diff --git a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml index d7babf16b3..be023bf4c7 100644 --- a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-06-29-todo-write-tool.md: df1bee2801b0e01b290b63f6edbe2e5b1be80cb7 -2026-06-29-todo-write-tool.zh.md: 7fa5cb2aad2b32ef0662df04ff6576be14a3a8e7 +2026-06-29-todo-write-tool.md: 760373d64f462e3717a174d5793e6d47ab76b0b4 +2026-06-29-todo-write-tool.zh.md: fd29e6049e6a729c2c7e78860ad7c065422da60e diff --git a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md index df1bee2801..760373d64f 100644 --- a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.md @@ -10,7 +10,7 @@ The harness gives the model bash and subagent tools but no way to record a struc ## Decision -Add a model-facing `todo_write(todos: [{ content, status }])` tool whose whole-list state lives on the event-sourced session log as a new `todo/write` `SessionEventMap` variant. Interactive hosts render from the durable event; the TUI folds it directly, while the [automation-only ACP bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) deliberately omits todo presentation. +Add a model-facing `todo_write(todos: [{ content, status }])` tool whose whole-list state lives on the event-sourced session log as a new `todo/write` `SessionEventMap` variant. Interactive hosts render from the durable event: the TUI folds it directly, the web client projects it into `ConversationSnapshot.todos` ([web todo display](2026-07-23-web-todo-display.md)), while the [automation-only ACP bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) deliberately omits todo presentation. ### Whole-list replace, three-state status @@ -18,7 +18,7 @@ The model sends the entire list every call; the new list replaces the old (last- ### State on the session log, not a service -The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and resume reconstruction for free: a reopened session re-derives the current list from the latest `todo/write`, with no separate persistence backend, in-memory service to rehydrate, or extra wiring. An in-memory `ctx.todos` service would have to reinvent all of that. +The list is appended as a `todo/write` event carrying the full `{ todos }` snapshot. The harness is event-sourced — the LLM history, tool calls, and turn structure all live on the log — so the todo list lives there too. This buys durability, replay, and resume reconstruction for free: a reopened session re-derives the current list from the latest `todo/write`, with no separate persistence backend, in-memory service to rehydrate, or extra wiring. An in-memory `ctx.todos` service would have to reinvent all of that. (Full-log consumers get this reconstruction outright; the web client's paged window gets it from the tail history page's host-computed projection — see the [web todo display note](2026-07-23-web-todo-display.md).) ### NOT a surface event diff --git a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md index 7fa5cb2aad..fd29e6049e 100644 --- a/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md +++ b/.agents/notes/implemented/feature/2026-06-29-todo-write-tool.zh.md @@ -10,7 +10,7 @@ harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结 ## 决策 -新增一个面向模型的 `todo_write(todos: [{ content, status }])` 工具，其整列表状态作为新的 `todo/write` `SessionEventMap` 变体存储在事件溯源的会话日志上。交互式宿主从持久事件渲染；TUI 直接折叠它，而[仅面向自动化的 ACP（Agent Client Protocol）桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)有意省略 todo 展示。 +新增一个面向模型的 `todo_write(todos: [{ content, status }])` 工具，其整列表状态作为新的 `todo/write` `SessionEventMap` 变体存储在事件溯源的会话日志上。交互式宿主从持久事件渲染：TUI 直接折叠它，web 客户端将其投影进 `ConversationSnapshot.todos`（[web todo 展示](2026-07-23-web-todo-display.md)），而[仅面向自动化的 ACP（Agent Client Protocol）桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)有意省略 todo 展示。 ### 整列表替换，三态 status @@ -18,7 +18,7 @@ harness 为模型提供了 bash 和 subagent 工具，却没有办法记录结 ### 状态在会话日志上，而非服务 -列表作为 `todo/write` 事件追加到日志，携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM（大语言模型）历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和恢复重建：重新打开的会话从最新的 `todo/write` 重新推导当前列表，无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。 +列表作为 `todo/write` 事件追加到日志，携带完整的 `{ todos }` 快照。harness 是事件溯源的——LLM（大语言模型）历史、工具调用和轮次结构都在日志上——所以 todo 列表也在那里。这免费获得了持久性、回放和恢复重建：重新打开的会话从最新的 `todo/write` 重新推导当前列表，无需独立的持久化后端、无需重新注水的内存服务、无需额外接线。一个内存中的 `ctx.todos` 服务需要重新发明以上所有。（全量 log 消费者直接获得这份重建；web 客户端的分页窗口则从尾页 history 携带的 host 计算投影获得——见 [web todo 展示 Note](2026-07-23-web-todo-display.md)。） ### 不是 surface 事件 diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml new file mode 100644 index 0000000000..4bccfa396e --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-23-web-todo-display.md +2026-07-23-web-todo-display.md: 830f55c86c893c4942a1a9d3b8529395d5f5e38b +2026-07-23-web-todo-display.zh.md: e68928d7eddaaa92ac831722a738ee2002342b38 diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md new file mode 100644 index 0000000000..830f55c86c --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.md @@ -0,0 +1,36 @@ +# Agent Note: Web todo display — snapshot side-effect channel + two render surfaces + +Status: implemented + +English | [中文](2026-07-23-web-todo-display.zh.md) + +## Problem + +`todo_write` appends `todo/write` whole-list snapshots to the session log; the TUI renders a persistent plan panel (the automation-only ACP bridge deliberately omits todo presentation). The web client dropped the event entirely: the host mux stream already forwards every session event, but `todo/write` is not a surface type (it never folds into `ConversationSnapshot.nodes`), and no side-effect branch accumulated it — the browser had no consumption point and no display surface. + +## Decision + +Consume `todo/write` as a Session side effect, not a surface node, and render it on two surfaces matching the split the TUI already draws. + +### Side-effect channel, converging with window replay + +`applyEventSideEffects` gains a `todo/write` case (whole list, last write wins). Unlike partial/openCalls, `rebuildDerivedFromWindow` deliberately does NOT reset it: the value is session-level — taken from the tail history page's full-log projection — and an arbitrary window may not contain the latest write, so an older-page prepend keeps it and only an in-window or live write overwrites it. Every `installWindow` caller is a tail request (`doOpen`, its gap re-pull, `repairGap`; `loadOlder` prepends without it), which the host answers with the projection or omits it only when the full log holds no `todo/write` — so an absent field is the authoritative empty list and is assigned as such. That distinction matters on rollback: a live write whose host crashed before persisting leaves the log empty, and preserving the prior value instead would strand the rolled-back plan on screen indefinitely. `ConversationSnapshot.todos` is the read surface. This follows the event's own contract ("log-only UI state; never derived history"): surfacing each write as a conversation node would render superseded lists as if they were still standing. + +### TodoPanel: the durable list as a persistent strip + +The panel mounts through the `conversation.input.dock` slot (a plain registrant plugin, `todoDockEntry`, the QueueDock posture: `inject: ['slots', 'conversation']` as the load-order seam, `order: -1` above the queue rows), hidden while empty, collapsible with the in-progress item as the collapsed one-line hint; ✓/●/○ glyphs mirror the TUI plan panel. It reads `snapshot.todos` via the standard-kit `useSession` hook the dock entry receives — no store, no service, no ctx. The inner component stays props-complete and framework-free; the dock adapter is a one-line wrapper. + +### TodoRow: the per-call row through the keyed toolview slot + +The dedicated `todo_write` chat row is a plain registrant plugin (`todoToolview`, mounted from `apply`) that registers into the keyed `conversation.chat.toolview` slot via `ctx.slots.register` — the same seam and load-order posture as the bash sample (`inject: ['slots', 'conversation']`), but a product registration. The summary derives from call args (`N/M done · active item`); unparseable args fall back to the generic row summary; clicking opens the details column with the raw args. No `ToolEventView` is added for todo — presentation is client-owned, and the durable list renders from the session event, not the tool card. + +## Alternatives considered + +- **Fold todo writes into `nodes` as surface entries** — replayed windows would render every superseded list; the event is deliberately not a surface type. +- **Hardcoding the panel inside `ConversationRoot`** — the original landing spot before the input-dock slot existed; the dock is the architecture's home for always-on strips above the composer, and a hardcode bypasses the slot registry's disposal and ordering. +- **Details column for the panel** — the details slot is single-occupant and selection-driven, a different lifetime than an always-on strip. +- **Host-computed view (a todo `ToolEventView`)** — presentation belongs to the client; the wire already carries the whole snapshot in the event payload. + +## Consequences + +Replay correctness is owned by one code path: any future change to window rebuild keeps todos consistent for free, and the fixture (fx-alpha turn 65) plus the assembled keyless snapshot (`apps/web/tests/todo-display.snapshot.ts`) pin the full chain (row summary and state, dock panel content, collapse round-trip) over the built client graph. `todos` is a required `ConversationSnapshot` field, so scripted fakes in specs must carry it. The TUI panel is untouched (the automation-only ACP bridge deliberately omits todo presentation); the web surfaces render the same event, adding one wire field and no new event type. That field is how cold-load reconstruction stays host-backed: the tail history page carries `todos` — the full-log latest `todo/write`, computed independently of the page window (the same backscan posture the view pairing uses) — so a reopened session restores the plan even when the last write precedes the window; that value survives an older-page prepend, is overwritten by any later write, and resets to empty when a tail response carries no projection. diff --git a/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md new file mode 100644 index 0000000000..e68928d7ed --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-23-web-todo-display.zh.md @@ -0,0 +1,36 @@ +# Agent Note: Web todo 展示——快照副作用通道 + 两个渲染面 + +Status: implemented + +[English](2026-07-23-web-todo-display.md) | 中文 + +## Problem + +`todo_write` 把 `todo/write` 的整份列表快照追加进会话日志；TUI 渲染一块常驻的 plan 面板（自动化专用的 ACP 桥接刻意不做 todo 呈现）。