Add outbound heartbeat monitoring (#1729)

* feat: add outbound heartbeat monitoring to external endpoints

Allow Beszel hub to periodically ping an external monitoring service
(e.g. BetterStack, Uptime Kuma, Healthchecks.io) with system status
summaries, enabling monitoring without exposing Beszel to the internet.

Configuration via environment variables:
- BESZEL_HUB_HEARTBEAT_URL: endpoint to ping (required to enable)
- BESZEL_HUB_HEARTBEAT_INTERVAL: seconds between pings (default: 60)
- BESZEL_HUB_HEARTBEAT_METHOD: HTTP method - POST/GET/HEAD (default: POST)

internal/hub/heartbeat/heartbeat.go

@@ -0,0 +1,280 @@
+// Package heartbeat sends periodic outbound pings to an external monitoring
+// endpoint (e.g. BetterStack, Uptime Kuma, Healthchecks.io) so operators can
+// monitor Beszel without exposing it to the internet.
+package heartbeat
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/henrygd/beszel"
+	"github.com/pocketbase/pocketbase/core"
+)
+
+// Default values for heartbeat configuration.
+const (
+	defaultInterval = 60 // seconds
+	httpTimeout     = 10 * time.Second
+)
+
+// Payload is the JSON body sent with each heartbeat request.
+type Payload struct {
+	// Status is "ok" when all non-paused systems are up, "warn" when alerts
+	// are triggered but no systems are down, and "error" when any system is down.
+	Status    string          `json:"status"`
+	Timestamp string          `json:"timestamp"`
+	Msg       string          `json:"msg"`
+	Systems   SystemsSummary  `json:"systems"`
+	Down      []SystemInfo    `json:"down_systems,omitempty"`
+	Alerts    []AlertInfo     `json:"triggered_alerts,omitempty"`
+	Version   string          `json:"beszel_version"`
+}
+
+// SystemsSummary contains counts of systems by status.
+type SystemsSummary struct {
+	Total   int `json:"total"`
+	Up      int `json:"up"`
+	Down    int `json:"down"`
+	Paused  int `json:"paused"`
+	Pending int `json:"pending"`
+}
+
+// SystemInfo identifies a system that is currently down.
+type SystemInfo struct {
+	ID   string `json:"id" db:"id"`
+	Name string `json:"name" db:"name"`
+	Host string `json:"host" db:"host"`
+}
+
+// AlertInfo describes a currently triggered alert.
+type AlertInfo struct {
+	SystemID   string  `json:"system_id"`
+	SystemName string  `json:"system_name"`
+	AlertName  string  `json:"alert_name"`
+	Threshold  float64 `json:"threshold"`
+}
+
+// Config holds heartbeat settings read from environment variables.
+type Config struct {
+	URL      string // endpoint to ping
+	Interval int    // seconds between pings
+	Method   string // HTTP method (GET or POST, default POST)
+}
+
+// Heartbeat manages the periodic outbound health check.
+type Heartbeat struct {
+	app    core.App
+	config Config
+	client *http.Client
+}
+
+// New creates a Heartbeat if configuration is present.
+// Returns nil if HEARTBEAT_URL is not set (feature disabled).
+func New(app core.App, getEnv func(string) (string, bool)) *Heartbeat {
+	url, ok := getEnv("HEARTBEAT_URL")
+	if !ok || url == "" {
+		return nil
+	}
+
+	interval := defaultInterval
+	if v, ok := getEnv("HEARTBEAT_INTERVAL"); ok {
+		if parsed, err := strconv.Atoi(v); err == nil && parsed > 0 {
+			interval = parsed
+		}
+	}
+
+	method := "POST"
+	if v, ok := getEnv("HEARTBEAT_METHOD"); ok {
+		v = strings.ToUpper(strings.TrimSpace(v))
+		if v == "GET" || v == "HEAD" {
+			method = v
+		}
+	}
+
+	return &Heartbeat{
+		app: app,
+		config: Config{
+			URL:      url,
+			Interval: interval,
+			Method:   method,
+		},
+		client: &http.Client{Timeout: httpTimeout},
+	}
+}
+
+// Start begins the heartbeat loop. It blocks and should be called in a goroutine.
+// The loop runs until the provided stop channel is closed.
+func (hb *Heartbeat) Start(stop <-chan struct{}) {
+	hb.app.Logger().Info("Heartbeat enabled",
+		"url", hb.config.URL,
+		"interval", fmt.Sprintf("%ds", hb.config.Interval),
+		"method", hb.config.Method,
+	)
+
+	// Send an initial heartbeat immediately on startup.
+	hb.send()
+
+	ticker := time.NewTicker(time.Duration(hb.config.Interval) * time.Second)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-stop:
