mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
03ffc6ebdb
* fix(jobs): reap stale dead-holder cycle/sync locks (#1972) A crashed sync (OOM, recycle, SIGKILL) stranded its gbrain_cycle_locks row until something contended for it — reclaim was on-contention only. Add a host-scoped background reaper: reapDeadHolderLocks deletes locks whose holder PID is provably dead on this host, scoped to the gbrain-sync:*/gbrain-cycle* namespaces only (never elections/supervisor/reindex), with a snapshot-matched delete (date_trunc on acquired_at) that is TOCTOU-safe against PID reuse. Reuses isHolderDeadLocally (same-host + ESRCH + 60s grace). doctor --fix now auto-reaps for no-autopilot brains. DRY: selectLockRows + shared mapper now back inspectLock + listStaleLocks (killed the triplication). * fix(db): bound pool disconnect so teardown can't eat CLI output (#1972) pool.end() against PgBouncer transaction-mode never drained, so disconnect blocked until the CLI's 10s force-exit fired and process.exit()'d mid-write, truncating stdout (e.g. #1959's relational query returned empty). Add a gbrain-owned endPoolBounded(pool): Promise.race of pool.end({timeout}) against a hard timer, so teardown is bounded regardless of what postgres.js does and is testable. connection-manager ends its direct + read pools concurrently so the per-pool bounds don't stack. PGLite disconnect is unaffected. * fix(cycle): complete cooperative-abort coverage + wire lock reaper (#1972) v0.42.29 made only the embed phase honor the abort signal; a 24h pull still showed force-evicts from a long non-embed phase ignoring it. Thread the signal into every cycle-reachable long loop: extract (extractForSlugs + the full-walk extractLinksFromDir/extractTimelineFromDir), extract_facts (per-page loop + embed signal + the phantom-redirect 30s lock-retry), and consolidate's bucket loop. Add a terminal abort check so an aborted cycle never stamps last_full_cycle_at as a completed run (Codex #9). lint now yields + checks abort every 200 pages (it's synchronous; the yield is what lets the signal land). New phase-duration force-evict attribution log names any phase that crosses the 30s deadline. Wire reapDeadHolderLocks at cycle start. * chore: bump version and changelog (v0.42.38.0) #1972 — stale-lock reaper, bounded pool disconnect, and complete cooperative-abort coverage across cycle phases. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(key-files): current-state for the #1972 reaper, bounded disconnect, abort coverage document-release: update db-lock.ts (reapDeadHolderLocks + selectLockRows DRY), db.ts (endPoolBounded), and abort-check.ts (coverage now spans extract/ extract_facts/consolidate/lint + terminal guard) entries to current truth. * test(isolation): fix shard-order flakes exposed by #1972's new test files Adding 3 new test files reshuffled the hash-based shards, exposing two pre-existing test-isolation bugs: - cycle-consolidate.test.ts assumed the global legacy-embedding preload's 1536-d gateway config still held at initSchema, but a co-sharded test that calls resetGateway() in teardown nulls it, so initSchema fell back to the 1280-d default and built a halfvec(1280) facts column its 1536-d fixtures can't fill. Re-pin the legacy OpenAI/1536 config in beforeAll (the pattern legacy-embedding-preload.ts documents for 1536-d fixture tests). - db-lock-heartbeat-takeover.test.ts (merged from master's #1794) mutated process.env.GBRAIN_LOCK_STEAL_GRACE_SECONDS raw, tripping check:test-isolation rule R1. Convert to withEnv(). --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
68 lines
2.3 KiB
TypeScript
68 lines
2.3 KiB
TypeScript
/**
|
|
* #1972 (Codex #7) — cooperative abort on the cycle-reachable extract paths.
|
|
*
|
|
* The cycle calls runExtractCore with `slugs` defined (incremental →
|
|
* extractForSlugs) or undefined (full walk → extractLinksFromDir /
|
|
* extractTimelineFromDir). All three must bail promptly on a pre-aborted
|
|
* signal. Behavioral, dryRun-only (no DB writes, so no FK setup needed).
|
|
*/
|
|
|
|
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|
import { mkdtempSync, writeFileSync, rmSync } from 'fs';
|
|
import { join } from 'path';
|
|
import { tmpdir } from 'os';
|
|
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
|
import { runExtractCore } from '../src/commands/extract.ts';
|
|
|
|
let engine: PGLiteEngine;
|
|
let dir: string;
|
|
|
|
beforeAll(async () => {
|
|
engine = new PGLiteEngine();
|
|
await engine.connect({ database_url: '' });
|
|
await engine.initSchema();
|
|
dir = mkdtempSync(join(tmpdir(), 'extract-abort-'));
|
|
// a.md links to b; both exist so the wikilink resolves.
|
|
writeFileSync(join(dir, 'a.md'), '# A\n\nsee [[b]] for more.\n');
|
|
writeFileSync(join(dir, 'b.md'), '# B\n\nplain.\n');
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await engine.disconnect();
|
|
rmSync(dir, { recursive: true, force: true });
|
|
});
|
|
|
|
function aborted(): AbortSignal {
|
|
const a = new AbortController();
|
|
a.abort(new Error('timeout'));
|
|
return a.signal;
|
|
}
|
|
|
|
describe('extract cooperative abort', () => {
|
|
test('incremental path (extractForSlugs) processes 0 pages when pre-aborted', async () => {
|
|
const r = await runExtractCore(engine, {
|
|
mode: 'links', dir, dryRun: true, slugs: ['a', 'b'], signal: aborted(),
|
|
});
|
|
expect(r.pages_processed).toBe(0);
|
|
});
|
|
|
|
test('incremental path processes all pages without a signal', async () => {
|
|
const r = await runExtractCore(engine, {
|
|
mode: 'links', dir, dryRun: true, slugs: ['a', 'b'],
|
|
});
|
|
expect(r.pages_processed).toBe(2);
|
|
});
|
|
|
|
test('full-walk path (extractLinksFromDir) creates 0 links when pre-aborted', async () => {
|
|
const r = await runExtractCore(engine, {
|
|
mode: 'links', dir, dryRun: true, signal: aborted(),
|
|
});
|
|
expect(r.links_created).toBe(0);
|
|
});
|
|
|
|
test('full-walk path resolves the wikilink without a signal', async () => {
|
|
const r = await runExtractCore(engine, { mode: 'links', dir, dryRun: true });
|
|
expect(r.links_created).toBeGreaterThanOrEqual(1);
|
|
});
|
|
});
|