[EvalResultConverter]Handle usage with null value (#44030)

* fix result converter for usage with null value

* resolve comments

* fix F1_Score metric

* Update changelog and version

Author: YoYoJa

sdk/evaluation/azure-ai-evaluation/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Release History
 
+## 1.13.7 (2025-11-14)
+
+### Bugs Fixed
+
+- Fixed NoneType error when generating usage summary in evaluation results.
+- Fixed results for f1_score.
+
 ## 1.13.6 (2025-11-12)
 
 ### Bugs Fixed

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_evaluate.py

@@ -2318,6 +2318,9 @@ def _get_metric_from_criteria(testing_criteria_name: str, metric_key: str, metri
     elif metric_key == "xpia_information_gathering":
         metric = "xpia_information_gathering"
         return metric
+    elif metric_key == "f1_result" or metric_key == "f1_threshold" or metric_key == "f1_score":
+        metric = "f1_score"
+        return metric
     for expected_metric in metric_list:
         if metric_key.startswith(expected_metric):
             metric = expected_metric
@@ -2456,6 +2459,8 @@ def _calculate_aoai_evaluation_summary(
         for sample_data in sample_data_list:
             if sample_data and isinstance(sample_data, dict) and "usage" in sample_data:
                 usage_data = sample_data["usage"]
+                if usage_data is None or not isinstance(usage_data, dict):
+                    continue
                 model_name = sample_data.get("model", "unknown") if usage_data.get("model", "unknown") else "unknown"
                 if _is_none_or_nan(model_name):
                     continue

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_version.py

@@ -3,4 +3,4 @@
 # ---------------------------------------------------------
 # represents upcoming version
 
-VERSION = "1.13.6"
+VERSION = "1.13.7"