feat: add .env file check and load it in startup script

add DNS update step and complete forgejo deployment after build

.env.gcloud-example

@@ -0,0 +1,3 @@
+PROJECT_NAME="the name of your gcp project, often referred to as the project"
+EMAIL="your email address to identify yourself with letsencrypt"
+APP_DOMAIN_NAME="your domain name for the app, e.g., frgdr.some-domain.com"

.gitignore

@@ -30,3 +30,6 @@ terraform.tfstate**
 *history*.txt
 *.tfvars
 gcloud/tf/.env
+gcloud/tf/k3s/forgejo/issuer.yaml
+gcloud/tf/k3s/forgejo/ingress.yaml
+.env

gcloud/tf/firewall.tf

@@ -7,8 +7,7 @@ resource "google_compute_firewall" "allow_http" {
   allow {
     protocol = "tcp"
     ports = [
-      "80", "443", // http/https
-      "30080"      // ports opened to access the python API via NodePort
+      "80", "443" // http/https
     ]
   }
 

gcloud/tf/k3s/forgejo/deployment.yaml

@@ -0,0 +1,68 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: forgejo-deployment
+  namespace: forgejo
+  labels:
+    app: forgejo-app
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: forgejo-app
+  template:
+    metadata:
+      labels:
+        app: forgejo-app
+    spec:
+      terminationGracePeriodSeconds: 10
+      containers:
+      - name: forgejo
+        image: codeberg.org/forgejo/forgejo:11.0.6
+        imagePullPolicy: IfNotPresent
+        env:
+        - name: FORGEJO__repository__ENABLE_PUSH_CREATE_USER
+          value: "true"
+        - name: FORGEJO__server__ROOT_URL
+          value: "https://frgdr.headshed.dev/"
+        - name: FORGEJO__repository__DEFAULT_BRANCH
+          value: "main"
+        - name: FORGEJO__server__LFS_START_SERVER
+          value: "true"
+        - name: FORGEJO__security__INSTALL_LOCK
+          value: "true"
+        - name: FORGEJO__service__DISABLE_REGISTRATION
+          value: "false"
+        ports:
+        - name: http
+          containerPort: 3000
+          protocol: TCP
+        - name: ssh
+          containerPort: 22
+        resources:
+          requests:
+            memory: "128Mi"
+            cpu: "100m"
+          limits:
+            memory: "256Mi"
+            cpu: "500m"        
+        tty: true
+        volumeMounts:
+        - name: forgejo-data
+          mountPath: /data
+        # - name: forgejo-timezone
+        #   mountPath: /etc/timezone
+        # - name: forgejo-localtime
+        #   mountPath: /etc/localtime
+      volumes:
+      - name: forgejo-data
+        persistentVolumeClaim:
+          claimName: forgejo-data-pvc
+      # - name: forgejo-timezone
+      #   configMap:
+      #     name: forgejo-timezone
+      # - name: forgejo-localtime
+      #   configMap:
+      #     name: forgejo-localtime

gcloud/tf/k3s/forgejo/ingress.yaml.template

@@ -0,0 +1,24 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: tls-forgejo-ingress-http
+  namespace: forgejo
+  annotations:
+    cert-manager.io/issuer: "le-cluster-issuer-http"
+    
+spec:
+  tls:
+    - hosts:
+        - ${APP_DOMAIN_NAME}
+      secretName: tls-frg-ingress-http
+  rules:
+    - host: ${APP_DOMAIN_NAME}
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: forgejo-app-service
+                port:
+                  name: web

gcloud/tf/k3s/forgejo/issuer.yaml.template

@@ -0,0 +1,17 @@
+apiVersion: cert-manager.io/v1
+kind: Issuer
+metadata:
+  name: le-cluster-issuer-http
+  namespace: forgejo
+spec:
+  acme:
+    email: ${EMAIL}
+    # We use the staging server here for testing to avoid throttling.
+    server: https://acme-staging-v02.api.letsencrypt.org/directory
+    # server: https://acme-v02.api.letsencrypt.org/directory
+    privateKeySecretRef:
+      name: http-issuer-account-key
+    solvers:
+      - http01:
+          ingress:
+            class: traefik

gcloud/tf/k3s/forgejo/pvc.yaml

@@ -0,0 +1,26 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: forgejo-local-pv
+spec:
+  capacity:
+    storage: 3Gi
+  accessModes:
+    - ReadWriteOnce
+  hostPath:
+    path: /mnt/disks/app-data/forgejo
+  storageClassName: local-path
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: forgejo-data-pvc
+  namespace: forgejo
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 3Gi
+  volumeName: forgejo-local-pv
+  storageClassName: local-path

