Merge pull request #295 from Control-D-Inc/release-branch-v1.5.0

Release branch v1.5.0

.github/workflows/ci.yml

@@ -9,18 +9,18 @@ jobs:
       fail-fast: false
       matrix:
         os: ["windows-latest", "ubuntu-latest", "macOS-latest"]
-        go: ["1.23.x"]
+        go: ["1.24.x"]
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v3
         with:
           fetch-depth: 1
-      - uses: WillAbides/setup-go-faster@v1.8.0
+      - uses: actions/setup-go@v6
         with:
           go-version: ${{ matrix.go }}
       - run: "go test -race ./..."
-      - uses: dominikh/staticcheck-action@v1.3.1
+      - uses: dominikh/staticcheck-action@v1.4.0
         with:
-          version: "2024.1.1"
+          version: "2025.1.1"
           install-go: false
           cache-key: ${{ matrix.go }}

.gitignore

@@ -12,3 +12,5 @@ ctrld-*
 
 # generated file
 cmd/cli/rsrc_*.syso
+ctrld
+ctrld.exe

cmd/cli/ad_windows.go

@@ -10,11 +10,12 @@ import (
 	hh "github.com/microsoft/wmi/pkg/hardware/host"
 
 	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/system"
 )
 
 // addExtraSplitDnsRule adds split DNS rule for domain if it's part of active directory.
 func addExtraSplitDnsRule(cfg *ctrld.Config) bool {
-	domain, err := getActiveDirectoryDomain()
+	domain, err := system.GetActiveDirectoryDomain()
 	if err != nil {
 		mainLog.Load().Debug().Msgf("unable to get active directory domain: %v", err)
 		return false

cmd/cli/ad_windows_test.go

@@ -5,14 +5,16 @@ import (
 	"testing"
 	"time"
 
-	"github.com/Control-D-Inc/ctrld"
-	"github.com/Control-D-Inc/ctrld/testhelper"
 	"github.com/stretchr/testify/assert"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/system"
+	"github.com/Control-D-Inc/ctrld/testhelper"
 )
 
 func Test_getActiveDirectoryDomain(t *testing.T) {
 	start := time.Now()
-	domain, err := getActiveDirectoryDomain()
+	domain, err := system.GetActiveDirectoryDomain()
 	if err != nil {
 		t.Fatal(err)
 	}

cmd/cli/cli.go

@@ -178,7 +178,15 @@ func RunMobile(appConfig *AppConfig, appCallback *AppCallback, stopCh chan struc
 	noConfigStart = false
 	homedir = appConfig.HomeDir
 	verbose = appConfig.Verbose
-	cdUID = appConfig.CdUID
+	if appConfig.ProvisionID != "" {
+		cdOrg = appConfig.ProvisionID
+	}
+	if appConfig.CustomHostname != "" {
+		customHostname = appConfig.CustomHostname
+	}
+	if appConfig.CdUID != "" {
+		cdUID = appConfig.CdUID
+	}
 	cdUpstreamProto = appConfig.UpstreamProto
 	logPath = appConfig.LogPath
 	run(appCallback, stopCh)
@@ -274,7 +282,7 @@ func run(appCallback *AppCallback, stopCh chan struct{}) {
 	}
 	p.mu.Unlock()
 
-	processLogAndCacheFlags()
+	processLogAndCacheFlags(v, &cfg)
 
 	// Log config do not have thing to validate, so it's safe to init log here,
 	// so it's able to log information in processCDFlags.
@@ -334,7 +342,17 @@ func run(appCallback *AppCallback, stopCh chan struct{}) {
 	updated := updateListenerConfig(&cfg, notifyExitToLogServer)
 
 	if cdUID != "" {
-		processLogAndCacheFlags()
+		processLogAndCacheFlags(v, &cfg)
+	}
+
+	// Persist intercept_mode to config when provided via CLI flag on full install.
+	// This ensures the config file reflects the actual running mode for RMM/MDM visibility.
+	if interceptMode == "dns" || interceptMode == "hard" {
+		if cfg.Service.InterceptMode != interceptMode {
+			cfg.Service.InterceptMode = interceptMode
+			updated = true
+			mainLog.Load().Info().Msgf("writing intercept_mode = %q to config", interceptMode)
+		}
 	}
 
 	if updated {
@@ -634,13 +652,19 @@ func processCDFlags(cfg *ctrld.Config) (*controld.ResolverConfig, error) {
 	logger.Info().Msgf("fetching Controld D configuration from API: %s", cdUID)
 	bo := backoff.NewBackoff("processCDFlags", logf, 30*time.Second)
 	bo.LogLongerThan = 30 * time.Second
+
 	ctx := context.Background()
-	resolverConfig, err := controld.FetchResolverConfig(cdUID, rootCmd.Version, cdDev)
+	req := &controld.ResolverConfigRequest{
+		RawUID:   cdUID,
+		Version:  rootCmd.Version,
+		Metadata: ctrld.SystemMetadataRuntime(context.Background()),
+	}
+	resolverConfig, err := controld.FetchResolverConfig(req, cdDev)
 	for {
 		if errUrlNetworkError(err) {
 			bo.BackOff(ctx, err)
 			logger.Warn().Msg("could not fetch resolver using bootstrap DNS, retrying...")
-			resolverConfig, err = controld.FetchResolverConfig(cdUID, rootCmd.Version, cdDev)
+			resolverConfig, err = controld.FetchResolverConfig(req, cdDev)
 			continue
 		}
 		break
@@ -772,7 +796,8 @@ func processListenFlag() {
 	})
 }
 
-func processLogAndCacheFlags() {
+// processLogAndCacheFlags processes log and cache related flags
+func processLogAndCacheFlags(v *viper.Viper, cfg *ctrld.Config) {
 	if logPath != "" {
 		cfg.Service.LogPath = logPath
 	}
@@ -1205,10 +1230,99 @@ func updateListenerConfig(cfg *ctrld.Config, notifyToLogServerFunc func()) bool
 	return updated
 }
 
+// tryUpdateListenerConfigIntercept handles listener binding for dns-intercept mode on macOS.
+// In intercept mode, pf redirects all outbound port-53 traffic to ctrld's listener,
+// so ctrld can safely listen on a non-standard port if port 53 is unavailable
+// (e.g., mDNSResponder holds *:53).
+//
+// Flow:
+//  1. If config has explicit (non-default) IP:port → use exactly that, no fallback
+//  2. Otherwise → try 127.0.0.1:53, then 127.0.0.1:5354, then fatal
+func tryUpdateListenerConfigIntercept(cfg *ctrld.Config, notifyFunc func(), fatal bool) (updated, ok bool) {
+	ok = true
+	lc := cfg.FirstListener()
+	if lc == nil {
+		return false, true
+	}
+
+	hasExplicitConfig := lc.IP != "" && lc.IP != "0.0.0.0" && lc.Port != 0
+	if !hasExplicitConfig {
+		// Set defaults for intercept mode
+		if lc.IP == "" || lc.IP == "0.0.0.0" {
+			lc.IP = "127.0.0.1"
+			updated = true
+		}
+		if lc.Port == 0 {
+			lc.Port = 53
+			updated = true
+		}
+	}
+
+	tryListen := func(ip string, port int) bool {
+		addr := net.JoinHostPort(ip, strconv.Itoa(port))
+		udpLn, udpErr := net.ListenPacket("udp", addr)
+		if udpLn != nil {
+			udpLn.Close()
+		}
+		tcpLn, tcpErr := net.Listen("tcp", addr)
+		if tcpLn != nil {
+			tcpLn.Close()
+		}
+		return udpErr == nil && tcpErr == nil
+	}
+
+	addr := net.JoinHostPort(lc.IP, strconv.Itoa(lc.Port))
+	if tryListen(lc.IP, lc.Port) {
+		mainLog.Load().Debug().Msgf("DNS intercept: listener available at %s", addr)
+		return updated, true
+	}
+
+	mainLog.Load().Info().Msgf("DNS intercept: cannot bind %s", addr)
+
+	if hasExplicitConfig {
+		// User specified explicit address — don't guess, just fail
+		if fatal {
+			notifyFunc()
+			mainLog.Load().Fatal().Msgf("DNS intercept: cannot listen on configured address %s", addr)
+		}
+		return updated, false
+	}
+
+	// Fallback: try port 5354 (mDNSResponder likely holds *:53)
+	if tryListen("127.0.0.1", 5354) {
+		mainLog.Load().Info().Msg("DNS intercept: port 53 unavailable (likely mDNSResponder), using 127.0.0.1:5354")
+		lc.IP = "127.0.0.1"
+		lc.Port = 5354
+		return true, true
+	}
+
+	if fatal {
+		notifyFunc()
+		mainLog.Load().Fatal().Msg("DNS intercept: cannot bind 127.0.0.1:53 or 127.0.0.1:5354")
+	}
+	return updated, false
+}
+
 // tryUpdateListenerConfig tries updating listener config with a working one.
 // If fatal is true, and there's listen address conflicted, the function do
 // fatal error.
 func tryUpdateListenerConfig(cfg *ctrld.Config, infoLogger *zerolog.Logger, notifyFunc func(), fatal bool) (updated, ok bool) {
+	// In intercept mode (macOS), pf redirects all port-53 traffic to ctrld's listener,
+	// so ctrld can safely listen on a non-standard port. Use a simple two-attempt flow:
+	// 1. If config has explicit non-default IP:port, use exactly that
+	// 2. Otherwise: try 127.0.0.1:53, then 127.0.0.1:5354, then fatal
+	// This bypasses the full cd-mode listener probing loop entirely.
+	// Check interceptMode (CLI flag) first, then fall back to config value.
+	// dnsIntercept bool is derived later in prog.run(), but we need to know
+	// the intercept mode here to select the right listener probing strategy.
+	im := interceptMode
+	if im == "" || im == "off" {
+		im = cfg.Service.InterceptMode
+	}
+	if (im == "dns" || im == "hard") && runtime.GOOS == "darwin" {
+		return tryUpdateListenerConfigIntercept(cfg, notifyFunc, fatal)
+	}
+
 	ok = true
 	lcc := make(map[string]*listenerConfigCheck)
 	cdMode := cdUID != ""
@@ -1507,7 +1621,12 @@ func cdUIDFromProvToken() string {
 	if customHostname != "" && !validHostname(customHostname) {
 		mainLog.Load().Fatal().Msgf("invalid custom hostname: %q", customHostname)
 	}
-	req := &controld.UtilityOrgRequest{ProvToken: cdOrg, Hostname: customHostname}
+
+	req := &controld.UtilityOrgRequest{
+		ProvToken: cdOrg,
+		Hostname:  customHostname,
+		Metadata:  ctrld.SystemMetadata(context.Background()),
+	}
 	// Process provision token if provided.
 	resolverConfig, err := controld.FetchResolverUID(req, rootCmd.Version, cdDev)
 	if err != nil {
@@ -1848,7 +1967,14 @@ func runningIface(s service.Service) *ifaceResponse {
 
 // doValidateCdRemoteConfig fetches and validates custom config for cdUID.
 func doValidateCdRemoteConfig(cdUID string, fatal bool) error {
-	rc, err := controld.FetchResolverConfig(cdUID, rootCmd.Version, cdDev)
+	// Username is only sent during initial provisioning (cdUIDFromProvToken).
+	// All subsequent calls use lightweight metadata to avoid EDR triggers.
+	req := &controld.ResolverConfigRequest{
+		RawUID:   cdUID,
+		Version:  rootCmd.Version,
+		Metadata: ctrld.SystemMetadataRuntime(context.Background()),
+	}
+	rc, err := controld.FetchResolverConfig(req, cdDev)
 	if err != nil {
 		logger := mainLog.Load().Fatal()
 		if !fatal {

cmd/cli/commands.go

@@ -13,6 +13,7 @@ import (
 	"os/exec"
 	"path/filepath"
 	"runtime"
+	"slices"
 	"sort"
 	"strconv"
 	"strings"
@@ -188,6 +189,8 @@ func initRunCmd() *cobra.Command {
 	runCmd.Flags().StringVarP(&iface, "iface", "", "", `Update DNS setting for iface, "auto" means the default interface gateway`)
 	_ = runCmd.Flags().MarkHidden("iface")
 	runCmd.Flags().StringVarP(&cdUpstreamProto, "proto", "", ctrld.ResolverTypeDOH, `Control D upstream type, either "doh" or "doh3"`)
+	runCmd.Flags().BoolVarP(&rfc1918, "rfc1918", "", false, "Listen on RFC1918 addresses when 127.0.0.1 is the only listener")
+	runCmd.Flags().StringVarP(&interceptMode, "intercept-mode", "", "", "OS-level DNS interception mode: 'dns' (with VPN split routing) or 'hard' (all DNS through ctrld, no VPN split routing)")
 
 	runCmd.FParseErrWhitelist = cobra.FParseErrWhitelist{UnknownFlags: true}
 	rootCmd.AddCommand(runCmd)
@@ -206,6 +209,7 @@ func initStartCmd() *cobra.Command {
 
 NOTE: running "ctrld start" without any arguments will start already installed ctrld service.`,
 		Args: func(cmd *cobra.Command, args []string) error {
+			args = filterEmptyStrings(args)
 			if len(args) > 0 {
 				return fmt.Errorf("'ctrld start' doesn't accept positional arguments\n" +
 					"Use flags instead (e.g. --cd, --iface) or see 'ctrld start --help' for all options")
@@ -219,12 +223,21 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 			sc := &service.Config{}
 			*sc = *svcConfig
 			osArgs := os.Args[2:]
+			osArgs = filterEmptyStrings(osArgs)
 			if os.Args[1] == "service" {
 				osArgs = os.Args[3:]
 			}
 			setDependencies(sc)
 			sc.Arguments = append([]string{"run"}, osArgs...)
 
+			// Validate --intercept-mode early, before installing the service.
+			// Without this, a typo like "--intercept-mode fds" would install the service,
+			// the child process would Fatal() on the invalid value, and the parent would
+			// then uninstall — confusing and destructive.
+			if interceptMode != "" && !validInterceptMode(interceptMode) {
+				mainLog.Load().Fatal().Msgf("invalid --intercept-mode value %q: must be 'off', 'dns', or 'hard'", interceptMode)
+			}
+
 			p := &prog{
 				router: router.New(&cfg, cdUID != ""),
 				cfg:    &cfg,
@@ -243,6 +256,49 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 			// Get current running iface, if any.
 			var currentIface *ifaceResponse
 
+			// Handle "ctrld start --intercept-mode dns|hard" on an existing
+			// service BEFORE the pin check. Adding intercept mode is an enhancement, not
+			// deactivation, so it doesn't require the deactivation pin. We modify the
+			// plist/registry directly and restart the service via the OS service manager.
+			osArgsEarly := os.Args[2:]
+			if os.Args[1] == "service" {
+				osArgsEarly = os.Args[3:]
+			}
+			osArgsEarly = filterEmptyStrings(osArgsEarly)
+			interceptOnly := onlyInterceptFlags(osArgsEarly)
+			svcExists := serviceConfigFileExists()
+			mainLog.Load().Debug().Msgf("intercept upgrade check: args=%v interceptOnly=%v svcConfigExists=%v interceptMode=%q", osArgsEarly, interceptOnly, svcExists, interceptMode)
+			if interceptOnly && svcExists {
+				// Remove any existing intercept flags before applying the new value.
+				_ = removeServiceFlag("--intercept-mode")
+
+				if interceptMode == "off" {
+					// "off" = remove intercept mode entirely (just the removal above).
+					mainLog.Load().Notice().Msg("Existing service detected — removing --intercept-mode from service arguments")
+				} else {
+					// Add the new mode value.
+					mainLog.Load().Notice().Msgf("Existing service detected — appending --intercept-mode %s to service arguments", interceptMode)
+					if err := appendServiceFlag("--intercept-mode"); err != nil {
+						mainLog.Load().Fatal().Err(err).Msg("failed to append intercept flag to service arguments")
+					}
+					if err := appendServiceFlag(interceptMode); err != nil {
+						mainLog.Load().Fatal().Err(err).Msg("failed to append intercept mode value to service arguments")
+					}
+				}
+
+				// Stop the service if running (bypasses ctrld pin — this is an
+				// enhancement, not deactivation). Then fall through to the normal
+				// startOnly path which handles start, self-check, and reporting.
+				if isCtrldRunning {
+					mainLog.Load().Notice().Msg("Stopping service for intercept mode upgrade")
+					_ = s.Stop()
+					isCtrldRunning = false
+				}
+				startOnly = true
+				isCtrldInstalled = true
+				// Fall through to startOnly path below.
+			}
+
 			// If pin code was set, do not allow running start command.
 			if isCtrldRunning {
 				if err := checkDeactivationPin(s, nil); isCheckDeactivationPinErr(err) {
@@ -267,20 +323,31 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 							return
 						}
 						if res.OK {
-							name := res.Name
-							if iff, err := net.InterfaceByName(name); err == nil {
-								_, _ = patchNetIfaceName(iff)
-								name = iff.Name
-							}
-							logger := mainLog.Load().With().Str("iface", name).Logger()
-							logger.Debug().Msg("setting DNS successfully")
-							if res.All {
-								// Log that DNS is set for other interfaces.
-								withEachPhysicalInterfaces(
-									name,
-									"set DNS",
-									func(i *net.Interface) error { return nil },
-								)
+							// In intercept mode, show intercept-specific status instead of
+							// per-interface DNS messages (which are irrelevant).
+							if res.InterceptMode != "" {
+								switch res.InterceptMode {
+								case "hard":
+									mainLog.Load().Notice().Msg("DNS hard intercept mode active — all DNS traffic intercepted, no VPN split routing")
+								default:
+									mainLog.Load().Notice().Msg("DNS intercept mode active — all DNS traffic intercepted via OS packet filter")
+								}
+							} else {
+								name := res.Name
+								if iff, err := net.InterfaceByName(name); err == nil {
+									_, _ = patchNetIfaceName(iff)
+									name = iff.Name
+								}
+								logger := mainLog.Load().With().Str("iface", name).Logger()
+								logger.Debug().Msg("setting DNS successfully")
+								if res.All {
+									// Log that DNS is set for other interfaces.
+									withEachPhysicalInterfaces(
+										name,
+										"set DNS",
+										func(i *net.Interface) error { return nil },
+									)
+								}
 							}
 						}
 					}
@@ -340,6 +407,7 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 			if !startOnly {
 				startOnly = len(osArgs) == 0
 			}
+
 			// If user run "ctrld start" and ctrld is already installed, starting existing service.
 			if startOnly && isCtrldInstalled {
 				tryReadingConfigWithNotice(false, true)
@@ -380,6 +448,10 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 						os.Exit(1)
 					}
 					reportSetDnsOk(sockDir)
+					// Verify service registration after successful start.
+					if err := verifyServiceRegistration(); err != nil {
+						mainLog.Load().Warn().Err(err).Msg("Service registry verification failed")
+					}
 				} else {
 					mainLog.Load().Error().Err(err).Msg("Failed to start existing ctrld service")
 					os.Exit(1)
@@ -388,7 +460,8 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 			}
 
