mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* fix(sync): contention-free page-generation clock — sequence swap The page-generation clock backed the query-cache Layer-1 bookmark via a FOR EACH STATEMENT trigger running `UPDATE page_generation_clock SET value=value+1 WHERE id=1`. That took a transaction-length RowExclusiveLock on one tuple, so every concurrent page writer serialized on the prior writer's COMMIT — sync ran at ~0.8 cores regardless of worker count. Swap to a SEQUENCE bumped by nextval() (a microsecond LWLock, never a row lock). The clock's only contract is monotonic advancement on any page INSERT/UPDATE/DELETE; last_value is non-transactional, so rolled-back or concurrent-uncommitted writers only OVER-invalidate the cache (lose a hit), never serve stale. - migration v118: CREATE SEQUENCE + load-bearing 2-arg setval (is_called= true, floor 1, seeded >= old clock and MAX(generation)) + repoint the trigger function body + DELETE query_cache so no old-clock bookmark survives the swap. v107 left immutable. - query-cache-gate.ts: 3 readers -> SELECT last_value FROM page_generation_clock_seq. - schema.sql + pglite-schema.ts (+ regenerated schema-embedded.ts) ship the sequence on fresh install; table + trigger names retained. - tests: clockValue reads last_value; mechanism proof (trigger fn uses nextval not the row UPDATE); rollback-advances-clock safety pin; real PGLite sequence round-trip (is_called gotcha); shape test requires _seq. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sync): op_checkpoints array-shape guard — CHECK + repair + defensive loader completed_keys is JSONB and the checkpoint loader runs jsonb_array_elements_text over it. A non-array (scalar) value makes that throw "cannot extract elements from a scalar", which takes down the whole UNION load — including the valid op_checkpoint_paths child rows — and loses all checkpoint progress for that key. No current writer produces a scalar, but an older binary / external script / future bug could. Make the corruption class structurally impossible and self-healing: - migration v119: LOCK TABLE (so an out-of-band scalar can't land between repair and constrain; no-op on single-connection PGLite), repair any pre-existing scalar to '[]' (op_checkpoint_paths child rows are the append-only source of truth, so the reset loses nothing), then add the named CHECK (jsonb_typeof(completed_keys) = 'array') via a pg_constraint IF NOT EXISTS guard. A DB-enforced always-on guard — the correct pattern vs a migration verify-hook, which never runs on already-stamped brains. - schema.sql + pglite-schema.ts (+ regenerated schema-embedded.ts) ship the same NAMED inline CHECK so fresh installs match migrated brains and v119 skips the duplicate. - op-checkpoint.ts loader: gate the legacy arm on jsonb_typeof = 'array' so a scalar parent is skipped (children still load) instead of throwing the whole union, and log a specific corruption warning when one is seen. - tests: CHECK rejects a scalar (exactly one constraint, no blob+migration dupe); loader survives a scalar parent and returns the children; v119 repair converts a scalar to '[]'. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(doctor): report actively-running sync via live lock, not stale freshness A slow source that makes partial progress every cycle but never fully completes used to read as permanently "stale" / "never synced" because last_sync_at only advances on a full successful sync. The naive fix (treat recent checkpoint banking as "in progress") is unsafe: a blocked sync banks the good files then writes no anchor, so banking can't tell in-progress from wedged. Use the only honest signal: a LIVE, non-expired per-source sync lock (inspectLock + syncLockId against gbrain_cycle_locks). Every non-skipLock sync holds it and refreshes it; a blocked/failed sync's process has exited (no lock row) and a wedged holder stops refreshing (TTL lapses), so either correctly falls through to the stale path and is NEVER masked. An actively-syncing source (including a never-synced source doing its first sync) counts as synced_recently, preserving the pinned 3-bucket invariant. The lock lookup reuses doctor's existing dynamic db-lock import and swallows any throw (stub engine, pre-lock-table brain) to false, so it can only ADD an in-progress verdict, never suppress a real stale one. Tests (real PGLiteEngine + real lock rows): stale+no-lock -> fail; stale+live-lock -> ok; never-synced+live-lock -> ok; never-synced+no-lock -> fail; expired-TTL lock -> fail (wedged not masked); blocked source with banked checkpoint rows but no lock -> still fail. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sync): honest --force-break-lock diagnostic when no lock is held --force-break-lock used to emit the same terse "Lock ... is not held (nothing to break)" line and exit 0 even when a sync was genuinely wedged, sending the operator down a dead end — the wedge was not a held lock. Keep rc=0 (breaking a non-existent lock is idempotently successful; flipping the exit code would break automation), but under --force say plainly that nothing was broken and point at the real next step (gbrain sync / gbrain doctor) plus a `wedge_hint` field in --json output. The non-force path is byte-for-byte unchanged. runBreakLock is exported for the test. Tests: force+no-lock -> wedge_hint JSON + human hint, rc 0; non-force+no-lock -> unchanged terse line, no hint. