ai-agents-streaming-tool-call--when-using-langgraph-s-astream-events-with-an-olla-d5c13b38

THEN Replace astream_events with astream for the graph execution. astream correctly parses tool calls from the Ollama proxy, while astream_events appears to lose the structured tool call information.

async def test():
    async for event in app.astream(
        {"messages": [HumanMessage(content="what is the weather in sf")]},
        config={"configurable": {"thread_id": 42}},
    ):
        print(event)