Luiz Gustavo
|
189a771cbe
|
W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard
CI / Web — typecheck + lint + build (push) Failing after 38s
CI / Scripts — Python smoke (push) Failing after 3s
CI / Web — npm audit (push) Failing after 33s
CI / Retrieval — golden set (Recall@5 + MRR) (push) Failing after 4s
Migrations:
- 0004_investigation_bureau.sql: 7 new tables (investigation_jobs + evidence,
hypotheses, contradictions, witnesses, gaps, residual_uncertainties), id
sequences, pg_notify trigger on investigation_jobs, RLS read-only public,
investigator role with least-privilege grants (no service_role).
- 0005_investigator_write_policies.sql: fixup adding RLS INSERT/UPDATE
policies bound to investigator + service_role + postgres (RLS with only a
SELECT policy was silently blocking the worker's claim UPDATE).
investigator-runtime/ (new Bun + TS container):
- src/main.ts: LISTEN/NOTIFY poller, claim-with-SKIP-LOCKED, drain pool,
healthcheck file, graceful SIGTERM shutdown.
- src/orchestrator.ts: chief-detective dispatch (evidence_chain → Locard).
Marks job failed when all per-item outputs error; surfaces first errors.
- src/lib/{env,pg,audit,ids,claude}.ts: typed config (gate #8), pool +
dedicated LISTEN client, NDJSON audit, sequence allocator (E-NNNN etc),
claude -p subprocess with quota detection (api_error_status=429).
- src/tools/write_evidence.ts: schema-validate (grade A/B/C custody steps),
resolve chunk_pk via FK, verify verbatim_excerpt actually appears in
chunk content, INSERT + render case/evidence/E-NNNN.md + audit.
- src/detectives/locard.ts: load chunk → call Claude with locard.md system
prompt → parse strict JSON → call writeEvidence locally.
- Dockerfile installs `claude` CLI (OAuth) at build time.
Compose:
- new `investigator` service builds from investigator-runtime/, connects
with low-privilege role, mounts case/ RW and wiki/+raw/ RO, 512m mem cap.
Web:
- /api/admin/investigate/test (POST+GET) gated by middleware (W0-F1).
POST creates a job, GET polls status. For W3.6 it becomes the chat tool.
End-to-end smoke: INSERT job → pg_notify → claim → Locard dispatch →
claude subprocess invoked. Auth works (CLI v2.1.150). Currently quota
exhausted (weekly limit · resets 3pm UTC) — pipeline catches the typed
isQuota error, marks job failed with surfaced reason. Architecture proven;
quota reset enables real evidence creation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-23 19:49:33 -03:00 |
|
Luiz Gustavo
|
eaf282c535
|
W2: rerank opt-in, analyze_image_region tool, RAG eval, graph cleanup, ADRs
CI / Web — typecheck + lint + build (push) Failing after 40s
CI / Scripts — Python smoke (push) Failing after 3s
CI / Web — npm audit (push) Failing after 29s
CI / Retrieval — golden set (Recall@5 + MRR) (push) Failing after 3s
- TD#8 hybrid.ts: rerank_strategy {always|when_top_k_gt|never} + threshold
(default skips rerank for top_k ≤ 15; chat tool uses threshold 10)
- O11 vision.ts + tools.ts: analyze_image_region tool — sharp-crops the
bbox, claude CLI reads the temp PNG via Read tool, Sonnet vision answers
- TD#12 /graph: SigmaGraph replaces ForceGraphCanvas; react-force-graph-2d
uninstalled (-37 transitive deps); force-graph-canvas.tsx deleted
- TD#27 messages/route.ts gatherContext slice sizes via CTX_* env vars
- TD#22 tests/rag/: golden.yaml (15 queries) + run.py (Recall@k + MRR +
negative-pass rate) + baseline.json + CI job in .forgejo/workflows/ci.yml
- docs/adrs/: ADR-001..005 published from systems-atelier deliverables
Verified live on disclosure.top: top_k=5 path skips rerank (6.7s embed-only,
was 12-15s with rerank); rerank=always still available on demand.
First RAG baseline: Recall@5 = 0.2083, MRR = 0.25, Negative pass = 1.0.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-23 19:20:09 -03:00 |
|
Luiz Gustavo
|
55cac8a395
|
W0+W1+W1.2: security hardening, observability, autocomplete, glitchtip, forgejo CI
CI / Web — typecheck + lint + build (push) Failing after 1m30s
CI / Scripts — Python smoke (push) Failing after 32s
CI / Web — npm audit (push) Failing after 37s
W0 — security hardening (5 fixes verified live on disclosure.top)
- middleware: gate /api/admin/* same as /admin/* (F1)
- imgproxy: tighten LOCAL_FILESYSTEM_ROOT from / to /var/lib/storage (F2)
- studio: real basic-auth label (bcrypt hash, middleware reference) (F3)
- relations: ENABLE ROW LEVEL SECURITY + public SELECT policy (F4)
- migration 0003: fold is_searchable + hybrid_search update into canonical (TD#2)
W1 — observability + resilience + autocomplete
- studio: HOSTNAME=0.0.0.0 so Next.js binds on loopback for healthcheck
- compose: PG_POOL_MAX=20, CLAUDE_CODE_OAUTH_TOKEN gated by separate env
- claude-code.ts: subprocess timeout configurable (CLAUDE_CODE_TIMEOUT_MS)
- openrouter.ts: retry with exponential backoff + Retry-After + in-memory
circuit breaker (promotes FALLBACK after CB_THRESHOLD failures)
- lib/logger.ts: pino logger (NDJSON prod / pretty dev) + withRequest helper
- middleware: mints correlation_id, stamps x-correlation-id response header,
emits structured http_request log per /api/* call
- messages/route.ts: switch to structured logger
- 60_meili_index.py: push documents + chunks into Meilisearch
- /api/search/autocomplete: parallel meili search (docs + chunks), 5-8ms p50
- search-autocomplete.tsx: debounced dropdown wired into search-panel
W1.2 — Glitchtip + Forgejo self-hosted
- compose: glitchtip-redis + glitchtip-web + glitchtip-worker (v4.2)
- compose: forgejo + forgejo-runner (server v9, runner v6) with group_add=988
- @sentry/nextjs SDK wired (instrumentation.ts + sentry.{client,server}.config.ts)
- /api/admin/throw smoke endpoint (gated by W0-F1 middleware)
- Synthetic event ingestion verified at glitchtip.disclosure.top
- forgejo.disclosure.top up, repo discadmin/disclosure-bureau created,
runner registered (labels: ubuntu-latest, docker)
- .forgejo/workflows/ci.yml: typecheck + lint + build + npm audit + python
syntax + compose validation
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-23 18:18:42 -03:00 |
|