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
+4 -243
View File
@@ -1,243 +1,4 @@
# Traefik ingress routes for all services — TLS via cert-manager + Cloudflare DNS-01
# Kong and open-webui ingresses moved to inactive/ — restore when needed
resource "kubernetes_ingress_v1" "ollama" {
metadata {
name = "ollama"
namespace = kubernetes_namespace.ollama.metadata[0].name
annotations = {
"traefik.ingress.kubernetes.io/router.entrypoints" = "websecure"
"cert-manager.io/cluster-issuer" = "letsencrypt-prod"
}
}
spec {
tls {
hosts = ["ollama.${var.infra_domain}"]
secret_name = "ollama-tls"
}
rule {
host = "ollama.${var.infra_domain}"
http {
path {
path = "/"
path_type = "Prefix"
backend {
service {
name = "ollama"
port { number = 11434 }
}
}
}
}
}
}
depends_on = [helm_release.cert_manager]
}
resource "kubernetes_ingress_v1" "registry" {
metadata {
name = "registry"
namespace = kubernetes_namespace.registry.metadata[0].name
annotations = {
"traefik.ingress.kubernetes.io/router.entrypoints" = "websecure"
"cert-manager.io/cluster-issuer" = "letsencrypt-prod"
"traefik.ingress.kubernetes.io/router.middlewares" = "registry-chunked@kubernetescrd"
"nginx.ingress.kubernetes.io/proxy-body-size" = "0"
"nginx.ingress.kubernetes.io/proxy-read-timeout" = "600"
"nginx.ingress.kubernetes.io/proxy-send-timeout" = "600"
}
}
spec {
tls {
hosts = ["registry.${var.infra_domain}"]
secret_name = "registry-tls"
}
rule {
host = "registry.${var.infra_domain}"
http {
path {
path = "/"
path_type = "Prefix"
backend {
service {
name = "registry"
port { number = 5000 }
}
}
}
}
}
}
depends_on = [helm_release.cert_manager]
}
resource "kubernetes_ingress_v1" "registry_ui" {
metadata {
name = "registry-ui"
namespace = kubernetes_namespace.registry.metadata[0].name
annotations = {
"traefik.ingress.kubernetes.io/router.entrypoints" = "websecure"
"cert-manager.io/cluster-issuer" = "letsencrypt-prod"
}
}
spec {
tls {
hosts = ["docker.neuralplatform.ai"]
secret_name = "docker-ui-tls"
}
rule {
host = "docker.neuralplatform.ai"
http {
path {
path = "/"
path_type = "Prefix"
backend {
service {
name = "registry-ui"
port { number = 80 }
}
}
}
}
}
}
depends_on = [helm_release.cert_manager]
}
# npm registry — Verdaccio (proxies npmjs.org, caches locally)
resource "kubernetes_ingress_v1" "npm_registry" {
metadata {
name = "npm-registry"
namespace = kubernetes_namespace.packages.metadata[0].name
annotations = {
"traefik.ingress.kubernetes.io/router.entrypoints" = "websecure"
"cert-manager.io/cluster-issuer" = "letsencrypt-prod"
}
}
spec {
tls {
hosts = ["npm.neuralplatform.ai"]
secret_name = "npm-registry-tls"
}
rule {
host = "npm.neuralplatform.ai"
http {
path {
path = "/"
path_type = "Prefix"
backend {
service {
name = "verdaccio"
port { number = 4873 }
}
}
}
}
}
}
depends_on = [helm_release.cert_manager]
}
# Alloy OTLP HTTP ingress — external log/trace ingestion from RunPod pods
# Auth: HTTP Basic Auth (username: pantheon, password: ALLOY_PUSH_TOKEN from Vault)
# Pods set: Authorization: Basic base64(pantheon:<token>)
# Traefik middleware strips auth before forwarding to Alloy.
resource "kubernetes_manifest" "alloy_otlp_basicauth_middleware" {
manifest = {
apiVersion = "traefik.io/v1alpha1"
kind = "Middleware"
metadata = {
name = "alloy-otlp-auth"
namespace = "monitoring"
}
spec = {
basicAuth = {
secret = "alloy-otlp-auth"
}
}
}
depends_on = [kubernetes_secret.alloy_otlp_auth]
}
resource "kubernetes_ingress_v1" "alloy_otlp" {
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 {
tls {
hosts = ["alloy.${var.infra_domain}"]
secret_name = "alloy-otlp-tls"
}
rule {
host = "alloy.${var.infra_domain}"
http {
path {
path = "/"
path_type = "Prefix"
backend {
service {
name = "alloy-otlp"
port { number = 4318 }
}
}
}
}
}
}
depends_on = [
kubernetes_manifest.alloy_otlp_basicauth_middleware,
kubernetes_service.alloy_otlp,
helm_release.cert_manager,
]
}
# PyPI registry — devpi (proxies pypi.org, caches locally)
resource "kubernetes_ingress_v1" "pypi_registry" {
metadata {
name = "pypi-registry"
namespace = kubernetes_namespace.packages.metadata[0].name
annotations = {
"traefik.ingress.kubernetes.io/router.entrypoints" = "websecure"
"cert-manager.io/cluster-issuer" = "letsencrypt-prod"
}
}
spec {
tls {
hosts = ["pypi.neuralplatform.ai"]
secret_name = "pypi-registry-tls"
}
rule {
host = "pypi.neuralplatform.ai"
http {
path {
path = "/"
path_type = "Prefix"
backend {
service {
name = "devpi"
port { number = 3141 }
}
}
}
}
}
}
depends_on = [helm_release.cert_manager]
}
# Ingresses — all moved to k8s/<service>/ingress.yaml, managed by Argo CD
# See: k8s/neuron/ingress.yaml, k8s/gitea/ingress.yaml, k8s/ollama/ingress.yaml,
# k8s/registry/ingress.yaml, k8s/packages/ingress.yaml,
# k8s/monitoring/ingress.yaml, k8s/adguard/ingress.yaml