Compare commits

..
Author SHA1 Message Date
08f2397615 fix(webhook): extract links for incremental push syncs (#2849)
GitHub webhook + sync-trigger 'sync' jobs never opted into extraction:
the standalone sync handler defaults noExtract to TRUE, so webhook-
imported pages advanced the source bookmark with links_extracted_at
unstamped — and nothing behind a standalone job ever swept them (the
autopilot cycle's extract phase only walks that cycle's changedSlugs).

Fix, both halves of the issue:
- webhook + sync-trigger payloads pass noExtract:false so normal
  incremental pushes get sync's inline link/timeline extraction.
- >100-file deferral branch: performSync surfaces extractDeferred, and
  the sync job handler queues a source-scoped extract{stale:true}
  follow-up job (idempotent sweep; extract handler gains a stale mode
  backed by the same extractStaleFromDB core as `gbrain extract --stale`).

Tests: new sync-large-deferral-extract.serial.test.ts drives a real
101-file incremental sync end-to-end (deferral flag → queued follow-up →
stale sweep recovers links + watermark); webhook payload contract test +
sync-trigger noExtract assertion salvaged from #2850.

Fixes #2849
Takeover of #2850

Co-authored-by: patentsong <patentsong@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:38:43 -07:00
19 changed files with 301 additions and 622 deletions
+1 -1
View File
@@ -1651,7 +1651,7 @@ async function extractTimelineFromDB(
* make re-extraction idempotent). EVERY processed page is stamped, including
* zero-link pages — they WERE processed.
*/
async function extractStaleFromDB(
export async function extractStaleFromDB(
engine: BrainEngine,
opts: {
dryRun: boolean;
+39 -3
View File
@@ -1479,7 +1479,31 @@ export async function registerBuiltinHandlers(
embedSkipReason = 'auto_embed_disabled';
}
return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason };
// #2849: large-sync extract deferral follow-up. performSync skips inline
// link/timeline extraction when totalChanges > 100, leaving
// links_extracted_at unstamped. A standalone sync job (webhook push,
// sync trigger) has no autopilot extract phase behind it, so the pages
// would stay extraction-stale until a manual `gbrain extract --stale`.
// Queue a source-scoped stale sweep instead. Best-effort + idempotent:
// a duplicate sweep finds 0 stale pages and no-ops.
let extractJobId: number | null = null;
if (result.extractDeferred) {
try {
const { MinionQueue } = await import('../core/minions/queue.ts');
const queue = new MinionQueue(engine);
const followUp = await queue.add(
'extract',
{ stale: true, ...(sourceId ? { sourceId } : {}) },
{
idempotency_key: `sync-extract-stale:${sourceId ?? 'default'}:${Math.floor(Date.now() / 30_000)}`,
maxWaiting: 1,
},
);
extractJobId = followUp.id;
} catch { /* best-effort: extract --stale sweeps it later */ }
}
return { ...result, embed_job_id: embedJobId, embed_skip_reason: embedSkipReason, extract_stale_job_id: extractJobId };
});
registerBuiltinJob(worker, engine, 'embed', async (job) => {
@@ -1652,6 +1676,20 @@ export async function registerBuiltinHandlers(
});
worker.register('extract', async (job) => {
// #2849: stale-sweep mode — the sync handler's large-sync deferral
// follow-up. DB-source (reads page content from the DB, so it runs on
// checkout-less brains), source-scopable, idempotent. Same core as
// `gbrain extract --stale`.
if (job.data.stale === true) {
const { extractStaleFromDB } = await import('./extract.ts');
return await extractStaleFromDB(engine, {
dryRun: !!job.data.dryRun,
jsonMode: false,
includeFrontmatter: false,
sourceIdFilter: typeof job.data.sourceId === 'string' ? job.data.sourceId : undefined,
catchUp: false,
});
}
const { runExtractCore } = await import('./extract.ts');
const mode = (typeof job.data.mode === 'string' && ['links', 'timeline', 'all'].includes(job.data.mode))
? (job.data.mode as 'links' | 'timeline' | 'all')
@@ -2059,8 +2097,6 @@ export async function registerBuiltinHandlers(
sourceId,
windowSeconds,
brainDir: repoPath,
// #2750: worker cancel/timeout/lock-loss propagates into the drain.
abortSignal: job.signal,
});
} catch (e) {
if (e instanceof LockUnavailableError) {
+8 -2
View File
@@ -2146,8 +2146,13 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
// Other event types (ping, pull_request, etc.) return 202 'ignored'
// so GitHub doesn't retry.
// D15.5: HMAC compare uses the shared safeHexEqual helper.
// D18: submits 'sync' job with auto_embed_backfill=true and priority -10
// (above autopilot's 0).
// D18: submits 'sync' job with extraction + auto_embed_backfill enabled and
// priority -10 (above autopilot's 0). noExtract:false opts normal
// incremental pushes into sync's inline link/timeline extraction (#2849
// — the standalone sync handler defaults noExtract to TRUE, which left
// webhook-imported pages permanently stale). Large (>100 file) pushes
// defer inline extract; the sync handler queues an extract --stale
// follow-up job for that branch.
// ---------------------------------------------------------------------------
const githubWebhookLimiter = rateLimit({
windowMs: 60_000,
@@ -2267,6 +2272,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
'sync',
{
sourceId: source.id,
noExtract: false,
auto_embed_backfill: true,
embed_reason: 'webhook',
},
+19 -1
View File
@@ -222,6 +222,14 @@ export interface SyncResult {
* everything," the exact misdiagnosis in the #1794 recurrence report.
*/
bankedFiles?: number;
/**
* #2849: true when extraction was REQUESTED (noExtract false) but this sync
* skipped inline link/timeline extraction because totalChanges > 100 (the
* #1794 large-sync deferral). links_extracted_at stays unstamped for the
* imported pages. The standalone `sync` job handler queues a source-scoped
* `extract --stale` follow-up when set; CLI runs print the manual hint.
*/
extractDeferred?: boolean;
}
/**
@@ -1379,6 +1387,10 @@ See also:
{
sourceId: sourceIdArg,
repoPath: source.local_path,
// #2849: opt in to inline extraction — the standalone sync handler
// defaults noExtract to TRUE (dedupe for doctor's [sync, extract]
// remediation plan), which would leave triggered syncs extraction-stale.
noExtract: false,
auto_embed_backfill: true,
embed_reason: 'sync_trigger',
},
@@ -3287,11 +3299,16 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
// the stale sweep scans the whole source, so banked-across-runs pages are
// covered regardless.
const extractOpts = opts.sourceId ? { sourceId: opts.sourceId } : undefined;
let extractDeferred = false;
if (!opts.noExtract && totalChanges > 100 && pagesAffected.length > 0) {
// #2849: surface the deferral to callers. A standalone sync job (webhook
// push, sync trigger) has no autopilot extract phase behind it, so the
// job handler queues an `extract --stale` follow-up off this flag.
extractDeferred = true;
slog(
` Large sync: deferring link/timeline extraction. ` +
`Run 'gbrain extract --stale${opts.sourceId ? ` --source-id ${opts.sourceId}` : ''}' ` +
`(or let the autopilot cycle's extract phase sweep it).`,
`(sync jobs queue this follow-up automatically).`,
);
}
if (!opts.noExtract && totalChanges <= 100 && pagesAffected.length > 0) {
@@ -3400,6 +3417,7 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
chunksCreated,
embedded,
pagesAffected,
extractDeferred,
};
}
+16 -77
View File
@@ -23,10 +23,6 @@
*/
import type { BrainEngine } from '../engine.ts';
import { anySignal } from '../abort-check.ts';
/** Fresh cleanup budget for the lock release after the window signal fires. */
const LOCK_RELEASE_GRACE_MS = 5_000;
export interface ExtractAtomsDrainDeps {
/**
@@ -34,13 +30,13 @@ export interface ExtractAtomsDrainDeps {
* via `withRefreshingLock`. MUST throw when the lock is held by another
* process (e.g. `LockUnavailableError`) the drain lets that propagate so
* the caller can report `cycle_already_running` and exit, matching the
* routine cycle's skip contract. The signal bounds lock acquisition too.
