mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
e734937254
* fix: pass sourceId in cycle sync phase to prevent full reimport cycle.ts calls performSync without sourceId, so it always reads the global config.sync.last_commit key instead of the per-source sources.last_commit. When the global anchor gets garbage-collected (after a force push or rebase), sync falls back to a full reimport of all files — on a large brain this takes 30+ minutes and blocks the autopilot cycle. The fix resolves the source id from the brain directory by querying the sources table. When a matching source exists, sync reads the per-source anchor which is updated on every successful sync and stays in sync with the repo history. Falls back gracefully to the global config path for pre-v0.18 brains without a sources table. * v0.22.5: tests + version bump for sync-cycle-source-id fix Adds 6 regression tests in test/core/cycle.test.ts pinning the new resolveSourceForDir() helper added to src/core/cycle.ts in this PR: 1. Seeded sources row → performSync receives matching sourceId 2. No matching row → sourceId=undefined (falls through to global key) 3. Different brainDir than registered source → undefined (no cross-match) 4. sources table missing (very old brain) → catch returns undefined, sync still runs. Uses a fresh PGLiteEngine because initSchema() only re-runs PENDING migrations; DROP TABLE on the shared engine would leave it permanently degraded for every later test in the file. (Codex review caught this landmine.) 5. Multiple rows with same local_path → resolver returns one matching id (non-deterministic; SQL has no ORDER BY). Documents the contract for the v0.23 UNIQUE-constraint follow-up. 6. Empty-string id row → resolver propagates "" (defensive case Codex flagged: schema PK prevents NULL but '' can be inserted). Extends the performSync mock at line 51-65 to also capture sourceId. Bumps: - VERSION: 0.22.4 → 0.22.5 - package.json: 0.22.4 → 0.22.5 - CHANGELOG.md: new [0.22.5] entry following v0.22.4 voice (release summary + numbers table + behavior matrix + To-take-advantage block + itemized changes + for-contributors) - CLAUDE.md: annotates src/core/cycle.ts entry with v0.22.5 (#475) note - llms-full.txt: regenerated via bun run build:llms Test results: - Unit: 28 pass / 0 fail in test/core/cycle.test.ts (22 prior + 6 new) - Full unit suite: pass (exit 0) - E2E: 236 pass / 0 fail across 26 files Plan + codex outside-voice review at: ~/.claude/plans/whimsical-bubbling-goose.md Follow-up TODOs filed for v0.23: - Normalize brainDir + sources.local_path before SQL compare - Add UNIQUE index on sources.local_path - Narrow resolveSourceForDir's catch to PG 42P01 (undefined_table) - Add doctor check for config.sync.last_commit / sources divergence Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: typecheck error in cycle.test.ts test 5 (sourceId regression) CI typecheck failed because `toContain()` on `string[]` rejects the `string | undefined` produced by `syncCalls.at(-1)?.sourceId`'s optional chain. Tests 1, 4, and 6 use `toBe()` which accepts `string | undefined` through its overload, but `toContain()` is stricter. Fix: pull the value into a typed variable, assert it's defined, then check membership. Makes the contract explicit ("resolver returned a defined sourceId, and it was one of the matching ids") instead of relying on a silent undefined → no-match-in-array assertion. Locally: - bun run typecheck: clean - bun test test/core/cycle.test.ts: 28 pass / 0 fail (75 expect calls) - All CI gate scripts: OK (jsonb, progress-to-stdout, wasm-embedded) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ci: add --timeout=60000 to E2E runner to prevent setupDB flake PR #475's Tier 1 (Mechanical) CI job hit a 5000.09ms beforeAll