gcloud/tf/k3s/forgejo/service.yaml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: forgejo-app-service
+  namespace: forgejo
+spec:
+  selector:
+    app: forgejo-app
+  ports:
+    - name: web
+      protocol: TCP
+      port: 3000
+      targetPort: 3000

gcloud/tf/main.tf

@@ -19,15 +19,12 @@ resource "google_compute_instance" "k3s" {
     }
   }
 
-  // Configuration to be a Spot Instance, to reduce costs
-  scheduling {
-    automatic_restart = true
-  }
+  // ensures that the instance is a Spot VM
+  // means it can be preempted, but it's cheaper
   # scheduling {
-  #   preemptible                 = false
-  #   automatic_restart           = true
-  #   provisioning_model          = "SPOT"
-  #   instance_termination_action = "STOP"
+  #   automatic_restart  = false
+  #   provisioning_model = "SPOT"
+  #   preemptible        = true
   # }
 
   // attach a disk for K3S
@@ -80,67 +77,9 @@ resource "google_compute_disk" "app_data_disk" {
   zone = var.zone
 }
 
-
-// load balancer ....
-
-
-# resource "google_compute_health_check" "http_health_check" {
-#   name                = "http-health-check"
-#   check_interval_sec  = 5
-#   timeout_sec         = 5
-#   healthy_threshold   = 2
-#   unhealthy_threshold = 2
-
-#   http_health_check {
-#     port = 80
-#   }
-# }
-
-resource "google_compute_http_health_check" "http_health_check" {
-  name                = "http-health-check"
-  request_path        = "/"
-  port                = 80
-  check_interval_sec  = 5
-  timeout_sec         = 5
-  healthy_threshold   = 2
-  unhealthy_threshold = 2
-}
-
-
-# resource "google_compute_target_pool" "k3s_pool" {
-#   name          = "k3s-target-pool"
-#   instances     = [google_compute_instance.k3s.self_link]
-#   health_checks = [google_compute_health_check.http_health_check.self_link]
-# }
-
-resource "google_compute_target_pool" "k3s_pool" {
-  name          = "k3s-target-pool"
-  instances     = [google_compute_instance.k3s.self_link]
-  health_checks = [google_compute_http_health_check.http_health_check.self_link]
-}
-
-resource "google_compute_forwarding_rule" "http_forwarding_rule" {
-  name                  = "http-forwarding-rule"
-  target                = google_compute_target_pool.k3s_pool.self_link
-  port_range            = "80"
-  ip_protocol           = "TCP"
-  load_balancing_scheme = "EXTERNAL"
-}
-
-resource "google_compute_forwarding_rule" "https_forwarding_rule" {
-  name                  = "https-forwarding-rule"
-  target                = google_compute_target_pool.k3s_pool.self_link
-  port_range            = "443"
-  ip_protocol           = "TCP"
-  load_balancing_scheme = "EXTERNAL"
-}
-
-
-
+// Outputs
 // ----------------------------------
 
-
-
 data "google_project" "project" {
   project_id = var.project_name # Use variable from tfvars
 }
@@ -154,7 +93,3 @@ output "k3s_vm_public_ip" {
   description = "Ephemeral public IP of the k3s VM"
 }
 
-output "load_balancer_ip" {
-  value       = google_compute_forwarding_rule.http_forwarding_rule.ip_address
-  description = "External IP address of the load balancer (HTTP)"
-}

gcloud/tf/provider.tf

@@ -4,6 +4,10 @@ terraform {
       source  = "hashicorp/google"
       version = "~> 4.0"
     }
+    # cloudflare = {
+    #   source  = "cloudflare/cloudflare"
+    #   version = "~> 5"
+    # }
   }
 }
 
@@ -16,9 +20,45 @@ provider "google" {
   project = var.project_name # Use variable from tfvars
   region  = "us-central1"    # Replace with your desired region
 }
+
 # provider "google" {
 #   credentials = file("<my-gcp-creds>.json")
 #   project     = var.project_name
 #   region      = var.region
 #   zone        = var.zone
 # }
+
+
+# provider "cloudflare" {
+#   api_token = var.cloudflare_api_token
+# }
+
+# variable "cloudflare_api_token" {
+#   description = "Cloudflare API token"
+#   sensitive   = true
+# }
+
+# variable "cloudflare_account_id" {
+#   description = "Cloudflare Account ID"
+#   sensitive   = true
+# }
+
+# variable "cloudflare_zone_id" {
+#   description = "Cloudflare Zone ID"
+#   sensitive   = true
+# }
+
+# variable "cloudflare_domain" {
+#   description = "Cloudflare Domain"
+#   sensitive   = true
+# }
+
+# resource "cloudflare_dns_record" "frgdr" {
+#   zone_id = var.cloudflare_zone_id
+#   name    = "frgdr"
+#   content = google_compute_instance.k3s.network_interface[0].access_config[0].nat_ip
+#   type    = "A"
+#   ttl     = 300 
+#   proxied = false
+#   comment = "Application domain record"
+# }

