QA claims check: Haiku→Sonnet + filter appellant claims only

Two fixes for claims_coverage false negatives (55% → expected ~85%+):

1. Model upgrade: Haiku → Sonnet for semantic matching. Haiku missed
   obvious matches (e.g., paragraph about "כריתת עצים" not matching
   claim about tree cutting). Sonnet understands context better.

2. Filter: only check appellant/respondent claims, not committee or
   permit_applicant claims. Committee claims are defensive positions
   ("the application complies with the plan") — they don't need to
   be "addressed" in the discussion section.

3. Send full discussion text (was truncated to 12K chars).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

mcp-server/src/legal_mcp/services/qa_validator.py

@@ -124,8 +124,17 @@ async def check_claims_coverage(blocks: list[dict], claims: list[dict]) -> dict:
     if not claims:
         return {"name": "claims_coverage", "passed": True, "errors": [], "severity": "critical"}
 
-    # Filter: only claims from original pleadings
+    # Filter: only APPELLANT claims from original pleadings.
-    source_claims = [c for c in claims if c.get("source_document", "") != "block-zayin"]
+    # Committee/permit_applicant claims are defensive positions, not claims
+    # that need to be "addressed" in the discussion.
+    source_claims = [
+        c for c in claims
+        if c.get("source_document", "") != "block-zayin"
+        and c.get("party_role") in ("appellant", "respondent")
+    ]
+    if not source_claims:
+        # Fallback: all non-block-zayin claims
+        source_claims = [c for c in claims if c.get("source_document", "") != "block-zayin"]
     if not source_claims:
         source_claims = claims
 
@@ -134,12 +143,12 @@ async def check_claims_coverage(blocks: list[dict], claims: list[dict]) -> dict:
     for i, c in enumerate(source_claims, 1):
         claims_text += f"טענה #{i}: {c['claim_text'][:300]}\n"
 
-    # Truncate discussion if needed
+    # Send full discussion — don't truncate
-    discussion = yod["content"][:12000]
+    discussion = yod["content"]
 
     client = _get_anthropic()
     message = client.messages.create(
-        model="claude-haiku-4-5-20251001",
+        model="claude-sonnet-4-20250514",
         max_tokens=8192,
         messages=[{
             "role": "user",