fix: AlertWriter graceful flush (#15) + Rolling-Update Robustheit (#19) — v1.2.95

#15 waf/alerts.go: AlertWriter.Close() flusht gepufferte Alerts + stoppt die Goroutine (stop/done-Channels, sync.Once, atomic closed; Kanal wird NIE geschlossen → Send racet ohne Panic). Wiring in cmd/edgeguard-waf nach ListenAndServe (graceful shutdown). -race-Test alerts_test.go.
#19 handlers/cluster_rollingupdate.go: (a) RollingUpdateStatus mutiert State nicht mehr beim GET — terminale Zustände altern in readRollingUpdateState nach 10 min aus (kein verlorenes 'done' bei parallelen Pollern). (b) State-File via sync.Mutex + configgen.AtomicWrite (kein partieller Read / Race zwischen Handler & Goroutine). (c) Version-Flip wird gegen die VORHER erfasste Secondary-Baseline geprüft statt gegen die Primary-Version (verhindert sofort-/nie-Flip).
Bewusst belassen: geteilter upgrade.sh-Pfad ist deterministischer Inhalt + an exakte sudoers-Zeile gebunden → Überschreib-Race benign; MST-Timestamp-Parse locale (Server laufen C-Locale).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Makefile

@@ -4,7 +4,7 @@
 
 GO       ?= $(shell which go || echo /usr/local/go/bin/go)
 MODULE   := git.netcell-it.de/projekte/edgeguard-native
-BINARIES := edgeguard-api edgeguard-scheduler edgeguard-ctl
+BINARIES := edgeguard-api edgeguard-scheduler edgeguard-ctl edgeguard-waf
 VERSION  := $(shell cat VERSION 2>/dev/null || echo 0.0.1-dev)
 LDFLAGS  := -s -w -X main.version=$(VERSION)
 GOFLAGS  := -trimpath -mod=readonly

VERSION

@@ -1 +1 @@
-1.1.162
+1.2.95

cmd/edgeguard-api/main.go

@@ -28,6 +28,8 @@ import (
 	squidrender "git.netcell-it.de/projekte/edgeguard-native/internal/squid"
 	unboundrender "git.netcell-it.de/projekte/edgeguard-native/internal/unbound"
 	wgrender "git.netcell-it.de/projekte/edgeguard-native/internal/wireguard"
+	kearender "git.netcell-it.de/projekte/edgeguard-native/internal/kea"
+	radiusrender "git.netcell-it.de/projekte/edgeguard-native/internal/freeradius"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/acme"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/alerts"
@@ -40,6 +42,7 @@ import (
 	"git.netcell-it.de/projekte/edgeguard-native/internal/aggregator"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/cluster/clustertls"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/cluster/jointoken"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/clusterjoin"
 	aptsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/apt"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/domainheaders"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/domains"
@@ -57,10 +60,14 @@ import (
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/setup"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/tlscerts"
 	wgsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/wireguard"
+	dhcpsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/dhcp"
+	oidcsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/oidc"
+	radiussvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/radius"
 	usersvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/users"
+	wafsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/waf"
 )
 
-var version = "1.1.162"
+var version = "1.2.35"
 
 func main() {
 	addr := os.Getenv("EDGEGUARD_API_ADDR")
@@ -175,6 +182,20 @@ func main() {
 			go runClusterHeartbeat(context.Background(), pool, nodeID, version)
 		}
 
+		// Secondary: push config_hash to primary every 5 min so the primary's
+		// ha_nodes reflects actual state. Without this, the primary retains the
+		// stale hash written at join-time and the drift banner never clears.
+		// st.IsClusterNode + PrimaryFQDN are only set on joined secondary nodes.
+		if nodeID != "" && st != nil && st.IsClusterNode && st.PrimaryFQDN != "" {
+			if primaryURL, normErr := clusterjoin.NormalizePrimaryURL(st.PrimaryFQDN); normErr == nil {
+				go runPrimaryPush(context.Background(), pool, nodeID, st.FQDN, version, primaryURL)
+			} else {
+				slog.Warn("cluster: cannot normalize primary URL for push", "primary", st.PrimaryFQDN, "error", normErr)
+			}
+			// runSecondaryConfigRender wird weiter unten gestartet sobald
+			// clusterAggregator verfügbar ist (braucht mTLS-Client für Cert-Sync).
+		}
+
 		// Phase 3.3: Cluster-CA + Peer-Cert. Founder-Pfad — auf einem
 		// frisch installierten Single-Node generieren wir die CA und
 		// signieren uns selbst, damit der Agent-Listener auf :8443
@@ -219,6 +240,12 @@ func main() {
 			}
 		}
 
+		// Secondary-Config-Render: jetzt wo der Aggregator bereit ist starten.
+		// Aggregator wird für Cert-Sync (mTLS GET /agent/cluster/tls-certs) benötigt.
+		if nodeID != "" && st != nil && st.IsClusterNode && st.PrimaryFQDN != "" {
+			go runSecondaryConfigRender(context.Background(), pool, secrets.New(""), clusterAggregator, nodeID)
+		}
+
 		auditRepo := audit.New(pool)
 		domainsRepo := domains.New(pool)
 		domainHeadersRepo := domainheaders.New(pool)
@@ -294,6 +321,14 @@ func main() {
 		authed.Use(requireAuth, handlers.RequireAdminForMutations())
 		setupHdl.RegisterAuthed(authed)
 		handlers.NewUsersHandler(usersRepo, auditRepo, nodeID).Register(authed)
+
+		// OIDC/Keycloak SSO — public Flow-Endpoints auf v1 (hinter SetupGate),
+		// Admin-Settings auf authed (PUT nur admin via RequireAdminForMutations).
+		oidcRepo := oidcsvc.New(pool, secretsBox)
+		oidcHdl := handlers.NewOIDCHandler(oidcRepo, oidcsvc.NewClient(oidcRepo), usersRepo, signer, setupStore).
+			WithAudit(auditRepo, nodeID)
+		oidcHdl.RegisterPublic(v1)
+		oidcHdl.RegisterAdmin(authed)
 		handlers.NewDomainsHandler(domainsRepo, routingRepo, domainHeadersRepo, auditRepo, nodeID, haproxyReloader).Register(authed)
 		handlers.NewBackendsHandler(backendsRepo, auditRepo, nodeID, haproxyReloader).Register(authed)
 		handlers.NewBackendServersHandler(backendServersRepo, auditRepo, nodeID, haproxyReloader).Register(authed)
@@ -324,7 +359,9 @@ func main() {
 		clusterHdl := handlers.NewClusterHandler(clusterStore, nodeID).
 			WithAggregator(clusterAggregator).
 			WithJoinFlow(clusterTLSStore, joinTokens).
-			WithPeerReloader(peerReloader)
+			WithPeerReloader(peerReloader).
+			WithAudit(auditRepo, nodeID).
+			WithVersion(version)
 		clusterHdl.Register(authed)
 		// /cluster/issue-cert läuft PUBLIC — joining Peer hat noch
 		// keine Session/Cert. Token + Nonce-Tracking ist die einzige
@@ -360,6 +397,8 @@ func main() {
 			return firewallrender.New(pool).Render(ctx)
 		}
 		handlers.NewFirewallHandler(fwZones, fwAddrObj, fwAddrGrp, fwSvc, fwSvcGrp, fwRules, fwNAT, auditRepo, nodeID, fwReloader, pool).Register(authed)
+		handlers.NewCrowdSecHandler(auditRepo, nodeID).Register(authed)
+		handlers.NewWafHandler(wafsvc.New(pool), auditRepo, nodeID, haproxyReloader).Register(authed)
 
 		// withFW wraps a service-reloader so that AFTER the service is
 		// reloaded, the firewall is also re-rendered. Necessary for
@@ -410,14 +449,28 @@ func main() {
 		}
 		handlers.NewNTPHandler(ntpRepo, auditRepo, nodeID, withFW(chronyReloader)).Register(authed)
 
+		// DHCP (Kea) — re-render kea-dhcp4.conf + manage service lifecycle.
+		keaReloader := func(ctx context.Context) error {
+			return kearender.New(pool).Render(ctx)
+		}
+		handlers.NewDHCPHandler(dhcpsvc.New(pool), auditRepo, nodeID, withFW(keaReloader)).Register(authed)
+
+		// RADIUS (FreeRADIUS) — re-render clients.conf + authorize + service lifecycle.
+		radiusReloader := func(ctx context.Context) error {
+			return radiusrender.New(pool, secretsBox).Render(ctx)
+		}
+		handlers.NewRADIUSHandler(radiussvc.New(pool, secretsBox), auditRepo, nodeID, withFW(radiusReloader)).Register(authed)
+
 		// Wire all service reloaders into systemHdl so RenderConfigs
 		// re-renders every service from DB state in one shot.
 		systemHdl.WithAllReloaders(map[string]func(context.Context) error{
-			"nftables":  fwReloader,
-			"wireguard": wgReloader,
-			"squid":     squidReloader,
-			"unbound":   unboundReloader,
-			"chrony":    chronyReloader,
+			"nftables":   fwReloader,
+			"wireguard":  wgReloader,
+			"squid":      squidReloader,
+			"unbound":    unboundReloader,
+			"chrony":     chronyReloader,
+			"kea":        keaReloader,
+			"freeradius": radiusReloader,
 		})
 
 		// License — node-local key store + DB-mirror of last verify
@@ -457,6 +510,10 @@ func main() {
 	// schon erledigt.
 	startAgentListener(version, agentHdl, systemHdl)
 
+	// Nach einem Upgrade-Neustart: wenn die State-Datei "updating-primary"
+	// enthält, sind wir gerade neu gestartet → Update abgeschlossen → "done".
+	handlers.FinishRollingUpdateIfPending()
+
 	log.Printf("edgeguard-api %s listening on %s", version, addr)
 	srv := &http.Server{Addr: addr, Handler: r}
 	if err := srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
@@ -560,10 +617,18 @@ func mountUI(r *gin.Engine) {
 			return
 		}
 		if info, err := os.Stat(full); err == nil && !info.IsDir() {
+			// Vite hashed assets are immutable — cache them forever.
+			// index.html must never be cached so updates take effect.
+			if strings.HasPrefix(clean, "/assets/") {
+				c.Header("Cache-Control", "public, max-age=31536000, immutable")
+			} else {
+				c.Header("Cache-Control", "no-cache, no-store, must-revalidate")
+			}
 			c.File(full)
 			return
 		}
 		// SPA fallback — React Router renders the right page.
+		c.Header("Cache-Control", "no-cache, no-store, must-revalidate")
 		c.File(indexPath)
 	})
 }
@@ -680,6 +745,116 @@ func runClusterHeartbeat(ctx context.Context, pool *pgxpoolPool, localID, versio
 	}
 }
 
+// runSecondaryConfigRender läuft auf Secondary-Nodes und re-rendert alle
+// Service-Configs wenn die Logical Replication Änderungen vom Primary
+// geliefert hat. Erkennt das an einem geänderten config_hash.
+// Tick: 5 min — balanciert Reaktionszeit gegen Reload-Overhead.
+//
+// Cert-Sync läuft auf jedem Tick unabhängig vom config_hash, da certbot-
+// Renewals auf dem Primary den Hash nicht ändern.
+func runSecondaryConfigRender(ctx context.Context, pool *pgxpoolPool, box *secrets.Box, agg *aggregator.Aggregator, localID string) {
+	const tick = 5 * time.Minute
+	t := time.NewTicker(tick)
+	defer t.Stop()
+	var lastHash string
+	render := func() {
+		rCtx, cancel := context.WithTimeout(ctx, 90*time.Second)
+		defer cancel()
+
+		// TLS-Zertifikate bei jedem Tick synchronisieren — unabhängig vom
+		// config_hash, da certbot-Renewals den Hash nicht berühren.
+		if err := handlers.SyncTLSCertsFromPrimary(rCtx, pool, agg, localID); err != nil {
+			slog.Warn("cluster: cert sync failed", "error", err)
+		}
+
+		hash, err := cluster.ComputeConfigHash(rCtx, pool)
+		if err != nil || hash == lastHash {
+			return
+		}
+		lastHash = hash
+		slog.Info("cluster: secondary config changed via replication, re-rendering", "hash", hash)
+		// HAProxy
+		if err := haproxy.New(pool).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary haproxy render failed", "error", err)
+		}
+		// nftables
+		if err := firewallrender.New(pool).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary nftables render failed", "error", err)
+		}
+		// WireGuard — Interface-Configs + wg-quick@<iface> reload
+		if err := wgrender.New(pool, box).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary wireguard render failed", "error", err)
+		}
+		// Squid forward proxy
+		if err := squidrender.New(pool).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary squid render failed", "error", err)
+		}
+		// Unbound DNS
+		if err := unboundrender.New(pool).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary unbound render failed", "error", err)
+		}
+		// Chrony NTP
+		if err := chronyrender.New(pool).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary chrony render failed", "error", err)
+		}
+		// Netzwerk-Interfaces (VLAN/Bridge/Bond) — erstellt Interface-Objekte,
+		// weist aber KEINE IPs zu (das ist node-spezifisch und darf nicht aus
+		// der Replikation kommen — sonst IP-Konflikt mit dem Primary).
+		if err := networkifs.NewGenerator(networkifs.New(pool)).Render(rCtx); err != nil {
+			slog.Warn("cluster: secondary interfaces render failed", "error", err)
+		}
+		// IP-Adressen werden auf dem Secondary NICHT aus der Replikation
+		// angewendet. Jeder Node konfiguriert seine eigenen IPs statisch
+		// (z.B. /etc/network/interfaces). Floating-Service-IPs werden von
+		// Keepalived verwaltet — nicht vom Renderer.
+	}
+	// Initialer Check nach kurzem Delay (Replication braucht einen Moment)
+	select {
+	case <-ctx.Done():
+		return
+	case <-time.After(30 * time.Second):
+		render()
+	}
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-t.C:
+			render()
+		}
+	}
+}
+
+// runPrimaryPush periodically pushes this secondary node's config_hash to the
+// primary via mTLS. The primary's ha_nodes view only gets config_hash written
+// during join-time autoRegister — after that the primary never hears about
+// hash changes unless we push. Without this, the drift banner shows stale
+// hashes from join-time forever.
+func runPrimaryPush(ctx context.Context, pool *pgxpoolPool, nodeID, fqdn, version, primaryURL string) {
+	const tick = 5 * time.Minute
+	t := time.NewTicker(tick)
+	defer t.Stop()
+	push := func() {
+		pCtx, cancel := context.WithTimeout(ctx, 15*time.Second)
+		defer cancel()
+		hash, _ := cluster.ComputeConfigHash(pCtx, pool)
+		if err := clusterjoin.PushSelfToPrimary(primaryURL, "", nodeID, fqdn, version, hash); err != nil {
+			slog.Warn("cluster: push-to-primary failed", "error", err)
+		} else {
+			slog.Debug("cluster: config_hash pushed to primary", "hash", hash)
+		}
+	}
+	push() // immediate push on API startup
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-t.C:
+			push()
+		}
+	}
+}
+
 func randomEphemeralSecret() []byte {
 	b := make([]byte, 32)
 	if _, err := rand.Read(b); err != nil {

cmd/edgeguard-ctl/cluster_replication.go

@@ -0,0 +1,589 @@
+package main
+
+import (
+	"crypto/rand"
+	"crypto/tls"
+	"crypto/x509"
+	"encoding/json"
+	"flag"
+	"fmt"
+	"net"
+	"net/http"
+	"os"
+	"os/exec"
+	"os/user"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/cluster/clustertls"
+)
+
+const (
+	egReplSecret = "/var/lib/edgeguard/pg-replication-secret"
+	egReplUser   = "edgeguard_replicator"
+	egPubName    = "edgeguard_shared"
+	egSubName    = "edgeguard_sub"
+)
+
+// pgConfig hält die zur Laufzeit erkannten PG-Pfade.
+type pgConfig struct {
+	Version string // z.B. "17"
+	Cluster string // z.B. "main"
+	DataDir string // /var/lib/postgresql/17/main
+	HBAPath string // /etc/postgresql/17/main/pg_hba.conf
+	ConfD   string // /etc/postgresql/17/main/conf.d
+}
+
+// detectPGConfig ermittelt Version, Cluster und Pfade aus der laufenden
+// PG-Instanz via SHOW hba_file / SHOW data_directory. Damit ist der Code
+// unabhängig von der PG-Hauptversion (16, 17, …).
+func detectPGConfig() (pgConfig, error) {
+	hbaRaw, err := psqlRun([]string{"-tA", "-c", "SHOW hba_file;"})
+	if err != nil {
+		return pgConfig{}, fmt.Errorf("cannot detect pg hba_file: %w", err)
+	}
+	hbaPath := strings.TrimSpace(string(hbaRaw))
+
+	dataRaw, err := psqlRun([]string{"-tA", "-c", "SHOW data_directory;"})
+	if err != nil {
+		return pgConfig{}, fmt.Errorf("cannot detect pg data_directory: %w", err)
+	}
+	dataDir := strings.TrimSpace(string(dataRaw))
+
+	// hbaPath: /etc/postgresql/<version>/<cluster>/pg_hba.conf
+	parts := strings.Split(filepath.ToSlash(hbaPath), "/")
+	if len(parts) < 6 {
+		return pgConfig{}, fmt.Errorf("unexpected hba_file path: %s", hbaPath)
+	}
+	version := parts[3]
+	cluster := parts[4]
+	confD := filepath.Join("/etc/postgresql", version, cluster, "conf.d")
+
+	return pgConfig{
+		Version: version,
+		Cluster: cluster,
+		DataDir: dataDir,
+		HBAPath: hbaPath,
+		ConfD:   confD,
+	}, nil
+}
+
+// localOnlyTables listet alle Tabellen die nicht in die Replikations-
+// Publication aufgenommen werden. Alles andere wird automatisch repliziert.
+var localOnlyTables = []string{
+	"ha_nodes",           // Node-Identität, Status
+	"network_interfaces", // Eigene Interfaces (eth0, eth1 …)
+	"ip_addresses",       // Eigene IP-Adressen (unterschiedlich pro Node!)
+	"static_routes",      // Node-spezifisches Routing
+	"cluster_settings",   // VIP-Interface kann pro Node unterschiedlich sein
+	"dns_settings",       // listen_addresses ist node-spezifisch
+	"ntp_settings",       // listen_addresses ist node-spezifisch
+	"dhcp_settings",      // ob DIESE Node DHCP betreibt (Dual-DHCP vermeiden)
+	"radius_settings",    // ob DIESE Node RADIUS betreibt + Listen-Adressen
+	"system_settings",    // Hostname, Maintenance-Mode etc.
+	"join_tokens_used",   // Token-Tracking nur auf Primary relevant
+	"audit_log",          // Lokales Audit-Protokoll
+	"alert_events",       // Lokale Laufzeit-Events
+	"backups",            // Backup-Historie ist per-Node
+	"goose_db_version",   // Migration-Tracking, internes Tool-State
+}
+
+// cmdClusterInitReplication richtet PG auf dieser Node als Logical-Replication-
+// Primary ein. Idempotent — kann gefahrlos mehrfach laufen.
+//
+// Ablauf:
+//  1. edgeguard_replicator-Rolle anlegen/aktualisieren
+//  2. Passwort → /var/lib/edgeguard/pg-replication-secret
+//  3. conf.d/edgeguard-replication.conf mit wal_level=logical schreiben
+//  4. pg_hba.conf für Replikations-Verbindungen aktualisieren
+//  5. SELECT-Grants auf alle geteilten Tabellen
+//  6. PUBLICATION erstellen (alle Tabellen außer localOnlyTables)
+//  7. PG reload
+func cmdClusterInitReplication(args []string) int {
+	fs := flag.NewFlagSet("cluster-init-replication", flag.ContinueOnError)
+	fs.SetOutput(os.Stderr)
+	if err := fs.Parse(args); err != nil {
+		return 2
+	}
+
+	pg, err := detectPGConfig()
+	if err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: PG-Erkennung:", err)
+		return 1
+	}
+	fmt.Printf("→ PostgreSQL %s/%s erkannt\n", pg.Version, pg.Cluster)
+
+	// 1. Passwort generieren
+	pass, err := generatePassword(32)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: generate password:", err)
+		return 1
+	}
+
+	// 2. edgeguard_replicator-Rolle anlegen/updaten
+	roleSQL := fmt.Sprintf(`DO $$
+BEGIN
+  IF NOT EXISTS (SELECT FROM pg_roles WHERE rolname = '%s') THEN
+    CREATE ROLE %s REPLICATION LOGIN PASSWORD '%s';
+  ELSE
+    ALTER ROLE %s PASSWORD '%s';
+  END IF;
+END
+$$`, egReplUser, egReplUser, pass, egReplUser, pass)
+	if err := psqlExec(roleSQL); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: create replication role:", err)
+		return 1
+	}
+	fmt.Printf("✓ Replication-Rolle %q angelegt/aktualisiert\n", egReplUser)
+
+	// 3. Passwort speichern
+	if err := os.MkdirAll(filepath.Dir(egReplSecret), 0o750); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: mkdir:", err)
+		return 1
+	}
+	if err := os.WriteFile(egReplSecret, []byte(pass), 0o600); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: write secret:", err)
+		return 1
+	}
+	// Ownership an edgeguard-api-User übergeben damit die API lesen kann
+	if u, err := user.Lookup("edgeguard"); err == nil {
+		uid, _ := strconv.Atoi(u.Uid)
+		gid, _ := strconv.Atoi(u.Gid)
+		_ = os.Chown(egReplSecret, uid, gid)
+	}
+	fmt.Printf("✓ Replication-Secret gespeichert: %s\n", egReplSecret)
+
+	// 4. conf.d/edgeguard-replication.conf schreiben
+	// wal_level=logical ist eine Obermenge von replica — unterstützt
+	// sowohl Logical Replication als auch ggfs. physisches WAL-Archiving.
+	if err := os.MkdirAll(pg.ConfD, 0o755); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: conf.d mkdir:", err)
+		return 1
+	}
+	replConf := `# EdgeGuard Logical Replication — automatisch generiert
+# Nicht manuell bearbeiten; wird von edgeguard-ctl cluster-init-replication verwaltet.
+wal_level = logical
+max_wal_senders = 10
+max_replication_slots = 20
+max_logical_replication_workers = 4
+wal_keep_size = 512MB
+# Lausche auf localhost + alle konfigurierten Interfaces damit Cluster-Peers
+# sich verbinden können. '*' ist sicher weil pg_hba.conf den Zugriff auf
+# bekannte Replikations-User beschränkt.
+listen_addresses = '*'
+`
+	confPath := filepath.Join(pg.ConfD, "edgeguard-replication.conf")
+	if err := os.WriteFile(confPath, []byte(replConf), 0o644); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: write postgresql conf:", err)
+		return 1
+	}
+	fmt.Printf("✓ %s geschrieben (wal_level=logical)\n", confPath)
+
+	// 5. pg_hba.conf aktualisieren
+	if err := ensureHBAReplication(pg.HBAPath); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: pg_hba.conf:", err)
+		return 1
+	}
+	fmt.Printf("✓ %s aktualisiert\n", pg.HBAPath)
+
+	// 6. PG reload (damit wal_level + pg_hba aktiv werden)
+	if out, err := exec.Command("pg_ctlcluster", pg.Version, pg.Cluster, "reload").CombinedOutput(); err != nil {
+		fmt.Fprintf(os.Stderr, "cluster-init-replication: pg reload failed: %v\n%s\n", err, out)
+		return 1
+	}
+	fmt.Printf("✓ PostgreSQL %s/%s neu geladen\n", pg.Version, pg.Cluster)
+
+	// 7. SELECT-Grants: edgeguard_replicator muss alle zu replizierenden
+	// Tabellen lesen können. DEFAULT PRIVILEGES sichert zukünftige Tabellen.
+	grantSQL := fmt.Sprintf(`
+GRANT SELECT ON ALL TABLES IN SCHEMA public TO %s;
+ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT SELECT ON TABLES TO %s;
+`, egReplUser, egReplUser)
+	if err := psqlDBExec("edgeguard", grantSQL); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: grant SELECT:", err)
+		return 1
+	}
+	fmt.Printf("✓ SELECT auf alle Tabellen für %q gewährt\n", egReplUser)
+
+	// 8. PUBLICATION erstellen — alle public-Tabellen außer localOnlyTables.
+	// Idempotent: DROP IF EXISTS + CREATE.
+	if err := createPublication(); err != nil {
+		fmt.Fprintln(os.Stderr, "cluster-init-replication: create publication:", err)
+		return 1
+	}
+	fmt.Printf("✓ PUBLICATION %q erstellt\n", egPubName)
+
+	fmt.Println()
+	fmt.Println("Nächste Schritte:")
+	fmt.Println("  1) Auf dem Secondary: edgeguard-ctl cluster-setup-standby <primary-ip>")
+	fmt.Println("  2) Cluster-Settings (VIP) auf BEIDEN Nodes separat konfigurieren")
+	fmt.Println("     → Settings → Cluster → VIP/Keepalived")
+	return 0
+}
+
+// createPublication baut die PUBLICATION dynamisch aus allen Tabellen
+// im public-Schema minus localOnlyTables. Idempotent: löscht eine
+// bestehende Publication gleichen Namens zuerst.
+func createPublication() error {
+	// Alle Tabellen im public-Schema ermitteln
+	listSQL := `SELECT tablename FROM pg_tables WHERE schemaname = 'public' ORDER BY tablename`
+	out, err := psqlDBRun("edgeguard", []string{"-tA", "-c", listSQL})
+	if err != nil {
+		return fmt.Errorf("list tables: %w", err)
+	}
+
+	excluded := make(map[string]bool)
+	for _, t := range localOnlyTables {
+		excluded[t] = true
+	}
+
+	var tables []string
+	for _, line := range strings.Split(strings.TrimSpace(string(out)), "\n") {
+		t := strings.TrimSpace(line)
+		if t == "" || excluded[t] {
+			continue
+		}
+		tables = append(tables, t)
+	}
+	if len(tables) == 0 {
+		return fmt.Errorf("keine Tabellen für Publication gefunden")
+	}
+
+	dropSQL := fmt.Sprintf("DROP PUBLICATION IF EXISTS %s;", egPubName)
+	if err := psqlDBExec("edgeguard", dropSQL); err != nil {
+		return fmt.Errorf("drop old publication: %w", err)
+	}
+
+	createSQL := fmt.Sprintf("CREATE PUBLICATION %s FOR TABLE %s;",
+		egPubName, strings.Join(tables, ", "))
+	if err := psqlDBExec("edgeguard", createSQL); err != nil {
+		return fmt.Errorf("create publication: %w", err)
+	}
+	return nil
+}
+
+// ensureHBAReplication fügt Einträge für die Replikations-Verbindung
+// in pg_hba.conf ein. Für Logical Replication brauchen wir einen
+// normalen "host edgeguard"-Eintrag (nicht "host replication").
+// Idempotent via Marker-Kommentar.
+func ensureHBAReplication(hbaPath string) error {
+	data, err := os.ReadFile(hbaPath)
+	if err != nil {
+		return fmt.Errorf("read: %w", err)
+	}
+	const marker = "# EdgeGuard replication"
+	if strings.Contains(string(data), marker) {
+		return nil
+	}
+	entry := fmt.Sprintf(`
+%s
+host edgeguard   %s 0.0.0.0/0 scram-sha-256
+host edgeguard   %s ::/0      scram-sha-256
+host replication %s 0.0.0.0/0 scram-sha-256
+host replication %s ::/0      scram-sha-256
+`, marker, egReplUser, egReplUser, egReplUser, egReplUser)
+	f, err := os.OpenFile(hbaPath, os.O_APPEND|os.O_WRONLY, 0o640)
+	if err != nil {
+		return fmt.Errorf("open: %w", err)
+	}
+	defer f.Close()
+	_, err = f.WriteString(entry)
+	return err
+}
+
+// cmdClusterSetupStandby richtet diesen Node als Logical-Replication-
+// Subscriber ein. Der Secondary behält seine eigene beschreibbare PG-
+// Instanz — nur die geteilten Tabellen werden vom Primary repliziert.
+// Node-spezifische Tabellen (Interfaces, IPs, Routen, VIP-Settings …)
+// bleiben lokal und werden NICHT überschrieben. Analog zu OPNsense's
+// HA-Sync: Interface-IPs und Hostname bleiben immer per-Node konfiguriert.
+//
+// Voraussetzungen:
+//   - cluster-join erfolgreich (TLS-Certs in /var/lib/edgeguard/cluster-tls/)
+//   - Primary hat cluster-init-replication ausgeführt
+//   - Dieser Node hat edgeguard-api schon gelaufen (Migrations ausgeführt)
+//
+// Ablauf:
+//  1. Replication-Credentials via mTLS vom Primary holen
+//  2. Bestehende Subscription löschen (idempotent)
+//  3. SUBSCRIPTION auf Primary erstellen (copy_data=true → Initialkopiierung)
+//  4. Warten bis Initialkopiierung abgeschlossen
+//  5. render-config ausführen damit Service-Configs den neuen Stand reflektieren
+func cmdClusterSetupStandby(args []string) int {
+	fs := flag.NewFlagSet("cluster-setup-standby", flag.ContinueOnError)
+	agentPort := fs.Int("agent-port", 8443, "mTLS agent port on primary")
+	tlsDir := fs.String("tls-dir", clustertls.DefaultDir, "Verzeichnis mit ca.crt + peer.{crt,key}")
+	fs.SetOutput(os.Stderr)
+	if err := fs.Parse(args); err != nil {
+		return 2
+	}
+	if fs.NArg() < 1 {
+		fmt.Fprintln(os.Stderr, "usage: edgeguard-ctl cluster-setup-standby <primary-ip-or-host>")
+		return 2
+	}
+	primaryHost := fs.Arg(0)
+
+	// 1. Replication-Credentials vom Primary holen
+	creds, err := fetchReplicationCreds(primaryHost, *agentPort, *tlsDir)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "cluster-setup-standby: replication-creds: %v\n", err)
+		return 1
+	}
+	fmt.Printf("✓ Replication-Credentials von %s:%d erhalten\n", primaryHost, *agentPort)
+
+	// 2. Bestehende Subscription löschen (idempotent)
+	dropSQL := fmt.Sprintf(`
+DO $$ BEGIN
+  IF EXISTS (SELECT FROM pg_subscription WHERE subname = '%s') THEN
+    ALTER SUBSCRIPTION %s DISABLE;
+    ALTER SUBSCRIPTION %s SET (slot_name = NONE);
+    DROP SUBSCRIPTION %s;
+  END IF;
+END $$;`, egSubName, egSubName, egSubName, egSubName)
+	if err := psqlDBExec("edgeguard", dropSQL); err != nil {
+		// Nicht fatal — wenn PG noch keine Subscription kennt ist das OK
+		fmt.Printf("  → keine bestehende Subscription gefunden (ok)\n")
+	} else {
+		fmt.Println("✓ Bestehende Subscription entfernt")
+	}
+
+	// 3. SUBSCRIPTION erstellen
+	// sslmode=require: Verbindung zwischen Cluster-Nodes soll immer verschlüsselt sein.
+	// copy_data=true: Initialkopiierung aller geteilten Tabellen vom Primary.
+	connStr := fmt.Sprintf(
+		"host=%s port=%d user=%s password=%s dbname=edgeguard sslmode=require",
+		creds.Host, creds.Port, creds.User, creds.Password,
+	)
+	createSQL := fmt.Sprintf(
+		"CREATE SUBSCRIPTION %s CONNECTION '%s' PUBLICATION %s WITH (copy_data = true, enabled = true);",
+		egSubName, connStr, egPubName,
+	)
+	// Via stdin (nicht -c), damit das Replikations-Passwort nicht in der
+	// Prozess-Argv (ps/proc) oder in PG-log_statement landet.
+	if err := psqlDBExecStdin("edgeguard", createSQL); err != nil {
+		fmt.Fprintf(os.Stderr, "cluster-setup-standby: create subscription: %v\n", err)
+		return 1
+	}
+	fmt.Printf("✓ SUBSCRIPTION %q erstellt — Initialkopiierung läuft\n", egSubName)
+
+	// 4. Warten bis Initialkopiierung abgeschlossen
+	fmt.Print("→ Warte auf Initialkopiierung")
+	deadline := time.Now().Add(5 * time.Minute)
+	for time.Now().Before(deadline) {
+		pendingSQL := fmt.Sprintf(`
+SELECT COUNT(*) FROM pg_subscription_rel
+WHERE srsubid = (SELECT oid FROM pg_subscription WHERE subname = '%s')
+  AND srsubstate != 'r';`, egSubName)
+		out, err := psqlDBRun("edgeguard", []string{"-tA", "-c", pendingSQL})
+		if err == nil && strings.TrimSpace(string(out)) == "0" {
+			break
+		}
+		fmt.Print(".")
+		time.Sleep(3 * time.Second)
+	}
+	fmt.Println()
+
+	// Finale Prüfung
+	checkSQL := fmt.Sprintf(`
+SELECT COUNT(*) FROM pg_subscription_rel
+WHERE srsubid = (SELECT oid FROM pg_subscription WHERE subname = '%s')
+  AND srsubstate != 'r';`, egSubName)
+	if out, err := psqlDBRun("edgeguard", []string{"-tA", "-c", checkSQL}); err == nil {
+		if n := strings.TrimSpace(string(out)); n != "0" {
+			fmt.Fprintf(os.Stderr,
+				"cluster-setup-standby: %s Tabellen noch nicht synchronisiert — prüfe PG-Logs\n", n)
+			fmt.Println("  → Subscription läuft trotzdem weiter im Hintergrund")
+		} else {
+			fmt.Println("✓ Alle geteilten Tabellen synchronisiert")
+		}
+	}
+
+	// 5. Master-Key vom Primary holen — für WireGuard-Key-Entschlüsselung
+	fmt.Println("→ Secrets Master-Key vom Primary synchronisieren...")
+	if err := syncMasterKey(primaryHost, *agentPort, *tlsDir); err != nil {
+		fmt.Fprintf(os.Stderr, "cluster-setup-standby: master-key: %v (WireGuard-Keys können nicht entschlüsselt werden)\n", err)
+	} else {
+		fmt.Println("✓ Master-Key synchronisiert")
+	}
+
+	// 6. render-config ausführen — muss als edgeguard-User laufen (DB-Zugriff)
+	fmt.Println("→ Service-Configs neu rendern...")
+	if out, err := exec.Command("sudo", "-u", "edgeguard", "edgeguard-ctl", "render-config").CombinedOutput(); err != nil {
+		fmt.Fprintf(os.Stderr, "cluster-setup-standby: render-config: %v\n%s\n", err, out)
+		fmt.Println("  → Manuell nachholen: sudo -u edgeguard edgeguard-ctl render-config")
+	} else {
+		fmt.Print(string(out))
+		fmt.Println("✓ Service-Configs aktualisiert")
+	}
+
+	fmt.Println()
+	fmt.Println("✓ Logical Replication eingerichtet.")
+	fmt.Println()
+	fmt.Println("Was repliziert wird (automatisch, in Echtzeit):")
+	fmt.Println("  Domains, Backends, Firewall-Rules, WireGuard, DNS-Zones,")
+	fmt.Println("  TLS-Certs, Users, Forward-Proxy, NTP-Pools, ...")
+	fmt.Println()
+	fmt.Println("Was NICHT repliziert wird (bleibt pro Node konfiguriert):")
+	fmt.Println("  Netzwerk-Interfaces, IP-Adressen, Routen,")
+	fmt.Println("  Cluster-Settings (VIP-Interface!), DNS/NTP-Listen-Adressen")
+	fmt.Println()
+	fmt.Println("Nächste Schritte:")
+	fmt.Println("  1) sudo systemctl restart edgeguard-api")
+	fmt.Println("  2) VIP/Keepalived auf BEIDEN Nodes separat konfigurieren:")
+	fmt.Println("     Settings → Cluster → VIP/Keepalived")
+	fmt.Println("  3) Bei Failover: edgeguard-ctl promote (auf dem Secondary)")
+	return 0
+}
+
+// pgReplicationCreds sind die Credentials die der Primary via mTLS zurückgibt.
+type pgReplicationCreds struct {
+	Host     string `json:"host"`
+	Port     int    `json:"port"`
+	User     string `json:"user"`
+	Password string `json:"password"`
+}
+
+// fetchReplicationCreds ruft GET /agent/cluster/pg-replication-info via mTLS ab.
+func fetchReplicationCreds(host string, agentPort int, tlsDir string) (*pgReplicationCreds, error) {
+	caPath := filepath.Join(tlsDir, "ca.crt")
+	certPath := filepath.Join(tlsDir, "peer.crt")
+	keyPath := filepath.Join(tlsDir, "peer.key")
+
+	caCert, err := os.ReadFile(caPath)
+	if err != nil {
+		return nil, fmt.Errorf("read ca.crt: %w", err)
+	}
+	pool := x509.NewCertPool()
+	pool.AppendCertsFromPEM(caCert)
+
+	cert, err := tls.LoadX509KeyPair(certPath, keyPath)
+	if err != nil {
+		return nil, fmt.Errorf("load peer cert: %w", err)
+	}
+
+	client := &http.Client{
+		Timeout: 15 * time.Second,
+		Transport: &http.Transport{
+			TLSClientConfig: &tls.Config{
+				RootCAs:      pool,
+				Certificates: []tls.Certificate{cert},
+			},
+		},
+	}
+
+	url := "https://" + net.JoinHostPort(host, strconv.Itoa(agentPort)) + "/agent/cluster/pg-replication-info"
+	resp, err := client.Get(url)
+	if err != nil {
+		return nil, fmt.Errorf("GET %s: %w", url, err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return nil, fmt.Errorf("GET %s: HTTP %d", url, resp.StatusCode)
+	}
+
+	var result struct {
+		Data pgReplicationCreds `json:"data"`
+	}
+	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
+		return nil, fmt.Errorf("decode response: %w", err)
+	}
+	return &result.Data, nil
+}
+
+// syncMasterKey holt den Secrets-Master-Key vom Primary via mTLS und schreibt
+// ihn nach /var/lib/edgeguard/.master_key. Dadurch können replizierte
+// verschlüsselte WireGuard-Keys und PSKs auf dem Secondary entschlüsselt werden.
+func syncMasterKey(host string, agentPort int, tlsDir string) error {
+	caPath := filepath.Join(tlsDir, "ca.crt")
+	certPath := filepath.Join(tlsDir, "peer.crt")
+	keyPath := filepath.Join(tlsDir, "peer.key")
+
+	caCert, err := os.ReadFile(caPath)
+	if err != nil {
+		return fmt.Errorf("read ca.crt: %w", err)
+	}
+	rootPool := x509.NewCertPool()
+	rootPool.AppendCertsFromPEM(caCert)
+	cert, err := tls.LoadX509KeyPair(certPath, keyPath)
+	if err != nil {
+		return fmt.Errorf("load peer cert: %w", err)
+	}
+	client := &http.Client{
+		Timeout: 15 * time.Second,
+		Transport: &http.Transport{
+			TLSClientConfig: &tls.Config{
+				RootCAs:      rootPool,
+				Certificates: []tls.Certificate{cert},
+			},
+		},
+	}
+	url := "https://" + net.JoinHostPort(host, strconv.Itoa(agentPort)) + "/agent/cluster/master-key"
+	resp, err := client.Get(url)
+	if err != nil {
+		return fmt.Errorf("GET %s: %w", url, err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("GET %s: HTTP %d", url, resp.StatusCode)
+	}
+	var result struct {
+		Data struct {
+			KeyHex string `json:"key_hex"`
+		} `json:"data"`
+	}
+	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
+		return fmt.Errorf("decode response: %w", err)
+	}
+	key := make([]byte, 32)
+	if _, err := fmt.Sscanf(result.Data.KeyHex, "%x", &key); err != nil {
+		return fmt.Errorf("decode key_hex: %w", err)
+	}
+	const masterKeyPath = "/var/lib/edgeguard/.master_key"
+	if err := os.WriteFile(masterKeyPath, key, 0o600); err != nil {
+		return fmt.Errorf("write master key: %w", err)
+	}
+	if u, err := user.Lookup("edgeguard"); err == nil {
+		uid, _ := strconv.Atoi(u.Uid)
+		gid, _ := strconv.Atoi(u.Gid)
+		_ = os.Chown(masterKeyPath, uid, gid)
+	}
+	return nil
+}
+
+// generatePassword erzeugt ein kryptographisch sicheres Passwort.
+func generatePassword(n int) (string, error) {
+	const charset = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
+	buf := make([]byte, n)
+	if _, err := rand.Read(buf); err != nil {
+		return "", err
+	}
+	for i, b := range buf {
+		buf[i] = charset[int(b)%len(charset)]
+	}
+	return string(buf), nil
+}
+
+// psqlDBExec führt SQL in der angegebenen Datenbank als postgres-Superuser aus.
+func psqlDBExec(db, sql string) error {
+	_, err := psqlDBRun(db, []string{"-v", "ON_ERROR_STOP=1", "-c", sql})
+	return err
+}
+
+// psqlDBExecStdin führt SQL über stdin (`-f -`) aus statt `-c`, damit
+// Secrets im SQL nicht in der Prozess-Argv / PG-Statement-Logs erscheinen.
+func psqlDBExecStdin(db, sql string) error {
+	cmd := buildPsqlCmd([]string{"-d", db, "-v", "ON_ERROR_STOP=1", "-f", "-"})
+	cmd.Stdin = strings.NewReader(sql)
+	if out, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("%w: %s", err, strings.TrimSpace(string(out)))
+	}
+	return nil
+}
+
+// psqlDBRun führt psql-Kommandos gegen eine bestimmte Datenbank aus.
+func psqlDBRun(db string, args []string) ([]byte, error) {
+	baseArgs := []string{"-d", db}
+	return psqlRun(append(baseArgs, args...))
+}

cmd/edgeguard-ctl/main.go

@@ -1,7 +1,6 @@
 // Command edgeguard-ctl is the admin CLI for setup, migrations and
-// (later) cluster ops. v1 wires migrate + initdb so postinst can
-// initialise a fresh node; cluster-* and promote remain stubs until
-// Phase 3.
+// cluster ops. v1.2 implements PG streaming replication setup,
+// VIP/Keepalived config and manual failover (promote).
 package main
 
 import (
@@ -11,7 +10,7 @@ import (
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/setup"
 )
 
-var version = "1.1.162"
+var version = "1.2.15"
 
 const usage = `edgeguard-ctl — EdgeGuard CLI
 
@@ -25,23 +24,25 @@ Commands:
   migrate check                Validate embedded migrations (no DB connect)
   migrate dump [dir]           Write embedded SQL files to dir (default: ./migrations)
   initdb                       Create PostgreSQL role + database (idempotent)
-  render-config                Regenerate haproxy / nftables configs from PG (--no-reload, --only=)
+  render-config                Regenerate all configs from PG (--no-reload, --only=svc)
+                               Services: haproxy nftables squid wireguard unbound chrony keepalived
   wg-import [--path <dir>] [iface…]
                                Import /etc/wireguard/*.conf files into the DB.
-                               Without iface arguments: imports all .conf files.
-                               With iface args: imports only the named interfaces.
   reset-password               Generate a one-time token for the /reset-password UI flow
   cluster-join <primary> --token <…>
-                               Provision Cluster-TLS material on this node by
-                               exchanging the join-token at the primary's
-                               /api/v1/cluster/issue-cert endpoint. Writes
-                               ca.crt + peer.{crt,key} into /var/lib/edgeguard/
-                               cluster-tls/. PG-Basebackup + KeyDB replica
-                               setup remain manual until Phase 3.5.
-  cluster-renew-self           Re-issue this node's peer.{crt,key} using the
-                               local cluster CA (founder/single-node only).
-                               1-year validity. Restart edgeguard-api after.
-  promote                      Promote this node's PG to primary (Phase 3, not yet implemented)
+                               Provision Cluster-TLS material; writes ca.crt + peer.{crt,key}
+  cluster-init-replication     Richtet PG Logical Replication auf dem Primary ein.
+                               Erstellt edgeguard_replicator-Rolle, setzt wal_level=logical,
+                               erstellt PUBLICATION edgeguard_shared (alle geteilten Tabellen).
+                               Auf dem Primary ausführen bevor der Secondary joined.
+  cluster-setup-standby <ip>   Richtet diesen Node als Logical-Replication-Subscriber ein.
+                               Erstellt SUBSCRIPTION gegen den Primary (Initialkopiierung
+                               aller geteilten Tabellen). Node-eigene Daten (Interfaces,
+                               IPs, Routen, VIP-Settings) bleiben unangetastet.
+                               Voraussetzung: cluster-join + cluster-init-replication.
+  cluster-renew-self           Re-issue this node's peer.{crt,key} using the local cluster CA.
+  promote                      Promote diesen PG-Standby zum Primary (manueller Failover).
+                               Kein Auto-Promote — Split-Brain-Schutz durch manuelle Entscheidung.
   dump-config                  Print effective config (Phase 3, not yet implemented)
 `
 
@@ -69,7 +70,13 @@ func main() {
 		os.Exit(cmdClusterJoin(os.Args[2:]))
 	case "cluster-renew-self":
 		os.Exit(cmdClusterRenewSelf(os.Args[2:]))
-	case "cluster-leave", "promote", "dump-config":
+	case "cluster-init-replication":
+		os.Exit(cmdClusterInitReplication(os.Args[2:]))
+	case "cluster-setup-standby":
+		os.Exit(cmdClusterSetupStandby(os.Args[2:]))
+	case "promote":
+		os.Exit(cmdPromote(os.Args[2:]))
+	case "cluster-leave", "dump-config":
 		fmt.Fprintf(os.Stderr, "edgeguard-ctl: %q is a Phase-3 stub — not yet implemented\n", os.Args[1])
 		os.Exit(1)
 	default:

cmd/edgeguard-ctl/promote.go

@@ -0,0 +1,160 @@
+package main
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/cluster"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/keepalived"
+)
+
+// cmdPromote promotes this node's PostgreSQL instance from Hot-Standby
+// to Primary. Manual failover — keine automatische Promotion, um Split-Brain
+// in 2-Node-Clustern ohne externen Quorum zu verhindern.
+//
+// Ablauf:
+//  1. Prüfen ob standby.signal vorhanden (wir sind wirklich Standby)
+//  2. pg_ctlcluster promote → PG wird Primary
+//  3. Warten bis pg_is_in_recovery() = false
+//  4. ha_nodes.pg_role auf 'primary' setzen
+//  5. KeyDB cluster:pg-primary-url auf lokal setzen
+//  6. keepalived.conf neu rendern (Primary bekommt Priorität 200)
+//  7. keepalived reload
+func cmdPromote(args []string) int {
+	pg, err := detectPGConfig()
+	if err != nil {
+		fmt.Fprintln(os.Stderr, "promote: PG-Erkennung:", err)
+		return 1
+	}
+
+	// 1. Standby-Signal prüfen
+	signalPath := filepath.Join(pg.DataDir, "standby.signal")
+	if _, err := os.Stat(signalPath); os.IsNotExist(err) {
+		fmt.Fprintf(os.Stderr,
+			"promote: %s nicht gefunden — diese Node ist kein PG-Standby oder wurde bereits promoted.\n",
+			signalPath)
+		return 1
+	}
+
+	fmt.Printf("→ Promoting PostgreSQL %s/%s zu Primary...\n", pg.Version, pg.Cluster)
+	if out, err := exec.Command("pg_ctlcluster", pg.Version, pg.Cluster, "promote").
+		CombinedOutput(); err != nil {
+		fmt.Fprintf(os.Stderr, "promote: pg_ctlcluster promote: %v\n%s\n", err, out)
+		return 1
+	}
+	fmt.Println("✓ pg_ctlcluster promote gesendet")
+
+	// 2. Warten bis PG wirklich Primary ist (pg_is_in_recovery = false)
+	fmt.Print("→ Warte auf PG Primary-Mode")
+	deadline := time.Now().Add(60 * time.Second)
+	for time.Now().Before(deadline) {
+		out, err := psqlRun([]string{"-tA", "-c", "SELECT pg_is_in_recovery();"})
+		if err == nil && strings.TrimSpace(string(out)) == "f" {
+			break
+		}
+		fmt.Print(".")
+		time.Sleep(2 * time.Second)
+	}
+	fmt.Println()
+	// Nochmal prüfen
+	out, err := psqlRun([]string{"-tA", "-c", "SELECT pg_is_in_recovery();"})
+	if err != nil || strings.TrimSpace(string(out)) != "f" {
+		fmt.Fprintln(os.Stderr, "promote: PG ist nach 60s noch in recovery — prüfe PG-Logs")
+		return 1
+	}
+	fmt.Println("✓ PostgreSQL ist jetzt Primary")
+
+	// 3. ha_nodes.pg_role + role aktualisieren
+	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
+	defer cancel()
+
+	pool, err := database.Open(ctx, database.ConnStringFromEnv())
+	if err != nil {
+		fmt.Fprintln(os.Stderr, "promote: db connect:", err)
+		fmt.Println("  → ha_nodes manuell updaten: UPDATE ha_nodes SET pg_role='primary', role='primary' WHERE id='<local-id>';")
+	} else {
+		defer pool.Close()
+		localID, err := loadLocalID()
+		if err != nil {
+			fmt.Fprintln(os.Stderr, "promote: local node ID:", err)
+		} else {
+			_, err = pool.Exec(ctx, `UPDATE ha_nodes SET pg_role='primary', role='primary', status='online', updated_at=NOW() WHERE id=$1`, localID)
+			if err != nil {
+				fmt.Fprintln(os.Stderr, "promote: update ha_nodes:", err)
+			} else {
+				fmt.Println("✓ ha_nodes.pg_role = 'primary' gesetzt")
+			}
+		}
+	}
+
+	// 4. KeyDB cluster:pg-primary-url updaten
+	if err := updateKeyDBPrimaryURL(); err != nil {
+		fmt.Fprintf(os.Stderr, "promote: KeyDB update: %v\n", err)
+		fmt.Println("  → Manuell: redis-cli SET cluster:pg-primary-url 'postgres://edgeguard@/edgeguard'")
+	} else {
+		fmt.Println("✓ KeyDB cluster:pg-primary-url aktualisiert")
+	}
+
+	// 5. Keepalived.conf neu rendern (Primary = Priorität 200)
+	if pool != nil {
+		localID, _ := loadLocalID()
+		kg := keepalived.New(pool, localID)
+		renderCtx, renderCancel := context.WithTimeout(context.Background(), 10*time.Second)
+		defer renderCancel()
+		if err := kg.Render(renderCtx); err != nil {
+			fmt.Fprintf(os.Stderr, "promote: keepalived render: %v\n", err)
+			fmt.Println("  → Manuell: edgeguard-ctl render-config --only=keepalived")
+		} else {
+			fmt.Println("✓ keepalived.conf neu gerendert (Priority 200)")
+		}
+	}
+
+	fmt.Println()
+	fmt.Println("✓ Promotion abgeschlossen. Diese Node ist jetzt der primäre EdgeGuard-Knoten.")
+	fmt.Println()
+	fmt.Println("Empfohlene Nachschritte:")
+	fmt.Println("  1) sudo systemctl restart edgeguard-api  (falls noch nicht laufend)")
+	fmt.Println("  2) Alte Primary-Node nach Recovery als neuen Standby einrichten:")
+	fmt.Println("     edgeguard-ctl cluster-setup-standby <diese-node-ip>")
+	return 0
+}
+
+// loadLocalID liest die Node-ID aus /var/lib/edgeguard/node.conf.
+func loadLocalID() (string, error) {
+	c, err := cluster.LoadLocalConfig("")
+	if err != nil {
+		return "", err
+	}
+	if c.NodeID == "" {
+		return "", fmt.Errorf("NODE_ID in node.conf ist leer")
+	}
+	return c.NodeID, nil
+}
+
+// updateKeyDBPrimaryURL schreibt den lokalen PG-DSN als cluster:pg-primary-url
+// in KeyDB, damit alle Nodes im Cluster Writes an diese Node schicken.
+func updateKeyDBPrimaryURL() error {
+	// edgeguard-api nutzt Unix-Socket-Auth, der DSN ist immer lokal.
+	const localDSN = "postgres://edgeguard@/edgeguard?host=/var/run/postgresql"
+	out, err := exec.Command("redis-cli",
+		"-s", "/var/run/keydb/keydb.sock",
+		"SET", "cluster:pg-primary-url", localDSN,
+	).CombinedOutput()
+	if err != nil {
+		// Fallback: Standard-Port
+		out2, err2 := exec.Command("redis-cli",
+			"-p", "6379",
+			"SET", "cluster:pg-primary-url", localDSN,
+		).CombinedOutput()
+		if err2 != nil {
+			return fmt.Errorf("%v: %s / %v: %s", err, out, err2, out2)
+		}
+	}
+	return nil
+}

cmd/edgeguard-ctl/render.go

@@ -8,10 +8,14 @@ import (
 	"time"
 
 	"git.netcell-it.de/projekte/edgeguard-native/internal/chrony"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/freeradius"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/kea"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/firewall"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/haproxy"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/cluster"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/keepalived"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/configorch"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/secrets"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/squid"
@@ -59,12 +63,29 @@ func cmdRenderConfig(args []string) int {
 	wg := wireguard.New(pool, secrets.New(""))
 	ub := unbound.New(pool)
 	cn := chrony.New(pool)
+	ke := kea.New(pool)
+	fr := freeradius.New(pool, secrets.New(""))
 	if skipReload {
 		hap.SkipReload = true
 		fw.SkipReload = true
+		sq.SkipReload = true
+		wg.SkipReload = true
+		ub.SkipReload = true
+		cn.SkipReload = true
+		ke.SkipReload = true
+		fr.SkipReload = true
 	}
 
-	gens := []configgen.Generator{hap, fw, sq, wg, ub, cn}
+	// keepalived: Node-ID aus node.conf für Prioritäts-Berechnung
+	var ka configgen.Generator
+	if lc, err := cluster.LoadLocalConfig(""); err == nil && lc.NodeID != "" {
+		ka = keepalived.New(pool, lc.NodeID)
+	}
+
+	gens := []configgen.Generator{hap, fw, sq, wg, ub, cn, ke, fr}
+	if ka != nil {
+		gens = append(gens, ka)
+	}
 
 	results, runErr := configorch.Run(ctx, gens, only)
 	fmt.Print(configorch.Summarise(results))

cmd/edgeguard-scheduler/main.go

@@ -41,7 +41,7 @@ import (
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/tlscerts"
 )
 
-var version = "1.1.162"
+var version = "1.2.35"
 
 const (
 	// renewTickInterval — how often we re-evaluate expiring certs.

cmd/edgeguard-waf/main.go

@@ -0,0 +1,107 @@
+// Command edgeguard-waf is the per-domain WAF SPOE agent for EdgeGuard.
+// HAProxy connects to it via the SPOE protocol (127.0.0.1:9000).
+// It loads per-domain WAF configs from PostgreSQL and uses Coraza v3
+// with the OWASP Core Rule Set to inspect HTTP requests.
+package main
+
+import (
+	"context"
+	"log/slog"
+	"os"
+	"os/signal"
+	"syscall"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/waf"
+	intwaf "git.netcell-it.de/projekte/edgeguard-native/internal/waf"
+)
+
+func main() {
+	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
+	defer stop()
+
+	dsn := database.ConnStringFromEnv()
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		slog.Error("waf: db connect", "error", err)
+		os.Exit(1)
+	}
+	defer pool.Close()
+
+	if err := database.Migrate(ctx, ""); err != nil {
+		slog.Error("waf: migrate", "error", err)
+		os.Exit(1)
+	}
+
+	repo := waf.New(pool)
+
+	crsDir := os.Getenv("EDGEGUARD_WAF_CRS_DIR")
+	if crsDir == "" {
+		crsDir = intwaf.DefaultCRSDir
+	}
+	spoeAddr := os.Getenv("EDGEGUARD_WAF_ADDR")
+	if spoeAddr == "" {
+		spoeAddr = intwaf.DefaultSPOEAddr
+	}
+
+	mgr := intwaf.NewManager(crsDir)
+
+	// Initial load.
+	if err := reload(ctx, repo, mgr); err != nil {
+		slog.Error("waf: initial load", "error", err)
+		os.Exit(1)
+	}
+
+	// Periodic config refresh every 30 seconds.
+	go func() {
+		t := time.NewTicker(30 * time.Second)
+		defer t.Stop()
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case <-t.C:
+				if err := reload(ctx, repo, mgr); err != nil {
+					slog.Warn("waf: reload", "error", err)
+				}
+			}
+		}
+	}()
+
+	alertWriter := intwaf.NewAlertWriter(pool, 2048)
+
+	agent := intwaf.SPOEAgent{
+		Manager:     mgr,
+		AlertWriter: alertWriter,
+		Addr:        spoeAddr,
+	}
+
+	slog.Info("waf: SPOE agent starting", "addr", spoeAddr, "crs", crsDir)
+	if err := agent.ListenAndServe(ctx); err != nil && ctx.Err() == nil {
+		slog.Error("waf: SPOE agent stopped", "error", err)
+		os.Exit(1)
+	}
+	// Graceful shutdown (ctx cancelled): gepufferte Alerts flushen.
+	alertWriter.Close()
+}
+
+// reload fetches all domain+waf_config pairs from DB and rebuilds engines.
+func reload(ctx context.Context, repo *waf.Repo, mgr *intwaf.Manager) error {
+	configs, err := repo.ListAllWithDomain(ctx)
+	if err != nil {
+		return err
+	}
+	domains := make([]intwaf.DomainConfig, 0, len(configs))
+	for _, c := range configs {
+		domains = append(domains, intwaf.DomainConfig{
+			Hostname: c.Hostname,
+			Config:   c.Config,
+		})
+	}
+	return mgr.Reload(domains)
+}
+
+// Ensure models package is used (imported transitively via services/waf).
+var _ = models.WafConfig{}

deploy/keepalived/keepalived.conf.tpl

@@ -0,0 +1,40 @@
+global_defs {
+    router_id {{ .RouterID }}
+    script_user root
+    enable_script_security
+    vrrp_garp_interval 0
+    vrrp_gna_interval 0
+}
+
+vrrp_script chk_edgeguard {
+    script "/usr/lib/edgeguard/keepalived-check.sh"
+    interval 2
+    weight -50
+    fall 3
+    rise 2
+}
+
+vrrp_instance VI_1 {
+    state {{ .State }}
+    interface {{ .Interface }}
+    virtual_router_id {{ .RouterID }}
+    priority {{ .Priority }}
+    advert_int 1
+{{ if .SrcIP }}    unicast_src_ip {{ .SrcIP }}
+    unicast_peer {
+        {{ .PeerIP }}
+    }
+{{ end }}    authentication {
+        auth_type PASS
+        auth_pass {{ .AuthPass }}
+    }
+    virtual_ipaddress {
+        {{ .VIP }}
+    }
+    track_script {
+        chk_edgeguard
+    }
+    notify_master  "/usr/lib/edgeguard/keepalived-master.sh"
+    notify_backup  "/usr/lib/edgeguard/keepalived-backup.sh"
+    notify_fault   "/usr/lib/edgeguard/keepalived-backup.sh"
+}

deploy/systemd/edgeguard-api.service

@@ -41,7 +41,7 @@ SystemCallFilter=@system-service
 # direkt in den distro-Conf-Dir (chrony+unbound) bzw. legen Symlinks
 # nach /etc/edgeguard/wireguard (wg). Ohne diese Pfade scheitern alle
 # UI-Mutationen an DNS/NTP/WireGuard-Settings still mit EROFS.
-ReadWritePaths=/etc/edgeguard /var/lib/edgeguard /var/log/edgeguard /var/backups/edgeguard /var/lib/apt /var/cache/apt /etc/apt/apt.conf.d /etc/chrony/conf.d /etc/unbound/unbound.conf.d /etc/wireguard
+ReadWritePaths=/etc/edgeguard /var/lib/edgeguard /var/log/edgeguard /var/backups/edgeguard /var/lib/apt /var/cache/apt /etc/apt/apt.conf.d /etc/chrony/conf.d /etc/unbound/unbound.conf.d /etc/wireguard /var/lib/crowdsec
 