* routine cycle's skip contract.
*/
withLock: <T>(work: () => Promise<T>, signal: AbortSignal) => Promise<T>;
/** Process one batch. The signal fires at the drain wallclock deadline. */
runBatch: (signal: AbortSignal) => Promise<{ extracted: number; skipped: number }>;
withLock: <T>(work: () => Promise<T>) => Promise<T>;
/** Process one bounded batch (rediscovers eligibility). Returns counts. */
runBatch: () => Promise<{ extracted: number; skipped: number }>;
/** Count remaining eligible-but-unextracted pages, or null on query error. */
countRemaining: (signal: AbortSignal) => Promise<number | null>;
countRemaining: () => Promise<number | null>;
/** Injectable clock. Production: Date.now. */
now: () => number;
/** Optional progress sink (one line per batch). */
@@ -52,8 +48,6 @@ export interface ExtractAtomsDrainOpts {
windowMs: number;
/** Hard cap on batches (belt-and-suspenders against a 0-progress loop). Default 1000. */
maxBatches?: number;
/** External caller cancellation (worker timeout / shutdown). */
abortSignal?: AbortSignal;
}
export interface ExtractAtomsDrainResult {
@@ -74,79 +68,35 @@ export async function runExtractAtomsDrain(
opts: ExtractAtomsDrainOpts,
): Promise<ExtractAtomsDrainResult> {
const maxBatches = opts.maxBatches ?? 1000;
const deadline = deps.now() + opts.windowMs;
// #2750: the window used to be checked only BETWEEN batches, so one slow
// batch (sequential LLM calls) or a hung lock/count/write overran it without
// bound (observed window=120s → 282.5s). A real-time deadline signal now
// cancels (Postgres) or abandons (PGLite, cooperative) whatever is in
// flight; the injected clock still drives loop-boundary checks so the pure
// loop stays unit-testable.
const signal = anySignal(
AbortSignal.timeout(Math.max(1, opts.windowMs)),
opts.abortSignal,
);
const result: ExtractAtomsDrainResult = await deps.withLock(async () => {
return deps.withLock(async () => {
const deadline = deps.now() + opts.windowMs;
let extracted = 0;
let skipped = 0;
let batches = 0;
let stopped: ExtractAtomsDrainResult['stopped'] = 'window';
while (deps.now() < deadline && !signal.aborted) {
while (deps.now() < deadline) {
if (batches >= maxBatches) { stopped = 'max_batches'; break; }
let before: number | null;
try {
before = await deps.countRemaining(signal);
} catch (err) {
if (signal.aborted) break;
throw err;
}
const before = await deps.countRemaining();
if (before === 0) { stopped = 'drained'; break; }
// The backlog count consumed the same wallclock budget — re-check so a
// slow count can't hand the batch a window that already expired.
if (deps.now() >= deadline || signal.aborted) break;
let r: { extracted: number; skipped: number };
try {
r = await deps.runBatch(signal);
} catch (err) {
if (signal.aborted) break;
throw err;
}
const r = await deps.runBatch();
extracted += r.extracted;
skipped += r.skipped;
batches++;
deps.onBatch?.({ batch: batches, extracted: r.extracted, remaining: before });
// A deadline abort inside the batch can surface as zero progress;
// window exhaustion wins over the generic no_progress label.
if (deps.now() >= deadline || signal.aborted) break;
// Stop if a batch made zero forward progress — extraction is failing or
// everything left is ineligible (e.g. all skipped). Prevents a hot loop
// that spends budget without draining.
if (r.extracted === 0 && r.skipped === 0) { stopped = 'no_progress'; break; }
}
// After the window elapsed, don't spend more unbounded time on a final
// count — report remaining as unknown instead of overrunning further.
const windowElapsed = signal.aborted || deps.now() >= deadline;
let remaining: number | null = null;
if (!windowElapsed) {
try {
remaining = await deps.countRemaining(signal);
} catch (err) {
if (!signal.aborted) throw err;
}
}
const remaining = await deps.countRemaining();
if (remaining === 0) stopped = 'drained';
return { phase: 'extract_atoms', status: 'ok', extracted, skipped, remaining, batches, stopped };
}, signal);
// Internal window expiry is a normal partial result. An EXTERNAL abort
// (worker cancel/timeout/shutdown) must reject so Minion records the abort.
if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
return result;
});
}
// ─── Shared wiring helper (v0.42.x #1685 DECISION 5A) ──────────────────────
@@ -184,8 +134,6 @@ export interface DrainForSourceOpts {
maxBatches?: number;
/** Optional per-batch progress sink (stderr line in dream; job progress in the handler). */
onBatch?: ExtractAtomsDrainDeps['onBatch'];
/** Worker cancellation / shutdown signal (Minion `job.signal`). */
abortSignal?: AbortSignal;
}
export async function runExtractAtomsDrainForSource(
@@ -201,17 +149,12 @@ export async function runExtractAtomsDrainForSource(
return runExtractAtomsDrain(
{
withLock: (work, signal) => withRefreshingLock(engine, lockId, work, {
ttlMinutes: 5,
signal,
releaseTimeoutMs: LOCK_RELEASE_GRACE_MS,
}),
runBatch: async (signal) => {
withLock: (work) => withRefreshingLock(engine, lockId, work, { ttlMinutes: 5 }),
runBatch: async () => {
const r = await runPhaseExtractAtoms(engine, {
sourceId: extractionSourceId,
dryRun: false,
brainDir: opts.brainDir,
abortSignal: signal,
});
const d = (r.details ?? {}) as Record<string, unknown>;
return {
@@ -219,14 +162,10 @@ export async function runExtractAtomsDrainForSource(
skipped: Number(d.duplicates_skipped ?? 0),
};
},
countRemaining: (signal) => countExtractAtomsBacklog(engine, extractionSourceId, signal),
countRemaining: () => countExtractAtomsBacklog(engine, extractionSourceId),
now: Date.now,
onBatch: opts.onBatch,
},
{
windowMs: opts.windowSeconds * 1000,
maxBatches: opts.maxBatches,
abortSignal: opts.abortSignal,
},
{ windowMs: opts.windowSeconds * 1000, maxBatches: opts.maxBatches },
);
}
+17 -68
View File
@@ -58,10 +58,6 @@ import { createHash } from 'crypto';
import { slugifySegment } from '../sync.ts';
const DEFAULT_BUDGET_USD = 0.3;
// #2750: fresh wallclock budget for the receipt/rollup bookkeeping writes when
// the caller's deadline already fired — committed atoms must not lose their
// cost/receipt trail, but the writes can't be unbounded either.
const BOOKKEEPING_GRACE_MS = 5_000;
// v0.42+ TODO: read atom_type enum from active pack manifest at runtime.
const ATOM_TYPES = [
@@ -159,13 +155,6 @@ export interface ExtractAtomsOpts {
* `heartbeat()` on the passed reporter.
