Maximize context and output per Anthropic best practices

Per official Anthropic documentation (April 2026):

Output tokens increased to match model capabilities:
- block-yod (discussion): 8K → 32K (Opus supports 128K)
- block-zayin (claims): 4K → 16K
- block-vav (background): 4K → 16K
- claims_extractor: 4K → 8K (fixes truncated JSON)
- qa_validator: 4K → 8K

Source documents sent in full (not truncated):
- Was: 3000 chars per doc, 15K total
- Now: full document text, no truncation
- Reduces hallucinations: "extract word-for-word quotes first"

Prompt structure follows long-context tips:
- Source documents placed FIRST (top of prompt)
- Instructions and query placed LAST
- "Queries at the end improve quality by up to 30%"

Extended thinking uses adaptive mode for Opus 4.6.
Streaming enabled for all requests > 21K tokens.

Unified JSON parsing via parse_llm_json() helper in config.py.
Applied to: classifier, claims_extractor, brainstorm, qa_validator,
learning_loop (5 files).

Also: extractor.py now supports .md files.

Sources:
- https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking
- https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/long-context-tips
- https://docs.anthropic.com/en/docs/minimizing-hallucinations
- https://docs.anthropic.com/en/docs/about-claude/models/overview

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

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

@@ -7,7 +7,6 @@
 
 from __future__ import annotations
 
-import json
 import logging
 import re
 from uuid import UUID
@@ -15,6 +14,7 @@ from uuid import UUID
 import anthropic
 
 from legal_mcp import config
+from legal_mcp.config import parse_llm_json
 from legal_mcp.services import db
 
 logger = logging.getLogger(__name__)
@@ -91,7 +91,7 @@ async def extract_claims_with_ai(
     client = _get_anthropic()
     message = client.messages.create(
         model="claude-sonnet-4-20250514",
-        max_tokens=4096,
+        max_tokens=8192,
         messages=[
             {
                 "role": "user",
@@ -105,17 +105,8 @@ async def extract_claims_with_ai(
     )
 
     raw = message.content[0].text.strip()
-    # Strip markdown code blocks if present
-    raw = re.sub(r"^```(?:json)?\s*", "", raw)
-    raw = re.sub(r"\s*```$", "", raw)
-    try:
-        # Extract JSON array from response
-        json_match = re.search(r"\[.*\]", raw, re.DOTALL)
-        if json_match:
-            claims = json.loads(json_match.group())
-        else:
-            claims = json.loads(raw)
-    except json.JSONDecodeError:
+    claims = parse_llm_json(raw)
+    if claims is None:
         logger.warning("Failed to parse claims response: %s", raw[:200])
         return []