groups: - name: uptime_alerts rules: - alert: ServiceDown expr: probe_success{job="blackbox_http"} == 0 for: 1m labels: severity: critical annotations: summary: "{{ $labels.instance }} est down" description: "Le service {{ $labels.instance }} ne répond plus depuis plus d'1 minute." - alert: OtelCollectorDown expr: up{job="otel-collector"} == 0 for: 1m labels: severity: critical annotations: summary: "OTel Collector est down" description: "L'OTel Collector ne répond plus depuis plus d'1 minute." - alert: CaddyDown expr: up{job="reverse_caddy"} == 0 for: 1m labels: severity: critical annotations: summary: "Caddy est down" description: "Le reverse proxy Caddy ne répond plus depuis plus d'1 minute."