Notice when the Watchdog alert stops arriving

Everything this server does assumes alerts arrive. If Prometheus stops
evaluating, or Alertmanager cannot reach us, nothing arrives — and
silence is indistinguishable from everything being fine. The cluster has
shipped the alert for exactly this case all along: Watchdog is
expr: vector(1), so it fires permanently and is re-sent forever, and it
is worth nothing unless something downstream notices it stop. Nothing
did. It arrived, opened no incident because a repeat_interval re-send is
not a new occurrence, and when the monitoring stack died the sweeper
quietly expired it and paged nobody.

So the handling is inverted for a configurable set of alerts: receiving
one opens no incident, and the absence of one does. TERDUT_DEADMAN_MATCHERS
selects them as label matchers, defaulting to alertname=Watchdog.

The unit of monitoring is the fingerprint rather than the alert name. Two
clusters sending the same Watchdog are two independent switches, so a
healthy one can never mask a dead one. Every matcher must name an
alertname, which keeps the sweeper's candidate query on alerts_name_idx
instead of JSON-extracting labels from every row, and leaves matching
with a single implementation.

A switch is dormant until its first heartbeat: a matcher nothing has ever
sent opens nothing, so a fresh deploy or a restored database does not
page. Resolving the incident by hand sticks, exactly as it does for an
alert-backed one, so a decommissioned source is a one-time page rather
than a nag; the switch re-arms only when the heartbeat comes back, and
dying again is a new incident.

The incident has no member alerts on purpose. Linking the heartbeat would
have the settled-incident cascade close it on the very sweep that opened
it, and there is no alert describing the problem anyway — the problem is
that no alert arrived. What happened is on the timeline instead, and
recovery is the only automatic way out.

One narrow exemption in the ingest guard makes recovery possible at all.
A heartbeat we declared dead is marked resolved, and the one that proves
us wrong carries the unchanged startsAt of an alert that never stopped
firing — so "resolution is terminal within an instance" would discard it
forever and a switch could die exactly once. The exemption is scoped to
resolution_source = 'deadman', which is the only resolution this server
infers from silence on a timeout of its own, so nothing another writer
set can be undone by a stale retry. Matched alerts are also held back
from the generic staleness expiry, which would otherwise resolve a
heartbeat as 'expiry' long before its own tighter deadline.

The timeout points the opposite way to TERDUT_STALE_AFTER: staleness is a
generous grace period around a repeat_interval you do not control, while
this is a deadline you set deliberately and configure the heartbeat's
route to beat. Inheriting a 4h or 12h repeat_interval gives a dead man's
switch with a twelve hour fuse, so the README spells out the route the
heartbeat needs.

