Merge branch 'master' into worktree/provider-credential-lifecycle
This commit is contained in:
Yichen Jiang
@@ -326,6 +326,8 @@
|
||||
|
||||
- id: tool-todo
|
||||
name: '@deepseek-ai/dsh-tool-todo'
|
||||
config:
|
||||
allowParallelInProgress: true
|
||||
|
||||
# Persisted same-session goals reach the model and the slash menu here; the
|
||||
# domain, driver, and `/goal` command are above.
|
||||
|
||||
@@ -474,11 +474,14 @@ function buildAlphaLog(): SessionEvent[] {
|
||||
push({ type: 'step/end', data: { turn, step: 0 } })
|
||||
push({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } })
|
||||
}
|
||||
// Turn 67: todo_write sample — the TodoRow toolview in the flow plus the
|
||||
// todo/write snapshot event feeding the TodoPanel plan strip.
|
||||
// Turn 71: todo_write sample — the TodoRow toolview in the flow plus the
|
||||
// todo/write snapshot event feeding the TodoPanel plan strip. Two items are
|
||||
// in_progress: this fixture chooses the parallel policy, so both surfaces
|
||||
// must render a parallel plan rather than the first active item alone.
|
||||
const fixtureTodos = [
|
||||
{ content: '梳理需求', status: 'completed' },
|
||||
{ content: '实现 fixture 样本', status: 'in_progress' },
|
||||
{ content: '跑后台构建', status: 'in_progress' },
|
||||
{ content: '浏览器验收', status: 'pending' },
|
||||
]
|
||||
// Turn 65: the terminal sample turn 60's two clean prompt rows cannot cover —
|
||||
@@ -531,7 +534,7 @@ function buildAlphaLog(): SessionEvent[] {
|
||||
toolTurn(70, 'web_fetch', '{"url":"https://www.deepseek.com/blog/harness-architecture"}', '# Harness architecture\n\nEverything is a plugin.')
|
||||
|
||||
const todoArgs = JSON.stringify({ todos: fixtureTodos })
|
||||
toolTurn(71, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 1 in progress, 1 completed.')
|
||||
toolTurn(71, 'todo_write', todoArgs, 'Updated todo list: 1 pending, 2 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).
|
||||
|
||||
@@ -242,6 +242,10 @@ describe('createFixtureApi', () => {
|
||||
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)
|
||||
// The sample is a parallel plan: this fixture chooses the parallel policy,
|
||||
// so the surfaces fed from here face more than one active item.
|
||||
const snapshot = events[todoAt] as { data: { todos: { status: string }[] } }
|
||||
expect(snapshot.data.todos.filter(t => t.status === 'in_progress')).toHaveLength(2)
|
||||
})
|
||||
|
||||
it('create adds a session and pushes host/session-added to open host streams', async () => {
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md
|
||||
README.md: bbd115eac0eb914914dc11e504639633c801abdd
|
||||
README.zh.md: 843b49e311fbf1a9157413c42a0ef3e9828284bc
|
||||
README.md: 8d6c26f67916f043251c58a3283542bd58a08666
|
||||
README.zh.md: 8dd43cca59f8dfda18ce036b5d8c6f948306c947
|
||||
|
||||
@@ -34,7 +34,7 @@ A `grep`/`glob` call declaring the `search` render intent renders its result inl
|
||||
|
||||
Tool rows use the keyed, session-scoped `'conversation.chat.toolview'` slot; its render site dispatches via `entryKey: toolName` with `GenericToolCard` as the call-site fallback. The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openFile`), and `ToolRowProps` composes it with the session standard kit. A registrant is a plain plugin with only the slot service edge: `ctx.slots.inject('conversation.chat.toolview', () => ctx.slots.register({ name: 'conversation.chat.toolview', key: '<tool>', inject? }, Row))`. The declaration is the activation and reload dependency; `ConversationService` is required only by registrations that call its actions. Trajectory and waterfall toolview slots share this shape and use their own render sites; RendersCheck rejects a declaration nobody renders.
|
||||
|
||||
The todo surfaces are two registrations over that shape, both using slot declaration injection without a `ConversationService` edge. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`<done>/<total> 已完成 · <active item>` parsed from its args, falling back to the generic summary on malformed or wrongly-shaped model JSON, and keeping the generic dot for non-ok execution states so a cancelled call never reads as a completed update). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: 0` — before Goal and Queue — and is the plan strip: it reads the host-computed `todos` projection via `useProjection` (standing plan: latest `todo/write` with no later `turn/start`) and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and starts collapsed as a header of title plus `"<done>/<total> tasks · <n> in progress"` (status glyphs are the figma check / progress / dashed-pending set). The dock adapter owns the selection so the panel stays a pure function of its props; the standing list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included.
|
||||
The todo surfaces are two registrations over that shape, both using slot declaration injection without a `ConversationService` edge. `TodoRow` takes the `'conversation.chat.toolview'` key `todo_write` and summarizes what the call attempted (`<done>/<total> completed · <active item>` plus a `+<n>` count of the other active ones, parsed from its args through `toolviews/plan-summary.ts` `planSummary`, 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). When the deployment permits parallel work, several items may be `in_progress` at once, so `planSummary` names the first and counts the rest, and deliberately returns the two unjoined: the row ellipsizes its summary text, so a count concatenated onto the end of the task name would be the first thing a narrow row clips. The row hands the count to `ToolRow`'s `summarySuffix`, the shared row's non-shrinking slot beside that ellipsized text (an error row drops it, since its collapsed summary is the failure line). `TodoDock` takes the `'conversation.input.dock'` list slot at `order: 0` — before Goal and Queue — and is the plan strip: it reads the host-computed `todos` projection via `useProjection` (standing plan: latest `todo/write` with no later `turn/start`) and renders `TodoPanel`, which takes the plain list, hides itself while the list is empty, and starts collapsed as a header of title plus its own `·`-joined per-status counts (localized, `1 completed · 2 in progress · 1 pending`, zero-count segments omitted; status glyphs are the figma check / progress / dashed-pending set), so it reports the parallel count without needing a name to truncate. The dock adapter owns the selection so the panel stays a pure function of its props; the standing list lives here rather than in the row so the row stays one line. Anything the input-zone composer chain hides (a `conversation.composer` takeover such as ui-question's) hides the whole dock, this strip included.
|
||||
|
||||
`QueueDock` is the terminal input-dock entry at `order: 20`. It hides while empty, renders one pending row directly, and defaults two or more rows to a collapsed `"<n> 条排队消息"` header whose button expands or collapses the complete list. The header exposes `aria-expanded` and `aria-controls`; the expanded list scrolls within a 180px height bound. An active edit or mutation keeps its rows visible, and emptying the queue restores the collapsed default for the next queue. Each visible ordinary-session row remains a single-line preview with its exact-occurrence edit, delete, and strict-steer actions; addressed subagents retain the rows as a read-only projection because their continuation transport does not expose queue mutation. If strict steer loses to a closed window, the original occurrence remains queued for normal delivery; if the driver already claimed it, normal delivery is already underway. Neither converged race displays a failure, while transport and unknown failures do.