Web 客户端把这个事件整个丢弃了：host mux 流本已转发每一个会话事件，但 `todo/write` 不是 surface 类型（它从不 fold 进 `ConversationSnapshot.nodes`），也没有任何副作用分支累积它——浏览器既无消费点，也无展示面。 + +## Decision + +把 `todo/write` 当作 Session 副作用消费，而非 surface 节点，并在两个面上渲染它，这两个面正对应 TUI 已经绘制的那套划分。 + +### 副作用通道，与窗口回放收敛 + +`applyEventSideEffects` 新增一个 `todo/write` 分支（整份列表，后写覆盖先写）。与 partial/openCalls 不同，`rebuildDerivedFromWindow` 刻意不重置它：该值是会话级的——取自尾页 history 携带的全量 log 投影——而任意窗口未必包含最近一次写入，因此往前翻页保留它，只有窗口内或实时的写入才会覆盖。`installWindow` 的每个调用方都是尾页请求（`doOpen`、其补洞重拉、`repairGap`；`loadOlder` 只往前拼接、不走它），而 host 对尾页请求要么带上投影、要么仅在全量 log 没有任何 `todo/write` 时省略——因此字段缺失就是权威的空列表，直接照此赋值。这个区分在回滚场景上要紧：实时写入若在 host 持久化前崩溃，log 里就是空的，此时保留旧值会让已回滚的计划永远留在屏幕上。`ConversationSnapshot.todos` 是读取面。这遵循事件自身的契约（「仅日志 UI 状态，绝非派生历史」）：把每次写入作为对话节点呈现，会让已被取代的列表看起来仍然有效。 + +### TodoPanel：长驻列表作为一条常驻横条 + +面板经 `conversation.input.dock` slot 挂载（普通注册者插件 `todoDockEntry`，QueueDock 同款姿势：`inject: ['slots', 'conversation']` 载序 seam，`order: -1` 排在队列条上方），空列表时隐藏，可折叠——折叠态以进行中项作为单行提示；✓/●/○ 字形与 TUI plan 面板一致。它经 dock entry 收到的标准件 `useSession` hook 读取 `snapshot.todos`——无 store、无 service、无 ctx。内部组件保持 props 完备且框架无关；dock 适配件只是一行包装。 + +### TodoRow：经 keyed toolview slot 的逐调用行 + +专用的 `todo_write` 对话行是一个普通注册者插件（`todoToolview`，由 `apply` 挂载），经 `ctx.slots.register` 注册进 keyed 的 `conversation.chat.toolview` slot——与 bash 样例同一接缝、同一载序姿态（`inject: ['slots', 'conversation']`），但属产品级注册。摘要由调用 args 推导（`N/M done · active item`）；无法解析的 args 回退到通用行摘要；点击会以原始 args 打开 details 列。todo 不新增任何 `ToolEventView`——呈现归客户端所有，常驻列表从会话事件渲染，而非工具卡。 + +## Alternatives considered + +- **把 todo 写入作为 surface 条目折叠进 `nodes`**——回放的窗口会渲染每一份已被取代的列表；该事件被刻意设计成非 surface 类型。 +- **面板硬编码进 `ConversationRoot`**——input-dock slot 出现之前的原始落点；dock 是本架构给"composer 上方常开横条"安排的家，硬编码绕开了 slot 注册表的 disposal 与定序。 +- **面板放进 details 列**——details slot 单占用且由选中驱动，生命周期不同于一条常开横条。 +- **host 计算的视图（一个 todo `ToolEventView`）**——呈现属于客户端；协议已在事件载荷里携带整份快照。 + +## Consequences + +回放正确性由一条代码路径掌管：未来对窗口重建的任何改动都免费保持 todos 一致；fx-alpha 第 65 轮的 fixture（测试前置数据）加 assembled keyless snapshot（`apps/web/tests/todo-display.snapshot.ts`）在构建产物客户端全图上钉住整条链（行摘要与状态、dock 面板内容、折叠往返）。`todos` 是 `ConversationSnapshot` 的必填字段，所以 spec 里脚本化的 fake 必须带上它。TUI 面板未受改动（自动化专用的 ACP 桥接刻意不做 todo 呈现）；Web 各面渲染同一个事件，只新增一个协议字段，不新增事件类型。冷加载重建正是靠这个字段由 host 兜底：history 尾页附带 `todos`——全量 log 上最新一次 `todo/write` 的投影，独立于分页窗口计算（与 view 配对同一种 backscan 姿势）——因此重开会话时即使最后一次写入落在窗口之前，计划也照常恢复；该值跨往前翻页保留，之后的任何写入照常覆盖，而尾页响应不带投影时复位为空。 diff --git a/apps/web/tests/code-mode-fixture.snapshot.ts b/apps/web/tests/code-mode-fixture.snapshot.ts index 6f4085da44..a727844b1b 100644 --- a/apps/web/tests/code-mode-fixture.snapshot.ts +++ b/apps/web/tests/code-mode-fixture.snapshot.ts @@ -213,9 +213,9 @@ it('trajectory and waterfall surface the run_code sub-calls with real timing', a }).toMatchInlineSnapshot(` { "subCells": [ - "#53Subbash · {"command":"ls notes","description":"List notes"}+0.8s", - "#54Subread · {"path":"notes/demo.txt"}+0.8s", - "#55Subread · {"path":"notes/missing.txt"}+0.8s", + "#51Subbash · {"command":"ls notes","description":"List notes"}+0.8s", + "#52Subread · {"path":"notes/demo.txt"}+0.8s", + "#53Subread · {"path":"notes/missing.txt"}+0.8s", ], } `) diff --git a/apps/web/tests/todo-display.snapshot.ts b/apps/web/tests/todo-display.snapshot.ts new file mode 100644 index 0000000000..3116bf4242 --- /dev/null +++ b/apps/web/tests/todo-display.snapshot.ts @@ -0,0 +1,189 @@ +// @vitest-environment jsdom +// Todo display snapshot over the BUILT client graph (the code-mode-fixture +// idiom: real bundles via AppWebEntry, keyless FixtureApiClient transport). +// Opens the fixture history session and pins the todo_write turn's two +// surfaces: the dedicated TodoRow in the chat flow (keyed toolview, summary +// derived from the call args) and the TodoPanel plan strip riding the +// 'conversation.input.dock' slot (fed by ConversationSnapshot.todos, seeded +// by the tail history page), including the collapse interaction. +import { readFileSync } from 'node:fs' +import { join } from 'node:path' +import { act, cleanup, fireEvent, screen, waitFor, within } from '@testing-library/react' +import { afterEach, beforeEach, expect, it, vi } from 'vitest' +import type { WebBootEntry } from '@deepseek-ai/dsh-client-modules/client' +import { AppWebEntry } from '@deepseek-ai/dsh-client-web' + +const PLUGINS: readonly (WebBootEntry & { dir: string })[] = [ + { id: '@deepseek-ai/dsh-client-connection', dir: 'connection', url: '/plugins/connection.js', rev: 'fx', inject: [], immediately: true }, + { id: '@deepseek-ai/dsh-client-runtime', dir: 'runtime', url: '/plugins/runtime.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-connection'], immediately: true }, + { id: '@deepseek-ai/dsh-client-ui-theme', dir: 'ui-theme', url: '/plugins/ui-theme.js', rev: 'fx', inject: [], immediately: true }, + { id: '@deepseek-ai/dsh-client-locale', dir: 'locale', url: '/plugins/locale.js', rev: 'fx', inject: [], immediately: true }, + { id: '@deepseek-ai/dsh-client-ui-layout', dir: 'ui-layout', url: '/plugins/ui-layout.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-runtime'] }, + { id: '@deepseek-ai/dsh-client-ui-sidebar', dir: 'ui-sidebar', url: '/plugins/ui-sidebar.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] }, + { id: '@deepseek-ai/dsh-client-ui-conversation', dir: 'ui-conversation', url: '/plugins/ui-conversation.js', rev: 'fx', inject: ['@deepseek-ai/dsh-client-ui-layout'] }, + { + id: '@deepseek-ai/dsh-client-ui-workspace', + dir: 'ui-workspace', + url: '/plugins/ui-workspace.js', + rev: 'fx', + inject: [ + '@deepseek-ai/dsh-client-runtime', + '@deepseek-ai/dsh-client-ui-conversation', + '@deepseek-ai/dsh-client-ui-sidebar', + ], + }, +] + +const bundles = new Map(PLUGINS.map(plugin => [ + plugin.url, + readFileSync(join(process.cwd(), 'packages/client', plugin.dir, 'lib/client.js'), 'utf8'), +])) + +interface FixtureWindow extends Window { + __DSH_BOOT__?: { rev: string; entries: WebBootEntry[] } + __ModuleLoader__?: unknown +} + +class ResizeObserverStub { + observe(): void {} + disconnect(): void {} + unobserve(): void {} +} + +const win = window as FixtureWindow +let unmount: (() => void) | undefined + +beforeEach(() => { + localStorage.clear() + document.title = 'DeepSeek Harness' + vi.stubGlobal('ResizeObserver', ResizeObserverStub) + vi.stubGlobal('requestAnimationFrame', (callback: FrameRequestCallback) => + setTimeout(() => { callback(0) }, 0) as unknown as number) + vi.stubGlobal('cancelAnimationFrame', (id: number) => { clearTimeout(id) }) +}) + +afterEach(() => { + act(() => { unmount?.() }) + unmount = undefined + cleanup() + delete win.__DSH_BOOT__ + delete win.__ModuleLoader__ + delete (globalThis as Record).__fxTiming + document.body.innerHTML = '' + document.head.querySelectorAll('style[data-plugin]').forEach((style) => { style.remove() }) + document.title = '' + history.replaceState(null, '', '/') + vi.unstubAllGlobals() +}) + +/** Boot the complete built client graph against the populated fixture branch. */ +function boot(): void { + history.replaceState(null, '', '/?fixture') + const root = document.createElement('div') + root.id = 'root' + document.body.appendChild(root) + win.__DSH_BOOT__ = { rev: 'fx', entries: PLUGINS.map(({ dir: _dir, ...plugin }) => plugin) } + act(() => { + const entry = new AppWebEntry(root, { + fetchBundle: (url) => { + const code = bundles.get(url) + return code === undefined ? Promise.reject(new Error(`missing built bundle ${url}`)) : Promise.resolve(code) + }, + executeBundle: (code) => { (0, eval)(code) }, + }) + void entry.run() + unmount = () => { entry.dispose() } + }) +} + +/** Collapse decorative whitespace while preserving the text a user sees. */ +function visibleText(element: Element): string { + return (element.textContent ?? '').replace(/\s+/g, ' ').trim() +} + +/** Open the fixture history session (the alpha log carrying the todo_write turn) and wait for its tail. */ +async function openFixtureSession(): Promise { + const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 }) + // Anchor on the expandable Workspace group row: the title and the blank + // session row can both read "fixture", and the session-count meta shifts + // when a blank session joins the group. + const group = (await within(tree).findAllByText('fixture')) + .map(el => el.closest('[role="treeitem"]')) + .find(el => el?.getAttribute('aria-expanded') !