+			return
+		case <-ticker.C:
+			hb.send()
+		}
+	}
+}
+
+// Send performs a single heartbeat ping. Exposed for the test-heartbeat API endpoint.
+func (hb *Heartbeat) Send() error {
+	return hb.send()
+}
+
+// GetConfig returns the current heartbeat configuration.
+func (hb *Heartbeat) GetConfig() Config {
+	return hb.config
+}
+
+func (hb *Heartbeat) send() error {
+	payload, err := hb.buildPayload()
+	if err != nil {
+		hb.app.Logger().Error("Heartbeat: failed to build payload", "err", err)
+		return err
+	}
+
+	var req *http.Request
+
+	if hb.config.Method == "GET" || hb.config.Method == "HEAD" {
+		req, err = http.NewRequest(hb.config.Method, hb.config.URL, nil)
+	} else {
+		body, jsonErr := json.Marshal(payload)
+		if jsonErr != nil {
+			hb.app.Logger().Error("Heartbeat: failed to marshal payload", "err", jsonErr)
+			return jsonErr
+		}
+		req, err = http.NewRequest("POST", hb.config.URL, bytes.NewReader(body))
+		if err == nil {
+			req.Header.Set("Content-Type", "application/json")
+		}
+	}
+
+	if err != nil {
+		hb.app.Logger().Error("Heartbeat: failed to create request", "err", err)
+		return err
+	}
+
+	req.Header.Set("User-Agent", "Beszel-Heartbeat")
+
+	resp, err := hb.client.Do(req)
+	if err != nil {
+		hb.app.Logger().Error("Heartbeat: request failed", "url", hb.config.URL, "err", err)
+		return err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode >= 400 {
+		hb.app.Logger().Warn("Heartbeat: non-success response",
+			"url", hb.config.URL,
+			"status", resp.StatusCode,
+		)
+		return fmt.Errorf("heartbeat endpoint returned status %d", resp.StatusCode)
+	}
+
+	return nil
+}
+
+func (hb *Heartbeat) buildPayload() (*Payload, error) {
+	db := hb.app.DB()
+
+	// Count systems by status.
+	var systemCounts []struct {
+		Status string `db:"status"`
+		Count  int    `db:"cnt"`
+	}
+	err := db.NewQuery("SELECT status, COUNT(*) as cnt FROM systems GROUP BY status").All(&systemCounts)
+	if err != nil {
+		return nil, fmt.Errorf("query system counts: %w", err)
+	}
+
+	summary := SystemsSummary{}
+	for _, sc := range systemCounts {
+		switch sc.Status {
+		case "up":
+			summary.Up = sc.Count
+		case "down":
+			summary.Down = sc.Count
+		case "paused":
+			summary.Paused = sc.Count
+		case "pending":
+			summary.Pending = sc.Count
+		}
+		summary.Total += sc.Count
+	}
+
+	// Get names of down systems.
+	var downSystems []SystemInfo
+	err = db.NewQuery("SELECT id, name, host FROM systems WHERE status = 'down'").All(&downSystems)
+	if err != nil {
+		return nil, fmt.Errorf("query down systems: %w", err)
+	}
+
+	// Get triggered alerts with system names.
+	var triggeredAlerts []struct {
+		SystemID   string  `db:"system"`
+		SystemName string  `db:"system_name"`
+		AlertName  string  `db:"name"`
+		Value      float64 `db:"value"`
+	}
+	err = db.NewQuery(`
+		SELECT a.system, s.name as system_name, a.name, a.value
+		FROM alerts a
+		JOIN systems s ON a.system = s.id
+		WHERE a.triggered = true
+	`).All(&triggeredAlerts)
+	if err != nil {
+		// Non-fatal: alerts info is supplementary.
+		triggeredAlerts = nil
+	}
+
+	alerts := make([]AlertInfo, 0, len(triggeredAlerts))
+	for _, ta := range triggeredAlerts {
+		alerts = append(alerts, AlertInfo{
+			SystemID:   ta.SystemID,
+			SystemName: ta.SystemName,
+			AlertName:  ta.AlertName,
+			Threshold:  ta.Value,
+		})
+	}
+
+	// Determine overall status.
+	status := "ok"
+	msg := "All systems operational"
+	if summary.Down > 0 {
+		status = "error"
+		names := make([]string, len(downSystems))
+		for i, ds := range downSystems {
+			names[i] = ds.Name
+		}
+		msg = fmt.Sprintf("%d system(s) down: %s", summary.Down, strings.Join(names, ", "))
+	} else if len(alerts) > 0 {
+		status = "warn"
+		msg = fmt.Sprintf("%d alert(s) triggered", len(alerts))
+	}
+
+	return &Payload{
+		Status:    status,
+		Timestamp: time.Now().UTC().Format(time.RFC3339),
+		Msg:       msg,
+		Systems:   summary,
+		Down:      downSystems,
+		Alerts:    alerts,
+		Version:   beszel.Version,
+	}, nil
+}

