Microsoft Azure Kubernetes Service (AKS) Node Pool Autoscale Capacity Ceiling Sentinel

id: azure-aks-nodepool-autoscale-limit-sentinel
namespace: company.cloud

inputs:
  - id: subscription_id
    type: STRING
    description: Azure Subscription ID.
  - id: resource_group
    type: STRING
    description: Azure Resource Group name.
  - id: cluster_name
    type: STRING
    description: Azure Kubernetes Service (AKS) cluster name.

tasks:
  - id: check_nodepool_limits
    type: io.kestra.plugin.scripts.shell.Commands
    containerImage: mcr.microsoft.com/azure-cli:latest
    commands:
      - |
        az login --service-principal -u "{{ secret('AZURE_CLIENT_ID') }}" -p "{{ secret('AZURE_CLIENT_SECRET') }}" --tenant "{{ secret('AZURE_TENANT_ID') }}" --output none
        az account set --subscription "{{ inputs.subscription_id }}"

        # Query node pools where current count meets or exceeds maxCount
        az aks nodepool list           --cluster-name "{{ inputs.cluster_name }}"           --resource-group "{{ inputs.resource_group }}"           --query "[?enableAutoScaling && count >= maxCount].{pool:name, current:count, max:maxCount}"           --output json > /tmp/nodepool_telemetry.json

        SATURATED_POOLS=$(jq 'length' /tmp/nodepool_telemetry.json)
        echo "::set-output name=saturated_pool_count::$SATURATED_POOLS::"

  - id: evaluate_nodepool_saturation
    type: io.kestra.plugin.core.flow.If
    condition: "{{ outputs.check_nodepool_limits.vars.saturated_pool_count | int > 0 }}"
    then:
      - id: notify_platform_team
        type: io.kestra.plugin.slack.notifications.SlackIncomingWebhook
        url: "{{ secret('SLACK_WEBHOOK') }}"
        payload: |
          {
            "channel": "#k8s-platform",
            "attachments": [
              {
                "color": "danger",
                "title": "🚨 AKS Node Pool Autoscale Capacity Saturated Alert",
                "text": "AKS Cluster `{{ inputs.cluster_name }}` has *{{ outputs.check_nodepool_limits.vars.saturated_pool_count }} node pool(s)* operating at their absolute maximum autoscale limit (`maxCount`)! New workloads and deployments are at severe risk of Pending scheduling starvation.",
                "footer": "Kestra Cloud Sentinel • Microsoft Azure AKS"
              }
            ]
          }

errors:
  - id: alert_pipeline_failure
    type: io.kestra.plugin.slack.notifications.SlackIncomingWebhook
    url: "{{ secret('SLACK_WEBHOOK') }}"
    payload: |
      {
        "channel": "#k8s-platform",
        "attachments": [
          {
            "color": "danger",
            "title": "⚠️ Azure AKS Node Pool Sentinel Failure",
            "text": "Failed to query AKS cluster node pools. Verify cluster name, resource group, and permissions.",
            "footer": "Kestra Workflow Failure Sentinel"
          }
        ]
      }

triggers:
  - id: periodic_schedule
    type: io.kestra.plugin.core.trigger.Schedule
    cron: "*/15 * * * *"
    disabled: true
    inputs:
      subscription_id: replace-with-your-subscription-id
      resource_group: replace-with-your-resource-group
      cluster_name: replace-with-your-cluster-name