*/
progress?: ProgressReporter;
/**
* #2750: caller deadline/cancellation. Forwarded to every gateway call and
* DB query/write so the drain window bounds real lifetime, plus a
* cooperative between-item check (the PGLite path, where query abort only
* abandons the waiter).
*/
abortSignal?: AbortSignal;
}
interface ExtractedAtom {
@@ -223,7 +212,6 @@ export async function discoverExtractablePages(
engine: BrainEngine,
sourceId: string,
affectedSlugs?: string[],
abortSignal?: AbortSignal,
): Promise<DiscoveredPage[]> {
const hasFilter = Array.isArray(affectedSlugs) && affectedSlugs.length > 0;
const sql = `
@@ -263,16 +251,13 @@ export async function discoverExtractablePages(
slug: string;
compiled_truth: string;
content_hash: string;
}>(sql, params, { signal: abortSignal });
}>(sql, params);
return rows.map((r) => ({
slug: r.slug,
content: r.compiled_truth,
contentHash: r.content_hash,
}));
} catch (err) {
// A deadline abort is not a fail-soft condition — propagate so the
// caller stops instead of proceeding with an empty page list.
if (abortSignal?.aborted) throw err;
const msg = err instanceof Error ? err.message : String(err);
console.error(`[extract_atoms] page-discovery query failed: ${msg}`);
return []; // fail-soft: transcript path still proceeds
@@ -297,7 +282,6 @@ export async function discoverExtractablePages(
export async function countExtractAtomsBacklog(
engine: BrainEngine,
sourceId?: string,
abortSignal?: AbortSignal,
): Promise<number | null> {
try {
// Two modes: scoped (the phase's per-source `remaining`) vs brain-wide
@@ -337,10 +321,9 @@ export async function countExtractAtomsBacklog(
const params = scoped
? [sourceId, extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION]
: [extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION];
const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params, { signal: abortSignal });
const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params);
return Number(rows[0]?.cnt ?? 0);
} catch (err) {
if (abortSignal?.aborted) throw err;
const msg = err instanceof Error ? err.message : String(err);
console.error(`[extract_atoms] backlog count failed: ${msg}`);
return null;
@@ -367,7 +350,6 @@ export async function atomsExistingForHashes(
engine: BrainEngine,
sourceId: string,
contentHash16s: string[],
abortSignal?: AbortSignal,
): Promise<Set<string>> {
if (contentHash16s.length === 0) return new Set();
try {
@@ -379,11 +361,9 @@ export async function atomsExistingForHashes(
AND deleted_at IS NULL
AND frontmatter->>'source_hash' = ANY($2::text[])`,
[sourceId, contentHash16s],
{ signal: abortSignal },
);
return new Set(rows.map(r => r.h));
} catch (err) {
if (abortSignal?.aborted) throw err;
const msg = err instanceof Error ? err.message : String(err);
console.error(`[extract_atoms] batch idempotency check failed (assuming none extracted): ${msg}`);
return new Set();
@@ -404,7 +384,6 @@ export async function runPhaseExtractAtoms(
): Promise<PhaseResult> {
const sourceId = opts.sourceId ?? 'default';
const chat = opts._chat ?? gatewayChat;
if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
// 1a. Get transcripts (test seam OR production discovery).
// v0.41.2.1: config loader switched to loadConfigWithEngine() so the
@@ -446,7 +425,7 @@ export async function runPhaseExtractAtoms(
if (opts._pages !== undefined) {
pages = opts._pages;
} else {
pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs, opts.abortSignal);
pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs);
}
// 2. Apply transcript-side source-hash idempotency in ONE batch query
@@ -458,7 +437,7 @@ export async function runPhaseExtractAtoms(
// Surface a heartbeat before the batch query so even an instant
// short-circuit shows a sign of life (closes Issue 2 silent-phase pain).
opts.progress?.heartbeat(`checking existing atoms for ${allHashes16.length} transcripts`);
const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16, opts.abortSignal);
const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16);
for (const t of transcripts) {
if (existingHashes.has(t.contentHash.slice(0, 16))) {
duplicatesSkipped++;
@@ -522,7 +501,6 @@ export async function runPhaseExtractAtoms(
const failures: Array<{ source: string; error: string }> = [];
let estimatedSpendUsd = 0;
const budgetCap = DEFAULT_BUDGET_USD;
let deadlineAborted = false;
// v0.41.19.0 (T3): throttled yield helper. Fires `opts.yieldDuringPhase`
// every 30s. Cycle.ts threads `buildYieldDuringPhase(lock, outer)` so
@@ -548,12 +526,6 @@ export async function runPhaseExtractAtoms(
}
for (const item of work) {
// #2750: cooperative between-item abort. Works on every engine — this is
// the primary bound on PGLite, where query abort only abandons the waiter.
if (opts.abortSignal?.aborted) {
deadlineAborted = true;
break;
}
await maybeYield();
if (estimatedSpendUsd >= budgetCap) {
if (item.kind === 'transcript') transcriptsSkipped++;
@@ -572,22 +544,16 @@ export async function runPhaseExtractAtoms(
},
],
maxTokens: 2000,
abortSignal: opts.abortSignal,
});
// Rough cost estimate — Haiku at ~$0.80/M input + $4/M output.
// A completed gateway call is billable even if the deadline fires
// immediately afterward, so record usage BEFORE the abort check.
estimatedSpendUsd +=
(result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
if (opts.abortSignal?.aborted) {
deadlineAborted = true;
break;
}
// Post-await yield: closes the "long LLM call past TTL" hazard
// codex flagged. The 30s throttle inside maybeYield bounds the
// actual refresh rate so this is cheap when calls are fast.
await maybeYield();
// Rough cost estimate — Haiku at ~$0.80/M input + $4/M output
estimatedSpendUsd +=
(result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
const atoms = parseAtomsResponse(result.text);
if (atoms.length === 0) {
if (item.kind === 'transcript') transcriptsProcessed++;
@@ -626,7 +592,7 @@ export async function runPhaseExtractAtoms(
},
timeline: '',
},
{ sourceId, signal: opts.abortSignal },
{ sourceId },
);
totalAtomsExtracted++;
}
@@ -639,11 +605,6 @@ export async function runPhaseExtractAtoms(
// Reporter rate-limits to ~1 line/sec; safe to tick every iter.
opts.progress?.tick(1, `${totalAtomsExtracted} atoms / ${duplicatesSkipped} skipped`);
} catch (err) {
// A deadline abort is a partial result, not a per-item failure.
if (opts.abortSignal?.aborted) {
deadlineAborted = true;
break;
}
failures.push({
source: originLabel,
error: err instanceof Error ? err.message : String(err),
@@ -654,12 +615,6 @@ export async function runPhaseExtractAtoms(
// v0.42 Wave B2: write extract receipt + rollup row when the phase
// actually extracted atoms. Both are best-effort per F-OUT-19 —
// audit-trail / search-visibility surfaces don't block the phase result.