internal/hub/hub.go

@@ -15,6 +15,7 @@ import (
 	"github.com/henrygd/beszel"
 	"github.com/henrygd/beszel/internal/alerts"
 	"github.com/henrygd/beszel/internal/hub/config"
+	"github.com/henrygd/beszel/internal/hub/heartbeat"
 	"github.com/henrygd/beszel/internal/hub/systems"
 	"github.com/henrygd/beszel/internal/records"
 	"github.com/henrygd/beszel/internal/users"
@@ -33,6 +34,8 @@ type Hub struct {
 	um            *users.UserManager
 	rm            *records.RecordManager
 	sm            *systems.SystemManager
+	hb            *heartbeat.Heartbeat
+	hbStop        chan struct{}
 	pubKey        string
 	signer        ssh.Signer
 	appURL        string
@@ -48,6 +51,10 @@ func NewHub(app core.App) *Hub {
 	hub.rm = records.NewRecordManager(hub)
 	hub.sm = systems.NewSystemManager(hub)
 	hub.appURL, _ = GetEnv("APP_URL")
+	hub.hb = heartbeat.New(app, GetEnv)
+	if hub.hb != nil {
+		hub.hbStop = make(chan struct{})
+	}
 	return hub
 }
 
@@ -88,6 +95,10 @@ func (h *Hub) StartHub() error {
 		if err := h.sm.Initialize(); err != nil {
 			return err
 		}
+		// start heartbeat if configured
+		if h.hb != nil {
+			go h.hb.Start(h.hbStop)
+		}
 		return e.Next()
 	})
 
@@ -287,6 +298,9 @@ func (h *Hub) registerApiRoutes(se *core.ServeEvent) error {
 	})
 	// send test notification
 	apiAuth.POST("/test-notification", h.SendTestNotification)
+	// heartbeat status and test
+	apiAuth.GET("/heartbeat-status", h.getHeartbeatStatus)
+	apiAuth.POST("/test-heartbeat", h.testHeartbeat)
 	// get config.yml content
 	apiAuth.GET("/config-yaml", config.GetYamlConfig)
 	// handle agent websocket connection
@@ -403,6 +417,36 @@ func (h *Hub) getUniversalToken(e *core.RequestEvent) error {
 	return e.JSON(http.StatusOK, response)
 }
 
