Files
terdut-server/internal/api/teams_test.go
T
Niklas Ye 9029d48584
CI / chart (pull_request) Successful in 2s
CI / security (pull_request) Failing after 19s
CI / test (pull_request) Successful in 5m34s
Let an operator authenticate with a seeded key, and reset the schema
- TERDUT_OPERATOR_KEY creates or re-keys the instance-scoped service account
  "terdut-operator" at every start, so terdut-operator needs no bootstrap
  handshake. An instance-scoped account now acts as owner of every team's
  configuration, but is not a member of any team.
- POST /api/teams takes an external_id (instance service accounts only) and
  is idempotent on it, so automation finds its own team again after a crash
  instead of adopting by display name. GET /api/teams?name= is removed.
- Integration and dead man's switch names are unique per team (409). The
  escalation PUT accepts usernames and resolves them itself.
- The 18 migrations are squashed into 001_schema.sql, with no Default team.
  TERDUT_DEADMAN_* and the env seeding of switches are removed: teams carry
  their own. Existing development databases must be recreated.

Security and robustness:
- GET /api/users no longer returns other people's email or ntfy topic to
  non-admins.
- The access log records the route pattern, so integration keys and ack
  tokens in the path are not written to the log. Server errors are logged.
- Rate limits take the client address TERDUT_TRUSTED_PROXIES hops from the
  right of X-Forwarded-For instead of trusting the first, forgeable entry.
- /api/bootstrap runs in a transaction under an advisory lock, so two
  concurrent calls cannot both create an administrator.
- API key last_used_at is written at most every five minutes.

Cleanup: remove GET /api/incidents/{id}/alerts, unused exports, SQLite
remnants in comments and config.

Claude-Session: https://claude.ai/code/session_016mBLURvJoMuUEr9cB2RpUN
2026-10-09 14:56:13 +02:00

516 lines
17 KiB
Go

package api_test
import (
"bytes"
"encoding/json"
"io"
"net/http"
"testing"
)
// The whole point of #4: two teams sharing one server must not see each other's
// work. These tests build two of them and check the boundary from both sides.
type teamFixture struct {
id int64
key string // integration key: how alerts get in
call func(method, path string, body any) *http.Response
}
// newTeam creates a team with its own member, integration key and API key. The
// admin does the creating, as an install's first user would.
func newTeam(t *testing.T, s *ts, name string) teamFixture {
t.Helper()
var team struct {
ID int64 `json:"id"`
}
decode(t, s.req(t, http.MethodPost, "/api/teams", map[string]string{"name": name}), &team)
var integration struct {
Key string `json:"key"`
URL string `json:"url"`
}
decode(t, s.req(t, http.MethodPost, "/api/teams/"+id64(team.ID)+"/integrations",
map[string]string{"name": name + " alertmanager"}), &integration)
if integration.Key == "" {
t.Fatalf("%s: integration key was not returned", name)
}
// A member of this team and no other.
var user struct {
ID int64 `json:"id"`
}
decode(t, s.req(t, http.MethodPost, "/api/users",
map[string]string{"username": name + "-user", "email": name + "@test.com"}), &user)
resp := s.req(t, http.MethodPost, "/api/teams/"+id64(team.ID)+"/members",
map[string]any{"user_id": user.ID, "role": "owner"})
resp.Body.Close()
if resp.StatusCode != http.StatusNoContent {
t.Fatalf("%s: add member: %d", name, resp.StatusCode)
}
var key struct {
Key string `json:"key"`
}
decode(t, s.req(t, http.MethodPost, "/api/users/"+id64(user.ID)+"/api-keys",
map[string]string{"name": "test"}), &key)
return teamFixture{
id: team.ID,
key: integration.Key,
call: func(method, path string, body any) *http.Response {
t.Helper()
var r io.Reader
if body != nil {
data, _ := json.Marshal(body)
r = bytes.NewReader(data)
}
req, _ := http.NewRequest(method, s.URL+path, r)
req.Header.Set("Authorization", "Bearer "+key.Key)
if body != nil {
req.Header.Set("Content-Type", "application/json")
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatalf("%s %s: %v", method, path, err)
}
return resp
},
}
}
// postToIntegration sends one firing alert on a team's integration key, the way
// a real Alertmanager receiver would.