 [Install]
 WantedBy=multi-user.target

deploy/systemd/edgeguard-waf.service

@@ -0,0 +1,32 @@
+[Unit]
+Description=EdgeGuard WAF SPOE Agent (Coraza/OWASP CRS)
+Documentation=https://git.netcell-it.de/projekte/edgeguard-native
+After=network-online.target postgresql.service edgeguard-api.service
+Wants=network-online.target
+Requires=postgresql.service
+
+[Service]
+Type=simple
+User=edgeguard
+Group=edgeguard
+ExecStart=/usr/bin/edgeguard-waf
+Restart=on-failure
+RestartSec=5
+
+# Hardening — WAF agent only needs DB access and one TCP listen socket.
+NoNewPrivileges=true
+ProtectSystem=strict
+ProtectHome=true
+ProtectKernelTunables=true
+ProtectKernelModules=true
+ProtectControlGroups=true
+PrivateTmp=true
+PrivateDevices=true
+RestrictAddressFamilies=AF_UNIX AF_INET AF_INET6
+SystemCallFilter=@system-service
+# CRS rules are read from /usr/share/edgeguard/waf/crs/ (read-only, OK).
+# Alerts/logs are written to /var/log/edgeguard/.
+ReadWritePaths=/var/log/edgeguard
+
+[Install]
+WantedBy=multi-user.target

go.mod

@@ -3,23 +3,32 @@ module git.netcell-it.de/projekte/edgeguard-native
 go 1.26.0
 
 require (
+	github.com/corazawaf/coraza/v3 v3.7.0
+	github.com/coreos/go-oidc/v3 v3.18.0
+	github.com/dropmorepackets/haproxy-go v0.0.8
 	github.com/fsnotify/fsnotify v1.10.1
 	github.com/gin-gonic/gin v1.10.0
 	github.com/go-acme/lego/v4 v4.35.2
 	github.com/gorilla/websocket v1.5.3
 	github.com/jackc/pgx/v5 v5.9.2
+	github.com/minio/minio-go/v7 v7.1.0
+	github.com/pkg/sftp v1.13.10
+	github.com/pquerna/otp v1.5.0
 	github.com/pressly/goose/v3 v3.27.1
 	github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
 	golang.org/x/crypto v0.51.0
+	golang.org/x/oauth2 v0.36.0
 )
 
 require (
+	github.com/boombuler/barcode v1.0.1 // indirect
 	github.com/bytedance/sonic v1.11.6 // indirect
 	github.com/bytedance/sonic/loader v0.1.1 // indirect
 	github.com/cenkalti/backoff/v5 v5.0.3 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/cloudwego/base64x v0.1.4 // indirect
 	github.com/cloudwego/iasm v0.2.0 // indirect
+	github.com/corazawaf/libinjection-go v0.3.2 // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.13 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
@@ -28,34 +37,43 @@ require (
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-playground/validator/v10 v10.23.0 // indirect
-	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/goccy/go-json v0.10.5 // indirect
+	github.com/goccy/go-yaml v1.19.2 // indirect
 	github.com/google/uuid v1.6.0 // indirect
+	github.com/gotnospirit/makeplural v0.0.0-20180622080156-a5f48d94d976 // indirect
+	github.com/gotnospirit/messageformat v0.0.0-20221001023931-dfe49f1eb092 // indirect
 	github.com/jackc/pgpassfile v1.0.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
 	github.com/jackc/puddle/v2 v2.2.2 // indirect
 	github.com/json-iterator/go v1.1.13-0.20220915233716-71ac16282d12 // indirect
+	github.com/kaptinlin/go-i18n v0.1.4 // indirect
+	github.com/kaptinlin/jsonschema v0.4.6 // indirect
 	github.com/klauspost/compress v1.18.5 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.11 // indirect
 	github.com/klauspost/crc32 v1.3.0 // indirect
 	github.com/kr/fs v0.1.0 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
+	github.com/magefile/mage v1.17.0 // indirect
 	github.com/mattn/go-isatty v0.0.21 // indirect
 	github.com/mfridman/interpolate v0.0.2 // indirect
 	github.com/miekg/dns v1.1.72 // indirect
 	github.com/minio/crc64nvme v1.1.1 // indirect
 	github.com/minio/md5-simd v1.1.2 // indirect
-	github.com/minio/minio-go/v7 v7.1.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee // indirect
-	github.com/pelletier/go-toml/v2 v2.2.2 // indirect
+	github.com/pelletier/go-toml/v2 v2.2.4 // indirect
+	github.com/petar-dambovaliev/aho-corasick v0.0.0-20250424160509-463d218d4745 // indirect
 	github.com/philhofer/fwd v1.2.0 // indirect
-	github.com/pkg/sftp v1.13.10 // indirect
 	github.com/rs/xid v1.6.0 // indirect
 	github.com/sethvargo/go-retry v0.3.0 // indirect
+	github.com/tidwall/gjson v1.18.0 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.1 // indirect
 	github.com/tinylib/msgp v1.6.1 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
+	github.com/valllabh/ocsf-schema-golang v1.0.3 // indirect
 	github.com/zeebo/xxh3 v1.1.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
@@ -68,4 +86,5 @@ require (
 	golang.org/x/tools v0.44.0 // indirect
 	google.golang.org/protobuf v1.36.11 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
+	rsc.io/binaryregexp v0.2.0 // indirect
 )

go.sum

@@ -1,3 +1,6 @@
+github.com/boombuler/barcode v1.0.1-0.20190219062509-6c824513bacc/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
+github.com/boombuler/barcode v1.0.1 h1:NDBbPmhS+EqABEs5Kg3n/5ZNjy73Pz7SIV+KCeqyXcs=
+github.com/boombuler/barcode v1.0.1/go.mod h1:paBWMcWSl3LHKBqUq+rly7CNSldXjb2rDl3JlRe0mD8=
 github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
 github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
 github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
@@ -10,13 +13,25 @@ github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/
 github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
 github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
 github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
+github.com/corazawaf/coraza-coreruleset v0.0.0-20240226094324-415b1017abdc h1:OlJhrgI3I+FLUCTI3JJW8MoqyM78WbqJjecqMnqG+wc=
+github.com/corazawaf/coraza-coreruleset v0.0.0-20240226094324-415b1017abdc/go.mod h1:7rsocqNDkTCira5T0M7buoKR2ehh7YZiPkzxRuAgvVU=
+github.com/corazawaf/coraza/v3 v3.7.0 h1:LIQqu1r+l6e/U/gyiZeykWaNNBY1TzRLz+aaI+QYEEM=
+github.com/corazawaf/coraza/v3 v3.7.0/go.mod h1:dOSt5evqC7EstouEv6ghhui01+oVUwp9X1vybWwqTlo=
+github.com/corazawaf/libinjection-go v0.3.2 h1:9rrKt0lpg4WvUXt+lwS06GywfqRXXsa/7JcOw5cQLwI=
+github.com/corazawaf/libinjection-go v0.3.2/go.mod h1:Ik/+w3UmTWH9yn366RgS9D95K3y7Atb5m/H/gXzzPCk=
+github.com/coreos/go-oidc/v3 v3.18.0 h1:V9orjXynvu5wiC9SemFTWnG4F45v403aIcjWo0d41+A=
+github.com/coreos/go-oidc/v3 v3.18.0/go.mod h1:DYCf24+ncYi+XkIH97GY1+dqoRlbaSI26KVTCI9SrY4=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dropmorepackets/haproxy-go v0.0.8 h1:kS2Wa8+ZDcnJdRSTiuBsaPun5hpdUPIuLQ+Drp9ZxYs=
+github.com/dropmorepackets/haproxy-go v0.0.8/go.mod h1:4a2AmmVjvg2zPNdizGZrMN8ZSUpj90U43VlcdbOIBnU=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
+github.com/foxcpp/go-mockdns v1.1.0 h1:jI0rD8M0wuYAxL7r/ynTrCQQq0BVqfB99Vgk7DlmewI=
+github.com/foxcpp/go-mockdns v1.1.0/go.mod h1:IhLeSFGed3mJIAXPH2aiRQB+kqz7oqu8ld2qVbOu7Wk=
 github.com/fsnotify/fsnotify v1.10.1 h1:b0/UzAf9yR5rhf3RPm9gf3ehBPpf0oZKIjtpKrx59Ho=
 github.com/fsnotify/fsnotify v1.10.1/go.mod h1:TLheqan6HD6GBK6PrDWyDPBaEV8LspOxvPSjC+bVfgo=
 github.com/gabriel-vasile/mimetype v1.4.13 h1:46nXokslUBsAJE/wMsp5gtO500a4F3Nkz9Ufpk2AcUM=
@@ -39,8 +54,10 @@ github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJn
 github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
 github.com/go-playground/validator/v10 v10.23.0 h1:/PwmTwZhS0dPkav3cdK9kV1FsAmrL8sThn8IHr/sO+o=
 github.com/go-playground/validator/v10 v10.23.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
-github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
-github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/goccy/go-json v0.10.5 h1:Fq85nIqj+gXn/S5ahsiTlK3TmC85qgirsdTP/+DeaC4=
+github.com/goccy/go-json v0.10.5/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M=
+github.com/goccy/go-yaml v1.19.2 h1:PmFC1S6h8ljIz6gMRBopkjP1TVT7xuwrButHID66PoM=
+github.com/goccy/go-yaml v1.19.2/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
@@ -48,6 +65,10 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
 github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
+github.com/gotnospirit/makeplural v0.0.0-20180622080156-a5f48d94d976 h1:b70jEaX2iaJSPZULSUxKtm73LBfsCrMsIlYCUgNGSIs=
+github.com/gotnospirit/makeplural v0.0.0-20180622080156-a5f48d94d976/go.mod h1:ZGQeOwybjD8lkCjIyJfqR5LD2wMVHJ31d6GdPxoTsWY=
+github.com/gotnospirit/messageformat v0.0.0-20221001023931-dfe49f1eb092 h1:c7gcNWTSr1gtLp6PyYi3wzvFCEcHJ4YRobDgqmIgf7Q=
+github.com/gotnospirit/messageformat v0.0.0-20221001023931-dfe49f1eb092/go.mod h1:ZZAN4fkkful3l1lpJwF8JbW41ZiG9TwJ2ZlqzQovBNU=
 github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
 github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
 github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 h1:iCEnooe7UlwOQYpKFhBabPMi4aNAfoODPEFNiAnClxo=
@@ -56,14 +77,18 @@ github.com/jackc/pgx/v5 v5.9.2 h1:3ZhOzMWnR4yJ+RW1XImIPsD1aNSz4T4fyP7zlQb56hw=
 github.com/jackc/pgx/v5 v5.9.2/go.mod h1:mal1tBGAFfLHvZzaYh77YS/eC6IX9OWbRV1QIIM0Jn4=
 github.com/jackc/puddle/v2 v2.2.2 h1:PR8nw+E/1w0GLuRFSmiioY6UooMp6KJv0/61nB7icHo=
 github.com/jackc/puddle/v2 v2.2.2/go.mod h1:vriiEXHvEE654aYKXXjOvZM39qJ0q+azkZFrfEOc3H4=
+github.com/jcchavezs/mergefs v0.1.1 h1:D45R17m6dHnSVZefnhynoeZvcK2Uw0oTrRfoUOQ0S5Y=
+github.com/jcchavezs/mergefs v0.1.1/go.mod h1:eRLTrsA+vFwQZ48hj8p8gki/5v9C2bFtHH5Mnn4bcGk=
 github.com/json-iterator/go v1.1.13-0.20220915233716-71ac16282d12 h1:9Nu54bhS/H/Kgo2/7xNSUuC5G28VR8ljfrLKU2G4IjU=
 github.com/json-iterator/go v1.1.13-0.20220915233716-71ac16282d12/go.mod h1:TBzl5BIHNXfS9+C35ZyJaklL7mLDbgUkcgXzSLa8Tk0=
+github.com/kaptinlin/go-i18n v0.1.4 h1:wCiwAn1LOcvymvWIVAM4m5dUAMiHunTdEubLDk4hTGs=
+github.com/kaptinlin/go-i18n v0.1.4/go.mod h1:g1fn1GvTgT4CiLE8/fFE1hboHWJ6erivrDpiDtCcFKg=
+github.com/kaptinlin/jsonschema v0.4.6 h1:vOSFg5tjmfkOdKg+D6Oo4fVOM/pActWu/ntkPsI1T64=
+github.com/kaptinlin/jsonschema v0.4.6/go.mod h1:1DUd7r5SdyB2ZnMtyB7uLv64dE3zTFTiYytDCd+AEL0=
 github.com/klauspost/compress v1.18.5 h1:/h1gH5Ce+VWNLSWqPzOVn6XBO+vJbCNGvjoaGBFW2IE=
 github.com/klauspost/compress v1.18.5/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
 github.com/klauspost/cpuid/v2 v2.0.1/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
-github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuVLDM=
-github.com/klauspost/cpuid/v2 v2.2.7/go.mod h1:Lcz8mBdAVJIBVzewtcLocK12l3Y+JytZYpaMropDUws=
 github.com/klauspost/cpuid/v2 v2.2.11 h1:0OwqZRYI2rFrjS4kvkDnqJkKHdHaRnCm68/DY4OxRzU=
 github.com/klauspost/cpuid/v2 v2.2.11/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
 github.com/klauspost/crc32 v1.3.0 h1:sSmTt3gUt81RP655XGZPElI0PelVTZ6YwCRnPSupoFM=
@@ -77,6 +102,8 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ=
 github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI=
+github.com/magefile/mage v1.17.0 h1:dS4tkq997Ism03akafC8509iqDjeE7TNTexI25Y7sXM=
+github.com/magefile/mage v1.17.0/go.mod h1:Yj51kqllmsgFpvvSzgrZPK9WtluG3kUhFaBUVLo4feA=
 github.com/mattn/go-isatty v0.0.21 h1:xYae+lCNBP7QuW4PUnNG61ffM4hVIfm+zUzDuSzYLGs=
 github.com/mattn/go-isatty v0.0.21/go.mod h1:ZXfXG4SQHsB/w3ZeOYbR0PrPwLy+n6xiMrJlRFqopa4=
 github.com/mfridman/interpolate v0.0.2 h1:pnuTK7MQIxxFz1Gr+rjSIx9u7qVjf5VOoM/u6BbAxPY=
@@ -97,8 +124,10 @@ github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee h1:W5t00kpgFd
 github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w=
 github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls=
-github.com/pelletier/go-toml/v2 v2.2.2 h1:aYUidT7k73Pcl9nb2gScu7NSrKCSHIDE89b3+6Wq+LM=
-github.com/pelletier/go-toml/v2 v2.2.2/go.mod h1:1t835xjRzz80PqgE6HHgN2JOsmgYu/h4qDAS4n929Rs=
+github.com/pelletier/go-toml/v2 v2.2.4 h1:mye9XuhQ6gvn5h28+VilKrrPoQVanw5PMw/TB0t5Ec4=
+github.com/pelletier/go-toml/v2 v2.2.4/go.mod h1:2gIqNv+qfxSVS7cM2xJQKtLSTLUE9V8t9Stt+h56mCY=
+github.com/petar-dambovaliev/aho-corasick v0.0.0-20250424160509-463d218d4745 h1:Vpr4VgAizEgEZsaMohpw6JYDP+i9Of9dmdY4ufNP6HI=
+github.com/petar-dambovaliev/aho-corasick v0.0.0-20250424160509-463d218d4745/go.mod h1:EHPiTAKtiFmrMldLUNswFwfZ2eJIYBHktdaUTZxYWRw=
 github.com/philhofer/fwd v1.2.0 h1:e6DnBTl7vGY+Gz322/ASL4Gyp1FspeMvx1RNDoToZuM=
 github.com/philhofer/fwd v1.2.0/go.mod h1:RqIHx9QI14HlwKwm98g9Re5prTQ6LdeRQn+gXJFxsJM=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
@@ -107,6 +136,8 @@ github.com/pkg/sftp v1.13.10/go.mod h1:bJ1a7uDhrX/4OII+agvy28lzRvQrmIQuaHrcI1Hbe
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pquerna/otp v1.5.0 h1:NMMR+WrmaqXU4EzdGJEE1aUUI0AMRzsp96fFFWNPwxs=
+github.com/pquerna/otp v1.5.0/go.mod h1:dkJfzwRKNiegxyNb54X/3fLwhCynbMspSyWKnvi1AEg=
 github.com/pressly/goose/v3 v3.27.1 h1:6uEvcprBybDmW4hcz3gYujhARhye+GoWKhEWyzD5sh4=
 github.com/pressly/goose/v3 v3.27.1/go.mod h1:maruOxsPnIG2yHHyo8UqKWXYKFcH7Q76csUV7+7KYoM=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
@@ -122,22 +153,30 @@ github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e/go.mod h1:XV66xRDq
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
-github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
-github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+github.com/tidwall/gjson v1.18.0 h1:FIDeeyB800efLX89e5a8Y0BNH+LOngJyGrIWxG2FKQY=
+github.com/tidwall/gjson v1.18.0/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
+github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
+github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4=
+github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
 github.com/tinylib/msgp v1.6.1 h1:ESRv8eL3u+DNHUoSAAQRE50Hm162zqAnBoGv9PzScPY=
 github.com/tinylib/msgp v1.6.1/go.mod h1:RSp0LW9oSxFut3KzESt5Voq4GVWyS+PSulT77roAqEA=
 github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go/codec v1.2.12 h1:9LC83zGrHhuUA9l16C9AHXAqEV/2wBQ4nkvumAE65EE=
 github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+github.com/valllabh/ocsf-schema-golang v1.0.3 h1:eR8k/3jP/OOqB8LRCtdJ4U+vlgd/gk5y3KMXoodrsrw=
+github.com/valllabh/ocsf-schema-golang v1.0.3/go.mod h1:sZ3as9xqm1SSK5feFWIR2CuGeGRhsM7TR1MbpBctzPk=
+github.com/zeebo/assert v1.3.0 h1:g7C04CbJuIDKNPFHmsk4hwZDO5O+kntRxzaUoNXj+IQ=
+github.com/zeebo/assert v1.3.0/go.mod h1:Pq9JiuJQpG8JLJdtkwrJESF0Foym2/D9XMU5ciN/wJ0=
 github.com/zeebo/xxh3 v1.1.0 h1:s7DLGDK45Dyfg7++yxI0khrfwq9661w9EN78eP/UZVs=
 github.com/zeebo/xxh3 v1.1.0/go.mod h1:IisAie1LELR4xhVinxWS5+zf1lA4p0MW4T+w+W07F5s=
 go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
@@ -153,11 +192,14 @@ golang.org/x/mod v0.35.0 h1:Ww1D637e6Pg+Zb2KrWfHQUnH2dQRLBQyAtpr/haaJeM=
 golang.org/x/mod v0.35.0/go.mod h1:+GwiRhIInF8wPm+4AoT6L0FA1QWAad3OMdTRx4tFYlU=
 golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
 golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
+golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=
+golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q=
 golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
 golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
-golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.44.0 h1:ildZl3J4uzeKP07r2F++Op7E9B29JRUy+a27EibtBTQ=
 golang.org/x/sys v0.44.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+golang.org/x/term v0.43.0 h1:S4RLU2sB31O/NCl+zFN9Aru9A/Cq2aqKpTZJ6B+DwT4=
+golang.org/x/term v0.43.0/go.mod h1:lrhlHNdQJHO+1qVYiHfFKVuVioJIheAc3fBSMFYEIsk=
 golang.org/x/text v0.37.0 h1:Cqjiwd9eSg8e0QAkyCaQTNHFIIzWtidPahFWR83rTrc=
 golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
 golang.org/x/tools v0.44.0 h1:UP4ajHPIcuMjT1GqzDWRlalUEoY+uzoZKnhOjbIPD2c=
@@ -179,4 +221,6 @@ modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw
 modernc.org/sqlite v1.49.1 h1:dYGHTKcX1sJ+EQDnUzvz4TJ5GbuvhNJa8Fg6ElGx73U=
 modernc.org/sqlite v1.49.1/go.mod h1:m0w8xhwYUVY3H6pSDwc3gkJ/irZT/0YEXwBlhaxQEew=
 nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
+rsc.io/binaryregexp v0.2.0 h1:HfqmD5MEmC0zvwBuF187nq9mdnXjXsSivRiXN7SmRkE=
+rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

internal/aggregator/aggregator.go

@@ -192,6 +192,80 @@ func agentURL(apiURL string, agentPort int, path string) (string, error) {
 	return u.String(), nil
 }
 
+// PostPeer sendet einen POST-Request an einen einzelnen Peer.
+// Wird vom Rolling-Update-Orchestrator genutzt um /agent/cluster/trigger-update
+// auf dem Secondary auszulösen.
+func (a *Aggregator) PostPeer(ctx context.Context, p models.HANode, path string) PeerResult {
+	start := time.Now()
+	res := PeerResult{NodeID: p.ID, FQDN: p.FQDN}
+	target, err := agentURL(p.APIURL, a.AgentPort, path)
+	if err != nil {
+		res.Err = "bad api_url: " + err.Error()
+		return res
+	}
+	reqCtx, cancel := context.WithTimeout(ctx, 15*time.Second)
+	defer cancel()
+	req, err := http.NewRequestWithContext(reqCtx, http.MethodPost, target, nil)
+	if err != nil {
+		res.Err = err.Error()
+		return res
+	}
+	req.Header.Set("Content-Type", "application/json")
+	resp, err := a.HTTPClient.Do(req)
+	if err != nil {
+		res.Err = err.Error()
+		res.Duration = time.Since(start).Milliseconds()
+		return res
+	}
+	defer resp.Body.Close()
+	body, _ := io.ReadAll(io.LimitReader(resp.Body, 1<<20))
+	if resp.StatusCode != http.StatusOK && resp.StatusCode != http.StatusAccepted {
+		res.Err = fmt.Sprintf("HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(body)))
+		res.Duration = time.Since(start).Milliseconds()
+		return res
+	}
+	res.OK = true
+	res.Duration = time.Since(start).Milliseconds()
+	return res
+}
+
+// PostPeerWithBody sendet einen POST-Request mit JSON-Body an einen Peer.
+// Wird für VIP-Schwenk-Tests genutzt (/agent/cluster/vip-cmd).
+func (a *Aggregator) PostPeerWithBody(ctx context.Context, p models.HANode, path string, body []byte) PeerResult {
+	start := time.Now()
+	res := PeerResult{NodeID: p.ID, FQDN: p.FQDN}
+	target, err := agentURL(p.APIURL, a.AgentPort, path)
+	if err != nil {
+		res.Err = "bad api_url: " + err.Error()
+		return res
+	}
+	reqCtx, cancel := context.WithTimeout(ctx, 15*time.Second)
+	defer cancel()
+	req, err := http.NewRequestWithContext(reqCtx, http.MethodPost, target, strings.NewReader(string(body)))
+	if err != nil {
+		res.Err = err.Error()
+		return res
+	}
+	req.Header.Set("Content-Type", "application/json")
+	resp, err := a.HTTPClient.Do(req)
+	if err != nil {
+		res.Err = err.Error()
+		res.Duration = time.Since(start).Milliseconds()
+		return res
+	}
+	defer resp.Body.Close()
+	respBody, _ := io.ReadAll(io.LimitReader(resp.Body, 1<<20))
+	if resp.StatusCode != http.StatusOK && resp.StatusCode != http.StatusAccepted && resp.StatusCode != http.StatusNoContent {
+		res.Err = fmt.Sprintf("HTTP %d: %s", resp.StatusCode, strings.TrimSpace(string(respBody)))
+		res.Duration = time.Since(start).Milliseconds()
+		return res
+	}
+	res.OK = true
+	res.Data = respBody
+	res.Duration = time.Since(start).Milliseconds()
+	return res
+}
+
 // Compile-time check dass cluster importiert wird (für Drift-Detection
 // vom hashSpec — die Aggregator-Resultate werden parallel im Drift-
 // Banner mitverarbeitet). Nicht runtime-essentiell, aber dokumentiert

internal/cluster/confighash.go

@@ -35,10 +35,13 @@ import (
 
 // hashTable beschreibt eine Tabelle die in den config-hash einfließt.
 type hashTable struct {
-	Name          string
-	Singleton     bool     // dns_settings, ntp_settings → eine row, id=1
-	ExtraExclude  []string // Spalten die zusätzlich aus to_jsonb gefiltert werden
-	SkipUpdatedAt bool     // setze true wenn updated_at semantisch relevant ist
+	Name             string
+	Singleton        bool     // dns_settings, ntp_settings → eine row, id=1
+	ExtraExclude     []string // Spalten die zusätzlich aus to_jsonb gefiltert werden
+	SkipUpdatedAt    bool     // setze true wenn updated_at semantisch relevant ist
+	MigrationDefault bool     // Tabelle hat migrations-erzeugte Default-Rows (firewall_zones, ntp_pools…)
+	                          // → zählt nicht als "user hat config" bei der Empty-DB-Erkennung
+	CustomSQL        string   // wenn gesetzt: direkt als Hash-Query verwenden (überschreibt hashSQL)
 }
 
 // hashSpec ist die Reihenfolge-stabile Liste. NEUE Tabellen hier
@@ -49,15 +52,13 @@ var hashSpec = []hashTable{
 	{Name: "backends"},
 	{Name: "backend_servers"},
 	{Name: "routing_rules"},
-	{Name: "network_interfaces"},
-	{Name: "ip_addresses"},
 	{Name: "tls_certs", ExtraExclude: []string{"last_renewed_at", "last_error"}},
 
-	{Name: "firewall_zones"},
+	{Name: "firewall_zones", MigrationDefault: true},
 	{Name: "firewall_address_objects"},
 	{Name: "firewall_address_groups"},
-	{Name: "firewall_services"},
-	{Name: "firewall_service_groups"},
+	{Name: "firewall_services", MigrationDefault: true},
+	{Name: "firewall_service_groups", MigrationDefault: true},
 	{Name: "firewall_rules"},
 	{Name: "firewall_nat_rules"},
 
@@ -67,12 +68,29 @@ var hashSpec = []hashTable{
 
 	{Name: "dns_zones"},
 	{Name: "dns_records"},
-	{Name: "dns_settings", Singleton: true},
 
-	{Name: "ntp_pools"},
-	{Name: "ntp_settings", Singleton: true},
+	{Name: "ntp_pools", MigrationDefault: true},
 
-	{Name: "static_routes"},
+	// DHCP: Subnets + Reservierungen sind geteilte Config (repliziert).
+	// dhcp_settings ist node-lokal (ob DIESE Node DHCP betreibt) → NICHT hier.
+	{Name: "dhcp_subnets"},
+	{Name: "dhcp_reservations"},
+
+	// RADIUS: Clients + Users sind geteilte Config (repliziert).
+	// radius_settings ist node-lokal → NICHT hier.
+	{Name: "radius_clients"},
+	{Name: "radius_users"},
+
+	// network_interfaces + ip_addresses sind BEWUSST NICHT im Drift-Hash.
+	// Sie stehen in cluster_replication.go localOnlyTables, werden also NICHT
+	// repliziert und sind per Design node-spezifisch (jede Node hat eigene
+	// Mgmt-/Host-IPs, z.B. utm-1=.6, utm-2=.8). Würde man sie hashen, wäre
+	// der config_hash zwischen zwei Nodes ZWANGSLÄUFIG dauerhaft verschieden
+	// → Drift-Banner, das kein Resync je beheben kann (Resync kopiert nur
+	// replizierte Tabellen). Migration 0030 wollte sie zwar replizieren,
+	// localOnlyTables schließt sie aber weiter aus → wir hashen sie nicht.
+	//
+	// static_routes, dns_settings, ntp_settings bleiben ebenfalls node-spezifisch.
 }
 
 // hashSQL rendert die SHA-Input-SQL für eine Tabelle.
@@ -100,22 +118,39 @@ func hashSQL(t hashTable) string {
 // ComputeConfigHash gibt den 16-hex-char-Hash über alle Spec-Tabellen
 // zurück. Fehlende Tabellen (transienter schema-flux) werden als
 // leerer Per-Table-Hash behandelt — kein Abbruch.
+//
+// Gibt "" zurück wenn alle user-konfigurierbaren Tabellen leer sind
+// (Singleton- und MigrationDefault-Tabellen zählen nicht als User-Config).
+// Das verhindert False-Positive-Drift-Banner auf frisch gejointen Secondaries.
 func ComputeConfigHash(ctx context.Context, pool *pgxpool.Pool) (string, error) {
 	if pool == nil {
 		return "", fmt.Errorf("nil pool")
 	}
 	h := sha256.New()
+	hasUserConfig := false
 	for _, t := range hashSpec {
 		var s string
-		if err := pool.QueryRow(ctx, hashSQL(t)).Scan(&s); err != nil {
+		sql := t.CustomSQL
+		if sql == "" {
+			sql = hashSQL(t)
+		}
+		if err := pool.QueryRow(ctx, sql).Scan(&s); err != nil {
 			// Migration fehlt o.ä. → leeren string nehmen, weiter.
 			s = ""
 		}
+		if s != "" && !t.Singleton && !t.MigrationDefault {
+			hasUserConfig = true
+		}
 		h.Write([]byte(t.Name))
 		h.Write([]byte{0})
 		h.Write([]byte(s))
 		h.Write([]byte{0})
 	}
+	if !hasUserConfig {
+		// Frisch gejoincter Secondary oder komplett leere DB →
+		// leerer String signalisiert "kein Drift prüfen" im Status-Handler.
+		return "", nil
+	}
 	return hex.EncodeToString(h.Sum(nil))[:16], nil
 }
 

internal/configgen/configgen.go

@@ -99,6 +99,33 @@ func RestartService(name string) error {
 	return nil
 }
 
+// StopService runs `sudo -n systemctl stop <name>.service`.
+func StopService(name string) error {
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemctl", "stop", name+".service")
+	if out, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("sudo systemctl stop %s.service: %w (output: %s)", name, err, strings.TrimSpace(string(out)))
+	}
+	return nil
+}
+
+// EnableService runs `sudo -n systemctl enable <name>.service` (boot-persistent).
+func EnableService(name string) error {
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemctl", "enable", name+".service")
+	if out, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("sudo systemctl enable %s.service: %w (output: %s)", name, err, strings.TrimSpace(string(out)))
+	}
+	return nil
+}
+
+// DisableService runs `sudo -n systemctl disable <name>.service`.
+func DisableService(name string) error {
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemctl", "disable", name+".service")
+	if out, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("sudo systemctl disable %s.service: %w (output: %s)", name, err, strings.TrimSpace(string(out)))
+	}
+	return nil
+}
+
 // EtcEdgeguard is the on-target config root. Templated path used by
 // all renderers — never let renderers hard-code their own.
 const EtcEdgeguard = "/etc/edgeguard"

internal/crowdsec/service.go

@@ -0,0 +1,432 @@
+// Package crowdsec wraps sudo /usr/bin/cscli calls for the edgeguard
+// management API. All list operations use -o json. Mutation operations
+// (add/delete) use the appropriate cscli sub-commands.
+//
+// edgeguard runs as a non-root system user; every cscli call goes
+// through sudo (allowed entries are in /etc/sudoers.d/edgeguard).
+package crowdsec
+
+import (
+	"bufio"
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"log/slog"
+	"os"
+	"os/exec"
+	"strings"
+)
+
+// ErrNotInstalled is returned when /usr/bin/cscli is not found.
+var ErrNotInstalled = errors.New("crowdsec not installed")
+
+// IsInstalled checks whether /usr/bin/cscli exists on this host.
+func IsInstalled() bool {
+	_, err := os.Stat("/usr/bin/cscli")
+	return err == nil
+}
+
+// ---------- Types -----------------------------------------------------------
+
+// Decision represents a single IP decision (ban/captcha/etc.) in CrowdSec.
+type Decision struct {
+	ID       int64  `json:"id"`
+	Origin   string `json:"origin"`
+	Type     string `json:"type"`
+	Scope    string `json:"scope"`
+	Value    string `json:"value"`
+	Duration string `json:"duration"`
+	Reason   string `json:"reason"`
+	Country  string `json:"country,omitempty"`
+	AS       string `json:"as,omitempty"`
+}
+
+// Alert represents a CrowdSec alert with associated decisions.
+type Alert struct {
+	ID          int64       `json:"id"`
+	Scenario    string      `json:"scenario"`
+	EventsCount int         `json:"events_count"`
+	Source      AlertSource `json:"source"`
+	StartAt     string      `json:"start_at"`
+	StopAt      string      `json:"stop_at"`
+	Decisions   []Decision  `json:"decisions,omitempty"`
+}
+
+// AlertSource holds the source IP/range info for an alert.
+type AlertSource struct {
+	IP      string `json:"ip"`
+	Country string `json:"cn,omitempty"`
+	ASName  string `json:"as_name,omitempty"`
+	Range   string `json:"range,omitempty"`
+	Scope   string `json:"scope,omitempty"`
+	Value   string `json:"value,omitempty"`
+}
+
+// Bouncer represents a registered CrowdSec bouncer.
+type Bouncer struct {
+	Name      string `json:"name"`
+	IPAddress string `json:"ip_address,omitempty"`
+	Revoked   bool   `json:"revoked"`
+	LastPull  string `json:"last_pull,omitempty"`
+	Type      string `json:"type,omitempty"`
+	Version   string `json:"version,omitempty"`
+	CreatedAt string `json:"created_at"`
+	AuthType  string `json:"auth_type,omitempty"`
+}
+
+// Machine represents a registered CrowdSec agent/machine.
+type Machine struct {
+	MachineID   string `json:"machineId"`
+	CreatedAt   string `json:"created_at"`
+	UpdatedAt   string `json:"updated_at"`
+	LastPush    string `json:"last_push,omitempty"`
+	IsValidated bool   `json:"isValidated"`
+	Version     string `json:"version,omitempty"`
+	Status      string `json:"status,omitempty"`
+}
+
+// HubItem represents a CrowdSec hub item (collection, parser, scenario, etc.).
+type HubItem struct {
+	Name         string `json:"name"`
+	Description  string `json:"description,omitempty"`
+	Status       string `json:"status"`
+	LocalVersion string `json:"local_version,omitempty"`
+	LocalPath    string `json:"local_path,omitempty"`
+	Author       string `json:"author,omitempty"`
+	Type         string `json:"type,omitempty"`
+}
+
+// Status summarises the runtime state of the CrowdSec stack on this node.
+type Status struct {
+	Installed      bool   `json:"installed"`
+	AgentRunning   bool   `json:"agent_running"`
+	BouncerRunning bool   `json:"bouncer_running"`
+	Version        string `json:"version,omitempty"`
+	DecisionCount  int    `json:"decision_count"`
+	AlertCount     int    `json:"alert_count"`
+	BouncerCount   int    `json:"bouncer_count"`
+	MachineCount   int    `json:"machine_count"`
+}
+
+// ---------- Helpers ---------------------------------------------------------
+
+// sudoCscli executes `sudo -n /usr/bin/cscli <args...>` and returns stdout.
+func sudoCscli(ctx context.Context, args ...string) ([]byte, error) {
+	full := append([]string{"-n", "/usr/bin/cscli"}, args...)
+	cmd := exec.CommandContext(ctx, "sudo", full...)
+	var out, errBuf bytes.Buffer
+	cmd.Stdout = &out
+	cmd.Stderr = &errBuf
+	if err := cmd.Run(); err != nil {
+		slog.Error("crowdsec: sudoCscli failed", "args", args, "error", err, "stderr", errBuf.String())
+		return nil, err
+	}
+	if errBuf.Len() > 0 {
+		slog.Warn("crowdsec: sudoCscli stderr", "args", args, "stderr", errBuf.String())
+	}
+	slog.Debug("crowdsec: sudoCscli ok", "args", args[0], "bytes", out.Len())
+	return out.Bytes(), nil
+}
+
+// systemctlActive returns true when the named unit is "active".
+func systemctlActive(ctx context.Context, unit string) bool {
+	cmd := exec.CommandContext(ctx, "systemctl", "is-active", "--quiet", unit)
+	return cmd.Run() == nil
+}
+
+// unmarshalSlice unmarshals JSON that may be "null" (cscli returns null
+// instead of [] when no items exist). Returns an empty slice in that case.
+func unmarshalSlice[T any](data []byte) ([]T, error) {
+	data = bytes.TrimSpace(data)
+	if bytes.Equal(data, []byte("null")) || len(data) == 0 {
+		return []T{}, nil
+	}
+	var result []T
+	if err := json.Unmarshal(data, &result); err != nil {
+		return nil, err
+	}
+	return result, nil
+}
+
+// ---------- ServiceStatus ---------------------------------------------------
+
+// ServiceStatus returns a Status struct describing the current state of the
+// CrowdSec agent and bouncer on this node. Does NOT need cscli installed —
+// it uses systemctl for the running-state checks. Version is extracted via
+// `cscli version` when available.
+func ServiceStatus(ctx context.Context) Status {
+	st := Status{
+		Installed:      IsInstalled(),
+		AgentRunning:   systemctlActive(ctx, "crowdsec"),
+		BouncerRunning: systemctlActive(ctx, "crowdsec-firewall-bouncer"),
+	}
+
+	if st.Installed {
+		// Grab version from `sudo -n /usr/bin/cscli version` — first line only.
+		// Output is not JSON; it looks like "version: v1.6.3-..."
+		if out, err := sudoCscli(ctx, "version"); err == nil {
+			scanner := bufio.NewScanner(bytes.NewReader(out))
+			if scanner.Scan() {
+				st.Version = strings.TrimSpace(scanner.Text())
+			}
+		}
+	}
+
+	// Only query cscli data endpoints when the agent is running — cscli
+	// hangs on its local socket when the agent is stopped, which would
+	// block the entire status response and leave the UI with no data.
+	if st.AgentRunning {
+		if decisions, err := Decisions(ctx); err == nil {
+			st.DecisionCount = len(decisions)
+		}
+		if alerts, err := Alerts(ctx, 500); err == nil {
+			st.AlertCount = len(alerts)
+		}
+		if bouncers, err := Bouncers(ctx); err == nil {
+			st.BouncerCount = len(bouncers)
+		}
+		if machines, err := Machines(ctx); err == nil {
+			st.MachineCount = len(machines)
+		}
+	}
+
+	return st
+}
+
+// ---------- Decisions -------------------------------------------------------
+
+// cscli decisions list -o json returns alert-level objects with nested
+// decisions[] arrays. These intermediate types are used only for parsing.
+type cscliDecisionRaw struct {
+	ID       int64  `json:"id"`
+	Duration string `json:"duration"`
+	Origin   string `json:"origin"`
+	Scope    string `json:"scope"`
+	Type     string `json:"type"`
+	Value    string `json:"value"`
+}
+
+type cscliAlertRaw struct {
+	Scenario  string             `json:"scenario"`
+	Decisions []cscliDecisionRaw `json:"decisions"`
+	Source    struct {
+		IP     string `json:"ip"`
+		CN     string `json:"cn"`
+		ASName string `json:"as_name"`
+	} `json:"source"`
+}
+
+// Decisions lists all active decisions by flattening the alert-level JSON
+// that cscli emits (each alert contains a nested decisions[] array).
+func Decisions(ctx context.Context) ([]Decision, error) {
+	if !IsInstalled() {
+		return nil, ErrNotInstalled
+	}
+	out, err := sudoCscli(ctx, "decisions", "list", "-o", "json")
+	if err != nil {
+		return nil, err
+	}
+	alerts, err := unmarshalSlice[cscliAlertRaw](out)
+	if err != nil {
+		return nil, err
+	}
+	var result []Decision
+	for _, a := range alerts {
+		for _, d := range a.Decisions {
+			result = append(result, Decision{
+				ID:       d.ID,
+				Origin:   d.Origin,
+				Type:     d.Type,
+				Scope:    d.Scope,
+				Value:    d.Value,
+				Duration: d.Duration,
+				Reason:   a.Scenario,
+				Country:  a.Source.CN,
+				AS:       a.Source.ASName,
+			})
+		}
+	}
+	if result == nil {
+		result = []Decision{}
+	}
+	return result, nil
+}
+
+// AddDecision creates a new ban/captcha decision for the given IP.
+func AddDecision(ctx context.Context, ip, duration, reason, typ string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "decisions", "add",
+		"--ip", ip,
+		"--duration", duration,
+		"--reason", reason,
+		"--type", typ,
+	)
+	return err
+}
+
+// DeleteDecisionByIP removes all decisions for a given IP address.
+func DeleteDecisionByIP(ctx context.Context, ip string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "decisions", "delete", "--ip", ip)
+	return err
+}
+
+// DeleteDecisionByID removes a single decision by its numeric ID.
+func DeleteDecisionByID(ctx context.Context, id string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "decisions", "delete", "--id", id)
+	return err
+}
+
+// ---------- Alerts ----------------------------------------------------------
+
+// Alerts lists recent alerts (up to limit).
+func Alerts(ctx context.Context, limit int) ([]Alert, error) {
+	if !IsInstalled() {
+		return nil, ErrNotInstalled
+	}
+	out, err := sudoCscli(ctx, "alerts", "list", "-o", "json",
+		"-l", fmt.Sprintf("%d", limit))
+	if err != nil {
+		return nil, err
+	}
+	return unmarshalSlice[Alert](out)
+}
+
+// DeleteAlert discards (deletes) a single alert by its ID.
+func DeleteAlert(ctx context.Context, id string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "alerts", "delete", "--id", id)
+	return err
+}
+
+// ---------- Bouncers --------------------------------------------------------
+
+// Bouncers lists all registered bouncers.
+func Bouncers(ctx context.Context) ([]Bouncer, error) {
+	if !IsInstalled() {
+		return nil, ErrNotInstalled
+	}
+	out, err := sudoCscli(ctx, "bouncers", "list", "-o", "json")
+	if err != nil {
+		return nil, err
+	}
+	return unmarshalSlice[Bouncer](out)
+}
+
+// DeleteBouncer removes a bouncer by name.
+func DeleteBouncer(ctx context.Context, name string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "bouncers", "delete", name)
+	return err
+}
+
+// ---------- Machines --------------------------------------------------------
+
+// cscliMachineRaw mirrors the actual cscli JSON with its mixed camelCase /
+// snake_case field names. Only used inside Machines().
+type cscliMachineRaw struct {
+	MachineID   string `json:"machineId"`
+	CreatedAt   string `json:"created_at"`
+	UpdatedAt   string `json:"updated_at"`
+	LastPush    string `json:"last_push"`
+	IsValidated bool   `json:"isValidated"`
+	Version     string `json:"version"`
+	Status      string `json:"status"`
+}
+
+// Machines lists all registered machines/agents.
+func Machines(ctx context.Context) ([]Machine, error) {
+	if !IsInstalled() {
+		return nil, ErrNotInstalled
+	}
+	out, err := sudoCscli(ctx, "machines", "list", "-o", "json")
+	if err != nil {
+		return nil, err
+	}
+	raw, err := unmarshalSlice[cscliMachineRaw](out)
+	if err != nil {
+		return nil, err
+	}
+	result := make([]Machine, len(raw))
+	for i, r := range raw {
+		result[i] = Machine{
+			MachineID:   r.MachineID,
+			CreatedAt:   r.CreatedAt,
+			UpdatedAt:   r.UpdatedAt,
+			LastPush:    r.LastPush,
+			IsValidated: r.IsValidated,
+			Version:     r.Version,
+			Status:      r.Status,
+		}
+	}
+	return result, nil
+}
+
+// DeleteMachine removes a machine by its machine ID.
+func DeleteMachine(ctx context.Context, id string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "machines", "delete", "--machine-id", id)
+	return err
+}
+
+// ---------- Collections -----------------------------------------------------
+
+// Collections lists installed/available hub collections.
+// cscli returns {"collections": [...]} (not a flat array) — we unwrap the key.
+func Collections(ctx context.Context) ([]HubItem, error) {
+	if !IsInstalled() {
+		return nil, ErrNotInstalled
+	}
+	out, err := sudoCscli(ctx, "collections", "list", "-o", "json")
+	if err != nil {
+		return nil, err
+	}
+	out = bytes.TrimSpace(out)
+	if bytes.Equal(out, []byte("null")) || len(out) == 0 {
+		return []HubItem{}, nil
+	}
+	// cscli wraps collections in {"collections": [...]}
+	var wrapper struct {
+		Collections []HubItem `json:"collections"`
+	}
+	if err := json.Unmarshal(out, &wrapper); err != nil {
+		return nil, err
+	}
+	if wrapper.Collections == nil {
+		return []HubItem{}, nil
+	}
+	return wrapper.Collections, nil
+}
+
+// InstallCollection installs a hub collection by name (--force to upgrade).
+func InstallCollection(ctx context.Context, name string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "collections", "install", name, "--force")
+	return err
+}
+
+// RemoveCollection removes a hub collection by name.
+func RemoveCollection(ctx context.Context, name string) error {
+	if !IsInstalled() {
+		return ErrNotInstalled
+	}
+	_, err := sudoCscli(ctx, "collections", "remove", name)
+	return err
+}

internal/database/migrations/0029_cluster_vip.sql

@@ -0,0 +1,36 @@
+-- +goose Up
+-- +goose StatementBegin
+
+-- pg_role: Rolle dieser Node in der PG-Replikation.
+-- "standalone" = kein Streaming-Replication-Setup
+-- "primary"    = WAL-Sender, repliziert an Standby(s)
+-- "standby"    = Hot-Standby, liest WAL vom Primary
+ALTER TABLE ha_nodes ADD COLUMN IF NOT EXISTS pg_role TEXT NOT NULL DEFAULT 'standalone';
+
+-- cluster_settings: VIP + VRRP-Konfiguration (Singleton, id=1).
+-- vip_address   = die virtuelle IP-Adresse (z.B. "89.163.205.10")
+-- vip_interface = Netzwerk-Interface (z.B. "eth0")
+-- vip_auth_pass = VRRP-Authentication-Passwort (max. 8 Zeichen, Keepalived-Limit)
+-- vrrp_router_id = VRRP Virtual Router ID (1–255, muss im Subnetz eindeutig sein)
+CREATE TABLE IF NOT EXISTS cluster_settings (
+    id              INTEGER PRIMARY KEY DEFAULT 1,
+    vip_address     TEXT,
+    vip_interface   TEXT,
+    vip_auth_pass   TEXT,
+    vrrp_router_id  INTEGER NOT NULL DEFAULT 51,
+    created_at      TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at      TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT cluster_settings_singleton CHECK (id = 1)
+);
+
+INSERT INTO cluster_settings (id) VALUES (1) ON CONFLICT DO NOTHING;
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+DROP TABLE IF EXISTS cluster_settings;
+ALTER TABLE ha_nodes DROP COLUMN IF EXISTS pg_role;
+
+-- +goose StatementEnd

internal/database/migrations/0030_cluster_sync_replication.sql

@@ -0,0 +1,21 @@
+-- +goose Up
+-- +goose StatementBegin
+
+-- HINWEIS (korrigiert v1.2.89): Diese Migration war urspr. dafür gedacht,
+-- network_interfaces und ip_addresses in die Cluster-Replikation aufzunehmen.
+-- Das wurde NICHT umgesetzt und ist auch NICHT gewollt: beide Tabellen sind
+-- node-spezifisch (jede Node hat eigene Mgmt-/Host-IPs) und stehen weiterhin
+-- in cluster_replication.go localOnlyTables → sie werden bewusst NICHT
+-- repliziert. Sie sind auch aus dem Drift-Hash (confighash.go) entfernt,
+-- da sie sonst dauerhaften False-Positive-Drift erzeugen.
+-- Diese Migration ist ein No-op / reiner Versions-Marker für goose.
+SELECT 1;
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+SELECT 1;
+
+-- +goose StatementEnd

internal/database/migrations/0031_forward_proxy_settings.sql

@@ -0,0 +1,25 @@
+-- +goose Up
+-- +goose StatementBegin
+
+-- forward_proxy_settings — Singleton-Row für globale Squid-Einstellungen.
+-- listen_addresses: Komma-separierte IPs auf denen Squid lauscht.
+-- Leer = alle Interfaces (http_port 3128). Typisch: LAN/VLAN-Gateway-IPs.
+CREATE TABLE IF NOT EXISTS forward_proxy_settings (
+    id               INTEGER PRIMARY KEY DEFAULT 1,
+    listen_addresses TEXT NOT NULL DEFAULT '',
+    listen_port      INTEGER NOT NULL DEFAULT 3128,
+    created_at       TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at       TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT forward_proxy_settings_singleton CHECK (id = 1)
+);
+
+INSERT INTO forward_proxy_settings (id) VALUES (1) ON CONFLICT DO NOTHING;
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+DROP TABLE IF EXISTS forward_proxy_settings;
+
+-- +goose StatementEnd

internal/database/migrations/0032_proxy_dns_extended_settings.sql

@@ -0,0 +1,37 @@
+-- +goose Up
+-- +goose StatementBegin
+
+ALTER TABLE forward_proxy_settings
+  ADD COLUMN IF NOT EXISTS cache_mem_mb      INTEGER NOT NULL DEFAULT 64,
+  ADD COLUMN IF NOT EXISTS cache_dir_mb      INTEGER NOT NULL DEFAULT 100,
+  ADD COLUMN IF NOT EXISTS max_obj_size_mb   INTEGER NOT NULL DEFAULT 4,
+  ADD COLUMN IF NOT EXISTS connect_timeout   INTEGER NOT NULL DEFAULT 60,
+  ADD COLUMN IF NOT EXISTS read_timeout      INTEGER NOT NULL DEFAULT 300,
+  ADD COLUMN IF NOT EXISTS request_timeout   INTEGER NOT NULL DEFAULT 300;
+
+ALTER TABLE dns_settings
+  ADD COLUMN IF NOT EXISTS prefetch            BOOLEAN NOT NULL DEFAULT false,
+  ADD COLUMN IF NOT EXISTS serve_expired       BOOLEAN NOT NULL DEFAULT false,
+  ADD COLUMN IF NOT EXISTS msg_cache_size_mb   INTEGER NOT NULL DEFAULT 64,
+  ADD COLUMN IF NOT EXISTS rrset_cache_size_mb INTEGER NOT NULL DEFAULT 128;
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+ALTER TABLE forward_proxy_settings
+  DROP COLUMN IF EXISTS cache_mem_mb,
+  DROP COLUMN IF EXISTS cache_dir_mb,
+  DROP COLUMN IF EXISTS max_obj_size_mb,
+  DROP COLUMN IF EXISTS connect_timeout,
+  DROP COLUMN IF EXISTS read_timeout,
+  DROP COLUMN IF EXISTS request_timeout;
+
+ALTER TABLE dns_settings
+  DROP COLUMN IF EXISTS prefetch,
+  DROP COLUMN IF EXISTS serve_expired,
+  DROP COLUMN IF EXISTS msg_cache_size_mb,
+  DROP COLUMN IF EXISTS rrset_cache_size_mb;
+
+-- +goose StatementEnd

internal/database/migrations/0033_cluster_settings_splitbrain.sql

@@ -0,0 +1,18 @@
+-- +goose Up
+-- Dual-path VRRP + Gateway-Tracking für Split-Brain-Schutz.
+-- hb_* = zweite VRRP-Instanz (VI_HB) auf dediziertem Heartbeat-Interface.
+-- gw_check_ip = Gateway-IP die von chk_gateway angepingt wird (weight -110).
+ALTER TABLE cluster_settings
+  ADD COLUMN IF NOT EXISTS hb_interface  VARCHAR,
+  ADD COLUMN IF NOT EXISTS hb_src_ip     VARCHAR,
+  ADD COLUMN IF NOT EXISTS hb_peer_ip    VARCHAR,
+  ADD COLUMN IF NOT EXISTS hb_router_id  INTEGER NOT NULL DEFAULT 52,
+  ADD COLUMN IF NOT EXISTS gw_check_ip   VARCHAR;
+
+-- +goose Down
+ALTER TABLE cluster_settings
+  DROP COLUMN IF EXISTS hb_interface,
+  DROP COLUMN IF EXISTS hb_src_ip,
+  DROP COLUMN IF EXISTS hb_peer_ip,
+  DROP COLUMN IF EXISTS hb_router_id,
+  DROP COLUMN IF EXISTS gw_check_ip;

internal/database/migrations/0034_totp.sql

@@ -0,0 +1,9 @@
+-- +goose Up
+ALTER TABLE users
+    ADD COLUMN totp_secret  TEXT,
+    ADD COLUMN totp_enabled BOOLEAN NOT NULL DEFAULT false;
+
+-- +goose Down
+ALTER TABLE users
+    DROP COLUMN totp_secret,
+    DROP COLUMN totp_enabled;

internal/database/migrations/0035_firewall_note_labels.sql

@@ -0,0 +1,17 @@
+-- +goose Up
+ALTER TABLE firewall_rules
+    ADD COLUMN IF NOT EXISTS note   TEXT,
+    ADD COLUMN IF NOT EXISTS labels TEXT[] NOT NULL DEFAULT '{}';
+
+ALTER TABLE firewall_nat_rules
+    ADD COLUMN IF NOT EXISTS note   TEXT,
+    ADD COLUMN IF NOT EXISTS labels TEXT[] NOT NULL DEFAULT '{}';
+
+-- +goose Down
+ALTER TABLE firewall_rules
+    DROP COLUMN IF EXISTS note,
+    DROP COLUMN IF EXISTS labels;
+
+ALTER TABLE firewall_nat_rules
+    DROP COLUMN IF EXISTS note,
+    DROP COLUMN IF EXISTS labels;

internal/database/migrations/0036_crowdsec.sql

@@ -0,0 +1,12 @@
+-- +goose Up
+CREATE TABLE IF NOT EXISTS crowdsec_settings (
+    id               INTEGER PRIMARY KEY DEFAULT 1 CHECK (id = 1),
+    enabled          BOOLEAN NOT NULL DEFAULT false,
+    simulation_mode  BOOLEAN NOT NULL DEFAULT false,
+    collections      TEXT[]  NOT NULL DEFAULT '{"crowdsecurity/linux","crowdsecurity/haproxy"}',
+    updated_at       TIMESTAMPTZ NOT NULL DEFAULT NOW()
+);
+INSERT INTO crowdsec_settings (id) VALUES (1) ON CONFLICT DO NOTHING;
+
+-- +goose Down
+DROP TABLE IF EXISTS crowdsec_settings;

internal/database/migrations/0037_waf.sql

@@ -0,0 +1,18 @@
+-- +goose Up
+CREATE TABLE IF NOT EXISTS waf_configs (
+    id              SERIAL PRIMARY KEY,
+    domain_id       BIGINT NOT NULL REFERENCES domains(id) ON DELETE CASCADE,
+    enabled         BOOLEAN  NOT NULL DEFAULT false,
+    mode            TEXT     NOT NULL DEFAULT 'detection'
+                             CHECK (mode IN ('detection','blocking')),
+    paranoia_level  INT      NOT NULL DEFAULT 1
+                             CHECK (paranoia_level BETWEEN 1 AND 4),
+    rule_exclusions TEXT[]   NOT NULL DEFAULT '{}',
+    trusted_proxies TEXT[]   NOT NULL DEFAULT '{}',
+    custom_rules    TEXT     NOT NULL DEFAULT '',
+    updated_at      TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT waf_configs_domain_unique UNIQUE (domain_id)
+);
+
+-- +goose Down
+DROP TABLE IF EXISTS waf_configs;

internal/database/migrations/0038_waf_alerts.sql

@@ -0,0 +1,20 @@
+-- +goose Up
+CREATE TABLE IF NOT EXISTS waf_alerts (
+    id         BIGSERIAL PRIMARY KEY,
+    domain_id  BIGINT REFERENCES domains(id) ON DELETE CASCADE,
+    hostname   TEXT        NOT NULL,
+    client_ip  TEXT        NOT NULL,
+    method     TEXT        NOT NULL,
+    uri        TEXT        NOT NULL,
+    rule_id    INT         NOT NULL DEFAULT 0,
+    rule_msg   TEXT        NOT NULL DEFAULT '',
+    severity   TEXT        NOT NULL DEFAULT '',
+    action     TEXT        NOT NULL,          -- 'detected' | 'blocked'
+    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
+);
+
+CREATE INDEX IF NOT EXISTS waf_alerts_domain_created ON waf_alerts(domain_id, created_at DESC);
+CREATE INDEX IF NOT EXISTS waf_alerts_created ON waf_alerts(created_at DESC);
+
+-- +goose Down
+DROP TABLE IF EXISTS waf_alerts;

internal/database/migrations/0039_waf_exclusion_notes.sql

@@ -0,0 +1,6 @@
+-- +goose Up
+ALTER TABLE waf_configs
+    ADD COLUMN IF NOT EXISTS exclusion_notes JSONB NOT NULL DEFAULT '{}';
+
+-- +goose Down
+ALTER TABLE waf_configs DROP COLUMN IF EXISTS exclusion_notes;

internal/database/migrations/0040_oidc_settings.sql

@@ -0,0 +1,35 @@
+-- +goose Up
+-- +goose StatementBegin
+
+-- OIDC / Keycloak SSO — Singleton-Settings (analog forward_proxy_settings).
+-- client_secret_enc: secrets.Box.Seal-Output (AES-256-GCM), NULL = nicht gesetzt.
+-- Rolle kommt bewusst NICHT aus dem Token, daher keine group/role-claim-Spalten.
+CREATE TABLE IF NOT EXISTS oidc_settings (
+    id                INTEGER     PRIMARY KEY DEFAULT 1,
+    enabled           BOOLEAN     NOT NULL DEFAULT false,
+    issuer_url        TEXT        NOT NULL DEFAULT '',
+    client_id         TEXT        NOT NULL DEFAULT '',
+    client_secret_enc BYTEA,
+    scopes            TEXT        NOT NULL DEFAULT 'openid email profile',
+    email_claim       TEXT        NOT NULL DEFAULT 'email',
+    button_label      TEXT        NOT NULL DEFAULT 'Sign in with SSO',
+    created_at        TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at        TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT oidc_settings_singleton CHECK (id = 1)
+);
+INSERT INTO oidc_settings (id) VALUES (1) ON CONFLICT DO NOTHING;
+
+-- Opportunistisches Linking: beim ersten SSO-Login wird der OIDC-'sub'
+-- gespeichert; weicht er später ab, wird der Login abgelehnt. Nullable,
+-- kein Backfill (Match-Schlüssel bleibt die verifizierte E-Mail).
+ALTER TABLE users ADD COLUMN IF NOT EXISTS oidc_subject TEXT;
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+ALTER TABLE users DROP COLUMN IF EXISTS oidc_subject;
+DROP TABLE IF EXISTS oidc_settings;
+
+-- +goose StatementEnd

internal/database/migrations/0041_dhcp.sql

@@ -0,0 +1,62 @@
+-- +goose Up
+-- +goose StatementBegin
+
+-- DHCP (Kea) — globale Singleton-Settings (node-lokal, wie dns_settings/
+-- ntp_settings: ob DIESE Node DHCP betreibt). Subnets/Reservierungen sind
+-- geteilte Config und werden repliziert.
+CREATE TABLE IF NOT EXISTS dhcp_settings (
+    id             INTEGER     PRIMARY KEY DEFAULT 1,
+    enabled        BOOLEAN     NOT NULL DEFAULT false,
+    default_lease  INTEGER     NOT NULL DEFAULT 3600,
+    max_lease      INTEGER     NOT NULL DEFAULT 7200,
+    domain_name    TEXT        NOT NULL DEFAULT '',
+    dns_servers    TEXT        NOT NULL DEFAULT '',
+    created_at     TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at     TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT dhcp_settings_singleton CHECK (id = 1)
+);
+INSERT INTO dhcp_settings (id) VALUES (1) ON CONFLICT DO NOTHING;
+
+-- Subnets: an ein Interface per NAME gebunden (nicht per node-lokaler FK,
+-- damit die Replikation nicht an divergierenden interface_id bricht).
+CREATE TABLE IF NOT EXISTS dhcp_subnets (
+    id             BIGSERIAL   PRIMARY KEY,
+    name           TEXT        NOT NULL,
+    interface_name TEXT        NOT NULL,
+    subnet_cidr    TEXT        NOT NULL,
+    pool_start     TEXT        NOT NULL DEFAULT '',
+    pool_end       TEXT        NOT NULL DEFAULT '',
+    gateway        TEXT        NOT NULL DEFAULT '',
+    dns_servers    TEXT        NOT NULL DEFAULT '',
+    lease_time     INTEGER,
+    active         BOOLEAN     NOT NULL DEFAULT true,
+    description    TEXT        NOT NULL DEFAULT '',
+    created_at     TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at     TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT dhcp_subnets_name_unique UNIQUE (name)
+);
+
+CREATE TABLE IF NOT EXISTS dhcp_reservations (
+    id          BIGSERIAL   PRIMARY KEY,
+    subnet_id   BIGINT      NOT NULL REFERENCES dhcp_subnets(id) ON DELETE CASCADE,
+    name        TEXT        NOT NULL DEFAULT '',
+    mac_address TEXT        NOT NULL,
+    ip_address  TEXT        NOT NULL,
+    hostname    TEXT        NOT NULL DEFAULT '',
+    active      BOOLEAN     NOT NULL DEFAULT true,
+    created_at  TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at  TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT dhcp_reservations_subnet_mac_unique UNIQUE (subnet_id, mac_address)
+);
+CREATE INDEX IF NOT EXISTS idx_dhcp_reservations_subnet ON dhcp_reservations(subnet_id);
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+DROP TABLE IF EXISTS dhcp_reservations;
+DROP TABLE IF EXISTS dhcp_subnets;
+DROP TABLE IF EXISTS dhcp_settings;
+
+-- +goose StatementEnd

internal/database/migrations/0042_radius.sql

@@ -0,0 +1,51 @@
+-- +goose Up
+-- +goose StatementBegin
+
+-- RADIUS (FreeRADIUS) — node-lokale Singleton-Settings (ob DIESE Node
+-- RADIUS betreibt + Listen). Clients/Users sind geteilte Config (repliziert).
+CREATE TABLE IF NOT EXISTS radius_settings (
+    id               INTEGER     PRIMARY KEY DEFAULT 1,
+    enabled          BOOLEAN     NOT NULL DEFAULT false,
+    listen_addresses TEXT        NOT NULL DEFAULT '',
+    created_at       TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at       TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT radius_settings_singleton CHECK (id = 1)
+);
+INSERT INTO radius_settings (id) VALUES (1) ON CONFLICT DO NOTHING;
+
+-- NAS-Clients (Geräte, die RADIUS-Requests senden): IP/CIDR + Shared Secret
+-- (verschlüsselt via secrets.Box).
+CREATE TABLE IF NOT EXISTS radius_clients (
+    id          BIGSERIAL   PRIMARY KEY,
+    name        TEXT        NOT NULL,
+    ipaddr      TEXT        NOT NULL,
+    secret_enc  BYTEA,
+    active      BOOLEAN     NOT NULL DEFAULT true,
+    description TEXT        NOT NULL DEFAULT '',
+    created_at  TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at  TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT radius_clients_name_unique UNIQUE (name)
+);
+
+-- Benutzer (PAP/CHAP): Name + Passwort (verschlüsselt; Cleartext nur zur
+-- Render-Zeit in die freeradius-lesbare authorize-Datei).
+CREATE TABLE IF NOT EXISTS radius_users (
+    id           BIGSERIAL   PRIMARY KEY,
+    username     TEXT        NOT NULL,
+    password_enc BYTEA,
+    active       BOOLEAN     NOT NULL DEFAULT true,
+    created_at   TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at   TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    CONSTRAINT radius_users_username_unique UNIQUE (username)
+);
+
+-- +goose StatementEnd
+
+-- +goose Down
+-- +goose StatementBegin
+
+DROP TABLE IF EXISTS radius_users;
+DROP TABLE IF EXISTS radius_clients;
+DROP TABLE IF EXISTS radius_settings;
+
+-- +goose StatementEnd

internal/firewall/firewall.go

@@ -22,6 +22,7 @@ import (
 	"context"
 	_ "embed"
 	"fmt"
+	"log/slog"
 	"net"
 	"os/exec"
 	"path/filepath"
@@ -138,6 +139,7 @@ type View struct {
 type WGSiteMasqEntry struct {
 	Iface  string // wg interface name, e.g. "wg7"
 	VPNNet string // network CIDR of the VPN subnet, e.g. "192.168.99.0/24"
+	L3     string // "ip" oder "ip6" — Familie von VPNNet
 }
 
