Files
api-company/flux/monitoring/helmrelease.yaml
T
AI-Agent 9bc28c2b46
Validate Flux manifests / kustomize-build (pull_request) Failing after 17s
feat: enable Alertmanager with Slack receiver in kube-prometheus-stack HelmRelease
- Set alertmanager.enabled: true (was false)
- Add Slack receiver config pointing to gatus-slack-webhook secret URL
- Add alertmanagerSpec.secrets to mount gatus-slack-webhook into Alertmanager pod
- Route: group by alertname+namespace, 30s wait, 5m interval, 4h repeat
- Channel: #api-alerts with summary title and description text

Closes leeworks-agents/api-company#210
2026-06-05 10:02:29 +00:00

111 lines
3.4 KiB
YAML

apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
name: kube-prometheus-stack
namespace: monitoring
spec:
interval: 15m
chart:
spec:
chart: kube-prometheus-stack
version: ">=58.0.0 <60.0.0"
sourceRef:
kind: HelmRepository
name: prometheus-community
namespace: flux-system
interval: 60m
install:
crds: CreateReplace
remediation:
retries: 3
upgrade:
crds: CreateReplace
remediation:
retries: 3
values:
grafana:
enabled: true
adminPassword: "${GRAFANA_ADMIN_PASSWORD}" # inject via Secret/substitution
ingress:
enabled: true
ingressClassName: nginx
annotations:
cert-manager.io/cluster-issuer: letsencrypt-prod
nginx.ingress.kubernetes.io/ssl-redirect: "true"
hosts:
- grafana.leeworks.dev
tls:
- secretName: grafana-tls
hosts:
- grafana.leeworks.dev
persistence:
enabled: true
size: 5Gi
sidecar:
dashboards:
enabled: true
prometheus:
prometheusSpec:
retention: 30d
storageSpec:
volumeClaimTemplate:
spec:
resources:
requests:
storage: 20Gi
# Scrape pods with prometheus.io/scrape=true annotations
podMonitorNamespaceSelector: {}
podMonitorSelector: {}
serviceMonitorNamespaceSelector: {}
serviceMonitorSelector: {}
# Additional scrape configs for annotation-based discovery
additionalScrapeConfigs:
- job_name: 'kubernetes-pods'
kubernetes_sd_configs:
- role: pod
relabel_configs:
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
action: keep
regex: "true"
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
action: replace
target_label: __metrics_path__
regex: (.+)
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
action: replace
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
target_label: __address__
- action: labelmap
regex: __meta_kubernetes_pod_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
action: replace
target_label: kubernetes_namespace
- source_labels: [__meta_kubernetes_pod_name]
action: replace
target_label: kubernetes_pod_name
alertmanager:
enabled: true
config:
global:
slack_api_url_file: /etc/alertmanager/secrets/gatus-slack-webhook/url
route:
receiver: slack-api-alerts
group_by: [alertname, namespace]
group_wait: 30s
group_interval: 5m
repeat_interval: 4h
receivers:
- name: slack-api-alerts
slack_configs:
- channel: '#api-alerts'
title: '{{ .CommonAnnotations.summary }}'
text: '{{ range .Alerts }}{{ .Annotations.description }}{{ end }}'
alertmanagerSpec:
secrets:
- gatus-slack-webhook
kubeStateMetrics:
enabled: true
nodeExporter:
enabled: true