feat: dashboard UX optimization + real-time backend stats + health probe fix + pool shuffle

- dashboard.html: major UX overhaul (+657/-308 lines)
- server.py: /api/admin/backends now returns real-time RPM and model_count
- pool_manager.py: random.shuffle backends for load distribution
- config.py: health probe endpoint /v1/models → /models
- docker-compose.yml: add SIDECAR_PRIMARY_WAIT_MAX_RETRIES=6

BIZ-52 post-review optimizations

docker-compose.yml

@@ -15,6 +15,7 @@ services:
       - SIDECAR_METRICS_PORT=9191
       - SIDECAR_DB_PATH=/app/data/sidecar_v2.db
       - SIDECAR_BACKUP_DIR=/app/data/backups
+      - SIDECAR_PRIMARY_WAIT_MAX_RETRIES=6
     volumes:
       - sidecar-data:/app/data