Add Terraform AWS infrastructure and enhanced CI/CD pipeline (FRE-4574)

- Terraform modules: VPC, ECS Fargate, RDS PostgreSQL, ElastiCache Redis, S3, Secrets Manager, CloudWatch
- Multi-environment support: staging and production configs
- ECS auto-scaling: CPU-based scaling with configurable min/max
- CI/CD: pnpm caching, Docker Buildx, Trivy security scanning, Terraform plan on PR
- Deploy: ECS service updates with automatic rollback on health check failure
- Backup: automated RDS snapshots, S3 versioning, ElastiCache snapshots
- Monitoring: CloudWatch dashboards, CPU/memory/5xx alarms
- Rollback script for manual service rollback
- Infrastructure documentation with architecture overview

.github/workflows/ci.yml

@@ -24,11 +24,14 @@ jobs:
         uses: actions/setup-node@v4
         with:
           node-version: ${{ env.NODE_VERSION }}
-          cache: "npm"
+          cache: "pnpm"
+      - uses: pnpm/action-setup@v4
+        with:
+          version: ${{ env.PNPM_VERSION }}
       - name: Install dependencies
-        run: npm ci
+        run: pnpm install --frozen-lockfile
       - name: Run linter
-        run: npm run lint
+        run: pnpm lint
 
   typecheck:
     name: Type Check
@@ -39,11 +42,14 @@ jobs:
         uses: actions/setup-node@v4
         with:
           node-version: ${{ env.NODE_VERSION }}
-          cache: "npm"
+          cache: "pnpm"
+      - uses: pnpm/action-setup@v4
+        with:
+          version: ${{ env.PNPM_VERSION }}
       - name: Install dependencies
-        run: npm ci
+        run: pnpm install --frozen-lockfile
       - name: Build all packages
-        run: npm run build
+        run: pnpm build
 
   test:
     name: Test Suite
@@ -77,15 +83,14 @@ jobs:
         uses: actions/setup-node@v4
         with:
           node-version: ${{ env.NODE_VERSION }}
-          cache: "npm"
+          cache: "pnpm"
+      - uses: pnpm/action-setup@v4
+        with:
+          version: ${{ env.PNPM_VERSION }}
       - name: Install dependencies
-        run: npm ci
+        run: pnpm install --frozen-lockfile
-      - name: Generate Prisma client
-        run: npx prisma generate --schema=packages/db/prisma/schema.prisma
-        env:
-          DATABASE_URL: "postgresql://shieldai:shieldai_dev@localhost:5432/shieldai"
       - name: Run tests with coverage
-        run: npm run test:coverage
+        run: pnpm test:coverage
         env:
           DATABASE_URL: "postgresql://shieldai:shieldai_dev@localhost:5432/shieldai"
           REDIS_URL: "redis://localhost:6379"
@@ -100,8 +105,9 @@ jobs:
   docker-build:
     name: Docker Build
     runs-on: ubuntu-latest
-    needs: [lint, typecheck]
+    needs: [lint, typecheck, test]
     strategy:
+      fail-fast: false
       matrix:
         include:
           - name: api
@@ -118,6 +124,8 @@ jobs:
             dockerfile: services/voiceprint/Dockerfile
     steps:
       - uses: actions/checkout@v4
+      - name: Docker Buildx
+        uses: docker/setup-buildx-action@v3
       - name: Build Docker image
         uses: docker/build-push-action@v5
         with:
@@ -127,3 +135,45 @@ jobs:
           tags: shieldai-${{ matrix.name }}:${{ github.sha }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
+
+  security-scan:
+    name: Security Scan
+    runs-on: ubuntu-latest
+    needs: [lint]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Run npm audit
+        run: pnpm audit --prod
+        continue-on-error: true
+      - name: Trivy filesystem scan
+        uses: aquasecurity/trivy-action@master
+        with:
+          scan-type: fs
+          scan-ref: "."
+          format: table
+          exit-code: 1
+          ignore-unfixed: true
+          severity: CRITICAL,HIGH
+
+  terraform-plan:
+    name: Terraform Plan
+    runs-on: ubuntu-latest
+    needs: [lint]
+    if: github.event_name == 'pull_request'
+    steps:
+      - uses: actions/checkout@v4
+      - name: Terraform Format
+        working-directory: infra
+        run: terraform fmt -check -diff
+      - name: Terraform Init
+        working-directory: infra
+        run: terraform init
+      - name: Terraform Validate
+        working-directory: infra
+        run: terraform validate
+      - name: Terraform Plan
+        working-directory: infra
+        run: terraform plan -var-file=environments/staging/terraform.tfvars.example -no-color
+        env:
+          TF_VAR_hibp_api_key: ${{ secrets.HIBP_API_KEY }}
+          TF_VAR_resend_api_key: ${{ secrets.RESEND_API_KEY }}

.github/workflows/deploy.yml

@@ -12,6 +12,7 @@ concurrency:
 
 env:
   NODE_VERSION: "20"
+  PNPM_VERSION: "9"
 
 jobs:
   detect-environment:
@@ -19,6 +20,7 @@ jobs:
     runs-on: ubuntu-latest
     outputs:
       environment: ${{ steps.detect.outputs.environment }}
+      tag: ${{ steps.tag.outputs.tag }}
     steps:
       - name: Detect deployment target
         id: detect
@@ -28,13 +30,59 @@ jobs:
           else
             echo "environment=staging" >> $GITHUB_OUTPUT
           fi
+      - name: Calculate tag
+        id: tag
+        run: |
+          if [ "${{ needs.detect-environment.outputs.environment }}" = "production" ]; then
+            echo "tag=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
+          else
+            echo "tag=${{ github.sha }}" >> $GITHUB_OUTPUT
+          fi
+
+  terraform-apply:
+    name: Terraform Apply
+    runs-on: ubuntu-latest
+    needs: detect-environment
+    environment: ${{ needs.detect-environment.outputs.environment }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup Terraform
+        uses: hashicorp/setup-terraform@v3
+        with:
+          terraform_version: "~> 1.5"
+      - name: Terraform Init
+        working-directory: infra/environments/${{ needs.detect-environment.outputs.environment }}
+        run: terraform init -backend-config="bucket=shieldai-${{ needs.detect-environment.outputs.environment }}-terraform-state"
+      - name: Terraform Plan
+        id: plan
+        working-directory: infra/environments/${{ needs.detect-environment.outputs.environment }}
+        run: |
+          terraform plan \
+            -var="hibp_api_key=${{ secrets.HIBP_API_KEY }}" \
+            -var="resend_api_key=${{ secrets.RESEND_API_KEY }}" \
+            -var="sentry_dsn=${{ secrets.SENTRY_DSN }}" \
+            -var="datadog_api_key=${{ secrets.DATADOG_API_KEY }}" \
+            -no-color | tee /tmp/terraform-plan.out
+      - name: Terraform Apply
+        working-directory: infra/environments/${{ needs.detect-environment.outputs.environment }}
+        run: |
+          terraform apply -auto-approve \
+            -var="hibp_api_key=${{ secrets.HIBP_API_KEY }}" \
+            -var="resend_api_key=${{ secrets.RESEND_API_KEY }}" \
+            -var="sentry_dsn=${{ secrets.SENTRY_DSN }}" \
+            -var="datadog_api_key=${{ secrets.DATADOG_API_KEY }}"
+        env:
+          AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          AWS_DEFAULT_REGION: us-east-1
 
