diff --git a/k8s/apps/api/kong-values.yaml b/k8s/apps/api/kong-values.yaml index 117285e..ac69f34 100644 --- a/k8s/apps/api/kong-values.yaml +++ b/k8s/apps/api/kong-values.yaml @@ -29,6 +29,18 @@ fullnameOverride: kong # stateless in DB-less mode, so replicas are pure redundancy. replicaCount: 2 +# Opt in to the `llm-serving-default-deny` NetworkPolicy, which admits port 8080 +# only from pods carrying this label. That policy is a compensating control, not +# hygiene: vLLM v0.11.0 is frozen on Volta and will never receive patches for +# several remote/unauthenticated advisories, so it must not be broadly reachable. +# +# Without this label Cilium DROPS the packets rather than refusing them, so the +# symptom is a request that hangs until the client's timeout — not a connection +# error. /v1/models still worked while this was missing, because +# request-termination answers inside Kong and never touches an upstream. +podLabels: + llm-client: "true" + env: # DB-less. Config comes from Kubernetes objects via the ingress controller, so # git stays the source of truth. A Postgres-backed Kong would put live routing