Codex ran out of room in the model's context window. Start a new thread or clear earlier history before retrying

What version of Codex CLI is running?

v0.124.0

What subscription do you have?

Pro 20x

Which model were you using?

gpt-5.5 xhigh

What platform is your computer?

Darwin 25.4.0 arm64 arm

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

VSCode

What issue are you seeing?

After a few hours of working, i start getting this which is the 1st time ever, i'm not sure if there is a bug or this is a new feature, because whatever it is this is really so bad, and even with 258K context window, we're working on a huge project and this new bug/feature is completely destroying everything!

Codex ran out of room in the model's context window. Start a new thread or clear earlier history before retrying

this never happen before with gpt-5.4 xhigh at all, i even have a very long session with gpt-5.4 i used over 5b tokens in the same session without any issues, but with gpt-5.5 xhigh i even didn't reach 20m/t and start getting this

■ Codex ran out of room in the model's context window. Start a new thread or clear earlier history before

Also

retrying.■ Error running remote compact task: { "error": { "message": "Your input exceeds the context window of this model. Please adjust your input and try again.", "type": "invalid_request_error", "param": "input", "code": "context_length_exceeded" } }

What steps can reproduce the bug?

Just working for a few hours and reached about 20m/t of usage and start getting this!

What is the expected behavior?

it should be fixed just like how we was using it with gpt-5.4 xhigh, not sure if this is a model limits or feature or a Codex CLI bug!

Additional information

_No response_