mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* fix-wave: dream.* DB merge + batch retry + extract_atoms idempotency + ze-switch env-gate + doctor check Closes PRs #1414, #1416, #1421 (rebuilt from designs by @garrytan-agents with structural improvements from /plan-eng-review + codex outside-voice). Three production reliability fixes in one wave: 1. dream.* DB-config merge (closes PR #1416 silent-config gap) - loadConfigWithEngine() sparse-merge extends with 7 dream.* keys - File > DB > defaults precedence (no GBRAIN_DREAM_* env vars) - extract-atoms switches to loadConfigWithEngine() so DB-plane keys reach it 2. Batch retry on transient connection drops (closes PR #1416 ~30%-loss bug) - withRetry() pure primitive exported from src/commands/extract.ts - 6 flush() sites snapshot-before-clear with onRetry callback - Reuses isRetryableConnError from src/core/retry-matcher.ts - retry-matcher extended with GBrainError{problem:'No database connection'} 3. extract_atoms source-hash idempotency + page-based discovery (closes #1414) - One raw SQL with NOT EXISTS subquery replaces 6 listPages + N atom checks - sourceId threaded through every putPage call (codex caught real bug) - NULL content_hash filter + dream_generated exclusion + transcript-side idempotency - cycle.ts passes union of syncPagesAffected + synthesizeWrittenSlugs 4. ze-switch pre-apply + pre-resume env-override gate (closes PR #1421) - Gate fires FIRST in apply AND resume; zero setConfig calls on refusal - ASCII warning box (no Unicode per repo D10) - --ignore-env-override escape hatch for power users - ApplyResult extended with refused variant 5. doctor embedding_env_override check (defense-in-depth for #1421) - Cross-surface parity: buildChecks() + doctorReportRemote() - Uses Check.details (not Check.issues per codex schema review) Co-Authored-By: garrytan-agents <garrytan-agents@users.noreply.github.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.41.10.0) Adds 61 new tests across 5 new files pinning the fix-wave contracts: - test/extract-batch-retry.test.ts (16 cases) — withRetry primitive + snapshot contract - test/extract-atoms-page-discovery.test.ts (17 cases) — discovery SQL + dual-source idempotency - test/ze-switch-env-override.test.ts (17 cases) — env-gate apply + resume + ZERO-setConfig assertion - test/doctor-embedding-env-override.test.ts (7 cases) — cross-surface parity - test/e2e/extract-atoms-discovery-sql.test.ts (4 cases) — real-Postgres parity for raw SQL Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(test): pin gateway to 1536-dim in 2 PGLite tests that hardcode 1536-vector inserts CI shards 1 + 4 failed persistently (not flake — confirmed via retry) after the v0.41.6.0 merge with this error: error: expected 1280 dimensions, not 1536 file: "vector.c", routine: "CheckExpectedDim" Two test files insert 1536-dim Float32Array vectors into `content_chunks.embedding` / `facts.embedding`, but v0.41.5.0 flipped `DEFAULT_EMBEDDING_DIMENSIONS` from 1536 to 1280 (ZE Matryoshka default). On a fresh CI bun process where no prior test pre-configured the gateway, `initSchema()` sizes the vector column at vector(1280) and the inserts throw. Locally this is hidden when an earlier test file in the shard happens to have called `configureGateway({embedding_dimensions: 1536})` — that state leaks forward through bun's shared process. The v0.41.6.0 LPT shard re-balancing reordered files so these two ran cold, surfacing the latent bug. Fix follows the canonical hermetic pattern from test/consolidate-valid-until.test.ts:23-34: pin the gateway to 1536d in beforeAll, reset in afterAll. Test is now isolated from shard ordering. test/search-types-filter.test.ts — shard 1 fail test/operations-find-trajectory.test.ts — shard 4 (6 fails) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: empty commit to trigger CI * chore: trigger CI again * chore: renumber v0.41.10.0 -> v0.41.10.1 Per request — version slot moved to .1 micro tier to leave .0 available for unrelated wave landing on master. --------- Co-authored-by: garrytan-agents <garrytan-agents@users.noreply.github.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
302 lines
13 KiB
TypeScript
302 lines
13 KiB
TypeScript
// Phase 4 (F3): loadConfigWithEngine() DB-merge contract.
