delete example

@thomas.solbjor her er "import" av tofu fra ditt repo med justeringer for å tilpasse patterns her. Også minimalisert til å kun opprette cluster, ingen managed services som postgres etc. Ta en titt.

Co-authored-by: Danijel Simeunovic <danijel.simeunovic@fortedigital.com>
Reviewed-on: #15
Reviewed-by: Danijel Simeunovic <danijel.simeunovic@fortedigital.com>
Co-authored-by: Ghost <>
Co-committed-by: Ghost <>

.gitattributes

@@ -0,0 +1,2 @@
+# Force LF line endings for shell scripts
+*.sh text eol=lf

.gitea/workflows/ai-review.yaml

@@ -34,6 +34,7 @@ jobs:
       with:
         submodules: true
         fetch-depth: 0
+        token: ${{ secrets.AI_REVIEW_TOKEN }}
 
     - name: Run inline review
       uses: docker://nikitafilonov/ai-review:v0.64.0

.gitignore

@@ -16,3 +16,11 @@ devbox.d/
 devbox.lock
 .devbox/
 bash.exe.stackdump
+
+# OpenTofu
+.tofu/configs/*.env
+.tofu/scripts/*.config
+.tofu/platforms/**/.terraform/
+.tofu/platforms/**/terraform.tfstate*
+.tofu/platforms/**/tfplan
+.tofu/platforms/**/.terraform.lock.hcl

.tofu/configs/aks.env.example

@@ -0,0 +1,9 @@
+# Azure AKS credentials — copy to aks.env and fill in values
+# NEVER commit aks.env to git!
+
+# Required
+AZURE_TENANT_ID=your-azure-tenant-id
+AZURE_SUBSCRIPTION_ID=your-azure-subscription-id
+
+# Optional — defaults to cluster name if not set
+ARM_RESOURCE_GROUP=

.tofu/configs/eks.env.example

@@ -0,0 +1,10 @@
+# AWS EKS credentials — copy to eks.env and fill in values
+# NEVER commit eks.env to git!
+
+# Required — AWS CLI profile or access key
+AWS_PROFILE=default
+AWS_REGION=eu-west-1
+
+# Optional — override with explicit keys instead of profile
+# AWS_ACCESS_KEY_ID=
+# AWS_SECRET_ACCESS_KEY=

.tofu/configs/gke.env.example

@@ -0,0 +1,9 @@
+# GCP GKE credentials — copy to gke.env and fill in values
+# NEVER commit gke.env to git!
+
+# Required
+GCP_PROJECT_ID=your-gcp-project-id
+GCP_REGION=europe-west4
+
+# Optional — path to service account JSON key (if not using gcloud auth)
+# GOOGLE_APPLICATION_CREDENTIALS=/path/to/sa-key.json

.tofu/configs/upc.env.example

@@ -0,0 +1,8 @@
+# UpCloud credentials — copy to upc.env and fill in values
+# NEVER commit upc.env to git!
+
+# Required
+UPCLOUD_TOKEN=your-upcloud-api-token
+
+# Optional — set after cluster creation for kubeconfig retrieval
+UPCLOUD_CLUSTER_ID=

.tofu/platforms/aks/dev/main.tf

@@ -0,0 +1,18 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  prefix              = "clst-dev"
+  location            = "norwayeast"
+  resource_group_name = "clst-dev-rg"
+
+  # AKS — small dev nodes
+  aks_node_vm_size = "Standard_B2s"
+  aks_node_count   = 2
+
+  enable_delete_lock = false
+
+  tags = {
+    Environment = "dev"
+    ManagedBy   = "tofu"
+  }
+}

.tofu/platforms/aks/dev/outputs.tf

@@ -0,0 +1,26 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_name" {
+  value = module.cluster.cluster_name
+}
+
+output "resource_group_name" {
+  value = module.cluster.resource_group_name
+}
+
+output "kubernetes_version" {
+  value = module.cluster.kubernetes_version
+}
+
+output "location" {
+  value = module.cluster.location
+}
+
+output "oidc_issuer_url" {
+  value = module.cluster.oidc_issuer_url
+}
+
+output "kubeconfig" {
+  value     = module.cluster.kubeconfig
+  sensitive = true
+}

.tofu/platforms/aks/dev/providers.tf

@@ -0,0 +1,17 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    azurerm = {
+      source  = "hashicorp/azurerm"
+      version = "~> 4.0"
+    }
+  }
+}
+
+provider "azurerm" {
+  features {}
+  # Credentials via environment variables:
+  #   ARM_SUBSCRIPTION_ID, ARM_TENANT_ID, ARM_CLIENT_ID, ARM_CLIENT_SECRET
+  # Or: az login (uses your Azure CLI session)
+}

.tofu/platforms/aks/modules/cluster/main.tf

@@ -0,0 +1,72 @@
+# Current Azure/Entra ID context — provides tenant_id used in outputs
+data "azurerm_client_config" "current" {}
+
+# ─── Resource Group ───────────────────────────────────────────────────
+
+resource "azurerm_resource_group" "main" {
+  name     = var.resource_group_name
+  location = var.location
+  tags     = var.tags
+}
+
+resource "azurerm_management_lock" "main" {
+  count      = var.enable_delete_lock ? 1 : 0
+  name       = "${var.prefix}-delete-lock"
+  scope      = azurerm_resource_group.main.id
+  lock_level = "CanNotDelete"
+  notes      = "Prevents accidental deletion of production resources"
+}
+
+# ─── Networking ───────────────────────────────────────────────────────
+
+resource "azurerm_virtual_network" "main" {
+  name                = "${var.prefix}-vnet"
+  resource_group_name = azurerm_resource_group.main.name
+  location            = azurerm_resource_group.main.location
+  address_space       = [var.vnet_address_space]
+  tags                = var.tags
+}
+
+# AKS nodes subnet
+resource "azurerm_subnet" "aks" {
+  name                 = "${var.prefix}-aks-subnet"
+  resource_group_name  = azurerm_resource_group.main.name
+  virtual_network_name = azurerm_virtual_network.main.name
+  address_prefixes     = [var.aks_subnet_cidr]
+}
+
+# ─── AKS Cluster ──────────────────────────────────────────────────────
+
+resource "azurerm_kubernetes_cluster" "main" {
+  name                = "${var.prefix}-aks"
+  resource_group_name = azurerm_resource_group.main.name
+  location            = azurerm_resource_group.main.location
+  dns_prefix          = replace(var.prefix, "-", "")
+  kubernetes_version  = var.aks_kubernetes_version
+  tags                = var.tags
+
+  default_node_pool {
+    name           = "system"
+    node_count     = var.aks_node_count
+    vm_size        = var.aks_node_vm_size
+    vnet_subnet_id = azurerm_subnet.aks.id
+    node_labels = {
+      prefix = var.prefix
+      role   = "worker"
+      env    = lookup(var.tags, "Environment", "dev")
+    }
+  }
+
+  identity {
+    type = "SystemAssigned"
+  }
+
+  network_profile {
+    network_plugin = "azure"
+    network_policy = "azure"
+  }
+
+  # Enable Workload Identity for keyless Azure service access (MSI)
+  oidc_issuer_enabled       = true
+  workload_identity_enabled = true
+}

.tofu/platforms/aks/modules/cluster/outputs.tf

@@ -0,0 +1,32 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_name" {
+  description = "AKS cluster name"
+  value       = azurerm_kubernetes_cluster.main.name
+}
+
+output "resource_group_name" {
+  description = "Resource group name"
+  value       = azurerm_resource_group.main.name
+}
+
+output "kubernetes_version" {
+  description = "Kubernetes version"
+  value       = azurerm_kubernetes_cluster.main.kubernetes_version
+}
+
+output "location" {
+  description = "Azure region"
+  value       = azurerm_resource_group.main.location
+}
+
+output "oidc_issuer_url" {
+  description = "AKS OIDC issuer URL (for workload identity federation)"
+  value       = azurerm_kubernetes_cluster.main.oidc_issuer_url
+}
+
+output "kubeconfig" {
+  description = "Kubeconfig for the AKS cluster"
+  value       = azurerm_kubernetes_cluster.main.kube_config_raw
+  sensitive   = true
+}

.tofu/platforms/aks/modules/cluster/providers.tf

@@ -0,0 +1,18 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    azurerm = {
+      source  = "hashicorp/azurerm"
+      version = "~> 4.0"
+    }
+    azuread = {
+      source  = "hashicorp/azuread"
+      version = "~> 3.0"
+    }
+    random = {
+      source  = "hashicorp/random"
+      version = "~> 3.0"
+    }
+  }
+}

.tofu/platforms/aks/modules/cluster/variables.tf

@@ -0,0 +1,56 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+variable "prefix" {
+  description = "Prefix for resource names"
+  type        = string
+}
+
+variable "location" {
+  description = "Azure region (e.g., norwayeast, westeurope, northeurope)"
+  type        = string
+}
+
+variable "resource_group_name" {
+  description = "Name of the Azure Resource Group to create"
+  type        = string
+}
+
+variable "vnet_address_space" {
+  description = "Address space for the virtual network"
+  type        = string
+  default     = "10.100.0.0/16"
+}
+
+variable "aks_subnet_cidr" {
+  description = "CIDR block for the AKS node subnet"
+  type        = string
+  default     = "10.100.0.0/22"
+}
+
+variable "aks_node_vm_size" {
+  description = "VM size for AKS worker nodes (e.g., Standard_B2s, Standard_D4s_v3)"
+  type        = string
+}
+
+variable "aks_node_count" {
+  description = "Number of AKS worker nodes"
+  type        = number
+}
+
+variable "aks_kubernetes_version" {
+  description = "Kubernetes version for AKS (null = latest stable)"
+  type        = string
+  default     = null
+}
+
+variable "enable_delete_lock" {
+  description = "Protect the resource group from accidental deletion"
+  type        = bool
+  default     = false
+}
+
+variable "tags" {
+  description = "Tags applied to all resources"
+  type        = map(string)
+  default     = {}
+}

.tofu/platforms/aks/prod/main.tf

@@ -0,0 +1,18 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  prefix              = "clst"
+  location            = "westeurope"
+  resource_group_name = "clst-prod-rg"
+
+  # AKS — general-purpose nodes for production
+  aks_node_vm_size = "Standard_D4s_v3"
+  aks_node_count   = 3
+
+  enable_delete_lock = true
+
+  tags = {
+    Environment = "prod"
+    ManagedBy   = "tofu"
+  }
+}

.tofu/platforms/aks/prod/outputs.tf

@@ -0,0 +1,26 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_name" {
+  value = module.cluster.cluster_name
+}
+
+output "resource_group_name" {
+  value = module.cluster.resource_group_name
+}
+
+output "kubernetes_version" {
+  value = module.cluster.kubernetes_version
+}
+
+output "location" {
+  value = module.cluster.location
+}
+
+output "oidc_issuer_url" {
+  value = module.cluster.oidc_issuer_url
+}
+
+output "kubeconfig" {
+  value     = module.cluster.kubeconfig
+  sensitive = true
+}

.tofu/platforms/aks/prod/providers.tf

@@ -0,0 +1,17 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    azurerm = {
+      source  = "hashicorp/azurerm"
+      version = "~> 4.0"
+    }
+  }
+}
+
+provider "azurerm" {
+  features {}
+  # Credentials via environment variables:
+  #   ARM_SUBSCRIPTION_ID, ARM_TENANT_ID, ARM_CLIENT_ID, ARM_CLIENT_SECRET
+  # Or: az login (uses your Azure CLI session)
+}

.tofu/platforms/aks/workload/main.tf

@@ -0,0 +1,173 @@
+# =============================================================================
+# Azure Workload Cluster
+# =============================================================================
+# A lean AKS cluster for running application workloads. No managed data
+# services — those live on the platform cluster. ArgoCD (on the platform
+# cluster) deploys apps to this cluster via the app-of-apps pattern.
+#
+# Platform components deployed by deploy-workload.sh:
+#   nginx-ingress, cert-manager, external-dns, external-secrets, alloy
+#
+# Usage:
+#   tofu init && tofu plan && tofu apply
+#   ./sync-tofu-outputs.sh --env azure-workload
+#   ./deploy-workload.sh --env azure-workload
+# =============================================================================
+
+variable "prefix" {
+  description = "Prefix for resource names (e.g., clst-workload)"
+  type        = string
+  default     = "clst-workload"
+}
+
+variable "location" {
+  description = "Azure region"
+  type        = string
+  default     = "norwayeast"
+}
+
+variable "resource_group_name" {
+  description = "Name of the Azure Resource Group to create"
+  type        = string
+  default     = "clst-workload-rg"
+}
+
+variable "vnet_address_space" {
+  description = "Address space for the virtual network"
+  type        = string
+  default     = "10.110.0.0/16"
+}
+
+variable "aks_subnet_cidr" {
+  description = "CIDR block for the AKS node subnet"
+  type        = string
+  default     = "10.110.0.0/22"
+}
+
+variable "aks_node_vm_size" {
+  description = "VM size for AKS worker nodes"
+  type        = string
+  default     = "Standard_B2s"
+}
+
+variable "aks_node_count" {
+  description = "Number of AKS worker nodes"
+  type        = number
+  default     = 2
+}
+
+variable "aks_kubernetes_version" {
+  description = "Kubernetes version for AKS (null = latest stable)"
+  type        = string
+  default     = null
+}
+
+variable "domain" {
+  description = "Public domain name — must have an existing Azure DNS zone"
+  type        = string
+}
+
+variable "dns_zone_resource_group" {
+  description = "Resource group containing the Azure DNS zone (defaults to cluster RG)"
+  type        = string
+  default     = ""
+}
+
+variable "tags" {
+  description = "Tags applied to all resources"
+  type        = map(string)
+  default = {
+    Environment = "workload"
+    ManagedBy   = "tofu"
+  }
+}
+
+# ─── Resource Group ───────────────────────────────────────────────────
+
+resource "azurerm_resource_group" "main" {
+  name     = var.resource_group_name
+  location = var.location
+  tags     = var.tags
+}
+
+# ─── Networking ───────────────────────────────────────────────────────
+
+resource "azurerm_virtual_network" "main" {
+  name                = "${var.prefix}-vnet"
+  resource_group_name = azurerm_resource_group.main.name
+  location            = azurerm_resource_group.main.location
+  address_space       = [var.vnet_address_space]
+  tags                = var.tags
+}
+
+resource "azurerm_subnet" "aks" {
+  name                 = "${var.prefix}-aks-subnet"
+  resource_group_name  = azurerm_resource_group.main.name
+  virtual_network_name = azurerm_virtual_network.main.name
+  address_prefixes     = [var.aks_subnet_cidr]
+}
+
+# ─── AKS Cluster ──────────────────────────────────────────────────────
+
+resource "azurerm_kubernetes_cluster" "main" {
+  name                = "${var.prefix}-aks"
+  resource_group_name = azurerm_resource_group.main.name
+  location            = azurerm_resource_group.main.location
+  dns_prefix          = replace(var.prefix, "-", "")
+  kubernetes_version  = var.aks_kubernetes_version
+  tags                = var.tags
+
+  default_node_pool {
+    name           = "system"
+    node_count     = var.aks_node_count
+    vm_size        = var.aks_node_vm_size
+    vnet_subnet_id = azurerm_subnet.aks.id
+    node_labels = {
+      prefix = var.prefix
+      role   = "worker"
+      env    = lookup(var.tags, "Environment", "workload")
+    }
+  }
+
+  identity {
+    type = "SystemAssigned"
+  }
+
+  network_profile {
+    network_plugin = "azure"
+    network_policy = "azure"
+  }
+
+  oidc_issuer_enabled       = true
+  workload_identity_enabled = true
+}
+
+# ─── External-DNS Workload Identity ──────────────────────────────────
+# Allows external-dns to manage Azure DNS records for app ingresses.
+
+data "azurerm_dns_zone" "main" {
+  name                = var.domain
+  resource_group_name = var.dns_zone_resource_group != "" ? var.dns_zone_resource_group : azurerm_resource_group.main.name
+}
+
+resource "azurerm_user_assigned_identity" "external_dns" {
+  name                = "${var.prefix}-external-dns-identity"
+  resource_group_name = azurerm_resource_group.main.name
+  location            = azurerm_resource_group.main.location
+  tags                = var.tags
+}
+
+resource "azurerm_role_assignment" "external_dns_dns_contributor" {
+  scope                = data.azurerm_dns_zone.main.id
+  role_definition_name = "DNS Zone Contributor"
+  principal_id         = azurerm_user_assigned_identity.external_dns.principal_id
+}
+
+resource "azurerm_federated_identity_credential" "external_dns" {
+  name                = "${var.prefix}-external-dns-fedcred"
+  resource_group_name = azurerm_resource_group.main.name
+  parent_id           = azurerm_user_assigned_identity.external_dns.id
+  audience            = ["api://AzureADTokenExchange"]
+  issuer              = azurerm_kubernetes_cluster.main.oidc_issuer_url
+  subject             = "system:serviceaccount:external-dns:external-dns"
+}

