# Grafana provisioned alert rules for the Scrabble contour. Each rule is a Prometheus
# instant query (refId A) fed into a threshold expression (refId C). noDataState/execErrState
# are OK so an absent metric never raises a false alert — notably cert-expiry, whose blackbox
# probe has no target on the test contour (caddy is HTTP-only there). Metric names are the
# real ones Prometheus exposes (edge_request_* from the gateway via the collector,
# node_*/pg_*/probe_ssl_* from the exporters). All route to the ops-email contact point.
apiVersion: 1
groups:
  - orgId: 1
    name: scrabble-service
    folder: Alerts
    interval: 1m
    rules:
      - uid: svc_target_down
        title: Scrape target down
        condition: C
        for: 3m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model: { refId: A, expr: up, instant: true }
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: lt, params: [1] }
        labels: { severity: critical }
        annotations: { summary: 'A Prometheus scrape target is down (up < 1).' }

      - uid: edge_error_rate
        title: Gateway internal-error rate high
        condition: C
        for: 10m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: sum by (service_name) (rate(edge_request_duration_count{result="internal"}[5m]))
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [0.05] }
        labels: { severity: warning }
        annotations: { summary: 'Sustained internal (5xx-equivalent) errors at the edge.' }

      - uid: edge_latency_p99
        title: Gateway request latency p99 high
        condition: C
        for: 10m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: histogram_quantile(0.99, sum by (le, service_name) (rate(edge_request_duration_bucket[5m])))
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [1] }
        labels: { severity: warning }
        annotations: { summary: 'Edge request p99 latency above 1s.' }

      - uid: tls_cert_expiry
        title: TLS certificate nearing expiry
        condition: C
        for: 15m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: (probe_ssl_earliest_cert_expiry - time()) / 86400
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: lt, params: [20] }
        labels: { severity: critical }
        annotations: { summary: 'Edge TLS cert has under 20 days left — Caddy ACME renewal may have failed.' }

  - orgId: 1
    name: scrabble-host
    folder: Alerts
    interval: 1m
    rules:
      - uid: host_mem_low
        title: Host memory low
        condition: C
        for: 5m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: lt, params: [0.1] }
        labels: { severity: critical }
        annotations: { summary: 'Under 10% host memory available.' }

      - uid: host_disk_low
        title: Host disk low
        condition: C
        for: 10m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: min(node_filesystem_avail_bytes / node_filesystem_size_bytes)
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: lt, params: [0.1] }
        labels: { severity: critical }
        annotations: { summary: 'A host filesystem is under 10% free.' }

      - uid: host_cpu_high
        title: Host CPU saturated
        condition: C
        for: 10m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: 1 - avg(rate(node_cpu_seconds_total{mode="idle"}[5m]))
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [0.9] }
        labels: { severity: warning }
        annotations: { summary: 'Host CPU above 90% for 10 minutes.' }

      - uid: pg_connections_high
        title: Postgres connections high
        condition: C
        for: 5m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: sum(pg_stat_activity_count) / max(pg_settings_max_connections)
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [0.8] }
        labels: { severity: warning }
        annotations: { summary: 'Postgres using over 80% of max_connections.' }

  # Continuous WAL archiving health (pgBackRest -> S3, point-in-time recovery). Both rules
  # read the postgres_exporter's built-in pg_stat_archiver metrics and are absent/NaN-safe:
  # on the test contour (and any host before archiving is armed) archive_mode is off, so
  # failed_count stays 0 and last_archive_age is NaN — neither threshold trips.
  - orgId: 1
    name: scrabble-backup
    folder: Alerts
    interval: 1m
    rules:
      - uid: pg_archive_failing
        title: WAL archiving failing
        condition: C
        for: 15m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 900, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: increase(pg_stat_archiver_failed_count[15m])
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [0] }
        labels: { severity: critical }
        annotations: { summary: 'pgBackRest archive_command is failing — PITR is degrading and pg_wal can fill the disk. Run `docker exec scrabble-postgres pgbackrest --stanza=scrabble --pg1-user=scrabble check`.' }