 // AutoFWRule is one auto-emitted inbound rule. Proto is "tcp" or
@@ -148,6 +150,8 @@ type AutoFWRule struct {
 	Proto   string
 	Port    int
 	DstIP   string
+	L3      string // "ip"/"ip6" — gesetzt für DstIP-Rules (Familie); leer = agnostisch
+	Iface   string // optional: scope auf ein iifname (z.B. DHCP udp/67 nur auf LAN)
 	Comment string
 }
 
@@ -162,7 +166,11 @@ type RuleLeg struct {
 	DstIfaces []string
 	SrcAddrs  []string
 	DstAddrs  []string
-	Service   ResolvedService // Proto="" → no service match (any)
+	// L3 ist "ip" (IPv4) oder "ip6" (IPv6) für das Adress-Matching —
+	// gesetzt, sobald SrcAddrs/DstAddrs nicht leer sind. Bei adresslosen
+	// Regeln bleibt es "" (familienagnostisch, kein ip/ip6-Match).
+	L3      string
+	Service ResolvedService // Proto="" → no service match (any)
 }
 
 // ResolvedRule has all addresses + services already expanded so the
@@ -195,6 +203,12 @@ type ResolvedNATRule struct {
 	DPortStart, DPortEnd int
 	TargetAddr string
 	TargetPortStart, TargetPortEnd int
+	// L3 ist "ip" oder "ip6" — Adressfamilie der Regel (aus SrcCIDR/
+	// DstCIDR/TargetAddr abgeleitet). TargetHost ist TargetAddr, bei
+	// IPv6 MIT Port in eckigen Klammern ("[2001:db8::1]") für korrekte
+	// nft-dnat-Syntax.
+	L3         string
+	TargetHost string
 	Comment  string
 }
 
@@ -280,26 +294,15 @@ func (g *Generator) loadView(ctx context.Context) (*View, error) {
 	if err != nil {
 		return nil, err
 	}
-	// Expand to one Leg per (rule × service); rules without a service
-	// produce one leg with empty Proto.
+	// Expand to one Leg per (rule × service × address-family). Rules
+	// without a service produce one leg-set with empty Proto.
 	for _, r := range rules {
 		if len(r.Services) == 0 {
-			view.Legs = append(view.Legs, RuleLeg{
-				RuleID: r.ID, Action: r.Action, Log: r.Log, Name: r.Name,
-				Comment: r.Comment,
-				SrcIfaces: r.SrcIfaces, DstIfaces: r.DstIfaces,
-				SrcAddrs: r.SrcAddrs, DstAddrs: r.DstAddrs,
-			})
+			view.Legs = append(view.Legs, expandFamilyLegs(r, ResolvedService{}, false)...)
 			continue
 		}
 		for _, svc := range r.Services {
-			view.Legs = append(view.Legs, RuleLeg{
-				RuleID: r.ID, Action: r.Action, Log: r.Log, Name: r.Name,
-				Comment: r.Comment,
-				SrcIfaces: r.SrcIfaces, DstIfaces: r.DstIfaces,
-				SrcAddrs: r.SrcAddrs, DstAddrs: r.DstAddrs,
-				Service: svc,
-			})
+			view.Legs = append(view.Legs, expandFamilyLegs(r, svc, true)...)
 		}
 	}
 
@@ -323,9 +326,14 @@ func (g *Generator) loadView(ctx context.Context) (*View, error) {
 			if wgRows.Scan(&name, &cidr) == nil {
 				view.WGServerIfaces = append(view.WGServerIfaces, name)
 				if _, ipNet, err := net.ParseCIDR(cidr); err == nil {
+					l3 := addrFamily(ipNet.String())
+					if l3 == "" {
+						l3 = "ip"
+					}
 					view.WGSiteMasq = append(view.WGSiteMasq, WGSiteMasqEntry{
 						Iface:  name,
 						VPNNet: ipNet.String(),
+						L3:     l3,
 					})
 				}
 			}
@@ -363,11 +371,24 @@ func (g *Generator) loadAutoRules(ctx context.Context) []AutoFWRule {
 		}
 	}
 
-	// Squid Forward-Proxy: wenn ≥1 aktive ACL → tcp 3128 inbound
-	// (squid bindet aktuell 0.0.0.0:3128, daher kein DstIP-Filter).
-	var aclCount int
-	if err := g.Pool.QueryRow(ctx, `SELECT count(*) FROM forward_proxy_acls WHERE active`).Scan(&aclCount); err == nil && aclCount > 0 {
-		out = append(out, AutoFWRule{Proto: "tcp", Port: 3128, Comment: "Forward-Proxy (Squid)"})
+	// Squid Forward-Proxy: lese Port + Listen-Adressen aus
+	// forward_proxy_settings. Für jede nicht-loopback IP eine
+	// Auto-Rule; leere Liste = alle Interfaces (generische Regel).
+	var squidAddrs string
+	var squidPort int
+	if err := g.Pool.QueryRow(ctx,
+		`SELECT listen_addresses, listen_port FROM forward_proxy_settings WHERE id=1`,
+	).Scan(&squidAddrs, &squidPort); err == nil && squidPort > 0 {
+		addrs := splitCSV(squidAddrs)
+		if len(addrs) == 0 {
+			out = append(out, AutoFWRule{Proto: "tcp", Port: squidPort, Comment: "Forward-Proxy (Squid)"})
+		} else {
+			for _, ip := range addrs {
+				if !isLoopback(ip) {
+					out = append(out, AutoFWRule{Proto: "tcp", Port: squidPort, DstIP: ip, Comment: "Forward-Proxy (Squid) auf " + ip})
+				}
+			}
+		}
 	}
 
 	// WireGuard server-mode: udp <listen_port> pro aktive iface.
@@ -398,7 +419,60 @@ func (g *Generator) loadAutoRules(ctx context.Context) []AutoFWRule {
 		}
 	}
 
-	return out
+	// DHCP (Kea): wenn auf DIESER Node aktiviert → udp/67 pro aktivem
+	// Subnet-Interface (gescopt auf die LAN-iface, NICHT global/WAN).
+	var dhcpEnabled bool
+	if err := g.Pool.QueryRow(ctx, `SELECT enabled FROM dhcp_settings WHERE id=1`).Scan(&dhcpEnabled); err == nil && dhcpEnabled {
+		rows, err := g.Pool.Query(ctx, `SELECT DISTINCT interface_name FROM dhcp_subnets WHERE active AND interface_name <> ''`)
+		if err == nil {
+			defer rows.Close()
+			for rows.Next() {
+				var iface string
+				if rows.Scan(&iface) == nil && iface != "" {
+					out = append(out, AutoFWRule{Proto: "udp", Port: 67, Iface: iface, Comment: "DHCP (Kea) auf " + iface})
+				}
+			}
+		}
+	}
+
+	// RADIUS (FreeRADIUS): wenn aktiviert → udp 1812 (auth) + 1813 (acct).
+	// Pro listen-IP, sonst global. FreeRADIUS verwirft unbekannte Clients selbst.
+	var radiusEnabled bool
+	var radiusListen string
+	if err := g.Pool.QueryRow(ctx, `SELECT enabled, listen_addresses FROM radius_settings WHERE id=1`).Scan(&radiusEnabled, &radiusListen); err == nil && radiusEnabled {
+		ips := splitCSV(radiusListen)
+		emit := func(ip string) {
+			out = append(out,
+				AutoFWRule{Proto: "udp", Port: 1812, DstIP: ip, Comment: "RADIUS-Auth (FreeRADIUS)"},
+				AutoFWRule{Proto: "udp", Port: 1813, DstIP: ip, Comment: "RADIUS-Acct (FreeRADIUS)"},
+			)
+		}
+		if len(ips) == 0 {
+			emit("")
+		} else {
+			for _, ip := range ips {
+				if !isLoopback(ip) && ip != "0.0.0.0" && ip != "::" {
+					emit(ip)
+				}
+			}
+		}
+	}
+
+	// Familien-Tag (ip/ip6) für DstIP-basierte Auto-Rules setzen; eine
+	// IPv6-Listen-Adresse muss `ip6 daddr` ergeben (sonst lehnt nft das
+	// gesamte Ruleset ab). Unparsebare DstIPs werden verworfen.
+	tagged := out[:0]
+	for _, r := range out {
+		if r.DstIP != "" {
+			fam := addrFamily(r.DstIP)
+			if fam == "" {
+				continue
+			}
+			r.L3 = fam
+		}
+		tagged = append(tagged, r)
+	}
+	return tagged
 }
 
 // splitCSV — wie in den Service-renderern.
@@ -422,6 +496,131 @@ func isLoopback(ip string) bool {
 	return strings.HasPrefix(ip, "127.")
 }
 
+// addrFamily klassifiziert einen nft-Adressausdruck (host, CIDR oder
+// range "a-b") als "ip" (IPv4), "ip6" (IPv6) oder "" (unbestimmt, z.B.
+// FQDN-Platzhalter). Adressen enthalten selbst kein '-', daher trennt der
+// erste Bindestrich sicher eine Range in ihr erstes Element.
+func addrFamily(expr string) string {
+	expr = strings.TrimSpace(expr)
+	if expr == "" {
+		return ""
+	}
+	if i := strings.IndexByte(expr, '-'); i > 0 {
+		expr = strings.TrimSpace(expr[:i])
+	}
+	if i := strings.IndexByte(expr, '/'); i > 0 {
+		expr = expr[:i]
+	}
+	ip := net.ParseIP(expr)
+	if ip == nil {
+		return ""
+	}
+	if ip.To4() != nil {
+		return "ip"
+	}
+	return "ip6"
+}
+
+// splitByFamily teilt eine Liste von nft-Adressausdrücken in v4 und v6.
+// Unbestimmte (FQDN o.ä.) werden verworfen.
+func splitByFamily(exprs []string) (v4, v6 []string) {
+	for _, e := range exprs {
+		switch addrFamily(e) {
+		case "ip":
+			v4 = append(v4, e)
+		case "ip6":
+			v6 = append(v6, e)
+		}
+	}
+	return v4, v6
+}
+
+// serviceL3: icmp ist v4-only, icmpv6 v6-only, tcp/udp/leer agnostisch.
+func serviceL3(svc ResolvedService) string {
+	switch svc.Proto {
+	case "icmp":
+		return "ip"
+	case "icmpv6":
+		return "ip6"
+	default:
+		return ""
+	}
+}
+
+// natFamily ermittelt die Adressfamilie einer NAT-Regel aus ihren
+// Adressen. ok=false bei gemischten v4/v6-Adressen (ungültig → die Regel
+// muss übersprungen werden, sonst bricht `nft -f` das gesamte Ruleset).
+func natFamily(r ResolvedNATRule) (fam string, ok bool) {
+	for _, a := range []string{r.SrcCIDR, r.DstCIDR, r.TargetAddr} {
+		f := addrFamily(a)
+		if f == "" {
+			continue
+		}
+		if fam == "" {
+			fam = f
+		} else if fam != f {
+			return "", false
+		}
+	}
+	if fam == "" {
+		fam = "ip" // keine Adressen (reine iface/proto-Regel) → v4-Default
+	}
+	return fam, true
+}
+
+// expandFamilyLegs materialisiert die nft-Zeilen für eine Regel + optional
+// einen Service, getrennt nach Adressfamilie. Adresslose Regeln ergeben eine
+// einzige familienagnostische Zeile (unverändertes v4-Verhalten, greift
+// zugleich für v6). Regeln mit Adressen werden pro Familie als separate
+// Zeile emittiert — ein nft-Paket ist immer entweder v4 oder v6.
+func expandFamilyLegs(r ResolvedRule, svc ResolvedService, hasSvc bool) []RuleLeg {
+	base := RuleLeg{
+		RuleID: r.ID, Action: r.Action, Log: r.Log, Name: r.Name, Comment: r.Comment,
+		SrcIfaces: r.SrcIfaces, DstIfaces: r.DstIfaces,
+	}
+	if hasSvc {
+		base.Service = svc
+	}
+
+	if len(r.SrcAddrs) == 0 && len(r.DstAddrs) == 0 {
+		// Kein Adress-Match → eine Zeile, L3 leer. Die Proto-Render-Logik
+		// im Template setzt icmp/icmpv6 selbst familienkorrekt.
+		return []RuleLeg{base}
+	}
+
+	src4, src6 := splitByFamily(r.SrcAddrs)
+	dst4, dst6 := splitByFamily(r.DstAddrs)
+	svcFam := ""
+	if hasSvc {
+		svcFam = serviceL3(svc)
+	}
+
+	var legs []RuleLeg
+	for _, fam := range []string{"ip", "ip6"} {
+		if svcFam != "" && svcFam != fam {
+			continue // icmp nur auf v4, icmpv6 nur auf v6
+		}
+		srcF, dstF := src4, dst4
+		if fam == "ip6" {
+			srcF, dstF = src6, dst6
+		}
+		// Eine eingeschränkte Seite ohne Mitglied dieser Familie → die
+		// Zeile würde nichts (oder Falsches) matchen → überspringen.
+		if len(r.SrcAddrs) > 0 && len(srcF) == 0 {
+			continue
+		}
+		if len(r.DstAddrs) > 0 && len(dstF) == 0 {
+			continue
+		}
+		leg := base
+		leg.L3 = fam
+		leg.SrcAddrs = srcF
+		leg.DstAddrs = dstF
+		legs = append(legs, leg)
+	}
+	return legs
+}
+
 // addrObjMap is keyed by id; value is the nft expression for that
 // object (e.g. "1.2.3.4", "10.0.0.0/24", "1.2.3.4-1.2.3.10").
 type addrObjMap map[int64]string
@@ -680,6 +879,19 @@ ORDER BY priority DESC, id ASC`)
 		if outZone != nil {
 			r.OutIfaces = zoneIfaces[*outZone]
 		}
+		fam, ok := natFamily(r)
+		if !ok {
+			// Gemischte v4/v6-Adressen → ungültige NAT-Regel. Überspringen
+			// statt das gesamte Ruleset mit `nft -f` zu brechen.
+			slog.Warn("firewall: NAT-Regel mit gemischten v4/v6-Adressen übersprungen", "id", r.ID)
+			continue
+		}
+		r.L3 = fam
+		r.TargetHost = r.TargetAddr
+		if fam == "ip6" && r.TargetAddr != "" && r.TargetPortStart > 0 {
+			// nft braucht [v6]:port für dnat-Targets mit Port.
+			r.TargetHost = "[" + r.TargetAddr + "]"
+		}
 		out = append(out, r)
 	}
 	return out, rows.Err()

internal/firewall/firewall_autorule_test.go

@@ -0,0 +1,64 @@
+package firewall
+
+import (
+	"bytes"
+	"os"
+	"os/exec"
+	"strings"
+	"testing"
+)
+
+// TestTemplate_autoRuleIface prüft, dass eine Auto-Rule mit Iface als
+// `iifname "<x>"`-gescopte Zeile rendert (DHCP udp/67 auf LAN) und dass
+// DstIP-basierte Auto-Rules unverändert bleiben.
+func TestTemplate_autoRuleIface(t *testing.T) {
+	view := &View{
+		AutoRules: []AutoFWRule{
+			{Proto: "udp", Port: 67, Iface: "eth1", Comment: "DHCP (Kea) auf eth1"},
+			{Proto: "udp", Port: 53, DstIP: "10.0.0.1", L3: "ip", Comment: "DNS"},
+			{Proto: "udp", Port: 53, DstIP: "2001:db8::1", L3: "ip6", Comment: "DNS v6"},
+		},
+	}
+	var buf bytes.Buffer
+	if err := tpl.Execute(&buf, view); err != nil {
+		t.Fatalf("template execute: %v", err)
+	}
+	out := buf.String()
+
+	if !strings.Contains(out, `iifname "eth1" udp dport 67 accept comment "auto: DHCP (Kea) auf eth1"`) {
+		t.Errorf("missing iface-scoped DHCP auto-rule\n----\n%s", out)
+	}
+	// v4-DstIP-Auto-Rule: ip daddr.
+	if !strings.Contains(out, `ip daddr 10.0.0.1 udp dport 53 accept`) {
+		t.Errorf("v4 DstIP auto-rule wrong\n----\n%s", out)
+	}
+	// Fix #5: v6-DstIP muss `ip6 daddr` ergeben (sonst bricht nft das Ruleset).
+	if !strings.Contains(out, `ip6 daddr 2001:db8::1 udp dport 53 accept`) {
+		t.Errorf("v6 DstIP auto-rule must use ip6 daddr\n----\n%s", out)
+	}
+
+	// Echte nft-Syntaxvalidierung (braucht root → via sudo, sonst skip).
+	nft, err := exec.LookPath("nft")
+	if err != nil {
+		t.Skip("nft not in PATH")
+	}
+	f, err := os.CreateTemp(t.TempDir(), "autorule-*.nft")
+	if err != nil {
+		t.Fatal(err)
+	}
+	_, _ = f.WriteString(out)
+	f.Close()
+	var cmd *exec.Cmd
+	if os.Geteuid() == 0 {
+		cmd = exec.Command(nft, "-c", "-f", f.Name())
+	} else {
+		cmd = exec.Command("sudo", "-n", nft, "-c", "-f", f.Name())
+	}
+	if combined, err := cmd.CombinedOutput(); err != nil {
+		msg := string(combined)
+		if strings.Contains(msg, "Operation not permitted") || strings.Contains(msg, "password is required") {
+			t.Skipf("nft -c needs root: %s", strings.TrimSpace(msg))
+		}
+		t.Fatalf("nft -c rejected ruleset: %v\n%s\n----\n%s", err, combined, out)
+	}
+}

internal/firewall/firewall_e2e_test.go

@@ -0,0 +1,142 @@
+package firewall
+
+import (
+	"context"
+	"os"
+	"os/exec"
+	"strings"
+	"testing"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+)
+
+// TestE2E_IPv6Render fährt den ECHTEN Generator gegen eine Test-DB:
+// alle Migrations + v4/v6-Seed + RenderToString + nft -c. Nur aktiv, wenn
+// EG_FWTEST_DSN gesetzt ist (sonst Skip — `go test ./...` bleibt DB-frei).
+func TestE2E_IPv6Render(t *testing.T) {
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the firewall end-to-end test")
+	}
+	ctx := context.Background()
+	// Retry: goose-Erst-Apply ist nicht concurrency-safe, wenn mehrere
+	// guarded Test-Pakete dieselbe frische DB parallel migrieren.
+	var mErr error
+	for i := 0; i < 3; i++ {
+		if mErr = database.Migrate(ctx, dsn); mErr == nil {
+			break
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	if mErr != nil {
+		t.Fatalf("migrate: %v", mErr)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	defer pool.Close()
+
+	for _, tbl := range []string{
+		"firewall_nat_rules", "firewall_rules",
+		"firewall_address_group_members", "firewall_address_groups",
+		"firewall_address_objects", "network_interfaces",
+	} {
+		if _, err := pool.Exec(ctx, "DELETE FROM "+tbl); err != nil {
+			t.Fatalf("clean %s: %v", tbl, err)
+		}
+	}
+
+	mustExec := func(sql string, args ...any) {
+		t.Helper()
+		if _, err := pool.Exec(ctx, sql, args...); err != nil {
+			t.Fatalf("seed failed (%s): %v", sql, err)
+		}
+	}
+	insID := func(sql string, args ...any) int64 {
+		t.Helper()
+		var id int64
+		if err := pool.QueryRow(ctx, sql, args...).Scan(&id); err != nil {
+			t.Fatalf("seed-id failed (%s): %v", sql, err)
+		}
+		return id
+	}
+
+	mustExec(`INSERT INTO network_interfaces (name,type,role) VALUES ('eth0','ethernet','wan'),('eth1','ethernet','lan')`)
+
+	v4net := insID(`INSERT INTO firewall_address_objects (name,kind,value) VALUES ('v4net','network','10.0.0.0/24') RETURNING id`)
+	v6net := insID(`INSERT INTO firewall_address_objects (name,kind,value) VALUES ('v6net','network','2001:db8:1::/64') RETURNING id`)
+	v6host := insID(`INSERT INTO firewall_address_objects (name,kind,value) VALUES ('v6host','host','2001:db8:2::5') RETURNING id`)
+	v6range := insID(`INSERT INTO firewall_address_objects (name,kind,value) VALUES ('v6range','range','2001:db8:3::1-2001:db8:3::9') RETURNING id`)
+
+	// Gemischte Gruppe (v4 + v6) → muss in zwei Familien-Zeilen splitten.
+	grp := insID(`INSERT INTO firewall_address_groups (name) VALUES ('mixed') RETURNING id`)
+	mustExec(`INSERT INTO firewall_address_group_members (group_id,object_id) VALUES ($1,$2),($1,$3)`, grp, v4net, v6net)
+
+	httpsSvc := insID(`INSERT INTO firewall_services (name,proto,port_start,port_end,builtin,description) VALUES ('t-https','tcp',443,443,false,'')
+		ON CONFLICT (name) DO UPDATE SET proto=excluded.proto RETURNING id`)
+	var pingV6 int64
+	_ = pool.QueryRow(ctx, `SELECT id FROM firewall_services WHERE proto='icmpv6' LIMIT 1`).Scan(&pingV6)
+
+	// (1) gemischte Gruppe + tcp443 → je eine ip- und ip6-Zeile.
+	mustExec(`INSERT INTO firewall_rules (name,action,src_zone,src_address_group_id,service_object_id) VALUES ('mixed-https','accept','any',$1,$2)`, grp, httpsSvc)
+	// (2) v6-host + icmpv6 → eine ip6-Zeile.
+	if pingV6 != 0 {
+		mustExec(`INSERT INTO firewall_rules (name,action,src_address_object_id,service_object_id) VALUES ('v6-ping','accept',$1,$2)`, v6host, pingV6)
+	}
+	// (3) v6-range src + v6net dst (kein Service).
+	mustExec(`INSERT INTO firewall_rules (name,action,src_address_object_id,dst_address_object_id) VALUES ('v6-range','drop',$1,$2)`, v6range, v6net)
+
+	// (a) v6-DNAT mit Port → dnat to [..]:port.
+	mustExec(`INSERT INTO firewall_nat_rules (name,kind,proto,match_dst_cidr,match_dport_start,target_addr,target_port_start) VALUES ('v6-dnat','dnat','tcp','2001:db8:9::/64',80,'2001:db8:9::2',8080)`)
+	// (b) v4-DNAT (Regression).
+	mustExec(`INSERT INTO firewall_nat_rules (name,kind,proto,match_dst_cidr,match_dport_start,target_addr,target_port_start) VALUES ('v4-dnat','dnat','tcp','1.2.3.4',80,'10.0.0.5',80)`)
+	// (c) gemischte Familie (v4 src, v6 target) → MUSS übersprungen werden.
+	mustExec(`INSERT INTO firewall_nat_rules (name,kind,proto,match_src_cidr,target_addr) VALUES ('mixed-snat','snat','any','10.0.0.0/24','2001:db8::99')`)
+
+	out, err := New(pool).RenderToString(ctx)
+	if err != nil {
+		t.Fatalf("render: %v", err)
+	}
+
+	for _, w := range []string{
+		"ip saddr { 10.0.0.0/24 }",
+		"ip6 saddr { 2001:db8:1::/64 }",
+		"ip6 nexthdr icmpv6",
+		"ip6 saddr { 2001:db8:3::1-2001:db8:3::9 }",
+		"dnat to [2001:db8:9::2]:8080",
+		"dnat to 10.0.0.5:80",
+	} {
+		if !strings.Contains(out, w) {
+			t.Errorf("rendered output missing %q\n----\n%s", w, out)
+		}
+	}
+	if strings.Contains(out, "2001:db8::99") {
+		t.Errorf("mixed-family NAT rule was not skipped\n----\n%s", out)
+	}
+
+	nft, err := exec.LookPath("nft")
+	if err != nil {
+		t.Skip("nft not in PATH — skipping syntax check")
+	}
+	f, err := os.CreateTemp(t.TempDir(), "e2e-*.nft")
+	if err != nil {
+		t.Fatal(err)
+	}
+	_, _ = f.WriteString(out)
+	f.Close()
+	var cmd *exec.Cmd
+	if os.Geteuid() == 0 {
+		cmd = exec.Command(nft, "-c", "-f", f.Name())
+	} else {
+		cmd = exec.Command("sudo", "-n", nft, "-c", "-f", f.Name())
+	}
+	if combined, err := cmd.CombinedOutput(); err != nil {
+		msg := string(combined)
+		if strings.Contains(msg, "Operation not permitted") || strings.Contains(msg, "password is required") {
+			t.Skipf("nft -c needs root (no usable sudo): %s", strings.TrimSpace(msg))
+		}
+		t.Fatalf("nft -c rejected the real-rendered ruleset: %v\n%s\n----\n%s", err, combined, out)
+	}
+}

internal/firewall/firewall_ipv6_test.go

@@ -0,0 +1,183 @@
+package firewall
+
+import (
+	"bytes"
+	"os"
+	"os/exec"
+	"strings"
+	"testing"
+)
+
+func TestAddrFamily(t *testing.T) {
+	cases := map[string]string{
+		"1.2.3.4":                 "ip",
+		"10.0.0.0/24":             "ip",
+		"1.2.3.4-1.2.3.10":        "ip",
+		"2001:db8::1":             "ip6",
+		"fd00::/64":               "ip6",
+		"2001:db8::1-2001:db8::5": "ip6",
+		"example.com":             "",
+		"":                        "",
+	}
+	for in, want := range cases {
+		if got := addrFamily(in); got != want {
+			t.Errorf("addrFamily(%q)=%q want %q", in, got, want)
+		}
+	}
+}
+
+func TestExpandFamilyLegs_splitsByFamily(t *testing.T) {
+	r := ResolvedRule{
+		ID: 1, Action: "accept",
+		SrcAddrs: []string{"10.0.0.0/24", "fd00::/64"},
+		DstAddrs: []string{"1.2.3.4", "2001:db8::1"},
+	}
+	legs := expandFamilyLegs(r, ResolvedService{}, false)
+	if len(legs) != 2 {
+		t.Fatalf("want 2 legs (v4+v6), got %d", len(legs))
+	}
+	var v4, v6 *RuleLeg
+	for i := range legs {
+		switch legs[i].L3 {
+		case "ip":
+			v4 = &legs[i]
+		case "ip6":
+			v6 = &legs[i]
+		}
+	}
+	if v4 == nil || v6 == nil {
+		t.Fatalf("missing family leg: %+v", legs)
+	}
+	if len(v4.SrcAddrs) != 1 || v4.SrcAddrs[0] != "10.0.0.0/24" || v4.DstAddrs[0] != "1.2.3.4" {
+		t.Errorf("v4 leg wrong: src=%v dst=%v", v4.SrcAddrs, v4.DstAddrs)
+	}
+	if len(v6.SrcAddrs) != 1 || v6.SrcAddrs[0] != "fd00::/64" || v6.DstAddrs[0] != "2001:db8::1" {
+		t.Errorf("v6 leg wrong: src=%v dst=%v", v6.SrcAddrs, v6.DstAddrs)
+	}
+}
+
+func TestExpandFamilyLegs_addresslessIsAgnostic(t *testing.T) {
+	legs := expandFamilyLegs(ResolvedRule{ID: 2, Action: "accept"}, ResolvedService{}, false)
+	if len(legs) != 1 || legs[0].L3 != "" {
+		t.Fatalf("addressless rule must be a single agnostic leg, got %d legs L3=%q", len(legs), legs[0].L3)
+	}
+}
+
+func TestExpandFamilyLegs_oneFamilyOnly(t *testing.T) {
+	// src nur v4, dst nur v4 → genau eine v4-Zeile (kein leerer v6-Leg).
+	r := ResolvedRule{ID: 3, Action: "drop", SrcAddrs: []string{"10.0.0.0/8"}}
+	legs := expandFamilyLegs(r, ResolvedService{}, false)
+	if len(legs) != 1 || legs[0].L3 != "ip" {
+		t.Fatalf("v4-only rule want 1 ip leg, got %+v", legs)
+	}
+}
+
+func TestExpandFamilyLegs_icmpFamilyMatch(t *testing.T) {
+	r6 := ResolvedRule{ID: 4, Action: "accept", SrcAddrs: []string{"fd00::/64"}}
+	if legs := expandFamilyLegs(r6, ResolvedService{Proto: "icmpv6"}, true); len(legs) != 1 || legs[0].L3 != "ip6" {
+		t.Fatalf("icmpv6+v6 want 1 ip6 leg, got %+v", legs)
+	}
+	if legs := expandFamilyLegs(r6, ResolvedService{Proto: "icmp"}, true); len(legs) != 0 {
+		t.Fatalf("icmp on v6-only addrs want 0 legs, got %+v", legs)
+	}
+}
+
+func TestNatFamily(t *testing.T) {
+	if _, ok := natFamily(ResolvedNATRule{SrcCIDR: "10.0.0.0/24", TargetAddr: "2001:db8::1"}); ok {
+		t.Error("mixed v4/v6 NAT must be rejected (ok=false)")
+	}
+	if fam, ok := natFamily(ResolvedNATRule{TargetAddr: "2001:db8::1"}); !ok || fam != "ip6" {
+		t.Errorf("v6 NAT: fam=%q ok=%v want ip6/true", fam, ok)
+	}
+	if fam, ok := natFamily(ResolvedNATRule{SrcCIDR: "10.0.0.0/24"}); !ok || fam != "ip" {
+		t.Errorf("v4 NAT: fam=%q ok=%v want ip/true", fam, ok)
+	}
+	if fam, ok := natFamily(ResolvedNATRule{}); !ok || fam != "ip" {
+		t.Errorf("addressless NAT: fam=%q ok=%v want ip/true (v4 default)", fam, ok)
+	}
+}
+
+// renderView ist ein gemischter v4/v6-View, der alle geänderten
+// Template-Zweige berührt.
+func renderView(t *testing.T) string {
+	t.Helper()
+	view := &View{
+		PeerIPv4: []string{"10.0.0.1"},
+		PeerIPv6: []string{"fd00::1"},
+		Legs: []RuleLeg{
+			{RuleID: 1, Action: "accept", L3: "ip", SrcAddrs: []string{"10.0.0.0/24"}, Service: ResolvedService{Proto: "tcp", PortStart: 443}},
+			{RuleID: 1, Action: "accept", L3: "ip6", SrcAddrs: []string{"fd00::/64"}, Service: ResolvedService{Proto: "tcp", PortStart: 443}},
+			{RuleID: 2, Action: "accept", Service: ResolvedService{Proto: "icmpv6"}}, // adresslos, agnostisch
+		},
+		NATRules: []ResolvedNATRule{
+			{ID: 5, Kind: "dnat", L3: "ip6", DstCIDR: "2001:db8::/64", Proto: "tcp", DPortStart: 80, TargetAddr: "fd00::2", TargetHost: "[fd00::2]", TargetPortStart: 8080},
+			{ID: 6, Kind: "snat", L3: "ip6", SrcCIDR: "fd00::/64", TargetAddr: "2001:db8::99"},
+			{ID: 7, Kind: "dnat", L3: "ip", DstCIDR: "1.2.3.4", Proto: "tcp", DPortStart: 80, TargetAddr: "10.0.0.5", TargetHost: "10.0.0.5", TargetPortStart: 80},
+		},
+		WGSiteMasq: []WGSiteMasqEntry{{Iface: "wg7", VPNNet: "fd00:99::/64", L3: "ip6"}},
+	}
+	var buf bytes.Buffer
+	if err := tpl.Execute(&buf, view); err != nil {
+		t.Fatalf("template execute: %v", err)
+	}
+	return buf.String()
+}
+
+func TestTemplate_v6AndV4Render(t *testing.T) {
+	out := renderView(t)
+	mustContain := []string{
+		"ip saddr { 10.0.0.0/24 }",       // v4-Regel unverändert
+		"ip6 saddr { fd00::/64 }",        // v6-Regel
+		"ip6 daddr 2001:db8::/64",        // v6-DNAT-Match
+		"dnat to [fd00::2]:8080",         // v6-DNAT-Target geklammert
+		"dnat to 10.0.0.5:80",            // v4-DNAT-Target unverändert
+		"ip6 saddr fd00::/64 snat to 2001:db8::99",
+		`oifname "wg7" ip6 saddr fd00:99::/64 masquerade`,
+	}
+	for _, w := range mustContain {
+		if !strings.Contains(out, w) {
+			t.Errorf("output missing %q\n----\n%s", w, out)
+		}
+	}
+	// v6-Adressen dürfen NIEMALS in einem ip-saddr/daddr-Set landen.
+	if strings.Contains(out, "ip saddr { fd00") || strings.Contains(out, "ip daddr { fd00") ||
+		strings.Contains(out, "ip saddr { 2001") {
+		t.Errorf("v6 address leaked into IPv4 match\n----\n%s", out)
+	}
+}
+
+// TestTemplate_nftSyntax validiert das gerenderte Ruleset mit `nft -c -f`
+// (Check-Modus, kein Apply). Wird übersprungen, wenn nft nicht installiert
+// ist (z.B. CI ohne nft).
+func TestTemplate_nftSyntax(t *testing.T) {
+	nft, err := exec.LookPath("nft")
+	if err != nil {
+		t.Skip("nft binary not available — skipping syntax check")
+	}
+	out := renderView(t)
+	f, err := os.CreateTemp(t.TempDir(), "ruleset-*.nft")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := f.WriteString(out); err != nil {
+		t.Fatal(err)
+	}
+	f.Close()
+	// `nft -c` liest die Kernel-Ruleset-Cache via netlink → braucht root.
+	// Als nicht-root via sudo -n versuchen; klappt das nicht, skip statt fail
+	// (auf den Nodes rendert/prüft edgeguard ohnehin als root).
+	var cmd *exec.Cmd
+	if os.Geteuid() == 0 {
+		cmd = exec.Command(nft, "-c", "-f", f.Name())
+	} else {
+		cmd = exec.Command("sudo", "-n", nft, "-c", "-f", f.Name())
+	}
+	combined, err := cmd.CombinedOutput()
+	if err != nil {
+		msg := string(combined)
+		if strings.Contains(msg, "Operation not permitted") || strings.Contains(msg, "a password is required") || strings.Contains(msg, "may not run sudo") {
+			t.Skipf("nft -c needs root (no usable sudo): %s", strings.TrimSpace(msg))
+		}
+		t.Fatalf("nft -c -f rejected the generated ruleset: %v\n%s\n----\n%s", err, combined, out)
+	}
+}

internal/firewall/ruleset.nft.tpl

@@ -3,7 +3,8 @@
 # Source: internal/firewall/firewall.go.
 # Re-generate via `edgeguard-ctl render-config` or via API mutations.
 
-flush ruleset
+add table inet edgeguard
+flush table inet edgeguard
 
 table inet edgeguard {
     set peer_ipv4 {
@@ -49,13 +50,18 @@ table inet edgeguard {
         # Cluster-internal: peers reach edgeguard-api over mTLS on :8443
         tcp dport 8443 ip  saddr @peer_ipv4 accept
         tcp dport 8443 ip6 saddr @peer_ipv6 accept
+        # Cluster-internal: PG Logical Replication (:5432) + KeyDB Active-Active (:6379)
+        tcp dport 5432 ip  saddr @peer_ipv4 accept
+        tcp dport 5432 ip6 saddr @peer_ipv6 accept
+        tcp dport 6379 ip  saddr @peer_ipv4 accept
+        tcp dport 6379 ip6 saddr @peer_ipv6 accept
 
         # ── Service-Auto-Rules (DNS/Squid/WG/...) ──
         # Aus dem laufenden Service-State abgeleitet — Operator
         # editiert diese nicht. Wenn der Service entfernt/disabled
         # wird, ist die Rule beim nächsten Render weg.
 {{range .AutoRules}}
-        {{if .DstIP}}ip daddr {{.DstIP}} {{end}}{{.Proto}} dport {{.Port}} accept comment "auto: {{.Comment}}"
+        {{if .Iface}}iifname "{{.Iface}}" {{end}}{{if .DstIP}}{{.L3}} daddr {{.DstIP}} {{end}}{{.Proto}} dport {{.Port}} accept comment "auto: {{.Comment}}"
 {{end}}
 
         # ── Operator-defined rules ──
@@ -65,7 +71,7 @@ table inet edgeguard {
                  die Comment-Zeile angehängt — sonst frisst nft die rule
                  als Teil des # Kommentars). */ -}}
         {{""}}
-        {{if .SrcIfaces}}iifname { {{join .SrcIfaces ", "}} } {{end}}{{if .DstIfaces}}oifname { {{join .DstIfaces ", "}} } {{end}}{{if .SrcAddrs}}ip saddr { {{join .SrcAddrs ", "}} } {{end}}{{if .DstAddrs}}ip daddr { {{join .DstAddrs ", "}} } {{end}}{{with .Service}}{{if and (or (eq .Proto "tcp") (eq .Proto "udp")) .PortStart}}{{.Proto}} dport {{.PortStart}}{{if and .PortEnd (ne .PortEnd .PortStart)}}-{{.PortEnd}}{{end}} {{else if eq .Proto "icmp"}}ip protocol icmp {{else if eq .Proto "icmpv6"}}ip6 nexthdr icmpv6 {{end}}{{end}}{{if .Log}}log prefix "edgeguard:{{.RuleID}} " group 0 {{end}}counter {{.Action}} comment "egid:{{.RuleID}}"
+        {{if .SrcIfaces}}iifname { {{join .SrcIfaces ", "}} } {{end}}{{if .DstIfaces}}oifname { {{join .DstIfaces ", "}} } {{end}}{{if .SrcAddrs}}{{.L3}} saddr { {{join .SrcAddrs ", "}} } {{end}}{{if .DstAddrs}}{{.L3}} daddr { {{join .DstAddrs ", "}} } {{end}}{{with .Service}}{{if and (or (eq .Proto "tcp") (eq .Proto "udp")) .PortStart}}{{.Proto}} dport {{.PortStart}}{{if and .PortEnd (ne .PortEnd .PortStart)}}-{{.PortEnd}}{{end}} {{else if eq .Proto "icmp"}}ip protocol icmp {{else if eq .Proto "icmpv6"}}ip6 nexthdr icmpv6 {{end}}{{end}}{{if .Log}}log prefix "edgeguard:{{.RuleID}} " group 0 {{end}}counter {{.Action}} comment "egid:{{.RuleID}}"
 {{end}}
 
         # ── DEFAULT-DROP LOGGING ───────────────────────────────────────
@@ -95,7 +101,7 @@ table inet edgeguard {
         # nach und erlauben new-state-Pakete von dort. Return-Pakete
         # gehen via ct state established schon durch.
 {{range .NATRules}}{{if or (eq .Kind "snat") (eq .Kind "masquerade")}}{{if .SrcCIDR}}
-        ip saddr {{.SrcCIDR}} ct state new accept comment "auto-forward for NAT rule {{.ID}}"
+        {{.L3}} saddr {{.SrcCIDR}} ct state new accept comment "auto-forward for NAT rule {{.ID}}"
 {{end}}{{end}}{{end}}
 
         # Auto-Forward für WireGuard-Server-Interfaces: Peer-to-Peer-
@@ -122,7 +128,7 @@ table inet edgeguard {
         {{""}}
         {{/* nft-Syntax: erst L3-match (ip saddr/daddr), DANN L4 (tcp/udp dport).
              Sonst quittiert der parser '... unexpected ip' an dieser Stelle. */}}
-        {{if .InIfaces}}iifname { {{join .InIfaces ", "}} } {{end}}{{if .SrcCIDR}}ip saddr {{.SrcCIDR}} {{end}}{{if .DstCIDR}}ip daddr {{.DstCIDR}} {{end}}{{if and .Proto (ne .Proto "any")}}{{.Proto}} {{else}}meta l4proto { tcp, udp } {{end}}{{if .DPortStart}}dport {{.DPortStart}}{{if and .DPortEnd (ne .DPortEnd .DPortStart)}}-{{.DPortEnd}}{{end}} {{end}}{{if .TargetAddr}}dnat to {{.TargetAddr}}{{if .TargetPortStart}}:{{.TargetPortStart}}{{if and .TargetPortEnd (ne .TargetPortEnd .TargetPortStart)}}-{{.TargetPortEnd}}{{end}}{{end}}{{end}}
+        {{if .InIfaces}}iifname { {{join .InIfaces ", "}} } {{end}}{{if .SrcCIDR}}{{.L3}} saddr {{.SrcCIDR}} {{end}}{{if .DstCIDR}}{{.L3}} daddr {{.DstCIDR}} {{end}}{{if and .Proto (ne .Proto "any")}}{{.Proto}} {{else}}meta l4proto { tcp, udp } {{end}}{{if .DPortStart}}dport {{.DPortStart}}{{if and .DPortEnd (ne .DPortEnd .DPortStart)}}-{{.DPortEnd}}{{end}} {{end}}{{if .TargetAddr}}dnat to {{.TargetHost}}{{if .TargetPortStart}}:{{.TargetPortStart}}{{if and .TargetPortEnd (ne .TargetPortEnd .TargetPortStart)}}-{{.TargetPortEnd}}{{end}}{{end}}{{end}}
 {{end}}{{end}}
     }
 
@@ -146,16 +152,16 @@ table inet edgeguard {
         # Masquerade schreibt die Source auf die lokale Tunnel-IP um; Return-Traffic
         # findet so den Weg zurück durch den Tunnel.
 {{range .WGSiteMasq}}
-        oifname "{{.Iface}}" ip saddr {{.VPNNet}} masquerade comment "auto: WireGuard site-to-site masquerade {{.Iface}}"
+        oifname "{{.Iface}}" {{.L3}} saddr {{.VPNNet}} masquerade comment "auto: WireGuard site-to-site masquerade {{.Iface}}"
 {{end}}
 {{range .NATRules}}{{if eq .Kind "snat"}}
         # NAT {{.ID}} (snat{{if .Comment}} — {{.Comment}}{{end}})
         {{""}}
-        {{if .OutIfaces}}oifname { {{join .OutIfaces ", "}} } {{end}}{{if .SrcCIDR}}ip saddr {{.SrcCIDR}} {{end}}{{if .TargetAddr}}snat to {{.TargetAddr}}{{end}}
+        {{if .OutIfaces}}oifname { {{join .OutIfaces ", "}} } {{end}}{{if .SrcCIDR}}{{.L3}} saddr {{.SrcCIDR}} {{end}}{{if .TargetAddr}}snat to {{.TargetAddr}}{{end}}
 {{end}}{{if eq .Kind "masquerade"}}
         # NAT {{.ID}} (masquerade{{if .Comment}} — {{.Comment}}{{end}})
         {{""}}
-        {{if .OutIfaces}}oifname { {{join .OutIfaces ", "}} } {{end}}{{if .SrcCIDR}}ip saddr {{.SrcCIDR}} {{end}}masquerade
+        {{if .OutIfaces}}oifname { {{join .OutIfaces ", "}} } {{end}}{{if .SrcCIDR}}{{.L3}} saddr {{.SrcCIDR}} {{end}}masquerade
 {{end}}{{end}}
     }
 }

internal/freeradius/freeradius.go

@@ -0,0 +1,157 @@
+// Package freeradius renders the FreeRADIUS client + user files from the
+// radius_* tables and manages the freeradius service lifecycle.
+//
+// Two files are rendered (mirrors the multi-file WireGuard renderer):
+//   - clients.conf  — NAS clients (ipaddr + shared secret)
+//   - authorize     — users file ("name" Cleartext-Password := "pw")
+// Both managed under /etc/edgeguard/freeradius/ and symlinked from the
+// distro paths by postinst. Shared secrets / passwords are decrypted via
+// secrets.Box at render time. Service runs ONLY when radius_settings.enabled
+// is true on this node (default off).
+package freeradius
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"strings"
+
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
+	radiussvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/radius"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/secrets"
+)
+
+const (
+	ConfDir       = configgen.EtcEdgeguard + "/freeradius"
+	ClientsPath   = ConfDir + "/clients.conf"
+	AuthorizePath = ConfDir + "/authorize"
+	serviceName   = "freeradius"
+)
+
+type Generator struct {
+	Pool       *pgxpool.Pool
+	Repo       *radiussvc.Repo
+	Box        *secrets.Box
+	SkipReload bool
+}
+
+func New(pool *pgxpool.Pool, box *secrets.Box) *Generator {
+	return &Generator{Pool: pool, Repo: radiussvc.New(pool, box), Box: box}
+}
+
+func (g *Generator) Name() string { return "freeradius" }
+
+// confEscape escaped FreeRADIUS-double-quoted-Strings (Backslash + Quote)
+// und strippt Steuerzeichen (CR/LF) als Defense-in-Depth gegen Zeilen-
+// Injection — die Werte werden zwar schon im Handler validiert.
+func confEscape(s string) string {
+	s = strings.ReplaceAll(s, "\r", "")
+	s = strings.ReplaceAll(s, "\n", "")
+	s = strings.ReplaceAll(s, `\`, `\\`)
+	s = strings.ReplaceAll(s, `"`, `\"`)
+	return s
+}
+
+// buildClients rendert clients.conf. mask=true ersetzt Secrets durch *** (Preview).
+func (g *Generator) buildClients(ctx context.Context, mask bool) (string, error) {
+	clients, err := g.Repo.ListClients(ctx)
+	if err != nil {
+		return "", err
+	}
+	var b bytes.Buffer
+	b.WriteString("# Generated by edgeguard-api — DO NOT EDIT.\n\n")
+	for _, c := range clients {
+		if !c.Active {
+			continue
+		}
+		secret := "***"
+		if !mask {
+			pt, err := g.Box.Open(c.SecretEnc)
+			if err != nil {
+				return "", fmt.Errorf("open secret for client %s: %w", c.Name, err)
+			}
+			secret = string(pt)
+		}
+		fmt.Fprintf(&b, "client %s {\n    ipaddr = %s\n    secret = \"%s\"\n    shortname = %s\n}\n\n",
+			c.Name, c.IPAddr, confEscape(secret), c.Name)
+	}
+	return b.String(), nil
+}
+
+// buildAuthorize rendert die Users-Datei. mask=true ersetzt Passwörter durch ***.
+func (g *Generator) buildAuthorize(ctx context.Context, mask bool) (string, error) {
+	users, err := g.Repo.ListUsers(ctx)
+	if err != nil {
+		return "", err
+	}
+	var b bytes.Buffer
+	b.WriteString("# Generated by edgeguard-api — DO NOT EDIT.\n\n")
+	for _, u := range users {
+		if !u.Active {
+			continue
+		}
+		pw := "***"
+		if !mask {
+			pt, err := g.Box.Open(u.PasswordEnc)
+			if err != nil {
+				return "", fmt.Errorf("open password for user %s: %w", u.Username, err)
+			}
+			pw = string(pt)
+		}
+		fmt.Fprintf(&b, "\"%s\" Cleartext-Password := \"%s\"\n", confEscape(u.Username), confEscape(pw))
+	}
+	return b.String(), nil
+}
+
+// RenderToString liefert beide Dateien (Secrets maskiert) für die Preview.
+func (g *Generator) RenderToString(ctx context.Context) (string, error) {
+	clients, err := g.buildClients(ctx, true)
+	if err != nil {
+		return "", err
+	}
+	authorize, err := g.buildAuthorize(ctx, true)
+	if err != nil {
+		return "", err
+	}
+	return "# ── clients.conf ──\n" + clients + "\n# ── authorize ──\n" + authorize, nil
+}
+
+func (g *Generator) Render(ctx context.Context) error {
+	settings, err := g.Repo.GetSettings(ctx)
+	if err != nil {
+		return fmt.Errorf("get radius settings: %w", err)
+	}
+
+	if !settings.Enabled {
+		if g.SkipReload {
+			return nil
+		}
+		_ = configgen.DisableService(serviceName)
+		_ = configgen.StopService(serviceName)
+		return nil
+	}
+
+	clients, err := g.buildClients(ctx, false)
+	if err != nil {
+		return err
+	}
+	authorize, err := g.buildAuthorize(ctx, false)
+	if err != nil {
+		return err
+	}
+	if err := configgen.AtomicWrite(ClientsPath, []byte(clients), 0o640); err != nil {
+		return fmt.Errorf("write clients.conf: %w", err)
+	}
+	if err := configgen.AtomicWrite(AuthorizePath, []byte(authorize), 0o640); err != nil {
+		return fmt.Errorf("write authorize: %w", err)
+	}
+	if g.SkipReload {
+		return nil
+	}
+	if err := configgen.EnableService(serviceName); err != nil {
+		return err
+	}
+	return configgen.RestartService(serviceName)
+}

internal/freeradius/freeradius_test.go

@@ -0,0 +1,83 @@
+package freeradius
+
+import (
+	"context"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+	radiussvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/radius"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/secrets"
+)
+
+// Guarded integration test: set EG_FWTEST_DSN (sonst skip).
+func TestRender_ClientsAndUsers(t *testing.T) {
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the freeradius renderer test")
+	}
+	ctx := context.Background()
+	var mErr error
+	for i := 0; i < 3; i++ {
+		if mErr = database.Migrate(ctx, dsn); mErr == nil {
+			break
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	if mErr != nil {
+		t.Fatalf("migrate: %v", mErr)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	defer pool.Close()
+
+	for _, q := range []string{`DELETE FROM radius_clients`, `DELETE FROM radius_users`} {
+		if _, err := pool.Exec(ctx, q); err != nil {
+			t.Fatalf("clean: %v", err)
+		}
+	}
+
+	box := secrets.New(t.TempDir() + "/master_key")
+	repo := radiussvc.New(pool, box)
+	if _, err := repo.CreateClient(ctx, "testnas", "10.0.0.0/24", `s3c"ret\x`, true, "lab"); err != nil {
+		t.Fatalf("create client: %v", err)
+	}
+	if _, err := repo.CreateUser(ctx, "alice", "alicepw", true); err != nil {
+		t.Fatalf("create user: %v", err)
+	}
+
+	g := New(pool, box)
+
+	clients, err := g.buildClients(ctx, false)
+	if err != nil {
+		t.Fatalf("buildClients: %v", err)
+	}
+	for _, want := range []string{
+		"client testnas {",
+		"ipaddr = 10.0.0.0/24",
+		`secret = "s3c\"ret\\x"`, // " und \ escaped → Secret-Roundtrip + Escaping
+		"shortname = testnas",
+	} {
+		if !strings.Contains(clients, want) {
+			t.Errorf("clients.conf missing %q\n----\n%s", want, clients)
+		}
+	}
+
+	authorize, err := g.buildAuthorize(ctx, false)
+	if err != nil {
+		t.Fatalf("buildAuthorize: %v", err)
+	}
+	if !strings.Contains(authorize, `"alice" Cleartext-Password := "alicepw"`) {
+		t.Errorf("authorize missing alice entry\n----\n%s", authorize)
+	}
+
+	// Maskierte Preview enthält keine echten Secrets.
+	masked, _ := g.buildClients(ctx, true)
+	if strings.Contains(masked, "s3c") {
+		t.Errorf("masked preview leaked secret:\n%s", masked)
+	}
+}

internal/handlers/auth.go

@@ -60,15 +60,22 @@ func (h *AuthHandler) WithClusterTLS(store *clustertls.Store) *AuthHandler {
 	return h
 }
 
+const totpPendingCookie = "edgeguard_totp_pending"
+
 // Register mounts /auth/login + /logout (public) and /auth/me
 // (gated by requireAuth, passed in as a per-route middleware).
 func (h *AuthHandler) Register(rg *gin.RouterGroup, requireAuth gin.HandlerFunc) {
 	g := rg.Group("/auth")
 	g.POST("/login", h.Login)
 	g.POST("/logout", h.Logout)
+	g.POST("/totp-verify", h.TOTPVerify)
 	g.GET("/me", requireAuth, h.Me)
 	g.POST("/reset-password", h.ResetPassword)
 	g.POST("/change-password", requireAuth, h.ChangePassword)
+	// TOTP self-service (authenticated user manages own 2FA)
+	g.POST("/totp/setup", requireAuth, h.TOTPSetup)
+	g.POST("/totp/confirm", requireAuth, h.TOTPConfirm)
+	g.DELETE("/totp", requireAuth, h.TOTPDisable)
 }
 
 type loginRequest struct {
@@ -77,9 +84,10 @@ type loginRequest struct {
 }
 
 type loginResponse struct {
-	Actor     string    `json:"actor"`
-	Role      string    `json:"role"`
-	ExpiresAt time.Time `json:"expires_at"`
+	Actor        string    `json:"actor"`
+	Role         string    `json:"role"`
+	ExpiresAt    time.Time `json:"expires_at"`
+	TOTPRequired bool      `json:"totp_required,omitempty"`
 }
 
 func (h *AuthHandler) Login(c *gin.Context) {
@@ -101,12 +109,14 @@ func (h *AuthHandler) Login(c *gin.Context) {
 	email := strings.TrimSpace(req.Email)
 	actor, role := "", "admin"
 	remote := c.ClientIP()
+	var totpEnabled bool
+	var viaDB bool // true wenn Rolle/TOTP bereits aus der DB-Row stammen
 
 	// 1. Try DB users table first.
 	if h.Users != nil {
-		u, hash, dbErr := h.Users.FindByEmail(c.Request.Context(), email)
+		ai, dbErr := h.Users.FindForAuth(c.Request.Context(), email)
 		if dbErr == nil {
-			if !u.Active {
+			if !ai.Active {
 				if h.Audit != nil {
 					_ = h.Audit.Log(c.Request.Context(), email, "auth.login.failed",
 						email, gin.H{"reason": "account_disabled", "remote": remote}, h.NodeID)
@@ -114,7 +124,7 @@ func (h *AuthHandler) Login(c *gin.Context) {
 				response.Unauthorized(c, errors.New("account_disabled"))
 				return
 			}
-			if !usersvc.VerifyPassword(hash, req.Password) {
+			if !usersvc.VerifyPassword(ai.PasswordHash, req.Password) {
 				if h.Audit != nil {
 					_ = h.Audit.Log(c.Request.Context(), email, "auth.login.failed",
 						email, gin.H{"reason": "invalid_credentials", "remote": remote}, h.NodeID)
@@ -122,9 +132,11 @@ func (h *AuthHandler) Login(c *gin.Context) {
 				response.Unauthorized(c, errors.New("invalid_credentials"))
 				return
 			}
-			actor = u.Email
-			role = u.Role
-			h.Users.RecordLogin(c.Request.Context(), u.ID)
+			actor = ai.Email
+			role = ai.Role
+			totpEnabled = ai.TOTPEnabled
+			viaDB = true
+			h.Users.RecordLogin(c.Request.Context(), ai.ID)
 		}
 	}
 
