You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Background subagent can remain running indefinitely after tool activity stops #4850
A background review subagent remained marked as running long after observable activity stopped. The status stayed at 100 completed tool calls and zero completed turns while elapsed time continued increasing past 15 minutes. The parent session received no result and could not complete the workflow.
Affected version
1.0.83
Steps to reproduce the behavior
Start a background general-purpose subagent for a final branch review.
Allow it to perform tool calls.
Observe the agent reach approximately 100 completed tool calls.
Continue checking its status after several minutes.
The agent remains running, with the tool-call count unchanged and no completed turn or result.
Expected behavior
The runtime should detect stalled subagents, surface the blocked tool or execution state, and either recover, fail with an actionable error, or enforce a bounded timeout. The parent should not wait indefinitely with no progress signal.
Additional context
Linux
Copilot CLI 1.0.83
Observed elapsed time: over 15 minutes
Status remained: running, 100 tool calls completed, 0 turns completed
Implementation and the full 78-test regression suite had already completed; the stalled operation was only a final read-only review.
No private repository content or session logs are attached.
Accuracy update: the agent ultimately returned after approximately 995 seconds (16.6 minutes). The issue is therefore a prolonged apparent stall with no changing progress indicators—not proven infinite execution. During the stall it remained marked running at 100 completed tool calls and 0 completed turns.
To get these things fixed, nobody is going to replicate in github team, use AI to prove it with an example cmnds and tell AI to add the description here with replication steps. The github team will then give these steps to AI and it will only then be fixed.
Writing words are not being fixed at all, no one has time to replicate.
Activity
tjgreen42 commentedon Sep 15, 2026
Accuracy update: the agent ultimately returned after approximately 995 seconds (16.6 minutes). The issue is therefore a prolonged apparent stall with no changing progress indicators—not proven infinite execution. During the stall it remained marked running at 100 completed tool calls and 0 completed turns.
npechett-wtg commentedon Sep 15, 2026
To get these things fixed, nobody is going to replicate in github team, use AI to prove it with an example cmnds and tell AI to add the description here with replication steps. The github team will then give these steps to AI and it will only then be fixed.
Writing words are not being fixed at all, no one has time to replicate.