Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 62bd7fb3b7 fix(schema): block scalars keep '#' as literal content
Inside a YAML block scalar '#' is content, not a comment; parseBlockScalar
was routing lines through stripComment/isBlank, truncating descriptions
like 'see issue #2029' and blanking comment-looking lines. Use the raw
line inside the scalar. Adds a pinning test.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 12:01:58 -07:00
Garry TanandClaude Fable 5 733fcd633a test(schema): point bundled-registry test at bundled.ts source of truth
The bundled pack list moved from load-active.ts to bundled.ts in the
truthful-inspection refactor; the T4 registry test still grepped
load-active.ts source. Assert BUNDLED_PACK_NAMES directly instead.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:55:16 -07:00
97e716b01f fix(minions): subagent default client resolves config-stored Anthropic key (#2048)
The legacy subagent path constructed a bare new Anthropic() (env-only), so
launchd/MCP workers whose key lives in gbrain config (anthropic_api_key)
failed auth. anthropic-key.ts now exports resolveAnthropicKey() (env first,
then config; hasAnthropicKey delegates) and makeSubagentHandler passes it as
apiKey.

Partial takeover of #2048 — only the auth patch; the path patches were
superseded by the outputRoot mechanism (#2415).

Co-authored-by: JiraiyaETH <JiraiyaETH@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:31:37 -07:00
ff737e4345 fix(schema): make bundled pack inspection truthful (#2029)
Two live bugs:
- parseYamlMini had no block-scalar support, so a 'description: |' swallowed
  every following top-level key — the active gbrain-recommended pack loaded
  with 0 page types. Add parseBlockScalar for |/|-/|+ and >/>-/>+ in both
  mapping and sequence-sibling positions.
- The bundled-pack list was hand-copied in three places (operations.ts had 2
  names, mutate.ts had 3, load-active.ts had 7). New single registry
  src/core/schema-pack/bundled.ts carries all 7 shipped packs; every
  consumer derives from it.

Takeover of #2029, rebased onto master (schema.ts hunks already landed).

Co-authored-by: JiraiyaETH <JiraiyaETH@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:31:37 -07:00
26 changed files with 289 additions and 654 deletions
-2
View File
@@ -2059,8 +2059,6 @@ 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) {
+13 -3
View File
@@ -18,12 +18,22 @@
import { loadConfig } from '../config.ts';
export function hasAnthropicKey(): boolean {
if (process.env.ANTHROPIC_API_KEY) return true;
return resolveAnthropicKey() !== undefined;
}
/**
* Resolve the actual key value: env first, then the gbrain config file.
* Callers constructing an Anthropic client directly (e.g. the legacy
* subagent path) must pass this as `apiKey` — a bare `new Anthropic()`
* only sees env, so launchd/MCP workers with config-stored keys fail.
*/
export function resolveAnthropicKey(): string | undefined {
if (process.env.ANTHROPIC_API_KEY) return process.env.ANTHROPIC_API_KEY;
try {
const cfg = loadConfig();
if (cfg?.anthropic_api_key) return true;
if (cfg?.anthropic_api_key) return cfg.anthropic_api_key;
} catch {
// loadConfig may throw on first-run installs; treat as no key available.
}
return false;
return undefined;
}
+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);
+5 -1
View File
@@ -48,6 +48,7 @@ import {
logSubagentHeartbeat,
} from './subagent-audit.ts';
import { resolveModel, isAnthropicProvider, TIER_DEFAULTS } from '../../model-config.ts';
import { resolveAnthropicKey } from '../../ai/anthropic-key.ts';
import { buildSystemPrompt, DEFAULT_SUBAGENT_SYSTEM } from '../system-prompt.ts';
import { toolLoop as gatewayToolLoop } from '../../ai/gateway.ts';
import type { ChatToolDef, ChatMessage, ChatBlock, ChatResult, ToolHandler } from '../../ai/gateway.ts';
@@ -186,7 +187,10 @@ export function makeSubagentHandler(deps: SubagentDeps) {
// lives at sdk.messages.create. Assigning sdk.messages directly gets the
// right object; JS method-call semantics preserve `this` at the call
// site (subagent.ts invokes client.create(...) with client === sdk.messages).
