What version of Codex CLI is running?

codex-cli 0.125.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.4

What platform is your computer?

Linux 6.19.8 x86_64 unknown (Debian 13, no idea why its "unknown")

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

GNOME Terminal

What issue are you seeing?

When model are summarying up, or reporting to user, example: I did... I changed..., it would cause working message be disappeared

What steps can reproduce the bug?

(Thread ID are not available due to sensitive info)
Let agent do a thing
When summarying up,
queue next message
Suppose, you should be seeing no working message initally
But Agent will still do its job, and the working message gonna came back after first tool call

What is the expected behavior?

Immediately able to see working

Additional information

No response