== null) + if (group === null || group === undefined) throw new Error('fixture Workspace group missing') + if (group.getAttribute('aria-expanded') === 'false') { + fireEvent.click(within(group).getByText('fixture')) + await waitFor(() => { + expect(group.getAttribute('aria-expanded')).toBe('true') + }) + } + const session = await within(tree).findByText('Fixture 历史会话') + fireEvent.click(session) + await waitFor(() => { + expect(document.querySelector('[data-sample="todo-row"]')).not.toBeNull() + }, { timeout: 10_000 }) +} + +it('renders the todo_write turn: dedicated tool row + the dock plan strip', async () => { + boot() + await openFixtureSession() + + const row = document.querySelector('[data-sample="todo-row"]') + if (row === null) throw new Error('todo row missing') + const panel = document.querySelector('[data-testid="todo-panel"]') + if (panel === null) throw new Error('todo panel missing from the input dock') + + expect({ + row: visibleText(row), + rowState: row.getAttribute('data-state'), + panelHeader: visibleText(panel.querySelector('button') ?? panel), + panelItems: [...panel.querySelectorAll('li')].map(item => ({ + status: item.getAttribute('data-status'), + text: visibleText(item), + })), + }).toMatchInlineSnapshot(` + { + "panelHeader": "Plan1/3", + "panelItems": [ + { + "status": "completed", + "text": "✓梳理需求", + }, + { + "status": "in_progress", + "text": "●实现 fixture 样本", + }, + { + "status": "pending", + "text": "○浏览器验收", + }, + ], + "row": "☰更新任务清单1/3 已完成 · 实现 fixture 样本", + "rowState": "ok", + } + `) +}) + +it('collapses the plan strip to the in-progress hint and restores it', async () => { + boot() + await openFixtureSession() + + const panel = document.querySelector('[data-testid="todo-panel"]') + if (panel === null) throw new Error('todo panel missing from the input dock') + const header = panel.querySelector('button') + if (header === null) throw new Error('todo panel header missing') + + fireEvent.click(header) + expect({ + collapsedHeader: visibleText(header), + listGone: panel.querySelector('ul') === null, + }).toMatchInlineSnapshot(` + { + "collapsedHeader": "Plan1/3实现 fixture 样本", + "listGone": true, + } + `) + + fireEvent.click(header) + expect(panel.querySelectorAll('li')).toHaveLength(3) +}) diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 07956b019b..311791e594 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -1137,7 +1137,7 @@ Record and update a structured task list for the current work. Send the ENTIRE l "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md index 0e42b0c6ab..3a37f3da6a 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.expected.md @@ -162,7 +162,7 @@ interface ToolArgsMap { content: string; /** pending (not started) | in_progress (now) | completed (done). */ status: "pending" | "in_progress" | "completed"; - } & Record)[]; + })[]; } & Record; /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal: { diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json index 285031a1de..1abccfd566 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.expected.json @@ -366,7 +366,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md index 055ad93065..0cee2a6517 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.expected.md @@ -145,7 +145,7 @@ interface ToolArgsMap { content: string; /** pending (not started) | in_progress (now) | completed (done). */ status: "pending" | "in_progress" | "completed"; - } & Record)[]; + })[]; } & Record; /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal: { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json index fa3eba25d8..b61d7bf623 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/tool-schemas.expected.json @@ -309,7 +309,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md index 055ad93065..0cee2a6517 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.expected.md @@ -145,7 +145,7 @@ interface ToolArgsMap { content: string; /** pending (not started) | in_progress (now) | completed (done). */ status: "pending" | "in_progress" | "completed"; - } & Record)[]; + })[]; } & Record; /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal: { diff --git a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md index 055ad93065..0cee2a6517 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md +++ b/examples/acp-agent/tests/snapshots/code-mode-workspace-context/system-prompt.expected.md @@ -145,7 +145,7 @@ interface ToolArgsMap { content: string; /** pending (not started) | in_progress (now) | completed (done). */ status: "pending" | "in_progress" | "completed"; - } & Record)[]; + })[]; } & Record; /** Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason. */ update_goal: { diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json index d4973bfea4..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/escalation-approved/tool-schemas.expected.json @@ -288,7 +288,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json index 5d27e93da3..9b5925605c 100644 --- a/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/lsp-definition/tool-schemas.expected.json @@ -325,7 +325,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json index e9f7a2ea63..8e093db8bd 100644 --- a/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/pty-tools/tool-schemas.expected.json @@ -417,7 +417,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json index dde0ba0d7a..beb93c6b53 100644 --- a/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/session-query-spill/tool-schemas.expected.json @@ -492,7 +492,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json index d4973bfea4..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/skill-load/tool-schemas.expected.json @@ -288,7 +288,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json index d4973bfea4..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/text-turn/tool-schemas.expected.json @@ -288,7 +288,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json index d4973bfea4..01ac777a42 100644 --- a/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json +++ b/examples/acp-agent/tests/snapshots/workspace-context/tool-schemas.expected.json @@ -288,7 +288,7 @@ "description": "The COMPLETE task list, replacing any previous list.", "items": { "type": "object", - "additionalProperties": true, + "additionalProperties": false, "properties": { "content": { "type": "string", diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 045b9bb736..6cae860e36 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884563,"data":{"title":"Reply with exactly DIRECT_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n } & Record)[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":true,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 8193973bee..c00a4119c7 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -3,7 +3,7 @@ {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"session/title","seq":2,"time":1783957884700,"data":{"title":"Reply with exactly WORKFLOW_CHILD_OK and","messageSeqs":[1],"source":{"kind":"fallback"}}} {"type":"step/start","seq":3,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n } & Record)[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":true,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":4,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are headless-agent, a coding assistant powered by the deepseek-v4-flash model. Your working directory is /tmp/advanced-headless.\n\nVerify your work by running the code or tests. Keep answers brief and factual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nTrack every background task id you start. You are notified in-session when a task finishes — do not busy-poll or sleep on one; keep working on independent steps and do not duplicate a running task's work. Before giving a final answer, collect every still-relevant task with task_output (set wait: true only when you are genuinely blocked on it), and task_kill tasks that stopped mattering.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\nUse the ralph tool ONLY when the direct human explicitly asks for a Ralph loop or fresh-agent iterative execution. Each Ralph round starts a fresh child with no conversation seed and uses the shared workspace as durable memory. Completion and blockers are worker reports, not independent evaluation. Use same-session goal tools for ordinary long-running objectives, and plain subagents or workflows for bounded delegation and fan-out.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's typed canonical JSON value. Tool arguments must be lossless JSON.\n- A FAILED tool call rejects with `ToolCallError`, whose `toolName` identifies the failed tool and whose `message` is human-readable — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ntype JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }\n\ninterface ToolArgsMap {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. */\n bash: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies. */\n run_in_background?: boolean;\n } & Record;\n /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */\n cordis_inspect: {\n /** Limit the report to one section. Omit for all sections. */\n what?: \"services\" | \"plugins\" | \"tools\" | \"dynamic\" | \"api\" | \"events\";\n /** Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\". */\n name?: string;\n } & Record;\n /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */\n cordis_mount: {\n /** Body of an async JS function; must `return` the plugin to mount. */\n code: string;\n } & Record;\n /** Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop). */\n cordis_unmount: {\n /** The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\"). */\n id: string;\n } & Record;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n } & Record;\n /** Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools. */\n ralph: {\n /** The immutable completion objective for every fresh Ralph round. */\n objective: string;\n /** Optional positive safe-integer round cap, bounded by the deployment ceiling. */\n maxRounds?: number;\n } & Record;\n /** Read a UTF-8 text file and