fix(snapshot): stabilize all recorder message ids

2026-07-30 17:51:07 +08:00
parent eb51d4c669
commit 466a2f12c3
12 changed files with 110 additions and 50 deletions
--- a/packages/support/acp-snapshot/README.i18n.yaml
+++ b/packages/support/acp-snapshot/README.i18n.yaml
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/support/acp-snapshot/README.md
-README.md: e3752dfb522cd55776f3ef796acdc15037e5a761
-README.zh.md: 6ce531640b5311662e4b958177e4417c8878617f
+README.md: c5a1a07b9f85e1a91c52fe102be17e4172be112d
+README.zh.md: 2454df9b3d8e67b4728d6582279ba21798d2ba9e
--- a/packages/support/acp-snapshot/README.md
+++ b/packages/support/acp-snapshot/README.md
@@ -8,7 +8,7 @@ Four layers, importable separately:

 - **`launchAcpTestAgent` (launcher)** — boots a source agent under tsx or a built `lib` agent under plain Node from a supplied cwd, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through startup, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. When Windows accepts forced termination but publishes its exit marker asynchronously, shutdown gives that marker a bounded grace before treating fallback refusal as a second failure. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy.
 - **`runScenario` (harness)** — drives ACP JSON-RPC stdio from a deterministic `input.json` script through the launcher, tees raw stdout for the expected-output and purity checks, and harvests every persisted raw JSONL session log (parent and subagent children, primary-first) after graceful stdin EOF. `AgentUnderTest` supplies absolute `binScript`, optional `libBinScript`, `configPath`, and `tsconfigPath` paths because the subprocess cwd is outside the repo; `workspaceParent` may move the generated child cwd from the platform temp directory when that grant is itself under test. Startup failures preserve captured agent stderr in the rejected diagnostic.
- **Normalizers** — pure functions turning captured surfaces into stable text or portable fixtures: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs and every native/JavaScript filesystem spelling of the generated cwd → tokens, longest-first; cwd-rooted separators selected as canonical `/` or host-native; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept, the same cwd-path policy), `tokenizeSessionFixtureCwd` (the generated workspace and its filesystem aliases → `{{cwd}}`, authored temp paths unchanged), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header Agent Note](../../../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)).
+- **Normalizers** — pure functions turning captured surfaces into stable text or portable fixtures: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs and every native/JavaScript filesystem spelling of the generated cwd → tokens, longest-first; cwd-rooted separators selected as canonical `/` or host-native; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept, the same cwd-path policy), `tokenizeSessionFixtureCwd` (the generated workspace and its filesystem aliases → `{{cwd}}`, authored temp paths unchanged), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header Agent Note](../../../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)), and `stabilizeFixtureMessageIds` (committed UUIDs carried into unchanged, unambiguous messages across any recorder's fixture-ready parent/child logs).
 - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, a tokenized pin per header class composed with independently shared `system-prompt.expected.md` and `tool-schemas.expected.json` sidecars, and a live uniformity guard. Its fixture guards reject orphan scenario dirs, missing files, multiple pins for one class, duplicate sidecar content, unscrubbed JSONL headers, and malformed pinning headers. Before record or refresh writes fixtures, an unchanged complete message retains its committed UUID when its identity-free value resolves to exactly one fresh ID and one existing ID across the scenario's parent/child logs; new, changed, and ambiguous messages keep fresh UUIDs. Refresh evaluates fresh leaves with the harvested run's ids, cwd, and every cwd alias, then reuses normalized-equivalent leaves only when the complete logical-record layout aligns and volatile string replacements form a bijection; ambiguous logs keep fresh strings, and fresh semantic values remain authoritative. It also expands packed timing envelopes before aligning event times, so switching between packed and unpacked layouts cannot shift later records. A newly inserted `session/title` receives its preceding event's time so feature-driven insertions do not churn the remainder of a fixture. Each scenario directory's `session.jsonl` plus contiguous `session.<n>.jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time.

