5-hour usage limit consumed unusually fast in Codex CLI

What version of Codex CLI is running?

codex-cli 0.155.1

What subscription do you have?

ChatGPT Plus

Which model were you using?

GPT-6 Astra (Low), then GPT-5.6 Sol (High)

What platform is your computer?

Linux 7.0.0-31-generic x86_64 x86_64

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

No response

Codex doctor report

What issue are you seeing?

Codex CLI is consuming my 5-hour usage allowance much faster than before. Today, a single request using GPT-6 Astra with Low reasoning consumed almost 50% of my 5-hour limit. I then switched to GPT-5.6 Sol with High reasoning, but after only two additional requests the remaining 5-hour allowance was exhausted. The entire limit was consumed within approximately 10 minutes. Previously, similar coding workflows, including running scripts and collecting data, allowed me to work for around 2 hours or longer before reaching the limit. This appears to be a significant recent regression in usage consumption.

What steps can reproduce the bug?

Uploaded thread: 019d1c26-a115-79f2-8508-58fde2d42a79

What is the expected behavior?

Usage should be comparable to previous Codex CLI behavior. Similar development sessions previously allowed approximately 2–3 hours or more of work before exhausting the 5-hour allowance. A single normal task should not consume almost half of the entire allowance unless there is an exceptional reason.

Additional information

No response

Start by reviewing the uploaded thread 019d1c26-a115-79f2-8508-58fde2d42a79 and the Codex CLI usage behavior for version 0.155.1. Compare the reported model, reasoning settings, request count, and roughly 10-minute session against prior behavior on Linux. Done means the unusually rapid allowance consumption is reproducible or explained with a clearly identified cause.