source ~/route53-arc-tf/global.env

cd ~/route53-arc-tf/03_arc
export PRIMARY_RC_ARN=$(terraform output -raw primary_rc_arn)
export SECONDARY_RC_ARN=$(terraform output -raw secondary_rc_arn)
export CLUSTER_ENDPOINT=$(terraform output -json arc_cluster_endpoints \
  | python3 -c "import json,sys; print(json.load(sys.stdin)[0]['Endpoint'])")

cd ~/route53-arc-tf/01_primary
export EC2_ID=$(terraform output -raw ec2_instance_id)
export PRIMARY_ALB_DNS=$(terraform output -raw alb_dns_name)

cd ~/route53-arc-tf/04_automation
export ALARM_NAME=$(terraform output -raw alarm_name)

echo "ALB DNS: $PRIMARY_ALB_DNS"

COMMAND_ID=$(aws ssm send-command \
  --instance-ids $EC2_ID \
  --document-name AWS-RunShellScript \
  --parameters 'commands=["systemctl start nginx && systemctl status nginx --no-pager | head -3"]' \
  --region $AWS_REGION \
  --query 'Command.CommandId' --output text)

sleep 10
aws ssm get-command-invocation \
  --command-id $COMMAND_ID --instance-id $EC2_ID \
  --region $AWS_REGION \
  --query '{Status: Status, Output: StandardOutputContent}' --output json

echo "Esperando que el primario se recupere..."

for i in $(seq 1 10); do
  TG_ARN=$(aws elbv2 describe-target-groups \
    --names route53-arc-primary-tg --region $AWS_REGION \
    --query 'TargetGroups[0].TargetGroupArn' --output text 2>/dev/null)

  TG_HEALTH=$(aws elbv2 describe-target-health \
    --target-group-arn $TG_ARN --region $AWS_REGION \
    --query 'TargetHealthDescriptions[0].TargetHealth.State' --output text 2>/dev/null)

  HTTP=$(curl -s -o /dev/null -w "%{http_code}" \
    --connect-timeout 3 --max-time 5 http://$PRIMARY_ALB_DNS/ 2>/dev/null)

  echo "[$(date '+%H:%M:%S')] Target Group: $TG_HEALTH | HTTP: $HTTP"

  if [ "$TG_HEALTH" = "healthy" ] && [ "$HTTP" = "200" ]; then
    echo "✅ Sitio primario recuperado y funcionando"
    break
  fi
  sleep 15
done

echo "=== EJECUTANDO FAILBACK ==="

aws route53-recovery-cluster update-routing-control-states \
  --update-routing-control-state-entries \
    "[{\"RoutingControlArn\":\"$PRIMARY_RC_ARN\",\"RoutingControlState\":\"On\"},
      {\"RoutingControlArn\":\"$SECONDARY_RC_ARN\",\"RoutingControlState\":\"Off\"}]" \
  --endpoint-url $CLUSTER_ENDPOINT --region $AWS_REGION

echo "✅ Failback ejecutado: Primario=ON | Secundario=OFF"

# Restablecer alarma
aws cloudwatch set-alarm-state \
  --alarm-name $ALARM_NAME \
  --state-value OK \
  --state-reason "Sitio primario recuperado – failback completado" \
  --region $AWS_REGION

echo "✅ Alarma restablecida a OK"

echo "=== Verificación Lab 6: Failback ==="

P=$(aws route53-recovery-cluster get-routing-control-state \
  --routing-control-arn $PRIMARY_RC_ARN \
  --endpoint-url $CLUSTER_ENDPOINT --region $AWS_REGION \
  --query 'RoutingControlState' --output text 2>/dev/null)

S=$(aws route53-recovery-cluster get-routing-control-state \
  --routing-control-arn $SECONDARY_RC_ARN \
  --endpoint-url $CLUSTER_ENDPOINT --region $AWS_REGION \
  --query 'RoutingControlState' --output text 2>/dev/null)

[ "$P" = "On"  ] && echo "✅ Primario: $P" || echo "❌ Primario: $P"
[ "$S" = "Off" ] && echo "✅ Secundario: $S" || echo "❌ Secundario: $S"

HTTP=$(curl -s -o /dev/null -w "%{http_code}" http://$PRIMARY_ALB_DNS/ 2>/dev/null)
[ "$HTTP" = "200" ] && echo "✅ Sitio primario: HTTP $HTTP" || echo "⚠️  HTTP $HTTP"

echo ""
echo "🎉 Ciclo completo: Detección → Notificación → Failover → Reparación → Failback"