terdut-operator/examples/demo/fire-alerts.sh

#!/usr/bin/env bash
# Sends a synthetic Alertmanager v4 webhook payload at the "platform" or
# "payments" demo team's TerdutAlertSource, so terdut-server opens (or
# resolves) an incident exactly the way it would for a real Alertmanager.
#
# The payload shape here is amPayload/amAlert, read straight out of
# terdut-server's own internal/api/alertmanager.go rather than guessed from
# its docs -- version/status/groupKey/groupLabels, and alerts[] carrying
# status/labels/annotations/startsAt/endsAt/generatorURL/fingerprint.
#
# Why this reads the webhook key out of a kubectl Secret instead of using
# the "url" key already in it: that URL is built from spec.networking.hostname
# (TERDUT_PUBLIC_URL), and nothing in this demo stands up real ingress for
# it (01-server.yaml's own comment) -- so it resolves nowhere. The key
# alone, against whatever you've actually port-forwarded BASE_URL to below,
# is the one part of that URL still usable here.
#
# Usage:
#   [CLUSTER=prod-eu] ./fire-alerts.sh <platform|payments> <high-cpu|disk-full|pod-crash|heartbeat> [resolve]
#
# CLUSTER stands in for a Prometheus externalLabel plus `cluster` in
# Alertmanager's group_by (terdut-server's README, "Several clusters, one
# team"): it is put on the alert's labels and on groupLabels, so the incident
# carries it and the web UI shows the cluster chip and the queue's cluster
# filter. It is also part of the group key and the fingerprint, which is what
# keeps the same alert in two clusters from joining one incident. Unset, the
# alert is sent exactly as before.
#
# Prerequisites: kubectl context pointed at the demo namespace, jq, curl,
# and (in another terminal) a running:
#   kubectl port-forward svc/terdut-operator-demo 8080:8080
set -euo pipefail

NAMESPACE="${NAMESPACE:-}"
CLUSTER="${CLUSTER:-}"
BASE_URL="${BASE_URL:-http://localhost:8080}"

usage() {
  cat >&2 <<'EOF'
usage: fire-alerts.sh <platform|payments> <scenario> [resolve]

scenarios:
  high-cpu    warning  -- CPU usage above 90% for 10 minutes
  disk-full   critical -- disk usage above 95%
  pod-crash   error    -- a pod crash-looping
  heartbeat   critical -- the team's dead man's switch heartbeat
              (matches the matcher in 06/07-deadman-*.yaml -- send this
              repeatedly to keep the switch alive, or stop sending it and
              watch terdut-server open an incident on its own once
              `timeout` passes with no heartbeat. "resolve" is not a valid
              third argument for this scenario: a heartbeat is only ever
              firing.)

env vars:
  NAMESPACE  kubectl -n for reading the webhook Secret (required)
  BASE_URL   where the port-forwarded terdut-server is (default http://localhost:8080)
  CLUSTER    optional cluster name, e.g. prod-eu: sent as a `cluster` label and
             group label, so the UI shows where the incident came from
EOF
  exit 1
}

[ $# -ge 2 ] || usage
team="$1" scenario="$2" verb="${3:-fire}"
[ -n "$NAMESPACE" ] || { echo "fire-alerts.sh: set NAMESPACE" >&2; exit 1; }

case "$team" in
  platform|payments) ;;
  *) usage ;;
esac

case "$scenario" in
  high-cpu)  alertname=TerdutDemoHighCPU         severity=warning  summary="CPU usage above 90% for 10 minutes" ;;
  disk-full) alertname=TerdutDemoDiskFull        severity=critical summary="Disk usage above 95% on /data" ;;
  pod-crash) alertname=TerdutDemoPodCrashLooping severity=error    summary="Pod web-7f8b9 is crash-looping (5 restarts in 10m)" ;;
  heartbeat)
    # Must match 06-deadman-platform.yaml / 07-deadman-payments.yaml's own
    # matcher exactly -- that's what makes this a heartbeat rather than a
    # third ordinary alert.
    case "$team" in
      platform) alertname=PlatformWatchdog ;;
      payments) alertname=PaymentsWatchdog ;;
    esac
    severity=critical summary="demo heartbeat"
    [ "$verb" = fire ] || { echo "fire-alerts.sh: heartbeat is only ever fired, never resolved -- just stop sending it" >&2; exit 1; }
    ;;
  *) usage ;;
esac

case "$verb" in
  fire)    status=firing ;;
  resolve) status=resolved ;;
  *) usage ;;
esac

secret_name="terdutalertsource-${team}-terdut-webhook"
key="$(kubectl -n "$NAMESPACE" get secret "$secret_name" -o jsonpath='{.data.key}' | base64 -d)"
[ -n "$key" ] || { echo "fire-alerts.sh: empty key read from Secret $secret_name -- has 08/09-alertsource-*.yaml reconciled yet?" >&2; exit 1; }

# Stable per (team, scenario) so a resolve targets the same alert a fire
# created: terdut-server correlates on (team_id, fingerprint), not on
# anything else in the payload. Real Alertmanager computes this from the
# alert's label set; a fixed string plays the same role here.
fingerprint="demo-${team}-${scenario}${CLUSTER:+-$CLUSTER}"

now="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
if [ "$status" = firing ]; then
  ends_at="0001-01-01T00:00:00Z" # Alertmanager's own "not resolved" zero value
else
  ends_at="$now"
fi

payload="$(jq -n \
  --arg status "$status" \
  --arg groupKey "demo:${team}:${scenario}${CLUSTER:+:$CLUSTER}" \
  --arg cluster "$CLUSTER" \
  --arg alertname "$alertname" \
  --arg team "$team" \
  --arg severity "$severity" \
  --arg summary "$summary" \
  --arg startsAt "$now" \
  --arg endsAt "$ends_at" \
  --arg fingerprint "$fingerprint" \
  '{
    version: "4",
    status: $status,
    groupKey: $groupKey,
    groupLabels: ({ alertname: $alertname, team: $team } + (if $cluster != "" then { cluster: $cluster } else {} end)),
    alerts: [{
      status: $status,
      labels: ({ alertname: $alertname, severity: $severity, team: $team, instance: "demo" } + (if $cluster != "" then { cluster: $cluster } else {} end)),
      annotations: { summary: $summary },
      startsAt: $startsAt,
      endsAt: $endsAt,
      generatorURL: "https://example.com/demo",
      fingerprint: $fingerprint
    }]
  }')"

url="${BASE_URL}/api/integrations/${key}/alertmanager"
echo "POST $url  (team=$team scenario=$scenario status=$status${CLUSTER:+ cluster=$CLUSTER})" >&2
code="$(curl -sS -o /tmp/fire-alerts-response.json -w '%{http_code}' \
  -X POST "$url" -H 'Content-Type: application/json' -d "$payload")"
echo "-> HTTP $code" >&2
cat /tmp/fire-alerts-response.json >&2
echo >&2

if [ "$code" != "200" ]; then
  exit 1
fi