Prerequisites

• I am running the latest code. Mention the version if possible as well.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new and useful enhancement to share.

Feature Description

In router mode (--models-dir / --models-preset), when a child server process hangs or becomes unresponsive, the parent router has no mechanism to detect or recover from this state. The monitoring thread blocks indefinitely on subprocess_join() with no timeout.

Motivation

Production
One bad child shouldn't take down entire router

Possible Implementation

Proposed Solution (Docker-style watchdog)
Implement a configurable timeout mechanism similar to docker stop