Merge master into worktree-windows-runtime

This commit is contained in:
Tianyi Cui
2026-07-21 23:39:14 +08:00
936 changed files with 36271 additions and 10361 deletions

View File

@@ -6,8 +6,8 @@ Four layers, importable separately:
- **`launchAcpTestAgent` (launcher)** — boots a source agent under tsx or a built `lib` agent under plain Node from a temp 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. 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; 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), `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/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 expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.expected.md` plus `tool-schemas.expected.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). 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.
- **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; cwd-rooted separators selected as canonical `/` or host-native; `session_info_update.updatedAt` → `{{updatedAt}}`; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept, the same cwd-path policy), `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/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 expected-output and re-persisted-log comparisons, record/refresh fixture write-back, rejection of structured `UNKNOWN_TOOL` results, the per-header-class pin (`system-prompt.expected.md` plus `tool-schemas.expected.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). Refresh preserves existing volatile fields by event position and gives a newly inserted `session/title` 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.
A consuming `*.snapshot.ts` is the scenario table plus one factory call:

View File

@@ -11,11 +11,16 @@
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./invariant": {
"types": "./lib/types/invariant.d.ts",
"default": "./lib/invariant.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/invariant.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
@@ -27,9 +32,11 @@
"vitest": "^4.1.8"
},
"peerDependencies": {
"@deepseek-ai/dsh-invariants": "^0.0.1",
"cordis": "^4.0.0-rc.7"
},
"devDependencies": {
"@deepseek-ai/dsh-invariants": "workspace:^",
"cordis": "^4.0.0-rc.7"
}
}

View File

@@ -43,6 +43,8 @@ export {
} from './normalize.ts'
export {
defineAcpSnapshotSuite,
refreshFixtureReplacements,
stabilizeRefreshLog,
type Scenario,
type SnapshotSuiteOptions,
} from './suite.ts'

View File

@@ -0,0 +1,30 @@
/**
* Package-owned invariant companion for `@deepseek-ai/dsh-acp-snapshot`.
* @module @deepseek-ai/dsh-acp-snapshot/invariant
*/
/* jscpd:ignore-start */
import type { Context } from 'cordis'
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
const PACKAGE_NAME = '@deepseek-ai/dsh-acp-snapshot'
/** Cordis companion plugin name. */
export const name = 'acp-snapshot-invariant'
/** Service required before the companion can reserve package ownership. */
export const inject = ['invariants']
/**
* No runtime invariant: this test-support package owns no production event stream or mutable data;
* consuming test suites exercise its behavior.
*/
const install: InvariantInstaller = () => {}
/**
* Register this package's invariant companion.
* @param ctx - Cordis context carrying the invariant service.
* @returns the installed registration's disposer after setup succeeds.
*/
export const apply = (ctx: Context): Promise<() => void> =>
Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install))
/* jscpd:ignore-end */

View File

@@ -11,6 +11,7 @@ const CWD = '{{cwd}}'
const SYSTEM = '{{system}}'
const TOOLS = '{{tools}}'
const MESSAGE_PREFIX = '{{messagePrefix}}'
const UPDATED_AT = '{{updatedAt}}'
/** A cwd-rooted path after volatile cwd replacement, through its last separator-delimited segment. */
const CWD_ROOTED_PATH_RE = /\{\{cwd\}\}(?:[\\/][^\s<>"'`]+)+/g
@@ -123,6 +124,8 @@ export function normalizeStdout(
if ('id' in frame && frame.id !== undefined && frame.id !== null) {
frame.id = stableId(frame.id)
}
const update = (frame.params as { update?: Record<string, unknown> } | undefined)?.update
if (update?.sessionUpdate === 'session_info_update') update.updatedAt = UPDATED_AT
return scrubValue(frame, ctx, cwdPathMode) as Record<string, unknown>
})
return frames.map(f => JSON.stringify(f)).join('\n') + '\n'

View File

@@ -479,8 +479,21 @@ export function stabilizeRefreshLog(fresh: string, existing: string, replacement
for (const { from, to } of replacements) stable = stable.split(from).join(to)
const existingRecords = parseJsonlRecords(existing)
const records = parseJsonlRecords(stable)
let existingIndex = 0
let previousEventTime: unknown
for (let i = 0; i < records.length; i++) {
preserveFixtureVolatiles(records[i] as Record<string, unknown>, existingRecords[i])
const record = records[i] as Record<string, unknown>
const existingRecord = existingRecords[existingIndex]
const insertedTitle = record.type === 'session/title' && existingRecord?.type !== 'session/title'
if (insertedTitle) {
/* v8 ignore next -- a title is turn-enclosed, so a preceding event time exists in every valid fixture. */
if (typeof previousEventTime !== 'number') throw new Error('acp-snapshot: inserted title has no preceding event time')
record.time = previousEventTime
} else {
preserveFixtureVolatiles(record, existingRecord)
existingIndex += 1
}
if (typeof record.time === 'number') previousEventTime = record.time
}
return records.map(record => JSON.stringify(record)).join('\n') + '\n'
}

View File

@@ -105,6 +105,24 @@ Additional instructions from: nested\AGENTS.md`,
expect(out).not.toContain('"id"')
})
it('stabilizes the timestamp carried by session title updates', () => {
const raw = JSON.stringify({
jsonrpc: '2.0',
method: 'session/update',
params: {
sessionId: ctx.sessionIds[0],
update: {
sessionUpdate: 'session_info_update',
title: 'Stable title',
updatedAt: '2026-07-20T17:03:13.689Z',
},
},
})
const out = normalizeStdout(raw, ctx)
expect(out).toContain('"updatedAt":"{{updatedAt}}"')
expect(out).not.toContain('2026-07-20T17:03:13.689Z')
})
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()

View File

@@ -451,6 +451,36 @@ describe('refreshFixtureReplacements', () => {
})
describe('stabilizeRefreshLog', () => {
it('aligns volatile times across a newly inserted log event', () => {
const fresh = [
'{"type":"session","id":"same","createdAt":200}',
'{"type":"turn/start","seq":0,"time":21}',
'{"type":"user/message","seq":1,"time":22}',
'{"type":"session/title","seq":2,"time":999}',
'{"type":"step/start","seq":3,"time":1000}',
'{"type":"request/header","seq":4,"time":1001}',
'',
].join('\n')
const existing = [
'{"type":"session","id":"same","createdAt":100}',
'{"type":"turn/start","seq":0,"time":11}',
'{"type":"user/message","seq":1,"time":12}',
'{"type":"step/start","seq":2,"time":13}',
'{"type":"request/header","seq":3,"time":14}',
'',
].join('\n')
expect(stabilizeRefreshLog(fresh, existing, [])).toBe([
'{"type":"session","id":"same","createdAt":100}',
'{"type":"turn/start","seq":0,"time":11}',
'{"type":"user/message","seq":1,"time":12}',
'{"type":"session/title","seq":2,"time":12}',
'{"type":"step/start","seq":3,"time":13}',
'{"type":"request/header","seq":4,"time":14}',
'',
].join('\n'))
})
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}',

View File

@@ -8,6 +8,11 @@
"src"
],
"references": [
{ "path": "../loader-smoke" }
{
"path": "../loader-smoke"
},
{
"path": "../../support/invariants"
}
]
}