Merge pull request #40 from CGC-2026/hotfix/cloud-infra

yml changes

Author: NickSavino

.github/workflows/deploy.yml

@@ -98,9 +98,71 @@ jobs:
             --query 'Command.CommandId' \
             --output text)
 
-          aws ssm get-command-invocation \
+      - name: Wait for SSM command to finish
+        run: |
+          set -euo pipefail
+
+          COMMAND_ID='${{ steps.ssm_send.outputs.command_id }}'
+          echo "Waiting on SSM CommandId: ${COMMAND_ID}"
+
+          for i in {1..80}; do
+            STATUS=$(aws ssm get-command-invocation \
+              --region "${AWS_REGION}" \
+              --command-id "${COMMAND_ID}" \
+              --instance-id "${EC2_INSTANCE_ID}" \
+              --query 'Status' \
+              --output text)
+
+            echo "SSM status: ${STATUS}"
+
+            case "$STATUS" in
+              Pending|InProgress|Delayed)
+                sleep 3
+                ;;
+              Success)
+                aws ssm get-command-invocation \
+                  --region "${AWS_REGION}" \
+                  --command-id "${COMMAND_ID}" \
+                  --instance-id "${EC2_INSTANCE_ID}" \
+                  --query '{Status:Status,ExitCode:ResponseCode,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
+                  --output json
+                exit 0
+                ;;
+              *)
+                aws ssm get-command-invocation \
+                  --region "${AWS_REGION}" \
+                  --command-id "${COMMAND_ID}" \
+                  --instance-id "${EC2_INSTANCE_ID}" \
+                  --query '{Status:Status,ExitCode:ResponseCode,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
+                  --output json
+                echo "SSM command failed with status: ${STATUS}" >&2
+                exit 1
+                ;;
+            esac
+          done
+
+          echo "SSM command did not finish in time" >&2
+          exit 1
+
+      - name: Verify health
+        run: |
+          set -euo pipefail
+
+          PUBLIC_IP=$(aws ec2 describe-instances \
             --region "${AWS_REGION}" \
-            --command-id "${COMMAND_ID}" \
-            --instance-id "${EC2_INSTANCE_ID}" \
-            --query '{Status:Status,ExitCode:ResponseCode,Stdout:StandardOutputContent,Stderr:StandardErrorContent}' \
-            --output json
+            --instance-ids "${EC2_INSTANCE_ID}" \
+            --query 'Reservations[0].Instances[0].PublicIpAddress' \
+            --output text)
+
+            test "${PUBLIC_IP}" != "None"
+
+          for i in {1..20}; do
+            if curl -fsS "${URL}" >/dev/null; then
+              echo "Health check passed"
+              exit 0
+            fi
+            echo "Health not ready yet (attempt $i/20) — retrying..."
+            sleep 3
+          done
+
+          echo "Health check failed"