Merge remote-tracking branch 'origin/master' into feat/sandbox-support

# Conflicts:
#	packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts

packages/support/acp-snapshot/tests/suite.spec.ts

@@ -1,11 +1,18 @@
-import { cpSync, mkdtempSync } from 'node:fs'
+import { cpSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs'
 import { rm } from 'node:fs/promises'
 import { tmpdir } from 'node:os'
 import { join } from 'node:path'
 import { fileURLToPath } from 'node:url'
 import { afterAll, describe, expect, it } from 'vitest'
-import { defineAcpSnapshotSuite, type Scenario } from '../src/index.ts'
-import { childFixturePaths, fixtureContext, headerDeltaCount, normalizedHeaders } from '../src/suite.ts'
+import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts'
+import {
+  childFixturePaths,
+  fixtureContext,
+  headerDeltaCount,
+  normalizedHeaders,
+  refreshFixtureReplacements,
+  stabilizeRefreshLog,
+} from '../src/suite.ts'
 
 /**
  * Unit tests for the suite factory, by running it: two synthetic suites over
@@ -55,16 +62,40 @@ const RECORD_SCENARIOS: Scenario[] = [
   { name: 'rec-skip', hasModelTurn: true, recorded: false, overridden: true },
 ]
 
-// Record mode mutates its snapshots dir, so run it on a throwaway copy —
-// except under the documented bootstrap knob, which regenerates the committed
-// fixtures/goldens in place.
+// Record/refresh modes mutate their snapshots dir, so run them on throwaway
+// copies — except record's documented bootstrap knob, which regenerates the
+// committed record fixtures/goldens in place.
 const BOOTSTRAP = process.env.ACP_SNAPSHOT_SPEC_BOOTSTRAP === '1'
 const recordDir = BOOTSTRAP ? RECORD_SRC : mkdtempSync(join(tmpdir(), 'acp-snap-record-suite-'))
 if (!BOOTSTRAP) cpSync(RECORD_SRC, recordDir, { recursive: true })
+const refreshDir = mkdtempSync(join(tmpdir(), 'acp-snap-refresh-suite-'))
+cpSync(REPLAY_DIR, refreshDir, { recursive: true })
+staleRefreshFixtures(refreshDir)
 afterAll(async () => {
   if (!BOOTSTRAP) await rm(recordDir, { recursive: true, force: true })
+  await rm(refreshDir, { recursive: true, force: true })
 })
 
+function staleRefreshFixtures(dir: string): void {
+  writeFileSync(join(dir, 'plain-turn', 'stdout.golden.jsonl'), 'stale stdout\n')
+
+  const plainBehaviorFile = join(dir, 'plain-turn', 'behavior.json')
+  const plainBehavior = JSON.parse(readFileSync(plainBehaviorFile, 'utf8')) as Record<string, unknown>
+  plainBehavior.echoEnv = true
+  writeFileSync(plainBehaviorFile, `${JSON.stringify(plainBehavior, null, 2)}\n`)
+
+  writeFileSync(join(dir, 'blocked-log', 'session.jsonl'), [
+    '{"type":"session","id":"99999999-8888-4777-8666-555555555555","createdAt":13,"cwd":"/rec/blocked-cwd"}',
+    '{"type":"hook/result","seq":1,"time":13,"data":{"decision":"stale","durationMs":99}}',
+    '',
+  ].join('\n'))
+  writeFileSync(join(dir, 'authored-error', 'session.jsonl'), [
+    '{"type":"session","id":"77777777-8888-4777-8666-555555555555","createdAt":13,"cwd":"/rec/error-cwd"}',
+    '{"type":"turn/end","seq":1,"time":9,"data":{"error":"stale"}}',
+    '',
+  ].join('\n'))
+}
+
 describe('defineAcpSnapshotSuite: replay mode', () => {
   defineAcpSnapshotSuite({ agent: AGENT, snapshotsDir: REPLAY_DIR, scenarios: REPLAY_SCENARIOS, mode: 'replay' })
 })
@@ -75,6 +106,27 @@ describe('defineAcpSnapshotSuite: record mode', () => {
   defineAcpSnapshotSuite({ agent: AGENT, snapshotsDir: recordDir, scenarios: RECORD_SCENARIOS, mode: 'record' })
 })
 
