GPT-5 Codex is repeatedly refusing to perform large tasks.
Resolved 💬 3 comments Opened Sep 19, 2025 by travisjbeck Closed Nov 11, 2025
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
0.38.0
Which model were you using?
gpt5-codex
What platform is your computer?
Darwin 24.6.0 arm64 arm
What steps can reproduce the bug?
<img width="2862" height="1470" alt="Image" src="https://github.com/user-attachments/assets/afe3942a-ec48-4f75-b7d6-6fec5766c3c4" />
GPT-5 Codex was working through a large code migration but then failed to resolve linting and TypeScript errors repeatedly. It said the task was too big.
What is the expected behavior?
To work through the issues one by one.
What do you see instead?
_No response_
Additional information
_No response_
3 Comments
Hi @travisjbeck, I think you are experiencing the same issue that I am in #3938. It seems to think that it's in a different environment (sandboxed and time-limited). I've noticed it since 0.39.0, so hopefully they can revert it soon.
Edit: I believe it comes from this recent change: #3874
try to change model, by typing /model and select model 3 ( gpt-5-codex high).
@adammikulis @travisjbeck
Thanks for the bug report. We've shared the feedback with the team members who are responsible for training our codex models. We're tracking this feedback and similar reports so we can make the model more robust in future iterations.
If you see other model behavior that you'd like to report, please use the recently-added /feedback command in the CLI. That will provide us with additional details including logs and conversation text.