 			if cdUID != "" {
-				_ = doValidateCdRemoteConfig(cdUID, true)
+				// Skip doValidateCdRemoteConfig() here - run command will handle
+				// validation and config fetch via processCDFlags().
 			} else if uid := cdUIDFromProvToken(); uid != "" {
 				cdUID = uid
 				mainLog.Load().Debug().Msg("using uid from provision token")
@@ -505,6 +578,10 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 					os.Exit(1)
 				}
 				reportSetDnsOk(sockDir)
+				// Verify service registration after successful start.
+				if err := verifyServiceRegistration(); err != nil {
+					mainLog.Load().Warn().Err(err).Msg("Service registry verification failed")
+				}
 			}
 		},
 	}
@@ -528,6 +605,8 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 	startCmd.Flags().BoolVarP(&skipSelfChecks, "skip_self_checks", "", false, `Skip self checks after installing ctrld service`)
 	startCmd.Flags().BoolVarP(&startOnly, "start_only", "", false, "Do not install new service")
 	_ = startCmd.Flags().MarkHidden("start_only")
+	startCmd.Flags().BoolVarP(&rfc1918, "rfc1918", "", false, "Listen on RFC1918 addresses when 127.0.0.1 is the only listener")
+	startCmd.Flags().StringVarP(&interceptMode, "intercept-mode", "", "", "OS-level DNS interception mode: 'dns' (with VPN split routing) or 'hard' (all DNS through ctrld, no VPN split routing)")
 
 	routerCmd := &cobra.Command{
 		Use: "setup",
@@ -566,6 +645,7 @@ NOTE: running "ctrld start" without any arguments will start already installed c
 
 NOTE: running "ctrld start" without any arguments will start already installed ctrld service.`,
 		Args: func(cmd *cobra.Command, args []string) error {
+			args = filterEmptyStrings(args)
 			if len(args) > 0 {
 				return fmt.Errorf("'ctrld start' doesn't accept positional arguments\n" +
 					"Use flags instead (e.g. --cd, --iface) or see 'ctrld start --help' for all options")
@@ -1381,3 +1461,61 @@ func initServicesCmd(commands ...*cobra.Command) *cobra.Command {
 
 	return serviceCmd
 }
+
+// filterEmptyStrings removes empty strings from a slice of strings.
+// It returns a new slice containing only non-empty strings.
+func filterEmptyStrings(slice []string) []string {
+	return slices.DeleteFunc(slice, func(s string) bool {
+		return s == ""
+	})
+}
+
+// validInterceptMode reports whether the given value is a recognized --intercept-mode.
+// This is the single source of truth for mode validation — used by the early start
+// command check, the runtime validation in prog.go, and onlyInterceptFlags below.
+// Add new modes here to have them recognized everywhere.
+func validInterceptMode(mode string) bool {
+	switch mode {
+	case "off", "dns", "hard":
+		return true
+	}
+	return false
+}
+
+// onlyInterceptFlags reports whether args contain only intercept mode
+// flags (--intercept-mode <value>) and flags that are auto-added by the
+// start command alias (--iface). This is used to detect "ctrld start --intercept-mode dns"
+// (or "off" to disable) on an existing installation, where the intent is to modify the
+// intercept flag on the existing service without replacing other arguments.
+//
+// Note: the startCmdAlias appends "--iface=auto" to os.Args when --iface isn't
+// explicitly provided, so we must allow it here.
+func onlyInterceptFlags(args []string) bool {
+	hasIntercept := false
+	for i := 0; i < len(args); i++ {
+		arg := args[i]
+		switch {
+		case arg == "--intercept-mode":
+			// Next arg must be a valid mode value.
+			if i+1 < len(args) && validInterceptMode(args[i+1]) {
+				hasIntercept = true
+				i++ // skip the value
+			} else {
+				return false
+			}
+		case strings.HasPrefix(arg, "--intercept-mode="):
+			val := strings.TrimPrefix(arg, "--intercept-mode=")
+			if validInterceptMode(val) {
+				hasIntercept = true
+			} else {
+				return false
+			}
+		case arg == "--iface=auto" || arg == "--iface" || arg == "auto":
+			// Auto-added by startCmdAlias or its value; safe to ignore.
+			continue
+		default:
+			return false
+		}
+	}
+	return hasIntercept
+}

cmd/cli/control_server.go

@@ -32,9 +32,10 @@ const (
 )
 
 type ifaceResponse struct {
-	Name string `json:"name"`
-	All  bool   `json:"all"`
-	OK   bool   `json:"ok"`
+	Name          string `json:"name"`
+	All           bool   `json:"all"`
+	OK            bool   `json:"ok"`
+	InterceptMode string `json:"intercept_mode,omitempty"` // "dns", "hard", or "" (not intercepting)
 }
 
 type controlServer struct {
@@ -217,7 +218,12 @@ func (p *prog) registerControlServerHandler() {
 		}
 
 		// Re-fetch pin code from API.
-		if rc, err := controld.FetchResolverConfig(cdUID, rootCmd.Version, cdDev); rc != nil {
+		rcReq := &controld.ResolverConfigRequest{
+			RawUID:   cdUID,
+			Version:  rootCmd.Version,
+			Metadata: ctrld.SystemMetadataRuntime(context.Background()),
+		}
+		if rc, err := controld.FetchResolverConfig(rcReq, cdDev); rc != nil {
 			if rc.DeactivationPin != nil {
 				cdDeactivationPin.Store(*rc.DeactivationPin)
 			} else {
@@ -271,6 +277,10 @@ func (p *prog) registerControlServerHandler() {
 				res.Name = p.runningIface
 				res.All = p.requiredMultiNICsConfig
 				res.OK = true
+				// Report intercept mode to the start command for proper log output.
+				if interceptMode == "dns" || interceptMode == "hard" {
+					res.InterceptMode = interceptMode
+				}
 			}
 		}
 		if err := json.NewEncoder(w).Encode(res); err != nil {

cmd/cli/dns_intercept_darwin_test.go

@@ -0,0 +1,143 @@
+//go:build darwin
+
+package cli
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// =============================================================================
+// buildPFAnchorRules tests
+// =============================================================================
+
+func TestPFBuildAnchorRules_Basic(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{Listener: map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}}}
+	rules := p.buildPFAnchorRules(nil)
+
+	// rdr (translation) must come before pass (filtering)
+	rdrIdx := strings.Index(rules, "rdr on lo0 inet proto udp")
+	passRouteIdx := strings.Index(rules, "pass out quick on ! lo0 route-to lo0 inet proto udp")
+	passInIdx := strings.Index(rules, "pass in quick on lo0 reply-to lo0")
+
+	if rdrIdx < 0 {
+		t.Fatal("missing rdr rule")
+	}
+	if passRouteIdx < 0 {
+		t.Fatal("missing pass out route-to rule")
+	}
+	if passInIdx < 0 {
+		t.Fatal("missing pass in on lo0 rule")
+	}
+	if rdrIdx >= passRouteIdx {
+		t.Error("rdr rules must come before pass out route-to rules")
+	}
+	if passRouteIdx >= passInIdx {
+		t.Error("pass out route-to must come before pass in on lo0")
+	}
+
+	// Both UDP and TCP rdr rules
+	if !strings.Contains(rules, "proto udp") || !strings.Contains(rules, "proto tcp") {
+		t.Error("must have both UDP and TCP rdr rules")
+	}
+}
+
+func TestPFBuildAnchorRules_WithVPNServers(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{Listener: map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}}}
+	vpnServers := []vpnDNSExemption{
+		{Server: "10.8.0.1"},
+		{Server: "10.8.0.2"},
+	}
+	rules := p.buildPFAnchorRules(vpnServers)
+
+	// VPN exemption rules must appear
+	for _, s := range vpnServers {
+		if !strings.Contains(rules, s.Server) {
+			t.Errorf("missing VPN exemption for %s", s.Server)
+		}
+	}
+
+	// VPN exemptions must come before route-to
+	exemptIdx := strings.Index(rules, "10.8.0.1 port 53 group")
+	routeIdx := strings.Index(rules, "pass out quick on ! lo0 route-to lo0 inet proto udp")
+	if exemptIdx < 0 {
+		t.Fatal("missing VPN exemption rule for 10.8.0.1")
+	}
+	if routeIdx < 0 {
+		t.Fatal("missing route-to rule")
+	}
+	if exemptIdx >= routeIdx {
+		t.Error("VPN exemptions must come before route-to rules")
+	}
+}
+
+func TestPFBuildAnchorRules_IPv4AndIPv6VPN(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{Listener: map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}}}
+	vpnServers := []vpnDNSExemption{
+		{Server: "10.8.0.1"},
+		{Server: "fd00::1"},
+	}
+	rules := p.buildPFAnchorRules(vpnServers)
+
+	// IPv4 server should use "inet"
+	lines := strings.Split(rules, "\n")
+	for _, line := range lines {
+		if strings.Contains(line, "10.8.0.1") && strings.HasPrefix(line, "pass") {
+			if !strings.Contains(line, "inet ") {
+				t.Error("IPv4 VPN server rule should contain 'inet'")
+			}
+			if strings.Contains(line, "inet6") {
+				t.Error("IPv4 VPN server rule should not contain 'inet6'")
+			}
+		}
+		if strings.Contains(line, "fd00::1") && strings.HasPrefix(line, "pass") {
+			if !strings.Contains(line, "inet6") {
+				t.Error("IPv6 VPN server rule should contain 'inet6'")
+			}
+		}
+	}
+}
+
+func TestPFBuildAnchorRules_Ordering(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{Listener: map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}}}
+	vpnServers := []vpnDNSExemption{
+		{Server: "10.8.0.1"},
+	}
+	rules := p.buildPFAnchorRules(vpnServers)
+
+	// Verify ordering: rdr → exemptions → route-to → pass in on lo0
+	rdrIdx := strings.Index(rules, "rdr on lo0 inet proto udp")
+	exemptIdx := strings.Index(rules, "pass out quick on ! lo0 inet proto { udp, tcp } from any to 10.8.0.1 port 53 group _ctrld")
+	routeIdx := strings.Index(rules, "pass out quick on ! lo0 route-to lo0 inet proto udp")
+	passInIdx := strings.Index(rules, "pass in quick on lo0 reply-to lo0")
+
+	if rdrIdx < 0 || exemptIdx < 0 || routeIdx < 0 || passInIdx < 0 {
+		t.Fatalf("missing expected rules: rdr=%d exempt=%d route=%d passIn=%d", rdrIdx, exemptIdx, routeIdx, passInIdx)
+	}
+
+	if !(rdrIdx < exemptIdx && exemptIdx < routeIdx && routeIdx < passInIdx) {
+		t.Errorf("incorrect rule ordering: rdr(%d) < exempt(%d) < route(%d) < passIn(%d)", rdrIdx, exemptIdx, routeIdx, passInIdx)
+	}
+}
+
+// TestPFAddressFamily tests the pfAddressFamily helper.
+func TestPFAddressFamily(t *testing.T) {
+	tests := []struct {
+		ip   string
+		want string
+	}{
+		{"10.0.0.1", "inet"},
+		{"192.168.1.1", "inet"},
+		{"127.0.0.1", "inet"},
+		{"::1", "inet6"},
+		{"fd00::1", "inet6"},
+		{"2001:db8::1", "inet6"},
+	}
+	for _, tt := range tests {
+		if got := pfAddressFamily(tt.ip); got != tt.want {
+			t.Errorf("pfAddressFamily(%q) = %q, want %q", tt.ip, got, tt.want)
+		}
+	}
+}

cmd/cli/dns_intercept_others.go

@@ -0,0 +1,39 @@
+//go:build !windows && !darwin
+
+package cli
+
+import (
+	"fmt"
+)
+
+// startDNSIntercept is not supported on this platform.
+// DNS intercept mode is only available on Windows (via WFP) and macOS (via pf).
+func (p *prog) startDNSIntercept() error {
+	return fmt.Errorf("dns intercept: not supported on this platform (only Windows and macOS)")
+}
+
+// stopDNSIntercept is a no-op on unsupported platforms.
+func (p *prog) stopDNSIntercept() error {
+	return nil
+}
+
+// exemptVPNDNSServers is a no-op on unsupported platforms.
+func (p *prog) exemptVPNDNSServers(exemptions []vpnDNSExemption) error {
+	return nil
+}
+
+// ensurePFAnchorActive is a no-op on unsupported platforms.
+func (p *prog) ensurePFAnchorActive() bool {
+	return false
+}
+
+// checkTunnelInterfaceChanges is a no-op on unsupported platforms.
+func (p *prog) checkTunnelInterfaceChanges() bool {
+	return false
+}
+
+// scheduleDelayedRechecks is a no-op on unsupported platforms.
+func (p *prog) scheduleDelayedRechecks() {}
+
+// pfInterceptMonitor is a no-op on unsupported platforms.
+func (p *prog) pfInterceptMonitor() {}

cmd/cli/dns_proxy.go

@@ -84,13 +84,7 @@ type upstreamForResult struct {
 	srcAddr        string
 }
 
-func (p *prog) serveDNS(mainCtx context.Context, listenerNum string) error {
-	// Start network monitoring
-	if err := p.monitorNetworkChanges(mainCtx); err != nil {
-		mainLog.Load().Error().Err(err).Msg("Failed to start network monitoring")
-		// Don't return here as we still want DNS service to run
-	}
-
+func (p *prog) serveDNS(listenerNum string) error {
 	listenerConfig := p.cfg.Listener[listenerNum]
 	// make sure ip is allocated
 	if allocErr := p.allocateIP(listenerConfig.IP); allocErr != nil {
@@ -110,7 +104,7 @@ func (p *prog) serveDNS(mainCtx context.Context, listenerNum string) error {
 		listenerConfig := p.cfg.Listener[listenerNum]
 		reqId := requestID()
 		ctx := context.WithValue(context.Background(), ctrld.ReqIdCtxKey{}, reqId)
-		if !listenerConfig.AllowWanClients && isWanClient(w.RemoteAddr()) {
+		if !listenerConfig.AllowWanClients && isWanClient(w.RemoteAddr()) && !isIPv6LoopbackListener(w.LocalAddr()) {
 			ctrld.Log(ctx, mainLog.Load().Debug(), "query refused, listener does not allow WAN clients: %s", w.RemoteAddr().String())
 			answer := new(dns.Msg)
 			answer.SetRcode(m, dns.RcodeRefused)
@@ -132,6 +126,23 @@ func (p *prog) serveDNS(mainCtx context.Context, listenerNum string) error {
 			return
 		}
 
+		// Interception probe: if we're expecting a probe query and this matches,
+		// signal the prober and respond NXDOMAIN. Used by both macOS pf probes
+		// (_pf-probe-*) and Windows NRPT probes (_nrpt-probe-*) to verify that
+		// DNS interception is actually routing queries to ctrld's listener.
+		if probeID, ok := p.pfProbeExpected.Load().(string); ok && probeID != "" && domain == probeID {
+			if chPtr, ok := p.pfProbeCh.Load().(*chan struct{}); ok && chPtr != nil {
+				select {
+				case *chPtr <- struct{}{}:
+				default:
+				}
+			}
+			answer := new(dns.Msg)
+			answer.SetRcode(m, dns.RcodeNameError) // NXDOMAIN
+			_ = w.WriteMsg(answer)
+			return
+		}
+
 		if _, ok := p.cacheFlushDomainsMap[domain]; ok && p.cache != nil {
 			p.cache.Purge()
 			ctrld.Log(ctx, mainLog.Load().Debug(), "received query %q, local cache is purged", domain)
@@ -198,7 +209,7 @@ func (p *prog) serveDNS(mainCtx context.Context, listenerNum string) error {
 	g, ctx := errgroup.WithContext(context.Background())
 	for _, proto := range []string{"udp", "tcp"} {
 		proto := proto
-		if needLocalIPv6Listener() {
+		if needLocalIPv6Listener(p.cfg.Service.InterceptMode) {
 			g.Go(func() error {
 				s, errCh := runDNSServer(net.JoinHostPort("::1", strconv.Itoa(listenerConfig.Port)), proto, handler)
 				defer s.Shutdown()
@@ -213,8 +224,8 @@ func (p *prog) serveDNS(mainCtx context.Context, listenerNum string) error {
 				return nil
 			})
 		}
-		// When we spawn a listener on 127.0.0.1, also spawn listeners on the RFC1918
-		// addresses of the machine. So ctrld could receive queries from LAN clients.
+		// When we spawn a listener on 127.0.0.1, also spawn listeners on the RFC1918 addresses of the machine
+		// if explicitly set via setting rfc1918 flag, so ctrld could receive queries from LAN clients.
 		if needRFC1918Listeners(listenerConfig) {
 			g.Go(func() error {
 				for _, addr := range ctrld.Rfc1918Addresses() {
@@ -427,6 +438,24 @@ func (p *prog) proxyLanHostnameQuery(ctx context.Context, msg *dns.Msg) *dns.Msg
 }
 
 func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
+	// DNS intercept recovery bypass: forward all queries to OS/DHCP resolver.
+	// This runs when upstreams are unreachable (e.g., captive portal network)
+	// and allows the network's DNS to handle authentication pages.
+	if dnsIntercept && p.recoveryBypass.Load() {
+		ctrld.Log(ctx, mainLog.Load().Debug(), "Recovery bypass active: forwarding to OS resolver")
+		resolver, err := ctrld.NewResolver(osUpstreamConfig)
+		if err == nil {
+			resolveCtx, cancel := osUpstreamConfig.Context(ctx)
+			defer cancel()
+			answer, _ := resolver.Resolve(resolveCtx, req.msg)
+			if answer != nil {
+				return &proxyResponse{answer: answer}
+			}
+		}
+		ctrld.Log(ctx, mainLog.Load().Debug(), "OS resolver failed during recovery bypass")
+		// Fall through to normal flow as last resort
+	}
+
 	var staleAnswer *dns.Msg
 	upstreams := req.ufr.upstreams
 	serveStaleCache := p.cache != nil && p.cfg.Service.CacheServeStale
@@ -439,9 +468,9 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 		// However, on Active Directory Domain Controller, where it has local DNS server
 		// running and listening on local addresses, these local addresses must be used
 		// as nameservers, so queries for ADDC could be resolved as expected.
-		if p.isAdDomainQuery(req.msg) {
+		if p.isAdDomainQuery(req.msg) && p.hasLocalDNS {
 			ctrld.Log(ctx, mainLog.Load().Debug(),
-				"AD domain query detected for %s in domain %s",
+				"AD domain query detected for %s in domain %s, using local DNS server",
 				req.msg.Question[0].Name, p.adDomain)
 			upstreamConfigs = []*ctrld.UpstreamConfig{localUpstreamConfig}
 			upstreams = []string{upstreamOSLocal}
@@ -512,6 +541,92 @@ func (p *prog) proxy(ctx context.Context, req *proxyRequest) *proxyResponse {
 			staleAnswer = answer
 		}
 	}
+
+	// VPN DNS split routing (only in dns-intercept mode)
+	if dnsIntercept && p.vpnDNS != nil && len(req.msg.Question) > 0 {
+		domain := req.msg.Question[0].Name
+		if vpnServers := p.vpnDNS.UpstreamForDomain(domain); len(vpnServers) > 0 {
+			ctrld.Log(ctx, mainLog.Load().Debug(), "VPN DNS route matched for domain %s, using servers: %v", domain, vpnServers)
+
+			for _, server := range vpnServers {
+				upstreamConfig := p.vpnDNS.upstreamConfigFor(server)
+				ctrld.Log(ctx, mainLog.Load().Debug(), "Querying VPN DNS server: %s", server)
+
+				dnsResolver, err := ctrld.NewResolver(upstreamConfig)
+				if err != nil {
+					ctrld.Log(ctx, mainLog.Load().Error().Err(err), "failed to create VPN DNS resolver")
+					continue
+				}
+				resolveCtx, cancel := upstreamConfig.Context(ctx)
+				answer, err := dnsResolver.Resolve(resolveCtx, req.msg)
+				cancel()
+				if answer != nil {
+					ctrld.Log(ctx, mainLog.Load().Debug(), "VPN DNS query successful")
+					if p.cache != nil {
+						ttl := 60 * time.Second
+						if len(answer.Answer) > 0 {
+							ttl = time.Duration(answer.Answer[0].Header().Ttl) * time.Second
+						}
+						for _, upstream := range upstreams {
+							p.cache.Add(dnscache.NewKey(req.msg, upstream), dnscache.NewValue(answer, time.Now().Add(ttl)))
+						}
+					}
+					return &proxyResponse{answer: answer}
+				}
+				ctrld.Log(ctx, mainLog.Load().Debug().Err(err), "VPN DNS server %s failed", server)
+			}
+
+			ctrld.Log(ctx, mainLog.Load().Debug(), "All VPN DNS servers failed, falling back to normal upstreams")
+		}
+	}
+
+	// Domain-less VPN DNS fallback: when a query is going to upstream.os via a
+	// split-rule (matched policy) and we have VPN DNS servers with no associated
+	// domains, try those servers for this query. This handles cases like F5 VPN
+	// where the VPN doesn't advertise DNS search domains but its DNS servers
+	// know the internal zones referenced by split-rules (e.g., *.provisur.local).
+	// These servers are NOT used for general OS resolver queries to avoid
+	// polluting captive portal / DHCP flows.
+	if dnsIntercept && p.vpnDNS != nil && req.ufr.matched &&
+		len(upstreams) > 0 && upstreams[0] == upstreamOS &&
+		len(req.msg.Question) > 0 && !p.isAdDomainQuery(req.msg) {
+		if dlServers := p.vpnDNS.DomainlessServers(); len(dlServers) > 0 {
+			domain := req.msg.Question[0].Name
+			ctrld.Log(ctx, mainLog.Load().Debug(),
+				"Split-rule query %s going to upstream.os, trying %d domain-less VPN DNS servers first: %v",
+				domain, len(dlServers), dlServers)
+
+			for _, server := range dlServers {
+				upstreamCfg := p.vpnDNS.upstreamConfigFor(server)
+				ctrld.Log(ctx, mainLog.Load().Debug(), "Querying domain-less VPN DNS server: %s", server)
+
+				dnsResolver, err := ctrld.NewResolver(upstreamCfg)
+				if err != nil {
+					ctrld.Log(ctx, mainLog.Load().Error().Err(err), "failed to create domain-less VPN DNS resolver")
+					continue
+				}
+				resolveCtx, cancel := upstreamCfg.Context(ctx)
+				answer, err := dnsResolver.Resolve(resolveCtx, req.msg)
+				cancel()
+				if answer != nil && answer.Rcode == dns.RcodeSuccess {
+					ctrld.Log(ctx, mainLog.Load().Debug(),
+						"Domain-less VPN DNS server %s answered %s successfully", server, domain)
+					return &proxyResponse{answer: answer}
+				}
+				if answer != nil {
+					ctrld.Log(ctx, mainLog.Load().Debug(),
+						"Domain-less VPN DNS server %s returned %s for %s, trying next",
+						server, dns.RcodeToString[answer.Rcode], domain)
+				} else {
+					ctrld.Log(ctx, mainLog.Load().Debug().Err(err),
+						"Domain-less VPN DNS server %s failed for %s", server, domain)
+				}
+			}
+			ctrld.Log(ctx, mainLog.Load().Debug(),
+				"All domain-less VPN DNS servers failed for %s, falling back to OS resolver", domain)
+		}
+	}
+
 	resolve1 := func(upstream string, upstreamConfig *ctrld.UpstreamConfig, msg *dns.Msg) (*dns.Msg, error) {
 		ctrld.Log(ctx, mainLog.Load().Debug(), "sending query to %s: %s", upstream, upstreamConfig.Name)
 		dnsResolver, err := ctrld.NewResolver(upstreamConfig)
@@ -777,10 +892,30 @@ func ttlFromMsg(msg *dns.Msg) uint32 {
 	return 0
 }
 
-func needLocalIPv6Listener() bool {
+func needLocalIPv6Listener(interceptMode string) bool {
+	if !ctrldnet.SupportsIPv6ListenLocal() {
+		mainLog.Load().Debug().Msg("IPv6 listener: not needed — SupportsIPv6ListenLocal() is false")
+		return false
+	}
 	// On Windows, there's no easy way for disabling/removing IPv6 DNS resolver, so we check whether we can
 	// listen on ::1, then spawn a listener for receiving DNS requests.
-	return ctrldnet.SupportsIPv6ListenLocal() && runtime.GOOS == "windows"
+	if runtime.GOOS == "windows" {
+		mainLog.Load().Debug().Msg("IPv6 listener: enabled (Windows)")
+		return true
+	}
+	// On macOS in intercept mode, pf can't redirect IPv6 DNS to an IPv4 listener (cross-AF rdr
+	// not supported), and blocking IPv6 DNS causes ~1s timeouts (BSD doesn't deliver ICMP errors
+	// to unconnected UDP sockets). Listening on [::1] lets us intercept IPv6 DNS directly.
+	//
+	// NOTE: We accept the intercept mode string as a parameter instead of reading the global
+	// dnsIntercept bool, because dnsIntercept is derived later in prog.run() — after the
+	// listener goroutines are already spawned. Same pattern as the port 5354 fallback fix (MR !860).
+	if (interceptMode == "dns" || interceptMode == "hard") && runtime.GOOS == "darwin" {
+		mainLog.Load().Debug().Msg("IPv6 listener: enabled (macOS intercept mode)")
+		return true
+	}
+	mainLog.Load().Debug().Str("os", runtime.GOOS).Str("interceptMode", interceptMode).Msg("IPv6 listener: not needed")
+	return false
 }
 
 // ipAndMacFromMsg extracts IP and MAC information included in a DNS message, if any.
@@ -916,13 +1051,36 @@ func (p *prog) getClientInfo(remoteIP string, msg *dns.Msg) *ctrld.ClientInfo {
 	} else {
 		ci.Hostname = p.ciTable.LookupHostname(ci.IP, ci.Mac)
 	}
-	ci.Self = p.queryFromSelf(ci.IP)
+
+	if ci.IP == "" {
+		mainLog.Load().Debug().Msgf("client info entry with empty IP address: %v", ci)
+	} else {
+		ci.Self = p.queryFromSelf(ci.IP)
+	}
+
+	// In DNS intercept mode, ALL queries are from the local machine — pf/WFP
+	// intercepts outbound DNS and redirects to ctrld. The source IP may be a
+	// virtual interface (Tailscale, VPN) that has no ARP/MAC entry, causing
+	// missing x-cd-mac, x-cd-host, and x-cd-os headers. Force Self=true and
+	// populate from the primary physical interface info.
+	if dnsIntercept && !ci.Self {
+		ci.Self = true
+	}
+
 	// If this is a query from self, but ci.IP is not loopback IP,
 	// try using hostname mapping for lookback IP if presents.
 	if ci.Self {
 		if name := p.ciTable.LocalHostname(); name != "" {
 			ci.Hostname = name
 		}
+		// If MAC is still empty (e.g., query arrived via virtual interface IP
+		// like Tailscale), fall back to the loopback MAC mapping which addSelf()
+		// populates from the primary physical interface.
+		if ci.Mac == "" {
+			if mac := p.ciTable.LookupMac("127.0.0.1"); mac != "" {
+				ci.Mac = mac
+			}
+		}
 	}
 	p.spoofLoopbackIpInClientInfo(ci)
 	return ci
@@ -960,7 +1118,13 @@ func (p *prog) doSelfUninstall(answer *dns.Msg) {
 	logger := mainLog.Load().With().Str("mode", "self-uninstall").Logger()
 	if p.refusedQueryCount > selfUninstallMaxQueries {
 		p.checkingSelfUninstall = true
-		_, err := controld.FetchResolverConfig(cdUID, rootCmd.Version, cdDev)
+
+		req := &controld.ResolverConfigRequest{
+			RawUID:   cdUID,
+			Version:  rootCmd.Version,
+			Metadata: ctrld.SystemMetadataRuntime(context.Background()),
+		}
+		_, err := controld.FetchResolverConfig(req, cdDev)
 		logger.Debug().Msg("maximum number of refused queries reached, checking device status")
 		selfUninstallCheck(err, p, logger)
 
@@ -1026,7 +1190,12 @@ func (p *prog) queryFromSelf(ip string) bool {
 	if val, ok := p.queryFromSelfMap.Load(ip); ok {
 		return val.(bool)
 	}
-	netIP := netip.MustParseAddr(ip)
+	netIP, err := netip.ParseAddr(ip)
+	if err != nil {
+		mainLog.Load().Debug().Err(err).Msgf("could not parse IP: %q", ip)
+		return false
+	}
+
 	regularIPs, loopbackIPs, err := netmon.LocalAddresses()
 	if err != nil {
 		mainLog.Load().Warn().Err(err).Msg("could not get local addresses")
@@ -1045,7 +1214,7 @@ func (p *prog) queryFromSelf(ip string) bool {
 // needRFC1918Listeners reports whether ctrld need to spawn listener for RFC 1918 addresses.
 // This is helpful for non-desktop platforms to receive queries from LAN clients.
 func needRFC1918Listeners(lc *ctrld.ListenerConfig) bool {
-	return lc.IP == "127.0.0.1" && lc.Port == 53 && !ctrld.IsDesktopPlatform()
+	return rfc1918 && lc.IP == "127.0.0.1" && lc.Port == 53
 }
 
 // ipFromARPA parses a FQDN arpa domain and return the IP address if valid.
@@ -1147,6 +1316,18 @@ func isWanClient(na net.Addr) bool {
 		!tsaddr.CGNATRange().Contains(ip)
 }
 
+// isIPv6LoopbackListener reports whether the listener address is [::1].
+// The [::1] listener only serves locally-redirected traffic (via pf on macOS
+// or system DNS on Windows), so queries arriving on it are always from this
+// machine — even when the source IP is a global IPv6 address (pf preserves the
+// original source IP during rdr).
+func isIPv6LoopbackListener(na net.Addr) bool {
+	if ap, err := netip.ParseAddrPort(na.String()); err == nil {
+		return ap.Addr() == netip.IPv6Loopback()
+	}
+	return false
+}
+
 // resolveInternalDomainTestQuery resolves internal test domain query, returning the answer to the caller.
 func resolveInternalDomainTestQuery(ctx context.Context, domain string, m *dns.Msg) *dns.Msg {
 	ctrld.Log(ctx, mainLog.Load().Debug(), "internal domain test query")
@@ -1187,7 +1368,7 @@ func FlushDNSCache() error {
 }
 
 // monitorNetworkChanges starts monitoring for network interface changes
-func (p *prog) monitorNetworkChanges(ctx context.Context) error {
+func (p *prog) monitorNetworkChanges() error {
 	mon, err := netmon.New(func(format string, args ...any) {
 		// Always fetch the latest logger (and inject the prefix)
 		mainLog.Load().Printf("netmon: "+format, args...)
@@ -1272,6 +1453,65 @@ func (p *prog) monitorNetworkChanges(ctx context.Context) error {
 			mainLog.Load().Debug().Msg("Ignoring interface change - no valid interfaces affected")
 			// check if the default IPs are still on an interface that is up
 			ValidateDefaultLocalIPsFromDelta(delta.New)
+			// Even minor interface changes can trigger macOS pf reloads — verify anchor.
+			// We check immediately AND schedule delayed re-checks (2s + 4s) to catch
+			// programs like Windscribe that modify pf rules and DNS settings
+			// asynchronously after the network change event fires.
+			if dnsIntercept && p.dnsInterceptState != nil {
+				if !p.pfStabilizing.Load() {
+					p.ensurePFAnchorActive()
+				}
+				// Check tunnel interfaces unconditionally — it decides internally
+				// whether to enter stabilization or rebuild immediately.
+				p.checkTunnelInterfaceChanges()
+				// Schedule delayed re-checks to catch async VPN teardown changes.
+				// These also refresh the OS resolver and VPN DNS routes.
+				p.scheduleDelayedRechecks()
+
+				// Detect interface appearance/disappearance — hypervisors (Parallels,
+				// VMware, VirtualBox) reload pf when creating/destroying virtual network
+				// interfaces, which can corrupt pf's internal translation state. The rdr
+				// rules survive in text form (watchdog says "intact") but stop evaluating.
+				// Spawn an async monitor that probes pf interception with backoff and
+				// forces a full pf reload if broken.
+				if delta.Old != nil {
+					interfaceChanged := false
+					var changedIface string
+					for ifaceName := range delta.Old.Interface {
+						if ifaceName == "lo0" {
+							continue
+						}
+						if _, exists := delta.New.Interface[ifaceName]; !exists {
+							interfaceChanged = true
+							changedIface = ifaceName
+							break
+						}
+					}
+					if !interfaceChanged {
+						for ifaceName := range delta.New.Interface {
+							if ifaceName == "lo0" {
+								continue
+							}
+							if _, exists := delta.Old.Interface[ifaceName]; !exists {
+								interfaceChanged = true
+								changedIface = ifaceName
+								break
+							}
+						}
+					}
+					if interfaceChanged {
+						mainLog.Load().Info().Str("interface", changedIface).
+							Msg("DNS intercept: interface appeared/disappeared — starting interception probe monitor")
+						go p.pfInterceptMonitor()
+					}
+				}
+			}
+			// Refresh VPN DNS on tunnel interface changes (e.g., Tailscale connect/disconnect)
+			// even though the physical interface didn't change. Runs after tunnel checks
+			// so the pf anchor rebuild includes current VPN DNS exemptions.
+			if dnsIntercept && p.vpnDNS != nil {
+				p.vpnDNS.Refresh(true)
+			}
 			return
 		}
 
