feat(api): add Kong RED metrics for LLM routes

Cluster-wide prometheus KongClusterPlugin (kong-metrics.yaml) +
chart-native ServiceMonitor (kong-values.yaml) expose
kong_http_requests_total/kong_latency_bucket/kong_bandwidth_bytes for
every route, LLM and otherwise. Dashboard filters to route=~"llm-.*"
for request rate, error rate, p95 upstream latency, and bandwidth.
Token-count metrics still need ai-proxy-advanced (Enterprise-only);
not attempted.

k8s/apps/api/kustomization.yaml

@@ -6,6 +6,7 @@ kind: Kustomization
 # or it is silently dropped with no error and no drift shown.
 resources:
   - ingress.yaml
+  - kong-metrics.yaml
   - llm-routes.yaml
   - model-auth.yaml
 # No top-level `namespace:` transformer on purpose: ingress.yaml sets its own