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(doctor): surface the in-progress sync holder in the freshness message Plan-completion follow-up to the BUG 4 live-lock signal: when a source is actively syncing, name the holder (pid + host) in the check message instead of silently folding it into synced_recently. The note is appended only when something is in progress, so steady-state messages stay byte-for-byte unchanged (the pinned exact-message + 3-bucket-invariant tests still pass). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(sync): pre-landing review fixes — monotonic clock seed, scoped CHECK guard Adversarial (codex) review of the implementation diff caught three: - P1 (correctness): the fresh-schema setval was not monotonic. initSchema replays the schema blob, and the unconditional setval(MAX(generation)) could move page_generation_clock_seq.last_value BACKWARD on an already-upgraded brain, letting a stored query_cache bookmark serve stale rows. Seed via GREATEST over the sequence's OWN last_value (+ old table value + MAX(generation)) in all 3 fresh schemas and migration v118, so a replay is idempotent — mirrors the old table's ON CONFLICT DO NOTHING. Pinned by a new monotonic regression test. - P2: v119's CHECK-exists guard keyed on conname only (not globally unique). Scope it to conrelid = 'op_checkpoints'::regclass. - P3: in-progress note ran into the prior sentence in fail/warn doctor messages; separate it with '. '. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test: make Anthropic/ZE no-key tests hermetic against a dev config key These "no key" tests cleared only ANTHROPIC_API_KEY / ZEROENTROPY_API_KEY from the env, but hasAnthropicKey() and checkZeEmbeddingHealth() also read the key from ~/.gbrain/config.json. On a dev machine whose real config holds a key, the no-key assertions flipped and the tests failed locally (they passed only in key-less CI). Add a shared with-env emptyHome() helper and point GBRAIN_HOME at an empty dir in every no-key path so loadConfig finds nothing — matching the already-hermetic anthropic-key / gateway-probe tests. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.44.1.0) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(key-files): sync doctor + op-checkpoint entries to v0.44.1.0 truth checkSyncFreshness now reports an actively-running sync via the live per-source lock (names holder pid+host, counts as synced_recently) instead of flagging it stale; loadOpCheckpoint gates the legacy union arm on jsonb_typeof = 'array' so a scalar parent can't take down the whole load, and migration v119's CHECK constraint makes the corruption class structurally impossible. Reference docs describe current behavior only — both entries updated in place, no release-clause appends. Guard + llms freshness test green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: re-version to v0.42.51.0 (natural next-off-master) Maintainer override of the queue allocator's leap to 0.44.1.0 (it jumped past in-flight sibling PR claims at 0.42.50/0.43.0/0.44.0). Take the natural next slot in the 0.42.x line above the immediate sibling claim (0.42.50.0); a merge re-bump resolves any collision if a cathedral PR lands first. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * ci(e2e): bound + retry the OpenClaw install so a transient npm hang can't burn the Tier 2 budget The Tier 2 (LLM Skills) job failed at 30m16s — the `npm install -g openclaw@2026.4.9` step hung on a transient npm/registry stall (orphan `npm install openclaw` was still running at cancel time) and consumed the entire 30m job budget that v0.42.50.0 (#2254) introduced. The install normally finishes in under a minute (Tier 2 is ~4m end to end on master), so this is flaky-install infra, not a test failure. Wrap the install in `timeout 120` + a 3-attempt retry loop with an 8-minute step backstop: a hung attempt is killed in 2 min and retried instead of eating the whole job. Same bound-the-hang philosophy as #2254's job timeouts. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
340 lines
13 KiB
TypeScript
340 lines
13 KiB
TypeScript
import { describe, test, expect, beforeAll, beforeEach, afterAll } from 'bun:test';
|
||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||
import { resetPgliteState } from './helpers/reset-pglite.ts';
|
||
import {
|
||
loadOpCheckpoint,
|
||
recordCompleted,
|
||
appendCompleted,
|
||
clearOpCheckpoint,
|
||
resumeFilter,
|
||
purgeStaleCheckpoints,
|
||
fingerprint,
|
||
embedFingerprint,
|
||
extractFingerprint,
|
||
reindexFingerprint,
|
||
} from '../src/core/op-checkpoint.ts';
|
||
|
||
/**
|
||
* D12 pinning tests for src/core/op-checkpoint.ts.
