I have been experiencing an issue with the Codex app, where occasionally the model will be stuck “Thinking” for several hours and not actually running any commands etc.
I am then quitting and restarting the Codex app, where I see that the task is actually finished, and I can see the response message from the model.
This has happened to me overnight, and Codex ate approximately 700 tokens.
Has anyone else experienced this issue or something similar? Do you have any fixes?
Hey @BoloJuju, that’s odd. To help us understand what’s happening, could you please share the time window (including timezone), numbered steps to reproduce with expected vs actual behavior, the exact error text (copy/paste) plus a screenshot if possible, your environment details (browser/app name and version, OS and version, and device model if mobile), and the request ID/trace ID if available.
please ping us at support@openai.com and share the above information there so we can look into this further.