global:
  # Global configuration
  resolve_timeout: 5m

  # SMTP configuration for email alerts (optional)
  # Uncomment and configure to enable email notifications
  # smtp_smarthost: 'smtp.gmail.com:587'
  # smtp_from: 'alerts@example.com'
  # smtp_auth_username: 'alerts@example.com'
  # smtp_auth_password: 'your-app-password'
  # smtp_require_tls: true

  # Slack webhook URL (optional)
  # slack_api_url: 'https://hooks.slack.com/services/YOUR/WEBHOOK/URL'

  # PagerDuty API URL (default)
  # pagerduty_url: 'https://events.pagerduty.com/v2/enqueue'

# Templates for customizing alert messages (optional)
# Uncomment and mount template files to customize alert formatting
# templates:
#   - '/etc/alertmanager/template/*.tmpl'

# Route tree for alert dispatch
route:
  # Default receiver for unmatched alerts
  receiver: "default"

  # Group alerts by these labels to reduce noise
  group_by: ["alertname", "severity", "connector"]

  # How long to wait before sending the first notification
  # This allows alerts to group together
  group_wait: 30s

  # How long to wait before sending notification about new alerts
  # added to a group for which an initial notification has been sent
  group_interval: 5m

  # How long to wait before re-sending a given alert
  repeat_interval: 4h

  # Child routes for specific alert types
  routes:
    # Route critical alerts to PagerDuty (wakes up on-call)
    - match:
        severity: critical
      receiver: "pagerduty-critical"
      # Continue to also send to other receivers if needed
      continue: false
      # Override repeat interval for critical alerts
      repeat_interval: 1h
      # Override group_wait for faster critical alert delivery
      group_wait: 10s

    # Route warning alerts to Slack (business hours follow-up)
    - match:
        severity: warning
      receiver: "slack-warnings"
      continue: false
      repeat_interval: 12h
      group_wait: 5m

    # Route SLO alerts to a dedicated channel
    - match_re:
        slo: ".*"
      receiver: "slack-slo"
      continue: false
      repeat_interval: 6h

# Inhibition rules to prevent alert spam
# An alert inhibits another if all label values match
inhibit_rules:
  # If connector is down, don't alert on lag or throughput
  - source_match:
      alertname: "KafkaConnectorNotRunning"
    target_match_re:
      alertname: "KafkaConnect(HighLag|NoOffsetCommits)"
    equal: ["connector"]

  # If high error rate, suppress DLQ volume alerts (same root cause)
  - source_match:
      alertname: "KafkaConnectHighErrorRate"
    target_match:
      alertname: "KafkaConnectDLQVolumeSpike"
    equal: ["connector"]

  # Critical alerts inhibit warning alerts for the same connector
  - source_match:
      severity: "critical"
    target_match:
      severity: "warning"
    equal: ["connector", "component"]

# Receiver definitions
receivers:
  # Default receiver (logs to Alertmanager UI only)
  - name: "default"
    # No external integrations configured
    # Alerts will appear in Alertmanager web UI at http://localhost:9093

  # PagerDuty receiver for critical alerts
  - name: "pagerduty-critical"
    pagerduty_configs:
      # Configure your PagerDuty integration key here
      # Get this from: PagerDuty > Services > Your Service > Integrations > Events API v2
      #
      # SECURITY RECOMMENDATION for production:
      # Use environment variable substitution: service_key: '${PAGERDUTY_INTEGRATION_KEY}'
      # Or use Docker secrets for better security
      #
      # For testing/local development, replace the placeholder below:
      - service_key: "<YOUR_PAGERDUTY_INTEGRATION_KEY>"
        # Optional: Add custom details to PagerDuty incidents
        description: "{{ .GroupLabels.alertname }}: {{ .GroupLabels.connector }}"
        details:
          severity: "{{ .CommonLabels.severity }}"
          component: "{{ .CommonLabels.component }}"
          summary: "{{ .CommonAnnotations.summary }}"
          description: "{{ .CommonAnnotations.description }}"
          runbook: "{{ .CommonAnnotations.runbook }}"
        # Optional: Link back to alert in Prometheus/Grafana
        client: "Prometheus"
        client_url: "http://localhost:9090/alerts"