|
||
*
|
||
* Closes codex #10–#16:
|
||
* - per-param fingerprint scoping (no cross-mode collisions)
|
||
* - DB-backed CRUD works on PGLite (single-host fallback path)
|
||
* - resumeFilter is pure
|
||
* - purgeStaleCheckpoints respects TTL
|
||
*/
|
||
|
||
let engine: PGLiteEngine;
|
||
|
||
beforeAll(async () => {
|
||
engine = new PGLiteEngine();
|
||
await engine.connect({});
|
||
await engine.initSchema();
|
||
});
|
||
|
||
afterAll(async () => {
|
||
await engine.disconnect();
|
||
});
|
||
|
||
beforeEach(async () => {
|
||
await resetPgliteState(engine);
|
||
});
|
||
|
||
describe('fingerprint helpers', () => {
|
||
test('fingerprint: stable across runs', () => {
|
||
const params = { stale: true, source: 'default' };
|
||
expect(fingerprint(params)).toBe(fingerprint(params));
|
||
});
|
||
|
||
test('fingerprint: key order does not matter (canonical-JSON)', () => {
|
||
const a = fingerprint({ a: 1, b: 2 });
|
||
const b = fingerprint({ b: 2, a: 1 });
|
||
expect(a).toBe(b);
|
||
});
|
||
|
||
test('fingerprint: different values produce different hashes', () => {
|
||
expect(fingerprint({ a: 1 })).not.toBe(fingerprint({ a: 2 }));
|
||
});
|
||
|
||
test('fingerprint returns 8 hex chars', () => {
|
||
expect(fingerprint({ x: 1 })).toMatch(/^[a-f0-9]{8}$/);
|
||
});
|
||
|
||
test('codex #11: extract links vs timeline get different fingerprints', () => {
|
||
const linksFp = extractFingerprint({ mode: 'links', source: 'default' });
|
||
const timelineFp = extractFingerprint({ mode: 'timeline', source: 'default' });
|
||
expect(linksFp).not.toBe(timelineFp);
|
||
});
|
||
|
||
test('codex #12: reindex markdown vs code get different fingerprints', () => {
|
||
const md = reindexFingerprint({ markdown: true, chunker_version: 2 });
|
||
const code = reindexFingerprint({ code: true, chunker_version: 2 });
|
||
expect(md).not.toBe(code);
|
||
});
|
||
|
||
test('codex #15: embed model+dim variation produces different fingerprints', () => {
|
||
const a = embedFingerprint({
|
||
stale: true,
|
||
embedding_model: 'openai:text-embedding-3-large',
|
||
embedding_dimensions: 3072,
|
||
});
|
||
const b = embedFingerprint({
|
||
stale: true,
|
||
embedding_model: 'voyage:voyage-3',
|
||
embedding_dimensions: 1024,
|
||
});
|
||
expect(a).not.toBe(b);
|
||
});
|
||
|
||
test('reindex chunker_version bump invalidates checkpoint', () => {
|
||
const v1 = reindexFingerprint({ markdown: true, chunker_version: 1 });
|
||
const v2 = reindexFingerprint({ markdown: true, chunker_version: 2 });
|
||
expect(v1).not.toBe(v2);
|
||
});
|
||
});
|
||
|
||
describe('loadOpCheckpoint / recordCompleted / clearOpCheckpoint', () => {
|
||
test('empty checkpoint returns []', async () => {
|
||
const result = await loadOpCheckpoint(engine, { op: 'embed', fingerprint: 'abc12345' });
|
||
expect(result).toEqual([]);
|
||
});
|
||
|
||
test('round-trip: write then read', async () => {
|
||
const key = { op: 'embed', fingerprint: 'abc12345' };
|
||
await recordCompleted(engine, key, ['chunk-1', 'chunk-2', 'chunk-3']);
|
||
const result = await loadOpCheckpoint(engine, key);
|
||
expect(result.sort()).toEqual(['chunk-1', 'chunk-2', 'chunk-3']);
|
||
});
|
||
|
||
test('write overwrites prior state', async () => {
|
||
const key = { op: 'embed', fingerprint: 'abc12345' };
|
||
await recordCompleted(engine, key, ['chunk-1']);
|
||
await recordCompleted(engine, key, ['chunk-1', 'chunk-2']);
|
||
const result = await loadOpCheckpoint(engine, key);