+// getHeartbeatStatus returns current heartbeat configuration and whether it's enabled
+func (h *Hub) getHeartbeatStatus(e *core.RequestEvent) error {
+	if h.hb == nil {
+		return e.JSON(http.StatusOK, map[string]any{
+			"enabled": false,
+			"msg":     "Set BESZEL_HUB_HEARTBEAT_URL to enable outbound heartbeat monitoring",
+		})
+	}
+	cfg := h.hb.GetConfig()
+	return e.JSON(http.StatusOK, map[string]any{
+		"enabled":  true,
+		"url":      cfg.URL,
+		"interval": cfg.Interval,
+		"method":   cfg.Method,
+	})
+}
+
+// testHeartbeat triggers a single heartbeat ping and returns the result
+func (h *Hub) testHeartbeat(e *core.RequestEvent) error {
+	if h.hb == nil {
+		return e.JSON(http.StatusOK, map[string]any{
+			"err": "Heartbeat not configured. Set BESZEL_HUB_HEARTBEAT_URL environment variable.",
+		})
+	}
+	if err := h.hb.Send(); err != nil {
+		return e.JSON(http.StatusOK, map[string]any{"err": err.Error()})
+	}
+	return e.JSON(http.StatusOK, map[string]any{"err": false})
+}
+
 // containerRequestHandler handles both container logs and info requests
 func (h *Hub) containerRequestHandler(e *core.RequestEvent, fetchFunc func(*systems.System, string) (string, error), responseKey string) error {
 	systemID := e.Request.URL.Query().Get("system")

