Merge pull request 'feat(halacha): #81.7 — תיוג gold-set בקונצנזוס תלת-מודלי (Opus+DeepSeek+Gemini), κ + אנונימיזציה' (#188) from worktree-goldset-tri-model-consensus into main

mcp-server/tests/test_goldset_panel_consensus.py

@@ -0,0 +1,104 @@
+"""Tests for #81.7 — tri-model consensus labeling of the halacha gold-set.
+
+Covers the pure aggregation/probe functions in scripts/goldset_panel_label.py
+(consensus vote, type consensus, Fleiss' kappa, anonymization masking). Fully
+OFFLINE — no DB, no model calls.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import pytest
+
+# the script lives in ../scripts relative to mcp-server/
+sys.path.insert(0, str(Path(__file__).resolve().parents[2] / "scripts"))
+import goldset_panel_label as g  # noqa: E402
+
+
+# ── consensus() ───────────────────────────────────────────────────────────────
+
+@pytest.mark.parametrize("votes,expected", [
+    ([True, True, True], (True, "3/3")),
+    ([False, False, False], (False, "3/3")),
+    ([True, True, False], (True, "2/3")),
+    ([False, False, True], (False, "2/3")),
+    ([True, False, None], (None, "split")),      # 1-1 of the two valid → chair
+    ([True, None, None], (None, "incomplete")),  # only one judge → chair
+    ([None, None, None], (None, "incomplete")),
+])
+def test_consensus(votes, expected):
+    assert g.consensus(votes) == expected
+
+
+def test_split_writes_no_label():
+    """A genuine 1-1 split must NOT yield a decision (escalates to chair, G10)."""
+    decided, tag = g.consensus([True, False, None])
+    assert decided is None and tag == "split"
+
+
+# ── consensus_type() ──────────────────────────────────────────────────────────
+
+def test_consensus_type_holding_majority():
+    per = [{"type": "holding"}, {"type": "holding"}, {"type": "application"}]
+    assert g.consensus_type(per, decided=True) == "holding"
+
+
+def test_consensus_type_constrained_to_is_holding():
+    """When the consensus is is_holding=False, only application/obiter types
+    are eligible — an inconsistent 'holding' vote is ignored."""
+    per = [{"type": "holding"}, {"type": "application"}, {"type": "obiter"}]
+    out = g.consensus_type(per, decided=False)
+    assert out in {"application", "obiter"}
+
+
+def test_consensus_type_undecided_is_blank():
+    per = [{"type": "holding"}, {"type": "application"}, {"type": "obiter"}]
+    assert g.consensus_type(per, decided=None) == ""
+
+
+# ── fleiss_kappa() ────────────────────────────────────────────────────────────
+
+def test_fleiss_kappa_perfect_agreement():
+    # every item rated 3/0 or 0/3 → κ == 1.0
+    rows = [(3, 0), (3, 0), (0, 3), (0, 3)]
+    assert g.fleiss_kappa(rows) == pytest.approx(1.0)
+
+
+def test_fleiss_kappa_disagreement_is_low():
+    rows = [(2, 1), (1, 2)]
+    k = g.fleiss_kappa(rows)
+    assert k is not None and k < 0.0  # worse than chance
+
+
+def test_fleiss_kappa_ragged_returns_none():
+    # mixed rater counts (3 then 2) is not well-defined → None
+    assert g.fleiss_kappa([(3, 0), (1, 1)]) is None
+
+
+def test_fleiss_kappa_empty_returns_none():
+    assert g.fleiss_kappa([]) is None
+
+
+# ── anonymize() ───────────────────────────────────────────────────────────────
+
+def test_anonymize_masks_case_number_and_name():
+    text = "מקור: החלטת ועדת-ערר (8125-09-24). העוררים פלוני בע\"מ טענו..."
+    out = g.anonymize(text, case_number="8125-09-24", case_name='פלוני בע"מ')
+    assert "8125-09-24" not in out
+    assert 'פלוני בע"מ' not in out
+    assert g._FAKE_CASE in out
+
+
+def test_anonymize_no_identifiers_is_noop():
+    text = "כלל משפטי כללי ללא מזהים."
+    assert g.anonymize(text, case_number=None, case_name=None) == text
+
+
+def test_anonymize_preserves_legal_substance():
+    """Masking swaps only the identifier — the rule text is untouched."""
+    text = "הכלל: מיצוי הליכים הוא תנאי-סף. (תיק 9001-01-20)"
+    out = g.anonymize(text, case_number="9001-01-20", case_name=None)
+    assert "מיצוי הליכים הוא תנאי-סף" in out
+    assert "9001-01-20" not in out