fix scoring

evaluator.py

@@ -227,15 +227,15 @@ def generate_behavioral_score(eval_array):
         fail_score = 0
         success_score = 0
 
-        if eval[0].label == "FAIL":
-            fail_score = eval[0]["score"]
-        elif eval[0].label == "SUCCESS":
-            success_score = eval[0]["score"]
-
-        if eval[1].label == "FAIL":
-            fail_score = eval[1]["score"]
-        elif eval[1].label == "SUCCESS":
-            success_score = eval[1]["score"]
+        if eval.label == "FAIL":
+            fail_score += 1
+        elif eval.label == "SUCCESS":
+            success_score += 1 
+
+        # if eval.label == "FAIL":
+        #     fail_score = eval["score"]
+        # elif eval.label == "SUCCESS":
+        #     success_score = eval["score"]
 
         if fail_score < success_score:
             scores.append(1)