Files
terdut-server/internal/api/router.go
T
Niklas Ye a27ff49171 Sign in through an OpenID Connect provider, and from a terminal
terdut can now sign people in through any OIDC provider (written against
Authentik), and let groups at the provider decide who may sign in, which
teams they belong to and whether they administer the install. Password
login keeps working alongside it; TERDUT_PASSWORD_LOGIN=false turns it off,
and is refused at startup unless SSO is configured. With no TERDUT_OIDC_*
setting nothing changes, so every existing install behaves as before.

Identity is (issuer, subject), never email or username: those are mutable
at the provider and a recycled address must not inherit an account. An
existing user is linked by email only when the provider marks it verified,
or TERDUT_OIDC_TRUST_EMAIL is set, which Authentik needs.

Group grants are marked source='oidc' on team_members and users, and the
sync changes only those rows. Hand-made memberships and administrators
are left alone, and the sync bypasses the last-owner and last-admin guards
because the provider is the source of truth for what it grants. Editing
managed access by hand is refused with 409, since the next sign-in would
undo it. The web UI badges it as SSO and disables the controls.

Groups are read only at sign-in, so an SSO session carries a hard ceiling
(sessions.max_expires_at, 12h by default) that sliding never extends.
There is no refresh token, which means API keys of somebody removed at the
provider stay valid until an administrator disables the user. That is
accepted and documented, not fixed.

A client with no browser, the TUI over SSH, signs in with a device code
run by terdut itself (POST /api/oidc/device and /device/token), so the
terminal never talks to the provider and ends up with the ordinary
terdut_session cookie. Only a browser session can approve a code; an API
key cannot. /device?code= sends a signed-out visitor through sign-in and
back, which is what oidc_logins.next is for.

oauth2 is pinned to v0.36.0: v0.37 needs Go 1.26 and the Dockerfile
builds on 1.25.

Migrations 011 and 012 add tables and defaulted columns only.
2026-09-26 21:37:40 +02:00

214 lines
10 KiB
Go

package api
import (
"database/sql"
"net/http"
"git.ryuvia.com/niklas/terdut-server/internal/config"
"git.ryuvia.com/niklas/terdut-server/internal/oidc"
"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()
oidcLimit := 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.With(passwordLoginOnly(!cfg.DisablePasswordLogin)).
Post("/api/signup", handleSignup(db, signupLimiter, notify.PublicURL))
// How to sign in: what the login form and the TUI offer before anybody types.
r.Get("/api/auth/config", handleAuthConfig(cfg))
// Signing in to the web UI. Login trades a password for a session cookie,
// which AuthMiddleware accepts in place of an API key.
r.With(passwordLoginOnly(!cfg.DisablePasswordLogin)).
Post("/api/login", handleLogin(db, loginLimit, notify.PublicURL))
r.Post("/api/logout", handleLogout(db, notify.PublicURL))
// Single sign-on. Both routes are navigations the browser makes, to and from
// the provider, so they answer with redirects rather than JSON.
if cfg.OIDC.Enabled() {
prov := oidc.New(cfg.OIDC, notify.PublicURL)
r.Get("/api/oidc/login", handleOIDCLogin(db, prov, oidcLimit, notify.PublicURL))
r.Get("/api/oidc/callback", handleOIDCCallback(db, prov, notify.PublicURL))
// Device login, for a client with no browser of its own. Both are
// unauthenticated: the device code in the body is the credential.
r.Post("/api/oidc/device", handleDeviceStart(db, oidcLimit, notify.PublicURL))
r.Post("/api/oidc/device/token", handleDeviceToken(db, cfg.OIDC.SessionMaxAge, 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))
// Approving or refusing a device login is done by somebody signed in
// to a browser, and needs the same SSO configuration the flow does.
if cfg.OIDC.Enabled() {
r.Post("/api/oidc/device/approve", handleDeviceDecision(db, true))
r.Post("/api/oidc/device/deny", handleDeviceDecision(db, false))
}
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.Patch("/api/teams/{teamID}/integrations/{integrationID}", handleRenameIntegration(db))
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
}