How are you running AnythingLLM?

Docker (remote machine)

What happened?

If an agent fails to run (e.g. there was an API error) then it attempts to re-try every minute. However, this sometimes continues to run even after the user has done /exit.

Is there a way to stop all attempts for any retries, or set a limit on the number of retries?

Are there known steps to reproduce?

Create an agent that fails during a request to a remote API. (This is via a custom skill, rather than the agent builder)