|
||||
|
||||
|
||||
@@ -34,7 +34,7 @@ Think 行默认保持折叠，并在不展开思维链的情况下暴露实时
|
||||
|
||||
审批经由本包声明的链接管编辑器：`ApprovalPanel` 注册为按选择器路由的 `'conversation.composer'` 配置项（ui-question 模式），在审批等待未决期间取代 InputBar 占据编辑器（琥珀色条、理由标题、来自运行中调用参数的配对命令行、一次性的拒绝／允许）。`contract/slots.ts` 中的 `PendingApproval` 领域面在运行时 `PendingWait` 载体之上拥有 wire 编码——带审计关联的 `ApprovalResponsePayload` 值；广播的 `approval/resolved` 帧使等待落定并恢复编辑器。运行时 manager 会将所有审批或问题等待通过 `SessionSummary.pendingInteraction` 投影出来，未实例化的 Session 也不例外；`ui-workspace` 负责其侧边栏呈现。未决等待完全离开消息流：问题（ui-question）与审批（ApprovalPanel）都经编辑器接管作答，不再保留只读占位卡。编辑器底行的 Access 席位挂载 `PermissionSelect`，由 host 计算的 `permissions` 投影经标准工具包 `useProjection` 供数（key 缺席即隐藏 chip）；chip 打开 Menu 原语下拉，其中 kebab-case 预设名渲染为 Title Case 标签；普通安全预设会立即经输入栏注入的 `command` 回调提交 `/permission <preset>`，而 `danger-full-access` 在界面中显示为 `Full access`，选择后先打开页面内的 Modal 风险确认。用户勾选确认项前启用按钮始终不可用；取消、Escape、关闭按钮与点击遮罩都不会提交命令。
|
||||
|
||||
todo 两个面就是在该形状上的两个注册项，都使用 slot 声明注入，不依赖 `ConversationService`。`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: 0` 占用 `'conversation.input.dock'` 列表 slot（位于 Goal 与 Queue 之前），是计划条：它经 `useProjection` 读取 host 计算的 `todos` 投影（站立计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏；列表非空时面板初始折叠，表头显示标题加 `"<已完成>/<总数> tasks · <n> in progress"`（状态图标为 figma 的勾选／进行中／虚线未开始一组）。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；站立列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。
|
||||
todo 两个面就是在该形状上的两个注册项，都使用 slot 声明注入，不依赖 `ConversationService`。`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 经 `toolviews/plan-summary.ts` 的 `planSummary` 解析出 `<已完成>/<总数> 已完成 · <进行中条目>`，以及「其余活跃项的数量」`+<n>`；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）。部署允许并行工作时，可以有多个条目同时处于 `in_progress`，因此 `planSummary` 给出第一个活跃条目并计数其余，且刻意不把两者拼成一个字符串：行会对摘要文本做省略号截断，把数量接在任务名末尾时，窄行最先裁掉的正是这个数量。该行把数量交给 `ToolRow` 的 `summarySuffix`——共享行在被截断文本旁的不收缩位（出错的行会丢弃它，因为其折叠摘要是失败首行）。`TodoDock` 以 `order: 0` 占用 `'conversation.input.dock'` 列表 slot（位于 Goal 与 Queue 之前），是计划条：它经 `useProjection` 读取 host 计算的 `todos` 投影（站立计划：其后没有更晚 `turn/start` 的最近一次 `todo/write`）并渲染 `TodoPanel`，后者接收纯列表，在列表为空时自我隐藏；列表非空时面板初始折叠，表头显示标题加它自行计算的、以 `·` 连接的各状态计数（本地化，形如 `1 已完成 · 2 进行中 · 1 待处理`，计数为零的段落省略；状态图标为 figma 的勾选／进行中／虚线未开始一组），因此它无需一个可被截断的任务名即可报告并行数量。选取由 dock 适配器负责，因此面板保持为其 props 的纯函数；站立列表放在此处而非行内，行才能保持单行。输入区 composer 链隐藏的一切（例如 ui-question 对 `conversation.composer` 的接管）也会隐藏整个 dock，包括这条计划条。
|
||||
|
||||
`QueueDock` 是 `order: 20` 的末端 input-dock 条目。队列为空时隐藏；只有一个待处理项时直接渲染该行；存在两个或更多待处理项时，默认收起为 `"<n> 条排队消息"` 表头，其按钮可展开或收起完整列表。表头暴露 `aria-expanded` 和 `aria-controls`；展开后的列表以 180px 为高度上限，并可滚动。存在进行中的编辑或变更时，列表行会保持可见；队列清空后，下一次出现队列时会恢复默认收起状态。普通会话中的每条可见行仍是单行预览，并提供针对精确单次入队项的编辑、删除和严格 steering 操作；已寻址 subagent 则保留只读行，因为其继续执行传输不提供 Queue 变更。如果严格 steering 输给已关闭的窗口，原单次入队项会留在 Queue 中正常投递；如果驱动器已经认领该项，正常投递就已开始。这两种已收敛的竞态都不显示失败，传输和未知错误仍会显示。
|
||||
|
||||
|
||||
@@ -89,6 +89,20 @@
|
||||
text-overflow: clip;
|
||||
}
|
||||
|
||||
/* Trailing summary fragment kept out of .summary's ellipsis, for a count whose
|
||||
whole value is that it survives a narrow row (the todo row's parallel-active
|
||||
`+n`). Repeats .summary's type because it sits beside that text, and its
|
||||
`nowrap` too: `flex: none` stops the box shrinking but not the text wrapping,
|
||||
which would break the one-line row in the narrow case the slot exists for. */
|
||||
.summarySuffix {
|
||||
flex: none;
|
||||
margin-left: 4px;
|
||||
white-space: nowrap;
|
||||
font-size: 14px;
|
||||
line-height: 24px;
|
||||
color: var(--dsw-alias-label-tertiary);
|
||||
}
|
||||
|
||||
/* File-tool path: same geometry as .summary; hover underline + pointer. */
|
||||
.fileLink {
|
||||
flex: 1 1 auto;
|
||||
|
||||
@@ -46,6 +46,14 @@ export interface ToolRowProps {
|
||||
icon: ReactNode
|
||||
title: string
|
||||
summary: string
|
||||
/**
|
||||
* Trailing summary fragment rendered outside the ellipsized summary text, so
|
||||
* a narrow row clips the summary before this. For a fragment whose whole
|
||||
* value is surviving that clip — the todo row's parallel-active count.
|
||||
* null/absent = the summary is the whole collapsed content. Dropped on an
|
||||
* error row, whose collapsed summary is the failure line instead.
|
||||
*/
|
||||
summarySuffix?: string | null | undefined
|
||||
/** Expanded-body input text; null = no input section. */
|
||||
body: string | null
|
||||
/** Flattened result text for the expanded Output section; null/absent = no output section. */
|
||||
@@ -139,6 +147,7 @@ export function ToolRow({
|
||||
icon,
|
||||
title,
|
||||
summary,
|
||||
summarySuffix,
|
||||
body,
|
||||
output,
|
||||
errorSummary,
|
||||
@@ -173,6 +182,9 @@ export function ToolRow({
|
||||
// the error color outranks both the args summary and a terminal description.
|
||||
const failureLine = state === 'error' ? errorSummary ?? null : null
|
||||
const summaryText = failureLine ?? summary
|
||||
// The failure line replaces the summary wholesale, so a suffix derived from
|
||||
// the call args has nothing left to sit beside.
|
||||
const suffix = failureLine === null ? summarySuffix ?? null : null
|
||||
// The failure line is error prose, not the path: no open-file affordance.
|
||||
const fileLink = filePath !== undefined && onOpenFile !== undefined && failureLine === null
|
||||
const isThink = variant === 'think'
|
||||
@@ -249,6 +261,7 @@ export function ToolRow({
|
||||
{summaryText}
|
||||
</span>
|
||||
)}
|
||||
{suffix !== null && <span className={css.summarySuffix}>{suffix}</span>}
|
||||
</>
|
||||
)}
|
||||
>
|
||||
|
||||
@@ -0,0 +1,60 @@
|
||||
/**
|
||||
* Pure plan derivation for the todo_write row's one-line summary. Several items
|
||||
* may be `in_progress` at once — parallel work runs concurrent tasks, so a
|
||||
* summary built from one active item would silently drop the rest. The plan
|
||||
* strip header derives its own counts inline and shares nothing with this, so
|
||||
* this stays inside the toolviews domain rather than in `contract/` (the
|
||||
* inter-domain face).
|
||||
* @module
|
||||
*/
|
||||
|
||||
/**
|
||||
* One list item as the row sees it: unvalidated model JSON parsed from a call's
|
||||
* args, so any field may be missing or mistyped.
|
||||
*/
|
||||
export interface PlanItemLike {
|
||||
content?: unknown
|
||||
status?: unknown
|
||||
}
|
||||
|
||||
/**
|
||||
* Counts plus the two halves of the summary, deliberately NOT pre-joined: the
|
||||
* row ellipsizes its summary text, and a count concatenated onto the end of the
|
||||
* task name is the first thing a narrow row clips — exactly when it carries
|
||||
* information. The row renders `activeExtra` in its own non-shrinking span
|
||||
* beside the truncatable text.
|
||||
*/
|
||||
export interface PlanSummary {
|
||||
done: number
|
||||
total: number
|
||||
/** First `in_progress` content, or null when that first item is unusable. */
|
||||
activeContent: string | null
|
||||
/** Active items beyond the first; 0 whenever there is no `activeContent` to sit beside. */
|
||||
activeExtra: number
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive the counts and the active summary from a whole-list snapshot. It names
|
||||
* the first `in_progress` item and counts the remaining active ones, so a
|
||||
* parallel plan reports how many tasks are running rather than naming one and
|
||||
* hiding the others. `activeContent` is null when nothing is in progress, or
|
||||
* when the first active item's content is missing, mistyped, or blank once
|
||||
* trimmed — the tool's own rule for usable content, applied here because a
|
||||
* rejected call keeps its args verbatim. The row then renders the counts alone
|
||||
* rather than falling back to the generic tool summary: the counts are already
|
||||
* known to be good, and the active-item clause is the only part an unusable
|
||||
* name costs.
|
||||
* @param todos - the whole list, in model order.
|
||||
* @returns the done/total counts and the two summary halves.