@@ -1280,6 +1520,11 @@ func (p *prog) monitorNetworkChanges(ctx context.Context) error {
 			return
 		}
 
+		mainLog.Load().Debug().Msg("Link state changed, re-bootstrapping")
+		for _, uc := range p.cfg.Upstream {
+			uc.ReBootstrap()
+		}
+
 		// Get IPs from default route interface in new state
 		selfIP := defaultRouteIP()
 
@@ -1340,6 +1585,26 @@ func (p *prog) monitorNetworkChanges(ctx context.Context) error {
 		if router.Name() == "" {
 			p.handleRecovery(RecoveryReasonNetworkChange)
 		}
+
+		// After network changes, verify our pf anchor is still active and
+		// refresh VPN DNS state. Order matters: tunnel checks first (may rebuild
+		// anchor), then VPN DNS refresh (updates exemptions in anchor), then
+		// delayed re-checks for async VPN teardown.
+		if dnsIntercept && p.dnsInterceptState != nil {
+			if !p.pfStabilizing.Load() {
+				p.ensurePFAnchorActive()
+			}
+			// Check tunnel interfaces unconditionally — it decides internally
+			// whether to enter stabilization or rebuild immediately.
+			p.checkTunnelInterfaceChanges()
+			// Refresh VPN DNS routes — runs after tunnel checks so the anchor
+			// rebuild includes current VPN DNS exemptions.
+			if p.vpnDNS != nil {
+				p.vpnDNS.Refresh(true)
+			}
+			// Schedule delayed re-checks to catch async VPN teardown changes.
+			p.scheduleDelayedRechecks()
+		}
 	})
 
 	mon.Start()
@@ -1406,9 +1671,6 @@ func (p *prog) checkUpstreamOnce(upstream string, uc *ctrld.UpstreamConfig) erro
 		return err
 	}
 
-	msg := new(dns.Msg)
-	msg.SetQuestion(".", dns.TypeNS)
-
 	timeout := 1000 * time.Millisecond
 	if uc.Timeout > 0 {
 		timeout = time.Millisecond * time.Duration(uc.Timeout)
@@ -1422,6 +1684,7 @@ func (p *prog) checkUpstreamOnce(upstream string, uc *ctrld.UpstreamConfig) erro
 	mainLog.Load().Debug().Msgf("Rebootstrapping resolver for upstream: %s", upstream)
 
 	start := time.Now()
+	msg := uc.VerifyMsg()
 	_, err = resolver.Resolve(ctx, msg)
 	duration := time.Since(start)
 
@@ -1466,22 +1729,57 @@ func (p *prog) handleRecovery(reason RecoveryReason) {
 	p.recoveryCancel = cancel
 	p.recoveryCancelMu.Unlock()
 
-	// Immediately remove our DNS settings from the interface.
 	// set recoveryRunning to true to prevent watchdogs from putting the listener back on the interface
 	p.recoveryRunning.Store(true)
-	// we do not want to restore any static DNS settings
-	// we must try to get the DHCP values, any static DNS settings
-	// will be appended to nameservers from the saved interface values
-	p.resetDNS(false, false)
 
-	// For an OS failure, reinitialize OS resolver nameservers immediately.
-	if reason == RecoveryReasonOSFailure {
-		mainLog.Load().Debug().Msg("OS resolver failure detected; reinitializing OS resolver nameservers")
-		ns := ctrld.InitializeOsResolver(true)
-		if len(ns) == 0 {
-			mainLog.Load().Warn().Msg("No nameservers found for OS resolver; using existing values")
+	// In DNS intercept mode, don't tear down WFP/pf filters.
+	// Instead, enable recovery bypass so proxy() forwards queries to
+	// the OS/DHCP resolver. This handles captive portal authentication
+	// without the overhead of filter teardown/rebuild.
+	if dnsIntercept && p.dnsInterceptState != nil {
+		p.recoveryBypass.Store(true)
+		mainLog.Load().Info().Msg("DNS intercept recovery: enabling DHCP bypass (filters stay active)")
+
+		// Reinitialize OS resolver to discover DHCP servers on the new network.
+		mainLog.Load().Debug().Msg("DNS intercept recovery: discovering DHCP nameservers")
+		dhcpServers := ctrld.InitializeOsResolver(true)
+		if len(dhcpServers) == 0 {
+			mainLog.Load().Warn().Msg("DNS intercept recovery: no DHCP nameservers found")
 		} else {
-			mainLog.Load().Info().Msgf("Reinitialized OS resolver with nameservers: %v", ns)
+			mainLog.Load().Info().Msgf("DNS intercept recovery: found DHCP nameservers: %v", dhcpServers)
+		}
+
+		// Exempt DHCP nameservers from intercept filters so the OS resolver
+		// can actually reach them on port 53.
+		if len(dhcpServers) > 0 {
+			// Build exemptions without an Interface — DHCP servers are not VPN-specific,
+			// so they only generate group-scoped pf rules (ctrld process only).
+			exemptions := make([]vpnDNSExemption, 0, len(dhcpServers))
+			for _, s := range dhcpServers {
+				host := s
+				if h, _, err := net.SplitHostPort(s); err == nil {
+					host = h
+				}
+				exemptions = append(exemptions, vpnDNSExemption{Server: host})
+			}
+			mainLog.Load().Info().Msgf("DNS intercept recovery: exempting DHCP nameservers from filters: %v", exemptions)
+			if err := p.exemptVPNDNSServers(exemptions); err != nil {
+				mainLog.Load().Warn().Err(err).Msg("DNS intercept recovery: failed to exempt DHCP nameservers — recovery queries may fail")
+			}
+		}
+	} else {
+		// Traditional flow: remove DNS settings to expose DHCP nameservers
+		p.resetDNS(false, false)
+
+		// For an OS failure, reinitialize OS resolver nameservers immediately.
+		if reason == RecoveryReasonOSFailure {
+			mainLog.Load().Debug().Msg("OS resolver failure detected; reinitializing OS resolver nameservers")
+			ns := ctrld.InitializeOsResolver(true)
+			if len(ns) == 0 {
+				mainLog.Load().Warn().Msg("No nameservers found for OS resolver; using existing values")
+			} else {
+				mainLog.Load().Info().Msgf("Reinitialized OS resolver with nameservers: %v", ns)
+			}
 		}
 	}
 
@@ -1502,23 +1800,46 @@ func (p *prog) handleRecovery(reason RecoveryReason) {
 	// reset the upstream failure count and down state
 	p.um.reset(recovered)
 
-	// For network changes we also reinitialize the OS resolver.
-	if reason == RecoveryReasonNetworkChange {
-		ns := ctrld.InitializeOsResolver(true)
-		if len(ns) == 0 {
-			mainLog.Load().Warn().Msg("No nameservers found for OS resolver during network-change recovery; using existing values")
-		} else {
-			mainLog.Load().Info().Msgf("Reinitialized OS resolver with nameservers: %v", ns)
+	// In DNS intercept mode, just disable the bypass — filters are still active.
+	if dnsIntercept && p.dnsInterceptState != nil {
+		p.recoveryBypass.Store(false)
+		mainLog.Load().Info().Msg("DNS intercept recovery complete: disabling DHCP bypass, resuming normal flow")
+
+		// Refresh VPN DNS routes in case VPN state changed during recovery.
+		if p.vpnDNS != nil {
+			p.vpnDNS.Refresh(true)
 		}
+
+		// Reinitialize OS resolver for the recovered state.
+		if reason == RecoveryReasonNetworkChange {
+			ns := ctrld.InitializeOsResolver(true)
+			if len(ns) == 0 {
+				mainLog.Load().Warn().Msg("No nameservers found for OS resolver during network-change recovery; using existing values")
+			} else {
+				mainLog.Load().Info().Msgf("Reinitialized OS resolver with nameservers: %v", ns)
+			}
+		}
+
+		p.recoveryRunning.Store(false)
+	} else {
+		// For network changes we also reinitialize the OS resolver.
+		if reason == RecoveryReasonNetworkChange {
+			ns := ctrld.InitializeOsResolver(true)
+			if len(ns) == 0 {
+				mainLog.Load().Warn().Msg("No nameservers found for OS resolver during network-change recovery; using existing values")
+			} else {
+				mainLog.Load().Info().Msgf("Reinitialized OS resolver with nameservers: %v", ns)
+			}
+		}
+
+		// Apply our DNS settings back and log the interface state.
+		p.setDNS()
+		p.logInterfacesState()
+
+		// allow watchdogs to put the listener back on the interface if its changed for any reason
+		p.recoveryRunning.Store(false)
 	}
 
-	// Apply our DNS settings back and log the interface state.
-	p.setDNS()
-	p.logInterfacesState()
-
-	// allow watchdogs to put the listener back on the interface if its changed for any reason
-	p.recoveryRunning.Store(false)
-
 	// Clear the recovery cancellation for a clean slate.
 	p.recoveryCancelMu.Lock()
 	p.recoveryCancel = nil

cmd/cli/dns_proxy_test.go

@@ -22,15 +22,15 @@ func Test_wildcardMatches(t *testing.T) {
 		domain   string
 		match    bool
 	}{
-		{"domain - prefix parent should not match", "*.windscribe.com", "windscribe.com", false},
-		{"domain - prefix", "*.windscribe.com", "anything.windscribe.com", true},
-		{"domain - prefix not match other s", "*.windscribe.com", "example.com", false},
-		{"domain - prefix not match s in name", "*.windscribe.com", "wwindscribe.com", false},
-		{"domain - suffix", "suffix.*", "suffix.windscribe.com", true},
-		{"domain - suffix not match other", "suffix.*", "suffix1.windscribe.com", false},
-		{"domain - both", "suffix.*.windscribe.com", "suffix.anything.windscribe.com", true},
-		{"domain - both not match", "suffix.*.windscribe.com", "suffix1.suffix.windscribe.com", false},
-		{"domain - case-insensitive", "*.WINDSCRIBE.com", "anything.windscribe.com", true},
+		{"domain - prefix parent should not match", "*.example.com", "example.com", false},
+		{"domain - prefix", "*.example.com", "anything.example.com", true},
+		{"domain - prefix not match other s", "*.example.com", "other.org", false},
+		{"domain - prefix not match s in name", "*.example.com", "eexample.com", false},
+		{"domain - suffix", "suffix.*", "suffix.example.com", true},
+		{"domain - suffix not match other", "suffix.*", "suffix1.example.com", false},
+		{"domain - both", "suffix.*.example.com", "suffix.anything.example.com", true},
+		{"domain - both not match", "suffix.*.example.com", "suffix1.suffix.example.com", false},
+		{"domain - case-insensitive", "*.EXAMPLE.com", "anything.example.com", true},
 		{"mac - prefix", "*:98:05:b4:2b", "d4:67:98:05:b4:2b", true},
 		{"mac - prefix not match other s", "*:98:05:b4:2b", "0d:ba:54:09:94:2c", false},
 		{"mac - prefix not match s in name", "*:98:05:b4:2b", "e4:67:97:05:b4:2b", false},
@@ -57,9 +57,9 @@ func Test_canonicalName(t *testing.T) {
 		domain    string
 		canonical string
 	}{
-		{"fqdn to canonical", "windscribe.com.", "windscribe.com"},
-		{"already canonical", "windscribe.com", "windscribe.com"},
-		{"case insensitive", "Windscribe.Com.", "windscribe.com"},
+		{"fqdn to canonical", "example.com.", "example.com"},
+		{"already canonical", "example.com", "example.com"},
+		{"case insensitive", "Example.Com.", "example.com"},
 	}
 
 	for _, tc := range tests {
@@ -464,3 +464,13 @@ func Test_isWanClient(t *testing.T) {
 		})
 	}
 }
+
+func Test_prog_queryFromSelf(t *testing.T) {
+	p := &prog{}
+	require.NotPanics(t, func() {
+		p.queryFromSelf("")
+	})
+	require.NotPanics(t, func() {
+		p.queryFromSelf("foo")
+	})
+}

cmd/cli/library.go

@@ -18,11 +18,13 @@ type AppCallback struct {
 
 // AppConfig allows overwriting ctrld cli flags from mobile platforms.
 type AppConfig struct {
-	CdUID         string
-	HomeDir       string
-	UpstreamProto string
-	Verbose       int
-	LogPath       string
+	CdUID          string
+	ProvisionID    string
+	CustomHostname string
+	HomeDir        string
+	UpstreamProto  string
+	Verbose        int
+	LogPath        string
 }
 
 const (

cmd/cli/main.go

@@ -1,7 +1,9 @@
 package cli
 
 import (
+	"encoding/hex"
 	"io"
+	"net"
 	"os"
 	"path/filepath"
 	"sync/atomic"
@@ -39,6 +41,10 @@ var (
 	skipSelfChecks    bool
 	cleanup           bool
 	startOnly         bool
+	rfc1918           bool
+	interceptMode     string // "", "dns", or "hard" — set via --intercept-mode flag or config
+	dnsIntercept      bool   // derived: interceptMode == "dns" || interceptMode == "hard"
+	hardIntercept     bool   // derived: interceptMode == "hard"
 
 	mainLog       atomic.Pointer[zerolog.Logger]
 	consoleWriter zerolog.ConsoleWriter
@@ -58,6 +64,16 @@ func init() {
 }
 
 func Main() {
+	// Fast path for pf interception probe subprocess. This runs before cobra
+	// initialization to minimize startup time. The parent process spawns us with
+	// "pf-probe-send <host> <hex-dns-packet>" and a non-_ctrld GID so pf
+	// intercepts the DNS query. If pf rdr is working, the query reaches ctrld's
+	// listener; if not, it goes to the real DNS server and ctrld detects the miss.
+	if len(os.Args) >= 4 && os.Args[1] == "pf-probe-send" {
+		pfProbeSend(os.Args[2], os.Args[3])
+		return
+	}
+
 	ctrld.InitConfig(v, "ctrld")
 	initCLI()
 	if err := rootCmd.Execute(); err != nil {
@@ -188,3 +204,25 @@ func initCache() {
 		cfg.Service.CacheSize = 4096
 	}
 }
+
+// pfProbeSend is a minimal subprocess that sends a pre-built DNS query packet
+// to the specified host on port 53. It's invoked by probePFIntercept() with a
+// non-_ctrld GID so pf interception applies to the query.
+//
+// Usage: ctrld pf-probe-send <host> <hex-encoded-dns-packet>
+func pfProbeSend(host, hexPacket string) {
+	packet, err := hex.DecodeString(hexPacket)
+	if err != nil {
+		os.Exit(1)
+	}
+	conn, err := net.DialTimeout("udp", net.JoinHostPort(host, "53"), time.Second)
+	if err != nil {
+		os.Exit(1)
+	}
+	defer conn.Close()
+	conn.SetDeadline(time.Now().Add(time.Second))
+	_, _ = conn.Write(packet)
+	// Read response (don't care about result, just need the send to happen)
+	buf := make([]byte, 512)
+	_, _ = conn.Read(buf)
+}

cmd/cli/netlink_linux.go

@@ -1,34 +0,0 @@
-package cli
-
-import (
-	"context"
-
-	"github.com/vishvananda/netlink"
-	"golang.org/x/sys/unix"
-)
-
-func (p *prog) watchLinkState(ctx context.Context) {
-	ch := make(chan netlink.LinkUpdate)
-	done := make(chan struct{})
-	defer close(done)
-	if err := netlink.LinkSubscribe(ch, done); err != nil {
-		mainLog.Load().Warn().Err(err).Msg("could not subscribe link")
-		return
-	}
-	for {
-		select {
-		case <-ctx.Done():
-			return
-		case lu := <-ch:
-			if lu.Change == 0xFFFFFFFF {
-				continue
-			}
-			if lu.Change&unix.IFF_UP != 0 {
-				mainLog.Load().Debug().Msgf("link state changed, re-bootstrapping")
-				for _, uc := range p.cfg.Upstream {
-					uc.ReBootstrap()
-				}
-			}
-		}
-	}
-}

cmd/cli/netlink_others.go

@@ -1,7 +0,0 @@
-//go:build !linux
-
-package cli
-
-import "context"
-
-func (p *prog) watchLinkState(ctx context.Context) {}

cmd/cli/os_linux.go

@@ -72,7 +72,15 @@ func setDNS(iface *net.Interface, nameservers []string) error {
 		SearchDomains: []dnsname.FQDN{},
 	}
 	if sds, err := searchDomains(); err == nil {
-		osConfig.SearchDomains = sds
+		// Filter the root domain, since it's not allowed by systemd.
+		// See https://github.com/systemd/systemd/issues/9515
+		filteredSds := slices.DeleteFunc(sds, func(s dnsname.FQDN) bool {
+			return s == "" || s == "."
+		})
+		if len(filteredSds) != len(sds) {
+			mainLog.Load().Debug().Msg(`Removed root domain "." from search domains list`)
+		}
+		osConfig.SearchDomains = filteredSds
 	} else {
 		mainLog.Load().Debug().Err(err).Msg("failed to get search domains list")
 	}

cmd/cli/os_windows.go

@@ -55,7 +55,7 @@ func setDNS(iface *net.Interface, nameservers []string) error {
 				mainLog.Load().Debug().Msgf("Existing forwarders content: %s", string(oldForwardersContent))
 			}
 
