f3918b863c
The page was a bare form: it did not say which switches existed or
whether they were alive. It now lists them, each with a Healthy, Dead or
Dormant badge, when its heartbeat was last heard and when it last opened
an incident (linked while that incident is open). A matcher that several
clusters satisfy is broken down per cluster, since a live cluster must
not hide a dead one. The form moved into a "New switch" sheet, and each
row has a Remove with a confirm.
That needed a switch to be a thing, so switches are rows now
(migration 009) with their own name, matcher, timeout and severity,
instead of one string with one team-wide timeout in deadman_configs.
Existing configuration is split into one row per matcher; a team whose
timeout was zero simply has none. The sweeper and the status endpoint
share one death rule (deadmanAlert.dead), so the page cannot disagree
with the pager. Incident group keys are unchanged, so incidents that
are open across the upgrade keep working.
The environment defaults (TERDUT_DEADMAN_*) are seeded into teams once
per install, recorded in settings, so a team that deletes its last
switch does not get it back on the next restart. Installs that already
had per-team rows are marked as seeded by the migration.
Removing a switch stops the watching but leaves an incident it already
opened open until someone resolves it.
API: GET/PUT /api/teams/{id}/deadman are replaced by
GET/POST /deadman/switches and DELETE /deadman/switches/{switchID}.
terdut-tui does not call them, so nothing to mirror there.
186 lines
8.6 KiB
Go
186 lines
8.6 KiB
Go
package api
|
|
|
|
import (
|
|
"database/sql"
|
|
"net/http"
|
|
|
|
"git.ryuvia.com/niklas/terdut-server/internal/config"
|
|
"git.ryuvia.com/niklas/terdut-server/internal/web"
|
|
"github.com/go-chi/chi/v5"
|
|
"github.com/go-chi/chi/v5/middleware"
|
|
)
|
|
|
|
// NewRouter builds the HTTP surface. notify is passed through to the webhook,
|
|
// the only handler that has to decide where a new incident's page goes; a zero
|
|
// notify disables notifications. Dead man's switches are per team and read from
|
|
// the database, so nothing about them is wired in here.
|
|
func NewRouter(db *sql.DB, notify NotifyConfig, cfg config.Config) http.Handler {
|
|
// One limiter each, both process-wide for the life of the router: login
|
|
// counts failed passwords, sign-up counts account creation, and mixing the
|
|
// two would let a burst of sign-ups lock somebody out of logging in.
|
|
loginLimit := newLoginLimiter()
|
|
signupLimiter := newLoginLimiter()
|
|
|
|
r := chi.NewRouter()
|
|
r.Use(middleware.Logger)
|
|
r.Use(middleware.Recoverer)
|
|
|
|
r.Get("/healthz", func(w http.ResponseWriter, r *http.Request) {
|
|
respond(w, http.StatusOK, map[string]string{"status": "ok"})
|
|
})
|
|
|
|
// Unauthenticated: bootstrap, the Alertmanager webhook receiver, and the
|
|
// Acknowledge button in a push notification. The last one is authorised by
|
|
// the scoped token in its path rather than an API key, and has to stay
|
|
// reachable from outside the cluster for the button to work.
|
|
r.Post("/api/bootstrap", handleBootstrap(db))
|
|
r.Post("/api/notify/ack/{token}", handleNotifyAck(db))
|
|
|
|
// Alert ingestion. The key in the path says both that the sender may post
|
|
// and which team the alerts belong to, which is why it needs no session.
|
|
//
|
|
// This is the only way in. The pre-teams /api/alertmanager/webhook, which
|
|
// took no credential at all, was removed in v0.13.0 once the cluster's
|
|
// Alertmanager had moved onto a key; a sender still posting there gets the
|
|
// JSON 404 every unknown /api path gets.
|
|
r.Post("/api/integrations/{key}/alertmanager", handleIntegrationWebhook(db, notify))
|
|
|
|
// Signing up. Both are unauthenticated by necessity: the caller has no
|
|
// account yet. The info endpoint says whether the door is open and whether
|
|
// an invite link is good, so the form can say so before somebody picks a
|
|
// password.