.tofu/platforms/aks/workload/outputs.tf

@@ -0,0 +1,4 @@
+output "cluster_name"                    { value = azurerm_kubernetes_cluster.main.name }
+output "resource_group_name"             { value = azurerm_resource_group.main.name }
+output "location"                        { value = azurerm_resource_group.main.location }
+output "external_dns_identity_client_id" { value = azurerm_user_assigned_identity.external_dns.client_id }

.tofu/platforms/aks/workload/providers.tf

@@ -0,0 +1,21 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    azurerm = {
+      source  = "hashicorp/azurerm"
+      version = "~> 4.0"
+    }
+    random = {
+      source  = "hashicorp/random"
+      version = "~> 3.0"
+    }
+  }
+}
+
+provider "azurerm" {
+  features {}
+  # Credentials via environment variables:
+  #   ARM_SUBSCRIPTION_ID, ARM_TENANT_ID, ARM_CLIENT_ID, ARM_CLIENT_SECRET
+  # Or: az login (uses your Azure CLI session)
+}

.tofu/platforms/eks/dev/main.tf

@@ -0,0 +1,21 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  region = var.region
+  prefix = "clst-dev"
+
+  # VPC
+  availability_zones = ["${var.region}a", "${var.region}b"]
+
+  # EKS — small dev nodes
+  node_instance_type = "t3.medium"
+  node_count         = 2
+  node_min_count     = 1
+  node_max_count     = 4
+  kubernetes_version = "1.30"
+
+  tags = {
+    Environment = "dev"
+    ManagedBy   = "tofu"
+  }
+}

.tofu/platforms/eks/dev/outputs.tf

@@ -0,0 +1,5 @@
+output "cluster_name"    { value = module.cluster.cluster_name }
+output "aws_region"      { value = module.cluster.aws_region }
+output "oidc_issuer_url" { value = module.cluster.oidc_issuer_url }
+output "oidc_provider_arn" { value = module.cluster.oidc_provider_arn }
+output "vpc_id"          { value = module.cluster.vpc_id }

.tofu/platforms/eks/dev/providers.tf

@@ -0,0 +1,24 @@
+terraform {
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+    tls = {
+      source  = "hashicorp/tls"
+      version = "~> 4.0"
+    }
+  }
+}
+
+# Authentication: set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN
+# or configure an AWS profile: export AWS_PROFILE=clst
+provider "aws" {
+  region = var.region
+}
+
+variable "region" {
+  description = "AWS region for dev environment"
+  type        = string
+  default     = "eu-west-1"
+}

.tofu/platforms/eks/modules/cluster/main.tf

@@ -0,0 +1,207 @@
+# ─── VPC ──────────────────────────────────────────────────────────────
+
+resource "aws_vpc" "main" {
+  cidr_block           = var.vpc_cidr
+  enable_dns_hostnames = true
+  enable_dns_support   = true
+
+  tags = merge(var.tags, { Name = "${var.prefix}-vpc" })
+}
+
+resource "aws_internet_gateway" "main" {
+  vpc_id = aws_vpc.main.id
+  tags   = merge(var.tags, { Name = "${var.prefix}-igw" })
+}
+
+# Public subnets (one per AZ) — for NAT gateways and load balancers
+resource "aws_subnet" "public" {
+  count             = length(var.availability_zones)
+  vpc_id            = aws_vpc.main.id
+  cidr_block        = cidrsubnet(var.vpc_cidr, 4, count.index)
+  availability_zone = var.availability_zones[count.index]
+
+  map_public_ip_on_launch = true
+
+  tags = merge(var.tags, {
+    Name                                        = "${var.prefix}-public-${count.index + 1}"
+    "kubernetes.io/cluster/${var.prefix}-eks"   = "shared"
+    "kubernetes.io/role/elb"                    = "1"
+  })
+}
+
+# Private subnets (one per AZ) — for EKS nodes
+resource "aws_subnet" "private" {
+  count             = length(var.availability_zones)
+  vpc_id            = aws_vpc.main.id
+  cidr_block        = cidrsubnet(var.vpc_cidr, 4, count.index + length(var.availability_zones))
+  availability_zone = var.availability_zones[count.index]
+
+  tags = merge(var.tags, {
+    Name                                        = "${var.prefix}-private-${count.index + 1}"
+    "kubernetes.io/cluster/${var.prefix}-eks"   = "shared"
+    "kubernetes.io/role/internal-elb"           = "1"
+  })
+}
+
+# NAT Gateway (single, in first public subnet — use one per AZ for prod HA)
+resource "aws_eip" "nat" {
+  domain = "vpc"
+  tags   = merge(var.tags, { Name = "${var.prefix}-nat-eip" })
+}
+
+resource "aws_nat_gateway" "main" {
+  allocation_id = aws_eip.nat.id
+  subnet_id     = aws_subnet.public[0].id
+  tags          = merge(var.tags, { Name = "${var.prefix}-nat" })
+
+  depends_on = [aws_internet_gateway.main]
+}
+
+resource "aws_route_table" "public" {
+  vpc_id = aws_vpc.main.id
+
+  route {
+    cidr_block = "0.0.0.0/0"
+    gateway_id = aws_internet_gateway.main.id
+  }
+
+  tags = merge(var.tags, { Name = "${var.prefix}-public-rt" })
+}
+
+resource "aws_route_table_association" "public" {
+  count          = length(var.availability_zones)
+  subnet_id      = aws_subnet.public[count.index].id
+  route_table_id = aws_route_table.public.id
+}
+
+resource "aws_route_table" "private" {
+  vpc_id = aws_vpc.main.id
+
+  route {
+    cidr_block     = "0.0.0.0/0"
+    nat_gateway_id = aws_nat_gateway.main.id
+  }
+
+  tags = merge(var.tags, { Name = "${var.prefix}-private-rt" })
+}
+
+resource "aws_route_table_association" "private" {
+  count          = length(var.availability_zones)
+  subnet_id      = aws_subnet.private[count.index].id
+  route_table_id = aws_route_table.private.id
+}
+
+# ─── EKS Cluster ──────────────────────────────────────────────────────
+
+resource "aws_iam_role" "eks_cluster" {
+  name_prefix = "${var.prefix}-eks-cluster-"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [{
+      Action    = "sts:AssumeRole"
+      Effect    = "Allow"
+      Principal = { Service = "eks.amazonaws.com" }
+    }]
+  })
+
+  tags = var.tags
+}
+
+resource "aws_iam_role_policy_attachment" "eks_cluster_policy" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEKSClusterPolicy"
+  role       = aws_iam_role.eks_cluster.name
+}
+
+resource "aws_eks_cluster" "main" {
+  name     = "${var.prefix}-eks"
+  role_arn = aws_iam_role.eks_cluster.arn
+  version  = var.kubernetes_version
+
+  vpc_config {
+    subnet_ids              = concat(aws_subnet.private[*].id, aws_subnet.public[*].id)
+    endpoint_private_access = true
+    endpoint_public_access  = true
+  }
+
+  # Enable OIDC issuer for IRSA (IAM Roles for Service Accounts)
+  access_config {
+    authentication_mode = "API_AND_CONFIG_MAP"
+  }
+
+  tags = var.tags
+
+  depends_on = [aws_iam_role_policy_attachment.eks_cluster_policy]
+}
+
+# OIDC provider — required for IRSA (IAM Roles for Service Accounts)
+data "tls_certificate" "eks" {
+  url = aws_eks_cluster.main.identity[0].oidc[0].issuer
+}
+
+resource "aws_iam_openid_connect_provider" "eks" {
+  client_id_list  = ["sts.amazonaws.com"]
+  thumbprint_list = [data.tls_certificate.eks.certificates[0].sha1_fingerprint]
+  url             = aws_eks_cluster.main.identity[0].oidc[0].issuer
+
+  tags = var.tags
+}
+
+# EKS Node Group
+
+resource "aws_iam_role" "eks_nodes" {
+  name_prefix = "${var.prefix}-eks-nodes-"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [{
+      Action    = "sts:AssumeRole"
+      Effect    = "Allow"
+      Principal = { Service = "ec2.amazonaws.com" }
+    }]
+  })
+
+  tags = var.tags
+}
+
+resource "aws_iam_role_policy_attachment" "eks_worker_node_policy" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEKSWorkerNodePolicy"
+  role       = aws_iam_role.eks_nodes.name
+}
+
+resource "aws_iam_role_policy_attachment" "eks_cni_policy" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEKS_CNI_Policy"
+  role       = aws_iam_role.eks_nodes.name
+}
+
+resource "aws_iam_role_policy_attachment" "eks_ecr_readonly" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly"
+  role       = aws_iam_role.eks_nodes.name
+}
+
+resource "aws_eks_node_group" "main" {
+  cluster_name    = aws_eks_cluster.main.name
+  node_group_name = "${var.prefix}-nodes"
+  node_role_arn   = aws_iam_role.eks_nodes.arn
+  subnet_ids      = aws_subnet.private[*].id
+
+  instance_types = [var.node_instance_type]
+
+  scaling_config {
+    desired_size = var.node_count
+    max_size     = var.node_max_count
+    min_size     = var.node_min_count
+  }
+
+  update_config {
+    max_unavailable = 1
+  }
+
+  tags = var.tags
+
+  depends_on = [
+    aws_iam_role_policy_attachment.eks_worker_node_policy,
+    aws_iam_role_policy_attachment.eks_cni_policy,
+    aws_iam_role_policy_attachment.eks_ecr_readonly,
+  ]
+}

.tofu/platforms/eks/modules/cluster/outputs.tf

@@ -0,0 +1,26 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_name" {
+  description = "EKS cluster name"
+  value       = aws_eks_cluster.main.name
+}
+
+output "aws_region" {
+  description = "AWS region"
+  value       = var.region
+}
+
+output "oidc_issuer_url" {
+  description = "EKS OIDC issuer URL (for IRSA)"
+  value       = aws_eks_cluster.main.identity[0].oidc[0].issuer
+}
+
+output "oidc_provider_arn" {
+  description = "IAM OIDC provider ARN (for IRSA trust policies)"
+  value       = aws_iam_openid_connect_provider.eks.arn
+}
+
+output "vpc_id" {
+  description = "VPC ID"
+  value       = aws_vpc.main.id
+}

.tofu/platforms/eks/modules/cluster/providers.tf

@@ -0,0 +1,12 @@
+terraform {
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+    tls = {
+      source  = "hashicorp/tls"
+      version = "~> 4.0"
+    }
+  }
+}

.tofu/platforms/eks/modules/cluster/variables.tf

@@ -0,0 +1,61 @@
+# ─── Region ──────────────────────────────────────────────────────────
+
+variable "region" {
+  description = "AWS region (e.g., eu-west-1, us-east-1)"
+  type        = string
+}
+
+variable "prefix" {
+  description = "Prefix for resource names (e.g., clst-dev)"
+  type        = string
+}
+
+# ─── Networking ───────────────────────────────────────────────────────
+
+variable "vpc_cidr" {
+  description = "VPC CIDR block"
+  type        = string
+  default     = "10.100.0.0/16"
+}
+
+variable "availability_zones" {
+  description = "List of AZs for subnets (2–3 recommended)"
+  type        = list(string)
+}
+
+# ─── EKS Cluster ─────────────────────────────────────────────────────
+
+variable "node_instance_type" {
+  description = "EKS node instance type (e.g., t3.medium, m5.xlarge)"
+  type        = string
+}
+
+variable "node_count" {
+  description = "Desired number of EKS worker nodes"
+  type        = number
+}
+
+variable "node_min_count" {
+  description = "Minimum number of EKS worker nodes"
+  type        = number
+  default     = 1
+}
+
+variable "node_max_count" {
+  description = "Maximum number of EKS worker nodes"
+  type        = number
+}
+
+variable "kubernetes_version" {
+  description = "Kubernetes version for EKS (e.g., \"1.30\")"
+  type        = string
+  default     = "1.30"
+}
+
+# ─── Tags ─────────────────────────────────────────────────────────────
+
+variable "tags" {
+  description = "Tags applied to all resources"
+  type        = map(string)
+  default     = {}
+}

