mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* fix(minions): self-identifying RSS watchdog + cgroup-aware default + pooler-reap self-heal (#1678) Problem 1: distinct WORKER_EXIT_RSS_WATCHDOG exit code + cause-keyed supervisor breaker (bypasses the stable-run reset that hid the 400x/24h loop) + rss_watchdog audit bucket + 80% soft-warn; cgroup-aware resolveDefaultMaxRssMb replaces the flat 2048 default at every spawn site. Problem 2: CONNECTION_ENDED classified retryable; postgres-engine sql getter throws a retryable error on a reaped instance pool instead of the misleading module-singleton fallthrough; promoteDelayed reconnect-retry; claim recovers on the next poll tick (no double-claim); lock-renewal tick reconnect-once dep. * feat(cycle): surface silent extract_atoms backlog + bounded --drain + fix lint clobbering the shared DB connection (#1678) Problem 3: extract_atoms_backlog doctor check + pack_gated skip marker + shared countExtractAtomsBacklog; `gbrain dream --phase extract_atoms --drain [--window N]` single-hold bounded drain (same cycleLockIdFor, rediscover each batch, reports remaining, exits non-zero while work remains). Also fixes a real production bug found via E2E: the cycle lint phase's resolveLintContentSanity created + disconnected a module-style engine that nulled the shared db singleton mid-cycle, breaking every later phase with "connect() has not been called". Lint now reuses the caller's live engine (cycle + Minion handlers thread it; standalone CLI keeps the create-own path). * chore: bump version and changelog (v0.41.39.0) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(#1678): pre-landing review — route transaction/withReservedConnection through the sql getter + drain treats failed count as incomplete Codex adversarial review findings: - #2: transaction(), withReservedConnection(), and one other site bypassed the v0.42.2.0 sql-getter self-heal via `this._sql || db.getConnection()`, so a reaped instance pool fell through to the module singleton there. Route all three through `this.sql` so they throw the retryable instance-pool error and recover consistently (MinionQueue.transaction hits this). - #4: `gbrain dream --drain` treated a null backlog count (query failure) as success via `remaining ?? 0`; now null exits EXIT_DRAIN_INCOMPLETE so automation never believes an unverified backlog drained. - #1 (claim orphan) + #3 (PGLite drain lock) documented as follow-ups in TODOS. * docs: document v0.42.2.0 #1678 modules + behavior in CLAUDE.md Adds Key Files entries for worker-exit-codes.ts, rss-default.ts, and extract-atoms-drain.ts, plus v0.42.2.0 annotations on worker.ts, child-worker-supervisor.ts, lock-renewal-tick.ts, and dream.ts. Regenerated llms-full.txt to match (test/build-llms.test.ts gate). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: re-version v0.42.2.0 → v0.42.5.0 across VERSION/package.json/CHANGELOG/docs/comments Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
81 lines
2.6 KiB
TypeScript
81 lines
2.6 KiB
TypeScript
/**
|
|
* issue #1678 — worker-side RSS watchdog behavior.
|
|
*
|
|
* Pins that:
|
|
* 1. Crossing the cap sets `rssWatchdogTriggered` (the flag the CLI reads to
|
|
* exit with WORKER_EXIT_RSS_WATCHDOG) and drains the worker.
|
|
* 2. The 80%-of-cap soft warn fires BEFORE the kill, once per crossing,
|
|
* carrying the peak + in-flight job kinds — and does NOT drain.
|
|
*
|
|
* Uses a real in-memory PGLite engine (canonical block per CLAUDE.md R3+R4)
|
|
* + a stubbed `getRss` so the test is deterministic and hermetic.
|
|
*/
|
|
|
|
import { describe, it, expect, beforeAll, afterAll } from 'bun:test';
|
|
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
|
import { MinionWorker } from '../src/core/minions/worker.ts';
|
|
|
|
const MB = 1024 * 1024;
|
|
|
|
let engine: PGLiteEngine;
|
|
|
|
beforeAll(async () => {
|
|
engine = new PGLiteEngine();
|
|
await engine.connect({});
|
|
await engine.initSchema();
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await engine.disconnect();
|
|
});
|
|
|
|
describe('worker RSS watchdog (issue #1678)', () => {
|
|
it('crossing the cap sets rssWatchdogTriggered and drains', async () => {
|
|
const worker = new MinionWorker(engine, {
|
|
queue: 'default',
|
|
concurrency: 1,
|
|
maxRssMb: 100,
|
|
getRss: () => 500 * MB, // 5x the cap
|
|
rssCheckInterval: 25,
|
|
healthCheckInterval: 0, // no self-health timer in this test
|
|
pollInterval: 25,
|
|
});
|
|
worker.register('noop', async () => {});
|
|
|
|
// start() resolves on its own: the periodic check trips the watchdog,
|
|
// gracefulShutdown sets running=false, the loop exits.
|
|
await worker.start();
|
|
expect(worker.rssWatchdogTriggered).toBe(true);
|
|
});
|
|
|
|
it('80% soft-warn fires before the kill and does not drain', async () => {
|
|
const warns: string[] = [];
|
|
const origWarn = console.warn;
|
|
console.warn = (...a: unknown[]) => { warns.push(a.join(' ')); };
|
|
|
|
const worker = new MinionWorker(engine, {
|
|
queue: 'default',
|
|
concurrency: 1,
|
|
maxRssMb: 100,
|
|
getRss: () => 85 * MB, // 85% — above soft line, below cap
|
|
rssCheckInterval: 25,
|
|
healthCheckInterval: 0,
|
|
pollInterval: 25,
|
|
});
|
|
worker.register('noop', async () => {});
|
|
|
|
const runPromise = worker.start();
|
|
// Let a couple of periodic checks fire.
|
|
await new Promise((r) => setTimeout(r, 120));
|
|
worker.stop();
|
|
await runPromise;
|
|
console.warn = origWarn;
|
|
|
|
const softWarn = warns.find((w) => w.includes('approaching cap'));
|
|
expect(softWarn).toBeDefined();
|
|
expect(softWarn).toContain('85%');
|
|
// Soft warn must NOT have drained the worker.
|
|
expect(worker.rssWatchdogTriggered).toBe(false);
|
|
});
|
|
});
|