Summary

This PR adds support forstreaming tool output in the OpenAI Agents SDK. Previously, users could only receive tool results after complete execution. Now, tools can yield incremental output during execution, enabling real-time progress feedback for long-running operations.

Key improvements:

• NewToolOutputStreamEvent for receiving incremental tool output
• Support for async generator functions as tools (returningAsyncIterator[str])
• Automatic chunk accumulation for final LLM output
• Full backward compatibility with existing non-streaming tools
• Works in bothRunner.run_streamed() andRunner.run() modes

Type system fix:
Fixed the type signature ofFunctionTool.on_invoke_tool from:

Callable[[...],Awaitable[Any]|AsyncIterator[str]]

to:

Callable[[...],Awaitable[Any|AsyncIterator[str]]]

This properly represents that the function always returns an awaitable, which then yields either a regular value or an async iterator.

Test plan

New tests (tests/test_tool_streaming.py):

1. test_basic_streaming_tool - Verifies basic streaming functionality
2. test_streaming_tool_with_arguments - Tests parameter handling
3. test_mixed_streaming_and_non_streaming_tools - Validates coexistence
4. test_streaming_tool_accumulation - Confirms proper output accumulation
5. test_streaming_tool_in_non_streaming_mode - TestsRunner.run() mode
6. test_streaming_tool_agent_association - Checks event metadata

Example (examples/tools/streaming_tool_example.py):

• Runnable example demonstrating streaming tools with realistic use case

Validation:

make format# ✅ All files formattedmake lint# ✅ All checks passedmake mypy# ✅ 347 files type-checked successfullymake tests# ✅ 926 tests passed (including 6 new streaming tests)

Issue number

N/A - New feature enhancement

Checks

• I've added new tests (6 comprehensive tests)
• I've added/updated the relevant documentation (4 language versions)
• I've runmake lint andmake format (all passed)
• I've made sure tests pass (926 passed, 3 skipped)

Usage Example

fromcollections.abcimportAsyncIteratorfromagentsimportAgent,Runner,function_tool@function_toolasyncdefsearch_documents(query:str)->AsyncIterator[str]:"""Search through documents and stream results."""documents= ["Doc 1...","Doc 2...","Doc 3..."]fordocindocuments:awaitasyncio.sleep(0.5)yielddocagent=Agent(name="Research Assistant",tools=[search_documents],)result=Runner.run_streamed(agent,input="Search for AI info")asyncforeventinresult.stream_events():ifevent.type=="tool_output_stream_event":print(f"[{event.tool_name}]{event.delta}",end="",flush=True)

Documentation

Updated streaming documentation in 4 languages:

• English:docs/streaming.md
• Chinese:docs/zh/streaming.md
• Japanese:docs/ja/streaming.md
• Korean:docs/ko/streaming.md

All include complete examples and key points about streaming tools.