.tofu/platforms/eks/prod/main.tf

@@ -0,0 +1,21 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  region = var.region
+  prefix = "clst"
+
+  # VPC
+  availability_zones = ["${var.region}a", "${var.region}b", "${var.region}c"]
+
+  # EKS — general-purpose nodes for production
+  node_instance_type = "m5.xlarge"
+  node_count         = 3
+  node_min_count     = 3
+  node_max_count     = 6
+  kubernetes_version = "1.30"
+
+  tags = {
+    Environment = "prod"
+    ManagedBy   = "tofu"
+  }
+}

.tofu/platforms/eks/prod/outputs.tf

@@ -0,0 +1,5 @@
+output "cluster_name"    { value = module.cluster.cluster_name }
+output "aws_region"      { value = module.cluster.aws_region }
+output "oidc_issuer_url" { value = module.cluster.oidc_issuer_url }
+output "oidc_provider_arn" { value = module.cluster.oidc_provider_arn }
+output "vpc_id"          { value = module.cluster.vpc_id }

.tofu/platforms/eks/prod/providers.tf

@@ -0,0 +1,22 @@
+terraform {
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+    tls = {
+      source  = "hashicorp/tls"
+      version = "~> 4.0"
+    }
+  }
+}
+
+provider "aws" {
+  region = var.region
+}
+
+variable "region" {
+  description = "AWS region for prod environment"
+  type        = string
+  default     = "eu-west-1"
+}

.tofu/platforms/eks/workload/main.tf

@@ -0,0 +1,339 @@
+# =============================================================================
+# AWS Workload Cluster
+# =============================================================================
+# A lean EKS cluster for running application workloads. No managed data
+# services — those live on the platform cluster. ArgoCD (on the platform
+# cluster) deploys apps to this cluster via the app-of-apps pattern.
+#
+# Platform components deployed by deploy-workload.sh:
+#   nginx-ingress, cert-manager, external-dns, external-secrets, alloy
+#
+# Usage:
+#   tofu init && tofu plan && tofu apply
+#   ./sync-tofu-outputs.sh --env aws-workload
+#   ./deploy-workload.sh --env aws-workload
+# =============================================================================
+
+variable "prefix" {
+  description = "Prefix for resource names (e.g., clst-workload)"
+  type        = string
+  default     = "clst-workload"
+}
+
+variable "availability_zones" {
+  description = "List of AZs for subnets"
+  type        = list(string)
+  default     = ["eu-west-1a", "eu-west-1b"]
+}
+
+variable "vpc_cidr" {
+  description = "VPC CIDR block"
+  type        = string
+  default     = "10.110.0.0/16"
+}
+
+variable "node_instance_type" {
+  description = "EKS node instance type"
+  type        = string
+  default     = "t3.medium"
+}
+
+variable "node_count" {
+  description = "Desired number of EKS worker nodes"
+  type        = number
+  default     = 2
+}
+
+variable "node_min_count" {
+  description = "Minimum number of EKS worker nodes"
+  type        = number
+  default     = 1
+}
+
+variable "node_max_count" {
+  description = "Maximum number of EKS worker nodes"
+  type        = number
+  default     = 4
+}
+
+variable "kubernetes_version" {
+  description = "Kubernetes version for EKS"
+  type        = string
+  default     = "1.30"
+}
+
+variable "domain" {
+  description = "Public domain name — must have an existing Route53 hosted zone"
+  type        = string
+}
+
+variable "tags" {
+  description = "Tags applied to all resources"
+  type        = map(string)
+  default = {
+    Environment = "workload"
+    ManagedBy   = "tofu"
+  }
+}
+
+# ─── VPC ──────────────────────────────────────────────────────────────
+
+resource "aws_vpc" "main" {
+  cidr_block           = var.vpc_cidr
+  enable_dns_hostnames = true
+  enable_dns_support   = true
+
+  tags = merge(var.tags, { Name = "${var.prefix}-vpc" })
+}
+
+resource "aws_internet_gateway" "main" {
+  vpc_id = aws_vpc.main.id
+  tags   = merge(var.tags, { Name = "${var.prefix}-igw" })
+}
+
+resource "aws_subnet" "public" {
+  count             = length(var.availability_zones)
+  vpc_id            = aws_vpc.main.id
+  cidr_block        = cidrsubnet(var.vpc_cidr, 4, count.index)
+  availability_zone = var.availability_zones[count.index]
+
+  map_public_ip_on_launch = true
+
+  tags = merge(var.tags, {
+    Name                                        = "${var.prefix}-public-${count.index + 1}"
+    "kubernetes.io/cluster/${var.prefix}-eks"   = "shared"
+    "kubernetes.io/role/elb"                    = "1"
+  })
+}
+
+resource "aws_subnet" "private" {
+  count             = length(var.availability_zones)
+  vpc_id            = aws_vpc.main.id
+  cidr_block        = cidrsubnet(var.vpc_cidr, 4, count.index + length(var.availability_zones))
+  availability_zone = var.availability_zones[count.index]
+
+  tags = merge(var.tags, {
+    Name                                        = "${var.prefix}-private-${count.index + 1}"
+    "kubernetes.io/cluster/${var.prefix}-eks"   = "shared"
+    "kubernetes.io/role/internal-elb"           = "1"
+  })
+}
+
+resource "aws_eip" "nat" {
+  domain = "vpc"
+  tags   = merge(var.tags, { Name = "${var.prefix}-nat-eip" })
+}
+
+resource "aws_nat_gateway" "main" {
+  allocation_id = aws_eip.nat.id
+  subnet_id     = aws_subnet.public[0].id
+  tags          = merge(var.tags, { Name = "${var.prefix}-nat" })
+
+  depends_on = [aws_internet_gateway.main]
+}
+
+resource "aws_route_table" "public" {
+  vpc_id = aws_vpc.main.id
+
+  route {
+    cidr_block = "0.0.0.0/0"
+    gateway_id = aws_internet_gateway.main.id
+  }
+
+  tags = merge(var.tags, { Name = "${var.prefix}-public-rt" })
+}
+
+resource "aws_route_table_association" "public" {
+  count          = length(var.availability_zones)
+  subnet_id      = aws_subnet.public[count.index].id
+  route_table_id = aws_route_table.public.id
+}
+
+resource "aws_route_table" "private" {
+  vpc_id = aws_vpc.main.id
+
+  route {
+    cidr_block     = "0.0.0.0/0"
+    nat_gateway_id = aws_nat_gateway.main.id
+  }
+
+  tags = merge(var.tags, { Name = "${var.prefix}-private-rt" })
+}
+
+resource "aws_route_table_association" "private" {
+  count          = length(var.availability_zones)
+  subnet_id      = aws_subnet.private[count.index].id
+  route_table_id = aws_route_table.private.id
+}
+
+# ─── EKS Cluster ──────────────────────────────────────────────────────
+
+resource "aws_iam_role" "eks_cluster" {
+  name_prefix = "${var.prefix}-eks-cluster-"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [{
+      Action    = "sts:AssumeRole"
+      Effect    = "Allow"
+      Principal = { Service = "eks.amazonaws.com" }
+    }]
+  })
+
+  tags = var.tags
+}
+
+resource "aws_iam_role_policy_attachment" "eks_cluster_policy" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEKSClusterPolicy"
+  role       = aws_iam_role.eks_cluster.name
+}
+
+resource "aws_eks_cluster" "main" {
+  name     = "${var.prefix}-eks"
+  role_arn = aws_iam_role.eks_cluster.arn
+  version  = var.kubernetes_version
+
+  vpc_config {
+    subnet_ids              = concat(aws_subnet.private[*].id, aws_subnet.public[*].id)
+    endpoint_private_access = true
+    endpoint_public_access  = true
+  }
+
+  access_config {
+    authentication_mode = "API_AND_CONFIG_MAP"
+  }
+
+  tags = var.tags
+
+  depends_on = [aws_iam_role_policy_attachment.eks_cluster_policy]
+}
+
+# OIDC provider — required for IRSA
+data "tls_certificate" "eks" {
+  url = aws_eks_cluster.main.identity[0].oidc[0].issuer
+}
+
+resource "aws_iam_openid_connect_provider" "eks" {
+  client_id_list  = ["sts.amazonaws.com"]
+  thumbprint_list = [data.tls_certificate.eks.certificates[0].sha1_fingerprint]
+  url             = aws_eks_cluster.main.identity[0].oidc[0].issuer
+
+  tags = var.tags
+}
+
+resource "aws_iam_role" "eks_nodes" {
+  name_prefix = "${var.prefix}-eks-nodes-"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [{
+      Action    = "sts:AssumeRole"
+      Effect    = "Allow"
+      Principal = { Service = "ec2.amazonaws.com" }
+    }]
+  })
+
+  tags = var.tags
+}
+
+resource "aws_iam_role_policy_attachment" "eks_worker_node_policy" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEKSWorkerNodePolicy"
+  role       = aws_iam_role.eks_nodes.name
+}
+
+resource "aws_iam_role_policy_attachment" "eks_cni_policy" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEKS_CNI_Policy"
+  role       = aws_iam_role.eks_nodes.name
+}
+
+resource "aws_iam_role_policy_attachment" "eks_ecr_readonly" {
+  policy_arn = "arn:aws:iam::aws:policy/AmazonEC2ContainerRegistryReadOnly"
+  role       = aws_iam_role.eks_nodes.name
+}
+
+resource "aws_eks_node_group" "main" {
+  cluster_name    = aws_eks_cluster.main.name
+  node_group_name = "${var.prefix}-nodes"
+  node_role_arn   = aws_iam_role.eks_nodes.arn
+  subnet_ids      = aws_subnet.private[*].id
+
+  instance_types = [var.node_instance_type]
+
+  scaling_config {
+    desired_size = var.node_count
+    max_size     = var.node_max_count
+    min_size     = var.node_min_count
+  }
+
+  update_config {
+    max_unavailable = 1
+  }
+
+  tags = var.tags
+
+  depends_on = [
+    aws_iam_role_policy_attachment.eks_worker_node_policy,
+    aws_iam_role_policy_attachment.eks_cni_policy,
+    aws_iam_role_policy_attachment.eks_ecr_readonly,
+  ]
+}
+
+# ─── External-DNS IRSA ───────────────────────────────────────────────
+# Allows external-dns to manage Route53 records for app ingresses.
+
+data "aws_route53_zone" "main" {
+  name         = var.domain
+  private_zone = false
+}
+
+data "aws_iam_policy_document" "external_dns_assume_role" {
+  statement {
+    effect = "Allow"
+
+    principals {
+      type        = "Federated"
+      identifiers = [aws_iam_openid_connect_provider.eks.arn]
+    }
+
+    actions = ["sts:AssumeRoleWithWebIdentity"]
+
+    condition {
+      test     = "StringEquals"
+      variable = "${replace(aws_iam_openid_connect_provider.eks.url, "https://", "")}:sub"
+      values   = ["system:serviceaccount:external-dns:external-dns"]
+    }
+
+    condition {
+      test     = "StringEquals"
+      variable = "${replace(aws_iam_openid_connect_provider.eks.url, "https://", "")}:aud"
+      values   = ["sts.amazonaws.com"]
+    }
+  }
+}
+
+resource "aws_iam_role" "external_dns_irsa" {
+  name_prefix        = "${var.prefix}-external-dns-irsa-"
+  assume_role_policy = data.aws_iam_policy_document.external_dns_assume_role.json
+
+  tags = var.tags
+}
+
+data "aws_iam_policy_document" "external_dns_route53" {
+  statement {
+    effect    = "Allow"
+    actions   = ["route53:ChangeResourceRecordSets"]
+    resources = ["arn:aws:route53:::hostedzone/${data.aws_route53_zone.main.zone_id}"]
+  }
+
+  statement {
+    effect  = "Allow"
+    actions = ["route53:ListHostedZones", "route53:ListResourceRecordSets", "route53:ListTagsForResource"]
+    resources = ["*"]
+  }
+}
+
+resource "aws_iam_role_policy" "external_dns_route53" {
+  name_prefix = "${var.prefix}-external-dns-route53-"
+  role        = aws_iam_role.external_dns_irsa.id
+  policy      = data.aws_iam_policy_document.external_dns_route53.json
+}

.tofu/platforms/eks/workload/outputs.tf

@@ -0,0 +1,3 @@
+output "cluster_name"              { value = aws_eks_cluster.main.name }
+output "aws_region"                { value = var.region }
+output "external_dns_irsa_role_arn" { value = aws_iam_role.external_dns_irsa.arn }

.tofu/platforms/eks/workload/providers.tf

@@ -0,0 +1,24 @@
+terraform {
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+    tls = {
+      source  = "hashicorp/tls"
+      version = "~> 4.0"
+    }
+  }
+}
+
+# Authentication: set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_SESSION_TOKEN
+# or configure an AWS profile: export AWS_PROFILE=clst
+provider "aws" {
+  region = var.region
+}
+
+variable "region" {
+  description = "AWS region for the workload environment"
+  type        = string
+  default     = "eu-west-1"
+}

.tofu/platforms/gke/dev/main.tf

@@ -0,0 +1,17 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  project_id = var.project_id
+  region     = var.region
+  prefix     = "clst-dev"
+
+  # GKE — small dev nodes
+  node_machine_type   = "e2-standard-2"
+  node_count          = 2
+  deletion_protection = false
+
+  labels = {
+    environment = "dev"
+    managed-by  = "tofu"
+  }
+}

.tofu/platforms/gke/dev/outputs.tf

@@ -0,0 +1,3 @@
+output "cluster_name" { value = module.cluster.cluster_name }
+output "project_id"   { value = module.cluster.project_id }
+output "region"       { value = module.cluster.region }

.tofu/platforms/gke/dev/providers.tf

@@ -0,0 +1,26 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "~> 6.0"
+    }
+  }
+}
+
+# Authentication: use Application Default Credentials (gcloud auth application-default login)
+# or set GOOGLE_APPLICATION_CREDENTIALS to a service account key file.
+provider "google" {
+  project = var.project_id
+  region  = var.region
+}
+
+variable "project_id" {
+  description = "GCP project ID for the dev environment"
+  type        = string
+}
+
+variable "region" {
+  description = "GCP region"
+  type        = string
+  default     = "europe-west4"
+}

