[BUG] [BUG] /ultrareview returns "failed" on tracking page despite "completed" status in CLI
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?
/ultrareview launched successfully, CLI showed completed status with empty findings [], but the tracking URL showed the review as failed. No review results were produced.
What Should Happen?
Review should complete successfully and return
findings (or explicitly return "no issues found").
If it fails, CLI status should reflect failed — not
completed.
Error Messages/Logs
No error message shown in CLI. Tracking URL
confirmed failure. Session ID:
session_01VvMgMUuGk95NUdN3UcZj4R
Steps to Reproduce
- Run /ultrareview in a git repo with local
uncommitted changes
- CLI output shows: Free ultrareview 1 of 3.
Ultrareview launched... Track: https://claude.ai/cod
e/session_01VvMgMUuGk95NUdN3UcZj4R
- Task notification arrives with status: completed
and findings []
- Visit tracking URL — status shows failed
Claude Model
Sonnet (default)
Is this a regression?
I don't know
Last Working Version
_No response_
Claude Code Version
2.1.123 (Claude Code)
Platform
Anthropic API
Operating System
Windows
Terminal/Shell
WSL (Windows Subsystem for Linux)
Additional Information
Additional Information:
Scope reported at launch: 3 files changed, 10517
insertions(+), 10517 deletions(-). This was a free
use (1 of 3). Requesting credit be restored since
the review failed to complete.
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