   build-and-push:
     name: Build and Push Docker Images
     runs-on: ubuntu-latest
-    needs: detect-environment
+    needs: [detect-environment]
     environment: ${{ needs.detect-environment.outputs.environment }}
     strategy:
+      fail-fast: false
       matrix:
         include:
           - name: api
@@ -47,6 +95,8 @@ jobs:
             dockerfile: services/voiceprint/Dockerfile
     steps:
       - uses: actions/checkout@v4
+      - name: Docker Buildx
+        uses: docker/setup-buildx-action@v3
       - name: Login to Container Registry
         uses: docker/login-action@v3
         with:
@@ -55,47 +105,127 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Calculate image tag
         id: tag
-        run: |
+        run: echo "tag=${{ needs.detect-environment.outputs.tag }}" >> $GITHUB_OUTPUT
-          if [ "${{ needs.detect-environment.outputs.environment }}" = "production" ]; then
-            echo "tag=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
-          else
-            echo "tag=staging-${{ github.sha }}" >> $GITHUB_OUTPUT
-          fi
       - name: Build and push ${{ matrix.name }}
         uses: docker/build-push-action@v5
         with:
           context: .
           file: ${{ matrix.dockerfile }}
           push: true
-          tags: ghcr.io/${{ github.repository_owner }}/shieldai-${{ matrix.name }}:${{ steps.tag.outputs.tag }}
+          tags: |
+            ghcr.io/${{ github.repository_owner }}/shieldai-${{ matrix.name }}:${{ steps.tag.outputs.tag }}
+            ghcr.io/${{ github.repository_owner }}/shieldai-${{ matrix.name }}:latest
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
-  deploy:
+  deploy-ecs:
-    name: Deploy to ${{ needs.detect-environment.outputs.environment }}
+    name: Deploy to ECS
     runs-on: ubuntu-latest
-    needs: [detect-environment, build-and-push]
+    needs: [detect-environment, terraform-apply, build-and-push]
     environment: ${{ needs.detect-environment.outputs.environment }}
+    strategy:
+      fail-fast: false
+      matrix:
+        service: [api, darkwatch, spamshield, voiceprint]
     steps:
       - uses: actions/checkout@v4
-      - name: Calculate deployment tag
+      - name: Configure AWS
-        id: tag
+        uses: aws-actions/configure-aws-credentials@v4
-        run: |
-          if [ "${{ needs.detect-environment.outputs.environment }}" = "production" ]; then
-            echo "tag=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
-          else
-            echo "tag=staging-${{ github.sha }}" >> $GITHUB_OUTPUT
-          fi
-      - name: Deploy via Docker Compose
-        uses: appleboy/ssh-action@v1
         with:
-          host: ${{ secrets.DEPLOY_HOST }}
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          username: ${{ secrets.DEPLOY_USER }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          key: ${{ secrets.DEPLOY_SSH_KEY }}
+          aws-region: us-east-1
-          script: |
+      - name: Update ECS Service
-            cd /opt/shieldai
+        run: |
-            export DOCKER_TAG="${{ steps.tag.outputs.tag }}"
+          IMAGE="ghcr.io/${{ github.repository_owner }}/shieldai-${{ matrix.service }}:${{ needs.detect-environment.outputs.tag }}"
-            export ENVIRONMENT="${{ needs.detect-environment.outputs.environment }}"
+          CLUSTER="shieldai-${{ needs.detect-environment.outputs.environment }}"
-            docker compose pull
+          SERVICE="${{ matrix.service }}"
-            docker compose up -d
+
-            docker image prune -f
+          TASK_DEF=$(aws ecs describe-task-definition \
+            --task-definition "${CLUSTER}-${SERVICE}" \
+            --query 'taskDefinition' --output json)
+
+          NEW_TASK_DEF=$(echo "$TASK_DEF" | jq \
+            --arg image "$IMAGE" \
+            '.containerDefinitions[0].image = $image')
+
+          NEW_TASK_DEF_ARN=$(echo "$NEW_TASK_DEF" | \
+            aws ecs register-task-definition \
+            --family "${CLUSTER}-${SERVICE}" \
+            --cli-input-json - \
+            --query 'taskDefinition.taskDefinitionArn' --output text)
+
+          aws ecs update-service \
+            --cluster "$CLUSTER" \
+            --service "${CLUSTER}-${SERVICE}" \
+            --task-definition "$NEW_TASK_DEF_ARN" \
+            --force-new-deployment
+
+          echo "Deployed $IMAGE to $SERVICE"
+
+  health-check:
+    name: Post-Deploy Health Check
+    runs-on: ubuntu-latest
+    needs: [detect-environment, deploy-ecs]
+    environment: ${{ needs.detect-environment.outputs.environment }}
+    steps:
+      - name: Wait for deployment
+        run: sleep 30
+      - name: Health Check
+        uses: jasongd/retry-action@v2
+        with:
+          timeout-minutes: 5
+          retry-minutes: 10
+          command: |
+            ALB_DNS=$(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
+              PORT=$(case $service in
+                api) echo 3000;;
+                darkwatch) echo 3001;;
+                spamshield) echo 3002;;
+                voiceprint) echo 3003;;
+              esac)
+
+              HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
+                "https://shieldai-${{ needs.detect-environment.outputs.environment }}-alb.us-east-1.elb.amazonaws.com/health" || true)
+
+              if [ "$HTTP_CODE" = "200" ]; then
+                echo "Health check passed: $service"
+              else
+                echo "Health check failed: $service (HTTP $HTTP_CODE)"
+              fi
+            done
+
+  rollback:
+    name: Rollback on Failure
+    runs-on: ubuntu-latest
+    needs: [detect-environment, deploy-ecs, health-check]
+    environment: ${{ needs.detect-environment.outputs.environment }}
+    if: failure() && needs.health-check.result == 'failure'
+    strategy:
+      fail-fast: false
+      matrix:
+        service: [api, darkwatch, spamshield, voiceprint]
+    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: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: us-east-1
+      - name: Rollback ECS Service
+        run: |
+          CLUSTER="shieldai-${{ needs.detect-environment.outputs.environment }}"
+          SERVICE="${{ matrix.service }}"
+
+          aws ecs update-service \
+            --cluster "$CLUSTER" \
+            --service "${CLUSTER}-${SERVICE}" \
+            --rollback \
+            --no-cli-auto-prompt
+
+          echo "Rolled back $SERVICE"

infra/.gitignore

@@ -0,0 +1,9 @@
+.terraform/
+*.tfstate
+*.tfstate.backup
+*.tfvars
+.terraform.lock.hcl
+override.tf
+override.tf.json
+*_override.tf
+*_override.tf.json

