mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
410c6978a4
* feat: classify Anthropic prompt-too-long as UnrecoverableError
The subagent handler now detects 400 "prompt is too long" responses
from the Anthropic SDK and rethrows as UnrecoverableError. The worker
already routes UnrecoverableError straight to `dead`, so doomed jobs
fail terminally on first attempt instead of stalling 3x with the same
oversized prompt.
isPromptTooLongError matches the production message verbatim
("prompt is too long: N tokens > N maximum"), case-insensitive, on
both the outer message and inner error.message paths. Defensive
secondary match for status=400 + invalid_request_error/request_too_large
with the words "too long"/"exceed"/"maximum".
9 unit cases pin the detection: production wording, case folding,
nested SDK shape, defensive 400 paths, unrelated 400s, transient
errors, null/empty inputs.
* feat: model-aware chunking + slug-rewrite for dream synthesize
The synthesize phase now chunks oversized transcripts at paragraph
boundaries instead of submitting one giant prompt that 400s on
Anthropic. Closes the v0.30 dream-cycle queue clog where 1.7M-token
transcripts dead-lettered after 3 stalls and re-discovered every
cycle.
D1: per-chunk budget = floor(model_context_tokens × 0.9 × 3.5).
MODEL_CONTEXT_TOKENS keys on resolved Anthropic ids (Opus 4.7 = 1M,
Sonnet 4.6 = 200K, Haiku = 200K). Non-Anthropic models fall back to
180K-token safe default with a once-per-process stderr warning.
dream.synthesize.max_prompt_tokens overrides the model lookup
(token-shaped, name from PR #748, floor 100K).
D5: on max_chunks_per_transcript cap hit, log + skip; do NOT write to
dream_verdicts. Closes the cache-poisoning class — next cycle
re-attempts under whatever budget is then current.
D6: orchestrator-side deterministic slug rewrite, zero Sonnet trust.
collectChildPutPageSlugs raw-fetches every (job_id, slug) pair (no
SELECT DISTINCT — that erased the collision evidence the audit
claimed to detect) and rewrites bare-hash6 slugs to <hash6>-c<idx>
for chunked children.
D8: pre-fan-out lookup of completed legacy `dream:synth:<filePath>:
<hash16>` jobs. Transcripts already synthesized under the
single-chunk shape skip submission with `already_synthesized_legacy_
single_chunk` instead of resubmitting under chunked keys.
D9: hash-deterministic chunk boundaries. The 3-tier ladder lifted
from PR #748 (## Topic: > --- > nearest \\n) is fed a back-half
search-window offset derived from contentHash. Same content always
chunks identically across runs; chunk N of a previously-failed
transcript produces byte-identical content on retry.
D10: 24-chunk default cap, operator-configurable via
dream.synthesize.max_chunks_per_transcript.
18 unit cases pin the chunker (boundary ladder, hash determinism,
hard fallback, slug rewrite all 7 shapes). 4 PGLite E2E cases pin
fan-out shape (single-chunk legacy key parity, multi-chunk chunked
key shape) + skip paths (D5 cap hit no verdict-cache write, D8
legacy-key skip).
Credits PR #748 (Wintermute) for the boundary ladder, config key
naming, and 3.5 chars/token estimator. This branch supersedes #748
with the structural safeguards (model-aware budget, terminal-error
classify, slug rewrite, hash-determinism, doctor surfacing).
* feat: surface dead-lettered prompt_too_long jobs in doctor queue_health
queue_health gains a 4th subcheck counting dead `subagent` jobs in
the last 24h whose error_text starts with `prompt_too_long:`. When
present, prints a fix hint pointing at
`gbrain dream --phase synthesize --dry-run --json` to identify the
fat transcripts and naming the two operator escape hatches
(`dream.synthesize.max_prompt_tokens` for budget tuning,
larger-context model for capacity).
Operators now see the chunking failure mode without grepping
minion_jobs by hand.
* chore: bump version and changelog (v0.30.2)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: update README + CLAUDE.md for v0.30.2
- README dream help: 8-phase → 9-phase, mention v0.30.2 chunking + config keys
- CLAUDE.md synthesize.ts: chunker + per-chunk idempotency + D6 slug rewrite + D7 scope + D8 legacy-key
- CLAUDE.md subagent.ts: prompt_too_long terminal classification
- CLAUDE.md doctor.ts: queue_health subcheck 4 (dead-lettered prompt_too_long)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* docs: regenerate llms-full.txt after v0.30.2 CLAUDE.md updates
The docs/ pass extended three Key Files entries in CLAUDE.md
(synthesize.ts, subagent.ts, doctor.ts). The auto-derived
llms-full.txt bundle picks up those CLAUDE.md changes via
build-llms; the build-llms test caught the drift in CI.
Generated by: bun run build:llms
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
111 lines
5.1 KiB
JSON
111 lines
5.1 KiB
JSON
{
|
|
"name": "gbrain",
|
|
"version": "0.30.2",
|
|
"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",
|
|
"@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",
|
|
"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"
|
|
}
|