber (HMR safety)', async () => {
    const ctx = await harness()
    const seen: number[] = []
    const detach = ctx.tasks.onTasksChanged(() => void seen.push(1))
    const fiber = await ctx.plugin(Object.assign((inner: Context) => {
      inner.tasks.onTasksChanged(() => void seen.push(2))
    }, { inject: ['tasks'] }))
    ctx.tasks.start(producer().spec)
    expect(seen).toEqual([1, 2])
    detach()
    detach() // second call of the same disposer is a no-op
    ctx.tasks.start(producer().spec)
    expect(seen).toEqual([1, 2, 2])
    await fiber.dispose()
    ctx.tasks.start(producer().spec)
    expect(seen).toEqual([1, 2, 2])
  })
 })
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/tasks/tasks/README.md
-README.md: 2f822bad139020f0ebae0165aa4e8893853f635d
+README.md: e7431cca0956429788274b0d44a249dd1e374156
-README.zh.md: fdc619fbb46267b2ae550c85cb14fcf8a916f638
+README.zh.md: e8c1162f66471eee3c04111c8617dd84295dc6cf
@@ -12,6 +12,7 @@ The background task registry seam (`ctx.tasks`). The abstract `TaskService` and
 - `kill(id, caller?, reason?)` invokes producer cancellation before changing status. A cancellation throw leaves the task running; success changes it to `stopping` and marks terminal delivery reported.
 - `wait(id, timeoutMs, caller?, signal?)` returns a terminal snapshot or the live snapshot at timeout. Aborting stops only the wait; settlement wins once it has committed terminal delivery to that waiter.
 - `onTaskDone(listener)` observes each terminal record with the exact owner. Listener throws and rejections are contained; listener work is not awaited.
 - `onTasksChanged(listener)` observes visible-set changes — registration, the stopping transition, settlement, and owner-disposal removal — carrying only the owner whose set moved, or `undefined` when an unowned task changed and every caller's set moved with it. It is owner-granular because removal is a change no per-task record can express, and it is not a superset of `onTaskDone`: it carries no delivery meaning and marks nothing reported.
 - `attachSurface(name)` declares a control surface for its effect lifetime. `start()` fails before producer execution when none is attached.
 Owned access compares the task's `SessionId` with the caller's. Ids such as `bash-1` are predictable, so this fence is the boundary. Unowned tasks are open to callers and last until service disposal.
@@ -12,6 +12,7 @@
 - `kill(id, caller?, reason?)` 在更改状态前调用生产方取消。取消抛出异常时任务保持运行；成功则把状态改为 `stopping`，并将终止交付标记为已报告。
 - `wait(id, timeoutMs, caller?, signal?)` 返回终止快照，或在超时时返回存活快照。中止只会停止等待；一旦终止交付已向该等待方提交，终止结果优先。
 - `onTaskDone(listener)` 观察每条终止记录及其精确 owner。监听器抛出的异常和产生的拒绝都会被隔离；系统不会等待监听器工作。
 - `onTasksChanged(listener)` 观察可见集合的变化——注册、转入 stopping、结算，以及 owner 销毁时的移除——只携带集合发生变化的那个 owner，或在无主任务变化、因而每个调用方的集合都随之变化时携带 `undefined`。它按 owner 分粒度，因为移除是任何逐任务记录都无法表达的变化；它也不是 `onTaskDone` 的超集：它不含任何投递含义，也不把任何东西标为已上报。
 - `attachSurface(name)` 在其 effect 生命周期内声明控制表层。如果没有附加任何表层，`start()` 会在生产方执行前失败。
 有 owner 的访问会比较任务的 `SessionId` 与调用方。`bash-1` 等 id 可预测，因此这道隔离是安全边界。无 owner 的任务向调用方开放，并持续到服务释放。
@@ -15,12 +15,17 @@
      "types": "./lib/types/invariant.d.ts",
      "default": "./lib/invariant.js"
    },
    "./brand": {
      "types": "./lib/types/brand.d.ts",
      "default": "./lib/types/brand.js"
    },
    "./src/*": "./src/*",
    "./package.json": "./package.json"
  },
  "files": [
    "lib/index.js",
    "lib/invariant.js",
    "lib/types/**/*.js",
    "lib/types/**/*.d.ts"
  ],
  "license": "BSD-3-Clause",
@@ -0,0 +1,28 @@
 /**
 * dsh-tasks' owned branded id, carried across the registry, the model-facing
 * control surface, and the client wire.
 *
 * It lives in its own leaf because the package root and `./types` both reach
 * `dsh-agent` through the owner and listener signatures, which a Client program
 * cannot resolve even as a type. A browser-safe consumer imports the id here;
 * `Branded<B>` itself comes from the zero-dependency `@deepseek-ai/dsh-brand`.
