Streaming A Background Response

[jpiabrantes]

Confirm this is an issue with the Python library and not an underlying OpenAI API

• This is an issue with the Python library

Describe the bug

In the past, I was streaming responses an sometimes I would get disconnected from OpenAI's server with an exception httpx.ReadError, httpx.ReadTimeout or httpx.RemoteProtocolError exception.

Then I read your documentation on Streaming a background response but now I often get another error:

openai.BadRequestError: This response can no longer be streamed because it is more than 5 minutes old

Here's my code:

state = {
        "cursor": None,
        "response_id": None,
    }
    max_retries = 3

    async with RealtimeDB() as realtime_db:
        for attempt in range(max_retries):
            try:
                if state["cursor"] is None or state["response_id"] is None:
                    # First attempt, or failed before getting response_id - start fresh
                    stream = await aopenai_client.responses.create(
                        model=model,
                        input=input,
                        instructions=instructions,
                        previous_response_id=previous_response_id,
                        tools=tools,
                        reasoning=reasoning,
                        stream=True,
                        background=True,
                    )
                    async for event in stream:
                        await _handle_event(event, state, realtime_db, thought_path, realtime_path)
                else:
                    # Resume from cursor
                    async with aopenai_client.responses.stream(
                        response_id=state["response_id"],
                        starting_after=state["cursor"],
                    ) as stream:
                        async for event in stream:
                            await _handle_event(event, state, realtime_db, thought_path, realtime_path)

                return state

            except (httpx.ReadError, httpx.ReadTimeout, httpx.RemoteProtocolError):
                if attempt == max_retries - 1:
                    raise
                await asyncio.sleep(2**attempt)

Note the error happens ~ten times a day out of ~1000 messages a day.

To Reproduce

state = {
        "cursor": None,
        "response_id": None,
    }
    max_retries = 3

    async with RealtimeDB() as realtime_db:
        for attempt in range(max_retries):
            try:
                if state["cursor"] is None or state["response_id"] is None:
                    # First attempt, or failed before getting response_id - start fresh
                    stream = await aopenai_client.responses.create(
                        model=model,
                        input=input,
                        instructions=instructions,
                        previous_response_id=previous_response_id,
                        tools=tools,
                        reasoning=reasoning,
                        stream=True,
                        background=True,
                    )
                    async for event in stream:
                        await _handle_event(event, state, realtime_db, thought_path, realtime_path)
                else:
                    # Resume from cursor
                    async with aopenai_client.responses.stream(
                        response_id=state["response_id"],
                        starting_after=state["cursor"],
                    ) as stream:
                        async for event in stream:
                            await _handle_event(event, state, realtime_db, thought_path, realtime_path)

                return state

            except (httpx.ReadError, httpx.ReadTimeout, httpx.RemoteProtocolError):
                if attempt == max_retries - 1:
                    raise
                await asyncio.sleep(2**attempt)

Code snippets

OS

macOS

Python version

3.12.2

Library version

2.15.0