 Committed session fixtures use canonical packed rows. An in-flight branch that merges this contract runs the [temporary repository migrator](../../../scripts/migrate-packed-session-fixtures.ts) with `pnpm run migrate:packed-session-fixtures`; its [removal proposal](../../../.agents/notes/proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md) owns deletion after affected branches converge.
@@ -59,7 +59,7 @@ Every scenario compares `stdout.expected.jsonl` with cwd-rooted separators canon

 The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log expected outputs, and owned prompt and tool-schema sidecars from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md).

-Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the TUI snapshot suite and the web browser e2e lane. Input scripts cover initialization, fresh-session creation, text prompting, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run.
+Constraints: `suite.ts` and `harness.ts` import vitest (the harness polls its durable-boundary waits through `vi.waitFor`), so the package entry is importable only inside a vitest run (the launcher and normalizers have no such dependency but ship from the same entry). The launcher and suite factory are ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection` — while the normalizers are transport-neutral session-log/text helpers also consumed by the JSON-RPC, TUI, and web snapshot recorders. Input scripts cover initialization, fresh-session creation, text prompting, cancellation, expected RPC failures, and durable turn-boundary waits. Permission round-trips are a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) mapped to the agent-issued `optionId`; an absent or exhausted queue answers `cancelled`, and an unoffered kind rejects the run.

 ## Model Experience

--- a/packages/support/acp-snapshot/README.zh.md
+++ b/packages/support/acp-snapshot/README.zh.md
@@ -8,7 +8,7 @@ ACP 快照套件工具包：无密钥快照层（`pnpm run test:snapshot`，见[

