human-in-the-loop state suspension

applicationwrite

SuspendedAction -> ExecutionPermission

Halt thread execution of an active agent action until an external operator approves or rejects the action via API.

Problem it solves

High-risk tool execution cannot be fully trusted to run autonomously without real-time human oversight.

Consumes

SuspendedAction

Emits

ExecutionPermission

Distilled from 1 source

The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.