openai/openai-python · error · RuntimeError

No final run object found

Error message

No final run object found

What it means

Raised by AssistantEventHandler.get_final_run after the stream is fully consumed. It means the stream completed without the handler ever storing a Run object in __current_run, which normally happens when a thread.run.* event carrying run data is processed. Typically the run never actually started or the stream ended before any run snapshot arrived.

Source

Thrown at src/openai/lib/streaming/_assistants.py:113

    def close(self) -> None:
        """
        Close the response and release the connection.

        Automatically called when the context manager exits.
        """
        if self.__stream:
            self.__stream.close()

    def until_done(self) -> None:
        """Waits until the stream has been consumed"""
        consume_sync_iterator(self)

    def get_final_run(self) -> Run:
        """Wait for the stream to finish and returns the completed Run object"""
        self.until_done()

        if not self.__current_run:
            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")

View on GitHub (pinned to 9917c6e28e)

Solutions

1. Inspect the raw events: override on_event or iterate stream to see which thread.run.* events actually arrived
2. Verify thread_id and assistant_id are valid and the run was accepted (check for APIError during streaming)
3. If you need resilience, call get_final_run inside try/except RuntimeError and fall back to client.beta.threads.runs.retrieve(run_id)
4. Upgrade the SDK - older builds had gaps in run event accumulation

Example fix

# before
run = stream.get_final_run()

# after
try:
    run = stream.get_final_run()
except RuntimeError:
    run = client.beta.threads.runs.retrieve(thread_id=thread_id, run_id=run_id)

null

null

try:
    run = stream.get_final_run()
except RuntimeError as e:
    if "No final run object" in str(e):
        run = client.beta.threads.runs.retrieve(thread_id=thread_id, run_id=run_id)

When it happens

Trigger: Calling stream.get_final_run() on an Assistants v2 run stream that produced no thread.run.created/queued/in_progress events - e.g. streaming with an invalid assistant_id or thread_id where the server closes the stream early, or consuming the stream after it errored client-side so run events were never accumulated.

Common situations: Using the Assistants streaming API (v2 beta) and calling get_final_run after until_done; runs cancelled server-side immediately; malformed thread/assistant ids; the API silently terminating the SSE stream.

Related errors

• A single event handler cannot be shared between multiple str
• No run steps found
• No messages 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/cfa4429b545eba3c. Report an issue: GitHub.