|
|
r.Get("/api/signup", handleSignupInfo(db))
|
|
r.Post("/api/signup", handleSignup(db, signupLimiter, notify.PublicURL))
|
|
|
|
// Signing in to the web UI. Login trades a password for a session cookie,
|
|
// which AuthMiddleware accepts in place of an API key.
|
|
r.Post("/api/login", handleLogin(db, loginLimit, notify.PublicURL))
|
|
r.Post("/api/logout", handleLogout(db, notify.PublicURL))
|
|
|
|
// All other /api routes require a valid API key.
|
|
r.Group(func(r chi.Router) {
|
|
r.Use(AuthMiddleware(db))
|
|
|
|
r.Get("/api/me", handleMe(db))
|
|
r.Put("/api/me/onboarding", handleDismissOnboarding(db))
|
|
// Proves the topic works, which is the only part of "notifications are
|
|
// set up" that the person holding the phone can confirm.
|
|
r.Post("/api/me/notify/test", handleTestNotification(notify, db))
|
|
|
|
// Readable by anyone signed in: the queue's assignment control and the
|
|
// on-call schedule both need to name people.
|
|
r.Get("/api/users", handleListUsers(db))
|
|
|
|
// Your own account, or anybody's if you are an admin. The handlers call
|
|
// requireSelfOrAdmin rather than sitting behind AdminOnly, because
|
|
// which rule applies depends on the {id} in the path.
|
|
r.Get("/api/users/{id}/teams", handleUserTeams(db))
|
|
r.Put("/api/users/{id}/notify", handleSetNotifyTarget(db))
|
|
r.Put("/api/users/{id}/password", handleSetPassword(db))
|
|
r.Post("/api/users/{id}/api-keys", handleCreateAPIKey(db))
|
|
r.Delete("/api/users/{id}/api-keys/{keyID}", handleDeleteAPIKey(db))
|
|
|
|
// Administration: who exists, and who is an administrator. Until #3
|
|
// these were open to any authenticated caller, which meant every user
|
|
// could delete every other one.
|
|
r.Group(func(r chi.Router) {
|
|
r.Use(AdminOnly)
|
|
|
|
r.Post("/api/users", handleCreateUser(db))
|
|
r.Delete("/api/users/{id}", handleDeleteUser(db))
|
|
r.Put("/api/users/{id}/admin", handleSetAdmin(db))
|
|
r.Put("/api/users/{id}/disabled", handleSetUserDisabled(db))
|
|
|
|
// What exists on this server, and how it behaves. /api/teams
|
|
// answers "what am I in"; this one answers "what is there".
|
|
r.Get("/api/admin/teams", handleAdminListTeams(db))
|
|
// One team and who is in it. The member list under
|
|
// /api/teams/{id}/members stays member-only and still 404s
|
|
// an administrator from outside; this is a different
|
|
// question, so it is a different endpoint.
|
|
r.Get("/api/admin/teams/{teamID}", handleAdminGetTeam(db))
|
|
r.Get("/api/admin/settings", handleGetSettings(db, cfg))
|
|
r.Put("/api/admin/settings", handleSetSettings(db))
|
|
})
|
|
|
|
// Alerts are read-only: they are Alertmanager's record, not a work
|
|
// queue. Everything a person does happens on the incident instead.
|
|
r.Get("/api/alerts", handleListAlerts(db))
|
|
r.Get("/api/alerts/{id}", handleGetAlert(db))
|
|
|
|
r.Get("/api/incidents", handleListIncidents(db))
|
|
r.Get("/api/incidents/{id}", handleGetIncident(db))
|
|
r.Get("/api/incidents/{id}/alerts", handleIncidentAlerts(db))
|
|
r.Get("/api/incidents/{id}/timeline", handleIncidentTimeline(db))
|
|
r.Get("/api/incidents/{id}/similar", handleIncidentSimilar(db))
|
|
r.Post("/api/incidents/{id}/acknowledge", handleIncidentAcknowledge(db))
|
|
r.Delete("/api/incidents/{id}/acknowledge", handleIncidentUnacknowledge(db))
|
|
r.Post("/api/incidents/{id}/resolve", handleIncidentResolve(db))
|
|
r.Post("/api/incidents/{id}/assign", handleIncidentAssign(db))
|
|
r.Post("/api/incidents/{id}/snooze", handleIncidentSnooze(db))
|
|
r.Delete("/api/incidents/{id}/snooze", handleIncidentUnsnooze(db))
|
|
r.Post("/api/incidents/{id}/archive", handleIncidentArchive(db))
|
|
r.Delete("/api/incidents/{id}/archive", handleIncidentUnarchive(db))
|
|
r.Post("/api/incidents/{id}/notes", handleCreateNote(db))
|
|
r.Delete("/api/incidents/{id}/notes/{eventID}", handleDeleteNote(db))
|
|
|
|
// Teams. A user sees the teams they belong to; an owner configures one.
