Repository navigation
Shift+Tab mode toggle resets model to gpt-5.2-codex; multi-agent cannot choose model or reasoning depth #9766
Description
What version of Codex is running?
v0.89.0
What subscription do you have?
team
Which model were you using?
gpt-5.2
What platform is your computer?
Windows 11
What terminal emulator and version are you using (if applicable)?
PowerShell
What issue are you seeing?
- When I toggle modes with Shift+Tab, the currently selected model is forcibly reset to gpt-
5.2-codex. - When multi-agent mode is started, agents are locked to gpt-5.2-codex and I cannot choose a
model or set reasoning depth.
What steps can reproduce the bug?
- Model reset breaks workflow consistency and makes model comparison difficult.
- Multi-agent work can’t assign the most suitable model for each task, reducing efficiency and
quality.
What is the expected behavior?
- Add a configuration entry point for multi-agent model selection (CLI flag / config file /
interactive menu).- Keep model selection independent from mode toggle.
Additional information
No response
Activity
sonobo commentedon Jan 23, 2026
I've proposed solution at #9783 (just in case)
malyutki commentedon Jan 25, 2026
Codex 0.91.0 the problem still occurs. If you set the Code to high or xhigh and change to Plan and back to Code it changes back to gpt-5.2-codex medium even if you choose a different model. Plan also don't remember changed model, but it seems that reasoning model in the Plan is remembered
3ld0ct0r commentedon Jan 28, 2026
For OpenAI Codex (v0.92.0) , it has changed wherein
When toggling modes with Shift+Tab, the currently selected model for
Code moderemains unchanged but on toggling toPlan modeit drops toMedium (default) (current)for that model - #9980oxysoft commentedon Mar 11, 2026
Cross-linking #14356 here because it proposes the cleaner control semantics that seem to sit underneath bugs like this.
Two pieces feel especially relevant:
That does not replace the bug fix here, but it does seem like the stronger mental model for avoiding this class of confusion.
etraut-openai commentedon Oct 12, 2026
(response from codex)
Closing as addressed in CLI 0.162.1. The forced gpt-5.2-codex fallback reported in 0.89 is obsolete; subagents can now inherit the parent model or use an explicit spawn model override (#14160, #17247, #18701). This does not imply separate Plan/Default model pickers; that distinct behavior is tracked in #38236. Please reopen if you can reproduce an actual forced-model reset in a current release.