@@ -133,16 +145,13 @@ func (h *AuthHandler) Login(c *gin.Context) {
 		if strings.EqualFold(st.AdminEmail, email) && st.VerifyAdminPassword(req.Password) {
 			actor = st.AdminEmail
 			role = "admin"
-			// Auto-migrate: insert the setup-store admin into the DB so it
-			// shows up in user management from this point on.
 			if h.Users != nil {
 				_, _ = h.Users.Upsert(c.Request.Context(), st.AdminEmail, req.Password, "admin", true)
 			}
 		}
 	}
 
-	// 3. Auth federation: cluster nodes forward failed auth to the primary
-	// via mTLS so users can log in with their primary credentials on any node.
+	// 3. Auth federation: cluster nodes forward failed auth to the primary.
 	if actor == "" && st.IsClusterNode && st.PrimaryFQDN != "" && h.ClusterTLS != nil {
 		if a, r, err := h.checkWithPrimary(c.Request.Context(), st.PrimaryFQDN, email, req.Password); err == nil {
 			actor = a
@@ -161,6 +170,33 @@ func (h *AuthHandler) Login(c *gin.Context) {
 		return
 	}
 
+	// Bei Fallback (Setup-Store) / Federation (Primary) stammen role/TOTP
+	// NICHT aus der DB. Rolle + TOTP-Status autoritativ aus der lokalen
+	// (replizierten) users-Row ableiten — damit 2FA greift und die Rolle
+	// nie aus einer Remote-Payload kommt. Ist der User lokal (noch) nicht
+	// vorhanden (Replikations-Lag/DB aus), bleibt es beim Fallback-Wert.
+	if actor != "" && !viaDB && h.Users != nil {
+		if ai, err := h.Users.FindForAuth(c.Request.Context(), actor); err == nil {
+			role = ai.Role
+			totpEnabled = ai.TOTPEnabled
+		}
+	}
+
+	// TOTP gate: password OK but 2FA required → issue a short-lived pending
+	// cookie and tell the UI to show the TOTP input.
+	if totpEnabled {
+		pending, ptok, err := h.Signer.IssueWithRoleTTL(actor, "totp_pending", 2*time.Minute)
+		if err != nil {
+			response.Internal(c, err)
+			return
+		}
+		c.SetSameSite(http.SameSiteStrictMode)
+		c.SetCookie(totpPendingCookie, pending, int(2*time.Minute/time.Second), "/", "", true, true)
+		_ = ptok
+		response.OK(c, loginResponse{TOTPRequired: true})
+		return
+	}
+
 	raw, tok, err := h.Signer.IssueWithRole(actor, role)
 	if err != nil {
 		response.Internal(c, err)
@@ -179,6 +215,146 @@ func (h *AuthHandler) Login(c *gin.Context) {
 	})
 }
 
+type totpVerifyRequest struct {
+	Code string `json:"code" binding:"required"`
+}
+
+// TOTPVerify completes the two-step login: verifies the TOTP code from the
+// pending cookie and, on success, issues a full session JWT.
+func (h *AuthHandler) TOTPVerify(c *gin.Context) {
+	var req totpVerifyRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	pendingRaw, err := c.Cookie(totpPendingCookie)
+	if err != nil || pendingRaw == "" {
+		response.Unauthorized(c, errors.New("no_pending_totp"))
+		return
+	}
+	ptok, err := h.Signer.Verify(pendingRaw)
+	if err != nil || ptok.Role != "totp_pending" {
+		response.Unauthorized(c, errors.New("invalid_pending_token"))
+		return
+	}
+
+	if h.Users == nil {
+		response.Internal(c, errors.New("users repo unavailable"))
+		return
+	}
+	ai, err := h.Users.FindForAuth(c.Request.Context(), ptok.Actor)
+	if err != nil || !ai.TOTPEnabled || ai.TOTPSecret == nil {
+		response.Unauthorized(c, errors.New("totp_not_configured"))
+		return
+	}
+	if !usersvc.VerifyTOTP(*ai.TOTPSecret, req.Code) {
+		if h.Audit != nil {
+			_ = h.Audit.Log(c.Request.Context(), ptok.Actor, "auth.totp.failed",
+				ptok.Actor, gin.H{"remote": c.ClientIP()}, h.NodeID)
+		}
+		response.Unauthorized(c, errors.New("invalid_totp_code"))
+		return
+	}
+
+	// Clear pending cookie, issue full session.
+	c.SetSameSite(http.SameSiteStrictMode)
+	c.SetCookie(totpPendingCookie, "", -1, "/", "", true, true)
+
+	raw, tok, err := h.Signer.IssueWithRole(ptok.Actor, ai.Role)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	setSessionCookie(c, raw, tok.Exp)
+
+	if h.Audit != nil {
+		_ = h.Audit.Log(c.Request.Context(), ptok.Actor, "auth.login.success",
+			ptok.Actor, gin.H{"role": ai.Role, "remote": c.ClientIP(), "totp": true}, h.NodeID)
+	}
+	response.OK(c, loginResponse{
+		Actor:     tok.Actor,
+		Role:      tok.Role,
+		ExpiresAt: time.Unix(tok.Exp, 0).UTC(),
+	})
+}
+
+// TOTPSetup generates a new TOTP secret for the authenticated user and returns
+// the provisioning URI (renders as QR code in the UI). Secret is not saved yet.
+func (h *AuthHandler) TOTPSetup(c *gin.Context) {
+	tok := CurrentToken(c)
+	if tok == nil {
+		response.Unauthorized(c, nil)
+		return
+	}
+	secret, uri, err := usersvc.GenerateTOTPSecret(tok.Actor)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"secret": secret, "uri": uri})
+}
+
+type totpConfirmRequest struct {
+	Secret string `json:"secret" binding:"required"`
+	Code   string `json:"code"   binding:"required"`
+}
+
+// TOTPConfirm verifies the code against the provisioned secret and, on success,
+// enables TOTP for the user.
+func (h *AuthHandler) TOTPConfirm(c *gin.Context) {
+	var req totpConfirmRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	tok := CurrentToken(c)
+	if tok == nil || h.Users == nil {
+		response.Unauthorized(c, nil)
+		return
+	}
+	u, _, err := h.Users.FindByEmail(c.Request.Context(), tok.Actor)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	if err := h.Users.ConfirmTOTP(c.Request.Context(), u.ID, req.Secret, req.Code); err != nil {
+		if err.Error() == "invalid_totp_code" {
+			response.Err(c, http.StatusUnprocessableEntity, err)
+			return
+		}
+		response.Internal(c, err)
+		return
+	}
+	if h.Audit != nil {
+		_ = h.Audit.Log(c.Request.Context(), tok.Actor, "auth.totp.enabled",
+			tok.Actor, nil, h.NodeID)
+	}
+	response.OK(c, gin.H{"ok": true})
+}
+
+// TOTPDisable disables TOTP for the authenticated user.
+func (h *AuthHandler) TOTPDisable(c *gin.Context) {
+	tok := CurrentToken(c)
+	if tok == nil || h.Users == nil {
+		response.Unauthorized(c, nil)
+		return
+	}
+	u, _, err := h.Users.FindByEmail(c.Request.Context(), tok.Actor)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	if err := h.Users.DisableTOTP(c.Request.Context(), u.ID); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	if h.Audit != nil {
+		_ = h.Audit.Log(c.Request.Context(), tok.Actor, "auth.totp.disabled",
+			tok.Actor, nil, h.NodeID)
+	}
+	response.OK(c, gin.H{"ok": true})
+}
+
 func (h *AuthHandler) Logout(c *gin.Context) {
 	clearSessionCookie(c)
 	response.OK(c, gin.H{"logged_out": true})

internal/handlers/cluster.go

@@ -7,6 +7,9 @@ import (
 	"encoding/pem"
 	"fmt"
 	"log/slog"
+	"net/http"
+	"os"
+	"os/exec"
 	"strings"
 	"time"
 
@@ -18,6 +21,7 @@ import (
 	"git.netcell-it.de/projekte/edgeguard-native/internal/cluster/jointoken"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/audit"
 )
 
 // ClusterHandler exposes cluster-state endpoints. /status ist die
@@ -31,6 +35,7 @@ type ClusterHandler struct {
 	Store      *cluster.Store
 	LocalID    string
 	Aggregator *aggregator.Aggregator
+	Version    string // laufende Binary-Version, für Rolling-Update-Koordination
 
 	// TLSStore + Tokens: optional, gesetzt bei Phase 3.4. Erlauben das
 	// Generieren von Join-Tokens und das Issue-Cert für joining Peers.
@@ -40,6 +45,11 @@ type ClusterHandler struct {
 	// PeerReloader: optional, gesetzt bei Phase 3.5. Nach Auto-Register
 	// triggert das den firewall-Render damit peer_ipv4 frisch ist.
 	PeerReloader PeerReloader
+
+	// Audit + NodeID: optional, gesetzt via WithAudit. Nötig für
+	// protokollierte, mutierende Aktionen wie den Replication-Repair.
+	Audit  *audit.Repo
+	NodeID string
 }
 
 func NewClusterHandler(store *cluster.Store, localID string) *ClusterHandler {
@@ -61,12 +71,27 @@ func (h *ClusterHandler) WithJoinFlow(store *clustertls.Store, tokens *jointoken
 	return h
 }
 
+// WithAudit setzt den Audit-Repo + NodeID für protokollierte Aktionen.
+func (h *ClusterHandler) WithAudit(a *audit.Repo, nodeID string) *ClusterHandler {
+	h.Audit = a
+	h.NodeID = nodeID
+	return h
+}
+
 func (h *ClusterHandler) Register(rg *gin.RouterGroup) {
 	g := rg.Group("/cluster")
 	g.GET("/nodes", h.ListNodes)
 	g.GET("/status", h.Status)
 	g.GET("/system/load", h.SystemLoad)
 	g.DELETE("/nodes/:id", h.DeleteNode)
+	g.GET("/vip-settings", h.GetVIPSettings)
+	g.PUT("/vip-settings", h.UpdateVIPSettings)
+	g.POST("/rolling-update", h.RollingUpdate)
+	g.GET("/rolling-update/status", h.RollingUpdateStatus)
+	g.POST("/repair-replication", h.RepairReplication)
+	g.GET("/repair-replication/status", h.RepairReplicationStatus)
+	g.GET("/vip-status", h.VIPStatus)
+	g.POST("/vip-test", h.VIPTest)
 	if h.TLSStore != nil {
 		g.GET("/cert-status", h.CertStatus)
 		g.POST("/renew-self", h.RenewSelf)
@@ -115,6 +140,85 @@ func (h *ClusterHandler) DeleteNode(c *gin.Context) {
 	response.NoContent(c)
 }
 
+// GetVIPSettings liest die cluster_settings-Singleton-Row (VIP/VRRP-Config).
+func (h *ClusterHandler) GetVIPSettings(c *gin.Context) {
+	if h.Store == nil {
+		response.NotFound(c, simpleError("cluster store not available"))
+		return
+	}
+	var cs vipSettingsRow
+	row := h.Store.Pool.QueryRow(c.Request.Context(), `
+		SELECT vip_address, vip_interface, vip_auth_pass, vrrp_router_id,
+		       hb_interface, hb_src_ip, hb_peer_ip, hb_router_id, gw_check_ip
+		FROM cluster_settings WHERE id = 1`)
+	if err := row.Scan(&cs.VIPAddress, &cs.VIPInterface, &cs.VIPAuthPass, &cs.VRRPRouterID,
+		&cs.HBInterface, &cs.HBSrcIP, &cs.HBPeerIP, &cs.HBRouterID, &cs.GWCheckIP); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, cs)
+}
+
+// UpdateVIPSettings speichert die VIP/VRRP-Konfiguration und triggert
+// einen Keepalived-Config-Render. Viewer-Schutz via RequireAdminForMutations-
+// Middleware auf der authed-Group — kein Extra-Check nötig.
+func (h *ClusterHandler) UpdateVIPSettings(c *gin.Context) {
+	var req vipSettingsRow
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if h.Store == nil {
+		response.NotFound(c, simpleError("cluster store not available"))
+		return
+	}
+	_, err := h.Store.Pool.Exec(c.Request.Context(), `
+		UPDATE cluster_settings
+		SET vip_address=$1, vip_interface=$2, vip_auth_pass=$3, vrrp_router_id=$4,
+		    hb_interface=$5, hb_src_ip=$6, hb_peer_ip=$7, hb_router_id=$8, gw_check_ip=$9,
+		    updated_at=NOW()
+		WHERE id=1`,
+		nullIfEmpty(req.VIPAddress), nullIfEmpty(req.VIPInterface),
+		nullIfEmpty(req.VIPAuthPass), req.VRRPRouterID,
+		nullIfEmpty(req.HBInterface), nullIfEmpty(req.HBSrcIP),
+		nullIfEmpty(req.HBPeerIP), req.HBRouterID, nullIfEmpty(req.GWCheckIP))
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	slog.Info("cluster: VIP settings updated", "vip", req.VIPAddress, "actor", actorOf(c))
+	// Keepalived-Config asynchron neu rendern
+	if h.PeerReloader != nil {
+		go func() {
+			rctx, cancel := context.WithTimeout(context.Background(), 15*time.Second)
+			defer cancel()
+			if err := h.PeerReloader(rctx); err != nil {
+				slog.Warn("cluster: keepalived render after VIP update failed", "error", err)
+			}
+		}()
+	}
+	response.NoContent(c)
+}
+
+type vipSettingsRow struct {
+	VIPAddress   *string `json:"vip_address"`
+	VIPInterface *string `json:"vip_interface"`
+	VIPAuthPass  *string `json:"vip_auth_pass"`
+	VRRPRouterID int     `json:"vrrp_router_id"`
+	HBInterface  *string `json:"hb_interface"`
+	HBSrcIP      *string `json:"hb_src_ip"`
+	HBPeerIP     *string `json:"hb_peer_ip"`
+	HBRouterID   int     `json:"hb_router_id"`
+	GWCheckIP    *string `json:"gw_check_ip"`
+}
+
+func nullIfEmpty(s *string) *string {
+	if s == nil || *s == "" {
+		return nil
+	}
+	return s
+}
+
 // RegisterPublic mountet die public (unauth) Endpoints — joining Peers
 // haben noch keine Session/Cert, deshalb läuft /issue-cert vor der
 // requireAuth-Middleware. Aufrufer muss diesen Group auf /api/v1 setzen
@@ -139,6 +243,15 @@ func (h *ClusterHandler) RegisterAgent(rg *gin.RouterGroup) {
 	g := rg.Group("/agent/cluster")
 	g.POST("/peers", h.AgentRegisterPeer)
 	g.GET("/identity", h.AgentIdentity)
+	g.GET("/pg-replication-info", h.AgentPGReplicationInfo)
+	g.GET("/master-key", h.AgentMasterKey)
+	g.GET("/version", h.AgentVersion)
+	g.POST("/trigger-update", h.AgentTriggerUpdate)
+	g.GET("/active-ips", h.AgentActiveIPs)
+	g.POST("/vip-cmd", h.AgentVIPCmd)
+	g.GET("/tls-certs", h.AgentTLSCerts)
+	g.POST("/repair-replication", h.AgentRepairReplication)
+	g.GET("/repair-replication/status", h.AgentRepairReplicationStatus)
 }
 
 // AgentIdentity gibt die eigene ha_nodes-Row zurück. Wird vom Primary
@@ -161,6 +274,59 @@ func (h *ClusterHandler) AgentIdentity(c *gin.Context) {
 	response.OK(c, node)
 }
 
+// AgentPGReplicationInfo gibt die Replication-Credentials für pg_basebackup
+// zurück. Nur über den mTLS-Agent-Listener erreichbar. Liest das Passwort
+// aus /var/lib/edgeguard/pg-replication-secret. Gibt 404 zurück wenn die
+// Datei fehlt (cluster-init-replication noch nicht ausgeführt).
+func (h *ClusterHandler) AgentPGReplicationInfo(c *gin.Context) {
+	const secretPath = "/var/lib/edgeguard/pg-replication-secret"
+	pass, err := readFileString(secretPath)
+	if err != nil {
+		response.NotFound(c, simpleError("pg-replication-secret nicht gefunden — cluster-init-replication auf dem Primary ausführen"))
+		return
+	}
+	// Host = eigene Public-IP aus ha_nodes (oder Fallback: FQDN)
+	host := ""
+	if h.Store != nil && h.LocalID != "" {
+		if node, err := h.Store.Get(c.Request.Context(), h.LocalID); err == nil {
+			if node.PublicIP != nil && *node.PublicIP != "" {
+				host = *node.PublicIP
+			}
+			if host == "" {
+				host = node.FQDN
+			}
+		}
+	}
+	response.OK(c, gin.H{
+		"host":     host,
+		"port":     5432,
+		"user":     "edgeguard_replicator",
+		"password": strings.TrimSpace(pass),
+	})
+}
+
+// AgentMasterKey gibt den Secrets-Master-Key zurück, damit cluster-setup-standby
+// ihn auf dem Secondary synchronisieren kann. Nur über den mTLS-Agent-Listener
+// erreichbar. Ohne gemeinsamen Master-Key können replizierte verschlüsselte
+// Felder (WireGuard private keys, PSKs) auf dem Secondary nicht entschlüsselt werden.
+func (h *ClusterHandler) AgentMasterKey(c *gin.Context) {
+	const keyPath = "/var/lib/edgeguard/.master_key"
+	data, err := os.ReadFile(keyPath)
+	if err != nil {
+		response.NotFound(c, simpleError("master key nicht gefunden"))
+		return
+	}
+	response.OK(c, gin.H{"key_hex": fmt.Sprintf("%x", data)})
+}
+
+func readFileString(path string) (string, error) {
+	b, err := os.ReadFile(path)
+	if err != nil {
+		return "", err
+	}
+	return string(b), nil
+}
+
 // PeerReloader: optionale Funktion die nach einem Auto-Register
 // Firewall + ggfs. andere Configs regeneriert (damit peer_ipv4-Set
 // frisch ist). Wird vom main.go gesetzt.
@@ -172,6 +338,12 @@ func (h *ClusterHandler) WithPeerReloader(r PeerReloader) *ClusterHandler {
 	return h
 }
 
+// WithVersion: setzt die laufende Binary-Version für Rolling-Update-Koordination.
+func (h *ClusterHandler) WithVersion(v string) *ClusterHandler {
+	h.Version = v
+	return h
+}
+
 func (h *ClusterHandler) ListNodes(c *gin.Context) {
 	nodes, err := h.Store.List(c.Request.Context())
 	if err != nil {
@@ -482,6 +654,14 @@ func (h *ClusterHandler) preRegisterJoiner(parent context.Context, clientIP, csr
 	slog.Info("cluster: joiner pre-registered, firewall updated", "fqdn", fqdn, "ip", clientIP)
 }
 
+// ptrStr dereferences a *string safely for comparison; nil → "".
+func ptrStr(s *string) string {
+	if s == nil {
+		return ""
+	}
+	return *s
+}
+
 // cnFromCSR extracts the Subject Common Name from a PEM-encoded CSR.
 // Returns empty string on any parse error.
 func cnFromCSR(csrPEM string) string {
@@ -555,6 +735,60 @@ func (h *ClusterHandler) reconcileJoiningPeers(placeholders []models.HANode) {
 	}
 }
 
+// AgentVersion gibt die laufende Binary-Version zurück. Wird vom Rolling-
+// Update-Orchestrator gepollt um zu erkennen wann der Secondary die neue
+// Version hat.
+func (h *ClusterHandler) AgentVersion(c *gin.Context) {
+	response.OK(c, gin.H{"version": h.Version})
+}
+
+// AgentTriggerUpdate startet den Upgrade-Prozess auf diesem Node via
+// systemd-run (detached). Wird vom Primary via mTLS aufgerufen um den
+// Secondary zuerst zu aktualisieren (Rolling-Update). Pattern identisch
+// zu /system/upgrade — nutzt dieselbe Sudoers-Whitelist aus dem postinst.
+func (h *ClusterHandler) AgentTriggerUpdate(c *gin.Context) {
+	const scriptPath = "/var/lib/edgeguard/upgrade.sh"
+	const script = `#!/bin/bash
+set -e
+sleep 2
+export DEBIAN_FRONTEND=noninteractive
+dpkg --configure -a || true
+retry_apt() {
+    local attempt=0 max=3 wait_for=15
+    while [ $attempt -lt $max ]; do
+        attempt=$((attempt + 1))
+        apt-get update -qq || true
+        if apt-get install -y -qq -o Dpkg::Options::=--force-confold \
+            edgeguard-api edgeguard-ui edgeguard; then return 0; fi
+        [ $attempt -lt $max ] && sleep $wait_for && wait_for=$((wait_for * 2))
+    done
+    return 1
+}
+retry_apt
+echo "[upgrade] complete"
+rm -f /var/lib/edgeguard/upgrade.sh
+`
+	if err := os.WriteFile(scriptPath, []byte(script), 0o755); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	const unitName = "edgeguard-upgrade.service"
+	_ = exec.Command("sudo", "-n", "/usr/bin/systemctl", "reset-failed", unitName).Run()
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemd-run",
+		"--unit="+unitName,
+		"--description=EdgeGuard self-upgrade",
+		"--collect",
+		"bash", scriptPath)
+	if err := cmd.Run(); err != nil {
+		slog.Warn("cluster: AgentTriggerUpdate: systemd-run failed", "error", err)
+		response.Internal(c, err)
+		return
+	}
+	slog.Info("cluster: rolling update triggered on this node by primary mTLS call",
+		"client", c.ClientIP())
+	c.JSON(http.StatusAccepted, gin.H{"status": "upgrading"})
+}
+
 var errInvalidJoinRequest = simpleError("missing token or csr")
 
 type simpleError string
@@ -623,14 +857,15 @@ func (h *ClusterHandler) RenewSelf(c *gin.Context) {
 // die wir wirklich brauchen — sonst kann ein joining Peer beliebige
 // ha_nodes-Felder überschreiben.
 type registerPeerRequest struct {
-	ID         string `json:"id"`           // Joiner's eigene node-id
-	Name       string `json:"name"`         // hostname
-	FQDN       string `json:"fqdn"`         // sollte mit Client-Cert-CN matchen
-	APIURL     string `json:"api_url"`      // https://<fqdn>
-	PublicIP   string `json:"public_ip"`    // optional
-	InternalIP string `json:"internal_ip"`  // mTLS-Listener-IP (für peer_ipv4-Set)
-	MgmtIP     string `json:"mgmt_ip"`      // optional
-	Version    string `json:"version"`
+	ID         string  `json:"id"`           // Joiner's eigene node-id
+	Name       string  `json:"name"`         // hostname
+	FQDN       string  `json:"fqdn"`         // sollte mit Client-Cert-CN matchen
+	APIURL     string  `json:"api_url"`      // https://<fqdn>
+	PublicIP   string  `json:"public_ip"`    // optional
+	InternalIP string  `json:"internal_ip"`  // mTLS-Listener-IP (für peer_ipv4-Set)
+	MgmtIP     string  `json:"mgmt_ip"`      // optional
+	Version    string  `json:"version"`
+	ConfigHash *string `json:"config_hash"`  // nil=absent (don't change), ""=no user config
 }
 
 // AgentRegisterPeer: vom Joiner nach issue-cert via mTLS aufgerufen.
@@ -693,23 +928,34 @@ func (h *ClusterHandler) AgentRegisterPeer(c *gin.Context) {
 		v := req.Version
 		n.Version = &v
 	}
+	if req.ConfigHash != nil {
+		n.ConfigHash = req.ConfigHash
+	}
 	// Placeholder zuerst löschen: ha_nodes hat UNIQUE(fqdn). Der INSERT
 	// in UpsertSelf verwendet ON CONFLICT(id) — greift NICHT bei fqdn-
 	// Konflikten. Ohne das Delete würde der INSERT mit "duplicate key on
 	// ha_nodes_fqdn_unique" scheitern und der Peer bliebe ewig "joining".
 	_ = h.Store.DeletePlaceholdersByFQDN(c.Request.Context(), req.FQDN, req.ID)
 
+	// Snapshot der aktuellen IPs VOR dem Upsert — zum Vergleich danach.
+	// Nur wenn sich public_ip oder internal_ip ändert, müssen wir nftables
+	// neu laden (@peer_ipv4-Set). Periodische Pushes vom Secondary (alle
+	// 5 min) ändern nur version/config_hash, nicht die IPs → kein Reset.
+	existing, _ := h.Store.Get(c.Request.Context(), req.ID)
+
 	out, err := h.Store.UpsertSelf(c.Request.Context(), n)
 	if err != nil {
 		response.Internal(c, err)
 		return
 	}
 
-	// Firewall-Reload damit peer_ipv4-Set die neue IP aufnimmt. Best-
-	// effort: Fehler loggen, Response weiter durchreichen — der Peer
-	// hat seine Identity erfolgreich registriert, Operator kann manuell
-	// nachrendern.
-	if h.PeerReloader != nil {
+	// Firewall-Reload nur wenn sich die Peer-IP geändert hat oder der
+	// Peer neu eingetragen wurde. Verhindert Counter-Reset alle 5 min
+	// durch den periodischen Secondary-Push (runPrimaryPush).
+	ipChanged := existing == nil ||
+		ptrStr(existing.PublicIP) != ptrStr(out.PublicIP) ||
+		ptrStr(existing.InternalIP) != ptrStr(out.InternalIP)
+	if ipChanged && h.PeerReloader != nil {
 		go func() {
 			rctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
 			defer cancel()

internal/handlers/cluster_certsync.go

@@ -0,0 +1,118 @@
+package handlers
+
+import (
+	"bytes"
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"log/slog"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/aggregator"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+const tlsCertDir = "/etc/edgeguard/tls"
+
+// AgentTLSCerts liefert alle .pem-Dateien aus /etc/edgeguard/tls/ als
+// Base64-Map. Wird vom Secondary via mTLS aufgerufen um Zertifikate
+// des Primary zu spiegeln.
+func (h *ClusterHandler) AgentTLSCerts(c *gin.Context) {
+	entries, err := os.ReadDir(tlsCertDir)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	certs := make(map[string]string, len(entries))
+	for _, e := range entries {
+		if e.IsDir() || !strings.HasSuffix(e.Name(), ".pem") {
+			continue
+		}
+		data, err := os.ReadFile(filepath.Join(tlsCertDir, e.Name()))
+		if err != nil {
+			continue
+		}
+		certs[e.Name()] = base64.StdEncoding.EncodeToString(data)
+	}
+	response.OK(c, gin.H{"certs": certs})
+}
+
+// SyncTLSCertsFromPrimary holt alle TLS-Zertifikate vom Primary via mTLS
+// und schreibt geänderte Dateien nach /etc/edgeguard/tls/. Relädt HAProxy
+// wenn mindestens ein Zertifikat aktualisiert wurde.
+//
+// Läuft auf dem Secondary bei jedem runSecondaryConfigRender-Tick —
+// nicht hash-gated, da certbot-Renewals den config_hash nicht ändern.
+func SyncTLSCertsFromPrimary(ctx context.Context, pool *pgxpool.Pool, agg *aggregator.Aggregator, localID string) error {
+	if agg == nil {
+		return nil
+	}
+	// Primary-Peer aus ha_nodes ermitteln
+	rows, err := pool.Query(ctx,
+		`SELECT id, fqdn, api_url FROM ha_nodes WHERE id != $1 LIMIT 1`, localID)
+	if err != nil {
+		return err
+	}
+	defer rows.Close()
+	var primary *models.HANode
+	for rows.Next() {
+		n := &models.HANode{}
+		if err := rows.Scan(&n.ID, &n.FQDN, &n.APIURL); err != nil {
+			continue
+		}
+		primary = n
+	}
+	if primary == nil {
+		return nil // kein Peer → Single-Node
+	}
+
+	results := agg.FanOut(ctx, []models.HANode{*primary}, "/agent/cluster/tls-certs", localID)
+	if len(results) == 0 || !results[0].OK {
+		return nil // Primary nicht erreichbar — nächster Tick
+	}
+
+	var payload struct {
+		Certs map[string]string `json:"certs"`
+	}
+	if err := json.Unmarshal(results[0].Data, &payload); err != nil {
+		return err
+	}
+
+	if err := os.MkdirAll(tlsCertDir, 0o750); err != nil {
+		return err
+	}
+
+	changed := false
+	for name, b64 := range payload.Certs {
+		data, err := base64.StdEncoding.DecodeString(b64)
+		if err != nil {
+			slog.Warn("cert-sync: base64 decode failed", "file", name, "error", err)
+			continue
+		}
+		path := filepath.Join(tlsCertDir, name)
+		existing, readErr := os.ReadFile(path)
+		if readErr == nil && bytes.Equal(existing, data) {
+			continue // unverändert
+		}
+		if err := os.WriteFile(path, data, 0o640); err != nil {
+			slog.Warn("cert-sync: write failed", "file", name, "error", err)
+			continue
+		}
+		changed = true
+		slog.Info("cert-sync: updated", "file", name)
+	}
+
+	if changed {
+		if err := exec.Command("sudo", "-n", "/usr/bin/systemctl", "reload", "haproxy.service").Run(); err != nil {
+			slog.Warn("cert-sync: haproxy reload failed", "error", err)
+		}
+	}
+	return nil
+}

internal/handlers/cluster_repair.go

@@ -0,0 +1,403 @@
+package handlers
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"log/slog"
+	"os"
+	"os/exec"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/gin-gonic/gin"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+// Replication-Repair ("Resync erzwingen") für das Config-Drift-Banner.
+//
+// Drift entsteht, wenn ein Peer einen anderen config_hash hat als dieser
+// Node — entweder weil die Logical-Replication-Subscription gestört ist
+// oder weil direkt in die DB des Subscribers geschrieben wurde. Die
+// Reparatur baut die Subscription neu auf und kopiert alle geteilten
+// Tabellen frisch vom Primary (einseitig: Primary = Source of Truth).
+//
+// Rollen-Erkennung: NICHT über ha_nodes.role/pg_role — die sind je Node
+// lokal und unzuverlässig (jede Node markiert sich selbst, pg_role bleibt
+// 'standalone' bis `promote`). Verlässlich ist die PUBLICATION: nur der
+// Primary hat `edgeguard_shared` (pg_publication ist für jeden DB-User
+// lesbar). Der Subscriber hat sie nicht → er ist das Resync-Ziel.
+//
+// Ablauf:
+//   - Klick auf dem Primary → Dispatch via mTLS an den Peer
+//     (POST /agent/cluster/repair-replication) mit der eigenen Adresse als
+//     primary_host; der Peer resynct von dort.
+//   - Klick direkt auf dem Subscriber → läuft lokal (Quelle = der Peer).
+//
+// Die eigentliche Arbeit läuft — analog zum Rolling-Update — in einer
+// transienten systemd-Unit, die `edgeguard-ctl cluster-setup-standby
+// <primary>` ausführt.
+
+const (
+	repairUnitName   = "edgeguard-repair-replication.service"
+	repairScriptPath = "/var/lib/edgeguard/repair-replication.sh"
+	repairAgentPath  = "/agent/cluster/repair-replication"
+	repairPubName    = "edgeguard_shared" // muss zu cmd/edgeguard-ctl egPubName passen
+)
+
+// validRepairHost erlaubt nur IPv4/IPv6/Hostnamen — der Wert landet in
+// einem Bash-Script das als root läuft, also strikt validieren.
+var validRepairHost = regexp.MustCompile(`^[A-Za-z0-9._:-]{1,253}$`)
+
+// repairDispatchBody ist der Body des Agent-Dispatch: der Primary teilt
+// dem Subscriber seine Adresse mit, von der resynct werden soll.
+type repairDispatchBody struct {
+	PrimaryHost string `json:"primary_host"`
+}
+
+// RepairReplication ist der UI-Endpoint. Hat dieser Node die Publication
+// (= Primary), wird der Resync an den Peer delegiert; sonst (Subscriber)
+// läuft er lokal mit dem Peer als Quelle.
+func (h *ClusterHandler) RepairReplication(c *gin.Context) {
+	if h.Store == nil {
+		response.Internal(c, errors.New("cluster store unavailable"))
+		return
+	}
+	ctx := c.Request.Context()
+	all, err := h.Store.List(ctx)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	local := findNode(all, h.LocalID)
+	peer := findOtherPeer(all, h.LocalID)
+	if peer == nil {
+		response.BadRequest(c, errors.New("kein Peer-Node im Cluster — nichts zu resyncen"))
+		return
+	}
+
+	isPrimary, err := h.nodeHasPublication(ctx)
+	if err != nil {
+		// Primary/Subscriber-Status nicht ermittelbar → NICHT raten
+		// (sonst Resync auf dem falschen Node). Abbrechen.
+		response.Internal(c, fmt.Errorf("primary-status nicht ermittelbar: %w", err))
+		return
+	}
+	if isPrimary {
+		// Primary → an den Subscriber-Peer delegieren, mit eigener Adresse.
+		if h.Aggregator == nil {
+			response.BadRequest(c, errors.New("kein mTLS-Aggregator verfügbar — Resync nicht delegierbar"))
+			return
+		}
+		primaryHost := pickPrimaryHost(local)
+		if primaryHost == "" || !validRepairHost.MatchString(primaryHost) {
+			response.BadRequest(c, errors.New("eigene Primary-Adresse (Mgmt/Internal/Public-IP/FQDN) fehlt oder ist ungültig"))
+			return
+		}
+		body, _ := json.Marshal(repairDispatchBody{PrimaryHost: primaryHost})
+		res := h.Aggregator.PostPeerWithBody(ctx, *peer, repairAgentPath, body)
+		if !res.OK {
+			response.Internal(c, fmt.Errorf("Resync auf %s anstoßen: %s", peer.FQDN, res.Err))
+			return
+		}
+		slog.Info("cluster: replication repair delegated", "target", peer.FQDN, "primary_host", primaryHost)
+		if h.Audit != nil {
+			_ = h.Audit.Log(ctx, actorOf(c), "cluster.repair-replication",
+				peer.FQDN, gin.H{"target": "peer", "peer": peer.FQDN, "primary_host": primaryHost}, h.NodeID)
+		}
+		response.Accepted(c, gin.H{"dispatched": true, "target": "peer", "peer_fqdn": peer.FQDN})
+		return
+	}
+
+	// Subscriber → lokal ausführen, Quelle = der Peer (Primary).
+	host := pickPrimaryHost(peer)
+	if err := h.startResync(ctx, host); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if h.Audit != nil {
+		_ = h.Audit.Log(ctx, actorOf(c), "cluster.repair-replication",
+			host, gin.H{"target": "local", "primary": host}, h.NodeID)
+	}
+	response.Accepted(c, gin.H{"dispatched": true, "target": "local", "primary": host})
+}
+
+// AgentRepairReplication wird vom Primary via mTLS auf dem Subscriber
+// aufgerufen und startet dort den lokalen Resync von primary_host.
+func (h *ClusterHandler) AgentRepairReplication(c *gin.Context) {
+	if h.Store == nil {
+		response.Internal(c, errors.New("cluster store unavailable"))
+		return
+	}
+	ctx := c.Request.Context()
+	var body repairDispatchBody
+	_ = c.ShouldBindJSON(&body) // best-effort; Fallback unten
+
+	host := strings.TrimSpace(body.PrimaryHost)
+	if host == "" {
+		// Fallback: Quelle aus ha_nodes (der andere Node).
+		if all, err := h.Store.List(ctx); err == nil {
+			host = pickPrimaryHost(findOtherPeer(all, h.LocalID))
+		}
+	}
+	if err := h.startResync(ctx, host); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	slog.Info("cluster: replication repair triggered by peer", "primary", host, "node", h.LocalID)
+	if h.Audit != nil {
+		_ = h.Audit.Log(ctx, "cluster-peer", "cluster.repair-replication",
+			host, gin.H{"target": "local", "primary": host, "via": "agent"}, h.NodeID)
+	}
+	response.Accepted(c, gin.H{"dispatched": true, "primary": host})
+}
+
+// startResync schreibt das Repair-Script und startet die transiente
+// systemd-Unit. Safety-Guard: läuft NIE auf dem Publication-Primary.
+func (h *ClusterHandler) startResync(ctx context.Context, primaryHost string) error {
+	primaryHost = strings.TrimSpace(primaryHost)
+	if primaryHost == "" {
+		return errors.New("keine Primary-Adresse für den Resync ermittelbar")
+	}
+	if !validRepairHost.MatchString(primaryHost) {
+		return fmt.Errorf("ungültige Primary-Adresse: %q", primaryHost)
+	}
+	// Niemals auf dem Primary (Publication-Quelle) resyncen — würde die
+	// eigene Config mit sich selbst überschreiben bzw. ist sinnlos.
+	// Bei Statusfehler fail-closed (NICHT resyncen).
+	isPrimary, err := h.nodeHasPublication(ctx)
+	if err != nil {
+		return fmt.Errorf("publication-status nicht ermittelbar: %w", err)
+	}
+	if isPrimary {
+		return errors.New("dieser Node ist der Publication-Primary — Resync läuft nur auf einem Subscriber")
+	}
+	if st := repairUnitState(); st == "activating" || st == "active" {
+		return errors.New("Resync läuft bereits")
+	}
+
+	script := fmt.Sprintf(`#!/bin/bash
+set -uo pipefail
+echo "[repair] resync der Logical-Replication-Subscription von Primary %[1]s"
+/usr/bin/edgeguard-ctl cluster-setup-standby %[1]s
+rc=$?
+if [ "$rc" -ne 0 ]; then
+    echo "[repair] cluster-setup-standby fehlgeschlagen (rc=$rc)"
+    exit "$rc"
+fi
+echo "[repair] abgeschlossen — config_hash wird beim nächsten Cluster-Status neu berechnet"
+rm -f %[2]s
+`, primaryHost, repairScriptPath)
+
+	if err := os.WriteFile(repairScriptPath, []byte(script), 0o755); err != nil {
+		return fmt.Errorf("write repair script: %w", err)
+	}
+	_ = exec.Command("sudo", "-n", "/usr/bin/systemctl", "reset-failed", repairUnitName).Run()
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemd-run",
+		"--unit="+repairUnitName,
+		"--description=EdgeGuard replication repair",
+		"--collect",
+		"bash", repairScriptPath)
+	if err := cmd.Run(); err != nil {
+		return fmt.Errorf("systemd-run failed: %w", err)
+	}
+	slog.Info("cluster: replication repair dispatched (local)", "primary", primaryHost, "node", h.LocalID)
+	return nil
+}
+
+// nodeHasPublication prüft, ob dieser Node die Replikations-Publication
+// besitzt — das verlässliche Primary-Signal. pg_publication ist für jeden
+// DB-User lesbar (anders als pg_subscription).
+func (h *ClusterHandler) nodeHasPublication(ctx context.Context) (bool, error) {
+	if h.Store == nil || h.Store.Pool == nil {
+		return false, errors.New("no db pool")
+	}
+	cctx, cancel := context.WithTimeout(ctx, 2*time.Second)
+	defer cancel()
+	var exists bool
+	if err := h.Store.Pool.QueryRow(cctx,
+		`SELECT EXISTS(SELECT 1 FROM pg_publication WHERE pubname = $1)`, repairPubName,
+	).Scan(&exists); err != nil {
+		return false, err
+	}
+	return exists, nil
+}
+
+// repairStatusResponse spiegelt den Zustand der transienten Repair-Unit.
+type repairStatusResponse struct {
+	Phase      string   `json:"phase"` // idle | running | success | failed
+	State      string   `json:"state"`
+	Result     string   `json:"result"`
+	ExitCode   int      `json:"exit_code"`
+	StartedAt  string   `json:"started_at,omitempty"`
+	FinishedAt string   `json:"finished_at,omitempty"`
+	Log        []string `json:"log"`
+}
+
+// RepairReplicationStatus liest den Job-Zustand. Auf dem Primary wird der
+// Status vom Subscriber-Peer geholt (dort läuft der Job); sonst lokal.
+func (h *ClusterHandler) RepairReplicationStatus(c *gin.Context) {
+	ctx := c.Request.Context()
+	// Status-Poll: bei Fehler kein 500 — einfach lokalen Status liefern.
+	isPrimary, _ := h.nodeHasPublication(ctx)
+	if h.Store != nil && isPrimary && h.Aggregator != nil {
+		if all, err := h.Store.List(ctx); err == nil {
+			if peer := findOtherPeer(all, h.LocalID); peer != nil {
+				results := h.Aggregator.FanOut(ctx,
+					[]models.HANode{*peer}, repairAgentPath+"/status", h.LocalID)
+				if len(results) == 1 && results[0].OK && len(results[0].Data) > 0 {
+					c.Data(200, "application/json", wrapEnvelope(results[0].Data))
+					return
+				}
+				// Peer nicht erreichbar → idle statt Fehler, damit das
+				// UI-Polling nicht hart abbricht.
+				response.OK(c, repairStatusResponse{Phase: "idle", Log: []string{}})
+				return
+			}
+		}
+	}
+	response.OK(c, localRepairStatus())
+}
+
+// AgentRepairReplicationStatus liefert den lokalen Job-Zustand an den
+// abfragenden Primary.
+func (h *ClusterHandler) AgentRepairReplicationStatus(c *gin.Context) {
+	response.OK(c, localRepairStatus())
+}
+
+// wrapEnvelope verpackt eine bereits entpackte data-Payload wieder in die
+// Standard-Envelope, damit das UI (isEnvelope) sie konsistent liest.
+func wrapEnvelope(data []byte) []byte {
+	out := []byte(`{"data":`)
+	out = append(out, data...)
+	out = append(out, []byte(`,"error":null,"message":"ok"}`)...)
+	return out
+}
+
+// localRepairStatus liest den Zustand der lokalen Repair-Unit aus systemd
+// (analog UpgradeStatus). Quelle der Wahrheit für Job-Ende ist die Unit.
+func localRepairStatus() repairStatusResponse {
+	out := repairStatusResponse{Phase: "idle", Log: []string{}}
+
+	if data, err := exec.Command("systemctl", "show", repairUnitName,
+		"--no-page",
+		"-p", "ActiveState",
+		"-p", "Result",
+		"-p", "ExecMainStatus",
+		"-p", "ExecMainStartTimestamp",
+		"-p", "ExecMainExitTimestamp",
+	).CombinedOutput(); err == nil {
+		for _, line := range strings.Split(string(data), "\n") {
+			kv := strings.SplitN(strings.TrimSpace(line), "=", 2)
+			if len(kv) != 2 {
+				continue
+			}
+			switch kv[0] {
+			case "ActiveState":
+				out.State = kv[1]
+			case "Result":
+				out.Result = kv[1]
+			case "ExecMainStatus":
+				out.ExitCode, _ = strconv.Atoi(kv[1])
+			case "ExecMainStartTimestamp":
+				if t, err := time.Parse("Mon 2006-01-02 15:04:05 MST", kv[1]); err == nil {
+					out.StartedAt = t.UTC().Format(time.RFC3339)
+				}
+			case "ExecMainExitTimestamp":
+				if t, err := time.Parse("Mon 2006-01-02 15:04:05 MST", kv[1]); err == nil {
+					out.FinishedAt = t.UTC().Format(time.RFC3339)
+				}
+			}
+		}
+	}
+
+	switch out.State {
+	case "activating", "active", "deactivating":
+		out.Phase = "running"
+	case "failed":
+		out.Phase = "failed"
+	case "inactive":
+		if out.Result == "success" && out.ExitCode == 0 && out.FinishedAt != "" {
+			out.Phase = "success"
+		} else if out.Result != "" && out.Result != "success" {
+			out.Phase = "failed"
+		}
+	}
+
+	if data, err := exec.Command("journalctl",
+		"-u", repairUnitName,
+		"--no-pager", "-n", "100", "-o", "cat",
+	).CombinedOutput(); err == nil {
+		lines := strings.Split(strings.TrimRight(string(data), "\n"), "\n")
+		if !(len(lines) == 1 && (lines[0] == "" || strings.HasPrefix(lines[0], "-- No entries"))) {
+			out.Log = lines
+		}
+	}
+	return out
+}
+
+// findNode liefert die ha_nodes-Row mit der gegebenen ID.
+func findNode(nodes []models.HANode, id string) *models.HANode {
+	for i := range nodes {
+		if nodes[i].ID == id {
+			return &nodes[i]
+		}
+	}
+	return nil
+}
+
+// findOtherPeer liefert den (einen) anderen Node im 2-Node-Cluster.
+// Bevorzugt einen online erreichbaren Peer.
+func findOtherPeer(nodes []models.HANode, localID string) *models.HANode {
+	var fallback *models.HANode
+	for i := range nodes {
+		n := &nodes[i]
+		if n.ID == localID {
+			continue
+		}
+		if n.Status == "online" {
+			return n
+		}
+		if fallback == nil {
+			fallback = n
+		}
+	}
+	return fallback
+}
+
+// pickPrimaryHost wählt die beste erreichbare Adresse eines Node:
+// Mgmt-IP → Internal-IP → Public-IP → FQDN. Strippt eine etwaige
+// CIDR-Maske (inet-Spalten können "10.0.0.5/32" liefern).
+func pickPrimaryHost(n *models.HANode) string {
+	if n == nil {
+		return ""
+	}
+	for _, cand := range []*string{n.MgmtIP, n.InternalIP, n.PublicIP} {
+		if cand != nil {
+			if h := strings.TrimSpace(strings.SplitN(*cand, "/", 2)[0]); h != "" {
+				return h
+			}
+		}
+	}
+	return strings.TrimSpace(n.FQDN)
+}
+
+// repairUnitState gibt den ActiveState der Repair-Unit zurück ("" wenn
+// unbekannt). Für den Doppelstart-Schutz.
+func repairUnitState() string {
+	out, err := exec.Command("systemctl", "show", repairUnitName, "--no-page", "-p", "ActiveState").CombinedOutput()
+	if err != nil {
+		return ""
+	}
+	for _, line := range strings.Split(string(out), "\n") {
+		if kv := strings.SplitN(strings.TrimSpace(line), "=", 2); len(kv) == 2 && kv[0] == "ActiveState" {
+			return kv[1]
+		}
+	}
+	return ""
+}

internal/handlers/cluster_rollingupdate.go

@@ -0,0 +1,295 @@
+package handlers
+
+import (
+	"context"
+	"encoding/json"
+	"log/slog"
+	"net/http"
+	"os"
+	"os/exec"
+	"sync"
+	"time"
+
+	"github.com/gin-gonic/gin"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+// ruStateMu serialisiert Lesen/Schreiben der Rolling-Update-State-Datei
+// (HTTP-Handler + Hintergrund-Goroutine greifen gleichzeitig zu).
+var ruStateMu sync.Mutex
+
+const rollingUpdateStateFile = "/var/lib/edgeguard/rolling-update-state.json"
+
+const (
+	phaseIdle              = "idle"
+	phaseUpdatingSecondary = "updating-secondary"
+	phaseWaitingSecondary  = "waiting-secondary"
+	phaseUpdatingPrimary   = "updating-primary"
+	phaseDone              = "done"
+	phaseFailed            = "failed"
+)
+
+// FinishRollingUpdateIfPending wird beim API-Start aufgerufen. Wenn die
+// State-Datei "updating-primary" enthält, bedeutet das dass der Primary
+// gerade erfolgreich neugestartet ist → Update abgeschlossen → "done" schreiben.
+func FinishRollingUpdateIfPending() {
+	st := readRollingUpdateState()
+	if st.Phase == phaseUpdatingPrimary {
+		writeRollingUpdateState(RollingUpdateState{
+			Phase:         phaseDone,
+			SecondaryID:   st.SecondaryID,
+			SecondaryFQDN: st.SecondaryFQDN,
+		})
+	}
+}
+
+// RollingUpdateState hält den Fortschritt des Rolling-Updates.
+// Persistiert in rollingUpdateStateFile damit der Status über
+// einen kurzen API-Neustart hinaus lesbar bleibt.
+type RollingUpdateState struct {
+	Phase         string    `json:"phase"`
+	SecondaryID   string    `json:"secondary_id,omitempty"`
+	SecondaryFQDN string    `json:"secondary_fqdn,omitempty"`
+	StartedAt     time.Time `json:"started_at,omitempty"`
+	UpdatedAt     time.Time `json:"updated_at"`
+	Error         string    `json:"error,omitempty"`
+}
+
+func readRollingUpdateState() RollingUpdateState {
+	ruStateMu.Lock()
+	defer ruStateMu.Unlock()
+	data, err := os.ReadFile(rollingUpdateStateFile)
+	if err != nil {
+		return RollingUpdateState{Phase: phaseIdle, UpdatedAt: time.Now()}
+	}
+	var s RollingUpdateState
+	if err := json.Unmarshal(data, &s); err != nil {
+		return RollingUpdateState{Phase: phaseIdle, UpdatedAt: time.Now()}
+	}
+	// Terminale Zustände altern aus (statt Mutation-on-GET): nach 10 min
+	// gilt done/failed als idle — so verliert kein paralleler Poller das
+	// Ergebnis und ein alter Stand bleibt nicht hängen.
+	if (s.Phase == phaseDone || s.Phase == phaseFailed) && !s.UpdatedAt.IsZero() &&
+		time.Since(s.UpdatedAt) > 10*time.Minute {
+		return RollingUpdateState{Phase: phaseIdle, UpdatedAt: time.Now()}
+	}
+	return s
+}
+
+func writeRollingUpdateState(s RollingUpdateState) {
+	s.UpdatedAt = time.Now()
+	data, err := json.Marshal(s)
+	if err != nil {
+		slog.Warn("rolling-update: failed to marshal state", "error", err)
+		return
+	}
+	ruStateMu.Lock()
+	defer ruStateMu.Unlock()
+	// AtomicWrite (temp+rename) → Leser sehen nie einen partiellen Stand.
+	if err := configgen.AtomicWrite(rollingUpdateStateFile, data, 0o600); err != nil {
+		slog.Warn("rolling-update: failed to write state file", "error", err)
+	}
+}
+
+// RollingUpdate startet den Rolling-Update-Prozess:
+// 1. Secondary aktualisieren (via mTLS /agent/cluster/trigger-update)
+// 2. Warten bis Secondary neue Version meldet
+// 3. Primary (dieser Node) aktualisieren (wie /system/upgrade)
+//
+// Kein Cluster vorhanden → 409 zurück damit der Client auf /system/upgrade
+// ausweichen kann. Wenn bereits ein Rolling-Update läuft → aktuellen State.
+func (h *ClusterHandler) RollingUpdate(c *gin.Context) {
+	if h.Aggregator == nil || h.Store == nil {
+		c.JSON(http.StatusConflict, gin.H{"error": "no cluster — use /system/upgrade"})
+		return
+	}
+
+	st := readRollingUpdateState()
+	if st.Phase != phaseIdle && st.Phase != phaseFailed && st.Phase != phaseDone {
+		response.OK(c, st)
+		return
+	}
+
+	nodes, err := h.Store.List(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	var secondary *models.HANode
+	for i := range nodes {
+		if nodes[i].ID != h.LocalID {
+			secondary = &nodes[i]
+			break
+		}
+	}
+	if secondary == nil {
+		c.JSON(http.StatusConflict, gin.H{"error": "no peer node — use /system/upgrade"})
+		return
+	}
+
+	newState := RollingUpdateState{
+		Phase:         phaseUpdatingSecondary,
+		SecondaryID:   secondary.ID,
+		SecondaryFQDN: secondary.FQDN,
+		StartedAt:     time.Now(),
+	}
+	writeRollingUpdateState(newState)
+	slog.Info("rolling-update: started", "secondary", secondary.FQDN)
+
+	go h.runRollingUpdate(secondary)
+
+	c.JSON(http.StatusAccepted, newState)
+}
+
+// RollingUpdateStatus gibt den aktuellen Rolling-Update-State zurück.
+// Read-only — terminale Zustände altern in readRollingUpdateState aus
+// (kein Reset-on-GET mehr, das parallelen Pollern das "done" wegnahm).
+func (h *ClusterHandler) RollingUpdateStatus(c *gin.Context) {
+	response.OK(c, readRollingUpdateState())
+}
+
+func (h *ClusterHandler) runRollingUpdate(secondary *models.HANode) {
+	ctx := context.Background()
+
+	// Vor dem Upgrade die aktuelle Secondary-Version als Baseline merken —
+	// der Flip wird gegen DIESEN Wert geprüft (nicht gegen die Primary-
+	// Version, die fälschlich sofort/nie „flippen" konnte).
+	baseline := secondaryVersion(ctx, h, secondary)
+	target := baseline
+	if target == "" {
+		target = h.Version // Fallback, falls Baseline nicht abrufbar
+	}
+
+	// 1. Secondary triggern
+	slog.Info("rolling-update: posting trigger-update to secondary", "fqdn", secondary.FQDN)
+	result := h.Aggregator.PostPeer(ctx, *secondary, "/agent/cluster/trigger-update")
+	if !result.OK {
+		writeRollingUpdateState(RollingUpdateState{
+			Phase:         phaseFailed,
+			SecondaryID:   secondary.ID,
+			SecondaryFQDN: secondary.FQDN,
+			Error:         "trigger-update failed: " + result.Err,
+		})
+		slog.Warn("rolling-update: secondary trigger failed", "error", result.Err)
+		return
+	}
+
+	// 2. Secondary-Version pollen — der Secondary restartet nach dem
+	//    Upgrade, danach zeigt /agent/cluster/version eine neue Version.
+	writeRollingUpdateState(RollingUpdateState{
+		Phase:         phaseWaitingSecondary,
+		SecondaryID:   secondary.ID,
+		SecondaryFQDN: secondary.FQDN,
+	})
+	slog.Info("rolling-update: waiting for secondary version flip")
+
+	// Kurze Wartezeit damit apt auf dem Secondary erst losläuft
+	time.Sleep(20 * time.Second)
+
+	deadline := time.Now().Add(10 * time.Minute)
+	versionFlipped := false
+	for time.Now().Before(deadline) {
+		results := h.Aggregator.FanOut(ctx, []models.HANode{*secondary}, "/agent/cluster/version", h.LocalID)
+		if len(results) > 0 && results[0].OK {
+			var ver struct {
+				Version string `json:"version"`
+			}
+			if err := json.Unmarshal(results[0].Data, &ver); err == nil {
+				slog.Info("rolling-update: secondary version", "version", ver.Version, "baseline", target)
+				if ver.Version != "" && ver.Version != target {
+					versionFlipped = true
+					break
+				}
+			}
+		}
+		time.Sleep(10 * time.Second)
+	}
+
+	if !versionFlipped {
+		writeRollingUpdateState(RollingUpdateState{
+			Phase:         phaseFailed,
+			SecondaryID:   secondary.ID,
+			SecondaryFQDN: secondary.FQDN,
+			Error:         "timeout (10 min) waiting for secondary version flip",
+		})
+		slog.Warn("rolling-update: secondary version flip timeout")
+		return
+	}
+
+	// 3. Primary (uns selbst) aktualisieren — identisch zu /system/upgrade
+	writeRollingUpdateState(RollingUpdateState{
+		Phase:         phaseUpdatingPrimary,
+		SecondaryID:   secondary.ID,
+		SecondaryFQDN: secondary.FQDN,
+	})
+	slog.Info("rolling-update: triggering primary self-upgrade")
+
+	const scriptPath = "/var/lib/edgeguard/upgrade.sh"
+	const script = `#!/bin/bash
+set -e
+sleep 2
+export DEBIAN_FRONTEND=noninteractive
+dpkg --configure -a || true
+retry_apt() {
+    local attempt=0 max=3 wait_for=15
+    while [ $attempt -lt $max ]; do
+        attempt=$((attempt + 1))
+        apt-get update -qq || true
+        if apt-get install -y -qq -o Dpkg::Options::=--force-confold \
+            edgeguard-api edgeguard-ui edgeguard; then return 0; fi
+        [ $attempt -lt $max ] && sleep $wait_for && wait_for=$((wait_for * 2))
+    done
+    return 1
+}
+retry_apt
+echo "[upgrade] complete"
+rm -f /var/lib/edgeguard/upgrade.sh
+`
+	if err := os.WriteFile(scriptPath, []byte(script), 0o755); err != nil {
+		writeRollingUpdateState(RollingUpdateState{
+			Phase:         phaseFailed,
+			SecondaryID:   secondary.ID,
+			SecondaryFQDN: secondary.FQDN,
+			Error:         "write upgrade script: " + err.Error(),
+		})
+		return
+	}
+
+	const unitName = "edgeguard-upgrade.service"
+	_ = exec.Command("sudo", "-n", "/usr/bin/systemctl", "reset-failed", unitName).Run()
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemd-run",
+		"--unit="+unitName,
+		"--description=EdgeGuard self-upgrade",
+		"--collect",
+		"bash", scriptPath)
+	if err := cmd.Run(); err != nil {
+		writeRollingUpdateState(RollingUpdateState{
+			Phase:         phaseFailed,
+			SecondaryID:   secondary.ID,
+			SecondaryFQDN: secondary.FQDN,
+			Error:         "systemd-run failed: " + err.Error(),
+		})
+		slog.Warn("rolling-update: primary systemd-run failed", "error", err)
+		return
+	}
+	// State bleibt "updating-primary" — der Primary restartet gleich.
+	// UI erkennt Version-Flip via /system/health und schließt den Flow.
+	slog.Info("rolling-update: primary upgrade dispatched, process will restart")
+}
+
+// secondaryVersion holt best-effort die laufende Version des Peers via mTLS.
+func secondaryVersion(ctx context.Context, h *ClusterHandler, secondary *models.HANode) string {
+	results := h.Aggregator.FanOut(ctx, []models.HANode{*secondary}, "/agent/cluster/version", h.LocalID)
+	if len(results) > 0 && results[0].OK {
+		var ver struct {
+			Version string `json:"version"`
+		}
+		if json.Unmarshal(results[0].Data, &ver) == nil {
+			return ver.Version
+		}
+	}
+	return ""
+}