|
|
r.Get("/api/teams", handleListTeams(db))
|
|
r.Post("/api/teams", handleCreateTeam(db))
|
|
r.Put("/api/teams/{teamID}", handleRenameTeam(db))
|
|
r.Delete("/api/teams/{teamID}", handleDeleteTeam(db))
|
|
r.Get("/api/teams/{teamID}/members", handleListTeamMembers(db))
|
|
r.Post("/api/teams/{teamID}/members", handleAddTeamMember(db))
|
|
r.Delete("/api/teams/{teamID}/members/{userID}", handleRemoveTeamMember(db))
|
|
|
|
// Invite links into this team.
|
|
r.Get("/api/teams/{teamID}/invites", handleListInvites(db))
|
|
r.Post("/api/teams/{teamID}/invites", handleCreateInvite(db, notify.PublicURL))
|
|
r.Delete("/api/teams/{teamID}/invites/{inviteID}", handleRevokeInvite(db))
|
|
|
|
// A team's escalation ladder: who is paged when nobody answers.
|
|
r.Get("/api/teams/{teamID}/escalation", handleGetEscalation(db))
|
|
r.Put("/api/teams/{teamID}/escalation", handleSetEscalation(db))
|
|
|
|
// A team's own dead man's switches: which of its alerts are heartbeats,
|
|
// and how long a silence has to last before somebody is paged.
|
|
r.Get("/api/teams/{teamID}/deadman/switches", handleListTeamDeadman(db))
|
|
r.Post("/api/teams/{teamID}/deadman/switches", handleCreateTeamDeadman(db))
|
|
r.Delete("/api/teams/{teamID}/deadman/switches/{switchID}", handleDeleteTeamDeadman(db))
|
|
|
|
// Integrations: where a team's alerts come in, and the key that says so.
|
|
r.Get("/api/teams/{teamID}/integrations", handleListIntegrations(db))
|
|
r.Post("/api/teams/{teamID}/integrations", handleCreateIntegration(db, notify.PublicURL))
|
|
r.Delete("/api/teams/{teamID}/integrations/{integrationID}", handleDeleteIntegration(db))
|
|
|
|
// The rota is per team. /api/schedule/current is the exception: it
|
|
// answers across every team the caller is in, which is what somebody on
|
|
// two rotas wants to see.
|
|
r.Get("/api/schedule/current", handleCurrentSchedule(db))
|
|
r.Post("/api/teams/{teamID}/schedule", handleCreateSchedule(db))
|
|
r.Get("/api/teams/{teamID}/schedule", handleListSchedule(db))
|
|
r.Delete("/api/teams/{teamID}/schedule/{id}", handleDeleteSchedule(db))
|
|
|
|
r.Get("/api/stats/incidents", handleStatsIncidents(db))
|
|
r.Get("/api/stats/alerts", handleStatsAlerts(db))
|
|
r.Get("/api/stats/alerts/top", handleStatsTop(db))
|
|
r.Get("/api/stats/alerts/by-hour", handleStatsByHour(db))
|
|
r.Get("/api/stats/alerts/by-day", handleStatsByDay(db))
|
|
})
|
|
|
|
// Anything else under /api is a mistake in a client, and should say so in
|
|
// JSON rather than get the web UI's HTML.
|
|
r.Handle("/api/*", http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
respond(w, http.StatusNotFound, errResp("not found"))
|
|
}))
|
|
|
|
// Everything outside /api is the web UI.
|
|
site, err := web.Handler()
|
|
if err != nil {
|
|
panic(err) // the site is embedded at build time; this cannot fail at runtime
|
|
}
|
|
r.Handle("/*", site)
|
|
|
|
return r
|
|
}
|