Problem
当发现某个agent偏离了预期开始瞎搞时，请让我可以人工杀掉它其实很大概率我起了另一个agent在做相同的任务了），我希望
Solution
How should it work?
Use Case
When would you use this?
Priority
-
High - Blocking issue -
Medium - Important improvement -
Low - Nice to have
Additional Info
(Optional: screenshots, examples, links)