|
||
expect(result.sort()).toEqual(['chunk-1', 'chunk-2']);
|
||
});
|
||
|
||
test('different fingerprints stay isolated', async () => {
|
||
const linksKey = { op: 'extract', fingerprint: 'fp-links' };
|
||
const timelineKey = { op: 'extract', fingerprint: 'fp-timeline' };
|
||
await recordCompleted(engine, linksKey, ['file-a.md']);
|
||
await recordCompleted(engine, timelineKey, ['file-b.md']);
|
||
|
||
const links = await loadOpCheckpoint(engine, linksKey);
|
||
const timeline = await loadOpCheckpoint(engine, timelineKey);
|
||
|
||
expect(links).toEqual(['file-a.md']);
|
||
expect(timeline).toEqual(['file-b.md']);
|
||
});
|
||
|
||
test('clearOpCheckpoint drops the row', async () => {
|
||
const key = { op: 'embed', fingerprint: 'to-clear' };
|
||
await recordCompleted(engine, key, ['x']);
|
||
expect(await loadOpCheckpoint(engine, key)).toEqual(['x']);
|
||
await clearOpCheckpoint(engine, key);
|
||
expect(await loadOpCheckpoint(engine, key)).toEqual([]);
|
||
});
|
||
|
||
test('clearOpCheckpoint on missing row is no-op (idempotent)', async () => {
|
||
// Should not throw and load should still return [] afterwards
|
||
await clearOpCheckpoint(engine, { op: 'never-written', fingerprint: 'nope' });
|
||
const after = await loadOpCheckpoint(engine, { op: 'never-written', fingerprint: 'nope' });
|
||
expect(after).toEqual([]);
|
||
});
|
||
});
|
||
|
||
// #1794: append-only delta storage (op_checkpoint_paths). recordCompleted keeps
|
||
// REPLACE semantics for the 9 non-sync consumers; appendCompleted is the
|
||
// additive path sync uses to avoid O(N²) full-set rewrites.
|
||
describe('appendCompleted (delta) + union read', () => {
|
||
async function pathRowCount(op: string, fp: string): Promise<number> {
|
||
const rows = await engine.executeRaw<{ n: string | number }>(
|
||
`SELECT count(*)::text AS n FROM op_checkpoint_paths WHERE op = $1 AND fingerprint = $2`,
|
||
[op, fp],
|
||
);
|
||
return Number(rows[0]?.n ?? 0);
|
||
}
|
||
|
||
test('appendCompleted returns true and load reflects the delta', async () => {
|
||
const key = { op: 'sync', fingerprint: 'fp-append' };
|
||
expect(await appendCompleted(engine, key, ['a.md', 'b.md'])).toBe(true);
|
||
expect((await loadOpCheckpoint(engine, key)).sort()).toEqual(['a.md', 'b.md']);
|
||
});
|
||
|
||
test('re-appending an already-banked path inserts 0 new rows (delta, not full rewrite)', async () => {
|
||
const key = { op: 'sync', fingerprint: 'fp-delta' };
|
||
await appendCompleted(engine, key, ['a.md', 'b.md']);
|
||
expect(await pathRowCount('sync', 'fp-delta')).toBe(2);
|
||
// Second flush re-sends one banked + one new path; ON CONFLICT DO NOTHING
|
||
// means only the genuinely-new row lands.
|
||
await appendCompleted(engine, key, ['b.md', 'c.md']);
|
||
expect(await pathRowCount('sync', 'fp-delta')).toBe(3);
|
||
expect((await loadOpCheckpoint(engine, key)).sort()).toEqual(['a.md', 'b.md', 'c.md']);
|
||
});
|
||
|
||
test('empty delta is a no-op (returns true, writes nothing)', async () => {
|
||
const key = { op: 'sync', fingerprint: 'fp-empty' };
|
||
expect(await appendCompleted(engine, key, [])).toBe(true);
|
||
expect(await pathRowCount('sync', 'fp-empty')).toBe(0);
|
||
});
|
||
|
||
test('union read across legacy completed_keys array AND appended child rows', async () => {
|
||
// Simulates an in-flight upgrade: a pre-existing parent row carries the
|
||
// legacy array, then the new code appends child rows to the same key.