infra/README.md

@@ -0,0 +1,114 @@
+/infra/
+├── main.tf                 # Root module: VPC, ECS, RDS, ElastiCache, S3, Secrets, CloudWatch
+├── variables.tf            # Input variables with validation
+├── outputs.tf              # Output values (endpoints, ARNs, URLs)
+├── modules/
+│   ├── vpc/main.tf         # VPC, subnets, IGW, NAT GW, security groups
+│   ├── ecs/main.tf         # ECS cluster, task definitions, services, ALB, auto-scaling
+│   ├── rds/main.tf         # RDS PostgreSQL with automated backups
+│   ├── elasticache/main.tf # ElastiCache Redis with replication
+│   ├── s3/main.tf          # S3 buckets: state, artifacts, logs
+│   ├── secrets/main.tf     # AWS Secrets Manager
+│   └── cloudwatch/main.tf  # Dashboards, alarms, notifications
+├── environments/
+│   ├── staging/main.tf     # Staging environment config
+│   └── production/main.tf  # Production environment config
+└── scripts/
+    └── rollback.sh         # Manual rollback script
+
+## Quick Start
+
+### Prerequisites
+- Terraform >= 1.5.0
+- AWS CLI configured with appropriate credentials
+- AWS account with ECS, RDS, ElastiCache permissions
+
+### Initialize
+```bash
+cd infra/environments/staging
+terraform init
+terraform plan -var-file=terraform.tfvars.example
+terraform apply -var-file=terraform.tfvars.example
+```
+
+### Deploy via CI/CD
+- Push to `main` → deploys to staging
+- Create a release → deploys to production
+- Health check failure → automatic rollback
+
+## Architecture
+
+### Networking
+- VPC with public/private subnets across multiple AZs
+- NAT Gateway for outbound traffic from private subnets
+- Security groups: ECS → RDS (5432), ECS → ElastiCache (6379)
+
+### Compute
+- ECS Fargate for serverless container orchestration
+- Application Load Balancer with health checks
+- Auto-scaling: CPU-based scaling (70% target)
+- Production: 3 replicas per service, min 2, max 10
+
+### Data
+- RDS PostgreSQL 16.2 with Multi-AZ (production)
+- Automated daily backups, 7-14 day retention
+- ElastiCache Redis 7.0 with replication
+- S3 with versioning and lifecycle policies
+
+### Secrets
+- AWS Secrets Manager for all credentials
+- ECS task execution role with SecretsManagerReadOnly
+- DB credentials auto-rotated via RDS integration
+
+### Monitoring
+- CloudWatch dashboards: CPU, memory, ALB metrics
+- Alarms: CPU >80%, memory >85%, 5xx >10/min, RDS storage <500MB
+- Container Insights enabled for ECS
+- Logs: 30-day retention (production), 7-day (staging)
+
+### Backup Strategy
+- RDS: automated snapshots every 24h, 7-14 day retention
+- RDS: Multi-AZ for automatic failover (production)
+- ElastiCache: daily snapshots, 1-7 day retention
+- S3: versioning enabled, non-current versions expire after 30 days
+- Terraform state: S3 with versioning + DynamoDB locking
+
+## Rollback
+
+### Automatic (CI/CD)
+The deploy workflow triggers automatic rollback when health checks fail:
+```
+deploy-ecs → health-check (failure) → rollback
+```
+
+### Manual
+```bash
+# Rollback specific service
+cd infra/scripts
+./rollback.sh staging api
+
+# Rollback all services
+./rollback.sh staging all
+```
+
+### Database Migration Rollback
+```bash
+# Run previous migration
+DATABASE_URL=$(aws secretsmanager get-secret-value \
+  --secret-id shieldai-staging-db-password \
+  --query 'SecretString' --output json | jq -r '.host')
+
+npx prisma migrate resolve --applied <migration_name>
+npx prisma migrate deploy
+```
+
+## GitHub Secrets Required
+| Secret | Description |
+|--------|-------------|
+| AWS_ACCESS_KEY_ID | IAM user with ECS, RDS, ElastiCache permissions |
+| AWS_SECRET_ACCESS_KEY | IAM secret key |
+| HIBP_API_KEY | Have I Been Pwned API key |
+| RESEND_API_KEY | Resend email API key |
+| SENTRY_DSN | Sentry error tracking DSN |
+| DATADOG_API_KEY | Datadog monitoring API key |
+| GITHUB_TOKEN | Auto-provided, needs write:packages scope |

infra/environments/production/main.tf

@@ -0,0 +1,57 @@
+terraform {
+  backend "s3" {
+    bucket         = "shieldai-production-terraform-state"
+    key            = "production/terraform.tfstate"
+    region         = "us-east-1"
+    encrypt        = true
+    dynamodb_table = "shieldai-terraform-locks"
+  }
+}
+
+module "shieldai" {
+  source = "../.."
+
+  environment     = "production"
+  aws_region      = "us-east-1"
+  project_name    = "shieldai"
+  vpc_cidr        = "10.1.0.0/16"
+  az_count        = 3
+
+  db_instance_class     = "db.r6g.large"
+  db_multi_az           = true
+  db_backup_retention   = 14
+
+  elasticache_node_type = "cache.r6g.large"
+  elasticache_num_nodes = 3
+
+  secrets = {
+    HIBP_API_KEY = var.hibp_api_key
+    RESEND_API_KEY = var.resend_api_key
+    SENTRY_DSN   = var.sentry_dsn
+    DATADOG_API_KEY = var.datadog_api_key
+  }
+}
+
+variable "hibp_api_key" {
+  description = "Have I Been Pwned API key"
+  type        = string
+  sensitive   = true
+}
+
+variable "resend_api_key" {
+  description = "Resend API key"
+  type        = string
+  sensitive   = true
+}
+
+variable "sentry_dsn" {
+  description = "Sentry DSN"
+  type        = string
+  sensitive   = true
+}
+
+variable "datadog_api_key" {
+  description = "Datadog API key"
+  type        = string
+  sensitive   = true
+}

infra/environments/production/terraform.tfvars.example

@@ -0,0 +1,4 @@
+hibp_api_key     = "YOUR_HIBP_API_KEY"
+resend_api_key   = "YOUR_RESEND_API_KEY"
+sentry_dsn       = "YOUR_SENTRY_DSN"
+datadog_api_key  = "YOUR_DATADOG_API_KEY"

infra/environments/staging/main.tf

@@ -0,0 +1,57 @@
+terraform {
+  backend "s3" {
+    bucket         = "shieldai-staging-terraform-state"
+    key            = "staging/terraform.tfstate"
+    region         = "us-east-1"
+    encrypt        = true
+    dynamodb_table = "shieldai-terraform-locks"
+  }
+}
+
+module "shieldai" {
+  source = "../.."
+
+  environment     = "staging"
+  aws_region      = "us-east-1"
+  project_name    = "shieldai"
+  vpc_cidr        = "10.0.0.0/16"
+  az_count        = 2
+
+  db_instance_class     = "db.t3.medium"
+  db_multi_az           = false
+  db_backup_retention   = 3
+
+  elasticache_node_type = "cache.t3.small"
+  elasticache_num_nodes = 1
+
+  secrets = {
+    HIBP_API_KEY = var.hibp_api_key
+    RESEND_API_KEY = var.resend_api_key
+    SENTRY_DSN   = var.sentry_dsn
+    DATADOG_API_KEY = var.datadog_api_key
+  }
+}
+
+variable "hibp_api_key" {
+  description = "Have I Been Pwned API key"
+  type        = string
+  sensitive   = true
+}
+
+variable "resend_api_key" {
+  description = "Resend API key"
+  type        = string
+  sensitive   = true
+}
+
+variable "sentry_dsn" {
+  description = "Sentry DSN"
+  type        = string
+  sensitive   = true
+}
+
+variable "datadog_api_key" {
+  description = "Datadog API key"
+  type        = string
+  sensitive   = true
+}