|
|
//
|
|
// Verifies precedence (env > file > DB > defaults) for the new v0.27.1
|
|
// multimodal flags so `gbrain config set embedding_multimodal true`
|
|
// actually flips the runtime gate even when the file plane is silent.
|
|
|
|
import { describe, expect, test } from 'bun:test';
|
|
import { loadConfigWithEngine, type GBrainConfig } from '../src/core/config.ts';
|
|
|
|
interface FakeEngine {
|
|
getConfig(key: string): Promise<string | null | undefined>;
|
|
}
|
|
|
|
function makeEngine(map: Record<string, string | null | undefined>): FakeEngine {
|
|
return {
|
|
async getConfig(key: string) {
|
|
return map[key];
|
|
},
|
|
};
|
|
}
|
|
|
|
describe('loadConfigWithEngine (Phase 4 / F3)', () => {
|
|
test('synthesizes a minimal base when base config is null (v0.36 codex /ship #3)', async () => {
|
|
// Pre-v0.36 this returned null and skipped DB-plane merge entirely.
|
|
// That meant env-only Postgres installs (no file config) couldn't see
|
|
// DB-plane overrides set via `gbrain config set` — the documented
|
|
// smoke test for `search_embedding_column` would silently fail.
|
|
// The fix synthesizes a minimal `{ engine: 'postgres' }` base so DB
|
|
// merge still runs; downstream callers either find the DB key or
|
|
// fall through to defaults.
|
|
const result = await loadConfigWithEngine(makeEngine({}), null);
|
|
expect(result).not.toBeNull();
|
|
expect(result?.engine).toBe('postgres');
|
|
});
|
|
|
|
test('DB-plane embedding_columns merge works even with null base (codex /ship #3 round-trip)', async () => {
|
|
// The whole point of the synthesized fallback: env-only installs
|
|
// calling `gbrain config set embedding_columns '...'` get those keys
|
|
// back when the resolver re-reads config. Verifies the merge path
|
|
// actually runs (not just that the function returns truthy).
|
|
const engine = makeEngine({
|
|
search_embedding_column: 'embedding_voyage',
|
|
embedding_columns: '{"embedding_voyage":{"provider":"voyage:voyage-3-large","dimensions":1024,"type":"vector"}}',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, null);
|
|
expect(merged?.search_embedding_column).toBe('embedding_voyage');
|
|
expect(merged?.embedding_columns?.embedding_voyage?.dimensions).toBe(1024);
|
|
});
|
|
|
|
test('DB flag fills in when file/env did not set it', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
embedding_multimodal: 'true',
|
|
embedding_image_ocr: 'false',
|
|
embedding_image_ocr_model: 'openai:gpt-4o-mini',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal).toBe(true);
|
|
expect(merged?.embedding_image_ocr).toBe(false);
|
|
expect(merged?.embedding_image_ocr_model).toBe('openai:gpt-4o-mini');
|
|
});
|
|
|
|
test('file/env precedence: file value wins over DB value', async () => {
|
|
const base: GBrainConfig = {
|
|
engine: 'pglite',
|
|
embedding_multimodal: false,
|
|
embedding_image_ocr_model: 'file-set-model',
|
|
};
|
|
const engine = makeEngine({
|
|
embedding_multimodal: 'true',
|
|
embedding_image_ocr_model: 'db-set-model',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal).toBe(false);
|
|
expect(merged?.embedding_image_ocr_model).toBe('file-set-model');
|
|
});
|
|
|
|
test('partial DB merge: only undefined fields fall through', async () => {
|
|
const base: GBrainConfig = {
|
|
engine: 'pglite',
|
|
embedding_multimodal: true,
|
|
// embedding_image_ocr NOT set in file plane
|
|
};
|
|
const engine = makeEngine({
|
|
embedding_multimodal: 'false',
|
|
embedding_image_ocr: 'true',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
// file/env wins for multimodal
|
|
expect(merged?.embedding_multimodal).toBe(true);
|
|
// DB fills in for ocr
|
|
expect(merged?.embedding_image_ocr).toBe(true);
|
|
});
|
|
|
|
test('engine.getConfig throwing is non-fatal — file/env config still returned', async () => {
|