-			hasLocalIPv6Listener := needLocalIPv6Listener()
+			hasLocalIPv6Listener := needLocalIPv6Listener(interceptMode)
 			mainLog.Load().Debug().Bool("has_ipv6_listener", hasLocalIPv6Listener).Msg("IPv6 listener status")
 
 			forwarders := slices.DeleteFunc(slices.Clone(nameservers), func(s string) bool {

cmd/cli/prog.go

@@ -35,6 +35,7 @@ import (
 	"github.com/Control-D-Inc/ctrld/internal/controld"
 	"github.com/Control-D-Inc/ctrld/internal/dnscache"
 	"github.com/Control-D-Inc/ctrld/internal/router"
+	"github.com/Control-D-Inc/ctrld/internal/router/dnsmasq"
 )
 
 const (
@@ -130,6 +131,7 @@ type prog struct {
 	runningIface              string
 	requiredMultiNICsConfig   bool
 	adDomain                  string
+	hasLocalDNS               bool
 	runningOnDomainController bool
 
 	selfUninstallMu       sync.Mutex
@@ -144,6 +146,55 @@ type prog struct {
 	recoveryCancel   context.CancelFunc
 	recoveryRunning  atomic.Bool
 
+	// recoveryBypass is set when dns-intercept mode enters recovery.
+	// When true, proxy() forwards all queries to OS/DHCP resolver
+	// instead of using the normal upstream flow.
+	recoveryBypass atomic.Bool
+
+	// DNS intercept mode state (platform-specific).
+	// On Windows: *wfpState, on macOS: *pfState, nil on other platforms.
+	dnsInterceptState any
+
+	// lastTunnelIfaces tracks the set of active VPN/tunnel interfaces (utun*, ipsec*, etc.)
+	// discovered during the last pf anchor rule build. When the set changes (e.g., a VPN
+	// connects and creates utun420), we rebuild the pf anchor to add interface-specific
+	// intercept rules for the new interface. Protected by mu.
+	lastTunnelIfaces []string //lint:ignore U1000 used on darwin
+
+	// pfStabilizing is true while we're waiting for a VPN's pf ruleset to settle.
+	// While true, the watchdog and network change callbacks do NOT restore our rules.
+	pfStabilizing atomic.Bool
+
+	// pfStabilizeCancel cancels the active stabilization goroutine, if any.
+	// Protected by mu.
+	pfStabilizeCancel context.CancelFunc //lint:ignore U1000 used on darwin
+
+	// pfLastRestoreTime records when we last restored our anchor (unix millis).
+	// Used to detect immediate re-wipes (VPN reconnect cycle).
+	pfLastRestoreTime atomic.Int64 //lint:ignore U1000 used on darwin
+
+	// pfBackoffMultiplier tracks exponential backoff for stabilization.
+	// Resets to 0 when rules survive for >60s.
+	pfBackoffMultiplier atomic.Int32 //lint:ignore U1000 used on darwin
+
+	// pfMonitorRunning ensures only one pfInterceptMonitor goroutine runs at a time.
+	// When an interface appears/disappears, we spawn a monitor that probes pf
+	// interception with exponential backoff and auto-heals if broken.
+	pfMonitorRunning atomic.Bool //lint:ignore U1000 used on darwin
+
+	// pfProbeExpected holds the domain name of a pending pf interception probe.
+	// When non-empty, the DNS handler checks incoming queries against this value
+	// and signals pfProbeCh if matched. The probe verifies that pf's rdr rules
+	// are actually translating packets (not just present in rule text).
+	pfProbeExpected atomic.Value // string
+
+	// pfProbeCh is signaled when the DNS handler receives the expected probe query.
+	// The channel is created by probePFIntercept() and closed when the probe arrives.
+	pfProbeCh atomic.Value // *chan struct{}
+
+	// VPN DNS manager for split DNS routing when intercept mode is active.
+	vpnDNS *vpnDNSManager
+
 	started       chan struct{}
 	onStartedDone chan struct{}
 	onStarted     []func()
@@ -212,7 +263,8 @@ func (p *prog) runWait() {
 				continue
 			}
 			if cdUID != "" {
-				if rc, err := processCDFlags(newCfg); err != nil {
+				rc, err := processCDFlags(newCfg)
+				if err != nil {
 					logger.Err(err).Msg("could not fetch ControlD config")
 					waitOldRunDone()
 					continue
@@ -224,6 +276,10 @@ func (p *prog) runWait() {
 			}
 		}
 
+		// Though the log configuration could not be changed during reloading, we still need to
+		// process the current flags here, so runtime internal logs can be used correctly.
+		processLogAndCacheFlags(v, newCfg)
+
 		waitOldRunDone()
 
 		p.mu.Lock()
@@ -319,7 +375,12 @@ func (p *prog) apiConfigReload() {
 	}
 
 	doReloadApiConfig := func(forced bool, logger zerolog.Logger) {
-		resolverConfig, err := controld.FetchResolverConfig(cdUID, rootCmd.Version, cdDev)
+		req := &controld.ResolverConfigRequest{
+			RawUID:   cdUID,
+			Version:  rootCmd.Version,
+			Metadata: ctrld.SystemMetadataRuntime(context.Background()),
+		}
+		resolverConfig, err := controld.FetchResolverConfig(req, cdDev)
 		selfUninstallCheck(err, p, logger)
 		if err != nil {
 			logger.Warn().Err(err).Msg("could not fetch resolver config")
@@ -328,7 +389,7 @@ func (p *prog) apiConfigReload() {
 
 		// Performing self-upgrade check for production version.
 		if isStable {
-			selfUpgradeCheck(resolverConfig.Ctrld.VersionTarget, curVer, &logger)
+			_ = selfUpgradeCheck(resolverConfig.Ctrld.VersionTarget, curVer, &logger)
 		}
 
 		if resolverConfig.DeactivationPin != nil {
@@ -480,9 +541,13 @@ func (p *prog) run(reload bool, reloadCh chan struct{}) {
 			}
 		}
 	}
-	if domain, err := getActiveDirectoryDomain(); err == nil && domain != "" && hasLocalDnsServerRunning() {
+	if domain, err := getActiveDirectoryDomain(); err == nil && domain != "" {
 		mainLog.Load().Debug().Msgf("active directory domain: %s", domain)
 		p.adDomain = domain
+		if hasLocalDnsServerRunning() {
+			mainLog.Load().Debug().Msg("local DNS server detected (Domain Controller)")
+			p.hasLocalDNS = true
+		}
 	}
 
 	var wg sync.WaitGroup
@@ -526,7 +591,15 @@ func (p *prog) run(reload bool, reloadCh chan struct{}) {
 			defer wg.Done()
 			p.runClientInfoDiscover(ctx)
 		}()
-		go p.watchLinkState(ctx)
+	}
+
+	if !reload {
+		go func() {
+			// Start network monitoring
+			if err := p.monitorNetworkChanges(); err != nil {
+				mainLog.Load().Error().Err(err).Msg("Failed to start network monitoring")
+			}
+		}()
 	}
 
 	for listenerNum := range p.cfg.Listener {
@@ -540,7 +613,7 @@ func (p *prog) run(reload bool, reloadCh chan struct{}) {
 				}
 				addr := net.JoinHostPort(listenerConfig.IP, strconv.Itoa(listenerConfig.Port))
 				mainLog.Load().Info().Msgf("starting DNS server on listener.%s: %s", listenerNum, addr)
-				if err := p.serveDNS(ctx, listenerNum); err != nil {
+				if err := p.serveDNS(listenerNum); err != nil {
 					mainLog.Load().Fatal().Err(err).Msgf("unable to start dns proxy on listener.%s", listenerNum)
 				}
 				mainLog.Load().Debug().Msgf("end of serveDNS listener.%s: %s", listenerNum, addr)
@@ -607,6 +680,12 @@ func (p *prog) setupClientInfoDiscover(selfIP string) {
 		format := ctrld.LeaseFileFormat(p.cfg.Service.DHCPLeaseFileFormat)
 		p.ciTable.AddLeaseFile(leaseFile, format)
 	}
+	if leaseFiles := dnsmasq.AdditionalLeaseFiles(); len(leaseFiles) > 0 {
+		mainLog.Load().Debug().Msgf("watching additional lease files: %v", leaseFiles)
+		for _, leaseFile := range leaseFiles {
+			p.ciTable.AddLeaseFile(leaseFile, ctrld.Dnsmasq)
+		}
+	}
 }
 
 // runClientInfoDiscover runs the client info discover.
@@ -699,6 +778,54 @@ func (p *prog) setDNS() {
 		p.csSetDnsOk = setDnsOK
 	}()
 
+	// Validate and resolve intercept mode.
+	// CLI flag (--intercept-mode) takes priority over config file.
+	// Valid values: "" (off), "dns" (with VPN split routing), "hard" (all DNS through ctrld).
+	if interceptMode != "" && !validInterceptMode(interceptMode) {
+		mainLog.Load().Fatal().Msgf("invalid --intercept-mode value %q: must be 'off', 'dns', or 'hard'", interceptMode)
+	}
+	if interceptMode == "" || interceptMode == "off" {
+		interceptMode = cfg.Service.InterceptMode
+		if interceptMode != "" && interceptMode != "off" {
+			mainLog.Load().Info().Msgf("Intercept mode enabled via config (intercept_mode = %q)", interceptMode)
+		}
+	}
+
+	// Derive convenience bools from interceptMode.
+	switch interceptMode {
+	case "dns":
+		dnsIntercept = true
+	case "hard":
+		dnsIntercept = true
+		hardIntercept = true
+	}
+
+	// DNS intercept mode: use OS-level packet interception (WFP/pf) instead of
+	// modifying interface DNS settings. This eliminates race conditions with VPN
+	// software that also manages DNS. See issue #489.
+	if dnsIntercept {
+		if err := p.startDNSIntercept(); err != nil {
+			mainLog.Load().Error().Err(err).Msg("DNS intercept mode failed — falling back to interface DNS settings")
+			// Fall through to traditional setDNS behavior.
+		} else {
+			if hardIntercept {
+				mainLog.Load().Info().Msg("Hard intercept mode active — all DNS through ctrld, no VPN split routing")
+			} else {
+				mainLog.Load().Info().Msg("DNS intercept mode active — skipping interface DNS configuration and watchdog")
+
+				// Initialize VPN DNS manager for split DNS routing.
+				// Discovers search domains from virtual/VPN interfaces and forwards
+				// matching queries to the DNS server on that interface.
+				// Skipped in --intercept-mode hard where all DNS goes through ctrld.
+				p.vpnDNS = newVPNDNSManager(p.exemptVPNDNSServers)
+				p.vpnDNS.Refresh(true)
+			}
+
+			setDnsOK = true
+			return
+		}
+	}
+
 	if cfg.Listener == nil {
 		return
 	}
@@ -725,7 +852,7 @@ func (p *prog) setDNS() {
 	if needRFC1918Listeners(lc) {
 		nameservers = append(nameservers, ctrld.Rfc1918Addresses()...)
 	}
-	if needLocalIPv6Listener() {
+	if needLocalIPv6Listener(p.cfg.Service.InterceptMode) {
 		nameservers = append(nameservers, "::1")
 	}
 
@@ -920,7 +1047,18 @@ func (p *prog) dnsWatchdog(iface *net.Interface, nameservers []string) {
 }
 
 // resetDNS performs a DNS reset for all interfaces.
+// In DNS intercept mode, this tears down the WFP/pf filters instead.
 func (p *prog) resetDNS(isStart bool, restoreStatic bool) {
+	if dnsIntercept && p.dnsInterceptState != nil {
+		if err := p.stopDNSIntercept(); err != nil {
+			mainLog.Load().Error().Err(err).Msg("Failed to stop DNS intercept mode during reset")
+		}
+
+		// Clean up VPN DNS manager
+		p.vpnDNS = nil
+
+		return
+	}
 	netIfaceName := ""
 	if netIface := p.resetDNSForRunningIface(isStart, restoreStatic); netIface != nil {
 		netIfaceName = netIface.Name
@@ -1467,14 +1605,15 @@ func selfUninstallCheck(uninstallErr error, p *prog, logger zerolog.Logger) {
 	}
 }
 
-// selfUpgradeCheck checks if the version target vt is greater
-// than the current one cv, perform self-upgrade then.
+// shouldUpgrade checks if the version target vt is greater than the current one cv.
+// Major version upgrades are not allowed to prevent breaking changes.
 //
 // The callers must ensure curVer and logger are non-nil.
-func selfUpgradeCheck(vt string, cv *semver.Version, logger *zerolog.Logger) {
+// Returns true if upgrade is allowed, false otherwise.
+func shouldUpgrade(vt string, cv *semver.Version, logger *zerolog.Logger) bool {
 	if vt == "" {
 		logger.Debug().Msg("no version target set, skipped checking self-upgrade")
-		return
+		return false
 	}
 	vts := vt
 	if !strings.HasPrefix(vts, "v") {
@@ -1483,28 +1622,58 @@ func selfUpgradeCheck(vt string, cv *semver.Version, logger *zerolog.Logger) {
 	targetVer, err := semver.NewVersion(vts)
 	if err != nil {
 		logger.Warn().Err(err).Msgf("invalid target version, skipped self-upgrade: %s", vt)
-		return
+		return false
 	}
+
+	// Prevent major version upgrades to avoid breaking changes
+	if targetVer.Major() != cv.Major() {
+		logger.Warn().
+			Str("target", vt).
+			Str("current", cv.String()).
+			Msgf("major version upgrade not allowed (target: %d, current: %d), skipped self-upgrade", targetVer.Major(), cv.Major())
+		return false
+	}
+
 	if !targetVer.GreaterThan(cv) {
 		logger.Debug().
 			Str("target", vt).
 			Str("current", cv.String()).
 			Msgf("target version is not greater than current one, skipped self-upgrade")
-		return
+		return false
 	}
 
+	return true
+}
+
+// performUpgrade executes the self-upgrade command.
+// Returns true if upgrade was initiated successfully, false otherwise.
+func performUpgrade(vt string) bool {
 	exe, err := os.Executable()
 	if err != nil {
 		mainLog.Load().Error().Err(err).Msg("failed to get executable path, skipped self-upgrade")
-		return
+		return false
 	}
 	cmd := exec.Command(exe, "upgrade", "prod", "-vv")
 	cmd.SysProcAttr = sysProcAttrForDetachedChildProcess()
 	if err := cmd.Start(); err != nil {
 		mainLog.Load().Error().Err(err).Msg("failed to start self-upgrade")
-		return
+		return false
 	}
-	mainLog.Load().Debug().Msgf("self-upgrade triggered, version target: %s", vts)
+	mainLog.Load().Debug().Msgf("self-upgrade triggered, version target: %s", vt)
+	return true
+}
+
+// selfUpgradeCheck checks if the version target vt is greater
+// than the current one cv, perform self-upgrade then.
+// Major version upgrades are not allowed to prevent breaking changes.
+//
+// The callers must ensure curVer and logger are non-nil.
+// Returns true if upgrade is allowed and should proceed, false otherwise.
+func selfUpgradeCheck(vt string, cv *semver.Version, logger *zerolog.Logger) bool {
+	if shouldUpgrade(vt, cv, logger) {
+		return performUpgrade(vt)
+	}
+	return false
 }
 
 // leakOnUpstreamFailure reports whether ctrld should initiate a recovery flow

cmd/cli/prog_linux.go

@@ -14,9 +14,6 @@ import (
 )
 
 func init() {
-	if isAndroid() {
-		return
-	}
 	if r, err := newLoopbackOSConfigurator(); err == nil {
 		useSystemdResolved = r.Mode() == "systemd-resolved"
 	}

cmd/cli/prog_test.go

@@ -1,11 +1,15 @@
 package cli
 
 import (
+	"runtime"
 	"testing"
 	"time"
 
