Run status stucked in 'queued'

Since last week ( July 21st) my Assistants have been stucking in the ‘queued’ status for a long time. Is it happening to anybody else?

No. This isn’t typical. Especially for a week.

There is a time-based cancelling function integrated in runs.

expired This happens when the function calling outputs were not submitted before expires_at and the run expires. Additionally, if the runs take too long to execute and go beyond the time stated in expires_at, our systems will expire the run.

https://platform.openai.com/docs/assistants/deep-dive/run-lifecycle

I’m not sure what this time is, but I’m feeling confident that it’s not > a week :rofl:. More likely to be some minutes-based timeframe.

Last time this issue was raised the staff of OpenAI came asking for some Thread IDs. There’s no promises but that this will happen again but could you share these IDs in the event that they do?

If you are new and you do not want to build all the code, you should try this:

Thanks for the answer, I didn’t mean that threads have been in the ‘queued’ status for a week. But since last week, I’ve been creating runs that get stucked in the ‘queued’ status.

This has been happening for numerous thread ids and for all the assistants I currently have.

I have also been experiencing this issue. 5-10 wait times on 4o assistant runs.

Were you able to solve it? It’s been happening to me when I add an image_url message.

Seems like it’s an internal error, but it’s not announced by OpenAI.

No. It comes and goes, luckily it hasn’t happened to me this week.