test(todo): pin configurable policy boundaries

2026-07-29 20:43:31 +08:00
parent 20a388fc81
commit 70730b8669
8 changed files with 35 additions and 14 deletions
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-29-todo-write-tool.md
-2026-06-29-todo-write-tool.md: f1fd8a6b273e569b752f477352e4877e556fc054
-2026-06-29-todo-write-tool.zh.md: f5cf3d96dd179bfba5dcac58b437bfc54214e1f9
+2026-06-29-todo-write-tool.md: c4cf64b7876bd8b80df80fe6fc27005715f96b5e
+2026-06-29-todo-write-tool.zh.md: 7c1785cdd525397621c8cdee63e1eb4f793a94f2
@@ -34,7 +34,7 @@ Each list belongs to the calling agent session, and non-agent calls are rejected

 ### Validation: the cheap middle

-The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content`: enforce the cheap invariants that make a plan *coherent* (no blank tasks, no dupes), but leave ordering, active-task discipline, and keeping the list current to the model via the tool description. A rejected write returns an `isError` result so the model self-corrects. The original design also capped the list at one `in_progress` task; that cap was removed for parallel work — the [parallel in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md) owns that decision.
+The schema enforces type/required/enum. Beyond that, `execute` rejects empty or duplicate `content` and, when `allowParallelInProgress` is `false`, more than one active task. Ordering and keeping the list current remain model disciplines expressed in the tool description. A rejected write returns an `isError` result so the model self-corrects. The required deployment policy and the durable invariant's independence from it are owned by the [parallel in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md).

 ## Why no cordis-catalog entry / no `@mode`

@@ -34,7 +34,7 @@ claude-code V1 的条目是 `{ content, status, activeForm }`；后来（V2）

 ### 校验：低成本的中间路线

-schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重复的 `content`：强制执行使计划*连贯*的低成本不变式（无空任务、无重复），但将排序、活跃任务纪律和保持列表最新通过工具描述交给模型。被拒绝的写入返回 `isError` 结果，使模型自行修正。原始设计还将列表限制为最多一个 `in_progress` 任务；该上限已为并行工作移除——[并行 in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md) 拥有该决定。
+schema 强制 type/required/enum。在此之上，`execute` 拒绝为空或重复的 `content`，并在 `allowParallelInProgress` 为 `false` 时拒绝超过一个活跃任务。排序和保持列表最新仍通过工具描述交给模型。被拒绝的写入返回 `isError` 结果，使模型自行修正。必填的部署策略及持久日志不变式独立于该策略这一约定，由[并行 in-progress Agent Note](2026-07-26-todo-parallel-in-progress.md) 负责。

 ## 为何没有 cordis-catalog 条目 / 没有 `@mode`

@@ -277,8 +277,8 @@ function buildAlphaLog(): SessionEvent[] {
  }
  // Turn 65: 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: the tool permits several, so both surfaces must render a
-  // parallel plan rather than the first active item alone.
+  // 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' },
@@ -44,6 +44,8 @@
    "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:^",
@@ -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'

@@ -17,14 +19,22 @@ function event(todos: unknown): SessionEvent {
 }

 describe('todo snapshot invariants', () => {
-  it('accepts a unique whole-list snapshot, including several active items', 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([
@@ -124,20 +124,23 @@ describe('tool-todo real Loader composition through cordis.yml', () => {
    expect(owner.session.events.findLast(e => e.type === 'todo/write')?.data.todos).toEqual(PARALLEL_TODOS)
  }, 30_000)

-  it('fails loading when allowParallelInProgress is omitted', async () => {
+  it.each([
+    { label: 'is omitted', configLines: [], failure: '$.allowParallelInProgress missing required value' },
+    { label: 'is not boolean', configLines: ['    allowParallelInProgress: "no"'], failure: '$.allowParallelInProgress' },
+  ])('fails loading when allowParallelInProgress $label', async ({ configLines, failure }) => {
    // loader.await() is all-settled; configuration failure leaves a FAILED
    // entry and escapes as a late rejection for the host boot to report.
    const rejections: unknown[] = []
    const onUnhandled = (err: unknown): void => { rejections.push(err) }
    process.on('unhandledRejection', onUnhandled)
    try {
-      const ctx = await boot([])
+      const ctx = await boot(configLines)
      const entry = [...ctx.loader.entries()].find(e => e.options.name === '@deepseek-ai/dsh-tool-todo')
      expect(entry?.fiber?.state).toBe(FiberState.FAILED)
      for (let i = 0; i < 100 && rejections.length === 0; i++) {
        await new Promise(resolve => setTimeout(resolve, 10))
      }
-      expect(rejections.map(String).join('\n')).toContain('$.allowParallelInProgress missing required value')
+      expect(rejections.map(String).join('\n')).toContain(failure)
    } finally {
      process.off('unhandledRejection', onUnhandled)
    }
@@ -4779,6 +4779,12 @@ importers:
        specifier: ^4.4.3
        version: 4.4.3
    devDependencies:
+      '@cordisjs/plugin-include':
+        specifier: workspace:^
+        version: link:../../../vendor/include
+      '@cordisjs/plugin-loader':
+        specifier: workspace:^
+        version: link:../../../vendor/loader
      '@deepseek-ai/dsh-agent':
        specifier: workspace:^
        version: link:../../core/agent
@@ -4814,7 +4820,7 @@ importers:
        version: link:../../ui/user-interaction
      cordis:
        specifier: ^4.0.0-rc.7
-        version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5)
+        version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader)

  packages/ui/app-boot:
    dependencies: