a4fbd60441
The core of #4, and what #1 is for: terdut stops being one shared space. A team owns its incidents, alerts, schedule and integrations; a user sees exactly the teams they are in. Everything that existed moves into one Default team and every existing user becomes an owner of it, so the upgrade is a no-op for the people using it. Ingestion is the load-bearing half. An alert arrives on a team's integration key, and the key is both the credential and the routing: it says that the sender may post, and which team the alerts belong to. That also closes the unauthenticated webhook -- the old path stays for one release, deprecated and routed to the oldest team, so an upgrade does not stop delivering while somebody edits the Alertmanager config. Scoping is enforced in as few places as possible, because the failure mode is silent. serveAs loads the caller's memberships once; list queries carry `team_id = ANY(...)`; and every incident route goes through incidentIDParam, which now parses the id AND checks the team in the same call, so a new handler cannot remember the first half and forget the second. Anything in another team is 404, never 403: whether an incident exists is that team's business. Two bugs this found, both of which would have been silent: * upsertAlerts decided "is this a new occurrence" by looking up the fingerprint alone. Across teams that made team B's first alert look like a re-send of team A's, so it opened no incident at all. The lookups are keyed on (team_id, fingerprint) now, as the index is. * Every uniqueness rule was written for one tenant. Two teams watching two clusters legitimately see the same fingerprint, the same groupKey, and want somebody on call on the same day; all three constraints move to include team_id. Roles inside a team are separate from the system administrator flag: an owner configures the team, a member works its incidents, and an admin is NOT implicitly in every team -- administration is about accounts, not about reading other people's incidents. An admin can still repair a team whose owner has left, which is why requireTeamOwner lets them through. A shift can only be given to somebody in the team. Paging a person who cannot open the incident is worse than paging nobody. The UI is updated only as far as keeping it working: it loads the viewer's teams with the session and uses the first one, since nobody has a second yet. "On call now" shows every team the viewer is in, named only when there is more than one, so the common case reads exactly as before. The team switcher, badges and per-team settings pages are the next step. Breaking for API clients: the schedule endpoints moved under the team, and /api/schedule/current returns an array rather than an object or a 404. terdut-tui will need a version for that. Per-team dead-man configuration is deliberately not here. A heartbeat's incident already opens in the team whose key received it, which is the part that matters for isolation; moving the matchers out of env into per-team rows is a change to how deadman.go is configured rather than to who sees what. Claude-Session: https://claude.ai/code/session_01RHPj4ggeFdEjKKfm4SHbD7
725 lines
22 KiB
Go
725 lines
22 KiB
Go
package api_test
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"sync"
|
|
"testing"
|
|
"time"
|
|
|
|
"git.ryuvia.com/niklas/terdut-server/internal/api"
|
|
)
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Fake ntfy
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// pushed is one message the fake ntfy received, in ntfy's JSON publish shape.
|
|
type pushed struct {
|
|
Topic string `json:"topic"`
|
|
Title string `json:"title"`
|
|
Message string `json:"message"`
|
|
Priority int `json:"priority"`
|
|
Tags []string `json:"tags"`
|
|
Click string `json:"click"`
|
|
Actions []struct {
|
|
Action string `json:"action"`
|
|
Label string `json:"label"`
|
|
URL string `json:"url"`
|
|
Method string `json:"method"`
|
|
Clear bool `json:"clear"`
|
|
} `json:"actions"`
|
|
}
|
|
|
|
// fakeNtfy records what the notifier published. status controls the reply, so a
|
|
// test can make delivery fail.
|
|
type fakeNtfy struct {
|
|
*httptest.Server
|
|
mu sync.Mutex
|
|
got []pushed
|
|
status int
|
|
}
|
|
|
|
func newFakeNtfy(t *testing.T) *fakeNtfy {
|
|
t.Helper()
|
|
f := &fakeNtfy{status: http.StatusOK}
|
|
f.Server = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
var msg pushed
|
|
if err := json.NewDecoder(r.Body).Decode(&msg); err != nil {
|
|
http.Error(w, "bad json", http.StatusBadRequest)
|
|
return
|
|
}
|
|
f.mu.Lock()
|
|
f.got = append(f.got, msg)
|
|
status := f.status
|
|
f.mu.Unlock()
|
|
w.WriteHeader(status)
|
|
}))
|
|
t.Cleanup(f.Close)
|
|
return f
|
|
}
|
|
|
|
func (f *fakeNtfy) messages() []pushed {
|
|
f.mu.Lock()
|
|
defer f.mu.Unlock()
|
|
return append([]pushed(nil), f.got...)
