Merge remote-tracking branch 'origin/master' into codex/simp-prune-workflow-worker-surface

# Conflicts:
#	docs/config-catalog.md
This commit is contained in:
Tianyi Cui
2026-07-14 17:41:20 +08:00
562 changed files with 4439 additions and 12572 deletions
@@ -12,17 +12,12 @@ const builtWorker = join(packageRoot, 'lib', 'worker.cjs')
const run = promisify(execFile)
/**
* The BUILT-output guard for the worker entry: every other suite runs
* unbuilt (src/ + tsx), so nothing else proves that `lib/index.js` resolves
* its sibling `lib/worker.cjs` and that the bundle boots a worker under plain
* node (no tsx loader). Keyless — a zero-agent script needs no provider —
* and self-skips until `pnpm run build` has produced the bundles.
* Keyless built-artifact guard: plain Node loads `lib/index.js` and its sibling
* `lib/worker.cjs` without tsx. Skips until the build produces both bundles.
*/
describe.skipIf(!existsSync(builtIndex) || !existsSync(builtWorker))('built worker entry (lib/worker.cjs)', () => {
it('the built engine spawns its built worker under plain node and completes a run', async () => {
// ESM resolves bare specifiers from the IMPORTING FILE's location, so the
// driver must live inside the package for its node_modules to apply — a
// temp-named file at the package root, removed on the way out.
// Keep the driver in-package so bare imports resolve its node_modules.
const driver = join(packageRoot, `.built-worker-driver-${process.pid}.mjs`)
try {
await writeFile(driver, `
@@ -36,7 +31,7 @@ await ctx.plugin(WorkerWorkflowEngine, {})
const run = ctx.workflows.start({
script: 'return 6 * 7',
meta: { name: 'built-smoke', description: 'built worker smoke' },
// A zero-agent script never touches the provider, so a bare id suffices.
// A zero-agent script never touches the provider.
parent: { id: 'built-smoke-parent', options: {} },
})
const result = await run.result
@@ -47,7 +42,6 @@ if (result.stopReason !== 'completed' || result.value !== 42) {
}
console.log('built-worker-smoke-ok')
`, 'utf8')
// Plain node — no tsx loader anywhere; the bundle must stand on its own.
const { stdout } = await run(process.execPath, [driver], { cwd: packageRoot, timeout: 60_000 })
expect(stdout).toContain('built-worker-smoke-ok')
} finally {
@@ -437,10 +437,7 @@ describe('runWorkerSession over an in-process MessageChannel', () => {
void runWorkerSession(host.port, init("return await agent('p')"))
await vi.waitFor(() => { expect(host.ofType(WorkerToHostType.ChildStart).length).toBe(1) })
const callId = host.ofType(WorkerToHostType.ChildStart)[0]!.callId
// Cancel FIRST, then the (stale) started reply: the worker processes them
// in order, so the agent() continuation resumes already-cancelled — the
// window the real host cannot produce (it refuses starts once cancelled)
// but a teardown race can.
// Simulate a teardown race by delivering cancellation before a stale start reply.
host.send({ type: HostToWorkerType.Cancel, reason: 'raced the start' })
host.send({ type: HostToWorkerType.ChildStarted, callId, childId: 'child-0' })
const result = await host.result()
@@ -448,7 +445,7 @@ describe('runWorkerSession over an in-process MessageChannel', () => {
await vi.waitFor(() => {
expect(host.ofType(WorkerToHostType.ChildDispose).map(m => m.callId)).toContain(callId)
})
// The child never became an agent-start: it was wound down pre-lifecycle.
// The unpublished child is disposed without a lifecycle announcement.
expect(host.ofType(WorkerToHostType.AgentStart)).toEqual([])
host.close()
})
@@ -17,27 +17,13 @@ function fakeParent(): Agent {
return { id: AgentId('workflow-parent'), options: {} } as unknown as Agent
}
// Worker-thread startup is CPU-bound (a fresh thread compiles the runtime on
// every start): on a contended CI runner it regularly blows past vitest's 5s
// default test timeout, observed repeatedly on the coverage lane.
// Allow cold worker startup on contended CI runners.
vi.setConfig({ testTimeout: 30_000 })
/**
* `vi.waitFor` with a contention-proof default timeout: the 1s default
* flaked repeatedly on the CI coverage lane, where worker-thread cold start
* (CPU-bound — a fresh thread compiles the runtime) competes with three
* sibling vitest workers for CPU. The 10s default is for exactly those
* races — waiting for a worker to start, run its first script line, or
* deliver an async child-registration message to the host. It is NOT for a
* wait that asserts the HOST reacted PROMPTLY to something that already
* happened (a settled result, an observed worker death): those keep an
* explicit tight override below, or the generous default would silently
* accept a multi-second regression in host-side reap latency as passing
* (proven by injecting a 6s delay into one such reap and watching the
* un-overridden version of this helper still pass in ~6s).
* @param assertion - retried until it stops throwing or the timeout elapses.
* @param timeout - override for a wait that must stay deliberately tight.
* @returns resolves when the assertion passes.
* Wait up to 10 seconds for CPU-bound worker startup or cross-thread delivery on contended CI.
* Host reactions after an observed event use explicit tight overrides, so this generous startup
* allowance cannot hide multi-second reap regressions.
*/
function waitFor(assertion: () => void, timeout = 10_000): Promise<void> {
return vi.waitFor(assertion, { timeout, interval: 50 })