 - **`launchAcpTestAgent`（启动器）**：从指定 cwd 在 tsx 下启动源 agent，或在普通 Node 下启动已构建 `lib` agent；通过原始字节 stdout tee 连接 SDK 客户端，收集会话更新和 stderr，在启动过程中公开异步 spawn 失败，对未处理权限请求快速失败，并负责优雅或带信号关闭。关闭会等待进程退出、继承 stdio 关闭和 ACP parser 耗尽，然后才解析或传播子级错误，使捕获内容完整，且调用方可在任一结果后移除自有路径。当 Windows 接受强制终止但异步发布退出标记时，关闭会给该标记有界宽限，然后才将回退拒绝视为第二次失败。快照和普通 e2e 套件共享该进程边界；测试只需提供 agent 路径、cwd、环境覆盖和任何权限策略。
 - **`runScenario`（harness）**：通过启动器从确定性 `input.json` 脚本驱动 ACP JSON-RPC stdio，将原始 stdout tee 给预期输出和纯度检查，并在优雅 stdin EOF 后收集每个持久化原始 JSONL 会话日志（父级和 subagent 子级，主级优先）。`AgentUnderTest` 提供绝对 `binScript`、可选 `libBinScript`、`configPath` 和 `tsconfigPath` 路径，因为子进程 cwd 位于仓库外。当生成子级 cwd 自身位于待测授权中时，`workspaceParent` 可以将它从平台临时目录移出。启动失败会在拒绝诊断中保留已捕获 agent stderr。
- **规范化器**：将已捕获接口转换为稳定文本或可移植 fixture 的纯函数：`normalizeStdout`（JSON-RPC id → 首次出现序列；UUID 以及生成 cwd 的每个原生/JavaScript 文件系统写法 → token，按最长优先；根据 cwd 的分隔符选择规范 `/` 或宿主原生形式；同时作为 stdout 纯度检查）、`normalizeSessionLog`（时间归零、保留 `seq`、使用同一 cwd 路径策略）、`tokenizeSessionFixtureCwd`（生成的 workspace 及其文件系统别名 → `{{cwd}}`，手工编写的临时路径保持不变）、`scrubSystemPrompts`（提示词文本 → `{{system}}`）、`scrubToolSchemas`（schema bulk → `{{tools}}`）和 `scrubRequestHeaders`（每个 pin 之外的所有 header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}`，保留结构；见[header 固定 Agent Note](../../../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)）。
+- **规范化器**：将已捕获接口转换为稳定文本或可移植 fixture 的纯函数：`normalizeStdout`（JSON-RPC id → 首次出现序列；UUID 以及生成 cwd 的每个原生/JavaScript 文件系统写法 → token，按最长优先；根据 cwd 的分隔符选择规范 `/` 或宿主原生形式；同时作为 stdout 纯度检查）、`normalizeSessionLog`（时间归零、保留 `seq`、使用同一 cwd 路径策略）、`tokenizeSessionFixtureCwd`（生成的 workspace 及其文件系统别名 → `{{cwd}}`，手工编写的临时路径保持不变）、`scrubSystemPrompts`（提示词文本 → `{{system}}`）、`scrubToolSchemas`（schema bulk → `{{tools}}`）、`scrubRequestHeaders`（每个 pin 之外的所有 header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}`，保留结构；见[header 固定 Agent Note](../../../.agents/notes/archived/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)）和 `stabilizeFixtureMessageIds`（针对任意录制器已准备写入 fixture 的父级/子级日志，将已提交 UUID 带入未变化且无歧义的消息）。
 - **`defineAcpSnapshotSuite`（工厂）**：为场景表注册完整 describe/it 树：每场景预期输出与重新持久化日志比较、录制/刷新 fixture 回写、拒绝结构化 `UNKNOWN_TOOL` 结果、每个 header 类别一个 token 化 pin（由可独立共享的 `system-prompt.expected.md` 和 `tool-schemas.expected.json` sidecar 组合而成），以及实时一致性保护。其 fixture 保护会拒绝遗留场景目录、缺失文件、一个类别包含多个 pin、重复的 sidecar 内容、未擦除的 JSONL header，以及格式错误的 pin header。在录制或刷新写入 fixture 前，如果一条未变化的完整消息去除身份后的值在场景的父级/子级日志中恰好对应一个本次生成的 ID 和一个现有 ID，它就会保留已提交的 UUID；新增、发生变化和有歧义的消息则保留本次生成的 UUID。刷新会使用收集所得本次运行的 id、cwd 及全部 cwd 别名评估本次生成的叶值；只有完整逻辑记录布局对齐且易变字符串替换形成双射时，才会复用规范化后等价的叶值；有歧义的日志保留本次生成的字符串，而本次生成的语义值仍为权威数据。它还会在对齐事件时间前展开打包时序 envelope，因此切换打包/非打包布局无法移动后续记录。新插入的 `session/title` 使用前一个事件的时间，因此功能驱动的插入不会扰动 fixture 余下部分。每个场景目录的 `session.jsonl` 和连续 `session.<n>.jsonl` 同级文件是有序主级/子级清单；场景表不重复其数量。必须在 vitest 收集时调用。

 签入仓库的会话 fixture 使用规范打包行。合并此契约的在途分支通过 `pnpm run migrate:packed-session-fixtures` 运行[临时仓库迁移器](../../../scripts/migrate-packed-session-fixtures.ts)；待受影响分支收敛后，由其[移除提案](../../../.agents/notes/proposed/process/2026-07-26-remove-packed-session-fixture-migrator.md)负责删除该迁移器。
@@ -59,7 +59,7 @@ defineAcpSnapshotSuite({

 示例还发布 `cordis.snapshot.yml` 回放 overlay，位于 `cordis.yml` 旁边（bin 在 `DSH_SNAPSHOT=replay` 下交换它们，见[单源回放配置 Agent Note](../../../.agents/notes/archived/testing/2026-07-04-single-source-acp-replay-config.md)）；回放 fixture 由 [`dsh-llm-replay`](../llm-replay/README.md) 提供，该包通过对子级设置的 `DSH_SNAPSHOT_*` env var 指向它。`pnpm run test:snapshot:record` 调用实时 LLM，并重写已记录场景的模型 fixture；`pnpm run test:snapshot:refresh` 保持无密钥，运行回放 overlay，并从已提交模型脚本重写 stdout、可比较会话日志预期输出，以及各 pin 自有的提示词与工具 schema sidecar。Fixture 角色、录制/回放/刷新语义和场景表字段记录在 `Scenario` 以及[快照 Agent Note](../../../.agents/notes/implemented/testing/2026-06-19-acp-snapshot-tests.md) 中。

