openai / openai/codex

Astra, Sol, Luna - Doesn't matter - usage limits are being burned through

Open
#45,067 3 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI rate-limits
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of Codex CLI is running?

codex-cli 0.154.0

What subscription do you have?

Plus

Which model were you using?

Sol and Astra - Med/Low - With subagents luna and terra

What platform is your computer?

MacOS M1 ARM64

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

WarpPreview v0.2026.09.02.08.27.preview_01

Codex doctor report
lots of PII so not comfortable pasting here
What issue are you seeing?

Insane level of token usage. Enough to make me turn off all codex reviews and go hunting on what might be eating up usage.
There's a big difference to before astra and after astra release

What steps can reproduce the bug?

Uploaded thread: 01a09629-3217-7ad0-8753-ad4fe6c96b40

What is the expected behavior?

About 2-3 hours of casual coding per 5h reset.

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 with the uploaded thread 01a09629-3217-7ad0-8753-ad4fe6c96b40 and compare token usage before and after the Astra release. Done means identifying what is consuming the usage and explaining or correcting the difference from the expected 2–3 hours of casual coding per five-hour reset.

Written by the indexing model from the issue text.

Assessment

Tech stack
macos
Domain
cli
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.