Codex got stuck: Codex ran out of room in the model's context window.
Resolved 💬 3 comments Opened Feb 2, 2026 by jiaxi98 Closed Feb 2, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
v0.93.0
What subscription do you have?
Pro
Which model were you using?
gpt-5.2-codex
What platform is your computer?
Linux 5.4.0-91-generic x86_64 x86_64
What terminal emulator and version are you using (if applicable)?
_No response_
What issue are you seeing?
Codex ran out of room in the model's context window. Start a new thread or clear earlier history before retrying.
- codex does not perform autocompact and the conversation got stuck
- this has been a long chat, but when I quit, it outputs: Token usage: total=0 input=0 output=0, To continue this session, run codex resume 92c9be60-410c-4c16-a907-a7990907a3fd
What steps can reproduce the bug?
Uploaded thread: 92c9be60-410c-4c16-a907-a7990907a3fd
What is the expected behavior?
The codex autocompact the context and work
Additional information
_No response_
3 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
After successfully autocompact lots of time, it finally breaks down and /compact won't help. Similar to the circumstances in https://github.com/openai/codex/issues/9142
Duplicate of #9046.