+describe('defineAcpSnapshotSuite: refresh mode', () => {
+  defineAcpSnapshotSuite({ agent: AGENT, snapshotsDir: refreshDir, scenarios: REPLAY_SCENARIOS, mode: 'refresh' })
+})
+
+describe('defineAcpSnapshotSuite: refresh write-back', () => {
+  it('rewrites stdout and comparable logs from a replay-mode child run', () => {
+    const stdout = readFileSync(join(refreshDir, 'plain-turn', 'stdout.golden.jsonl'), 'utf8')
+    expect(stdout).not.toContain('stale stdout')
+    expect(stdout).toContain('env:{\\"mode\\":\\"replay\\"')
+    expect(stdout).not.toContain('\\"mode\\":\\"refresh\\"')
+
+    const blocked = readFileSync(join(refreshDir, 'blocked-log', 'session.jsonl'), 'utf8')
+    expect(blocked).toContain('"decision":"block"')
+    expect(blocked).not.toContain('"decision":"stale"')
+
+    const authored = readFileSync(join(refreshDir, 'authored-error', 'session.jsonl'), 'utf8')
+    expect(authored).toContain('"error":"model exploded"')
+    expect(authored).not.toContain('"error":"stale"')
+  })
+})
+
 describe('defineAcpSnapshotSuite: registration contract', () => {
   it("throws when a scenario's header class has no pinning scenario", () => {
     expect(() => {
@@ -175,3 +227,56 @@ describe('headerDeltaCount', () => {
     expect(headerDeltaCount(`${other}\n`)).toBe(0)
   })
 })
+
+describe('refreshFixtureReplacements', () => {
+  it('maps fresh ids and cwd values to the existing fixture values, skipping non-replacements', () => {
+    const log = (content: string): HarvestedLog => ({ id: 'diagnostic', createdAt: 1, content })
+    const logs = [
+      log('{"type":"session","id":"","cwd":"/same"}\n'),
+      log('{"type":"session","id":"new-parent","cwd":"/new"}\n'),
+      log('{"type":"session","id":"new-child","cwd":"/new"}\n'),
+    ]
+    const fixtures = [
+      '{"type":"session","id":"","cwd":"/same"}\n',
+      '{"type":"session","id":"old-parent","cwd":"/old"}\n',
+    ]
+    expect(refreshFixtureReplacements(logs, fixtures)).toEqual([
+      { from: 'new-parent', to: 'old-parent' },
+      { from: '/new', to: '/old' },
+    ])
+  })
+})
+
+describe('stabilizeRefreshLog', () => {
+  it('keeps volatile fixture fields while preserving fresh meaningful payloads', () => {
+    const fresh = [
+      '{"type":"session","id":"new-child","createdAt":200,"cwd":"/new","parentSession":"new-parent","seedLength":1}',
+      '{"type":"hook/result","seq":1,"time":22,"data":{"decision":"block","durationMs":37}}',
+      '{"type":"turn/end","seq":2,"time":33,"data":{"error":"fresh error"}}',
+      '{"type":"tool/result","seq":3,"time":44,"data":{"text":"new-parent in /new"}}',
+      '{"type":"hook/result","seq":4,"time":55,"data":{"decision":"allow","durationMs":5}}',
+      '',
+    ].join('\n')
+    const existing = [
+      '{"type":"session","id":"old-child","createdAt":100,"cwd":"/old","parentSession":"old-parent","seedLength":5}',
+      '{"type":"hook/result","seq":1,"time":11,"data":{"decision":"stale","durationMs":99}}',
+      '{"type":"turn/end","seq":2,"data":{"error":"stale"}}',
+      '{"type":"assistant/message","seq":3,"time":12,"data":{"text":"different type"}}',
+      '{"type":"hook/result","seq":4,"time":13,"data":{"decision":"stale"}}',
+      '',
+    ].join('\n')
+
+    expect(stabilizeRefreshLog(fresh, existing, [
+      { from: 'new-parent', to: 'old-parent' },
+      { from: 'new-child', to: 'old-child' },
+      { from: '/new', to: '/old' },
+    ])).toBe([
+      '{"type":"session","id":"old-child","createdAt":100,"cwd":"/old","parentSession":"old-parent","seedLength":1}',
+      '{"type":"hook/result","seq":1,"time":11,"data":{"decision":"block","durationMs":99}}',
+      '{"type":"turn/end","seq":2,"time":33,"data":{"error":"fresh error"}}',
+      '{"type":"tool/result","seq":3,"time":44,"data":{"text":"old-parent in /old"}}',
+      '{"type":"hook/result","seq":4,"time":13,"data":{"decision":"allow","durationMs":5}}',
+      '',
+    ].join('\n'))
+  })
+})