.tofu/platforms/gke/modules/cluster/main.tf

@@ -0,0 +1,115 @@
+# ─── Required APIs ────────────────────────────────────────────────────
+
+resource "google_project_service" "compute" {
+  project            = var.project_id
+  service            = "compute.googleapis.com"
+  disable_on_destroy = false
+}
+
+resource "google_project_service" "container" {
+  project            = var.project_id
+  service            = "container.googleapis.com"
+  disable_on_destroy = false
+}
+
+# ─── Networking ───────────────────────────────────────────────────────
+
+resource "google_compute_network" "main" {
+  project                 = var.project_id
+  name                    = "${var.prefix}-vpc"
+  auto_create_subnetworks = false
+
+  depends_on = [google_project_service.compute]
+}
+
+resource "google_compute_subnetwork" "main" {
+  project       = var.project_id
+  name          = "${var.prefix}-subnet"
+  ip_cidr_range = "10.100.0.0/22"
+  region        = var.region
+  network       = google_compute_network.main.id
+
+  # Secondary ranges required for GKE VPC-native cluster
+  secondary_ip_range {
+    range_name    = "pods"
+    ip_cidr_range = "10.200.0.0/14" # /14 = ~262k pod IPs
+  }
+
+  secondary_ip_range {
+    range_name    = "services"
+    ip_cidr_range = "10.204.0.0/20" # /20 = ~4k service IPs
+  }
+}
+
+# ─── GKE Cluster ──────────────────────────────────────────────────────
+#
+# Regional cluster (3 control-plane replicas) for HA.
+# Workload Identity enabled — allows K8s service accounts to impersonate
+# Google Service Accounts for keyless access to GCP services.
+
+resource "google_container_cluster" "main" {
+  project  = var.project_id
+  name     = "${var.prefix}-gke"
+  location = var.region # regional cluster
+
+  network    = google_compute_network.main.id
+  subnetwork = google_compute_subnetwork.main.id
+
+  # VPC-native cluster with alias IP ranges
+  ip_allocation_policy {
+    cluster_secondary_range_name  = "pods"
+    services_secondary_range_name = "services"
+  }
+
+  # Workload Identity pool — enables OIDC token projection for pods
+  workload_identity_config {
+    workload_pool = "${var.project_id}.svc.id.goog"
+  }
+
+  # Remove default node pool — we manage our own below
+  remove_default_node_pool = true
+  initial_node_count       = 1
+
+  deletion_protection = var.deletion_protection
+
+  dynamic "release_channel" {
+    for_each = var.kubernetes_version == null ? [1] : []
+    content {
+      channel = "STABLE"
+    }
+  }
+
+  resource_labels = var.labels
+
+  depends_on = [google_project_service.container]
+}
+
+resource "google_container_node_pool" "main" {
+  project    = var.project_id
+  name       = "${var.prefix}-nodes"
+  location   = var.region
+  cluster    = google_container_cluster.main.name
+  node_count = var.node_count
+
+  node_config {
+    machine_type = var.node_machine_type
+
+    # GKE_METADATA mode is required for Workload Identity
+    workload_metadata_config {
+      mode = "GKE_METADATA"
+    }
+
+    oauth_scopes = [
+      "https://www.googleapis.com/auth/cloud-platform",
+    ]
+
+    labels = merge(var.labels, {
+      role = "worker"
+    })
+  }
+
+  management {
+    auto_repair  = true
+    auto_upgrade = true
+  }
+}

.tofu/platforms/gke/modules/cluster/outputs.tf

@@ -0,0 +1,16 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_name" {
+  description = "GKE cluster name"
+  value       = google_container_cluster.main.name
+}
+
+output "project_id" {
+  description = "GCP project ID"
+  value       = var.project_id
+}
+
+output "region" {
+  description = "GCP region"
+  value       = var.region
+}

.tofu/platforms/gke/modules/cluster/providers.tf

@@ -0,0 +1,8 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "~> 6.0"
+    }
+  }
+}

.tofu/platforms/gke/modules/cluster/variables.tf

@@ -0,0 +1,48 @@
+# ─── Project / Region ────────────────────────────────────────────────
+
+variable "project_id" {
+  description = "GCP project ID"
+  type        = string
+}
+
+variable "region" {
+  description = "GCP region (e.g., europe-west4, europe-west1)"
+  type        = string
+}
+
+variable "prefix" {
+  description = "Prefix for resource names (e.g., clst-dev)"
+  type        = string
+}
+
+# ─── GKE Cluster ─────────────────────────────────────────────────────
+
+variable "node_machine_type" {
+  description = "GKE node machine type (e.g., e2-standard-2, e2-standard-4)"
+  type        = string
+}
+
+variable "node_count" {
+  description = "Number of nodes per zone (regional cluster spawns nodes in each zone)"
+  type        = number
+}
+
+variable "kubernetes_version" {
+  description = "GKE Kubernetes version channel (null = STABLE release channel)"
+  type        = string
+  default     = null
+}
+
+variable "deletion_protection" {
+  description = "Prevent cluster deletion (set true for production)"
+  type        = bool
+  default     = false
+}
+
+# ─── Labels ──────────────────────────────────────────────────────────
+
+variable "labels" {
+  description = "Labels applied to all resources"
+  type        = map(string)
+  default     = {}
+}

.tofu/platforms/gke/prod/main.tf

@@ -0,0 +1,17 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  project_id = var.project_id
+  region     = var.region
+  prefix     = "clst"
+
+  # GKE — general-purpose nodes for production
+  node_machine_type   = "e2-standard-4"
+  node_count          = 3
+  deletion_protection = true
+
+  labels = {
+    environment = "prod"
+    managed-by  = "tofu"
+  }
+}

.tofu/platforms/gke/prod/outputs.tf

@@ -0,0 +1,3 @@
+output "cluster_name" { value = module.cluster.cluster_name }
+output "project_id"   { value = module.cluster.project_id }
+output "region"       { value = module.cluster.region }

.tofu/platforms/gke/prod/providers.tf

@@ -0,0 +1,24 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "~> 6.0"
+    }
+  }
+}
+
+provider "google" {
+  project = var.project_id
+  region  = var.region
+}
+
+variable "project_id" {
+  description = "GCP project ID for the prod environment"
+  type        = string
+}
+
+variable "region" {
+  description = "GCP region"
+  type        = string
+  default     = "europe-west1"
+}

.tofu/platforms/gke/workload/main.tf

@@ -0,0 +1,194 @@
+# =============================================================================
+# GCP Workload Cluster
+# =============================================================================
+# A lean GKE cluster for running application workloads. No managed data
+# services — those live on the platform cluster. ArgoCD (on the platform
+# cluster) deploys apps to this cluster via the app-of-apps pattern.
+#
+# Platform components deployed by deploy-workload.sh:
+#   nginx-ingress, cert-manager, external-dns, external-secrets, alloy
+#
+# Usage:
+#   tofu init && tofu plan && tofu apply
+#   ./sync-tofu-outputs.sh --env gcp-workload
+#   ./deploy-workload.sh --env gcp-workload
+# =============================================================================
+
+variable "prefix" {
+  description = "Prefix for resource names (e.g., clst-workload)"
+  type        = string
+  default     = "clst-workload"
+}
+
+variable "node_machine_type" {
+  description = "GKE node machine type"
+  type        = string
+  default     = "e2-standard-2"
+}
+
+variable "node_count" {
+  description = "Number of nodes per zone"
+  type        = number
+  default     = 1
+}
+
+variable "kubernetes_version" {
+  description = "GKE Kubernetes version (null = STABLE release channel)"
+  type        = string
+  default     = null
+}
+
+variable "deletion_protection" {
+  description = "Prevent cluster deletion"
+  type        = bool
+  default     = false
+}
+
+variable "labels" {
+  description = "Labels applied to all resources"
+  type        = map(string)
+  default = {
+    environment = "workload"
+    managed-by  = "tofu"
+  }
+}
+
+# ─── Required APIs ────────────────────────────────────────────────────
+
+resource "google_project_service" "compute" {
+  project            = var.project_id
+  service            = "compute.googleapis.com"
+  disable_on_destroy = false
+}
+
+resource "google_project_service" "container" {
+  project            = var.project_id
+  service            = "container.googleapis.com"
+  disable_on_destroy = false
+}
+
+resource "google_project_service" "iam" {
+  project            = var.project_id
+  service            = "iam.googleapis.com"
+  disable_on_destroy = false
+}
+
+resource "google_project_service" "dns" {
+  project            = var.project_id
+  service            = "dns.googleapis.com"
+  disable_on_destroy = false
+}
+
+# ─── Networking ───────────────────────────────────────────────────────
+
+resource "google_compute_network" "main" {
+  project                 = var.project_id
+  name                    = "${var.prefix}-vpc"
+  auto_create_subnetworks = false
+
+  depends_on = [google_project_service.compute]
+}
+
+resource "google_compute_subnetwork" "main" {
+  project       = var.project_id
+  name          = "${var.prefix}-subnet"
+  ip_cidr_range = "10.110.0.0/22"
+  region        = var.region
+  network       = google_compute_network.main.id
+
+  secondary_ip_range {
+    range_name    = "pods"
+    ip_cidr_range = "10.210.0.0/14"
+  }
+
+  secondary_ip_range {
+    range_name    = "services"
+    ip_cidr_range = "10.214.0.0/20"
+  }
+}
+
+# ─── GKE Cluster ──────────────────────────────────────────────────────
+
+resource "google_container_cluster" "main" {
+  project  = var.project_id
+  name     = "${var.prefix}-gke"
+  location = var.region
+
+  network    = google_compute_network.main.id
+  subnetwork = google_compute_subnetwork.main.id
+
+  ip_allocation_policy {
+    cluster_secondary_range_name  = "pods"
+    services_secondary_range_name = "services"
+  }
+
+  workload_identity_config {
+    workload_pool = "${var.project_id}.svc.id.goog"
+  }
+
+  remove_default_node_pool = true
+  initial_node_count       = 1
+
+  deletion_protection = var.deletion_protection
+
+  dynamic "release_channel" {
+    for_each = var.kubernetes_version == null ? [1] : []
+    content {
+      channel = "STABLE"
+    }
+  }
+
+  resource_labels = var.labels
+
+  depends_on = [google_project_service.container]
+}
+
+resource "google_container_node_pool" "main" {
+  project    = var.project_id
+  name       = "${var.prefix}-nodes"
+  location   = var.region
+  cluster    = google_container_cluster.main.name
+  node_count = var.node_count
+
+  node_config {
+    machine_type = var.node_machine_type
+
+    workload_metadata_config {
+      mode = "GKE_METADATA"
+    }
+
+    oauth_scopes = [
+      "https://www.googleapis.com/auth/cloud-platform",
+    ]
+
+    labels = merge(var.labels, { role = "worker" })
+  }
+
+  management {
+    auto_repair  = true
+    auto_upgrade = true
+  }
+}
+
+# ─── External-DNS Workload Identity ──────────────────────────────────
+# Allows external-dns to manage Cloud DNS records for app ingresses.
+
+resource "google_service_account" "external_dns" {
+  project      = var.project_id
+  account_id   = "${var.prefix}-external-dns"
+  display_name = "External-DNS Service Account (Workload Identity)"
+
+  depends_on = [google_project_service.iam]
+}
+
+resource "google_project_iam_member" "external_dns_dns_admin" {
+  project = var.project_id
+  role    = "roles/dns.admin"
+  member  = "serviceAccount:${google_service_account.external_dns.email}"
+}
+
+resource "google_service_account_iam_member" "external_dns_workload_identity" {
+  service_account_id = google_service_account.external_dns.name
+  role               = "roles/iam.workloadIdentityUser"
+  member             = "serviceAccount:${var.project_id}.svc.id.goog[external-dns/external-dns]"
+}

.tofu/platforms/gke/workload/outputs.tf

@@ -0,0 +1,4 @@
+output "cluster_name"           { value = google_container_cluster.main.name }
+output "project_id"             { value = var.project_id }
+output "region"                 { value = var.region }
+output "external_dns_gsa_email" { value = google_service_account.external_dns.email }

.tofu/platforms/gke/workload/providers.tf

@@ -0,0 +1,26 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "~> 6.0"
+    }
+  }
+}
+
+# Authentication: use Application Default Credentials (gcloud auth application-default login)
+# or set GOOGLE_APPLICATION_CREDENTIALS to a service account key file.
+provider "google" {
+  project = var.project_id
+  region  = var.region
+}
+
+variable "project_id" {
+  description = "GCP project ID for the workload environment"
+  type        = string
+}
+
+variable "region" {
+  description = "GCP region"
+  type        = string
+  default     = "europe-west4"
+}

.tofu/platforms/upc/dev/main.tf

@@ -0,0 +1,14 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  prefix       = "clst-dev"
+  zone         = "no-svg1"
+  node_plan    = "DEV-1xCPU-2GB"
+  node_count   = 2
+  network_cidr = "10.100.0.0/24"
+
+  tags = {
+    Environment = "dev"
+    ManagedBy   = "tofu"
+  }
+}

.tofu/platforms/upc/dev/outputs.tf

@@ -0,0 +1,13 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_id" {
+  value = module.cluster.cluster_id
+}
+
+output "cluster_name" {
+  value = module.cluster.cluster_name
+}
+
+output "zone" {
+  value = module.cluster.zone
+}

.tofu/platforms/upc/dev/providers.tf

@@ -0,0 +1,14 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    upcloud = {
+      source  = "UpCloudLtd/upcloud"
+      version = "~> 5.0"
+    }
+  }
+}
+
+provider "upcloud" {
+  # Set via environment variables: UPCLOUD_USERNAME, UPCLOUD_PASSWORD
+}

