Monitorizar resultados de negocio: paneles en verde, caja vacía

# GitHub Actions: a synthetic check that fails (and emails the owner) when a vital page breaks
on:
  schedule:
    - cron: "*/10 * * * *"
jobs:
  check:
    runs-on: ubuntu-latest
    steps:
      - run: |
          for path in / /book /checkout; do
            code=$(curl -s -o /dev/null -L --max-time 20 -w '%{http_code}' "https://www.example.com$path")
            [ "$code" = "200" ] || { echo "FAIL $path -> $code"; exit 1; }
          done

-- Paid, but no reservation after 15 minutes: should always be empty
SELECT p.id, p.amount, p.created_at
FROM payments p
LEFT JOIN reservations r ON r.payment_id = p.id
WHERE p.status = 'succeeded'
  AND r.id IS NULL
  AND p.created_at < now() - interval '15 minutes';

groups:
  - name: booking-slo
    rules:
      - record: booking:success_ratio:rate1h
        expr: |
          sum(rate(bookings_completed_total[1h]))
            / sum(rate(bookings_started_total[1h]))
      - alert: BookingSuccessBelowObjective
        expr: |
          booking:success_ratio:rate1h < 0.995
            and sum(rate(bookings_started_total[1h])) * 3600 > 20   # enough traffic to judge
        for: 15m
        labels:
          severity: page
        annotations:
          summary: "Fewer than 99.5% of started bookings complete"
          runbook_url: "https://runbooks.example.com/booking-success"