//
// #2750: bookkeeping runs on a FRESH short grace signal, never the caller's
// work deadline — the deadline may have already fired (partial run) and
// committed atoms must not lose their receipt/cost trail; but the writes
// stay bounded so the overrun is capped at the grace window.
const bookkeepingSignal = opts.dryRun ? undefined : AbortSignal.timeout(BOOKKEEPING_GRACE_MS);
if (!opts.dryRun && totalAtomsExtracted > 0) {
const runId = `atoms-${Date.now().toString(36)}-${sourceId.slice(0, 4)}`;
try {
@@ -674,24 +629,19 @@ export async function runPhaseExtractAtoms(
summary:
`Extracted ${totalAtomsExtracted} atoms from ` +
`${transcriptsProcessed} transcripts + ${pagesProcessed} pages.`,
}, { signal: bookkeepingSignal });
});
} catch (err) {
console.error(`[extract_atoms] receipt write failed: ${(err as Error).message}`);
}
}
if (!opts.dryRun) {
try {
await upsertExtractRollup(engine, {
kind: 'atoms',
source_id: sourceId,
cost_delta: estimatedSpendUsd,
// A deadline-truncated run is not a completed round.
round_completed_delta: failures.length === 0 && !deadlineAborted ? 1 : 0,
halt_delta: failures.length > 0 ? 1 : 0,
}, { signal: bookkeepingSignal });
} catch (err) {
console.error(`[extract_atoms] rollup write failed: ${(err as Error).message}`);
}
await upsertExtractRollup(engine, {
kind: 'atoms',
source_id: sourceId,
cost_delta: estimatedSpendUsd,
round_completed_delta: failures.length === 0 ? 1 : 0,
halt_delta: failures.length > 0 ? 1 : 0,
});
}
return {
@@ -720,7 +670,6 @@ export async function runPhaseExtractAtoms(
budget_usd: budgetCap,
source_id: sourceId,
dry_run: opts.dryRun ?? false,
deadline_aborted: deadlineAborted,
},
};
}
+22 -50
View File
@@ -26,8 +26,7 @@ import type { BrainEngine } from './engine.ts';
export interface DbLockHandle {
id: string;
/** Optional signal bounds the release DELETE (deadline-bound callers). */
release: (signal?: AbortSignal) => Promise<void>;
release: () => Promise<void>;
refresh: () => Promise<void>;
}
@@ -174,7 +173,6 @@ export async function tryAcquireDbLock(
engine: BrainEngine,
lockId: string,
ttlMinutes: number = DEFAULT_TTL_MINUTES,
opts: { signal?: AbortSignal } = {},
): Promise<DbLockHandle | null> {
const pid = process.pid;
const host = hostname();
@@ -207,26 +205,20 @@ export async function tryAcquireDbLock(
// `gbrain sync --break-lock --max-age <s>` uses last_refreshed_at (not
// acquired_at) to identify wedged-but-alive holders without stealing
// healthy long-running holders that are actively refreshing.
// #2750: routed through executeRaw so a deadline-bound caller's signal
// can cancel a hung acquire (pool exhaustion). Cancellation is
// transactional; in the rare ambiguous-commit case the row's TTL is the
// backstop (drain locks use a short 5-minute TTL).
const rows = await engine.executeRaw<{ id: string }>(
`INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
VALUES ($1, $2, $3, NOW(), NOW() + $4::interval, NOW())
ON CONFLICT (id) DO UPDATE
SET holder_pid = $2,
holder_host = $3,
acquired_at = NOW(),
ttl_expires_at = NOW() + $4::interval,
last_refreshed_at = NOW()
WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
AND (gbrain_cycle_locks.last_refreshed_at IS NULL
OR gbrain_cycle_locks.last_refreshed_at < NOW() - $5 * INTERVAL '1 second')
RETURNING id`,
[lockId, pid, host, ttl, stealGraceSeconds],
{ signal: opts.signal },
);
const rows: Array<{ id: string }> = await sql`
INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
VALUES (${lockId}, ${pid}, ${host}, NOW(), NOW() + ${ttl}::interval, NOW())
ON CONFLICT (id) DO UPDATE
SET holder_pid = ${pid},
holder_host = ${host},
acquired_at = NOW(),
ttl_expires_at = NOW() + ${ttl}::interval,
last_refreshed_at = NOW()
WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
AND (gbrain_cycle_locks.last_refreshed_at IS NULL
OR gbrain_cycle_locks.last_refreshed_at < NOW() - ${stealGraceSeconds} * INTERVAL '1 second')
RETURNING id
`;
if (rows.length === 0) return null;
const deregister = registerCleanup(`db-lock:${lockId}`, async () => {
await sql`
@@ -249,17 +241,12 @@ export async function tryAcquireDbLock(
[ttl, lockId, pid],
);
},
release: async (signal?: AbortSignal) => {
release: async () => {
deregister();
// Direct session pool (same rationale as refresh, #1794) + optional
// signal so a deadline-bound caller's release can't hang forever on
// an exhausted pooler. TTL is the backstop if the DELETE is cancelled.
await engine.executeRawDirect(
`DELETE FROM gbrain_cycle_locks
WHERE id = $1 AND holder_pid = $2`,
[lockId, pid],
{ signal },
);
await sql`
DELETE FROM gbrain_cycle_locks
WHERE id = ${lockId} AND holder_pid = ${pid}
`;
},
};
}
@@ -316,11 +303,6 @@ export async function tryAcquireDbLock(
const first = await acquireOnce();
if (first) return first;
// #2750: deadline-bound callers prefer an honest busy result over the
// best-effort same-host takeover below, whose inspect/delete/retry calls
// are not signal-bounded. The initial upsert already reclaims expired locks.
if (opts.signal) return null;
// v0.42 (#1780 Gap 3): the lock is held and its TTL hasn't expired (the
// upsert's ON CONFLICT ... WHERE ttl_expires_at < NOW() returned no row).
// If the holder is on THIS host, provably dead, and past the grace window,
@@ -814,10 +796,6 @@ export interface WithRefreshingLockOpts {
ttlMinutes?: number;
/** Heartbeat-fail threshold in ms — abort if SELECT 1 takes longer. Default 30000. */
heartbeatTimeoutMs?: number;
/** #2750: bound lock acquisition with the caller's deadline signal. */
signal?: AbortSignal;
/** Fresh cleanup budget for the release DELETE when `signal` is set. Default 5000. */
releaseTimeoutMs?: number;
}
/**
@@ -837,7 +815,7 @@ export async function withRefreshingLock<T>(
// Refresh 6x per TTL window so a missed tick doesn't expire the lock.
const refreshIntervalMs = Math.max(15000, (ttlMinutes * 60 * 1000) / 6);
const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes, { signal: opts.signal });
const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes);
if (!handle) throw new LockUnavailableError(lockId);
let healthOk = true;
@@ -876,13 +854,7 @@ export async function withRefreshingLock<T>(
return await work();
} finally {
clearInterval(interval);
// #2750: when the caller is deadline-bound, its work signal may already
// have fired — release on a FRESH short grace signal so cleanup neither
// inherits the spent deadline nor hangs unbounded. TTL is the backstop.
const releaseSignal = opts.signal
? AbortSignal.timeout(opts.releaseTimeoutMs ?? 5_000)
: undefined;
try { await handle.release(releaseSignal); } catch { /* idempotent; TTL backstop */ }
try { await handle.release(); } catch { /* idempotent */ }
if (!healthOk) {
// Surface that the heartbeat detected backend trouble — caller can
// log to the connection-events audit if desired.
+1 -9
View File
@@ -696,16 +696,8 @@ export interface BrainEngine {
* is included in the INSERT column list so ON CONFLICT (source_id, slug)
* DO UPDATE actually targets the intended row instead of fabricating a
* duplicate at (default, slug). Multi-source brains MUST pass sourceId.
*
* `opts.signal` (#2750): optional cancellation for deadline-bound writers.
* Postgres cancels the in-flight statement; PGLite pre-checks only (query
* cancellation is not possible in-process cooperative abort between calls).
*/
putPage(
slug: string,
page: PageInput,
opts?: { sourceId?: string; signal?: AbortSignal },
): Promise<Page>;
putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page>;
/**
* v0.41.13 (#1309) identity-based dedup pre-check for the import pipeline.
