---
# Platform-health alert rules (docs/10, R-OBS-04). These complement the default node/kubernetes
# rules bundled by kube-prometheus-stack and add FIRST-CLASS alerts for the platform's own moving
# parts: nodes, Longhorn, Flux, cert-manager, networking/VPN, backups, identity, and the monitoring
# stack's own capacity ("don't let the monitor blind itself").
#
# Each rule maps to a docs/10 platform-health bullet and carries a severity (critical = page-worthy
# vs warning = degraded/capacity) plus enough annotation context (summary + runbook) to act.
#
# The `release: kube-prometheus-stack` label makes the operator's Prometheus select these rules
# (ruleSelector). Some expressions depend on exporters/ServiceMonitors owned by other workstreams
# (Flux, cert-manager, Longhorn, Velero, Keycloak, Cilium/Hubble ship their own metrics); the rules
# are authored to fire as soon as those series arrive. Metric names flagged TODO need confirming at
# bring-up against the deployed exporter.
#
# runbook_url points at a docs base; swap for the real runbook location when it exists.

# =====================================================================================
# Nodes
# =====================================================================================
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-nodes
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.nodes
      rules:
        - alert: NodeExporterDown
          expr: up{job="node-exporter"} == 0
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Node exporter down on {{ $labels.instance }}"
            description: "Prometheus cannot scrape node-exporter on {{ $labels.instance }} for 5m — the node may be down or unreachable."
            runbook_url: "https://home.keithjackson.dev/runbooks/node-down"
        - alert: NodeMemoryPressureHigh
          expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) > 0.90
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "Memory pressure high on {{ $labels.instance }}"
            description: "Available memory below 10% for 10m on {{ $labels.instance }} — the ~22 GiB box is under pressure."
            runbook_url: "https://home.keithjackson.dev/runbooks/node-memory"
        - alert: NodeDiskFillingUp
          expr: |
            (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay|squashfs"}
              / node_filesystem_size_bytes{fstype!~"tmpfs|overlay|squashfs"}) < 0.10
          for: 15m
          labels:
            severity: warning
          annotations:
            summary: "Disk filling up on {{ $labels.instance }} ({{ $labels.mountpoint }})"
            description: "Less than 10% free on {{ $labels.mountpoint }} of {{ $labels.instance }} for 15m."
            runbook_url: "https://home.keithjackson.dev/runbooks/node-disk"

# =====================================================================================
# Storage — Longhorn
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-longhorn
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.longhorn
      rules:
        # longhorn_volume_robustness: 0=unknown 1=healthy 2=degraded 3=faulted
        - alert: LonghornVolumeDegraded
          expr: longhorn_volume_robustness == 2
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "Longhorn volume degraded: {{ $labels.volume }}"
            description: "Volume {{ $labels.volume }} has been degraded (replica rebuild / missing replica) for 10m."
            runbook_url: "https://home.keithjackson.dev/runbooks/longhorn-degraded"
        - alert: LonghornVolumeFaulted
          expr: longhorn_volume_robustness == 3
          for: 1m
          labels:
            severity: critical
          annotations:
            summary: "Longhorn volume FAULTED: {{ $labels.volume }}"
            description: "Volume {{ $labels.volume }} is faulted — data at risk / offline. Immediate attention required."
            runbook_url: "https://home.keithjackson.dev/runbooks/longhorn-faulted"
        - alert: LonghornVolumeCapacityHigh
          expr: (longhorn_volume_actual_size_bytes / longhorn_volume_capacity_bytes) > 0.85
          for: 30m
          labels:
            severity: warning
          annotations:
            summary: "Longhorn volume near capacity: {{ $labels.volume }}"
            description: "Volume {{ $labels.volume }} is over 85% used for 30m."
            runbook_url: "https://home.keithjackson.dev/runbooks/longhorn-capacity"
        - alert: LonghornNodeStorageHigh
          expr: (longhorn_node_storage_usage_bytes / longhorn_node_storage_capacity_bytes) > 0.85
          for: 30m
          labels:
            severity: warning
          annotations:
            summary: "Longhorn node storage near capacity: {{ $labels.node }}"
            description: "Longhorn node {{ $labels.node }} is over 85% of its storage capacity for 30m."
            runbook_url: "https://home.keithjackson.dev/runbooks/longhorn-capacity"

