feat(analysis): analyze_protocol — comparative hearing-protocol analysis (WS4 #203)

מנתח פרוטוקול-דיון מול כתבי-הטענות: אילו טענות ירדו/חוזקו/עלו-חדשות + חידוד
שאלות משפטיות, ומחלץ נתוני כותרת (א–ד). התוצאה נכנסת לידע-התיק.

- protocol_analyzer.py — ניתוח השוואתי דרך claude_session (Opus 4.8, effort=high,
  מקומי בלבד); שער anti-hallucination (quote-or-retract) ב-_normalize_change;
  חילוץ א–ד + הזנת hearing_date חזרה ל-cases (לא דורס קלט-יו"ר).
- claims_extractor: protocol → claim_type='protocol'; extract_claims קולט protocol.
- block_writer._build_claims_context מחריג claim_type='protocol' מבלוק ז (INV-WR4).
- db: טבלת protocol_analysis (V47, idempotent per-doc) + replace/list helpers.
- tools/drafting + server: analyze_protocol + get_protocol_analysis (extract/get).
- ספ 04-analysis-writing §1.3 + 15 בדיקות.

Invariants: G1 (נרמול-במקור: hearing_date לעמודה הקנונית), G2 (ידע-תיק נגזר
ממקור-האמת protocol+legal_arguments, לא מסלול מקביל), INV-TOOL3 (idempotent
per document_id), INV-TOOL4 (extract/get symmetry), INV-AH (quote-or-retract),
INV-WR4 (בלוק ז = טענות-כתב מקוריות בלבד), claude_session local-only, G12 (נקי
מ-Paperclip — leak-guard עובר).

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

mcp-server/tests/test_protocol_analyzer.py

@@ -0,0 +1,141 @@
+"""Tests for the comparative protocol analyzer (WS4 / #203).
+
+Covers the pure (non-LLM, non-DB) logic: the anti-hallucination normalization
+gate, protocol-document discovery, claim_type tagging for protocols, and the
+block-ז filter that keeps oral hearing arguments out of the original-pleadings
+summary (INV-WR4).
+"""
+from __future__ import annotations
+
+import pytest
+
+from legal_mcp.services import protocol_analyzer as pa
+from legal_mcp.services.claims_extractor import _infer_claim_type
+
+
+# ── claim_type tagging — protocol distinct from written pleadings ───────────
+
+@pytest.mark.parametrize("doc_type,title,expected", [
+    ("protocol", "פרוטוקול דיון", "protocol"),
+    ("appeal", "פרוטוקול הדיון מיום 1.1", "protocol"),   # title-based
+    ("appeal", "כתב ערר", "claim"),
+    ("response", "כתב תשובה", "response"),
+    ("response", "תגובת המשיבה", "reply"),
+])
+def test_infer_claim_type(doc_type, title, expected):
+    assert _infer_claim_type(doc_type, title) == expected
+
+
+# ── _find_protocol ─────────────────────────────────────────────────────────
+
+def test_find_protocol_by_doc_type():
+    docs = [
+        {"id": "1", "doc_type": "appeal", "title": "כתב ערר"},
+        {"id": "2", "doc_type": "protocol", "title": "פרוטוקול"},
+    ]
+    assert pa._find_protocol(docs)["id"] == "2"
+
+
+def test_find_protocol_by_title_fallback():
+    docs = [
+        {"id": "1", "doc_type": "reference", "title": "פרוטוקול הדיון"},
+        {"id": "2", "doc_type": "appeal", "title": "כתב ערר"},
+    ]
+    assert pa._find_protocol(docs)["id"] == "1"
+
+
+def test_find_protocol_none():
+    docs = [{"id": "1", "doc_type": "appeal", "title": "כתב ערר"}]
+    assert pa._find_protocol(docs) is None
+
+
+# ── _normalize_change — anti-hallucination gate (INV-AH) ───────────────────
+
+_AID = "11111111-1111-1111-1111-111111111111"
+
+
+def test_normalize_change_valid():
+    row = pa._normalize_change(
+        {
+            "change_type": "dropped",
+            "party_role": "appellant",
+            "argument_id": _AID,
+            "argument_title": "טענת השיהוי",
+            "summary": "העורר ויתר על הטענה בדיון.",
+            "sharpened_question": "האם נותרה טענת סף?",
+            "evidence_quote": "ב\"כ העורר: איננו עומדים על טענת השיהוי.",
+            "page_number": 3,
+        },
+        valid_argument_ids={_AID},
+    )
+    assert row is not None
+    assert row["change_type"] == "dropped"
+    assert str(row["argument_id"]) == _AID
+    assert row["page_number"] == 3
+
+
+def test_normalize_change_drops_row_without_evidence_quote():
+    # quote-or-retract: no verbatim support → row is rejected at source.
+    row = pa._normalize_change(
+        {"change_type": "strengthened", "summary": "חוזקה", "evidence_quote": ""},
+        valid_argument_ids=set(),
+    )
+    assert row is None
+
+
+def test_normalize_change_drops_row_without_summary():
+    row = pa._normalize_change(
+        {"change_type": "dropped", "summary": "", "evidence_quote": "ציטוט"},
+        valid_argument_ids=set(),
+    )
+    assert row is None
+
+
+def test_normalize_change_rejects_bad_change_type():
+    row = pa._normalize_change(
+        {"change_type": "modified", "summary": "x", "evidence_quote": "y"},
+        valid_argument_ids=set(),
+    )
+    assert row is None
+
+
+def test_normalize_change_drops_hallucinated_argument_id():
+    # An argument_id that isn't one of this case's arguments must be dropped
+    # (FK safety) — but the row itself, being newly_raised-shaped, survives.
+    row = pa._normalize_change(
+        {
+            "change_type": "newly_raised",
+            "party_role": "respondent",
+            "argument_id": "99999999-9999-9999-9999-999999999999",
+            "summary": "סוגיה חדשה שעלתה בדיון.",
+            "evidence_quote": "ב\"כ המשיבה העלה לראשונה את שאלת הסמכות.",
+        },
+        valid_argument_ids={_AID},
+    )
+    assert row is not None
+    assert row["argument_id"] is None
+    assert row["change_type"] == "newly_raised"
+
+
+def test_normalize_change_invalid_party_role_blanked():
+    row = pa._normalize_change(
+        {
+            "change_type": "strengthened",
+            "party_role": "judge",      # not a valid party
+            "summary": "חוזקה הטענה.",
+            "evidence_quote": "ציטוט מבסס.",
+        },
+        valid_argument_ids=set(),
+    )
+    assert row is not None
+    assert row["party_role"] == ""
+
+
+def test_normalize_change_truncates_quote():
+    long_quote = "א" * 500
+    row = pa._normalize_change(
+        {"change_type": "dropped", "summary": "x", "evidence_quote": long_quote},
+        valid_argument_ids=set(),
+    )
+    assert row is not None
+    assert len(row["evidence_quote"]) == 200