codex can't stop writing continue
Resolved 💬 2 comments Opened Nov 19, 2025 by markuskruse Closed Nov 19, 2025
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
0.58.0
What subscription do you have?
pro
Which model were you using?
gpt-5.1-codex (reasoning medium, summaries auto)
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
I run codex through WSL in a session. So I type codex in wsl, the prompt opens and I can type my requestst.
At one point, it started spamming "Continue" all over the page. I hit Ctrl+C and told it to stop.
Then it worked mostly fine, some minor outbursts. It promised to never do it again (of course).
Then this happened:
<img width="2048" height="1123" alt="Image" src="https://github.com/user-attachments/assets/603eb12b-b619-4b7c-990e-33068587944d" />
It was a bit funny how it realized that it was abnormal behaviour, but still not able to stop it. Reminds me of the verse in Romans 7:15-20.
What steps can reproduce the bug?
Really not sure.
What is the expected behavior?
Not abnormal output.
Additional information
Happy to share prompts.
2 Comments
Thanks for the bug report. We'll share the feedback with the team responsible for training our codex models. If you see other model behavior that you'd like to report, please use the
/feedbackcommand in the CLI. That will provide us with additional details including logs and conversation text.Thanks. Ok, I asked codex if /feedback was shared. It said it wasn't, that it was only feedback to the agent. Then again, it wouldn't be the first time it seemed to be sure, when it was wrong. :-)