return line-numbered content. */\n read: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n } & Record;\n /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */\n skill: {\n /** The exact skill name from the available skills list. */\n name: string;\n } & Record;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`. */\n subagent_fork: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n /** Run as a background task and return its id; collect with task_output or stop with task_kill. */\n run_in_background?: boolean;\n } & Record;\n /** Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops. */\n task_kill: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Optional short reason, recorded in the log and forwarded to the task. */\n reason?: string;\n } & Record;\n /** List your background tasks (running and finished) with their ids, kinds, and statuses. */\n task_list: Record;\n /** Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap. */\n task_output: {\n /** Task id returned by the tool that started the background work. */\n task_id: string;\n /** Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive. */\n wait?: boolean;\n /** Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum. */\n timeout_ms?: number;\n } & Record;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n } & Record;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: ({\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional provider override this phase is expected to use. */\n provider?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n } & Record)[];\n } & Record;\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n } & Record;\n /** Create or fully replace a UTF-8 text file. */\n write: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n } & Record;\n}\n\ninterface ToolOutputMap {\n bash: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n exitCode: number | null;\n signal: string | null;\n timedOut: boolean;\n aborted: boolean;\n timeoutMs: number;\n stdout: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n stderr: {\n text: string;\n truncated: boolean;\n spillPath?: string;\n };\n sandbox?: {\n mode: string;\n denied: boolean;\n enforcement?: string;\n runnerFailed?: boolean;\n };\n };\n cordis_inspect: string;\n cordis_mount: {\n id: string;\n pluginName: string;\n state: \"pending\" | \"loading\" | \"active\" | \"failed\" | \"disposed\" | \"unloading\";\n provides: string[];\n waitingFor: string[];\n };\n cordis_unmount: {\n id: string;\n pluginName: string;\n };\n edit: {\n path: string;\n before: string;\n after: string;\n };\n ralph: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n read: {\n path: string;\n offset: number;\n lines: {\n number: number;\n text: string;\n }[];\n totalLines: number;\n };\n skill: {\n name: string;\n provider: string;\n resourceBase?: {\n kind: \"directory\";\n path: string;\n } | {\n kind: \"url\";\n url: string;\n } | {\n kind: \"opaque\";\n description: string;\n };\n content: string;\n };\n subagent: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n subagent_fork: {\n kind: \"background\";\n taskId: string;\n } | {\n kind: \"foreground\";\n runId: string;\n output: JsonValue[];\n };\n task_kill: {\n outcome: \"cancellation-requested\" | \"already-finished\";\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n task_list: ({\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n })[];\n task_output: {\n text: string;\n task: {\n id: string;\n kind: string;\n label: string;\n status: \"running\" | \"stopping\" | \"completed\" | \"killed\" | \"failed\";\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n };\n };\n todo_write: {\n todos: ({\n content: string;\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n counts: {\n pending: number;\n inProgress: number;\n completed: number;\n };\n };\n workflow: {\n runId: string;\n agentsStarted: number;\n result: JsonValue;\n };\n write: {\n path: string;\n operation: \"create\" | \"update\";\n before: string | null;\n after: string;\n };\n}\n\ntype ToolName = keyof ToolOutputMap\n\ndeclare class ToolCallError extends Error {\n readonly name: \"ToolCallError\";\n readonly toolName: ToolName;\n}\n\ndeclare const tools: {\n [K in ToolName]: (args: ToolArgsMap[K]) => Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies."}},"required":["command","description"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]},"name":{"type":"string","description":"Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"."}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, output: { schema: { type: 'string' }, render(_args, value) { return [{ type: 'text', text: value }] } }, async execute(args) { return args.text } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'integer'|'boolean'|'null'|'object'|'array'|'json', required?: true, description?, enum?, const?, items?, properties? }; every direct DSL object declares additionalProperties: true|false, and oneOf: [schema, schema, ...] replaces type for an exact-one union. A raw JSON-Schema { type: 'object', properties, required?: […] } wrapper is also accepted with open-by-default objects. A tool's `execute` MUST return the lossless JSON value declared by `output.schema`; `output.render(args, value)` separately returns Native/model content blocks. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"ralph","description":"Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.","parameters":{"type":"object","properties":{"objective":{"type":"string","description":"The immutable completion objective for every fresh Ralph round."},"maxRounds":{"type":"number","description":"Optional positive safe-integer round cap, bounded by the deployment ceiling."}},"required":["objective"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to return a task id; collect with `task_output` and stop with `task_kill`.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."},"run_in_background":{"type":"boolean","description":"Run as a background task and return its id; collect with task_output or stop with task_kill."}},"required":["description","prompt"]}},{"name":"task_kill","description":"Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"reason":{"type":"string","description":"Optional short reason, recorded in the log and forwarded to the task."}},"required":["task_id"]}},{"name":"task_list","description":"List your background tasks (running and finished) with their ids, kinds, and statuses.","parameters":{"type":"object","properties":{}}},{"name":"task_output","description":"Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the tool that started the background work."},"wait":{"type":"boolean","description":"Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive."},"timeout_ms":{"type":"number","description":"Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum."}},"required":["task_id"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","additionalProperties":false,"properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","additionalProperties":true,"properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","additionalProperties":true,"properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).","additionalProperties":true}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":5,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index eaab0a43f9..76a5ba568d 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -6,7 +6,7 @@ // approval/question requests exercise replay and composer takeover with stable rpcIds. import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' -import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types' +import type { SessionEvent, SessionId, TodoItem } from '@deepseek-ai/dsh-session/types' import type { ApiProxy, ClientRequest, ClientResponse, HistoryEntry, HostFrame, MuxFrame, RpcReceipt, RpcRequest, RpcResponse, RpcResult, ServerRequest, ServerResponse, SessionSummary, @@ -167,6 +167,22 @@ function buildAlphaLog(): SessionEvent[] { push({ type: 'step/end', data: { turn, step: 0 } }) push({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } }) } + // Turn 65: todo_write sample — the TodoRow toolview in the flow plus the + // todo/write snapshot event feeding the TodoPanel plan strip. + const fixtureTodos = [ + { content: '梳理需求', status: 'completed' }, + { content: '实现 fixture 样本', status: 'in_progress' }, + { content: '浏览器验收', status: 'pending' }, + ] + const todoArgs = JSON.stringify({ todos: fixtureTodos }) + toolTurn(65, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 1 in progress, 1 completed.') + // The real tool appends the snapshot mid-execution — between tool/call and + // tool/result — so the fixture reproduces that exact ordering (the last + // toolTurn events run ... tool/call, tool/result, step/end, turn/end). + const callIndex = events.length - 4 + const callTime = events[callIndex]?.time as number + events.splice(callIndex + 1, 0, { type: 'todo/write', time: callTime + 400, data: { todos: fixtureTodos } }) + events.forEach((e, i) => { e.seq = i }) return events as unknown as SessionEvent[] } @@ -281,6 +297,15 @@ function pageOf( return { events, hasMore: start > 0 } } +/** Current todo projection over the full log (host parallel: latest todo/write, last write wins). */ +function backscanTodos(log: readonly SessionEvent[]): TodoItem[] | undefined { + for (let i = log.length - 1; i >= 0; i--) { + const event = log[i] + if (event !== undefined && event.type === 'todo/write') return event.data.todos + } + return undefined +} + interface StreamConn { push(envelope: RpcRequest): void } @@ -619,12 +644,14 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy { const log = logs.get(request.payload.sessionId) ?? [] // Snapshot at request time, deliver after the transit delay (mirrors a real host under latency). const page = pageOf(log, request.payload.beforeSeq, request.payload.maxMessages ?? 