# Alertmanager for the llmgw cluster.
#
# Nothing is sent anywhere yet, on purpose. Where an alert should go — an
# address, a Slack workspace, a webhook — is a decision with credentials
# attached, and a monitoring system that quietly starts mailing people is worse
# than one that is visibly not wired up. Alerts group and fire here and are
# visible at :9093 and in Prometheus; add a receiver below to make them travel.
global:
  resolve_timeout: 5m

route:
  # By alert and by what it is about, so five nodes going quiet in the same
  # network blip arrive as one notification rather than five.
  group_by: ['alertname', 'node', 'model']
  group_wait: 30s
  group_interval: 5m
  # Long, because a repeat is a reminder and not news. A cluster with one thing
  # wrong should not produce a message an hour.
  repeat_interval: 12h
  receiver: none

  routes:
    # Critical gets its own branch so it can be pointed somewhere else later
    # without touching the rest: the difference between "a node is draining"
    # and "nothing is serving" is who should be woken.
    - matchers: [severity="critical"]
      receiver: none
      group_wait: 10s
      repeat_interval: 4h

receivers:
  - name: none

inhibit_rules:
  # A node that is down explains every replica on it. Reporting both says the
  # same thing twice and buries whichever is the actual cause.
  - source_matchers: [alertname="NodeNotReady"]
    target_matchers: [alertname="EndpointMetricsStale"]
    equal: ['node']
  - source_matchers: [alertname="ControlPlaneUnreachable"]
    target_matchers: [severity="warning"]