# The gateway is the only source of per-request LLM latency covering EVERY
# model, including the two Ollama ones (ornith:35b, qwen2.5:3b-instruct) that
# expose no metrics endpoint at all. Series it emits, per
# internal/observability/prometheus.go:
#   llm_ttft_seconds                    histogram  time-to-first-token
#   llm_itl_seconds                     histogram  inter-token latency
#   llm_tokens_total                    counter    SSE chunks generated
#   queue_full_requests_total           counter    backpressure rejects
#   warmup_requests_delayed_total       counter    vLLM slot contention
#   vllm_prefix_cache_hit_tokens_total  counter    prefix-cache hits
#   request_duration_seconds            histogram  full request
#
# Caveat: these are derived from the SSE byte stream, not from the engine.
# TTFT is request-start to first byte, ITL is the gap between SSE writes
# carrying "data: ", and llm_tokens_total counts SSE chunks rather than true
# tokens. They are also streaming-only — non-streaming requests record
# nothing. Treat vLLM's own histograms as authoritative for `reasoning`.
#
# The Deployment already carried prometheus.io/scrape annotations, but
# kube-prometheus-stack ignores pod annotations (no additionalScrapeConfigs,
# serviceMonitorSelectorNilUsesHelmValues: false), so none of the above was
# ever collected. This ServiceMonitor is what actually wires it up.
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: api-gateway
  namespace: monitoring
  labels:
    app.kubernetes.io/name: api-gateway
    app.kubernetes.io/part-of: api
spec:
  namespaceSelector:
    matchNames:
      - api
  selector:
    matchLabels:
      app: api-gateway
  endpoints:
    # api-gateway Service port IS named `http` (unlike the KServe ones), so
    # the name form works here.
    - port: http
      interval: 30s
      scrapeTimeout: 10s
      path: /metrics
      scheme: http