chatcmpl-gemini3-streaming.py

from agents import Agent, ModelSettings, Runner, function_tool, OpenAIChatCompletionsModel
from openai.types.shared import Reasoning

from openai import AsyncOpenAI
import os

custom_client = AsyncOpenAI(
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
    api_key=os.getenv("GEMINI_API_KEY")
)

my_model = OpenAIChatCompletionsModel(
        model="gemini-3-pro-preview",
        openai_client=custom_client,
    )

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

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

async def main():

    result = Runner.run_streamed(
        agent, """think about life, then use echo_tool
<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(event, flush=True)

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

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