|
|
}
|
|
|
|
func (f *fakeNtfy) failWith(status int) {
|
|
f.mu.Lock()
|
|
defer f.mu.Unlock()
|
|
f.status = status
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Harness
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// notifyTS builds a server with notifications enabled, the admin on call today,
|
|
// and a topic on the admin — the setup every delivery test needs.
|
|
func notifyTS(t *testing.T, cfg api.NotifyConfig) (*ts, *fakeNtfy) {
|
|
t.Helper()
|
|
f := newFakeNtfy(t)
|
|
cfg.BaseURL = f.URL
|
|
s := newTS(t, cfg)
|
|
|
|
putOnCall(t, s, 1)
|
|
setTopic(t, s, 1, "terdut-admin")
|
|
return s, f
|
|
}
|
|
|
|
func putOnCall(t *testing.T, s *ts, userID int) {
|
|
t.Helper()
|
|
today := time.Now().UTC().Format("2006-01-02")
|
|
resp := s.req(t, http.MethodPost, "/api/teams/"+defaultTeam+"/schedule",
|
|
map[string]any{"user_id": userID, "dates": []string{today}})
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusCreated {
|
|
t.Fatalf("schedule assignment returned %d", resp.StatusCode)
|
|
}
|
|
}
|
|
|
|
func setTopic(t *testing.T, s *ts, userID int, topic string) {
|
|
t.Helper()
|
|
resp := s.req(t, http.MethodPut,
|
|
fmt.Sprintf("/api/users/%d/notify", userID), map[string]any{"ntfy_topic": topic})
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
t.Fatalf("set notify topic returned %d", resp.StatusCode)
|
|
}
|
|
}
|
|
|
|
func (s *ts) sweepNotify(t *testing.T) {
|
|
t.Helper()
|
|
api.NotifySweep(context.Background(), s.db, s.notify)
|
|
}
|
|
|
|
// countNotifications reports how many outbox rows exist, optionally of one kind.
|
|
func (s *ts) countNotifications(t *testing.T, kind string) int {
|
|
t.Helper()
|
|
var n int
|
|
query := "SELECT COUNT(*) FROM notifications"
|
|
args := []any{}
|
|
if kind != "" {
|
|
query += " WHERE kind = $1"
|
|
args = append(args, kind)
|
|
}
|
|
if err := s.db.QueryRow(query, args...).Scan(&n); err != nil {
|
|
t.Fatalf("count notifications: %v", err)
|
|
}
|
|
return n
|
|
}
|
|
|
|
// fireCritical posts a single critical alert, which opens one incident.
|
|
func fireCritical(t *testing.T, s *ts) {
|
|
t.Helper()
|
|
postWebhook(t, s, []map[string]any{
|
|
amAlert("fp-notify", "DiskFull", "firing", "2026-05-20T10:00:00Z", zeroTime,
|
|
map[string]string{"severity": "critical"}),
|
|
}, "{}:{alertname=\"DiskFull\"}")
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Delivery
|
|
// ---------------------------------------------------------------------------
|
|
|
|
func TestNotify_TriggeredIncidentPagesOnCall(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
|
|
if got := s.countNotifications(t, "triggered"); got != 1 {
|
|
t.Fatalf("expected 1 queued notification, got %d", got)
|
|
}
|
|
s.sweepNotify(t)
|
|
|
|
msgs := f.messages()
|
|
if len(msgs) != 1 {
|
|
t.Fatalf("expected 1 push, got %d", len(msgs))
|
|
}
|
|
m := msgs[0]
|
|
|
|
if m.Topic != "terdut-admin" {
|
|
t.Errorf("expected the on-call user's topic, got %q", m.Topic)
|
|
}
|
|
if m.Priority != 5 {
|
|
t.Errorf("expected max priority for a critical incident, got %d", m.Priority)
|
|
}
|
|
if !strings.Contains(m.Title, "DiskFull") {
|
|
t.Errorf("expected the incident title in %q", m.Title)
|
|
}
|
|
if !strings.Contains(m.Message, "severity critical") {
|
|
t.Errorf("expected the severity in %q", m.Message)
|
|
}
|
|
if m.Click != "https://terdut.example.com/incidents/1" {
|
|
t.Errorf("unexpected click target %q", m.Click)
|
|
}
|
|
if len(m.Actions) != 1 || m.Actions[0].Label != "Acknowledge" {
|
|
t.Fatalf("expected an Acknowledge action, got %+v", m.Actions)
|
|
}
|
|
if m.Actions[0].Method != http.MethodPost {
|
|
t.Errorf("expected the action to POST, got %q", m.Actions[0].Method)
|
|
}
|
|
}
|
|
|
|
// A delivered row must not be delivered again on the next pass.
|
|
func TestNotify_DeliveredOnlyOnce(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
s.sweepNotify(t)
|
|
|
|
if got := len(f.messages()); got != 1 {
|
|
t.Errorf("expected 1 push across two passes, got %d", got)
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Delivery on the timeline
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// notifyEvents picks the notifier's entries out of an incident's timeline.
|
|
// Asserted through the API rather than the table: the timeline is what the
|
|
// clients read, so its shape is the contract worth covering.
|
|
func notifyEvents(t *testing.T, s *ts, id int) []map[string]any {
|
|
t.Helper()
|
|
var out []map[string]any
|
|
for _, e := range timeline(t, s, id) {
|
|
if e["type"] == "notified" || e["type"] == "notify_failed" {
|
|
out = append(out, e)
|
|
}
|
|
}
|
|
return out
|
|
}
|
|
|
|
func TestNotify_DeliveryIsRecordedOnTheTimeline(t *testing.T) {
|
|
s, _ := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
// Queued is not notified: nothing is on the timeline until ntfy accepts it.
|
|
if got := notifyEvents(t, s, 1); len(got) != 0 {
|
|
t.Fatalf("expected no event before delivery, got %v", got)
|
|
}
|
|
|
|
s.sweepNotify(t)
|
|
|
|
events := notifyEvents(t, s, 1)
|
|
if len(events) != 1 {
|
|
t.Fatalf("expected 1 notification event, got %v", events)
|
|
}
|
|
e := events[0]
|
|
if e["type"] != "notified" {
|
|
t.Errorf("expected a notified event, got %v", e["type"])
|
|
}
|
|
if e["detail"] != "triggered" {
|
|
t.Errorf("expected the kind in detail, got %v", e["detail"])
|
|
}
|
|
if e["username"] != "admin" {
|
|
t.Errorf("expected the paged user attached, got %v", e["username"])
|
|
}
|
|
// The topic is a shared secret with ntfy; the timeline is not the place for it.
|
|
for _, v := range e {
|
|
if s, ok := v.(string); ok && strings.Contains(s, "terdut-admin") {
|
|
t.Errorf("expected the topic kept out of the timeline, found it in %v", e)
|
|
}
|
|
}
|
|
}
|
|
|
|
// A redelivery-free pass must not double-log either.
|
|
func TestNotify_TimelineRecordsOneEventPerDelivery(t *testing.T) {
|
|
s, _ := notifyTS(t, api.NotifyConfig{
|
|
PublicURL: "https://terdut.example.com",
|
|
RepeatEvery: 15 * time.Minute,
|
|
})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
s.sweepNotify(t)
|
|
s.ageNotifications(t, 20*time.Minute)
|
|
s.sweepNotify(t)
|
|
|
|
events := notifyEvents(t, s, 1)
|
|
if len(events) != 2 {
|
|
t.Fatalf("expected one event per delivery, got %v", events)
|
|
}
|
|
if events[0]["detail"] != "triggered" || events[1]["detail"] != "reminder" {
|
|
t.Errorf("expected triggered then reminder, got %v and %v",
|
|
events[0]["detail"], events[1]["detail"])
|
|
}
|
|
}
|
|
|
|
func TestNotify_AllClearIsRecordedOnTheTimeline(t *testing.T) {
|
|
s, _ := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
postWebhook(t, s, []map[string]any{
|
|
amAlert("fp-notify", "DiskFull", "resolved", "2026-05-20T10:00:00Z",
|
|
"2026-05-20T11:00:00Z", map[string]string{"severity": "critical"}),
|
|
}, "{}:{alertname=\"DiskFull\"}")
|
|
s.sweepNotify(t)
|
|
|
|
events := notifyEvents(t, s, 1)
|
|
if len(events) != 2 {
|
|
t.Fatalf("expected the all-clear recorded, got %v", events)
|
|
}
|
|
if events[1]["detail"] != "resolved" {
|
|
t.Errorf("expected a resolved event, got %v", events[1]["detail"])
|
|
}
|
|
}
|
|
|
|
// A page to the shared fallback belongs to nobody, and the timeline has to say
|
|
// so rather than attributing it to whoever happens to be on call now.
|
|
func TestNotify_FallbackDeliveryHasNoUser(t *testing.T) {
|
|
f := newFakeNtfy(t)
|
|
s := newTS(t, api.NotifyConfig{
|
|
BaseURL: f.URL,
|
|
FallbackTopic: "terdut-oncall",
|
|
PublicURL: "https://terdut.example.com",
|
|
})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
events := notifyEvents(t, s, 1)
|
|
if len(events) != 1 {
|
|
t.Fatalf("expected 1 notification event, got %v", events)
|
|
}
|
|
if got, ok := events[0]["username"]; ok && got != nil && got != "" {
|
|
t.Errorf("expected no user on a fallback-topic page, got %v", got)
|
|
}
|
|
}
|
|
|
|
// The failure worth seeing: nobody was paged, and the timeline says so instead
|
|
// of looking exactly like a delivery that worked.
|
|
func TestNotify_ExhaustedRetriesAreRecordedOnce(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
f.failWith(http.StatusInternalServerError)
|
|
|
|
fireCritical(t, s)
|
|
// One pass per attempt, each made due by clearing the backoff the last one set.
|
|
for i := 0; i < 10; i++ {
|
|
s.sweepNotify(t)
|
|
s.exec(t, "UPDATE notifications SET send_after = $1 WHERE sent_at IS NULL",
|
|
time.Now().Add(-time.Second).Unix())
|
|
}
|
|
|
|
events := notifyEvents(t, s, 1)
|
|
if len(events) != 1 {
|
|
t.Fatalf("expected exactly one failure event, got %v", events)
|
|
}
|
|
if events[0]["type"] != "notify_failed" {
|
|
t.Errorf("expected notify_failed, got %v", events[0]["type"])
|
|
}
|
|
detail, _ := events[0]["detail"].(string)
|
|
if !strings.HasPrefix(detail, "triggered: ") || !strings.Contains(detail, "500") {
|
|
t.Errorf("expected the kind and the reason in %q", detail)
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Acknowledging from the notification
|
|
// ---------------------------------------------------------------------------
|
|
|
|
func TestNotify_AckButtonAcknowledgesIncident(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
ackURL := f.messages()[0].Actions[0].URL
|
|
// The action URL is built for the public hostname; point it at the test
|
|
// server, which is the same handler.
|
|
path := ackURL[strings.Index(ackURL, "/api/notify/ack/"):]
|
|
|
|
resp, err := http.Post(s.URL+path, "application/json", nil)
|
|
if err != nil {
|
|
t.Fatalf("ack: %v", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
t.Fatalf("expected 200 from the ack button, got %d", resp.StatusCode)
|
|
}
|
|
|
|
inc := getIncident(t, s, 1)
|
|
if inc["status"] != "acknowledged" {
|
|
t.Errorf("expected the incident acknowledged, got %v", inc["status"])
|
|
}
|
|
if inc["acknowledged_by"] != "admin" {
|
|
t.Errorf("expected the ack attributed to the token's user, got %v", inc["acknowledged_by"])
|
|
}
|
|
|
|
// The timeline must record it the same way the authenticated route would.
|
|
events := timeline(t, s, 1)
|
|
if !contains(eventTypes(events), "acknowledged") {
|
|
t.Errorf("expected an acknowledged event, got %v", eventTypes(events))
|
|
}
|
|
for _, e := range events {
|
|
if e["type"] == "acknowledged" && e["username"] != "admin" {
|
|
t.Errorf("expected the acknowledged event attributed to admin, got %v", e["username"])
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestNotify_AckRejectsUnknownToken(t *testing.T) {
|
|
s, _ := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
fireCritical(t, s)
|
|
|
|
resp, err := http.Post(s.URL+"/api/notify/ack/deadbeef", "application/json", nil)
|
|
if err != nil {
|
|
t.Fatalf("ack: %v", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusNotFound {
|
|
t.Errorf("expected 404 for an unknown token, got %d", resp.StatusCode)
|
|
}
|
|
if inc := getIncident(t, s, 1); inc["status"] != "triggered" {
|
|
t.Errorf("expected the incident untouched, got %v", inc["status"])
|
|
}
|
|
}
|
|
|
|
func TestNotify_AckRejectsExpiredToken(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
ackURL := f.messages()[0].Actions[0].URL
|
|
path := ackURL[strings.Index(ackURL, "/api/notify/ack/"):]
|
|
|
|
// Age the token past its TTL. The token's inputs are wall-clock timestamps,
|
|
// so this is the same trick the sweeper tests use.
|
|
s.exec(t, "UPDATE incident_ack_tokens SET expires_at = $1", time.Now().Add(-time.Minute).Unix())
|
|
|
|
resp, err := http.Post(s.URL+path, "application/json", nil)
|
|
if err != nil {
|
|
t.Fatalf("ack: %v", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusNotFound {
|
|
t.Errorf("expected 404 for an expired token, got %d", resp.StatusCode)
|
|
}
|
|
if inc := getIncident(t, s, 1); inc["status"] != "triggered" {
|
|
t.Errorf("expected the incident untouched, got %v", inc["status"])
|
|
}
|
|
}
|
|
|
|
// The sweeper is what stops expired tokens accumulating forever.
|
|
func TestNotify_SweepPurgesExpiredAckTokens(t *testing.T) {
|
|
s, _ := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
s.exec(t, "UPDATE incident_ack_tokens SET expires_at = $1", time.Now().Add(-time.Minute).Unix())
|
|
|
|
api.Sweep(context.Background(), s.db, 168*time.Hour, 6*time.Hour, s.deadman, s.notify)
|
|
|
|
var n int
|
|
if err := s.db.QueryRow("SELECT COUNT(*) FROM incident_ack_tokens").Scan(&n); err != nil {
|
|
t.Fatalf("count tokens: %v", err)
|
|
}
|
|
if n != 0 {
|
|
t.Errorf("expected expired tokens purged, %d left", n)
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Reminders
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// ageNotifications backdates every sent notification so the next pass sees the
|
|
// reminder as due.
|
|
func (s *ts) ageNotifications(t *testing.T, by time.Duration) {
|
|
t.Helper()
|
|
s.exec(t, "UPDATE notifications SET created_at = $1 WHERE sent_at IS NOT NULL",
|
|
time.Now().Add(-by).Unix())
|
|
}
|
|
|
|
func TestNotify_UnacknowledgedIncidentIsRenotified(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{
|
|
PublicURL: "https://terdut.example.com",
|
|
RepeatEvery: 15 * time.Minute,
|
|
})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
s.ageNotifications(t, 20*time.Minute)
|
|
s.sweepNotify(t)
|
|
|
|
msgs := f.messages()
|
|
if len(msgs) != 2 {
|
|
t.Fatalf("expected a reminder push, got %d message(s)", len(msgs))
|
|
}
|
|
if !strings.Contains(msgs[1].Title, "Still unacknowledged") {
|
|
t.Errorf("expected the reminder to say so, got %q", msgs[1].Title)
|
|
}
|
|
if msgs[1].Topic != "terdut-admin" {
|
|
t.Errorf("expected the reminder on the same topic, got %q", msgs[1].Topic)
|
|
}
|
|
// Each page carries its own credential.
|
|
if len(msgs[1].Actions) != 1 || msgs[1].Actions[0].URL == msgs[0].Actions[0].URL {
|
|
t.Errorf("expected the reminder to carry a fresh ack token")
|
|
}
|
|
}
|
|
|
|
func TestNotify_AcknowledgedIncidentStopsReminders(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{
|
|
PublicURL: "https://terdut.example.com",
|
|
RepeatEvery: 15 * time.Minute,
|
|
})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
resp := s.req(t, http.MethodPost, "/api/incidents/1/acknowledge", nil)
|
|
resp.Body.Close()
|
|
|
|
s.ageNotifications(t, 20*time.Minute)
|
|
s.sweepNotify(t)
|
|
|
|
if got := len(f.messages()); got != 1 {
|
|
t.Errorf("expected no reminder once acknowledged, got %d message(s)", got)
|
|
}
|
|
}
|
|
|
|
// Snooze is the deliberate "not now", and it is what mutes the pager.
|
|
func TestNotify_SnoozedIncidentStopsReminders(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{
|
|
PublicURL: "https://terdut.example.com",
|
|
RepeatEvery: 15 * time.Minute,
|
|
})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
resp := s.req(t, http.MethodPost, "/api/incidents/1/snooze", map[string]any{"duration": "1h"})
|
|
if resp.StatusCode != http.StatusOK {
|
|
t.Fatalf("snooze returned %d", resp.StatusCode)
|
|
}
|
|
resp.Body.Close()
|
|
|
|
s.ageNotifications(t, 20*time.Minute)
|
|
s.sweepNotify(t)
|
|
|
|
if got := len(f.messages()); got != 1 {
|
|
t.Errorf("expected no reminder while snoozed, got %d message(s)", got)
|
|
}
|
|
}
|
|
|
|
func TestNotify_ZeroRepeatDisablesReminders(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
s.ageNotifications(t, 24*time.Hour)
|
|
s.sweepNotify(t)
|
|
|
|
if got := len(f.messages()); got != 1 {
|
|
t.Errorf("expected reminders off, got %d message(s)", got)
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Resolution
|
|
// ---------------------------------------------------------------------------
|
|
|
|
func TestNotify_ResolvedIncidentSendsAllClear(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
postWebhook(t, s, []map[string]any{
|
|
amAlert("fp-notify", "DiskFull", "resolved", "2026-05-20T10:00:00Z",
|
|
"2026-05-20T11:00:00Z", map[string]string{"severity": "critical"}),
|
|
}, "{}:{alertname=\"DiskFull\"}")
|
|
s.sweepNotify(t)
|
|
|
|
msgs := f.messages()
|
|
if len(msgs) != 2 {
|
|
t.Fatalf("expected an all-clear push, got %d message(s)", len(msgs))
|
|
}
|
|
if !strings.HasPrefix(msgs[1].Title, "Resolved:") {
|
|
t.Errorf("expected a resolved title, got %q", msgs[1].Title)
|
|
}
|
|
if msgs[1].Priority != 2 {
|
|
t.Errorf("expected the all-clear at low priority, got %d", msgs[1].Priority)
|
|
}
|
|
// Nothing to acknowledge on a closed incident.
|
|
if len(msgs[1].Actions) != 0 {
|
|
t.Errorf("expected no actions on the all-clear, got %+v", msgs[1].Actions)
|
|
}
|
|
}
|
|
|
|
// Closing an incident by hand sends nothing: the person who did it knows.
|
|
func TestNotify_ManualResolveSendsNothing(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
resp := s.req(t, http.MethodPost, "/api/incidents/1/resolve", nil)
|
|
resp.Body.Close()
|
|
s.sweepNotify(t)
|
|
|
|
if got := len(f.messages()); got != 1 {
|
|
t.Errorf("expected no push for a manual resolve, got %d message(s)", got)
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Routing and configuration
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// With nobody on call the page goes to the shared fallback, and carries no
|
|
// Acknowledge button — there is no user to attribute the acknowledgement to.
|
|
func TestNotify_FallbackTopicHasNoAckButton(t *testing.T) {
|
|
f := newFakeNtfy(t)
|
|
s := newTS(t, api.NotifyConfig{
|
|
BaseURL: f.URL,
|
|
FallbackTopic: "terdut-oncall",
|
|
PublicURL: "https://terdut.example.com",
|
|
})
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
msgs := f.messages()
|
|
if len(msgs) != 1 {
|
|
t.Fatalf("expected 1 push, got %d", len(msgs))
|
|
}
|
|
if msgs[0].Topic != "terdut-oncall" {
|
|
t.Errorf("expected the fallback topic, got %q", msgs[0].Topic)
|
|
}
|
|
if len(msgs[0].Actions) != 0 {
|
|
t.Errorf("expected no ack button on a shared topic, got %+v", msgs[0].Actions)
|
|
}
|
|
}
|
|
|
|
// Nobody on call and no fallback means there is nowhere to send: queueing would
|
|
// only pile up rows that can never be delivered.