internal/handlers/cluster_viptest.go

@@ -0,0 +1,319 @@
+package handlers
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"log/slog"
+	"os/exec"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+// vipInfo enthält die für einen VIP-Schwenk notwendigen Daten.
+type vipInfo struct {
+	ID      int64  `json:"id"`
+	Address string `json:"address"`
+	Prefix  int    `json:"prefix"`
+	Device  string `json:"device"`
+}
+
+// VIPStatusEntry kombiniert einen VIP mit den Nodes die ihn gerade halten.
+type VIPStatusEntry struct {
+	VIP      vipInfo  `json:"vip"`
+	ActiveOn []string `json:"active_on"` // FQDNs der Nodes mit diesem VIP
+}
+
+// AgentActiveIPs gibt alle aktiven IPv4-Adressen dieses Nodes zurück.
+// Wird vom Primary genutzt um zu prüfen welcher Node welchen VIP hält.
+func (h *ClusterHandler) AgentActiveIPs(c *gin.Context) {
+	ips, err := localActiveIPs()
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"ips": ips})
+}
+
+// vipCmdRequest ist der Body für den AgentVIPCmd-Endpoint.
+type vipCmdRequest struct {
+	Action  string `json:"action"`  // "add" | "del"
+	Address string `json:"address"` // z.B. "10.0.5.1"
+	Prefix  int    `json:"prefix"`  // z.B. 24
+	Device  string `json:"device"`  // z.B. "vlan100"
+}
+
+// AgentVIPCmd führt `ip addr add/del` auf diesem Node aus.
+// Wird vom Primary via mTLS für VIP-Schwenk-Tests aufgerufen.
+func (h *ClusterHandler) AgentVIPCmd(c *gin.Context) {
+	var req vipCmdRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if req.Action != "add" && req.Action != "del" {
+		response.BadRequest(c, simpleError("action must be 'add' or 'del'"))
+		return
+	}
+	if req.Address == "" || req.Device == "" || req.Prefix <= 0 || req.Prefix > 128 {
+		response.BadRequest(c, simpleError("address, device, prefix required"))
+		return
+	}
+	if err := runVIPCmd(req.Action, req.Address, req.Prefix, req.Device); err != nil {
+		slog.Warn("cluster: agent vip-cmd failed",
+			"action", req.Action, "addr", req.Address, "dev", req.Device, "error", err)
+		response.Internal(c, err)
+		return
+	}
+	slog.Info("cluster: agent vip-cmd ok",
+		"action", req.Action, "addr", req.Address, "prefix", req.Prefix,
+		"dev", req.Device, "caller", c.ClientIP())
+	response.OK(c, gin.H{"ok": true})
+}
+
+// VIPStatus liest alle VIPs (is_vip=true) aus der DB und fragt alle Nodes
+// welche davon sie gerade aktiv haben. Nur sinnvoll im Cluster-Modus.
+func (h *ClusterHandler) VIPStatus(c *gin.Context) {
+	vips, err := loadVIPs(c.Request.Context(), h.Store.Pool)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	nodeIPs := h.collectActiveIPs(c.Request.Context())
+	result := make([]VIPStatusEntry, 0, len(vips))
+	for _, v := range vips {
+		entry := VIPStatusEntry{VIP: v}
+		for fqdn, ips := range nodeIPs {
+			for _, ip := range ips {
+				if ip == v.Address {
+					entry.ActiveOn = append(entry.ActiveOn, fqdn)
+					break
+				}
+			}
+		}
+		result = append(result, entry)
+	}
+	response.OK(c, gin.H{"vips": result})
+}
+
+// vipTestRequest steuert einen VIP-Schwenk.
+type vipTestRequest struct {
+	IPAddressID int64  `json:"ip_address_id"`
+	Action      string `json:"action"` // "to_secondary" | "restore"
+}
+
+// vipTestStep beschreibt einen Schritt des Schwenk-Prozesses.
+type vipTestStep struct {
+	Step    string `json:"step"`
+	OK      bool   `json:"ok"`
+	Message string `json:"message,omitempty"`
+}
+
+// VIPTest schwenkt einen VIP vom Primary auf den Secondary ("to_secondary")
+// oder zurück ("restore"). Nur vom Primary aufzurufen.
+func (h *ClusterHandler) VIPTest(c *gin.Context) {
+	var req vipTestRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if req.Action != "to_secondary" && req.Action != "restore" {
+		response.BadRequest(c, simpleError("action must be 'to_secondary' or 'restore'"))
+		return
+	}
+
+	vips, err := loadVIPs(c.Request.Context(), h.Store.Pool)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	var target *vipInfo
+	for i := range vips {
+		if vips[i].ID == req.IPAddressID {
+			target = &vips[i]
+			break
+		}
+	}
+	if target == nil {
+		response.NotFound(c, simpleError("VIP not found or not marked as VIP"))
+		return
+	}
+
+	all, err := h.Store.List(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	var peer *models.HANode
+	for i := range all {
+		if all[i].ID != h.LocalID {
+			peer = &all[i]
+			break
+		}
+	}
+	if peer == nil {
+		response.BadRequest(c, simpleError("kein Secondary-Peer gefunden"))
+		return
+	}
+
+	var steps []vipTestStep
+	addrPfx := fmt.Sprintf("%s/%d", target.Address, target.Prefix)
+
+	if req.Action == "to_secondary" {
+		// 1. VIP auf Secondary via mTLS hinzufügen
+		steps = append(steps, h.peerVIPCmd(c.Request.Context(), *peer, target, "add",
+			fmt.Sprintf("add %s dev %s auf %s", addrPfx, target.Device, peer.FQDN)))
+		// 2. VIP vom Primary entfernen (nur wenn Secondary-Add erfolgreich)
+		if steps[0].OK {
+			steps = append(steps, localVIPStep(target, "del",
+				fmt.Sprintf("del %s dev %s lokal", addrPfx, target.Device)))
+		}
+	} else {
+		// 1. VIP auf Primary zurückholen
+		steps = append(steps, localVIPStep(target, "add",
+			fmt.Sprintf("add %s dev %s lokal", addrPfx, target.Device)))
+		// 2. VIP auf Secondary entfernen
+		steps = append(steps, h.peerVIPCmd(c.Request.Context(), *peer, target, "del",
+			fmt.Sprintf("del %s dev %s auf %s", addrPfx, target.Device, peer.FQDN)))
+	}
+
+	slog.Info("cluster: vip-test", "action", req.Action, "vip", target.Address,
+		"dev", target.Device, "peer", peer.FQDN, "actor", actorOf(c))
+	response.OK(c, gin.H{"steps": steps})
+}
+
+// ── Hilfsfunktionen ───────────────────────────────────────────────────────
+
+func loadVIPs(ctx context.Context, pool *pgxpool.Pool) ([]vipInfo, error) {
+	rows, err := pool.Query(ctx, `
+		SELECT ia.id, ia.address, ia.prefix, ni.name
+		FROM ip_addresses ia
+		JOIN network_interfaces ni ON ni.id = ia.interface_id
+		WHERE ia.is_vip = true AND ia.active = true
+		ORDER BY ni.name, ia.address`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var out []vipInfo
+	for rows.Next() {
+		var v vipInfo
+		if err := rows.Scan(&v.ID, &v.Address, &v.Prefix, &v.Device); err != nil {
+			return nil, err
+		}
+		out = append(out, v)
+	}
+	return out, rows.Err()
+}
+
+// collectActiveIPs fragt alle Cluster-Nodes (lokal + Peers via mTLS) nach
+// ihren aktiven IPv4-Adressen und gibt eine Map[fqdn][]ip zurück.
+func (h *ClusterHandler) collectActiveIPs(ctx context.Context) map[string][]string {
+	result := make(map[string][]string)
+	if h.Store == nil {
+		return result
+	}
+	all, err := h.Store.List(ctx)
+	if err != nil {
+		return result
+	}
+	// Lokaler Node
+	if ips, err := localActiveIPs(); err == nil {
+		for _, n := range all {
+			if n.ID == h.LocalID {
+				result[n.FQDN] = ips
+				break
+			}
+		}
+	}
+	// Peers via mTLS-Aggregator
+	if h.Aggregator != nil {
+		var peers []models.HANode
+		for _, n := range all {
+			if n.ID != h.LocalID {
+				peers = append(peers, n)
+			}
+		}
+		if len(peers) > 0 {
+			peerResults := h.Aggregator.FanOut(ctx, peers, "/agent/cluster/active-ips", h.LocalID)
+			for _, pr := range peerResults {
+				if !pr.OK || len(pr.Data) == 0 {
+					continue
+				}
+				var payload struct {
+					IPs []string `json:"ips"`
+				}
+				if err := json.Unmarshal(pr.Data, &payload); err == nil {
+					result[pr.FQDN] = payload.IPs
+				}
+			}
+		}
+	}
+	return result
+}
+
+// localActiveIPs liest alle aktiven IPv4-Adressen des lokalen Nodes via `ip`.
+func localActiveIPs() ([]string, error) {
+	out, err := exec.Command("ip", "-4", "-o", "addr", "show").Output()
+	if err != nil {
+		return nil, err
+	}
+	var ips []string
+	for _, line := range strings.Split(string(out), "\n") {
+		parts := strings.Fields(line)
+		for i, p := range parts {
+			if p == "inet" && i+1 < len(parts) {
+				addr := strings.SplitN(parts[i+1], "/", 2)[0]
+				ips = append(ips, addr)
+			}
+		}
+	}
+	return ips, nil
+}
+
+// peerVIPCmd ruft AgentVIPCmd auf dem Peer via mTLS auf.
+func (h *ClusterHandler) peerVIPCmd(ctx context.Context, peer models.HANode, vip *vipInfo, action, stepLabel string) vipTestStep {
+	step := vipTestStep{Step: stepLabel}
+	if h.Aggregator == nil {
+		step.Message = "aggregator nicht verfügbar"
+		return step
+	}
+	body, _ := json.Marshal(vipCmdRequest{
+		Action:  action,
+		Address: vip.Address,
+		Prefix:  vip.Prefix,
+		Device:  vip.Device,
+	})
+	res := h.Aggregator.PostPeerWithBody(ctx, peer, "/agent/cluster/vip-cmd", body)
+	step.OK = res.OK
+	if !res.OK {
+		step.Message = res.Err
+	}
+	return step
+}
+
+// localVIPStep führt ip addr add/del auf dem lokalen Node aus.
+func localVIPStep(vip *vipInfo, action, stepLabel string) vipTestStep {
+	step := vipTestStep{Step: stepLabel}
+	if err := runVIPCmd(action, vip.Address, vip.Prefix, vip.Device); err != nil {
+		step.Message = err.Error()
+		return step
+	}
+	step.OK = true
+	return step
+}
+
+// runVIPCmd führt `sudo /usr/lib/edgeguard/vip-cmd.sh {action} {addr/prefix} {dev}` aus.
+func runVIPCmd(action, address string, prefix int, device string) error {
+	addrPfx := fmt.Sprintf("%s/%d", address, prefix)
+	out, err := exec.Command("sudo", "-n", "/usr/lib/edgeguard/vip-cmd.sh", action, addrPfx, device).CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("vip-cmd.sh %s %s %s: %s", action, addrPfx, device, strings.TrimSpace(string(out)))
+	}
+	return nil
+}

internal/handlers/crowdsec.go

@@ -0,0 +1,285 @@
+package handlers
+
+import (
+	"errors"
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+
+	crowdsec "git.netcell-it.de/projekte/edgeguard-native/internal/crowdsec"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/audit"
+)
+
+// CrowdSecHandler exposes the CrowdSec IDS/IPS management REST API:
+//
+//	GET    /crowdsec/status
+//	GET    /crowdsec/decisions
+//	POST   /crowdsec/decisions
+//	DELETE /crowdsec/decisions         (?ip=<ip> or ?id=<id>)
+//	GET    /crowdsec/alerts
+//	DELETE /crowdsec/alerts/:id
+//	GET    /crowdsec/bouncers
+//	DELETE /crowdsec/bouncers/:name
+//	GET    /crowdsec/machines
+//	DELETE /crowdsec/machines/:id
+//	GET    /crowdsec/collections
+//	POST   /crowdsec/collections/:name/install
+//	DELETE /crowdsec/collections/:name
+type CrowdSecHandler struct {
+	Audit  *audit.Repo
+	NodeID string
+}
+
+// NewCrowdSecHandler returns a CrowdSecHandler wired with audit and node-id.
+func NewCrowdSecHandler(a *audit.Repo, nodeID string) *CrowdSecHandler {
+	return &CrowdSecHandler{Audit: a, NodeID: nodeID}
+}
+
+// Register mounts all CrowdSec routes onto the provided authenticated router
+// group.
+func (h *CrowdSecHandler) Register(rg *gin.RouterGroup) {
+	g := rg.Group("/crowdsec")
+	g.GET("/status", h.Status)
+	g.GET("/decisions", h.ListDecisions)
+	g.POST("/decisions", h.AddDecision)
+	g.DELETE("/decisions", h.DeleteDecision)
+	g.GET("/alerts", h.ListAlerts)
+	g.DELETE("/alerts/:id", h.DeleteAlert)
+	g.GET("/bouncers", h.ListBouncers)
+	g.DELETE("/bouncers/:name", h.DeleteBouncer)
+	g.GET("/machines", h.ListMachines)
+	g.DELETE("/machines/:id", h.DeleteMachine)
+	g.GET("/collections", h.ListCollections)
+	g.POST("/collections/:name/install", h.InstallCollection)
+	g.DELETE("/collections/:name", h.RemoveCollection)
+}
+
+// csNotInstalled responds with 503 when cscli is absent.
+func csNotInstalled(c *gin.Context) {
+	c.JSON(http.StatusServiceUnavailable, gin.H{"error": "crowdsec not installed"})
+}
+
+// ---------- Status ----------------------------------------------------------
+
+// Status returns live status of the CrowdSec agent + bouncer.
+// Does NOT require cscli — uses systemctl for running-state checks.
+func (h *CrowdSecHandler) Status(c *gin.Context) {
+	st := crowdsec.ServiceStatus(c.Request.Context())
+	response.OK(c, st)
+}
+
+// ---------- Decisions -------------------------------------------------------
+
+// ListDecisions returns all active decisions.
+func (h *CrowdSecHandler) ListDecisions(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	list, err := crowdsec.Decisions(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"decisions": list})
+}
+
+// addDecisionBody is the expected JSON body for POST /crowdsec/decisions.
+type addDecisionBody struct {
+	IP       string `json:"ip"       binding:"required"`
+	Duration string `json:"duration" binding:"required"`
+	Reason   string `json:"reason"`
+	Type     string `json:"type"`
+}
+
+// AddDecision creates a new ban/captcha decision.
+func (h *CrowdSecHandler) AddDecision(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	var body addDecisionBody
+	if err := c.ShouldBindJSON(&body); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if body.Reason == "" {
+		body.Reason = "manual ban"
+	}
+	if body.Type == "" {
+		body.Type = "ban"
+	}
+	if err := crowdsec.AddDecision(c.Request.Context(), body.IP, body.Duration, body.Reason, body.Type); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "crowdsec.decision.add", body.IP,
+		gin.H{"duration": body.Duration, "type": body.Type, "reason": body.Reason}, h.NodeID)
+	response.Created(c, gin.H{"ip": body.IP, "duration": body.Duration, "type": body.Type})
+}
+
+// DeleteDecision removes a decision by IP (?ip=) or by ID (?id=).
+func (h *CrowdSecHandler) DeleteDecision(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	ip := c.Query("ip")
+	id := c.Query("id")
+	if ip == "" && id == "" {
+		response.BadRequest(c, errors.New("query parameter 'ip' or 'id' required"))
+		return
+	}
+	var err error
+	var target string
+	if ip != "" {
+		err = crowdsec.DeleteDecisionByIP(c.Request.Context(), ip)
+		target = ip
+	} else {
+		err = crowdsec.DeleteDecisionByID(c.Request.Context(), id)
+		target = id
+	}
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "crowdsec.decision.delete", target, nil, h.NodeID)
+	response.OK(c, gin.H{"deleted": target})
+}
+
+// ---------- Alerts ----------------------------------------------------------
+
+// ListAlerts returns recent CrowdSec alerts.
+func (h *CrowdSecHandler) ListAlerts(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	list, err := crowdsec.Alerts(c.Request.Context(), 200)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"alerts": list})
+}
+
+// DeleteAlert discards a single alert.
+func (h *CrowdSecHandler) DeleteAlert(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	id := c.Param("id")
+	if err := crowdsec.DeleteAlert(c.Request.Context(), id); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"deleted": id})
+}
+
+// ---------- Bouncers --------------------------------------------------------
+
+// ListBouncers returns all registered bouncers.
+func (h *CrowdSecHandler) ListBouncers(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	list, err := crowdsec.Bouncers(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"bouncers": list})
+}
+
+// DeleteBouncer removes a bouncer by name.
+func (h *CrowdSecHandler) DeleteBouncer(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	name := c.Param("name")
+	if err := crowdsec.DeleteBouncer(c.Request.Context(), name); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "crowdsec.bouncer.delete", name, nil, h.NodeID)
+	response.OK(c, gin.H{"deleted": name})
+}
+
+// ---------- Machines --------------------------------------------------------
+
+// ListMachines returns all registered machines.
+func (h *CrowdSecHandler) ListMachines(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	list, err := crowdsec.Machines(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"machines": list})
+}
+
+// DeleteMachine removes a machine by ID.
+func (h *CrowdSecHandler) DeleteMachine(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	id := c.Param("id")
+	if err := crowdsec.DeleteMachine(c.Request.Context(), id); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "crowdsec.machine.delete", id, nil, h.NodeID)
+	response.OK(c, gin.H{"deleted": id})
+}
+
+// ---------- Collections -----------------------------------------------------
+
+// ListCollections returns all hub collections and their install status.
+func (h *CrowdSecHandler) ListCollections(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	list, err := crowdsec.Collections(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"collections": list})
+}
+
+// InstallCollection installs a hub collection by name.
+func (h *CrowdSecHandler) InstallCollection(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	name := c.Param("name")
+	if err := crowdsec.InstallCollection(c.Request.Context(), name); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.Created(c, gin.H{"installed": name})
+}
+
+// RemoveCollection removes a hub collection by name.
+func (h *CrowdSecHandler) RemoveCollection(c *gin.Context) {
+	if !crowdsec.IsInstalled() {
+		csNotInstalled(c)
+		return
+	}
+	name := c.Param("name")
+	if err := crowdsec.RemoveCollection(c.Request.Context(), name); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"removed": name})
+}

internal/handlers/dhcp.go

@@ -0,0 +1,346 @@
+package handlers
+
+import (
+	"context"
+	"errors"
+	"log/slog"
+	"net"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/audit"
+	dhcpsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/dhcp"
+)
+
+// DHCPHandler exposes /api/v1/dhcp/{settings,subnets,reservations} for
+// the Kea DHCPv4 server.
+type DHCPHandler struct {
+	Repo     *dhcpsvc.Repo
+	Audit    *audit.Repo
+	NodeID   string
+	Reloader func(ctx context.Context) error
+}
+
+func NewDHCPHandler(repo *dhcpsvc.Repo, a *audit.Repo, nodeID string, reloader func(context.Context) error) *DHCPHandler {
+	return &DHCPHandler{Repo: repo, Audit: a, NodeID: nodeID, Reloader: reloader}
+}
+
+func (h *DHCPHandler) reload(ctx context.Context, op string) {
+	if h.Reloader == nil {
+		return
+	}
+	if err := h.Reloader(ctx); err != nil {
+		slog.Warn("kea: reload after mutation failed", "op", op, "error", err)
+	}
+}
+
+func (h *DHCPHandler) Register(rg *gin.RouterGroup) {
+	g := rg.Group("/dhcp")
+	g.GET("/settings", h.GetSettings)
+	g.PUT("/settings", h.UpdateSettings)
+
+	s := g.Group("/subnets")
+	s.GET("", h.ListSubnets)
+	s.POST("", h.CreateSubnet)
+	s.GET("/:id", h.GetSubnet)
+	s.PUT("/:id", h.UpdateSubnet)
+	s.DELETE("/:id", h.DeleteSubnet)
+	s.GET("/:id/reservations", h.ListReservationsForSubnet)
+	s.POST("/:id/reservations", h.CreateReservation)
+
+	r := g.Group("/reservations")
+	r.GET("", h.ListAllReservations)
+	r.GET("/:id", h.GetReservation)
+	r.PUT("/:id", h.UpdateReservation)
+	r.DELETE("/:id", h.DeleteReservation)
+}
+
+// ── Settings ─────────────────────────────────────────────────────────
+
+func (h *DHCPHandler) GetSettings(c *gin.Context) {
+	s, err := h.Repo.GetSettings(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, s)
+}
+
+func (h *DHCPHandler) UpdateSettings(c *gin.Context) {
+	var req models.DHCPSettings
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if req.DefaultLease <= 0 {
+		req.DefaultLease = 3600
+	}
+	if req.MaxLease < req.DefaultLease {
+		req.MaxLease = req.DefaultLease
+	}
+	if err := validateIPList(req.DNSServers); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.UpdateSettings(c.Request.Context(), req)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.settings.update", "",
+		gin.H{"enabled": out.Enabled}, h.NodeID)
+	response.OK(c, out)
+	h.reload(c.Request.Context(), "settings.update")
+}
+
+// ── Subnets ──────────────────────────────────────────────────────────
+
+func (h *DHCPHandler) ListSubnets(c *gin.Context) {
+	out, err := h.Repo.ListSubnets(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"subnets": out})
+}
+
+func (h *DHCPHandler) GetSubnet(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	s, err := h.Repo.GetSubnet(c.Request.Context(), id)
+	if err != nil {
+		h.subnetErr(c, err)
+		return
+	}
+	response.OK(c, s)
+}
+
+func (h *DHCPHandler) CreateSubnet(c *gin.Context) {
+	var req models.DHCPSubnet
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := h.validateSubnet(c, &req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.CreateSubnet(c.Request.Context(), req)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.subnet.create", out.Name, out, h.NodeID)
+	response.Created(c, out)
+	h.reload(c.Request.Context(), "subnet.create")
+}
+
+func (h *DHCPHandler) UpdateSubnet(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var req models.DHCPSubnet
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := h.validateSubnet(c, &req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.UpdateSubnet(c.Request.Context(), id, req)
+	if err != nil {
+		h.subnetErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.subnet.update", out.Name, out, h.NodeID)
+	response.OK(c, out)
+	h.reload(c.Request.Context(), "subnet.update")
+}
+
+func (h *DHCPHandler) DeleteSubnet(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	if err := h.Repo.DeleteSubnet(c.Request.Context(), id); err != nil {
+		h.subnetErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.subnet.delete", "", gin.H{"id": id}, h.NodeID)
+	response.OK(c, gin.H{"ok": true})
+	h.reload(c.Request.Context(), "subnet.delete")
+}
+
+// ── Reservations ─────────────────────────────────────────────────────
+
+func (h *DHCPHandler) ListAllReservations(c *gin.Context) {
+	out, err := h.Repo.ListAllReservations(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"reservations": out})
+}
+
+func (h *DHCPHandler) ListReservationsForSubnet(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	out, err := h.Repo.ListReservationsForSubnet(c.Request.Context(), id)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"reservations": out})
+}
+
+func (h *DHCPHandler) GetReservation(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	v, err := h.Repo.GetReservation(c.Request.Context(), id)
+	if err != nil {
+		h.resvErr(c, err)
+		return
+	}
+	response.OK(c, v)
+}
+
+func (h *DHCPHandler) CreateReservation(c *gin.Context) {
+	subnetID, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var req models.DHCPReservation
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	req.SubnetID = subnetID
+	if err := validateReservation(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.CreateReservation(c.Request.Context(), req)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.reservation.create", out.MACAddress, out, h.NodeID)
+	response.Created(c, out)
+	h.reload(c.Request.Context(), "reservation.create")
+}
+
+func (h *DHCPHandler) UpdateReservation(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var req models.DHCPReservation
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := validateReservation(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.UpdateReservation(c.Request.Context(), id, req)
+	if err != nil {
+		h.resvErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.reservation.update", out.MACAddress, out, h.NodeID)
+	response.OK(c, out)
+	h.reload(c.Request.Context(), "reservation.update")
+}
+
+func (h *DHCPHandler) DeleteReservation(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	if err := h.Repo.DeleteReservation(c.Request.Context(), id); err != nil {
+		h.resvErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "dhcp.reservation.delete", "", gin.H{"id": id}, h.NodeID)
+	response.OK(c, gin.H{"ok": true})
+	h.reload(c.Request.Context(), "reservation.delete")
+}
+
+// ── Validation + error mapping ───────────────────────────────────────
+
+func (h *DHCPHandler) validateSubnet(c *gin.Context, s *models.DHCPSubnet) error {
+	s.Name = strings.TrimSpace(s.Name)
+	s.InterfaceName = strings.TrimSpace(s.InterfaceName)
+	if s.Name == "" {
+		return errors.New("name ist erforderlich")
+	}
+	if s.InterfaceName == "" {
+		return errors.New("interface_name ist erforderlich")
+	}
+	if exists, err := h.Repo.InterfaceExists(c.Request.Context(), s.InterfaceName); err == nil && !exists {
+		return errors.New("interface_name existiert nicht: " + s.InterfaceName)
+	}
+	if _, _, err := net.ParseCIDR(s.SubnetCIDR); err != nil {
+		return errors.New("subnet_cidr ist kein gültiges CIDR: " + s.SubnetCIDR)
+	}
+	if (s.PoolStart == "") != (s.PoolEnd == "") {
+		return errors.New("pool_start und pool_end müssen beide gesetzt sein (oder beide leer)")
+	}
+	for _, ip := range []string{s.PoolStart, s.PoolEnd, s.Gateway} {
+		if ip != "" && net.ParseIP(ip) == nil {
+			return errors.New("ungültige IP-Adresse: " + ip)
+		}
+	}
+	return validateIPList(s.DNSServers)
+}
+
+func validateReservation(r *models.DHCPReservation) error {
+	r.MACAddress = strings.TrimSpace(strings.ToLower(r.MACAddress))
+	r.IPAddress = strings.TrimSpace(r.IPAddress)
+	if _, err := net.ParseMAC(r.MACAddress); err != nil {
+		return errors.New("mac_address ist ungültig: " + r.MACAddress)
+	}
+	if net.ParseIP(r.IPAddress) == nil {
+		return errors.New("ip_address ist ungültig: " + r.IPAddress)
+	}
+	return nil
+}
+
+// validateIPList prüft eine optionale Komma-Liste von IPs.
+func validateIPList(csv string) error {
+	for _, p := range strings.Split(csv, ",") {
+		p = strings.TrimSpace(p)
+		if p != "" && net.ParseIP(p) == nil {
+			return errors.New("ungültige IP in dns_servers: " + p)
+		}
+	}
+	return nil
+}
+
+func (h *DHCPHandler) subnetErr(c *gin.Context, err error) {
+	if errors.Is(err, dhcpsvc.ErrSubnetNotFound) {
+		response.NotFound(c, err)
+		return
+	}
+	response.Internal(c, err)
+}
+
+func (h *DHCPHandler) resvErr(c *gin.Context, err error) {
+	if errors.Is(err, dhcpsvc.ErrReservationNotFound) {
+		response.NotFound(c, err)
+		return
+	}
+	response.Internal(c, err)
+}

internal/handlers/dns.go

@@ -306,7 +306,7 @@ func (h *DNSHandler) UpdateSettings(c *gin.Context) {
 // cached RRs from the resolver. Useful after DNS propagation or when
 // stale records need to be evicted immediately.
 func (h *DNSHandler) FlushCache(c *gin.Context) {
-	out, err := exec.CommandContext(c.Request.Context(), "unbound-control", "flush_zone", ".").CombinedOutput()
+	out, err := exec.CommandContext(c.Request.Context(), "/usr/sbin/unbound-control", "flush_zone", ".").CombinedOutput()
 	if err != nil {
 		slog.Error("dns flush-cache failed", "err", err, "out", string(out))
 		response.Internal(c, err)
@@ -388,7 +388,7 @@ func validateZone(z *models.DNSZone) error {
 // stats_noreset liest die Zähler ohne sie zurückzusetzen — safe für
 // wiederholte Aufrufe aus dem UI.
 func (h *DNSHandler) Stats(c *gin.Context) {
-	out, err := exec.Command("unbound-control", "stats_noreset").Output()
+	out, err := exec.Command("/usr/sbin/unbound-control", "stats_noreset").Output()
 	if err != nil {
 		response.OK(c, gin.H{
 			"error": "unbound-control nicht verfügbar: " + err.Error(),

internal/handlers/firewall.go

@@ -138,6 +138,7 @@ func (h *FirewallHandler) Register(rg *gin.RouterGroup) {
 	rl.POST("", h.CreateRule)
 	rl.GET("/:id", h.GetRule)
 	rl.PUT("/:id", h.UpdateRule)
+	rl.PATCH("/:id", h.PatchRule)
 	rl.DELETE("/:id", h.DeleteRule)
 
 	nat := g.Group("/nat-rules")
@@ -145,6 +146,7 @@ func (h *FirewallHandler) Register(rg *gin.RouterGroup) {
 	nat.POST("", h.CreateNAT)
 	nat.GET("/:id", h.GetNAT)
 	nat.PUT("/:id", h.UpdateNAT)
+	nat.PATCH("/:id", h.PatchNAT)
 	nat.DELETE("/:id", h.DeleteNAT)
 }
 
@@ -758,6 +760,48 @@ func (h *FirewallHandler) DeleteRule(c *gin.Context) {
 	response.NoContent(c); h.reload(c.Request.Context(), "delete")
 }
 
+func (h *FirewallHandler) PatchRule(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var body struct {
+		Note   *string  `json:"note"`
+		Labels []string `json:"labels"`
+	}
+	if err := c.ShouldBindJSON(&body); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	ctx := c.Request.Context()
+	if body.Note != nil {
+		if err := h.Rules.PatchNote(ctx, id, *body.Note); err != nil {
+			if errors.Is(err, firewall.ErrRuleNotFound) {
+				response.NotFound(c, err)
+				return
+			}
+			response.Internal(c, err)
+			return
+		}
+	}
+	if body.Labels != nil {
+		if err := h.Rules.PatchLabels(ctx, id, body.Labels); err != nil {
+			if errors.Is(err, firewall.ErrRuleNotFound) {
+				response.NotFound(c, err)
+				return
+			}
+			response.Internal(c, err)
+			return
+		}
+	}
+	out, err := h.Rules.Get(ctx, id)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, out)
+}
+
 // ── NAT Rules ──────────────────────────────────────────────────────────
 
 func (h *FirewallHandler) ListNAT(c *gin.Context) {
@@ -858,6 +902,48 @@ func (h *FirewallHandler) DeleteNAT(c *gin.Context) {
 	response.NoContent(c); h.reload(c.Request.Context(), "delete")
 }
 
+func (h *FirewallHandler) PatchNAT(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var body struct {
+		Note   *string  `json:"note"`
+		Labels []string `json:"labels"`
+	}
+	if err := c.ShouldBindJSON(&body); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	ctx := c.Request.Context()
+	if body.Note != nil {
+		if err := h.NATRules.PatchNote(ctx, id, *body.Note); err != nil {
+			if errors.Is(err, firewall.ErrNATRuleNotFound) {
+				response.NotFound(c, err)
+				return
+			}
+			response.Internal(c, err)
+			return
+		}
+	}
+	if body.Labels != nil {
+		if err := h.NATRules.PatchLabels(ctx, id, body.Labels); err != nil {
+			if errors.Is(err, firewall.ErrNATRuleNotFound) {
+				response.NotFound(c, err)
+				return
+			}
+			response.Internal(c, err)
+			return
+		}
+	}
+	out, err := h.NATRules.Get(ctx, id)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, out)
+}
+
 // ── Validators ─────────────────────────────────────────────────────────
 
 func validateAddrObjValue(kind, value string) error {

internal/handlers/forwardproxy.go

@@ -39,6 +39,8 @@ func (h *ForwardProxyHandler) reload(ctx context.Context, op string) {
 func (h *ForwardProxyHandler) Register(rg *gin.RouterGroup) {
 	base := rg.Group("/forward-proxy")
 	base.GET("/stats", h.Stats)
+	base.GET("/settings", h.GetSettings)
+	base.PUT("/settings", h.UpdateSettings)
 
 	g := base.Group("/acls")
 	g.GET("", h.List)
@@ -48,6 +50,34 @@ func (h *ForwardProxyHandler) Register(rg *gin.RouterGroup) {
 	g.DELETE("/:id", h.Delete)
 }
 
+func (h *ForwardProxyHandler) GetSettings(c *gin.Context) {
+	s, err := h.Repo.GetSettings(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, s)
+}
+
+func (h *ForwardProxyHandler) UpdateSettings(c *gin.Context) {
+	var req models.ForwardProxySettings
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if req.ListenPort <= 0 || req.ListenPort > 65535 {
+		req.ListenPort = 3128
+	}
+	out, err := h.Repo.UpdateSettings(c.Request.Context(), req)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "forward_proxy.settings.update", "settings", out, h.NodeID)
+	response.OK(c, out)
+	h.reload(c.Request.Context(), "settings.update")
+}
+
 func (h *ForwardProxyHandler) List(c *gin.Context) {
 	out, err := h.Repo.List(c.Request.Context())
 	if err != nil {

internal/handlers/ipaddresses.go

@@ -1,7 +1,9 @@
 package handlers
 
 import (
+	"context"
 	"errors"
+	"log/slog"
 	"strconv"
 
 	"github.com/gin-gonic/gin"
@@ -13,13 +15,27 @@ import (
 )
 
 type IPAddressesHandler struct {
-	Repo   *ipaddresses.Repo
-	Audit  *audit.Repo
-	NodeID string
+	Repo      *ipaddresses.Repo
+	Generator *ipaddresses.Generator
+	Audit     *audit.Repo
+	NodeID    string
 }
 
 func NewIPAddressesHandler(repo *ipaddresses.Repo, a *audit.Repo, nodeID string) *IPAddressesHandler {
-	return &IPAddressesHandler{Repo: repo, Audit: a, NodeID: nodeID}
+	return &IPAddressesHandler{
+		Repo:      repo,
+		Generator: ipaddresses.NewGenerator(repo),
+		Audit:     a,
+		NodeID:    nodeID,
+	}
+}
+
+func (h *IPAddressesHandler) applyAsync() {
+	go func() {
+		if err := h.Generator.Render(context.Background()); err != nil {
+			slog.Warn("ip-addresses: apply failed", "error", err)
+		}
+	}()
 }
 
 func (h *IPAddressesHandler) Register(rg *gin.RouterGroup) {
@@ -70,6 +86,7 @@ func (h *IPAddressesHandler) Create(c *gin.Context) {
 	}
 	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "ip_address.create",
 		req.Address, out, h.NodeID)
+	h.applyAsync()
 	response.Created(c, out)
 }
 
@@ -94,6 +111,7 @@ func (h *IPAddressesHandler) Update(c *gin.Context) {
 	}
 	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "ip_address.update",
 		out.Address, out, h.NodeID)
+	h.applyAsync()
 	response.OK(c, out)
 }
 
@@ -112,5 +130,6 @@ func (h *IPAddressesHandler) Delete(c *gin.Context) {
 	}
 	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "ip_address.delete",
 		strconv.FormatInt(id, 10), gin.H{"id": id}, h.NodeID)
+	h.applyAsync()
 	response.NoContent(c)
 }

internal/handlers/networks.go

@@ -1,7 +1,9 @@
 package handlers
 
 import (
+	"context"
 	"errors"
+	"log/slog"
 	"strconv"
 
 	"github.com/gin-gonic/gin"
@@ -15,18 +17,34 @@ import (
 )
 
 type NetworksHandler struct {
-	Repo   *networkifs.Repo
-	IPs    *ipaddresses.Repo
-	Zones  *firewall.ZonesRepo
-	Audit  *audit.Repo
-	NodeID string
+	Repo      *networkifs.Repo
+	Generator *networkifs.Generator
+	IPs       *ipaddresses.Repo
+	Zones     *firewall.ZonesRepo
+	Audit     *audit.Repo
+	NodeID    string
 }
 
 func NewNetworksHandler(
 	repo *networkifs.Repo, ips *ipaddresses.Repo,
 	zones *firewall.ZonesRepo, a *audit.Repo, nodeID string,
 ) *NetworksHandler {
-	return &NetworksHandler{Repo: repo, IPs: ips, Zones: zones, Audit: a, NodeID: nodeID}
+	return &NetworksHandler{
+		Repo:      repo,
+		Generator: networkifs.NewGenerator(repo),
+		IPs:       ips,
+		Zones:     zones,
+		Audit:     a,
+		NodeID:    nodeID,
+	}
+}
+
+func (h *NetworksHandler) applyAsync() {
+	go func() {
+		if err := h.Generator.Render(context.Background()); err != nil {
+			slog.Warn("network-interfaces: apply failed", "error", err)
+		}
+	}()
 }
 
 func (h *NetworksHandler) Register(rg *gin.RouterGroup) {
@@ -88,6 +106,7 @@ func (h *NetworksHandler) Create(c *gin.Context) {
 		return
 	}
 	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "network_interface.create", req.Name, out, h.NodeID)
+	h.applyAsync()
 	response.Created(c, out)
 }
 
@@ -122,6 +141,7 @@ func (h *NetworksHandler) Update(c *gin.Context) {
 		return
 	}
 	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "network_interface.update", out.Name, out, h.NodeID)
+	h.applyAsync()
 	response.OK(c, out)
 }
 
@@ -140,6 +160,7 @@ func (h *NetworksHandler) Delete(c *gin.Context) {
 	}
 	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "network_interface.delete",
 		strconv.FormatInt(id, 10), gin.H{"id": id}, h.NodeID)
+	h.applyAsync()
 	response.NoContent(c)
 }
 

internal/handlers/oidc.go

@@ -0,0 +1,349 @@
+package handlers
+
+import (
+	"crypto/rand"
+	"crypto/subtle"
+	"encoding/base64"
+	"encoding/json"
+	"errors"
+	"net/http"
+	"net/url"
+	"strings"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"golang.org/x/oauth2"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/audit"
+	oidcsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/oidc"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/session"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/setup"
+	usersvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/users"
+)
+
+// OIDC / Keycloak SSO. Additiv zum lokalen Passwort-Login. Regeln:
+//   - kein Auto-Provisioning (E-Mail muss als User existieren),
+//   - Rolle kommt aus der DB-Row (nie aus dem Token),
+//   - lokaler Login + TOTP bleiben unangetastet.
+//
+// Flow-State (state/PKCE-verifier/nonce) liegt stateless in einem 5-min
+// signierten HttpOnly-Cookie (SameSite=Lax, da der IdP-Redirect ein
+// top-level cross-site GET ist). Nach Erfolg wird dieselbe Session wie
+// beim lokalen Login ausgestellt (setSessionCookie + Signer).
+
+const (
+	oidcFlowCookie = "edgeguard_oidc_flow"
+	oidcFlowTTL    = 5 * time.Minute
+)
+
+type OIDCHandler struct {
+	Repo   *oidcsvc.Repo
+	Auth   oidcsvc.Authenticator
+	Users  *usersvc.Repo
+	Signer *session.Signer
+	Setup  *setup.Store
+	Audit  *audit.Repo
+	NodeID string
+}
+
+func NewOIDCHandler(repo *oidcsvc.Repo, auth oidcsvc.Authenticator, users *usersvc.Repo, signer *session.Signer, setupStore *setup.Store) *OIDCHandler {
+	return &OIDCHandler{Repo: repo, Auth: auth, Users: users, Signer: signer, Setup: setupStore}
+}
+
+func (h *OIDCHandler) WithAudit(a *audit.Repo, nodeID string) *OIDCHandler {
+	h.Audit = a
+	h.NodeID = nodeID
+	return h
+}
+
+// RegisterPublic mountet die unauth. Endpoints (auf v1, hinter SetupGate).
+func (h *OIDCHandler) RegisterPublic(rg *gin.RouterGroup) {
+	g := rg.Group("/auth/oidc")
+	g.GET("/settings", h.PublicSettings)
+	g.GET("/login", h.Login)
+	g.GET("/callback", h.Callback)
+}
+
+// RegisterAdmin mountet die Admin-Endpoints (auf authed: requireAuth +
+// RequireAdminForMutations → GET für alle, PUT nur admin).
+func (h *OIDCHandler) RegisterAdmin(rg *gin.RouterGroup) {
+	g := rg.Group("/oidc")
+	g.GET("/settings", h.GetSettings)
+	g.PUT("/settings", h.UpdateSettings)
+}
+
+// PublicSettings: nur, was die Login-Seite braucht.
+func (h *OIDCHandler) PublicSettings(c *gin.Context) {
+	s, err := h.Repo.Get(c.Request.Context())
+	if err != nil {
+		// Kein Datensatz/kein DB → SSO einfach „aus".
+		response.OK(c, gin.H{"enabled": false, "button_label": ""})
+		return
+	}
+	response.OK(c, gin.H{"enabled": s.Enabled, "button_label": s.ButtonLabel})
+}
+
+// GetSettings: Admin-Sicht ohne Secret, mit secret_configured + redirect_uri.
+func (h *OIDCHandler) GetSettings(c *gin.Context) {
+	s, err := h.Repo.Get(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	hasSecret, _ := h.Repo.HasSecret(c.Request.Context())
+	response.OK(c, gin.H{
+		"enabled":          s.Enabled,
+		"issuer_url":       s.IssuerURL,
+		"client_id":        s.ClientID,
+		"scopes":           s.Scopes,
+		"email_claim":      s.EmailClaim,
+		"button_label":     s.ButtonLabel,
+		"secret_configured": hasSecret,
+		"redirect_uri":     h.redirectURI(c),
+	})
+}
+
+type oidcUpdateBody struct {
+	Enabled      bool    `json:"enabled"`
+	IssuerURL    string  `json:"issuer_url"`
+	ClientID     string  `json:"client_id"`
+	ClientSecret *string `json:"client_secret"` // nil = unverändert, "" = löschen
+	Scopes       string  `json:"scopes"`
+	EmailClaim   string  `json:"email_claim"`
+	ButtonLabel  string  `json:"button_label"`
+}
+
+// UpdateSettings: PUT (admin via RequireAdminForMutations).
+func (h *OIDCHandler) UpdateSettings(c *gin.Context) {
+	var body oidcUpdateBody
+	if err := c.ShouldBindJSON(&body); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	body.IssuerURL = strings.TrimSpace(body.IssuerURL)
+	body.ClientID = strings.TrimSpace(body.ClientID)
+	if body.Scopes == "" {
+		body.Scopes = "openid email profile"
+	}
+	if body.EmailClaim == "" {
+		body.EmailClaim = "email"
+	}
+	if body.ButtonLabel == "" {
+		body.ButtonLabel = "Sign in with SSO"
+	}
+
+	if body.Enabled {
+		if body.IssuerURL == "" || body.ClientID == "" {
+			response.BadRequest(c, errors.New("issuer_url und client_id sind erforderlich, wenn OIDC aktiviert ist"))
+			return
+		}
+		if u, err := url.Parse(body.IssuerURL); err != nil || u.Scheme != "https" || u.Host == "" {
+			response.BadRequest(c, errors.New("issuer_url muss eine gültige https-URL sein"))
+			return
+		}
+		hasSecret, _ := h.Repo.HasSecret(c.Request.Context())
+		providing := body.ClientSecret != nil && *body.ClientSecret != ""
+		if !hasSecret && !providing {
+			response.BadRequest(c, errors.New("client_secret ist erforderlich (noch keins gespeichert)"))
+			return
+		}
+	}
+
+	if err := h.Repo.Update(c.Request.Context(), oidcsvc.UpdateInput{
+		Enabled:      body.Enabled,
+		IssuerURL:    body.IssuerURL,
+		ClientID:     body.ClientID,
+		Scopes:       body.Scopes,
+		EmailClaim:   body.EmailClaim,
+		ButtonLabel:  body.ButtonLabel,
+		ClientSecret: body.ClientSecret,
+	}); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	h.audit(c, actorOf(c), "oidc.settings.updated", actorOf(c),
+		gin.H{"enabled": body.Enabled, "issuer": body.IssuerURL})
+	response.OK(c, gin.H{"ok": true})
+}
+
+// Login: 302 zum IdP. Setzt das signierte Flow-Cookie.
+func (h *OIDCHandler) Login(c *gin.Context) {
+	ctx := c.Request.Context()
+	s, err := h.Repo.Get(ctx)
+	if err != nil || !s.Enabled {
+		h.fail(c, "disabled")
+		return
+	}
+	state, err1 := randToken(24)
+	nonce, err2 := randToken(24)
+	if err1 != nil || err2 != nil {
+		h.fail(c, "server")
+		return
+	}
+	verifier := oauth2.GenerateVerifier()
+	redirectURI := h.redirectURI(c)
+
+	authURL, err := h.Auth.AuthCodeURL(ctx, redirectURI, state, nonce, verifier)
+	if err != nil {
+		h.fail(c, "config")
+		return
+	}
+
+	blob, _ := json.Marshal(oidcFlow{State: state, Verifier: verifier, Nonce: nonce})
+	signed, err := h.Signer.SignBlob(blob, oidcFlowTTL)
+	if err != nil {
+		h.fail(c, "server")
+		return
+	}
+	h.setFlowCookie(c, signed)
+	c.Redirect(http.StatusFound, authURL)
+}
+
+// Callback: verifiziert Flow + Token, mappt auf DB-User, stellt Session aus.
+func (h *OIDCHandler) Callback(c *gin.Context) {
+	ctx := c.Request.Context()
+
+	// Flow-Cookie lesen + sofort entwerten (single-use).
+	rawFlow, _ := c.Cookie(oidcFlowCookie)
+	h.clearFlowCookie(c)
+	if rawFlow == "" {
+		h.fail(c, "expired")
+		return
+	}
+	payload, err := h.Signer.VerifyBlob(rawFlow)
+	if err != nil {
+		h.fail(c, "expired")
+		return
+	}
+	var flow oidcFlow
+	if json.Unmarshal(payload, &flow) != nil {
+		h.fail(c, "expired")
+		return
+	}
+
+	if c.Query("error") != "" {
+		h.fail(c, "denied")
+		return
+	}
+	if subtle.ConstantTimeCompare([]byte(c.Query("state")), []byte(flow.State)) != 1 {
+		h.fail(c, "state")
+		return
+	}
+	code := c.Query("code")
+	if code == "" {
+		h.fail(c, "exchange")
+		return
+	}
+
+	claims, err := h.Auth.Exchange(ctx, h.redirectURI(c), code, flow.Verifier)
+	if err != nil {
+		h.fail(c, "token")
+		return
+	}
+	if subtle.ConstantTimeCompare([]byte(claims.Nonce), []byte(flow.Nonce)) != 1 {
+		h.fail(c, "nonce")
+		return
+	}
+	if !claims.EmailVerified || claims.Email == "" {
+		h.audit(c, claims.Email, "auth.login.failed", claims.Email,
+			gin.H{"via": "oidc", "reason": "email_unverified", "remote": c.ClientIP()})
+		h.fail(c, "unverified")
+		return
+	}
+
+	u, _, err := h.Users.FindByEmail(ctx, claims.Email)
+	if err != nil {
+		reason := "oidc_no_account"
+		if !errors.Is(err, usersvc.ErrNotFound) {
+			reason = "server"
+		}
+		h.audit(c, claims.Email, "auth.login.failed", claims.Email,
+			gin.H{"via": "oidc", "reason": reason, "remote": c.ClientIP()})
+		h.fail(c, map[bool]string{true: "no_account", false: "server"}[reason == "oidc_no_account"])
+		return
+	}
+	if !u.Active {
+		h.audit(c, u.Email, "auth.login.failed", u.Email,
+			gin.H{"via": "oidc", "reason": "account_disabled", "remote": c.ClientIP()})
+		h.fail(c, "disabled")
+		return
+	}
+
+	// Opportunistisches sub-Linking + Schutz gegen E-Mail-Reassignment.
+	if stored, err := h.Users.GetOIDCSubject(ctx, u.ID); err == nil {
+		if stored != "" && stored != claims.Subject {
+			h.audit(c, u.Email, "auth.login.failed", u.Email,
+				gin.H{"via": "oidc", "reason": "subject_mismatch", "remote": c.ClientIP()})
+			h.fail(c, "subject_mismatch")
+			return
+		}
+		if stored == "" {
+			_ = h.Users.SetOIDCSubject(ctx, u.ID, claims.Subject)
+		}
+	}
+
+	h.Users.RecordLogin(ctx, u.ID)
+
+	// Rolle STRIKT aus der DB-Row (nie aus Claims).
+	raw, tok, err := h.Signer.IssueWithRole(u.Email, u.Role)
+	if err != nil {
+		h.fail(c, "server")
+		return
+	}
+	setSessionCookie(c, raw, tok.Exp)
+	h.audit(c, u.Email, "auth.login.success", u.Email,
+		gin.H{"via": "oidc", "role": u.Role, "remote": c.ClientIP()})
+	c.Redirect(http.StatusFound, "/dashboard")
+}
+
+// ── Helpers ──────────────────────────────────────────────────────────
+
+type oidcFlow struct {
+	State    string `json:"s"`
+	Verifier string `json:"v"`
+	Nonce    string `json:"n"`
+}
+
+// redirectURI = https://<FQDN>/api/v1/auth/oidc/callback (FQDN aus setup.json,
+// Fallback Request-Host). Muss im IdP als Redirect-URI registriert sein.
+func (h *OIDCHandler) redirectURI(c *gin.Context) string {
+	host := ""
+	if h.Setup != nil {
+		if st, err := h.Setup.Load(); err == nil && st != nil {
+			host = strings.TrimSpace(st.FQDN)
+		}
+	}
+	if host == "" {
+		host = c.Request.Host
+	}
+	return "https://" + host + "/api/v1/auth/oidc/callback"
+}
+
+func (h *OIDCHandler) fail(c *gin.Context, reason string) {
+	c.Redirect(http.StatusFound, "/login?sso_error="+url.QueryEscape(reason))
+}
+
+func (h *OIDCHandler) audit(c *gin.Context, actor, action, subject string, detail any) {
+	if h.Audit != nil {
+		_ = h.Audit.Log(c.Request.Context(), actor, action, subject, detail, h.NodeID)
+	}
+}
+
+func (h *OIDCHandler) setFlowCookie(c *gin.Context, raw string) {
+	c.SetSameSite(http.SameSiteLaxMode)
+	c.SetCookie(oidcFlowCookie, raw, int(oidcFlowTTL.Seconds()), "/", "", true, true)
+}
+
+func (h *OIDCHandler) clearFlowCookie(c *gin.Context) {
+	c.SetSameSite(http.SameSiteLaxMode)
+	c.SetCookie(oidcFlowCookie, "", -1, "/", "", true, true)
+}
+
+func randToken(n int) (string, error) {
+	b := make([]byte, n)
+	if _, err := rand.Read(b); err != nil {
+		return "", err
+	}
+	return base64.RawURLEncoding.EncodeToString(b), nil
+}

internal/handlers/oidc_test.go

@@ -0,0 +1,202 @@
+package handlers
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+	oidcsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/oidc"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/session"
+	usersvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/users"
+)
+
+// mockAuth erfüllt oidcsvc.Authenticator und liefert vorgegebene Claims —
+// kein echter IdP nötig.
+type mockAuth struct {
+	claims *oidcsvc.Claims
+	err    error
+}
+
+func (m *mockAuth) AuthCodeURL(_ context.Context, _, state, _, _ string) (string, error) {
+	return "https://idp.example/authorize?state=" + state, nil
+}
+func (m *mockAuth) Exchange(_ context.Context, _, _, _ string) (*oidcsvc.Claims, error) {
+	return m.claims, m.err
+}
+
+func oidcTestSetup(t *testing.T) (*usersvc.Repo, *pgxpool.Pool, *session.Signer) {
+	t.Helper()
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the oidc handler test")
+	}
+	ctx := context.Background()
+	// Retry: goose-Erst-Apply ist nicht concurrency-safe, wenn mehrere
+	// guarded Test-Pakete dieselbe frische DB parallel migrieren.
+	var mErr error
+	for i := 0; i < 3; i++ {
+		if mErr = database.Migrate(ctx, dsn); mErr == nil {
+			break
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	if mErr != nil {
+		t.Fatalf("migrate: %v", mErr)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	t.Cleanup(pool.Close)
+	return usersvc.New(pool), pool, session.NewSigner([]byte("0123456789abcdef0123456789abcdef"), nil, 0)
+}
+
+func seedUser(t *testing.T, repo *usersvc.Repo, pool *pgxpool.Pool, email, role string, active bool) {
+	t.Helper()
+	ctx := context.Background()
+	_, _ = pool.Exec(ctx, `DELETE FROM users WHERE email=$1`, email)
+	if _, err := repo.Create(ctx, email, "Sup3rSecret-pw-123", role, active); err != nil {
+		t.Fatalf("seed user: %v", err)
+	}
+}
+
+func runCallback(t *testing.T, h *OIDCHandler, flow oidcFlow, queryState, code string) *httptest.ResponseRecorder {
+	t.Helper()
+	gin.SetMode(gin.TestMode)
+	rec := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(rec)
+	blob, _ := json.Marshal(flow)
+	signed, err := h.Signer.SignBlob(blob, oidcFlowTTL)
+	if err != nil {
+		t.Fatal(err)
+	}
+	req := httptest.NewRequest(http.MethodGet,
+		"/api/v1/auth/oidc/callback?state="+queryState+"&code="+code, nil)
+	req.AddCookie(&http.Cookie{Name: oidcFlowCookie, Value: signed})
+	c.Request = req
+	h.Callback(c)
+	return rec
+}
+
+func sessionCookie(rec *httptest.ResponseRecorder) string {
+	for _, ck := range rec.Result().Cookies() {
+		if ck.Name == cookieName && ck.Value != "" && ck.MaxAge >= 0 {
+			return ck.Value
+		}
+	}
+	return ""
+}
+
+func TestCallback_KnownActiveUser_RoleFromDB(t *testing.T) {
+	users, pool, signer := oidcTestSetup(t)
+	seedUser(t, users, pool, "sso-viewer@test.local", "viewer", true)
+
+	h := NewOIDCHandler(nil, &mockAuth{claims: &oidcsvc.Claims{
+		Email: "sso-viewer@test.local", EmailVerified: true, Subject: "sub-1", Nonce: "N",
+	}}, users, signer, nil)
+
+	rec := runCallback(t, h, oidcFlow{State: "S", Verifier: "v", Nonce: "N"}, "S", "code")
+
+	if loc := rec.Header().Get("Location"); loc != "/dashboard" {
+		t.Fatalf("expected redirect to /dashboard, got %q (body proves failure path)", loc)
+	}
+	raw := sessionCookie(rec)
+	if raw == "" {
+		t.Fatal("expected a session cookie to be set")
+	}
+	tok, err := signer.Verify(raw)
+	if err != nil {
+		t.Fatalf("session token invalid: %v", err)
+	}
+	// Kernbeweis: Rolle kommt aus der DB-Row (viewer), nicht aus Claims.
+	if tok.Role != "viewer" {
+		t.Errorf("token role = %q, want viewer (role must come from DB)", tok.Role)
+	}
+	if tok.Actor != "sso-viewer@test.local" {
+		t.Errorf("token actor = %q", tok.Actor)
+	}
+}
+
+func TestCallback_UnknownEmail_Rejected(t *testing.T) {
+	users, pool, signer := oidcTestSetup(t)
+	_, _ = pool.Exec(context.Background(), `DELETE FROM users WHERE email=$1`, "ghost@test.local")
+
+	h := NewOIDCHandler(nil, &mockAuth{claims: &oidcsvc.Claims{
+		Email: "ghost@test.local", EmailVerified: true, Subject: "x", Nonce: "N",
+	}}, users, signer, nil)
+
+	rec := runCallback(t, h, oidcFlow{State: "S", Nonce: "N"}, "S", "code")
+	if !strings.Contains(rec.Header().Get("Location"), "sso_error=no_account") {
+		t.Fatalf("expected sso_error=no_account, got %q", rec.Header().Get("Location"))
+	}
+	if sessionCookie(rec) != "" {
+		t.Fatal("no session cookie expected for unknown user")
+	}
+}
+
+func TestCallback_InactiveUser_Rejected(t *testing.T) {
+	users, pool, signer := oidcTestSetup(t)
+	seedUser(t, users, pool, "sso-disabled@test.local", "admin", false)
+
+	h := NewOIDCHandler(nil, &mockAuth{claims: &oidcsvc.Claims{
+		Email: "sso-disabled@test.local", EmailVerified: true, Subject: "x", Nonce: "N",
+	}}, users, signer, nil)
+
+	rec := runCallback(t, h, oidcFlow{State: "S", Nonce: "N"}, "S", "code")
+	if !strings.Contains(rec.Header().Get("Location"), "sso_error=disabled") {
+		t.Fatalf("expected sso_error=disabled, got %q", rec.Header().Get("Location"))
+	}
+	if sessionCookie(rec) != "" {
+		t.Fatal("no session cookie expected for inactive user")
+	}
+}
+
+func TestCallback_EmailUnverified_Rejected(t *testing.T) {
+	users, pool, signer := oidcTestSetup(t)
+	seedUser(t, users, pool, "sso-unverified@test.local", "admin", true)
+
+	h := NewOIDCHandler(nil, &mockAuth{claims: &oidcsvc.Claims{
+		Email: "sso-unverified@test.local", EmailVerified: false, Subject: "x", Nonce: "N",
+	}}, users, signer, nil)
+
+	rec := runCallback(t, h, oidcFlow{State: "S", Nonce: "N"}, "S", "code")
+	if !strings.Contains(rec.Header().Get("Location"), "sso_error=unverified") {
+		t.Fatalf("expected sso_error=unverified, got %q", rec.Header().Get("Location"))
+	}
+	if sessionCookie(rec) != "" {
+		t.Fatal("no session cookie expected for unverified email")
+	}
+}
+
+func TestCallback_NonceMismatch_Rejected(t *testing.T) {
+	users, pool, signer := oidcTestSetup(t)
+	seedUser(t, users, pool, "sso-nonce@test.local", "admin", true)
+
+	h := NewOIDCHandler(nil, &mockAuth{claims: &oidcsvc.Claims{
+		Email: "sso-nonce@test.local", EmailVerified: true, Subject: "x", Nonce: "WRONG",
+	}}, users, signer, nil)
+
+	rec := runCallback(t, h, oidcFlow{State: "S", Nonce: "N"}, "S", "code")
+	if !strings.Contains(rec.Header().Get("Location"), "sso_error=nonce") {
+		t.Fatalf("expected sso_error=nonce, got %q", rec.Header().Get("Location"))
+	}
+}
+
+func TestCallback_StateMismatch_Rejected(t *testing.T) {
+	users, _, signer := oidcTestSetup(t)
+	h := NewOIDCHandler(nil, &mockAuth{claims: &oidcsvc.Claims{}}, users, signer, nil)
+
+	rec := runCallback(t, h, oidcFlow{State: "S", Nonce: "N"}, "WRONG", "code")
+	if !strings.Contains(rec.Header().Get("Location"), "sso_error=state") {
+		t.Fatalf("expected sso_error=state, got %q", rec.Header().Get("Location"))
+	}
+}

internal/handlers/radius.go

@@ -0,0 +1,359 @@
+package handlers
+
+import (
+	"context"
+	"errors"
+	"log/slog"
+	"net"
+	"regexp"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/audit"
+	radiussvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/radius"
+)
+
+// RADIUSHandler exposes /api/v1/radius/{settings,clients,users} for the
+// FreeRADIUS server (files-based PAP/CHAP).
+type RADIUSHandler struct {
+	Repo     *radiussvc.Repo
+	Audit    *audit.Repo
+	NodeID   string
+	Reloader func(ctx context.Context) error
+}
+
+func NewRADIUSHandler(repo *radiussvc.Repo, a *audit.Repo, nodeID string, reloader func(context.Context) error) *RADIUSHandler {
+	return &RADIUSHandler{Repo: repo, Audit: a, NodeID: nodeID, Reloader: reloader}
+}
+
+func (h *RADIUSHandler) reload(ctx context.Context, op string) {
+	if h.Reloader == nil {
+		return
+	}
+	if err := h.Reloader(ctx); err != nil {
+		slog.Warn("freeradius: reload after mutation failed", "op", op, "error", err)
+	}
+}
+
+func (h *RADIUSHandler) Register(rg *gin.RouterGroup) {
+	g := rg.Group("/radius")
+	g.GET("/settings", h.GetSettings)
+	g.PUT("/settings", h.UpdateSettings)
+
+	c := g.Group("/clients")
+	c.GET("", h.ListClients)
+	c.POST("", h.CreateClient)
+	c.GET("/:id", h.GetClient)
+	c.PUT("/:id", h.UpdateClient)
+	c.DELETE("/:id", h.DeleteClient)
+
+	u := g.Group("/users")
+	u.GET("", h.ListUsers)
+	u.POST("", h.CreateUser)
+	u.GET("/:id", h.GetUser)
+	u.PUT("/:id", h.UpdateUser)
+	u.DELETE("/:id", h.DeleteUser)
+}
+
+var validClientName = regexp.MustCompile(`^[A-Za-z0-9_.-]+$`)
+
+// ── Settings ─────────────────────────────────────────────────────────
+
+func (h *RADIUSHandler) GetSettings(c *gin.Context) {
+	s, err := h.Repo.GetSettings(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, s)
+}
+
+func (h *RADIUSHandler) UpdateSettings(c *gin.Context) {
+	var req models.RADIUSSettings
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := validateIPList(req.ListenAddresses); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.UpdateSettings(c.Request.Context(), req)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.settings.update", "",
+		gin.H{"enabled": out.Enabled}, h.NodeID)
+	response.OK(c, out)
+	h.reload(c.Request.Context(), "settings.update")
+}
+
+// ── Clients ──────────────────────────────────────────────────────────
+
+type clientView struct {
+	models.RADIUSClient
+	SecretConfigured bool `json:"secret_configured"`
+}
+
+func clientToView(c models.RADIUSClient) clientView {
+	return clientView{RADIUSClient: c, SecretConfigured: len(c.SecretEnc) > 0}
+}
+
+func (h *RADIUSHandler) ListClients(c *gin.Context) {
+	list, err := h.Repo.ListClients(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	out := make([]clientView, 0, len(list))
+	for _, cl := range list {
+		out = append(out, clientToView(cl))
+	}
+	response.OK(c, gin.H{"clients": out})
+}
+
+func (h *RADIUSHandler) GetClient(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	cl, err := h.Repo.GetClient(c.Request.Context(), id)
+	if err != nil {
+		h.clientErr(c, err)
+		return
+	}
+	response.OK(c, clientToView(*cl))
+}
+
+type clientBody struct {
+	Name        string  `json:"name"`
+	IPAddr      string  `json:"ipaddr"`
+	Secret      *string `json:"secret"` // create: required; update: nil=unchanged
+	Active      bool    `json:"active"`
+	Description string  `json:"description"`
+}
+
+func (b *clientBody) validate(creating bool) error {
+	b.Name = strings.TrimSpace(b.Name)
+	b.IPAddr = strings.TrimSpace(b.IPAddr)
+	if !validClientName.MatchString(b.Name) {
+		return errors.New("name darf nur Buchstaben/Ziffern/._- enthalten")
+	}
+	if net.ParseIP(b.IPAddr) == nil {
+		if _, _, err := net.ParseCIDR(b.IPAddr); err != nil {
+			return errors.New("ipaddr ist keine gültige IP/CIDR: " + b.IPAddr)
+		}
+	}
+	if creating && b.Secret == nil {
+		return errors.New("secret ist erforderlich")
+	}
+	if b.Secret != nil {
+		if len(*b.Secret) < 6 {
+			return errors.New("secret muss mind. 6 Zeichen haben (leer löscht es nicht)")
+		}
+		if strings.ContainsAny(*b.Secret, "\r\n") {
+			return errors.New("secret darf keine Zeilenumbrüche enthalten")
+		}
+	}
+	return nil
+}
+
+func (h *RADIUSHandler) CreateClient(c *gin.Context) {
+	var b clientBody
+	if err := c.ShouldBindJSON(&b); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := b.validate(true); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.CreateClient(c.Request.Context(), b.Name, b.IPAddr, *b.Secret, b.Active, b.Description)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.client.create", out.Name, gin.H{"ipaddr": out.IPAddr}, h.NodeID)
+	response.Created(c, clientToView(*out))
+	h.reload(c.Request.Context(), "client.create")
+}
+
+func (h *RADIUSHandler) UpdateClient(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var b clientBody
+	if err := c.ShouldBindJSON(&b); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := b.validate(false); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.UpdateClient(c.Request.Context(), id, b.Name, b.IPAddr, b.Secret, b.Active, b.Description)
+	if err != nil {
+		h.clientErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.client.update", out.Name, gin.H{"ipaddr": out.IPAddr}, h.NodeID)
+	response.OK(c, clientToView(*out))
+	h.reload(c.Request.Context(), "client.update")
+}
+
+func (h *RADIUSHandler) DeleteClient(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	if err := h.Repo.DeleteClient(c.Request.Context(), id); err != nil {
+		h.clientErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.client.delete", "", gin.H{"id": id}, h.NodeID)
+	response.OK(c, gin.H{"ok": true})
+	h.reload(c.Request.Context(), "client.delete")
+}
+
+// ── Users ────────────────────────────────────────────────────────────
+
+type userView struct {
+	models.RADIUSUser
+	PasswordConfigured bool `json:"password_configured"`
+}
+
+func userToView(u models.RADIUSUser) userView {
+	return userView{RADIUSUser: u, PasswordConfigured: len(u.PasswordEnc) > 0}
+}
+
+func (h *RADIUSHandler) ListUsers(c *gin.Context) {
+	list, err := h.Repo.ListUsers(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	out := make([]userView, 0, len(list))
+	for _, u := range list {
+		out = append(out, userToView(u))
+	}
+	response.OK(c, gin.H{"users": out})
+}
+
+func (h *RADIUSHandler) GetUser(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	u, err := h.Repo.GetUser(c.Request.Context(), id)
+	if err != nil {
+		h.userErr(c, err)
+		return
+	}
+	response.OK(c, userToView(*u))
+}
+
+type userBody struct {
+	Username string  `json:"username"`
+	Password *string `json:"password"`
+	Active   bool    `json:"active"`
+}
+
+func (b *userBody) validate(creating bool) error {
+	b.Username = strings.TrimSpace(b.Username)
+	if b.Username == "" || strings.ContainsAny(b.Username, "\r\n") {
+		return errors.New("username ist erforderlich (ohne Zeilenumbrüche)")
+	}
+	if creating && (b.Password == nil || *b.Password == "") {
+		return errors.New("password ist erforderlich")
+	}
+	if b.Password != nil {
+		if *b.Password == "" {
+			return errors.New("password darf nicht leer sein (löscht es nicht)")
+		}
+		if strings.ContainsAny(*b.Password, "\r\n") {
+			return errors.New("password darf keine Zeilenumbrüche enthalten")
+		}
+	}
+	return nil
+}
+
+func (h *RADIUSHandler) CreateUser(c *gin.Context) {
+	var b userBody
+	if err := c.ShouldBindJSON(&b); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := b.validate(true); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.CreateUser(c.Request.Context(), b.Username, *b.Password, b.Active)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.user.create", out.Username, nil, h.NodeID)
+	response.Created(c, userToView(*out))
+	h.reload(c.Request.Context(), "user.create")
+}
+
+func (h *RADIUSHandler) UpdateUser(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	var b userBody
+	if err := c.ShouldBindJSON(&b); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if err := b.validate(false); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	out, err := h.Repo.UpdateUser(c.Request.Context(), id, b.Username, b.Password, b.Active)
+	if err != nil {
+		h.userErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.user.update", out.Username, nil, h.NodeID)
+	response.OK(c, userToView(*out))
+	h.reload(c.Request.Context(), "user.update")
+}
+
+func (h *RADIUSHandler) DeleteUser(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	if err := h.Repo.DeleteUser(c.Request.Context(), id); err != nil {
+		h.userErr(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "radius.user.delete", "", gin.H{"id": id}, h.NodeID)
+	response.OK(c, gin.H{"ok": true})
+	h.reload(c.Request.Context(), "user.delete")
+}
+
+// ── error mapping ────────────────────────────────────────────────────
+
+func (h *RADIUSHandler) clientErr(c *gin.Context, err error) {
+	if errors.Is(err, radiussvc.ErrClientNotFound) {
+		response.NotFound(c, err)
+		return
+	}
+	response.Internal(c, err)
+}
+
+func (h *RADIUSHandler) userErr(c *gin.Context, err error) {
+	if errors.Is(err, radiussvc.ErrUserNotFound) {
+		response.NotFound(c, err)
+		return
+	}
+	response.Internal(c, err)
+}

internal/handlers/system.go

@@ -118,10 +118,12 @@ func (h *SystemHandler) Register(rg *gin.RouterGroup) {
 	g.POST("/haproxy-reload", h.HAProxyReload)
 	g.POST("/render-configs", h.RenderConfigs)
 	g.POST("/service-restart", h.ServiceRestart)
+	g.POST("/service-toggle", h.ServiceToggle)
 	g.GET("/upgrade-status", h.UpgradeStatus)
 	g.GET("/ipv6", h.IPv6)
 	g.POST("/ipv6", h.SetIPv6)
 	g.GET("/config-preview", h.ConfigPreview)
+	g.GET("/vip-status", h.VIPStatus)
 }
 
 // RegisterAgent mountet die read-only System-Endpoints auf der mTLS-
@@ -188,10 +190,14 @@ var servicesToCheck = []struct{ Label, Unit string }{
 	{"edgeguard-scheduler", "edgeguard-scheduler"},
 	{"haproxy", "haproxy"},
 	{"nftables", "nftables"},
+	{"keepalived", "keepalived"},
 	{"unbound", "unbound"},
 	{"chrony", "chrony"},
 	{"squid", "squid"},
 	{"postgresql", "postgresql"},
+	{"crowdsec", "crowdsec"},
+	{"crowdsec-firewall-bouncer", "crowdsec-firewall-bouncer"},
+	{"edgeguard-waf", "edgeguard-waf"},
 }
 
 type serviceStatus struct {
@@ -630,6 +636,53 @@ func (h *SystemHandler) ServiceRestart(c *gin.Context) {
 	response.OK(c, gin.H{"ok": true, "service": svc})
 }
 
+// toggleAllowlist defines which services may be started/stopped via the UI.
+var toggleAllowlist = map[string]bool{
+	"crowdsec":                  true,
+	"crowdsec-firewall-bouncer": true,
+	"edgeguard-waf":             true,
+	"squid":                     true,
+	"unbound":                   true,
+}
+
+// ServiceToggle starts or stops (and enables/disables) a service.
+// Body: {"service": "crowdsec", "enabled": true}
+func (h *SystemHandler) ServiceToggle(c *gin.Context) {
+	var req struct {
+		Service string `json:"service" binding:"required"`
+		Enabled bool   `json:"enabled"`
+	}
+	if err := c.ShouldBindJSON(&req); err != nil {
+		response.Err(c, http.StatusBadRequest, simpleErr("service and enabled required"))
+		return
+	}
+	svc := strings.TrimSpace(req.Service)
+	if !toggleAllowlist[svc] {
+		response.Err(c, http.StatusBadRequest, simpleErr("service not in toggle allowlist: "+svc))
+		return
+	}
+	unit := svc + ".service"
+	action := "stop"
+	sysdAction := "disable"
+	if req.Enabled {
+		action = "start"
+		sysdAction = "enable"
+	}
+	if out, err := exec.Command("sudo", "-n", "/usr/bin/systemctl", sysdAction, unit).CombinedOutput(); err != nil {
+		response.Err(c, http.StatusInternalServerError, simpleErr(strings.TrimSpace(string(out))+": "+err.Error()))
+		return
+	}
+	if out, err := exec.Command("sudo", "-n", "/usr/bin/systemctl", action, unit).CombinedOutput(); err != nil {
+		response.Err(c, http.StatusInternalServerError, simpleErr(strings.TrimSpace(string(out))+": "+err.Error()))
+		return
+	}
+	if h.Audit != nil {
+		_ = h.Audit.Log(c.Request.Context(), actorOf(c), "system.service_toggle",
+			svc, gin.H{"service": svc, "enabled": req.Enabled}, h.NodeID)
+	}
+	response.OK(c, gin.H{"ok": true, "service": svc, "enabled": req.Enabled})
+}
+
 // RenderConfigs erzwingt ein Re-Render aller Service-Configs aus dem
 // aktuellen DB-State. Läuft haproxy + alle ExtraReloaders (nftables,
 // wireguard, squid, unbound, chrony) durch. Fehler werden gesammelt
@@ -1077,6 +1130,87 @@ func classifyLinkType(ifc net.Interface) string {
 	return ""
 }
 
+// VIPStatus returns the VRRP state and active VIPs for this node.
+// Uses net.Interfaces() (no shell-out) to check which VIPs from
+// ip_addresses WHERE is_vip=true are currently assigned locally.
+// MASTER = at least one VIP is locally present; BACKUP = none present.
+func (h *SystemHandler) VIPStatus(c *gin.Context) {
+	type vipEntry struct {
+		Address string `json:"address"`
+		Prefix  int    `json:"prefix"`
+		Device  string `json:"device"`
+		Active  bool   `json:"active"`
+	}
+	type vipStatus struct {
+		VRRPState        string     `json:"vrrp_state"`
+		KeepalivedActive bool       `json:"keepalived_active"`
+		VIPs             []vipEntry `json:"vips"`
+	}
+
+	ctx := c.Request.Context()
+
+	// keepalived service active?
+	kaOut, _ := exec.CommandContext(ctx, "systemctl", "is-active", "keepalived").Output()
+	kaActive := strings.TrimSpace(string(kaOut)) == "active"
+
+	// query VIPs from DB
+	var dbVIPs []vipEntry
+	if h.Pool != nil {
+		rows, err := h.Pool.Query(ctx,
+			`SELECT a.address, a.prefix, COALESCE(i.name,'') AS device
+			   FROM ip_addresses a
+			   LEFT JOIN network_interfaces i ON i.id = a.interface_id
+			  WHERE a.is_vip = true AND a.active = true
+			  ORDER BY a.address`)
+		if err == nil {
+			defer rows.Close()
+			for rows.Next() {
+				var e vipEntry
+				if err2 := rows.Scan(&e.Address, &e.Prefix, &e.Device); err2 == nil {
+					dbVIPs = append(dbVIPs, e)
+				}
+			}
+		}
+	}
+
+	// build set of locally assigned IPs
+	localIPs := make(map[string]bool)
+	if ifaces, err := net.Interfaces(); err == nil {
+		for _, ifc := range ifaces {
+			if addrs, err2 := ifc.Addrs(); err2 == nil {
+				for _, a := range addrs {
+					if ipnet, ok := a.(*net.IPNet); ok {
+						localIPs[ipnet.IP.String()] = true
+					}
+				}
+			}
+		}
+	}
+
+	anyActive := false
+	for i := range dbVIPs {
+		dbVIPs[i].Active = localIPs[dbVIPs[i].Address]
+		if dbVIPs[i].Active {
+			anyActive = true
+		}
+	}
+
+	state := "UNKNOWN"
+	if kaActive {
+		if anyActive {
+			state = "MASTER"
+		} else {
+			state = "BACKUP"
+		}
+	}
+
+	response.OK(c, vipStatus{
+		VRRPState:        state,
+		KeepalivedActive: kaActive,
+		VIPs:             dbVIPs,
+	})
+}
+
 func flagsToList(f net.Flags) []string {
 	var out []string
 	if f&net.FlagUp != 0 {

internal/handlers/users.go

@@ -35,6 +35,7 @@ func (h *UsersHandler) Register(rg *gin.RouterGroup) {
 	g.PUT("/:id", h.Update)
 	g.POST("/:id/password", h.SetPassword)
 	g.DELETE("/:id", h.Delete)
+	g.DELETE("/:id/totp", h.DisableTOTP)
 }
 
 func (h *UsersHandler) List(c *gin.Context) {
@@ -164,3 +165,22 @@ func (h *UsersHandler) Delete(c *gin.Context) {
 		c.Param("id"), nil, h.NodeID)
 	response.OK(c, gin.H{"ok": true})
 }
+
+// DisableTOTP allows an admin to disable 2FA for any user.
+func (h *UsersHandler) DisableTOTP(c *gin.Context) {
+	id, ok := parseID(c)
+	if !ok {
+		return
+	}
+	if err := h.Repo.DisableTOTP(c.Request.Context(), id); err != nil {
+		if errors.Is(err, users.ErrNotFound) {
+			response.NotFound(c, err)
+			return
+		}
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "user.totp.disabled",
+		c.Param("id"), nil, h.NodeID)
+	response.OK(c, gin.H{"ok": true})
+}

internal/handlers/waf.go

@@ -0,0 +1,227 @@
+package handlers
+
+import (
+	"context"
+	"errors"
+	"log/slog"
+	"net"
+	"net/http"
+	"regexp"
+	"strconv"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/handlers/response"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/audit"
+	wafsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/waf"
+)
+
+// wafRuleIDRe erlaubt nur einzelne CRS-Rule-IDs oder Ranges ("942100" /
+// "942100-942999") als Exclusion — verhindert SecLang-Direktiven-Injection.
+var wafRuleIDRe = regexp.MustCompile(`^[0-9]{1,9}(-[0-9]{1,9})?$`)
+
+// WafHandler exposes the per-domain WAF configuration REST API:
+//
+//	GET    /waf/configs              — list all configs (one per domain)
+//	GET    /waf/configs/:domain_id   — get config for a domain
+//	PUT    /waf/configs/:domain_id   — upsert config for a domain
+type WafHandler struct {
+	Repo     *wafsvc.Repo
+	Audit    *audit.Repo
+	NodeID   string
+	Reloader func(ctx context.Context) error
+}
+
+func NewWafHandler(repo *wafsvc.Repo, a *audit.Repo, nodeID string, reloader func(context.Context) error) *WafHandler {
+	return &WafHandler{Repo: repo, Audit: a, NodeID: nodeID, Reloader: reloader}
+}
+
+func (h *WafHandler) Register(rg *gin.RouterGroup) {
+	g := rg.Group("/waf")
+	g.GET("/configs", h.List)
+	g.GET("/configs/:domain_id", h.Get)
+	g.PUT("/configs/:domain_id", h.Upsert)
+	g.GET("/alerts", h.ListAlerts)
+	g.DELETE("/alerts", h.PurgeAlerts)
+}
+
+// List returns all WAF configs.
+func (h *WafHandler) List(c *gin.Context) {
+	configs, err := h.Repo.List(c.Request.Context())
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"configs": configs})
+}
+
+// Get returns the WAF config for a single domain.
+// Returns a default (disabled) config when none exists yet.
+func (h *WafHandler) Get(c *gin.Context) {
+	domainID, err := strconv.ParseInt(c.Param("domain_id"), 10, 64)
+	if err != nil {
+		response.BadRequest(c, errors.New("invalid domain_id"))
+		return
+	}
+	cfg, err := h.Repo.GetByDomain(c.Request.Context(), domainID)
+	if err != nil {
+		if errors.Is(err, wafsvc.ErrNotFound) {
+			// Return a default config so the UI always gets a usable object.
+			response.OK(c, gin.H{"config": defaultConfig(domainID)})
+			return
+		}
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"config": cfg})
+}
+
+// upsertBody is the accepted JSON for PUT /waf/configs/:domain_id.
+type upsertBody struct {
+	Enabled         bool              `json:"enabled"`
+	Mode            string            `json:"mode"`
+	ParanoiaLevel   int               `json:"paranoia_level"`
+	RuleExclusions  []string          `json:"rule_exclusions"`
+	ExclusionNotes  map[string]string `json:"exclusion_notes"`
+	TrustedProxies  []string          `json:"trusted_proxies"`
+	CustomRules     string            `json:"custom_rules"`
+}
+
+// Upsert creates or updates the WAF config for a domain.
+func (h *WafHandler) Upsert(c *gin.Context) {
+	domainID, err := strconv.ParseInt(c.Param("domain_id"), 10, 64)
+	if err != nil {
+		response.BadRequest(c, errors.New("invalid domain_id"))
+		return
+	}
+	var body upsertBody
+	if err := c.ShouldBindJSON(&body); err != nil {
+		response.BadRequest(c, err)
+		return
+	}
+	if body.Mode == "" {
+		body.Mode = "detection"
+	}
+	if body.ParanoiaLevel < 1 || body.ParanoiaLevel > 4 {
+		body.ParanoiaLevel = 1
+	}
+	if body.RuleExclusions == nil {
+		body.RuleExclusions = []string{}
+	}
+	if body.TrustedProxies == nil {
+		body.TrustedProxies = []string{}
+	}
+
+	if body.ExclusionNotes == nil {
+		body.ExclusionNotes = map[string]string{}
+	}
+	// Exclusions müssen reine Rule-IDs/Ranges sein (sonst Direktiven-Injection
+	// in die SecLang-Config via Newline).
+	for _, ex := range body.RuleExclusions {
+		if !wafRuleIDRe.MatchString(strings.TrimSpace(ex)) {
+			response.BadRequest(c, errors.New("ungültige Rule-Exclusion (nur IDs/Ranges erlaubt): "+ex))
+			return
+		}
+	}
+	// Trusted-Proxies müssen gültige IPs/CIDRs sein.
+	for _, p := range body.TrustedProxies {
+		p = strings.TrimSpace(p)
+		if p == "" {
+			continue
+		}
+		if net.ParseIP(p) == nil {
+			if _, _, err := net.ParseCIDR(p); err != nil {
+				response.BadRequest(c, errors.New("ungültiger Trusted-Proxy (IP/CIDR): "+p))
+				return
+			}
+		}
+	}
+	cfg := models.WafConfig{
+		DomainID:       domainID,
+		Enabled:        body.Enabled,
+		Mode:           body.Mode,
+		ParanoiaLevel:  body.ParanoiaLevel,
+		RuleExclusions: body.RuleExclusions,
+		ExclusionNotes: body.ExclusionNotes,
+		TrustedProxies: body.TrustedProxies,
+		CustomRules:    body.CustomRules,
+	}
+	result, err := h.Repo.Upsert(c.Request.Context(), cfg)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "waf.config.upsert",
+		strconv.FormatInt(domainID, 10),
+		gin.H{"enabled": body.Enabled, "mode": body.Mode, "paranoia_level": body.ParanoiaLevel},
+		h.NodeID)
+	// Reload HAProxy so the SPOE filter is added/removed based on
+	// whether any domain now has WAF enabled.
+	if h.Reloader != nil {
+		go func() {
+			if err := h.Reloader(context.Background()); err != nil {
+				slog.Warn("waf: haproxy reload after config change failed", "error", err)
+			}
+		}()
+	}
+	c.JSON(http.StatusOK, gin.H{"config": result})
+}
+
+// ListAlerts returns recent WAF alerts. Optional: ?domain_id=X&limit=N
+func (h *WafHandler) ListAlerts(c *gin.Context) {
+	var domainID *int64
+	if v := c.Query("domain_id"); v != "" {
+		id, err := strconv.ParseInt(v, 10, 64)
+		if err != nil {
+			response.BadRequest(c, errors.New("invalid domain_id"))
+			return
+		}
+		domainID = &id
+	}
+	limit := 200
+	if v := c.Query("limit"); v != "" {
+		if n, err := strconv.Atoi(v); err == nil && n > 0 {
+			limit = n
+		}
+	}
+	alerts, err := h.Repo.ListAlerts(c.Request.Context(), domainID, limit)
+	if err != nil {
+		response.Internal(c, err)
+		return
+	}
+	response.OK(c, gin.H{"alerts": alerts})
+}
+
+// PurgeAlerts deletes old WAF alerts. Optional: ?days=N (default 30)
+func (h *WafHandler) PurgeAlerts(c *gin.Context) {
+	days := 30
+	if v := c.Query("days"); v != "" {
+		if n, err := strconv.Atoi(v); err == nil && n > 0 {
+			days = n
+		}
+	}
+	if err := h.Repo.PurgeAlerts(c.Request.Context(), days); err != nil {
+		response.Internal(c, err)
+		return
+	}
+	_ = h.Audit.Log(c.Request.Context(), actorOf(c), "waf.alerts.purge",
+		"", gin.H{"days": days}, h.NodeID)
+	response.OK(c, gin.H{"ok": true, "days": days})
+}
+
+// defaultConfig returns a sensible disabled default for a domain
+// that has no WAF config row yet.
+func defaultConfig(domainID int64) models.WafConfig {
+	return models.WafConfig{
+		DomainID:       domainID,
+		Enabled:        false,
+		Mode:           "detection",
+		ParanoiaLevel:  1,
+		RuleExclusions: []string{},
+		ExclusionNotes: map[string]string{},
+		TrustedProxies: []string{},
+		CustomRules:    "",
+	}
+}

internal/haproxy/haproxy.cfg.tpl

@@ -80,6 +80,11 @@ frontend public_https
     bind [::]:443 ssl crt /etc/edgeguard/tls/ alpn h2,http/1.1
     bind quic6@:443 ssl crt /etc/edgeguard/tls/ alpn h3
     {{- end}}
+    {{- if .WAFEnabled}}
+    # WAF: SPOE-Filter — edgeguard-waf inspiziert jeden Request.
+    # filter muss vor allen http-request/http-response-Direktiven stehen.
+    filter spoe engine edgeguard-waf config /etc/edgeguard/haproxy/coraza-spoe.cfg
+    {{- end}}
 
     # Alt-Svc: signalisiert dass h3 auf demselben Port verfügbar ist.
     # ma=86400 = Browser darf den Hinweis 24h cachen.
@@ -91,6 +96,10 @@ frontend public_https
     # echte Source-IP ohne XFF-Chain-Parsing brauchen.
     http-request set-header X-Forwarded-Proto https
     http-request set-header X-Real-IP %[src]
+    {{- if .WAFEnabled}}
+    # WAF: Request blockieren wenn edgeguard-waf txn.waf.status gesetzt hat.
+    http-request deny deny_status 403 if { var(txn.waf.status) -m found }
+    {{- end}}
 
     {{- if .GlobalMaintenance}}
     # Whole-Box-Maintenance — Settings → Maintenance-Mode aktiv. Dieser
@@ -195,6 +204,16 @@ backend rl_{{$d.ID}}
 {{- end}}
 {{- end}}
 
+{{- if .WAFEnabled}}
+
+# SPOE-Backend für edgeguard-waf (TCP, kein HTTP-Parsing).
+backend spoe-edgeguard-waf
+    mode    tcp
+    timeout connect 100ms
+    timeout server   1s
+    server  spoe-waf-1 127.0.0.1:9000
+{{- end}}
+
 {{- range $b := .Backends}}
 
 backend eg_backend_{{$b.ID}}

internal/haproxy/haproxy.go

@@ -24,6 +24,7 @@ import (
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/domains"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/routingrules"
 	"git.netcell-it.de/projekte/edgeguard-native/internal/services/setup"
+	wafsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/waf"
 )
 
 //go:embed haproxy.cfg.tpl
@@ -64,25 +65,29 @@ type Generator struct {
 	ServersRepo   *backendservers.Repo
 	RoutingRepo   *routingrules.Repo
 	HeadersRepo   *domainheaders.Repo
+	WafRepo       *wafsvc.Repo
 
 	// SetupStore (optional): wenn gesetzt, lesen wir Whole-Box-
 	// Maintenance-Status hieraus und reichen ihn als View.GlobalMaintenance
 	// ans Template weiter.
 	SetupStore *setup.Store
 
-	OutputPath string
-	SkipReload bool
+	OutputPath     string
+	SPOEConfigPath string
+	SkipReload     bool
 }
 
 func New(pool *pgxpool.Pool) *Generator {
 	return &Generator{
-		Pool:         pool,
-		DomainsRepo:  domains.New(pool),
-		BackendsRepo: backends.New(pool),
-		ServersRepo:  backendservers.New(pool),
-		RoutingRepo:  routingrules.New(pool),
-		HeadersRepo:  domainheaders.New(pool),
-		SetupStore:   setup.NewStore(setup.DefaultDir),
+		Pool:           pool,
+		DomainsRepo:    domains.New(pool),
+		BackendsRepo:   backends.New(pool),
+		ServersRepo:    backendservers.New(pool),
+		RoutingRepo:    routingrules.New(pool),
+		HeadersRepo:    domainheaders.New(pool),
+		WafRepo:        wafsvc.New(pool),
+		SetupStore:     setup.NewStore(setup.DefaultDir),
+		SPOEConfigPath: filepath.Join(configgen.EtcEdgeguard, "haproxy", "coraza-spoe.cfg"),
 	}
 }
 
@@ -116,6 +121,17 @@ func (g *Generator) Render(ctx context.Context) error {
 	if err := configgen.AtomicWrite(out, buf.Bytes(), 0o644); err != nil {
 		return fmt.Errorf("haproxy: write: %w", err)
 	}
+	// Write SPOE config whenever WAF is enabled; remove it when disabled
+	// so HAProxy doesn't fail on a missing backend reference.
+	if view.WAFEnabled {
+		spoeOut := g.SPOEConfigPath
+		if spoeOut == "" {
+			spoeOut = filepath.Join(configgen.EtcEdgeguard, "haproxy", "coraza-spoe.cfg")
+		}
+		if err := configgen.AtomicWrite(spoeOut, []byte(spoeCfg), 0o644); err != nil {
+			return fmt.Errorf("haproxy: write spoe config: %w", err)
+		}
+	}
 	if g.SkipReload {
 		return nil
 	}
@@ -125,6 +141,29 @@ func (g *Generator) Render(ctx context.Context) error {
 	return nil
 }
 
+// spoeCfg is the static SPOE configuration for edgeguard-waf.
+// HAProxy 3.x format: [<engine-name>] section + spoe-agent / spoe-message
+// (no square brackets around spoe-agent/spoe-message keywords).
+// spoeCfg uses `option continue-on-error` so that HAProxy never blocks
+// a request when the SPOE agent is slow or unavailable. Without this,
+// a timeout during CRS engine initialization would block all traffic,
+// including domains without WAF configured.
+const spoeCfg = `# Generated by edgeguard-api. DO NOT EDIT.
+[edgeguard-waf]
+spoe-agent edgeguard-waf-agent
+    messages        edgeguard-waf-req
+    option          var-prefix waf
+    option          continue-on-error
+    timeout         hello      100ms
+    timeout         idle       30s
+    timeout         processing 1s
+    use-backend     spoe-edgeguard-waf
+
+spoe-message edgeguard-waf-req
+    args src=src method=method uri=url ver=req.ver headers=req.hdrs host=req.hdr(host)
+    event on-frontend-http-request
+`
+
 // View is what the template consumes. Routes per domain are pre-
 // joined here so the template can stay declarative; Servers leben pro
 // BackendView, damit das Template einen `backend …`-Block mit den N
@@ -148,6 +187,11 @@ type View struct {
 	// IPv6Enabled: wenn true fügt das Template zusätzliche
 	// bind-Direktiven für [::]:80, [::]:443 und [::]:3443 hinzu.
 	IPv6Enabled bool
+
+	// WAFEnabled: wenn true wird der SPOE-Filter für edgeguard-waf
+	// in public_https eingebunden und das spoe-Backend gerendert.
+	// Wird gesetzt sobald mindestens eine Domain WAF enabled hat.
+	WAFEnabled bool
 }
 
 type DomainView struct {
@@ -289,6 +333,14 @@ func (g *Generator) loadView(ctx context.Context) (*View, error) {
 		}
 	}
 	v := &View{Domains: domViews, Backends: activeBackends, HTTPDomains: httpDomains}
+
+	// Check whether any domain has WAF enabled.
+	if g.WafRepo != nil {
+		if wafEnabled, err := g.WafRepo.ListEnabled(ctx); err == nil {
+			v.WAFEnabled = len(wafEnabled) > 0
+		}
+	}
+
 	if g.SetupStore != nil {
 		if st, err := g.SetupStore.Load(); err == nil && st != nil {
 			v.GlobalMaintenance = st.MaintenanceMode

internal/kea/kea.go

@@ -0,0 +1,235 @@
+// Package kea renders the Kea DHCPv4 server config from the dhcp_*
+// tables and manages the kea-dhcp4-server service lifecycle.
+//
+// The config is built as a Go struct and json-marshalled (NOT a text
+// template) so the output is always syntactically valid JSON. Managed
+// at /etc/edgeguard/kea/kea-dhcp4.conf (edgeguard-owned); postinst
+// symlinks /etc/kea/kea-dhcp4.conf to it.
+//
+// Safety: the service runs ONLY when dhcp_settings.enabled is true on
+// THIS node (a DHCP server is network-sensitive; default off). enabled
+// → enable + restart; disabled → disable + stop.
+package kea
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
+	dhcpsvc "git.netcell-it.de/projekte/edgeguard-native/internal/services/dhcp"
+)
+
+const (
+	ConfPath    = configgen.EtcEdgeguard + "/kea/kea-dhcp4.conf"
+	serviceName = "kea-dhcp4-server"
+	leaseFile   = "/var/lib/kea/kea-leases4.csv"
+	keaBinary   = "/usr/sbin/kea-dhcp4"
+)
+
+type Generator struct {
+	Pool       *pgxpool.Pool
+	Repo       *dhcpsvc.Repo
+	SkipReload bool
+}
+
+func New(pool *pgxpool.Pool) *Generator {
+	return &Generator{Pool: pool, Repo: dhcpsvc.New(pool)}
+}
+
+func (g *Generator) Name() string { return "kea" }
+
+// ── Kea config JSON shape ────────────────────────────────────────────
+
+type keaConfig struct {
+	Dhcp4 dhcp4 `json:"Dhcp4"`
+}
+type dhcp4 struct {
+	InterfacesConfig ifcfg        `json:"interfaces-config"`
+	LeaseDatabase    leaseDB      `json:"lease-database"`
+	ValidLifetime    int          `json:"valid-lifetime"`
+	MaxValidLifetime int          `json:"max-valid-lifetime"`
+	OptionData       []optionData `json:"option-data,omitempty"`
+	Subnet4          []subnet4    `json:"subnet4"`
+	Loggers          []logger     `json:"loggers"`
+}
+type ifcfg struct {
+	Interfaces []string `json:"interfaces"`
+}
+type leaseDB struct {
+	Type    string `json:"type"`
+	Persist bool   `json:"persist"`
+	Name    string `json:"name"`
+}
+type optionData struct {
+	Name string `json:"name"`
+	Data string `json:"data"`
+}
+type subnet4 struct {
+	ID           int64         `json:"id"`
+	Subnet       string        `json:"subnet"`
+	Pools        []pool        `json:"pools,omitempty"`
+	OptionData   []optionData  `json:"option-data,omitempty"`
+	Reservations []reservation `json:"reservations,omitempty"`
+}
+type pool struct {
+	Pool string `json:"pool"`
+}
+type reservation struct {
+	HWAddress string `json:"hw-address"`
+	IPAddress string `json:"ip-address"`
+	Hostname  string `json:"hostname,omitempty"`
+}
+type logger struct {
+	Name          string   `json:"name"`
+	Severity      string   `json:"severity"`
+	OutputOptions []outOpt `json:"output_options"`
+}
+type outOpt struct {
+	Output string `json:"output"`
+}
+
+// buildConfig assembliert die Kea-Config aus dem DB-State.
+func (g *Generator) buildConfig(ctx context.Context) (*keaConfig, *bool, error) {
+	settings, err := g.Repo.GetSettings(ctx)
+	if err != nil {
+		return nil, nil, fmt.Errorf("get dhcp settings: %w", err)
+	}
+	subnets, err := g.Repo.ListSubnets(ctx)
+	if err != nil {
+		return nil, nil, fmt.Errorf("list subnets: %w", err)
+	}
+	resv, err := g.Repo.ListAllReservations(ctx)
+	if err != nil {
+		return nil, nil, fmt.Errorf("list reservations: %w", err)
+	}
+	bySubnet := map[int64][]reservation{}
+	for _, r := range resv {
+		if !r.Active {
+			continue
+		}
+		bySubnet[r.SubnetID] = append(bySubnet[r.SubnetID], reservation{
+			HWAddress: r.MACAddress, IPAddress: r.IPAddress, Hostname: r.Hostname,
+		})
+	}
+
+	ifaceSet := map[string]bool{}
+	ifaces := []string{} // nie nil → JSON "[]" statt "null" (Kea lehnt null ab)
+	var sn4 []subnet4
+
+	for _, s := range subnets {
+		if !s.Active {
+			continue
+		}
+		if !ifaceSet[s.InterfaceName] {
+			ifaceSet[s.InterfaceName] = true
+			ifaces = append(ifaces, s.InterfaceName)
+		}
+		sub := subnet4{ID: s.ID, Subnet: s.SubnetCIDR}
+		if s.PoolStart != "" && s.PoolEnd != "" {
+			sub.Pools = []pool{{Pool: s.PoolStart + " - " + s.PoolEnd}}
+		}
+		if s.Gateway != "" {
+			sub.OptionData = append(sub.OptionData, optionData{Name: "routers", Data: s.Gateway})
+		}
+		dns := s.DNSServers
+		if dns == "" {
+			dns = settings.DNSServers
+		}
+		if dns != "" {
+			sub.OptionData = append(sub.OptionData, optionData{Name: "domain-name-servers", Data: normalizeCSV(dns)})
+		}
+		sub.Reservations = bySubnet[s.ID]
+		sn4 = append(sn4, sub)
+	}
+
+	d := dhcp4{
+		InterfacesConfig: ifcfg{Interfaces: ifaces},
+		LeaseDatabase:    leaseDB{Type: "memfile", Persist: true, Name: leaseFile},
+		ValidLifetime:    settings.DefaultLease,
+		MaxValidLifetime: settings.MaxLease,
+		Subnet4:          sn4,
+		Loggers: []logger{{
+			Name: "kea-dhcp4", Severity: "INFO",
+			OutputOptions: []outOpt{{Output: "stdout"}},
+		}},
+	}
+	if settings.DNSServers != "" {
+		d.OptionData = append(d.OptionData, optionData{Name: "domain-name-servers", Data: normalizeCSV(settings.DNSServers)})
+	}
+	if settings.DomainName != "" {
+		d.OptionData = append(d.OptionData, optionData{Name: "domain-name", Data: settings.DomainName})
+	}
+	if d.Subnet4 == nil {
+		d.Subnet4 = []subnet4{}
+	}
+	return &keaConfig{Dhcp4: d}, &settings.Enabled, nil
+}
+
+func (g *Generator) RenderToString(ctx context.Context) (string, error) {
+	cfg, _, err := g.buildConfig(ctx)
+	if err != nil {
+		return "", err
+	}
+	b, err := json.MarshalIndent(cfg, "", "  ")
+	if err != nil {
+		return "", err
+	}
+	return string(b) + "\n", nil
+}
+
+func (g *Generator) Render(ctx context.Context) error {
+	cfg, enabled, err := g.buildConfig(ctx)
+	if err != nil {
+		return err
+	}
+
+	// Default-off / disabled: Service stoppen + disablen, nichts weiter.
+	if enabled == nil || !*enabled {
+		if g.SkipReload {
+			return nil
+		}
+		_ = configgen.DisableService(serviceName)
+		_ = configgen.StopService(serviceName)
+		return nil
+	}
+
+	b, err := json.MarshalIndent(cfg, "", "  ")
+	if err != nil {
+		return err
+	}
+	if err := configgen.AtomicWrite(ConfPath, append(b, '\n'), 0o644); err != nil {
+		return fmt.Errorf("write kea config: %w", err)
+	}
+	if g.SkipReload {
+		return nil
+	}
+	// Best-effort Config-Test (verhindert Restart mit kaputter Semantik).
+	if _, statErr := os.Stat(keaBinary); statErr == nil {
+		if out, terr := exec.Command(keaBinary, "-t", ConfPath).CombinedOutput(); terr != nil {
+			return fmt.Errorf("kea-dhcp4 -t rejected config: %w (output: %s)", terr, strings.TrimSpace(string(out)))
+		}
+	}
+	if err := configgen.EnableService(serviceName); err != nil {
+		return err
+	}
+	return configgen.RestartService(serviceName)
+}
+
+// normalizeCSV trimmt Whitespace um Komma-getrennte Werte (Kea will
+// "a,b,c" ohne Leerzeichen-Toleranz-Probleme).
+func normalizeCSV(s string) string {
+	parts := strings.Split(s, ",")
+	out := make([]string, 0, len(parts))
+	for _, p := range parts {
+		if t := strings.TrimSpace(p); t != "" {
+			out = append(out, t)
+		}
+	}
+	return strings.Join(out, ",")
+}

internal/kea/kea_test.go

@@ -0,0 +1,89 @@
+package kea
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"os/exec"
+	"strings"
+	"testing"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+)
+
+// Guarded integration test: set EG_FWTEST_DSN (sonst skip).
+func TestRender_DHCPConfig(t *testing.T) {
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the kea renderer test")
+	}
+	ctx := context.Background()
+	var mErr error
+	for i := 0; i < 3; i++ {
+		if mErr = database.Migrate(ctx, dsn); mErr == nil {
+			break
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	if mErr != nil {
+		t.Fatalf("migrate: %v", mErr)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	defer pool.Close()
+
+	for _, q := range []string{
+		`DELETE FROM dhcp_reservations`,
+		`DELETE FROM dhcp_subnets`,
+		`UPDATE dhcp_settings SET enabled=true, default_lease=3600, max_lease=7200, domain_name='lan', dns_servers='1.1.1.1, 8.8.8.8' WHERE id=1`,
+	} {
+		if _, err := pool.Exec(ctx, q); err != nil {
+			t.Fatalf("seed (%s): %v", q, err)
+		}
+	}
+	var subID int64
+	if err := pool.QueryRow(ctx, `
+INSERT INTO dhcp_subnets (name, interface_name, subnet_cidr, pool_start, pool_end, gateway, dns_servers, active)
+VALUES ('lan','eth1','10.0.0.0/24','10.0.0.100','10.0.0.200','10.0.0.1','',true) RETURNING id`).Scan(&subID); err != nil {
+		t.Fatalf("seed subnet: %v", err)
+	}
+	if _, err := pool.Exec(ctx, `
+INSERT INTO dhcp_reservations (subnet_id, mac_address, ip_address, hostname, active)
+VALUES ($1,'aa:bb:cc:dd:ee:ff','10.0.0.50','printer',true)`, subID); err != nil {
+		t.Fatalf("seed reservation: %v", err)
+	}
+
+	out, err := New(pool).RenderToString(ctx)
+	if err != nil {
+		t.Fatalf("render: %v", err)
+	}
+	if !json.Valid([]byte(out)) {
+		t.Fatalf("rendered config is not valid JSON:\n%s", out)
+	}
+	for _, want := range []string{
+		`"10.0.0.0/24"`,
+		`"10.0.0.100 - 10.0.0.200"`,
+		`"aa:bb:cc:dd:ee:ff"`,
+		`"routers"`,
+		`"eth1"`,
+		`"hw-address"`,
+		`"valid-lifetime": 3600`,
+	} {
+		if !strings.Contains(out, want) {
+			t.Errorf("rendered config missing %q\n----\n%s", want, out)
+		}
+	}
+
+	// Best-effort: echte Kea-Validierung, falls die Binary da ist.
+	if _, statErr := os.Stat(keaBinary); statErr == nil {
+		f, _ := os.CreateTemp(t.TempDir(), "kea-*.conf")
+		_, _ = f.WriteString(out)
+		f.Close()
+		if combined, err := exec.Command(keaBinary, "-t", f.Name()).CombinedOutput(); err != nil {
+			t.Fatalf("kea-dhcp4 -t rejected rendered config: %v\n%s", err, combined)
+		}
+	}
+}

internal/keepalived/keepalived.conf.tpl

@@ -0,0 +1,72 @@
+global_defs {
+    router_id {{ .RouterID }}
+    script_user root
+    enable_script_security
+}
+
+vrrp_script chk_edgeguard {
+    script "/usr/lib/edgeguard/keepalived-check.sh"
+    interval 2
+    weight -50
+    fall 3
+    rise 2
+}
+{{ if .GWCheckIP }}
+vrrp_script chk_gateway {
+    script "/usr/lib/edgeguard/keepalived-gw-check.sh {{ .GWCheckIP }}"
+    interval 5
+    weight -110
+    fall 2
+    rise 2
+}
+{{ end }}
+{{ if .HBInterface }}
+vrrp_sync_group VG_1 {
+    group {
+        VI_1
+        VI_HB
+    }
+}
+{{ end }}
+vrrp_instance VI_1 {
+    state {{ .State }}
+    interface {{ .Interface }}
+    virtual_router_id {{ .RouterID }}
+    priority {{ .Priority }}
+    advert_int 1
+{{ if .SrcIP }}    unicast_src_ip {{ .SrcIP }}
+    unicast_peer {
+        {{ .PeerIP }}
+    }
+{{ end }}    authentication {
+        auth_type PASS
+        auth_pass {{ .AuthPass }}
+    }
+    virtual_ipaddress {
+{{ range .VIPs }}        {{ .Address }}/{{ .Prefix }} dev {{ .Device }}
+{{ end }}    }
+    track_script {
+        chk_edgeguard
+{{ if .GWCheckIP }}        chk_gateway
+{{ end }}    }
+    notify_master  "/usr/lib/edgeguard/keepalived-master.sh"
+    notify_backup  "/usr/lib/edgeguard/keepalived-backup.sh"
+    notify_fault   "/usr/lib/edgeguard/keepalived-backup.sh"
+}
+{{ if .HBInterface }}
+vrrp_instance VI_HB {
+    state {{ .State }}
+    interface {{ .HBInterface }}
+    virtual_router_id {{ .HBRouterID }}
+    priority {{ .Priority }}
+    advert_int 1
+{{ if .HBSrcIP }}    unicast_src_ip {{ .HBSrcIP }}
+    unicast_peer {
+        {{ .HBPeerIP }}
+    }
+{{ end }}    authentication {
+        auth_type PASS
+        auth_pass {{ .AuthPass }}
+    }
+}
+{{ end }}

internal/keepalived/keepalived.go

@@ -0,0 +1,210 @@
+// Package keepalived rendert /etc/keepalived/keepalived.conf aus
+// cluster_settings (VIP/VRRP-Config) und ha_nodes (local vs. peer).
+//
+// Split-Brain-Strategie: kein Auto-Promote. notify_master loggt nur
+// und sendet einen internen Alert. Promotion ist immer manuell via
+// "edgeguard-ctl promote" — das ist die einzig sichere Option ohne
+// externes Quorum in einem 2-Node-Cluster.
+package keepalived
+
+import (
+	"bytes"
+	"context"
+	_ "embed"
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+	"text/template"
+
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+const ConfPath = "/etc/keepalived/keepalived.conf"
+
+//go:embed keepalived.conf.tpl
+var cfgTpl string
+
+var tpl = template.Must(template.New("keepalived").Parse(cfgTpl))
+
+// VIPEntry ist eine einzelne VIP-Adresse die keepalived verwaltet.
+type VIPEntry struct {
+	Address string // z.B. 89.163.205.100
+	Prefix  int    // z.B. 24
+	Device  string // z.B. eth0
+}
+
+// View ist der Template-Kontext.
+type View struct {
+	State     string // MASTER | BACKUP
+	Interface string // Interface für VRRP-Advertisements (VI_1)
+	RouterID  int
+	Priority  int    // MASTER=200, BACKUP=100
+	SrcIP     string // eigene Public-IP (unicast_src_ip)
+	PeerIP    string // Peer-Public-IP (unicast_peer)
+	AuthPass  string
+	VIPs      []VIPEntry // alle is_vip=true Einträge aus ip_addresses
+	// Dual-path VRRP (Split-Brain-Schutz, Migration 0033)
+	HBInterface string
+	HBSrcIP     string
+	HBPeerIP    string
+	HBRouterID  int
+	// GW-Tracking
+	GWCheckIP string
+}
+
+type generator struct {
+	pool    *pgxpool.Pool
+	localID string
+}
+
+func New(pool *pgxpool.Pool, localID string) configgen.Generator {
+	return &generator{pool: pool, localID: localID}
+}
+
+func (g *generator) Name() string { return "keepalived" }
+
+func (g *generator) Render(ctx context.Context) error {
+	cs, vips, local, peer, err := g.loadData(ctx)
+	if err != nil {
+		return fmt.Errorf("keepalived: load: %w", err)
+	}
+	if len(vips) == 0 {
+		// Keine VIPs konfiguriert → keepalived.conf nicht schreiben.
+		return nil
+	}
+	v := g.buildView(cs, vips, local, peer)
+	var buf bytes.Buffer
+	if err := tpl.Execute(&buf, v); err != nil {
+		return fmt.Errorf("keepalived: template: %w", err)
+	}
+	if err := configgen.AtomicWrite(ConfPath, buf.Bytes(), 0o640); err != nil {
+		return fmt.Errorf("keepalived: write: %w", err)
+	}
+	if err := reloadKeepalived(); err != nil {
+		return fmt.Errorf("keepalived: reload: %w", err)
+	}
+	return nil
+}
+
+func (g *generator) loadData(ctx context.Context) (*models.ClusterSettings, []VIPEntry, *models.HANode, *models.HANode, error) {
+	var cs models.ClusterSettings
+	row := g.pool.QueryRow(ctx, `
+		SELECT id, vip_address, vip_interface, vip_auth_pass, vrrp_router_id,
+		       hb_interface, hb_src_ip, hb_peer_ip, hb_router_id, gw_check_ip
+		FROM cluster_settings WHERE id = 1`)
+	if err := row.Scan(&cs.ID, &cs.VIPAddress, &cs.VIPInterface, &cs.VIPAuthPass, &cs.VRRPRouterID,
+		&cs.HBInterface, &cs.HBSrcIP, &cs.HBPeerIP, &cs.HBRouterID, &cs.GWCheckIP); err != nil {
+		return nil, nil, nil, nil, fmt.Errorf("cluster_settings: %w", err)
+	}
+
+	// Alle VIPs aus ip_addresses (is_vip=true, active=true) inkl. Interface-Name.
+	vipRows, err := g.pool.Query(ctx, `
+		SELECT ia.address, ia.prefix, ni.name
+		FROM ip_addresses ia
+		JOIN network_interfaces ni ON ia.interface_id = ni.id
+		WHERE ia.is_vip = true AND ia.active = true
+		ORDER BY ni.name, ia.address`)
+	if err != nil {
+		return nil, nil, nil, nil, fmt.Errorf("ip_addresses: %w", err)
+	}
+	defer vipRows.Close()
+	var vips []VIPEntry
+	for vipRows.Next() {
+		var v VIPEntry
+		if err := vipRows.Scan(&v.Address, &v.Prefix, &v.Device); err != nil {
+			continue
+		}
+		vips = append(vips, v)
+	}
+
+	nodeRows, err := g.pool.Query(ctx, `SELECT id, fqdn, role, pg_role, public_ip, status FROM ha_nodes ORDER BY joined_at`)
+	if err != nil {
+		return nil, nil, nil, nil, fmt.Errorf("ha_nodes: %w", err)
+	}
+	defer nodeRows.Close()
+
+	var local, peer *models.HANode
+	for nodeRows.Next() {
+		n := &models.HANode{}
+		if err := nodeRows.Scan(&n.ID, &n.FQDN, &n.Role, &n.PGRole, &n.PublicIP, &n.Status); err != nil {
+			continue
+		}
+		if n.ID == g.localID {
+			local = n
+		} else {
+			peer = n
+		}
+	}
+	if local == nil {
+		return nil, nil, nil, nil, fmt.Errorf("local node %s not in ha_nodes", g.localID)
+	}
+	return &cs, vips, local, peer, nil
+}
+
+func (g *generator) buildView(cs *models.ClusterSettings, vips []VIPEntry, local, peer *models.HANode) View {
+	v := View{
+		RouterID:    cs.VRRPRouterID,
+		VIPs:        vips,
+		Interface:   deref(cs.VIPInterface),
+		AuthPass:    deref(cs.VIPAuthPass),
+		HBInterface: deref(cs.HBInterface),
+		HBSrcIP:     deref(cs.HBSrcIP),
+		HBPeerIP:    deref(cs.HBPeerIP),
+		HBRouterID:  cs.HBRouterID,
+		GWCheckIP:   deref(cs.GWCheckIP),
+	}
+	if v.Interface == "" {
+		v.Interface = "eth0"
+	}
+	if v.AuthPass == "" {
+		v.AuthPass = "edgeguard"
+	}
+	if v.HBRouterID == 0 {
+		v.HBRouterID = 52
+	}
+
+	// pg_role=standby ist das härtere Signal — ein Standby-Node ist niemals
+	// MASTER, auch wenn role='primary' noch aus dem Join-Prozess stammt.
+	// Reihenfolge: standby → BACKUP; sonst primary-Check.
+	if local.PGRole == "standby" {
+		v.State = "BACKUP"
+		v.Priority = 100
+	} else if local.PGRole == "primary" || local.Role == "primary" {
+		v.State = "MASTER"
+		v.Priority = 200
+	} else {
+		v.State = "BACKUP"
+		v.Priority = 100
+	}
+
+	if local.PublicIP != nil {
+		v.SrcIP = *local.PublicIP
+	}
+	if peer != nil && peer.PublicIP != nil {
+		v.PeerIP = *peer.PublicIP
+	}
+	return v
+}
+
+func reloadKeepalived() error {
+	if _, err := os.Stat("/run/keepalived.pid"); os.IsNotExist(err) {
+		// keepalived läuft noch nicht — erster Render beim Start.
+		return nil
+	}
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemctl", "reload-or-restart", "keepalived.service")
+	if out, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("sudo systemctl reload-or-restart keepalived.service: %w (output: %s)", err, strings.TrimSpace(string(out)))
+	}
+	return nil
+}
+
+func deref(s *string) string {
+	if s == nil {
+		return ""
+	}
+	return *s
+}

internal/models/cluster_settings.go

@@ -0,0 +1,24 @@
+package models
+
+import "time"
+
+// ClusterSettings ist die Singleton-Tabelle (id=1) für VIP/VRRP-
+// und Replikations-Konfiguration. Angelegt in Migration 0029.
+// hb_* = zweite VRRP-Instanz für Split-Brain-Schutz (0033).
+// gw_check_ip = Gateway-IP für vrrp_script chk_gateway (0033).
+type ClusterSettings struct {
+	ID           int       `gorm:"column:id;primaryKey"   json:"id"`
+	VIPAddress   *string   `gorm:"column:vip_address"     json:"vip_address,omitempty"`
+	VIPInterface *string   `gorm:"column:vip_interface"   json:"vip_interface,omitempty"`
+	VIPAuthPass  *string   `gorm:"column:vip_auth_pass"   json:"vip_auth_pass,omitempty"`
+	VRRPRouterID int       `gorm:"column:vrrp_router_id"  json:"vrrp_router_id"`
+	HBInterface  *string   `gorm:"column:hb_interface"    json:"hb_interface,omitempty"`
+	HBSrcIP      *string   `gorm:"column:hb_src_ip"       json:"hb_src_ip,omitempty"`
+	HBPeerIP     *string   `gorm:"column:hb_peer_ip"      json:"hb_peer_ip,omitempty"`
+	HBRouterID   int       `gorm:"column:hb_router_id"    json:"hb_router_id"`
+	GWCheckIP    *string   `gorm:"column:gw_check_ip"     json:"gw_check_ip,omitempty"`
+	CreatedAt    time.Time `gorm:"column:created_at"      json:"created_at"`
+	UpdatedAt    time.Time `gorm:"column:updated_at"      json:"updated_at"`
+}
+
+func (ClusterSettings) TableName() string { return "cluster_settings" }

internal/models/dhcp.go

@@ -0,0 +1,53 @@
+package models
+
+import "time"
+
+// DHCPSettings ist die node-lokale Singleton-Konfiguration des Kea-DHCPv4-
+// Servers (ob diese Node DHCP betreibt + globale Defaults).
+type DHCPSettings struct {
+	ID           int       `gorm:"column:id;primaryKey"   json:"id"`
+	Enabled      bool      `gorm:"column:enabled"         json:"enabled"`
+	DefaultLease int       `gorm:"column:default_lease"   json:"default_lease"`
+	MaxLease     int       `gorm:"column:max_lease"       json:"max_lease"`
+	DomainName   string    `gorm:"column:domain_name"     json:"domain_name"`
+	DNSServers   string    `gorm:"column:dns_servers"     json:"dns_servers"`
+	CreatedAt    time.Time `gorm:"column:created_at"      json:"created_at"`
+	UpdatedAt    time.Time `gorm:"column:updated_at"      json:"updated_at"`
+}
+
+func (DHCPSettings) TableName() string { return "dhcp_settings" }
+
+// DHCPSubnet ist ein vom DHCP-Server bedientes Subnetz (an ein Interface
+// per NAME gebunden — cluster-sicher, da interface_id node-lokal wäre).
+type DHCPSubnet struct {
+	ID            int64     `gorm:"column:id;primaryKey"      json:"id"`
+	Name          string    `gorm:"column:name"               json:"name"`
+	InterfaceName string    `gorm:"column:interface_name"     json:"interface_name"`
+	SubnetCIDR    string    `gorm:"column:subnet_cidr"        json:"subnet_cidr"`
+	PoolStart     string    `gorm:"column:pool_start"         json:"pool_start"`
+	PoolEnd       string    `gorm:"column:pool_end"           json:"pool_end"`
+	Gateway       string    `gorm:"column:gateway"            json:"gateway"`
+	DNSServers    string    `gorm:"column:dns_servers"        json:"dns_servers"`
+	LeaseTime     *int      `gorm:"column:lease_time"         json:"lease_time,omitempty"`
+	Active        bool      `gorm:"column:active"             json:"active"`
+	Description   string    `gorm:"column:description"        json:"description"`
+	CreatedAt     time.Time `gorm:"column:created_at"         json:"created_at"`
+	UpdatedAt     time.Time `gorm:"column:updated_at"         json:"updated_at"`
+}
+
+func (DHCPSubnet) TableName() string { return "dhcp_subnets" }
+
+// DHCPReservation ist eine statische MAC→IP-Zuordnung innerhalb eines Subnets.
+type DHCPReservation struct {
+	ID         int64     `gorm:"column:id;primaryKey"   json:"id"`
+	SubnetID   int64     `gorm:"column:subnet_id"       json:"subnet_id"`
+	Name       string    `gorm:"column:name"            json:"name"`
+	MACAddress string    `gorm:"column:mac_address"     json:"mac_address"`
+	IPAddress  string    `gorm:"column:ip_address"      json:"ip_address"`
+	Hostname   string    `gorm:"column:hostname"        json:"hostname"`
+	Active     bool      `gorm:"column:active"          json:"active"`
+	CreatedAt  time.Time `gorm:"column:created_at"      json:"created_at"`
+	UpdatedAt  time.Time `gorm:"column:updated_at"      json:"updated_at"`
+}
+
+func (DHCPReservation) TableName() string { return "dhcp_reservations" }

internal/models/dns.go

@@ -40,16 +40,20 @@ func (DNSRecord) TableName() string { return "dns_records" }
 // Optionen. Default kommt aus der Migration (alle Werte sinnvoll
 // für die typische LAN-Resolver-Rolle).
 type DNSSettings struct {
-	ID                int64     `gorm:"primaryKey"                  json:"id"`
-	ListenAddresses   string    `gorm:"column:listen_addresses"     json:"listen_addresses"`
-	ListenPort        int       `gorm:"column:listen_port"          json:"listen_port"`
-	UpstreamForwards  string    `gorm:"column:upstream_forwards"    json:"upstream_forwards"`
-	AccessACL         string    `gorm:"column:access_acl"           json:"access_acl"`
-	DNSSEC            bool      `gorm:"column:dnssec"               json:"dnssec"`
-	QNameMinimisation bool      `gorm:"column:qname_minimisation"   json:"qname_minimisation"`
-	CacheMinTTL       int       `gorm:"column:cache_min_ttl"        json:"cache_min_ttl"`
-	CacheMaxTTL       int       `gorm:"column:cache_max_ttl"        json:"cache_max_ttl"`
-	UpdatedAt         time.Time `gorm:"column:updated_at"           json:"updated_at"`
+	ID                int64     `gorm:"primaryKey"                    json:"id"`
+	ListenAddresses   string    `gorm:"column:listen_addresses"       json:"listen_addresses"`
+	ListenPort        int       `gorm:"column:listen_port"            json:"listen_port"`
+	UpstreamForwards  string    `gorm:"column:upstream_forwards"      json:"upstream_forwards"`
+	AccessACL         string    `gorm:"column:access_acl"             json:"access_acl"`
+	DNSSEC            bool      `gorm:"column:dnssec"                 json:"dnssec"`
+	QNameMinimisation bool      `gorm:"column:qname_minimisation"     json:"qname_minimisation"`
+	CacheMinTTL       int       `gorm:"column:cache_min_ttl"          json:"cache_min_ttl"`
+	CacheMaxTTL       int       `gorm:"column:cache_max_ttl"          json:"cache_max_ttl"`
+	Prefetch          bool      `gorm:"column:prefetch"               json:"prefetch"`
+	ServeExpired      bool      `gorm:"column:serve_expired"          json:"serve_expired"`
+	MsgCacheSizeMB    int       `gorm:"column:msg_cache_size_mb"      json:"msg_cache_size_mb"`
+	RRSetCacheSizeMB  int       `gorm:"column:rrset_cache_size_mb"    json:"rrset_cache_size_mb"`
+	UpdatedAt         time.Time `gorm:"column:updated_at"             json:"updated_at"`
 }
 
 func (DNSSettings) TableName() string { return "dns_settings" }

internal/models/firewall_nat_rule.go

@@ -33,6 +33,8 @@ type FirewallNATRule struct {
 	TargetPortEnd   *int      `gorm:"column:target_port_end"      json:"target_port_end,omitempty"`
 