gcloud/tf/scripts/build-gcloud-k3s-pipeline-wait-dns.json

@@ -0,0 +1,56 @@
+[
+    {
+        "name": "run pre-flight checks",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/pre-flight-checks.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "list gcloud infrastructure",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/list_gloud_infra.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "create tfvars",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/create_tfvars.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "run tofu",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/run_tofu.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "wait for user input to continue",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/wait_for_user_input_dns.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "copy .env to k3s-vm-1",
+        "function": "RunCommand",
+        "params": [
+            "gcloud/tf/scripts/copy_env_to_first_node.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    }
+]

gcloud/tf/scripts/build-gcloud-k3s-pipeline.json

@@ -3,7 +3,7 @@
         "name": "run pre-flight checks",
         "function": "RunCommand",
         "params": [
-            "./scripts/pre-flight-checks.sh"
+            "./gcloud/tf/scripts/pre-flight-checks.sh"
         ],
         "retryCount": 0,
         "shouldAbort": true
@@ -12,7 +12,16 @@
         "name": "list gcloud infrastructure",
         "function": "RunCommand",
         "params": [
-            "./scripts/list_gloud_infra.sh"
+            "./gcloud/tf/scripts/list_gloud_infra.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "create tfvars",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/create_tfvars.sh"
         ],
         "retryCount": 0,
         "shouldAbort": true
@@ -21,7 +30,16 @@
         "name": "run tofu",
         "function": "RunCommand",
         "params": [
-            "./scripts/run_tofu.sh"
+            "./gcloud/tf/scripts/run_tofu.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "copy .env to k3s-vm-1",
+        "function": "RunCommand",
+        "params": [
+            "gcloud/tf/scripts/copy_env_to_first_node.sh"
         ],
         "retryCount": 0,
         "shouldAbort": true

gcloud/tf/scripts/cert-manager/install_cert-manager.sh

@@ -0,0 +1,34 @@
+#!/usr/bin/env bash
+
+if kubectl -n cert-manager get pods 2>/dev/null | grep -q 'Running'; then
+    echo "cert-manager pods already running. Skipping installation."
+    exit 0
+fi
+
+
+
+
+kubectl apply -f https://github.com/cert-manager/cert-manager/releases/download/v1.17.2/cert-manager.yaml
+
+
+echo "Waiting for cert-manager pods to be in 'Running' state..."
+MAX_RETRIES=10
+RETRY=0
+
+while [ $RETRY -lt $MAX_RETRIES ]; do
+    NOT_READY_PODS=$(kubectl -n cert-manager get pods --no-headers | grep -v 'Running' | wc -l)
+    if [ "$NOT_READY_PODS" -eq 0 ]; then
+        echo "All cert-manager pods are running."
+        break
+    else
+        echo "$NOT_READY_PODS pods are not ready yet. Waiting..."
+        RETRY=$((RETRY + 1))
+        sleep 5
+    fi
+done
+
+if [ "$NOT_READY_PODS" -ne 0 ]; then
+    echo "Failed to get all cert-manager pods running after $MAX_RETRIES attempts."
+    exit 1
+fi
+

gcloud/tf/scripts/copy_env_to_first_node.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+
+source .env
+
+for i in {1..10}; do
+    # Check if the instance is running
+    INSTANCE_STATUS=$(gcloud compute instances describe k3s-vm-1 --zone=us-central1-a --project="$PROJECT_NAME" --format='get(status)')
+    if [[ "$INSTANCE_STATUS" != "RUNNING" ]]; then
+        echo "Instance k3s-vm-1 is not running. Attempt $i/10. Waiting 5 seconds..."
+        sleep 5
+        continue
+    fi
+
+    # Check if the directory exists on the remote host
+    if gcloud compute ssh k3s-vm-1 --zone=us-central1-a --project="$PROJECT_NAME" --command="test -d /opt/src/infctl-cli/"; then
+        echo "/opt/src/infctl-cli/ exists on k3s-vm-1."
+        break
+    else
+        echo "/opt/src/infctl-cli/ does not exist yet. Attempt $i/10. Waiting 5 seconds..."
+        sleep 5
+    fi
+done
+
+# Final check after loop
+if ! gcloud compute ssh k3s-vm-1 --zone=us-central1-a --project="$PROJECT_NAME" --command="test -d /opt/src/infctl-cli/"; then
+    echo "ERROR: /opt/src/infctl-cli/ does not exist on k3s-vm-1 after 10 attempts. Exiting."
+    exit 1
+fi
+
+gcloud compute scp .env  k3s-vm-1:/opt/src/infctl-cli/.env --zone=us-central1-a --project=$PROJECT_NAME
+

