terdut-server/internal/api/router.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. version is reported
// verbatim by GET /api/version, unauthenticated like /healthz: a client
// deciding whether it can talk to this server — terdut-tui, terdut-operator —
// needs to ask before it holds a credential for it, and the version is not a
// secret.
func NewRouter(db *sql.DB, notify NotifyConfig, cfg config.Config, version string) 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.
	trustedProxies.Store(int64(cfg.TrustedProxies))
	loginLimit := newLoginLimiter(db)
	signupLimiter := newLoginLimiter(db)
	oidcLimit := newLoginLimiter(db)

	metrics := newMetricsService(cfg)

	r := chi.NewRouter()
	r.Use(requestLogger)
	r.Use(middleware.Recoverer)
	r.Use(securityHeaders(notify.PublicURL))

	r.Get("/healthz", func(w http.ResponseWriter, r *http.Request) {
		respond(w, http.StatusOK, map[string]string{"status": "ok"})
	})
	r.Get("/api/version", func(w http.ResponseWriter, r *http.Request) {
		respond(w, http.StatusOK, map[string]string{"version": version})
	})

	// 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.
	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))
		// Which kinds of notification channel this server can deliver, so the
		// UI offers only those.
		r.Get("/api/notify/providers", handleListProviders(notify.Providers))

		// 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.Get("/api/users/{id}/channels", handleListChannels(db))
		r.Post("/api/users/{id}/channels", handleCreateChannel(db, notify.Providers))
		r.Patch("/api/users/{id}/channels/{channelID}", handleUpdateChannel(db, notify.Providers))
		r.Delete("/api/users/{id}/channels/{channelID}", handleDeleteChannel(db))
		// Proves the channel works, which is the only part of "notifications are
		// set up" that the person holding the phone can confirm.
		r.Post("/api/users/{id}/channels/{channelID}/test", handleTestChannel(db, notify))
		r.Put("/api/users/{id}/password", handleSetPassword(db))
		// The picture itself is readable by anyone signed in (like the user
		// list), changeable only by its owner or an administrator.
		r.Get("/api/users/{id}/avatar", handleGetAvatar(db))
		r.Put("/api/users/{id}/avatar", handleSetAvatar(db))
		r.Delete("/api/users/{id}/avatar", handleDeleteAvatar(db))
		r.Get("/api/users/{id}/api-keys", handleListAPIKeys(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.
		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, notify.Providers))
			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/clusters", handleListClusters(db))
		r.Get("/api/incidents/{id}", handleGetIncident(db))
		r.Get("/api/incidents/{id}/timeline", handleIncidentTimeline(db))
		r.Get("/api/incidents/{id}/metrics", handleIncidentMetrics(db, metrics))
		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))

		// Service accounts: a scoped, non-human credential for automation
		// (terdut-operator, most likely) that needs to manage the resources
		// below without impersonating a human user. See SERVICE-ACCOUNTS.md.
		r.Get("/api/service-accounts", handleListServiceAccounts(db))
		r.Post("/api/service-accounts", handleCreateServiceAccount(db))
		r.Post("/api/service-accounts/{id}/keys", handleCreateServiceAccountKey(db))
		r.Delete("/api/service-accounts/{id}/keys/{keyID}", handleDeleteServiceAccountKey(db))

		// Operator mode (TERDUT_OPERATOR_MODE) makes every write below refuse a
		// human caller (a session or a user's own API key) while still letting
		// a service account through — see OperatorModeBlock. opMode is a no-op
		// wrapper when the flag is off, so this costs nothing on a server that
		// never sets it.
		opMode := OperatorModeBlock(cfg)

		// Teams. A user sees the teams they belong to; an owner configures one.
		r.Get("/api/teams", handleListTeams(db))
		r.With(opMode).Post("/api/teams", handleCreateTeam(db))
		r.With(opMode).Put("/api/teams/{teamID}", handleRenameTeam(db))
		r.With(opMode).Delete("/api/teams/{teamID}", handleDeleteTeam(db))
		r.Get("/api/teams/{teamID}/members", handleListTeamMembers(db, notify.Providers))
		r.Post("/api/teams/{teamID}/members", handleAddTeamMember(db))
		r.Delete("/api/teams/{teamID}/members/{userID}", handleRemoveTeamMember(db))

		// A team's own OIDC group binding: which provider groups grant member
		// and owner access to it.
		r.Get("/api/teams/{teamID}/oidc-groups", handleGetTeamOIDCGroups(db))
		r.With(opMode).Put("/api/teams/{teamID}/oidc-groups", handleSetTeamOIDCGroups(db))

		// Invite links into this team. Not operator-mode-gated: membership is
		// deliberately never gitops-managed (see terdut-operator's DESIGN.md
		// §4.2), so it stays editable regardless of this flag.
		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, notify.Providers))
		r.With(opMode).Put("/api/teams/{teamID}/escalation", handleSetEscalation(db, notify.Providers))

		// 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.With(opMode).Post("/api/teams/{teamID}/deadman/switches", handleCreateTeamDeadman(db))
		r.With(opMode).Put("/api/teams/{teamID}/deadman/switches/{switchID}", handleUpdateTeamDeadman(db))
		r.With(opMode).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.With(opMode).Post("/api/teams/{teamID}/integrations", handleCreateIntegration(db, notify.PublicURL))
		r.With(opMode).Patch("/api/teams/{teamID}/integrations/{integrationID}", handleRenameIntegration(db))
		r.With(opMode).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))
		r.Get("/api/stats/alerts/heatmap", handleStatsHeatmap(db))
		r.Get("/api/stats/alerts/{name}", handleStatsAlert(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
}