From 5039c4ae40835a23db8a4876d1352eba9dd6d092 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:38:57 +0800 Subject: [PATCH] fix(snapshot): include agent stderr in failures --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 4 ++++ .../support/acp-snapshot/tests/fixtures/fake-acp-agent.ts | 3 +++ packages/support/acp-snapshot/tests/harness.spec.ts | 8 ++++++++ 4 files changed, 16 insertions(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 03254a17a0..55e9aadf4d 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Three layers, importable separately: -- **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). +- **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). Startup failures preserve captured agent stderr in the rejected diagnostic. - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}`), `scrubToolSchemas` (schema bulk → `{{tools}}`), and `scrubRequestHeaders` (all header bulk → `{{system}}`/`{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.golden.md` plus `tool-schemas.golden.json`) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt/schema-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 3bae0ba279..4933e11e88 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -281,6 +281,10 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) + } catch (error: unknown) { + const stderr = stderrChunks.join('') + if (stderr === '') throw error + throw new Error(`snapshot-harness: scenario failed: ${String(error)}\nagent stderr:\n${stderr}`, { cause: error }) } finally { // Failure-safe teardown: kill a still-running child and drop the temp dirs // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index d5fcd75a93..fccd1d6fcc 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -24,6 +24,8 @@ interface ScriptedLog { /** The whole scripted behavior for one run. Every field defaults to the least surprising choice. */ interface Behavior { + /** Exit during startup after writing any configured stderr note. */ + failOnBoot?: boolean /** Reject every `session/new` (exercises the expect-error step without extra dirs). */ rejectNewSession?: boolean /** Reject `session/new` only when `additionalDirectories` is non-empty (the real bridge's rule). */ @@ -62,6 +64,7 @@ const behavior: Behavior = fixtureFile === '' : JSON.parse(readFileSync(join(dirname(fixtureFile), 'behavior.json'), 'utf8')) as Behavior if (behavior.stderrNote !== undefined) process.stderr.write(`${behavior.stderrNote}\n`) +if (behavior.failOnBoot === true) process.exit(7) let nextOutboundId = 1000 let sessionId = '' diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 01b93dc81e..42ccbd7de4 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -38,6 +38,14 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('includes agent stderr when the ACP connection closes during startup', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ failOnBoot: true, stderrNote: 'fake agent requested startup failure' }) + await expect(runScenario( + { steps: [{ op: 'initialize' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + )).rejects.toThrow(/agent stderr:\nfake agent requested startup failure/) + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true,