gcloud/tf/scripts/create_tfvars.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+
+set -a
+
+# read environment variables from .env file
+# for value $PROJECT_NAME
+. .env
+
+
+# Check if PROJECT_NAME environment variable is set
+if [ -z "$PROJECT_NAME" ]; then
+  echo "Error: PROJECT_NAME environment variable is not set."
+  echo "Please set the PROJECT_NAME variable and try again."
+  exit 1
+fi
+
+# Get the directory where the script is located
+SCRIPT_DIR="$(dirname "$(readlink -f "$0")")"
+cd "$SCRIPT_DIR" || { echo "Failed to change directory to $SCRIPT_DIR"; exit 1; }
+# Define the template file path and output file path
+TEMPLATE_FILE="../terraform.tfvars.template"
+OUTPUT_FILE="../terraform.tfvars"
+
+
+# Use envsubst to substitute the PROJECT_NAME variable into the template
+envsubst < "$TEMPLATE_FILE" > "$OUTPUT_FILE"
+if [ $? -ne 0 ]; then
+  echo "Error: Failed to substitute variables in the template."
+  exit 1
+fi
+
+echo "tfvars has been created at $OUTPUT_FILE"

gcloud/tf/scripts/forgejo/create_ingress.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+set -a
+
+# read environment variables from .env file
+# for value of APP_DOMAIN_NAME
+
+. .env
+
+if [ -z "$APP_DOMAIN_NAME" ]; then
+  echo "Error: APP_DOMAIN_NAME environment variable is not set. Please set it in the .env file."
+  exit 1
+fi
+
+# Get the directory where the script is located
+SCRIPT_DIR="$(dirname "$(readlink -f "$0")")"
+cd "$SCRIPT_DIR" || { echo "Failed to change directory to $SCRIPT_DIR"; exit 1; }
+# Define the template file path and output file path
+TEMPLATE_FILE="../../k3s/forgejo/ingress.yaml.template"
+OUTPUT_FILE="../../k3s/forgejo/ingress.yaml"
+
+
+# Use envsubst to substitute the APP_DOMAIN_NAME variable into the template
+envsubst < "$TEMPLATE_FILE" > "$OUTPUT_FILE"
+if [ $? -ne 0 ]; then
+  echo "Error: Failed to substitute variables in the template."
+  exit 1
+fi
+
+echo "Ingress configuration has been created at $OUTPUT_FILE"   

gcloud/tf/scripts/forgejo/create_issuer.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+
+set -a
+
+# read environment variables from .env file
+# for value of EMAIL
+
+. .env
+
+
+# Check if EMAIL environment variable is set
+if [ -z "$EMAIL" ]; then
+  echo "Error: EMAIL environment variable is not set."
+  echo "Please set the EMAIL variable and try again."
+  exit 1
+fi
+
+# Get the directory where the script is located
+SCRIPT_DIR="$(dirname "$(readlink -f "$0")")"
+cd "$SCRIPT_DIR" || { echo "Failed to change directory to $SCRIPT_DIR"; exit 1; }
+# Define the template file path and output file path
+TEMPLATE_FILE="../../k3s/forgejo/issuer.yaml.template"
+OUTPUT_FILE="../../k3s/forgejo/issuer.yaml"
+
+
+# Use envsubst to substitute the EMAIL variable into the template
+envsubst < "$TEMPLATE_FILE" > "$OUTPUT_FILE"
+if [ $? -ne 0 ]; then
+  echo "Error: Failed to substitute variables in the template."
+  exit 1
+fi
+
+echo "Issuer configuration has been created at $OUTPUT_FILE"

gcloud/tf/scripts/forgejo/install_forgejo.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+set -e
+
+echo "Installing Forgejo"
+
+# Get the directory where the script is located
+SCRIPT_DIR="$(dirname "$(readlink -f "$0")")"
+# Define namespace
+NAMESPACE="forgejo"
+MANIFESTS_DIR="${SCRIPT_DIR}/../../k3s/forgejo"
+
+echo "Creating namespace..."
+if ! kubectl get namespace "${NAMESPACE}" >/dev/null 2>&1; then
+    kubectl create namespace "${NAMESPACE}"
+else
+    echo "Namespace '${NAMESPACE}' already exists."
+fi
+
+echo "Creating PersistentVolumeClaim..."
+kubectl apply -f ${MANIFESTS_DIR}/pvc.yaml
+
+
+echo "Creating Service..."
+kubectl apply -f ${MANIFESTS_DIR}/service.yaml
+
+
+echo "Creating Deployment..."
+kubectl apply -f ${MANIFESTS_DIR}/deployment.yaml
+
+
+echo "Creating Certificate Issuer..."
+kubectl apply -f ${MANIFESTS_DIR}/issuer.yaml
+
+
+echo "Creating Ingress..."
+kubectl apply -f ${MANIFESTS_DIR}/ingress.yaml
+
+
+echo "Forgejo installation complete."
+echo "Verify deployment with: kubectl -n ${NAMESPACE} get pods,svc,ingress,pvc"
+
+exit;
+
+# Note: The ingressTCP.yaml is for a different application (galene) and should be applied separately
+# echo "Note: The ingressTCP.yaml is for the galene application and has not been applied."

