Python: [BREAKING] changed AIFunction to FunctionTool and @ai_function to @tool (#3413)

* changed AIFunction to FunctionTool and @ai_function to @tool

* test and mypy fixes

* mypy fix

* switch function tool to always_require

* fix noop

* fix github copilot imports

* test fixes

* fix ollama test

* fixes for tests

* fix tests

* reverted change to always_require and extended timeout

* fix test

python/samples/autogen-migration/README.md

@@ -53,7 +53,7 @@ python samples/autogen-migration/orchestrations/04_magentic_one.py
 
 - **Default behavior differences**: AutoGen's `AssistantAgent` is single-turn by default (`max_tool_iterations=1`), while AF's `ChatAgent` is multi-turn and continues tool execution automatically.
 - **Thread management**: AF agents are stateless by default. Use `agent.get_new_thread()` and pass it to `run()`/`run_stream()` to maintain conversation state, similar to AutoGen's conversation context.
-- **Tools**: AutoGen uses `FunctionTool` wrappers; AF uses `@ai_function` decorators with automatic schema inference.
+- **Tools**: AutoGen uses `FunctionTool` wrappers; AF uses `@tool` decorators with automatic schema inference.
 - **Orchestration patterns**:
   - `RoundRobinGroupChat` → `SequentialBuilder` or `WorkflowBuilder`
   - `SelectorGroupChat` → `GroupChatBuilder` with LLM-based speaker selection

python/samples/autogen-migration/orchestrations/01_round_robin_group_chat.py

@@ -103,6 +103,7 @@ async def run_agent_framework_with_cycle() -> None:
         WorkflowContext,
         WorkflowOutputEvent,
         executor,
+        tool,
     )
     from agent_framework.openai import OpenAIChatClient
 

python/samples/autogen-migration/orchestrations/03_swarm.py

@@ -102,6 +102,7 @@ async def run_agent_framework() -> None:
         RequestInfoEvent,
         WorkflowRunState,
         WorkflowStatusEvent,
+        tool,
     )
     from agent_framework.openai import OpenAIChatClient
 

python/samples/autogen-migration/orchestrations/04_magentic_one.py

@@ -63,6 +63,7 @@ async def run_agent_framework() -> None:
         MagenticBuilder,
         MagenticFinalResultEvent,
         MagenticOrchestratorMessageEvent,
+        tool,
     )
     from agent_framework.openai import OpenAIChatClient
 

python/samples/autogen-migration/single_agent/02_assistant_agent_with_tool.py

@@ -46,12 +46,13 @@ async def run_autogen() -> None:
 
 
 async def run_agent_framework() -> None:
-    """Agent Framework agent with @ai_function decorator."""
-    from agent_framework import ai_function
+    """Agent Framework agent with @tool decorator."""
+    from agent_framework import tool
     from agent_framework.openai import OpenAIChatClient
 
-    # Define tool with @ai_function decorator (automatic schema inference)
-    @ai_function
+    # Define tool with @tool decorator (automatic schema inference)
+    # NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+    @tool(approval_mode="never_require")
     def get_weather(location: str) -> str:
         """Get the weather for a location.