internal/api/deadman_test.go

@@ -0,0 +1,468 @@
+package api_test
+
+import (
+	"net/http"
+	"testing"
+	"time"
+
+	"github.com/yeniklas/terdut-server/internal/api"
+)
+
+// ---------------------------------------------------------------------------
+// Harness
+// ---------------------------------------------------------------------------
+
+// watchdogGroupKey is what Alertmanager sends for a Watchdog grouped by
+// alertname, which is how the deployed route is configured.
+const watchdogGroupKey = `{}:{alertname="Watchdog"}`
+
+// deadmanCfg watches Watchdog with a timeout short enough to reason about and
+// long enough that a fresh heartbeat is never accidentally stale.
+func deadmanCfg() api.DeadmanConfig {
+	return api.ParseDeadmanConfig("alertname=Watchdog", time.Hour, "critical")
+}
+
+// deadmanTS is notifyTS with dead man's switch handling on: notifications
+// enabled against a fake ntfy, the admin on call today with a topic.
+func deadmanTS(t *testing.T, cfg api.DeadmanConfig) (*ts, *fakeNtfy) {
+	t.Helper()
+	f := newFakeNtfy(t)
+	s := newDeadmanTS(t, cfg, api.NotifyConfig{
+		BaseURL:   f.URL,
+		PublicURL: "https://terdut.example.com",
+	})
+
+	putOnCall(t, s, 1)
+	setTopic(t, s, 1, "terdut-admin")
+	return s, f
+}
+
+// heartbeat posts one Watchdog webhook. Its startsAt never changes: a dead man's
+// switch alert fires once and is re-sent unchanged forever, which is precisely
+// what makes its absence meaningful.
+func heartbeat(t *testing.T, s *ts, fingerprint string, labels map[string]string) {
+	t.Helper()
+	postWebhook(t, s, []map[string]any{
+		amAlert(fingerprint, "Watchdog", "firing", "2026-05-20T10:00:00Z", zeroTime, labels),
+	}, watchdogGroupKey)
+}
+
+// silence back-dates a heartbeat's received_at, which is the only clock the
+// sweeper reads. There is no fake clock in this package.
+func silence(t *testing.T, s *ts, fingerprint string, ago time.Duration) {
+	t.Helper()
+	s.exec(t, "UPDATE alerts SET received_at = ? WHERE fingerprint = ?",
+		time.Now().Add(-ago).Unix(), fingerprint)
+}
+
+// ageIncidents back-dates every incident. The re-arm rule compares a heartbeat
+// against the last incident raised for its switch, so a test that wants a second
+// episode has to put the first one in the past — there is no fake clock here.
+func ageIncidents(t *testing.T, s *ts, ago time.Duration) {
+	t.Helper()
+	past := time.Now().Add(-ago).Unix()
+	s.exec(t, `UPDATE incidents
+	              SET triggered_at = ?,
+	                  resolved_at  = CASE WHEN resolved_at IS NULL THEN NULL ELSE ? END`,
+		past, past)
+}
+
+// incidentByGroup reads the incident for a group key, resolved ones included.
+func incidentByGroup(t *testing.T, s *ts, groupKey string) (id int64, status, severity string, source *string) {
+	t.Helper()
+	err := s.db.QueryRow(`
+		SELECT id, status, COALESCE(severity, ''), resolution_source
+		FROM   incidents WHERE group_key = ? ORDER BY id DESC LIMIT 1`,
+		groupKey).Scan(&id, &status, &severity, &source)
+	if err != nil {
+		t.Fatalf("read incident for group %s: %v", groupKey, err)
+	}
+	return id, status, severity, source
+}
+
+// ---------------------------------------------------------------------------
+// Receiving a heartbeat
+// ---------------------------------------------------------------------------
+
+// The whole inversion: arrival of a dead man's switch alert is good news, and
+// good news is not an incident.
+func TestDeadman_HeartbeatOpensNoIncident(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+
+	if got := s.countIncidents(t); got != 0 {
+		t.Fatalf("expected a heartbeat to open no incident, got %d", got)
+	}
+	if got := s.countNotifications(t, ""); got != 0 {
+		t.Errorf("expected no notification for a heartbeat, got %d", got)
+	}
+	if status, _, _ := s.alertRow(t, "fp-watchdog"); status != "firing" {
+		t.Errorf("expected the heartbeat to be stored firing, got %q", status)
+	}
+}
+
+// A heartbeat routed into a group alongside real alerts must not join their
+// incident: it is not a symptom of anything.
+func TestDeadman_MixedGroupExcludesHeartbeat(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	postWebhook(t, s, []map[string]any{