hook timeout in `E2E: Tags > (unnamed)`. Cause: scripts/run-e2e.sh invokes `bun test "$f"` without a --timeout flag, falling back to bun's 5s default. setupDB() does TRUNCATE CASCADE on ~30 tables, and on a CI runner under load that can exceed 5s. Match what the unit suite uses (--timeout=60000 in package.json's "test" script). Same 1m ceiling, no behavior change for healthy runs; just removes the artificial 5s floor on hooks. Verified locally: bun test --timeout=60000 test/e2e/mechanical.test.ts runs 78 pass / 0 fail in 27.99s against a fresh pgvector pg16 docker container. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: root <root@localhost> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
73 lines
2.9 KiB
JSON
73 lines
2.9 KiB
JSON
{
|
|
"name": "gbrain",
|
|
"version": "0.22.5",
|
|
"description": "Postgres-native personal knowledge brain with hybrid RAG search",
|
|
"type": "module",
|
|
"main": "src/core/index.ts",
|
|
"bin": {
|
|
"gbrain": "src/cli.ts"
|
|
},
|
|
"exports": {
|
|
".": "./src/core/index.ts",
|
|
"./engine": "./src/core/engine.ts",
|
|
"./types": "./src/core/types.ts",
|
|
"./operations": "./src/core/operations.ts",
|
|
"./minions": "./src/core/minions/index.ts",
|
|
"./engine-factory": "./src/core/engine-factory.ts",
|
|
"./pglite-engine": "./src/core/pglite-engine.ts",
|
|
"./link-extraction": "./src/core/link-extraction.ts",
|
|
"./import-file": "./src/core/import-file.ts",
|
|
"./transcription": "./src/core/transcription.ts",
|
|
"./embedding": "./src/core/embedding.ts",
|
|
"./config": "./src/core/config.ts",
|
|
"./markdown": "./src/core/markdown.ts",
|
|
"./backoff": "./src/core/backoff.ts",
|
|
"./search/hybrid": "./src/core/search/hybrid.ts",
|
|
"./search/expansion": "./src/core/search/expansion.ts",
|
|
"./extract": "./src/commands/extract.ts"
|
|
},
|
|
"scripts": {
|
|
"dev": "bun run src/cli.ts",
|
|
"build": "bun build --compile --outfile bin/gbrain src/cli.ts",
|
|
"build:all": "bun build --compile --target=bun-darwin-arm64 --outfile bin/gbrain-darwin-arm64 src/cli.ts && bun build --compile --target=bun-linux-x64 --outfile bin/gbrain-linux-x64 src/cli.ts",
|
|
"build:schema": "bash scripts/build-schema.sh",
|
|
"build:llms": "bun run scripts/build-llms.ts",
|
|
"test": "scripts/check-jsonb-pattern.sh && scripts/check-progress-to-stdout.sh && scripts/check-wasm-embedded.sh && bun run typecheck && bun test --timeout=60000",
|
|
"check:wasm": "scripts/check-wasm-embedded.sh",
|
|
"test:e2e": "bash scripts/run-e2e.sh",
|
|
"typecheck": "tsc --noEmit",
|
|
"check:jsonb": "scripts/check-jsonb-pattern.sh",
|
|
"check:progress": "scripts/check-progress-to-stdout.sh",
|
|
"postinstall": "command -v gbrain >/dev/null 2>&1 && gbrain apply-migrations --yes --non-interactive || echo '[gbrain] postinstall skipped. If installed via bun install -g github:...: run `gbrain doctor` and `gbrain apply-migrations --yes` manually. See https://github.com/garrytan/gbrain/issues/218' 1>&2",
|
|
"prepublish:clawhub": "bun run build:all",
|
|
"publish:clawhub": "clawhub package publish . --family bundle-plugin"
|
|
},
|
|
"openclaw": {
|
|
"compat": {
|
|
"pluginApi": ">=2026.4.0"
|
|
}
|
|
},
|
|
"dependencies": {
|
|
"@anthropic-ai/sdk": "^0.30.0",
|
|
"@aws-sdk/client-s3": "^3.1028.0",
|
|
"@dqbd/tiktoken": "^1.0.22",
|
|
"@electric-sql/pglite": "0.4.3",
|
|
"@modelcontextprotocol/sdk": "^1.0.0",
|
|
"gray-matter": "^4.0.3",
|
|
"marked": "^18.0.0",
|
|
"openai": "^4.0.0",
|
|
"pgvector": "^0.2.0",
|
|
"postgres": "^3.4.0",
|
|
"tree-sitter-wasms": "0.1.13",
|
|
"web-tree-sitter": "0.22.6"
|
|
},
|
|
"devDependencies": {
|
|
"@types/bun": "latest",
|
|
"typescript": "^5.6.0"
|
|
},
|
|
"trustedDependencies": [
|
|
"@electric-sql/pglite"
|
|
],
|
|
"license": "MIT"
|
|
}
|