Groundedness Evaluator to not add tool result to tool call message (#43290)

* Groundededness Evalautor to not add tool result to tool call message

* Fixing reformatting issues

Author: singankit

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_common/_base_eval.py

@@ -5,6 +5,7 @@
 import inspect
 from abc import ABC, abstractmethod
 import json
+import copy
 from typing import (
     Any,
     Callable,
@@ -500,7 +501,7 @@ def _parse_tools_from_response(self, response):
                 if message.get("role") == "assistant" and isinstance(message.get("content"), list):
                     for content_item in message.get("content"):
                         if isinstance(content_item, dict) and content_item.get("type") == "tool_call":
-                            tool_calls.append(content_item)
+                            tool_calls.append(copy.deepcopy(content_item))
 
                 # Extract tool results from tool messages
                 elif message.get("role") == "tool" and message.get("tool_call_id"):