|
||||
*/
|
||||
export function planSummary(todos: readonly PlanItemLike[]): PlanSummary {
|
||||
const active = todos.filter(t => t.status === 'in_progress')
|
||||
const first = active[0]?.content
|
||||
const named = typeof first === 'string' && first.trim() !== ''
|
||||
return {
|
||||
done: todos.filter(t => t.status === 'completed').length,
|
||||
total: todos.length,
|
||||
activeContent: named ? first : null,
|
||||
activeExtra: named ? active.length - 1 : 0,
|
||||
}
|
||||
}
|
||||
@@ -2,9 +2,10 @@
|
||||
// "Tool call" card, registered into the keyed 'conversation.chat.toolview'
|
||||
// hole like the bash sample (a product registration, not a sample). The row
|
||||
// composes ToolRow (chrome, running sweep, whole-row expand) and swaps in a
|
||||
// summary of 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 until expanded.
|
||||
// summary of the written list (counts + active items) from the call args, with
|
||||
// the parallel-active count riding ToolRow's non-shrinking summary suffix so a
|
||||
// narrow row never clips it; the durable list itself renders in the TodoPanel
|
||||
// above the composer, so the row stays one line until expanded.
|
||||
|
||||
import { IconChecklistOutline14 } from '@deepseek-ai/dsh-client-ui-primitives'
|
||||
import type { Context } from 'cordis'
|
||||
@@ -13,18 +14,26 @@ import type { ToolRowProps } from '../contract/slots.ts'
|
||||
import { toolRowModel } from '../contract/tool-call-model.ts'
|
||||
import { ToolRow } from '../chat/ToolRow.tsx'
|
||||
import { NS } from '../locales.ts'
|
||||
import { planSummary, type PlanItemLike } from './plan-summary.ts'
|
||||
|
||||
/** Todo row props: the toolview runtime share plus the standard locale seat. */
|
||||
type TodoRowProps = ToolRowProps & PropsLocale<'conversation'>
|
||||
|
||||
/** 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 {
|
||||
function isItem(value: unknown): value is PlanItemLike {
|
||||
return typeof value === 'object' && value !== null
|
||||
}
|
||||
|
||||
function summarize(argsRaw: string, t: TodoRowProps['t']): string | null {
|
||||
/**
|
||||
* The row's summary split at the ellipsis boundary: `text` truncates, `extra`
|
||||
* is the parallel-active count that must not, so a narrow row never clips the
|
||||
* one part that says several tasks are running.
|
||||
*/
|
||||
interface RowSummary {
|
||||
text: string
|
||||
extra: number
|
||||
}
|
||||
|
||||
function summarize(argsRaw: string, t: TodoRowProps['t']): RowSummary | null {
|
||||
let parsed: unknown
|
||||
try {
|
||||
parsed = JSON.parse(argsRaw)
|
||||
@@ -37,12 +46,12 @@ function summarize(argsRaw: string, t: TodoRowProps['t']): string | null {
|
||||
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(item => item.status === 'completed').length
|
||||
const active = todos.find(item => item.status === 'in_progress')
|
||||
const head = t('todo.completed', { done, total: todos.length })
|
||||
return typeof active?.content === 'string' && active.content !== ''
|
||||
? `${head} · ${active.content}`
|
||||
: head
|
||||
const { done, total, activeContent, activeExtra } = planSummary(todos)
|
||||
const head = t('todo.completed', { done, total })
|
||||
return {
|
||||
text: activeContent === null ? head : `${head} · ${activeContent}`,
|
||||
extra: activeExtra,
|
||||
}
|
||||
}
|
||||
|
||||
/** One-line plan update row (the whole row toggles the call's Input/Output
|
||||
@@ -52,7 +61,7 @@ function summarize(argsRaw: string, t: TodoRowProps['t']): string | null {
|
||||
export function TodoRow({ toolName, block, inspect, t }: TodoRowProps) {
|
||||
const model = toolRowModel(toolName, block)
|
||||
const argsRaw = ('kind' in block ? block.call?.argsRaw : block.argsRaw) ?? ''
|
||||
const summary = summarize(argsRaw, t) ?? model.summary
|
||||
const summary = summarize(argsRaw, t) ?? { text: model.summary, extra: 0 }
|
||||
return (
|
||||
<ToolRow
|
||||
t={t}
|
||||
@@ -60,7 +69,8 @@ export function TodoRow({ toolName, block, inspect, t }: TodoRowProps) {
|
||||
toolName={toolName}
|
||||
icon={<IconChecklistOutline14 />}
|
||||
title={t('todo.rowTitle')}
|
||||
summary={summary}
|
||||
summary={summary.text}
|
||||
summarySuffix={summary.extra > 0 ? `+${summary.extra}` : null}
|
||||
body={model.body}
|
||||
output={model.output}
|
||||
errorSummary={model.errorSummary}
|
||||
|
||||
@@ -301,6 +301,20 @@ describe('ToolRow', () => {
|
||||
expect(view.getByText('List files')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('renders summarySuffix outside the ellipsized summary span, and drops it on a failure line', () => {
|
||||
const view = render(<ToolRow {...rowProps} summarySuffix="+2" />)
|
||||
const summary = view.getByText('List files')
|
||||
const suffix = view.getByText('+2')
|
||||
// Separate spans: .summary truncates, the suffix must not travel inside it.
|
||||
expect(summary.contains(suffix)).toBe(false)
|
||||
view.unmount()
|
||||
// The failure line replaces the summary wholesale, so the suffix goes with it.
|
||||
const failed = render(
|
||||
<ToolRow {...rowProps} state="error" errorSummary="boom" summarySuffix="+2" />,
|
||||
)
|
||||
expect(failed.queryByText('+2')).toBeNull()
|
||||
})
|
||||
|
||||
it('an error file row drops the open-file link (the summary is failure prose, not the path)', () => {
|
||||
const open = vi.fn()
|
||||
const view = render(
|
||||
|
||||
@@ -1,10 +1,13 @@
|
||||
// @vitest-environment jsdom
|
||||
/**
|
||||
* Todo display acceptance: the TodoPanel plan strip (empty-hidden, status
|
||||
* rows, collapse), its TodoDock adapter (selects the plan off the session
|
||||
* snapshot and follows changes), and the todo_write toolview row (progress
|
||||
* summary from args, generic fallback on malformed JSON, shared ToolRow
|
||||
* state dots and leading expansion).
|
||||
* Todo display acceptance: the TodoPanel plan strip (empty-hidden, status rows
|
||||
* including several `in_progress` at once, collapse), its TodoDock adapter
|
||||
* (selects the plan off the session snapshot and follows changes), the row's
|
||||
* plan summary (counts plus the two halves of the active summary — the named
|
||||
* task and the `+N` count that parallel work adds, kept apart so the row never
|
||||
* ellipsizes the count away), and the todo_write toolview row (progress summary
|
||||
* from args, generic fallback on malformed JSON, shared ToolRow state dots and
|
||||
* leading expansion).
|
||||
*/
|
||||
import { act, cleanup, fireEvent, render, screen } from '@testing-library/react'
|
||||
import { afterEach, describe, expect, it, vi } from 'vitest'
|
||||
@@ -17,6 +20,7 @@ import { zh as commonZh } from '@deepseek-ai/dsh-client-locale/src/locales/zh.ts
|
||||
import { TodoRow, todoToolview } from '../src/client/toolviews/todo-row.tsx'
|
||||
import type { TodoDockProps } from '../src/client/skeleton/TodoPanel.tsx'
|
||||
import { TodoDock, TodoPanel, todoDockEntry } from '../src/client/skeleton/TodoPanel.tsx'
|
||||
import { planSummary } from '../src/client/toolviews/plan-summary.ts'
|
||||
import { NS, zh } from '../src/client/locales.ts'
|
||||
|
||||
type TodoRowProps = Parameters<typeof TodoRow>[0]
|
||||
@@ -32,6 +36,49 @@ const LIST: TodoItem[] = [
|
||||
{ content: '补测试', status: 'pending' },
|
||||
]
|
||||
|
||||
/** A parallel plan: three tasks running at once (concurrent subagents). */
|
||||
const PARALLEL: TodoItem[] = [
|
||||
{ content: '搭骨架', status: 'completed' },
|
||||
{ content: '写组件', status: 'in_progress' },
|
||||
{ content: '跑后台构建', status: 'in_progress' },
|
||||
{ content: '读源码', status: 'in_progress' },
|
||||
{ content: '补测试', status: 'pending' },
|
||||
]
|
||||
|
||||
describe('planSummary', () => {
|
||||
it('counts done/total and names the single active item with no extra count', () => {
|
||||
expect(planSummary(LIST)).toEqual({ done: 1, total: 3, activeContent: '写组件', activeExtra: 0 })
|
||||
})
|
||||
|
||||
it('reports the extra active count separately when several items are in progress', () => {
|
||||
// Parallel work marks several: naming one and hiding the rest would lose
|
||||
// them, and the count stays unjoined so the row cannot ellipsize it.
