Merge remote-tracking branch 'origin/master' into codex/session-title

# Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/bash-spill/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cancel/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/error-finish/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-edit/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-read/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/fs-write/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/model-switching/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/multi-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/skill-load/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/text-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/todo-plan/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workflow-run/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workspace-context/stdout.expected.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/stdout.expected.jsonl # examples/headless-agent/tests/headless.snapshot.ts # packages/examples/README.md # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/package.json # packages/ui/README.md # packages/ui/acp/README.md
2026-07-21 02:13:10 +08:00
parent 77df80359a 9a5c81f9e5
commit bb7db52941
273 changed files with 13033 additions and 314 deletions
--- a/examples/headless-agent/tests/headless.snapshot.ts
+++ b/examples/headless-agent/tests/headless.snapshot.ts
@@ -14,10 +14,14 @@ import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-l
 import { describe, expect, it } from 'vitest'

 const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots')
-const scenarioDir = join(snapshotsDir, 'advanced-toolchain')
-const sessionFixture = join(scenarioDir, 'session.jsonl')
-const streamExpected = join(scenarioDir, 'stream-json.expected.jsonl')
-const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
+const advancedScenarioDir = join(snapshotsDir, 'advanced-toolchain')
+const advancedSessionFixture = join(advancedScenarioDir, 'session.jsonl')
+const advancedStreamExpected = join(advancedScenarioDir, 'stream-json.expected.jsonl')
+const advancedConfigPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url))
+const goalScenarioDir = join(snapshotsDir, 'goal-tools')
+const goalConfigPath = fileURLToPath(new URL('../goal.cordis.snapshot.yml', import.meta.url))
+const ralphScenarioDir = join(snapshotsDir, 'ralph-loop')
+const ralphConfigPath = fileURLToPath(new URL('../ralph.cordis.snapshot.yml', import.meta.url))
 const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url))
 const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url))
 const refreshing = process.env.DSH_SNAPSHOT === 'refresh'
@@ -73,12 +77,36 @@ function normalizeHeadlessStream(rawStdout: string, cwd: string): string {
  return normalizeStdout(`${normalizedRecords.map(record => JSON.stringify(record)).join('\n')}\n`, context)
 }

-async function advancedPrompt(): Promise<string> {
-  const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as {
+/** Zero durable goal timestamps inside both metadata records and rendered XML JSON. */
+function normalizeGoalTimestamps(value: unknown): unknown {
+  if (typeof value === 'string') {
+    return value.replace(/("(?:createdAt|updatedAt|clearedAt)":)\d+/g, '$10')
+  }
+  if (Array.isArray(value)) return value.map(normalizeGoalTimestamps)
+  if (value !== null && typeof value === 'object') {
+    return Object.fromEntries(Object.entries(value).map(([key, item]) => [
+      key,
+      ['createdAt', 'updatedAt', 'clearedAt'].includes(key) && typeof item === 'number'
+        ? 0
+        : normalizeGoalTimestamps(item),
+    ]))
+  }
+  return value
+}
+
+/** Normalize the stream's durable goal timestamps after the shared scrubbers. */
+function normalizeGoalStream(rawStdout: string, cwd: string): string {
+  return parseJsonl(normalizeHeadlessStream(rawStdout, cwd))
+    .map(record => JSON.stringify(normalizeGoalTimestamps(record)))
+    .join('\n') + '\n'
+}
+
+async function scenarioPrompt(dir: string, label: string): Promise<string> {
+  const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as {
    steps?: { op?: unknown; text?: unknown }[]
  }
  const prompt = input.steps?.find(step => step.op === 'prompt')?.text
-  if (typeof prompt !== 'string') throw new Error('advanced-toolchain input has no prompt step')
+  if (typeof prompt !== 'string') throw new Error(`${label} input has no prompt step`)
  return prompt
 }