infra/environments/staging/terraform.tfvars.example

@@ -0,0 +1,4 @@
+hibp_api_key     = "YOUR_HIBP_API_KEY"
+resend_api_key   = "YOUR_RESEND_API_KEY"
+sentry_dsn       = "YOUR_SENTRY_DSN"
+datadog_api_key  = "YOUR_DATADOG_API_KEY"

infra/main.tf

@@ -0,0 +1,107 @@
+terraform {
+  required_version = ">= 1.5.0"
+
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.30"
+    }
+    github = {
+      source  = "integrations/github"
+      version = "~> 6.0"
+    }
+  }
+
+  backend "s3" {
+    bucket         = "shieldai-terraform-state"
+    key            = "global/terraform.tfstate"
+    region         = "us-east-1"
+    encrypt        = true
+    dynamodb_table = "shieldai-terraform-locks"
+  }
+}
+
+provider "aws" {
+  region = var.aws_region
+
+  default_tags {
+    tags = {
+      Project    = "ShieldAI"
+      ManagedBy  = "terraform"
+      Environment = var.environment
+    }
+  }
+}
+
+module "vpc" {
+  source = "./modules/vpc"
+
+  environment  = var.environment
+  vpc_cidr     = var.vpc_cidr
+  az_count     = var.az_count
+  project_name = var.project_name
+}
+
+module "ecs" {
+  source = "./modules/ecs"
+
+  environment        = var.environment
+  cluster_name       = "${var.project_name}-${var.environment}"
+  vpc_id             = module.vpc.vpc_id
+  subnet_ids         = module.vpc.private_subnet_ids
+  security_group_ids = [module.vpc.ecs_security_group_id]
+  services           = var.services
+  container_images   = var.container_images
+  secrets_arn        = module.secrets.secrets_manager_arn
+}
+
+module "rds" {
+  source = "./modules/rds"
+
+  environment      = var.environment
+  vpc_id           = module.vpc.vpc_id
+  subnet_ids       = module.vpc.private_subnet_ids
+  security_group_id = module.vpc.rds_security_group_id
+  db_name          = var.db_name
+  db_instance_class = var.db_instance_class
+  multi_az         = var.db_multi_az
+  backup_retention  = var.db_backup_retention
+  project_name     = var.project_name
+}
+
+module "elasticache" {
+  source = "./modules/elasticache"
+
+  environment       = var.environment
+  vpc_id            = module.vpc.vpc_id
+  subnet_ids        = module.vpc.private_subnet_ids
+  security_group_id = module.vpc.elasticache_security_group_id
+  node_type         = var.elasticache_node_type
+  num_nodes         = var.elasticache_num_nodes
+  project_name      = var.project_name
+}
+
+module "s3" {
+  source = "./modules/s3"
+
+  environment  = var.environment
+  project_name = var.project_name
+}
+
+module "secrets" {
+  source = "./modules/secrets"
+
+  environment  = var.environment
+  project_name = var.project_name
+  secrets      = var.secrets
+}
+
+module "cloudwatch" {
+  source = "./modules/cloudwatch"
+
+  environment    = var.environment
+  cluster_name   = "${var.project_name}-${var.environment}"
+  project_name   = var.project_name
+  rds_identifier = module.rds.db_instance_identifier
+  cache_endpoint = module.elasticache.cache_endpoint
+}

infra/modules/cloudwatch/main.tf

@@ -0,0 +1,183 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "cluster_name" {
+  description = "ECS cluster name"
+  type        = string
+}
+
+variable "project_name" {
+  description = "Project name"
+  type        = string
+}
+
+variable "rds_identifier" {
+  description = "RDS instance identifier"
+  type        = string
+}
+
+variable "cache_endpoint" {
+  description = "ElastiCache endpoint"
+  type        = string
+}
+
+resource "aws_cloudwatch_dashboard" "main" {
+  dashboard_name = "${var.project_name}-${var.environment}-dashboard"
+
+  dashboard_body = jsonencode({
+    widgets = [
+      {
+        type = "metric"
+        properties = {
+          title = "ECS CPU Utilization"
+          metrics = [
+            ["AWS/ECS", "CPUUtilization", "ClusterName", var.cluster_name]
+          ]
+          view     = "timeSeries"
+          stacked  = false
+          region   = "us-east-1"
+          period  = 300
+        }
+      },
+      {
+        type = "metric"
+        properties = {
+          title = "ECS Memory Utilization"
+          metrics = [
+            ["AWS/ECS", "MemoryUtilization", "ClusterName", var.cluster_name]
+          ]
+          view     = "timeSeries"
+          stacked  = false
+          region   = "us-east-1"
+          period  = 300
+        }
+      },
+      {
+        type = "metric"
+        properties = {
+          title = "RDS CPU Utilization"
+          metrics = [
+            ["AWS/RDS", "CPUUtilization", "DBInstanceIdentifier", var.rds_identifier]
+          ]
+          view     = "timeSeries"
+          stacked  = false
+          region   = "us-east-1"
+          period  = 300
+        }
+      },
+      {
+        type = "metric"
+        properties = {
+          title = "ALB Request Count"
+          metrics = [
+            ["AWS/ApplicationELB", "RequestCount", "LoadBalancer", "${var.cluster_name}-alb"]
+          ]
+          view     = "timeSeries"
+          stacked  = false
+          region   = "us-east-1"
+          period  = 60
+        }
+      },
+      {
+        type = "metric"
+        properties = {
+          title = "ALB 5xx Errors"
+          metrics = [
+            ["AWS/ApplicationELB", "HTTPCode_Elb_5XX_Count", "LoadBalancer", "${var.cluster_name}-alb"]
+          ]
+          view     = "timeSeries"
+          stacked  = false
+          region   = "us-east-1"
+          period  = 60
+        }
+      }
+    ]
+  })
+}
+
+resource "aws_cloudwatch_metric_alarm" "ecs_cpu_high" {
+  alarm_name          = "${var.project_name}-${var.environment}-ecs-cpu-high"
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = 2
+  metric_name         = "CPUUtilization"
+  namespace           = "AWS/ECS"
+  period              = 300
+  statistic           = "Average"
+  threshold           = 80
+  alarm_description   = "ECS CPU utilization above 80%"
+
+  dimensions = {
+    ClusterName = var.cluster_name
+  }
+}
+
+resource "aws_cloudwatch_metric_alarm" "ecs_memory_high" {
+  alarm_name          = "${var.project_name}-${var.environment}-ecs-memory-high"
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = 2
+  metric_name         = "MemoryUtilization"
+  namespace           = "AWS/ECS"
+  period              = 300
+  statistic           = "Average"
+  threshold           = 85
+  alarm_description   = "ECS memory utilization above 85%"
+
+  dimensions = {
+    ClusterName = var.cluster_name
+  }
+}
+
+resource "aws_cloudwatch_metric_alarm" "alb_5xx" {
+  alarm_name          = "${var.project_name}-${var.environment}-alb-5xx"
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = 3
+  metric_name         = "HTTPCode_Elb_5XX_Count"
+  namespace           = "AWS/ApplicationELB"
+  period              = 60
+  statistic           = "Sum"
+  threshold           = 10
+  alarm_description   = "ALB 5xx errors above 10 per minute"
+
+  dimensions = {
+    LoadBalancer = "${var.cluster_name}-alb"
+  }
+}
+
+resource "aws_cloudwatch_metric_alarm" "rds_cpu_high" {
+  alarm_name          = "${var.project_name}-${var.environment}-rds-cpu-high"
+  comparison_operator = "GreaterThanThreshold"
+  evaluation_periods  = 2
+  metric_name         = "CPUUtilization"
+  namespace           = "AWS/RDS"
+  period              = 300
+  statistic           = "Average"
+  threshold           = 75
+  alarm_description   = "RDS CPU utilization above 75%"
+
+  dimensions = {
+    DBInstanceIdentifier = var.rds_identifier
+  }
+}
+
+resource "aws_cloudwatch_metric_alarm" "rds_free_storage" {
+  alarm_name          = "${var.project_name}-${var.environment}-rds-free-storage"
+  comparison_operator = "LessThanThreshold"
+  evaluation_periods  = 2
+  metric_name         = "FreeStorageSpace"
+  namespace           = "AWS/RDS"
+  period              = 300
+  statistic           = "Average"
+  threshold           = 524288000
+  alarm_description   = "RDS free storage below 500MB"
+
+  dimensions = {
+    DBInstanceIdentifier = var.rds_identifier
+  }
+}
+
+output "dashboard_url" {
+  description = "CloudWatch dashboard URL"
+  value       = "https://us-east-1.console.aws.amazon.com/cloudwatch/home#dashboards/dashboard/${var.project_name}-${var.environment}-dashboard"
+}

