Deployment: Staging deploy workflow for EC2 via SSM

.env.example

@@ -25,7 +25,7 @@ API_BASE_URL=http://localhost:8000
 CRON_INTERVAL_MINUTES=5
 
 # Postgres
-POSTGRES_SERVER=localhost
+POSTGRES_SERVER=db
 POSTGRES_PORT=5432
 POSTGRES_DB=kaapi
 POSTGRES_USER=postgres

.github/workflows/cd-production.yml

@@ -36,8 +36,47 @@ jobs:
           REPOSITORY: ${{ vars.AWS_RESOURCE_PREFIX }}-repo
           TAG: ${{ github.ref_name }}
         run: |
-          docker build -t $REGISTRY/$REPOSITORY:latest ./backend
+          docker build \
+            -t $REGISTRY/$REPOSITORY:latest \
+            -t $REGISTRY/$REPOSITORY:$TAG \
+            ./backend
           docker push $REGISTRY/$REPOSITORY:latest
+          docker push $REGISTRY/$REPOSITORY:$TAG
+
+      - name: Run database migrations
+        env:
+          CLUSTER: ${{ vars.AWS_RESOURCE_PREFIX }}-cluster
+          SERVICE: ${{ vars.AWS_RESOURCE_PREFIX }}-service
+          TASK_DEF: ${{ vars.AWS_RESOURCE_PREFIX }}-task
+        run: |
+          CONTAINER_NAME=$(aws ecs describe-task-definition --task-definition $TASK_DEF --query 'taskDefinition.containerDefinitions[0].name' --output text)
+
+          NETWORK_CONFIG=$(aws ecs describe-services --cluster $CLUSTER --services $SERVICE \
+            --query 'services[0].networkConfiguration' --output json | jq -c '.')
+
+          TASK_ARN=$(aws ecs run-task \
+            --cluster $CLUSTER \
+            --launch-type FARGATE \
+            --task-definition $TASK_DEF \
+            --count 1 \
+            --network-configuration "$NETWORK_CONFIG" \
+            --overrides "{\"containerOverrides\":[{\"name\":\"$CONTAINER_NAME\",\"command\":[\"uv\",\"run\",\"alembic\",\"upgrade\",\"head\"]}]}" \
+            --query 'tasks[0].taskArn' --output text)
+
+          echo "Migration task started: $TASK_ARN"
+          aws ecs wait tasks-stopped --cluster $CLUSTER --tasks "$TASK_ARN"
+
+          EXIT_CODE=$(aws ecs describe-tasks --cluster $CLUSTER --tasks "$TASK_ARN" \
+            --query "tasks[0].containers[?name=='$CONTAINER_NAME'].exitCode | [0]" --output text)
+
+          if [ "$EXIT_CODE" != "0" ]; then
+            echo "Migration failed with exit code $EXIT_CODE"
+            aws ecs describe-tasks --cluster $CLUSTER --tasks "$TASK_ARN" \
+              --query "tasks[0].{stopCode:stopCode,stoppedReason:stoppedReason,containerReason:containers[?name=='$CONTAINER_NAME'].reason | [0]}" \
+              --output json
+            exit 1
+          fi
+          echo "Migration completed successfully"
 
       - name: Deploy to ECS
         run: |

.github/workflows/cd-staging-ec2.yml

@@ -0,0 +1,59 @@
+name: Deploy Kaapi staging to EC2
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+concurrency:
+  group: staging-ec2-deploy
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment: AWS_STAGING_ENV
+
+    permissions:
+      id-token: write
+      contents: read
+
+    steps:
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v6
+        with:
+          role-to-assume: ${{ secrets.STAGING_EC2_DEPLOY_ROLE_ARN }}
+          aws-region: ap-south-1
+
+      - name: Trigger deploy on EC2 via SSM
+        id: ssm
+        env:
+          INSTANCE_ID: ${{ secrets.STAGING_EC2_INSTANCE_ID }}
+        run: |
+          CMD_ID=$(aws ssm send-command \
+            --instance-ids "$INSTANCE_ID" \
+            --document-name "AWS-RunShellScript" \
+            --comment "Deploy kaapi-backend kaapi-staging" \
+            --parameters commands='["set -eux","chown -R ubuntu:ubuntu /data/kaapi-backend","sudo -iu ubuntu bash -lc \"cd /data/kaapi-backend && git fetch --all && git pull origin main && docker compose -f docker-compose.staging.yml build && docker compose -f docker-compose.staging.yml --profile migrate run --rm migrate && docker compose -f docker-compose.staging.yml up -d --remove-orphans && docker image prune -f\""]' \
+            --cloud-watch-output-config CloudWatchOutputEnabled=true \
+            --query "Command.CommandId" --output text)
+          echo "cmd_id=$CMD_ID" >> "$GITHUB_OUTPUT"
+          echo "Sent SSM command: $CMD_ID"
+
+      - name: Wait for SSM command to finish
+        env:
+          INSTANCE_ID: ${{ secrets.STAGING_EC2_INSTANCE_ID }}
+          CMD_ID: ${{ steps.ssm.outputs.cmd_id }}
+        run: |
+          WAIT_EXIT=0
+          aws ssm wait command-executed \
+            --command-id "$CMD_ID" \
+            --instance-id "$INSTANCE_ID" || WAIT_EXIT=$?
+
+          aws ssm get-command-invocation \
+            --command-id "$CMD_ID" \
+            --instance-id "$INSTANCE_ID" \
+            --query '{Status:Status,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
+            --output json
+
+          exit $WAIT_EXIT

docker-compose.staging.yml

@@ -0,0 +1,67 @@
+version: "3.9"
+
+services:
+  backend:
+    image: "${DOCKER_IMAGE_BACKEND?Variable not set}:${TAG:-latest}"
+    container_name: backend
+    restart: always
+    build:
+      context: ./backend
+    env_file:
+      - .env
+    ports:
+      - "8000:80"
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:80/api/v1/utils/health/"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    command: >
+      uv run uvicorn app.main:app --host 0.0.0.0 --port 80 --reload
+    develop:
+      watch:
+        # Sync backend source code into container immediately on change
+        - action: sync
+          path: ./backend/app
+          target: /app/app
+        # Rebuild image if dependencies change
+        - action: rebuild
+          path: ./backend/pyproject.toml
+        - action: rebuild
+          path: ./backend/uv.lock
+    logging:
+      driver: awslogs
+      options:
+        awslogs-region: ap-south-1
+        awslogs-group: /ec2/kaapi-staging
+        awslogs-stream: backend
+        awslogs-create-group: "true"
+
+  migrate:
+    image: "${DOCKER_IMAGE_BACKEND?Variable not set}:${TAG:-latest}"
+    build:
+      context: ./backend
+    env_file:
+      - .env
+    profiles: ["migrate"]
+    command: ["uv", "run", "alembic", "upgrade", "head"]
+
+  celery_worker:
+    image: "${DOCKER_IMAGE_BACKEND?Variable not set}:${TAG:-latest}"
+    container_name: celery-worker
+    restart: always
+    build:
+      context: ./backend
+    depends_on:
+      backend:
+        condition: service_healthy
+    env_file:
+      - .env
+    command: ["uv", "run", "celery", "-A", "app.celery.celery_app", "worker", "--loglevel=info"]
+    logging:
+      driver: awslogs
+      options:
+        awslogs-region: ap-south-1
+        awslogs-group: /ec2/kaapi-staging
+        awslogs-stream: celery-worker
+        awslogs-create-group: "true"