disclosure-bureau/investigator-runtime
Luiz Gustavo 0a5c03c29a
Some checks failed
CI / Web — typecheck + lint + build (push) Failing after 34s
CI / Scripts — Python smoke (push) Failing after 4s
CI / Web — npm audit (push) Failing after 35s
CI / Retrieval — golden set (Recall@5 + MRR) (push) Failing after 4s
W4 followup: Poirot soft-truncate at sentence boundary
Live PT-BR smoke on j-edgar-hoover produced verdict_pt_br at 304 chars
(prompt says ≤ 280). The writer correctly rejected it ("verdict too long
(304 > 280)") but the job failed instead of trimming.

Fix: detective now trims each language field at the nearest sentence
boundary (period or semicolon) above 60% of the cap; falls back to a hard
cut at the cap. Applied to verdict / verdict_pt_br (≤280), and to
access_to_event*, bias_notes* (≤800) for defense in depth.

The contract with the writer stays strict; the detective just becomes
forgiving about the model going 5-10% over.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-24 12:11:35 -03:00
..
prompts W4: bilingual EN + PT-BR Investigation Bureau (CLAUDE.md §3 contract) 2026-05-24 12:02:59 -03:00
src W4 followup: Poirot soft-truncate at sentence boundary 2026-05-24 12:11:35 -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