feat(principles): canonical_statement synthesis service + throttled backfill (Phase E groundwork, #152)

Grounded (INV-AH) multi-instance synthesis with drift guard + chair gate
(pending_review, G10). Single path used by backfill, MCP tool, nightly drain.
HELD from production run pending the principles-redesign (rename+cull, #152).

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

mcp-server/tests/test_panel_extraction.py

@@ -0,0 +1,116 @@
+"""Unit tests for the tri-model panel extraction core (#152, Phase A).
+
+Pure logic only — classify (the chair's approval rule), _coerce_list (judge-reply
+normalisation), and cluster_candidates (cross-model matching/voting) with injected
+embeddings. No LLM, no Voyage, no DB.
+"""
+from __future__ import annotations
+
+import pytest
+
+from legal_mcp import config
+from legal_mcp.services import panel_extraction as pe
+
+
+# ── classify — chaim's rule ────────────────────────────────────────
+
+def test_classify_three_votes_approves_regardless_of_score():
+    assert pe.classify(3, 0.10) == "approved"
+    assert pe.classify(3, 0.99) == "approved"
+
+
+def test_classify_two_votes_gated_by_floor():
+    floor = config.HALACHA_PANEL_SCORE_FLOOR
+    assert pe.classify(2, floor) == "approved"
+    assert pe.classify(2, floor + 0.05) == "approved"
+    assert pe.classify(2, floor - 0.01) == "pending_review"
+
+
+def test_classify_one_or_zero_votes_rejected():
+    assert pe.classify(1, 0.99) == "rejected"
+    assert pe.classify(0, 0.99) == "rejected"
+
+
+# ── _coerce_list — judge reply normalisation ───────────────────────
+
+def test_coerce_list_accepts_bare_list():
+    raw = [{"rule_statement": "כלל", "supporting_quote": "ציטוט", "score": 0.9}]
+    out = pe._coerce_list(raw)
+    assert len(out) == 1 and out[0]["rule_type"] == "interpretive"
+
+
+def test_coerce_list_unwraps_dict_wrapper_and_drops_incomplete():
+    raw = {"principles": [
+        {"rule_statement": "כלל", "supporting_quote": "ציטוט", "rule_type": "holding", "score": 1.5},
+        {"rule_statement": "", "supporting_quote": "ציטוט"},          # no rule → drop
+        {"rule_statement": "כלל2", "supporting_quote": ""},            # no quote → drop
+    ]}
+    out = pe._coerce_list(raw)
+    assert len(out) == 1
+    assert out[0]["rule_type"] == "holding"
+    assert out[0]["score"] == 1.0           # clamped to [0,1]
+
+
+def test_coerce_list_bad_rule_type_falls_back():
+    out = pe._coerce_list([{"rule_statement": "כלל", "supporting_quote": "צ", "rule_type": "obiter", "score": 0.5}])
+    assert out[0]["rule_type"] == "interpretive"
+
+
+def test_coerce_list_junk_returns_empty():
+    assert pe._coerce_list("nonsense") == []
+    assert pe._coerce_list(None) == []
+
+
+# ── cluster_candidates — cross-model matching & voting ─────────────
+
+def _c(rule, score):
+    return {"rule_statement": rule, "supporting_quote": "q", "reasoning_summary": "",
+            "rule_type": "interpretive", "score": score}
+
+
+def test_cluster_merges_across_models_counts_votes_and_means_score():
+    # same principle proposed by all three (identical embedding) → 1 cluster, 3 votes
+    a, b, c = _c("X", 0.9), _c("X", 0.8), _c("X", 0.7)
+    per_model = {"claude": [a], "deepseek": [b], "gemini": [c]}
+    embs = {id(a): [1.0, 0.0], id(b): [1.0, 0.0], id(c): [1.0, 0.0]}
+    out = pe.cluster_candidates(per_model, embs)
+    assert len(out) == 1
+    cl = out[0]
+    assert cl["votes"] == 3
+    assert cl["score"] == pytest.approx((0.9 + 0.8 + 0.7) / 3, abs=1e-3)
+    assert cl["verdict"] == "approved"
+    assert cl["voters"] == ["claude", "deepseek", "gemini"]
+
+
+def test_cluster_separates_distinct_principles():
+    a, b = _c("X", 0.9), _c("Y", 0.9)
+    per_model = {"claude": [a, b]}
+    embs = {id(a): [1.0, 0.0], id(b): [0.0, 1.0]}  # orthogonal → 2 clusters
+    out = pe.cluster_candidates(per_model, embs)
+    assert len(out) == 2
+    assert all(cl["votes"] == 1 and cl["verdict"] == "rejected" for cl in out)
+
+
+def test_cluster_same_model_twice_counts_one_vote_keeps_best_score():
+    # one model proposes two near-dupes; another proposes the same → 2 votes, not 3
+    a1, a2 = _c("X", 0.6), _c("X", 0.95)
+    b = _c("X", 0.88)
+    per_model = {"claude": [a1, a2], "deepseek": [b]}
+    embs = {id(a1): [1.0, 0.0], id(a2): [1.0, 0.0], id(b): [1.0, 0.0]}
+    out = pe.cluster_candidates(per_model, embs)
+    assert len(out) == 1
+    cl = out[0]
+    assert cl["votes"] == 2                       # claude counts once
+    # claude's best (0.95) and deepseek (0.88) → mean
+    assert cl["score"] == pytest.approx((0.95 + 0.88) / 2, abs=1e-3)
+    assert cl["rule_statement"] == "X"
+
+
+def test_cluster_sorted_strongest_first():
+    a = _c("X", 0.9)   # 1 vote
+    b, c = _c("Y", 0.9), _c("Y", 0.9)  # 2 votes
+    per_model = {"claude": [a, b], "deepseek": [c]}
+    embs = {id(a): [1.0, 0.0], id(b): [0.0, 1.0], id(c): [0.0, 1.0]}
+    out = pe.cluster_candidates(per_model, embs)
+    assert out[0]["rule_statement"] == "Y" and out[0]["votes"] == 2
+    assert out[1]["rule_statement"] == "X" and out[1]["votes"] == 1