Add evaluation framework and fix call graph extraction

- Add evaluation test suite with TypeScript and Python fixtures
- Fix MCP server to defer CodeGraph init until rootUri received
- Fix call edge extraction by calling resolveReferences() after indexAll/sync
- Fix glob matching for root-level files (e.g., **/*.py now matches auth.py)
- Fix duplicate node extraction for methods inside classes
- Update context tests to use buildContext for semantic search + graph traversal
- Export unused formatter functions to fix build

Evaluation results:
- TypeScript: 96% precision, 79% recall, 85% F1
- Python: 99% precision, 80% recall, 85% F1

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

__tests__/evaluation/fixtures/python-project/validation.py

@@ -0,0 +1,27 @@
+"""Validation utilities."""
+
+import re
+
+
+def validate_email(email: str) -> bool:
+    """Validate email format."""
+    pattern = r'^[^\s@]+@[^\s@]+\.[^\s@]+$'
+    return bool(re.match(pattern, email))
+
+
+def validate_password(password: str) -> bool:
+    """Validate password strength."""
+    if len(password) < 8:
+        return False
+    if not re.search(r'[A-Z]', password):
+        return False
+    if not re.search(r'[a-z]', password):
+        return False
+    if not re.search(r'[0-9]', password):
+        return False
+    return True
+
+
+def validate_task_title(title: str) -> bool:
+    """Validate task title."""
+    return bool(title and len(title.strip()) >= 1 and len(title) <= 200)