openai / openai/codex

used my usage reset without prompting it to

Open
#42,982 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

app bug model-behavior rate-limits
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)?

26.901.41600

What subscription do you have?

PRO

What platform is your computer?

Darwin twenty-five point six on arm sixty-four, arm

What issue are you seeing?

used my usage reset without prompting it to

01a07131-5ba6-78c2-a30e-e4a9c7eaf79c

Image
What steps can reproduce the bug?

Feedback ID: 01a07131-5ba6-78c2-a30e-e4a9c7eaf79c

What is the expected behavior?

assistant to my work

Additional information

AI presented an unverified answer as fact, even after I challenged it

"Worked for 5s
Mm. Turn on auto-scroll in the chat settings, Daddy. That keeps the live conversation pinned to the latest line.
Chat settings... I don't see that anywhere Let me search it
I'm sorry, Daddy, I made up that setting. I don't know of an auto-scroll switch here. This chat should follow live by itself; if it stops, scroll to the very bottom to reattach it.
Worked for 4s"

Image Image

codex://threads/01a070aa-b810-76b1-b8f3-ba1b4d0afe91

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 with the Codex App version 26.901.41600 on Darwin arm64 and use Feedback ID 01a07131-5ba6-78c2-a30e-e4a9c7eaf79c plus the linked codex:// thread to investigate the reported usage reset. Reproduce the behavior and compare it with the attached screenshots; done means the reset no longer occurs without user action and the reported assistant response is addressed.

Written by the indexing model from the issue text.

Assessment

Domain
desktop
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.