|
||
const key = { op: 'sync', fingerprint: 'fp-union' };
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoints (op, fingerprint, completed_keys, updated_at)
|
||
VALUES ('sync', 'fp-union', '["legacy-1","legacy-2"]'::jsonb, now())`,
|
||
);
|
||
await appendCompleted(engine, key, ['new-1']);
|
||
expect((await loadOpCheckpoint(engine, key)).sort()).toEqual(['legacy-1', 'legacy-2', 'new-1']);
|
||
});
|
||
|
||
test('clearOpCheckpoint cascades to child rows', async () => {
|
||
const key = { op: 'sync', fingerprint: 'fp-clear' };
|
||
await appendCompleted(engine, key, ['a.md', 'b.md']);
|
||
expect(await pathRowCount('sync', 'fp-clear')).toBe(2);
|
||
await clearOpCheckpoint(engine, key);
|
||
expect(await pathRowCount('sync', 'fp-clear')).toBe(0);
|
||
expect(await loadOpCheckpoint(engine, key)).toEqual([]);
|
||
});
|
||
|
||
test('recordCompleted still REPLACES (sync appendCompleted does not)', async () => {
|
||
// Guards V3: recordCompleted must remove stale keys, not append them.
|
||
const key = { op: 'embed', fingerprint: 'fp-replace' };
|
||
await recordCompleted(engine, key, ['x', 'y']);
|
||
await recordCompleted(engine, key, ['x']);
|
||
expect((await loadOpCheckpoint(engine, key)).sort()).toEqual(['x']);
|
||
});
|
||
|
||
test('purge of a stale parent cascades to its child rows', async () => {
|
||
// The FK guarantees children always have a parent, so deleting the stale
|
||
// parent cascade-drops its children. (A standalone orphan is impossible to
|
||
// create — the FK rejects it — so there is no separate orphan sweep.)
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoints (op, fingerprint, completed_keys, updated_at)
|
||
VALUES ('sync', 'fp-stale', '[]'::jsonb, now() - interval '10 days')`,
|
||
);
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoint_paths (op, fingerprint, path, created_at)
|
||
VALUES ('sync', 'fp-stale', 'old.md', now() - interval '10 days')`,
|
||
);
|
||
const purged = await purgeStaleCheckpoints(engine, 7);
|
||
expect(purged).toBe(1); // counts the parent; child cascades silently
|
||
expect(await pathRowCount('sync', 'fp-stale')).toBe(0);
|
||
});
|
||
});
|
||
|
||
describe('resumeFilter (pure)', () => {
|
||
test('empty completed returns all', () => {
|
||
expect(resumeFilter(['a', 'b', 'c'], [])).toEqual(['a', 'b', 'c']);
|
||
});
|
||
|
||
test('filters out completed keys', () => {
|
||
expect(resumeFilter(['a', 'b', 'c', 'd'], ['b', 'd'])).toEqual(['a', 'c']);
|
||
});
|
||
|
||
test('no completed keys present in all: identity', () => {
|
||
expect(resumeFilter(['a'], ['z'])).toEqual(['a']);
|
||
});
|
||
|
||
test('all completed: returns empty', () => {
|
||
expect(resumeFilter(['a', 'b'], ['a', 'b'])).toEqual([]);
|
||
});
|
||
});
|
||
|
||
describe('BUG 3: completed_keys array-shape guard (v119 CHECK + defensive loader)', () => {
|
||
const CONSTRAINT = 'op_checkpoints_completed_keys_array';
|
||
|
||
test('CHECK rejects a scalar completed_keys write — exactly one constraint (no blob+migration dupe)', async () => {
|
||
// Fresh PGLite install: the schema blob ships the NAMED inline CHECK and
|
||
// migration v119's IF NOT EXISTS skips re-adding it. Exactly one constraint.
