Sleeping/looping background agents incorrectly shown in 'Ready for Review'
Resolved 💬 3 comments Opened May 12, 2026 by KathrynN Closed May 14, 2026
Bug (in Agent View)
Background agents that are sleeping (e.g. waiting 10 minutes via ScheduleWakeup) or running a /loop cycle sometimes appear in the "Ready for Review" section of the UI instead of remaining in their own "Running" or "Sleeping" section.
Expected behaviour
Agents in a sleep/loop state should stay in whatever section represents active-but-waiting background jobs. They haven't produced a final result and aren't awaiting user review.
Actual behaviour
These agents intermittently show up under "Ready for Review", which implies they've completed and need attention. Clicking into them shows they're still mid-loop or sleeping.
Steps to reproduce
- open claude with
claude agents - Start a background agent with a
/loopor a longScheduleWakeupdelay (~10 minutes) - Check the job list while the agent is sleeping
- Observe the agent listed under "Ready for Review" instead of an active/sleeping section
Environment
- Claude Code CLI (macOS)
- Opus model
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