50) + // Tail page carries the session-level todo projection (host parallel: full-log backscan). + const todos = request.payload.beforeSeq === undefined ? backscanTodos(log) : undefined const doomed = failNextHistory failNextHistory = false const delay = historyDelayMs if (delay > 0) await new Promise(resolve => setTimeout(resolve, delay)) if (doomed) throw new Error('fixture: simulated history transport failure') - return ok(request, page) + return ok(request, { ...page, ...todos === undefined ? {} : { todos } }) }, prompt: (request) => { const { sessionId: id, mode, content } = request.payload diff --git a/packages/client/connection/tests/fixture.spec.ts b/packages/client/connection/tests/fixture.spec.ts index 0374f92b3b..ae427710ae 100644 --- a/packages/client/connection/tests/fixture.spec.ts +++ b/packages/client/connection/tests/fixture.spec.ts @@ -71,6 +71,21 @@ describe('createFixtureApi', () => { expect(empty.result.value).toEqual({ events: [], hasMore: false }) }) + it('emits the todo/write snapshot at the real tool boundary: between tool/call and tool/result, timestamps monotonic', async () => { + const api = createFixtureApi() + const tail = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 10 })) + if (!tail.result.ok) throw new Error('history failed') + const events = tail.result.value.events.map(e => e.event) + const todoAt = events.findIndex(e => e.type === 'todo/write') + expect(todoAt).toBeGreaterThan(0) + // Production ordering (the tool appends mid-execution): call → snapshot → result. + expect(events[todoAt - 1]?.type).toBe('tool/call') + expect(events[todoAt + 1]?.type).toBe('tool/result') + const times = events.slice(todoAt - 1, todoAt + 2).map(e => e.time) + expect(times[0]).toBeLessThanOrEqual(times[1] ?? 0) + expect(times[1]).toBeLessThanOrEqual(times[2] ?? 0) + }) + it('create adds a session and pushes host/session-added to open host streams', async () => { const api = createFixtureApi() const abort = new AbortController() diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 5e73979b0b..055ce4eb86 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -README.md: 4724ebc75d441252245a0e811a4ae34f8b529a98 -README.zh.md: 6a0076742efccaf946910c77c77a9b74194b9dc5 +# pnpm run verify-translation-pairing --write packages/client/runtime/README.md +README.md: d7b7bbc4e4e05893689a8f2dcac82763b4c67ef8 +README.zh.md: d2054170cd6f31505793812fff46cc0f2356ad75 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index 4724ebc75d..d7b7bbc4e4 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Client cordis boot and React-free object services: SlotsService wraps SlotCore and supplies renderer data sources; SessionsService owns Session objects, list/scope/history state; WorkspacesService depends on SessionsService and owns Workspace objects, list/actions, default-target derivation, and the New Session blank-reuse entry (`connectWorkspace`). The runtime fans the shared Host stream into both managers. Client sessions are always Host-born (Session+Agent+cwd in one `session.create`); the client holds no pre-entity session state — a session's Agent scope (the client mirror of host dsh-scope, keyed by the shared agent/session id) is born when its row enters the list mirror and dies with the prune. Contract: api-contracts v3 §4. +Client cordis boot and React-free object services: SlotsService wraps SlotCore and supplies renderer data sources; SessionsService owns Session objects, list/scope/history state; WorkspacesService depends on SessionsService and owns Workspace objects, list/actions, default-target derivation, and the New Session blank-reuse entry (`connectWorkspace`). The runtime fans the shared Host stream into both managers. Client sessions are always Host-born (Session+Agent+cwd in one `session.create`); the client holds no pre-entity session state — a session's Agent scope (the client mirror of host dsh-scope, keyed by the shared agent/session id) is born when its row enters the list mirror and dies with the prune. Contract: api-contracts v3 §4. `ConversationSnapshot` carries `todos` — the session's current todo projection: taken from the tail history page's full-log value (host-computed, independent of the page window), preserved across an older-page prepend, and overwritten by each live `todo/write` (last write wins). A tail response that omits the field means the log holds no `todo/write`, so the list resets to empty — a plan the log never kept (a write lost to a host crash) disappears on the next open or resync. ## Workspace and Session lists diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index 6a0076742e..d2054170cd 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -客户端 cordis 启动与不依赖 React 的对象服务：SlotsService 包装 SlotCore 并提供 renderer 数据源；SessionsService 拥有 Session 对象、列表／scope／history 状态；WorkspacesService 依赖 SessionsService，拥有 Workspace 对象、列表／操作、默认目标派生，以及 New Session 空会话复用入口（`connectWorkspace`）。运行时把共享 Host 流分发给两个 manager。客户端 Session 一律由 Host 出生（一次 `session.create` 同瞬产出 Session+Agent+cwd）；客户端不持有任何实体化之前的会话状态——Agent scope（host dsh-scope 的客户端镜像，以 agent/session 共用 id 为键）在会话行进入列表镜像时出生，随 prune 死亡。契约：api-contracts v3 §4。 +客户端 cordis 启动与不依赖 React 的对象服务：SlotsService 包装 SlotCore 并提供 renderer 数据源；SessionsService 拥有 Session 对象、列表／scope／history 状态；WorkspacesService 依赖 SessionsService，拥有 Workspace 对象、列表／操作、默认目标派生，以及 New Session 空会话复用入口（`connectWorkspace`）。运行时把共享 Host 流分发给两个 manager。客户端 Session 一律由 Host 出生（一次 `session.create` 同瞬产出 Session+Agent+cwd）；客户端不持有任何实体化之前的会话状态——Agent scope（host dsh-scope 的客户端镜像，以 agent/session 共用 id 为键）在会话行进入列表镜像时出生，随 prune 死亡。契约：api-contracts v3 §4。`ConversationSnapshot` 携带 `todos`——会话当前的 todo 投影：取自尾页 history 携带的全量 log 值（host 计算，独立于分页窗口），跨往前翻页保留，并被每次实时 `todo/write` 覆盖（后写胜出）。尾页响应省略该字段即表示 log 中没有任何 `todo/write`，因此列表复位为空——log 从未留下的计划（写入因 host 崩溃丢失）会在下一次打开或 resync 时消失。 ## Workspace 与 Session 列表 diff --git a/packages/client/runtime/src/client/index.ts b/packages/client/runtime/src/client/index.ts index b1300a192c..b4a418628f 100644 --- a/packages/client/runtime/src/client/index.ts +++ b/packages/client/runtime/src/client/index.ts @@ -30,7 +30,7 @@ export type { export type { AssistantBlock, AssistantMessageNode, CodeSubCall, ComposerPhase, ContextMessageNode, ConversationNode, ConversationSnapshot, QueuedMessage, RunningToolCall, - SteeringMessageNode, ToolResultNode, UnknownSurfaceNode, UserMessageNode, + SteeringMessageNode, TodoItem, ToolResultNode, UnknownSurfaceNode, UserMessageNode, } from './sessions/conversation.ts' export { PendingWait } from './sessions/pending.ts' export type { PendingInteraction, PendingKind, PendingPayloads } from './sessions/pending.ts' diff --git a/packages/client/runtime/src/client/sessions/conversation.ts b/packages/client/runtime/src/client/sessions/conversation.ts index 49ae8634ec..e1b2c42962 100644 --- a/packages/client/runtime/src/client/sessions/conversation.ts +++ b/packages/client/runtime/src/client/sessions/conversation.ts @@ -4,11 +4,14 @@ // string here (narrow to real brands when convenient). import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' +import type { TodoItem } from '@deepseek-ai/dsh-session/types' import type { RpcError, SessionId, ToolCallView, ToolResultView, } from '@deepseek-ai/dsh-client-connection/client' import type { PendingInteraction } from './pending.ts' +export type { TodoItem } + /** Assistant content blocks sorted by what the UI cares about * (text body / collapsible reasoning / tool-call card head / other fallback). */ export type AssistantBlock = @@ -241,4 +244,7 @@ export interface ConversationSnapshot { */ blank: boolean lastAgentError: string | null + /** Current whole-list `todo/write` projection — the tail page's full-log value, then each live + * write (last write wins); empty = the log holds no plan. */ + todos: readonly TodoItem[] } diff --git a/packages/client/runtime/src/client/sessions/session.ts b/packages/client/runtime/src/client/sessions/session.ts index 75c55bc4bd..1dd0283429 100644 --- a/packages/client/runtime/src/client/sessions/session.ts +++ b/packages/client/runtime/src/client/sessions/session.ts @@ -2,7 +2,7 @@ import type { Context } from 'cordis' import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' -import type { SessionEvent } from '@deepseek-ai/dsh-session/types' +import type { SessionEvent, TodoItem } from '@deepseek-ai/dsh-session/types' import type { HistoryEntry, IApiClient, MuxFrame, RpcError, RpcId, RpcResult, SessionId, ToolEventView, @@ -99,6 +99,9 @@ export class Session implements ObservableSnapshot { private queueCache: { rev: number; value: QueuedMessage[] } | null = null private frozenRev = 0 private nodesCache: { folded: readonly ConversationNode[]; frozenRev: number; value: readonly ConversationNode[] } | null = null + /** Current whole-list todo/write projection: each tail history response replaces it (an omitted + * field is the authoritative empty list) and every live write overwrites it. */ + private todos: readonly TodoItem[] = [] /** `run_code` sub-dispatches by parent callId (window-derived, like openCalls). Appends * copy-on-write the per-parent array so published snapshot references never mutate. */ private codeDispatches = new Map() @@ -479,13 +482,13 @@ export class Session implements ObservableSnapshot { this.openError = result.error return } - this.installWindow(result.value.events, result.value.hasMore) + this.installWindow(result.value.events, result.value.hasMore, result.value.todos) // Gap detection (§D.3-4): baseline past the window tail and liveBuffer did not cover it -> pull the tail page once more. const tailSeq = this.windowTailSeq() if (this.subscribedLastSeq !