-	"github.com/Control-D-Inc/ctrld"
+	"github.com/Masterminds/semver/v3"
+	"github.com/rs/zerolog"
 	"github.com/stretchr/testify/assert"
+
+	"github.com/Control-D-Inc/ctrld"
 )
 
 func Test_prog_dnsWatchdogEnabled(t *testing.T) {
@@ -55,3 +59,215 @@ func Test_prog_dnsWatchdogInterval(t *testing.T) {
 		})
 	}
 }
+
+func Test_shouldUpgrade(t *testing.T) {
+	// Helper function to create a version
+	makeVersion := func(v string) *semver.Version {
+		ver, err := semver.NewVersion(v)
+		if err != nil {
+			t.Fatalf("failed to create version %s: %v", v, err)
+		}
+		return ver
+	}
+
+	tests := []struct {
+		name           string
+		versionTarget  string
+		currentVersion *semver.Version
+		shouldUpgrade  bool
+		description    string
+	}{
+		{
+			name:           "empty version target",
+			versionTarget:  "",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when version target is empty",
+		},
+		{
+			name:           "invalid version target",
+			versionTarget:  "invalid-version",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when version target is invalid",
+		},
+		{
+			name:           "same version",
+			versionTarget:  "v1.0.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when target version equals current version",
+		},
+		{
+			name:           "older version",
+			versionTarget:  "v1.0.0",
+			currentVersion: makeVersion("v1.1.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when target version is older than current version",
+		},
+		{
+			name:           "patch upgrade allowed",
+			versionTarget:  "v1.0.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow patch version upgrade within same major version",
+		},
+		{
+			name:           "minor upgrade allowed",
+			versionTarget:  "v1.1.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow minor version upgrade within same major version",
+		},
+		{
+			name:           "major upgrade blocked",
+			versionTarget:  "v2.0.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block major version upgrade",
+		},
+		{
+			name:           "major downgrade blocked",
+			versionTarget:  "v1.0.0",
+			currentVersion: makeVersion("v2.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block major version downgrade",
+		},
+		{
+			name:           "version without v prefix",
+			versionTarget:  "1.0.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should handle version target without v prefix",
+		},
+		{
+			name:           "complex version upgrade allowed",
+			versionTarget:  "v1.5.3",
+			currentVersion: makeVersion("v1.4.2"),
+			shouldUpgrade:  true,
+			description:    "should allow complex version upgrade within same major version",
+		},
+		{
+			name:           "complex major upgrade blocked",
+			versionTarget:  "v3.1.0",
+			currentVersion: makeVersion("v2.5.3"),
+			shouldUpgrade:  false,
+			description:    "should block complex major version upgrade",
+		},
+		{
+			name:           "pre-release version upgrade allowed",
+			versionTarget:  "v1.0.1-beta.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow pre-release version upgrade within same major version",
+		},
+		{
+			name:           "pre-release major upgrade blocked",
+			versionTarget:  "v2.0.0-alpha.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block pre-release major version upgrade",
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			// Create test logger
+			testLogger := zerolog.New(zerolog.NewTestWriter(t)).With().Logger()
+
+			// Call the function and capture the result
+			result := shouldUpgrade(tc.versionTarget, tc.currentVersion, &testLogger)
+
+			// Assert the expected result
+			assert.Equal(t, tc.shouldUpgrade, result, tc.description)
+		})
+	}
+}
+
+func Test_selfUpgradeCheck(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("skipped due to Windows file locking issue on Github Action runners")
+	}
+
+	// Helper function to create a version
+	makeVersion := func(v string) *semver.Version {
+		ver, err := semver.NewVersion(v)
+		if err != nil {
+			t.Fatalf("failed to create version %s: %v", v, err)
+		}
+		return ver
+	}
+
+	tests := []struct {
+		name           string
+		versionTarget  string
+		currentVersion *semver.Version
+		shouldUpgrade  bool
+		description    string
+	}{
+		{
+			name:           "upgrade allowed",
+			versionTarget:  "v1.0.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow upgrade and attempt to perform it",
+		},
+		{
+			name:           "upgrade blocked",
+			versionTarget:  "v2.0.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block upgrade and not attempt to perform it",
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			// Create test logger
+			testLogger := zerolog.New(zerolog.NewTestWriter(t)).With().Logger()
+
+			// Call the function and capture the result
+			result := selfUpgradeCheck(tc.versionTarget, tc.currentVersion, &testLogger)
+
+			// Assert the expected result
+			assert.Equal(t, tc.shouldUpgrade, result, tc.description)
+		})
+	}
+}
+
+func Test_performUpgrade(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("skipped due to Windows file locking issue on Github Action runners")
+	}
+
+	tests := []struct {
+		name           string
+		versionTarget  string
+		expectedResult bool
+		description    string
+	}{
+		{
+			name:           "valid version target",
+			versionTarget:  "v1.0.1",
+			expectedResult: true,
+			description:    "should attempt to perform upgrade with valid version target",
+		},
+		{
+			name:           "empty version target",
+			versionTarget:  "",
+			expectedResult: true,
+			description:    "should attempt to perform upgrade even with empty version target",
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			// Call the function and capture the result
+			result := performUpgrade(tc.versionTarget)
+			assert.Equal(t, tc.expectedResult, result, tc.description)
+		})
+	}
+}

cmd/cli/service_args_darwin.go

@@ -0,0 +1,134 @@
+//go:build darwin
+
+package cli
+
+import (
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+)
+
+const launchdPlistPath = "/Library/LaunchDaemons/ctrld.plist"
+
+// serviceConfigFileExists returns true if the launchd plist for ctrld exists on disk.
+// This is more reliable than checking launchctl status, which may report "not found"
+// if the service was unloaded but the plist file still exists.
+func serviceConfigFileExists() bool {
+	_, err := os.Stat(launchdPlistPath)
+	return err == nil
+}
+
+// appendServiceFlag appends a CLI flag (e.g., "--intercept-mode") to the installed
+// service's launch arguments. This is used when upgrading an existing installation
+// to intercept mode without losing the existing --cd flag and other arguments.
+//
+// On macOS, this modifies the launchd plist at /Library/LaunchDaemons/ctrld.plist
+// using the "defaults" command, which is the standard way to edit plists.
+//
+// The function is idempotent: if the flag already exists, it's a no-op.
+func appendServiceFlag(flag string) error {
+	// Read current ProgramArguments from plist.
+	out, err := exec.Command("defaults", "read", launchdPlistPath, "ProgramArguments").CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("failed to read plist ProgramArguments: %w (output: %s)", err, strings.TrimSpace(string(out)))
+	}
+
+	// Check if the flag is already present (idempotent).
+	args := string(out)
+	if strings.Contains(args, flag) {
+		mainLog.Load().Debug().Msgf("Service flag %q already present in plist, skipping", flag)
+		return nil
+	}
+
+	// Use PlistBuddy to append the flag to ProgramArguments array.
+	// PlistBuddy is more reliable than "defaults" for array manipulation.
+	addCmd := exec.Command(
+		"/usr/libexec/PlistBuddy",
+		"-c", fmt.Sprintf("Add :ProgramArguments: string %s", flag),
+		launchdPlistPath,
+	)
+	if out, err := addCmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("failed to append %q to plist ProgramArguments: %w (output: %s)", flag, err, strings.TrimSpace(string(out)))
+	}
+
+	mainLog.Load().Info().Msgf("Appended %q to service launch arguments", flag)
+	return nil
+}
+
+// verifyServiceRegistration is a no-op on macOS (launchd plist verification not needed).
+func verifyServiceRegistration() error {
+	return nil
+}
+
+// removeServiceFlag removes a CLI flag (and its value, if the next argument is not
+// a flag) from the installed service's launch arguments. For example, removing
+// "--intercept-mode" also removes the following "dns" or "hard" value argument.
+//
+// The function is idempotent: if the flag doesn't exist, it's a no-op.
+func removeServiceFlag(flag string) error {
+	// Read current ProgramArguments to find the index.
+	out, err := exec.Command("/usr/libexec/PlistBuddy", "-c", "Print :ProgramArguments", launchdPlistPath).CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("failed to read plist ProgramArguments: %w (output: %s)", err, strings.TrimSpace(string(out)))
+	}
+
+	// Parse the PlistBuddy output to find the flag's index.
+	// PlistBuddy prints arrays as:
+	//   Array {
+	//       /path/to/ctrld
+	//       run
+	//       --cd=xxx
+	//       --intercept-mode
+	//       dns
+	//   }
+	lines := strings.Split(string(out), "\n")
+	var entries []string
+	for _, line := range lines {
+		trimmed := strings.TrimSpace(line)
+		if trimmed == "Array {" || trimmed == "}" || trimmed == "" {
+			continue
+		}
+		entries = append(entries, trimmed)
+	}
+
+	index := -1
+	for i, entry := range entries {
+		if entry == flag {
+			index = i
+			break
+		}
+	}
+
+	if index < 0 {
+		mainLog.Load().Debug().Msgf("Service flag %q not present in plist, skipping removal", flag)
+		return nil
+	}
+
+	// Check if the next entry is a value (not a flag). If so, delete it first
+	// (deleting by index shifts subsequent entries down, so delete value before flag).
+	hasValue := index+1 < len(entries) && !strings.HasPrefix(entries[index+1], "-")
+	if hasValue {
+		delVal := exec.Command(
+			"/usr/libexec/PlistBuddy",
+			"-c", fmt.Sprintf("Delete :ProgramArguments:%d", index+1),
+			launchdPlistPath,
+		)
+		if out, err := delVal.CombinedOutput(); err != nil {
+			return fmt.Errorf("failed to remove value for %q from plist: %w (output: %s)", flag, err, strings.TrimSpace(string(out)))
+		}
+	}
+
+	// Delete the flag itself.
+	delCmd := exec.Command(
+		"/usr/libexec/PlistBuddy",
+		"-c", fmt.Sprintf("Delete :ProgramArguments:%d", index),
+		launchdPlistPath,
+	)
+	if out, err := delCmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("failed to remove %q from plist ProgramArguments: %w (output: %s)", flag, err, strings.TrimSpace(string(out)))
+	}
+
+	mainLog.Load().Info().Msgf("Removed %q from service launch arguments", flag)
+	return nil
+}

cmd/cli/service_args_others.go

@@ -0,0 +1,38 @@
+//go:build !darwin && !windows
+
+package cli
+
+import (
+	"fmt"
+	"os"
+)
+
+// serviceConfigFileExists checks common service config file locations on Linux.
+func serviceConfigFileExists() bool {
+	// systemd unit file
+	if _, err := os.Stat("/etc/systemd/system/ctrld.service"); err == nil {
+		return true
+	}
+	// SysV init script
+	if _, err := os.Stat("/etc/init.d/ctrld"); err == nil {
+		return true
+	}
+	return false
+}
+
+// appendServiceFlag is not yet implemented on this platform.
+// Linux services (systemd) store args in unit files; intercept mode
+// should be set via the config file (intercept_mode) on these platforms.
+func appendServiceFlag(flag string) error {
+	return fmt.Errorf("appending service flags is not supported on this platform; use intercept_mode in config instead")
+}
+
+// verifyServiceRegistration is a no-op on this platform.
+func verifyServiceRegistration() error {
+	return nil
+}
+
+// removeServiceFlag is not yet implemented on this platform.
+func removeServiceFlag(flag string) error {
+	return fmt.Errorf("removing service flags is not supported on this platform; use intercept_mode in config instead")
+}

cmd/cli/service_args_windows.go

@@ -0,0 +1,153 @@
+//go:build windows
+
+package cli
+
+import (
+	"fmt"
+	"strings"
+
+	"golang.org/x/sys/windows/svc/mgr"
+)
+
+// serviceConfigFileExists returns true if the ctrld Windows service is registered.
+func serviceConfigFileExists() bool {
+	m, err := mgr.Connect()
+	if err != nil {
+		return false
+	}
+	defer m.Disconnect()
+	s, err := m.OpenService(ctrldServiceName)
+	if err != nil {
+		return false
+	}
+	s.Close()
+	return true
+}
+
+// appendServiceFlag appends a CLI flag (e.g., "--intercept-mode") to the installed
+// Windows service's BinPath arguments. This is used when upgrading an existing
+// installation to intercept mode without losing the existing --cd flag.
+//
+// The function is idempotent: if the flag already exists, it's a no-op.
+func appendServiceFlag(flag string) error {
+	m, err := mgr.Connect()
+	if err != nil {
+		return fmt.Errorf("failed to connect to Windows SCM: %w", err)
+	}
+	defer m.Disconnect()
+
+	s, err := m.OpenService(ctrldServiceName)
+	if err != nil {
+		return fmt.Errorf("failed to open service %q: %w", ctrldServiceName, err)
+	}
+	defer s.Close()
+
+	config, err := s.Config()
+	if err != nil {
+		return fmt.Errorf("failed to read service config: %w", err)
+	}
+
+	// Check if flag already present (idempotent).
+	if strings.Contains(config.BinaryPathName, flag) {
+		mainLog.Load().Debug().Msgf("Service flag %q already present in BinPath, skipping", flag)
+		return nil
+	}
+
+	// Append the flag to BinPath.
+	config.BinaryPathName = strings.TrimSpace(config.BinaryPathName) + " " + flag
+
+	if err := s.UpdateConfig(config); err != nil {
+		return fmt.Errorf("failed to update service config with %q: %w", flag, err)
+	}
+
+	mainLog.Load().Info().Msgf("Appended %q to service BinPath", flag)
+	return nil
+}
+
+// verifyServiceRegistration opens the Windows Service Control Manager and verifies
+// that the ctrld service is correctly registered: logs the BinaryPathName, checks
+// that --intercept-mode is present if expected, and verifies SERVICE_AUTO_START.
+func verifyServiceRegistration() error {
+	m, err := mgr.Connect()
+	if err != nil {
+		return fmt.Errorf("failed to connect to Windows SCM: %w", err)
+	}
+	defer m.Disconnect()
+
+	s, err := m.OpenService(ctrldServiceName)
+	if err != nil {
+		return fmt.Errorf("failed to open service %q: %w", ctrldServiceName, err)
+	}
+	defer s.Close()
+
+	config, err := s.Config()
+	if err != nil {
+		return fmt.Errorf("failed to read service config: %w", err)
+	}
+
+	mainLog.Load().Debug().Msgf("Service registry: BinaryPathName = %q", config.BinaryPathName)
+
+	// If intercept mode is set, verify the flag is present in BinPath.
+	if interceptMode == "dns" || interceptMode == "hard" {
+		if !strings.Contains(config.BinaryPathName, "--intercept-mode") {
+			return fmt.Errorf("service registry: --intercept-mode flag missing from BinaryPathName (expected mode %q)", interceptMode)
+		}
+		mainLog.Load().Debug().Msgf("Service registry: --intercept-mode flag present in BinaryPathName")
+	}
+
+	// Verify auto-start. mgr.StartAutomatic == 2 == SERVICE_AUTO_START.
+	if config.StartType != mgr.StartAutomatic {
+		return fmt.Errorf("service registry: StartType is %d, expected SERVICE_AUTO_START (%d)", config.StartType, mgr.StartAutomatic)
+	}
+
+	return nil
+}
+
+// removeServiceFlag removes a CLI flag (and its value, if present) from the installed
+// Windows service's BinPath. For example, removing "--intercept-mode" also removes
+// the following "dns" or "hard" value. The function is idempotent.
+func removeServiceFlag(flag string) error {
+	m, err := mgr.Connect()
+	if err != nil {
+		return fmt.Errorf("failed to connect to Windows SCM: %w", err)
+	}
+	defer m.Disconnect()
+
+	s, err := m.OpenService(ctrldServiceName)
+	if err != nil {
+		return fmt.Errorf("failed to open service %q: %w", ctrldServiceName, err)
+	}
+	defer s.Close()
+
+	config, err := s.Config()
+	if err != nil {
+		return fmt.Errorf("failed to read service config: %w", err)
+	}
+
+	if !strings.Contains(config.BinaryPathName, flag) {
+		mainLog.Load().Debug().Msgf("Service flag %q not present in BinPath, skipping removal", flag)
+		return nil
+	}
+
+	// Split BinPath into parts, find and remove the flag + its value (if any).
+	parts := strings.Fields(config.BinaryPathName)
+	var newParts []string
+	for i := 0; i < len(parts); i++ {
+		if parts[i] == flag {
+			// Skip the flag. Also skip the next part if it's a value (not a flag).
+			if i+1 < len(parts) && !strings.HasPrefix(parts[i+1], "-") {
+				i++ // skip value too
+			}
+			continue
+		}
+		newParts = append(newParts, parts[i])
+	}
+	config.BinaryPathName = strings.Join(newParts, " ")
+
+	if err := s.UpdateConfig(config); err != nil {
+		return fmt.Errorf("failed to update service config: %w", err)
+	}
+
+	mainLog.Load().Info().Msgf("Removed %q from service BinPath", flag)
+	return nil
+}

