LiteLlm model in ADK ignores stream=True — no streaming happens

[Asvin31]

** Please make sure you read the contribution guide and file the issues in the right place. **
Contribution guide.

Describe the bug

When using LiteLlm inside LlmAgent or SequentialAgent with stream=True, ADK does not actually stream the response.

To Reproduce
Steps to reproduce the behavior:

1. Set up a LlmAgent using LiteLlm(stream=True)
2. Use Runner.run_async() to handle a message
3. Observe that no streaming happens; full response is returned after delay

Expected behavior
Streaming responses via LiteLLM and Ollama should work when stream=True is passed to LiteLlm.

[zakahan]

You should configure RunConfig instead of using the stream field of litellm (currently google-adk 1.8).

Please refer to this code.

import os

from google.adk import Runner
from google.adk.agents import Agent, RunConfig
from google.adk.agents.run_config import StreamingMode
from google.adk.models.lite_llm import LiteLlm
from google.adk.sessions import InMemorySessionService
from google.genai import types


def create_litellm_model(
    model: str = os.getenv("API_MODEL_NAME"),
    api_key: str = os.getenv("API_KEY"),
    api_base: str = os.getenv("API_BASE_URL")
):
    return LiteLlm(
        model=f"openai/{model}",
        api_key=api_key,
        api_base=api_base,
    )


app_name = "ChatBot"
user_id = "user_01"
session_id = "12345678"

session_service = InMemorySessionService()

root_agent = Agent(
    model = create_litellm_model(),
    name = app_name,
    description="This is a chatbot",
    instruction="You are a chatbot and you can answer users' questions.",
)


async def main(prompt: str, stream: bool):
    run_config = RunConfig(
        streaming_mode=StreamingMode.NONE if not stream else StreamingMode.SSE,
    )

    await session_service.create_session(
        app_name=app_name,
        user_id=user_id,
        session_id=session_id,
    )

    runner = Runner(
        app_name=app_name,
        agent=root_agent,
        session_service=session_service,
    )
    message = types.Content(role="user", parts=[types.Part(text=prompt)])
    async for event in runner.run_async(
            user_id=user_id,
            session_id=session_id,
            new_message=message,
            run_config=run_config
    ):
        if event.content and event.content.parts and event.content.parts[0].text:
            print(event.content.parts[0].text, end="", flush=True)

if __name__ == "__main__":
    import asyncio
    x = asyncio.run(
        main(
            prompt="please tell me a story.",
            stream=True
        )
    )