|
||||
expect(planSummary(PARALLEL)).toEqual({ done: 1, total: 5, activeContent: '写组件', activeExtra: 2 })
|
||||
})
|
||||
|
||||
it('has no hint when nothing is in progress', () => {
|
||||
expect(planSummary([{ content: '都完了', status: 'completed' }]))
|
||||
.toEqual({ done: 1, total: 1, activeContent: null, activeExtra: 0 })
|
||||
})
|
||||
|
||||
it('has no hint when the first active item carries no usable content (model JSON)', () => {
|
||||
// Unvalidated args: a missing, mistyped, empty, or whitespace-only content
|
||||
// yields no hint — and no orphan count, even with a second active item to
|
||||
// count. Whitespace-only is the tool's own rejection rule (trimmed
|
||||
// non-empty), and a rejected call keeps its args verbatim.
|
||||
expect(planSummary([{ status: 'in_progress' }, { content: 'x', status: 'in_progress' }]))
|
||||
.toMatchObject({ activeContent: null, activeExtra: 0 })
|
||||
expect(planSummary([{ content: 42, status: 'in_progress' }]).activeContent).toBeNull()
|
||||
expect(planSummary([{ content: '', status: 'in_progress' }]).activeContent).toBeNull()
|
||||
expect(planSummary([{ content: ' ', status: 'in_progress' }, { content: 'x', status: 'in_progress' }]))
|
||||
.toMatchObject({ activeContent: null, activeExtra: 0 })
|
||||
})
|
||||
|
||||
it('is empty-safe', () => {
|
||||
expect(planSummary([])).toEqual({ done: 0, total: 0, activeContent: null, activeExtra: 0 })
|
||||
})
|
||||
})
|
||||
|
||||
describe('TodoPanel', () => {
|
||||
it('renders nothing while the list is empty', () => {
|
||||
const { container } = render(<TodoPanel todos={[]} t={t} />)
|
||||
@@ -80,6 +127,18 @@ describe('TodoPanel', () => {
|
||||
expect(screen.getAllByRole('listitem')).toHaveLength(3)
|
||||
})
|
||||
|
||||
it('marks every parallel active item, and counts them all in the header', () => {
|
||||
render(<TodoPanel todos={PARALLEL} t={t} />)
|
||||
fireEvent.click(screen.getByRole('button', { expanded: false }))
|
||||
// The old unconditional cap made this list unreachable: three items carry
|
||||
// the in-progress glyph at once, and the header counts all three.
|
||||
const statuses = screen.getAllByRole('listitem').map(li => li.getAttribute('data-status'))
|
||||
expect(statuses.filter(s => s === 'in_progress')).toHaveLength(3)
|
||||
expect(screen.getByText('跑后台构建')).toBeTruthy()
|
||||
expect(screen.getByText('读源码')).toBeTruthy()
|
||||
expect(screen.getByText('1 已完成 · 3 进行中 · 1 待处理')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('an all-completed list collapses the summary to the done count alone', () => {
|
||||
render(<TodoPanel todos={[{ content: '都完了', status: 'completed' }]} t={t} />)
|
||||
expect(screen.getByRole('button', { expanded: false })).toBeTruthy()
|
||||
@@ -145,12 +204,30 @@ describe('TodoRow', () => {
|
||||
expect(screen.getByText('1/3 已完成 · 写组件')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('reports the extra active count outside the ellipsized summary text', () => {
|
||||
const { container } = render(<TodoRow {...rowProps(resultNode(JSON.stringify({ todos: PARALLEL })))} />)
|
||||
const text = screen.getByText('1/5 已完成 · 写组件')
|
||||
const extra = screen.getByText('+2')
|
||||
// Separate spans: .summary truncates, the count must not travel inside it.
|
||||
expect(text.contains(extra)).toBe(false)
|
||||
expect(container.textContent).toContain('1/5 已完成 · 写组件+2')
|
||||
})
|
||||
|
||||
it('omits the active clause when no item is in progress and reads running-call args', () => {
|
||||
const args = JSON.stringify({ todos: [{ content: 'x', status: 'completed' }] })
|
||||
render(<TodoRow {...rowProps({ callId: 'c1', name: 'todo_write', argsRaw: args, turn: 1, step: 1, time: 1_000, callView: null })} />)
|
||||
expect(screen.getByText('1/1 已完成')).toBeTruthy()
|
||||
})
|
||||
|
||||
it('keeps the counts when an active item has unusable content, instead of the generic summary', () => {
|
||||
// planSummary yields activeContent null here, but the counts are known good,
|
||||
// so the row drops only the active clause — `?? model.summary` never runs.
|
||||
const args = JSON.stringify({ todos: [{ content: 'done', status: 'completed' }, { content: 42, status: 'in_progress' }] })
|
||||
const { container } = render(<TodoRow {...rowProps(resultNode(args))} />)
|
||||
expect(screen.getByText('1/2 已完成')).toBeTruthy()
|
||||
expect(container.textContent).not.toContain('+')
|
||||
})
|
||||
|
||||
it('keeps the non-ok execution states visible through the shared row states', () => {
|
||||
// A running call (no result yet) carries the running state (row sweep).
|
||||
const args = JSON.stringify({ todos: LIST })
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
/**
|
||||
* The one-line contract of the ToolRow summary line as CSS text. jsdom has no
|
||||
* layout, so the rendering specs (chat-tool-row.spec.tsx) can pin which spans
|
||||
* exist but not whether a narrow row still fits on one line; these read the
|
||||
* declarations the layout depends on.
|
||||
*/
|
||||
import { readFileSync } from 'node:fs'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { describe, expect, it } from 'vitest'
|
||||
|
||||
const css = readFileSync(fileURLToPath(new URL('../src/client/chat/ToolRow.module.css', import.meta.url)), 'utf8')
|
||||
/** Declarations only: the sheet's prose names the properties it explains. */
|
||||
const declarationText = css.replace(/\/\*[\s\S]*?\*\//g, ' ')
|
||||
|
||||
function declarations(selector: string): string[] {
|
||||
// Anchored at a rule boundary: an unanchored match would silently read a
|
||||
// compound rule that merely contains the selector (`.root:hover .summarySuffix`)
|
||||
// if one ever lands above the base rule.
|
||||
const rule = new RegExp(`(?:^|\\})\\s*\\${selector}\\s*\\{([^{}]*)\\}`).exec(declarationText)
|
||||
if (rule === null) throw new Error(`ToolRow.module.css has no \`${selector}\` rule`)
|
||||
return (rule[1] ?? '').split(';').map(part => part.trim()).filter(Boolean)
|
||||
}
|
||||
|
||||
describe('ToolRow.module.css summary line', () => {
|
||||
it('keeps the summary suffix on one line and unshrunk', () => {
|
||||
// `flex: none` stops the box shrinking, not the text wrapping: without
|
||||
// `nowrap`, a row too narrow for title + separator + suffix wraps the `+n`
|
||||
// onto a second line — the exact case the slot exists to survive.
|
||||
expect(declarations('.summarySuffix')).toEqual(expect.arrayContaining([
|
||||
'flex: none',
|
||||
'white-space: nowrap',
|
||||
]))
|
||||
})
|
||||
|
||||
it('leaves the truncation to the summary text alone', () => {
|
||||
// The suffix must never ellipsize: a clipped count reads as a smaller
|
||||
// number rather than as missing information.
|
||||
expect(declarations('.summary')).toEqual(expect.arrayContaining([
|
||||
'overflow: hidden',
|
||||
'text-overflow: ellipsis',
|
||||
'white-space: nowrap',
|
||||
]))
|
||||
expect(declarations('.summarySuffix')).not.toEqual(expect.arrayContaining(['text-overflow: ellipsis']))
|
||||
})
|
||||
})
|
||||
@@ -161,7 +161,7 @@ export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap]
|
||||
export interface TodoItem {
|
||||
/** What this task is — a short imperative line shown in the UI. */
|
||||
content: string
|
||||
/** Lifecycle state. `in_progress` marks the single task being worked now. */
|
||||
/** Lifecycle state. `in_progress` marks a task being worked now; parallel work may mark several. */
|
||||
status: 'pending' | 'in_progress' | 'completed'
|
||||
}
|
||||
|
||||
|
||||
@@ -45,6 +45,7 @@
|
||||
"@deepseek-ai/dsh-session-persistence-sqlite": "workspace:^",
|
||||
"@deepseek-ai/dsh-subprocess": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-subagent": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-todo": "workspace:^",
|
||||
"@deepseek-ai/dsh-tool-web": "workspace:^",
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
}
|
||||
|
||||
@@ -10,6 +10,7 @@ import type { Config as CodexHooksConfig } from '@deepseek-ai/dsh-hooks-codex'
|
||||
import type { Config as JsonlConfig } from '@deepseek-ai/dsh-session-persistence-jsonl'
|
||||
import type { Config as SqliteConfig } from '@deepseek-ai/dsh-session-persistence-sqlite'
|
||||
import type { Config as ToolSubagentConfig } from '@deepseek-ai/dsh-tool-subagent'
|
||||
import type { Config as ToolTodoConfig } from '@deepseek-ai/dsh-tool-todo'
|
||||
import type { Config as ToolWebConfig } from '@deepseek-ai/dsh-tool-web'
|
||||
import type { ProjectProfile } from '../../project/types.ts'
|
||||
import { defineFeatures } from '../define-feature.ts'
|
||||
@@ -126,7 +127,12 @@ config:
|
||||
id: 'default',
|
||||
label: 'todo_write tool',
|
||||
default: true,
|
||||
resources: [{ kind: 'npm-cordis-config-entry', id: 'tool-todo', package: '@deepseek-ai/dsh-tool-todo' }],
|
||||
resources: [{
|
||||
kind: 'npm-cordis-config-entry',
|
||||
id: 'tool-todo',
|
||||
package: '@deepseek-ai/dsh-tool-todo',
|
||||
config: { allowParallelInProgress: true } satisfies ToolTodoConfig,
|
||||
}],
|
||||
}],
|
||||
},
|
||||
{
|
||||
|
||||
@@ -27,6 +27,9 @@
|
||||
{
|
||||
"path": "../../subagent/tool-subagent"
|
||||
},
|
||||
{
|
||||
"path": "../../todo/tool-todo"
|
||||
},
|
||||
{
|
||||
"path": "../../web/tool-web"
|
||||
},
|
||||
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/todo/tool-todo/README.md
|
||||
README.md: 456d4a08d88b145d574362ffa0874faef9167b22
|
||||
README.zh.md: ec37682773e50c3f153525f6c2b6b6cce583144f
|
||||
README.md: 914e89a000e4bb87ebd7844f05db3809c6726528
|
||||
README.zh.md: c88dbf976fa5110028fcc964ab9aa8efcc3244d3
|
||||
|
||||
@@ -14,9 +14,15 @@ Registers one tool, `todo_write(todos: [{ content, status }])`, on `ctx.tools`.
