codex - 💡(How to fix) Fix GPT-5.5 Fast task took >1 hour and consumed unusually high usage for ~2k LOC change

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…

Root Cause

The usage consumption also appeared abnormal. This single task consumed about 23% of my 5-hour limit, and my weekly limit dropped by roughly 5–6%. In my experience, a task that modifies around two thousand lines normally should not consume this much quota. Because my weekly limit was already low, this task effectively exhausted it and then started consuming my paid Credits.

RAW_BUFFERClick to expand / collapse

I’m reporting a Codex performance / usage-metering issue.

Feedback ID: 019e6a3f-1eab-74e0-bdcb-e60ca575395b

Environment

  • Codex app version: 26.519.81530 (3178)
  • Model / mode: gpt-5.5 fast
  • Device: MacBook Pro, 16-inch, M5 Max, 128 GB memory
  • macOS: Tahoe 26.5
  • Plan: 20x Pro plan

What happened I asked Codex to complete a relatively small code-modification task that changed around ~2,000 lines of code. With gpt-5.5 fast enabled, the task took more than one hour to finish.

The usage consumption also appeared abnormal. This single task consumed about 23% of my 5-hour limit, and my weekly limit dropped by roughly 5–6%. In my experience, a task that modifies around two thousand lines normally should not consume this much quota. Because my weekly limit was already low, this task effectively exhausted it and then started consuming my paid Credits.

Expected behavior For a ~2k LOC modification task, gpt-5.5 fast should complete much faster than one hour and should not consume such a large percentage of both the 5-hour limit and the weekly limit.

Request Could the team investigate whether there is a performance regression or usage-metering issue affecting gpt-5.5 fast in Codex? If the quota / Credit consumption was abnormal, please also consider restoring or compensating the affected usage.

<img width="482" height="108" alt="Image" src="https://github.com/user-attachments/assets/0ce3fd33-6873-4e63-af1a-51f5f60d5f94" /> <img width="568" height="208" alt="Image" src="https://github.com/user-attachments/assets/9dabe515-dded-4942-971d-bb679aed52a3" />

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 GPT-5.5 Fast task took >1 hour and consumed unusually high usage for ~2k LOC change