Add S3/DDB gateway endpoints and payroll-batch DLQ (#37)

Audit M-22: S3 and DynamoDB traffic from the VPC was billed through
the NAT gateway; gateway endpoints are free and keep it on the AWS
backbone.

Audit L-15: payroll-batch messages were silently lost after max
receives. Adds a 14-day DLQ with maxReceiveCount 3 and an ALARM-only
notification to site-alerts so a caught failure is actually seen.

template.yaml

@@ -110,6 +110,28 @@ Resources:
       DestinationCidrBlock: 0.0.0.0/0
       NatGatewayId: !Ref NatGateway
 
+  # Gateway endpoints (audit M-22): keep S3/DynamoDB traffic off the NAT
+  # gateway — free, and removes per-GB NAT data-processing charges.
+  S3GatewayEndpoint:
+    Type: AWS::EC2::VPCEndpoint
+    Properties:
+      VpcId: !Ref Vpc
+      ServiceName: !Sub com.amazonaws.${AWS::Region}.s3
+      VpcEndpointType: Gateway
+      RouteTableIds:
+        - !Ref PublicRouteTable
+        - !Ref PrivateRouteTable
+
+  DynamoDbGatewayEndpoint:
+    Type: AWS::EC2::VPCEndpoint
+    Properties:
+      VpcId: !Ref Vpc
+      ServiceName: !Sub com.amazonaws.${AWS::Region}.dynamodb
+      VpcEndpointType: Gateway
+      RouteTableIds:
+        - !Ref PublicRouteTable
+        - !Ref PrivateRouteTable
+
   PrivateSubnetRouteTableAssociation:
     Type: AWS::EC2::SubnetRouteTableAssociation
     Properties:
@@ -196,6 +218,37 @@ Resources:
       DelaySeconds: 600
       MessageRetentionPeriod: 86400
       VisibilityTimeout: 60
+      RedrivePolicy:
+        deadLetterTargetArn: !GetAtt PayrollBatchDLQ.Arn
+        maxReceiveCount: 3
+
+  # Audit L-15: payroll-batch messages were lost after max receives. 14-day
+  # retention so a failure on Friday survives the weekend.
+  PayrollBatchDLQ:
+    Type: AWS::SQS::Queue
+    Properties:
+      QueueName: payments-payroll-batch-dlq
+      MessageRetentionPeriod: 1209600
+
+  PayrollBatchDLQAlarm:
+    Type: AWS::CloudWatch::Alarm
+    Properties:
+      AlarmName: payments-payroll-batch-dlq-messages
+      AlarmDescription: Failed payroll-batch messages landed in the DLQ
+      Namespace: AWS/SQS
+      MetricName: ApproximateNumberOfMessagesVisible
+      Dimensions:
+        - Name: QueueName
+          Value: !GetAtt PayrollBatchDLQ.QueueName
+      Statistic: Maximum
+      Period: 300
+      EvaluationPeriods: 1
+      Threshold: 0
+      ComparisonOperator: GreaterThanThreshold
+      TreatMissingData: notBreaching
+      # ALARM-only notification by convention — no OK/recovery action
+      AlarmActions:
+        - !Sub arn:aws:sns:${AWS::Region}:${AWS::AccountId}:site-alerts
 
   ProcessPayrollEmailLogGroup:
     Type: AWS::Logs::LogGroup