codex - 💡(How to fix) Fix Limits are vanishing very fast [2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openai/codex#19376Fetched 2026-04-25 06:10:24
View on GitHub
Comments
2
Participants
2
Timeline
8
Reactions
0
Timeline (top)
labeled ×3commented ×2closed ×1mentioned ×1
RAW_BUFFERClick to expand / collapse

What version of Codex CLI is running?

0.124.0

What subscription do you have?

Enterprise Account

Which model were you using?

gpt-5.4, gpt-5.4-codex

What platform is your computer?

Darwin 25.3.0 arm64 arm

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

iTerm2

What issue are you seeing?

I had a session and during exit here is what i saw:

Before Chat:

5h: 89, Weekly: 80

Chat

Token usage: total=74,846 input=65,209 (+ 2,364,288 cached) output=9,637 (reasoning 2,196)

After that

5h: 81, Weekly: 79

It was a single prompt.

Issue started happening today, i noticed weekly time window also shifted, usualy it was from Monday to Monday, not it says it resets on 30th April.

What steps can reproduce the bug?

Using current cli to test gpt-5.4 for token consumption

What is the expected behavior?

Usage should last a lot more.

Additional information

No response

extent analysis

TL;DR

The issue might be related to incorrect token consumption tracking or a shift in the weekly time window, potentially causing unexpected usage resets.

Guidance

  • Verify the token consumption tracking by checking the Codex CLI documentation for any updates or changes to how tokens are counted, especially for the gpt-5.4 model.
  • Check the Enterprise Account settings to see if there have been any changes to the subscription plan or billing cycle that could affect the weekly time window.
  • Test the token consumption with a different model, like gpt-5.4-codex, to see if the issue is model-specific.
  • Review the Codex CLI version 0.124.0 release notes for any known issues related to token tracking or time windows.

Notes

The issue seems to be related to the Codex CLI and its interaction with the gpt-5.4 model, but without more information about the specific prompts or usage patterns, it's difficult to provide a more targeted solution.

Recommendation

Apply workaround: Monitor token usage closely and adjust prompts or usage patterns to minimize the impact of potential incorrect tracking, until the root cause can be identified and fixed.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

codex - 💡(How to fix) Fix Limits are vanishing very fast [2 comments, 2 participants]