*
+1 -2
View File
@@ -187,7 +187,6 @@ function buildReceiptFrontmatter(input: ExtractReceiptInput): Record<string, unk
export async function writeReceipt(
engine: BrainEngine,
input: ExtractReceiptInput,
opts?: { signal?: AbortSignal },
): Promise<{ slug: string; page: Page }> {
const slug = receiptSlug(input);
const title = `${input.kind}${input.round}${input.source_id}`;
@@ -202,7 +201,7 @@ export async function writeReceipt(
compiled_truth,
frontmatter,
},
{ sourceId: input.source_id, signal: opts?.signal },
{ sourceId: input.source_id },
);
return { slug, page };
-4
View File
@@ -70,7 +70,6 @@ function today(): string {
export async function upsertExtractRollup(
engine: BrainEngine,
input: RollupUpsertInput,
opts?: { signal?: AbortSignal },
): Promise<{ ok: boolean; error?: string }> {
const day = input.day ?? today();
const cost = input.cost_delta ?? 0;
@@ -97,12 +96,9 @@ export async function upsertExtractRollup(
rollup_write_failures = extract_rollup_7d.rollup_write_failures + EXCLUDED.rollup_write_failures,
updated_at = now()`,
[input.kind, input.source_id, day, cost, halts, evalFails, evalPasses, completed, failures],
{ signal: opts?.signal },
);
return { ok: true };
} catch (err) {
// Signal-bounded callers get the abort surfaced, not a swallowed `ok:false`.
if (opts?.signal?.aborted) throw err;
const msg = (err as Error).message || String(err);
// Don't spam: log once per process per (kind, day) error class.
rollupErrorLogOnce(input.kind, day, msg);
+1 -9
View File
@@ -1003,15 +1003,7 @@ export class PGLiteEngine implements BrainEngine {
return { slug: r.slug, id: Number(r.id) };
}
async putPage(
slug: string,
page: PageInput,
opts?: { sourceId?: string; signal?: AbortSignal },
): Promise<Page> {
// #2750: PGLite is in-process WASM — no query cancellation. Pre-check so
// an already-fired deadline skips the write; abort is cooperative
// between calls (same posture as executeRaw's documented gap).
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
slug = validateSlug(slug);
const hash = page.content_hash || contentHash(page);
const frontmatter = page.frontmatter || {};
+3 -55
View File
@@ -72,32 +72,6 @@ function escapeSqlStringLiteral(value: string): string {
return value.replace(/'/g, "''");
}
/**
* #2750: race a promise against an AbortSignal, detaching the listener once
* settled (long-lived drain signals are reused across many calls, so a bare
* Promise.race would leak one listener per call). The abandoned promise keeps
* running; used only for pool-acquisition waits where that is harmless.
*/
function waitForSignal<T>(work: Promise<T>, signal?: AbortSignal): Promise<T> {
if (!signal) return work;
if (signal.aborted) return Promise.reject(new DOMException('aborted', 'AbortError'));
return new Promise<T>((resolve, reject) => {
let settled = false;
const finish = (fn: () => void) => {
if (settled) return;
settled = true;
signal.removeEventListener('abort', onAbort);
fn();
};
const onAbort = () => finish(() => reject(new DOMException('aborted', 'AbortError')));
signal.addEventListener('abort', onAbort, { once: true });
work.then(
(value) => finish(() => resolve(value)),
(err) => finish(() => reject(err)),
);
});
}
export function getPostgresSchema(
dims: number = DEFAULT_EMBEDDING_DIMENSIONS,
model: string = DEFAULT_EMBEDDING_MODEL,
@@ -1087,12 +1061,7 @@ export class PostgresEngine implements BrainEngine {
});
}
async putPage(
slug: string,
page: PageInput,
opts?: { sourceId?: string; signal?: AbortSignal },
): Promise<Page> {
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
slug = validateSlug(slug);
const sql = this.sql;
const hash = page.content_hash || contentHash(page);
@@ -1127,7 +1096,7 @@ export class PostgresEngine implements BrainEngine {
const sourceUri = page.source_uri ?? null;
const ingestedVia = page.ingested_via ?? null;
const ingestedAt = (sourceKind || sourceUri || ingestedVia) ? new Date() : null;
const pending = sql`
const rows = await sql`
INSERT INTO pages (source_id, slug, type, page_kind, title, compiled_truth, timeline, frontmatter, content_hash, updated_at, effective_date, effective_date_source, import_filename, chunker_version, source_path, source_kind, source_uri, ingested_via, ingested_at)
VALUES (${sourceId}, ${slug}, ${page.type}, ${pageKind}, ${page.title}, ${page.compiled_truth}, ${page.timeline || ''}, ${sql.json(frontmatter as Parameters<typeof sql.json>[0])}, ${hash}, now(), ${effectiveDate}, ${effectiveDateSource}, ${importFilename}, COALESCE(${chunkerVersion}::smallint, ${MARKDOWN_CHUNKER_VERSION}), ${sourcePath}, ${sourceKind}, ${sourceUri}, ${ingestedVia}, ${ingestedAt})
ON CONFLICT (source_id, slug) DO UPDATE SET
@@ -1150,22 +1119,6 @@ export class PostgresEngine implements BrainEngine {
ingested_at = COALESCE(EXCLUDED.ingested_at, pages.ingested_at)
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at
`;
// #2750: cancel the in-flight statement when the caller's deadline fires,
// same .cancel() wiring as runUnsafe (postgres.js pending queries).
if (opts?.signal) {
const signal = opts.signal;
const onAbort = () => {
try { (pending as unknown as { cancel?: () => void }).cancel?.(); } catch { /* best-effort */ }
};
signal.addEventListener('abort', onAbort, { once: true });
try {
const rows = await pending;
return rowToPage(rows[0]);
} finally {
signal.removeEventListener('abort', onAbort);
}
}
const rows = await pending;
return rowToPage(rows[0]);
}
@@ -5854,16 +5807,11 @@ export class PostgresEngine implements BrainEngine {
params?: unknown[],
opts?: { signal?: AbortSignal },
): Promise<T[]> {
// #2750: an already-fired signal short-circuits BEFORE any pool routing,
// and the direct-pool acquisition itself is signal-bounded — under pooler
// exhaustion `ddl()` can stall indefinitely, which used to make even a
// "bounded" lock release hang past its caller's deadline.
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
// Inside an open transaction, _sql is the reserved tx connection (set via
// defineProperty in transaction()); never reroute off it.