gcloud/tf/scripts/install-forgejo-pipeline.json

@@ -0,0 +1,47 @@
+[
+    {
+        "name": "install cert-manager",
+        "function": "RunCommand",
+        "params": [
+            "gcloud/tf/scripts/cert-manager/install_cert-manager.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "install traefik",
+        "function": "RunCommand",
+        "params": [
+            "gcloud/tf/scripts/install_traefik.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "create forgejo ingress",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/forgejo/create_ingress.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "create forgejo issuer",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/forgejo/create_issuer.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    },
+    {
+        "name": "install forgejo",
+        "function": "RunCommand",
+        "params": [
+            "./gcloud/tf/scripts/forgejo/install_forgejo.sh"
+        ],
+        "retryCount": 0,
+        "shouldAbort": true
+    }
+]

gcloud/tf/scripts/k3s-vm-startup.sh

@@ -1,8 +1,11 @@
 #!/bin/bash
 
+# Redirect all output to a log file for reliability
+exec > /tmp/startup.log 2>&1
+
 INFCTL_GIT_REPO="https://codeberg.org/headshed/infctl-cli.git"
-INFCTL_GIT_REPO_BRANCH="feature/gcloud-k3s"
-INFCTL_INSTALL_DIR="/opt/infctl-cli"
+INFCTL_GIT_REPO_BRANCH="main"
+INFCTL_INSTALL_DIR="/opt/src"
 
 # ensure only run once
 if [[ -f /etc/startup_was_launched ]]; then exit 0; fi
@@ -100,3 +103,32 @@ if [[ ! -d "$INFCTL_INSTALL_DIR" ]]; then
     chown -R user:user "$INFCTL_INSTALL_DIR"
 fi
 
+for i in {1..100}; do
+    if [[ -f /opt/src/infctl-cli/.env ]]; then
+        echo ".env file found."
+        break
+    else
+        echo ".env file not found. Attempt $i/100. Waiting 5 seconds..."
+        sleep 5
+    fi
+done
+
+# Final check after loop
+if [[ ! -f /opt/src/infctl-cli/.env ]]; then
+    echo "ERROR: .env file not found after 10 attempts. Exiting."
+    exit 1
+fi
+
+# load .env file
+source /opt/src/infctl-cli/.env
+cd $INFCTL_INSTALL_DIR/infctl-cli || "echo 'Failed to change directory to $INFCTL_INSTALL_DIR/infctl-cli' ; exit 1"
+
+# check to see if INSTALL_FORGEJO is set to "true"
+if [[ "$INSTALL_FORGEJO" == "true" ]]; then
+    # install forgejo using infctl
+    # ....
+    export KUBECONFIG=/etc/rancher/k3s/k3s.yaml
+    LOG_FORMAT=none infctl -f "${INFCTL_INSTALL_DIR}/infctl-cli/gcloud/tf/scripts/install-forgejo-pipeline.json" 
+    touch /etc/forgejo_was_installed
+
+fi

gcloud/tf/scripts/pre-flight-checks.sh

@@ -47,4 +47,19 @@ echo
 kubectl version --client
 echo 
 
+echo "🧪 checking we have envsubst insatalled..."
+if ! command -v envsubst &> /dev/null
+then
+    echo "❌ envsubst could not be found, please install it first"
+    echo
+    echo "on ubuntu you can install it with: sudo apt-get install -y gettext-base"
+    echo
+    exit 1
+fi
+echo "✅ envsubst is installed,..."
+echo
+envsubst --version
+echo    
 