 	Comment         *string   `gorm:"column:comment"              json:"comment,omitempty"`
+	Note            *string   `gorm:"column:note"                 json:"note,omitempty"`
+	Labels          []string  `gorm:"column:labels"               json:"labels"`
 	CreatedAt       time.Time `gorm:"column:created_at"           json:"created_at"`
 	UpdatedAt       time.Time `gorm:"column:updated_at"           json:"updated_at"`
 }

internal/models/firewall_rule.go

@@ -36,6 +36,8 @@ type FirewallRule struct {
 
 	Log                 bool      `gorm:"column:log"                       json:"log"`
 	Comment             *string   `gorm:"column:comment"                   json:"comment,omitempty"`
+	Note                *string   `gorm:"column:note"                      json:"note,omitempty"`
+	Labels              []string  `gorm:"column:labels;serializer:json"    json:"labels"`
 	CreatedAt           time.Time `gorm:"column:created_at"                json:"created_at"`
 	UpdatedAt           time.Time `gorm:"column:updated_at"                json:"updated_at"`
 }

internal/models/forward_proxy_settings.go

@@ -0,0 +1,19 @@
+package models
+
+import "time"
+
+type ForwardProxySettings struct {
+	ID              int       `gorm:"primaryKey"              json:"id"`
+	ListenAddresses string    `gorm:"column:listen_addresses" json:"listen_addresses"`
+	ListenPort      int       `gorm:"column:listen_port"      json:"listen_port"`
+	CacheMemMB      int       `gorm:"column:cache_mem_mb"     json:"cache_mem_mb"`
+	CacheDirMB      int       `gorm:"column:cache_dir_mb"     json:"cache_dir_mb"`
+	MaxObjSizeMB    int       `gorm:"column:max_obj_size_mb"  json:"max_obj_size_mb"`
+	ConnectTimeout  int       `gorm:"column:connect_timeout"  json:"connect_timeout"`
+	ReadTimeout     int       `gorm:"column:read_timeout"     json:"read_timeout"`
+	RequestTimeout  int       `gorm:"column:request_timeout"  json:"request_timeout"`
+	CreatedAt       time.Time `gorm:"column:created_at"       json:"created_at"`
+	UpdatedAt       time.Time `gorm:"column:updated_at"       json:"updated_at"`
+}
+
+func (ForwardProxySettings) TableName() string { return "forward_proxy_settings" }

internal/models/ha_node.go

@@ -4,7 +4,7 @@ import "time"
 
 // HANode mirrort eine Row der ha_nodes-Tabelle. Erweitert in Migration
 // 0020 um version/config_hash/mgmt_ip/status für Cluster-Phase-3-
-// Drift-Detection + Health-State.
+// Drift-Detection + Health-State. Migration 0029 fügt PGRole hinzu.
 type HANode struct {
 	ID         string     `gorm:"column:id;primaryKey"           json:"id"`
 	Name       string     `gorm:"column:name"                    json:"name"`
@@ -14,6 +14,7 @@ type HANode struct {
 	InternalIP *string    `gorm:"column:internal_ip;type:inet"   json:"internal_ip,omitempty"`
 	MgmtIP     *string    `gorm:"column:mgmt_ip;type:inet"       json:"mgmt_ip,omitempty"`
 	Role       string     `gorm:"column:role"                    json:"role"`
+	PGRole     string     `gorm:"column:pg_role"                 json:"pg_role"`
 	Version    *string    `gorm:"column:version"                 json:"version,omitempty"`
 	ConfigHash *string    `gorm:"column:config_hash"             json:"config_hash,omitempty"`
 	Status     string     `gorm:"column:status"                  json:"status"`

internal/models/oidc_settings.go

@@ -0,0 +1,21 @@
+package models
+
+import "time"
+
+// OIDCSettings ist die Singleton-Konfiguration für OIDC/Keycloak-SSO.
+// ClientSecretEnc trägt den verschlüsselten Client-Secret (secrets.Box)
+// und wird NIE serialisiert (json:"-").
+type OIDCSettings struct {
+	ID              int       `gorm:"column:id;primaryKey"        json:"id"`
+	Enabled         bool      `gorm:"column:enabled"              json:"enabled"`
+	IssuerURL       string    `gorm:"column:issuer_url"           json:"issuer_url"`
+	ClientID        string    `gorm:"column:client_id"            json:"client_id"`
+	ClientSecretEnc []byte    `gorm:"column:client_secret_enc"    json:"-"`
+	Scopes          string    `gorm:"column:scopes"               json:"scopes"`
+	EmailClaim      string    `gorm:"column:email_claim"          json:"email_claim"`
+	ButtonLabel     string    `gorm:"column:button_label"         json:"button_label"`
+	CreatedAt       time.Time `gorm:"column:created_at"           json:"created_at"`
+	UpdatedAt       time.Time `gorm:"column:updated_at"           json:"updated_at"`
+}
+
+func (OIDCSettings) TableName() string { return "oidc_settings" }

internal/models/radius.go

@@ -0,0 +1,43 @@
+package models
+
+import "time"
+
+// RADIUSSettings ist die node-lokale Singleton-Konfiguration des
+// FreeRADIUS-Servers (ob diese Node RADIUS betreibt + Listen-Adressen).
+type RADIUSSettings struct {
+	ID              int       `gorm:"column:id;primaryKey"      json:"id"`
+	Enabled         bool      `gorm:"column:enabled"           json:"enabled"`
+	ListenAddresses string    `gorm:"column:listen_addresses"  json:"listen_addresses"`
+	CreatedAt       time.Time `gorm:"column:created_at"        json:"created_at"`
+	UpdatedAt       time.Time `gorm:"column:updated_at"        json:"updated_at"`
+}
+
+func (RADIUSSettings) TableName() string { return "radius_settings" }
+
+// RADIUSClient ist ein NAS-Client (IP/CIDR + Shared Secret). SecretEnc
+// wird via secrets.Box verschlüsselt und nie serialisiert.
+type RADIUSClient struct {
+	ID          int64     `gorm:"column:id;primaryKey"  json:"id"`
+	Name        string    `gorm:"column:name"          json:"name"`
+	IPAddr      string    `gorm:"column:ipaddr"        json:"ipaddr"`
+	SecretEnc   []byte    `gorm:"column:secret_enc"    json:"-"`
+	Active      bool      `gorm:"column:active"        json:"active"`
+	Description string    `gorm:"column:description"   json:"description"`
+	CreatedAt   time.Time `gorm:"column:created_at"    json:"created_at"`
+	UpdatedAt   time.Time `gorm:"column:updated_at"    json:"updated_at"`
+}
+
+func (RADIUSClient) TableName() string { return "radius_clients" }
+
+// RADIUSUser ist ein PAP/CHAP-Benutzer. PasswordEnc wird via secrets.Box
+// verschlüsselt und nie serialisiert.
+type RADIUSUser struct {
+	ID          int64     `gorm:"column:id;primaryKey"   json:"id"`
+	Username    string    `gorm:"column:username"       json:"username"`
+	PasswordEnc []byte    `gorm:"column:password_enc"   json:"-"`
+	Active      bool      `gorm:"column:active"         json:"active"`
+	CreatedAt   time.Time `gorm:"column:created_at"     json:"created_at"`
+	UpdatedAt   time.Time `gorm:"column:updated_at"     json:"updated_at"`
+}
+
+func (RADIUSUser) TableName() string { return "radius_users" }

internal/models/waf.go

@@ -0,0 +1,20 @@
+package models
+
+import "time"
+
+// WafConfig holds the per-domain WAF policy.
+// Default on creation: enabled=false, mode=detection, paranoia_level=1.
+type WafConfig struct {
+	ID               int64             `gorm:"primaryKey"                   json:"id"`
+	DomainID         int64             `gorm:"column:domain_id;uniqueIndex"  json:"domain_id"`
+	Enabled          bool              `gorm:"column:enabled"               json:"enabled"`
+	Mode             string            `gorm:"column:mode"                  json:"mode"`           // "detection" | "blocking"
+	ParanoiaLevel    int               `gorm:"column:paranoia_level"        json:"paranoia_level"` // 1–4
+	RuleExclusions   []string          `gorm:"column:rule_exclusions;type:text[]" json:"rule_exclusions"`
+	ExclusionNotes   map[string]string `gorm:"column:exclusion_notes;type:jsonb"  json:"exclusion_notes"` // rule_id → note
+	TrustedProxies   []string          `gorm:"column:trusted_proxies;type:text[]" json:"trusted_proxies"`
+	CustomRules      string            `gorm:"column:custom_rules"          json:"custom_rules"`
+	UpdatedAt        time.Time         `gorm:"column:updated_at"            json:"updated_at"`
+}
+
+func (WafConfig) TableName() string { return "waf_configs" }

internal/services/clusterjoin/join.go

@@ -128,7 +128,7 @@ func Join(req Request) error {
 	// synchronous on the primary side.
 	var autoRegErr error
 	for i := 0; i < 3; i++ {
-		if err := autoRegister(primary, tlsDir, req.CommonName, req.Version, req.NodeID); err == nil {
+		if err := autoRegister(primary, tlsDir, req.CommonName, req.Version, req.NodeID, ""); err == nil {
 			autoRegErr = nil
 			break
 		} else {
@@ -217,7 +217,18 @@ func issueCert(primary, token, csr string, insecure bool) (caCert, peerCert stri
 	return env.Data.CACert, env.Data.PeerCert, nil
 }
 
-func autoRegister(primary, tlsDir, commonName, version, nodeID string) error {
+// PushSelfToPrimary sends this node's current identity + configHash to the
+// primary via mTLS. Exported for use by the API server's periodic push
+// goroutine so the primary's ha_nodes always reflects the secondary's actual
+// config_hash (not the stale join-time value).
+func PushSelfToPrimary(primaryURL, tlsDir, nodeID, fqdn, version, configHash string) error {
+	if tlsDir == "" {
+		tlsDir = clustertls.DefaultDir
+	}
+	return autoRegister(primaryURL, tlsDir, fqdn, version, nodeID, configHash)
+}
+
+func autoRegister(primary, tlsDir, commonName, version, nodeID, configHash string) error {
 	u, err := url.Parse(primary)
 	if err != nil {
 		return err
@@ -231,11 +242,12 @@ func autoRegister(primary, tlsDir, commonName, version, nodeID string) error {
 	}
 	hostname, _ := os.Hostname()
 	body, _ := json.Marshal(map[string]string{
-		"id":      nodeID,
-		"name":    hostname,
-		"fqdn":    commonName,
-		"api_url": "https://" + commonName + ":3443",
-		"version": version,
+		"id":          nodeID,
+		"name":        hostname,
+		"fqdn":        commonName,
+		"api_url":     "https://" + commonName + ":3443",
+		"version":     version,
+		"config_hash": configHash,
 	})
 
 	pair, err := tls.LoadX509KeyPair(tlsDir+"/peer.crt", tlsDir+"/peer.key")

internal/services/configorch/configorch.go

@@ -44,6 +44,7 @@ func Run(ctx context.Context, gens []configgen.Generator, only []string) ([]Resu
 		whitelist[n] = true
 	}
 	out := make([]Result, 0, len(gens))
+	var errs []error
 	for _, g := range gens {
 		if len(whitelist) > 0 && !whitelist[g.Name()] {
 			out = append(out, Result{Name: g.Name(), Skipped: true})
@@ -52,11 +53,14 @@ func Run(ctx context.Context, gens []configgen.Generator, only []string) ([]Resu
 		err := g.Render(ctx)
 		out = append(out, Result{Name: g.Name(), Err: err})
 		if err != nil && !errors.Is(err, configgen.ErrNotImplemented) {
-			// hard failure — surface it but return what's done so far
-			return out, fmt.Errorf("%s: %w", g.Name(), err)
+			// Weitermachen: die Generatoren sind unabhängig und reloaden
+			// inline (nft/Service-Reload sind atomar). Abbrechen würde die
+			// restlichen Dienste auf altem Stand lassen → halb angewandt.
+			// Stattdessen alle versuchen und Fehler gesammelt zurückgeben.
+			errs = append(errs, fmt.Errorf("%s: %w", g.Name(), err))
 		}
 	}
-	return out, nil
+	return out, errors.Join(errs...)
 }
 
 // Summarise turns the result slice into a human-readable multiline

internal/services/dhcp/dhcp.go

@@ -0,0 +1,238 @@
+// Package dhcp provides CRUD against the dhcp_settings (singleton),
+// dhcp_subnets, and dhcp_reservations tables. The Kea config renderer
+// in internal/kea consumes these.
+package dhcp
+
+import (
+	"context"
+	"errors"
+
+	"github.com/jackc/pgx/v5"
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+var (
+	ErrSubnetNotFound      = errors.New("dhcp subnet not found")
+	ErrReservationNotFound = errors.New("dhcp reservation not found")
+)
+
+type Repo struct {
+	Pool *pgxpool.Pool
+}
+
+func New(pool *pgxpool.Pool) *Repo { return &Repo{Pool: pool} }
+
+// ── Settings (singleton id=1) ────────────────────────────────────────
+
+func (r *Repo) GetSettings(ctx context.Context) (*models.DHCPSettings, error) {
+	var s models.DHCPSettings
+	if err := r.Pool.QueryRow(ctx, `
+SELECT id, enabled, default_lease, max_lease, domain_name, dns_servers, created_at, updated_at
+FROM dhcp_settings WHERE id=1`).Scan(
+		&s.ID, &s.Enabled, &s.DefaultLease, &s.MaxLease, &s.DomainName, &s.DNSServers,
+		&s.CreatedAt, &s.UpdatedAt,
+	); err != nil {
+		return nil, err
+	}
+	return &s, nil
+}
+
+func (r *Repo) UpdateSettings(ctx context.Context, s models.DHCPSettings) (*models.DHCPSettings, error) {
+	row := r.Pool.QueryRow(ctx, `
+UPDATE dhcp_settings
+   SET enabled=$1, default_lease=$2, max_lease=$3, domain_name=$4, dns_servers=$5, updated_at=NOW()
+ WHERE id=1
+RETURNING id, enabled, default_lease, max_lease, domain_name, dns_servers, created_at, updated_at`,
+		s.Enabled, s.DefaultLease, s.MaxLease, s.DomainName, s.DNSServers)
+	var out models.DHCPSettings
+	if err := row.Scan(&out.ID, &out.Enabled, &out.DefaultLease, &out.MaxLease,
+		&out.DomainName, &out.DNSServers, &out.CreatedAt, &out.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &out, nil
+}
+
+// ── Subnets ──────────────────────────────────────────────────────────
+
+const subnetCols = `id, name, interface_name, subnet_cidr, pool_start, pool_end,
+       gateway, dns_servers, lease_time, active, description, created_at, updated_at`
+
+func scanSubnet(row pgx.Row) (*models.DHCPSubnet, error) {
+	var s models.DHCPSubnet
+	if err := row.Scan(&s.ID, &s.Name, &s.InterfaceName, &s.SubnetCIDR, &s.PoolStart,
+		&s.PoolEnd, &s.Gateway, &s.DNSServers, &s.LeaseTime, &s.Active, &s.Description,
+		&s.CreatedAt, &s.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &s, nil
+}
+
+func (r *Repo) ListSubnets(ctx context.Context) ([]models.DHCPSubnet, error) {
+	rows, err := r.Pool.Query(ctx, `SELECT `+subnetCols+` FROM dhcp_subnets ORDER BY name ASC`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.DHCPSubnet, 0, 8)
+	for rows.Next() {
+		s, err := scanSubnet(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *s)
+	}
+	return out, rows.Err()
+}
+
+func (r *Repo) GetSubnet(ctx context.Context, id int64) (*models.DHCPSubnet, error) {
+	s, err := scanSubnet(r.Pool.QueryRow(ctx, `SELECT `+subnetCols+` FROM dhcp_subnets WHERE id=$1`, id))
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrSubnetNotFound
+		}
+		return nil, err
+	}
+	return s, nil
+}
+
+func (r *Repo) CreateSubnet(ctx context.Context, s models.DHCPSubnet) (*models.DHCPSubnet, error) {
+	return scanSubnet(r.Pool.QueryRow(ctx, `
+INSERT INTO dhcp_subnets (name, interface_name, subnet_cidr, pool_start, pool_end,
+       gateway, dns_servers, lease_time, active, description)
+VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9,$10)
+RETURNING `+subnetCols,
+		s.Name, s.InterfaceName, s.SubnetCIDR, s.PoolStart, s.PoolEnd,
+		s.Gateway, s.DNSServers, s.LeaseTime, s.Active, s.Description))
+}
+
+func (r *Repo) UpdateSubnet(ctx context.Context, id int64, s models.DHCPSubnet) (*models.DHCPSubnet, error) {
+	out, err := scanSubnet(r.Pool.QueryRow(ctx, `
+UPDATE dhcp_subnets
+   SET name=$1, interface_name=$2, subnet_cidr=$3, pool_start=$4, pool_end=$5,
+       gateway=$6, dns_servers=$7, lease_time=$8, active=$9, description=$10, updated_at=NOW()
+ WHERE id=$11
+RETURNING `+subnetCols,
+		s.Name, s.InterfaceName, s.SubnetCIDR, s.PoolStart, s.PoolEnd,
+		s.Gateway, s.DNSServers, s.LeaseTime, s.Active, s.Description, id))
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrSubnetNotFound
+		}
+		return nil, err
+	}
+	return out, nil
+}
+
+func (r *Repo) DeleteSubnet(ctx context.Context, id int64) error {
+	tag, err := r.Pool.Exec(ctx, `DELETE FROM dhcp_subnets WHERE id=$1`, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrSubnetNotFound
+	}
+	return nil
+}
+
+// ── Reservations ─────────────────────────────────────────────────────
+
+const resvCols = `id, subnet_id, name, mac_address, ip_address, hostname, active, created_at, updated_at`
+
+func scanResv(row pgx.Row) (*models.DHCPReservation, error) {
+	var r models.DHCPReservation
+	if err := row.Scan(&r.ID, &r.SubnetID, &r.Name, &r.MACAddress, &r.IPAddress,
+		&r.Hostname, &r.Active, &r.CreatedAt, &r.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &r, nil
+}
+
+func (r *Repo) ListAllReservations(ctx context.Context) ([]models.DHCPReservation, error) {
+	rows, err := r.Pool.Query(ctx, `SELECT `+resvCols+` FROM dhcp_reservations ORDER BY subnet_id, ip_address`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.DHCPReservation, 0, 16)
+	for rows.Next() {
+		v, err := scanResv(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *v)
+	}
+	return out, rows.Err()
+}
+
+func (r *Repo) ListReservationsForSubnet(ctx context.Context, subnetID int64) ([]models.DHCPReservation, error) {
+	rows, err := r.Pool.Query(ctx, `SELECT `+resvCols+` FROM dhcp_reservations WHERE subnet_id=$1 ORDER BY ip_address`, subnetID)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.DHCPReservation, 0, 8)
+	for rows.Next() {
+		v, err := scanResv(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *v)
+	}
+	return out, rows.Err()
+}
+
+func (r *Repo) GetReservation(ctx context.Context, id int64) (*models.DHCPReservation, error) {
+	v, err := scanResv(r.Pool.QueryRow(ctx, `SELECT `+resvCols+` FROM dhcp_reservations WHERE id=$1`, id))
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrReservationNotFound
+		}
+		return nil, err
+	}
+	return v, nil
+}
+
+func (r *Repo) CreateReservation(ctx context.Context, v models.DHCPReservation) (*models.DHCPReservation, error) {
+	return scanResv(r.Pool.QueryRow(ctx, `
+INSERT INTO dhcp_reservations (subnet_id, name, mac_address, ip_address, hostname, active)
+VALUES ($1,$2,$3,$4,$5,$6)
+RETURNING `+resvCols,
+		v.SubnetID, v.Name, v.MACAddress, v.IPAddress, v.Hostname, v.Active))
+}
+
+func (r *Repo) UpdateReservation(ctx context.Context, id int64, v models.DHCPReservation) (*models.DHCPReservation, error) {
+	out, err := scanResv(r.Pool.QueryRow(ctx, `
+UPDATE dhcp_reservations
+   SET name=$1, mac_address=$2, ip_address=$3, hostname=$4, active=$5, updated_at=NOW()
+ WHERE id=$6
+RETURNING `+resvCols,
+		v.Name, v.MACAddress, v.IPAddress, v.Hostname, v.Active, id))
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrReservationNotFound
+		}
+		return nil, err
+	}
+	return out, nil
+}
+
+func (r *Repo) DeleteReservation(ctx context.Context, id int64) error {
+	tag, err := r.Pool.Exec(ctx, `DELETE FROM dhcp_reservations WHERE id=$1`, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrReservationNotFound
+	}
+	return nil
+}
+
+// InterfaceExists prüft, ob ein Interface-Name in network_interfaces existiert
+// (für die Validierung beim Anlegen/Ändern von Subnets).
+func (r *Repo) InterfaceExists(ctx context.Context, name string) (bool, error) {
+	var exists bool
+	err := r.Pool.QueryRow(ctx, `SELECT EXISTS(SELECT 1 FROM network_interfaces WHERE name=$1)`, name).Scan(&exists)
+	return exists, err
+}

internal/services/dns/dns.go

@@ -204,12 +204,16 @@ func (r *Repo) DeleteRecord(ctx context.Context, id int64) error {
 func (r *Repo) GetSettings(ctx context.Context) (*models.DNSSettings, error) {
 	row := r.Pool.QueryRow(ctx, `
 SELECT id, listen_addresses, listen_port, upstream_forwards, access_acl,
-       dnssec, qname_minimisation, cache_min_ttl, cache_max_ttl, updated_at
+       dnssec, qname_minimisation, cache_min_ttl, cache_max_ttl,
+       prefetch, serve_expired, msg_cache_size_mb, rrset_cache_size_mb,
+       updated_at
 FROM dns_settings WHERE id=1`)
 	var s models.DNSSettings
 	if err := row.Scan(&s.ID, &s.ListenAddresses, &s.ListenPort, &s.UpstreamForwards,
 		&s.AccessACL, &s.DNSSEC, &s.QNameMinimisation,
-		&s.CacheMinTTL, &s.CacheMaxTTL, &s.UpdatedAt); err != nil {
+		&s.CacheMinTTL, &s.CacheMaxTTL,
+		&s.Prefetch, &s.ServeExpired, &s.MsgCacheSizeMB, &s.RRSetCacheSizeMB,
+		&s.UpdatedAt); err != nil {
 		return nil, err
 	}
 	return &s, nil
@@ -220,16 +224,22 @@ func (r *Repo) UpdateSettings(ctx context.Context, s models.DNSSettings) (*model
 UPDATE dns_settings SET
    listen_addresses=$1, listen_port=$2, upstream_forwards=$3, access_acl=$4,
    dnssec=$5, qname_minimisation=$6, cache_min_ttl=$7, cache_max_ttl=$8,
+   prefetch=$9, serve_expired=$10, msg_cache_size_mb=$11, rrset_cache_size_mb=$12,
    updated_at=NOW()
 WHERE id=1
 RETURNING id, listen_addresses, listen_port, upstream_forwards, access_acl,
-          dnssec, qname_minimisation, cache_min_ttl, cache_max_ttl, updated_at`,
+          dnssec, qname_minimisation, cache_min_ttl, cache_max_ttl,
+          prefetch, serve_expired, msg_cache_size_mb, rrset_cache_size_mb,
+          updated_at`,
 		s.ListenAddresses, s.ListenPort, s.UpstreamForwards, s.AccessACL,
-		s.DNSSEC, s.QNameMinimisation, s.CacheMinTTL, s.CacheMaxTTL)
+		s.DNSSEC, s.QNameMinimisation, s.CacheMinTTL, s.CacheMaxTTL,
+		s.Prefetch, s.ServeExpired, s.MsgCacheSizeMB, s.RRSetCacheSizeMB)
 	var out models.DNSSettings
 	if err := row.Scan(&out.ID, &out.ListenAddresses, &out.ListenPort, &out.UpstreamForwards,
 		&out.AccessACL, &out.DNSSEC, &out.QNameMinimisation,
-		&out.CacheMinTTL, &out.CacheMaxTTL, &out.UpdatedAt); err != nil {
+		&out.CacheMinTTL, &out.CacheMaxTTL,
+		&out.Prefetch, &out.ServeExpired, &out.MsgCacheSizeMB, &out.RRSetCacheSizeMB,
+		&out.UpdatedAt); err != nil {
 		return nil, err
 	}
 	return &out, nil

internal/services/firewall/natrules.go

@@ -23,7 +23,7 @@ SELECT id, name, priority, enabled, kind,
        in_zone, out_zone, proto,
        match_src_cidr, match_dst_cidr, match_dport_start, match_dport_end,
        target_addr, target_port_start, target_port_end,
-       comment, created_at, updated_at
+       comment, note, labels, created_at, updated_at
 FROM firewall_nat_rules
 `
 
@@ -57,52 +57,58 @@ func (r *NATRulesRepo) Get(ctx context.Context, id int64) (*models.FirewallNATRu
 }
 
 func (r *NATRulesRepo) Create(ctx context.Context, x models.FirewallNATRule) (*models.FirewallNATRule, error) {
+	if x.Labels == nil {
+		x.Labels = []string{}
+	}
 	row := r.Pool.QueryRow(ctx, `
 INSERT INTO firewall_nat_rules (
     name, priority, enabled, kind,
     in_zone, out_zone, proto,
     match_src_cidr, match_dst_cidr, match_dport_start, match_dport_end,
     target_addr, target_port_start, target_port_end,
-    comment
+    comment, note, labels
 ) VALUES (
     $1, $2, $3, $4,
     $5, $6, $7,
     $8, $9, $10, $11,
     $12, $13, $14,
-    $15
+    $15, $16, $17
 )
 RETURNING id, name, priority, enabled, kind,
           in_zone, out_zone, proto,
           match_src_cidr, match_dst_cidr, match_dport_start, match_dport_end,
           target_addr, target_port_start, target_port_end,
-          comment, created_at, updated_at`,
+          comment, note, labels, created_at, updated_at`,
 		x.Name, x.Priority, x.Enabled, x.Kind,
 		x.InZone, x.OutZone, x.Proto,
 		x.MatchSrcCIDR, x.MatchDstCIDR, x.MatchDPortStart, x.MatchDPortEnd,
 		x.TargetAddr, x.TargetPortStart, x.TargetPortEnd,
-		x.Comment)
+		x.Comment, x.Note, x.Labels)
 	return scanNATRule(row)
 }
 
 func (r *NATRulesRepo) Update(ctx context.Context, id int64, x models.FirewallNATRule) (*models.FirewallNATRule, error) {
+	if x.Labels == nil {
+		x.Labels = []string{}
+	}
 	row := r.Pool.QueryRow(ctx, `
 UPDATE firewall_nat_rules SET
    name = $1, priority = $2, enabled = $3, kind = $4,
    in_zone = $5, out_zone = $6, proto = $7,
    match_src_cidr = $8, match_dst_cidr = $9, match_dport_start = $10, match_dport_end = $11,
    target_addr = $12, target_port_start = $13, target_port_end = $14,
-   comment = $15, updated_at = NOW()
-WHERE id = $16
+   comment = $15, note = $16, labels = $17, updated_at = NOW()
+WHERE id = $18
 RETURNING id, name, priority, enabled, kind,
           in_zone, out_zone, proto,
           match_src_cidr, match_dst_cidr, match_dport_start, match_dport_end,
           target_addr, target_port_start, target_port_end,
-          comment, created_at, updated_at`,
+          comment, note, labels, created_at, updated_at`,
 		x.Name, x.Priority, x.Enabled, x.Kind,
 		x.InZone, x.OutZone, x.Proto,
 		x.MatchSrcCIDR, x.MatchDstCIDR, x.MatchDPortStart, x.MatchDPortEnd,
 		x.TargetAddr, x.TargetPortStart, x.TargetPortEnd,
-		x.Comment, id)
+		x.Comment, x.Note, x.Labels, id)
 	out, err := scanNATRule(row)
 	if err != nil {
 		if errors.Is(err, pgx.ErrNoRows) {
@@ -124,6 +130,37 @@ func (r *NATRulesRepo) Delete(ctx context.Context, id int64) error {
 	return nil
 }
 
+// PatchNote updates only the note field of a NAT rule.
+func (r *NATRulesRepo) PatchNote(ctx context.Context, id int64, note string) error {
+	var n *string
+	if note != "" {
+		n = &note
+	}
+	tag, err := r.Pool.Exec(ctx, `UPDATE firewall_nat_rules SET note = $1, updated_at = NOW() WHERE id = $2`, n, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrNATRuleNotFound
+	}
+	return nil
+}
+
+// PatchLabels replaces the labels array of a NAT rule.
+func (r *NATRulesRepo) PatchLabels(ctx context.Context, id int64, labels []string) error {
+	if labels == nil {
+		labels = []string{}
+	}
+	tag, err := r.Pool.Exec(ctx, `UPDATE firewall_nat_rules SET labels = $1, updated_at = NOW() WHERE id = $2`, labels, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrNATRuleNotFound
+	}
+	return nil
+}
+
 func scanNATRule(row interface{ Scan(...any) error }) (*models.FirewallNATRule, error) {
 	var x models.FirewallNATRule
 	if err := row.Scan(
@@ -131,9 +168,12 @@ func scanNATRule(row interface{ Scan(...any) error }) (*models.FirewallNATRule,
 		&x.InZone, &x.OutZone, &x.Proto,
 		&x.MatchSrcCIDR, &x.MatchDstCIDR, &x.MatchDPortStart, &x.MatchDPortEnd,
 		&x.TargetAddr, &x.TargetPortStart, &x.TargetPortEnd,
-		&x.Comment, &x.CreatedAt, &x.UpdatedAt,
+		&x.Comment, &x.Note, &x.Labels, &x.CreatedAt, &x.UpdatedAt,
 	); err != nil {
 		return nil, err
 	}
+	if x.Labels == nil {
+		x.Labels = []string{}
+	}
 	return &x, nil
 }

internal/services/firewall/rules.go

@@ -23,7 +23,7 @@ SELECT id, name, priority, enabled, action,
        src_zone, src_address_object_id, src_address_group_id, src_cidr,
        dst_zone, dst_address_object_id, dst_address_group_id, dst_cidr,
        service_object_id, service_group_id,
-       log, comment, created_at, updated_at
+       log, comment, note, labels, created_at, updated_at
 FROM firewall_rules
 `
 
@@ -57,52 +57,58 @@ func (r *RulesRepo) Get(ctx context.Context, id int64) (*models.FirewallRule, er
 }
 
 func (r *RulesRepo) Create(ctx context.Context, x models.FirewallRule) (*models.FirewallRule, error) {
+	if x.Labels == nil {
+		x.Labels = []string{}
+	}
 	row := r.Pool.QueryRow(ctx, `
 INSERT INTO firewall_rules (
     name, priority, enabled, action,
     src_zone, src_address_object_id, src_address_group_id, src_cidr,
     dst_zone, dst_address_object_id, dst_address_group_id, dst_cidr,
     service_object_id, service_group_id,
-    log, comment
+    log, comment, note, labels
 ) VALUES (
     $1, $2, $3, $4,
     $5, $6, $7, $8,
     $9, $10, $11, $12,
     $13, $14,
-    $15, $16
+    $15, $16, $17, $18
 )
 RETURNING id, name, priority, enabled, action,
           src_zone, src_address_object_id, src_address_group_id, src_cidr,
           dst_zone, dst_address_object_id, dst_address_group_id, dst_cidr,
           service_object_id, service_group_id,
-          log, comment, created_at, updated_at`,
+          log, comment, note, labels, created_at, updated_at`,
 		x.Name, x.Priority, x.Enabled, x.Action,
 		x.SrcZone, x.SrcAddressObjectID, x.SrcAddressGroupID, x.SrcCIDR,
 		x.DstZone, x.DstAddressObjectID, x.DstAddressGroupID, x.DstCIDR,
 		x.ServiceObjectID, x.ServiceGroupID,
-		x.Log, x.Comment)
+		x.Log, x.Comment, x.Note, x.Labels)
 	return scanRule(row)
 }
 
 func (r *RulesRepo) Update(ctx context.Context, id int64, x models.FirewallRule) (*models.FirewallRule, error) {
+	if x.Labels == nil {
+		x.Labels = []string{}
+	}
 	row := r.Pool.QueryRow(ctx, `
 UPDATE firewall_rules SET
    name = $1, priority = $2, enabled = $3, action = $4,
    src_zone = $5, src_address_object_id = $6, src_address_group_id = $7, src_cidr = $8,
    dst_zone = $9, dst_address_object_id = $10, dst_address_group_id = $11, dst_cidr = $12,
    service_object_id = $13, service_group_id = $14,
-   log = $15, comment = $16, updated_at = NOW()
-WHERE id = $17
+   log = $15, comment = $16, note = $17, labels = $18, updated_at = NOW()
+WHERE id = $19
 RETURNING id, name, priority, enabled, action,
           src_zone, src_address_object_id, src_address_group_id, src_cidr,
           dst_zone, dst_address_object_id, dst_address_group_id, dst_cidr,
           service_object_id, service_group_id,
-          log, comment, created_at, updated_at`,
+          log, comment, note, labels, created_at, updated_at`,
 		x.Name, x.Priority, x.Enabled, x.Action,
 		x.SrcZone, x.SrcAddressObjectID, x.SrcAddressGroupID, x.SrcCIDR,
 		x.DstZone, x.DstAddressObjectID, x.DstAddressGroupID, x.DstCIDR,
 		x.ServiceObjectID, x.ServiceGroupID,
-		x.Log, x.Comment, id)
+		x.Log, x.Comment, x.Note, x.Labels, id)
 	out, err := scanRule(row)
 	if err != nil {
 		if errors.Is(err, pgx.ErrNoRows) {
@@ -124,6 +130,37 @@ func (r *RulesRepo) Delete(ctx context.Context, id int64) error {
 	return nil
 }
 
+// PatchNote updates only the note field of a rule.
+func (r *RulesRepo) PatchNote(ctx context.Context, id int64, note string) error {
+	var n *string
+	if note != "" {
+		n = &note
+	}
+	tag, err := r.Pool.Exec(ctx, `UPDATE firewall_rules SET note = $1, updated_at = NOW() WHERE id = $2`, n, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrRuleNotFound
+	}
+	return nil
+}
+
+// PatchLabels replaces the labels array of a rule.
+func (r *RulesRepo) PatchLabels(ctx context.Context, id int64, labels []string) error {
+	if labels == nil {
+		labels = []string{}
+	}
+	tag, err := r.Pool.Exec(ctx, `UPDATE firewall_rules SET labels = $1, updated_at = NOW() WHERE id = $2`, labels, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrRuleNotFound
+	}
+	return nil
+}
+
 func scanRule(row interface{ Scan(...any) error }) (*models.FirewallRule, error) {
 	var x models.FirewallRule
 	if err := row.Scan(
@@ -131,9 +168,12 @@ func scanRule(row interface{ Scan(...any) error }) (*models.FirewallRule, error)
 		&x.SrcZone, &x.SrcAddressObjectID, &x.SrcAddressGroupID, &x.SrcCIDR,
 		&x.DstZone, &x.DstAddressObjectID, &x.DstAddressGroupID, &x.DstCIDR,
 		&x.ServiceObjectID, &x.ServiceGroupID,
-		&x.Log, &x.Comment, &x.CreatedAt, &x.UpdatedAt,
+		&x.Log, &x.Comment, &x.Note, &x.Labels, &x.CreatedAt, &x.UpdatedAt,
 	); err != nil {
 		return nil, err
 	}
+	if x.Labels == nil {
+		x.Labels = []string{}
+	}
 	return &x, nil
 }

internal/services/forwardproxy/forwardproxy.go

@@ -1,6 +1,6 @@
 // Package forwardproxy provides CRUD against the forward_proxy_acls
-// table. Renderer in internal/squid consumes the same rows to emit
-// /etc/edgeguard/squid/squid.conf.
+// table and settings in forward_proxy_settings. Renderer in internal/squid
+// consumes both tables to emit /etc/edgeguard/squid/squid.conf.
 package forwardproxy
 
 import (
@@ -97,6 +97,52 @@ func (r *Repo) Delete(ctx context.Context, id int64) error {
 	return nil
 }
 
+// Settings returns the singleton forward_proxy_settings row.
+func (r *Repo) GetSettings(ctx context.Context) (*models.ForwardProxySettings, error) {
+	var s models.ForwardProxySettings
+	if err := r.Pool.QueryRow(ctx, `
+SELECT id, listen_addresses, listen_port,
+       cache_mem_mb, cache_dir_mb, max_obj_size_mb,
+       connect_timeout, read_timeout, request_timeout,
+       created_at, updated_at
+FROM forward_proxy_settings WHERE id=1`).Scan(
+		&s.ID, &s.ListenAddresses, &s.ListenPort,
+		&s.CacheMemMB, &s.CacheDirMB, &s.MaxObjSizeMB,
+		&s.ConnectTimeout, &s.ReadTimeout, &s.RequestTimeout,
+		&s.CreatedAt, &s.UpdatedAt,
+	); err != nil {
+		return nil, err
+	}
+	return &s, nil
+}
+
+func (r *Repo) UpdateSettings(ctx context.Context, s models.ForwardProxySettings) (*models.ForwardProxySettings, error) {
+	var out models.ForwardProxySettings
+	if err := r.Pool.QueryRow(ctx, `
+UPDATE forward_proxy_settings SET
+   listen_addresses=$1, listen_port=$2,
+   cache_mem_mb=$3, cache_dir_mb=$4, max_obj_size_mb=$5,
+   connect_timeout=$6, read_timeout=$7, request_timeout=$8,
+   updated_at=NOW()
+WHERE id=1
+RETURNING id, listen_addresses, listen_port,
+          cache_mem_mb, cache_dir_mb, max_obj_size_mb,
+          connect_timeout, read_timeout, request_timeout,
+          created_at, updated_at`,
+		s.ListenAddresses, s.ListenPort,
+		s.CacheMemMB, s.CacheDirMB, s.MaxObjSizeMB,
+		s.ConnectTimeout, s.ReadTimeout, s.RequestTimeout,
+	).Scan(
+		&out.ID, &out.ListenAddresses, &out.ListenPort,
+		&out.CacheMemMB, &out.CacheDirMB, &out.MaxObjSizeMB,
+		&out.ConnectTimeout, &out.ReadTimeout, &out.RequestTimeout,
+		&out.CreatedAt, &out.UpdatedAt,
+	); err != nil {
+		return nil, err
+	}
+	return &out, nil
+}
+
 func scan(row interface{ Scan(...any) error }) (*models.ForwardProxyACL, error) {
 	var a models.ForwardProxyACL
 	if err := row.Scan(

internal/services/ipaddresses/apply.go

@@ -0,0 +1,105 @@
+package ipaddresses
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"os/exec"
+	"strings"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
+)
+
+// ConfPath wird von edgeguard-apply-ipaddresses gelesen.
+const ConfPath = "/etc/edgeguard/ip-addresses.conf"
+
+type Generator struct {
+	Repo *Repo
+}
+
+func NewGenerator(repo *Repo) *Generator { return &Generator{Repo: repo} }
+
+// Render schreibt /etc/edgeguard/ip-addresses.conf (Format: dev|addr/prefix)
+// und triggert das apply-Skript via sudo.
+func (g *Generator) Render(ctx context.Context) error {
+	return g.render(ctx, false)
+}
+
+// RenderSecondary wie Render, aber schließt Ethernet-Interface-IPs aus.
+// Auf einem Secondary-Node werden eth0-IPs (Public-IP + VIP) von
+// cloud-init bzw. Keepalived verwaltet — edgeguard soll sie nicht
+// überschreiben oder entfernen.
+func (g *Generator) RenderSecondary(ctx context.Context) error {
+	return g.render(ctx, true)
+}
+
+func (g *Generator) render(ctx context.Context, excludeEthernet bool) error {
+	type addrRow struct {
+		dev    string
+		addr   string
+		prefix int
+	}
+
+	q := `
+		SELECT ni.name, ia.address, ia.prefix
+		FROM ip_addresses ia
+		JOIN network_interfaces ni ON ni.id = ia.interface_id
+		WHERE ia.active = true`
+	if excludeEthernet {
+		q += `
+		  AND ni.type != 'ethernet'`
+	}
+	q += `
+		ORDER BY ni.name, ia.address`
+
+	rows, err := g.Repo.Pool.Query(ctx, q)
+	if err != nil {
+		return fmt.Errorf("query: %w", err)
+	}
+	defer rows.Close()
+
+	var entries []addrRow
+	for rows.Next() {
+		var r addrRow
+		if err := rows.Scan(&r.dev, &r.addr, &r.prefix); err != nil {
+			return fmt.Errorf("scan: %w", err)
+		}
+		entries = append(entries, r)
+	}
+	if err := rows.Err(); err != nil {
+		return err
+	}
+
+	var buf bytes.Buffer
+	buf.WriteString("# Generated by edgeguard-api — DO NOT EDIT.\n")
+	buf.WriteString("# Read by edgeguard-apply-ipaddresses. Format: dev|address/prefix\n")
+	for _, e := range entries {
+		fmt.Fprintf(&buf, "%s|%s/%d\n",
+			sanitize(e.dev), sanitize(e.addr), e.prefix)
+	}
+
+	if err := configgen.AtomicWrite(ConfPath, buf.Bytes(), 0o644); err != nil {
+		return fmt.Errorf("write %s: %w", ConfPath, err)
+	}
+	if err := applyIPAddresses(); err != nil {
+		return fmt.Errorf("apply: %w", err)
+	}
+	return nil
+}
+
+func applyIPAddresses() error {
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemctl",
+		"restart", "edgeguard-ipaddresses.service")
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("systemctl restart edgeguard-ipaddresses.service: %s: %w",
+			strings.TrimSpace(string(out)), err)
+	}
+	return nil
+}
+
+func sanitize(s string) string {
+	s = strings.ReplaceAll(s, "|", "")
+	s = strings.ReplaceAll(s, "\n", "")
+	return strings.TrimSpace(s)
+}

internal/services/networkifs/apply.go

@@ -0,0 +1,103 @@
+package networkifs
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"os/exec"
+	"strings"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/configgen"
+)
+
+// ConfPath is read by edgeguard-apply-interfaces.
+const ConfPath = "/etc/edgeguard/interfaces.conf"
+
+type Generator struct {
+	Repo *Repo
+}
+
+func NewGenerator(repo *Repo) *Generator { return &Generator{Repo: repo} }
+
+// Render writes /etc/edgeguard/interfaces.conf (format: type|name|parent|vlan_id|mtu|members)
+// for VLAN/bridge/bond interfaces and triggers edgeguard-interfaces.service.
+// Ethernet and WireGuard interfaces are managed by the OS / wg-quick and are excluded.
+func (g *Generator) Render(ctx context.Context) error {
+	rows, err := g.Repo.Pool.Query(ctx, `
+		SELECT type, name,
+		       COALESCE(parent, ''),
+		       COALESCE(vlan_id::text, ''),
+		       COALESCE(mtu::text, ''),
+		       members
+		FROM network_interfaces
+		WHERE active = true
+		  AND type IN ('vlan', 'bridge', 'bond')
+		  AND (type = 'vlan' OR jsonb_array_length(members) > 0)
+		ORDER BY type, name`,
+	)
+	if err != nil {
+		return fmt.Errorf("query: %w", err)
+	}
+	defer rows.Close()
+
+	type ifRow struct {
+		typ     string
+		name    string
+		parent  string
+		vlanID  string
+		mtu     string
+		members []string
+	}
+
+	var entries []ifRow
+	for rows.Next() {
+		var r ifRow
+		var membersRaw []byte
+		if err := rows.Scan(&r.typ, &r.name, &r.parent, &r.vlanID, &r.mtu, &membersRaw); err != nil {
+			return fmt.Errorf("scan: %w", err)
+		}
+		if len(membersRaw) > 0 {
+			_ = json.Unmarshal(membersRaw, &r.members)
+		}
+		entries = append(entries, r)
+	}
+	if err := rows.Err(); err != nil {
+		return err
+	}
+
+	var buf bytes.Buffer
+	buf.WriteString("# Generated by edgeguard-api — DO NOT EDIT.\n")
+	buf.WriteString("# Read by edgeguard-apply-interfaces. Format: type|name|parent|vlan_id|mtu|members\n")
+	for _, e := range entries {
+		fmt.Fprintf(&buf, "%s|%s|%s|%s|%s|%s\n",
+			sanitizeIf(e.typ), sanitizeIf(e.name), sanitizeIf(e.parent),
+			sanitizeIf(e.vlanID), sanitizeIf(e.mtu),
+			sanitizeIf(strings.Join(e.members, ",")))
+	}
+
+	if err := configgen.AtomicWrite(ConfPath, buf.Bytes(), 0o644); err != nil {
+		return fmt.Errorf("write %s: %w", ConfPath, err)
+	}
+	if err := applyInterfaces(); err != nil {
+		return fmt.Errorf("apply: %w", err)
+	}
+	return nil
+}
+
+func applyInterfaces() error {
+	cmd := exec.Command("sudo", "-n", "/usr/bin/systemctl",
+		"restart", "edgeguard-interfaces.service")
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("systemctl restart edgeguard-interfaces.service: %s: %w",
+			strings.TrimSpace(string(out)), err)
+	}
+	return nil
+}
+
+func sanitizeIf(s string) string {
+	s = strings.ReplaceAll(s, "|", "")
+	s = strings.ReplaceAll(s, "\n", "")
+	return strings.TrimSpace(s)
+}

internal/services/oidc/client.go

@@ -0,0 +1,181 @@
+package oidc
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"errors"
+	"fmt"
+	"strings"
+	"sync"
+
+	gooidc "github.com/coreos/go-oidc/v3/oidc"
+	"golang.org/x/oauth2"
+)
+
+// Claims sind die aus dem ID-Token extrahierten Felder, die der Login-
+// Flow braucht. Bewusst minimal — Rolle kommt NIE aus dem Token.
+type Claims struct {
+	Subject       string
+	Email         string
+	EmailVerified bool
+	Nonce         string
+}
+
+// Authenticator ist der testbare Seam: Aufbau der Auth-URL und der
+// Code-Exchange inkl. ID-Token-Verifikation + Claim-Extraktion. Der
+// Handler hängt nur hieran, sodass Tests einen Fake injizieren können.
+type Authenticator interface {
+	// AuthCodeURL baut die Redirect-URL zum IdP (state + nonce + PKCE-Challenge).
+	AuthCodeURL(ctx context.Context, redirectURI, state, nonce, pkceVerifier string) (string, error)
+	// Exchange tauscht den Code (PKCE), verifiziert das ID-Token und gibt
+	// die Claims zurück. Prüft Issuer/Audience/Signatur/Expiry.
+	Exchange(ctx context.Context, redirectURI, code, pkceVerifier string) (*Claims, error)
+}
+
+// Client implementiert Authenticator gegen einen echten OIDC-Provider.
+// Provider+Verifier werden lazy aufgebaut und gecached; bei geänderten
+// Settings (Fingerprint) neu aufgebaut.
+type Client struct {
+	repo *Repo
+
+	mu       sync.Mutex
+	cacheKey string
+	provider *gooidc.Provider
+	verifier *gooidc.IDTokenVerifier
+}
+
+func NewClient(repo *Repo) *Client { return &Client{repo: repo} }
+
+// loaded baut (oder reused) Provider+Verifier aus den aktuellen Settings.
+// Cache-Key = Fingerprint(issuer, client_id, scopes); Rebuild bei Änderung.
+func (c *Client) loaded(ctx context.Context) (*gooidc.Provider, *gooidc.IDTokenVerifier, error) {
+	s, err := c.repo.Get(ctx)
+	if err != nil {
+		return nil, nil, err
+	}
+	if !s.Enabled {
+		return nil, nil, ErrDisabled
+	}
+	if strings.TrimSpace(s.IssuerURL) == "" || strings.TrimSpace(s.ClientID) == "" {
+		return nil, nil, fmt.Errorf("oidc: issuer_url and client_id required")
+	}
+	key := fingerprint(s.IssuerURL, s.ClientID, s.Scopes)
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	if c.provider == nil || c.cacheKey != key {
+		prov, err := gooidc.NewProvider(ctx, s.IssuerURL)
+		if err != nil {
+			return nil, nil, fmt.Errorf("oidc: discovery: %w", err)
+		}
+		c.provider = prov
+		c.verifier = prov.Verifier(&gooidc.Config{ClientID: s.ClientID})
+		c.cacheKey = key
+	}
+	return c.provider, c.verifier, nil
+}
+
+func (c *Client) oauthConfig(prov *gooidc.Provider, clientID, secret, redirectURI, scopes string) oauth2.Config {
+	return oauth2.Config{
+		ClientID:     clientID,
+		ClientSecret: secret,
+		Endpoint:     prov.Endpoint(),
+		RedirectURL:  redirectURI,
+		Scopes:       splitScopes(scopes),
+	}
+}
+
+// AuthCodeURL implementiert Authenticator.
+func (c *Client) AuthCodeURL(ctx context.Context, redirectURI, state, nonce, pkceVerifier string) (string, error) {
+	s, err := c.repo.Get(ctx)
+	if err != nil {
+		return "", err
+	}
+	prov, _, err := c.loaded(ctx)
+	if err != nil {
+		return "", err
+	}
+	secret, _ := c.repo.ClientSecret(ctx)
+	cfg := c.oauthConfig(prov, s.ClientID, secret, redirectURI, s.Scopes)
+	return cfg.AuthCodeURL(state,
+		gooidc.Nonce(nonce),
+		oauth2.S256ChallengeOption(pkceVerifier),
+	), nil
+}
+
+// Exchange implementiert Authenticator.
+func (c *Client) Exchange(ctx context.Context, redirectURI, code, pkceVerifier string) (*Claims, error) {
+	s, err := c.repo.Get(ctx)
+	if err != nil {
+		return nil, err
+	}
+	prov, verifier, err := c.loaded(ctx)
+	if err != nil {
+		return nil, err
+	}
+	secret, _ := c.repo.ClientSecret(ctx)
+	cfg := c.oauthConfig(prov, s.ClientID, secret, redirectURI, s.Scopes)
+
+	tok, err := cfg.Exchange(ctx, code, oauth2.VerifierOption(pkceVerifier))
+	if err != nil {
+		return nil, fmt.Errorf("oidc: code exchange: %w", err)
+	}
+	rawID, ok := tok.Extra("id_token").(string)
+	if !ok || rawID == "" {
+		return nil, errors.New("oidc: no id_token in response")
+	}
+	idToken, err := verifier.Verify(ctx, rawID)
+	if err != nil {
+		return nil, fmt.Errorf("oidc: id_token verify: %w", err)
+	}
+	return extractClaims(idToken, s.EmailClaim)
+}
+
+// extractClaims liest E-Mail (via konfigurierbarem Claim), email_verified,
+// sub und nonce aus dem verifizierten ID-Token.
+func extractClaims(idToken *gooidc.IDToken, emailClaim string) (*Claims, error) {
+	var raw map[string]any
+	if err := idToken.Claims(&raw); err != nil {
+		return nil, fmt.Errorf("oidc: decode claims: %w", err)
+	}
+	if emailClaim == "" {
+		emailClaim = "email"
+	}
+	out := &Claims{Subject: idToken.Subject}
+	if v, ok := raw[emailClaim].(string); ok {
+		out.Email = strings.TrimSpace(strings.ToLower(v))
+	}
+	// email_verified kann bool oder "true"/"false" sein.
+	switch ev := raw["email_verified"].(type) {
+	case bool:
+		out.EmailVerified = ev
+	case string:
+		out.EmailVerified = ev == "true"
+	}
+	if n, ok := raw["nonce"].(string); ok {
+		out.Nonce = n
+	}
+	return out, nil
+}
+
+func splitScopes(s string) []string {
+	out := []string{}
+	for _, p := range strings.Fields(s) {
+		if p != "" {
+			out = append(out, p)
+		}
+	}
+	if len(out) == 0 {
+		out = []string{gooidc.ScopeOpenID, "email", "profile"}
+	}
+	return out
+}
+
+func fingerprint(parts ...string) string {
+	h := sha256.New()
+	for _, p := range parts {
+		h.Write([]byte(p))
+		h.Write([]byte{0})
+	}
+	return hex.EncodeToString(h.Sum(nil))
+}

internal/services/oidc/settings.go

@@ -0,0 +1,111 @@
+// Package oidc kapselt die OIDC/Keycloak-SSO-Konfiguration (Singleton-
+// Settings + verschlüsseltes Client-Secret) und einen lazy aufgebauten
+// OIDC-Provider/Verifier. Login-Flow-State ist stateless (signiertes
+// Cookie im Handler), daher hält dieses Paket keinen Request-State.
+package oidc
+
+import (
+	"context"
+	"errors"
+
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/secrets"
+)
+
+// ErrDisabled signalisiert, dass OIDC nicht aktiviert/konfiguriert ist.
+var ErrDisabled = errors.New("oidc: not enabled")
+
+// Repo liest/schreibt die oidc_settings-Singleton-Row und ver-/entschlüsselt
+// das Client-Secret via secrets.Box.
+type Repo struct {
+	pool *pgxpool.Pool
+	box  *secrets.Box
+}
+
+func New(pool *pgxpool.Pool, box *secrets.Box) *Repo {
+	return &Repo{pool: pool, box: box}
+}
+
+// Get liefert die Settings (client_secret_enc als Bytes, NULL → nil).
+func (r *Repo) Get(ctx context.Context) (*models.OIDCSettings, error) {
+	var s models.OIDCSettings
+	if err := r.pool.QueryRow(ctx, `
+SELECT id, enabled, issuer_url, client_id, client_secret_enc,
+       scopes, email_claim, button_label, created_at, updated_at
+FROM oidc_settings WHERE id = 1`).Scan(
+		&s.ID, &s.Enabled, &s.IssuerURL, &s.ClientID, &s.ClientSecretEnc,
+		&s.Scopes, &s.EmailClaim, &s.ButtonLabel, &s.CreatedAt, &s.UpdatedAt,
+	); err != nil {
+		return nil, err
+	}
+	return &s, nil
+}
+
+// ClientSecret entschlüsselt das gespeicherte Client-Secret ("" wenn keins).
+func (r *Repo) ClientSecret(ctx context.Context) (string, error) {
+	s, err := r.Get(ctx)
+	if err != nil {
+		return "", err
+	}
+	if len(s.ClientSecretEnc) == 0 {
+		return "", nil
+	}
+	pt, err := r.box.Open(s.ClientSecretEnc)
+	if err != nil {
+		return "", err
+	}
+	return string(pt), nil
+}
+
+// HasSecret meldet, ob ein Client-Secret hinterlegt ist (für die Admin-UI,
+// ohne das Secret selbst preiszugeben).
+func (r *Repo) HasSecret(ctx context.Context) (bool, error) {
+	var present bool
+	err := r.pool.QueryRow(ctx,
+		`SELECT client_secret_enc IS NOT NULL FROM oidc_settings WHERE id = 1`).Scan(&present)
+	return present, err
+}
+
+// UpdateInput beschreibt eine Settings-Änderung. ClientSecret nutzt
+// write-only-Semantik: nil = unverändert, "" = löschen, sonst neu sealen.
+type UpdateInput struct {
+	Enabled      bool
+	IssuerURL    string
+	ClientID     string
+	Scopes       string
+	EmailClaim   string
+	ButtonLabel  string
+	ClientSecret *string
+}
+
+// Update schreibt die Settings. Das Secret wird nur angefasst, wenn
+// ClientSecret != nil.
+func (r *Repo) Update(ctx context.Context, in UpdateInput) error {
+	if in.ClientSecret == nil {
+		_, err := r.pool.Exec(ctx, `
+UPDATE oidc_settings
+   SET enabled=$1, issuer_url=$2, client_id=$3, scopes=$4,
+       email_claim=$5, button_label=$6, updated_at=NOW()
+ WHERE id=1`,
+			in.Enabled, in.IssuerURL, in.ClientID, in.Scopes, in.EmailClaim, in.ButtonLabel)
+		return err
+	}
+
+	var enc []byte
+	if *in.ClientSecret != "" {
+		sealed, err := r.box.Seal([]byte(*in.ClientSecret))
+		if err != nil {
+			return err
+		}
+		enc = sealed
+	}
+	_, err := r.pool.Exec(ctx, `
+UPDATE oidc_settings
+   SET enabled=$1, issuer_url=$2, client_id=$3, scopes=$4,
+       email_claim=$5, button_label=$6, client_secret_enc=$7, updated_at=NOW()
+ WHERE id=1`,
+		in.Enabled, in.IssuerURL, in.ClientID, in.Scopes, in.EmailClaim, in.ButtonLabel, enc)
+	return err
+}

internal/services/oidc/settings_test.go

@@ -0,0 +1,90 @@
+package oidc
+
+import (
+	"context"
+	"os"
+	"testing"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/secrets"
+)
+
+// migrateRetry umgeht die goose-Erst-Apply-Race, wenn mehrere guarded
+// Test-Pakete dieselbe frische DB parallel migrieren.
+func migrateRetry(ctx context.Context, dsn string) error {
+	var err error
+	for i := 0; i < 3; i++ {
+		if err = database.Migrate(ctx, dsn); err == nil {
+			return nil
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	return err
+}
+
+// Guarded integration test: set EG_FWTEST_DSN (sonst skip).
+func testRepo(t *testing.T) *Repo {
+	t.Helper()
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the oidc settings test")
+	}
+	ctx := context.Background()
+	if err := migrateRetry(ctx, dsn); err != nil {
+		t.Fatalf("migrate: %v", err)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	t.Cleanup(pool.Close)
+	box := secrets.New(t.TempDir() + "/master_key")
+	// Settings auf einen sauberen Default zurücksetzen.
+	if _, err := pool.Exec(ctx, `UPDATE oidc_settings SET enabled=false, issuer_url='', client_id='', client_secret_enc=NULL WHERE id=1`); err != nil {
+		t.Fatalf("reset: %v", err)
+	}
+	return New(pool, box)
+}
+
+func TestSettings_SecretWriteOnly(t *testing.T) {
+	r := testRepo(t)
+	ctx := context.Background()
+	str := func(s string) *string { return &s }
+
+	// 1) Neues Secret setzen.
+	if err := r.Update(ctx, UpdateInput{Enabled: true, IssuerURL: "https://idp.example/realms/x", ClientID: "eg", ClientSecret: str("s3cr3t")}); err != nil {
+		t.Fatal(err)
+	}
+	if has, _ := r.HasSecret(ctx); !has {
+		t.Fatal("HasSecret should be true after setting a secret")
+	}
+	got, err := r.ClientSecret(ctx)
+	if err != nil || got != "s3cr3t" {
+		t.Fatalf("ClientSecret = %q, %v; want s3cr3t", got, err)
+	}
+
+	// 2) Update mit nil → Secret bleibt unverändert.
+	if err := r.Update(ctx, UpdateInput{Enabled: true, IssuerURL: "https://idp.example/realms/x", ClientID: "eg2", ClientSecret: nil}); err != nil {
+		t.Fatal(err)
+	}
+	got, _ = r.ClientSecret(ctx)
+	if got != "s3cr3t" {
+		t.Fatalf("secret should be preserved on nil update, got %q", got)
+	}
+	if s, _ := r.Get(ctx); s.ClientID != "eg2" {
+		t.Fatalf("client_id should update to eg2, got %q", s.ClientID)
+	}
+
+	// 3) Update mit "" → Secret gelöscht.
+	if err := r.Update(ctx, UpdateInput{Enabled: false, IssuerURL: "", ClientID: "", ClientSecret: str("")}); err != nil {
+		t.Fatal(err)
+	}
+	if has, _ := r.HasSecret(ctx); has {
+		t.Fatal("HasSecret should be false after clearing the secret")
+	}
+	got, _ = r.ClientSecret(ctx)
+	if got != "" {
+		t.Fatalf("secret should be empty after clear, got %q", got)
+	}
+}