-约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 TUI 快照套件和 web 浏览器 e2e lane 消费。输入脚本覆盖初始化、新建会话、文本提示、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once`等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。
+约束：`suite.ts` 与 `harness.ts` 导入 vitest（harness 通过 `vi.waitFor` 轮询其持久边界等待），因此包入口只能在 vitest 运行中导入（启动器和规范化器没有此依赖，但从同一入口发布）。启动器和套件工厂按设计专用于 ACP，启动器使用 SDK 的 `ClientSideConnection`；规范化器是与传输无关的会话日志/文本辅助工具，还由 JSON-RPC、TUI 和 web 快照录制器消费。输入脚本覆盖初始化、新建会话、文本提示、取消、预期 RPC 失败和持久轮次边界等待。权限往返是选项类别选择（`allow_once`、`reject_once`等）的 FIFO 队列，映射到 agent 发出的 `optionId`；缺少或耗尽的队列回答 `cancelled`，未提供类别会拒绝运行。

 ## 模型体验

--- a/packages/support/acp-snapshot/src/index.ts
+++ b/packages/support/acp-snapshot/src/index.ts
@@ -46,6 +46,7 @@ export {
 export {
  defineAcpSnapshotSuite,
  refreshFixtureReplacements,
+  stabilizeFixtureMessageIds,
  stabilizeRefreshLog,
  type Scenario,
  type SnapshotSuiteOptions,
--- a/packages/support/acp-snapshot/src/suite.ts
+++ b/packages/support/acp-snapshot/src/suite.ts
@@ -554,8 +554,8 @@ function uniqueMessageIds(logs: readonly string[]): Map<string, string | undefin
 * Match unchanged complete messages across a scenario's fresh and existing logs.
 * New, changed, repeated, or otherwise ambiguous messages keep their fresh ids.
 */
-function fixtureMessageIdReplacements(logs: HarvestedLog[], fixtures: string[]): FixtureReplacement[] {
-  const freshIds = uniqueMessageIds(logs.map(log => log.content))
+function fixtureMessageIdReplacements(logs: readonly string[], fixtures: readonly string[]): FixtureReplacement[] {
+  const freshIds = uniqueMessageIds(logs)
  const existingIds = uniqueMessageIds(fixtures)
  const replacements: FixtureReplacement[] = []
  for (const [fingerprint, fresh] of freshIds) {
@@ -573,6 +573,18 @@ function applyFixtureReplacements(content: string, replacements: readonly Fixtur
  return stable
 }

