Update evaluate.py

evaluate.py

@@ -58,14 +58,14 @@ def load_test_fixtures():
     global test_fixtures
     test_fixtures = []
     env_path = os.environ.get("TEST_FIXTURES_PATH", "").strip()
-    candidates = [env_path] if env_path else ["conversation_test_fixtures_v8.jsonl", "conversation_test_fixtures_v5.jsonl"]
+    candidates = [env_path] if env_path else ["conversation_test_fixtures_v10.jsonl", "conversation_test_fixtures_v8.jsonl"]
     path = next((p for p in candidates if p and os.path.exists(p)), None)
     if not path:
         print("Warning: No test fixtures file found for evaluation.")
         return
     
-    # Use the corrected v8 file if available
-    if "conversation_test_fixtures_v8.jsonl" in path:
+    # Use the corrected v10 file if available
+    if "conversation_test_fixtures_v10.jsonl" in path:
         print(f"Using corrected test fixtures: {path}")
 
     with open(path, "r", encoding="utf-8") as f:
@@ -109,7 +109,7 @@ def run_comprehensive_evaluation(
 ):
     global test_fixtures
     if not test_fixtures:
-        return "No test fixtures loaded. Please ensure conversation_test_fixtures_v8.jsonl exists.", [], []
+        return "No test fixtures loaded. Please ensure conversation_test_fixtures_v10.jsonl exists.", [], []
 
     def _norm(label: str) -> str:
         label = (label or "").strip().lower()