internal/services/radius/radius.go

@@ -0,0 +1,239 @@
+// Package radius provides CRUD against radius_settings (singleton),
+// radius_clients and radius_users. Shared secrets / user passwords are
+// sealed at rest via secrets.Box. The FreeRADIUS renderer in
+// internal/freeradius consumes these.
+package radius
+
+import (
+	"context"
+	"errors"
+
+	"github.com/jackc/pgx/v5"
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+	"git.netcell-it.de/projekte/edgeguard-native/internal/services/secrets"
+)
+
+var (
+	ErrClientNotFound = errors.New("radius client not found")
+	ErrUserNotFound   = errors.New("radius user not found")
+)
+
+type Repo struct {
+	Pool *pgxpool.Pool
+	Box  *secrets.Box
+}
+
+func New(pool *pgxpool.Pool, box *secrets.Box) *Repo { return &Repo{Pool: pool, Box: box} }
+
+// ── Settings ─────────────────────────────────────────────────────────
+
+func (r *Repo) GetSettings(ctx context.Context) (*models.RADIUSSettings, error) {
+	var s models.RADIUSSettings
+	if err := r.Pool.QueryRow(ctx, `
+SELECT id, enabled, listen_addresses, created_at, updated_at FROM radius_settings WHERE id=1`).Scan(
+		&s.ID, &s.Enabled, &s.ListenAddresses, &s.CreatedAt, &s.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &s, nil
+}
+
+func (r *Repo) UpdateSettings(ctx context.Context, s models.RADIUSSettings) (*models.RADIUSSettings, error) {
+	var out models.RADIUSSettings
+	if err := r.Pool.QueryRow(ctx, `
+UPDATE radius_settings SET enabled=$1, listen_addresses=$2, updated_at=NOW() WHERE id=1
+RETURNING id, enabled, listen_addresses, created_at, updated_at`,
+		s.Enabled, s.ListenAddresses).Scan(
+		&out.ID, &out.Enabled, &out.ListenAddresses, &out.CreatedAt, &out.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &out, nil
+}
+
+// ── Clients ──────────────────────────────────────────────────────────
+
+const clientCols = `id, name, ipaddr, secret_enc, active, description, created_at, updated_at`
+
+func scanClient(row pgx.Row) (*models.RADIUSClient, error) {
+	var c models.RADIUSClient
+	if err := row.Scan(&c.ID, &c.Name, &c.IPAddr, &c.SecretEnc, &c.Active, &c.Description,
+		&c.CreatedAt, &c.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &c, nil
+}
+
+func (r *Repo) ListClients(ctx context.Context) ([]models.RADIUSClient, error) {
+	rows, err := r.Pool.Query(ctx, `SELECT `+clientCols+` FROM radius_clients ORDER BY name`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.RADIUSClient, 0, 8)
+	for rows.Next() {
+		c, err := scanClient(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *c)
+	}
+	return out, rows.Err()
+}
+
+func (r *Repo) GetClient(ctx context.Context, id int64) (*models.RADIUSClient, error) {
+	c, err := scanClient(r.Pool.QueryRow(ctx, `SELECT `+clientCols+` FROM radius_clients WHERE id=$1`, id))
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrClientNotFound
+		}
+		return nil, err
+	}
+	return c, nil
+}
+
+func (r *Repo) CreateClient(ctx context.Context, name, ipaddr, secret string, active bool, desc string) (*models.RADIUSClient, error) {
+	enc, err := r.Box.Seal([]byte(secret))
+	if err != nil {
+		return nil, err
+	}
+	return scanClient(r.Pool.QueryRow(ctx, `
+INSERT INTO radius_clients (name, ipaddr, secret_enc, active, description)
+VALUES ($1,$2,$3,$4,$5) RETURNING `+clientCols,
+		name, ipaddr, enc, active, desc))
+}
+
+// UpdateClient: secret==nil → unverändert, ""→löschen, sonst neu sealen.
+func (r *Repo) UpdateClient(ctx context.Context, id int64, name, ipaddr string, secret *string, active bool, desc string) (*models.RADIUSClient, error) {
+	if secret == nil {
+		out, err := scanClient(r.Pool.QueryRow(ctx, `
+UPDATE radius_clients SET name=$1, ipaddr=$2, active=$3, description=$4, updated_at=NOW()
+WHERE id=$5 RETURNING `+clientCols, name, ipaddr, active, desc, id))
+		return mapClientErr(out, err)
+	}
+	var enc []byte
+	if *secret != "" {
+		sealed, err := r.Box.Seal([]byte(*secret))
+		if err != nil {
+			return nil, err
+		}
+		enc = sealed
+	}
+	out, err := scanClient(r.Pool.QueryRow(ctx, `
+UPDATE radius_clients SET name=$1, ipaddr=$2, secret_enc=$3, active=$4, description=$5, updated_at=NOW()
+WHERE id=$6 RETURNING `+clientCols, name, ipaddr, enc, active, desc, id))
+	return mapClientErr(out, err)
+}
+
+func mapClientErr(c *models.RADIUSClient, err error) (*models.RADIUSClient, error) {
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrClientNotFound
+		}
+		return nil, err
+	}
+	return c, nil
+}
+
+func (r *Repo) DeleteClient(ctx context.Context, id int64) error {
+	tag, err := r.Pool.Exec(ctx, `DELETE FROM radius_clients WHERE id=$1`, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrClientNotFound
+	}
+	return nil
+}
+
+// ── Users ────────────────────────────────────────────────────────────
+
+const userCols = `id, username, password_enc, active, created_at, updated_at`
+
+func scanUser(row pgx.Row) (*models.RADIUSUser, error) {
+	var u models.RADIUSUser
+	if err := row.Scan(&u.ID, &u.Username, &u.PasswordEnc, &u.Active, &u.CreatedAt, &u.UpdatedAt); err != nil {
+		return nil, err
+	}
+	return &u, nil
+}
+
+func (r *Repo) ListUsers(ctx context.Context) ([]models.RADIUSUser, error) {
+	rows, err := r.Pool.Query(ctx, `SELECT `+userCols+` FROM radius_users ORDER BY username`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.RADIUSUser, 0, 8)
+	for rows.Next() {
+		u, err := scanUser(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *u)
+	}
+	return out, rows.Err()
+}
+
+func (r *Repo) GetUser(ctx context.Context, id int64) (*models.RADIUSUser, error) {
+	u, err := scanUser(r.Pool.QueryRow(ctx, `SELECT `+userCols+` FROM radius_users WHERE id=$1`, id))
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrUserNotFound
+		}
+		return nil, err
+	}
+	return u, nil
+}
+
+func (r *Repo) CreateUser(ctx context.Context, username, password string, active bool) (*models.RADIUSUser, error) {
+	enc, err := r.Box.Seal([]byte(password))
+	if err != nil {
+		return nil, err
+	}
+	return scanUser(r.Pool.QueryRow(ctx, `
+INSERT INTO radius_users (username, password_enc, active) VALUES ($1,$2,$3) RETURNING `+userCols,
+		username, enc, active))
+}
+
+func (r *Repo) UpdateUser(ctx context.Context, id int64, username string, password *string, active bool) (*models.RADIUSUser, error) {
+	if password == nil {
+		u, err := scanUser(r.Pool.QueryRow(ctx, `
+UPDATE radius_users SET username=$1, active=$2, updated_at=NOW() WHERE id=$3 RETURNING `+userCols,
+			username, active, id))
+		return mapUserErr(u, err)
+	}
+	var enc []byte
+	if *password != "" {
+		sealed, err := r.Box.Seal([]byte(*password))
+		if err != nil {
+			return nil, err
+		}
+		enc = sealed
+	}
+	u, err := scanUser(r.Pool.QueryRow(ctx, `
+UPDATE radius_users SET username=$1, password_enc=$2, active=$3, updated_at=NOW() WHERE id=$4 RETURNING `+userCols,
+		username, enc, active, id))
+	return mapUserErr(u, err)
+}
+
+func mapUserErr(u *models.RADIUSUser, err error) (*models.RADIUSUser, error) {
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrUserNotFound
+		}
+		return nil, err
+	}
+	return u, nil
+}
+
+func (r *Repo) DeleteUser(ctx context.Context, id int64) error {
+	tag, err := r.Pool.Exec(ctx, `DELETE FROM radius_users WHERE id=$1`, id)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrUserNotFound
+	}
+	return nil
+}

internal/services/session/session.go

@@ -96,14 +96,15 @@ func loadOrCreateSecret(path string) ([]byte, error) {
 	return secret, nil
 }
 
-// IssueWithRole returns a signed token for the given actor + role.
-func (s *Signer) IssueWithRole(actor, role string) (string, *Token, error) {
+// issue builds + signs a token with an explicit TTL. No shared-state
+// mutation — safe for concurrent use of the shared Signer singleton.
+func (s *Signer) issue(actor, role string, ttl time.Duration) (string, *Token, error) {
 	now := s.Now()
 	t := Token{
 		Actor: actor,
 		Role:  role,
 		Iat:   now.Unix(),
-		Exp:   now.Add(s.TTL).Unix(),
+		Exp:   now.Add(ttl).Unix(),
 	}
 	data, err := json.Marshal(t)
 	if err != nil {
@@ -117,9 +118,20 @@ func (s *Signer) IssueWithRole(actor, role string) (string, *Token, error) {
 	return encoded, &t, nil
 }
 
+// IssueWithRole returns a signed token for the given actor + role.
+func (s *Signer) IssueWithRole(actor, role string) (string, *Token, error) {
+	return s.issue(actor, role, s.TTL)
+}
+
 // Issue is IssueWithRole with empty role.
 func (s *Signer) Issue(actor string) (string, *Token, error) {
-	return s.IssueWithRole(actor, "")
+	return s.issue(actor, "", s.TTL)
+}
+
+// IssueWithRoleTTL issues a token with a custom TTL — no longer mutates
+// the shared Signer (previously a data race under concurrent logins).
+func (s *Signer) IssueWithRoleTTL(actor, role string, ttl time.Duration) (string, *Token, error) {
+	return s.issue(actor, role, ttl)
 }
 
 // Verify checks a token. Returns ErrInvalidToken or ErrExpiredToken.
@@ -165,3 +177,67 @@ var (
 	ErrInvalidToken = errors.New("invalid session token")
 	ErrExpiredToken = errors.New("session token expired")
 )
+
+// blobEnvelope umhüllt eine beliebige Payload mit einem Ablaufzeitpunkt.
+type blobEnvelope struct {
+	Exp     int64  `json:"exp"`
+	Payload []byte `json:"p"`
+}
+
+// SignBlob signiert beliebige Bytes mit dem Session-Secret (HMAC-SHA256,
+// gleiches Format wie Tokens: base64url(json).base64url(sig)) und einer
+// TTL. Für stateless, cluster-sichere Kurzzeit-Cookies (z.B. der
+// OIDC-Flow-State). Das Secret ist clusterweit synchron (.jwt_fingerprint).
+func (s *Signer) SignBlob(payload []byte, ttl time.Duration) (string, error) {
+	env := blobEnvelope{
+		Exp:     s.Now().Add(ttl).Unix(),
+		Payload: payload,
+	}
+	data, err := json.Marshal(env)
+	if err != nil {
+		return "", err
+	}
+	mac := hmac.New(sha256.New, s.Secret)
+	mac.Write(data)
+	return base64.RawURLEncoding.EncodeToString(data) + "." +
+		base64.RawURLEncoding.EncodeToString(mac.Sum(nil)), nil
+}
+
+// VerifyBlob prüft Signatur + Ablauf und gibt die ursprüngliche Payload
+// zurück. ErrInvalidToken / ErrExpiredToken bei Fehlern.
+func (s *Signer) VerifyBlob(raw string) ([]byte, error) {
+	if raw == "" {
+		return nil, ErrInvalidToken
+	}
+	dot := -1
+	for i := 0; i < len(raw); i++ {
+		if raw[i] == '.' {
+			dot = i
+			break
+		}
+	}
+	if dot <= 0 || dot >= len(raw)-1 {
+		return nil, ErrInvalidToken
+	}
+	payload, err := base64.RawURLEncoding.DecodeString(raw[:dot])
+	if err != nil {
+		return nil, ErrInvalidToken
+	}
+	sig, err := base64.RawURLEncoding.DecodeString(raw[dot+1:])
+	if err != nil {
+		return nil, ErrInvalidToken
+	}
+	mac := hmac.New(sha256.New, s.Secret)
+	mac.Write(payload)
+	if subtle.ConstantTimeCompare(mac.Sum(nil), sig) != 1 {
+		return nil, ErrInvalidToken
+	}
+	var env blobEnvelope
+	if err := json.Unmarshal(payload, &env); err != nil {
+		return nil, ErrInvalidToken
+	}
+	if s.Now().Unix() >= env.Exp {
+		return nil, ErrExpiredToken
+	}
+	return env.Payload, nil
+}

internal/services/session/ttl_test.go

@@ -0,0 +1,47 @@
+package session
+
+import (
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+)
+
+// TestSigner_TTLNotShared beweist Fix #1: IssueWithRoleTTL darf das geteilte
+// s.TTL nicht mehr mutieren. Unter `go test -race` schlägt die alte Version
+// als Data-Race an; zusätzlich prüfen wir, dass parallele normale Logins nie
+// die kurze TOTP-TTL erben.
+func TestSigner_TTLNotShared(t *testing.T) {
+	s := NewSigner([]byte("0123456789abcdef0123456789abcdef"), nil, time.Hour)
+	var wg sync.WaitGroup
+	var bad int32
+	for i := 0; i < 200; i++ {
+		wg.Add(2)
+		go func() {
+			defer wg.Done()
+			_, _, _ = s.IssueWithRoleTTL("a", "totp_pending", 2*time.Minute)
+		}()
+		go func() {
+			defer wg.Done()
+			_, tok, err := s.IssueWithRole("b", "admin")
+			if err != nil {
+				atomic.AddInt32(&bad, 1)
+				return
+			}
+			// Normale Session muss ~1h gelten, nie die 2-Min-TOTP-TTL.
+			if tok.Exp-tok.Iat < int64((30 * time.Minute).Seconds()) {
+				atomic.AddInt32(&bad, 1)
+			}
+		}()
+	}
+	wg.Wait()
+	if bad > 0 {
+		t.Fatalf("%d normale Tokens bekamen eine zu kurze TTL → geteilter Zustand", bad)
+	}
+
+	// TTL-Override wirkt weiterhin korrekt für den TOTP-Token.
+	_, ptok, _ := s.IssueWithRoleTTL("x", "totp_pending", 2*time.Minute)
+	if d := ptok.Exp - ptok.Iat; d > int64((3 * time.Minute).Seconds()) {
+		t.Fatalf("totp-pending TTL = %ds, want ~120s", d)
+	}
+}

internal/services/users/users.go

@@ -12,6 +12,7 @@ import (
 
 	"github.com/jackc/pgx/v5"
 	"github.com/jackc/pgx/v5/pgxpool"
+	"github.com/pquerna/otp/totp"
 	"golang.org/x/crypto/bcrypt"
 )
 
@@ -27,22 +28,30 @@ type User struct {
 	Email       string     `json:"email"`
 	Role        string     `json:"role"`
 	Active      bool       `json:"active"`
+	TOTPEnabled bool       `json:"totp_enabled"`
 	LastLoginAt *time.Time `json:"last_login_at"`
 	CreatedAt   time.Time  `json:"created_at"`
 	UpdatedAt   time.Time  `json:"updated_at"`
 }
 
+// AuthInfo is returned by FindForAuth — contains credentials needed during login.
+type AuthInfo struct {
+	User
+	PasswordHash string
+	TOTPSecret   *string
+}
+
 type Repo struct {
 	pool *pgxpool.Pool
 }
 
 func New(pool *pgxpool.Pool) *Repo { return &Repo{pool: pool} }
 
-const selectCols = `id, email, role, active, last_login_at, created_at, updated_at`
+const selectCols = `id, email, role, active, totp_enabled, last_login_at, created_at, updated_at`
 
 func scan(row pgx.Row) (User, error) {
 	var u User
-	err := row.Scan(&u.ID, &u.Email, &u.Role, &u.Active,
+	err := row.Scan(&u.ID, &u.Email, &u.Role, &u.Active, &u.TOTPEnabled,
 		&u.LastLoginAt, &u.CreatedAt, &u.UpdatedAt)
 	return u, err
 }
@@ -71,7 +80,7 @@ func (r *Repo) FindByEmail(ctx context.Context, email string) (User, string, err
 	var hash string
 	err := r.pool.QueryRow(ctx,
 		`SELECT `+selectCols+`, password_hash FROM users WHERE lower(email)=lower($1)`,
-		email).Scan(&u.ID, &u.Email, &u.Role, &u.Active,
+		email).Scan(&u.ID, &u.Email, &u.Role, &u.Active, &u.TOTPEnabled,
 		&u.LastLoginAt, &u.CreatedAt, &u.UpdatedAt, &hash)
 	if errors.Is(err, pgx.ErrNoRows) {
 		return u, "", ErrNotFound
@@ -79,6 +88,70 @@ func (r *Repo) FindByEmail(ctx context.Context, email string) (User, string, err
 	return u, hash, err
 }
 
+// FindForAuth returns full auth credentials including TOTP secret. ErrNotFound if absent.
+func (r *Repo) FindForAuth(ctx context.Context, email string) (*AuthInfo, error) {
+	var a AuthInfo
+	err := r.pool.QueryRow(ctx,
+		`SELECT `+selectCols+`, password_hash, totp_secret FROM users WHERE lower(email)=lower($1)`,
+		email).Scan(&a.ID, &a.Email, &a.Role, &a.Active, &a.TOTPEnabled,
+		&a.LastLoginAt, &a.CreatedAt, &a.UpdatedAt, &a.PasswordHash, &a.TOTPSecret)
+	if errors.Is(err, pgx.ErrNoRows) {
+		return nil, ErrNotFound
+	}
+	return &a, err
+}
+
+// GenerateTOTPSecret creates a new TOTP secret for the given email and returns
+// the secret + the otpauth:// provisioning URI (for QR code rendering in the UI).
+// The secret is NOT saved yet — call ConfirmTOTP after the user verifies the code.
+func GenerateTOTPSecret(email string) (secret, uri string, err error) {
+	key, err := totp.Generate(totp.GenerateOpts{
+		Issuer:      "EdgeGuard",
+		AccountName: email,
+	})
+	if err != nil {
+		return "", "", err
+	}
+	return key.Secret(), key.URL(), nil
+}
+
+// ConfirmTOTP verifies the given TOTP code against the (not-yet-saved) secret
+// and, on success, persists it and enables TOTP for the user.
+func (r *Repo) ConfirmTOTP(ctx context.Context, userID int64, secret, code string) error {
+	if !totp.Validate(code, secret) {
+		return errors.New("invalid_totp_code")
+	}
+	tag, err := r.pool.Exec(ctx,
+		`UPDATE users SET totp_secret=$1, totp_enabled=true, updated_at=NOW() WHERE id=$2`,
+		secret, userID)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrNotFound
+	}
+	return nil
+}
+
+// DisableTOTP clears the TOTP secret and disables 2FA for the given user.
+func (r *Repo) DisableTOTP(ctx context.Context, userID int64) error {
+	tag, err := r.pool.Exec(ctx,
+		`UPDATE users SET totp_secret=NULL, totp_enabled=false, updated_at=NOW() WHERE id=$1`,
+		userID)
+	if err != nil {
+		return err
+	}
+	if tag.RowsAffected() == 0 {
+		return ErrNotFound
+	}
+	return nil
+}
+
+// VerifyTOTP checks a live TOTP code against the stored secret.
+func VerifyTOTP(secret, code string) bool {
+	return totp.Validate(code, secret)
+}
+
 func (r *Repo) Count(ctx context.Context) (int, error) {
 	var n int
 	err := r.pool.QueryRow(ctx, `SELECT COUNT(*) FROM users`).Scan(&n)
@@ -167,6 +240,21 @@ func (r *Repo) RecordLogin(ctx context.Context, id int64) {
 	_, _ = r.pool.Exec(ctx, `UPDATE users SET last_login_at=NOW() WHERE id=$1`, id)
 }
 
+// GetOIDCSubject liefert den gespeicherten OIDC-'sub' des Users ("" wenn
+// noch nicht verknüpft).
+func (r *Repo) GetOIDCSubject(ctx context.Context, id int64) (string, error) {
+	var sub string
+	err := r.pool.QueryRow(ctx, `SELECT COALESCE(oidc_subject, '') FROM users WHERE id=$1`, id).Scan(&sub)
+	return sub, err
+}
+
+// SetOIDCSubject speichert den OIDC-'sub' beim ersten erfolgreichen
+// SSO-Login (opportunistisches Linking).
+func (r *Repo) SetOIDCSubject(ctx context.Context, id int64, sub string) error {
+	_, err := r.pool.Exec(ctx, `UPDATE users SET oidc_subject=$1, updated_at=NOW() WHERE id=$2`, sub, id)
+	return err
+}
+
 // VerifyPassword is a constant-time bcrypt compare.
 func VerifyPassword(hash, password string) bool {
 	return bcrypt.CompareHashAndPassword([]byte(hash), []byte(password)) == nil

internal/services/waf/waf.go

@@ -0,0 +1,227 @@
+// Package waf implements CRUD for per-domain WAF policies (waf_configs).
+package waf
+
+import (
+	"context"
+	"errors"
+	"time"
+
+	"github.com/jackc/pgx/v5"
+	"github.com/jackc/pgx/v5/pgxpool"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+var ErrNotFound = errors.New("waf config not found")
+
+type Repo struct {
+	Pool *pgxpool.Pool
+}
+
+func New(pool *pgxpool.Pool) *Repo { return &Repo{Pool: pool} }
+
+const baseSelect = `
+SELECT id, domain_id, enabled, mode, paranoia_level,
+       rule_exclusions, exclusion_notes, trusted_proxies, custom_rules, updated_at
+FROM waf_configs
+`
+
+func scan(row pgx.Row) (*models.WafConfig, error) {
+	var c models.WafConfig
+	err := row.Scan(
+		&c.ID, &c.DomainID, &c.Enabled, &c.Mode, &c.ParanoiaLevel,
+		&c.RuleExclusions, &c.ExclusionNotes, &c.TrustedProxies, &c.CustomRules, &c.UpdatedAt,
+	)
+	if err != nil {
+		return nil, err
+	}
+	if c.ExclusionNotes == nil {
+		c.ExclusionNotes = map[string]string{}
+	}
+	return &c, nil
+}
+
+// List returns all WAF configs ordered by domain_id.
+func (r *Repo) List(ctx context.Context) ([]models.WafConfig, error) {
+	rows, err := r.Pool.Query(ctx, baseSelect+" ORDER BY domain_id ASC")
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.WafConfig, 0, 16)
+	for rows.Next() {
+		c, err := scan(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *c)
+	}
+	return out, rows.Err()
+}
+
+// GetByDomain returns the WAF config for a domain, or ErrNotFound.
+func (r *Repo) GetByDomain(ctx context.Context, domainID int64) (*models.WafConfig, error) {
+	row := r.Pool.QueryRow(ctx, baseSelect+" WHERE domain_id = $1", domainID)
+	c, err := scan(row)
+	if err != nil {
+		if errors.Is(err, pgx.ErrNoRows) {
+			return nil, ErrNotFound
+		}
+		return nil, err
+	}
+	return c, nil
+}
+
+// Upsert inserts or updates the WAF config for a domain.
+// Returns the resulting row.
+func (r *Repo) Upsert(ctx context.Context, c models.WafConfig) (*models.WafConfig, error) {
+	c.UpdatedAt = time.Now()
+	if c.ExclusionNotes == nil {
+		c.ExclusionNotes = map[string]string{}
+	}
+	row := r.Pool.QueryRow(ctx, `
+		INSERT INTO waf_configs
+		    (domain_id, enabled, mode, paranoia_level,
+		     rule_exclusions, exclusion_notes, trusted_proxies, custom_rules, updated_at)
+		VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9)
+		ON CONFLICT (domain_id) DO UPDATE SET
+		    enabled          = EXCLUDED.enabled,
+		    mode             = EXCLUDED.mode,
+		    paranoia_level   = EXCLUDED.paranoia_level,
+		    rule_exclusions  = EXCLUDED.rule_exclusions,
+		    exclusion_notes  = EXCLUDED.exclusion_notes,
+		    trusted_proxies  = EXCLUDED.trusted_proxies,
+		    custom_rules     = EXCLUDED.custom_rules,
+		    updated_at       = EXCLUDED.updated_at
+		RETURNING id, domain_id, enabled, mode, paranoia_level,
+		          rule_exclusions, exclusion_notes, trusted_proxies, custom_rules, updated_at
+	`,
+		c.DomainID, c.Enabled, c.Mode, c.ParanoiaLevel,
+		c.RuleExclusions, c.ExclusionNotes, c.TrustedProxies, c.CustomRules, c.UpdatedAt,
+	)
+	return scan(row)
+}
+
+// ListEnabled returns only configs with enabled=true (used by the WAF agent).
+func (r *Repo) ListEnabled(ctx context.Context) ([]models.WafConfig, error) {
+	rows, err := r.Pool.Query(ctx, baseSelect+" WHERE enabled = true ORDER BY domain_id ASC")
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]models.WafConfig, 0, 8)
+	for rows.Next() {
+		c, err := scan(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, *c)
+	}
+	return out, rows.Err()
+}
+
+// WafAlert mirrors the waf_alerts DB row.
+type WafAlert struct {
+	ID        int64      `json:"id"`
+	DomainID  *int64     `json:"domain_id,omitempty"`
+	Hostname  string     `json:"hostname"`
+	ClientIP  string     `json:"client_ip"`
+	Method    string     `json:"method"`
+	URI       string     `json:"uri"`
+	RuleID    int        `json:"rule_id"`
+	RuleMsg   string     `json:"rule_msg"`
+	Severity  string     `json:"severity"`
+	Action    string     `json:"action"`
+	CreatedAt time.Time  `json:"created_at"`
+}
+
+// ListAlerts returns recent WAF alerts, optionally filtered by domain_id.
+func (r *Repo) ListAlerts(ctx context.Context, domainID *int64, limit int) ([]WafAlert, error) {
+	if limit <= 0 || limit > 1000 {
+		limit = 200
+	}
+	var rows interface{ Next() bool; Scan(...any) error; Close(); Err() error }
+	var err error
+	if domainID != nil {
+		rows2, e := r.Pool.Query(ctx, `
+			SELECT id, domain_id, hostname, client_ip, method, uri,
+			       rule_id, rule_msg, severity, action, created_at
+			FROM waf_alerts
+			WHERE domain_id = $1
+			ORDER BY created_at DESC LIMIT $2
+		`, *domainID, limit)
+		rows, err = rows2, e
+	} else {
+		rows2, e := r.Pool.Query(ctx, `
+			SELECT id, domain_id, hostname, client_ip, method, uri,
+			       rule_id, rule_msg, severity, action, created_at
+			FROM waf_alerts
+			ORDER BY created_at DESC LIMIT $1
+		`, limit)
+		rows, err = rows2, e
+	}
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]WafAlert, 0, limit)
+	for rows.Next() {
+		var a WafAlert
+		if err := rows.Scan(
+			&a.ID, &a.DomainID, &a.Hostname, &a.ClientIP, &a.Method, &a.URI,
+			&a.RuleID, &a.RuleMsg, &a.Severity, &a.Action, &a.CreatedAt,
+		); err != nil {
+			return nil, err
+		}
+		out = append(out, a)
+	}
+	return out, rows.Err()
+}
+
+// PurgeAlerts removes alerts older than the given number of days.
+func (r *Repo) PurgeAlerts(ctx context.Context, olderThanDays int) error {
+	_, err := r.Pool.Exec(ctx,
+		`DELETE FROM waf_alerts WHERE created_at < NOW() - ($1 || ' days')::interval`,
+		olderThanDays,
+	)
+	return err
+}
+
+// DomainConfigPair combines a domain hostname with its WAF config.
+type DomainConfigPair struct {
+	Hostname string
+	Config   models.WafConfig
+}
+
+// ListAllWithDomain returns all WAF configs joined with their domain name.
+// Used by the WAF agent to build the hostname→engine mapping.
+func (r *Repo) ListAllWithDomain(ctx context.Context) ([]DomainConfigPair, error) {
+	rows, err := r.Pool.Query(ctx, `
+		SELECT d.name,
+		       w.id, w.domain_id, w.enabled, w.mode, w.paranoia_level,
+		       w.rule_exclusions, w.trusted_proxies, w.custom_rules, w.updated_at
+		FROM waf_configs w
+		JOIN domains d ON d.id = w.domain_id
+		WHERE d.active = true
+		ORDER BY d.name ASC
+	`)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	out := make([]DomainConfigPair, 0, 16)
+	for rows.Next() {
+		var p DomainConfigPair
+		var c models.WafConfig
+		if err := rows.Scan(
+			&p.Hostname,
+			&c.ID, &c.DomainID, &c.Enabled, &c.Mode, &c.ParanoiaLevel,
+			&c.RuleExclusions, &c.TrustedProxies, &c.CustomRules, &c.UpdatedAt,
+		); err != nil {
+			return nil, err
+		}
+		p.Config = c
+		out = append(out, p)
+	}
+	return out, rows.Err()
+}

internal/squid/squid.cfg.tpl

@@ -2,12 +2,14 @@
 # Source: internal/squid/squid.go (template: squid.cfg.tpl).
 # Re-generate via `edgeguard-ctl render-config --only=squid`.
 
-http_port {{.ListenPort}}
+{{range .ListenAddrs -}}
+{{if .Addr}}http_port {{.Addr}}:{{.Port}}
+{{else}}http_port {{.Port}}
+{{end}}{{- end}}
 
-# Standard cache directory + small in-memory cache. Forward proxy
-# isn't a CDN — we keep cache modest to avoid disk pressure.
-cache_dir ufs /var/spool/squid 100 16 256
-cache_mem 64 MB
+cache_dir ufs /var/spool/squid {{.CacheDirMB}} 16 256
+cache_mem {{.CacheMemMB}} MB
+maximum_object_size {{.MaxObjSizeMB}} MB
 
 # Logging — combined access log, rotated by logrotate.
 access_log /var/log/squid/access.log squid
@@ -56,7 +58,9 @@ http_access allow localhost
 http_access allow localnet
 http_access deny all
 
-# Hostnames + visible name — operator can override via squid.conf
-# drop-in if needed.
+connect_timeout {{.ConnectTimeout}} seconds
+read_timeout {{.ReadTimeout}} seconds
+request_timeout {{.RequestTimeout}} seconds
+
 visible_hostname edgeguard-proxy
 forwarded_for on

internal/squid/squid.go

@@ -11,6 +11,7 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"strings"
 	"text/template"
 
 	"github.com/jackc/pgx/v5/pgxpool"
@@ -21,8 +22,8 @@ import (
 )
 
 const (
-	confPath   = "/etc/edgeguard/squid/squid.conf"
-	listenPort = 3128
+	confPath          = "/etc/edgeguard/squid/squid.conf"
+	defaultListenPort = 3128
 )
 
 //go:embed squid.cfg.tpl
@@ -30,9 +31,20 @@ var cfgTpl string
 
 var tpl = template.Must(template.New("squid").Parse(cfgTpl))
 
+type ListenAddr struct {
+	Addr string // empty = all interfaces
+	Port int
+}
+
 type View struct {
-	ListenPort int
-	ACLs       []models.ForwardProxyACL
+	ListenAddrs    []ListenAddr
+	ACLs           []models.ForwardProxyACL
+	CacheMemMB     int
+	CacheDirMB     int
+	MaxObjSizeMB   int
+	ConnectTimeout int
+	ReadTimeout    int
+	RequestTimeout int
 }
 
 type Generator struct {
@@ -52,7 +64,45 @@ func (g *Generator) renderBuf(ctx context.Context) (bytes.Buffer, error) {
 	if err != nil {
 		return bytes.Buffer{}, fmt.Errorf("list acls: %w", err)
 	}
-	view := View{ListenPort: listenPort, ACLs: acls}
+
+	// Read all settings — fall back to defaults if table not migrated yet.
+	s := models.ForwardProxySettings{
+		ListenPort:     defaultListenPort,
+		CacheMemMB:     64,
+		CacheDirMB:     100,
+		MaxObjSizeMB:   4,
+		ConnectTimeout: 60,
+		ReadTimeout:    300,
+		RequestTimeout: 300,
+	}
+	_ = g.Pool.QueryRow(ctx, `
+SELECT listen_addresses, listen_port,
+       cache_mem_mb, cache_dir_mb, max_obj_size_mb,
+       connect_timeout, read_timeout, request_timeout
+FROM forward_proxy_settings WHERE id=1`).Scan(
+		&s.ListenAddresses, &s.ListenPort,
+		&s.CacheMemMB, &s.CacheDirMB, &s.MaxObjSizeMB,
+		&s.ConnectTimeout, &s.ReadTimeout, &s.RequestTimeout,
+	)
+
+	var listenAddrs []ListenAddr
+	for _, raw := range splitCSV(s.ListenAddresses) {
+		listenAddrs = append(listenAddrs, ListenAddr{Addr: raw, Port: s.ListenPort})
+	}
+	if len(listenAddrs) == 0 {
+		listenAddrs = []ListenAddr{{Addr: "", Port: s.ListenPort}}
+	}
+
+	view := View{
+		ListenAddrs:    listenAddrs,
+		ACLs:           acls,
+		CacheMemMB:     s.CacheMemMB,
+		CacheDirMB:     s.CacheDirMB,
+		MaxObjSizeMB:   s.MaxObjSizeMB,
+		ConnectTimeout: s.ConnectTimeout,
+		ReadTimeout:    s.ReadTimeout,
+		RequestTimeout: s.RequestTimeout,
+	}
 	var body bytes.Buffer
 	if err := tpl.Execute(&body, view); err != nil {
 		return bytes.Buffer{}, fmt.Errorf("template: %w", err)
@@ -60,6 +110,17 @@ func (g *Generator) renderBuf(ctx context.Context) (bytes.Buffer, error) {
 	return body, nil
 }
 
+func splitCSV(s string) []string {
+	var out []string
+	for _, p := range strings.Split(s, ",") {
+		p = strings.TrimSpace(p)
+		if p != "" {
+			out = append(out, p)
+		}
+	}
+	return out
+}
+
 func (g *Generator) RenderToString(ctx context.Context) (string, error) {
 	buf, err := g.renderBuf(ctx)
 	if err != nil {

internal/unbound/unbound.cfg.tpl

@@ -31,8 +31,10 @@ server:
     do-tcp: yes
     cache-min-ttl: {{.Settings.CacheMinTTL}}
     cache-max-ttl: {{.Settings.CacheMaxTTL}}
-    msg-cache-size: 64m
-    rrset-cache-size: 128m
+    msg-cache-size: {{.Settings.MsgCacheSizeMB}}m
+    rrset-cache-size: {{.Settings.RRSetCacheSizeMB}}m
+    prefetch: {{if .Settings.Prefetch}}yes{{else}}no{{end}}
+    serve-expired: {{if .Settings.ServeExpired}}yes{{else}}no{{end}}
     num-threads: 2
 
     # Hardening

internal/waf/alerts.go

@@ -0,0 +1,120 @@
+package waf
+
+import (
+	"context"
+	"log/slog"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	"github.com/jackc/pgx/v5/pgxpool"
+)
+
+// Alert represents a single WAF rule match that was logged.
+type Alert struct {
+	ID        int64     `json:"id"`
+	DomainID  *int64    `json:"domain_id,omitempty"`
+	Hostname  string    `json:"hostname"`
+	ClientIP  string    `json:"client_ip"`
+	Method    string    `json:"method"`
+	URI       string    `json:"uri"`
+	RuleID    int       `json:"rule_id"`
+	RuleMsg   string    `json:"rule_msg"`
+	Severity  string    `json:"severity"`
+	Action    string    `json:"action"` // "detected" | "blocked"
+	CreatedAt time.Time `json:"created_at"`
+}
+
+// AlertWriter accepts Alert values via a buffered channel and writes
+// them to PostgreSQL asynchronously so SPOE handling stays low-latency.
+type AlertWriter struct {
+	pool      *pgxpool.Pool
+	ch        chan Alert
+	stop      chan struct{}
+	done      chan struct{}
+	closeOnce sync.Once
+	closed    atomic.Bool
+}
+
+// NewAlertWriter creates an AlertWriter and starts its background goroutine.
+// bufSize is the number of unwritten alerts that can queue before drops.
+func NewAlertWriter(pool *pgxpool.Pool, bufSize int) *AlertWriter {
+	aw := &AlertWriter{
+		pool: pool,
+		ch:   make(chan Alert, bufSize),
+		stop: make(chan struct{}),
+		done: make(chan struct{}),
+	}
+	go aw.run()
+	return aw
+}
+
+// Send enqueues an alert. Drops silently if the channel is full (or the
+// writer is closing) to avoid slowing down / panicking SPOE handling.
+func (aw *AlertWriter) Send(a Alert) {
+	if aw.closed.Load() {
+		return
+	}
+	select {
+	case aw.ch <- a:
+	default:
+		slog.Warn("waf: alert channel full — dropping alert", "host", a.Hostname, "rule", a.RuleID)
+	}
+}
+
+// Close stops the writer and flushes buffered alerts (best-effort).
+// Safe to call multiple times. The channel is never closed → Send never
+// panics even if it races with Close.
+func (aw *AlertWriter) Close() {
+	aw.closeOnce.Do(func() {
+		aw.closed.Store(true)
+		close(aw.stop)
+	})
+	<-aw.done
+}
+
+func (aw *AlertWriter) run() {
+	defer close(aw.done)
+	for {
+		select {
+		case a := <-aw.ch:
+			aw.write(a)
+		case <-aw.stop:
+			// Restliche gepufferte Alerts noch wegschreiben, dann Ende.
+			for {
+				select {
+				case a := <-aw.ch:
+					aw.write(a)
+				default:
+					return
+				}
+			}
+		}
+	}
+}
+
+func (aw *AlertWriter) write(a Alert) {
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	// Resolve domain_id from hostname (best-effort).
+	var domainID *int64
+	var id int64
+	if err := aw.pool.QueryRow(ctx,
+		`SELECT id FROM domains WHERE name = $1 AND active = true LIMIT 1`,
+		a.Hostname,
+	).Scan(&id); err == nil {
+		domainID = &id
+	}
+
+	if _, err := aw.pool.Exec(ctx, `
+		INSERT INTO waf_alerts
+		    (domain_id, hostname, client_ip, method, uri,
+		     rule_id, rule_msg, severity, action)
+		VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9)
+	`, domainID, a.Hostname, a.ClientIP, a.Method, a.URI,
+		a.RuleID, a.RuleMsg, a.Severity, a.Action,
+	); err != nil {
+		slog.Warn("waf: write alert to db failed", "error", err)
+	}
+}

internal/waf/alerts_test.go

@@ -0,0 +1,61 @@
+package waf
+
+import (
+	"context"
+	"os"
+	"sync"
+	"testing"
+	"time"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/database"
+)
+
+// Beweist Fix #15: AlertWriter.Close() flusht, ist idempotent, und Send/Close
+// racen ohne Panic (Kanal wird nie geschlossen). Guarded per EG_FWTEST_DSN.
+func TestAlertWriter_CloseFlush(t *testing.T) {
+	dsn := os.Getenv("EG_FWTEST_DSN")
+	if dsn == "" {
+		t.Skip("set EG_FWTEST_DSN to run the alert-writer test")
+	}
+	ctx := context.Background()
+	var mErr error
+	for i := 0; i < 3; i++ {
+		if mErr = database.Migrate(ctx, dsn); mErr == nil {
+			break
+		}
+		time.Sleep(700 * time.Millisecond)
+	}
+	if mErr != nil {
+		t.Fatalf("migrate: %v", mErr)
+	}
+	pool, err := database.Open(ctx, dsn)
+	if err != nil {
+		t.Fatalf("open: %v", err)
+	}
+	defer pool.Close()
+
+	aw := NewAlertWriter(pool, 64)
+	for i := 0; i < 20; i++ {
+		aw.Send(Alert{Hostname: "t.local", ClientIP: "203.0.113.1", Method: "GET", URI: "/", Action: "detected"})
+	}
+
+	// Send parallel zu Close → darf nicht paniken.
+	var wg sync.WaitGroup
+	for i := 0; i < 10; i++ {
+		wg.Add(1)
+		go func() { defer wg.Done(); aw.Send(Alert{Hostname: "t.local", Action: "detected"}) }()
+	}
+
+	done := make(chan struct{})
+	go func() { aw.Close(); close(done) }()
+	select {
+	case <-done:
+	case <-time.After(10 * time.Second):
+		t.Fatal("Close() did not return (flush hung)")
+	}
+	wg.Wait()
+
+	// Idempotent + Send nach Close ist No-op (kein Panic).
+	aw.Close()
+	aw.Send(Alert{Hostname: "after.local", Action: "detected"})
+}

internal/waf/engine.go

@@ -0,0 +1,106 @@
+// Package waf implements the per-domain WAF engine for EdgeGuard.
+// It wraps Coraza v3 (OWASP Core Rule Set) and exposes a simple
+// hostname-keyed engine manager that the SPOE agent uses.
+package waf
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	"github.com/corazawaf/coraza/v3"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+const (
+	DefaultCRSDir   = "/usr/share/edgeguard/waf/crs"
+	DefaultSPOEAddr = "127.0.0.1:9000"
+)
+
+// BuildEngine creates a Coraza WAF instance for the given domain config.
+// crsDir is the path to the OWASP CRS directory (may be empty — engine
+// works without CRS, using only the basic Coraza core rules).
+func BuildEngine(cfg models.WafConfig, crsDir string) (coraza.WAF, error) {
+	directives := buildDirectives(cfg, crsDir)
+	wafCfg := coraza.NewWAFConfig().
+		WithRequestBodyAccess().
+		WithDirectives(directives)
+	return coraza.NewWAF(wafCfg)
+}
+
+// buildDirectives assembles the SecLang directives for a domain config.
+func buildDirectives(cfg models.WafConfig, crsDir string) string {
+	var sb strings.Builder
+
+	sb.WriteString("SecRequestBodyAccess On\n")
+	sb.WriteString("SecResponseBodyAccess Off\n")
+	sb.WriteString("SecRequestBodyLimit 13107200\n")   // 12.5 MB
+	sb.WriteString("SecRequestBodyInMemoryLimit 131072\n") // 128 KB
+
+	sb.WriteString(fmt.Sprintf("SecRuleEngine %s\n", ruleEngineMode(cfg.Mode)))
+
+	if crsDir != "" && crsAvailable(crsDir) {
+		// Paranoia level MUST be set before CRS rules are included.
+		pl := cfg.ParanoiaLevel
+		if pl < 1 || pl > 4 {
+			pl = 1
+		}
+		sb.WriteString(fmt.Sprintf(
+			"SecAction \"id:900000,phase:1,nolog,pass,t:none,setvar:tx.paranoia_level=%d\"\n", pl,
+		))
+		setupConf := filepath.Join(crsDir, "crs-setup.conf")
+		if _, err := os.Stat(setupConf); err == nil {
+			sb.WriteString(fmt.Sprintf("Include %s\n", setupConf))
+		}
+		rulesGlob := filepath.Join(crsDir, "rules", "*.conf")
+		sb.WriteString(fmt.Sprintf("Include %s\n", rulesGlob))
+	}
+
+	// Rule exclusions (applied after CRS load so they override CRS).
+	for _, id := range cfg.RuleExclusions {
+		id = strings.TrimSpace(id)
+		if id != "" {
+			sb.WriteString(fmt.Sprintf("SecRuleRemoveById %s\n", id))
+		}
+	}
+
+	// Trusted proxies are NOT a SecLang directive — they are applied in the
+	// SPOE agent (spoe.go): when the connection source is a trusted proxy,
+	// the real client IP is taken from X-Forwarded-For before Coraza sees
+	// it. (Previously this loop emitted a bogus, unrelated directive.)
+
+	// Custom rules (appended last so they can override CRS).
+	if strings.TrimSpace(cfg.CustomRules) != "" {
+		sb.WriteString(cfg.CustomRules)
+		sb.WriteString("\n")
+	}
+
+	return sb.String()
+}
+
+func ruleEngineMode(mode string) string {
+	switch mode {
+	case "blocking":
+		return "On"
+	default: // "detection"
+		return "DetectionOnly"
+	}
+}
+
+// crsAvailable returns true when the CRS rules directory exists and
+// contains at least one .conf file.
+func crsAvailable(crsDir string) bool {
+	rulesDir := filepath.Join(crsDir, "rules")
+	entries, err := os.ReadDir(rulesDir)
+	if err != nil {
+		return false
+	}
+	for _, e := range entries {
+		if strings.HasSuffix(e.Name(), ".conf") {
+			return true
+		}
+	}
+	return false
+}

internal/waf/manager.go

@@ -0,0 +1,127 @@
+package waf
+
+import (
+	"fmt"
+	"log/slog"
+	"net"
+	"sync"
+
+	"github.com/corazawaf/coraza/v3"
+
+	"git.netcell-it.de/projekte/edgeguard-native/internal/models"
+)
+
+// DomainEngine bundles a Coraza WAF with its operating mode.
+type DomainEngine struct {
+	WAF            coraza.WAF
+	Mode           string   // "detection" | "blocking"
+	TrustedProxies []string // wenn src ∈ diese → echte Client-IP aus X-Forwarded-For
+}
+
+// Manager holds per-domain Coraza engine instances. Engines are
+// rebuilt only when their configuration changes (UpdatedAt differs).
+// All public methods are safe for concurrent use.
+type Manager struct {
+	mu         sync.RWMutex
+	engines    map[string]*DomainEngine // hostname → engine (nil entry = disabled)
+	configKeys map[string]configKey     // hostname → last-seen config fingerprint
+	crsDir     string
+}
+
+// configKey identifies a specific WAF config snapshot so we only
+// rebuild the engine when something actually changed.
+type configKey struct {
+	enabled       bool
+	mode          string
+	paranoiaLevel int
+	updatedAt     int64 // unix nano
+}
+
+// NewManager creates an empty Manager with the given CRS directory.
+func NewManager(crsDir string) *Manager {
+	if crsDir == "" {
+		crsDir = DefaultCRSDir
+	}
+	return &Manager{
+		engines:    make(map[string]*DomainEngine),
+		configKeys: make(map[string]configKey),
+		crsDir:     crsDir,
+	}
+}
+
+// DomainConfig pairs a domain hostname with its WAF policy.
+type DomainConfig struct {
+	Hostname string
+	Config   models.WafConfig
+}
+
+// Reload refreshes engines from the given list, rebuilding only when
+// the config has actually changed since the last call.
+func (m *Manager) Reload(domains []DomainConfig) error {
+	m.mu.RLock()
+	prevEngines := m.engines
+	prevKeys := m.configKeys
+	m.mu.RUnlock()
+
+	newEngines := make(map[string]*DomainEngine, len(domains))
+	newKeys := make(map[string]configKey, len(domains))
+
+	for _, dc := range domains {
+		ck := configKey{
+			enabled:       dc.Config.Enabled,
+			mode:          dc.Config.Mode,
+			paranoiaLevel: dc.Config.ParanoiaLevel,
+			updatedAt:     dc.Config.UpdatedAt.UnixNano(),
+		}
+		newKeys[dc.Hostname] = ck
+
+		if !dc.Config.Enabled {
+			newEngines[dc.Hostname] = nil
+			continue
+		}
+
+		// Reuse existing engine if config hasn't changed.
+		if prev, ok := prevKeys[dc.Hostname]; ok && prev == ck {
+			if existing := prevEngines[dc.Hostname]; existing != nil {
+				newEngines[dc.Hostname] = existing
+				continue
+			}
+		}
+
+		waf, err := BuildEngine(dc.Config, m.crsDir)
+		if err != nil {
+			return fmt.Errorf("waf: build engine for %s: %w", dc.Hostname, err)
+		}
+		newEngines[dc.Hostname] = &DomainEngine{WAF: waf, Mode: dc.Config.Mode, TrustedProxies: dc.Config.TrustedProxies}
+		slog.Info("waf: engine (re)loaded",
+			"host", dc.Hostname,
+			"mode", dc.Config.Mode,
+			"paranoia_level", dc.Config.ParanoiaLevel,
+			"crs", crsAvailable(m.crsDir),
+		)
+	}
+
+	m.mu.Lock()
+	m.engines = newEngines
+	m.configKeys = newKeys
+	m.mu.Unlock()
+	return nil
+}
+
+// GetForHost returns the DomainEngine for the given hostname, or
+// (nil, false) when the domain has no WAF or WAF is disabled.
+func (m *Manager) GetForHost(host string) (*DomainEngine, bool) {
+	// Strip port if present (e.g. "example.com:443" → "example.com").
+	// SplitHostPort errors for a bare host or bare IPv6 literal → keep as-is.
+	if h, _, err := net.SplitHostPort(host); err == nil {
+		host = h
+	}
+	m.mu.RLock()
+	de, ok := m.engines[host]
+	m.mu.RUnlock()
+	if !ok || de == nil {
+		return nil, false
+	}
+	return de, true
+}
+

internal/waf/spoe.go

@@ -0,0 +1,243 @@
+package waf
+
+import (
+	"context"
+	"log/slog"
+	"net"
+	"net/http"
+	"strings"
+
+	"github.com/corazawaf/coraza/v3/types"
+	"github.com/dropmorepackets/haproxy-go/pkg/encoding"
+	"github.com/dropmorepackets/haproxy-go/spop"
+)
+
+// SPOEAgent wraps the haproxy-go SPOE server and dispatches each
+// inspected request to the appropriate per-domain Coraza engine.
+type SPOEAgent struct {
+	Manager      *Manager
+	AlertWriter  *AlertWriter
+	Addr         string
+}
+
+// ListenAndServe starts the SPOE agent. Blocks until ctx is cancelled.
+func (a *SPOEAgent) ListenAndServe(ctx context.Context) error {
+	agent := spop.Agent{
+		Addr:        a.Addr,
+		Handler:     spop.HandlerFunc(a.handle),
+		BaseContext: ctx,
+	}
+	return agent.ListenAndServe()
+}
+
+// handle is called by the haproxy-go SPOE library for every NOTIFY
+// frame HAProxy sends. It extracts the request data, runs Coraza,
+// and optionally sets a txn.waf.status variable to trigger a deny ACL.
+func (a *SPOEAgent) handle(ctx context.Context, w *encoding.ActionWriter, m *encoding.Message) {
+	var (
+		clientIP string
+		method   string
+		uri      string // full request URI (path + optional ?query)
+		httpVer  string
+		host     string
+		rawHdrs  string
+	)
+
+	// Iterate over the key-value pairs HAProxy sent with this message.
+	entry := encoding.AcquireKVEntry()
+	defer encoding.ReleaseKVEntry(entry)
+	for m.KV.Next(entry) {
+		switch {
+		case entry.NameEquals("src"):
+			addr := entry.ValueAddr()
+			if addr.IsValid() {
+				clientIP = addr.String()
+			}
+		case entry.NameEquals("method"):
+			method = string(entry.ValueBytes())
+		case entry.NameEquals("uri"):
+			uri = string(entry.ValueBytes())
+		case entry.NameEquals("ver"):
+			httpVer = string(entry.ValueBytes())
+		case entry.NameEquals("host"):
+			host = string(entry.ValueBytes())
+		case entry.NameEquals("headers"):
+			rawHdrs = string(entry.ValueBytes())
+		}
+		entry.Reset()
+	}
+
+	if host == "" {
+		return
+	}
+
+	de, ok := a.Manager.GetForHost(host)
+	if !ok {
+		return // WAF not configured or disabled for this domain
+	}
+
+	// Trusted-Proxy-Handling: stammt die Verbindung von einem konfigurierten
+	// Trusted-Proxy, ist die echte Client-IP das letzte X-Forwarded-For-Glied
+	// (das der Proxy angehängt hat), nicht die Proxy-IP selbst.
+	if clientIP != "" && len(de.TrustedProxies) > 0 && ipMatchesAny(clientIP, de.TrustedProxies) {
+		if real := rightmostXFF(rawHdrs); real != "" {
+			clientIP = real
+		}
+	}
+
+	tx := de.WAF.NewTransaction()
+	defer func() {
+		tx.ProcessLogging()
+		if err := tx.Close(); err != nil {
+			slog.Warn("waf: tx.Close", "error", err)
+		}
+	}()
+
+	// Feed connection metadata.
+	if clientIP != "" {
+		tx.ProcessConnection(clientIP, 0, "", 0)
+	}
+
+	if uri == "" {
+		uri = "/"
+	}
+	if httpVer == "" {
+		httpVer = "HTTP/1.1"
+	}
+	tx.ProcessURI(uri, method, httpVer)
+
+	// Feed Host header first (required by many CRS rules).
+	tx.AddRequestHeader("Host", host)
+
+	// Parse and feed all raw headers.
+	parseHeaders(rawHdrs, func(name, val string) {
+		if !strings.EqualFold(name, "host") { // already added above
+			tx.AddRequestHeader(name, val)
+		}
+	})
+
+	// Evaluate request headers.
+	interruption := tx.ProcessRequestHeaders()
+
+	// Log all matched rules (detection + blocking).
+	for _, mr := range tx.MatchedRules() {
+		a.sendAlert(host, clientIP, method, uri, mr, interruption != nil)
+	}
+
+	if interruption != nil {
+		status := interruption.Status
+		if status == 0 {
+			status = http.StatusForbidden
+		}
+		slog.Info("waf: request blocked",
+			"host", host, "method", method, "uri", uri,
+			"client", clientIP, "status", status, "rule", interruption.RuleID,
+		)
+		if de.Mode == "blocking" {
+			if err := w.SetInt64(encoding.VarScopeTransaction, "status", int64(status)); err != nil {
+				slog.Warn("waf: SetInt64 status", "error", err)
+			}
+		}
+	}
+}
+
+// sendAlert enqueues a WAF alert for async DB write.
+// Control-flow rules (pass+nolog with empty message) are skipped —
+// they are CRS paranoia-level skip-markers, not real detections.
+func (a *SPOEAgent) sendAlert(host, clientIP, method, uri string, mr types.MatchedRule, blocked bool) {
+	if a.AlertWriter == nil {
+		return
+	}
+	ruleID := mr.Rule().ID()
+	// Skip CRS setup/initialization rules (900xxx–909xxx) — they fire on
+	// every request as part of CRS init and are not security events.
+	// Real detection rules start at 910xxx (IP reputation) and above.
+	if ruleID > 0 && ruleID < 910000 {
+		return
+	}
+	// Skip control-flow rules with no message (PL-skip markers).
+	if mr.Message() == "" {
+		return
+	}
+	action := "detected"
+	if blocked && mr.Disruptive() {
+		action = "blocked"
+	}
+	a.AlertWriter.Send(Alert{
+		Hostname: host,
+		ClientIP: clientIP,
+		Method:   method,
+		URI:      uri,
+		RuleID:   mr.Rule().ID(),
+		RuleMsg:  mr.Message(),
+		Severity: mr.Rule().Severity().String(),
+		Action:   action,
+	})
+}
+
+// rightmostXFF gibt den letzten (vom nächstgelegenen Proxy angehängten)
+// X-Forwarded-For-Eintrag zurück, sofern es eine gültige IP ist.
+func rightmostXFF(rawHdrs string) string {
+	var val string
+	for _, line := range strings.Split(rawHdrs, "\n") {
+		line = strings.TrimRight(line, "\r")
+		idx := strings.IndexByte(line, ':')
+		if idx <= 0 {
+			continue
+		}
+		if strings.EqualFold(strings.TrimSpace(line[:idx]), "x-forwarded-for") {
+			val = strings.TrimSpace(line[idx+1:]) // letzter XFF-Header gewinnt
+		}
+	}
+	if val == "" {
+		return ""
+	}
+	parts := strings.Split(val, ",")
+	cand := strings.TrimSpace(parts[len(parts)-1])
+	if net.ParseIP(cand) == nil {
+		return ""
+	}
+	return cand
+}
+
+// ipMatchesAny prüft, ob ip exakt einer IP oder einem CIDR aus list entspricht.
+func ipMatchesAny(ip string, list []string) bool {
+	parsed := net.ParseIP(ip)
+	if parsed == nil {
+		return false
+	}
+	for _, e := range list {
+		e = strings.TrimSpace(e)
+		if e == "" {
+			continue
+		}
+		if strings.Contains(e, "/") {
+			if _, n, err := net.ParseCIDR(e); err == nil && n.Contains(parsed) {
+				return true
+			}
+		} else if pe := net.ParseIP(e); pe != nil && pe.Equal(parsed) {
+			return true
+		}
+	}
+	return false
+}
+
+// parseHeaders splits HAProxy raw headers ("Name: value\r\n…") and
+// calls fn for each valid header line.
+func parseHeaders(raw string, fn func(name, val string)) {
+	for _, line := range strings.Split(raw, "\n") {
+		line = strings.TrimRight(line, "\r")
+		if line == "" {
+			continue
+		}
+		idx := strings.IndexByte(line, ':')
+		if idx <= 0 {
+			continue
+		}
+		name := strings.TrimSpace(line[:idx])
+		val := strings.TrimSpace(line[idx+1:])
+		if name != "" {
+			fn(name, val)
+		}
+	}
+}

internal/waf/spoe_test.go

@@ -0,0 +1,37 @@
+package waf
+
+import "testing"
+
+// Beweist Fix #2: Trusted-Proxy-XFF-Auflösung.
+func TestRightmostXFF(t *testing.T) {
+	cases := map[string]string{
+		"X-Forwarded-For: 203.0.113.7":                       "203.0.113.7",
+		"X-Forwarded-For: 203.0.113.7, 10.0.0.1":             "10.0.0.1", // rightmost
+		"x-forwarded-for: 1.2.3.4 , 5.6.7.8":                 "5.6.7.8",
+		"Host: x\r\nX-Forwarded-For: 2001:db8::1":            "2001:db8::1",
+		"X-Forwarded-For: not-an-ip":                         "",
+		"User-Agent: foo":                                    "",
+		"":                                                   "",
+	}
+	for raw, want := range cases {
+		if got := rightmostXFF(raw); got != want {
+			t.Errorf("rightmostXFF(%q) = %q, want %q", raw, got, want)
+		}
+	}
+}
+
+func TestIPMatchesAny(t *testing.T) {
+	list := []string{"10.0.0.5", "192.168.0.0/16", "2001:db8::/32"}
+	yes := []string{"10.0.0.5", "192.168.4.7", "2001:db8::abcd"}
+	no := []string{"10.0.0.6", "172.16.0.1", "2002::1", "garbage"}
+	for _, ip := range yes {
+		if !ipMatchesAny(ip, list) {
+			t.Errorf("ipMatchesAny(%q) = false, want true", ip)
+		}
+	}
+	for _, ip := range no {
+		if ipMatchesAny(ip, list) {
+			t.Errorf("ipMatchesAny(%q) = true, want false", ip)
+		}
+	}
+}