codex app does not respect model_reasoning_effort
Resolved 💬 3 comments Opened Feb 4, 2026 by SunRunAway Closed Feb 4, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of the Codex App are you using (From “About Codex” dialog)?
260203.1501 (523)
What subscription do you have?
plus
What issue are you seeing?
in .codex/config.toml
model = "gpt-5.2"
model_reasoning_effort = "high"When I start codex.app, the reasoning level of a new thread is High,
but when click a previous thread, the reasoning level becomes medium.
What steps can reproduce the bug?
- Create a new thread in the Codex tui. Right now it uses GPT-5.2 with model_reasoning_effort=high.
- Select this session in the Codex app. The UI shows GPT-5.2 medium.
What is the expected behavior?
_No response_
Additional information
_No response_
3 Comments
The
model_reasoning_effortaffects the default reasoning level. When you switch to an existing thread, the app will go back to the reasoning level that was last used in that thread. If you want to change the reasoning level on an existing thread, you can use the control in the UI.I found a better way to reproduce it.
And I’ve found that as long as the same thread is used alternately in the Codex TUI and the Codex app, after using the Codex TUI, the thread’s reasoning level in the Codex app gets reset to medium.