Tianyi Cui
81d434896d
Adds the snapshot-test harness and the keyless replay pipeline end-to-end. - snapshot-harness.ts: boots the real acp-agent subprocess via the cordis Loader (preserving TSX_TSCONFIG_PATH so unbuilt dsh-* imports resolve from a temp cwd), tees raw stdout into an SDK ClientSideConnection, interprets a per-scenario input.json DSL (initialize / newSession capturing the random sessionId / prompt / cancel), closes stdin to trigger graceful shutdown, and harvests the persisted session.jsonl. Failure-safe: a finally block SIGKILLs a live child, awaits its exit, and removes both temp dirs even on a thrown step or harvest. Raw bytes are buffered and decoded once (no multibyte split). - snapshot-normalize.ts (+ spec): two pure normalizers (stdout frames + session JSONL) scrub cwd, session ids / UUIDs, and JSON-RPC ids, and zero time / createdAt — but keep `seq` (deterministic by contract). normalizeStdout throws on a non-JSON line (the stdout-purity check). - start.ts: selects cordis.snapshot.yml (replay, providerless) or cordis.snapshot-record.yml (record, real adapter) from DSH_SNAPSHOT, skips .env in replay, and disposes the ctx on stdin end so persistence flushes before exit (harvest-after-flush, not on the prompt response). - acp.snapshot.ts: asserts the normalized stdout golden (and, for model scenarios, the re-persisted JSONL golden) via toMatchFileSnapshot; record mode writes the harvested log back to the scenario fixture; an orphan-fixture guard fails on an unregistered scenario dir. - handshake scenario: initialize + session/new (no model call; a header-only session.jsonl, since session/new persists no events). - vitest.snapshot.config.ts, test:snapshot / test:snapshot:record scripts, a pre-push snapshot job, and the knip entry. Incorporates Codex review: record-fixture writeback, failure-safe teardown, seq-not-scrubbed, harvest-after-flush. Per docs/rfc/implemented/2026-06-19.
94 lines
3.6 KiB
TypeScript
94 lines
3.6 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import { type NormalizeContext, normalizeSessionLog, normalizeStdout } from '../tests/snapshot-normalize.ts'
|
|
|
|
/**
|
|
* Unit tests for the pure snapshot normalizers. Live as a *.spec.ts (runs in
|
|
* the default unit gate) and import the harness-side normalizers directly.
|
|
*/
|
|
|
|
const ctx: NormalizeContext = {
|
|
sessionIds: ['11111111-2222-3333-4444-555555555555'],
|
|
cwd: '/tmp/acp-snap-cwd-abc123',
|
|
}
|
|
|
|
describe('normalizeStdout', () => {
|
|
it('rewrites JSON-RPC ids to a stable first-seen sequence', () => {
|
|
const raw = [
|
|
JSON.stringify({ jsonrpc: '2.0', id: 42, method: 'initialize' }),
|
|
JSON.stringify({ jsonrpc: '2.0', id: 42, result: {} }),
|
|
JSON.stringify({ jsonrpc: '2.0', id: 99, method: 'session/new' }),
|
|
].join('\n')
|
|
const out = normalizeStdout(raw, ctx)
|
|
expect(out).toContain('"id": 1')
|
|
expect(out).toContain('"id": 2')
|
|
expect(out).not.toContain('42')
|
|
expect(out).not.toContain('99')
|
|
})
|
|
|
|
it('scrubs the cwd and session id anywhere they appear', () => {
|
|
const raw = JSON.stringify({
|
|
jsonrpc: '2.0', method: 'session/update',
|
|
params: { sessionId: ctx.sessionIds[0], cwd: ctx.cwd, note: `at ${ctx.cwd}/x` },
|
|
})
|
|
const out = normalizeStdout(raw, ctx)
|
|
expect(out).toContain('{{sessionId}}')
|
|
expect(out).toContain('{{cwd}}')
|
|
expect(out).not.toContain(ctx.cwd)
|
|
expect(out).not.toContain(ctx.sessionIds[0] as string)
|
|
})
|
|
|
|
it('scrubs a stray UUID not in the known list', () => {
|
|
const raw = JSON.stringify({ jsonrpc: '2.0', method: 'x', params: { id: 'aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee' } })
|
|
expect(normalizeStdout(raw, ctx)).toContain('{{sessionId}}')
|
|
})
|
|
|
|
it('leaves notification frames without an id untouched in id-space', () => {
|
|
const raw = JSON.stringify({ jsonrpc: '2.0', method: 'session/update', params: {} })
|
|
const out = normalizeStdout(raw, ctx)
|
|
expect(out).not.toContain('"id"')
|
|
})
|
|
|
|
it('throws on a non-JSON stdout line (the purity check)', () => {
|
|
const raw = `${JSON.stringify({ jsonrpc: '2.0', id: 1 })}\noops a log leaked\n`
|
|
expect(() => normalizeStdout(raw, ctx)).toThrow()
|
|
})
|
|
|
|
it('ignores blank lines', () => {
|
|
const raw = `\n${JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'm' })}\n\n`
|
|
expect(() => normalizeStdout(raw, ctx)).not.toThrow()
|
|
})
|
|
})
|
|
|
|
describe('normalizeSessionLog', () => {
|
|
const header = (over: object) => JSON.stringify({ type: 'session', version: 1, id: 's', createdAt: 123, ...over })
|
|
const event = (over: object) => JSON.stringify({ type: 'turn/start', seq: 1, time: 999, data: { turn: 1 }, ...over })
|
|
|
|
it('zeroes the header createdAt', () => {
|
|
const out = normalizeSessionLog(`${header({})}\n`, ctx)
|
|
expect(out).toContain('"createdAt": 0')
|
|
expect(out).not.toContain('123')
|
|
})
|
|
|
|
it('zeroes each event time but keeps seq', () => {
|
|
const out = normalizeSessionLog(`${header({})}\n${event({ seq: 7, time: 999 })}\n`, ctx)
|
|
expect(out).toContain('"time": 0')
|
|
expect(out).toContain('"seq": 7') // seq is deterministic — NOT scrubbed
|
|
expect(out).not.toContain('999')
|
|
})
|
|
|
|
it('scrubs cwd and session id deep inside event data', () => {
|
|
const ev = JSON.stringify({
|
|
type: 'tool/result', seq: 2, time: 5,
|
|
data: { content: [{ type: 'text', text: `wrote ${ctx.cwd}/proof.txt` }] },
|
|
})
|
|
const out = normalizeSessionLog(`${header({ cwd: ctx.cwd })}\n${ev}\n`, ctx)
|
|
expect(out).toContain('{{cwd}}')
|
|
expect(out).not.toContain(ctx.cwd)
|
|
})
|
|
|
|
it('scrubs the session id in the header', () => {
|
|
const out = normalizeSessionLog(`${header({ id: ctx.sessionIds[0] })}\n`, ctx)
|
|
expect(out).toContain('{{sessionId}}')
|
|
})
|
|
})
|