  # Slack receiver for warning alerts
  - name: "slack-warnings"
    slack_configs:
      # Configure your Slack webhook URL
      # Get this from: Slack > Apps > Incoming Webhooks > Add New Webhook
      #
      # SECURITY RECOMMENDATION for production:
      # Use environment variable substitution: api_url: '${SLACK_WEBHOOK_URL}'
      # Or use Docker secrets for better security
      #
      # For testing/local development, replace the placeholder below:
      - api_url: "<YOUR_SLACK_WEBHOOK_URL>"
        channel: "#cdc-alerts-warnings"
        # Optional: Customize message appearance
        title: ":warning: {{ .GroupLabels.alertname }}"
        text: |
          *Connector:* {{ .GroupLabels.connector }}
          *Severity:* {{ .CommonLabels.severity }}
          *Summary:* {{ .CommonAnnotations.summary }}

          {{ .CommonAnnotations.description }}
        # Optional: Color-code messages (good, warning, danger)
        color: "warning"
        # Optional: Add action buttons
        actions:
          - type: button
            text: "View in Prometheus"
            url: "http://localhost:9090/alerts"
          - type: button
            text: "View in Grafana"
            url: "http://localhost:3000"

  # Slack receiver for SLO alerts
  - name: "slack-slo"
    slack_configs:
      # SECURITY RECOMMENDATION for production:
      # Use environment variable substitution: api_url: '${SLACK_WEBHOOK_URL}'
      # Or use Docker secrets for better security
      - api_url: "<YOUR_SLACK_WEBHOOK_URL>"
        channel: "#cdc-slo-tracking"
        title: ":chart_with_downwards_trend: {{ .GroupLabels.alertname }}"
        text: |
          *SLO Type:* {{ .CommonLabels.slo }}
          *Connector:* {{ .GroupLabels.connector }}
          *Summary:* {{ .CommonAnnotations.summary }}

          {{ .CommonAnnotations.description }}
        color: "warning"

  # Email receiver example (uncomment and configure global SMTP settings above)
  # - name: 'email-ops'
  #   email_configs:
  #     - to: 'ops-team@example.com'
  #       from: 'alerts@example.com'
  #       subject: '[{{ .Status | toUpper }}] {{ .GroupLabels.alertname }}'
  #       html: |
  #         <h2>{{ .GroupLabels.alertname }}</h2>
  #         <p><strong>Severity:</strong> {{ .CommonLabels.severity }}</p>
  #         <p><strong>Connector:</strong> {{ .GroupLabels.connector }}</p>
  #         <p><strong>Summary:</strong> {{ .CommonAnnotations.summary }}</p>
  #         <p>{{ .CommonAnnotations.description }}</p>
  #       headers:
  #         Subject: '[{{ .Status | toUpper }}] {{ .GroupLabels.alertname }}'

  # Webhook receiver example (send to custom webhook endpoint)
  # - name: 'custom-webhook'
  #   webhook_configs:
  #     - url: 'http://your-webhook-endpoint/alerts'
  #       send_resolved: true
  #       http_config:
  #         basic_auth:
  #           username: 'webhook-user'
  #           password: 'webhook-password'

# Time-based muting (optional)
# Useful for maintenance windows or known downtime
# mute_time_intervals:
#   - name: 'maintenance-window'
#     time_intervals:
#       - times:
#           - start_time: '02:00'
#             end_time: '04:00'
#         weekdays: ['saturday', 'sunday']
#         months: ['january:december']
#
# Then in route:
# routes:
#   - match:
#       severity: warning
#     receiver: 'slack-warnings'
#     mute_time_intervals:
#       - 'maintenance-window'