const inTransaction = this._sql !== null && this.connectionManager?.peekReadPool() !== this._sql;
const conn = (!inTransaction && this.connectionManager?.isDualPoolActive())
? await waitForSignal(this.connectionManager.ddl(), opts?.signal)
? await this.connectionManager.ddl()
: this.sql;
return this.runUnsafe<T>(conn, sql, params, opts);
}
@@ -17,7 +17,6 @@ import { runPhaseExtractAtoms, parseAtomsResponse } from '../../src/core/cycle/e
import { runPhaseSynthesizeConcepts } from '../../src/core/cycle/synthesize-concepts.ts';
import { resetPgliteState } from '../helpers/reset-pglite.ts';
import type { ChatResult, ChatOpts } from '../../src/core/ai/gateway.ts';
import type { BrainEngine } from '../../src/core/engine.ts';
let engine: PGLiteEngine;
@@ -178,180 +177,6 @@ describe('v0.41 T5: runPhaseExtractAtoms via stubbed chat', () => {
expect((result.details?.failures as unknown[]).length).toBe(1);
});
// ── #2750: caller deadline bounds the phase ────────────────────────────
test('caller deadline aborts a hung chat before processing the next item', async () => {
let calls = 0;
const chat = async (opts: ChatOpts) => {
calls++;
return await new Promise<never>((_resolve, reject) => {
const signal = opts.abortSignal;
if (!signal) return reject(new Error('missing abort signal'));
if (signal.aborted) return reject(signal.reason);
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
});
};
const started = Date.now();
const result = await runPhaseExtractAtoms(engine, {
_transcripts: [
{ filePath: '/hung.txt', content: 'a', contentHash: 'hung-a' },
{ filePath: '/never.txt', content: 'b', contentHash: 'hung-b' },
],
_pages: [],
_chat: chat as typeof import('../../src/core/ai/gateway.ts').chat,
abortSignal: AbortSignal.timeout(25),
});
expect(Date.now() - started).toBeLessThan(2_000);
expect(calls).toBe(1);
expect(result.status).toBe('ok');
expect(result.details?.deadline_aborted).toBe(true);
expect(result.details?.atoms_extracted).toBe(0);
expect(result.details?.failures).toEqual([]);
});
test('billable chat usage is counted when the deadline fires as the response resolves', async () => {
const controller = new AbortController();
const chat = async (opts: ChatOpts): Promise<ChatResult> => {
controller.abort(new DOMException('deadline', 'TimeoutError'));
return stubChat(`[{"title":"late","atom_type":"insight","body":"b"}]`, {
input_tokens: 1_000,
output_tokens: 500,
})(opts);
};
const result = await runPhaseExtractAtoms(engine, {
_transcripts: [{ filePath: '/late.txt', content: 'a', contentHash: 'late' }],
_pages: [],
_chat: chat,
abortSignal: controller.signal,
});
expect(result.details?.deadline_aborted).toBe(true);
expect(Number(result.details?.estimated_spend_usd)).toBeGreaterThan(0);
expect(result.details?.atoms_extracted).toBe(0);
});
test('deadline after partial progress still writes receipt and incomplete rollup', async () => {
const controller = new AbortController();
let calls = 0;
let notifySecondChat!: () => void;
const secondChatStarted = new Promise<void>((resolve) => { notifySecondChat = resolve; });
const chat = async (opts: ChatOpts): Promise<ChatResult> => {
calls++;
if (calls === 1) {
return stubChat(`[{"title":"committed","atom_type":"insight","body":"b"}]`)(opts);
}
notifySecondChat();
return await new Promise<never>((_resolve, reject) => {
const signal = opts.abortSignal;
if (!signal) return reject(new Error('missing abort signal'));
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
});
};
const pending = runPhaseExtractAtoms(engine, {
_transcripts: [
{ filePath: '/committed.txt', content: 'a', contentHash: 'committed-a' },
{ filePath: '/hung.txt', content: 'b', contentHash: 'hung-b' },
],
_pages: [],
_chat: chat,
abortSignal: controller.signal,
});
await secondChatStarted;
controller.abort(new DOMException('deadline', 'TimeoutError'));
const result = await pending;
const atoms = await engine.executeRaw<{ n: number }>(
`SELECT COUNT(*)::int AS n FROM pages WHERE type = 'atom'`,
);
const receipts = await engine.executeRaw<{ n: number }>(
`SELECT COUNT(*)::int AS n FROM pages WHERE type = 'extract_receipt'`,
);
const rollups = await engine.executeRaw<{
cost_usd: string | number;
round_completed_count: string | number;
}>(
`SELECT cost_usd, round_completed_count
FROM extract_rollup_7d
WHERE kind = 'atoms' AND source_id = 'default'`,
);
expect(result.details?.deadline_aborted).toBe(true);
expect(atoms[0].n).toBe(1);
expect(receipts[0].n).toBe(1);
expect(Number(rollups[0].cost_usd)).toBeGreaterThan(0);
expect(Number(rollups[0].round_completed_count)).toBe(0);
});
test('bookkeeping runs on a fresh grace signal, not the fired work deadline', async () => {
const controller = new AbortController();
let putCalls = 0;
let receiptSignal: AbortSignal | undefined;
let rollupSignal: AbortSignal | undefined;
const signalAwareEngine = {
executeRaw: async (sql: string, _params?: unknown[], opts?: { signal?: AbortSignal }) => {
if (sql.includes('INSERT INTO extract_rollup_7d')) rollupSignal = opts?.signal;
return [];
},
putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
putCalls++;
if (putCalls === 1) {
// Atom write in flight; the work deadline fires before bookkeeping.
controller.abort(new DOMException('work deadline', 'TimeoutError'));
} else {
receiptSignal = opts?.signal;
}
return {};
},
} as unknown as BrainEngine;
const result = await runPhaseExtractAtoms(signalAwareEngine, {
_transcripts: [{ filePath: '/one.txt', content: 'a', contentHash: 'one' }],
_pages: [],
_chat: stubChat(`[{"title":"one","atom_type":"insight","body":"b"}]`),
abortSignal: controller.signal,
});
expect(result.details?.atoms_extracted).toBe(1);
expect(putCalls).toBe(2); // atom write + receipt write
expect(receiptSignal).toBeDefined();
expect(receiptSignal).not.toBe(controller.signal);
expect(receiptSignal?.aborted).toBe(false);
expect(rollupSignal).toBe(receiptSignal);
});
test('caller deadline cancels a hung atom write and stops the phase', async () => {
const controller = new AbortController();
let notifyWriteStarted!: () => void;
const writeStarted = new Promise<void>((resolve) => { notifyWriteStarted = resolve; });
let writeCalls = 0;
const signalAwareEngine = {
executeRaw: async () => [],
putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
writeCalls++;
notifyWriteStarted();
return await new Promise<never>((_resolve, reject) => {
const signal = opts?.signal;
if (!signal) return reject(new Error('missing abort signal'));
if (signal.aborted) return reject(signal.reason);
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
});
},
} as unknown as BrainEngine;
const pending = runPhaseExtractAtoms(signalAwareEngine, {
_transcripts: [{ filePath: '/hung-write.txt', content: 'a', contentHash: 'hung-write' }],
_pages: [],
_chat: stubChat(`[{"title":"hung write","atom_type":"insight","body":"b"}]`),
abortSignal: controller.signal,
});
await writeStarted;
controller.abort(new DOMException('deadline', 'TimeoutError'));
const result = await pending;
expect(writeCalls).toBe(1);
expect(result.details?.deadline_aborted).toBe(true);
expect(result.details?.atoms_extracted).toBe(0);
});
// v0.41.2.1 regression case (D9 #14 wording): with _pages:[] and same
// _transcripts, all PRE-EXISTING PhaseResult.details fields match
// pre-fix values byte-for-byte. The new fields (pages_processed,
+9 -131
View File
@@ -43,135 +43,26 @@ describe('runExtractAtomsDrain (issue #1678)', () => {
expect(batches).toBe(3);
});
it('stops at the wallclock window; remaining is unknown (no post-window count)', async () => {
// Each batch consumes 60ms of the 100ms window: two batches fit, the
// third boundary check sees 120 ≥ 100 and stops. #2750: after the window
// elapses the final countRemaining is SKIPPED (it would overrun the
// window), so remaining reports null.
let now = 0;
it('stops at the wallclock window with remaining > 0', async () => {
// SYNC stepping clock: now() #1 sets deadline (0+100=100); the while-check
// then sees 50, 50 (two batches), then 999999 → past deadline → stop.
