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

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" />