LiteLlm finalizes a stream cut off mid-answer as finish_reason STOP with no error #7693

import asyncio, json, threading, time

import uvicorn
from starlette.applications import Starlette
from starlette.responses import StreamingResponse
from starlette.routing import Route

from google.adk.models.lite_llm import LiteLlm
from google.adk.models.llm_request import LlmRequest
from google.genai import types


def chunk(delta, finish=None):
    return {"id": "c1", "object": "chat.completion.chunk", "created": int(time.time()), "model": "gpt-4o",
            "choices": [{"index": 0, "delta": delta, "finish_reason": finish}]}


async def completions(request):
    cut = (await request.json())["model"] == "cut"

    async def sse():
        yield f"data: {json.dumps(chunk({'role': 'assistant', 'content': 'Oslo is '}))}\n\n"
        yield f"data: {json.dumps(chunk({'content': '4C and'}))}\n\n"
        if cut:
            raise ConnectionResetError("server dropped the stream")
        yield f"data: {json.dumps(chunk({'content': ' cloudy.'}))}\n\n"
        yield f"data: {json.dumps(chunk({}, 'stop'))}\n\n"
        yield "data: [DONE]\n\n"

    return StreamingResponse(sse(), media_type="text/event-stream")


server = uvicorn.Server(uvicorn.Config(
    Starlette(routes=[Route("/v1/chat/completions", completions, methods=["POST"])]),
    port=8797, log_level="critical"))
threading.Thread(target=server.run, daemon=True).start()
while not server.started:
    time.sleep(0.05)


async def main():
    for model in ("complete", "cut"):
        llm = LiteLlm(model=f"openai/{model}", api_base="http://127.0.0.1:8797/v1", api_key="unused")
        request = LlmRequest(model=f"openai/{model}", contents=[types.Content(role="user", parts=[types.Part(text="weather?")])])
        last = None
        async for response in llm.generate_content_async(request, stream=True):
            last = response
        text = "".join(p.text or "" for p in last.content.parts)
        print(f"{model:9} final: partial={last.partial} finish_reason={last.finish_reason} error_code={last.error_code} text={text!r}")

asyncio.run(main())
server.should_exit = True