fix(report): keep personal-report heartbeats ref'd during chapter writes
Independent Staging Quality Gate / validate (push) Successful in 7m56s
Independent Staging Quality Gate / publish (push) Successful in 1m49s

Staging lost the job lease mid-chapter because the unref'd interval never
fired outside an HTTP request. Refresh the lease on section progress and
leave the heartbeat timer ref'd so a long model await cannot starve it.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Jesse_Chen
2026-09-03 02:13:13 +08:00
parent 4329426530
commit 5c0bec0c94
5 changed files with 46 additions and 21 deletions
+15 -14
View File
@@ -165,11 +165,6 @@ function reportFailureCode(code: PersonalReportWorkerErrorCode): PersonalReportF
}
}
function timerUnref(timer: ReturnType<typeof globalThis.setInterval>): void {
const candidate = timer as ReturnType<typeof globalThis.setInterval> & { unref?: () => void };
candidate.unref?.();
}
function defaultRetryDelayMs(job: PersonalReportJobRecord): number {
const exponent = Math.max(0, Math.min(job.attemptCount - 1, 5));
return 5_000 * (2 ** exponent);
@@ -269,22 +264,26 @@ export function createPersonalReportWorker(deps: PersonalReportWorkerDeps) {
const controller = new AbortController();
let heartbeatError: unknown = null;
let heartbeatChain = Promise.resolve();
const refreshLease = async () => {
if (heartbeatError !== null || controller.signal.aborted) return;
await deps.jobs.heartbeatLease({
jobId: job.id,
leaseToken: job.leaseToken!,
leaseSeconds,
});
};
const heartbeatTimer = setIntervalFn(() => {
heartbeatChain = heartbeatChain
.then(async () => {
if (heartbeatError !== null || controller.signal.aborted) return;
await deps.jobs.heartbeatLease({
jobId: job.id,
leaseToken: job.leaseToken!,
leaseSeconds,
});
})
.then(refreshLease)
.catch((error) => {
heartbeatError = error;
controller.abort(error);
});
}, heartbeatIntervalMs);
timerUnref(heartbeatTimer);
// Keep this timer ref'd. The worker runs from instrumentation, not an HTTP
// request; unref'd intervals in Next.js standalone are skipped while the
// only in-flight work is a long model await, which is exactly when the
// lease must be extended.
let report: PersonalReportRecord | null = null;
const generationStartedAt = now().getTime();
@@ -339,6 +338,8 @@ export function createPersonalReportWorker(deps: PersonalReportWorkerDeps) {
signal: controller.signal,
sectionService: deps.sectionService,
onProgress: async (progress) => {
await refreshLease();
if (heartbeatError !== null) throw heartbeatError;
const percent = progress.total > 0
? Math.min(89, 30 + Math.floor((progress.completed / progress.total) * 55))
: 30;
@@ -422,6 +422,12 @@ test("production writer and worker keep the same signal on initial and repair mo
assert.match(workerSource, /generatePersonalReport\(\{[\s\S]*signal: context\.signal,[\s\S]*\}\)/);
assert.match(workerSource, /leaseSeconds: 600/);
assert.match(workerSource, /heartbeatIntervalMs: 20_000/);
const workerCore = readFileSync(
new URL("../src/lib/personal-report-worker-core.ts", import.meta.url),
"utf8",
);
assert.match(workerCore, /onProgress: async \(progress\) => \{\s*await refreshLease\(\)/);
assert.doesNotMatch(workerCore, /timerUnref\(heartbeatTimer\)/);
});
test("an all-blocked plan still produces a valid v2 document with honest disclosures and no invented thematic section", async () => {
+21 -3
View File
@@ -87,7 +87,9 @@ function jobRecord(overrides: Partial<PersonalReportJobRecord> = {}): PersonalRe
function createHarness(input: Readonly<{
job?: PersonalReportJobRecord;
report?: PersonalReportRecord | null;
generate?: () => Promise<GeneratePersonalReportResult>;
generate?: (context: {
onProgress?: (progress: Readonly<{ phase: string; completed: number; total: number }>) => Promise<void> | void;
}) => Promise<GeneratePersonalReportResult>;
loseLeaseBeforeCompletion?: boolean;
markReadyError?: PersonalReportJobServiceError;
billing?: ReportBillingPort;
@@ -326,10 +328,10 @@ function createHarness(input: Readonly<{
assert.equal(userId, USER_ID);
return { birth_time_status: "confirmed" };
},
generate: async () => {
generate: async (context) => {
events.push("generate");
generateCount += 1;
return input.generate?.() ?? { status: "ready", document: READY_DOCUMENT, evidenceHash: "c".repeat(64) };
return input.generate?.(context) ?? { status: "ready", document: READY_DOCUMENT, evidenceHash: "c".repeat(64) };
},
billing: input.billing
? {
@@ -385,6 +387,22 @@ test("tick recovers first, heartbeats, persists the report, then closes the leas
);
});
test("section progress heartbeats the lease before recording percent", async () => {
const harness = createHarness({
generate: async (context) => {
await context.onProgress?.({ phase: "section:theme-career", completed: 1, total: 4 });
return { status: "ready", document: READY_DOCUMENT, evidenceHash: "c".repeat(64) };
},
});
const result = await harness.worker.tick();
assert.equal(result.outcome, "ready");
const generateAt = harness.events.indexOf("generate");
const progressAt = harness.events.indexOf("progress:section:theme-career:43");
assert.ok(generateAt >= 0);
assert.ok(progressAt > generateAt);
assert.ok(harness.events.slice(generateAt + 1, progressAt).includes("heartbeat"));
});
test("a restarted process reclaims an expired lease and does not create a second report or job", async () => {
const harness = createHarness({
job: jobRecord({