internal/site/src/components/routes/settings/heartbeat.tsx

@@ -0,0 +1,215 @@
+import { t } from "@lingui/core/macro"
+import { Trans } from "@lingui/react/macro"
+import { redirectPage } from "@nanostores/router"
+import clsx from "clsx"
+import { LoaderCircleIcon, SendIcon } from "lucide-react"
+import { useEffect, useState } from "react"
+import { $router } from "@/components/router"
+import { Badge } from "@/components/ui/badge"
+import { Button } from "@/components/ui/button"
+import { Separator } from "@/components/ui/separator"
+import { toast } from "@/components/ui/use-toast"
+import { isAdmin, pb } from "@/lib/api"
+
+interface HeartbeatStatus {
+	enabled: boolean
+	url?: string
+	interval?: number
+	method?: string
+	msg?: string
+}
+
+export default function HeartbeatSettings() {
+	const [status, setStatus] = useState<HeartbeatStatus | null>(null)
+	const [isLoading, setIsLoading] = useState(true)
+	const [isTesting, setIsTesting] = useState(false)
+
+	if (!isAdmin()) {
+		redirectPage($router, "settings", { name: "general" })
+	}
+
+	useEffect(() => {
+		fetchStatus()
+	}, [])
+
+	async function fetchStatus() {
+		try {
+			setIsLoading(true)
+			const res = await pb.send<HeartbeatStatus>("/api/beszel/heartbeat-status", {})
+			setStatus(res)
+		} catch (error: any) {
+			toast({
+				title: t`Error`,
+				description: error.message,
+				variant: "destructive",
+			})
+		} finally {
+			setIsLoading(false)
+		}
+	}
+
+	async function sendTestHeartbeat() {
+		setIsTesting(true)
+		try {
+			const res = await pb.send<{ err: string | false }>("/api/beszel/test-heartbeat", {
+				method: "POST",
+			})
+			if ("err" in res && !res.err) {
+				toast({
+					title: t`Heartbeat sent successfully`,
+					description: t`Check your monitoring service`,
+				})
+			} else {
+				toast({
+					title: t`Error`,
+					description: (res.err as string) ?? t`Failed to send heartbeat`,
+					variant: "destructive",
+				})
+			}
+		} catch (error: any) {
+			toast({
+				title: t`Error`,
+				description: error.message,
+				variant: "destructive",
+			})
+		} finally {
+			setIsTesting(false)
+		}
+	}
+
+	const TestIcon = isTesting ? LoaderCircleIcon : SendIcon
+
+	return (
+		<div>
+			<div>
+				<h3 className="text-xl font-medium mb-2">
+					<Trans>Heartbeat Monitoring</Trans>
+				</h3>
+				<p className="text-sm text-muted-foreground leading-relaxed">
+					<Trans>
+						Send periodic outbound pings to an external monitoring service so you can monitor Beszel without exposing it
+						to the internet.
+					</Trans>
+				</p>
+			</div>
+			<Separator className="my-4" />
+
+			{isLoading ? (
+				<div className="flex items-center gap-2 text-muted-foreground py-4">
+					<LoaderCircleIcon className="h-4 w-4 animate-spin" />
+					<Trans>Loading heartbeat status...</Trans>
+				</div>
+			) : status?.enabled ? (
+				<div className="space-y-5">
+					<div className="flex items-center gap-2">
+						<Badge variant="success">
+							<Trans>Active</Trans>
+						</Badge>
+					</div>
+					<div className="grid gap-4 sm:grid-cols-2">
+						<ConfigItem label={t`Endpoint URL`} value={status.url ?? ""} mono />
+						<ConfigItem label={t`Interval`} value={`${status.interval}s`} />
+						<ConfigItem label={t`HTTP Method`} value={status.method ?? "POST"} />
+					</div>
+
+					<Separator />
+
+					<div>
+						<h4 className="text-base font-medium mb-1">
+							<Trans>Test heartbeat</Trans>
+						</h4>
+						<p className="text-sm text-muted-foreground leading-relaxed mb-3">
+							<Trans>Send a single heartbeat ping to verify your endpoint is working.</Trans>
+						</p>
+						<Button
+							type="button"
+							variant="outline"
+							className="flex items-center gap-1.5"
+							onClick={sendTestHeartbeat}
+							disabled={isTesting}
+						>
+							<TestIcon className={clsx("h-4 w-4", isTesting && "animate-spin")} />
+							<Trans>Send test heartbeat</Trans>
+						</Button>
+					</div>
+
+					<Separator />
+
+					<div>
+						<h4 className="text-base font-medium mb-1">
+							<Trans>Payload format</Trans>
+						</h4>
+						<p className="text-sm text-muted-foreground leading-relaxed mb-2">
+							<Trans>
+								When using POST, each heartbeat includes a JSON payload with system status summary, list of down
+								systems, and triggered alerts.
+							</Trans>
+						</p>
+						<p className="text-sm text-muted-foreground leading-relaxed">
+							<Trans>
+								The overall status is <code className="bg-muted rounded-sm px-1 text-primary">ok</code> when all systems
+								are up, <code className="bg-muted rounded-sm px-1 text-primary">warn</code> when alerts are triggered,
+								and <code className="bg-muted rounded-sm px-1 text-primary">error</code> when any system is down.
+							</Trans>
+						</p>
+					</div>
+				</div>
+			) : (
+				<div className="space-y-4">
+					<p className="text-sm text-muted-foreground leading-relaxed">
+						<Trans>Heartbeat monitoring is not configured.</Trans>
+					</p>
+					<div>
+						<h4 className="text-base font-medium mb-1">
+							<Trans>Configuration</Trans>
+						</h4>
+						<p className="text-sm text-muted-foreground leading-relaxed mb-3">
+							<Trans>Set the following environment variables on your Beszel hub to enable heartbeat monitoring:</Trans>
+						</p>
+						<div className="grid gap-2">
+							<EnvVarItem
+								name="BESZEL_HUB_HEARTBEAT_URL"
+								description={t`Endpoint URL to ping (required)`}
+								example="https://uptime.betterstack.com/api/v1/heartbeat/xxxx"
+							/>
+							<EnvVarItem
+								name="BESZEL_HUB_HEARTBEAT_INTERVAL"
+								description={t`Seconds between pings (default: 60)`}
+								example="60"
+							/>
+							<EnvVarItem
+								name="BESZEL_HUB_HEARTBEAT_METHOD"
+								description={t`HTTP method: POST, GET, or HEAD (default: POST)`}
+								example="POST"
+							/>
+						</div>
+					</div>
+					<p className="text-sm text-muted-foreground leading-relaxed">
+						<Trans>After setting the environment variables, restart your Beszel hub for changes to take effect.</Trans>
+					</p>
+				</div>
+			)}
+		</div>
+	)
+}
+
+function ConfigItem({ label, value, mono }: { label: string; value: string; mono?: boolean }) {
+	return (
+		<div>
+			<p className="text-sm font-medium mb-0.5">{label}</p>
+			<p className={clsx("text-sm text-muted-foreground break-all", mono && "font-mono")}>{value}</p>
+		</div>
+	)
+}
+
+function EnvVarItem({ name, description, example }: { name: string; description: string; example: string }) {
+	return (
+		<div className="bg-muted/50 rounded-md px-3 py-2">
+			<code className="text-sm font-mono text-primary">{name}</code>
+			<p className="text-sm text-muted-foreground mt-0.5">{description}</p>
+			<p className="text-xs text-muted-foreground mt-0.5">
+				<Trans>Example:</Trans> <code className="font-mono">{example}</code>
+			</p>
+		</div>
+	)
+}

