# Stable client-facing name for the chat model, deliberately decoupled from the
# process that currently serves it.
#
# poimen-memory addresses this Service, not a pod and not an InferenceService. That
# means the vLLM -> candle-vllm handoff changes only this file's selector. The client
# config never changes again, so the ingest cutover has no window in which the host
# name is wrong.
#
# Two ports on purpose:
#   - 80    matches every other predictor Service in this namespace, and matches
#           poimen-memory's LLM_CHAT_BASE, which carries no port number.
#   - 8080  is the container port. It is also the only port llm-serving-ingress and
#           poimen-memory-llm-egress permit, and the port the handoff readiness check
#           uses. Publishing it directly avoids a port translation that is easy to get
#           wrong in a curl.
#
# The selector names the vLLM reasoning pod today. To hand off, replace the three
# selector labels with candle-vllm's pod labels and nothing else. Do not delete and
# recreate this Service: a delete drops the ClusterIP, and a client that cached the
# name during the gap will fail until it re-resolves.
apiVersion: v1
kind: Service
metadata:
  name: reasoning-long-predictor
  namespace: llm-serving
  labels:
    app.kubernetes.io/part-of: llm-serving
    app: reasoning-long-predictor
spec:
  type: ClusterIP
  selector:
    app.kubernetes.io/name: llm-reasoning
    component: predictor
    serving.kserve.io/inferenceservice: reasoning
  ports:
    - name: http
      protocol: TCP
      port: 80
      targetPort: 8080
    - name: http-8080
      protocol: TCP
      port: 8080
      targetPort: 8080