docs: add documentation for real-time streaming of function call argu…

…ments

docs/streaming.md

@@ -31,6 +31,73 @@ if __name__ == "__main__":
  asyncio.run(main())
 ```
 
+### Function call argument streaming
+
+Function call arguments are now streamed in real-time as they are generated, providing immediate feedback during large parameter generation. This is especially useful for scenarios like code generation, API request building, or complex configuration creation.
+
+```python
+import asyncio
+from openai.types.responses import ResponseFunctionCallArgumentsDeltaEvent
+from agents import Agent, Runner, function_tool
+
+@function_tool
+def write_file(filename: str, content: str) -> str:
+ """Write content to a file."""
+ return f"File {filename} written successfully"
+
+async def main():
+ agent = Agent(
+ name="CodeGenerator",
+ instructions="You are a helpful coding assistant. When asked to create files, use the write_file tool.",
+ tools=[write_file],
+ )
+
+ result = Runner.run_streamed(
+ agent,
+ input="Create a Python script that prints 'Hello, World!' and saves it as hello.py"
+ )
+
+ function_name = None
+ current_arguments = ""
+
+ async for event in result.stream_events():
+ if event.type == "raw_response_event":
+ # Function call started
+ if event.data.type == "response.output_item.added":
+ if hasattr(event.data.item, 'name'):
+ function_name = event.data.item.name
+ print(f"📞 Function call streaming started: {function_name}()")
+ print("📝 Arguments building...")
+
+ # Real-time argument streaming
+ elif isinstance(event.data, ResponseFunctionCallArgumentsDeltaEvent):
+ current_arguments += event.data.delta
+ print(f" + {event.data.delta}", end="", flush=True)
+
+ # Function call completed
+ elif event.data.type == "response.output_item.done":
+ if hasattr(event.data.item, 'name'):
+ print(f"\n✅ Function call streaming completed: {function_name}")
+ print(f"🔧 Final arguments: {current_arguments}")
+
+ print(f"\n🎉 Result: {result.final_output}")
+
+
+if __name__ == "__main__":
+ asyncio.run(main())
+```
+
+This will show the function arguments being built incrementally:
+```
+📞 Function call streaming started: write_file()
+📝 Arguments building...
+ + {"filename": "
+ + hello.py", "content": "
+ + print('Hello, World!')"}
+✅ Function call streaming completed: write_file
+🔧 Final arguments: {"filename": "hello.py", "content": "print('Hello, World!')"}
+```
+
 ## Run item events and agent events
 
 [`RunItemStreamEvent`][agents.stream_events.RunItemStreamEvent]s are higher level events. They inform you when an item has been fully generated. This allows you to push progress updates at the level of "message generated", "tool ran", etc, instead of each token. Similarly, [`AgentUpdatedStreamEvent`][agents.stream_events.AgentUpdatedStreamEvent] gives you updates when the current agent changes (e.g. as the result of a handoff).