internal/site/src/components/routes/settings/layout.tsx

@@ -2,7 +2,14 @@ import { t } from "@lingui/core/macro"
 import { Trans, useLingui } from "@lingui/react/macro"
 import { useStore } from "@nanostores/react"
 import { getPagePath, redirectPage } from "@nanostores/router"
-import { AlertOctagonIcon, BellIcon, FileSlidersIcon, FingerprintIcon, SettingsIcon } from "lucide-react"
+import {
+	AlertOctagonIcon,
+	BellIcon,
+	FileSlidersIcon,
+	FingerprintIcon,
+	HeartPulseIcon,
+	SettingsIcon,
+} from "lucide-react"
 import { lazy, useEffect } from "react"
 import { $router } from "@/components/router.tsx"
 import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card.tsx"
@@ -18,12 +25,14 @@ const notificationsSettingsImport = () => import("./notifications.tsx")
 const configYamlSettingsImport = () => import("./config-yaml.tsx")
 const fingerprintsSettingsImport = () => import("./tokens-fingerprints.tsx")
 const alertsHistoryDataTableSettingsImport = () => import("./alerts-history-data-table.tsx")
+const heartbeatSettingsImport = () => import("./heartbeat.tsx")
 
 const GeneralSettings = lazy(generalSettingsImport)
 const NotificationsSettings = lazy(notificationsSettingsImport)
 const ConfigYamlSettings = lazy(configYamlSettingsImport)
 const FingerprintsSettings = lazy(fingerprintsSettingsImport)
 const AlertsHistoryDataTableSettings = lazy(alertsHistoryDataTableSettingsImport)
+const HeartbeatSettings = lazy(heartbeatSettingsImport)
 
 export async function saveSettings(newSettings: Partial<UserSettings>) {
 	try {
@@ -88,6 +97,13 @@ export default function SettingsLayout() {
 			admin: true,
 			preload: configYamlSettingsImport,
 		},
+		{
+			title: t`Heartbeat`,
+			href: getPagePath($router, "settings", { name: "heartbeat" }),
+			icon: HeartPulseIcon,
+			admin: true,
+			preload: heartbeatSettingsImport,
+		},
 	]
 
 	const page = useStore($router)
@@ -141,5 +157,7 @@ function SettingsContent({ name }: { name: string }) {
 			return <FingerprintsSettings />
 		case "alert-history":
 			return <AlertsHistoryDataTableSettings />
+		case "heartbeat":
+			return <HeartbeatSettings />
 	}
 }

supplemental/CHANGELOG.md

@@ -1,3 +1,9 @@
+## Unreleased
+
+- Add outbound heartbeat monitoring to external services (BetterStack, Uptime Kuma, Healthchecks.io, etc.) with system status summary payload. Configured via `BESZEL_HUB_HEARTBEAT_URL`, `BESZEL_HUB_HEARTBEAT_INTERVAL`, and `BESZEL_HUB_HEARTBEAT_METHOD` environment variables.
+
+- Add Heartbeat settings page to the admin UI with status display, configuration reference, and test button.
+
 ## 0.18.3
 
 - Add experimental sysfs AMD GPU collector. (#737, #1569)