cmd/cli/vpn_dns.go

@@ -0,0 +1,255 @@
+package cli
+
+import (
+	"context"
+	"strings"
+	"sync"
+
+	"tailscale.com/net/netmon"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// vpnDNSExemption represents a VPN DNS server that needs pf/WFP exemption,
+// including the interface it was discovered on. The interface is used on macOS
+// to create interface-scoped pf exemptions that allow the VPN's local DNS
+// handler (e.g., Tailscale's MagicDNS Network Extension) to receive queries
+// from all processes — not just ctrld.
+type vpnDNSExemption struct {
+	Server     string // DNS server IP (e.g., "100.100.100.100")
+	Interface  string // Interface name from scutil (e.g., "utun11"), may be empty
+	IsExitMode bool   // True if this VPN is in exit/full-tunnel mode (all traffic routed through VPN)
+}
+
+// vpnDNSExemptFunc is called when VPN DNS servers change, to update
+// the intercept layer (WFP/pf) to permit VPN DNS traffic.
+type vpnDNSExemptFunc func(exemptions []vpnDNSExemption) error
+
+// vpnDNSManager tracks active VPN DNS configurations and provides
+// domain-to-upstream routing for VPN split DNS.
+type vpnDNSManager struct {
+	mu      sync.RWMutex
+	configs []ctrld.VPNDNSConfig
+	// Map of domain suffix → DNS servers for fast lookup
+	routes map[string][]string
+	// DNS servers from VPN interfaces that have no domain/suffix config.
+	// These are NOT added to the global OS resolver. They're only used
+	// as additional nameservers for queries that match split-DNS rules
+	// (from ctrld config, AD domain, or VPN suffix config).
+	domainlessServers []string
+	// Called when VPN DNS server list changes, to update intercept exemptions.
+	onServersChanged vpnDNSExemptFunc
+}
+
+// newVPNDNSManager creates a new manager. Only call when dnsIntercept is active.
+// exemptFunc is called whenever VPN DNS servers are discovered/changed, to update
+// the OS-level intercept rules to permit ctrld's outbound queries to those IPs.
+func newVPNDNSManager(exemptFunc vpnDNSExemptFunc) *vpnDNSManager {
+	return &vpnDNSManager{
+		routes:           make(map[string][]string),
+		onServersChanged: exemptFunc,
+	}
+}
+
+// Refresh re-discovers VPN DNS configs from the OS.
+// Called on network change events.
+func (m *vpnDNSManager) Refresh(guardAgainstNoNameservers bool) {
+	logger := mainLog.Load()
+
+	logger.Debug().Msg("Refreshing VPN DNS configurations")
+	configs := ctrld.DiscoverVPNDNS(context.Background())
+
+	// Detect exit mode: if the default route goes through a VPN DNS interface,
+	// the VPN is routing ALL traffic (exit node / full tunnel). This is more
+	// reliable than scutil flag parsing because the routing table is the ground
+	// truth for traffic flow, regardless of how the VPN presents itself in scutil.
+	if dri, err := netmon.DefaultRouteInterface(); err == nil && dri != "" {
+		for i := range configs {
+			if configs[i].InterfaceName == dri {
+				if !configs[i].IsExitMode {
+					logger.Info().Msgf("VPN DNS on %s: default route interface match — EXIT MODE (route-based detection)", dri)
+				}
+				configs[i].IsExitMode = true
+			}
+		}
+	}
+
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	m.configs = configs
+	m.routes = make(map[string][]string)
+
+	// Build domain -> DNS servers mapping
+	for _, config := range configs {
+		logger.Debug().Msgf("Processing VPN interface %s with %d domains and %d servers",
+			config.InterfaceName, len(config.Domains), len(config.Servers))
+
+		for _, domain := range config.Domains {
+			// Normalize domain: remove leading dot, Linux routing domain prefix (~),
+			// and convert to lowercase.
+			domain = strings.TrimPrefix(domain, "~")
+			domain = strings.TrimPrefix(domain, ".")
+			domain = strings.ToLower(domain)
+
+			if domain != "" {
+				m.routes[domain] = append([]string{}, config.Servers...)
+				logger.Debug().Msgf("Added VPN DNS route: %s -> %v", domain, config.Servers)
+			}
+		}
+	}
+
+	// Collect unique VPN DNS exemptions (server + interface) for pf/WFP rules.
+	type exemptionKey struct{ server, iface string }
+	seen := make(map[exemptionKey]bool)
+	var exemptions []vpnDNSExemption
+	for _, config := range configs {
+		for _, server := range config.Servers {
+			key := exemptionKey{server, config.InterfaceName}
+			if !seen[key] {
+				seen[key] = true
+				exemptions = append(exemptions, vpnDNSExemption{
+					Server:     server,
+					Interface:  config.InterfaceName,
+					IsExitMode: config.IsExitMode,
+				})
+			}
+		}
+	}
+
+	// Collect domain-less VPN DNS servers. These are NOT added to the global
+	// OS resolver (that would pollute captive portal / DHCP flows). Instead,
+	// they're stored separately and only used for queries that match existing
+	// split-DNS rules (from ctrld config, AD domain, or VPN suffix config).
+	var domainlessServers []string
+	seen2 := make(map[string]bool)
+	for _, config := range configs {
+		if len(config.Domains) == 0 && len(config.Servers) > 0 {
+			logger.Debug().Msgf("VPN interface %s has DNS servers but no domains, storing as split-rule fallback: %v",
+				config.InterfaceName, config.Servers)
+			for _, s := range config.Servers {
+				if !seen2[s] {
+					seen2[s] = true
+					domainlessServers = append(domainlessServers, s)
+				}
+			}
+		}
+	}
+	m.domainlessServers = domainlessServers
+
+	logger.Debug().Msgf("VPN DNS refresh completed: %d configs, %d routes, %d domainless servers, %d unique exemptions",
+		len(m.configs), len(m.routes), len(m.domainlessServers), len(exemptions))
+
+	// Update intercept rules to permit VPN DNS traffic.
+	// Always call onServersChanged — including when exemptions is empty — so that
+	// stale exemptions from a previous VPN session get cleared on disconnect.
+	if m.onServersChanged != nil {
+		if err := m.onServersChanged(exemptions); err != nil {
+			logger.Error().Err(err).Msg("Failed to update intercept exemptions for VPN DNS servers")
+		}
+	}
+}
+
+// UpstreamForDomain checks if the domain matches any VPN search domain.
+// Returns VPN DNS servers if matched, nil otherwise.
+func (m *vpnDNSManager) UpstreamForDomain(domain string) []string {
+	if domain == "" {
+		return nil
+	}
+
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+
+	domain = strings.TrimSuffix(domain, ".")
+	domain = strings.ToLower(domain)
+
+	if servers, ok := m.routes[domain]; ok {
+		return append([]string{}, servers...)
+	}
+
+	for vpnDomain, servers := range m.routes {
+		if strings.HasSuffix(domain, "."+vpnDomain) {
+			return append([]string{}, servers...)
+		}
+	}
+
+	return nil
+}
+
+// DomainlessServers returns VPN DNS servers that have no associated domains.
+// These should only be used for queries matching split-DNS rules, not for
+// general OS resolver queries (to avoid polluting captive portal / DHCP flows).
+func (m *vpnDNSManager) DomainlessServers() []string {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+	return append([]string{}, m.domainlessServers...)
+}
+
+// CurrentServers returns the current set of unique VPN DNS server IPs.
+func (m *vpnDNSManager) CurrentServers() []string {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+
+	seen := make(map[string]bool)
+	var servers []string
+	for _, ss := range m.routes {
+		for _, s := range ss {
+			if !seen[s] {
+				seen[s] = true
+				servers = append(servers, s)
+			}
+		}
+	}
+	return servers
+}
+
+// CurrentExemptions returns VPN DNS server + interface pairs for pf exemption rules.
+func (m *vpnDNSManager) CurrentExemptions() []vpnDNSExemption {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+
+	type key struct{ server, iface string }
+	seen := make(map[key]bool)
+	var exemptions []vpnDNSExemption
+	for _, config := range m.configs {
+		for _, server := range config.Servers {
+			k := key{server, config.InterfaceName}
+			if !seen[k] {
+				seen[k] = true
+				exemptions = append(exemptions, vpnDNSExemption{
+					Server:     server,
+					Interface:  config.InterfaceName,
+					IsExitMode: config.IsExitMode,
+				})
+			}
+		}
+	}
+	return exemptions
+}
+
+// Routes returns a copy of the current VPN DNS routes for debugging.
+func (m *vpnDNSManager) Routes() map[string][]string {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+
+	routes := make(map[string][]string)
+	for domain, servers := range m.routes {
+		routes[domain] = append([]string{}, servers...)
+	}
+	return routes
+}
+
+// upstreamConfigFor creates a legacy upstream configuration for the given VPN DNS server.
+func (m *vpnDNSManager) upstreamConfigFor(server string) *ctrld.UpstreamConfig {
+	endpoint := server
+	if !strings.Contains(server, ":") {
+		endpoint = server + ":53"
+	}
+
+	return &ctrld.UpstreamConfig{
+		Name:     "VPN DNS",
+		Type:     ctrld.ResolverTypeLegacy,
+		Endpoint: endpoint,
+		Timeout:  2000,
+	}
+}

cmd/ctrld_library/main.go

@@ -28,15 +28,17 @@ type AppCallback interface {
 // Start configures utility with config.toml from provided directory.
 // This function will block until Stop is called
 // Check port availability prior to calling it.
-func (c *Controller) Start(CdUID string, HomeDir string, UpstreamProto string, logLevel int, logPath string) {
+func (c *Controller) Start(CdUID string, ProvisionID string, CustomHostname string, HomeDir string, UpstreamProto string, logLevel int, logPath string) {
 	if c.stopCh == nil {
 		c.stopCh = make(chan struct{})
 		c.Config = cli.AppConfig{
-			CdUID:         CdUID,
-			HomeDir:       HomeDir,
-			UpstreamProto: UpstreamProto,
-			Verbose:       logLevel,
-			LogPath:       logPath,
+			CdUID:          CdUID,
+			ProvisionID:    ProvisionID,
+			CustomHostname: CustomHostname,
+			HomeDir:        HomeDir,
+			UpstreamProto:  UpstreamProto,
+			Verbose:        logLevel,
+			LogPath:        logPath,
 		}
 		appCallback := mapCallback(c.AppCallback)
 		cli.RunMobile(&c.Config, &appCallback, c.stopCh)

config.go

@@ -9,7 +9,6 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"math/rand"
 	"net"
 	"net/http"
 	"net/netip"
@@ -83,6 +82,10 @@ const (
 	endpointPrefixQUIC  = "quic://"
 	endpointPrefixH3    = "h3://"
 	endpointPrefixSdns  = "sdns://"
+
+	rebootstrapNotStarted = 0
+	rebootstrapStarted    = 1
+	rebootstrapInProgress = 2
 )
 
 var (
@@ -237,6 +240,7 @@ type ServiceConfig struct {
 	RefetchTime             *int           `mapstructure:"refetch_time" toml:"refetch_time,omitempty"`
 	ForceRefetchWaitTime    *int           `mapstructure:"force_refetch_wait_time" toml:"force_refetch_wait_time,omitempty"`
 	LeakOnUpstreamFailure   *bool          `mapstructure:"leak_on_upstream_failure" toml:"leak_on_upstream_failure,omitempty"`
+	InterceptMode           string         `mapstructure:"intercept_mode" toml:"intercept_mode,omitempty" validate:"omitempty,oneof=off dns hard"`
 	Daemon                  bool           `mapstructure:"-" toml:"-"`
 	AllocateIP              bool           `mapstructure:"-" toml:"-"`
 }
@@ -265,7 +269,7 @@ type UpstreamConfig struct {
 	Discoverable *bool `mapstructure:"discoverable" toml:"discoverable"`
 
 	g                  singleflight.Group
-	rebootstrap        atomic.Bool
+	rebootstrap        atomic.Int64
 	bootstrapIPs       []string
 	bootstrapIPs4      []string
 	bootstrapIPs6      []string
@@ -276,6 +280,12 @@ type UpstreamConfig struct {
 	http3RoundTripper  http.RoundTripper
 	http3RoundTripper4 http.RoundTripper
 	http3RoundTripper6 http.RoundTripper
+	doqConnPool        *doqConnPool
+	doqConnPool4       *doqConnPool
+	doqConnPool6       *doqConnPool
+	dotClientPool      *dotConnPool
+	dotClientPool4     *dotConnPool
+	dotClientPool6     *dotConnPool
 	certPool           *x509.CertPool
 	u                  *url.URL
 	fallbackOnce       sync.Once
@@ -358,6 +368,15 @@ func (uc *UpstreamConfig) Init() {
 	}
 }
 
+// VerifyMsg creates and returns a new DNS message could be used for testing upstream health.
+func (uc *UpstreamConfig) VerifyMsg() *dns.Msg {
+	msg := new(dns.Msg)
+	msg.RecursionDesired = true
+	msg.SetQuestion(".", dns.TypeNS)
+	msg.SetEdns0(4096, false) // ensure handling of large DNS response
+	return msg
+}
+
 // VerifyDomain returns the domain name that could be resolved by the upstream endpoint.
 // It returns empty for non-ControlD upstream endpoint.
 func (uc *UpstreamConfig) VerifyDomain() string {
@@ -481,49 +500,141 @@ func (uc *UpstreamConfig) SetupBootstrapIP() {
 // ReBootstrap re-setup the bootstrap IP and the transport.
 func (uc *UpstreamConfig) ReBootstrap() {
 	switch uc.Type {
-	case ResolverTypeDOH, ResolverTypeDOH3:
+	case ResolverTypeDOH, ResolverTypeDOH3, ResolverTypeDOQ, ResolverTypeDOT:
 	default:
 		return
 	}
 	_, _, _ = uc.g.Do("ReBootstrap", func() (any, error) {
-		if uc.rebootstrap.CompareAndSwap(false, true) {
+		if uc.rebootstrap.CompareAndSwap(rebootstrapNotStarted, rebootstrapStarted) {
 			ProxyLogger.Load().Debug().Msgf("re-bootstrapping upstream ip for %v", uc)
 		}
 		return true, nil
 	})
 }
 
-// SetupTransport initializes the network transport used to connect to upstream server.
-// For now, only DoH upstream is supported.
-func (uc *UpstreamConfig) SetupTransport() {
+// ForceReBootstrap immediately replaces the upstream transport, closing old
+// connections and creating new ones synchronously. Unlike ReBootstrap() which
+// sets a lazy flag (new transport created on next query), this ensures the
+// transport is ready before any queries arrive. Use when external events
+// (e.g. firewall state flush) are known to have killed existing connections.
+func (uc *UpstreamConfig) ForceReBootstrap() {
 	switch uc.Type {
-	case ResolverTypeDOH:
-		uc.setupDOHTransport()
-	case ResolverTypeDOH3:
-		uc.setupDOH3Transport()
+	case ResolverTypeDOH, ResolverTypeDOH3, ResolverTypeDOQ, ResolverTypeDOT:
+	default:
+		return
+	}
+	ProxyLogger.Load().Debug().Msgf("force re-bootstrapping upstream transport for %v", uc)
+	uc.SetupTransport()
+	// Clear any pending lazy re-bootstrap flag so ensureSetupTransport()
+	// doesn't redundantly recreate the transport we just built.
+	uc.rebootstrap.Store(rebootstrapNotStarted)
+}
+
+// closeTransports closes idle connections on all existing transports.
+// This is called before creating new transports during re-bootstrap to
+// force in-flight requests on stale connections to fail quickly, rather
+// than waiting for the full context deadline (e.g. 5s) after a firewall
+// state table flush kills the underlying TCP/QUIC connections.
+func (uc *UpstreamConfig) closeTransports() {
+	if t := uc.transport; t != nil {
+		t.CloseIdleConnections()
+	}
+	if t := uc.transport4; t != nil {
+		t.CloseIdleConnections()
+	}
+	if t := uc.transport6; t != nil {
+		t.CloseIdleConnections()
+	}
+	if p := uc.doqConnPool; p != nil {
+		p.CloseIdleConnections()
+	}
+	if p := uc.doqConnPool4; p != nil {
+		p.CloseIdleConnections()
+	}
+	if p := uc.doqConnPool6; p != nil {
+		p.CloseIdleConnections()
+	}
+	if p := uc.dotClientPool; p != nil {
+		p.CloseIdleConnections()
+	}
+	if p := uc.dotClientPool4; p != nil {
+		p.CloseIdleConnections()
+	}
+	if p := uc.dotClientPool6; p != nil {
+		p.CloseIdleConnections()
+	}
+	// http3RoundTripper is stored as http.RoundTripper but the concrete type
+	// (*http3.Transport) exposes CloseIdleConnections via this interface.
+	type idleCloser interface {
+		CloseIdleConnections()
+	}
+	for _, rt := range []http.RoundTripper{uc.http3RoundTripper, uc.http3RoundTripper4, uc.http3RoundTripper6} {
+		if c, ok := rt.(idleCloser); ok {
+			c.CloseIdleConnections()
+		}
 	}
 }
 
