Fix 6 P1 infrastructure issues from code review (FRE-4574)

- ALB: deploy to public subnets instead of private (adds public_subnet_ids var)
- ECS: fix launch_desired_count → launch_type = FARGATE
- Secrets: accept actual RDS/ElastiCache endpoints from parent module
- Deploy: fix circular dependency (needs.detect → steps.detect)
- Health check: dynamic ALB DNS lookup via aws elbv2 CLI
- Health check: exit 1 on failure so rollback triggers

Co-Authored-By: Paperclip <noreply@paperclip.ing>

.github/workflows/deploy.yml

@@ -33,7 +33,7 @@ jobs:
       - name: Calculate tag
         id: tag
         run: |
-          if [ "${{ needs.detect-environment.outputs.environment }}" = "production" ]; then
+          if [ "${{ steps.detect.outputs.environment }}" = "production" ]; then
             echo "tag=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
           else
             echo "tag=${{ github.sha }}" >> $GITHUB_OUTPUT
@@ -169,36 +169,47 @@ jobs:
     needs: [detect-environment, deploy-ecs]
     environment: ${{ needs.detect-environment.outputs.environment }}
     steps:
+      - name: Configure AWS
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: us-east-1
       - name: Wait for deployment
         run: sleep 30
       - name: Health Check
-        uses: jasongd/retry-action@v2
+        id: health
-        with:
+        run: |
-          timeout-minutes: 5
+          ENV="${{ needs.detect-environment.outputs.environment }}"
-          retry-minutes: 10
+          CLUSTER="shieldai-${ENV}"
-          command: |
-            ALB_DNS=$(aws ecs describe-services \
-              --cluster "shieldai-${{ needs.detect-environment.outputs.environment }}" \
-              --services "shieldai-${{ needs.detect-environment.outputs.environment }}-api" \
-              --query 'services[0].loadBalancers[0].targetGroupArn' --output text)
 
-            for service in api darkwatch spamshield voiceprint; do
+          ALB_DNS=$(aws elbv2 describe-load-balancers \
-              PORT=$(case $service in
+            --query "LoadBalancers[?contains(LoadBalancerName, '${CLUSTER}-alb')].DNSName" \
-                api) echo 3000;;
+            --output text)
-                darkwatch) echo 3001;;
-                spamshield) echo 3002;;
-                voiceprint) echo 3003;;
-              esac)
 
-              HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
+          if [ -z "$ALB_DNS" ]; then
-                "https://shieldai-${{ needs.detect-environment.outputs.environment }}-alb.us-east-1.elb.amazonaws.com/health" || true)
+            echo "Health check failed: ALB DNS not found"
+            exit 1
+          fi
 
-              if [ "$HTTP_CODE" = "200" ]; then
+          echo "ALB DNS: $ALB_DNS"
-                echo "Health check passed: $service"
+
-              else
+          FAILED=0
-                echo "Health check failed: $service (HTTP $HTTP_CODE)"
+          for service in api darkwatch spamshield voiceprint; do
-              fi
+            HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
-            done
+              "http://${ALB_DNS}/health" || true)
+
+            if [ "$HTTP_CODE" = "200" ]; then
+              echo "Health check passed: $service"
+            else
+              echo "Health check failed: $service (HTTP $HTTP_CODE)"
+              FAILED=1
+            fi
+          done
+
+          if [ "$FAILED" -eq 1 ]; then
+            exit 1
+          fi
 
   rollback:
     name: Rollback on Failure

infra/main.tf

@@ -49,6 +49,7 @@ module "ecs" {
   cluster_name       = "${var.project_name}-${var.environment}"
   vpc_id             = module.vpc.vpc_id
   subnet_ids         = module.vpc.private_subnet_ids
+  public_subnet_ids  = module.vpc.public_subnet_ids
   security_group_ids = [module.vpc.ecs_security_group_id]
   services           = var.services
   container_images   = var.container_images
@@ -91,9 +92,11 @@ module "s3" {
 module "secrets" {
   source = "./modules/secrets"
 
-  environment  = var.environment
+  environment          = var.environment
-  project_name = var.project_name
+  project_name         = var.project_name
-  secrets      = var.secrets
+  rds_endpoint         = module.rds.db_endpoint
+  elasticache_endpoint = module.elasticache.cache_endpoint
+  secrets              = var.secrets
 }
 
 module "cloudwatch" {

infra/modules/ecs/main.tf

@@ -14,7 +14,12 @@ variable "vpc_id" {
 }
 
 variable "subnet_ids" {
-  description = "Private subnet IDs"
+  description = "Private subnet IDs for ECS tasks"
+  type        = list(string)
+}
+
+variable "public_subnet_ids" {
+  description = "Public subnet IDs for ALB"
   type        = list(string)
 }
 
@@ -273,7 +278,7 @@ resource "aws_ecs_service" "services" {
   task_definition = aws_ecs_task_definition.services[each.key].arn
   desired_count   = var.environment == "production" ? 3 : 1
 
-  launch_desired_count = "FARGATE"
+  launch_type = "FARGATE"
 
   network_configuration {
     subnets          = var.subnet_ids
@@ -307,7 +312,7 @@ resource "aws_lb" "main" {
   internal           = false
   load_balancer_type = "application"
   security_groups    = var.security_group_ids
-  subnets            = var.subnet_ids
+  subnets            = var.public_subnet_ids
 
   tags = {
     Name = "${var.cluster_name}-alb"

infra/modules/secrets/main.tf

@@ -8,6 +8,16 @@ variable "project_name" {
   type        = string
 }
 
+variable "rds_endpoint" {
+  description = "RDS instance endpoint"
+  type        = string
+}
+
+variable "elasticache_endpoint" {
+  description = "ElastiCache primary endpoint"
+  type        = string
+}
+
 variable "secrets" {
   description = "Secrets to store"
   type        = map(string)
@@ -29,15 +39,13 @@ resource "aws_secretsmanager_secret_version" "main" {
   secret_id = aws_secretsmanager_secret.main.id
 
   secret_string = jsonencode(merge({
-    DATABASE_URL = "postgresql://shieldai:${var.project_name}@${var.project_name}-${var.environment}-db.${data.aws_caller_identity.current.account_id}.us-east-1.rds.amazonaws.com:5432/shieldai"
+    DATABASE_URL = "postgresql://shieldai:${var.project_name}@${var.rds_endpoint}:5432/shieldai"
-    REDIS_URL    = "redis://${var.project_name}-${var.environment}-redis.${data.aws_caller_identity.current.account_id}.us-east-1.cache.amazonaws.com:6379"
+    REDIS_URL    = "redis://${var.elasticache_endpoint}:6379"
     NODE_ENV     = var.environment
     LOG_LEVEL    = var.environment == "production" ? "info" : "debug"
   }, var.secrets))
 }
 
-data "aws_caller_identity" "current" {}
-
 output "secrets_manager_arn" {
   description = "Secrets Manager ARN"
   value       = aws_secretsmanager_secret.main.arn