|
||||
|
||||
The list belongs to the ONE agent session that called the tool. There is no subagent/shared/swarm scope: a non-agent caller (no `exec.agent`) has nowhere to write the list and is rejected. This is a deliberate scope limit — see the Agent Note.
|
||||
|
||||
## Configuration
|
||||
|
||||
`allowParallelInProgress` is required: every composition must choose whether several todos may be `in_progress` at once. It is a deployment choice, not a fixed rule: whether concurrent active tasks are legitimate depends on runtime concurrency the tool cannot observe. Use `true` for agents that may fan out work and `false` to enforce the single-active discipline.
|
||||
|
||||
The flag moves the model-facing instruction and the accepted input together — `true` asks the model to mark every actively worked task and accepts any number, `false` asks for exactly one and rejects a call marking more with `Error: invalid todos: at most one task may be in_progress (got <n>)`. The durable-log invariant does NOT follow it: a log written while parallel work was allowed must still replay after a deployment tightens the policy, so the invariant stays silent on the active count.
|
||||
|
||||
## Validation
|
||||
|
||||
Beyond the schema's type/required/enum checks, `execute` rejects an empty or duplicate `content`, more than one `in_progress` task (a coherent plan has at most one task active), and any item key beyond `content`/`status` — an extended item shape (ids, nesting) fails loud instead of silently flattening, keeping the logged snapshot equal to what the model believes it wrote. Ordering and the discipline of keeping the list current are left to the model via the tool description.
|
||||
Beyond the schema's type/required/enum checks, `execute` rejects an empty or duplicate `content`, and any item key beyond `content`/`status` — an extended item shape (ids, nesting) fails loud instead of silently flattening, keeping the logged snapshot equal to what the model believes it wrote. How many tasks may be `in_progress` at once is the deployment's call (§ Configuration): a composition that chooses `true` permits parallel work (concurrent subagents, background commands) to mark several tasks simultaneously. Ordering and the discipline of keeping the list current are left to the model via the tool description.
|
||||
|
||||
## Rendering
|
||||
|
||||
@@ -50,7 +56,7 @@ Prefix-stable while the definition and visibility are unchanged. Plugin lifecycl
|
||||
|
||||
#### What the model sees
|
||||
|
||||
Each assistant tool call retains the entire replacement list in its arguments. Success returns exactly `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.` Stable failures are ``Error: invalid todo: `content` must be a non-empty string``, `Error: invalid todos: duplicate content "<content>"`, `Error: invalid todos: at most one task may be in_progress, got <count>`, and `Error: todo_write requires an owning agent session`. The full `todo/write` session event is UI and replay state, not a second model message.
|
||||
Each assistant tool call retains the entire replacement list in its arguments. Success returns exactly `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.` Stable failures are ``Error: invalid todo: `content` must be a non-empty string``, `Error: invalid todos: duplicate content "<content>"`, `Error: todo_write requires an owning agent session`, and — only where the deployment set `allowParallelInProgress: false` — `Error: invalid todos: at most one task may be in_progress (got <n>)`. The full `todo/write` session event is UI and replay state, not a second model message.
|
||||
|
||||
#### Token effect
|
||||
|
||||
|
||||
@@ -14,9 +14,15 @@
|
||||
|
||||
该列表属于调用工具的唯一 agent 会话。不存在 subagent／共享／swarm scope：非 agent 调用方（没有 `exec.agent`）无处写入列表，因此会被拒绝。这是有意设置的 scope 限制，详见 Agent Note（agent 决策记录）。
|
||||
|
||||
## 配置
|
||||
|
||||
`allowParallelInProgress` 是必填项：每个组合都必须选择是否允许多个 todo 同时处于 `in_progress`。这是部署层的选择而非固定规则：并发的活跃任务是否合理，取决于工具无法观测的运行时并发情况。可能并行展开工作的 agent 使用 `true`，`false` 则强制执行单活跃项纪律。
|
||||
|
||||
该开关会同时改变面向模型的指令与接受的输入——`true` 要求模型标记每个正在推进的任务并接受任意数量；`false` 要求恰好一个，并以 `Error: invalid todos: at most one task may be in_progress (got <n>)` 拒绝标记更多的调用。持久日志不变式**不**跟随它：在允许并行时写下的日志，在部署收紧策略之后仍必须可回放，因此不变式对活跃数量保持沉默。
|
||||
|
||||
## 验证
|
||||
|
||||
除 schema 的类型／必填／枚举检查外，`execute` 还会拒绝空或重复的 `content`、同时存在多个 `in_progress` 任务的情况（连贯计划最多只有一个活跃任务），以及 `content`/`status` 之外的任何条目键——扩展条目形状（id、嵌套）会明确报错而不是被静默压平，保证落日志的快照与模型自认为写入的内容一致。列表的顺序及及时更新由模型依照工具描述负责。
|
||||
除 schema 的类型／必填／枚举检查外，`execute` 还会拒绝空或重复的 `content`，以及 `content`/`status` 之外的任何条目键——扩展条目形状（id、嵌套）会明确报错而不是被静默压平，保证落日志的快照与模型自认为写入的内容一致。同时可以有多少任务处于 `in_progress` 由部署决定（见 § 配置）：选择 `true` 的组合允许并行工作（并发 subagent、后台命令）同时将多个任务标记为 `in_progress`。列表的顺序及及时更新由模型依照工具描述负责。
|
||||
|
||||
## 渲染
|
||||
|
||||
@@ -50,7 +56,7 @@
|
||||
|
||||
#### 模型看到的内容
|
||||
|
||||
每个 assistant 工具调用都会在参数中保留整个替换列表。成功时原样返回 `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.`。稳定失败文本为 ``Error: invalid todo: `content` must be a non-empty string``、`Error: invalid todos: duplicate content "<content>"`、`Error: invalid todos: at most one task may be in_progress, got <count>` 和 `Error: todo_write requires an owning agent session`。完整 `todo/write` 会话事件是 UI 与回放状态，而非第二条模型消息。
|
||||
每个 assistant 工具调用都会在参数中保留整个替换列表。成功时原样返回 `Updated todo list: <pending> pending, <inProgress> in progress, <completed> completed.`。稳定失败文本为 ``Error: invalid todo: `content` must be a non-empty string``、`Error: invalid todos: duplicate content "<content>"`、`Error: todo_write requires an owning agent session`，以及——仅在部署设置了 `allowParallelInProgress: false` 时——`Error: invalid todos: at most one task may be in_progress (got <n>)`。完整 `todo/write` 会话事件是 UI 与回放状态，而非第二条模型消息。
|
||||
|
||||
#### Token 影响
|
||||
|
||||
|
||||
@@ -30,6 +30,7 @@
|
||||
],
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"schemastery": "^3.18.0",
|
||||
"zod": "^4.4.3"
|
||||
},
|
||||
"peerDependencies": {
|
||||
@@ -41,6 +42,8 @@
|
||||
"cordis": "^4.0.0-rc.7"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@cordisjs/plugin-include": "workspace:^",
|
||||
"@cordisjs/plugin-loader": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop": "workspace:^",
|
||||
"@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
|
||||
|
||||
@@ -6,7 +6,8 @@
|
||||
*/
|
||||
|
||||
import type { Context } from 'cordis'
|
||||
import { z } from 'zod'
|
||||
import z from 'schemastery'
|
||||
import { z as zod } from 'zod'
|
||||
import type { ZodType } from 'zod'
|
||||
import { defineTool } from '@deepseek-ai/dsh-tools'
|
||||
import type { TodoItem } from '@deepseek-ai/dsh-session'
|
||||
@@ -24,29 +25,73 @@ export const inject = ['tools']
|
||||
/** The valid {@link TodoItem} statuses, as a runtime set for input narrowing. */
|
||||
const STATUSES = ['pending', 'in_progress', 'completed'] as const
|
||||
|
||||
const DESCRIPTION =
|
||||
/** Model-facing todo tool configuration. */
|
||||
export interface Config {
|
||||
/**
|
||||
* Required deployment choice for whether several todos may be `in_progress` at once. True suits
|
||||
* agents that run work concurrently — subagents, background commands, workflow fan-out — and the
|
||||
* description then instructs the model to mark every actively worked task. False restores the
|
||||
* single-active discipline: the description asks for exactly one, and a call marking more is
|
||||
* rejected.
