apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: edu-master-webinar
  namespace: edu-master
  labels:
    release: prometheus-stack
spec:
  groups:
    - name: edu_master.webinar
      rules:
        # No successful webinar check for 5m (~2-3 missed 2-min checks).
        # Catches: playwright hangs/timeouts, version skew, site changes, hung job.
        # The last_success > 0 guard is mandatory: checker.py initialises
        # last_success to 0, so without it `time() - 0` equals the current epoch
        # and humanizeDuration renders ~20722d on every pod restart. Keep the
        # duration expression on the left so $value stays the real gap.
        - alert: WebinarCheckerNoSuccessfulCheck
          expr: |
            ((time() - webinar_check_last_success_timestamp_seconds) > 300)
              and (webinar_check_last_success_timestamp_seconds > 0)
              and (webinar_check_last_run_timestamp_seconds > 0)
          for: 2m
          labels:
            severity: critical
          annotations:
            summary: "Webinar checker has no successful check for 5m"
            description: "edu-master/webinar-checker: last successful webinar check was {{ $value | humanizeDuration }} ago. Checks are failing or hanging (see consecutive failures alert). Notifications about new webinars are NOT being sent."

        # Checks are running but none has ever succeeded since pod start.
        # Split out from the rule above so a zeroed gauge never feeds
        # humanizeDuration.
        - alert: WebinarCheckerNeverSucceeded
          expr: |
            (webinar_check_last_success_timestamp_seconds == 0)
              and (webinar_check_last_run_timestamp_seconds > 0)
          for: 10m
          labels:
            severity: critical
          annotations:
            summary: "Webinar checker has never completed a successful check"
            description: 'edu-master/webinar-checker: checks have been running for 10m but not one has ever succeeded since the pod started, so every check is failing. Check pod logs (Loki: {namespace="edu-master", container="webinar-checker"}).'

        # Fast path: 3 consecutive failures (~6+ min at 2-min interval).
        - alert: WebinarCheckerConsecutiveFailures
          expr: |
            webinar_check_consecutive_failures >= 3
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "Webinar checker failing consecutively"
            description: 'edu-master/webinar-checker: {{ $value }} consecutive webinar check failures (timeout / playwright error / page error). Check pod logs (Loki: {namespace="edu-master", container="webinar-checker"}).'

        # Metrics endpoint not scraped for 10m: pod down, metrics server dead, or ServiceMonitor broken.
        - alert: WebinarCheckerScrapeDown
          expr: |
            absent(webinar_check_last_run_timestamp_seconds) == 1
          for: 10m
          labels:
            severity: critical
          annotations:
            summary: "Webinar checker metrics missing"
            description: "edu-master/webinar-checker: no metrics series for 10m. Pod may be down, metrics server dead, or ServiceMonitor/Service broken. Webinar checks are unobserved."

        # EDU session lost: session-keeper down or credentials expired. Without PHPSESSID every check is skipped.
        - alert: EduPhpsessidMissing
          expr: |
            edu_phpsessid_present == 0
          for: 10m
          labels:
            severity: critical
          annotations:
            summary: "EDU_PHPSESSID missing"
            description: "edu-master: EDU_PHPSESSID absent from redis for 10m. Webinar/diari/schedule checks are all skipped. Check session-keeper logs and EDU credentials."

        # Hard deps: checker and playwright deployments unavailable.
        - alert: WebinarCheckerDeploymentDown
          expr: |
            kube_deployment_status_replicas_unavailable{deployment="webinar-checker", namespace="edu-master"} > 0
          for: 10m
          labels:
            severity: critical
          annotations:
            summary: "Webinar checker deployment unavailable"
            description: "edu-master/webinar-checker deployment has {{ $value }} unavailable replica(s) for 10m."

        - alert: PlaywrightServiceDown
          expr: |
            kube_deployment_status_replicas_unavailable{deployment="playwright-service", namespace="edu-master"} > 0
          for: 10m
          labels:
            severity: critical
          annotations:
            summary: "Playwright service unavailable"
            description: "edu-master/playwright-service deployment has {{ $value }} unavailable replica(s) for 10m. All webinar/diari/schedule checks fail without it."