docs(principles): move research into docs/precedent-corpus-redesign/ (README + research-full) (#153)

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

mcp-server/src/legal_mcp/config.py

@@ -184,6 +184,15 @@ HALACHA_PANEL_MATCH_COSINE = float(os.environ.get("HALACHA_PANEL_MATCH_COSINE",
 # to the legacy path (e.g. if all three judges are unreachable).
 HALACHA_PANEL_REGIME_ENABLED = os.environ.get("HALACHA_PANEL_REGIME_ENABLED", "true").lower() == "true"
 
+# Importance layer (#153) — principle-level gold matching. OUR_CHAIR's citations
+# (tier-1 gold, protective) vs other chairs' (tier-2 weight). Match threshold: a
+# chair-citation's match_context (or a digest's headline_holding) is matched to the
+# cited precedent's principles by cosine; ≥ this → the principle is flagged. Tuned
+# toward RECALL (a false-negative buries a principle the chair relied on; a
+# false-positive merely over-protects). 0.72 = paraphrase floor on voyage-law-2.
+OUR_CHAIR_NAME = os.environ.get("OUR_CHAIR_NAME", "דפנה תמיר")
+HALACHA_GOLD_MATCH_THRESHOLD = float(os.environ.get("HALACHA_GOLD_MATCH_THRESHOLD", "0.72"))
+
 # 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