const makeAnthropic = deps.makeAnthropic ?? (() => new Anthropic());
// Resolve the key env-first, then config (anthropic_api_key) — a bare
// new Anthropic() only reads env, so launchd/MCP workers whose key lives
// in the gbrain config file would fail auth (#2048).
const makeAnthropic = deps.makeAnthropic ?? (() => new Anthropic({ apiKey: resolveAnthropicKey() }));
const client: MessagesClient = deps.client ?? makeAnthropic().messages;
const config = deps.config ?? loadConfig() ?? ({ engine: 'postgres' } as GBrainConfig);
const rateLeaseKey = deps.rateLeaseKey ?? DEFAULT_RATE_KEY;
+2 -1
View File
@@ -4562,7 +4562,8 @@ const list_schema_packs: Operation = {
const { existsSync, readdirSync } = await import('node:fs');
const { join } = await import('node:path');
const { gbrainPath } = await import('./config.ts');
const bundled = ['gbrain-base', 'gbrain-recommended'];
const { BUNDLED_PACK_NAMES } = await import('./schema-pack/bundled.ts');
const bundled = [...BUNDLED_PACK_NAMES];
const installedDir = gbrainPath('schema-packs');
const installed: string[] = [];
if (existsSync(installedDir)) {
+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);
}
+24
View File
@@ -0,0 +1,24 @@
// Bundled schema-pack registry — single source of truth for the packs that
// ship in src/core/schema-pack/base/. Keep every bundled-pack consumer
// (CLI/MCP inspection, active-pack loading, mutation guards, upgrade
// discovery) on this one list so they cannot drift.
//
// v0.39 T8 — gbrain-base + gbrain-recommended.
// v0.41 T4 — lens packs: creator, investor, engineer, everything (meta-pack).
// v0.42 type-unification — gbrain-base-v2, the 15-type canonical successor.
export const BUNDLED_PACK_NAMES = [
'gbrain-base',
'gbrain-recommended',
'gbrain-creator',
'gbrain-investor',
'gbrain-engineer',
'gbrain-everything',
'gbrain-base-v2',
] as const;
export type BundledPackName = typeof BUNDLED_PACK_NAMES[number];
export function isBundledPackName(name: string): name is BundledPackName {
return (BUNDLED_PACK_NAMES as readonly string[]).includes(name);
}
+2 -22
View File
@@ -37,6 +37,7 @@ import {
type ResolutionInput,
type ResolutionResult,
} from './registry.ts';
import { isBundledPackName } from './bundled.ts';
/**
* Inputs the caller (operations.ts handler / engine query path) provides.
@@ -92,28 +93,7 @@ export function _resetPackLocatorForTests(): void {
* throwing UnknownPackError with a paste-ready install hint.
*/
function defaultPackLocator(name: string): string | null {
// v0.39 T8 — bundled packs registry. gbrain-base + gbrain-recommended
// ship in src/core/schema-pack/base/. Add a new entry here to bundle
// additional canonical packs.
//
// v0.41 T4 — lens packs join the bundle: creator (atoms + concepts +
// extract_atoms/synthesize_concepts phases), investor (theses + bet
// resolution + 3 calibration domains), engineer (gstack-learnings bridge
// + 3 calibration domains), everything (meta-pack stacking all three
// via extends + borrow_from). Each ships as a real YAML at base/<name>.yaml.
const BUNDLED: ReadonlyArray<string> = [
'gbrain-base',
'gbrain-recommended',
'gbrain-creator',
'gbrain-investor',
'gbrain-engineer',
'gbrain-everything',
// v0.42 type-unification: 15-type canonical successor to gbrain-base.
// Ships as install default (Lane E T17) + via gbrain onboard pack
// upgrade flow (the unify-types Minion handler).