.tofu/platforms/upc/modules/cluster/main.tf

@@ -0,0 +1,56 @@
+# Router for the private network
+resource "upcloud_router" "kubernetes" {
+  name = "${var.prefix}-${var.cluster_name}-router"
+}
+
+# Gateway for internet connectivity
+resource "upcloud_gateway" "kubernetes" {
+  name     = "${var.prefix}-${var.cluster_name}-gateway"
+  zone     = var.zone
+  features = ["nat"]
+  router {
+    id = upcloud_router.kubernetes.id
+  }
+}
+
+# Private network for the Kubernetes cluster
+resource "upcloud_network" "kubernetes" {
+  name   = "${var.prefix}-${var.cluster_name}-network"
+  zone   = var.zone
+  router = upcloud_router.kubernetes.id
+
+  ip_network {
+    address            = var.network_cidr
+    dhcp               = true
+    dhcp_default_route = true
+    family             = "IPv4"
+    gateway            = cidrhost(var.network_cidr, 1)
+  }
+
+  depends_on = [upcloud_gateway.kubernetes]
+}
+
+# Kubernetes cluster
+resource "upcloud_kubernetes_cluster" "main" {
+  name                    = "${var.prefix}-${var.cluster_name}"
+  zone                    = var.zone
+  network                 = upcloud_network.kubernetes.id
+  control_plane_ip_filter = var.control_plane_ip_filter
+
+  private_node_groups = true
+}
+
+# Node group for worker nodes
+resource "upcloud_kubernetes_node_group" "workers" {
+  cluster       = upcloud_kubernetes_cluster.main.id
+  name          = "${var.prefix}-${var.cluster_name}-workers"
+  node_count    = var.node_count
+  plan          = var.node_plan
+  anti_affinity = var.node_count > 1
+  labels = {
+    prefix  = var.prefix
+    cluster = var.cluster_name
+    role    = "worker"
+    env     = lookup(var.tags, "Environment", "dev")
+  }
+}

.tofu/platforms/upc/modules/cluster/outputs.tf

@@ -0,0 +1,31 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_id" {
+  description = "The ID of the Kubernetes cluster"
+  value       = upcloud_kubernetes_cluster.main.id
+}
+
+output "cluster_name" {
+  description = "The name of the Kubernetes cluster"
+  value       = upcloud_kubernetes_cluster.main.name
+}
+
+output "network_id" {
+  description = "The ID of the private network"
+  value       = upcloud_network.kubernetes.id
+}
+
+output "network_cidr" {
+  description = "The CIDR block of the private network"
+  value       = var.network_cidr
+}
+
+output "kubernetes_version" {
+  description = "The Kubernetes version of the cluster"
+  value       = upcloud_kubernetes_cluster.main.version
+}
+
+output "zone" {
+  description = "The zone where the cluster is deployed"
+  value       = var.zone
+}

.tofu/platforms/upc/modules/cluster/providers.tf

@@ -0,0 +1,8 @@
+terraform {
+  required_providers {
+    upcloud = {
+      source  = "UpCloudLtd/upcloud"
+      version = "~> 5.0"
+    }
+  }
+}

.tofu/platforms/upc/modules/cluster/variables.tf

@@ -0,0 +1,44 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+variable "prefix" {
+  description = "Prefix for resource names"
+  type        = string
+}
+
+variable "cluster_name" {
+  description = "Name of the Kubernetes cluster"
+  type        = string
+  default     = "main"
+}
+
+variable "zone" {
+  description = "UpCloud zone"
+  type        = string
+}
+
+variable "node_plan" {
+  description = "UpCloud server plan for worker nodes"
+  type        = string
+}
+
+variable "node_count" {
+  description = "Number of worker nodes"
+  type        = number
+}
+
+variable "network_cidr" {
+  description = "CIDR block for the private network"
+  type        = string
+  default     = "10.100.0.0/24"
+}
+
+variable "control_plane_ip_filter" {
+  description = "CIDRs allowed to access the K8s API"
+  type        = list(string)
+  default     = ["0.0.0.0/0"]
+}
+
+variable "tags" {
+  description = "Labels to apply to resources"
+  type        = map(string)
+}

.tofu/platforms/upc/prod/main.tf

@@ -0,0 +1,16 @@
+module "cluster" {
+  source = "../modules/cluster"
+
+  prefix       = "clst"
+  zone         = "de-fra1"
+  node_plan    = "4xCPU-8GB"
+  node_count   = 3
+  network_cidr = "10.100.0.0/24"
+
+  control_plane_ip_filter = ["0.0.0.0/0"] # TODO: restrict to known CIDRs
+
+  tags = {
+    Environment = "prod"
+    ManagedBy   = "tofu"
+  }
+}

.tofu/platforms/upc/prod/outputs.tf

@@ -0,0 +1,13 @@
+# ─── Cluster ─────────────────────────────────────────────────────────
+
+output "cluster_id" {
+  value = module.cluster.cluster_id
+}
+
+output "cluster_name" {
+  value = module.cluster.cluster_name
+}
+
+output "zone" {
+  value = module.cluster.zone
+}

.tofu/platforms/upc/prod/providers.tf

@@ -0,0 +1,14 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    upcloud = {
+      source  = "UpCloudLtd/upcloud"
+      version = "~> 5.0"
+    }
+  }
+}
+
+provider "upcloud" {
+  # Set via environment variables: UPCLOUD_USERNAME, UPCLOUD_PASSWORD
+}

.tofu/platforms/upc/workload/main.tf

@@ -0,0 +1,116 @@
+# =============================================================================
+# UpCloud Workload Cluster
+# =============================================================================
+# A lean UCS cluster for running application workloads. No managed data
+# services — those live on the platform cluster. ArgoCD (on the platform
+# cluster) deploys apps to this cluster via the app-of-apps pattern.
+#
+# Platform components deployed by deploy-workload.sh:
+#   nginx-ingress, cert-manager, external-dns, external-secrets, alloy
+#
+# Usage:
+#   tofu init && tofu plan && tofu apply
+#   ./sync-tofu-outputs.sh --env upcloud-workload
+#   ./deploy-workload.sh --env upcloud-workload
+# =============================================================================
+
+variable "prefix" {
+  description = "Prefix for resource names"
+  type        = string
+  default     = "clst-workload"
+}
+
+variable "zone" {
+  description = "UpCloud zone"
+  type        = string
+  default     = "fi-hel1"
+}
+
+variable "node_plan" {
+  description = "UpCloud server plan for worker nodes"
+  type        = string
+  default     = "2xCPU-4GB"
+}
+
+variable "node_count" {
+  description = "Number of worker nodes"
+  type        = number
+  default     = 2
+}
+
+variable "network_cidr" {
+  description = "CIDR block for the private network"
+  type        = string
+  default     = "10.110.0.0/24"
+}
+
+variable "control_plane_ip_filter" {
+  description = "CIDRs allowed to access the K8s API"
+  type        = list(string)
+  default     = ["0.0.0.0/0"]
+}
+
+variable "tags" {
+  description = "Labels to apply to resources"
+  type        = map(string)
+  default = {
+    Environment = "workload"
+    ManagedBy   = "tofu"
+  }
+}
+
+# ─── Networking ───────────────────────────────────────────────────────
+
+resource "upcloud_router" "kubernetes" {
+  name = "${var.prefix}-workload-router"
+}
+
+resource "upcloud_gateway" "kubernetes" {
+  name     = "${var.prefix}-workload-gateway"
+  zone     = var.zone
+  features = ["nat"]
+  router {
+    id = upcloud_router.kubernetes.id
+  }
+}
+
+resource "upcloud_network" "kubernetes" {
+  name   = "${var.prefix}-workload-network"
+  zone   = var.zone
+  router = upcloud_router.kubernetes.id
+
+  ip_network {
+    address            = var.network_cidr
+    dhcp               = true
+    dhcp_default_route = true
+    family             = "IPv4"
+    gateway            = cidrhost(var.network_cidr, 1)
+  }
+
+  depends_on = [upcloud_gateway.kubernetes]
+}
+
+# ─── Kubernetes Cluster ───────────────────────────────────────────────
+
+resource "upcloud_kubernetes_cluster" "main" {
+  name                    = "${var.prefix}-workload"
+  zone                    = var.zone
+  network                 = upcloud_network.kubernetes.id
+  control_plane_ip_filter = var.control_plane_ip_filter
+
+  private_node_groups = true
+}
+
+resource "upcloud_kubernetes_node_group" "workers" {
+  cluster       = upcloud_kubernetes_cluster.main.id
+  name          = "${var.prefix}-workload-workers"
+  node_count    = var.node_count
+  plan          = var.node_plan
+  anti_affinity = var.node_count > 1
+  labels = {
+    prefix  = var.prefix
+    cluster = "workload"
+    role    = "worker"
+    env     = lookup(var.tags, "Environment", "workload")
+  }
+}

.tofu/platforms/upc/workload/outputs.tf

@@ -0,0 +1,3 @@
+output "cluster_name" { value = upcloud_kubernetes_cluster.main.name }
+output "cluster_id"   { value = upcloud_kubernetes_cluster.main.id }
+output "zone"         { value = var.zone }

.tofu/platforms/upc/workload/providers.tf

@@ -0,0 +1,14 @@
+terraform {
+  required_version = ">= 1.0"
+
+  required_providers {
+    upcloud = {
+      source  = "UpCloudLtd/upcloud"
+      version = "~> 5.0"
+    }
+  }
+}
+
+provider "upcloud" {
+  # Set via environment variables: UPCLOUD_USERNAME, UPCLOUD_PASSWORD
+}

.tofu/scripts/get-kubeconfig.sh

@@ -0,0 +1,66 @@
+#!/bin/bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TOFU_ROOT="$(dirname "$SCRIPT_DIR")"
+PROJECT_ROOT="$(dirname "$TOFU_ROOT")"
+
+CLUSTER="${1:?Usage: $0 <cluster> (e.g., aks-dev, eks-prod)}"
+PLATFORM="${CLUSTER%%-*}"
+ENV="${CLUSTER#*-}"
+
+KUBECONFIG_FILE="$PROJECT_ROOT/private/$CLUSTER/kubeconfig"
+
+if [[ -f "$KUBECONFIG_FILE" ]]; then
+  echo "Kubeconfig already exists: $KUBECONFIG_FILE"
+  echo ""
+  echo "  export KUBECONFIG=$KUBECONFIG_FILE"
+else
+  echo "No cached kubeconfig. Fetching from platform..."
+
+  # Load platform credentials
+  ENV_FILE="$TOFU_ROOT/configs/$PLATFORM.env"
+  if [[ -f "$ENV_FILE" ]]; then
+    set -a; source "$ENV_FILE"; set +a
+  fi
+
+  TOFU_DIR="$TOFU_ROOT/platforms/$PLATFORM/$ENV"
+  mkdir -p "$(dirname "$KUBECONFIG_FILE")"
+
+  case "$PLATFORM" in
+    aks)
+      cd "$TOFU_DIR"
+      RG=$(tofu output -raw resource_group_name 2>/dev/null || echo "$CLUSTER-rg")
+      NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "$CLUSTER")
+      az aks get-credentials --resource-group "$RG" --name "$NAME" --file "$KUBECONFIG_FILE" --overwrite-existing
+      ;;
+    eks)
+      cd "$TOFU_DIR"
+      NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "$CLUSTER")
+      REGION=$(tofu output -raw aws_region 2>/dev/null || echo "${AWS_REGION:-eu-west-1}")
+      aws eks update-kubeconfig --name "$NAME" --region "$REGION" --kubeconfig "$KUBECONFIG_FILE"
+      ;;
+    gke)
+      cd "$TOFU_DIR"
+      NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "$CLUSTER")
+      REGION=$(tofu output -raw region 2>/dev/null || echo "${GCP_REGION:-europe-west4}")
+      PROJECT=$(tofu output -raw project_id 2>/dev/null || echo "${GCP_PROJECT_ID:-}")
+      gcloud container clusters get-credentials "$NAME" --region "$REGION" --project "$PROJECT"
+      cp ~/.kube/config "$KUBECONFIG_FILE"
+      ;;
+    upc)
+      cd "$TOFU_DIR"
+      CLUSTER_ID=$(tofu output -raw cluster_id 2>/dev/null || echo "${UPCLOUD_CLUSTER_ID:-}")
+      upctl kubernetes config "$CLUSTER_ID" > "$KUBECONFIG_FILE"
+      ;;
+    *)
+      echo "Error: unknown platform '$PLATFORM'"
+      exit 1
+      ;;
+  esac
+
+  chmod 600 "$KUBECONFIG_FILE"
+  echo "Kubeconfig saved: $KUBECONFIG_FILE"
+  echo ""
+  echo "  export KUBECONFIG=$KUBECONFIG_FILE"
+fi