func postToIntegration(t *testing.T, s *ts, key, fingerprint, name string) {
t.Helper()
payload := map[string]any{
"version": "4",
"status": "firing",
"groupKey": "{}:{alertname=\"" + name + "\"}",
"groupLabels": map[string]string{"alertname": name},
"alerts": []map[string]any{
amAlert(fingerprint, name, "firing", "2026-09-20T10:00:00Z", zeroTime, nil),
},
}
data, _ := json.Marshal(payload)
resp, err := http.Post(s.URL+"/api/integrations/"+key+"/alertmanager",
"application/json", bytes.NewReader(data))
if err != nil {
t.Fatalf("post alert: %v", err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
t.Fatalf("post alert: %d", resp.StatusCode)
}
}
func list(t *testing.T, resp *http.Response) []map[string]any {
t.Helper()
var out []map[string]any
decode(t, resp, &out)
return out
}
// An alert posted on one team's key opens an incident in that team and nowhere
// else, and neither team can read the other's queue.
func TestTeams_IncidentsAreScopedToTheReceivingTeam(t *testing.T) {
s := newTS(t)
red := newTeam(t, s, "red")
blue := newTeam(t, s, "blue")
postToIntegration(t, s, red.key, "fp-red", "RedDiskFull")
postToIntegration(t, s, blue.key, "fp-blue", "BlueDiskFull")
redIncidents := list(t, red.call(http.MethodGet, "/api/incidents", nil))
if len(redIncidents) != 1 {
t.Fatalf("red should see exactly its own incident, saw %d", len(redIncidents))
}
if title := redIncidents[0]["title"]; title != "RedDiskFull" {
t.Errorf("red saw %v", title)
}
if teamID := int64(redIncidents[0]["team_id"].(float64)); teamID != red.id {
t.Errorf("red's incident belongs to team %d, want %d", teamID, red.id)
}
blueIncidents := list(t, blue.call(http.MethodGet, "/api/incidents", nil))
if len(blueIncidents) != 1 || blueIncidents[0]["title"] != "BlueDiskFull" {
t.Fatalf("blue should see exactly its own incident, saw %v", blueIncidents)
}
// Reading the other team's incident by id is not found rather than
// forbidden: its existence is the other team's business.
otherID := int64(blueIncidents[0]["id"].(float64))
for _, path := range []string{
"/api/incidents/" + id64(otherID),
"/api/incidents/" + id64(otherID) + "/timeline",
} {
resp := red.call(http.MethodGet, path, nil)
resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Errorf("red reading %s: expected 404, got %d", path, resp.StatusCode)
}
}
// And cannot act on it either.
for _, path := range []string{"/acknowledge", "/resolve", "/archive"} {
resp := red.call(http.MethodPost, "/api/incidents/"+id64(otherID)+path, nil)
resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Errorf("red posting %s: expected 404, got %d", path, resp.StatusCode)
}
}
}
// Alerts, the raw signal record, are scoped the same way.
func TestTeams_AlertsAndStatsAreScoped(t *testing.T) {
s := newTS(t)
red := newTeam(t, s, "red")
blue := newTeam(t, s, "blue")
postToIntegration(t, s, red.key, "fp-red", "RedDiskFull")
postToIntegration(t, s, blue.key, "fp-blue-1", "BlueDiskFull")
postToIntegration(t, s, blue.key, "fp-blue-2", "BlueMemory")
if alerts := list(t, red.call(http.MethodGet, "/api/alerts", nil)); len(alerts) != 1 {
t.Errorf("red should see 1 alert, saw %d", len(alerts))
}
if alerts := list(t, blue.call(http.MethodGet, "/api/alerts", nil)); len(alerts) != 2 {
t.Errorf("blue should see 2 alerts, saw %d", len(alerts))
}
// Statistics count your own work only — otherwise a team's volume, and the
// names of its alerts, leak through the totals.
