codex - 💡(How to fix) Fix Sending feedback from the CLI used up 6% of my 5hr limit [2 comments, 3 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#19989Fetched 2026-04-29 06:24:05
View on GitHub
Comments
2
Participants
3
Timeline
6
Reactions
0
Author
Timeline (top)
labeled ×3commented ×2unlabeled ×1
RAW_BUFFERClick to expand / collapse

What version of Codex CLI is running?

OpenAI Codex (v0.125.0)

What subscription do you have?

plus

Which model were you using?

gpt-5.5 low

What platform is your computer?

Darwin 25.4.0 arm64 arm

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

ghostty

What issue are you seeing?

Sent a feedback from the CLI the first thing in the morning, was at 100%, and after that, it was 96%.

What steps can reproduce the bug?

Uploaded thread: 019dd440-75b9-73b2-80c8-4ae0367d7dc7

What is the expected behavior?

shouldn't use the llm usage.

Additional information

subsequent feedback did not use another 6%.

extent analysis

TL;DR

The issue might be related to incorrect usage tracking after sending feedback from the CLI, and verifying the usage tracking mechanism could help identify the cause.

Guidance

  • Review the usage tracking logic to ensure it correctly accounts for feedback submissions.
  • Check if the gpt-5.5 low model has specific usage tracking rules that might be causing the discrepancy.
  • Verify if the issue persists after multiple feedback submissions to see if the usage percentage continues to decrease.
  • Investigate the uploaded thread 019dd440-75b9-73b2-80c8-4ae0367d7dc7 for more information on the feedback submission process.

Notes

The issue seems to be specific to the gpt-5.5 low model and the Codex CLI, so any solution or workaround might need to be tailored to this specific configuration.

Recommendation

Apply workaround: Monitor usage tracking after feedback submissions to identify any patterns or inconsistencies, as the root cause is not immediately clear.

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