.tofu/scripts/setup-cluster.sh

@@ -0,0 +1,246 @@
+#!/bin/bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TOFU_ROOT="$(dirname "$SCRIPT_DIR")"
+PROJECT_ROOT="$(dirname "$TOFU_ROOT")"
+
+# ─── Usage ────────────────────────────────────────────────────────────
+usage() {
+  cat <<EOF
+Usage: $0 <cluster> [options]
+
+  Provision a Kubernetes cluster using OpenTofu.
+  Mirrors bootstrap.sh convention: cluster = <platform>-<env>
+
+  Clusters:   aks-dev | aks-prod | eks-dev | eks-prod
+              gke-dev | gke-prod | upc-dev | upc-prod
+              <platform>-workload (for workload clusters)
+
+  Options:
+    --plan        Plan only, don't apply
+    --destroy     Destroy the cluster (use teardown-cluster.sh instead)
+    --auto        Skip confirmation prompts
+    -h, --help    Show this help
+
+  Examples:
+    $0 aks-dev
+    $0 eks-prod --plan
+    $0 upc-dev --auto
+
+  Prerequisites:
+    - tofu, kubectl, helm installed
+    - Platform credentials in .tofu/configs/<platform>.env
+    - Cluster config in clusters/<cluster>.yaml
+
+  After provisioning, run:
+    ./bootstrap.sh <cluster>
+EOF
+  exit "${1:-0}"
+}
+
+# ─── Parse arguments ──────────────────────────────────────────────────
+CLUSTER=""
+PLAN_ONLY=false
+DESTROY=false
+AUTO_APPROVE=false
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --plan)       PLAN_ONLY=true; shift ;;
+    --destroy)    DESTROY=true; shift ;;
+    --auto)       AUTO_APPROVE=true; shift ;;
+    -h|--help)    usage 0 ;;
+    -*)           echo "Unknown option: $1"; usage 1 ;;
+    *)
+      if [[ -z "$CLUSTER" ]]; then
+        CLUSTER="$1"
+      else
+        echo "Error: unexpected argument '$1'"
+        usage 1
+      fi
+      shift
+      ;;
+  esac
+done
+
+[[ -z "$CLUSTER" ]] && { echo "Error: <cluster> argument required"; usage 1; }
+
+# ─── Map cluster → platform + env ────────────────────────────────────
+PLATFORM="${CLUSTER%%-*}"   # aks-dev → aks
+ENV="${CLUSTER#*-}"         # aks-dev → dev
+
+case "$PLATFORM" in
+  aks|eks|gke|upc) ;;
+  *) echo "Error: unknown platform '$PLATFORM'. Expected: aks, eks, gke, upc"; exit 1 ;;
+esac
+
+TOFU_DIR="$TOFU_ROOT/platforms/$PLATFORM/$ENV"
+if [[ ! -d "$TOFU_DIR" ]]; then
+  echo "Error: tofu directory not found: $TOFU_DIR"
+  echo "Available environments for $PLATFORM:"
+  ls -1 "$TOFU_ROOT/platforms/$PLATFORM/" 2>/dev/null | grep -v modules || echo "  (none)"
+  exit 1
+fi
+
+echo "========================================="
+echo "  Kubernetes Cluster Setup"
+echo "========================================="
+echo ""
+echo "  Cluster:   $CLUSTER"
+echo "  Platform:  $PLATFORM"
+echo "  Env:       $ENV"
+echo "  Tofu dir:  $TOFU_DIR"
+echo ""
+
+# ─── Prerequisites ────────────────────────────────────────────────────
+echo "=== Checking Prerequisites ==="
+command -v tofu    >/dev/null 2>&1 || { echo "Error: tofu is not installed."; exit 1; }
+command -v kubectl >/dev/null 2>&1 || { echo "Error: kubectl is not installed."; exit 1; }
+command -v helm    >/dev/null 2>&1 || { echo "Error: helm is not installed."; exit 1; }
+echo "  tofu, kubectl, helm: OK"
+
+# ─── Load platform credentials ────────────────────────────────────────
+ENV_FILE="$TOFU_ROOT/configs/$PLATFORM.env"
+if [[ -f "$ENV_FILE" ]]; then
+  echo "  Loading credentials from configs/$PLATFORM.env"
+  set -a
+  # shellcheck disable=SC1090
+  source "$ENV_FILE"
+  set +a
+else
+  echo "  Warning: $ENV_FILE not found — using existing environment/CLI auth"
+  echo "  Copy configs/$PLATFORM.env.example → configs/$PLATFORM.env to configure"
+fi
+
+# ─── Load cluster config (if exists) ──────────────────────────────────
+CLUSTER_CONFIG="$PROJECT_ROOT/clusters/$CLUSTER.yaml"
+if [[ -f "$CLUSTER_CONFIG" ]]; then
+  echo "  Loading cluster config from clusters/$CLUSTER.yaml"
+  if command -v yq >/dev/null 2>&1; then
+    eval "$(yq -r 'to_entries[] | "export CLUSTER_\(.key)=\"\(.value)\""' "$CLUSTER_CONFIG")"
+    echo "  Cluster name: ${CLUSTER_clusterName:-$CLUSTER}"
+  else
+    echo "  Warning: yq not installed — cluster config not loaded"
+  fi
+else
+  echo "  Warning: $CLUSTER_CONFIG not found — using defaults"
+fi
+echo ""
+
+# ─── Run OpenTofu ─────────────────────────────────────────────────────
+cd "$TOFU_DIR"
+
+echo "=== Initializing OpenTofu ==="
+tofu init
+
+echo ""
+if $DESTROY; then
+  echo "=== Planning Destruction ==="
+  tofu plan -destroy -out=tfplan
+
+  if ! $AUTO_APPROVE; then
+    echo ""
+    read -rp "DESTROY cluster $CLUSTER? This is irreversible. (yes/no) " REPLY
+    [[ "$REPLY" == "yes" ]] || { echo "Cancelled."; exit 1; }
+  fi
+
+  echo "Destroying infrastructure..."
+  tofu apply tfplan
+  echo ""
+  echo "=== Cluster $CLUSTER Destroyed ==="
+
+elif $PLAN_ONLY; then
+  echo "=== Planning Infrastructure ==="
+  tofu plan
+  echo ""
+  echo "=== Plan complete (--plan mode, no changes applied) ==="
+
+else
+  echo "=== Planning Infrastructure ==="
+  tofu plan -out=tfplan
+
+  if ! $AUTO_APPROVE; then
+    echo ""
+    read -rp "Apply this plan for $CLUSTER? (y/n) " -n 1 REPLY
+    echo
+    [[ "$REPLY" =~ ^[Yy]$ ]] || { echo "Cancelled."; exit 1; }
+  fi
+
+  echo "Applying infrastructure..."
+  tofu apply tfplan
+
+  # ─── Save kubeconfig ──────────────────────────────────────────────
+  KUBECONFIG_DIR="$PROJECT_ROOT/private/$CLUSTER"
+  mkdir -p "$KUBECONFIG_DIR"
+  KUBECONFIG_FILE="$KUBECONFIG_DIR/kubeconfig"
+
+  echo ""
+  echo "=== Saving Kubeconfig ==="
+
+  case "$PLATFORM" in
+    aks)
+      if tofu output -raw kubeconfig > "$KUBECONFIG_FILE" 2>/dev/null; then
+        echo "  Saved from tofu output"
+      else
+        echo "  Fetching from Azure CLI..."
+        RG=$(tofu output -raw resource_group_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}-rg")
+        NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}")
+        az aks get-credentials --resource-group "$RG" --name "$NAME" --file "$KUBECONFIG_FILE" --overwrite-existing
+      fi
+      ;;
+    eks)
+      NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}")
+      REGION=$(tofu output -raw aws_region 2>/dev/null || echo "${AWS_REGION:-eu-west-1}")
+      aws eks update-kubeconfig --name "$NAME" --region "$REGION" --kubeconfig "$KUBECONFIG_FILE"
+      ;;
+    gke)
+      NAME=$(tofu output -raw cluster_name 2>/dev/null || echo "${CLUSTER_clusterName:-$CLUSTER}")
+      REGION=$(tofu output -raw region 2>/dev/null || echo "${GCP_REGION:-europe-west4}")
+      PROJECT=$(tofu output -raw project_id 2>/dev/null || echo "${GCP_PROJECT_ID:-}")
+      gcloud container clusters get-credentials "$NAME" --region "$REGION" --project "$PROJECT" 2>/dev/null \
+        && cp ~/.kube/config "$KUBECONFIG_FILE" \
+        || echo "  Warning: could not fetch kubeconfig via gcloud"
+      ;;
+    upc)
+      if tofu output -raw kubeconfig > "$KUBECONFIG_FILE" 2>/dev/null; then
+        echo "  Saved from tofu output"
+      else
+        CLUSTER_ID=$(tofu output -raw cluster_id 2>/dev/null || echo "${UPCLOUD_CLUSTER_ID:-}")
+        if [[ -n "$CLUSTER_ID" ]]; then
+          upctl kubernetes config "$CLUSTER_ID" > "$KUBECONFIG_FILE"
+        else
+          echo "  Warning: could not determine cluster ID for kubeconfig"
+        fi
+      fi
+      ;;
+  esac
+
+  if [[ -f "$KUBECONFIG_FILE" ]]; then
+    chmod 600 "$KUBECONFIG_FILE"
+    echo "  Kubeconfig: $KUBECONFIG_FILE"
+  fi
+
+  # ─── Wait for nodes ──────────────────────────────────────────────
+  echo ""
+  echo "=== Waiting for Cluster Nodes ==="
+  export KUBECONFIG="$KUBECONFIG_FILE"
+  if kubectl wait --for=condition=Ready nodes --all --timeout=300s 2>/dev/null; then
+    echo "  All nodes ready"
+  else
+    echo "  Warning: nodes not ready within timeout — check cluster status"
+  fi
+
+  # ─── Summary ─────────────────────────────────────────────────────
+  echo ""
+  echo "========================================="
+  echo "  Cluster $CLUSTER Provisioned"
+  echo "========================================="
+  echo ""
+  echo "  Kubeconfig: $KUBECONFIG_FILE"
+  echo ""
+  echo "  Next steps:"
+  echo "    export KUBECONFIG=$KUBECONFIG_FILE"
+  echo "    ./bootstrap.sh $CLUSTER"
+  echo ""
+fi

.tofu/scripts/teardown-cluster.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# Delegate to setup-cluster.sh with --destroy flag
+exec "$SCRIPT_DIR/setup-cluster.sh" "$@" --destroy

README.md

@@ -1,9 +1,9 @@
 # Kubernetes Cluster - GitOps Configuration
 
-> **Kubernetes cluster bootstrapping and GitOps configuration repository** using ArgoCD for UpCloud Managed Kubernetes
+> **Kubernetes cluster bootstrapping and GitOps configuration repository** using ArgoCD for multi-cloud Kubernetes (UpCloud, AWS EKS, Azure AKS, GCP GKE)
 
 [![GitOps](https://img.shields.io/badge/GitOps-ArgoCD-blue)](https://argoproj.github.io/cd/)
-[![Kubernetes](https://img.shields.io/badge/Kubernetes-UpCloud-orange)](https://upcloud.com/)
+[![Kubernetes](https://img.shields.io/badge/Kubernetes-Multi--Cloud-orange)]()
 
 ---
 
@@ -57,7 +57,7 @@ This repository contains the complete GitOps configuration for our Kubernetes cl
 
