disclosure-bureau/investigator-runtime
Luiz Gustavo b3a6a3c1a3
Some checks failed
CI / Web — typecheck + lint + build (push) Failing after 38s
CI / Scripts — Python smoke (push) Failing after 3s
CI / Web — npm audit (push) Failing after 27s
CI / Retrieval — golden set (Recall@5 + MRR) (push) Failing after 3s
W5.2: best-seller case-writer — single voice, scene-driven, anti-skeptic
User: "shouldn't mention the names of the mind-clones, should merge all
analyses and write like a best-seller author would, about what happened."

Voice rewrite (prompts/case-writer.md):
  - Reference voices: Erik Larson, Sam Kean, John McPhee, Mark Bowden.
    Plainspoken non-fiction, scene-driven, fascinated.
  - One narrator. NEVER say "Sherlock Holmes argues" / "Sun-Tzu builds
    the case" / "the team concluded". No internal-process names reach
    the reader.
  - Hook the first paragraph. Open in a scene with a date, place, and
    person doing something specific. NOT "This case investigates..."
  - Show, don't argue. Verbatim quotes stay source-language in
    blockquotes; the narration around them is the narrator's voice.
  - Every claim cites a chunk with [[doc-id/pNNN#cNNNN]].
  - Forbidden ceremony: "In summary…", "Em suma…", "Ultimately…",
    "It is worth noting…", detective names, probability tables,
    hypothesis tournaments.
  - The honest unknown is the subject, not a failure: "Whatever was in
    the sky over Sandia in December 1948, the government never said."
  - 4-6 numbered scenes, each title-cased specifically ("The Green
    Sphere Over Highway 60" not "Background").
  - Bilingual EN + PT-BR per CLAUDE.md §3 — sections alternate, no
    mid-paragraph language mixing.
  - Refusal: emit INSUFFICIENT_ARTEFACTS rather than padding when the
    corpus is thin.

Raw-material pipeline (src/detectives/case_writer.ts):
  - hybridSearch(topic, lang, top_k=18) gives the narrator real corpus
    scenes with verbatim text + chunk_id citations + bbox metadata.
    This is what was missing — v1 only saw pre-digested hypothesis
    artefacts, which is how the academic prose got there.
  - Dropped the hypotheses + contradictions queries from the loader.
    They were skeptic-framing scaffolding that doesn't belong in the
    raw material a best-seller narrator works from.
  - New buildPrompt sections: "Primary-source scenes", "Curated
    verbatim quotes", "Anomalies and surprises", "Named witnesses".
    Anomalies (Taleb's outlier gaps) reframed: drop dominant_model
    skeptic baseline, keep title + why_surprising as gold material.
  - Refusal floor: < 4 scenes from hybridSearch → skip with reason.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 14:21:53 -03:00
..
prompts W5.2: best-seller case-writer — single voice, scene-driven, anti-skeptic 2026-05-24 14:21:53 -03:00
src W5.2: best-seller case-writer — single voice, scene-driven, anti-skeptic 2026-05-24 14:21:53 -03:00
Dockerfile W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard 2026-05-23 19:49:33 -03:00
package-lock.json W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard 2026-05-23 19:49:33 -03:00
package.json W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard 2026-05-23 19:49:33 -03:00
tsconfig.json W3.1-W3.4: Investigation Bureau foundation — migrations, runtime, Locard 2026-05-23 19:49:33 -03:00