+/**
+ * Carry committed UUIDs into unchanged, unambiguous messages in fresh session fixtures.
+ *
+ * @param logs Fresh fixture-ready session JSONL contents for one scenario.
+ * @param fixtures Existing fixture contents in matching order; missing fixtures may be empty strings.
+ * @returns The fresh contents with only reusable message UUIDs replaced.
+ */
+export function stabilizeFixtureMessageIds(logs: readonly string[], fixtures: readonly string[]): string[] {
+  const replacements = fixtureMessageIdReplacements(logs, fixtures)
+  return logs.map(log => applyFixtureReplacements(log, replacements))
+}
+
 /** One packed row's member times, or `undefined` for an ordinary record. */
 function packedTimes(record: Record<string, unknown>): number[] | undefined {
  if (!PACKED_CHUNK_ROW_TYPES.has(record.type as string)) return undefined
@@ -626,7 +638,7 @@ export function unknownToolCallIds(rawLog: string): string[] {
 * @returns Literal replacements from fresh values to the fixture's existing values.
 */
 export function refreshFixtureReplacements(logs: HarvestedLog[], fixtures: string[]): FixtureReplacement[] {
-  const replacements = fixtureMessageIdReplacements(logs, fixtures)
+  const replacements = fixtureMessageIdReplacements(logs.map(log => log.content), fixtures)
  for (let i = 0; i < logs.length; i++) {
    const fresh = parseJsonlRecords((logs[i] as HarvestedLog).content)[0]
    const existing = parseJsonlRecords(fixtures[i] ?? '')[0]
@@ -1111,23 +1123,22 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void {
            const path = join(dir, file)
            return existsSync(path) ? readFile(path, 'utf8') : ''
          }))
-          const replacements = REFRESHING
+          const refreshReplacements = REFRESHING
            ? refreshFixtureReplacements(result.sessionLogs, existingFixtures)
-            : fixtureMessageIdReplacements(result.sessionLogs, existingFixtures)
-          const primary = (result.sessionLogs[0] as HarvestedLog).content
-          await writeFile(join(dir, outputFixtureFiles[0] as string), scrub(portableFixture(
-            REFRESHING
-              ? stabilizeRefreshLog(primary, existingFixtures[0] as string, replacements, ctx)
-              : applyFixtureReplacements(primary, replacements),
-          )))
-          for (let i = 1; i < result.sessionLogs.length; i++) {
-            const child = (result.sessionLogs[i] as HarvestedLog).content
-            await writeFile(join(dir, outputFixtureFiles[i] as string), scrub(portableFixture(
-              REFRESHING
-                ? stabilizeRefreshLog(child, existingFixtures[i] as string, replacements, ctx)
-                : applyFixtureReplacements(child, replacements),
-            )))
-          }
+            : []
+          const outputFixtures = REFRESHING
+            ? result.sessionLogs.map((log, index) => scrub(portableFixture(stabilizeRefreshLog(
+              log.content,
+              existingFixtures[index] as string,
+              refreshReplacements,
+              ctx,
+            ))))
+            : stabilizeFixtureMessageIds(
+              result.sessionLogs.map(log => scrub(portableFixture(log.content))),
+              existingFixtures,
+            )
+          await Promise.all(outputFixtures.map((fixture, index) =>
+            writeFile(join(dir, outputFixtureFiles[index] as string), fixture)))
          if (RECORDING) {
            const outputNames = new Set(outputFixtureFiles)
            const entries = await readdir(dir, { withFileTypes: true })
--- a/packages/support/acp-snapshot/tests/suite.spec.ts
+++ b/packages/support/acp-snapshot/tests/suite.spec.ts
@@ -4,7 +4,12 @@ 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 HarvestedLog, type Scenario } from '../src/index.ts'
+import {
+  defineAcpSnapshotSuite,
+  stabilizeFixtureMessageIds,
+  type HarvestedLog,
+  type Scenario,
+} from '../src/index.ts'
 import {
  assertUniqueSnapshotContents,
  claimSharedSnapshot,
@@ -635,6 +640,36 @@ describe('unknownToolCallIds', () => {
  })
 })

+describe('stabilizeFixtureMessageIds', () => {
+  it('reuses one committed message UUID across fixture-ready parent and child logs', () => {
+    const freshId = '11111111-1111-4111-8111-111111111111'
+    const existingId = '22222222-2222-4222-8222-222222222222'
+    const log = (session: string, id: string): string => [
+      JSON.stringify({ type: 'session', id: session, cwd: '{{cwd}}' }),
+      JSON.stringify({
+        type: 'user/message',
+        data: { role: 'user', content: [{ type: 'text', text: 'same' }], source: { kind: 'user' }, id },
+      }),
+      '',
+    ].join('\n')
+    const fresh = [log('fresh-parent', freshId), log('fresh-child', freshId)]
+    const existing = [log('old-parent', existingId), log('old-child', existingId)]
+
+    const stable = stabilizeFixtureMessageIds(fresh, existing)
+
+    expect(stable).toHaveLength(2)
+    for (const fixture of stable) {
+      expect(fixture).toContain(`"id":"${existingId}"`)
+      expect(fixture).not.toContain(freshId)
+    }
+  })
+
+  it('leaves fresh fixtures unchanged when no committed counterpart exists', () => {
+    const fresh = '{"type":"session","id":"new"}\n'
+    expect(stabilizeFixtureMessageIds([fresh], [''])).toEqual([fresh])
+  })
+})
+
 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 })