'gbrain-base-v2',
];
if (BUNDLED.includes(name)) {
if (isBundledPackName(name)) {
// Resolve bundled YAML relative to this source file. Works in both
// direct-bun execution and bun --compile binaries.
const here = dirname(fileURLToPath(import.meta.url));
+31
View File
@@ -159,6 +159,29 @@ export function parseYamlMini(content: string): unknown {
return parseMapping(baseIndent);
}
function parseBlockScalar(parentIndent: number, folded: boolean): string {
const contentIndent = parentIndent + 2;
const out: string[] = [];
while (i < lines.length) {
const raw = lines[i];
// Inside a block scalar everything is literal content — '#' is NOT a
// comment here, so use the raw line (no stripComment / isBlank).
if (raw.trim() === '') {
out.push('');
i++;
continue;
}
const indent = indentOf(raw);
if (indent <= parentIndent) break;
out.push(raw.slice(Math.min(contentIndent, indent)));
i++;
}
if (folded) {
return out.join(' ').replace(/\s+$/u, '');
}
return out.join('\n').replace(/\n+$/u, '');
}
function parseSequence(baseIndent: number): unknown[] {
const result: unknown[] = [];
while (i < lines.length) {
@@ -227,6 +250,10 @@ export function parseYamlMini(content: string): unknown {
i++;
if (rest2 === '') {
map[key2] = parseBlock(nextIndent + 2);
} else if (rest2 === '|' || rest2 === '|-' || rest2 === '|+') {
map[key2] = parseBlockScalar(nextIndent, false);
} else if (rest2 === '>' || rest2 === '>-' || rest2 === '>+') {
map[key2] = parseBlockScalar(nextIndent, true);
} else {
map[key2] = parseScalar(rest2);
}
@@ -257,6 +284,10 @@ export function parseYamlMini(content: string): unknown {
i++;
if (rest === '') {
result[key] = parseBlock(indent + 2);
} else if (rest === '|' || rest === '|-' || rest === '|+') {
result[key] = parseBlockScalar(indent, false);
} else if (rest === '>' || rest === '>-' || rest === '>+') {
result[key] = parseBlockScalar(indent, true);
} else {
result[key] = parseScalar(rest);
}
+2 -1
View File
@@ -65,6 +65,7 @@ import { invalidateQueryCache } from './query-cache-invalidator.ts';
import { logMutationFailure, logMutationSuccess, type MutationActor, type MutationOp } from './mutate-audit.ts';
import { runFilePlaneLintRules } from './lint-rules.ts';
import { withPackLock, type PackLockOpts } from './pack-lock.ts';
import { BUNDLED_PACK_NAMES as BUNDLED_PACK_NAME_LIST } from './bundled.ts';
import type { BrainEngine } from '../engine.ts';
export type PackFileFormat = 'json' | 'yaml';
@@ -93,7 +94,7 @@ export class SchemaPackMutationError extends Error {
}
}
export const BUNDLED_PACK_NAMES = new Set(['gbrain-base', 'gbrain-recommended', 'gbrain-base-v2']);
export const BUNDLED_PACK_NAMES = new Set<string>(BUNDLED_PACK_NAME_LIST);
export interface MutateResult {
/** Pack name that was mutated. */
+33 -1
View File
@@ -10,7 +10,7 @@ import { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { withEnv } from '../helpers/with-env.ts';
import { hasAnthropicKey } from '../../src/core/ai/anthropic-key.ts';
import { hasAnthropicKey, resolveAnthropicKey } from '../../src/core/ai/anthropic-key.ts';
const tmpDirs: string[] = [];
function freshHome(withConfig?: Record<string, unknown>): string {
@@ -62,3 +62,35 @@ describe('hasAnthropicKey', () => {
);
});
});
describe('resolveAnthropicKey (#2048 — subagent config-key auth)', () => {
test('env wins over config', async () => {
const home = freshHome({ anthropic_api_key: 'sk-from-config' });
await withEnv(
