Stopped effectively working, although reporting "working"

Resolved 💬 3 comments Opened Jan 6, 2026 by dcs-scd Closed Jan 17, 2026

💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

OpenAI Codex (v0.77.0)

What subscription do you have?

pro

Which model were you using?

gpt-5.2-pro with API

What platform is your computer?

Linux 6.8.0-88-generic x86_64 x86_64

What issue are you seeing?

Model debugged local code and ran for a while ok, but then it reported working with no progress. i stopped, resumed, asked for progress report. No answer, continue to say "working", but it was consuming my credits. Not cool!!! So I am not sure what really happen and where were the changes made to my code for which a fair number of credits were consumed.

What steps can reproduce the bug?

Uploaded thread: 019b90a0-425f-7b03-97dd-82014a78f2b2

What is the expected behavior?

Provide value for the money!

Additional information

_No response_

View original on GitHub ↗

3 Comments

github-actions[bot] contributor · 7 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

#6671

Powered by Codex Action

etraut-openai contributor · 7 months ago

Thanks for using the /feedback tool.

In your session, I'm seeing the AGENTS.md instructions and one prompt that looks like a small bit of xml. Did you intend to give Codex some instruction in the prompt? I'm guessing that the lack of instruction is what confused it. The log unfortunately doesn't appear to include any details about the cancelation or token usage.

etraut-openai contributor · 7 months ago

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 /feedback command. That will provide us with additional details including logs and conversation text.