mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
eec2d2bf7b
* fix: bound tree-sitter chunker + harden walker + plumb strategy
`gbrain sync --strategy code` against a 1500-file repo could pin one
thread at 99% CPU for hours with zero disk writes and a `page_count`
that stayed at 0. Three real defects, all closed in one commit:
1. **Tree-sitter chunker had no wall-clock cap.** A single pathological
file could wedge the whole sync inside WASM. New `parseWithTimeout`
helper in src/core/chunkers/code.ts wraps `parser.parse()` with
`setTimeoutMicros(timeoutMs * 1000)`, throws `ChunkerTimeoutError`
on null, and the caller's try/finally reaps parser+tree (closes the
leak codex flagged where the catch block returned without delete()).
Default 30s, override via `GBRAIN_CHUNKER_TIMEOUT_MS`. Falls back to
recursive chunks on timeout — degrades search quality on that one
file, doesn't wedge sync.
2. **Code-strategy first-sync silently no-op'd on code files.**
`performFullSync` called `runImport(repoPath)` with no strategy;
`runImport` only ever walked `.md`/`.mdx`. Now `opts.strategy`
threads end-to-end (full-sync write path AND dry-run). Code files
actually reach the dispatcher, which already routes them to
`importCodeFile` correctly.
3. **Walker was thrice-redundant.** `collectMarkdownFiles` (lstat-safe,
import path) and `walkSyncableFiles` (statSync, cost-preview path,
weaker for no good reason) collapsed into one hardened
`collectSyncableFiles` in src/commands/import.ts: lstat + symlink-
skip with canonical log line; inode-cycle Map keyed on
`${st_dev}:${st_ino}` (defense-in-depth for non-symlink loops);
`MAX_WALK_DEPTH=32` structural backstop with `GBRAIN_MAX_WALK_DEPTH`
override; `.sort()` output (codex C8: `runImport`'s checkpoint
resume is index-based against a sorted list). Walker-context
multimodal carve-out preserved at one site (codex C5).
Plus structured `[gbrain phase] <name> start/done` stderr lines on
git_pull, fullsync.import, collect_files, and per-file slow path
(>5s). When the next hang lands, log says which phase wedged.
Tests:
- `test/sync-walker-symlink.test.ts` — 7 cases (self-symlink loop,
symlink-chain inode cycle, max-depth bailout, strategy filter,
dot-dir skip, multimodal preservation, deterministic ordering)
- `test/chunker-timeout.test.ts` — 7 cases (parser-stub seam,
ChunkerTimeoutError shape, env wiring, fallback behavior, fail-loud
if setTimeoutMicros API missing, cleanup contract under exception)
Smoke against the user's actual amarillo-v2 repo: 494 code files
walked in 22ms, 2 symlinks skipped with the canonical log line.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* chore: bump version 0.30.1 → 0.31.2 + CHANGELOG + TODOS
VERSION 0.31.2, package.json synced. CHANGELOG entry under [0.31.2]
with full release-summary + numbers + upgrader-cost note + To take
advantage block. v0.30.2 entry preserved below from master. TODOS.md
files the gbrain query <common-keyword> 7-day-zombie investigation
(PIDs 39429, 46624) and the deferred amarillo-shape PGLite + Postgres
E2E as v0.31.3 follow-ups.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(test): use withEnv() helper instead of direct process.env mutation
CI's check-test-isolation lint (rule R1) flagged the two new test files
for mutating process.env directly. The repo-wide convention is to wrap
env mutations in withEnv() (test/helpers/with-env.ts), which saves +
restores prior values via try/finally even when the callback throws.
Direct process.env writes leak across files in the same bun test
process (parallel runner loads multiple files into one shard process).
