Howie/auto func sample 2 (#41901)

* add auto function call sample (#41885)

* update

* Update sample_agents_auto_function_call.py

* added async sample and use project client

* update

* fix spelling

* update change log

* Update CHANGELOG.md

* update version

* update

* update version

* Fix OpenApi Tool

* resolved comment

* Update

* fix code to pass test

* update

* update

* update

* update

* update

Author: howieleung

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

@@ -4,13 +4,12 @@
 
 ## 1.1.0b4 (Unreleased)
 
-### Features Added
-
-- Added support for MCP tool. For more information, see https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/model-context-protocol
-
 ### Sample updates
 
-- Added sample showing usage of MCP tool.
+- Added a sample showing usage of MCP tool, [`sample_agents_mcp.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_mcp.py).
+- Added a sample showing auto function call for a synchronous client, [`sample_agents_auto_function_call.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_auto_function_call.py)
+- Added a sample showing auto function call for an asynchronous client, [`sample_agents_auto_function_call_async.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_async/sample_agents_auto_function_call_async.py).
+
 
 ## 1.1.0b3 (2025-06-30)
 

sdk/ai/azure-ai-agents/README.md

@@ -422,33 +422,29 @@ Here is an example to integrate Azure AI Search:
 <!-- SNIPPET:sample_agents_azure_ai_search.create_agent_with_azure_ai_search_tool -->
 
 ```python
-with AIProjectClient(
-    endpoint=os.environ["PROJECT_ENDPOINT"],
-    credential=DefaultAzureCredential(),
-) as project_client:
-    conn_id = project_client.connections.get_default(ConnectionType.AZURE_AI_SEARCH).id
-
-    print(conn_id)
-
-    # Initialize agent AI search tool and add the search index connection id
-    ai_search = AzureAISearchTool(
-        index_connection_id=conn_id,
-        index_name="sample_index",
-        query_type=AzureAISearchQueryType.SIMPLE,
-        top_k=3,
-        filter="",
-    )
+conn_id = project_client.connections.get_default(ConnectionType.AZURE_AI_SEARCH).id
 
-    # Create agent with AI search tool and process agent run
-    agents_client = project_client.agents
+print(conn_id)
 
-    agent = agents_client.create_agent(
-        model=os.environ["MODEL_DEPLOYMENT_NAME"],
-        name="my-agent",
-        instructions="You are a helpful agent",
-        tools=ai_search.definitions,
-        tool_resources=ai_search.resources,
-    )
+# Initialize agent AI search tool and add the search index connection id
+ai_search = AzureAISearchTool(
+    index_connection_id=conn_id,
+    index_name="sample_index",
+    query_type=AzureAISearchQueryType.SIMPLE,
+    top_k=3,
+    filter="",
+)
+
+# Create agent with AI search tool and process agent run
+agents_client = project_client.agents
+
+agent = agents_client.create_agent(
+    model=os.environ["MODEL_DEPLOYMENT_NAME"],
+    name="my-agent",
+    instructions="You are a helpful agent",
+    tools=ai_search.definitions,
+    tool_resources=ai_search.resources,
+)
 ```
 
 <!-- END SNIPPET -->
@@ -531,8 +527,12 @@ agent = await agents_client.create_agent(
 
 <!-- END SNIPPET -->
 
-Notice that if `enable_auto_function_calls` is called, the SDK will invoke the functions automatically during `create_and_process` or streaming.  If you prefer to execute them manually, refer to [`sample_agents_stream_eventhandler_with_functions.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_streaming/sample_agents_stream_eventhandler_with_functions.py) or
-[`sample_agents_functions.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_functions.py)
+When `enable_auto_function_calls` is called, the SDK will automatically invoke functions during both `create_and_process` and streaming workflows. This simplifies agent logic by handling function execution internally.  Furthermore, although function tools and definitions are preserved in Agent service, their function implements are not.  Therefore, if your code queries earlier created agents through `update_agents` or `get_agents` function, you MUST also provide the function implementations through `enable_auto_function_calls` to complete auto function callings.
+
+- For examples of automatic function calls in action, refer to [`sample_agents_auto_function_call.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_auto_function_call.py) or [`sample_agents_auto_function_call_async.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_async/sample_agents_auto_function_call_async.py).
+- If you prefer to manage function execution manually, refer to [`sample_agents_stream_eventhandler_with_functions.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_streaming/sample_agents_stream_eventhandler_with_functions.py) or
+[`sample_agents_functions.py`](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_functions.py).
+
 