@@ -93,11 +121,11 @@ async function persistedLogs(cwd: string): Promise<PersistedLog[]> {

 describe('headless stream-json snapshots', () => {
  it('replays the advanced toolchain through the one-shot app', async () => {
-    const prompt = await advancedPrompt()
+    const prompt = await scenarioPrompt(advancedScenarioDir, 'advanced-toolchain')
    const fixtureFiles = [
-      sessionFixture,
-      join(scenarioDir, 'session.1.jsonl'),
-      join(scenarioDir, 'session.2.jsonl'),
+      advancedSessionFixture,
+      join(advancedScenarioDir, 'session.1.jsonl'),
+      join(advancedScenarioDir, 'session.2.jsonl'),
    ]
    let expectedSessions = await Promise.all(fixtureFiles.map(file => readFile(file, 'utf8')))
    let runCwd = ''
@@ -105,13 +133,16 @@ describe('headless stream-json snapshots', () => {
      label: 'advanced headless stream-json snapshot',
      tempDirPrefix: 'headless-snapshot-advanced-',
      binScript,
-      configPath,
-      binArgs: ['--config', configPath, '--output-format', 'stream-json', prompt],
+      configPath: advancedConfigPath,
+      binArgs: ['--config', advancedConfigPath, '--output-format', 'stream-json', prompt],
      tsconfigPath,
      env: {
        DSH_SNAPSHOT: 'replay',
-        DSH_SNAPSHOT_FILE: sessionFixture,
-        DSH_SNAPSHOT_CHILD_FILES: [join(scenarioDir, 'session.1.jsonl'), join(scenarioDir, 'session.2.jsonl')].join(delimiter),
+        DSH_SNAPSHOT_FILE: advancedSessionFixture,
+        DSH_SNAPSHOT_CHILD_FILES: [
+          join(advancedScenarioDir, 'session.1.jsonl'),
+          join(advancedScenarioDir, 'session.2.jsonl'),
+        ].join(delimiter),
        NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
      },
      prepare: (cwd) => { runCwd = cwd },
@@ -157,6 +188,131 @@ describe('headless stream-json snapshots', () => {
      },
    })

