mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
041d89babe
* feat(conversation-parser): add bold-name-no-time builtin (Circleback/Granola/Zoom, no timestamp) The 14th built-in pattern parses `**Speaker:** text` transcripts with NO per-line timestamp — the shape Circleback / Granola / Zoom emit. Every prior builtin required a time anchor, so this shape matched nothing: a production brain had 104 conversation pages + 3,423 eligible pages silently extracting zero facts. Messages anchor at T00:00:00Z of the frontmatter date (no fabricated wall-clock; line order preserves sequence), same convention as irc-classic. Hardening beyond the original community proposal: - regex `/^\*\*(?!\[)(.+?):\*\*\s*(.*)$/`: the colon-inside-bold (NOT declaration order) is what prevents shadowing bold-paren-time; the `(?!\[)` lookahead rejects telegram-bracket `**[18:37] Name:**` so disabling telegram-bracket yields an honest no_match instead of speaker="[18:37] Name". - new optional PatternEntry.score_full_body: `**Label:** text` is a common prose idiom, so a notes page with bold labels clustered in its first 10 lines scored 0.3 on the head pass (NOT < SCORING_HEAD_TRIGGER_THRESHOLD, so the full-body fallback never fired) and cleared the 0.05 floor. parse.ts now recomputes the winner's score over the full body before the floor, so such a page drops to its true low density and stays no_match. - scrubbed pre-existing real names from bold-paren-time test_positive samples (privacy rule). Fixtures use placeholder names only. Pinned by new bold-name-no-time + clustered-head no_match cases in parse.test.ts and the eval corpus. Co-Authored-By: garrytan-agents <noreply@github.com> Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(orphans): scope orphan_ratio + find_orphans by source; fix total_linkable denominator `gbrain doctor --source <id>` and `gbrain orphans --source <id>` now scope the orphan scan to that source instead of reporting brain-wide. Three fixes: - findOrphanPages(opts?: { sourceId?, sourceIds? }) on both engines scopes the CANDIDATE set (scalar `= $1` or federated `= ANY($1::text[])`). Inbound links from ANY source still count, so a page in source X linked FROM source Y is reachable and NOT an orphan of X (the deliberate, less-surprising definition). - corrected the total_linkable denominator in findOrphans: it now enumerates all live pages (scoped) and subtracts every excluded-by-slug page, not just excluded orphans. The old `total - excludedOrphans` left excluded NON-orphan pages (templates/, scratch/) with inbound links in the denominator, inflating it and suppressing warnings. Changes orphan_ratio output for every brain, in the accurate direction. - the find_orphans MCP op threads sourceScopeOpts(ctx), closing a cross-source read leak where a source-bound OAuth client saw brain-wide orphans (v0.34.1 source-isolation class). doctor uses an explicit `--source` flag parse (NOT resolveSourceWithTier, which would scope bare invocations to a default), and under explicit --source reports the ratio with a low-scale caveat below 100 entity pages instead of a vacuous "ok". Thin-client doctor --source orphan_ratio deferred (TODOS.md). Pinned by test/orphans-source-scope.test.ts (PGLite: scoping, cross-source inbound, denominator, find_orphans op scope) + a Postgres↔PGLite parity case in test/e2e/engine-parity.test.ts (scalar + federated binding). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: v0.41.29.0 — bold-name-no-time + orphan source scoping VERSION + package.json → 0.41.29.0; CHANGELOG entry; CLAUDE.md conversation-parser (13→14 patterns) + orphans source-scoping notes; regenerated llms bundles; TODOS for thin-client doctor --source + check-test-real-names widening. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: garrytan-agents <noreply@github.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
146 lines
7.4 KiB
JSON
146 lines
7.4 KiB
JSON
{
|
|
"name": "gbrain",
|
|
"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",
|
|
"./ai/gateway": "./src/core/ai/gateway.ts",
|
|
"./extract": "./src/commands/extract.ts",
|
|
"./ingestion": "./src/core/ingestion/index.ts",
|
|
"./ingestion/test-harness": "./src/core/ingestion/test-harness.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 && cd .. && bun run scripts/build-admin-embedded.ts",
|
|
"build:admin-embedded": "bun run scripts/build-admin-embedded.ts",
|
|
"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": "bash scripts/run-verify-parallel.sh",
|
|
"check:source-config-leak": "scripts/check-source-config-leak.sh",
|
|
"check:no-pii-agent-voice": "scripts/check-no-pii-in-agent-voice.sh",
|
|
"check:synthetic-corpus-privacy": "scripts/check-synthetic-corpus-privacy.sh",
|
|
"check:system-of-record": "scripts/check-system-of-record.sh",
|
|
"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-proposal-pii.sh && scripts/check-test-real-names.sh && scripts/check-jsonb-pattern.sh && scripts/check-source-id-projection.sh && scripts/check-source-config-leak.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 && scripts/check-skill-brain-first.sh && scripts/check-operations-filter-bypass.sh && scripts/check-gateway-routed-no-direct-anthropic.sh && scripts/check-worker-pool-atomicity.sh && scripts/check-no-double-retry.sh && scripts/check-batch-audit-site.sh",
|
|
"check:gateway-routed": "scripts/check-gateway-routed-no-direct-anthropic.sh",
|
|
"check:worker-pool-atomicity": "scripts/check-worker-pool-atomicity.sh",
|
|
"check:resolver": "bun src/cli.ts check-resolvable --strict --skills-dir skills/",
|
|
"check:skill-brain-first": "scripts/check-skill-brain-first.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:heavy": "bash scripts/run-heavy.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:no-double-retry": "scripts/check-no-double-retry.sh",
|
|
"check:batch-audit-site": "scripts/check-batch-audit-site.sh",
|
|
"check:worker-lock-renewal-shape": "scripts/check-worker-lock-renewal-shape.sh",
|
|
"check:source-id-projection": "scripts/check-source-id-projection.sh",
|
|
"check:privacy": "scripts/check-privacy.sh",
|
|
"check:proposal-pii": "scripts/check-proposal-pii.sh",
|
|
"check:eval-glossary": "scripts/check-eval-glossary-fresh.sh",
|
|
"check:test-names": "scripts/check-test-real-names.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:admin-embedded": "scripts/check-admin-embedded.sh",
|
|
"check:test-isolation": "scripts/check-test-isolation.sh",
|
|
"check:fuzz-purity": "scripts/check-fuzz-purity.sh",
|
|
"check:operations-filter-bypass": "scripts/check-operations-filter-bypass.sh",
|
|
"check:fixture-privacy": "scripts/check-fixture-privacy.sh",
|
|
"check:conversation-parser": "bun src/cli.ts eval conversation-parser test/fixtures/conversation-formats/all.jsonl --no-llm",
|
|
"check:source-scope-onboard": "scripts/check-source-scope-onboard.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"
|
|
},
|
|
"extensions": [
|
|
"./src/openclaw-context-engine.ts"
|
|
]
|
|
},
|
|
"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",
|
|
"chokidar": "^4.0.3",
|
|
"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",
|
|
"js-yaml": "^3.14.2",
|
|
"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",
|
|
"@types/js-yaml": "^3.12.10",
|
|
"bun-types": "^1.3.13",
|
|
"fast-check": "^4.8.0",
|
|
"typescript": "^5.6.0"
|
|
},
|
|
"trustedDependencies": [
|
|
"@electric-sql/pglite"
|
|
],
|
|
"engines": {
|
|
"bun": ">=1.3.10"
|
|
},
|
|
"license": "MIT",
|
|
"version": "0.41.29.0"
|
|
}
|