|
const base: GBrainConfig = {
|
|
engine: 'pglite',
|
|
embedding_multimodal: true,
|
|
};
|
|
const engine: FakeEngine = {
|
|
async getConfig() {
|
|
throw new Error('config table missing');
|
|
},
|
|
};
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal).toBe(true);
|
|
});
|
|
|
|
test('null/empty DB values are ignored (not coerced to false)', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
embedding_multimodal: null,
|
|
embedding_image_ocr: '',
|
|
embedding_image_ocr_model: undefined,
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal).toBeUndefined();
|
|
expect(merged?.embedding_image_ocr).toBeUndefined();
|
|
expect(merged?.embedding_image_ocr_model).toBeUndefined();
|
|
});
|
|
|
|
test('non-"true" DB string values resolve to false (strict equality)', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
embedding_multimodal: 'TRUE', // wrong case
|
|
embedding_image_ocr: '1', // wrong format
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal).toBe(false);
|
|
expect(merged?.embedding_image_ocr).toBe(false);
|
|
});
|
|
|
|
// v0.28.11 (PR #719): embedding_multimodal_model precedence parity with the
|
|
// sibling embedding_image_ocr_model field. Confirms the new key participates
|
|
// in the same env > file > DB > undefined merge contract so that
|
|
// embedMultimodal() routes correctly regardless of which plane set it.
|
|
describe('embedding_multimodal_model precedence', () => {
|
|
test('DB value fills in when file/env did not set it', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
embedding_multimodal_model: 'voyage:voyage-multimodal-3',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal_model).toBe('voyage:voyage-multimodal-3');
|
|
});
|
|
|
|
test('file value wins over DB value', async () => {
|
|
const base: GBrainConfig = {
|
|
engine: 'pglite',
|
|
embedding_multimodal_model: 'voyage:voyage-multimodal-3',
|
|
};
|
|
const engine = makeEngine({
|
|
embedding_multimodal_model: 'voyage:voyage-3-large',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal_model).toBe('voyage:voyage-multimodal-3');
|
|
});
|
|
|
|
test('all unset stays undefined', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal_model).toBeUndefined();
|
|
});
|
|
|
|
test('null/empty DB string is ignored (does not clobber)', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
embedding_multimodal_model: '',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.embedding_multimodal_model).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
// v0.41.2.1 — dream.* DB-plane merge (closes PR #1416's silent-config bug).
|
|
// Precedence is file > DB > defaults per key. There is NO env layer for
|
|
// dream.* — adding env shadows is a separate PR (out of scope for the
|
|
// fix wave). These tests pin that contract.
|
|
describe('dream.* DB-plane merge (v0.41.2.1)', () => {
|
|
test('DB value fills in for all 5 dream.synthesize.* keys when base unset', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
'dream.synthesize.session_corpus_dir': '/tmp/sessions',
|
|
'dream.synthesize.meeting_transcripts_dir': '/tmp/meetings',
|
|
'dream.synthesize.verdict_model': 'anthropic:claude-haiku-4-5',
|
|
'dream.synthesize.max_prompt_tokens': '180000',
|
|
'dream.synthesize.max_chunks_per_transcript': '32',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream?.synthesize?.session_corpus_dir).toBe('/tmp/sessions');
|
|
expect(merged?.dream?.synthesize?.meeting_transcripts_dir).toBe('/tmp/meetings');
|
|
expect(merged?.dream?.synthesize?.verdict_model).toBe('anthropic:claude-haiku-4-5');
|
|
expect(merged?.dream?.synthesize?.max_prompt_tokens).toBe(180000);
|
|
expect(merged?.dream?.synthesize?.max_chunks_per_transcript).toBe(32);
|
|
});
|
|
|
|
test('DB value fills in for both dream.patterns.* keys when base unset', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
