mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 21:19:18 +00:00
* wip: federated sync v2 pre-merge snapshot
* v0.40.5.0 Federated Sync v2 — parallel source sync + push triggers + per-source health
Bump VERSION + package.json + CHANGELOG header + migration walkthrough filename
to v0.40.5.0 (claiming the next free slot in the v0.40.x patch series after
master's v0.40.1.0).
What ships (6 components, all behind sync.federated_v2 feature flag default-on):
1. Per-source sync lock — syncLockId(sourceId), phantom-redirect parity
2. Parallel sync --all — pMapAllSettled fan-out, --max-sources N cap
3. embed-backfill minion handler — D2 per-source lock + D6 $10/job budget + D15.1
fire-and-forget submission + D19 source-level cooldown + 24h $25 rolling cap
4. sync trigger CLI + POST /webhooks/github — HMAC-verified (60 req/min/IP),
X-GitHub-Event=push + ref filter against tracked_branch
5. sources status + federation_health doctor — batched GROUP BY pipeline
(4 queries instead of 6×N per-source roundtrips)
6. sources federate/unfederate hook — auto-submit embed-backfill on flip
Correctness fixes (unconditional):
- D21: sync.ts:959 facts backstop now passes sourceId to engine.getPage
- D15.4: redactSourceConfig + CI guard prevent webhook_secret leak
- D15.5: safeHexEqual extracted to src/core/timing-safe.ts
Schema:
- Migration v89 (sources_github_repo_index): partial expression index on
config->>'github_repo' for fast webhook source-lookup
Tests:
- 14 new test files, 112 cases. 4 IRON-RULE regressions pinned (SYNC_LOCK_ID
back-compat, phantom per-source lock, embed-backfill kill+resume,
webhook HMAC prefix-strip). All 9449 unit tests pass.
Caught at test-write time: the webhook handler had a Buffer.from('sha256=...',
'hex') truncation bug — without the prefix-strip, every signature would have
"matched" empty buffers. Pinned by a test/sources-webhook.test.ts IRON-RULE.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(check-source-config-leak): tighten regex to source-row patterns only
The v0.40.5.0 wave added scripts/check-source-config-leak.sh with a
too-broad pattern (JSON\.stringify\(.*config) that flagged any variable
named 'config' — catching the GLOBAL gbrain config.json serializers in
src/commands/init.ts (status envelopes) and src/core/config.ts (the
config-file write site). On the CI runner without rg installed, the
grep -rE fallback fired correctly and produced 4 false positives that
broke the `verify` script.
Tightened the patterns to specifically match `(source|src|row|s).config`
property access — the actual risk shape (a sources-table row being
serialized whole). The global gbrain config has a different shape and
threat model (file-mode 0o600 at the write site), so it's safe to
exempt at the regex level rather than per-file whitelist.
Also fixed a latent bug: the rg branch used `--include='*.ts'` (grep's
flag, not rg's). rg silently rejected it and CANDIDATES came back empty,
so the local-dev runs (which have rg) would never have caught a real
leak. Now branches on tool availability: `-g '*.ts'` for rg, `--include`
for grep -rE. Both branches verified against a synthetic leak fixture.
Also added init.ts + config.ts to the whitelist as a belt-and-suspenders
since they handle gbrain-global config (not source rows) and could
otherwise reflect-back via regex iteration.
CI: `bun run verify` exit 0 locally with both the original false-positive
fixture (clean repo) and a synthetic leak fixture (correctly caught,
exit 1).
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
122 lines
4.1 KiB
TypeScript
122 lines
4.1 KiB
TypeScript
/**
|
|
* Tests for `gbrain sync trigger` CLI (v0.40 D18).
