Files
homelab/k8s
Story Crater Bot b695cee987 fix(api): label Kong pods llm-client=true so llm-serving NetworkPolicy admits them — chat/embeddings/rerank/score routes silently hung until the client timeout because Cilium dropped Kong's packets
llm-serving-default-deny admits port 8080 only from pods carrying
llm-client=true. Kong lacked it, so every route that actually contacts an
upstream timed out. /v1/models masked the problem: request-termination answers
inside Kong and never touches an upstream, so it returned 200 throughout.

Opting in via podLabels rather than relaxing the policy — it is a compensating
control, not hygiene, since vLLM v0.11.0 is frozen on Volta and will not receive
patches for several remote/unauthenticated advisories.

podLabels land only in the pod template, not spec.selector.matchLabels, so this
is not an immutable-field change.
2026-08-13 07:55:21 -07:00
..