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/config.py

@@ -67,3 +67,29 @@ ALLOWED_EXTERNAL_SERVICES = {
 
 # Audit
 AUDIT_ENABLED = os.environ.get("AUDIT_ENABLED", "true").lower() == "true"
+
+
+# ── Utility ───────────────────────────────────────────────────────
+
+def parse_llm_json(raw: str):
+    """Parse JSON from LLM response, stripping markdown code blocks and extra text."""
+    import json
+    import re
+    raw = raw.strip()
+    # Strip markdown code blocks
+    raw = re.sub(r"^```(?:json)?\s*\n?", "", raw)
+    raw = re.sub(r"\n?\s*```$", "", raw)
+    # Try direct parse first
+    try:
+        return json.loads(raw)
+    except json.JSONDecodeError:
+        pass
+    # Try to find JSON object or array
+    for pattern in [r"\{.*\}", r"\[.*\]"]:
+        match = re.search(pattern, raw, re.DOTALL)
+        if match:
+            try:
+                return json.loads(match.group())
+            except json.JSONDecodeError:
+                continue
+    return None