Replace Haiku with Sonnet in classifier for better accuracy

classify_document and identify_parties both used Haiku, which produced
parsing failures and 0% confidence on Beit HaKerem documents.
Sonnet handles Hebrew legal documents more reliably.

No more Haiku usage in the entire codebase.

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

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

@@ -98,8 +98,8 @@ async def classify_document(text: str) -> dict:
 
     client = _get_anthropic()
     message = client.messages.create(
-        model="claude-haiku-4-5-20251001",
-        max_tokens=256,
+        model="claude-sonnet-4-20250514",
+        max_tokens=512,
         messages=[
             {
                 "role": "user",
@@ -136,7 +136,7 @@ async def identify_parties(text: str) -> dict:
 
     client = _get_anthropic()
     message = client.messages.create(
-        model="claude-haiku-4-5-20251001",
+        model="claude-sonnet-4-20250514",
         max_tokens=512,
         messages=[
             {