The Disclosure Bureau — declassified UAP/UFO wiki
Find a file
Luiz Gustavo dd75a67964
Some checks failed
CI / Web — typecheck + lint + build (push) Failing after 45s
CI / Scripts — Python smoke (push) Failing after 5s
CI / Web — npm audit (push) Failing after 40s
CI / Retrieval — golden set (Recall@5 + MRR) (push) Failing after 3s
W3.8: Investigation Bureau complete — Poirot, Taleb, Tetlock, Case-Writer
Brings the bureau from 4 → 8 detectives. All eight run as Bun + claude-CLI
subprocesses against the same Supabase + investigation_jobs LISTEN/NOTIFY
queue, sharing search.ts hybridSearch and writer-side validators that
gate writes against schema + FK.

New detectives:

  Poirot (witness_analysis)
    - prompts/poirot.md — credibility / access / bias / corroboration /
      verdict; uses entity_mentions JOIN chunks to pull 12 chunks per
      person; resolves corroboration_refs chunk_ids defensively (accepts
      bare cNNNN even when the model emits pNNN/cNNNN).
    - INSERT into public.witnesses with W-NNNN naming.
    - Tone: purple (#9b5de5).

  Taleb (outlier_scan)
    - prompts/taleb.md — "surprise is relative to a model"; at most 3
      outliers; each requires explicit dominant_model + why_surprising +
      what_it_implies; fan-out into public.gaps with scope.kind="outlier".
    - Same unscoped-fallback as Dupin (Pass 1 with doc_id, Pass 2 widens
      to corpus if hits < 3).
    - Tone: yellow (#ffd23f).

  Tetlock (calibrate_hypothesis)
    - prompts/tetlock.md — honest Bayesian update; emits new_posterior +
      Δ + recommended_action ∈ {keep, downgrade, upgrade, supersede}.
    - write_calibration UPDATEs public.hypotheses + APPENDS a
      "## Calibration history" section to the H-NNNN.md case file
      (calibration is append-only — each datapoint matters). Posterior
      band auto-corrected to match Tetlock thresholds.
    - NO_NEW_EVIDENCE sentinel handled; pure 'keep' with |Δ|<0.005 only
      touches updated_at + reviewed_by.
    - Tone: teal (#26d4cc).

  Case-Writer (case_report)
    - prompts/case-writer.md — Dr. Watson assembles all artefacts
      (E-NNNN, H-NNNN, R-NNNN, W-NNNN, G-NNNN) into a five-act narrative.
      ILIKE filter on topic; doc_id optional scope.
    - Larger budget cap (≥ $0.50) + longer timeout for prose generation.
    - Writes case/reports/<slug>.md with frontmatter (topic + counts);
      no DB table for v0.
    - New page /c/[slug] renders the report via MarkdownBody + stat chips.
    - Tone: gold (#e0c080).

Hardening across the bureau:
  - Sentinel parsing now accepts backticked AND prose-trailing forms
    (Holmes NO_HYPOTHESES, Dupin NO_CONTRADICTIONS, Schneier
    INSUFFICIENT_HYPOTHESIS, Poirot INSUFFICIENT_TESTIMONY, Taleb
    NO_OUTLIERS, Tetlock NO_NEW_EVIDENCE, Case-Writer
    INSUFFICIENT_ARTEFACTS). Avoids the failure mode where the model
    refuses honestly but the runtime treated it as a parse error
    (observed live with Poirot+Hoover identifying the DIRECTOR
    false-positive disambiguation issue in entity_mentions).

Chat tool extensions (web/lib/chat/tools.ts):
  - request_investigation now accepts 7 kinds. Each routes to its
    detective with appropriate validation (hypothesis_id regex,
    person_id kebab-case, topic non-empty, doc_id for evidence_chain).
  - ETA per kind: Holmes/Dupin 60s, Poirot 45s, Schneier/Tetlock 30s,
    Taleb 50s, Case-Writer 180s (longer prose), Locard 30×n_chunks.