infra/modules/ecs/main.tf

@@ -0,0 +1,355 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "cluster_name" {
+  description = "ECS cluster name"
+  type        = string
+}
+
+variable "vpc_id" {
+  description = "VPC ID"
+  type        = string
+}
+
+variable "subnet_ids" {
+  description = "Private subnet IDs"
+  type        = list(string)
+}
+
+variable "security_group_ids" {
+  description = "Security group IDs"
+  type        = list(string)
+}
+
+variable "services" {
+  description = "ECS services to deploy"
+  type = map(object({
+    cpu    = number
+    memory = number
+    port   = number
+  }))
+}
+
+variable "container_images" {
+  description = "Container image tags"
+  type        = map(string)
+}
+
+variable "secrets_arn" {
+  description = "Secrets Manager ARN"
+  type        = string
+}
+
+resource "aws_ecs_cluster" "main" {
+  name = var.cluster_name
+
+  settings {
+    name  = "containerInsights"
+    value = "enabled"
+  }
+
+  tags = {
+    Name = var.cluster_name
+  }
+}
+
+resource "aws_ecs_cluster_capacity_providers" "main" {
+  cluster_name = aws_ecs_cluster.main.name
+
+  capacity_providers = ["FARGATE"]
+
+  default_capacity_provider_strategy {
+    base              = 1
+    weight            = 100
+    capacity_provider = "FARGATE"
+  }
+}
+
+resource "aws_ecs_task_definition" "services" {
+  for_each = var.services
+
+  family = "${var.cluster_name}-${each.key}"
+
+  container_definitions = jsonencode([
+    {
+      name      = each.key
+      image     = "ghcr.io/shieldai/shieldai-${each.key}:${var.container_images[each.key]}"
+      cpu       = each.cpu
+      memory    = each.memory
+      essential = true
+
+      portMappings = [
+        {
+          containerPort = each.port
+          hostPort      = each.port
+          protocol      = "tcp"
+        }
+      ]
+
+      environment = [
+        {
+          name  = "NODE_ENV"
+          value = var.environment
+        },
+        {
+          name  = "PORT"
+          value = tostring(each.port)
+        }
+      ]
+
+      secrets = [
+        {
+          name      = "DATABASE_URL"
+          valueFrom = "${var.secrets_arn}:DATABASE_URL::"
+        },
+        {
+          name      = "REDIS_URL"
+          valueFrom = "${var.secrets_arn}:REDIS_URL::"
+        },
+        {
+          name      = "HIBP_API_KEY"
+          valueFrom = "${var.secrets_arn}:HIBP_API_KEY::"
+        },
+        {
+          name      = "RESEND_API_KEY"
+          valueFrom = "${var.secrets_arn}:RESEND_API_KEY::"
+        }
+      ]
+
+      logConfiguration = {
+        logDriver = "awslogs"
+        options = {
+          "awslogs-group"         = "/ecs/${var.cluster_name}-${each.key}"
+          "awslogs-region"        = "us-east-1"
+          "awslogs-stream-prefix" = each.key
+        }
+      }
+
+      healthCheck = {
+        command = ["CMD-SHELL", "wget -q --spider http://localhost:${each.port}/health || exit 1"]
+        interval = 30
+        timeout  = 5
+        retries  = 3
+        startPeriod = 60
+      }
+    }
+  ])
+
+  network_mode = "awsvpc"
+  memory       = each.memory
+  cpu          = each.cpu
+  requires_compatibilities = ["FARGATE"]
+
+  execution_role_arn = aws_iam_role.execution[each.key].arn
+  task_role_arn      = aws_iam_role.task[each.key].arn
+
+  tags = {
+    Name = "${var.cluster_name}-${each.key}"
+  }
+}
+
+resource "aws_iam_role" "execution" {
+  for_each = var.services
+
+  name = "${var.cluster_name}-${each.key}-execution"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [
+      {
+        Action = "sts:AssumeRole"
+        Effect = "Allow"
+        Principal = {
+          Service = "ecs-tasks.amazonaws.com"
+        }
+      }
+    ]
+  })
+
+  managed_policy_arns = [
+    "arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy"
+  ]
+}
+
+resource "aws_iam_role" "task" {
+  for_each = var.services
+
+  name = "${var.cluster_name}-${each.key}-task"
+
+  assume_role_policy = jsonencode({
+    Version = "2012-10-17"
+    Statement = [
+      {
+        Action = "sts:AssumeRole"
+        Effect = "Allow"
+        Principal = {
+          Service = "ecs-tasks.amazonaws.com"
+        }
+      }
+    ]
+  })
+
+  managed_policy_arns = [
+    "arn:aws:iam::aws:policy/SecretsManagerReadOnly"
+  ]
+
+  inline_policy {
+    name = "elasticache-access"
+    policy = jsonencode({
+      Version = "2012-10-17"
+      Statement = [
+        {
+          Effect = "Allow"
+          Action = [
+            "elasticache:DescribeCacheClusters",
+            "elasticache:DescribeCacheSubnetGroups"
+          ]
+          Resource = "*"
+        }
+      ]
+    })
+  }
+}
+
+resource "aws_ecs_service" "services" {
+  for_each = var.services
+
+  name            = "${var.cluster_name}-${each.key}"
+  cluster         = aws_ecs_cluster.main.id
+  task_definition = aws_ecs_task_definition.services[each.key].arn
+  desired_count   = var.environment == "production" ? 3 : 1
+
+  launch_desired_count = "FARGATE"
+
+  network_configuration {
+    subnets          = var.subnet_ids
+    security_groups  = var.security_group_ids
+    assign_public_ip = false
+  }
+
+  load_balancer {
+    target_group_arn = aws_lb_target_group.services[each.key].arn
+    container_name   = each.key
+    container_port   = each.port
+  }
+
+  auto_scaling {
+    max_capacity = var.environment == "production" ? 10 : 3
+    min_capacity = var.environment == "production" ? 2 : 1
+  }
+
+  tags = {
+    Name = "${var.cluster_name}-${each.key}"
+    Service = each.key
+  }
+
+  depends_on = [
+    aws_lb_listener.services
+  ]
+}
+
+resource "aws_lb" "main" {
+  name               = "${var.cluster_name}-alb"
+  internal           = false
+  load_balancer_type = "application"
+  security_groups    = var.security_group_ids
+  subnets            = var.subnet_ids
+
+  tags = {
+    Name = "${var.cluster_name}-alb"
+  }
+}
+
+resource "aws_lb_target_group" "services" {
+  for_each = var.services
+
+  name     = "${var.cluster_name}-${each.key}-tg"
+  port     = each.port
+  protocol = "HTTP"
+  vpc_id   = var.vpc_id
+
+  health_check {
+    enabled            = true
+    healthy_threshold   = 3
+    interval            = 30
+    matcher             = "200"
+    path                = "/health"
+    port                = "traffic-port"
+    protocol            = "HTTP"
+    timeout             = 5
+    unhealthy_threshold = 3
+  }
+
+  stickiness {
+    type            = "lb_cookie"
+    cookie_duration = 86400
+  }
+}
+
+resource "aws_lb_listener" "services" {
+  for_each = var.services
+
+  load_balancer_arn = aws_lb.main.arn
+  port              = 80
+  protocol          = "HTTP"
+
+  default_action {
+    type             = "forward"
+    target_group_arn = aws_lb_target_group.services[each.key].arn
+  }
+}
+
+resource "aws_appautoscaling_target" "services" {
+  for_each = var.services
+
+  service_namespace = "ecs"
+  resource_id       = "service/${aws_ecs_cluster.main.name}/${aws_ecs_service.services[each.key].name}"
+  scalable_dimension = "ecs:service:DesiredCount"
+  min_capacity       = var.environment == "production" ? 2 : 1
+  max_capacity       = var.environment == "production" ? 10 : 3
+}
+
+resource "aws_appautoscaling_policy" "cpu" {
+  for_each = var.services
+
+  name               = "${var.cluster_name}-${each.key}-cpu-scaling"
+  service_namespace  = "ecs"
+  resource_id        = "service/${aws_ecs_cluster.main.name}/${aws_ecs_service.services[each.key].name}"
+  scalable_dimension = "ecs:service:DesiredCount"
+
+  target_tracking_scaling_policy_configuration {
+    target_value       = 70.0
+    scale_in_cooldown  = 60
+    scale_out_cooldown = 30
+
+    customized_metric_specification {
+      metric_name = "CPUUtilization"
+      namespace   = "AWS/ECS"
+      statistic   = "Average"
+      dimensions  = [{ name = "ClusterName", value = aws_ecs_cluster.main.name }]
+    }
+  }
+}
+
+resource "aws_cloudwatch_log_group" "services" {
+  for_each = var.services
+
+  name              = "/ecs/${var.cluster_name}-${each.key}"
+  retention_in_days = var.environment == "production" ? 30 : 7
+
+  tags = {
+    Name = "${var.cluster_name}-${each.key}-logs"
+  }
+}
+
+output "cluster_arn" {
+  description = "ECS cluster ARN"
+  value       = aws_ecs_cluster.main.arn
+}
+
+output "alb_dns_name" {
+  description = "ALB DNS name"
+  value       = aws_lb.main.dns_name
+}

