Restructure and variablize config

.gitignore

@@ -4,3 +4,5 @@ worker.yaml
 talosconfig
 terraform/.terraform/
 terraform/.terraform.lock.hcl
+terraform.tfstate
+terraform/terraform.tfvars

Makefile

@@ -1,6 +1,6 @@
-.PHONY: init plan apply destroy kubeconfig talosconfig argocd-password bootstrap decrypt post-apply fluentbit-secret
+.PHONY: init plan apply destroy clean kubeconfig talosconfig argocd-password bootstrap decrypt post-apply fluentbit-secret
 
-SECRET=dumpnet
+SECRET ?= dumpnet
 TF_DIR=terraform
 SOPS_FILES=controlplane.yaml worker.yaml talosconfig
 
@@ -12,11 +12,29 @@ plan:
 	cd $(TF_DIR) && terraform plan
 
 apply:
+	cd $(TF_DIR) && terraform apply -target=talos_cluster_kubeconfig.this
 	cd $(TF_DIR) && terraform apply
 
 destroy:
 	cd $(TF_DIR) && terraform destroy
 
+# Full clean slate - run before destroy when recreating from scratch
+# Removes resources that block terraform from recreating cleanly
+clean:
+	@echo "==> Force-deleting Secrets Manager secret..."
+	-aws secretsmanager delete-secret --secret-id $(SECRET) --force-delete-without-recovery 2>/dev/null || true
+	@echo "==> Emptying S3 buckets..."
+	-aws s3 rm s3://dumpnet-logs --recursive 2>/dev/null || true
+	-aws s3 rm s3://dumpnet-athena-results --recursive 2>/dev/null || true
+	@echo "==> Clearing stale kubeconfig contexts..."
+	-kubectl config delete-context admin@dumpnet 2>/dev/null || true
+	-kubectl config delete-cluster dumpnet 2>/dev/null || true
+	-kubectl config delete-user admin@dumpnet 2>/dev/null || true
+	@echo "==> Clearing stale talosctl contexts..."
+	-talosctl config remove dumpnet 2>/dev/null || true
+	-talosctl config remove dumpnet-1 2>/dev/null || true
+	@echo "==> Done. Run 'make destroy' then 'make apply' to rebuild from scratch."
+
 # Bootstrap ArgoCD app of apps (run once after cluster is up)
 bootstrap:
 	kubectl apply -f apps/apps.yaml
@@ -32,6 +50,9 @@ talosconfig:
 	talosctl config context dumpnet
 
 kubeconfig:
+	-kubectl config delete-context admin@dumpnet 2>/dev/null || true
+	-kubectl config delete-cluster dumpnet 2>/dev/null || true
+	-kubectl config delete-user admin@dumpnet 2>/dev/null || true
 	aws secretsmanager get-secret-value --secret-id $(SECRET) \
 	  --query SecretString --output text | python3 -c \
 	  "import sys,json; print(json.load(sys.stdin)['cluster']['kubeconfig'])" \

README.md

@@ -23,7 +23,7 @@ GitOps cluster management for dumpnet — a single-node Talos/Kubernetes cluster
 
 Sensitive files (`talosconfig`, `controlplane.yaml`, `worker.yaml`) are **gitignored** and never stored in the repo in any form. They are managed as follows:
 
-- **Cluster credentials** (kubeconfig, talosconfig, ArgoCD password) → stored in AWS Secrets Manager at `dumpnet/cluster`
+- **Cluster credentials** (kubeconfig, talosconfig, ArgoCD password) → stored in AWS Secrets Manager at `dumpnet`
 - **Talos machine configs** → encrypted with SOPS + age, stored outside the repo
 - **Age private key** → lives at `~/.age/key.txt` — **back this up securely**
 
