import asyncio
from agent_framework.openai import OpenAIChatClient
from agent_framework import Agent
from agent_framework.azure import AzureOpenAIChatClient
from dotenv import load_dotenv
import os

load_dotenv()

async def main():
    # client = OpenAIChatClient(
    #     base_url="https://models.github.ai/inference",
    #     model_id="openai/gpt-4.1-mini",
    #     api_key=os.getenv("APIKEY"),
    # )

    client = AzureOpenAIChatClient(
        api_version="2024-12-01-preview",
        endpoint=os.getenv("AZURE_AI_PROJECT_ENDPOINT"),
        deployment_name=os.getenv("AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"),
        api_key=os.getenv("FOUNDRY_APIKEY")
    )

    agent = client.as_agent(
       instructions="You are a friendly assistant. Keep your answers concise and helpful.", name="ConversationAgent"
    )

    session = agent.create_session()
    async for chunk in agent.run("My name is Alice and I love hiking.", session=session, stream=True):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    
    print("\n\n")
    
    async for chunk in agent.run("What do you remember about me?", session=session, stream=True):
        if chunk.text:
            print(chunk.text, end="", flush=True)
    
if __name__ == "__main__":
    asyncio.run(main())