|
|
*
|
|
* Validates the push-trigger entry point:
|
|
* - Help text renders
|
|
* - --source <id> required (exits 2)
|
|
* - --priority invalid (exits 2)
|
|
* - Non-existent source errors before submit (exits 1)
|
|
* - Successful submit prints job_id=N on stdout
|
|
* - Default priority is high (-10)
|
|
*/
|
|
import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
|
|
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
|
import { runSyncTrigger } from '../src/commands/sync.ts';
|
|
import { MinionQueue } from '../src/core/minions/queue.ts';
|
|
|
|
let engine: PGLiteEngine;
|
|
|
|
beforeAll(async () => {
|
|
engine = new PGLiteEngine();
|
|
await engine.connect({});
|
|
await engine.initSchema();
|
|
}, 30000);
|
|
|
|
afterAll(async () => {
|
|
await engine.disconnect();
|
|
});
|
|
|
|
beforeEach(async () => {
|
|
await engine.executeRaw('DELETE FROM minion_jobs');
|
|
});
|
|
|
|
/** Capture process.exit and stdout/stderr writes for one runSyncTrigger call. */
|
|
async function capture(args: string[]): Promise<{
|
|
stdout: string;
|
|
stderr: string;
|
|
exitCode: number | null;
|
|
}> {
|
|
const origExit = process.exit;
|
|
const origLog = console.log;
|
|
const origErr = console.error;
|
|
let stdout = '';
|
|
let stderr = '';
|
|
let exitCode: number | null = null;
|
|
const exitError = new Error('__exit__');
|
|
process.exit = ((code?: number) => {
|
|
exitCode = code ?? 0;
|
|
throw exitError;
|
|
}) as never;
|
|
console.log = (...a: unknown[]) => { stdout += a.map(String).join(' ') + '\n'; };
|
|
console.error = (...a: unknown[]) => { stderr += a.map(String).join(' ') + '\n'; };
|
|
try {
|
|
await runSyncTrigger(engine, args);
|
|
} catch (e) {
|
|
if (e !== exitError) throw e;
|
|
} finally {
|
|
process.exit = origExit;
|
|
console.log = origLog;
|
|
console.error = origErr;
|
|
}
|
|
return { stdout, stderr, exitCode };
|
|
}
|
|
|
|
describe('runSyncTrigger', () => {
|
|
test('--help prints usage and returns', async () => {
|
|
const { stdout, exitCode } = await capture(['--help']);
|
|
expect(exitCode).toBeNull();
|
|
expect(stdout).toContain('gbrain sync trigger');
|
|
expect(stdout).toContain('--source');
|
|
expect(stdout).toContain('--priority');
|
|
});
|
|
|
|
test('missing --source exits 2 with hint', async () => {
|
|
const { stderr, exitCode } = await capture([]);
|
|
expect(exitCode).toBe(2);
|
|
expect(stderr).toContain('--source <id> is required');
|
|
});
|
|
|
|
test('invalid --priority exits 2', async () => {
|
|
const { stderr, exitCode } = await capture(['--source', 'default', '--priority', 'urgent']);
|
|
expect(exitCode).toBe(2);
|
|
expect(stderr).toContain('Invalid --priority value');
|
|
});
|
|
|
|
test('non-existent source exits 1', async () => {
|
|
const { stderr, exitCode } = await capture(['--source', 'does-not-exist']);
|
|
expect(exitCode).toBe(1);
|
|
expect(stderr).toContain('not found');
|
|
});
|
|
|
|
test('valid trigger submits sync job + prints job_id=N to stdout', async () => {
|
|
const { stdout, exitCode } = await capture(['--source', 'default']);
|
|
expect(exitCode).toBeNull();
|
|
expect(stdout).toMatch(/^job_id=\d+$/m);
|
|
|
|
// Verify a sync job exists with auto_embed_backfill + priority -10
|
|
const queue = new MinionQueue(engine);
|
|
const jobs = await queue.getJobs({ name: 'sync', limit: 5 });
|
|
expect(jobs.length).toBe(1);
|
|
const job = jobs[0];
|
|
expect(job.priority).toBe(-10);
|
|
expect((job.data as { sourceId: string }).sourceId).toBe('default');
|
|
expect((job.data as { auto_embed_backfill: boolean }).auto_embed_backfill).toBe(true);
|
|
});
|
|
|
|
test('--priority normal maps to 0', async () => {
|
|
const { exitCode } = await capture(['--source', 'default', '--priority', 'normal']);
|
|
expect(exitCode).toBeNull();
|
|
const queue = new MinionQueue(engine);
|
|
const jobs = await queue.getJobs({ name: 'sync', limit: 5 });
|
|
expect(jobs[0].priority).toBe(0);
|
|
});
|
|
|
|
test('--priority low maps to 5', async () => {
|
|
const { exitCode } = await capture(['--source', 'default', '--priority', 'low']);
|
|
expect(exitCode).toBeNull();
|
|
const queue = new MinionQueue(engine);
|
|
const jobs = await queue.getJobs({ name: 'sync', limit: 5 });
|
|
expect(jobs[0].priority).toBe(5);
|
|
});
|
|
});
|