|
||||
*/
|
||||
allowParallelInProgress: boolean
|
||||
}
|
||||
|
||||
/** Schemastery configuration for the todo tool consumer. */
|
||||
export const Config: z<Config> = z.object({
|
||||
allowParallelInProgress: z.boolean().required(),
|
||||
})
|
||||
|
||||
const DESCRIPTION_HEAD =
|
||||
'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).'
|
||||
+ 'todo per concrete step before you start. '
|
||||
|
||||
const DESCRIPTION_PARALLEL =
|
||||
'Mark every todo being actively worked '
|
||||
+ 'on `in_progress` — several at once when work genuinely runs in parallel (e.g. '
|
||||
+ 'concurrent subagents or background commands), one for sequential work; while '
|
||||
+ 'work remains, at least one task should be `in_progress`. '
|
||||
|
||||
const DESCRIPTION_SINGLE =
|
||||
'Keep AT MOST ONE todo `in_progress` at a '
|
||||
+ 'time; while work remains, exactly one active task should be `in_progress`. '
|
||||
|
||||
const DESCRIPTION_TAIL =
|
||||
'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).'
|
||||
|
||||
/**
|
||||
* The model-facing description for one activation. The active-status clause is the only part that
|
||||
* varies, because it is the only instruction the parallel policy changes.
|
||||
* @param allowParallel - whether several todos may be `in_progress` at once.
|
||||
* @returns the composed tool description.
|
||||
*/
|
||||
function describe(allowParallel: boolean): string {
|
||||
return DESCRIPTION_HEAD
|
||||
+ (allowParallel ? DESCRIPTION_PARALLEL : DESCRIPTION_SINGLE)
|
||||
+ DESCRIPTION_TAIL
|
||||
}
|
||||
|
||||
/**
|
||||
* Validate the value constraints the ParameterSchemaSpec can't express and build the canonical {@link
|
||||
* TodoItem}[]: trimmed non-empty unique content and at most one in-progress item. The registry
|
||||
* has already enforced the status enum and rejected unknown item keys (`additionalProperties:
|
||||
* false` — the logged snapshot must equal what the model believes it wrote, so a nested/extended
|
||||
* item shape fails loud at the schema boundary instead of silently flattening); the cast below
|
||||
* records that guarantee.
|
||||
* TodoItem}[]: trimmed non-empty unique content, and at most one `in_progress` item unless the
|
||||
* deployment allows parallel work. The registry has already enforced the status enum and rejected
|
||||
* unknown item keys (`additionalProperties: false` — the logged snapshot must equal what the model
|
||||
* believes it wrote, so a nested/extended item shape fails loud at the schema boundary instead of
|
||||
* silently flattening); the cast below records that guarantee.
|
||||
* @param raw - the model-supplied list, already schema-checked.
|
||||
* @param allowParallel - whether several items may be `in_progress` at once.
|
||||
* @returns the canonical list.
|
||||
*/
|
||||
function toTodoList(raw: { content: string; status: string }[]): TodoItem[] {
|
||||
function toTodoList(raw: { content: string; status: string }[], allowParallel: boolean): TodoItem[] {
|
||||
const todos: TodoItem[] = []
|
||||
const seen = new Set<string>()
|
||||
let inProgress = 0
|
||||
let active = 0
|
||||
for (const item of raw) {
|
||||
const content = item.content.trim()
|
||||
if (content.length === 0) {
|
||||
@@ -56,27 +101,32 @@ function toTodoList(raw: { content: string; status: string }[]): TodoItem[] {
|
||||
throw new Error(`invalid todos: duplicate content ${JSON.stringify(content)}`)
|
||||
}
|
||||
seen.add(content)
|
||||
const status = item.status as TodoItem['status']
|
||||
if (status === 'in_progress') inProgress++
|
||||
todos.push({ content, status })
|
||||
if (item.status === 'in_progress') active++
|
||||
todos.push({ content, status: item.status as TodoItem['status'] })
|
||||
}
|
||||
if (inProgress > 1) {
|
||||
throw new Error(`invalid todos: at most one task may be in_progress, got ${inProgress}`)
|
||||
if (!allowParallel && active > 1) {
|
||||
throw new Error(`invalid todos: at most one task may be in_progress (got ${active})`)
|
||||
}
|
||||
return todos
|
||||
}
|
||||
|
||||
/** Wire payload schema of the `todos` projection (whole list or pre-first-write null). */
|
||||
const todosProjectionSchema: ZodType<TodoItem[] | null> = z.union([
|
||||
z.array(z.object({
|
||||
content: z.string(),
|
||||
status: z.union([z.literal('pending'), z.literal('in_progress'), z.literal('completed')]),
|
||||
const todosProjectionSchema: ZodType<TodoItem[] | null> = zod.union([
|
||||
zod.array(zod.object({
|
||||
content: zod.string(),
|
||||
status: zod.union([zod.literal('pending'), zod.literal('in_progress'), zod.literal('completed')]),
|
||||
})),
|
||||
z.null(),
|
||||
zod.null(),
|
||||
])
|
||||
|
||||
/** Register the `todo_write` tool on `ctx.tools` and, when the session-projection seam is composed, the `todos` unit. */
|
||||
export function apply(ctx: Context): void {
|
||||
/**
|
||||
* Register the `todo_write` tool on `ctx.tools` and, when the session-projection seam is composed,
|
||||
* the `todos` unit.
|
||||
* @param ctx - registrant context carrying the tool registry.
|
||||
* @param config - deployment's explicit todo policy.
|
||||
*/
|
||||
export function apply(ctx: Context, config: Config): void {
|
||||
const allowParallel = config.allowParallelInProgress
|
||||
// The unit child activates only when a projection registry is composed
|
||||
// (headless assemblies without the seam stay unaffected). Standing-plan fold:
|
||||
// latest whole todo/write list, cleared by the next turn/start (turn/end keeps
|
||||
@@ -99,7 +149,7 @@ export function apply(ctx: Context): void {
|
||||
})
|
||||
ctx.tools.register(defineTool({
|
||||
name: 'todo_write',
|
||||
description: DESCRIPTION,
|
||||
description: describe(allowParallel),
|
||||
parameters: {
|
||||
todos: {
|
||||
type: 'array',
|
||||
@@ -155,7 +205,7 @@ export function apply(ctx: Context): void {
|
||||
}],
|
||||
},
|
||||
execute(args, exec) {
|
||||
const todos = toTodoList(args.todos)
|
||||
const todos = toTodoList(args.todos, allowParallel)
|
||||
if (!exec.agent) {
|
||||
// The list is per-agent-session state; a non-agent caller (no owning
|
||||
// session) has nowhere to write it. Reject rather than silently no-op.
|
||||
|
||||
@@ -12,11 +12,18 @@ export const name = 'tool-todo-invariant'
|
||||
/** Service required before the companion can reserve package ownership. */
|
||||
export const inject = ['invariants']
|
||||
|
||||
/** Validate one whole-list todo snapshot before it reaches the durable log. */
|
||||
/**
|
||||
* Validate one whole-list todo snapshot before it reaches the durable log.
|
||||
*
|
||||
* Deliberately silent on how many items are `in_progress`. That is the tool's
|
||||
* per-deployment policy (`Config.allowParallelInProgress`), not a durable-shape
|
||||
* rule: a log written while parallel work was allowed must still replay after a
|
||||
* deployment tightens the policy, so tying the invariant to the current config
|
||||
* would reject history that was valid when it was written.
