litellm-claude-streaming.py

from agents import Agent, ModelSettings, Runner, function_tool
from agents.extensions.models.litellm_model import LitellmModel
from openai.types.shared import Reasoning


@function_tool
def echo_tool(input: str) -> str:
    print("called echo_tool")
    return input

@function_tool
def speak_tool(input: str) -> str:
    print("called speak_tool")
    return input

@function_tool
def final_tool(input: str) -> str:
    print("called final_tool")
    return input

model = LitellmModel(
    model="claude-opus-4-5-20251101",
)

agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant",
    model=model,
    tools=[echo_tool, speak_tool, final_tool],
    model_settings=ModelSettings(reasoning=Reasoning(effort="low"))
)

async def main():

    result = Runner.run_streamed(
        agent, """Think about two key words related to the meaning of life, then use both echo_tool and speak_tool to pass in these two keywords
<tool_preambles>
- Always begin by rephrasing the user's goal in a friendly, clear, and concise manner, before calling any tools.
- Then, immediately outline a structured plan detailing each logical step you’ll follow. - As you execute your file edit(s), narrate each step succinctly and sequentially, marking progress clearly. 
- Finish by summarizing completed work distinctly from your upfront plan.
</tool_preambles>"""
    )
    async for event in result.stream_events():
         print(".", end="", flush=True)

    print("--------------------------------")
    print(result.final_output)
    print("----------")
    print(result.to_input_list())

import asyncio
if __name__ == "__main__":
    asyncio.run(main())