+echo "✅ Pre-flight checks passed. You are ready to proceed 🙂"
+echo

gcloud/tf/scripts/run_tofu.sh

@@ -1,5 +1,12 @@
 #!/usr/bin/env bash
 
+# Get the directory where the script is located
+SCRIPT_DIR="$(dirname "$(readlink -f "$0")")"
+cd "$SCRIPT_DIR" || { echo "Failed to change directory to $SCRIPT_DIR"; exit 1; }
+TF_DIR="../"
+
+cd "$TF_DIR" || { echo "Failed to change directory to $TF_DIR"; exit 1; }
+
 if [[ -d ".terraform" && -f ".terraform.lock.hcl" ]]; then
     echo "✅ Terraform already initialized"
     # tofu init

gcloud/tf/scripts/wait_for_user_input_dns.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+echo "Please configure DNS using the IP address from the previous stage."
+echo "you have 120 seconds."
+for i in {120..1}; do
+    echo -ne "Time remaining: $i seconds\r"
+    sleep 1
+done
+echo ""
+
+exit 0

gcloud/tf/terraform.tfvars.template

@@ -0,0 +1,13 @@
+// Your GCP project name
+// it will be refererred as the project id
+// in Google Cloud
+// ----------------------------------
+project_name = "${PROJECT_NAME}"
+
+// where to deploy to
+// region
+region = "us-central1"
+zone   = "us-central1-a"
+
+// application name
+app_name = "${PROJECT_NAME}-k3s-cluster"

scripts/failue.sh

@@ -1,20 +1,29 @@
 #!/usr/bin/env bash
 
-# sleep 5
+for i in {1..5}; do
+    echo "working ..."
+    sleep 0.5
+done
 
-echo "crash"
+sleep 2
 
-# sleep 1
+echo "not working ..."
 
-echo "bang"
+sleep 1
 
-# sleep 2
+figlet "boom"
 
-echo "wallop"
+sleep 1
 
-# sleep 1
+figlet  "bang"
 
-echo "Houston, we have a problem"
+sleep 2
+
+echo "oh dear, oh my..."
+
+sleep 1
+
+figlet "Houston, we have a problem"
 
 sleep 1
 

scripts/success.sh

@@ -1,20 +1,29 @@
 #!/usr/bin/env bash
 
-# sleep 5
+for i in {1..5}; do
+    echo "working ..."
+    sleep 0.5
+done
 
-echo "bish"
+sleep 2
 
-# sleep 1
+echo "still working ..."
 
-echo "bash"
+sleep 1
 
-# sleep 2
+figlet "bish"
 
-echo "bosh"
+sleep 1
 
-# sleep 1
+figlet "bash"
 
-echo "lovely jubbly"
+sleep 2
+
+figlet "bosh"
+
+sleep 1
+
+figlet "LOVELY JUBBLY"
 
 sleep 1
 

vagrant/dev/ubuntu/Vagrantfile

@@ -117,7 +117,11 @@ Vagrant.configure("2") do |config|
       vb.cpus = 1
     end    
 
-    ws.vm.provision "shell", path: "ansible/provision_workstation.sh"
+    ws.vm.provision "shell", 
+      path: "ansible/provision_workstation.sh",
+      env: {
+        "INSTALL_LONGHORN" => ENV['INSTALL_LONGHORN'] || "false"
+      }
   end
 
 

vagrant/dev/ubuntu/ansible/install_longhorn.yaml

@@ -0,0 +1,16 @@
+---
+- name: Install longhorn using infctl
+  hosts: localhost
+  become: true
+  become_user: vagrant
+  serial: 1 # Ensure tasks are executed one host at a time
+  vars_files:
+    - vars.yaml
+
+  tasks:
+
+    - name: run infctl longhorn pipeline
+      ansible.builtin.command: >
+        bash -c 'cd /home/vagrant && LOG_FILE=/tmp/longhorn_log.txt LOG_FORMAT=basic infctl -f pipelines/vagrant-longhorn.json'
+      register: longhorn_result
+      ignore_errors: false

vagrant/dev/ubuntu/ansible/install_metallb.yaml

@@ -0,0 +1,16 @@
+---
+- name: Install metallb using infctl
+  hosts: localhost
+  become: true
+  become_user: vagrant
+  serial: 1 # Ensure tasks are executed one host at a time
+  vars_files:
+    - vars.yaml
+
+  tasks:
+
+    - name: run ======== infctl metallb pipeline
+      ansible.builtin.command: >
+        bash -c 'cd /home/vagrant && LOG_FILE=/tmp/metallb_log.txt LOG_FORMAT=basic infctl -f ./pipelines/vagrant-metallb.json'
+      register: metallb_result
+      ignore_errors: false

vagrant/dev/ubuntu/ansible/install_traefik.yaml

@@ -0,0 +1,20 @@
+---
+- name: Install traefik using infctl
+  hosts: localhost
+  become: true
+  become_user: vagrant
+  serial: 1 # Ensure tasks are executed one host at a time
+  vars_files:
+    - vars.yaml
+
+  tasks:
+
+    - name: run infctl traefik pipeline
+      ansible.builtin.command: infctl -f pipelines/vagrant-ingress.json
+      args:
+        chdir: /home/vagrant
+      environment:
+        LOG_FILE: /tmp/traefik_log.txt
+        LOG_FORMAT: none
+      register: traefik_result
+      ignore_errors: false

vagrant/dev/ubuntu/ansible/provision_workstation.sh

@@ -4,7 +4,8 @@
 sudo apt-get update
 sudo apt-get install -y software-properties-common git vim python3.10-venv jq figlet
 