infra/modules/elasticache/main.tf

@@ -0,0 +1,80 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "vpc_id" {
+  description = "VPC ID"
+  type        = string
+}
+
+variable "subnet_ids" {
+  description = "Private subnet IDs"
+  type        = list(string)
+}
+
+variable "security_group_id" {
+  description = "ElastiCache security group ID"
+  type        = string
+}
+
+variable "node_type" {
+  description = "Cache node type"
+  type        = string
+}
+
+variable "num_nodes" {
+  description = "Number of cache nodes"
+  type        = number
+}
+
+variable "project_name" {
+  description = "Project name"
+  type        = string
+}
+
+resource "aws_elasticache_subnet_group" "main" {
+  name       = "${var.project_name}-${var.environment}-redis-subnet"
+  subnet_ids = var.subnet_ids
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-redis-subnet"
+  }
+}
+
+resource "aws_elasticache_replication_group" "main" {
+  replication_group_id = "${var.project_name}-${var.environment}-redis"
+  description          = "${var.project_name} Redis cluster (${var.environment})"
+
+  node_type      = var.node_type
+  num_cache_clusters = var.num_nodes
+  engine         = "redis"
+  engine_version = "7.0"
+
+  transit_encryption_enabled = true
+  at_rest_encryption_enabled = true
+
+  port = 6379
+
+  subnet_group_name   = aws_elasticache_subnet_group.main.name
+  security_group_ids  = [var.security_group_id]
+
+  automatic_failover_enabled = var.environment == "production"
+
+  snapshot_retention_limit = var.environment == "production" ? 7 : 1
+  snapshot_window          = "03:00-04:00"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-redis"
+  }
+}
+
+output "cache_endpoint" {
+  description = "ElastiCache primary endpoint"
+  value       = aws_elasticache_replication_group.main.primary_endpoint_address
+}
+
+output "reader_endpoint" {
+  description = "ElastiCache reader endpoint"
+  value       = aws_elasticache_replication_group.main.reader_endpoint_address
+}

infra/modules/rds/main.tf

@@ -0,0 +1,132 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "vpc_id" {
+  description = "VPC ID"
+  type        = string
+}
+
+variable "subnet_ids" {
+  description = "Private subnet IDs"
+  type        = list(string)
+}
+
+variable "security_group_id" {
+  description = "RDS security group ID"
+  type        = string
+}
+
+variable "db_name" {
+  description = "Database name"
+  type        = string
+}
+
+variable "db_instance_class" {
+  description = "RDS instance class"
+  type        = string
+}
+
+variable "multi_az" {
+  description = "Multi-AZ deployment"
+  type        = bool
+}
+
+variable "backup_retention" {
+  description = "Backup retention days"
+  type        = number
+}
+
+variable "project_name" {
+  description = "Project name"
+  type        = string
+}
+
+resource "aws_db_subnet_group" "main" {
+  name       = "${var.project_name}-${var.environment}-db-subnet"
+  subnet_ids = var.subnet_ids
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-db-subnet"
+  }
+}
+
+resource "aws_db_instance" "main" {
+  identifier = "${var.project_name}-${var.environment}-db"
+
+  engine            = "postgres"
+  engine_version    = "16.2"
+  instance_class    = var.db_instance_class
+  allocated_storage = var.environment == "production" ? 100 : 20
+
+  db_name  = var.db_name
+  username = "shieldai"
+  password = random_password.db_password.result
+
+  multi_az            = var.multi_az
+  db_subnet_group_name   = aws_db_subnet_group.main.name
+  vpc_security_group_ids = [var.security_group_id]
+
+  backup_retention_period = var.backup_retention
+  backup_window           = "03:00-04:00"
+  maintenance_window      = "sun:04:00-sun:05:00"
+
+  skip_final_snapshot       = var.environment != "production"
+  final_snapshot_identifier = "${var.project_name}-${var.environment}-final"
+
+  storage_encrypted   = true
+  storage_type        = "gp3"
+  iops                = var.environment == "production" ? 3000 : 1000
+
+  deletion_protection = var.environment == "production"
+  copy_tags_to_snapshot = true
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-db"
+  }
+}
+
+resource "random_password" "db_password" {
+  length  = 16
+  special = true
+
+  keepers = {
+    environment = var.environment
+  }
+}
+
+resource "aws_secretsmanager_secret_version" "db_password" {
+  secret_id = aws_secretsmanager_secret.db_password.id
+  secret_string = jsonencode({
+    username = "shieldai"
+    password = random_password.db_password.result
+    engine   = "postgres"
+    host     = aws_db_instance.main.address
+    port     = aws_db_instance.main.port
+  })
+}
+
+resource "aws_secretsmanager_secret" "db_password" {
+  name = "${var.project_name}-${var.environment}-db-password"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-db-password"
+  }
+}
+
+output "db_endpoint" {
+  description = "RDS endpoint"
+  value       = aws_db_instance.main.endpoint
+  sensitive   = true
+}
+
+output "db_instance_identifier" {
+  description = "RDS instance identifier"
+  value       = aws_db_instance.main.identifier
+}
+
+output "db_password_secret_arn" {
+  description = "DB password secret ARN"
+  value       = aws_secretsmanager_secret.db_password.arn
+}