{ ANTHROPIC_API_KEY: 'sk-from-env', GBRAIN_HOME: home, DATABASE_URL: undefined, GBRAIN_DATABASE_URL: undefined },
async () => {
expect(resolveAnthropicKey()).toBe('sk-from-env');
},
);
});
test('config key returned when env unset', async () => {
const home = freshHome({ anthropic_api_key: 'sk-from-config' });
await withEnv(
{ ANTHROPIC_API_KEY: undefined, GBRAIN_HOME: home, DATABASE_URL: undefined, GBRAIN_DATABASE_URL: undefined },
async () => {
expect(resolveAnthropicKey()).toBe('sk-from-config');
},
);
});
test('neither → undefined', async () => {
const home = freshHome();
await withEnv(
{ ANTHROPIC_API_KEY: undefined, GBRAIN_HOME: home, DATABASE_URL: undefined, GBRAIN_DATABASE_URL: undefined },
async () => {
expect(resolveAnthropicKey()).toBeUndefined();
},
);
});
});
@@ -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;
+6 -6
View File
@@ -55,13 +55,13 @@ describe('v0.41 T4: all 4 bundled lens packs parse cleanly', () => {
});
describe('v0.41 T4: bundled registry includes lens packs', () => {
test('load-active.ts BUNDLED array source includes the 4 lens pack names', () => {
const loadActiveSrc = readFileSync(
join(here, '..', 'src', 'core', 'schema-pack', 'load-active.ts'),
'utf-8',
);
test('BUNDLED_PACK_NAMES includes the 4 lens pack names', async () => {
// The bundled list moved from load-active.ts to bundled.ts (the
// single source of truth); assert the array directly instead of
// grepping source text.
const { BUNDLED_PACK_NAMES } = await import('../src/core/schema-pack/bundled.ts');
for (const name of PACK_NAMES) {
expect(loadActiveSrc).toContain(`'${name}'`);
expect(BUNDLED_PACK_NAMES).toContain(name);
}
});
});
+3
View File
@@ -149,6 +149,9 @@ describe('list_schema_packs', () => {
seedPack('mine');
const result = await operationsByName.list_schema_packs!.handler(ctxOf(), {}) as { bundled: string[]; installed: string[] };
expect(result.bundled).toContain('gbrain-base');
expect(result.bundled).toContain('gbrain-recommended');
expect(result.bundled).toContain('gbrain-base-v2');
expect(result.bundled).toContain('gbrain-investor');
expect(result.installed).toContain('mine');
});
});
+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);
});
});
+38 -1
View File
@@ -64,11 +64,14 @@ describe('gbrain schema CLI (Phase C)', () => {
expect(r.stdout + r.stderr).toMatch(/schema|active|list|show|validate|use/i);
});
test('schema list shows gbrain-base bundled', () => {
test('schema list shows all bundled packs', () => {
const r = gbrain(['schema', 'list']);
expect(r.code).toBe(0);
expect(r.stdout).toContain('Bundled packs:');
expect(r.stdout).toContain('gbrain-base');
expect(r.stdout).toContain('gbrain-recommended');
expect(r.stdout).toContain('gbrain-base-v2');
expect(r.stdout).toContain('gbrain-investor');
});
test('schema show gbrain-base prints manifest details', () => {
@@ -97,6 +100,40 @@ describe('gbrain schema CLI (Phase C)', () => {
expect(r.stdout).toContain('valid manifest');
});
test('schema show/validate exposes bundled gbrain-recommended', () => {
const show = gbrain(['schema', 'show', 'gbrain-recommended']);
expect(show.code).toBe(0);
expect(show.stdout).toContain('gbrain-recommended v1.0.0');
expect(show.stdout).toContain('Page types (');
expect(show.stdout).toContain('meeting :: temporal');
const validate = gbrain(['schema', 'validate', 'gbrain-recommended']);
expect(validate.code).toBe(0);
expect(validate.stdout).toContain('valid manifest');
});
test('schema show exposes bundled gbrain-base-v2 successor pack', () => {
