feat(halacha): strict-rubric quality gate + dedup-on-insert (#81,#82)

Bake the 2026-06-03 strict-cleanup rubric into the extraction pipeline so the
corpus stays clean at the source instead of accumulating duplicates, obiter
dicta, truncated quotes and thin restatements that clog the review queue.

#81 — quality gate:
- New pure module halacha_quality.py with unit-tested validators:
  non-decision/obiter (Wambaugh markers), truncated-quote (mid-word cut),
  thin-restatement (rule≈quote), quote-unverified.
- Validators run in halacha_extractor._process; a non-decision is re-typed
  obiter; flags persist in new halachot.quality_flags column.
- Auto-approve now requires confidence>=threshold AND no quality flags;
  flagged items route to pending_review regardless of confidence.
- Both extraction prompts hardened: reject undecided dicta, exclude
  case-specific applications, require abstraction, forbid over-splitting.

#82 — dedup-on-insert (store_halachot_for_chunk):
- Within the same precedent, skip a halacha whose normalized supporting_quote
  already exists, or whose rule-embedding has cosine>=HALACHA_DEDUP_COSINE
  (0.93) against an already-stored one. Makes re-runs idempotent.

Migration: halachot.quality_flags TEXT[] (additive, idempotent ALTER).
Tests: 19 new unit tests; full suite 156 passed. Validated end-to-end against
dev DB (dedup skips dups, flag blocks auto-approve, re-run inserts 0).
Calibration: flags fire on only ~10% of current survivors (low false-positive).

Spec: docs/halacha-strict-rubric.md

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

mcp-server/src/legal_mcp/config.py

@@ -144,6 +144,16 @@ HALACHA_AUTO_APPROVE_THRESHOLD = float(
     os.environ.get("HALACHA_AUTO_APPROVE_THRESHOLD", "0.80")
 )
 
+# Halacha dedup-on-insert — within-precedent semantic cosine ceiling. Before
+# storing a halacha, store_halachot_for_chunk skips it if its rule-embedding has
+# cosine >= this value against an already-stored halacha of the SAME precedent
+# (exact normalized supporting_quote is always skipped regardless). 0.93 is the
+# conservative auto-skip floor: the 2026-06-03 cleanup showed the 0.90-0.95 band
+# is "almost entirely" same-rule-reworded, but auto-skip is unreviewed so we sit
+# just above the manual-cleanup 0.90 to avoid dropping a genuinely distinct
+# principle. Set > 1.0 to disable semantic dedup (exact-quote dedup still runs).
+HALACHA_DEDUP_COSINE = float(os.environ.get("HALACHA_DEDUP_COSINE", "0.93"))
+
 # Google Cloud Vision (OCR for scanned PDFs)
 GOOGLE_CLOUD_VISION_API_KEY = os.environ.get("GOOGLE_CLOUD_VISION_API_KEY", "")