const times = [0, 50, 50, 999_999];
let ti = 0;
const now = () => times[Math.min(ti++, times.length - 1)];
const result = await runExtractAtomsDrain(
{
withLock: passThroughLock,
countRemaining: async () => 5, // never drains
runBatch: async () => {
now += 60;
return { extracted: 1, skipped: 0 };
},
now: () => now,
runBatch: async () => ({ extracted: 1, skipped: 0 }),
now,
},
{ windowMs: 100 },
);
expect(result.stopped).toBe('window');
expect(result.remaining).toBeNull();
expect(result.remaining).toBe(5);
expect(result.batches).toBe(2);
});
it('passes one drain-level deadline signal into count and batch', async () => {
const seen: AbortSignal[] = [];
const controller = new AbortController();
let now = 0;
const result = await runExtractAtomsDrain(
{
withLock: passThroughLock,
countRemaining: async (signal) => {
seen.push(signal);
return 5;
},
runBatch: async (signal) => {
seen.push(signal);
now = 100;
return { extracted: 1, skipped: 0 };
},
now: () => now,
},
{ windowMs: 100, abortSignal: controller.signal },
);
expect(result.stopped).toBe('window');
expect(result.batches).toBe(1);
expect(seen.length).toBe(2);
expect(seen[0]).toBe(seen[1]);
// Combined (timeout + external) signal, not the raw external one.
expect(seen[0]).not.toBe(controller.signal);
});
it('aborts a hung backlog count at the window deadline and releases the lock', async () => {
let released = false;
const result = await runExtractAtomsDrain(
{
withLock: async (work) => {
try { return await work(); }
finally { released = true; }
},
// Hangs until the drain's real-time deadline signal fires (10ms).
countRemaining: (signal) => new Promise((_resolve, reject) => {
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
}),
runBatch: async () => ({ extracted: 0, skipped: 0 }),
now: () => 0, // injected clock never advances — the SIGNAL must save us
},
{ windowMs: 10 },
);
expect(result.stopped).toBe('window');
expect(result.remaining).toBeNull();
expect(released).toBe(true);
});
it('rethrows external cancellation after releasing the lock', async () => {
const controller = new AbortController();
let released = false;
const pending = runExtractAtomsDrain(
{
withLock: async (work) => {
try { return await work(); }
finally { released = true; }
},
countRemaining: (signal) => new Promise((_resolve, reject) => {
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
}),
runBatch: async () => ({ extracted: 0, skipped: 0 }),
now: () => 0,
},
{ windowMs: 1_000_000, abortSignal: controller.signal },
);
controller.abort(new DOMException('worker timeout', 'AbortError'));
await expect(pending).rejects.toThrow('worker timeout');
expect(released).toBe(true);
});
it('classifies a deadline-exhausted zero-progress batch as window, not no_progress', async () => {
let now = 0;
const result = await runExtractAtomsDrain(
{
withLock: passThroughLock,
countRemaining: async () => 5,
runBatch: async () => {
now = 100; // batch consumed the whole window and returned nothing
return { extracted: 0, skipped: 0 };
},
now: () => now,
},
{ windowMs: 100 },
);
expect(result.stopped).toBe('window');
expect(result.batches).toBe(1);
});
it('bounds a hung lock acquisition with the drain deadline signal', async () => {
const started = Date.now();
await expect(runExtractAtomsDrain(
{
withLock: (_work, signal) => new Promise((_resolve, reject) => {
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
}),
countRemaining: async () => 1,
runBatch: async () => ({ extracted: 0, skipped: 0 }),
now: Date.now,
},
{ windowMs: 10 },
)).rejects.toThrow();
expect(Date.now() - started).toBeLessThan(1_000);
});
it('stops on a zero-progress batch (no hot loop)', async () => {
let batches = 0;
const result = await runExtractAtomsDrain(
@@ -242,17 +133,4 @@ describe('shared wiring helper holds the cycle lock (5A)', () => {
expect(src).toContain('cycleLockIdFor(opts.sourceId)');
expect(src).toContain('withRefreshingLock(engine, lockId');
});
// #2750: the deadline signal must reach the phase, the backlog count, AND
// the lock wrapper — and the transcript path (brainDir) must stay wired
// exactly as the routine callers expect (PR #2752 takeover reverted its
// unsanctioned transcript-suppression scope change).
it('threads the drain deadline signal through phase, count, and lock', () => {
const jobsSrc = readFileSync(join(import.meta.dir, '../src/commands/jobs.ts'), 'utf8');
expect(src).toContain('abortSignal: signal');
expect(src).toContain('countExtractAtomsBacklog(engine, extractionSourceId, signal)');
expect(src).toContain('brainDir: opts.brainDir');
expect(src).not.toContain('_transcripts');
expect(jobsSrc).toContain('abortSignal: job.signal');
});
});
+6 -9
View File
@@ -24,18 +24,15 @@ import type { BrainEngine } from '../../src/core/engine.ts';
// Mock engine: healthCheck() calls engine.executeRaw; return empty rows so
// the query path exercises without needing Postgres.
//
// #1849: start() acquires the queue-scoped DB singleton lock via
// tryAcquireDbLock. #2750 routed the acquire upsert through engine.executeRaw
// (signal-boundable) and release through engine.executeRawDirect, so the
// stub returns a single row from the lock upsert (length 1 → acquired) and
// empty rows everywhere else. Each spawned runner is a fresh process, so
// there's no cross-test lock state to clean up.
// #1849: start() now acquires the queue-scoped DB singleton lock via
// tryAcquireDbLock, which uses the postgres `sql` tagged-template escape hatch.
// The stub returns a single row from every call so acquire succeeds (length 1
// → acquired) and refresh/release are no-ops. Each spawned runner is a fresh
// process, so there's no cross-test lock state to clean up.
const sqlStub = (..._args: unknown[]) => Promise.resolve([{ id: 'supervisor-lock' }]);
const mockEngine: Partial<BrainEngine> = {
kind: 'postgres' as const,
executeRaw: async (query: string) =>
query.includes('gbrain_cycle_locks') ? [{ id: 'supervisor-lock' }] : [],
executeRawDirect: async () => [],
executeRaw: async () => [],
sql: sqlStub,
} as unknown as BrainEngine;
+1 -26
View File
@@ -98,39 +98,14 @@ describe('PostgresEngine.executeRawDirect — routing decision (PR #1816)', () =
});
test('already-aborted signal short-circuits with AbortError before routing the query', async () => {
let unsafeCalls = 0;
let ddlCalls = 0;
const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
const readConn = fakeSql('read');
const directConn = fakeSql('direct');
const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
e.connectionManager.ddl = async () => { ddlCalls++; return directConn; };
const ac = new AbortController();
ac.abort();
await expect(
engine.executeRawDirect('UPDATE minion_jobs SET x=1', [], { signal: ac.signal }),
).rejects.toThrow(/abort/i);
// #2750: short-circuits BEFORE pool routing — no ddl(), no unsafe().