 *
 * @module @deepseek-ai/dsh-tasks/brand
 */
 import type { Branded } from '@deepseek-ai/dsh-brand'
 /**
 * Identifies a background task. The registry generates `<kind>-N`; predictable
 * ids rely on owner authorization rather than secrecy.
 */
 export type TaskId = Branded<'TaskId'>
 /**
 * Brand a string as a {@link TaskId}.
 * @param id - the raw task-id string (the registry generates `<kind>-N`).
 * @returns the same string, branded; no validation is performed.
 */
 export function TaskId(id: string): TaskId {
  return id as TaskId
 }
@@ -8,7 +8,9 @@
 import { Context, Service } from 'cordis'
 import type { Agent } from '@deepseek-ai/dsh-agent'
-import type { TaskDoneListener, TaskId, TaskRead, TaskSnapshot, TaskStart } from './types.ts'
+import type {
  TaskDoneListener, TaskId, TaskRead, TaskSnapshot, TaskStart, TasksChangedListener,
 } from './types.ts'
 export { TaskId } from './types.ts'
 export type {
@@ -21,6 +23,7 @@ export type {
  TaskSnapshot,
  TaskStart,
  TaskStatus,
  TasksChangedListener,
 } from './types.ts'
 declare module 'cordis' {
@@ -129,6 +132,22 @@ export abstract class TaskService extends Service {
   */
  abstract onTaskDone(listener: TaskDoneListener): () => void
  /**
   * Register an effect-scoped observer of visible-set changes. It fires after
   * every commit that changes what {@link list} returns for that owner —
   * registration, the stopping transition, settlement, and owner-disposal
   * removal — so an observer re-reads rather than accumulating deltas.
   *
   * This is not a superset of {@link onTaskDone}: that one delivers the terminal
   * record under first-wins semantics a control surface couples to notice
   * delivery, while this one carries no delivery meaning and marks nothing
   * reported. Listeners are contained and never awaited.
   * @param listener - receives the owner whose visible set changed, or
   *   `undefined` when an unowned task changed and every caller's set did.
   * @returns disposer that unregisters the listener.
   */
  abstract onTasksChanged(listener: TasksChangedListener): () => void
  /**
   * Attach an effect-scoped surface that can read and stop tasks. {@link start}
   * refuses work while none is attached.
@@ -4,24 +4,11 @@
 * @module @deepseek-ai/dsh-tasks/types
 */
 import type { Branded } from '@deepseek-ai/dsh-brand'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import type { SessionId } from '@deepseek-ai/dsh-session'
 import type { TaskId } from './brand.ts'
-/**
+export { TaskId } from './brand.ts'
 * Identifies a background task. The registry generates `<kind>-N`; predictable
 * ids rely on owner authorization rather than secrecy.
 */
 export type TaskId = Branded<'TaskId'>
 /**
 * Brand a string as a {@link TaskId}.
 * @param id - the raw task-id string (the registry generates `<kind>-N`).
 * @returns the same string, branded; no validation is performed.
 */
 export function TaskId(id: string): TaskId {
  return id as TaskId
 }
 /**
 * Task lifecycle: `running`, optionally `stopping`, then exactly one terminal
@@ -157,3 +144,14 @@ export type TaskDoneListener = (
  snapshot: TaskSnapshot,
  owner: Agent | undefined,
 ) => void | PromiseLike<void>
 /**
 * Observation callback for a change to what one owner's {@link TaskService.list}
 * would return. It is owner-granular rather than task-granular because the
 * change may be a removal, which no per-task record can express, and because
 * its consumers re-read the whole visible set anyway.
 *
 * An `undefined` owner means an unowned task changed, so every caller's visible
 * set changed with it.
