openai / openai/codex

Astra reasoning level frequently reset to Medium

Open
#44,668 3 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

app bug config
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of the Codex App are you using (From “About Codex” dialog)?

Version 26.903.71938

What subscription do you have?

x20

What platform is your computer?

Mac

What issue are you seeing?

In about 5% of my turns, the reasoning level is reset to Medium from X-High.

What steps can reproduce the bug?

Not sure why this happens.

What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the issue in Codex App version 26.903.71938 on Mac, using X-High reasoning and observing whether it resets to Medium during turns. The cause and reproduction steps are not identified in the report; done means the reasoning level remains X-High across affected turns and the behavior is covered by a regression check.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos
Domain
desktop
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.