# =====================================================================================
# GitOps — Flux
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-flux
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.flux
      rules:
        - alert: FluxReconciliationFailure
          expr: |
            max by (namespace, name, kind) (
              gotk_reconcile_condition{type="Ready", status="False"}
            ) == 1
          for: 15m
          labels:
            severity: warning
          annotations:
            summary: "Flux resource not ready: {{ $labels.kind }}/{{ $labels.name }}"
            description: "{{ $labels.kind }} {{ $labels.namespace }}/{{ $labels.name }} has failed to reconcile (Ready=False) for 15m — GitOps drift/failure (R-GITOPS-03)."
            runbook_url: "https://home.keithjackson.dev/runbooks/flux-reconcile"
        - alert: FluxResourceSuspended
          expr: |
            max by (namespace, name, kind) (gotk_suspend_status) == 1
          for: 1h
          labels:
            severity: warning
          annotations:
            summary: "Flux resource suspended: {{ $labels.kind }}/{{ $labels.name }}"
            description: "{{ $labels.kind }} {{ $labels.namespace }}/{{ $labels.name }} has been suspended for 1h — reconciliation/drift-correction is off."
            runbook_url: "https://home.keithjackson.dev/runbooks/flux-suspended"

# =====================================================================================
# Certificates — cert-manager
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-certificates
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.certificates
      rules:
        - alert: CertificateExpiringSoon
          expr: (certmanager_certificate_expiration_timestamp_seconds - time()) < (14 * 24 * 3600)
          for: 1h
          labels:
            severity: warning
          annotations:
            summary: "Certificate expiring soon: {{ $labels.name }}"
            description: "Certificate {{ $labels.namespace }}/{{ $labels.name }} expires in under 14 days."
            runbook_url: "https://home.keithjackson.dev/runbooks/cert-expiry"
        - alert: CertificateExpiryImminent
          expr: (certmanager_certificate_expiration_timestamp_seconds - time()) < (3 * 24 * 3600)
          for: 1h
          labels:
            severity: critical
          annotations:
            summary: "Certificate expiry imminent: {{ $labels.name }}"
            description: "Certificate {{ $labels.namespace }}/{{ $labels.name }} expires in under 3 days and has not renewed."
            runbook_url: "https://home.keithjackson.dev/runbooks/cert-expiry"
        - alert: CertificateNotReady
          expr: certmanager_certificate_ready_status{condition="False"} == 1
          for: 1h
          labels:
            severity: warning
          annotations:
            summary: "Certificate not ready / issuance failing: {{ $labels.name }}"
            description: "Certificate {{ $labels.namespace }}/{{ $labels.name }} has been in a not-ready state for 1h (ACME issuance failure?)."
            runbook_url: "https://home.keithjackson.dev/runbooks/cert-issuance"

# =====================================================================================
# Networking — VPN / egress-gateway / denied flows (Hubble)
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-networking
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.networking
      rules:
        # VPN tunnel health. The concrete metric depends on the egress-gateway VPN sidecar chosen by
        # WS-NET (docs/03). Written against a gluetun-style up gauge; confirm/adjust at bring-up.
        - alert: VPNTunnelDown
          # TODO(WS-NET): confirm metric name of the egress VPN exporter (docs/03).
          expr: max(gluetun_vpn_up) == 0 or absent(gluetun_vpn_up)
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Egress VPN tunnel down"
            description: "The egress-gateway VPN tunnel is down (or its metric is absent) for 5m — outbound traffic could leak or stall (R-SEC-03 leak risk)."
            runbook_url: "https://home.keithjackson.dev/runbooks/vpn-down"
        - alert: EgressGatewayUnhealthy
          expr: |
            max by (pod) (kube_pod_status_ready{namespace="egress", condition="true"}) == 0
          for: 10m
          labels:
            severity: critical
          annotations:
            summary: "Egress gateway unhealthy"
            description: "No ready egress-gateway pod for 10m — VPN-scoped egress is unavailable."
            runbook_url: "https://home.keithjackson.dev/runbooks/egress-gateway"
        - alert: HubbleDeniedFlowSpike
          # Cilium/Hubble denied (policy-drop) flows. Requires hubble metrics enabled (docs/03).
          expr: sum(rate(hubble_drop_total{reason="POLICY_DENIED"}[5m])) > 5
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "Spike in policy-denied network flows"
            description: "Policy-denied flow rate is elevated for 10m — a NetworkPolicy regression or an intrusion probe (R-SEC-03)."
            runbook_url: "https://home.keithjackson.dev/runbooks/denied-flows"