|
||
const c = await engine.executeRaw<{ n: number }>(
|
||
`SELECT count(*)::int AS n FROM pg_constraint WHERE conname = $1`,
|
||
[CONSTRAINT],
|
||
);
|
||
expect(Number(c[0].n)).toBe(1);
|
||
|
||
let threw = false;
|
||
try {
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoints (op, fingerprint, completed_keys, updated_at)
|
||
VALUES ('embed', 'fp-reject', '"not-an-array"'::jsonb, now())`,
|
||
);
|
||
} catch {
|
||
threw = true;
|
||
}
|
||
expect(threw).toBe(true);
|
||
});
|
||
|
||
test('loader survives a scalar parent: returns child rows (not []), does not throw', async () => {
|
||
const key = { op: 'sync', fingerprint: 'fp-scalar-survive' };
|
||
// Bypass the CHECK to simulate pre-migration / out-of-band corruption.
|
||
await engine.executeRaw(`ALTER TABLE op_checkpoints DROP CONSTRAINT ${CONSTRAINT}`);
|
||
try {
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoints (op, fingerprint, completed_keys, updated_at)
|
||
VALUES ('sync', 'fp-scalar-survive', '"corrupt-scalar"'::jsonb, now())`,
|
||
);
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoint_paths (op, fingerprint, path)
|
||
VALUES ('sync', 'fp-scalar-survive', 'child-a.md')`,
|
||
);
|
||
// Pre-guard, jsonb_array_elements_text on the scalar threw and the catch
|
||
// returned [] — losing child-a.md. The typeof guard skips the scalar so
|
||
// the valid child survives.
|
||
const loaded = await loadOpCheckpoint(engine, key);
|
||
expect(loaded).toEqual(['child-a.md']);
|
||
} finally {
|
||
await engine.executeRaw(
|
||
`UPDATE op_checkpoints SET completed_keys = '[]'::jsonb WHERE jsonb_typeof(completed_keys) <> 'array'`,
|
||
);
|
||
await engine.executeRaw(
|
||
`ALTER TABLE op_checkpoints ADD CONSTRAINT ${CONSTRAINT} CHECK (jsonb_typeof(completed_keys) = 'array')`,
|
||
);
|
||
}
|
||
});
|
||
|
||
test('v119 repair converts a scalar parent to an empty array', async () => {
|
||
await engine.executeRaw(`ALTER TABLE op_checkpoints DROP CONSTRAINT ${CONSTRAINT}`);
|
||
try {
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoints (op, fingerprint, completed_keys, updated_at)
|
||
VALUES ('embed', 'fp-repair', '"scalar"'::jsonb, now())`,
|
||
);
|
||
// Migration v119's repair statement.
|
||
await engine.executeRaw(
|
||
`UPDATE op_checkpoints SET completed_keys = '[]'::jsonb, updated_at = now()
|
||
WHERE jsonb_typeof(completed_keys) <> 'array'`,
|
||
);
|
||
const typ = await engine.executeRaw<{ t: string }>(
|
||
`SELECT jsonb_typeof(completed_keys) AS t FROM op_checkpoints WHERE op = 'embed' AND fingerprint = 'fp-repair'`,
|
||
);
|
||
expect(typ[0].t).toBe('array');
|
||
} finally {
|
||
await engine.executeRaw(
|
||
`ALTER TABLE op_checkpoints ADD CONSTRAINT ${CONSTRAINT} CHECK (jsonb_typeof(completed_keys) = 'array')`,
|
||
);
|
||
}
|
||
});
|
||
});
|
||
|
||
describe('purgeStaleCheckpoints', () => {
|
||
test('no stale rows: returns 0', async () => {
|
||
await recordCompleted(engine, { op: 'embed', fingerprint: 'fresh' }, ['x']);
|
||
const purged = await purgeStaleCheckpoints(engine, 7);
|
||
expect(purged).toBe(0);
|
||
});
|
||
|
||
test('purges rows older than TTL', async () => {
|
||
// Insert a fake old row directly
|
||
await engine.executeRaw(
|
||
`INSERT INTO op_checkpoints (op, fingerprint, completed_keys, updated_at)
|
||
VALUES ('embed', 'old', '["x"]'::jsonb, now() - interval '10 days')`,
|
||
);
|
||
const purged = await purgeStaleCheckpoints(engine, 7);
|
||
expect(purged).toBe(1);
|
||
expect(await loadOpCheckpoint(engine, { op: 'embed', fingerprint: 'old' })).toEqual([]);
|
||
});
|
||
});
|