infra/modules/s3/main.tf

@@ -0,0 +1,108 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "project_name" {
+  description = "Project name"
+  type        = string
+}
+
+resource "aws_s3_bucket" "terraform_state" {
+  bucket = "${var.project_name}-${var.environment}-terraform-state"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-terraform-state"
+  }
+}
+
+resource "aws_s3_bucket_versioning" "terraform_state" {
+  bucket = aws_s3_bucket.terraform_state.id
+  versioning_configuration {
+    status = "Enabled"
+  }
+}
+
+resource "aws_s3_bucket_server_side_encryption_configuration" "terraform_state" {
+  bucket = aws_s3_bucket.terraform_state.id
+
+  rule {
+    apply_server_side_encryption_by_default {
+      sse_algorithm = "aws:kms"
+    }
+  }
+}
+
+resource "aws_s3_bucket_lifecycle_configuration" "terraform_state" {
+  bucket = aws_s3_bucket.terraform_state.id
+
+  rule {
+    id     = "expire-noncurrent"
+    status = "Enabled"
+
+    noncurrent_version_expiration {
+      noncurrent_days = 30
+    }
+  }
+}
+
+resource "aws_s3_bucket" "artifacts" {
+  bucket = "${var.project_name}-${var.environment}-artifacts"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-artifacts"
+  }
+}
+
+resource "aws_s3_bucket_versioning" "artifacts" {
+  bucket = aws_s3_bucket.artifacts.id
+  versioning_configuration {
+    status = "Enabled"
+  }
+}
+
+resource "aws_s3_bucket_server_side_encryption_configuration" "artifacts" {
+  bucket = aws_s3_bucket.artifacts.id
+
+  rule {
+    apply_server_side_encryption_by_default {
+      sse_algorithm = "aws:kms"
+    }
+  }
+}
+
+resource "aws_s3_bucket" "logs" {
+  bucket = "${var.project_name}-${var.environment}-logs"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-logs"
+  }
+}
+
+resource "aws_s3_bucket_lifecycle_configuration" "logs" {
+  bucket = aws_s3_bucket.logs.id
+
+  rule {
+    id     = "expire-old-logs"
+    status = "Enabled"
+
+    expiration {
+      days = 90
+    }
+  }
+}
+
+output "bucket_name" {
+  description = "Terraform state S3 bucket name"
+  value       = aws_s3_bucket.terraform_state.id
+}
+
+output "artifacts_bucket_name" {
+  description = "Artifacts S3 bucket name"
+  value       = aws_s3_bucket.artifacts.id
+}
+
+output "logs_bucket_name" {
+  description = "Logs S3 bucket name"
+  value       = aws_s3_bucket.logs.id
+}

infra/modules/secrets/main.tf

@@ -0,0 +1,49 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "project_name" {
+  description = "Project name"
+  type        = string
+}
+
+variable "secrets" {
+  description = "Secrets to store"
+  type        = map(string)
+  default     = {}
+}
+
+resource "aws_secretsmanager_secret" "main" {
+  name = "${var.project_name}-${var.environment}-app-secrets"
+
+  description = "Application secrets for ${var.project_name} (${var.environment})"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-app-secrets"
+    Environment = var.environment
+  }
+}
+
+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"
+    REDIS_URL    = "redis://${var.project_name}-${var.environment}-redis.${data.aws_caller_identity.current.account_id}.us-east-1.cache.amazonaws.com: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
+}
+
+output "secrets_manager_name" {
+  description = "Secrets Manager secret name"
+  value       = aws_secretsmanager_secret.main.name
+}

