model_reasoning_effort and model are not setting the default model
Open 💬 2 comments Opened Jan 23, 2026 by malyutki
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
codex-cli 0.89.0
What subscription do you have?
PRO
Which model were you using?
gpt-5.2 and gpt-5.2-codex
What platform is your computer?
Darwin 25.2.0 arm64 arm
What terminal emulator and version are you using (if applicable)?
terminal, warp
What issue are you seeing?
Setting:
model = "gpt-5.2"
model_reasoning_effort = "high"
isn't setting model and reasoning as default and each new session is starting with medium reasoning and always gpt-5.2-codex
What steps can reproduce the bug?
open new session and check /status
What is the expected behavior?
new sessions starts with correct model and reasoning effort
Additional information
_No response_
2 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
I've proposed the solution at https://github.com/openai/codex/issues/9783 (just in case leaving comment here with the link)