@@ -57,6 +57,13 @@ cp terraform/terraform.tfvars.example terraform/terraform.tfvars
 make apply
 ```
 
+> **Note:** `make apply` runs two Terraform passes internally. The first pass
+> (`-target=talos_cluster_kubeconfig.this`) brings up the EC2 instance, bootstraps
+> the cluster, and retrieves the kubeconfig. The second pass then uses that live
+> kubeconfig to provision Kubernetes resources (namespaces, ArgoCD Helm release).
+> This two-phase approach is necessary because the Helm and Kubernetes Terraform
+> providers need a reachable cluster to initialize.
+
 This will:
 - Allocate an EIP
 - Create a dedicated subnet and security group
@@ -90,11 +97,23 @@ make argocd-password
 
 Then log in at https://argocd.dumpnet.chat — ArgoCD will finish deploying ingress-nginx and metrics-server automatically.
 
+## Rebuilding from Scratch
+
+To fully tear down and recreate the cluster:
+
+```bash
+make clean    # force-delete secret, empty S3, clear stale kube/talos contexts
+make destroy  # tear down all terraform resources
+make apply    # recreate everything
+make post-apply  # wait for cluster ready, bootstrap ArgoCD
+make bootstrap   # apply App of Apps
+```
+
 ## Day-to-Day
 
 - **Add a new app**: add a manifest to `manifests/` and values to `charts/` — ArgoCD picks it up on next sync
 - **Add a DNS record**: add the subdomain to `dns_records` in `terraform/terraform.tfvars` and run `make apply`
-- **Cluster access**: `make kubeconfig` or `make talosconfig` (pulls from Secrets Manager)
+- **Cluster access**: `make kubeconfig` or `make talosconfig` (pulls from Secrets Manager, safe to re-run — automatically clears any stale context from a previous cluster before merging)
 - **Emergency talosctl access**: `make decrypt` to get configs in `/tmp`
 
 ## Makefile Reference
@@ -104,9 +123,10 @@ Then log in at https://argocd.dumpnet.chat — ArgoCD will finish deploying ingr
 | `make apply` | Create/update cluster infrastructure |
 | `make plan` | Preview infrastructure changes |
 | `make destroy` | Tear down everything |
+| `make clean` | Pre-destroy cleanup (force-delete secret, empty S3 buckets, clear stale kube/talos contexts) |
 | `make post-apply` | One-time bootstrap after fresh cluster creation |
 | `make bootstrap` | Apply App of Apps only |
-| `make kubeconfig` | Pull kubeconfig from Secrets Manager |
+| `make kubeconfig` | Pull kubeconfig from Secrets Manager (clears stale context first) |
 | `make talosconfig` | Pull talosconfig from Secrets Manager |
 | `make argocd-password` | Print ArgoCD admin password |
 | `make decrypt` | Decrypt Talos configs to /tmp |
@@ -141,6 +161,22 @@ dumpnet-argo/
     └── outputs.tf
 ```
 
+## Forking / Multiple Environments
+
+Global per-cluster config lives in **`values.yaml`** at the repo root:
+
+```yaml
+clusterName: dumpnet
+domain: dumpnet.chat
+repoURL: https://forge.keane.sh/ian/dumpnet-argo.git
+certEmail: dumpnetcerts@keane.sh
+awsRegion: us-east-1
+```
+
+This file is passed as the first `valueFiles` entry to every Helm chart, so `domain`, `certEmail`, `clusterName`, and `awsRegion` are available as `{{ .Values.* }}` in all chart values. Terraform variables in `terraform/variables.tf` mirror these same settings for the infrastructure side.
+
+**The one thing that can't be templated** is `repoURL` in the ArgoCD `Application` manifests themselves (under `apps/` and `manifests/`). These are plain YAML consumed by ArgoCD before any Helm rendering happens — there's no way to interpolate them without a [Config Management Plugin](https://argo-cd.readthedocs.io/en/stable/operator-manual/config-management-plugins/). When forking this repo, do a global find/replace on `forge.keane.sh/ian/dumpnet-argo` with your own repo URL.
+
 ## Notes
 
 - The control plane taint is disabled via `allowSchedulingOnControlPlanes: true` in the Talos machine config — no manual taint removal needed

charts/argocd/values.yaml

@@ -5,7 +5,7 @@ server:
   ingress:
     enabled: true
     ingressClassName: nginx
-    hostname: argocd.dumpnet.chat
+    hostname: argocd.{{ .Values.domain }}
     tls: true
     annotations:
       cert-manager.io/cluster-issuer: letsencrypt-prod

charts/cert-manager/cluster-issuers.yaml

@@ -5,7 +5,7 @@ metadata:
 spec:
   acme:
     server: https://acme-v02.api.letsencrypt.org/directory
-    email: dumpnetcerts@keane.sh
+    email: {{ .Values.certEmail }}
     privateKeySecretRef:
       name: letsencrypt-prod
     solvers:
@@ -20,7 +20,7 @@ metadata:
 spec:
   acme:
     server: https://acme-staging-v02.api.letsencrypt.org/directory
-    email: dumpnetcerts@keane.sh
+    email: {{ .Values.certEmail }}
     privateKeySecretRef:
       name: letsencrypt-staging
     solvers:

charts/fluent-bit/values.yaml

@@ -47,8 +47,8 @@ config:
     [OUTPUT]
         Name                         s3
         Match                        kube.*
-        bucket                       dumpnet-logs
-        region                       us-east-1
+        bucket                       {{ .Values.clusterName }}-logs
+        region                       {{ .Values.awsRegion }}
         s3_key_format                /logs/%Y/%m/%d/$TAG[4].%H%M%S.gz
         total_file_size              100M
         upload_timeout               10m

manifests/cluster/argocd.yaml

@@ -14,6 +14,7 @@ spec:
       targetRevision: "*"
       helm:
         valueFiles:
+          - $values/values.yaml
           - $values/charts/argocd/values.yaml
   destination:
     server: https://kubernetes.default.svc

manifests/cluster/cert-manager.yaml

@@ -32,12 +32,17 @@ metadata:
   namespace: argocd
 spec:
   project: default
-  source:
-    repoURL: https://forge.keane.sh/ian/dumpnet-argo.git
-    targetRevision: HEAD
-    path: charts/cert-manager
-    directory:
-      include: "cluster-issuers.yaml"
+  sources:
+    - repoURL: https://forge.keane.sh/ian/dumpnet-argo.git
+      targetRevision: HEAD
+      ref: values
+    - repoURL: https://forge.keane.sh/ian/dumpnet-argo.git
+      targetRevision: HEAD
+      path: charts/cert-manager
+      helm:
+        valueFiles:
+          - $values/values.yaml
+        releaseName: cert-manager-issuers
   destination:
     server: https://kubernetes.default.svc
     namespace: cert-manager