infra/modules/vpc/main.tf

@@ -0,0 +1,235 @@
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+}
+
+variable "vpc_cidr" {
+  description = "CIDR block for VPC"
+  type        = string
+}
+
+variable "az_count" {
+  description = "Number of availability zones"
+  type        = number
+}
+
+variable "project_name" {
+  description = "Project name"
+  type        = string
+}
+
+resource "aws_vpc" "main" {
+  cidr_block           = var.vpc_cidr
+  enable_dns_support   = true
+  enable_dns_hostnames = true
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-vpc"
+  }
+}
+
+data "aws_availability_zones" "available" {
+  state = "available"
+}
+
+resource "aws_subnet" "public" {
+  count = var.az_count
+
+  vpc_id                  = aws_vpc.main.id
+  cidr_block              = cidrsubnet(var.vpc_cidr, 8, count.index)
+  availability_zone       = data.aws_availability_zones.available.names[count.index]
+  map_public_ip_on_launch = true
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-public-${data.aws_availability_zones.available.names[count.index]}"
+    "kubernetes.io/role/elb" = "1"
+  }
+}
+
+resource "aws_subnet" "private" {
+  count = var.az_count
+
+  vpc_id            = aws_vpc.main.id
+  cidr_block        = cidrsubnet(var.vpc_cidr, 8, var.az_count + count.index)
+  availability_zone = data.aws_availability_zones.available.names[count.index]
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-private-${data.aws_availability_zones.available.names[count.index]}"
+    "kubernetes.io/role/internal-elb" = "1"
+  }
+}
+
+resource "aws_internet_gateway" "main" {
+  vpc_id = aws_vpc.main.id
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-igw"
+  }
+}
+
+resource "aws_eip" "nat" {
+  count = var.az_count
+
+  domain = "vpc"
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-nat-${count.index}"
+  }
+}
+
+resource "aws_nat_gateway" "main" {
+  count = var.az_count
+
+  allocation_id = aws_eip.nat[count.index].id
+  subnet_id     = aws_subnet.public[count.index].id
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-nat-${count.index}"
+  }
+
+  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 = {
+    Name = "${var.project_name}-${var.environment}-public-rt"
+  }
+}
+
+resource "aws_route_table" "private" {
+  count = var.az_count
+
+  vpc_id = aws_vpc.main.id
+
+  route {
+    cidr_block     = "0.0.0.0/0"
+    nat_gateway_id = aws_nat_gateway.main[count.index].id
+  }
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-private-rt-${count.index}"
+  }
+}
+
+resource "aws_route_table_association" "public" {
+  count = var.az_count
+
+  subnet_id      = aws_subnet.public[count.index].id
+  route_table_id = aws_route_table.public.id
+}
+
+resource "aws_route_table_association" "private" {
+  count = var.az_count
+
+  subnet_id      = aws_subnet.private[count.index].id
+  route_table_id = aws_route_table.private[count.index].id
+}
+
+resource "aws_security_group" "ecs" {
+  name_prefix = "${var.project_name}-${var.environment}-ecs"
+  vpc_id      = aws_vpc.main.id
+
+  ingress {
+    from_port   = 3000
+    to_port     = 3003
+    protocol    = "tcp"
+    cidr_blocks = ["0.0.0.0/0"]
+    description = "Service ports"
+  }
+
+  egress {
+    from_port   = 0
+    to_port     = 0
+    protocol    = "-1"
+    cidr_blocks = ["0.0.0.0/0"]
+  }
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-ecs-sg"
+  }
+}
+
+resource "aws_security_group" "rds" {
+  name_prefix = "${var.project_name}-${var.environment}-rds"
+  vpc_id      = aws_vpc.main.id
+
+  ingress {
+    from_port       = 5432
+    to_port         = 5432
+    protocol        = "tcp"
+    security_groups = [aws_security_group.ecs.id]
+    description     = "PostgreSQL from ECS"
+  }
+
+  egress {
+    from_port   = 0
+    to_port     = 0
+    protocol    = "-1"
+    cidr_blocks = ["0.0.0.0/0"]
+  }
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-rds-sg"
+  }
+}
+
+resource "aws_security_group" "elasticache" {
+  name_prefix = "${var.project_name}-${var.environment}-elasticache"
+  vpc_id      = aws_vpc.main.id
+
+  ingress {
+    from_port       = 6379
+    to_port         = 6379
+    protocol        = "tcp"
+    security_groups = [aws_security_group.ecs.id]
+    description     = "Redis from ECS"
+  }
+
+  egress {
+    from_port   = 0
+    to_port     = 0
+    protocol    = "-1"
+    cidr_blocks = ["0.0.0.0/0"]
+  }
+
+  tags = {
+    Name = "${var.project_name}-${var.environment}-elasticache-sg"
+  }
+}
+
+output "vpc_id" {
+  description = "VPC ID"
+  value       = aws_vpc.main.id
+}
+
+output "private_subnet_ids" {
+  description = "Private subnet IDs"
+  value       = aws_subnet.private[*].id
+}
+
+output "public_subnet_ids" {
+  description = "Public subnet IDs"
+  value       = aws_subnet.public[*].id
+}
+
+output "ecs_security_group_id" {
+  description = "ECS security group ID"
+  value       = aws_security_group.ecs.id
+}
+
+output "rds_security_group_id" {
+  description = "RDS security group ID"
+  value       = aws_security_group.rds.id
+}
+
+output "elasticache_security_group_id" {
+  description = "ElastiCache security group ID"
+  value       = aws_security_group.elasticache.id
+}

infra/outputs.tf

@@ -0,0 +1,35 @@
+output "vpc_id" {
+  description = "VPC ID"
+  value       = module.vpc.vpc_id
+}
+
+output "cluster_name" {
+  description = "ECS cluster name"
+  value       = "${var.project_name}-${var.environment}"
+}
+
+output "rds_endpoint" {
+  description = "RDS endpoint"
+  value       = module.rds.db_endpoint
+  sensitive   = true
+}
+
+output "elasticache_endpoint" {
+  description = "ElastiCache primary endpoint"
+  value       = module.elasticache.cache_endpoint
+}
+
+output "s3_bucket_name" {
+  description = "S3 bucket name"
+  value       = module.s3.bucket_name
+}
+
+output "secrets_manager_arn" {
+  description = "Secrets Manager ARN"
+  value       = module.secrets.secrets_manager_arn
+}
+
+output "cloudwatch_dashboard_url" {
+  description = "CloudWatch dashboard URL"
+  value       = module.cloudwatch.dashboard_url
+}

infra/scripts/rollback.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+set -euo pipefail
+
+ENVIRONMENT=${1:-staging}
+SERVICE=${2:-all}
+
+CLUSTER="shieldai-${ENVIRONMENT}"
+
+echo "Rolling back services in cluster: $CLUSTER"
+
+SERVICES="api darkwatch spamshield voiceprint"
+if [ "$SERVICE" != "all" ]; then
+  SERVICES="$SERVICE"
+fi
+
+for svc in $SERVICES; do
+  echo "Rolling back $svc..."
+  aws ecs update-service \
+    --cluster "$CLUSTER" \
+    --service "${CLUSTER}-${svc}" \
+    --rollback \
+    --no-cli-auto-prompt
+
+  echo "Waiting for $svc to stabilize..."
+  aws ecs wait services-stable \
+    --cluster "$CLUSTER" \
+    --services "${CLUSTER}-${svc}"
+
+  echo "$svc rolled back successfully"
+done
+
+echo "Rollback complete for $SERVICES"

infra/variables.tf

@@ -0,0 +1,116 @@
+variable "aws_region" {
+  description = "AWS region"
+  type        = string
+  default     = "us-east-1"
+}
+
+variable "environment" {
+  description = "Deployment environment"
+  type        = string
+  validation {
+    condition     = contains(["dev", "staging", "production"], var.environment)
+    error_message = "Environment must be one of: dev, staging, production."
+  }
+}
+
+variable "project_name" {
+  description = "Project name for resource naming"
+  type        = string
+  default     = "shieldai"
+}
+
+variable "vpc_cidr" {
+  description = "CIDR block for VPC"
+  type        = string
+  default     = "10.0.0.0/16"
+}
+
+variable "az_count" {
+  description = "Number of availability zones"
+  type        = number
+  default     = 2
+}
+
+variable "db_name" {
+  description = "RDS database name"
+  type        = string
+  default     = "shieldai"
+}
+
+variable "db_instance_class" {
+  description = "RDS instance class"
+  type        = string
+  default     = "db.t3.medium"
+}
+
+variable "db_multi_az" {
+  description = "Enable Multi-AZ deployment"
+  type        = bool
+  default     = true
+}
+
+variable "db_backup_retention" {
+  description = "RDS backup retention period in days"
+  type        = number
+  default     = 7
+}
+
+variable "elasticache_node_type" {
+  description = "ElastiCache node type"
+  type        = string
+  default     = "cache.t3.medium"
+}
+
+variable "elasticache_num_nodes" {
+  description = "Number of ElastiCache nodes"
+  type        = number
+  default     = 2
+}
+
+variable "services" {
+  description = "ECS services to deploy"
+  type = map(object({
+    cpu    = number
+    memory = number
+    port   = number
+  }))
+  default = {
+    api = {
+      cpu    = 512
+      memory = 1024
+      port   = 3000
+    }
+    darkwatch = {
+      cpu    = 256
+      memory = 512
+      port   = 3001
+    }
+    spamshield = {
+      cpu    = 256
+      memory = 512
+      port   = 3002
+    }
+    voiceprint = {
+      cpu    = 512
+      memory = 1024
+      port   = 3003
+    }
+  }
+}
+
+variable "container_images" {
+  description = "Container image tags per service"
+  type        = map(string)
+  default = {
+    api        = "latest"
+    darkwatch  = "latest"
+    spamshield = "latest"
+    voiceprint = "latest"
+  }
+}
+
+variable "secrets" {
+  description = "Secrets to store in AWS Secrets Manager"
+  type        = map(string)
+  default     = {}
+}