 ### Create Agent With Azure Function Call
 
@@ -696,13 +696,6 @@ Below is an example of how to create an Azure Logic App utility tool and registe
 <!-- SNIPPET:sample_agents_logic_apps.register_logic_app -->
 
 ```python
-
-# Create the agents client
-project_client = AIProjectClient(
-    endpoint=os.environ["PROJECT_ENDPOINT"],
-    credential=DefaultAzureCredential(),
-)
-
 # Extract subscription and resource group from the project scope
 subscription_id = os.environ["SUBSCRIPTION_ID"]
 resource_group = os.environ["resource_group_name"]
@@ -952,9 +945,11 @@ To understand what calls were made by the main agent to the connected ones, we w
 for run_step in agents_client.run_steps.list(thread_id=thread.id, run_id=run.id, order=ListSortOrder.ASCENDING):
     if isinstance(run_step.step_details, RunStepToolCallDetails):
         for tool_call in run_step.step_details.tool_calls:
-            print(f"\tAgent: {tool_call._data['connected_agent']['name']} "
-                  f"query: {tool_call._data['connected_agent']['arguments']} ",
-                  f"output: {tool_call._data['connected_agent']['output']}")
+            print(
+                f"\tAgent: {tool_call._data['connected_agent']['name']} "
+                f"query: {tool_call._data['connected_agent']['arguments']} ",
+                f"output: {tool_call._data['connected_agent']['output']}",
+            )
 ```
 