UI integration:
  - chat-bubble inline card paints each detective in its tone color.
  - /jobs/[id] page header swaps name/subtitle/tone per detective;
    question label adapts ("Topic" / "Hypothesis under attack" /
    "Witness under analysis" / "Topic to outlier-scan" / "Hypothesis
    under recalibration" / "Case to assemble").
  - job-status-poller renders: case-report link card (gold), outlier
    cards (yellow), witness cards (purple) — alongside existing
    hypothesis, evidence, contradiction cards.
  - /api/jobs/[id] hydrates witnesses (JOIN entities for canonical_name)
    + gaps (with scope JSONB).
  - /c/[slug] page reads /data/ufo/case/reports/<slug>.md and renders
    with MarkdownBody, frontmatter parsed for stat chips.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-23 22:11:39 -03:00
.claude/agents rebuild entity layer from Sonnet-vision reextract pipeline 2026-05-21 12:20:24 -03:00
.forgejo/workflows W2: rerank opt-in, analyze_image_region tool, RAG eval, graph cleanup, ADRs 2026-05-23 19:20:09 -03:00
.nirvana/outputs/disclosure-bureau phase-0: kill stubs, ship 20 curated anchor events, configure SMTP 2026-05-18 00:44:17 -03:00
case/gaps rebuild entity layer from Sonnet-vision reextract pipeline 2026-05-21 12:20:24 -03:00
docs/adrs W2: rerank opt-in, analyze_image_region tool, RAG eval, graph cleanup, ADRs 2026-05-23 19:20:09 -03:00
infra W3 followup: drop _FOR_WEB token, fix claude CLI args + writer guards, BIGSERIAL grants 2026-05-23 21:05:35 -03:00
investigator-runtime W3.8: Investigation Bureau complete — Poirot, Taleb, Tetlock, Case-Writer 2026-05-23 22:11:39 -03:00
scripts W0+W1+W1.2: security hardening, observability, autocomplete, glitchtip, forgejo CI 2026-05-23 18:18:42 -03:00
tests/rag W2: rerank opt-in, analyze_image_region tool, RAG eval, graph cleanup, ADRs 2026-05-23 19:20:09 -03:00
web W3.8: Investigation Bureau complete — Poirot, Taleb, Tetlock, Case-Writer 2026-05-23 22:11:39 -03:00
wiki/entities/events phase-0: kill stubs, ship 20 curated anchor events, configure SMTP 2026-05-18 00:44:17 -03:00
.gitignore W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard 2026-05-23 19:49:33 -03:00
CHANGELOG.md W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard 2026-05-23 19:49:33 -03:00
CLAUDE-schema-full.md phase-0: kill stubs, ship 20 curated anchor events, configure SMTP 2026-05-18 00:44:17 -03:00
CLAUDE.md baseline: Disclosure Bureau pipeline + Next.js UI + Supabase stack 2026-05-17 22:44:36 -03:00
CORPUS-SNAPSHOT.md baseline: Disclosure Bureau pipeline + Next.js UI + Supabase stack 2026-05-17 22:44:36 -03:00
README.md baseline: Disclosure Bureau pipeline + Next.js UI + Supabase stack 2026-05-17 22:44:36 -03:00

The Disclosure Bureau

Investigative wiki + agentic chat sobre o corpus declassificado do US Department of War em war.gov/ufo (116 PDFs, 3.435 páginas, 34k+ entidades, 28 vídeos UAP).

Live: disclosure.top

O que é

Pipeline de IA que transforma documentos UAP/UFO declassificados em uma wiki investigativa navegável + chat agêntico com retrieval semântico bilíngue (EN + PT-BR) e citações com bbox crop no PDF original.

A premissa metodológica é o padrão Karpathy LLM Wiki: ler tudo, compilar conhecimento em markdown cross-referenciado, navegar via wiki-links — não por busca vetorial. Em cima dessa wiki rodamos uma camada de hybrid retrieval (BM25 + BGE-M3 dense + cross-encoder rerank) para perguntas livres no chat.

A camada investigativa segue protocolo Investigation Bureau (Holmes/Poirot/Dupin/Locard + Schneier/Tetlock/Taleb): chain-of-custody, hypothesis tournament, residual uncertainty.

Arquitetura

PDFs (raw/)
  ↓ pdftoppm 72 DPI + pdftotext
processing/ (png + ocr)
  ↓ Sonnet 4.6 subagents (page-rebuilder, image-analyst, table-stitcher)
raw/<doc>--subagent/ (chunks bilíngues + bbox + anomaly flags)
  ↓ scripts/30 (BGE-M3 embed) + 31 (entity_mentions)
Postgres + pgvector + tsvector
  ↓ hybrid_search RPC + reranker
chat agente (OpenRouter) cita [[doc/p007#c0042]] → frontend renderiza crop bbox