|
||||
*/
|
||||
function validateTodos(value: unknown, fail: InvariantFailure): void {
|
||||
if (!Array.isArray(value)) fail('todo/write todos must be an array')
|
||||
const seen = new Set<string>()
|
||||
let active = 0
|
||||
for (const item of value) {
|
||||
if (typeof item !== 'object' || item === null) fail('todo/write entries must be objects')
|
||||
const { content, status } = item as Record<string, unknown>
|
||||
@@ -28,9 +35,7 @@ function validateTodos(value: unknown, fail: InvariantFailure): void {
|
||||
if (typeof status !== 'string' || !TODO_STATUSES.has(status)) {
|
||||
fail(`todo/write carries unknown status ${JSON.stringify(status)}`)
|
||||
}
|
||||
if (status === 'in_progress') active += 1
|
||||
}
|
||||
if (active > 1) fail(`todo/write contains ${active} in-progress entries; at most one is allowed`)
|
||||
}
|
||||
|
||||
/* jscpd:ignore-start -- package companions share replay and dispatch plumbing */
|
||||
|
||||
@@ -18,7 +18,7 @@ async function harness(adapter: MockAdapter): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await mountAgentLoopTestDependencies(ctx)
|
||||
await ctx.plugin(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(ToolTodo)
|
||||
await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
return ctx
|
||||
}
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import SessionStore, { type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
import * as TodoInvariant from '@deepseek-ai/dsh-tool-todo/invariant'
|
||||
import InvariantService from '@deepseek-ai/dsh-invariants'
|
||||
|
||||
@@ -17,13 +19,22 @@ function event(todos: unknown): SessionEvent {
|
||||
}
|
||||
|
||||
describe('todo snapshot invariants', () => {
|
||||
it('accepts a unique whole-list snapshot with one active item', async () => {
|
||||
const ctx = await setup()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event([
|
||||
it('accepts historical and live parallel snapshots under the single-active tool policy', async () => {
|
||||
const todos = [
|
||||
{ content: 'Inspect state', status: 'completed' },
|
||||
{ content: 'Apply fix', status: 'in_progress' },
|
||||
{ content: 'Watch background build', status: 'in_progress' },
|
||||
{ content: 'Run checks', status: 'pending' },
|
||||
])) }).not.toThrow()
|
||||
] as const
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(ToolTodo, { allowParallelInProgress: false })
|
||||
ctx.sessions.create().append('todo/write', { todos: [...todos] })
|
||||
await ctx.plugin(InvariantService, { enabled: true })
|
||||
|
||||
await expect(ctx.plugin(TodoInvariant).then(() => undefined)).resolves.toBeUndefined()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(todos)) }).not.toThrow()
|
||||
})
|
||||
|
||||
it.each([
|
||||
@@ -36,7 +47,6 @@ describe('todo snapshot invariants', () => {
|
||||
[[{ content: 'same', status: 'pending' }, { content: 'same', status: 'completed' }], /repeats content/],
|
||||
[[{ content: 'task', status: 42 }], /unknown status/],
|
||||
[[{ content: 'task', status: 'paused' }], /unknown status/],
|
||||
[[{ content: 'one', status: 'in_progress' }, { content: 'two', status: 'in_progress' }], /at most one/],
|
||||
])('rejects an incoherent durable todo snapshot', async (todos, message) => {
|
||||
const ctx = await setup()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(todos)) }).toThrow(message)
|
||||
|
||||
139
packages/todo/tool-todo/tests/loader-composition.spec.ts
Normal file
139
packages/todo/tool-todo/tests/loader-composition.spec.ts
Normal file
@@ -0,0 +1,139 @@
|
||||
// Proves `allowParallelInProgress` is real configurability and not a constant:
|
||||
// the flag is set in a cordis.yml booted through the real Loader, and both faces
|
||||
// it controls — the model-facing description and the accepted input — follow it.
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { pathToFileURL } from 'node:url'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import Loader from '@cordisjs/plugin-loader'
|
||||
import Include from '@cordisjs/plugin-include'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import AgentRegistry, { Inbox } from '@deepseek-ai/dsh-agent'
|
||||
import type { Agent } from '@deepseek-ai/dsh-agent'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
||||
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
|
||||
|
||||
let root: string | undefined
|
||||
let context: Context | undefined
|
||||
|
||||
afterEach(async () => {
|
||||
await context?.fiber.dispose()
|
||||
context = undefined
|
||||
if (root !== undefined) await rm(root, { recursive: true, force: true })
|
||||
root = undefined
|
||||
})
|
||||
|
||||
function agent(ctx: Context): Agent {
|
||||
const scope = ctx.plugin(() => {})
|
||||
const id = SessionId('todo-loader-agent')
|
||||
const session = Session.create(id)
|
||||
const value: Agent = {
|
||||
id, options: {}, session, inbox: new Inbox(session, { inserted: () => {}, discarded: () => {}, claimed: () => {} }),
|
||||
status: 'idle', ctx: scope.ctx,
|
||||
followup: () => {}, steer: () => {}, inject: () => {}, send: () => {}, cancel() {},
|
||||
runMaintenance: task => task(new AbortController().signal),
|
||||
whenIdle: () => Promise.resolve(),
|
||||
}
|
||||
ctx.agents.register(value)
|
||||
return value
|
||||
}
|
||||
|
||||
function resultText(result: { content: { type: string; text?: string }[] }): string {
|
||||
return result.content.filter(block => block.type === 'text').map(block => block.text).join('')
|
||||
}
|
||||
|
||||
/**
|
||||
* Boot a cordis.yml carrying the given tool-todo config block.
|
||||
* @param configLines - YAML lines nested under the tool's `config:` key.
|
||||
* @returns the booted context.
|
||||
*/
|
||||
async function boot(configLines: readonly string[]): Promise<Context> {
|
||||
root = await mkdtemp(join(tmpdir(), 'dsh-todo-loader-'))
|
||||
const configPath = join(root, 'cordis.yml')
|
||||
await writeFile(configPath, [
|
||||
"- name: '@deepseek-ai/dsh-agent'",
|
||||
"- name: '@deepseek-ai/dsh-system-prompt'",
|
||||
"- name: '@deepseek-ai/dsh-tools'",
|
||||
"- name: '@deepseek-ai/dsh-tool-todo'",
|
||||
...configLines.length > 0 ? [' config:', ...configLines] : [],
|
||||
'',
|
||||
].join('\n'))
|
||||
|
||||
const ctx = new Context()
|
||||
context = ctx
|
||||
ctx.baseUrl = pathToFileURL(root).href + '/'
|
||||
await ctx.plugin(Loader)
|
||||
ctx.loader.builtins.include = Include
|
||||
const modules = new Map<string, unknown>([
|
||||
['@deepseek-ai/dsh-agent', AgentRegistry],
|
||||
['@deepseek-ai/dsh-system-prompt', SystemPrompt],
|
||||
['@deepseek-ai/dsh-tools', ToolRegistry],
|
||||
['@deepseek-ai/dsh-tool-todo', ToolTodo],
|
||||
])
|
||||
ctx.loader.internal = {
|
||||
version: 'v2',
|
||||
async import(specifier: string) {
|
||||
if (!modules.has(specifier)) throw new Error(`unexpected Loader import: ${specifier}`)
|
||||
return modules.get(specifier)
|
||||
},
|
||||
} as unknown as NonNullable<typeof ctx.loader.internal>
|
||||
await ctx.loader.create({ name: 'cordis:include', config: { path: pathToFileURL(configPath).href } })
|
||||
await ctx.loader.await()
|
||||
return ctx
|
||||
}
|
||||
|
||||
const PARALLEL_TODOS = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'in_progress' },
|
||||
]
|
||||
|
||||
describe('tool-todo real Loader composition through cordis.yml', () => {
|
||||
it('allowParallelInProgress: false narrows the description and rejects a parallel write', async () => {
|
||||
const ctx = await boot([' allowParallelInProgress: false'])
|
||||
const description = ctx.tools.schemas().find(s => s.name === 'todo_write')?.description ?? ''
|
||||
expect(description).toContain('Keep AT MOST ONE todo `in_progress`')
|
||||
expect(description).not.toContain('several at once')
|
||||
|
||||
const owner = agent(ctx)
|
||||
const result = await ctx.tools.execute({
|
||||
signal: new AbortController().signal,
|
||||
callId: CallId('parallel'),
|
||||
name: 'todo_write',
|
||||
arguments: { todos: PARALLEL_TODOS },
|
||||
agent: owner,
|
||||
})
|
||||
expect(result.isError).toBe(true)
|
||||
expect(resultText(result)).toContain('at most one task may be in_progress')
|
||||
expect(owner.session.events.some(e => e.type === 'todo/write')).toBe(false)
|
||||
}, 30_000)
|
||||
|
||||
it('allowParallelInProgress: true permits a parallel write end to end', async () => {
|
||||
const ctx = await boot([' allowParallelInProgress: true'])
|
||||
const description = ctx.tools.schemas().find(s => s.name === 'todo_write')?.description ?? ''
|
||||
expect(description).toContain('several at once when work genuinely runs in parallel')
|
||||
|
||||
const owner = agent(ctx)
|
||||
const result = await ctx.tools.execute({
|
||||
signal: new AbortController().signal,
|
||||
callId: CallId('parallel-enabled'),
|
||||
name: 'todo_write',
|
||||
arguments: { todos: PARALLEL_TODOS },
|
||||
agent: owner,
|
||||
})
|
||||
expect(result.isError).toBe(false)
|
||||
expect(owner.session.events.findLast(e => e.type === 'todo/write')?.data.todos).toEqual(PARALLEL_TODOS)
|
||||
}, 30_000)
|
||||
|
||||
it.each([
|
||||
{ label: 'is omitted', configLines: [], failure: '$.allowParallelInProgress missing required value' },
|
||||
{ label: 'is not boolean', configLines: [' allowParallelInProgress: "no"'], failure: '$.allowParallelInProgress expected boolean' },
|
||||
])('fails loading when allowParallelInProgress $label', async ({ configLines, failure }) => {
|
||||
// The policy is self-contained, so misconfiguration fails at load: the
|
||||
// entry's apply rejects and boot never reaches a running tool.
