Repository navigation
Codex Pro quota draining abnormally since 2026-06-25; local logs show needs_follow_up token loops #30086
Description
What issue are you seeing?
Starting around 2026-06-25, my ChatGPT Pro account started showing abnormally fast Codex quota consumption. This appears similar to #29963, #30002, and #30054: quota drains much faster than the local token evidence suggests, and local logs show repeated model_needs_follow_up=true samples inside single turns.
I submitted in-product feedback with logs attached.
Uploaded thread: 019effb1-407c-7383-8b89-0fdbc95e418e
What version of the Codex App are you using?
- Codex app:
26.616.81150(CFBundleVersion4306) - Codex CLI:
0.142.0 - Platform: macOS arm64
- Auth mode: ChatGPT login
- Subscription: ChatGPT Pro
- Main model/config: mostly
gpt-5.5, reasoninghigh/xhigh, default service tier
What steps can reproduce the bug?
- Use Codex desktop / CLI with a Pro account.
- Run normal Codex work after 2026-06-25.
- Watch the 5h / weekly quota move much faster than expected.
- Inspect local diagnostics. I used sanitized aggregates from
~/.codex/logs_2.sqliteand session JSONL files, without prompt content or account identifiers.
Sanitized local evidence
From codex_core::session::turn logs, grouping only post-sampling token usage rows:
| Local date | Turns | Sampling rows | model_needs_follow_up=true rows |
Turns with >=5 true samples | Max single-turn token delta | Max samples in one turn |
|---|---|---|---|---|---|---|
| 2026-06-23 | 95 | 171 | 77 | 6 | 60,747 | 14 |
| 2026-06-24 | 178 | 431 | 253 | 29 | 234,317 | 16 |
| 2026-06-25 | 126 | 302 | 177 | 20 | 100,615 | 15 |
Worst redacted single-turn examples:
| Redacted turn | Local date/time | Model | Effort | Duration | Samples | True samples | total_usage_tokens delta |
token_limit_reached |
|---|---|---|---|---|---|---|---|---|
| Turn A | 2026-06-24 03:04:50-03:07:31 | gpt-5.5 |
xhigh |
161s | 4 | 3 | 234,317 | true |
| Turn B | 2026-06-24 00:26:20-00:31:14 | gpt-5.5 |
high |
294s | 13 | 12 | 229,144 | true |
| Turn C | 2026-06-25 11:31:39-11:33:55 | gpt-5.4 |
medium |
136s | 15 | 14 | 100,615 | false |
| Turn D | 2026-06-25 02:59:49-03:01:13 | gpt-5.5 |
xhigh |
84s | 7 | 6 | 69,933 | false |
Session-level local summary also shows the quota meter already high on a small fresh session:
| Local date/time | Session total tokens | 5h quota shown in rate limits | Weekly quota shown in rate limits |
|---|---|---|---|
| 2026-06-26 00:35-00:48 | 359,784 | 38% -> 40% used | 24% used |
| 2026-06-26 00:37-00:37 | 44,848 | 38% used | 24% used |
| 2026-06-26 00:41-00:43 | 333,968 | 39% used | 24% used |
The CLI status line also showed weekly 76% left immediately after opening a fresh temporary TUI for feedback.
Expected behavior
- Pro quota consumption should remain proportional to actual usage.
- A single turn should not repeatedly sample with
model_needs_follow_up=trueand accumulate large token deltas unless it is genuinely doing that much work. - 5h / weekly quota should not drain at the effective rates reported by users in Codex quota consumption has a serious bug #29963, Server-side quota accounting over-reports consumption after 5h reset: Pro 5h limit burned in ~41 min / ~1.35M tokens #30002, and Codex budget draining drastically since 2026-06-25: needs_follow_up loop + rate_limits.used_percent no longer reported #30054.
- If this is a quota accounting or reset bug, incorrectly consumed paid quota should be restored.
Additional notes
I did not include account IDs, email addresses, local user paths, prompt text, auth tokens, or raw session logs in this public issue. The attached in-product feedback upload should give maintainers the diagnostic context via the uploaded thread ID above.
Activity
github-actions commentedon Jun 25, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
reabiliti commentedon Jun 25, 2026
I can reproduce a very similar local signature on another ChatGPT Pro account / Codex desktop setup.
Local diagnostics from
~/.codex/logs_2.sqlite, using onlycodex_core::session::turnrows withpost sampling token usageand no prompt/account/path content:model_needs_follow_up=truerowsWorst loop-like turns, redacted:
total_usage_tokensdeltatotal_usage_tokenstoken_limit_reachedgpt-5.5highgpt-5.5highgpt-5.5highgpt-5.5highgpt-5.5highThis looks consistent with the same pattern described here: many repeated sampling rows inside a single turn, most of them with
model_needs_follow_up=true, and large accumulatedtotal_usage_tokensdeltas.I also observed unusually fast Pro weekly quota movement around the same date. There may be some local context size contribution, but the repeated follow-up sampling signature appears to be a separate multiplier.
aatiya-knowhow commentedon Jun 25, 2026
I am seeing similar behavior. Goal mode explodes in token usage as a result; jobs that normally consume ~200k-400k tokens now consume upwards of 2.5M+ tokens. On a $200/mo pro plan my 5 hr limit was exhausted with a single session running in goal mode across two agent threads in about 2 hours. Weekly limit seems to be affected by this as well - I burnt about 30% of my weekly limit since this morning.
eraserkason commentedon Jul 5, 2026
问题解决了吗？我现在还没解决，并且 在 auth没有泄露的情况下，我的额度会一直无缘无故的被消耗