openai/openai-python · warning · RuntimeError

No messages found

Error message

No messages found

What it means

Raised by AssistantEventHandler.get_final_messages after stream completion when __message_snapshots is empty. Messages are accumulated from thread.message.* events; if the run produced no message events (e.g. it was cancelled, failed, or only called tools), the snapshot dict is empty and this error surfaces.

Source

Thrown at src/openai/lib/streaming/_assistants.py:131

            raise RuntimeError("No final run object found")

        return self.__current_run

    def get_final_run_steps(self) -> list[RunStep]:
        """Wait for the stream to finish and returns the steps taken in this run"""
        self.until_done()

        if not self.__run_step_snapshots:
            raise RuntimeError("No run steps found")

        return [step for step in self.__run_step_snapshots.values()]

    def get_final_messages(self) -> list[Message]:
        """Wait for the stream to finish and returns the messages emitted in this run"""
        self.until_done()

        if not self.__message_snapshots:
            raise RuntimeError("No messages found")

        return [message for message in self.__message_snapshots.values()]

    def __text_deltas__(self) -> Iterator[str]:
        for event in self:
            if event.event != "thread.message.delta":
                continue

            for content_delta in event.data.delta.content or []:
                if content_delta.type == "text" and content_delta.text and content_delta.text.value:
                    yield content_delta.text.value

    # event handlers

    def on_end(self) -> None:
        """Fires when the stream has finished.

        This happens if the stream is read to completion

View on GitHub (pinned to 9917c6e28e)

Solutions

1. Check the final run status via get_final_run() (or __current_run.status) before asking for messages
2. Wrap in try/except RuntimeError and default to an empty list if absent messages are acceptable
3. Ensure custom event overrides call super().on_event(event) so message snapshots accumulate
4. Verify the thread had a user message and the run was not cancelled

Example fix

# before
messages = stream.get_final_messages()

# after
run = stream.get_final_run()
if run.status == "completed":
    messages = stream.get_final_messages()
else:
    messages = []
    print(f"run ended with status {run.status}")

null

null

try:
    messages = stream.get_final_messages()
except RuntimeError:
    messages = []

When it happens

Trigger: Calling get_final_messages() on a run that emitted no thread.message.created/delta events - cancelled or failed runs, runs consisting only of tool steps, invalid inputs where the stream closes early, or a custom handler that skips accumulate_event.

Common situations: Assistants v2 streaming with runs that end in status cancelled/failed; handlers that override on_event without chaining; expecting a message from a run that only submitted tool outputs.

Related errors

• A single event handler cannot be shared between multiple str
• No final run object found
• No run steps found
• Stream has not been started yet
• Encountered a message delta with no previous snapshot

AI-assisted analysis of openai/openai-python@9917c6e28e (2026-08-28). Data as JSON: /api/errors/3e7acf6d47d3fe4a. Report an issue: GitHub.