# =====================================================================================
# Backups — Velero
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-backups
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.backups
      rules:
        - alert: VeleroBackupFailure
          expr: increase(velero_backup_failure_total[1h]) > 0
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Velero backup failed: schedule {{ $labels.schedule }}"
            description: "One or more Velero backups failed in the last hour (R-STATE-03 — off-cluster DR at risk)."
            runbook_url: "https://home.keithjackson.dev/runbooks/backup-failure"
        - alert: VeleroBackupPartialFailure
          expr: increase(velero_backup_partial_failure_total[1h]) > 0
          for: 5m
          labels:
            severity: warning
          annotations:
            summary: "Velero backup partially failed"
            description: "A Velero backup completed with partial failures in the last hour — some resources/volumes were skipped."
            runbook_url: "https://home.keithjackson.dev/runbooks/backup-partial"
        - alert: VeleroNoRecentBackup
          expr: (time() - velero_backup_last_successful_timestamp{schedule!=""}) > (24 * 3600)
          for: 1h
          labels:
            severity: critical
          annotations:
            summary: "No successful Velero backup in 24h: {{ $labels.schedule }}"
            description: "Schedule {{ $labels.schedule }} has not produced a successful backup in over 24h (missed schedule)."
            runbook_url: "https://home.keithjackson.dev/runbooks/backup-missed"

# =====================================================================================
# Identity — Keycloak (SSO is a critical dependency — docs/15)
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-identity
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.identity
      rules:
        - alert: KeycloakDown
          expr: |
            max(kube_pod_status_ready{namespace="keycloak", condition="true"}) == 0
            or absent(kube_pod_status_ready{namespace="keycloak"})
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Keycloak IdP down"
            description: "No ready Keycloak pod for 5m — SSO is unavailable and dependent services cannot authenticate (docs/15)."
            runbook_url: "https://home.keithjackson.dev/runbooks/keycloak-down"
        - alert: KeycloakDatabaseDown
          # Keycloak's PostgreSQL (Longhorn-backed, DR-critical). Metric from postgres-exporter or
          # the bundled chart; confirm label set at bring-up.
          expr: |
            max(kube_pod_status_ready{namespace="keycloak", pod=~".*postgres.*", condition="true"}) == 0
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Keycloak database unavailable"
            description: "Keycloak's PostgreSQL is not ready for 5m — the IdP will fail (docs/15)."
            runbook_url: "https://home.keithjackson.dev/runbooks/keycloak-db"

# =====================================================================================
# The monitor's own capacity — don't let the monitor blind itself (docs/10)
# =====================================================================================
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: platform-health-monitoring-self
  namespace: monitoring
  labels:
    release: kube-prometheus-stack
    platform-health: "true"
spec:
  groups:
    - name: platform-health.monitoring-self
      rules:
        - alert: MonitoringVolumeFillingUp
          expr: |
            (kubelet_volume_stats_available_bytes{namespace="monitoring"}
              / kubelet_volume_stats_capacity_bytes{namespace="monitoring"}) < 0.15
          for: 15m
          labels:
            severity: warning
          annotations:
            summary: "Monitoring PVC filling up: {{ $labels.persistentvolumeclaim }}"
            description: "PVC {{ $labels.persistentvolumeclaim }} (Prometheus/Loki) is under 15% free — retention/PVC size may need raising before the monitor goes blind."
            runbook_url: "https://home.keithjackson.dev/runbooks/monitoring-capacity"
        - alert: PrometheusTargetsMissing
          expr: |
            (count(up == 0) / count(up)) > 0.10
          for: 15m
          labels:
            severity: warning
          annotations:
            summary: "More than 10% of Prometheus targets are down"
            description: "Over 10% of scrape targets have been down for 15m — a broad monitoring blind spot."
            runbook_url: "https://home.keithjackson.dev/runbooks/targets-down"