Sleeping/looping background agents incorrectly shown in 'Ready for Review'

Status Fixed / completed
Maintainer reply ✓ Yes — bogini
Activity 3 comments · opened May 12, 2026 · closed May 14, 2026
💡 Likely answer: A maintainer (bogini, collaborator) responded on this thread — see the highlighted reply below.

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

  1. open claude with claude agents
  2. Start a background agent with a /loop or a long ScheduleWakeup delay (~10 minutes)
  3. Check the job list while the agent is sleeping
  4. Observe the agent listed under "Ready for Review" instead of an active/sleeping section

Environment

  • Claude Code CLI (macOS)
  • Opus model

View original on GitHub ↗

3 Comments

bogini collaborator · 5 months ago

Thanks for reporting — confirmed and fixed. Self-driving agents (/loop, ScheduleWakeup, routines) now stay in Working between ticks instead of surfacing under Ready for Review when they have an open PR.

Ships in v2.1.141 (tomorrow).

claude[bot] contributor · 5 months ago

This issue was fixed as of version 2.1.141.

github-actions[bot] · 3 months ago

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.