|
||||
await expect(boot(configLines)).rejects.toThrow(failure)
|
||||
}, 30_000)
|
||||
})
|
||||
@@ -42,7 +42,7 @@ async function harness(withTodoTool: boolean): Promise<Bench> {
|
||||
await ctx.plugin(UserInteractionService)
|
||||
await ctx.plugin(AgentRegistry)
|
||||
await ctx.plugin(SessionProjectionRegistry)
|
||||
if (withTodoTool) await ctx.plugin(ToolTodo)
|
||||
if (withTodoTool) await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
const session = ctx.sessions.create()
|
||||
ctx.agents.register({ id: session.id, session, status: 'idle', ctx } as Agent)
|
||||
const api = createApiProxy(ctx, { provider: 'p', model: 'm', cwd: '/tmp', workspaceRoot: '/tmp' })
|
||||
@@ -116,7 +116,7 @@ describe('todos projection provider', () => {
|
||||
it('drops the key when the tool-todo fiber unloads (HMR safety)', async () => {
|
||||
const bench = await harness(false)
|
||||
seedMessage(bench.session)
|
||||
const fiber = await bench.ctx.plugin(ToolTodo)
|
||||
const fiber = await bench.ctx.plugin(ToolTodo, { allowParallelInProgress: true })
|
||||
expect((await bench.tailProjections())?.values).toEqual({ todos: null })
|
||||
await fiber.dispose()
|
||||
expect('todos' in ((await bench.tailProjections())?.values ?? {})).toBe(false)
|
||||
|
||||
@@ -26,11 +26,11 @@ function agentWithSession(id = 'parent-1'): Agent & { session: Session } {
|
||||
return { id: SessionId(id), session } as unknown as Agent & { session: Session }
|
||||
}
|
||||
|
||||
async function setup(): Promise<Context> {
|
||||
async function setup(allowParallelInProgress: boolean): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(tool)
|
||||
await ctx.plugin(tool, { allowParallelInProgress })
|
||||
return ctx
|
||||
}
|
||||
|
||||
@@ -52,7 +52,7 @@ function text(result: { content: { type: string; text?: string }[] }): string {
|
||||
|
||||
describe('dsh-tool-todo', () => {
|
||||
it('registers a `todo_write` tool whose schema is an array of {content,status}', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const schema = ctx.tools.schemas().find(s => s.name === 'todo_write')
|
||||
expect(schema).toBeDefined()
|
||||
const props = (schema!.parameters as { properties?: Record<string, unknown> }).properties ?? {}
|
||||
@@ -65,7 +65,7 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('appends a todo/write event carrying the whole list to the calling session', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('writer')
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'plan', status: 'in_progress' },
|
||||
@@ -85,7 +85,7 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('stores the trimmed content (the dedupe/length key), not the raw input', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('trim')
|
||||
const result = await callTodo(ctx, { todos: [{ content: ' plan the work ', status: 'pending' }] }, { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
@@ -95,7 +95,7 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('replaces the list on a second call (last-write-wins on the log)', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('writer-2')
|
||||
await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent })
|
||||
await callTodo(ctx, { todos: [
|
||||
@@ -111,38 +111,99 @@ describe('dsh-tool-todo', () => {
|
||||
})
|
||||
|
||||
it('rejects a malformed status before execute runs (registry arg-validation)', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: [{ content: 'x', status: 'doing' }] })
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it('rejects a non-array todos argument', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: 'nope' })
|
||||
expect(result.isError).toBe(true)
|
||||
})
|
||||
|
||||
it('accepts several in_progress items at once (parallel work)', async () => {
|
||||
const ctx = await setup(true)
|
||||
const agent = agentWithSession('parallel')
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'in_progress' },
|
||||
{ content: 'merge results', status: 'pending' },
|
||||
]
|
||||
const result = await callTodo(ctx, { todos }, { agent })
|
||||
expect(result.isError).toBe(false)
|
||||
if (result.isError) throw new Error('expected todo_write success')
|
||||
expect(result.value).toEqual({
|
||||
todos,
|
||||
counts: { pending: 1, inProgress: 2, completed: 0 },
|
||||
})
|
||||
expect(agent.session.events.findLast(e => e.type === 'todo/write')!.data.todos).toEqual(todos)
|
||||
})
|
||||
|
||||
describe('allowParallelInProgress', () => {
|
||||
const parallel = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'in_progress' },
|
||||
]
|
||||
|
||||
it('false rejects a call marking several items in_progress', async () => {
|
||||
const ctx = await setup(false)
|
||||
const agent = agentWithSession('single-active')
|
||||
const result = await callTodo(ctx, { todos: parallel }, { agent })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('at most one task may be in_progress')
|
||||
// A rejected call must not reach the durable log.
|
||||
expect(agent.session.events.some(e => e.type === 'todo/write')).toBe(false)
|
||||
})
|
||||
|
||||
it('false still accepts one active item', async () => {
|
||||
const ctx = await setup(false)
|
||||
const todos: TodoItem[] = [
|
||||
{ content: 'run subagent a', status: 'in_progress' },
|
||||
{ content: 'run subagent b', status: 'pending' },
|
||||
]
|
||||
const result = await callTodo(ctx, { todos })
|
||||
expect(result.isError).toBe(false)
|
||||
})
|
||||
|
||||
it('true accepts the very list false rejects', async () => {
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: parallel })
|
||||
expect(result.isError).toBe(false)
|
||||
})
|
||||
|
||||
it('instructs the model to keep at most one active, while true instructs parallel', async () => {
|
||||
const single = await setup(false)
|
||||
const singleDesc = single.tools.schemas().find(s => s.name === 'todo_write')!.description
|
||||
expect(singleDesc).toContain('Keep AT MOST ONE todo `in_progress`')
|
||||
expect(singleDesc).not.toContain('several at once')
|
||||
|
||||
const parallelDesc = (await setup(true)).tools.schemas().find(s => s.name === 'todo_write')!.description
|
||||
expect(parallelDesc).toContain('several at once when work genuinely runs in parallel')
|
||||
expect(parallelDesc).not.toContain('AT MOST ONE')
|
||||
})
|
||||
})
|
||||
|
||||
it.each([
|
||||
{ label: 'empty content', todos: [{ content: ' ', status: 'pending' }], fragment: 'non-empty' },
|
||||
{ label: 'duplicate content', todos: [{ content: 'dup', status: 'pending' }, { content: 'dup', status: 'completed' }], fragment: 'duplicate' },
|
||||
{ label: 'two in_progress', todos: [{ content: 'a', status: 'in_progress' }, { content: 'b', status: 'in_progress' }], fragment: 'in_progress' },
|
||||
{ label: 'unknown item keys', todos: [{ content: 'a', status: 'pending', children: [] }], fragment: 'not a declared property' },
|
||||
])('rejects $label as an isError result', async ({ todos, fragment }) => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain(fragment)
|
||||
})
|
||||
|
||||
it('rejects a non-agent caller (the list has no owning session)', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const result = await callTodo(ctx, { todos: [{ content: 'a', status: 'pending' }] }, { agent: undefined })
|
||||
expect(result.isError).toBe(true)
|
||||
expect(text(result)).toContain('owning agent session')
|
||||
})
|
||||
|
||||
it('presents the call with a stable title and the list as raw input', async () => {
|
||||
const ctx = await setup()
|
||||
const ctx = await setup(true)
|
||||
const def = ctx.tools.get('todo_write')!
|
||||
const todos = [{ content: 'a', status: 'pending' }]
|
||||
expect(def.presentCall?.({ todos })).toEqual({ card: 'generic', title: 'Update todo list', kind: 'other', rawInput: todos })
|
||||
@@ -152,7 +213,7 @@ describe('dsh-tool-todo', () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(tool)
|
||||
const fiber = await ctx.plugin(tool, { allowParallelInProgress: true })
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(true)
|
||||
await fiber.dispose()
|
||||
expect(ctx.tools.schemas().some(s => s.name === 'todo_write')).toBe(false)
|
||||
|
||||
Reference in New Issue
Block a user