# Prometheus for the llmgw cluster.
#
# One scrape target for the whole fleet. Agents publish nothing of their own —
# the control plane gathers what they report and republishes it, so node health,
# disk and endpoint state all arrive here from 10.0.0.140.
global:
  scrape_interval: 15s
  evaluation_interval: 15s
  external_labels:
    cluster: mynodes

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['localhost:9093']

rule_files:
  - /etc/prometheus/rules/llmgw.yml

scrape_configs:
  # The control plane's dedicated metrics port. Not its admin listener: that one
  # is loopback because it also serves pprof, and pprof can dump the heap where
  # API keys sit in plaintext.
  - job_name: llmgw
    static_configs:
      - targets: ['10.0.0.140:9091']
        labels:
          instance: control-plane

  - job_name: prometheus
    static_configs:
      - targets: ['localhost:9090']