      # Fires only when the last archive is >30 min old AND pg_wal is actually growing (WAL is being
      # produced but not archived). A genuinely idle database archives nothing — Postgres does not
      # force-switch an empty segment on archive_timeout — so `last_archive_age` alone false-triggers
      # during quiet hours; the pg_wal-growth guard removes that. `and on()` bridges the differing
      # label sets (last_archive_age has a server label, the pg_wal gauge does not); delta() (not
      # increase) suits the pg_wal_size_bytes gauge. Real archive failures are caught by pg_archive_failing.
      - uid: pg_archive_stalled
        title: WAL archiving stalled
        condition: C
        for: 15m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 2100, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: (pg_stat_archiver_last_archive_age > 1800) and on() (delta(pg_wal_size_bytes[35m]) > 16777216)
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [1800] }
        labels: { severity: critical }
        annotations: { summary: 'No WAL archived for over 30 minutes while pg_wal keeps growing — archiving is genuinely stalled; the PITR recovery point is frozen and pg_wal will fill the disk. Run `docker exec scrabble-postgres pgbackrest --stanza=scrabble --pg1-user=scrabble check`.' }

  # Remote Telegram bot health. The bot runs on its own host and exports no telemetry of its own; the
  # gateway observes it through the bot-link (botlink_connected_bots) and the health it reports over
  # that stream (bot_tg_*). All absent/NaN-safe: before a bot ever connects the metrics are absent, so
  # noDataState OK keeps them quiet on a fresh contour. The alert email does NOT go through the bot, so
  # a bot-down alert is deliverable.
  - orgId: 1
    name: scrabble-bot
    folder: Alerts
    interval: 1m
    rules:
      - uid: bot_disconnected
        title: Telegram bot disconnected
        condition: C
        for: 5m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 300, to: 0 }
            datasourceUid: prometheus
            model: { refId: A, expr: botlink_connected_bots, instant: true }
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: lt, params: [1] }
        labels: { severity: critical }
        annotations: { summary: 'No Telegram bot is connected to the gateway bot-link — out-of-app push and admin sends are down. Check the bot host.' }

      # Positive liveness: a bot is connected but its last successful Bot API call is over 5 minutes
      # old — the getUpdates long-poll returns every ~minute even when idle, so a stale stamp means the
      # bot is wedged (no errors, no traffic). Guarded by "and connected" so a mere disconnect (owned by
      # bot_disconnected) does not double-fire.
      - uid: bot_tg_stale
        title: Telegram bot not reaching the Bot API
        condition: C
        for: 5m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 600, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: (time() - bot_tg_last_ok_unix) and on() (botlink_connected_bots >= 1)
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [300] }
        labels: { severity: critical }
        annotations: { summary: 'A connected Telegram bot has not reached the Bot API in over 5 minutes — the update poll is wedged. Check the bot host and Telegram reachability.' }

      # 429s should be ~never once the bot honours Retry-After; any sustained rate-limiting is a symptom
      # (a send loop, a misbehaving path) worth investigating.
      - uid: bot_tg_rate_limited
        title: Telegram bot rate-limited (429)
        condition: C
        for: 5m
        noDataState: OK
        execErrState: OK
        data:
          - refId: A
            relativeTimeRange: { from: 900, to: 0 }
            datasourceUid: prometheus
            model:
              refId: A
              expr: increase(bot_tg_errors_total{kind="rate_limited"}[15m])
              instant: true
          - refId: C
            datasourceUid: __expr__
            model:
              refId: C
              type: threshold
              expression: A
              conditions:
                - evaluator: { type: gt, params: [0] }
        labels: { severity: warning }
        annotations: { summary: 'The Telegram bot is being rate-limited (HTTP 429). It should honour Retry-After, so sustained 429s point to a send loop or a hot path.' }