-source /vagrant/.envrc
+# shellcheck disable=SC1091
+source /vagrant/.envrc 
 
 # Set up ansible environment for vagrant user
 sudo -u vagrant mkdir -p /home/vagrant/.ansible
@@ -24,10 +25,10 @@ sudo chmod +x /home/vagrant/pipelines/*.sh
 
 # Copy the Vagrant private keys (these will be synced by Vagrant)
 for i in {1..3}; do
-sudo -u vagrant cp /vagrant/.vagrant/machines/vm$i/virtualbox/private_key /home/vagrant/.ssh/vm${i}_key
-sudo -u root cp /vagrant/.vagrant/machines/vm$i/virtualbox/private_key /root/.ssh/vm${i}_key
-sudo chmod 600 /home/vagrant/.ssh/vm${i}_key
-sudo chmod 600 /root/.ssh/vm${i}_key
+sudo -u vagrant cp "/vagrant/.vagrant/machines/vm$i/virtualbox/private_key" "/home/vagrant/.ssh/vm${i}_key"
+sudo -u root cp "/vagrant/.vagrant/machines/vm$i/virtualbox/private_key" "/root/.ssh/vm${i}_key"
+sudo chmod 600 "/home/vagrant/.ssh/vm${i}_key"
+sudo chmod 600 "/root/.ssh/vm${i}_key"
 done
 
 # Disable host key checking for easier learning
@@ -46,18 +47,17 @@ cd "$ANSIBLE_DIR" || {
 if [ ! -d "venv" ]; then
     echo "Creating Python virtual environment in ./venv..."
     python3 -m venv venv
-    source "venv/bin/activate"
-    if [ $? -ne 0 ]; then
+    # shellcheck disable=SC1091
+    if ! source "venv/bin/activate"; then
         echo "Failed to activate virtual environment. Please check your Python installation."
         exit 1
     fi
     echo "Virtual environment created and activated."
-    cp /vagrant/ansible/requirements.txt .
+    cp "/vagrant/ansible/requirements.txt" .
     if [ -f "requirements.txt" ]; then
         echo "Installing dependencies from requirements.txt..."
         pip install --upgrade pip
-        pip install -r requirements.txt
-        if [ $? -ne 0 ]; then
+        if ! pip install -r requirements.txt; then
             echo "Failed to install dependencies from requirements.txt."
             exit 1
         fi
@@ -76,7 +76,13 @@ ls -al "$ANSIBLE_VENV_DIR/bin/activate"
 
 if [ -d "$ANSIBLE_VENV_DIR" ]; then
     echo "Activating Ansible virtual environment..."
-    source "$ANSIBLE_VENV_DIR/bin/activate"
+    if [ -f "$ANSIBLE_VENV_DIR/bin/activate" ]; then
+        # shellcheck source=/dev/null
+        source "$ANSIBLE_VENV_DIR/bin/activate"
+    else
+        echo "Virtualenv activate script not found!" >&2
+        exit 1
+    fi
 else
     echo "Ansible virtual environment not found at $ANSIBLE_VENV_DIR. Please create it before running this script."
     exit 1
@@ -86,13 +92,13 @@ echo ""
 
 ansible --version
 
-if [ $? -ne 0 ]; then
+if ! ansible --version; then
     echo "Ansible is not installed or not found in the virtual environment. Please check your installation."
     exit 1
 fi
 
 
-eval `ssh-agent -s`
+eval "$(ssh-agent -s)"
 ssh-add # ~/machines/*/virtualbox/private_key
 
 BASHRC="/home/vagrant/.bashrc"
@@ -103,10 +109,11 @@ if ! grep -qF "$BLOCK_START" "$BASHRC"; then
     cat <<'EOF' >> "$BASHRC"
 
 # ADDED BY infctl provisioning
-eval `ssh-agent -s`
+eval "$(ssh-agent -s)"
 ssh-add ~/machines/*/virtualbox/private_key
 ssh-add -L
-source /vagrant/.envrc
+# shellcheck disable=SC1091
+source /vagrant/.envrc 
 EOF
 else
     echo "Provisioning block already present in $BASHRC"
@@ -114,7 +121,7 @@ fi
 
 echo 
 echo -------------------------
-echo 
+echo
 
 su - vagrant
 id
@@ -125,48 +132,63 @@ echo
 
 ssh-add ~/.ssh/vm*_key
 
-ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible --inventory-file /home/vagrant/ansible/ansible_inventory.ini  -m ping vm1,vm2,vm3 
-
-if [ $? -ne 0 ]; then
+if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible --inventory-file /home/vagrant/ansible/ansible_inventory.ini  -m ping vm1,vm2,vm3; then
     echo "Ansible ping failed. Please check your Vagrant VMs and network configuration."
     exit 1
 fi
 