 */
 export type TasksChangedListener = (owner: Agent | undefined) => void
@@ -2,7 +2,9 @@ import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import { TaskId, TaskService } from '@deepseek-ai/dsh-tasks'
-import type { TaskDoneListener, TaskRead, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks'
+import type {
  TaskDoneListener, TaskRead, TaskSnapshot, TaskStart, TasksChangedListener,
 } from '@deepseek-ai/dsh-tasks'
 /**
 * Minimal concrete registry: one canned record. The seam owns the contract
@@ -50,6 +52,10 @@ class StubTaskService extends TaskService {
    return () => {}
  }
  onTasksChanged(_listener: TasksChangedListener): () => void {
    return () => {}
  }
  attachSurface(_name: string): () => void {
    return () => {}
  }
@@ -70,6 +76,8 @@ describe('TaskService seam', () => {
    await expect(ctx.tasks.wait(id, 5)).resolves.toMatchObject({ id })
    const detachListener = ctx.tasks.onTaskDone(() => {})
    detachListener()
    const detachChanges = ctx.tasks.onTasksChanged(() => {})
    detachChanges()
    detachSurface()
  })
@@ -1281,6 +1281,9 @@ importers:
      '@deepseek-ai/dsh-client-ui-subagent':
        specifier: workspace:^
        version: link:../../client/ui-subagent
      '@deepseek-ai/dsh-client-ui-task':
        specifier: workspace:^
        version: link:../../client/ui-task
      '@deepseek-ai/dsh-client-ui-theme':
        specifier: workspace:^
        version: link:../../client/ui-theme
@@ -2324,6 +2327,40 @@ importers:
        specifier: ^4.0.0-rc.7
        version: link:../../../vendor/cordis
  packages/client/ui-task:
    dependencies:
      react:
        specifier: ^18.2.0
        version: 18.3.1
    devDependencies:
      '@deepseek-ai/dsh-client-locale':
        specifier: workspace:^
        version: link:../locale
      '@deepseek-ai/dsh-client-runtime':
        specifier: workspace:^
        version: link:../runtime
      '@deepseek-ai/dsh-client-test-runtime':
        specifier: workspace:^
        version: link:../test-runtime
      '@deepseek-ai/dsh-client-ui-conversation':
        specifier: workspace:^
        version: link:../ui-conversation
      '@deepseek-ai/dsh-client-ui-primitives':
        specifier: workspace:^
        version: link:../ui-primitives
      '@deepseek-ai/dsh-client-ui-slots':
        specifier: workspace:^
        version: link:../ui-slots
      '@deepseek-ai/dsh-invariants':
        specifier: workspace:^
        version: link:../../support/invariants
      '@types/react':
        specifier: ~18.3.1
        version: 18.3.31
      cordis:
        specifier: ^4.0.0-rc.7
        version: link:../../../vendor/cordis
  packages/client/ui-theme:
    dependencies:
      clsx:
@@ -3898,6 +3935,9 @@ importers:
      '@deepseek-ai/dsh-subagent':
        specifier: workspace:^
        version: link:../../subagent/subagent
      '@deepseek-ai/dsh-tasks':
        specifier: workspace:^
        version: link:../../tasks/tasks
      '@deepseek-ai/dsh-tools':
        specifier: workspace:^
        version: link:../../core/tools
@@ -191,6 +191,7 @@ export const LINK_MAP: Readonly<Record<string, string>> = {
  TaskRead: 'tasks.md',
  TaskSnapshot: 'tasks.md',
  TaskStart: 'tasks.md',
  TasksChangedListener: 'tasks.md',
  TokenMeasurement: 'token-meter.md',
  CodeDispatchLog: 'tools.md',
  PostToolDecision: 'tools.md',
@@ -65,6 +65,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly<Record<string, SentenceContract>> = {
  'packages/client/ui-conversation': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' },
  'packages/client/ui-tool': { kind: 'none', reason: 'Browser-side Tool presentation layer; renders logged calls without changing model context.' },
  'packages/client/ui-deliverables': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' },
  'packages/client/ui-task': { kind: 'none', reason: 'Browser-side read-only projection of ctx.tasks records; dsh-tool-tasks owns the model-facing surface.' },
  'packages/client/ui-slash': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' },
  'packages/client/ui-command': { kind: 'indirect', reason: 'The dispatch paths trigger the host command.execute RPC; each command handler\'s host package owns any model-visible effect.' },
  'packages/client/ui-model': { kind: 'indirect', reason: 'Selection routes session.selectModel; the host snapshots the target at the next prompt-assembly boundary and owns the model-visible effect.' },
@@ -71,6 +71,7 @@
      "@deepseek-ai/dsh-llm-retry/types": ["./packages/llm/llm-retry/src/types.ts"],
      "@deepseek-ai/dsh-llm/message": ["./packages/llm/llm/src/message.ts"],
      "@deepseek-ai/dsh-commands/brand": ["./packages/ui/commands/src/brand.ts"],
      "@deepseek-ai/dsh-tasks/brand": ["./packages/tasks/tasks/src/brand.ts"],
      "@deepseek-ai/dsh-compact/checkpoint": ["./packages/compact/compact/src/checkpoint.ts"],
      "@deepseek-ai/dsh-tools/presentation": ["./packages/core/tools/src/presentation.ts"],