const r = gbrain(['schema', 'show', 'gbrain-base-v2']);
expect(r.code).toBe(0);
expect(r.stdout).toContain('gbrain-base-v2 v1.0.0');
expect(r.stdout).toContain('Page types (');
expect(r.stdout).toContain('Link verbs (14)');
});
test('schema active loads configured gbrain-recommended with real types', () => {
const home = mkdtempSync(join(tmpdir(), 'gbrain-schema-active-recommended-'));
try {
mkdirSync(join(home, '.gbrain'), { recursive: true });
writeFileSync(join(home, '.gbrain', 'config.json'), JSON.stringify({ schema_pack: 'gbrain-recommended' }), 'utf-8');
const r = gbrain(['schema', 'active'], { GBRAIN_HOME: home });
expect(r.code).toBe(0);
expect(r.stdout).toContain('Active pack: gbrain-recommended');
expect(r.stdout).not.toContain('Page types: 0');
} finally {
rmSync(home, { recursive: true, force: true });
}
});
test('schema active reports default resolution', () => {
const r = gbrain(['schema', 'active']);
expect(r.code).toBe(0);
+49
View File
@@ -345,6 +345,34 @@ describe('YAML mini-parser', () => {
expect(result.types[1].weight).toBe(2);
});
test('parses block scalar without swallowing following keys', () => {
const yaml = `name: blocky
description: |
First line.
Second line.
page_types:
- name: meeting
primitive: temporal
path_prefixes:
- meetings/
aliases: []
extractable: true
expert_routing: false`;
const result = parseYamlMini(yaml) as { description: string; page_types: Array<Record<string, unknown>> };
expect(result.description).toBe('First line.\nSecond line.');
expect(result.page_types).toHaveLength(1);
expect(result.page_types[0].name).toBe('meeting');
});
test('block scalar keeps # as literal content, not a comment', () => {
const yaml = `description: |
See issue #2029 for context.
name: hashy`;
const result = parseYamlMini(yaml) as Record<string, unknown>;
expect(result.description).toBe('See issue #2029 for context.');
expect(result.name).toBe('hashy');
});
test('strips comments', () => {
const result = parseYamlMini('# top comment\nname: value # inline comment') as Record<string, unknown>;
expect(result.name).toBe('value');
@@ -374,6 +402,27 @@ extends: null`;
const pack = loadPackFromString(json, 'fixture.json');
expect(pack.name).toBe('json-pack');
});
test('loads block-scalar pack descriptions without losing page types', () => {
const pack = loadPackFromString(`api_version: gbrain-schema-pack-v1
name: recommended-fixture
version: 1.0.0
extends: gbrain-base
description: |
Operational starter pack.
page_types:
- name: meeting
primitive: temporal
path_prefixes:
- meetings/
aliases: []
extractable: true
expert_routing: false
link_types: []`, 'fixture.yaml');
expect(pack.name).toBe('recommended-fixture');
expect(pack.extends).toBe('gbrain-base');
expect(pack.page_types.map((t) => t.name)).toContain('meeting');
});
});
describe('ReDoS guard', () => {
+4 -1
View File
@@ -103,7 +103,10 @@ describe('locateMutablePackFile — bundled guard', () => {
expect(BUNDLED_PACK_NAMES.has('gbrain-recommended')).toBe(true);
// v0.42 (T22): gbrain-base-v2 joins the bundled set.
expect(BUNDLED_PACK_NAMES.has('gbrain-base-v2')).toBe(true);
expect(BUNDLED_PACK_NAMES.size).toBe(3);
// Derived from the single bundled registry — the lens packs (creator,
// investor, engineer, everything) are read-only too.
expect(BUNDLED_PACK_NAMES.has('gbrain-investor')).toBe(true);
expect(BUNDLED_PACK_NAMES.size).toBe(7);
});
it('rejects gbrain-base-v2 with PACK_READONLY (bundled guard)', () => {