Stack

  • Embedding: BGE-M3 self-hosted (1024-dim, multilíngue, $0)
  • Reranker: BGE-Reranker-v2-M3 self-hosted ($0)
  • Vetor + texto: Postgres 15 + pgvector + tsvector bilíngue (pt_unaccent, en_unaccent)
  • LLM (chat): OpenRouter — DeepSeek v4 free como default
  • Frontend: Next.js 15 + React 19 + Tailwind + assistant-ui (Pattern C streaming)
  • Auth + persistência: Supabase self-hosted (GoTrue, PostgREST, Storage, Imgproxy)
  • Reverse proxy: Traefik + Let's Encrypt
  • Imagens: sharp via /api/crop (bbox on-demand, cached 1ano)

Layout

/Users/guto/ufo/
├── CLAUDE.md                       # contrato vinculante (24 tipos de markdown)
├── CLAUDE-schema-full.md           # schema detalhado
├── README.md                       # este arquivo
├── raw/                            # 116 PDFs imutáveis + chunks v0.2.0 derivados
│   ├── <pdfs>
│   ├── <doc-id>--subagent/         # chunks rebuilt (chunks/c*.md + _index.json + document.md)
│   └── _batch-rebuild/             # logs do orchestrator
├── processing/                     # intermediários (PNG, OCR, vision JSON)
├── wiki/                           # markdown gerado (documents/, pages/, entities/, tables/, images/)
├── case/                           # artefatos Investigation Bureau (case-report, hypotheses, gaps)
├── scripts/                        # 33 scripts numerados (Phase 0 → manutenção)
├── infra/                          # docker-compose, embed-service, migrations, deploy
└── web/                            # Next.js frontend

Quick start

# 1. Converter PDFs em PNG + OCR (uma vez)
./scripts/01-convert-pdfs.sh

# 2. Rebuild chunks bilíngues (Sonnet 4.6 via Claude Code subagents)
python3 scripts/28-batch-rebuild-all.py --workers 2

# 3. (após batch) Indexar em Postgres + embeddings
python3 scripts/30-index-chunks-to-db.py --skip-existing

# 4. (opcional) Materializar entity_mentions p/ grafo
python3 scripts/31-populate-entity-mentions.py

# 5. Deploy
cd infra/disclosure-stack && ./scripts/deploy.sh

Detalhes completos em infra/DEPLOY-CHECKLIST.md.

Features do frontend

URL Função
/ Lista de documentos com resumo de 3 linhas, filtros (collection, classification, sort), busca
/d/<doc> Visão legado (page grid + frontmatter)
/d/<doc>/v2 Render rico de chunks com lang toggle (PT/EN/both), paged vs flow
/d/<doc>/v2/<page> Single page V2 com PNG side-by-side
/d/<doc>/full Texto consolidado bilíngue
/e/<class> Lista paginada de entidades por classe (people, locations, ...)
/e/<class>/<id> Detalhe da entidade + co-mentions + chunks live
/search?q=... Hybrid search URL-shareable
/timeline Cronologia de eventos por década
/graph Grafo força-direcionado de co-menções (Obsidian-style)
/admin/stats Analytics do corpus (FS + DB)
/admin/batch Monitor de progresso do rebuild
/admin/indexer Estado da camada de retrieval

Atalhos globais:

  • ⌘K / Ctrl+K em qualquer página → command palette com hybrid_search
  • Toggle 🌐 EN ↔ PT-BR fixo bottom-left (cookie 1ano)
  • Chat 💬 botão flutuante bottom-right com 12 ferramentas

Os 12 tools do agente

🔍 Retrieval: hybrid_search, read_chunk, get_page_chunks, list_anomalies 🔗 Grafo: entity_neighbors, entity_path, co_mention_chunks 📄 Wiki: read_document, read_page, read_entity, search_corpus 🧭 UI: navigate_to

Citações tipo [[doc-id/p007#c0042]] viram cards interativos com crop bbox + texto bilíngue + link.

Custos

Item Custo
Rebuild chunks (Sonnet 4.6 via Claude Code Max 20x) ~$200 one-shot p/ 116 docs
Embedding BGE-M3 self-host $0/mês
Reranker BGE-Reranker-v2-M3 self-host $0/mês
Postgres + pgvector já incluso no VPS
Chat LLM (DeepSeek free via OpenRouter) $0/req
VPS (16GB / 4 CPU) ~€10/mês

Documentação

Licença + procedência

  • PDFs declassificados: domínio público (US Department of War / FBI / DOS / NASA)
  • Código deste projeto: MIT
  • Modelos: BGE-M3 (MIT), DeepSeek v4 (proprietary via OpenRouter free tier)
  • Branding: The Disclosure Bureau / disclosure.top — pessoal

Wiki investigativa, não advocacy. Toda claim tem chain-of-custody até a página + bbox do PDF original.