== null && tailSeq !== null && this.subscribedLastSeq > tailSeq) { result = (await this.api.sessions.history({ sessionId: this.sessionId, maxMessages: PAGE_MESSAGES })).result if (generation !== this.openGeneration) return - if (result.ok) this.installWindow(result.value.events, result.value.hasMore) + if (result.ok) this.installWindow(result.value.events, result.value.hasMore, result.value.todos) } this.openState = 'open' } catch (error) { @@ -503,11 +506,19 @@ export class Session implements ObservableSnapshot { * Stitching MUST NOT route through acceptLiveEvent: openState is still 'loading' here * (doOpen flips it after install), so recursing would push every buffered event straight * back into liveBuffer where nothing ever drains it — a silent drop loop (audit S1). */ - private installWindow(entries: HistoryEntry[], hasMore: boolean): void { + private installWindow(entries: HistoryEntry[], hasMore: boolean, todos: readonly TodoItem[] | undefined): void { this.events = entries.map(e => e.event) this.views = entries.map(e => e.view) this.baseSeq = this.events[0]?.seq ?? 0 this.hasMore = hasMore + // Session-level projection from the tail page (full-log latest todo/write, + // independent of the window); an in-window write below re-derives the same + // value, and later live events keep overwriting it. Every caller here is a + // tail request (no beforeSeq), which the host answers with the projection + // or omits it only when the full log holds no todo/write — so an absent + // field is the authoritative empty list, not a missing carrier. Assigning + // it clears a plan the log never kept (a write lost to a host crash). + this.todos = todos ?? [] this.foldAdapter.reset(this.events, this.baseSeq, this.views) this.rebuildDerivedFromWindow() const buffered = this.liveBuffer @@ -558,7 +569,7 @@ export class Session implements ObservableSnapshot { const { result } = await this.api.sessions.history({ sessionId: this.sessionId, maxMessages: PAGE_MESSAGES }) // Failure or superseded by a full resync: drop — the resync path rebuilds and clears the buffer itself. if (result.ok && generation === this.openGeneration && this.openState === 'open') { - this.installWindow(result.value.events, result.value.hasMore) + this.installWindow(result.value.events, result.value.hasMore, result.value.todos) } } catch (error) { console.error('[web-runtime] gap repair failed:', error) @@ -678,6 +689,10 @@ export class Session implements ObservableSnapshot { if (this.openCalls.delete(String(event.data.callId))) this.callsRev++ return } + case 'todo/write': { + this.todos = event.data.todos + return + } case 'turn/end': { // Aborted turns never finalize. The accumulated partial is VALUE, not residue: freeze it // into an interrupted terminal node (pulse stops, text survives) instead of deleting it. @@ -722,7 +737,10 @@ export class Session implements ObservableSnapshot { /** Re-derive state (partial/openCalls/frozenNodes) from raw window events after a rebuild — keeps * paging/stitching consistent, and makes the live freeze and the history replay converge on the - * same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text). */ + * same interrupted nodes (chunks are logged, so the replayed sweep re-freezes identical text). + * todos is deliberately NOT reset: it is session-level (seeded by the tail page's full-log + * projection, not derivable from an arbitrary window). The window always extends to the log + * tail, so an in-window todo/write can only overwrite it with the same latest value. */ private rebuildDerivedFromWindow(): void { this.partial = null this.openCalls.clear() @@ -792,6 +810,7 @@ export class Session implements ObservableSnapshot { promptError: this.promptError, blank: this.blankBit, lastAgentError: this.lastAgentError, + todos: this.todos, } } } diff --git a/packages/client/runtime/tests/event-script.ts b/packages/client/runtime/tests/event-script.ts index 7fb150bb20..ada8550136 100644 --- a/packages/client/runtime/tests/event-script.ts +++ b/packages/client/runtime/tests/event-script.ts @@ -40,6 +40,8 @@ export const ev = { at(seq, { type: 'step/end', data: { turn, step } }), turnEnd: (seq: number, turn: number, reason: 'completed' | 'cancelled' = 'completed'): SessionEvent => at(seq, { type: 'turn/end', data: { turn, reason: { kind: reason } } }), + todoWrite: (seq: number, todos: { content: string; status: 'pending' | 'in_progress' | 'completed' }[]): SessionEvent => + at(seq, { type: 'todo/write', data: { todos } }), } /** One complete plain turn (turn/start → user → step → assistant → turn/end), 6 events from startSeq. */ diff --git a/packages/client/runtime/tests/fake-api.ts b/packages/client/runtime/tests/fake-api.ts index dcb334f6ea..8874f0da23 100644 --- a/packages/client/runtime/tests/fake-api.ts +++ b/packages/client/runtime/tests/fake-api.ts @@ -62,7 +62,7 @@ export class FakeApiClient implements IApiClient { onList: (payload: unknown) => Promise> = () => Promise.resolve(ok({ items: [] })) onCreate: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-new' as SessionId })) onHistory: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) - => Promise> = + => Promise> = () => Promise.resolve(ok({ events: [], hasMore: false })) onPrompt: (payload: unknown) => Promise> = () => Promise.resolve(ok({ accepted: true as const })) diff --git a/packages/client/runtime/tests/session.spec.ts b/packages/client/runtime/tests/session.spec.ts index f5cf9a2138..6c223ef58b 100644 --- a/packages/client/runtime/tests/session.spec.ts +++ b/packages/client/runtime/tests/session.spec.ts @@ -22,9 +22,9 @@ function makeSession(api = new FakeApiClient()): { api: FakeApiClient; session: return { api, session: new Session(SID, api) } } -function histResponse(events: SessionEvent[], hasMore = false) { +function histResponse(events: SessionEvent[], hasMore = false, todos?: { content: string; status: 'pending' | 'in_progress' | 'completed' }[]) { // history now returns HistoryEntry[] ({event, view?}); these tests are view-less. - return Promise.resolve(ok({ events: entries(events) as never[], hasMore })) + return Promise.resolve(ok({ events: entries(events) as never[], hasMore, ...todos === undefined ? {} : { todos } })) } describe('open', () => { @@ -153,6 +153,42 @@ describe('live event path', () => { }) }) + it('folds todo/write into snapshot.todos last-write-wins, live and on window replay', async () => { + const listA = [{ content: '搭骨架', status: 'completed' as const }, { content: '写组件', status: 'in_progress' as const }] + const listB = [{ content: '搭骨架', status: 'completed' as const }, { content: '写组件', status: 'completed' as const }] + const { session } = await opened() + expect(session.getSnapshot().todos).toEqual([]) + const feed = (event: SessionEvent) => { session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event }) } + feed(ev.todoWrite(6, listA)) + expect(session.getSnapshot().todos).toEqual(listA) + feed(ev.todoWrite(7, listB)) + expect(session.getSnapshot().todos).toEqual(listB) + // Window replay converges on the same last snapshot (history contains both writes). + const replayed = makeSession() + replayed.api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ev.todoWrite(6, listA), ev.todoWrite(7, listB)]) + await replayed.session.open() + expect(replayed.session.getSnapshot().todos).toEqual(listB) + }) + + it('seeds todos from the tail page projection when the last write precedes the window', async () => { + const list = [{ content: '窗口外的计划', status: 'in_progress' as const }] + // Cold open: the page window carries NO todo/write; the projection rides the response. + const { api, session } = makeSession() + api.onHistory = () => histResponse(plainTurn(100, 9, '问', '答'), true, list) + await session.open() + expect(session.getSnapshot().todos).toEqual(list) + // Paging an older window in must not clear the session-level projection. + api.onHistory = () => histResponse(plainTurn(94, 8, '旧问', '旧答'), false) + await session.loadOlder() + expect(session.getSnapshot().todos).toEqual(list) + // A later live write still overrides the seeded projection. + session.handleMuxEnvelope('r' as never, { + type: 'session/event', sessionId: SID, + event: ev.todoWrite(106, [{ content: '新计划', status: 'pending' as const }]), + }) + expect(session.getSnapshot().todos).toEqual([{ content: '新计划', status: 'pending' }]) + }) + it('repairs a seq gap by repulling the tail page instead of appending a hole', async () => { const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) // tail seq = 5 const repaired = [...plainTurn(0, 0, 'a', 'b'), ...plainTurn(6, 1, 'c', 'd')] @@ -166,6 +202,37 @@ describe('live event path', () => { const seqs = session.getSnapshot().nodes.map(n => n.seq) expect(seqs).toEqual([1, 3, 7, 9]) // both turns' user/assistant, no hole, no duplicate 9 }) + + it('gap repair adopts the repull response projection (a missed todo/write outside the new tail page)', async () => { + const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) // tail seq = 5 + expect(session.getSnapshot().todos).toEqual([]) + // The missed range contained a todo/write that the repulled page no longer + // covers; the response's session-level projection is the only carrier. + const current = [{ content: '断线期间写的', status: 'in_progress' as const }] + api.onHistory = () => histResponse([...plainTurn(0, 0, 'a', 'b'), ...plainTurn(8, 1, 'c', 'd')], false, current) + session.handleMuxEnvelope('r' as never, { type: 'session/event', sessionId: SID, event: ev.assistant(11, 1, 'd') }) + await