Both files refactored:
- test/sync-walker-symlink.test.ts (GBRAIN_EMBEDDING_MULTIMODAL)
- test/chunker-timeout.test.ts (GBRAIN_CHUNKER_TIMEOUT_MS)
All 14 cases still pass. `bun run verify` clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
113 lines
5.1 KiB
JSON
113 lines
5.1 KiB
JSON
{
|
|
"name": "gbrain",
|
|
"version": "0.31.2",
|
|
"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:admin": "cd admin && bun run build",
|
|
"build:schema": "bash scripts/build-schema.sh",
|
|
"build:llms": "bun run scripts/build-llms.ts",
|
|
"build:pglite-snapshot": "bun run scripts/build-pglite-snapshot.ts",
|
|
"test": "bash scripts/run-unit-parallel.sh",
|
|
"test:full": "bun run verify && bash scripts/run-unit-parallel.sh && bun run test:slow && ([ -n \"$DATABASE_URL\" ] && bash scripts/run-e2e.sh || echo '[test:full] skipped E2E (no DATABASE_URL); run docker-compose -f docker-compose.ci.yml up + bun run test:e2e to include' 1>&2)",
|
|
"verify": "bun run check:privacy && bun run check:jsonb && bun run check:progress && bun run check:test-isolation && bun run check:wasm && bun run check:admin-build && bun run check:admin-scope-drift && bun run check:cli-exec && bun run typecheck",
|
|
"check:admin-scope-drift": "scripts/check-admin-scope-drift.sh",
|
|
"check:cli-exec": "scripts/check-cli-executable.sh",
|
|
"check:all": "scripts/check-privacy.sh && scripts/check-jsonb-pattern.sh && scripts/check-progress-to-stdout.sh && scripts/check-no-legacy-getconnection.sh && scripts/check-test-isolation.sh && scripts/check-trailing-newline.sh && scripts/check-wasm-embedded.sh && scripts/check-exports-count.sh && scripts/check-admin-build.sh && scripts/check-admin-scope-drift.sh && scripts/check-cli-executable.sh",
|
|
"check:wasm": "scripts/check-wasm-embedded.sh",
|
|
"check:newlines": "scripts/check-trailing-newline.sh",
|
|
"test:e2e": "bash scripts/run-e2e.sh",
|
|
"test:slow": "bash scripts/run-slow-tests.sh",
|
|
"test:profile": "bash scripts/profile-tests.sh",
|
|
"test:serial": "bash scripts/run-serial-tests.sh",
|
|
"ci:local": "bash scripts/ci-local.sh",
|
|
"ci:local:diff": "bash scripts/ci-local.sh --diff",
|
|
"ci:select-e2e": "bun run scripts/select-e2e.ts",
|
|
"typecheck": "tsc --noEmit",
|
|
"check:jsonb": "scripts/check-jsonb-pattern.sh",
|
|
"check:privacy": "scripts/check-privacy.sh",
|
|
"check:progress": "scripts/check-progress-to-stdout.sh",
|
|
"check:exports-count": "scripts/check-exports-count.sh",
|
|
"check:admin-build": "scripts/check-admin-build.sh",
|
|
"check:test-isolation": "scripts/check-test-isolation.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": {
|
|
"@ai-sdk/anthropic": "^3.0.71",
|
|
"@ai-sdk/google": "^3.0.64",
|
|
"@ai-sdk/openai": "^3.0.53",
|
|
"@ai-sdk/openai-compatible": "^2.0.41",
|
|
"@anthropic-ai/sdk": "^0.30.0",
|
|
"@aws-sdk/client-s3": "^3.1028.0",
|
|
"@dqbd/tiktoken": "^1.0.22",
|
|
"@electric-sql/pglite": "0.4.3",
|
|
"@jsquash/avif": "^2.1.1",
|
|
"@jsquash/png": "^3.1.1",
|
|
"@modelcontextprotocol/sdk": "1.29.0",
|
|
"ai": "^6.0.168",
|
|
"cookie-parser": "^1.4.7",
|
|
"cors": "^2.8.5",
|
|
"eventsource-parser": "^3.0.8",
|
|
"exifr": "^7.1.3",
|
|
"express": "^5.1.0",
|
|
"express-rate-limit": "^7.5.0",
|
|
"gray-matter": "^4.0.3",
|
|
"heic-decode": "^2.1.0",
|
|
"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",
|
|
"zod": "^4.3.6"
|
|
},
|
|
"devDependencies": {
|
|
"@types/bun": "latest",
|
|
"@types/cookie-parser": "^1.4.7",
|
|
"@types/cors": "^2.8.19",
|
|
"@types/express": "^5.0.6",
|
|
"bun-types": "^1.3.13",
|
|
"typescript": "^5.6.0"
|
|
},
|
|
"trustedDependencies": [
|
|
"@electric-sql/pglite"
|
|
],
|
|
"engines": {
|
|
"bun": ">=1.3.10"
|
|
},
|
|
"license": "MIT"
|
|
}
|