The model has issues with recurrent visual perception.

Resolved 💬 2 comments Opened Apr 22, 2026 by tesoldofficial Closed Apr 22, 2026

What version of Codex CLI is running?

0.122.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.4 xhigh

What platform is your computer?

CLI

What terminal emulator and version are you using (if applicable)?

_No response_

What issue are you seeing?

<img width="503" height="641" alt="Image" src="https://github.com/user-attachments/assets/c67e2125-7b10-4de4-a07c-abc8d5fdefa9" /> Here is an example of the lines next to the folders that I gave the model to create.

What i got:

<img width="390" height="748" alt="Image" src="https://github.com/user-attachments/assets/a9b7f881-e846-4357-a5ea-ecb92246fece" />

<img width="487" height="607" alt="Image" src="https://github.com/user-attachments/assets/f5b18902-1b36-4880-9fa1-29d7a084ae25" />

<img width="255" height="421" alt="Image" src="https://github.com/user-attachments/assets/5c336d26-e1a7-4f30-a376-88b6a6e13589" />

Every time I manually sent her a screenshot, she would find errors, try to fix them - doing a poor job in the process - and then, after looking at the screenshot generated by Playwright, she would somehow claim that everything was now perfect.

What steps can reproduce the bug?

Uploaded thread: 019db474-53ec-7a71-b150-28ad9dcfa204

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