Failed ultrareview run (30-min remote timeout) consumed a free-tier quota slot [BUG]
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
I ran /ultrareview on a 5-file / ~875-line diff (branch
codex/legacy-deep-audit → main). The local CLI reported "Free ultrareview
1 of 3" and launched the cloud session. ~30 minutes later, the task
notification returned:
> Remote review failed: remote session exceeded 30 minutes
No findings, no partial output, no review document was produced. The free-run
counter still decremented — so a server-side timeout cost me one of three free
runs without delivering the service.
Session details
- Session URL: https://claude.ai/code/session_015WntuMErtjkGTCwmmZVcMm
- Task ID:
rluiy9now - Date: 2026-04-28
- Scope: 5 files, +875 / -17
- CLI: Claude Code (Opus 4.7, 1M context)
- Outcome:
status: failed,summary: remote session exceeded 30 minutes
Expected behavior
A failed run that produced no output should not count against the free-tier
quota. Either:
- The 30-min timeout should auto-refund the slot, or
- There should be a self-serve way to flag failed runs for credit.
Ask
Please refund the consumed slot (return me to 3/3 free runs) and consider
auto-refunding on failed task notifications going forward. Happy to re-run
the review on the same diff once the slot is restored.
What Should Happen?
A failed run that produced no output should not count against the free-tier
quota. Either:
- The 30-min timeout should auto-refund the slot, or
- There should be a self-serve way to flag failed runs for credit.
Error Messages/Logs
Steps to Reproduce
Run /ultrareview
Claude Model
None
Is this a regression?
Yes, this worked in a previous version
Last Working Version
_No response_
Claude Code Version
v2.1.121
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
Terminal.app (macOS)
Additional Information
Please refund the consumed slot (return me to 3/3 free runs) and consider
auto-refunding on failed task notifications going forward. Happy to re-run
the review on the same diff once the slot is restored.
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