 # install_keepalived.yaml
-ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_keepalived.yaml --inventory-file ansible_inventory.ini 
-if [ $? -ne 0 ]; then
+if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_keepalived.yaml --inventory-file ansible_inventory.ini; then
     echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
     exit 1
 fi
 echo "Keepalived installation completed."
 
 # install_k3s_3node.yaml
-ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_k3s_3node.yaml --inventory-file ansible_inventory.ini 
-if [ $? -ne 0 ]; then
+if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_k3s_3node.yaml --inventory-file ansible_inventory.ini; then
     echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
     exit 1
 fi
 
 # copy_k8s_config.yaml
-ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook copy_k8s_config.yaml --inventory-file ansible_inventory.ini 
-if [ $? -ne 0 ]; then
+if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook copy_k8s_config.yaml --inventory-file ansible_inventory.ini; then
     echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
     exit 1
 fi
 
-ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_dnsmasq.yaml --inventory-file ansible_inventory.ini 
-if [ $? -ne 0 ]; then
+if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_dnsmasq.yaml --inventory-file ansible_inventory.ini; then
     echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
     exit 1
 fi
 
+# Wait for Kubernetes API to be ready
+echo "Waiting for 30 seconds for Kubernetes API to be ready..."
+sleep 30
+echo "done waiting for kubernetes API"
+
 # check infctl 
-cd /home/vagrant
-bash /home/vagrant/scripts/check_install_infctl.sh 
-if [ $? -ne 0 ]; then
+cd /home/vagrant || exit
+if ! bash /home/vagrant/scripts/check_install_infctl.sh; then
     echo "infctl check failed. Please check your installation."
     exit 1
 fi
 
+# Optionally install Longhorn, MetalLB, and Traefik
+if [ "${INSTALL_LONGHORN}" = "true" ]; then
+    cd /home/vagrant/ansible || { echo "Failed to change directory to /home/vagrant/ansible"; exit 1; }
 
+    if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_longhorn.yaml --inventory-file ansible_inventory.ini; then
+        echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
+        exit 1
+    fi
 
+    if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_metallb.yaml --inventory-file ansible_inventory.ini; then
+        echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
+        exit 1
+    fi
+
+    if ! ANSIBLE_SUPPRESS_INTERPRETER_DISCOVERY_WARNING=1 ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook install_traefik.yaml --inventory-file ansible_inventory.ini; then
+        echo "Ansible playbook failed. Please check your Vagrant VMs and network configuration."
+        exit 1
+    fi
+fi

vagrant/dev/ubuntu/scripts/install_metallb.sh

@@ -12,24 +12,31 @@ if ! kubectl get deployment -n metallb-system controller &>/dev/null; then
     exit 1
   fi
   
-  # Wait for MetalLB components to be ready
-  echo "Waiting for MetalLB components to be ready..."
-  kubectl wait --namespace metallb-system \
-    --for=condition=ready pod \
-    --selector=app=metallb \
-    --timeout=90s
+  echo "Waiting for MetalLB pods to be in 'Running' state..."
+  MAX_RETRIES=10
+  RETRY=0
+
+  while [ $RETRY -lt $MAX_RETRIES ]; do
+    NOT_READY_PODS=$(kubectl -n metallb-system get pods --no-headers | grep -v 'Running' | wc -l)
+    if [ "$NOT_READY_PODS" -eq 0 ]; then
+      echo "All MetalLB pods are running."
+      break
+    else
+      echo "$NOT_READY_PODS MetalLB pods are not ready yet. Waiting..."
+      RETRY=$((RETRY + 1))
+      sleep 5
+    fi
+  done
+
+  if [ "$NOT_READY_PODS" -ne 0 ]; then
+    echo "Failed to get all MetalLB pods running after $MAX_RETRIES attempts."
+    exit 1
+  fi
 
 else
   echo "MetalLB is already installed."
 fi
 
-# Wait for the webhook service to be ready
-echo "Waiting for MetalLB webhook service to be ready..."
-kubectl wait --namespace metallb-system \
-  --for=condition=ready pod \
-  --selector=component=webhook \
-  --timeout=90s
-
 # Check if the IPAddressPool already exists
 if ! kubectl get ipaddresspool -n metallb-system default &>/dev/null; then
   echo "Creating MetalLB IPAddressPool..."