      "@deepseek-ai/dsh-tool-subagent-control/list-agents": ["./packages/subagent/tool-subagent-control/src/list-agents.ts"],
@@ -171,6 +172,7 @@
      "@deepseek-ai/dsh-client-ui-permission": ["./packages/client/ui-permission/src"],
      "@deepseek-ai/dsh-client-ui-skill": ["./packages/client/ui-skill/src"],
      "@deepseek-ai/dsh-client-ui-subagent": ["./packages/client/ui-subagent/src"],
      "@deepseek-ai/dsh-client-ui-task": ["./packages/client/ui-task/src"],
      "@deepseek-ai/dsh-client-ui-plan": ["./packages/client/ui-plan/src"],
      "@deepseek-ai/dsh-client-ui-question": ["./packages/client/ui-question/src"],
      "@deepseek-ai/dsh-client-ui-trajectory": ["./packages/client/ui-trajectory/src"],
@@ -66,6 +66,7 @@
    { "path": "./packages/client/ui-command" },
    { "path": "./packages/client/ui-skill" },
    { "path": "./packages/client/ui-subagent" },
    { "path": "./packages/client/ui-task" },
    { "path": "./packages/client/ui-goal" },
    { "path": "./packages/client/ui-model" },
    { "path": "./packages/client/ui-permission" },
@@ -54,6 +54,7 @@
    "apps/web/tests/produced-files.e2e.ts",
    "apps/web/tests/subagent-conversation.e2e.ts",
    "apps/web/tests/sidebar-subagent-activity.e2e.ts",
    "apps/web/tests/background-task-list.e2e.ts",
    "apps/web/tests/bash-abort-row.e2e.ts",
    "apps/web/tests/skill-tool-row.e2e.ts",
    "apps/web/tests/turn-tail-actions.e2e.ts",
		`@@ -0,0 +1,2 @@`
							`- list "Background tasks":`
							`- listitem: bash sleep 45 running {{duration}}`
		`@@ -0,0 +1,2 @@`
							`- list "Background tasks":`
							`- listitem: "bash sleep 45 signal: SIGTERM {{duration}}"`
`@@ -151,4 +151,4 @@ interface TaskRead {`

	`## Service behavior`	`## Service behavior`

	The abstract [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam defines atomic `start`, caller-scoped `get` and `list`, `read`, `kill`, bounded `wait`, contained `onTaskDone` listeners, and the `attachSurface` availability fence; [`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) is the process-local implementation. Authorization compares owner sessions; owner cleanup selects the exact registered `Agent` instance. See [`dsh-tasks`](../../packages/tasks/tasks/README.md) for the seam contract, [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md) for the registry lifecycle, and [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md) for the model-facing surface.	The abstract [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam defines atomic `start`, caller-scoped `get` and `list`, `read`, `kill`, bounded `wait`, contained `onTaskDone` and `onTasksChanged` listeners, and the `attachSurface` availability fence; [`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) is the process-local implementation. The two listener kinds are not nested: `onTaskDone` delivers one terminal record under first-wins semantics a control surface couples to notice delivery, while `onTasksChanged` observes every visible-set change — registration, the stopping transition, settlement, and owner-disposal removal — carrying only the owner whose set moved, or `undefined` when an unowned task changed and every caller's set moved with it. Authorization compares owner sessions; owner cleanup selects the exact registered `Agent` instance. See [`dsh-tasks`](../../packages/tasks/tasks/README.md) for the seam contract, [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md) for the registry lifecycle, and [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md) for the model-facing surface.
`@@ -151,4 +151,4 @@ interface TaskRead {`

	`## 服务行为`	`## 服务行为`

	抽象的 [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam 定义原子 `start`、限定调用方作用域的 `get` 和 `list`、`read`、`kill`、有界 `wait`、故障隔离的 `onTaskDone` 监听器，以及 `attachSurface` 可用性防线；[`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) 是其进程局部实现。授权会比较拥有者会话；拥有者清理会选择确切的已注册 `Agent` 实例。seam 契约见 [`dsh-tasks`](../../packages/tasks/tasks/README.md)，注册表生命周期见 [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md)，面向模型的接口见 [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md)。	抽象的 [`TaskService`](../../packages/tasks/tasks/src/index.ts) seam 定义原子 `start`、限定调用方作用域的 `get` 和 `list`、`read`、`kill`、有界 `wait`、故障隔离的 `onTaskDone` 与 `onTasksChanged` 监听器，以及 `attachSurface` 可用性防线；[`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) 是其进程局部实现。两类监听器不是包含关系：`onTaskDone` 按控制面与通知投递绑定的 first-wins 语义投递唯一一条终态记录，而 `onTasksChanged` 观察每一次可见集合的变化——注册、转入 stopping、结算，以及 owner 销毁时的移除——只携带集合发生变化的那个 owner，或在无主任务变化、因而每个调用方的集合都随之变化时携带 `undefined`。授权会比较拥有者会话；拥有者清理会选择确切的已注册 `Agent` 实例。seam 契约见 [`dsh-tasks`](../../packages/tasks/tasks/README.md)，注册表生命周期见 [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md)，面向模型的接口见 [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md)。
		`@@ -0,0 +1,3 @@`
							`import { clientBundle } from '../tsdown.client.ts'`

							`export default clientBundle('@deepseek-ai/dsh-client-ui-task', ['lib/types/index.js', 'lib/types/invariant.js'])`