manifests/cluster/fluent-bit.yaml

@@ -14,6 +14,7 @@ spec:
       targetRevision: "*"
       helm:
         valueFiles:
+          - $values/values.yaml
           - $values/charts/fluent-bit/values.yaml
   destination:
     server: https://kubernetes.default.svc

terraform/argocd.tf

@@ -5,10 +5,10 @@ resource "random_password" "argocd_admin" {
   override_special = "!#$%&*()-_=+[]{}?"
 }
 
-# Single secrets manager secret for all dumpnet secrets
+# Single secrets manager secret for all cluster secrets
 resource "aws_secretsmanager_secret" "dumpnet" {
-  name        = "dumpnet"
-  description = "All dumpnet secrets"
+  name        = var.cluster_name
+  description = "All ${var.cluster_name} secrets"
 }
 
 resource "aws_secretsmanager_secret_version" "dumpnet" {

terraform/logging.tf

@@ -1,6 +1,6 @@
 # S3 bucket for logs
 resource "aws_s3_bucket" "logs" {
-  bucket = "dumpnet-logs"
+  bucket = "${var.cluster_name}-logs"
 }
 
 resource "aws_s3_bucket_lifecycle_configuration" "logs" {
@@ -10,7 +10,9 @@ resource "aws_s3_bucket_lifecycle_configuration" "logs" {
     id     = "expire-old-logs"
     status = "Enabled"
 
-    filter {}
+    filter {
+      prefix = ""
+    }
 
     transition {
       days          = 30
@@ -34,16 +36,16 @@ resource "aws_s3_bucket_server_side_encryption_configuration" "logs" {
 
 # Athena database + workgroup
 resource "aws_athena_database" "logs" {
-  name   = "dumpnet_logs"
+  name   = "${replace(var.cluster_name, "-", "_")}_logs"
   bucket = aws_s3_bucket.athena_results.bucket
 }
 
 resource "aws_s3_bucket" "athena_results" {
-  bucket = "dumpnet-athena-results"
+  bucket = "${var.cluster_name}-athena-results"
 }
 
 resource "aws_athena_workgroup" "logs" {
-  name = "dumpnet-logs"
+  name = "${var.cluster_name}-logs"
 
   configuration {
     result_configuration {
@@ -58,7 +60,7 @@ resource "aws_athena_workgroup" "logs" {
 
 # IAM user for fluent-bit to write to S3
 resource "aws_iam_user" "fluentbit" {
-  name = "dumpnet-fluentbit"
+  name = "${var.cluster_name}-fluentbit"
 }
 
 resource "aws_iam_access_key" "fluentbit" {

terraform/outputs.tf

@@ -3,5 +3,5 @@ output "public_ip" {
 }
 
 output "argocd_password_secret" {
-  value = "aws secretsmanager get-secret-value --secret-id dumpnet/cluster --query SecretString --output text | python3 -m json.tool"
+  value = "aws secretsmanager get-secret-value --secret-id ${var.cluster_name} --query SecretString --output text | python3 -m json.tool"
 }

terraform/variables.tf

@@ -3,7 +3,8 @@ variable "talos_version" {
 }
 
 variable "cluster_name" {
-  default = "dumpnet"
+  description = "Name used for cluster resources, S3 buckets, secrets, etc."
+  default     = "dumpnet"
 }
 
 variable "instance_type" {
@@ -19,8 +20,13 @@ variable "ami_id" {
   default     = "ami-000f1b0ad9d8ceafd"
 }
 
+variable "aws_region" {
+  description = "AWS region"
+  default     = "us-east-1"
+}
+
 variable "hosted_zone_id" {
-  description = "Route53 hosted zone ID for dumpnet.chat"
+  description = "Route53 hosted zone ID"
 }
 
 variable "domain" {
@@ -33,3 +39,13 @@ variable "dns_records" {
   type        = list(string)
   default     = ["argocd"]
 }
+
+variable "cert_manager_email" {
+  description = "Email for Let's Encrypt certificate notifications"
+  default     = "dumpnetcerts@keane.sh"
+}
+
+variable "state_bucket" {
+  description = "S3 bucket for Terraform remote state (set in backend config, documented here for reference)"
+  default     = "iankeane-tfstate"
+}

values.yaml

@@ -0,0 +1,10 @@
+# Global cluster configuration
+# Override any of these in terraform.tfvars or by forking the repo.
+# NOTE: repoURL in apps/apps.yaml and manifests/*.yaml must be updated manually —
+#       ArgoCD Application spec fields cannot be templated via Helm values.
+
+clusterName: dumpnet
+domain: dumpnet.chat
+repoURL: https://forge.keane.sh/ian/dumpnet-argo.git
+certEmail: dumpnetcerts@keane.sh
+awsRegion: us-east-1