expect(ddlCalls).toBe(0);
expect(unsafeCalls).toBe(0);
});
test('#2750: signal bounds a stalled direct-pool acquisition before unsafe starts', async () => {
let unsafeCalls = 0;
const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
const directConn = fakeSql('direct');
const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
e.connectionManager.ddl = () => new Promise<FakeSql>(() => {}); // pooler exhausted: never resolves
const started = Date.now();
await expect(engine.executeRawDirect(
'DELETE FROM gbrain_cycle_locks',
[],
{ signal: AbortSignal.timeout(10) },
)).rejects.toThrow(/abort/i);
expect(Date.now() - started).toBeLessThan(1_000);
expect(unsafeCalls).toBe(0);
});
});
+23
View File
@@ -16,6 +16,7 @@
*/
import { describe, test, expect } from 'bun:test';
import { createHmac } from 'node:crypto';
import { readFileSync } from 'node:fs';
import { safeHexEqual } from '../src/core/timing-safe.ts';
const GITHUB_SECRET = 'super-secret-webhook-key';
@@ -123,3 +124,25 @@ describe('Branch ref construction (D5)', () => {
expect(pushedRef === `refs/heads/${trackedBranch}`).toBe(false);
});
});
describe('Webhook sync job extraction contract (#2849)', () => {
test('opts into extraction before the pushed commit is consumed', () => {
const serveSource = readFileSync(
new URL('../src/commands/serve-http.ts', import.meta.url),
'utf8',
);
const routeStart = serveSource.indexOf("'/webhooks/github'");
const queueStart = serveSource.indexOf('const job = await queue.add(', routeStart);
const responseStart = serveSource.indexOf('res.status(202)', queueStart);
expect(routeStart).toBeGreaterThanOrEqual(0);
expect(queueStart).toBeGreaterThan(routeStart);
expect(responseStart).toBeGreaterThan(queueStart);
const routeSource = serveSource.slice(queueStart, responseStart);
const payload = routeSource.match(
/queue\.add\(\s*'sync',\s*\{([\s\S]*?)\}\s*,\s*\{/,
);
expect(payload).not.toBeNull();
expect(payload?.[1]).toMatch(/\bnoExtract:\s*false\b/);
});
});
@@ -0,0 +1,130 @@
/**
* #2849 large-sync extract deferral queues an `extract --stale` follow-up.
*
* performSync's incremental path skips inline link/timeline extraction when
* totalChanges > 100 (the #1794 large-sync deferral), leaving
* links_extracted_at unstamped. Pre-fix, a standalone sync job (webhook push,
* `gbrain sync trigger`) had NOTHING behind it to sweep those pages the
* autopilot cycle's extract phase only walks that cycle's changedSlugs so a
* large webhook push left extraction permanently stale until a manual
* `gbrain extract --stale`.
*
* Pins:
* (a) performSync surfaces `extractDeferred: true` on the >100 branch and
* leaves the pages unstamped/unlinked.
* (b) the `sync` job handler queues an `extract` job with
* { stale: true, sourceId? } when extractDeferred is set.
* (c) the `extract` handler's stale mode actually sweeps: links created +
* watermark stamped (end-to-end recovery, no manual step).
*
* Marked .serial.test.ts spawns git subprocesses + shares one PGLite engine.
*/
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from 'fs';
import { execSync } from 'child_process';
import { tmpdir } from 'os';
import { join } from 'path';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { MinionWorker } from '../src/core/minions/worker.ts';
import { MinionQueue } from '../src/core/minions/queue.ts';
import { registerBuiltinHandlers } from '../src/commands/jobs.ts';
let engine: PGLiteEngine;
let worker: MinionWorker;
let repoPath: string;
function git(cmd: string): void { execSync(cmd, { cwd: repoPath, stdio: 'pipe' }); }
describe('#2849 — large sync defers extract and queues a stale sweep', () => {
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
worker = new MinionWorker(engine, { queue: 'test' });
await registerBuiltinHandlers(worker, engine, { quiet: true });
repoPath = mkdtempSync(join(tmpdir(), 'gbrain-large-defer-'));
git('git init');
git('git config user.email "t@t.com"');
git('git config user.name "T"');
mkdirSync(join(repoPath, 'people'), { recursive: true });
mkdirSync(join(repoPath, 'notes'), { recursive: true });
writeFileSync(join(repoPath, 'people/alice.md'), [
'---', 'type: person', 'title: Alice', '---', '', 'Alice is a founder.',
].join('\n'));
git('git add -A && git commit -m "initial"');
// Seed: full first sync imports the anchor page + sets last_commit.
const { performSync } = await import('../src/commands/sync.ts');
await performSync(engine, { repoPath, full: true, noPull: true, noEmbed: true });
// Second commit: 101 new pages → incremental totalChanges > 100.
for (let i = 0; i < 101; i++) {
writeFileSync(join(repoPath, `notes/n${i}.md`), [
'---', 'type: note', `title: Note ${i}`, '---', '',
`[Alice](people/alice) appears in note ${i}.`,
].join('\n'));
}
git('git add -A && git commit -m "add 101 pages"');
}, 120_000);
afterAll(async () => {
if (repoPath) rmSync(repoPath, { recursive: true, force: true });
if (engine) await engine.disconnect();
}, 60_000);
test('sync handler defers inline extract and queues extract{stale} follow-up; stale sweep recovers', async () => {
const syncHandler = (worker as unknown as { handlers: Map<string, (job: unknown) => Promise<unknown>> })
.handlers.get('sync');
expect(syncHandler).toBeDefined();
// Same payload shape the webhook submits (minus embed backfill noise).
const result = await syncHandler!({
data: { repoPath, noExtract: false, noPull: true, auto_embed_backfill: false },
signal: { aborted: false },
updateProgress: async () => {},
}) as { status: string; extractDeferred?: boolean; extract_stale_job_id?: number | null };
expect(result.status).toBe('synced');
// (a) inline extract was deferred, pages left stale.
expect(result.extractDeferred).toBe(true);
const staleBefore = await engine.countStalePagesForExtraction();
expect(staleBefore).toBeGreaterThan(100);
expect(await engine.getLinks('notes/n0')).toHaveLength(0);
// (b) a follow-up extract job with stale:true was queued.
expect(result.extract_stale_job_id).toBeGreaterThan(0);
const queue = new MinionQueue(engine);
const extractJobs = await queue.getJobs({ name: 'extract', limit: 5 });
expect(extractJobs.length).toBe(1);
expect((extractJobs[0].data as { stale: boolean }).stale).toBe(true);
// (c) running the extract handler's stale mode recovers: links + stamps.
const extractHandler = (worker as unknown as { handlers: Map<string, (job: unknown) => Promise<unknown>> })
.handlers.get('extract');
await extractHandler!({
data: extractJobs[0].data,
signal: { aborted: false },
updateProgress: async () => {},
});
const links = await engine.getLinks('notes/n0');
expect(links.some(l => l.to_slug === 'people/alice')).toBe(true);
const rows = await engine.executeRaw<{ links_extracted_at: string | null }>(
`SELECT links_extracted_at FROM pages WHERE slug = 'notes/n0'`,
);
expect(rows[0]?.links_extracted_at).not.toBeNull();
}, 180_000);
test('sub-threshold sync does NOT set extractDeferred (no spurious follow-up)', async () => {
// One more small commit → inline extract path, no deferral.
writeFileSync(join(repoPath, 'notes/small.md'), [
'---', 'type: note', 'title: Small', '---', '', 'No big deal.',
].join('\n'));
git('git add -A && git commit -m "one small page"');
const { performSync } = await import('../src/commands/sync.ts');
const result = await performSync(engine, { repoPath, noPull: true, noEmbed: true });
expect(result.status).toBe('synced');
expect(result.extractDeferred).toBeFalsy();
}, 60_000);
});
+4
View File
@@ -100,6 +100,10 @@ describe('runSyncTrigger', () => {
const job = jobs[0];
expect(job.priority).toBe(-10);
expect((job.data as { sourceId: string }).sourceId).toBe('default');
// #2849: opt in to inline extraction — the standalone sync handler
// defaults noExtract to TRUE, which would leave triggered syncs
// extraction-stale.
expect((job.data as { noExtract: boolean }).noExtract).toBe(false);
expect((job.data as { auto_embed_backfill: boolean }).auto_embed_backfill).toBe(true);
});