+		amAlert("fp-mixed-wd", "Watchdog", "firing", "2026-05-20T10:00:00Z", zeroTime, nil),
+		amAlert("fp-mixed-disk", "DiskFull", "firing", "2026-05-20T10:00:00Z", zeroTime,
+			map[string]string{"severity": "critical"}),
+	}, `{}:{namespace="prod"}`)
+
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected 1 incident for the real alert, got %d", got)
+	}
+
+	var alerts []map[string]any
+	decode(t, s.req(t, http.MethodGet, "/api/incidents/1/alerts", nil), &alerts)
+	if len(alerts) != 1 {
+		t.Fatalf("expected 1 member alert, got %d", len(alerts))
+	}
+	if name := alerts[0]["name"]; name != "DiskFull" {
+		t.Errorf("expected only the real alert linked, got %v", name)
+	}
+}
+
+// A matcher scoped by label only claims the alerts it names, so a heartbeat from
+// somewhere else stays an ordinary alert.
+func TestDeadman_LabelScopedMatcherIgnoresOthers(t *testing.T) {
+	s, _ := deadmanTS(t, api.ParseDeadmanConfig("alertname=Watchdog,cluster=prod", time.Hour, "critical"))
+
+	heartbeat(t, s, "fp-dev", map[string]string{"cluster": "dev"})
+
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected an unmatched Watchdog to behave like any other alert, got %d incidents", got)
+	}
+}
+
+// ---------------------------------------------------------------------------
+// Silence
+// ---------------------------------------------------------------------------
+
+func TestDeadman_SilenceOpensIncident(t *testing.T) {
+	s, f := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 2*time.Hour)
+	sweep(t, s, noArchive)
+
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected silence to open 1 incident, got %d", got)
+	}
+	id, status, severity, _ := incidentByGroup(t, s, "deadman:fp-watchdog")
+	if status != "triggered" {
+		t.Errorf("expected a triggered incident, got %q", status)
+	}
+	if severity != "critical" {
+		t.Errorf("expected the configured severity, got %q", severity)
+	}
+
+	// The alert list must not keep claiming a dead heartbeat is firing.
+	alertStatus, source, _ := s.alertRow(t, "fp-watchdog")
+	if alertStatus != "resolved" || source == nil || *source != "deadman" {
+		t.Errorf("expected the heartbeat resolved as deadman, got %q / %v", alertStatus, source)
+	}
+
+	// Nobody was told anything by an alert here, so the page has to come from
+	// the switch itself.
+	s.sweepNotify(t)
+	msgs := f.messages()
+	if len(msgs) != 1 {
+		t.Fatalf("expected 1 page, got %d", len(msgs))
+	}
+	if msgs[0].Topic != "terdut-admin" {
+		t.Errorf("expected the on-call topic, got %q", msgs[0].Topic)
+	}
+	if msgs[0].Priority != 5 {
+		t.Errorf("expected a critical page to override quiet hours (priority 5), got %d", msgs[0].Priority)
+	}
+
+	// The timeline says why, with the age of the last heartbeat.
+	types := eventTypes(timeline(t, s, int(id)))
+	found := false
+	for _, ty := range types {
+		if ty == "deadman_silent" {
+			found = true
+		}
+	}
+	if !found {
+		t.Errorf("expected a deadman_silent event, got %v", types)
+	}
+}
+
+// The generic staleness sweep must keep its hands off heartbeats: they answer to
+// their own, much tighter, timeout, and an 'expiry' resolution here would be
+// both wrong and unrecoverable.
+func TestDeadman_GenericExpiryLeavesHeartbeatAlone(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 5*time.Minute)
+
+	// staleAfter far tighter than the dead man's switch timeout.
+	sweep(t, s, time.Minute)
+
+	status, source, _ := s.alertRow(t, "fp-watchdog")
+	if status != "firing" || source != nil {
+		t.Errorf("expected a live heartbeat left alone, got %q / %v", status, source)
+	}
+	if got := s.countIncidents(t); got != 0 {
+		t.Errorf("expected no incident for a heartbeat that is still fresh, got %d", got)
+	}
+}
+
+// An explicit resolved from Alertmanager is the sender telling us the heartbeat
+// stopped. There is nothing left to wait out.
+func TestDeadman_AlertmanagerResolvedIsImmediateDeath(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	postWebhook(t, s, []map[string]any{
+		amAlert("fp-watchdog", "Watchdog", "resolved", "2026-05-20T10:00:00Z", zeroTime, nil),
+	}, watchdogGroupKey)
+
+	// No ageing: received_at is seconds old, well inside the timeout.