var stats map[string]any
decode(t, red.call(http.MethodGet, "/api/stats/alerts", nil), &stats)
if total := stats["total"].(float64); total != 1 {
t.Errorf("red's alert stats counted %v alerts, want 1", total)
}
top := list(t, red.call(http.MethodGet, "/api/stats/alerts/top", nil))
for _, row := range top {
if name := row["name"].(string); name != "RedDiskFull" {
t.Errorf("red's top alerts named %q, which is not theirs", name)
}
}
}
// The same fingerprint, the same groupKey and the same date are all legitimate
// in two teams at once: two clusters running the same rules, two rotas.
func TestTeams_SameFingerprintInTwoTeams(t *testing.T) {
s := newTS(t)
red := newTeam(t, s, "red")
blue := newTeam(t, s, "blue")
postToIntegration(t, s, red.key, "fp-shared", "DiskFull")
postToIntegration(t, s, blue.key, "fp-shared", "DiskFull")
for _, team := range []struct {
name string
f teamFixture
}{{"red", red}, {"blue", blue}} {
incidents := list(t, team.f.call(http.MethodGet, "/api/incidents", nil))
if len(incidents) != 1 {
t.Errorf("%s: expected its own incident for the shared fingerprint, saw %d",
team.name, len(incidents))
}
}
// And both rotas can name somebody for the same day.
for _, team := range []struct {
name string
f teamFixture
}{{"red", red}, {"blue", blue}} {
var members []map[string]any
decode(t, team.f.call(http.MethodGet, "/api/teams/"+id64(team.f.id)+"/members", nil), &members)
userID := int64(members[0]["user_id"].(float64))
resp := team.f.call(http.MethodPost, "/api/teams/"+id64(team.f.id)+"/schedule",
map[string]any{"user_id": userID, "dates": []string{"2026-10-01"}})
resp.Body.Close()
if resp.StatusCode != http.StatusCreated {
t.Errorf("%s: taking 2026-10-01 returned %d", team.name, resp.StatusCode)
}
}
}
// An unknown key delivers nothing, and says so rather than accepting silently.
func TestTeams_UnknownIntegrationKeyIsRejected(t *testing.T) {
s := newTS(t)
team := newTeam(t, s, "red")
resp, err := http.Post(s.URL+"/api/integrations/not-a-real-key/alertmanager",
"application/json", bytes.NewReader([]byte(`{"version":"4","status":"firing","alerts":[]}`)))
if err != nil {
t.Fatalf("post: %v", err)
}
resp.Body.Close()
if resp.StatusCode != http.StatusUnauthorized {
t.Errorf("expected 401 for an unknown key, got %d", resp.StatusCode)
}
if incidents := list(t, team.call(http.MethodGet, "/api/incidents", nil)); len(incidents) != 0 {
t.Errorf("a rejected payload opened %d incident(s)", len(incidents))
}
}
// Team configuration is an owner's job; working incidents is a member's.
func TestTeams_MemberCannotConfigureTheTeam(t *testing.T) {
s := newTS(t)
team := newTeam(t, s, "red")
// A plain member of the same team.
var user struct {
ID int64 `json:"id"`
}
decode(t, s.req(t, http.MethodPost, "/api/users",
map[string]string{"username": "plain", "email": "plain@test.com"}), &user)
resp := s.req(t, http.MethodPost, "/api/teams/"+id64(team.id)+"/members",
map[string]any{"user_id": user.ID, "role": "member"})
resp.Body.Close()
var key struct {
Key string `json:"key"`
}
decode(t, s.req(t, http.MethodPost, "/api/users/"+id64(user.ID)+"/api-keys",
map[string]string{"name": "test"}), &key)
call := func(method, path string, body any) *http.Response {
t.Helper()
var r io.Reader
if body != nil {
data, _ := json.Marshal(body)
r = bytes.NewReader(data)
}
req, _ := http.NewRequest(method, s.URL+path, r)
req.Header.Set("Authorization", "Bearer "+key.Key)
if body != nil {
req.Header.Set("Content-Type", "application/json")
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatalf("%s %s: %v", method, path, err)
}
return resp
}
base := "/api/teams/" + id64(team.id)
for _, c := range []struct {
name string
method string
path string
body any
}{
{"mint an integration key", http.MethodPost, base + "/integrations",
map[string]string{"name": "mine"}},
{"take a shift", http.MethodPost, base + "/schedule",
map[string]any{"user_id": user.ID, "dates": []string{"2026-11-01"}}},
{"add a member", http.MethodPost, base + "/members",
map[string]any{"user_id": 1}},
{"delete the team", http.MethodDelete, base, nil},
} {
resp := call(c.method, c.path, c.body)
resp.Body.Close()
if resp.StatusCode != http.StatusForbidden {
t.Errorf("%s: expected 403, got %d", c.name, resp.StatusCode)
}
}
// But they can read what the team is doing.
