# Interruption of running agents due to high server load

**URL:** <https://forum.cursor.com/t/interruption-of-running-agents-due-to-high-server-load/168495>\
**Category:** Feedback\
**Tags:** subagents\
**Created:** [August 15, 2026, 5:19pm UTC](https://forum.cursor.com/t/interruption-of-running-agents-due-to-high-server-load/168495 "2026-08-15T17:19:49Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Artemonim](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/artemonim/32/56113_2.png) [@Artemonim](https://forum.cursor.com/u/Artemonim)\
**Post date:** [August 15, 2026, 5:19pm UTC](https://forum.cursor.com/t/interruption-of-running-agents-due-to-high-server-load/168495/1 "2026-08-15T17:19:49Z")

</div>

In my comment on the bug report, I explained that the system terminated the Subagent with an error indicating a model overload on the Cursor servers.

> [@The chat with the subagent won't load until the subagent is finished](https://forum.cursor.com/t/the-chat-with-the-subagent-wont-load-until-the-subagent-is-finished/166872/13):
>
> Subagent was interrupted due to the error “We are experiencing high load on the Grok 4.6 model; please try another one or Auto,” and after this interruption, it remained in a state where it could not be opened. If the main Agent hadn’t been instructed by me to git stage between Subagent calls, this could have ruined several hours of coordinated agent work and I wouldn’t have been able to find out exactly what work the subagent had managed to complete and where he had lef…

I find it strange that, in my case, the Subagent which had been running for more than 20 minutes was terminated, rather than another user attempting to make a new request.

I believe that when the load is too high, it’s better to prevent new users from submitting requests rather than interrupting sessions that are already in progress.