Model thinking level resets to "medium (default)" when sending prompt in 0.104.0 with different thinking level configured

What version of Codex CLI is running?

0.104.0

What subscription do you have?

Pro

Which model were you using?

GPT 5.2 xHigh but not model specific

What platform is your computer?

Windows 11 x64

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

Windows Terminal (PowerShell 7)

What issue are you seeing?

The statusline shows the expected thinking mode of the model (gpt-5.2 xhigh) but on sending the prompt via Return, the model switches to gpt-5.2 medium (default).

When stopping the agent, typing /mode, now "medium" thinking is selected and shown as default.
The default thinking mode in the config is xhigh however.

No subagent configuration is with this thinking/model combination fwiw.

Suggestion

None

What steps can reproduce the bug?

Unsure yet, opening different codex sessions and/or using /new, /fork and maybe subagents might trigger this.
0.101.0 was fine for sure. This only happened after upgrading to 0.104.0

What is the expected behavior?

Model stays as the session was configured.

Additional information

None