'dream.patterns.lookback_days': '45',
|
|
'dream.patterns.min_evidence': '4',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream?.patterns?.lookback_days).toBe(45);
|
|
expect(merged?.dream?.patterns?.min_evidence).toBe(4);
|
|
});
|
|
|
|
test('file value wins over DB value (per-key precedence)', async () => {
|
|
const base: GBrainConfig = {
|
|
engine: 'pglite',
|
|
dream: {
|
|
synthesize: { session_corpus_dir: '/from-file' },
|
|
patterns: { lookback_days: 7 },
|
|
},
|
|
};
|
|
const engine = makeEngine({
|
|
'dream.synthesize.session_corpus_dir': '/from-db',
|
|
'dream.synthesize.meeting_transcripts_dir': '/db-meetings',
|
|
'dream.patterns.lookback_days': '30',
|
|
'dream.patterns.min_evidence': '5',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream?.synthesize?.session_corpus_dir).toBe('/from-file');
|
|
expect(merged?.dream?.synthesize?.meeting_transcripts_dir).toBe('/db-meetings');
|
|
expect(merged?.dream?.patterns?.lookback_days).toBe(7);
|
|
expect(merged?.dream?.patterns?.min_evidence).toBe(5);
|
|
});
|
|
|
|
test('parent objects (cfg.dream, cfg.dream.synthesize, cfg.dream.patterns) are allocated even when file plane has none', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
'dream.synthesize.session_corpus_dir': '/just-this-one',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream).toBeDefined();
|
|
expect(merged?.dream?.synthesize).toBeDefined();
|
|
expect(merged?.dream?.synthesize?.session_corpus_dir).toBe('/just-this-one');
|
|
// patterns parent NOT allocated when no patterns key is set
|
|
expect(merged?.dream?.patterns).toBeUndefined();
|
|
});
|
|
|
|
test('invalid DB int values fall back to undefined (do not throw)', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
'dream.synthesize.max_prompt_tokens': 'abc',
|
|
'dream.patterns.min_evidence': 'not-a-number',
|
|
'dream.patterns.lookback_days': '-5', // negative; existing dbInt() rejects
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream?.synthesize?.max_prompt_tokens).toBeUndefined();
|
|
expect(merged?.dream?.patterns?.min_evidence).toBeUndefined();
|
|
expect(merged?.dream?.patterns?.lookback_days).toBeUndefined();
|
|
// cfg.dream stays undefined since no leaf populated
|
|
expect(merged?.dream).toBeUndefined();
|
|
});
|
|
|
|
test('empty DB values do not clobber unset file plane', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({
|
|
'dream.synthesize.session_corpus_dir': '',
|
|
'dream.synthesize.meeting_transcripts_dir': undefined,
|
|
'dream.synthesize.verdict_model': null,
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream).toBeUndefined();
|
|
});
|
|
|
|
test('cfg.dream stays undefined when neither plane sets anything', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine = makeEngine({});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream).toBeUndefined();
|
|
});
|
|
|
|
test('mixed: file sets synthesize.session_corpus_dir; DB sets patterns.lookback_days', async () => {
|
|
const base: GBrainConfig = {
|
|
engine: 'pglite',
|
|
dream: { synthesize: { session_corpus_dir: '/file-only' } },
|
|
};
|
|
const engine = makeEngine({
|
|
'dream.patterns.lookback_days': '14',
|
|
});
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream?.synthesize?.session_corpus_dir).toBe('/file-only');
|
|
expect(merged?.dream?.patterns?.lookback_days).toBe(14);
|
|
});
|
|
|
|
test('engine.getConfig throwing leaves dream.* unset (non-fatal, mirrors content_sanity)', async () => {
|
|
const base: GBrainConfig = { engine: 'pglite' };
|
|
const engine: FakeEngine = {
|
|
async getConfig() {
|
|
throw new Error('config table missing');
|
|
},
|
|
};
|
|
const merged = await loadConfigWithEngine(engine, base);
|
|
expect(merged?.dream).toBeUndefined();
|
|
expect(merged?.engine).toBe('pglite');
|
|
});
|
|
});
|
|
});
|