 ### What's Inside
 
-- **Infrastructure Applications**: Traefik, Cert-Manager, Kyverno, Prometheus, Grafana, Loki, Tempo, Sealed Secrets
+- **Infrastructure Applications**: Traefik, Cert-Manager, Kyverno, Prometheus, Grafana, Loki, Tempo, Sealed Secrets, Homepage (platform dashboard)
 - **Business Applications**: MCP10X, MusicMan, Dot-AI Stack, ArgoCD MCP
 - **Policies**: Kyverno security policies for secret management, namespace controls, pod verification
 - **Monitoring**: Full observability stack with metrics, logs, traces, and alerting
@@ -80,35 +80,70 @@ This repository contains the complete GitOps configuration for our Kubernetes cl
 
 ```
 .
-├── bootstrap.sh                # Cluster initialization script
-├── _app-of-apps.yaml          # Root ArgoCD Application (App-of-Apps pattern)
+├── bootstrap.sh                # Cluster initialization (ArgoCD + GitOps)
+├── _app-of-apps-{cluster}.yaml # Root ArgoCD Application (per cluster)
+│
+├── .tofu/                     # Infrastructure provisioning (OpenTofu)
+│   ├── platforms/             # Per-platform IaC (one dir per cloud)
+│   │   ├── aks/               # Azure AKS (modules/ + dev/ + prod/ + workload/)
+│   │   ├── eks/               # AWS EKS
+│   │   ├── gke/               # GCP GKE
+│   │   └── upc/               # UpCloud
+│   ├── configs/               # Platform credentials (git-ignored)
+│   │   └── *.env.example      # Template for each platform
+│   └── scripts/               # Cluster lifecycle scripts
+│       ├── setup-cluster.sh   # Create cluster: ./setup-cluster.sh aks-dev
+│       ├── teardown-cluster.sh
+│       └── get-kubeconfig.sh
+│
+├── clusters/                  # Cluster metadata (domain, trustedIPs, etc.)
 │
 ├── infra/                     # Infrastructure ArgoCD Applications (Kustomize multi-cluster)
-│   ├── base/                  # Base ArgoCD Application manifests (EU defaults)
-│   │   ├── kustomization.yaml
-│   │   ├── traefik-application.yaml
-│   │   ├── keycloak.yaml
-│   │   ├── grafana.yaml
-│   │   ├── gitea.yaml
-│   │   ├── gitea-actions.yaml
-│   │   ├── tempo.yaml
-│   │   ├── renovate.yaml
-│   │   ├── ...                # All other Application manifests
-│   │   └── secrets.yaml
-│   ├── overlays/              # Per-cluster overrides
-│   │   ├── upc-dev/           # UpCloud Dev cluster (uses base as-is)
-│   │   └── upc-prod/         # UpCloud Prod cluster (patches value paths)
+│   ├── base/                  # Base ArgoCD Application manifests (one dir per component)
+│   │   ├── kustomization.yaml # Aggregates all component subdirectories
+│   │   ├── traefik-application/
+│   │   │   ├── kustomization.yaml
+│   │   │   └── traefik-application.yaml
+│   │   ├── keycloak/
+│   │   │   ├── kustomization.yaml
+│   │   │   └── keycloak.yaml
+│   │   ├── grafana/
+│   │   ├── prometheus/
+│   │   ├── ...               # Each component in its own subdirectory
+│   │   └── secrets/
+│   ├── overlays/              # Per-cluster overrides (Kustomize)
+│   │   ├── upc-dev/           # UpCloud Dev — includes all base components
+│   │   ├── upc-prod/         # UpCloud Prod — all components + patches
+│   │   ├── aks-dev/          # Azure AKS Dev — selective components only
+│   │   ├── aks-prod/         # Azure AKS Prod
+│   │   ├── eks-dev/           # AWS EKS Dev
+│   │   ├── eks-prod/         # AWS EKS Prod
+│   │   ├── gke-dev/          # GCP GKE Dev
+│   │   └── gke-prod/         # GCP GKE Prod
 │   ├── dashboards/            # Grafana dashboard ConfigMaps
 │   └── values/                # Helm value overrides
-│       ├── base/              # Shared values (all clusters)
-│       ├── upc-dev/           # UpCloud Dev-specific values
-│       └── upc-prod/         # UpCloud Prod-specific values
+│       ├── base/              # Shared cloud-agnostic values
+│       ├── upc-dev/           # UpCloud Dev (storage, LB, pricing)
+│       ├── upc-prod/         # UpCloud Prod
+│       ├── eks-dev/           # AWS EKS Dev
+│       ├── eks-prod/         # AWS EKS Prod
+│       ├── aks-dev/        # Azure AKS Dev
+│       ├── aks-prod/       # Azure AKS Prod
+│       ├── gke-dev/          # GCP GKE Dev
+│       └── gke-prod/         # GCP GKE Prod
 │
-├── apps/                      # Business Applications
-│   ├── mcp10x.yaml
-│   ├── musicman.yaml
-│   ├── dot-ai-stack.yaml
-│   └── argo-mcp.yaml
+├── apps/                      # Business Applications (Kustomize, same pattern as infra)
+│   ├── base/                  # One subdirectory per app
+│   │   ├── kustomization.yaml
+│   │   ├── musicman/
+│   │   ├── mcp10x/
+│   │   ├── dot-ai-stack/
+│   │   ├── ts-mcp/
+│   │   └── argo-mcp/
+│   └── overlays/              # Per-cluster: cherry-pick or include all
+│       ├── upc-dev/           # All apps
+│       ├── upc-prod/         # All apps + patches
+│       └── aks-dev/          # Selective apps only
 │
 ├── cluster-resources/         # Cluster-wide Kubernetes resources
 │   ├── letsencrypt-issuer.yaml
@@ -343,7 +378,6 @@ kubectl patch application myapp -n argocd \
 | **Fluent-Bit** | Log shipping | `monitoring` | DaemonSet |
 | **OpenCost** | Cost monitoring | `monitoring` | 1 |
 | **Renovate** | Dependency updates | `renovate` | CronJob |
-| **Trivy** | Vulnerability scanning | `trivy-system` | 1 |
 
 **Full specs**: [Technical Reference - Infrastructure Components](docs/REFERENCE.md#infrastructure-components)
 
@@ -361,7 +395,7 @@ kubectl patch application myapp -n argocd \
 ## 📖 Key Concepts
 
 ### App-of-Apps Pattern
-`_app-of-apps.yaml` is the root Application that manages all other Applications in `infra/`. Kustomize overlays in `infra/overlays/{upc-dev,upc-prod}/` render the base Applications with per-cluster patches (e.g., swapping value file paths from `upc-dev` to `upc-prod`).
+`_app-of-apps-{cluster}.yaml` is the root Application that manages all other Applications in `infra/`. Each component in `infra/base/` lives in its own subdirectory (e.g., `infra/base/grafana/`). Overlays can either include **all** components (via `../../base`) or **cherry-pick** specific ones (via `../../base/grafana`, `../../base/prometheus`, etc.). Per-cluster patches swap Helm value file paths. Supported clusters: `upc-dev`, `upc-prod`, `eks-dev`, `eks-prod`, `aks-dev`, `aks-prod`, `gke-dev`, `gke-prod`.
 
 ### Multi-Source Pattern
 Applications reference both:
@@ -458,16 +492,14 @@ Documentation lives in `docs/`. To update:
 ## 📝 Notes
 
 ### Current Environment
-- **Provider**: UpCloud Managed Kubernetes
+- **Provider**: Multi-cloud (UpCloud, AWS EKS, Azure AKS, GCP GKE)
+- **Active clusters**: UpCloud (upc-dev, upc-prod)
 - **Environment**: Production (internal use only)
-- **Clusters**: Multi-cluster (upc-dev, upc-prod) via Kustomize overlays
 - **Auth**: Disabled for ArgoCD (internal access)
-- **Backup**: None (cluster rebuildable via GitOps)
+- **Backup**: Gitea daily backup to S3-compatible storage
 
 ### Known Limitations
-- No automated backups (yet)
 - Secret rotation not automated
-- Multi-cluster limited to upc-dev and upc-prod environments
 - DNS management is manual
 
 **Future improvements**: See [Operations Runbook - Disaster Recovery](docs/OPERATIONS-RUNBOOK.md#disaster-recovery)
@@ -504,7 +536,7 @@ Internal use only. Not for public distribution.
 
 ---
 
-**Last Updated**: 2026-03-16
+**Last Updated**: 2026-04-22
 **Documentation Version**: 1.0.0
 
 **🚀 Ready to get started? Check out the [Documentation Index](docs/README.md)!**

_app-of-apps-aks-dev.yaml

@@ -1,33 +1,32 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+---
 apiVersion: argoproj.io/v1alpha1
 kind: Application
 metadata:
-  name: network-policies
+  name: infrastructure-apps
   namespace: argocd
   labels:
-    app.kubernetes.io/name: network-policies
+    app.kubernetes.io/name: infrastructure-apps
     app.kubernetes.io/part-of: platform
-    app.kubernetes.io/managed-by: argocd
-  annotations:
-    argocd.argoproj.io/sync-wave: "1"
   finalizers:
   - resources-finalizer.argocd.argoproj.io
 spec:
   project: default
-
   source:
     repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
     targetRevision: HEAD
-    path: cluster-resources/network
-
+    path: infra/overlays/aks-dev
   destination:
     server: https://kubernetes.default.svc
-
+    namespace: default
   syncPolicy:
     automated:
       prune: true
       selfHeal: true
-      allowEmpty: false
-
     syncOptions:
-    - Validate=true
-    - ServerSideApply=true
+    - CreateNamespace=true

_app-of-apps-aks-prod.yaml

@@ -1,27 +1,29 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+---
 apiVersion: argoproj.io/v1alpha1
 kind: Application
 metadata:
-  name: secrets
+  name: infrastructure-apps
   namespace: argocd
-  annotations:
-    argocd.argoproj.io/sync-wave: "2"
-    notifications.argoproj.io/subscribe.on-sync-succeeded.slack: ""
-    notifications.argoproj.io/subscribe.on-sync-failed.slack: ""
-    notifications.argoproj.io/subscribe.on-degraded.slack: ""
   labels:
-    app.kubernetes.io/name: secrets
+    app.kubernetes.io/name: infrastructure-apps
     app.kubernetes.io/part-of: platform
-    app.kubernetes.io/managed-by: argocd
   finalizers:
   - resources-finalizer.argocd.argoproj.io
 spec:
   project: default
   source:
     repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
-    path: secrets/upc-dev
+    targetRevision: HEAD
+    path: infra/overlays/aks-prod
   destination:
     server: https://kubernetes.default.svc
-    namespace: secrets
+    namespace: default
   syncPolicy:
     automated:
       prune: true

_app-of-apps-eks-dev.yaml

@@ -0,0 +1,32 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+---
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: infrastructure-apps
+  namespace: argocd
+  labels:
+    app.kubernetes.io/name: infrastructure-apps
+    app.kubernetes.io/part-of: platform
+  finalizers:
+  - resources-finalizer.argocd.argoproj.io
+spec:
+  project: default
+  source:
+    repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
+    targetRevision: HEAD
+    path: infra/overlays/eks-dev
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: default
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+    - CreateNamespace=true

_app-of-apps-eks-prod.yaml

@@ -0,0 +1,32 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+---
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: infrastructure-apps
+  namespace: argocd
+  labels:
+    app.kubernetes.io/name: infrastructure-apps
+    app.kubernetes.io/part-of: platform
+  finalizers:
+  - resources-finalizer.argocd.argoproj.io
+spec:
+  project: default
+  source:
+    repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
+    targetRevision: HEAD
+    path: infra/overlays/eks-prod
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: default
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+    - CreateNamespace=true

_app-of-apps-gke-dev.yaml

@@ -0,0 +1,32 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+---
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: infrastructure-apps
+  namespace: argocd
+  labels:
+    app.kubernetes.io/name: infrastructure-apps
+    app.kubernetes.io/part-of: platform
+  finalizers:
+  - resources-finalizer.argocd.argoproj.io
+spec:
+  project: default
+  source:
+    repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
+    targetRevision: HEAD
+    path: infra/overlays/gke-dev
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: default
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+    - CreateNamespace=true

_app-of-apps-gke-prod.yaml

@@ -0,0 +1,32 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  annotations:
+    argocd.argoproj.io/sync-wave: "-1"
+---
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: infrastructure-apps
+  namespace: argocd
+  labels:
+    app.kubernetes.io/name: infrastructure-apps
+    app.kubernetes.io/part-of: platform
+  finalizers:
+  - resources-finalizer.argocd.argoproj.io
+spec:
+  project: default
+  source:
+    repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
+    targetRevision: HEAD
+    path: infra/overlays/gke-prod
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: default
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+    - CreateNamespace=true

_app-of-apps-upc-prod.yaml

@@ -18,7 +18,7 @@ metadata:
 spec:
   project: default
   source:
-    repoURL: git@github.com:fortedigital/sturdy-adventure.git
+    repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
     targetRevision: HEAD
     path: infra/overlays/upc-prod
   destination:

apps/base/argo-mcp/kustomization.yaml

@@ -0,0 +1,6 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- argo-mcp.yaml
+- argocdmcp-auth-oidc-sealed.yaml
+- argocd-mcp-credentials.yaml

apps/base/dot-ai-stack/dot-ai-stack.yaml

@@ -37,7 +37,7 @@ spec:
       - $values/infra/values/base/dot-ai-stack-values.yaml
       - $values/infra/values/upc-dev/dot-ai-stack-values.yaml
 
-  - repoURL: git@github.com:fortedigital/sturdy-adventure.git
+  - repoURL: ssh://git@git.forteapps.net:2222/Forte/launchpad.git
     targetRevision: HEAD
     ref: values
 

apps/base/dot-ai-stack/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- dot-ai-stack.yaml
+- dot-ai-secrets.yaml

apps/base/kustomization.yaml

@@ -1,8 +1,8 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
-- dot-ai-stack.yaml
-- mcp10x.yaml
-- musicman.yaml
-- ts-mcp.yaml
-- argo-mcp.yaml
+- dot-ai-stack
+- mcp10x
+- musicman
+- ts-mcp
+- argo-mcp

apps/base/mcp10x/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- mcp10x.yaml
+- forte10x-app-credentials-sealed.yaml

apps/base/musicman/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- musicman.yaml
+- musicman-credentials.yaml

apps/base/musicman/musicman-credentials.yaml

@@ -4,6 +4,8 @@ metadata:
   creationTimestamp: null
   name: musicman-credentials
   namespace: music-man
+  annotations:
+    argocd.argoproj.io/sync-wave: "12"
 spec:
   encryptedData:
     DATABASE_URL: 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

apps/base/musicman/musicman.yaml

@@ -36,13 +36,8 @@ spec:
     automated:
       prune: true
       selfHeal: true
-      allowEmpty: false
-
     syncOptions:
     - CreateNamespace=true
-    - Validate=true
-    - ServerSideApply=false
-    - Replace=false
     retry:
       limit: 5
       backoff:

apps/base/ts-mcp/kustomization.yaml

@@ -0,0 +1,5 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- ts-mcp.yaml
+- ts-mcp-secrets-sealed.yaml

apps/base/ts-mcp/ts-mcp-secrets-sealed.yaml

@@ -0,0 +1,13 @@
+---
+apiVersion: bitnami.com/v1alpha1
+kind: SealedSecret
+metadata:
+  name: ts-mcp-secrets
+  namespace: ts-mcp
+spec:
+  encryptedData:
+    AZURE_CLIENT_SECRET: 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
+  template:
+    metadata:
+      name: ts-mcp-secrets
+      namespace: ts-mcp

apps/overlays/aks-dev/kustomization.yaml

@@ -0,0 +1,4 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- ../../base/musicman

apps/overlays/upc-dev/dbunk-demo/dbunk-demo.yaml

@@ -0,0 +1,47 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: dbunk-demo
+  namespace: argocd
+  annotations:
+    argocd.argoproj.io/sync-wave: "12"
+  labels:
+    app.kubernetes.io/name: dbunk-demo
+    app.kubernetes.io/part-of: apps
+    app.kubernetes.io/managed-by: argocd
+  finalizers:
+  - resources-finalizer.argocd.argoproj.io
+spec:
+  project: default
+
+  sources:
+  - repoURL: ssh://git@git.forteapps.net:2222/Forte/forte-helm.git
+    path: forteapp
+    targetRevision: HEAD
+    helm:
+      valueFiles:
+      - $values/dbunk-demo/values.yaml
+
+  - repoURL: ssh://git@git.forteapps.net:2222/Forte/helm-prod-values.git
+    targetRevision: HEAD
+    ref: values
+
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: dbunk-demo
+
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+      allowEmpty: false
+    syncOptions:
+    - CreateNamespace=true
+    - Validate=true
+    - ServerSideApply=true
+    retry:
+      limit: 5
+      backoff:
+        duration: 5s
+        factor: 2
+        maxDuration: 3m

apps/overlays/upc-dev/dbunk-demo/kustomization.yaml

@@ -0,0 +1,4 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+- dbunk-demo.yaml

apps/overlays/upc-dev/kustomization.yaml

