The front already tracks which models are in-flight (engine.active); model-loaded-
status now returns a front-native `running` list. The models page shows a pulsing
green dot inside each model's engine/GPU tag while that model is serving a request,
toggled in place via a 2s poll of the fast front endpoint (no list re-render, so it
never re-hits the slow cache scan). Dot styling lives in base.html.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011DDv7BchtZQWsnPG6Jm49m