b9fa74b875
feat(corpus): corpus redesign — eliminate halacha queue, verified-by-citation layer, rank-at-retrieval ( #153 )
...
G12 Leak-Guard / leak-guard (pull_request) Successful in 5s
Lint — undefined names / undefined-names (pull_request) Successful in 12s
Implements chaim's 2026-06-20 directive (5 steps; step 6 deferred):
1. No review queue — HALACHA_NO_REVIEW_QUEUE=true (auto-approve all → background);
migration cleared 2,416 pending_review → approved.
2. Verified layer — halachot.verified/cite_count from chair citations
(db.refresh_verified_layer + scripts/build_verified_layer.py runs citator on
ALL committee decisions). 2,775 verified / 137 precedents.
3. Retrieval ranks verified ≫ background — HALACHA_VERIFIED_BOOST in both semantic
+ lexical halacha queries; filter now includes background (<> rejected).
5. Disabled destructive panel cap/novelty — HALACHA_PANEL_REGIME_ENABLED=false
(8508/1049/1200 proved it lost 22-30 genuine principles incl. Lustrenik).
4. Ingest contract — going-forward already queues metadata; backfill_practice_area.py
+ 206 re-queued to the metadata drain.
Source of truth: docs/precedent-corpus-redesign/00-final-synthesis.md. Quality flags
are 97% false-positive (nli-audit) → no longer gate. UI queue removal → Claude Design
gate. 429 tests green (no regressions).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-20 13:55:00 +00:00
afe6894441
docs(principles): FINAL synthesis — eliminate queue; verified=chair-cited-in-context; nli 97% FP ( #153 )
...
chaim directive 2026-06-20: no halacha queue ever; trusted = only what a chair
actually cited, in context; corpus grows by citations; few-verified-now is fine.
nli-audit: nli_unsupported flag is 97% false-positive (29/30) — the 'noise' was
imaginary. Two layers: raw background (auto, no gate) vs verified (auto-canon from
citations). +06 indexed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-20 13:33:13 +00:00
38c395d0de
docs(principles): 3-case evidence (8508/1049/1200) — aggressive lost 22-30 genuine each; no-cull decided ( #153 )
...
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-20 12:51:58 +00:00
c1f92db2a0
docs(principles): refine synthesis — 2nd 8508 run (keep-when-in-doubt → 70/70 kept); no-cull triple-confirmed ( #153 )
...
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-20 12:40:30 +00:00
0f7549a137
docs(principles): final synthesis — keep-all+rank-at-retrieval; 8508 test killed cap/novelty (lost Lustrenik) ( #153 )
...
8508-03-24 test: panel+cap cut 70→3, losing ~22 genuine principles incl. the
core Lustrenik betterment rule. Lesson: cap + novelty-filter is destructive for
RAG (which needs applied doctrine). Quality-at-source = dedup+noise-only, no cap.
PR#304 regime flagged for revision.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-20 12:36:42 +00:00