 <!-- END SNIPPET -->
@@ -969,7 +964,7 @@ messages = agents_client.messages.list(thread_id=thread.id, order=ListSortOrder.
 for msg in messages:
     if msg.text_messages:
         last_text = msg.text_messages[-1]
-        text = last_text.text.value.replace('\u3010', '[').replace('\u3011', ']')
+        text = last_text.text.value.replace("\u3010", "[").replace("\u3011", "]")
         print(f"{msg.role}: {text}")
 ```
 

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

@@ -6,4 +6,4 @@
 # Changes may cause incorrect behavior and will be lost if the code is regenerated.
 # --------------------------------------------------------------------------
 
-VERSION = "1.1.0b3"
+VERSION = "1.1.0b4"

sdk/ai/azure-ai-agents/azure/ai/agents/aio/operations/_patch.py

@@ -1043,8 +1043,13 @@ async def submit_tool_outputs(  # pylint: disable=arguments-differ
         :type thread_id: str
         :param run_id: Required.
         :type run_id: str
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
+
         :keyword content_type: Body Parameter content-type. Content type parameter for JSON body.
          Default value is "application/json".
         :paramtype content_type: str
@@ -1118,8 +1123,13 @@ async def submit_tool_outputs(
         :type run_id: str
         :param body: Is either a JSON type or a IO[bytes] type. Required.
         :type body: JSON or IO[bytes]
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
+
         :return: ThreadRun. The ThreadRun is compatible with MutableMapping
         :rtype: ~azure.ai.agents.models.ThreadRun
         :raises ~azure.core.exceptions.HttpResponseError:
@@ -1198,8 +1208,13 @@ async def submit_tool_outputs_stream(
         :type thread_id: str
         :param run_id: Required.
         :type run_id: str
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
+
         :keyword content_type: Body Parameter content-type. Content type parameter for JSON body.
          Default value is "application/json".
         :paramtype content_type: str
@@ -1230,8 +1245,13 @@ async def submit_tool_outputs_stream(  # pyright: ignore[reportInconsistentOverl
         :type run_id: str
         :param body: Is either a JSON type or a IO[bytes] type. Required.
         :type body: JSON or IO[bytes]
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
+
         :keyword event_handler: The event handler to use for processing events during the run.
         :paramtype event_handler: ~azure.ai.agents.models.AsyncAgentEventHandler
         :raises ~azure.core.exceptions.HttpResponseError:

sdk/ai/azure-ai-agents/azure/ai/agents/models/_patch.py

@@ -790,6 +790,13 @@ def resources(self) -> ToolResources:
         """
         return ToolResources()
 
+    def execute(self, tool_call: Any) -> None:
+        """
+        OpenApiTool does not execute client-side.
+        :param Any tool_call: The tool call to execute.
+        :type tool_call: Any
+        """
+
 
 class McpTool(Tool[MCPToolDefinition]):
     """
@@ -901,26 +908,46 @@ def update_headers(self, key: str, value: str) -> None:
                 server_label=self._server_label, headers=self._headers, require_approval=self._require_approval
             )
         else:
-            raise ValueError(f"Header key cannot be empty.")
+            raise ValueError("Header key cannot be empty.")
 
     @property
     def server_label(self) -> str:
-        """Get the server label."""
+        """
+        Get the server label for the MCP tool.
+
+        :return: The label identifying the MCP server.
+        :rtype: str
+        """
         return self._server_label
 
     @property
     def server_url(self) -> str:
-        """Get the server URL."""
+        """
+        Get the server URL for the MCP tool.
+
+        :return: The endpoint URL for the MCP server.
+        :rtype: str
+        """
         return self._server_url
 
     @property
     def allowed_tools(self) -> List[str]:
-        """Get the list of allowed tools."""
+        """
+        Get the list of allowed tools for the MCP server.
+
+        :return: A copy of the list of tool names that are allowed to be executed on this MCP server.
+        :rtype: List[str]
+        """
         return self._allowed_tools.copy()
 
     @property
     def headers(self) -> Dict[str, str]:
-        """Get the headers for the MCP tool."""
+        """
+        Get the headers for the MCP tool.
+
+        :return: Dictionary of HTTP headers to be sent with MCP server requests.
+        :rtype: Dict[str, str]
+        """
         return self._resource.headers
 
     @property

sdk/ai/azure-ai-agents/azure/ai/agents/operations/_patch.py

@@ -1065,7 +1065,11 @@ def submit_tool_outputs(  # pylint: disable=arguments-differ
         :type thread_id: str
         :param run_id: Required.
         :type run_id: str
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
         :keyword content_type: Body Parameter content-type. Content type parameter for JSON body.
          Default value is "application/json".
@@ -1143,7 +1147,11 @@ def submit_tool_outputs(
         :type run_id: str
         :param body: Is either a JSON type or a IO[bytes] type. Required.
         :type body: JSON or IO[bytes]
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
         :return: ThreadRun. The ThreadRun is compatible with MutableMapping
         :rtype: ~azure.ai.agents.models.ThreadRun
@@ -1232,7 +1240,11 @@ def submit_tool_outputs_stream(
         :type thread_id: str
         :param run_id: Required.
         :type run_id: str
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
         :keyword content_type: Body Parameter content-type. Content type parameter for JSON body.
          Default value is "application/json".
@@ -1249,8 +1261,8 @@ def submit_tool_outputs_stream(  # pyright: ignore[reportInconsistentOverload]
         run_id: str,
         body: Union[JSON, IO[bytes]] = _Unset,
         *,
-        tool_outputs: Optional[List[_models.ToolOutput]] = None,
-        tool_approvals: Optional[List[_models.ToolApproval]] = None,
+        tool_outputs: Optional[List[_models.ToolOutput]] = _Unset,
+        tool_approvals: Optional[List[_models.ToolApproval]] = _Unset,
         event_handler: _models.BaseAgentEventHandler,
         **kwargs: Any,
     ) -> None:
@@ -1264,7 +1276,11 @@ def submit_tool_outputs_stream(  # pyright: ignore[reportInconsistentOverload]
         :type run_id: str
         :param body: Is either a JSON type or a IO[bytes] type. Required.
         :type body: JSON or IO[bytes]
+        :keyword tool_outputs: A list of tools for which the outputs are being submitted. Default value
+         is None.
         :paramtype tool_outputs: list[~azure.ai.agents.models.ToolOutput]
+        :keyword tool_approvals: A list of tool approvals allowing data to be sent to tools. Default
+         value is None.
         :paramtype tool_approvals: list[~azure.ai.agents.models.ToolApproval]
         :keyword event_handler: The event handler to use for processing events during the run.
         :paramtype event_handler: ~azure.ai.agents.models.BaseAgentEventHandler