@@ -2,6 +2,7 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
 - ../../base
+- dbunk-demo
 
 # No patches needed — base already has "upc-dev" paths
 # upc-dev is the default/base cluster

bootstrap.sh

@@ -1,8 +1,9 @@
 #!/bin/zsh
+
 # in case of  $'\r': command not found error, run command below first
 # sed -i 's/\r$//' ./bootstrap.sh
 
-CLUSTER="${1:?Usage: ./bootstrap.sh <cluster> (upc-dev|upc-prod)}"
+CLUSTER="${1:?Usage: ./bootstrap.sh <cluster> (upc-dev|upc-prod|aks-dev|aks-prod|eks-dev|eks-prod|gke-dev|gke-prod)}"
 
 echo "running $0 for cluster: ${CLUSTER}..."
 
@@ -17,7 +18,7 @@ echo "Bootstrapping cluster: ${clusterName} (${CLUSTER})..."
 Bootstrap()
 {
     ArgoCd
-#    Gitea
+    Gitea
 }
 
 
@@ -27,8 +28,8 @@ Bootstrap()
 Gitea()
 {
     echo "Installing secret..."
-    kubectl apply -f private/gitea-repo-main.yaml
-    kubectl apply -f private/main.key
+    kubectl apply -f "private/${CLUSTER}/gitea-repo-main.yaml"
+    kubectl apply -f "private/${CLUSTER}/main.key"
 }
 
 ############################################################
@@ -36,10 +37,15 @@ Gitea()
 ############################################################
 ArgoCd()
 {
+    # Pre-create ConfigMap for repo-server env (must exist before Helm upgrade)
+    kubectl create namespace argocd --dry-run=client -o yaml | kubectl apply -f -
+    kubectl apply -f cluster-resources/argocd-repo-server-config.yaml
+
     # install argocd
     echo "Installing ArgoCD..."
     helm upgrade --install argocd argo-cd \
             --repo https://argoproj.github.io/argo-helm \
+            --version "7.8.0" \
             --namespace argocd --create-namespace \
             --values infra/values/base/argocd-values.yaml \
             --values "infra/values/${CLUSTER}/argocd-values.yaml" \
@@ -49,4 +55,4 @@ ArgoCd()
     kubectl apply -f "_app-of-apps-${CLUSTER}.yaml" -n argocd
 }
 
-# Bootstrap
+Bootstrap

cluster-resources/argocd-oidc-secret-sync.yaml

@@ -0,0 +1,83 @@
+# CronJob: syncs OIDC client secret from registrar-managed
+# argocd-oidc-credentials into argocd-secret (oidc.clientSecret key).
+# Runs every 2 min. No-ops if source secret doesn't exist yet
+# (safe for fresh deploys before Keycloak is up).
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: argocd-oidc-sync
+  namespace: argocd
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: argocd-oidc-sync
+  namespace: argocd
+rules:
+- apiGroups: [""]
+  resources: ["secrets"]
+  resourceNames: ["argocd-oidc-credentials", "argocd-secret"]
+  verbs: ["get", "patch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: argocd-oidc-sync
+  namespace: argocd
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: argocd-oidc-sync
+subjects:
+- kind: ServiceAccount
+  name: argocd-oidc-sync
+  namespace: argocd
+---
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: argocd-oidc-sync
+  namespace: argocd
+spec:
+  schedule: "*/2 * * * *"
+  concurrencyPolicy: Forbid
+  successfulJobsHistoryLimit: 1
+  failedJobsHistoryLimit: 3
+  jobTemplate:
+    spec:
+      backoffLimit: 1
+      template:
+        spec:
+          serviceAccountName: argocd-oidc-sync
+          restartPolicy: Never
+          containers:
+          - name: sync
+            image: bitnami/kubectl:latest
+            command: ["/bin/sh", "-c"]
+            args:
+            - |
+              set -e
+
+              # Exit gracefully if source secret doesn't exist yet
+              if ! kubectl get secret argocd-oidc-credentials -n argocd >/dev/null 2>&1; then
+                echo "argocd-oidc-credentials not found — skipping (Keycloak not ready yet)"
+                exit 0
+              fi
+
+              # Read current OIDC client secret
+              NEW_SECRET=$(kubectl get secret argocd-oidc-credentials -n argocd \
+                -o jsonpath='{.data.client-secret}' | base64 -d)
+
+              # Read current value in argocd-secret (if any)
+              CURRENT=$(kubectl get secret argocd-secret -n argocd \
+                -o jsonpath='{.data.oidc\.clientSecret}' 2>/dev/null | base64 -d || echo "")
+
+              # Only patch if changed
+              if [ "$NEW_SECRET" = "$CURRENT" ]; then
+                echo "oidc.clientSecret already up to date"
+                exit 0
+              fi
+
+              kubectl patch secret argocd-secret -n argocd --type merge \
+                -p "{\"stringData\":{\"oidc.clientSecret\":\"${NEW_SECRET}\"}}"
+              echo "Patched argocd-secret with oidc.clientSecret"

cluster-resources/argocd-repo-server-config.yaml

@@ -0,0 +1,9 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: argocd-repo-server-config
+  namespace: argocd
+data:
+  # Disable git submodule checkout - submodules (e.g. shared-prompts)
+  # are not needed for K8s manifest generation
+  ARGOCD_GIT_MODULES_ENABLED: "false"

cluster-resources/azuredns-config-sealed.yaml

@@ -0,0 +1,15 @@
+---
+apiVersion: bitnami.com/v1alpha1
+kind: SealedSecret
+metadata:
+  creationTimestamp: null
+  name: azuredns-config
+  namespace: cert-manager
+spec:
+  encryptedData:
+    client-secret: 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
+  template:
+    metadata:
+      creationTimestamp: null
+      name: azuredns-config
+      namespace: cert-manager

cluster-resources/gitea-backup-cronjob.yaml

@@ -57,17 +57,17 @@ spec:
                 - sh
                 - -c
                 - |
-                  mc alias set upcloud "${S3_ENDPOINT}" "${AWS_ACCESS_KEY_ID}" "${AWS_SECRET_ACCESS_KEY}"
+                  mc alias set s3 "${S3_ENDPOINT}" "${AWS_ACCESS_KEY_ID}" "${AWS_SECRET_ACCESS_KEY}"
 
                   TIMESTAMP=$(date +%Y%m%d-%H%M%S)
                   KEY="gitea-dump-${TIMESTAMP}.zip"
                   echo "Uploading ${KEY}..."
-                  mc cp /backup/gitea-dump.zip "upcloud/${S3_BUCKET}/${KEY}" && \
+                  mc cp /backup/gitea-dump.zip "s3/${S3_BUCKET}/${KEY}" && \
                   echo "Upload complete."
 
                   # Prune backups older than 7 days
                   echo "Pruning backups older than 7 days..."
-                  mc rm --older-than 7d --force "upcloud/${S3_BUCKET}/" 2>&1 || true
+                  mc rm --older-than 7d --force "s3/${S3_BUCKET}/" 2>&1 || true
                   echo "Pruning complete."
               envFrom:
                 - secretRef:

cluster-resources/letsencrypt-issuer.yaml

@@ -12,10 +12,24 @@ spec:
     privateKeySecretRef:
       name: letsencrypt-staging-key
     solvers:
+    - dns01:
+        azureDNS:
+          subscriptionID: 1b52bc03-6815-4574-b579-60745dce544d
+          resourceGroupName: forteapps-domain
+          hostedZoneName: forteapps.net
+          environment: AzurePublicCloud
+          clientID: 3b7a4ebf-894c-4f5d-9b1e-2b61312f8e74
+          clientSecretSecretRef:
+            name: azuredns-config
+            key: client-secret
+      selector:
+        dnsNames:
+        - '*.forteapps.net'
+        - 'forteapps.net'
+    # HTTP-01 fallback for non-wildcard certificates
     - http01:
         ingress:
           class: traefik
-
 ---
 # Production ClusterIssuer for browser-trusted certificates
 apiVersion: cert-manager.io/v1
@@ -30,6 +44,146 @@ spec:
     privateKeySecretRef:
       name: letsencrypt-prod-key
     solvers:
+    # DNS-01 solver for wildcard certificates (*.forteapps.net)
+    - dns01:
+        azureDNS:
+          subscriptionID: 1b52bc03-6815-4574-b579-60745dce544d
+          resourceGroupName: forteapps-domain
+          hostedZoneName: forteapps.net
+          environment: AzurePublicCloud
+          clientID: 3b7a4ebf-894c-4f5d-9b1e-2b61312f8e74
+          clientSecretSecretRef:
+            name: azuredns-config
+            key: client-secret
+      selector:
+        dnsNames:
+        - '*.forteapps.net'
+        - 'forteapps.net'
+    # HTTP-01 fallback for non-wildcard certificates
     - http01:
         ingress:
           class: traefik
+
+# =============================================================================
+# CONFIGURATION INSTRUCTIONS FOR AZURE DNS WITH WILDCARD CERTIFICATES
+# =============================================================================
+#
+# PREREQUISITES IN AZURE DNS PORTAL:
+# ----------------------------------
+# 1. Ensure you have an Azure DNS Zone for "forteapps.net" created in your
+#    Azure subscription. If not, create it in Azure Portal:
+#    - Search for "DNS zones" → Create → Zone name: forteapps.net
+#    - Note the Resource Group where you create it (e.g., "dns-zones-rg")
+#
+# 2. Configure NS records at your domain registrar to point to Azure DNS:
+#    - In Azure Portal → DNS zones → forteapps.net
+#    - Note the 4 NS records shown (e.g., ns1-04.azure-dns.com, etc.)
+#    - Go to your domain registrar and update the NS records to these values
+#
+# AUTHENTICATION (Service Principal - Required for UpCloud/non-Azure clusters):
+# ----------------------------------------------------------------------------
+# Since your cluster runs on UpCloud (not AKS), you must use Service Principal
+# authentication. Managed Identity only works with Azure-hosted resources.
+#
+# =============================================================================
+# SETUP: Service Principal for UpCloud Clusters
+# =============================================================================
+#
+# 1. Create Azure AD App Registration:
+#    az ad sp create-for-rbac --name cert-manager-dns --sdk-auth
+#    # Save the JSON output - you'll need appId (clientID) and password (clientSecret)
+#
+# 2. Assign DNS Zone Contributor role:
+#    az role assignment create \
+#      --role "DNS Zone Contributor" \
+#      --assignee <SERVICE_PRINCIPAL_CLIENT_ID> \
+#      --scope /subscriptions/<SUBSCRIPTION_ID>/resourceGroups/<DNS_RESOURCE_GROUP>/providers/Microsoft.Network/dnszones/forteapps.net
+#
+# 3. Create Kubernetes secret for the service principal:
+#    kubectl create secret generic azuredns-config \
+#      --namespace cert-manager \
+#      --from-literal=client-secret=YOUR_CLIENT_SECRET
+#
+# 4. Update the ClusterIssuer above with:
+#    - subscriptionID: Your Azure subscription ID
+#    - resourceGroupName: The resource group containing your DNS zone
+#    - clientID: The Service Principal appId/clientID
+#    - clientSecretSecretRef: References the secret created in step 3
+#
+# =============================================================================
+# ALTERNATIVE DNS PROVIDERS (for reference):
+# =============================================================================
+
+# -----------------------------------------------------------------------------
+# Cloudflare (original configuration)
+# -----------------------------------------------------------------------------
+# Create secret with: kubectl create secret generic cloudflare-api-token-secret \
+#   --from-literal=api-token=YOUR_CLOUDFLARE_API_TOKEN -n cert-manager
+#
+# dns01:
+#   cloudflare:
+#     email: your-cloudflare-email@example.com
+#     apiTokenSecretRef:
+#       name: cloudflare-api-token-secret
+#       key: api-token
+
+# -----------------------------------------------------------------------------
+# AWS Route53
+# -----------------------------------------------------------------------------
+# Create secret with: kubectl create secret generic route53-credentials \
+#   --from-literal=secret-access-key=YOUR_SECRET_KEY -n cert-manager
+#
+# dns01:
+#   route53:
+#     region: us-east-1
+#     hostedZoneID: ZXXXXXXXXXXXXX
+#     accessKeyID: YOUR_ACCESS_KEY_ID
+#     secretAccessKeySecretRef:
+#       name: route53-credentials
+#       key: secret-access-key
+
+# -----------------------------------------------------------------------------
+# Google Cloud DNS
+# -----------------------------------------------------------------------------
+# Create secret with service account JSON key:
+# kubectl create secret generic clouddns-service-account \
+#   --from-file=service-account.json=path/to/key.json -n cert-manager
+#
+# dns01:
+#   cloudDNS:
+#     project: YOUR_GCP_PROJECT_ID
+#     hostedZoneName: example-com
+#     serviceAccountSecretRef:
+#       name: clouddns-service-account
+#       key: service-account.json
+
+# -----------------------------------------------------------------------------
+# GoDaddy
+# -----------------------------------------------------------------------------
+# Requires external webhook: https://github.com/snowdrop/godaddy-webhook
+#
+# dns01:
+#   webhook:
+#     groupName: acme.yourcompany.com
+#     solverName: godaddy
+#     config:
+#       apiKeySecretRef:
+#         name: godaddy-api-credentials
+#         key: api-key
+#       apiSecretSecretRef:
+#         name: godaddy-api-credentials
+#         key: api-secret
+
+# -----------------------------------------------------------------------------
+# Manual/Dynamic DNS (for homelab)
+# -----------------------------------------------------------------------------
+# Requires RFC2136 provider or external webhook
+#
+# dns01:
+#   rfc2136:
+#     nameserver: your-dns-server.example.com
+#     tsigKeyName: cert-manager-key
+#     tsigAlgorithm: HMACSHA256
+#     tsigSecretSecretRef:
+#       name: tsig-secret
+#       key: secret

cluster-resources/policies/label-checker.yaml

@@ -1,41 +0,0 @@
-apiVersion: kyverno.io/v1
-kind: ClusterPolicy
-metadata:
-  name: require-labels
-  annotations:
-    policies.kyverno.io/title: Require Labels
-    policies.kyverno.io/category: Best Practices
-    policies.kyverno.io/minversion: 1.6.0
-    policies.kyverno.io/severity: medium
-    policies.kyverno.io/subject: Pod, Label
-    policies.kyverno.io/description: Define and use labels that identify semantic attributes of your application or Deployment. A common set of labels allows tools to work collaboratively, describing objects in a common manner that all tools can understand. The recommended labels describe applications in a way that can be queried. This policy validates that the label `app.kubernetes.io/name` is specified with some value.
-spec:
-  validationFailureAction: Audit
-  background: true
-  rules:
-  - name: check-for-labels
-    skipBackgroundRequests: true
-    exclude:
-      any:
-      - resources:
-          namespaces:
-          - kube-system
-          - istio-system
-          - argocd
-          - cert-manager
-          - monitoring
-          - secrets
-          - kyverno
-          - trivy-system
-    match:
-      any:
-      - resources:
-          kinds:
-          - Pod
-    validate:
-      message: The label `app.kubernetes.io/name` is required.
-      allowExistingViolations: true
-      pattern:
-        metadata:
-          labels:
-            app.kubernetes.io/name: "?*"

cluster-resources/policies/secret-cloner.yaml

@@ -16,7 +16,6 @@ spec:
       - resources:
           namespaces:
           - kube-system
-          - trivy-system
           - monitoring
           - argocd
           - cert-manager

clusters/aks-dev.yaml

@@ -0,0 +1,12 @@
+# Cluster config reference — values must match the corresponding overlay files.
+# Read by bootstrap.sh at install time; NOT auto-propagated to ArgoCD value files.
+clusterName: k8s-launchpad # → infra/values/aks-dev/argocd-values.yaml (notifications.context.clusterName)
+domain: example.com # → infra/values/base/gitea-values.yaml, renovate-values.yaml, keycloak-values.yaml (subdomains)
+argocdDomain: argocd.example.com # → infra/values/aks-dev/argocd-values.yaml (global.domain)
+grafanaDomain: grafana.example.com # → infra/values/aks-dev/grafana-values.yaml (ingress.hosts)
+keycloakDomain: id.example.com # → infra/values/aks-dev/keycloak-values.yaml (ingress.hostname)
+dotaiDomain: kubemcp.example.com # → infra/values/aks-dev/dot-ai-stack-values.yaml (dot-ai.ingress.host) — create if needed
+dotaiUiDomain: kubemcpui.example.com # → infra/values/aks-dev/dot-ai-stack-values.yaml (dot-ai-ui.ingress.host) — create if needed
+letsencryptEmail: admin@example.com # → cluster-resources/letsencrypt-issuer.yaml (spec.acme.email)
+trustedIPs: "10.0.0.0/8,168.63.129.16/32" # → infra/values/aks-dev/traefik-values.yaml (ports.*.trustedIPs) — VNet CIDR + Azure health probe
+cloudProvider: azure # → determines overlay directory and cloud-specific LB/storage annotations