for _, path := range []string{base + "/members", base + "/integrations", base + "/schedule"} {
resp := call(http.MethodGet, path, nil)
resp.Body.Close()
if resp.StatusCode != http.StatusOK {
t.Errorf("reading %s: expected 200, got %d", path, resp.StatusCode)
}
}
}
// A team's own OIDC group binding follows the same rule as its schedule and
// its integrations: an owner sets it, a member may only read it, an outsider
// learns nothing, and an administrator can still reach it to repair a team
// whose owner has left.
func TestTeamOIDCGroups_OwnerOnlyToEdit(t *testing.T) {
s := newTS(t)
team := newTeam(t, s, "sre") // team.call authenticates as its owner
// A plain member of the same team.
var plain struct {
ID int64 `json:"id"`
}
decode(t, s.req(t, http.MethodPost, "/api/users",
map[string]string{"username": "plain", "email": "plain@test.com"}), &plain)
resp := s.req(t, http.MethodPost, "/api/teams/"+id64(team.id)+"/members",
map[string]any{"user_id": plain.ID, "role": "member"})
resp.Body.Close()
var key struct {
Key string `json:"key"`
}
decode(t, s.req(t, http.MethodPost, "/api/users/"+id64(plain.ID)+"/api-keys",
map[string]string{"name": "test"}), &key)
memberCall := func(method, path string, body any) *http.Response {
t.Helper()
var r io.Reader
if body != nil {
data, _ := json.Marshal(body)
r = bytes.NewReader(data)
}
req, _ := http.NewRequest(method, s.URL+path, r)
req.Header.Set("Authorization", "Bearer "+key.Key)
if body != nil {
req.Header.Set("Content-Type", "application/json")
}
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatalf("%s %s: %v", method, path, err)
}
return resp
}
// A member of a different team altogether.
_, outsiderCall := member(t, s, "outsider")
path := "/api/teams/" + id64(team.id) + "/oidc-groups"
resp = team.call(http.MethodPut, path, map[string]string{"member_group": "sre", "owner_group": "sre-leads"})
resp.Body.Close()
if resp.StatusCode != http.StatusNoContent {
t.Errorf("owner PUT: %d, want 204", resp.StatusCode)
}
var got struct {
MemberGroup string `json:"member_group"`
OwnerGroup string `json:"owner_group"`
}
decode(t, team.call(http.MethodGet, path, nil), &got)
if got.MemberGroup != "sre" || got.OwnerGroup != "sre-leads" {
t.Errorf("owner GET after PUT: %+v", got)
}
resp = memberCall(http.MethodGet, path, nil)
resp.Body.Close()
if resp.StatusCode != http.StatusOK {
t.Errorf("member GET: %d, want 200", resp.StatusCode)
}
resp = memberCall(http.MethodPut, path, map[string]string{"member_group": "anything"})
resp.Body.Close()
if resp.StatusCode != http.StatusForbidden {
t.Errorf("member PUT: %d, want 403", resp.StatusCode)
}
// 404, not 403: whether the team exists is itself something only its
// members should learn.
resp = outsiderCall(http.MethodGet, path, nil)
resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Errorf("outsider GET: %d, want 404", resp.StatusCode)
}
resp = outsiderCall(http.MethodPut, path, map[string]string{"member_group": "anything"})
resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Errorf("outsider PUT: %d, want 404", resp.StatusCode)
}
// An administrator who is not a member may still set it, the same bypass
// that lets one repair a team whose owner has left.
resp = s.req(t, http.MethodPut, path, map[string]string{"member_group": "sre2"})
resp.Body.Close()
if resp.StatusCode != http.StatusNoContent {
t.Errorf("admin PUT: %d, want 204", resp.StatusCode)
}
// An empty string clears a binding, stored as NULL rather than the literal
// empty string, so an empty group claim can never accidentally match it.