vi.waitFor(() => { + expect(api.callsOf('session.history').length).toBe(2) + }) + await Promise.resolve() + expect(session.getSnapshot().todos).toEqual(current) + }) + + it('clears the plan when a tail response omits the projection (a write the log never kept)', async () => { + // Live write lands, then the host crashes before persisting it: the + // authoritative log holds no todo/write, so the resync tail response + // carries no projection — an omitted field on a tail request is the empty + // list, not a missing carrier, and the rolled-back plan must disappear. + const { api, session } = await opened(plainTurn(0, 0, 'a', 'b')) + session.handleMuxEnvelope('r' as never, { + type: 'session/event', sessionId: SID, + event: ev.todoWrite(6, [{ content: '丢失的计划', status: 'in_progress' as const }]), + }) + expect(session.getSnapshot().todos).toEqual([{ content: '丢失的计划', status: 'in_progress' }]) + api.onHistory = () => histResponse(plainTurn(0, 0, 'a', 'b')) + await session.resync() + expect(session.getSnapshot().todos).toEqual([]) + }) }) describe('paging', () => { diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 8117d42ea4..2ffa02d313 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -README.md: b9ec555f158722ea1f41e01c4b3f7131d3fe3467 -README.zh.md: b1e3c1f4331148ebf1c58b4bcd4869270bb44311 +# pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md +README.md: b242812411d513931ecd2767622f9e23fb0aaa34 +README.zh.md: 77f68e02d8d9161c413ae7d224121bc53547ba12 diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index b9ec555f15..b242812411 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Conversation domain: skeleton (header/tabs/composer/empty state), chat view (grouped step-summary flow, streaming tail isolation, stats line, per-tool row slot with a bash sample registrant), minimal details panel, scope-addressed ConversationService. Contract: api-contracts v3 §7 plus the slot terminal design (store seat / props shares). +Conversation domain: skeleton (header/tabs/composer/empty state), chat view (grouped step-summary flow, streaming tail isolation, stats line, per-tool row slot with a bash sample registrant and the todo row), input dock (queue rows plus the todo plan strip), minimal details panel, scope-addressed ConversationService. Contract: api-contracts v3 §7 plus the slot terminal design (store seat / props shares). The no-session hero renders the frontend Session Intent from the Session list projection, including its frontend Workspace Intent when no real Workspace exists. It declares `conversation.empty.workspace`, where ui-workspace registers the same picker used by the sidebar. WorkspacesService starts the cross-object flow; each Workspace or Session object owns its own materialization. The Session keeps its identity across publication and retains any prompt that still needs connection or delivery; ConversationRoot reads that `pendingPrompt` from `useSession` and edits or retries it through the scoped ConversationService. @@ -12,6 +12,8 @@ Generic tool rows classify the built-in bash, read, search, write, edit, and run Tool rows are slots too — the standalone tool ring (`ToolViewRegistry`/`ctx.toolviews`/outlet) is retired. The chat entry declares the keyed `'conversation.chat.toolview'` hole (session scope; the key space is runtime-open); its render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`) and `ToolRowProps` pre-composes it with the session standard kit. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam (apply mounts ConversationService after the chat registration, so the service being present guarantees the slot is declared); session differentiation happens inside the component (`useSessions` reading `parentId` — the bash sample is the third-party-posture exemplar). Trajectory/waterfall toolview slots share this shape and land with their own render sites (RendersCheck rejects a declaration nobody renders). +The todo surfaces are two registrations over that shape, both plain registrant plugins with `inject: ['slots', 'conversation']`. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`/ 已完成 · ` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: -1` — above the queue rows — and is the durable plan strip: it selects `todos` off the session snapshot and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and collapses to a one-line header carrying the in-progress item. The dock adapter owns the selection so the panel stays a pure function of its props; the persistent list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included. + Per-session UI state (selection, ordinary composer draft, active view) lives in the declared chat store (`stores.ts` `createChatStore`): apply constructs one handle and passes it to the conversation, chat-view, and details registrations, so the session slots share one instance per session (selection written by the chat view, read by details) and the framework owns instance lifecycle and draft persistence. The frontend Session Intent comes from the Session list projection; after publication, any retained prompt comes from that Session's conversation snapshot. Components are pure — the framework standard kit (`useSession`/`sessionId` when session-scoped, plus global `useSessions`/`useWorkspaces`) and the store faces (`useStore`/`actions`) arrive automatically from the registration declaration; inject factories contribute plain data and callbacks for runtime Session actions, send/stop, tabs, details, and paging. `src/client/` is organized for the future package split: `contract/` is the sole inter-domain shared face (`slots.ts` slot declarations + composed slot props including the tool-row contract, `views.ts` shared primitives, `tool-call-model.ts`); the `skeleton/`, `chat/`, and `toolviews/` (sample registrants) domain directories import contract files and never each other; `apply.ts` is the only assembly point allowed to import all three domains. The `/client` export surface is the contract only — `apply`/`inject`, the two service classes, and the `contract/` type families; implementation components (skeleton, chat rows) and the store factory stay internal and reach the page exclusively through apply's slot registrations (tests take them via the `./src/*` subpath). diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index b1e3c1f433..77f68e02d8 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -会话领域：骨架（标题栏／标签页／编辑器／空状态）、聊天视图（分组步骤摘要流、流式尾部隔离、统计行、逐工具行 slot 及一个 bash 示例注册方）、最小详情面板、按 scope 寻址的 ConversationService。契约：api-contracts v3 §7 加 slot 终端设计（store seat／props share）。 +会话领域：骨架（标题栏／标签页／编辑器／空状态）、聊天视图（分组步骤摘要流、流式尾部隔离、统计行、逐工具行 slot 及一个 bash 示例注册方与 todo 行）、输入区 dock（队列行加 todo 计划条）、最小详情面板、按 scope 寻址的 ConversationService。契约：api-contracts v3 §7 加 slot 终端设计（store seat／props share）。 无会话主视觉区会渲染来自 Session 列表投影的前端 Session Intent；没有真实 Workspace 时，还会包含其前端 Workspace Intent。它声明 `conversation.empty.workspace`，ui-workspace 会在此注册侧边栏所用的同一选择器。WorkspacesService 启动跨对象流程；每个 Workspace 或 Session 对象拥有自身的物化。Session 在发布期间保持身份，并保留任何仍需连接或交付的提示词；ConversationRoot 读取该 `pendingPrompt`，其来源是 `useSession`，再通过 scope 内的 ConversationService 编辑或重试。 @@ -12,6 +12,8 @@ 工具行同样是 slot：独立工具环（`ToolViewRegistry`／`ctx.toolviews`／outlet）已经退役。聊天配置项声明键控的 `'conversation.chat.toolview'` 空位（Session scope；key 空间在运行时开放）；其渲染点逐行通过 `entryKey: toolName` 分发，并以 `GenericToolCard` 作为调用点 `fallback`。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`／`toolName`／`block`／`openDetails`），`ToolRowProps` 则预先将其与 Session 标准工具包组合。注册方只是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作为加载顺序 seam（apply 在聊天注册后挂载 ConversationService，因此服务存在即可保证 slot 已声明）；Session 区分在组件内部完成（`useSessions` 读取 `parentId`，bash 示例是第三方姿态的范例）。Trajectory/waterfall 工具视图 slot 共享此形状，并随各自的渲染点落地（RendersCheck 会拒绝没有任何渲染方的声明）。 +todo 两个面就是在该形状上的两个注册项，都是普通注册方插件，`inject: ['slots', 'conversation']`。`TodoRow` 占用 `'conversation.chat.toolview'` 的 `todo_write` key，摘要该次调用「试图写入」的内容（从其 args 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`；模型 JSON 残缺或形状不对时回落到通用摘要；非 ok 执行状态保留通用状态点，使被取消的调用绝不读成一次已完成的更新）。`TodoDock` 以 `order: -1` 占用 `'conversation.input.dock'` 列表 slot（位于队列行之上），是常驻的计划条：它从会话快照中选取 `todos` 并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏，折叠时收成携带进行中条目的单行表头。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；常驻列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。 + 逐 Session UI 状态（选择、普通编辑器草稿、活跃视图）位于已声明的聊天 store（`stores.ts` `createChatStore`）中：apply 构造一个 handle，并将其传给会话、聊天视图和详情注册，因此 Session slot 每个 Session 共享一个实例（选择由聊天视图写入、详情读取），框架拥有实例生命周期与草稿持久化。前端 Session Intent 来自 Session 列表投影；发布后，任何保留的提示词都来自该 Session 的会话快照。组件保持纯粹：框架标准工具包（Session scope 下的 `useSession`／`sessionId`，以及全局 `useSessions`／`useWorkspaces`）和 store 表层（`useStore`／`actions`）会从注册声明自动到达；inject factory 为运行时 Session 操作、发送／停止、标签页、详情和分页贡献普通数据与回调。 `src/client/` 按未来的包拆分组织：`contract/` 是唯一的跨领域共享表层（`slots.ts` slot 声明 + 组合后的 slot props，包括工具行契约、`views.ts` 共享原语、`tool-call-model.ts`）；`skeleton/`、`chat/` 和 `toolviews/`（示例注册方）领域目录只导入 contract 文件，彼此绝不导入；`apply.ts` 是唯一允许导入全部三个领域的组装点。`/client` 导出表层只包含契约：`apply`／`inject`、两个服务类和 `contract/` 类型家族；实现组件（骨架、聊天行）与 store factory 保持内部状态，只能通过 apply 的 slot 注册到达页面（测试通过 `./src/*` 子路径获取它们）。 