+    expect(result.stderr).toBe('')
+    const normalized = normalizeHeadlessStream(result.stdout, runCwd)
+    if (refreshing) await writeFile(advancedStreamExpected, normalized)
+    expect(normalized).toBe(await readFile(advancedStreamExpected, 'utf8'))
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
+  it('replays persisted goal tools through the one-shot app', async () => {
+    const prompt = await scenarioPrompt(goalScenarioDir, 'goal-tools')
+    const streamExpected = join(goalScenarioDir, 'stream-json.expected.jsonl')
+    let runCwd = ''
+    const result = await runLoaderSmoke({
+      label: 'goal tools headless stream-json snapshot',
+      tempDirPrefix: 'headless-snapshot-goal-tools-',
+      binScript,
+      configPath: goalConfigPath,
+      binArgs: ['--config', goalConfigPath, '--output-format', 'stream-json', prompt],
+      tsconfigPath,
+      env: {
+        DSH_SNAPSHOT: 'replay',
+        DSH_SNAPSHOT_FILE: join(goalScenarioDir, 'session.jsonl'),
+        DSH_SNAPSHOT_OVERRIDE: join(goalScenarioDir, 'replay.override.json'),
+        NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
+      },
+      prepare: (cwd) => { runCwd = cwd },
+      inspect: async (cwd) => {
+        const logs = await persistedLogs(cwd)
+        expect(logs).toHaveLength(1)
+        const records = parseJsonl(logs[0]?.content ?? '')
+        const calls = records.filter(record => record.type === 'tool/call')
+          .map(record => (record.data as JsonObject | undefined)?.name)
+        expect(calls).toEqual(['create_goal', 'get_goal'])
+        const goalChanges = records.filter((record) => {
+          if (record.type !== 'context/message') return false
+          const data = record.data as JsonObject | undefined
+          const meta = data?.meta as JsonObject | undefined
+          return meta?.kind === 'goal/change'
+        })
+        expect(goalChanges).toHaveLength(1)
+        const data = goalChanges[0]?.data as JsonObject | undefined
+        const meta = data?.meta as JsonObject | undefined
+        const goal = meta?.goal as JsonObject | undefined
+        expect(meta?.operation).toBe('create')
+        expect(goal).toMatchObject({
+          objective: 'Finish the headless goal-tool snapshot proof',
+          phase: 'active',
+          maxGoalRounds: 7,
+        })
+      },
+    })
+
+    expect(result.stderr).toBe('')
+    const normalized = normalizeGoalStream(result.stdout, runCwd)
+    if (refreshing) await writeFile(streamExpected, normalized)
+    expect(normalized).toBe(await readFile(streamExpected, 'utf8'))
+  }, LOADER_SMOKE_TEST_TIMEOUT_MS)
+
+  it('replays two fresh Ralph rounds through the one-shot app', async () => {
+    const prompt = await scenarioPrompt(ralphScenarioDir, 'ralph-loop')
+    const streamExpected = join(ralphScenarioDir, 'stream-json.expected.jsonl')
+    let runCwd = ''
+    const result = await runLoaderSmoke({
+      label: 'Ralph loop headless stream-json snapshot',
+      tempDirPrefix: 'headless-snapshot-ralph-loop-',
+      binScript,
+      configPath: ralphConfigPath,
+      binArgs: ['--config', ralphConfigPath, '--output-format', 'stream-json', prompt],
+      tsconfigPath,
+      env: {
+        DSH_SNAPSHOT: 'replay',
+        DSH_SNAPSHOT_FILE: join(ralphScenarioDir, 'session.jsonl'),
+        DSH_SNAPSHOT_OVERRIDE: join(ralphScenarioDir, 'replay.override.json'),
+        DSH_SNAPSHOT_CHILD_FILES: [
+          join(ralphScenarioDir, 'session.1.jsonl'),
+          join(ralphScenarioDir, 'session.2.jsonl'),
+        ].join(delimiter),
+        NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '),
+      },
+      prepare: (cwd) => { runCwd = cwd },
+      inspect: async (cwd) => {
+        const logs = await persistedLogs(cwd)
+        expect(logs).toHaveLength(3)
+        const parent = logs.find(log => typeof log.header.parentSession !== 'string')
+        if (parent === undefined) throw new Error('Ralph snapshot did not persist its parent session')
+        const parentId = parent.header.id
+        expect(typeof parentId).toBe('string')
+        const children = logs.filter(log => typeof log.header.parentSession === 'string')
+          .sort((left, right) => Number(left.header.createdAt) - Number(right.header.createdAt))
+        expect(children).toHaveLength(2)
+        expect(children.map(child => child.header.parentSession)).toEqual([parentId, parentId])
+        expect(children.map(child => child.header.cwd)).toEqual([parent.header.cwd, parent.header.cwd])
+        expect(parent.header.delegationDepth).toBe(0)
+        expect(children.map(child => child.header.delegationDepth)).toEqual([1, 1])
+        expect(children.map(child => child.header.seedLength)).toEqual([undefined, undefined])
+        expect(new Set(children.map(child => child.header.id)).size).toBe(2)
+
+        const parentRecords = parseJsonl(parent.content)
+        const parentCalls = parentRecords.filter(record => record.type === 'tool/call')
+        expect(parentCalls.map(record => (record.data as JsonObject | undefined)?.name)).toEqual(['ralph'])
+        const parentResult = parentRecords.find(record => record.type === 'tool/result')
+        const parentResultData = parentResult?.data as JsonObject | undefined
+        expect(parentResultData?.isError).toBe(false)
+        expect(JSON.stringify(parentResultData?.content)).toContain('reported completion after 2 rounds')
+
+        const childRecords = children.map(child => parseJsonl(child.content))
+        const childPrompts = childRecords.map((records) => {
+          const message = records.find(record => record.type === 'user/message')
+          return JSON.stringify((message?.data as JsonObject | undefined)?.content)
+        })
+        expect(childPrompts[0]).toContain('Ralph round: 1 of 2.')
+        expect(childPrompts[0]).toContain('(none — this is the first round)')
+        expect(childPrompts[0]).not.toContain('ROUND_ONE_HANDOFF')
+        expect(childPrompts[1]).toContain('Ralph round: 2 of 2.')
+        expect(childPrompts[1]).toContain('ROUND_ONE_HANDOFF')
+        for (const childPrompt of childPrompts) {
+          expect(childPrompt).toContain('Prove two fresh Ralph rounds through the shipped headless app.')
+          expect(childPrompt).not.toContain('Run a two-round fresh-agent Ralph loop')
+        }
+        for (const records of childRecords) {
+          const calls = records.filter(record => record.type === 'tool/call')
+          expect(calls.map(record => (record.data as JsonObject | undefined)?.name))
+            .toEqual(['structured_output'])
+        }
+      },
+    })
+
    expect(result.stderr).toBe('')
    const normalized = normalizeHeadlessStream(result.stdout, runCwd)
    if (refreshing) await writeFile(streamExpected, normalized)