Fix test assertions for new unified output format and apply black formatting (#46336)

Agent-Logs-Url: https://github.com/Azure/azure-sdk-for-python/sessions/23f40ca5-7114-46ec-89be-a369e38ac971

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: m7md7sien <16615690+m7md7sien@users.noreply.github.com>

Author: Copilot

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py

@@ -232,7 +232,7 @@ async def _do_eval(self, eval_input: Dict) -> Dict[str, Union[float, str]]:  # t
         if _is_intermediate_response(eval_input.get("response")):
             return self._return_not_applicable_result(
                 "Intermediate response. Please provide the agent's final response for evaluation.",
-                self.threshold
+                self.threshold,
             )
 
         # Preprocess messages if they are lists

sdk/evaluation/azure-ai-evaluation/tests/unittests/test_agent_evaluators.py

@@ -66,11 +66,11 @@ def test_tool_call_accuracy_evaluator_missing_inputs(self, mock_model_config):
                 }
             ],
         )
+        assert result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_score"] is None
+        assert result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_result"] == "not_applicable"
+        assert result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_status"] == "skipped"
         assert (
-            result[ToolCallAccuracyEvaluator._RESULT_KEY] == ToolCallAccuracyEvaluator._DEFAULT_TOOL_CALL_ACCURACY_SCORE
-        )
-        assert (
-            "not applicable" in result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_reason"].lower()
+            "not applicable" in result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_reasoning"].lower()
             and ToolCallAccuracyEvaluator._TOOL_DEFINITIONS_MISSING_MESSAGE
-            in result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_reason"]
+            in result[f"{ToolCallAccuracyEvaluator._RESULT_KEY}_reasoning"]
         )