diff --git a/packages/client/ui-conversation/src/client/apply.ts b/packages/client/ui-conversation/src/client/apply.ts index c8d5be336d..208d75c5d4 100644 --- a/packages/client/ui-conversation/src/client/apply.ts +++ b/packages/client/ui-conversation/src/client/apply.ts @@ -13,6 +13,8 @@ import { InputHub } from './input/hub.ts' import { InputBar } from './skeleton/InputBar.tsx' import { ChatView } from './chat/ChatView.tsx' import { bashToolviewSample } from './toolviews/bash-sample.tsx' +import { todoToolview } from './toolviews/todo-row.tsx' +import { todoDockEntry } from './skeleton/TodoPanel.tsx' import { queueDockEntry } from './queue/QueueDock.tsx' import { ConversationRoot } from './skeleton/ConversationRoot.tsx' import { ConversationSession } from './skeleton/ConversationSession.tsx' @@ -182,6 +184,12 @@ export function apply(ctx: Context): void { // The bash sample rides that exact seam, in third-party posture. ctx.plugin(bashToolviewSample) + // The todo_write row rides the same seam (a product registration, not a sample). + ctx.plugin(todoToolview) + + // The plan strip rides the input dock above the queue rows (same posture). + ctx.plugin(todoDockEntry) + // The read-only queue dock entry (T9 file territory) rides the same // registration seam into the input dock declared above. ctx.plugin(queueDockEntry) diff --git a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css new file mode 100644 index 0000000000..17c9c890a7 --- /dev/null +++ b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.module.css @@ -0,0 +1,111 @@ +/* Plan strip pinned above the composer: bordered card on the composer card's + axis (776px column inside 32px side padding). Colors resolve through + --dsw-alias-* tokens only; the active row rides the business blue, done + rows fade to tertiary. */ + +.root { + flex: none; + overflow: hidden; + margin: 8px auto 0; + width: calc(100% - 64px); + max-width: 776px; + border: 1px solid var(--dsw-alias-border-l2); + border-radius: 12px; + background: var(--dsw-alias-bg-base); +} + +.header { + display: flex; + align-items: center; + gap: 8px; + width: 100%; + padding: 8px 12px; + border: none; + background: transparent; + text-align: left; + cursor: pointer; +} + +.header:hover { + background: var(--dsw-alias-interactive-bg-hover); +} + +.title { + font-size: 13px; + line-height: 16px; + font-weight: 510; + color: var(--dsw-alias-label-primary); +} + +.progress { + font-size: 12px; + line-height: 16px; + color: var(--dsw-alias-label-tertiary); +} + +.activeHint { + flex: 1; + min-width: 0; + overflow: hidden; + font-size: 12px; + line-height: 16px; + color: var(--dsw-alias-label-secondary); + text-overflow: ellipsis; + white-space: nowrap; +} + +.chevron { + display: grid; + flex: none; + place-items: center; + margin-left: auto; + color: var(--dsw-alias-label-secondary); +} + +.list { + margin: 0; + padding: 0 12px 8px; + list-style: none; + max-height: 180px; + overflow-y: auto; +} + +.item { + display: flex; + align-items: baseline; + gap: 8px; + padding: 2px 0; + font-size: 13px; + line-height: 20px; + color: var(--dsw-alias-label-secondary); +} + +.glyph { + flex: none; + width: 14px; + text-align: center; + color: var(--dsw-alias-label-tertiary); +} + +.item[data-status='completed'] .content { + color: var(--dsw-alias-label-tertiary); + text-decoration: line-through; +} + +.item[data-status='completed'] .glyph { + color: var(--dsw-alias-state-success-primary); +} + +.item[data-status='in_progress'] .content { + font-weight: 510; + color: var(--dsw-alias-label-primary); +} + +.item[data-status='in_progress'] .glyph { + color: var(--dsw-alias-state-business-primary); +} + +.content { + min-width: 0; + overflow-wrap: anywhere; +} diff --git a/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx new file mode 100644 index 0000000000..283eeb3e5e --- /dev/null +++ b/packages/client/ui-conversation/src/client/skeleton/TodoPanel.tsx @@ -0,0 +1,87 @@ +// TodoPanel: persistent plan strip above the composer (the web counterpart +// of the TUI plan panel). Renders the latest todo/write whole-list snapshot — +// no data of its own, hidden while the list is empty. Mounted through the +// 'conversation.input.dock' slot (QueueDock posture): the dock adapter does +// the selecting, so the panel takes the plain list and stays framework-free. + +import { useState } from 'react' +import type { Context } from 'cordis' +import type { PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots' +import type { TodoItem } from '@deepseek-ai/dsh-client-runtime/client' +import { IconChevronDownOutline14, IconChevronUpOutline14 } from '@deepseek-ai/dsh-client-ui-primitives' +import css from './TodoPanel.module.css' + +export interface TodoPanelProps { + /** The session's current plan (empty renders nothing) — selected by the dock adapter. */ + todos: readonly TodoItem[] +} + +/** Status glyphs mirror the TUI plan panel (✓ done / ● active / ○ pending). */ +const STATUS_GLYPHS: Record = { + completed: '✓', in_progress: '●', pending: '○', +} + +export function TodoPanel({ todos }: TodoPanelProps) { + const [collapsed, setCollapsed] = useState(false) + if (todos.length === 0) return null + + const done = todos.filter(t => t.status === 'completed').length + const active = todos.find(t => t.status === 'in_progress') + + return ( +
+ + {!collapsed && ( +
    + {todos.map(item => ( +
  • + {STATUS_GLYPHS[item.status]} + {item.content} +
    • + ))} +
+ )} +
+ ) +} + +/** Full props of a dock entry: InputZone owner share + session standard kit + global seat. */ +export type TodoDockProps = PropsRuntime<'conversation.input.dock'> + +/** Dock adapter: selects the plan off the session snapshot and hands the strip a plain list. */ +export function TodoDock({ useSession }: TodoDockProps) { + const todos = useSession(s => s.todos) + return +} + +/** + * The plan strip as a plain registrant plugin (QueueDock posture). + * `inject: ['conversation']` is the ordering seam: the conversation service + * mounts after ui-conversation's slot registrations, so the + * 'conversation.input.dock' declaration is on the ledger by then. + */ +export const todoDockEntry = { + name: 'conversation-todo-dock', + inject: ['slots', 'conversation'], + /** + * Register the plan strip into the input dock (list entry, above the queue rows). + * @param ctx - registrant context (disposal rides ctx.effect inside slots.register). + */ + apply(ctx: Context): void { + ctx.slots.register({ name: 'conversation.input.dock', id: 'todo', order: -1 }, TodoDock) + }, +} diff --git a/packages/client/ui-conversation/src/client/toolviews/todo-row.module.css b/packages/client/ui-conversation/src/client/toolviews/todo-row.module.css new file mode 100644 index 0000000000..ff4068d49c --- /dev/null +++ b/packages/client/ui-conversation/src/client/toolviews/todo-row.module.css @@ -0,0 +1,42 @@ +/* todo_write plan-update row: title + progress summary on one line. */ + +.row { + display: flex; + align-items: center; + gap: 8px; + height: 24px; + min-width: 0; + cursor: pointer; + border-radius: 6px; + font-size: 13px; +} + +.row:hover { + background: var(--dsw-alias-interactive-bg-hover); +} + +.badge { + flex: none; + color: var(--dsw-alias-state-business-primary); +} + +.title { + flex: none; + font-weight: 510; + color: var(--dsw-alias-label-primary); +} + +.summary { + flex: 1 1 auto; + min-width: 0; + overflow: hidden; + text-overflow: ellipsis; + white-space: nowrap; + color: var(--dsw-alias-label-secondary); +} + +.err { + flex: none; + color: var(--dsw-alias-state-error-primary); + font-size: 11px; +} diff --git a/packages/client/ui-conversation/src/client/toolviews/todo-row.tsx b/packages/client/ui-conversation/src/client/toolviews/todo-row.tsx new file mode 100644 index 0000000000..353e7a5441 --- /dev/null +++ b/packages/client/ui-conversation/src/client/toolviews/todo-row.tsx @@ -0,0 +1,93 @@ +// todo_write toolview: plan-flavored summary row replacing the generic +// "Tool call" card, registered into the keyed 'conversation.chat.toolview' +// hole like the bash sample (a product registration, not a sample). The row +// summarizes the written list (counts + active item) from the call args; the +// durable list itself renders in the TodoPanel above the composer, so the +// row stays one line. + +import type { KeyboardEvent } from 'react' +import type { Context } from 'cordis' +import { StateDot } from '@deepseek-ai/dsh-client-ui-primitives' +import type { ToolRowProps } from '../contract/slots.ts' +import { toolRowModel } from '../contract/tool-call-model.ts' +import css from './todo-row.module.css' + +/** One parsed args item, shape-checked (model JSON: any field may be missing or mistyped). */ +interface TodoWriteItem { content?: unknown; status?: unknown } + +function isItem(value: unknown): value is TodoWriteItem { + return typeof value === 'object' && value !== null +} + +function summarize(argsRaw: string): string | null { + let parsed: unknown + try { + parsed = JSON.parse(argsRaw) + } catch { + // Mid-stream truncation or malformed model JSON: fall back to the generic summary. + return null + } + // Valid JSON with an invalid shape (null root, non-array todos, null items — + // a rejected tool/call retains such args verbatim): same generic fallback. + if (typeof parsed !== 'object' || parsed === null) return null + const todos = (parsed as { todos?: unknown }).todos + if (!Array.isArray(todos) || !todos.every(isItem)) return null + const done = todos.filter(t => t.status === 'completed').length + const active = todos.find(t => t.status === 'in_progress') + const head = `${done}/${todos.length} 已完成` + return typeof active?.content === 'string' && active.content !== '' + ? `${head} · ${active.content}` + : head +} + +/** One-line plan update row (click opens the raw args in details). Non-ok + * execution states keep the generic row's dot semantics — a cancelled call + * wrote no todo/write, so it must not read as a completed update. */ +export function TodoRow({ toolName, block, openDetails }: ToolRowProps) { + const model = toolRowModel(toolName, block) + const argsRaw = ('kind' in block ? block.call?.argsRaw : block.argsRaw) ?? '' + const summary = summarize(argsRaw) ?? model.summary + // Button semantics, not a