Deployment: Production CD for guardrails

.github/workflows/cd-production.yml

@@ -0,0 +1,96 @@
+name: Deploy Kaapi Guardrails to EC2 Production
+
+on:
+  push:
+    tags:
+      - "v*" # Deploy only when tags like v1.0.0, v2.1.0, etc., are created
+
+concurrency:
+  group: guardrail-production-ec2-deploy
+  cancel-in-progress: false
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment: AWS_ENV_SECRETS
+
+    permissions:
+      id-token: write
+      contents: read
+
+    steps:
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v6
+        with:
+          role-to-assume: ${{ secrets.EC2_DEPLOY_ROLE_ARN }}
+          aws-region: ${{ secrets.AWS_REGION }}
+
+      - name: Trigger deploy on EC2 via SSM
+        id: ssm
+        env:
+          INSTANCE_ID: ${{ secrets.EC2_INSTANCE_ID }}
+          BUILD_DIRECTORY: ${{ secrets.BUILD_DIRECTORY }}
+        run: |
+          DEPLOY_CMD="cd ${BUILD_DIRECTORY} && git fetch --tags origin && git checkout --force ${{ github.sha }} && docker compose build && docker compose run --rm --entrypoint '' backend uv run alembic upgrade head && docker compose up -d --remove-orphans && docker image prune -f"
+
+          CMD_ID=$(aws ssm send-command \
+            --instance-ids "$INSTANCE_ID" \
+            --document-name "AWS-RunShellScript" \
+            --comment "Deploy kaapi-guardrails production" \
+            --parameters "commands=[\"set -eux\", \"sudo chown -R ec2-user:ec2-user ${BUILD_DIRECTORY}\", \"sudo -iu ec2-user bash -lc \\\"${DEPLOY_CMD}\\\"\"]" \
+            --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.EC2_INSTANCE_ID }}
+          CMD_ID: ${{ steps.ssm.outputs.cmd_id }}
+        run: |
+          for i in {1..20}; do
+            STATUS=$(aws ssm get-command-invocation \
+              --command-id "$CMD_ID" \
+              --instance-id "$INSTANCE_ID" \
+              --query "Status" \
+              --output text)
+
+            echo "Current Status: $STATUS"
+
+            if [ "$STATUS" = "Success" ]; then
+              echo "Deployment completed successfully."
+
+              aws ssm get-command-invocation \
+                --command-id "$CMD_ID" \
+                --instance-id "$INSTANCE_ID" \
+                --query '{Status:Status,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
+                --output json
+
+              exit 0
+            fi
+
+            if [ "$STATUS" = "Failed" ] || [ "$STATUS" = "Cancelled" ] || [ "$STATUS" = "TimedOut" ]; then
+              echo "Deployment failed."
+
+              aws ssm get-command-invocation \
+                --command-id "$CMD_ID" \
+                --instance-id "$INSTANCE_ID" \
+                --query '{Status:Status,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
+                --output json
+
+              exit 1
+            fi
+
+            sleep 15
+          done
+
+          echo "Deployment timed out after waiting too long."
+
+          aws ssm get-command-invocation \
+            --command-id "$CMD_ID" \
+            --instance-id "$INSTANCE_ID" \
+            --query '{Status:Status,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
+            --output json
+
+          exit 1