#!/bin/sh

# Configuration
MAX_RETRIES=3
DELAY_SECONDS=5
API_URL="https://api.<YOUR_DD_SITE>/api/unstable/deployments/gates/evaluate"
API_KEY="<YOUR_API_KEY>"

PAYLOAD=$(cat <<EOF
{
  "data": {
    "type": "deployment_gates_evaluation_request",
    "attributes": {
      "service": "$1",
      "env": "$2",
      "version": "$3"
    }
  }
}
EOF
)

current_attempt=0
while [ $current_attempt -lt $MAX_RETRIES ]; do
   current_attempt=$((current_attempt + 1))
   RESPONSE=$(curl -s -w "%{http_code}" -o response.txt -X POST "$API_URL" \
       -H "Content-Type: application/json" \
       -H "DD-API-KEY: $API_KEY" \
       -d "$PAYLOAD")

   # Extracts the last 3 digits of the status code
   HTTP_CODE=$(echo "$RESPONSE" | tail -c 4)
   RESPONSE_BODY=$(cat response.txt)

   if [ ${HTTP_CODE} -ge 500 ]  &&  [ ${HTTP_CODE} -le 599 ]; then
       # Status code 5xx indicates a server error, so the call is retried
       echo "Attempt $current_attempt: 5xx Error ($HTTP_CODE). Retrying in $DELAY_SECONDS seconds..."
       sleep $DELAY_SECONDS
       continue

   elif [ ${HTTP_CODE} -ne 200 ]; then
       # Only 200 is an expected status code
       echo "Unexpected HTTP Code ($HTTP_CODE): $RESPONSE_BODY"
       exit 1
   fi

   # At this point, we have received a 200 status code. So, we check the gate status returned
   GATE_STATUS=$(echo "$RESPONSE_BODY" | jq -r '.data.attributes.gate_status')

   if [[ "$GATE_STATUS" == "pass" ]]; then
       echo "Gate evaluation PASSED"
       exit 0
   else
       echo "Gate evaluation FAILED"
       exit 1
   fi
done

# If we arrive here, it means that we received several 5xx errors from the API. To not block deployments, we can treat this case as a success
echo "All retries exhausted, but treating 5xx errors as success."
exit 0

apiVersion: argoproj.io/v1alpha1
kind: ClusterAnalysisTemplate
metadata:
  name: datadog-job-analysis
spec:
  args:
    - name: service
    - name: env
  metrics:
    - name: datadog-job
      provider:
        job:
          spec:
            ttlSecondsAfterFinished: 300
            backoffLimit: 0
            template:
              spec:
                restartPolicy: Never
                containers:
                  - name: datadog-check
                    image: alpine:latest
                    command: ["/bin/sh", "-c"]
                    args:
                      - |
                        apk add --no-cache curl jq

                        # Configuration
                        MAX_RETRIES=3
                        DELAY_SECONDS=5
                        API_URL="https://api.<YOUR_DD_SITE>/api/unstable/deployments/gates/evaluate"
                        API_KEY="<YOUR_API_KEY>"

                        PAYLOAD='{
                          "data": {
                            "type": "deployment_gates_evaluation_request",
                            "attributes": {
                              "service": "{{ args.service }}",
                              "env": "{{ args.env }}",
                              "version": "{{ args.version }}",
                            }
                          }
                        }'

                        current_attempt=0
                        while [ $current_attempt -lt $MAX_RETRIES ]; do
                          current_attempt=$((current_attempt + 1))
                          RESPONSE=$(curl -s -w "%{http_code}" -o response.txt -X POST "$API_URL" \
                              -H "Content-Type: application/json" \
                              -H "DD-API-KEY: $API_KEY" \
                              -d "$PAYLOAD")

                          # Extracts the last 3 digits of the status code
                          HTTP_CODE=$(echo "$RESPONSE" | tail -c 4)
                          RESPONSE_BODY=$(cat response.txt)

                          if [ ${HTTP_CODE} -ge 500 ]  &&  [ ${HTTP_CODE} -le 599 ]; then
                              # Status code 5xx indicates a server error, so the call is retried
                              echo "Attempt $current_attempt: 5xx Error ($HTTP_CODE). Retrying in $DELAY_SECONDS seconds..."
                              sleep $DELAY_SECONDS
                              continue

                          elif [ ${HTTP_CODE} -ne 200 ]; then
                              # Only 200 is an expected status code
                              echo "Unexpected HTTP Code ($HTTP_CODE): $RESPONSE_BODY"
                              exit 1
                          fi

                          # At this point, we have received a 200 status code. So, we check the gate status returned
                          GATE_STATUS=$(echo "$RESPONSE_BODY" | jq -r '.data.attributes.gate_status')

                          if [[ "$GATE_STATUS" == "pass" ]]; then
                              echo "Gate evaluation PASSED"
                              exit 0
                          else
                              echo "Gate evaluation FAILED"
                              exit 1
                          fi
                        done

                        # If we arrive here, it means that we received several 5xx errors from the API. To not block deployments, we can treat this case as a success
                        echo "All retries exhausted, but treating 5xx errors as success."
                        exit 0                        

apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
  name: rollouts-demo
  labels:
    tags.datadoghq.com/service: transaction-backend
    tags.datadoghq.com/env: dev
spec:
  replicas: 5
  strategy:
    canary:
      steps:
        ...
        - analysis:
            templates:
              - templateName: datadog-job-analysis
                clusterScope: true # Only needed for cluster analysis
            args:
              - name: env
                valueFrom:
                  fieldRef:
                    fieldPath: metadata.labels['tags.datadoghq.com/env']
              - name: service
                valueFrom:
                  fieldRef:
                    fieldPath: metadata.labels['tags.datadoghq.com/service']
              - name: version #Only required if one or more APM Faulty Deployment Detection rules are evaluated  
                valueFrom:
                  fieldRef:
                    fieldPath: metadata.labels['tags.datadoghq.com/version']
        - ...