+	sweep(t, s, noArchive)
+
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected a resolved heartbeat to open an incident at once, got %d", got)
+	}
+	// Alertmanager told the truth first, so its resolution source stands.
+	if _, source, _ := s.alertRow(t, "fp-watchdog"); source == nil || *source != "alertmanager" {
+		t.Errorf("expected the Alertmanager resolution source kept, got %v", source)
+	}
+}
+
+// Each label set is its own switch, so one healthy source cannot mask a dead one.
+func TestDeadman_TracksEachFingerprintSeparately(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-a", map[string]string{"cluster": "a"})
+	heartbeat(t, s, "fp-b", map[string]string{"cluster": "b"})
+	silence(t, s, "fp-b", 2*time.Hour)
+	sweep(t, s, noArchive)
+
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected only the silent switch to page, got %d incidents", got)
+	}
+	if _, status, _, _ := incidentByGroup(t, s, "deadman:fp-b"); status != "triggered" {
+		t.Errorf("expected the incident to belong to the silent switch, got %q", status)
+	}
+	if status, _, _ := s.alertRow(t, "fp-a"); status != "firing" {
+		t.Errorf("expected the live switch untouched, got %q", status)
+	}
+}
+
+// A switch nothing has ever been heard from is dormant. A fresh deploy, a
+// restored database or a typo'd alertname must not page.
+func TestDeadman_UnheardOfSwitchIsDormant(t *testing.T) {
+	s, _ := deadmanTS(t, api.ParseDeadmanConfig("alertname=NeverSent", time.Hour, "critical"))
+
+	sweep(t, s, noArchive)
+
+	if got := s.countIncidents(t); got != 0 {
+		t.Fatalf("expected a switch that never chirped to be dormant, got %d incidents", got)
+	}
+}
+
+// ---------------------------------------------------------------------------
+// Recovery and re-arming
+// ---------------------------------------------------------------------------
+
+// The returning heartbeat carries the unchanged startsAt of an alert that never
+// stopped firing, so this also covers the ingest guard exemption: without it the
+// upsert would discard the payload and the switch could die exactly once.
+func TestDeadman_RecoveryResolvesIncident(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 2*time.Hour)
+	sweep(t, s, noArchive)
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	if status, source, _ := s.alertRow(t, "fp-watchdog"); status != "firing" || source != nil {
+		t.Fatalf("expected the returning heartbeat to be accepted, got %q / %v", status, source)
+	}
+
+	sweep(t, s, noArchive)
+
+	_, status, _, source := incidentByGroup(t, s, "deadman:fp-watchdog")
+	if status != "resolved" {
+		t.Errorf("expected recovery to close the incident, got %q", status)
+	}
+	if source == nil || *source != "recovered" {
+		t.Errorf("expected resolution_source recovered, got %v", source)
+	}
+	if got := s.countNotifications(t, "resolved"); got != 1 {
+		t.Errorf("expected 1 all-clear, got %d", got)
+	}
+}
+
+// Resolving a dead man's switch incident sticks, exactly as it does for an
+// alert-backed one. A source that is gone for good is a one-time page.
+func TestDeadman_ManualResolveSticksWhileSilent(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 2*time.Hour)
+	sweep(t, s, noArchive)
+
+	s.req(t, http.MethodPost, "/api/incidents/1/resolve", nil).Body.Close()
+
+	// Still silent, several sweeps later.
+	sweep(t, s, noArchive)
+	sweep(t, s, noArchive)
+
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected a manually resolved incident to stay closed, got %d", got)
+	}
+}
+
+// ...but the switch re-arms, so a heartbeat that comes back and dies again is a
+// new incident rather than silence forever.
+func TestDeadman_ReArmsAfterHeartbeatReturns(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 2*time.Hour)
+	sweep(t, s, noArchive)
+	s.req(t, http.MethodPost, "/api/incidents/1/resolve", nil).Body.Close()
+
+	// That episode is yesterday's news; the heartbeat now returns after it.
+	ageIncidents(t, s, 10*time.Hour)
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	sweep(t, s, noArchive)
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected the live switch to open nothing, got %d incidents", got)
+	}
+
+	silence(t, s, "fp-watchdog", 2*time.Hour)