resp = team.call(http.MethodPut, path, map[string]string{"member_group": "", "owner_group": ""})
resp.Body.Close()
var cleared struct {
MemberGroup string `json:"member_group"`
OwnerGroup string `json:"owner_group"`
}
decode(t, team.call(http.MethodGet, path, nil), &cleared)
if cleared.MemberGroup != "" || cleared.OwnerGroup != "" {
t.Errorf("cleared: %+v", cleared)
}
}
// A team is not somewhere an outsider can look, whatever they know about it.
func TestTeams_OutsiderSeesNothing(t *testing.T) {
s := newTS(t)
red := newTeam(t, s, "red")
blue := newTeam(t, s, "blue")
base := "/api/teams/" + id64(red.id)
for _, path := range []string{base + "/members", base + "/integrations", base + "/schedule"} {
resp := blue.call(http.MethodGet, path, nil)
resp.Body.Close()
if resp.StatusCode != http.StatusNotFound {
t.Errorf("blue reading %s: expected 404, got %d", path, resp.StatusCode)
}
}
// /api/teams lists your own, never the install's.
teams := list(t, blue.call(http.MethodGet, "/api/teams", nil))
if len(teams) != 1 || teams[0]["name"] != "blue" {
t.Errorf("blue's team list: %v", teams)
}
}
// ---------------------------------------------------------------------------
// GET /api/teams?name= (TEAM-LOOKUP.md)
// ---------------------------------------------------------------------------
// Everybody signed in can list users to name them, but only an admin (or the
// row's owner) sees an email or an ntfy topic, which is a publish secret.
func TestListUsers_RedactsEmailAndTopicForOthers(t *testing.T) {
s := newTS(t)
red := newTeam(t, s, "red")
_ = newTeam(t, s, "blue")
s.exec(t, "UPDATE users SET ntfy_topic = 'secret-topic'")
var asAdmin []map[string]any
decode(t, s.req(t, http.MethodGet, "/api/users", nil), &asAdmin)
for _, u := range asAdmin {
if u["email"] == "" || u["ntfy_topic"] != "secret-topic" {
t.Errorf("admin should see everything, got %v", u)
}
}
asMember := list(t, red.call(http.MethodGet, "/api/users", nil))
if len(asMember) < 3 {
t.Fatalf("expected the whole user list, got %v", asMember)
}
for _, u := range asMember {
own := u["username"] == "red-user"
if own != (u["email"] != "") || own != (u["ntfy_topic"] != nil) {
t.Errorf("only red-user's own row should keep email and topic, got %v", u)
}
}
}
// Names identify integrations and switches within a team.
func TestTeamNames_AreUniquePerTeam(t *testing.T) {
s := newTS(t) // creates one integration named "test" in the default team
dup := s.req(t, http.MethodPost, "/api/teams/"+defaultTeam+"/integrations", map[string]string{"name": "test"})
dup.Body.Close()
if dup.StatusCode != http.StatusConflict {
t.Errorf("duplicate integration name: expected 409, got %d", dup.StatusCode)
}
body := map[string]any{"matcher": "alertname=Watchdog", "timeout_seconds": 60, "severity": "critical"}
first := s.req(t, http.MethodPost, "/api/teams/"+defaultTeam+"/deadman/switches", body)
first.Body.Close()
second := s.req(t, http.MethodPost, "/api/teams/"+defaultTeam+"/deadman/switches", body)
second.Body.Close()
if first.StatusCode != http.StatusCreated || second.StatusCode != http.StatusConflict {
t.Errorf("duplicate switch name: expected 201 then 409, got %d then %d", first.StatusCode, second.StatusCode)
}
// The same name in another team is fine.
other := newTeam(t, s, "elsewhere")
ok := s.req(t, http.MethodPost, "/api/teams/"+id64(other.id)+"/integrations", map[string]string{"name": "test"})
ok.Body.Close()
if ok.StatusCode != http.StatusCreated {
t.Errorf("same name in another team: expected 201, got %d", ok.StatusCode)
}
}