mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* fix(core): drain fire-and-forget sinks before disconnect via a background-work registry (#1762) New src/core/background-work.ts registry (Map<name,drainer>, ordered drain, awaited abort). facts-queue (order 0, abort=shutdown), last-retrieved (1), and eval-capture (3, now self-tracked) register as sinks. Both CLI exit paths (op-dispatch finally + handleCliOnly finally) drain the registry before engine.disconnect() so a PGLite db.close() can't race in-flight work into the re-pump busy-loop that pinned the single-writer lock. Op-dispatch error path converts process.exit(1) to exitCode+return so the finally still drains. * fix(ai): bound every outbound AI call so a stalled provider can't hang (#1762/#1775) withDefaultTimeout composes a per-touchpoint default deadline (chat 300s, embed/multimodal 60s) with any caller signal via AbortSignal.any. Applied at the SDK call layer (chat generateText, expand generateObject, OCR, per-sub-batch embed) — covers native-anthropic + retries — plus per-request multimodal fetch. embedQuery forwards abortSignal. Env: GBRAIN_AI_{CHAT,EMBED,MULTIMODAL}_TIMEOUT_MS. * fix(postgres): module-mode reconnect preserves the shared singleton (#1745) reconnect() branches on connection style. Module-singleton engines re-establish idempotently via db.connect() (no-op when alive) + refresh the ConnectionManager read pool, never db.disconnect() — so a transient blip no longer nulls the shared sql out from under concurrent ops (which threw 'connect() has not been called'). Fail-loud on real connect failure. Instance pools keep teardown+recreate. * fix(search): bound the query-time embed so a stall falls back to keyword (#1775) search/query default to cheap-hybrid (embeds the query); a stalled provider made the embed never settle, so the keyword fallback never engaged and the command force-exited with no output. One shared QueryEmbedDeadline (6s, floored 2s per embed) covers both the cache-lookup and inner embeds via embedQueryBounded (abortSignal + Promise.race) → existing keyword fallback engages. Also registers the search-cache background-work drainer (now bounded). Env: GBRAIN_QUERY_EMBED_TIMEOUT_MS. * test+chore: reliability wave tests + v0.42.11.0 (#1762 #1745 #1775) New: background-work registry unit, query-embed deadline unit, eval-capture drain unit, postgres reconnect E2E (#1745), gbrain capture exit-clean case in the PGLite serial test. Updated fix-wave-structural assertions to the registry shape. VERSION/package.json/CHANGELOG -> 0.42.11.0; TODOS retrofit marked done. Incorporates + hardens PR #1763 (drain-before-disconnect + embed fetch timeout); the residual hung-Haiku hole is closed by the facts shutdown() abort belt. Co-Authored-By: ElliotDrel <noreply@github.com> Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: document background-work registry + v0.42.11.0 reliability wave in CLAUDE.md (regen llms) * chore: bump release version 0.42.11.0 -> 0.42.20.0 Rename the reliability-wave release version per request. Trio (VERSION / package.json / CHANGELOG) reconciled; in-code version-tag comments and test fixtures updated; llms regenerated. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: ElliotDrel <noreply@github.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
78 lines
2.5 KiB
TypeScript
78 lines
2.5 KiB
TypeScript
/**
|
|
* v0.42.20.0 (#1762) — eval-capture is the 4th fire-and-forget DB-write sink the
|
|
* background-work registry drains before CLI disconnect. `captureEvalCandidate`
|
|
* is `void`-ed by the search/query op handlers; its async `logEvalCandidate`
|
|
* write is the same lock-pin / disconnect-race class as the other sinks. These
|
|
* tests pin the bounded drain (`awaitPendingEvalCaptures`).
|
|
*/
|
|
import { describe, test, expect, afterEach } from 'bun:test';
|
|
import {
|
|
captureEvalCandidate,
|
|
awaitPendingEvalCaptures,
|
|
_resetPendingEvalCapturesForTests,
|
|
type CaptureContext,
|
|
} from '../src/core/eval-capture.ts';
|
|
import type { BrainEngine } from '../src/core/engine.ts';
|
|
import type { SearchResult } from '../src/core/types.ts';
|
|
|
|
function makeCtx(): CaptureContext {
|
|
const result: SearchResult = {
|
|
slug: 'people/alice-example',
|
|
page_id: 1,
|
|
title: 'Alice Example',
|
|
type: 'person',
|
|
chunk_text: '…',
|
|
chunk_source: 'compiled_truth',
|
|
chunk_id: 42,
|
|
chunk_index: 0,
|
|
score: 0.9,
|
|
stale: false,
|
|
source_id: 'default',
|
|
};
|
|
return {
|
|
tool_name: 'query',
|
|
query: 'who is alice',
|
|
results: [result],
|
|
meta: { vector_enabled: true, detail_resolved: 'medium', expansion_applied: false },
|
|
latency_ms: 1,
|
|
remote: false,
|
|
expand_enabled: false,
|
|
detail: null,
|
|
job_id: null,
|
|
subagent_id: null,
|
|
};
|
|
}
|
|
|
|
afterEach(() => _resetPendingEvalCapturesForTests());
|
|
|
|
describe('awaitPendingEvalCaptures', () => {
|
|
test('empty set drains instantly', async () => {
|
|
const r = await awaitPendingEvalCaptures(50);
|
|
expect(r.unfinished).toBe(0);
|
|
});
|
|
|
|
test('drains a settled capture to unfinished:0', async () => {
|
|
const engine = {
|
|
logEvalCandidate: async () => 1,
|
|
logEvalCaptureFailure: async () => {},
|
|
} as unknown as BrainEngine;
|
|
void captureEvalCandidate(engine, makeCtx(), { scrub_pii: false });
|
|
const r = await awaitPendingEvalCaptures(1000);
|
|
expect(r.unfinished).toBe(0);
|
|
});
|
|
|
|
test('a hanging capture is bounded by the timeout (not a hang)', async () => {
|
|
const engine = {
|
|
// Never resolves — simulates a wedged DB write.
|
|
logEvalCandidate: () => new Promise<number>(() => {}),
|
|
logEvalCaptureFailure: async () => {},
|
|
} as unknown as BrainEngine;
|
|
void captureEvalCandidate(engine, makeCtx(), { scrub_pii: false });
|
|
const start = Date.now();
|
|
const r = await awaitPendingEvalCaptures(150);
|
|
const elapsed = Date.now() - start;
|
|
expect(r.unfinished).toBe(1);
|
|
expect(elapsed).toBeLessThan(1000);
|
|
});
|
|
});
|