+	sweep(t, s, noArchive)
+
+	if got := s.countIncidents(t); got != 2 {
+		t.Fatalf("expected a second death to open a second incident, got %d", got)
+	}
+}
+
+// A dead man's switch incident has no member alerts — linking the heartbeat
+// would have the settled-incident cascade close it on the very sweep that opened
+// it — so the cascade has to leave it alone.
+func TestDeadman_SettledCascadeLeavesIncidentOpen(t *testing.T) {
+	s, _ := deadmanTS(t, deadmanCfg())
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 2*time.Hour)
+	sweep(t, s, noArchive)
+	sweep(t, s, noArchive)
+
+	if _, status, _, _ := incidentByGroup(t, s, "deadman:fp-watchdog"); status != "triggered" {
+		t.Fatalf("expected the incident to stay open until the switch recovers, got %q", status)
+	}
+}
+
+// ---------------------------------------------------------------------------
+// Configuration
+// ---------------------------------------------------------------------------
+
+func TestParseDeadmanConfig(t *testing.T) {
+	tests := []struct {
+		name     string
+		matchers string
+		timeout  time.Duration
+		want     []api.DeadmanMatcher
+		enabled  bool
+	}{
+		{
+			name:     "single alertname",
+			matchers: "alertname=Watchdog",
+			timeout:  time.Hour,
+			want:     []api.DeadmanMatcher{{Name: "Watchdog", Labels: map[string]string{}}},
+			enabled:  true,
+		},
+		{
+			name:     "several matchers with extra labels and whitespace",
+			matchers: " alertname=Watchdog, cluster=prod ; alertname=EdgeHeartbeat ",
+			timeout:  time.Hour,
+			want: []api.DeadmanMatcher{
+				{Name: "Watchdog", Labels: map[string]string{"cluster": "prod"}},
+				{Name: "EdgeHeartbeat", Labels: map[string]string{}},
+			},
+			enabled: true,
+		},
+		{
+			// Mandatory: it is what keeps the sweeper's candidate query on an index.
+			name:     "matcher without alertname is dropped",
+			matchers: "cluster=prod; alertname=Watchdog",
+			timeout:  time.Hour,
+			want:     []api.DeadmanMatcher{{Name: "Watchdog", Labels: map[string]string{}}},
+			enabled:  true,
+		},
+		{
+			name:     "malformed condition drops only its matcher",
+			matchers: "alertname=Watchdog,garbage; alertname=Other",
+			timeout:  time.Hour,
+			want:     []api.DeadmanMatcher{{Name: "Other", Labels: map[string]string{}}},
+			enabled:  true,
+		},
+		{
+			name:     "zero timeout disables",
+			matchers: "alertname=Watchdog",
+			timeout:  0,
+			want:     []api.DeadmanMatcher{{Name: "Watchdog", Labels: map[string]string{}}},
+			enabled:  false,
+		},
+		{
+			name:     "no usable matchers disables",
+			matchers: "",
+			timeout:  time.Hour,
+			want:     nil,
+			enabled:  false,
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			got := api.ParseDeadmanConfig(tc.matchers, tc.timeout, "critical")
+			if len(got.Matchers) != len(tc.want) {
+				t.Fatalf("got %d matchers %v, want %d", len(got.Matchers), got.Matchers, len(tc.want))
+			}
+			for i, w := range tc.want {
+				if got.Matchers[i].Name != w.Name {
+					t.Errorf("matcher %d: name %q, want %q", i, got.Matchers[i].Name, w.Name)
+				}
+				if len(got.Matchers[i].Labels) != len(w.Labels) {
+					t.Errorf("matcher %d: labels %v, want %v", i, got.Matchers[i].Labels, w.Labels)
+					continue
+				}
+				for k, v := range w.Labels {
+					if got.Matchers[i].Labels[k] != v {
+						t.Errorf("matcher %d: label %s=%q, want %q", i, k, got.Matchers[i].Labels[k], v)
+					}
+				}
+			}
+		})
+	}
+}
+
+// A zero config is off, which is what keeps the feature opt-in for anything
+// building a router without one.
+func TestDeadman_DisabledConfigIsInert(t *testing.T) {
+	s, _ := deadmanTS(t, api.DeadmanConfig{})
+
+	heartbeat(t, s, "fp-watchdog", nil)
+	silence(t, s, "fp-watchdog", 48*time.Hour)
+	sweep(t, s, time.Hour)
+
+	// Ordinary alert handling: an incident from the arrival, not the absence.
+	if got := s.countIncidents(t); got != 1 {
+		t.Fatalf("expected plain alert handling with deadman off, got %d incidents", got)
+	}
+	if _, source, _ := s.alertRow(t, "fp-watchdog"); source == nil || *source != "expiry" {
+		t.Errorf("expected the generic sweeper to own the alert, got %v", source)
+	}
+}