Migrate k8s config from Terraform to Argo CD + ESO

Phase 1: Install External Secrets Operator via Argo CD app
- apps/external-secrets.yaml — ESO Helm chart install
- apps/external-secrets-config.yaml — ClusterSecretStore deployment
- k8s/external-secrets/cluster-secret-store.yaml — Vault backend using vault-token Secret

Phase 2: Create k8s manifests for all services
- k8s/neuron/ — PVC, ConfigMap, ExternalSecrets (neuron-secrets, cloudflared-secret), Ingress
- k8s/gitea/ — PVC, ConfigMap (custom CSS), ExternalSecret (gitea-db), Ingress
- k8s/github-runner/ — ExternalSecret (github-runner-secret)
- k8s/gitea-runner/ — ExternalSecret (gitea-runner-secret)
- k8s/monitoring/ — ExternalSecrets (grafana, slack), Alloy OTLP service+middleware, datasources ConfigMap, Ingress
- k8s/postgres/ — ExternalSecret (postgres-passwords)
- k8s/vault/ — ExternalSecret (vault-gcp-sa from Vault)
- k8s/adguard/ — PVCs, ConfigMap, Certificate, Ingress, ddclient Deployment+ExternalSecret
- k8s/ollama/ — PVC, Ingress
- k8s/headscale/ — PVC
- k8s/packages/ — PVCs, ConfigMap, Ingresses
- k8s/registry/ — PVC, Ingresses
- k8s/backup/ — CronJob, ExternalSecret (backup-credentials)

New Argo CD apps for Helm releases:
- apps/kube-prometheus-stack.yaml, loki.yaml, tempo.yaml, alloy.yaml
- apps/postgres.yaml, redis.yaml, vault.yaml

New Argo CD apps for k8s config paths:
- apps/neuron-config, gitea-config, ci-config, gitea-runner-config
- apps/monitoring-config, adguard-config, ollama-config, headscale-config
- apps/packages-config, registry-config, postgres-config, vault-config, backup

Phase 3: Strip Terraform to infrastructure-only
- All kubernetes_* and helm_release resources removed from service .tf files
- Each service .tf now contains only kubernetes_namespace (bootstrap dependency)
- variables.tf stripped to only cloudflare_api_key, cloudflare_email, gitea_api_token
- namespaces.tf gains external-secrets namespace
- ingress.tf, backup.tf, ddclient.tf emptied (resources in k8s/)
- cert-manager.tf, argocd.tf, traefik.tf unchanged (bootstrap)
This commit is contained in:
Will Anderson
2026-03-25 10:29:14 -05:00
parent dd0f8a49a3
commit 4d0cfb1bbf
74 changed files with 1895 additions and 1726 deletions
@@ -0,0 +1,11 @@
---
# Traefik BasicAuth middleware — strips auth before forwarding to Alloy
# Secret alloy-otlp-auth is synced from Vault via ExternalSecret (see external-secrets.yaml)
apiVersion: traefik.io/v1alpha1
kind: Middleware
metadata:
name: alloy-otlp-auth
namespace: monitoring
spec:
basicAuth:
secret: alloy-otlp-auth
@@ -0,0 +1,18 @@
---
# Expose Alloy's OTLP HTTP port (4318) for external log/trace ingestion from RunPod pods
apiVersion: v1
kind: Service
metadata:
name: alloy-otlp
namespace: monitoring
labels:
app: alloy-otlp
spec:
selector:
app.kubernetes.io/name: alloy
ports:
- name: otlp-http
port: 4318
targetPort: 4318
protocol: TCP
type: ClusterIP
@@ -0,0 +1,23 @@
---
# alloy-otlp-auth — bcrypt htpasswd entry for Traefik BasicAuth middleware
# Username: pantheon, password: alloy push token from Vault secret/alloy
apiVersion: external-secrets.io/v1beta1
kind: ExternalSecret
metadata:
name: alloy-otlp-auth
namespace: monitoring
spec:
refreshInterval: 1h
secretStoreRef:
name: vault
kind: ClusterSecretStore
target:
name: alloy-otlp-auth
creationPolicy: Owner
# ESO does not bcrypt — the htpasswd entry must be pre-hashed in Vault.
# Store via: vault kv patch secret/alloy htpasswd_entry="pantheon:$(htpasswd -nbB pantheon <token> | cut -d: -f2)"
data:
- secretKey: users
remoteRef:
key: secret/data/alloy
property: htpasswd_entry
@@ -0,0 +1,37 @@
---
# Grafana extra datasources — Loki and Tempo with cross-linking
# Discovered by Grafana sidecar via label grafana_datasource=1
apiVersion: v1
kind: ConfigMap
metadata:
name: grafana-extra-datasources
namespace: monitoring
labels:
grafana_datasource: "1"
data:
datasources.yaml: |
apiVersion: 1
datasources:
- name: Loki
type: loki
uid: loki
url: http://loki-gateway.monitoring.svc.cluster.local
access: proxy
jsonData:
httpHeaderName1: X-Scope-OrgID
secureJsonData:
httpHeaderValue1: legion
- name: Tempo
type: tempo
uid: tempo
url: http://tempo.monitoring.svc.cluster.local:3100
access: proxy
jsonData:
lokiSearch:
datasourceUid: loki
tracesToLogsV2:
datasourceUid: loki
filterByTraceID: true
filterBySpanID: false
tracesToMetrics:
datasourceUid: prometheus
@@ -0,0 +1,40 @@
---
# grafana-admin-secret — Grafana admin password from Vault
apiVersion: external-secrets.io/v1beta1
kind: ExternalSecret
metadata:
name: grafana-admin-secret
namespace: monitoring
spec:
refreshInterval: 1h
secretStoreRef:
name: vault
kind: ClusterSecretStore
target:
name: grafana-admin-secret
creationPolicy: Owner
data:
- secretKey: admin-password
remoteRef:
key: secret/data/grafana
property: admin_password
---
# slack-bot-token — Slack bot token for Alertmanager notifications
apiVersion: external-secrets.io/v1beta1
kind: ExternalSecret
metadata:
name: slack-bot-token
namespace: monitoring
spec:
refreshInterval: 1h
secretStoreRef:
name: vault
kind: ClusterSecretStore
target:
name: slack-bot-token
creationPolicy: Owner
data:
- secretKey: bot_token
remoteRef:
key: secret/data/slack
property: bot_token
@@ -0,0 +1,29 @@
---
# Alloy OTLP HTTP ingress — external log/trace ingestion from RunPod pods
# Auth: HTTP Basic Auth (username: pantheon, password: ALLOY_PUSH_TOKEN)
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: alloy-otlp
namespace: monitoring
annotations:
traefik.ingress.kubernetes.io/router.entrypoints: websecure
traefik.ingress.kubernetes.io/router.middlewares: monitoring-alloy-otlp-auth@kubernetescrd
cert-manager.io/cluster-issuer: letsencrypt-prod
spec:
ingressClassName: traefik
tls:
- hosts:
- alloy.neuralplatform.ai
secretName: alloy-otlp-tls
rules:
- host: alloy.neuralplatform.ai
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: alloy-otlp
port:
number: 4318