|
|
func TestNotify_NoTargetQueuesNothing(t *testing.T) {
|
|
f := newFakeNtfy(t)
|
|
s := newTS(t, api.NotifyConfig{BaseURL: f.URL})
|
|
|
|
fireCritical(t, s)
|
|
|
|
if got := s.countNotifications(t, ""); got != 0 {
|
|
t.Errorf("expected nothing queued without a target, got %d", got)
|
|
}
|
|
s.sweepNotify(t)
|
|
if got := len(f.messages()); got != 0 {
|
|
t.Errorf("expected no push, got %d", got)
|
|
}
|
|
}
|
|
|
|
// The zero NotifyConfig is what every pre-existing test runs under.
|
|
func TestNotify_DisabledQueuesNothing(t *testing.T) {
|
|
s := newTS(t)
|
|
putOnCall(t, s, 1)
|
|
setTopic(t, s, 1, "terdut-admin")
|
|
|
|
fireCritical(t, s)
|
|
|
|
if got := s.countNotifications(t, ""); got != 0 {
|
|
t.Errorf("expected nothing queued with notifications off, got %d", got)
|
|
}
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Retries
|
|
// ---------------------------------------------------------------------------
|
|
|
|
func TestNotify_FailedDeliveryRetriesWithBackoff(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{PublicURL: "https://terdut.example.com"})
|
|
f.failWith(http.StatusInternalServerError)
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
|
|
var attempts int
|
|
var sentAt *int64
|
|
var sendAfter int64
|
|
var lastError *string
|
|
if err := s.db.QueryRow(
|
|
"SELECT attempts, sent_at, send_after, last_error FROM notifications WHERE id = 1").
|
|
Scan(&attempts, &sentAt, &sendAfter, &lastError); err != nil {
|
|
t.Fatalf("read notification: %v", err)
|
|
}
|
|
if attempts != 1 {
|
|
t.Errorf("expected 1 attempt recorded, got %d", attempts)
|
|
}
|
|
if sentAt != nil {
|
|
t.Errorf("expected the row unsent, got sent_at %v", *sentAt)
|
|
}
|
|
if sendAfter <= time.Now().Unix() {
|
|
t.Errorf("expected the retry pushed into the future, got %d", sendAfter)
|
|
}
|
|
if lastError == nil || !strings.Contains(*lastError, "500") {
|
|
t.Errorf("expected the failure recorded, got %v", lastError)
|
|
}
|
|
|
|
// Backing off means the next pass leaves it alone until it is due.
|
|
s.sweepNotify(t)
|
|
if got := len(f.messages()); got != 1 {
|
|
t.Errorf("expected no immediate retry, got %d attempt(s)", got)
|
|
}
|
|
|
|
// Once due and once ntfy recovers, it goes out.
|
|
f.failWith(http.StatusOK)
|
|
s.exec(t, "UPDATE notifications SET send_after = $1 WHERE id = 1", time.Now().Add(-time.Second).Unix())
|
|
s.sweepNotify(t)
|
|
|
|
if err := s.db.QueryRow("SELECT sent_at FROM notifications WHERE id = 1").Scan(&sentAt); err != nil {
|
|
t.Fatalf("read notification: %v", err)
|
|
}
|
|
if sentAt == nil {
|
|
t.Error("expected the retry to succeed once ntfy recovered")
|
|
}
|
|
}
|
|
|
|
// An ntfy outage must not produce a reminder backlog that all lands at once
|
|
// when it comes back: the previous page has to have been sent first.
|
|
func TestNotify_UnsentNotificationBlocksReminders(t *testing.T) {
|
|
s, f := notifyTS(t, api.NotifyConfig{
|
|
PublicURL: "https://terdut.example.com",
|
|
RepeatEvery: 15 * time.Minute,
|
|
})
|
|
f.failWith(http.StatusInternalServerError)
|
|
|
|
fireCritical(t, s)
|
|
s.sweepNotify(t)
|
|
s.exec(t, "UPDATE notifications SET created_at = $1", time.Now().Add(-time.Hour).Unix())
|
|
s.sweepNotify(t)
|
|
|
|
if got := s.countNotifications(t, "reminder"); got != 0 {
|
|
t.Errorf("expected no reminders queued behind an undelivered page, got %d", got)
|
|
}
|
|
}
|