# SLO: Availability
# Target: 99.9% uptime (43 minutes/month downtime budget)

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: memory-availability
  namespace: monitoring
spec:
  groups:
    - name: availability
      interval: 1m
      rules:
        # Error rate SLI
        - record: memory:availability:error_ratio
          expr: |
            sum(rate(http_requests_total{service="memory",status=~"5.."}[5m]))
            /
            sum(rate(http_requests_total{service="memory"}[5m]))

        # Availability alert (< 99.9%)
        - alert: MemoryAvailabilityLow
          expr: |
            (1 - memory:availability:error_ratio) < 0.999
          for: 5m
          labels:
            severity: critical
            slo: availability
          annotations:
            summary: "Memory API availability below 99.9%"
            description: "Current availability: {{ $value | humanizePercentage }}"

        # Recording rule for SLO dashboard
        - record: memory:availability:slo
          expr: |
            (1 - memory:availability:error_ratio)