-func (uc *UpstreamConfig) setupDOHTransport() {
+// SetupTransport initializes the network transport used to connect to upstream servers.
+// For now, DoH/DoH3/DoQ/DoT upstreams are supported.
+func (uc *UpstreamConfig) SetupTransport() {
+	switch uc.Type {
+	case ResolverTypeDOH, ResolverTypeDOH3, ResolverTypeDOQ, ResolverTypeDOT:
+	default:
+		return
+	}
+
+	// Close existing transport connections before creating new ones.
+	// This forces in-flight requests on stale connections (e.g. after a
+	// firewall state table flush) to fail fast instead of waiting for
+	// the full context deadline timeout.
+	uc.closeTransports()
+
+	ips := uc.bootstrapIPs
 	switch uc.IPStack {
-	case IpStackBoth, "":
-		uc.transport = uc.newDOHTransport(uc.bootstrapIPs)
 	case IpStackV4:
-		uc.transport = uc.newDOHTransport(uc.bootstrapIPs4)
+		ips = uc.bootstrapIPs4
 	case IpStackV6:
-		uc.transport = uc.newDOHTransport(uc.bootstrapIPs6)
-	case IpStackSplit:
+		ips = uc.bootstrapIPs6
+	}
+
+	uc.transport = uc.newDOHTransport(ips)
+	uc.http3RoundTripper = uc.newDOH3Transport(ips)
+	uc.doqConnPool = uc.newDOQConnPool(ips)
+	uc.dotClientPool = uc.newDOTClientPool(ips)
+	if uc.IPStack == IpStackSplit {
 		uc.transport4 = uc.newDOHTransport(uc.bootstrapIPs4)
+		uc.http3RoundTripper4 = uc.newDOH3Transport(uc.bootstrapIPs4)
+		uc.doqConnPool4 = uc.newDOQConnPool(uc.bootstrapIPs4)
+		uc.dotClientPool4 = uc.newDOTClientPool(uc.bootstrapIPs4)
 		if HasIPv6() {
 			uc.transport6 = uc.newDOHTransport(uc.bootstrapIPs6)
+			uc.http3RoundTripper6 = uc.newDOH3Transport(uc.bootstrapIPs6)
+			uc.doqConnPool6 = uc.newDOQConnPool(uc.bootstrapIPs6)
+			uc.dotClientPool6 = uc.newDOTClientPool(uc.bootstrapIPs6)
 		} else {
 			uc.transport6 = uc.transport4
+			uc.http3RoundTripper6 = uc.http3RoundTripper4
+			uc.doqConnPool6 = uc.doqConnPool4
+			uc.dotClientPool6 = uc.dotClientPool4
 		}
-		uc.transport = uc.newDOHTransport(uc.bootstrapIPs)
+	}
+}
+
+func (uc *UpstreamConfig) ensureSetupTransport() {
+	uc.transportOnce.Do(func() {
+		uc.SetupTransport()
+	})
+	if uc.rebootstrap.CompareAndSwap(rebootstrapStarted, rebootstrapInProgress) {
+		uc.SetupTransport()
+		uc.rebootstrap.Store(rebootstrapNotStarted)
 	}
 }
 
 func (uc *UpstreamConfig) newDOHTransport(addrs []string) *http.Transport {
+	if uc.Type != ResolverTypeDOH {
+		return nil
+	}
 	transport := http.DefaultTransport.(*http.Transport).Clone()
 	transport.MaxIdleConnsPerHost = 100
 	transport.TLSClientConfig = &tls.Config{
@@ -586,7 +697,7 @@ func (uc *UpstreamConfig) ErrorPing() error {
 
 func (uc *UpstreamConfig) ping() error {
 	switch uc.Type {
-	case ResolverTypeDOH, ResolverTypeDOH3:
+	case ResolverTypeDOH, ResolverTypeDOH3, ResolverTypeDOQ:
 	default:
 		return nil
 	}
@@ -620,6 +731,14 @@ func (uc *UpstreamConfig) ping() error {
 			if err := ping(uc.doh3Transport(typ)); err != nil {
 				return err
 			}
+		case ResolverTypeDOQ:
+			// For DoQ, we just ensure transport is set up by calling doqTransport
+			// DoQ doesn't use HTTP, so we can't ping it the same way
+			_ = uc.doqTransport(typ)
+		case ResolverTypeDOT:
+			// For DoT, we just ensure transport is set up by calling dotTransport
+			// DoT doesn't use HTTP, so we can't ping it the same way
+			_ = uc.dotTransport(typ)
 		}
 	}
 
@@ -653,46 +772,8 @@ func (uc *UpstreamConfig) isNextDNS() bool {
 }
 
 func (uc *UpstreamConfig) dohTransport(dnsType uint16) http.RoundTripper {
-	uc.transportOnce.Do(func() {
-		uc.SetupTransport()
-	})
-	if uc.rebootstrap.CompareAndSwap(true, false) {
-		uc.SetupTransport()
-	}
-	switch uc.IPStack {
-	case IpStackBoth, IpStackV4, IpStackV6:
-		return uc.transport
-	case IpStackSplit:
-		switch dnsType {
-		case dns.TypeA:
-			return uc.transport4
-		default:
-			return uc.transport6
-		}
-	}
-	return uc.transport
-}
-
-func (uc *UpstreamConfig) bootstrapIPForDNSType(dnsType uint16) string {
-	switch uc.IPStack {
-	case IpStackBoth:
-		return pick(uc.bootstrapIPs)
-	case IpStackV4:
-		return pick(uc.bootstrapIPs4)
-	case IpStackV6:
-		return pick(uc.bootstrapIPs6)
-	case IpStackSplit:
-		switch dnsType {
-		case dns.TypeA:
-			return pick(uc.bootstrapIPs4)
-		default:
-			if HasIPv6() {
-				return pick(uc.bootstrapIPs6)
-			}
-			return pick(uc.bootstrapIPs4)
-		}
-	}
-	return pick(uc.bootstrapIPs)
+	uc.ensureSetupTransport()
+	return transportByIpStack(uc.IPStack, dnsType, uc.transport, uc.transport4, uc.transport6)
 }
 
 func (uc *UpstreamConfig) netForDNSType(dnsType uint16) (string, string) {
@@ -937,10 +1018,6 @@ func ResolverTypeFromEndpoint(endpoint string) string {
 	return ResolverTypeDOT
 }
 
-func pick(s []string) string {
-	return s[rand.Intn(len(s))]
-}
-
 // upstreamUID generates an unique identifier for an upstream.
 func upstreamUID() string {
 	b := make([]byte, 4)
@@ -976,3 +1053,18 @@ func bootstrapIPsFromControlDDomain(domain string) []string {
 	}
 	return nil
 }
+
+func transportByIpStack[T any](ipStack string, dnsType uint16, transport, transport4, transport6 T) T {
+	switch ipStack {
+	case IpStackBoth, IpStackV4, IpStackV6:
+		return transport
+	case IpStackSplit:
+		switch dnsType {
+		case dns.TypeA:
+			return transport4
+		default:
+			return transport6
+		}
+	}
+	return transport
+}

config_internal_test.go

@@ -2,6 +2,7 @@ package ctrld
 
 import (
 	"net/url"
+	"sync"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -505,6 +506,52 @@ func TestUpstreamConfig_IsDiscoverable(t *testing.T) {
 	}
 }
 
+func TestRebootstrapRace(t *testing.T) {
+	uc := &UpstreamConfig{
+		Name:         "test-doh",
+		Type:         ResolverTypeDOH,
+		Endpoint:     "https://example.com/dns-query",
+		Domain:       "example.com",
+		bootstrapIPs: []string{"1.1.1.1", "1.0.0.1"},
+	}
+
+	uc.SetupTransport()
+
+	if uc.transport == nil {
+		t.Fatal("initial transport should be set")
+	}
+
+	const goroutines = 100
+
+	uc.ReBootstrap()
+
+	started := make(chan struct{})
+	go func() {
+		close(started)
+		for {
+			switch uc.rebootstrap.Load() {
+			case rebootstrapStarted, rebootstrapInProgress:
+				uc.ReBootstrap()
+			default:
+				return
+			}
+		}
+	}()
+
+	<-started
+
+	var wg sync.WaitGroup
+	wg.Add(goroutines)
+	for range goroutines {
+		go func() {
+			defer wg.Done()
+			uc.ensureSetupTransport()
+		}()
+	}
+
+	wg.Wait()
+}
+
 func ptrBool(b bool) *bool {
 	return &b
 }

config_quic.go

@@ -9,34 +9,17 @@ import (
 	"runtime"
 	"sync"
 
-	"github.com/miekg/dns"
 	"github.com/quic-go/quic-go"
 	"github.com/quic-go/quic-go/http3"
 )
 
-func (uc *UpstreamConfig) setupDOH3Transport() {
-	switch uc.IPStack {
-	case IpStackBoth, "":
-		uc.http3RoundTripper = uc.newDOH3Transport(uc.bootstrapIPs)
-	case IpStackV4:
-		uc.http3RoundTripper = uc.newDOH3Transport(uc.bootstrapIPs4)
-	case IpStackV6:
-		uc.http3RoundTripper = uc.newDOH3Transport(uc.bootstrapIPs6)
-	case IpStackSplit:
-		uc.http3RoundTripper4 = uc.newDOH3Transport(uc.bootstrapIPs4)
-		if HasIPv6() {
-			uc.http3RoundTripper6 = uc.newDOH3Transport(uc.bootstrapIPs6)
-		} else {
-			uc.http3RoundTripper6 = uc.http3RoundTripper4
-		}
-		uc.http3RoundTripper = uc.newDOH3Transport(uc.bootstrapIPs)
-	}
-}
-
 func (uc *UpstreamConfig) newDOH3Transport(addrs []string) http.RoundTripper {
+	if uc.Type != ResolverTypeDOH3 {
+		return nil
+	}
 	rt := &http3.Transport{}
 	rt.TLSClientConfig = &tls.Config{RootCAs: uc.certPool}
-	rt.Dial = func(ctx context.Context, addr string, tlsCfg *tls.Config, cfg *quic.Config) (quic.EarlyConnection, error) {
+	rt.Dial = func(ctx context.Context, addr string, tlsCfg *tls.Config, cfg *quic.Config) (*quic.Conn, error) {
 		_, port, _ := net.SplitHostPort(addr)
 		// if we have a bootstrap ip set, use it to avoid DNS lookup
 		if uc.BootstrapIP != "" {
@@ -71,24 +54,18 @@ func (uc *UpstreamConfig) newDOH3Transport(addrs []string) http.RoundTripper {
 }
 
 func (uc *UpstreamConfig) doh3Transport(dnsType uint16) http.RoundTripper {
-	uc.transportOnce.Do(func() {
-		uc.SetupTransport()
-	})
-	if uc.rebootstrap.CompareAndSwap(true, false) {
-		uc.SetupTransport()
-	}
-	switch uc.IPStack {
-	case IpStackBoth, IpStackV4, IpStackV6:
-		return uc.http3RoundTripper
-	case IpStackSplit:
-		switch dnsType {
-		case dns.TypeA:
-			return uc.http3RoundTripper4
-		default:
-			return uc.http3RoundTripper6
-		}
-	}
-	return uc.http3RoundTripper
+	uc.ensureSetupTransport()
+	return transportByIpStack(uc.IPStack, dnsType, uc.http3RoundTripper, uc.http3RoundTripper4, uc.http3RoundTripper6)
+}
+
+func (uc *UpstreamConfig) doqTransport(dnsType uint16) *doqConnPool {
+	uc.ensureSetupTransport()
+	return transportByIpStack(uc.IPStack, dnsType, uc.doqConnPool, uc.doqConnPool4, uc.doqConnPool6)
+}
+
+func (uc *UpstreamConfig) dotTransport(dnsType uint16) *dotConnPool {
+	uc.ensureSetupTransport()
+	return transportByIpStack(uc.IPStack, dnsType, uc.dotClientPool, uc.dotClientPool4, uc.dotClientPool6)
 }
 
 // Putting the code for quic parallel dialer here:
@@ -96,14 +73,14 @@ func (uc *UpstreamConfig) doh3Transport(dnsType uint16) http.RoundTripper {
 //   - quic dialer is different with net.Dialer
 //   - simplification for quic free version
 type parallelDialerResult struct {
-	conn quic.EarlyConnection
+	conn *quic.Conn
 	err  error
 }
 
 type quicParallelDialer struct{}
 
 // Dial performs parallel dialing to the given address list.
-func (d *quicParallelDialer) Dial(ctx context.Context, addrs []string, tlsCfg *tls.Config, cfg *quic.Config) (quic.EarlyConnection, error) {
+func (d *quicParallelDialer) Dial(ctx context.Context, addrs []string, tlsCfg *tls.Config, cfg *quic.Config) (*quic.Conn, error) {
 	if len(addrs) == 0 {
 		return nil, errors.New("empty addresses")
 	}
@@ -158,3 +135,17 @@ func (d *quicParallelDialer) Dial(ctx context.Context, addrs []string, tlsCfg *t
 
 	return nil, errors.Join(errs...)
 }
+
+func (uc *UpstreamConfig) newDOQConnPool(addrs []string) *doqConnPool {
+	if uc.Type != ResolverTypeDOQ {
+		return nil
+	}
+	return newDOQConnPool(uc, addrs)
+}
+
+func (uc *UpstreamConfig) newDOTClientPool(addrs []string) *dotConnPool {
+	if uc.Type != ResolverTypeDOT {
+		return nil
+	}
+	return newDOTClientPool(uc, addrs)
+}

discover_user_darwin.go

@@ -0,0 +1,135 @@
+//go:build darwin
+
+package ctrld
+
+import (
+	"context"
+	"os/exec"
+	"strconv"
+	"strings"
+)
+
+// DiscoverMainUser attempts to find the primary user on macOS systems.
+// This is designed to work reliably under RMM deployments where traditional
+// environment variables and session detection may not be available.
+//
+// Priority chain (deterministic, lowest UID wins among candidates):
+// 1. Console user from stat -f %Su /dev/console
+// 2. Active console session user via scutil
+// 3. First user with UID >= 501 from dscl (standard macOS user range)
+func DiscoverMainUser(ctx context.Context) string {
+	logger := ProxyLogger.Load().Debug()
+
+	// Method 1: Check console owner via stat
+	logger.Msg("attempting to discover user via console stat")
+	if user := getConsoleUser(ctx); user != "" && user != "root" {
+		logger.Str("method", "stat").Str("user", user).Msg("found user via console stat")
+		return user
+	}
+
+	// Method 2: Check active console session via scutil
+	logger.Msg("attempting to discover user via scutil ConsoleUser")
+	if user := getScutilConsoleUser(ctx); user != "" && user != "root" {
+		logger.Str("method", "scutil").Str("user", user).Msg("found user via scutil ConsoleUser")
+		return user
+	}
+
+	// Method 3: Find lowest UID >= 501 from directory services
+	logger.Msg("attempting to discover user via dscl directory scan")
+	if user := getLowestRegularUser(ctx); user != "" {
+		logger.Str("method", "dscl").Str("user", user).Msg("found user via dscl scan")
+		return user
+	}
+
+	logger.Msg("all user discovery methods failed")
+	return "unknown"
+}
+
+// getConsoleUser uses stat to find the owner of /dev/console
+func getConsoleUser(ctx context.Context) string {
+	cmd := exec.CommandContext(ctx, "stat", "-f", "%Su", "/dev/console")
+	out, err := cmd.Output()
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to stat /dev/console")
+		return ""
+	}
+	return strings.TrimSpace(string(out))
+}
+
+// getScutilConsoleUser uses scutil to get the current console user
+func getScutilConsoleUser(ctx context.Context) string {
+	cmd := exec.CommandContext(ctx, "scutil", "-r", "ConsoleUser")
+	out, err := cmd.Output()
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to get ConsoleUser via scutil")
+		return ""
+	}
+	
+	lines := strings.Split(string(out), "\n")
+	for _, line := range lines {
+		if strings.Contains(line, "Name :") {
+			parts := strings.Fields(line)
+			if len(parts) >= 3 {
+				return strings.TrimSpace(parts[2])
+			}
+		}
+	}
+	return ""
+}
+
+// getLowestRegularUser finds the user with the lowest UID >= 501
+func getLowestRegularUser(ctx context.Context) string {
+	// Get list of all users with UID >= 501
+	cmd := exec.CommandContext(ctx, "dscl", ".", "list", "/Users", "UniqueID")
+	out, err := cmd.Output()
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to list users via dscl")
+		return ""
+	}
+
+	var candidates []struct {
+		name string
+		uid  int
+	}
+
+	lines := strings.Split(string(out), "\n")
+	for _, line := range lines {
+		fields := strings.Fields(line)
+		if len(fields) != 2 {
+			continue
+		}
+
+		username := fields[0]
+		uidStr := fields[1]
+		
+		uid, err := strconv.Atoi(uidStr)
+		if err != nil {
+			continue
+		}
+
+		// Only consider regular users (UID >= 501 on macOS)
+		if uid >= 501 {
+			candidates = append(candidates, struct {
+				name string
+				uid  int
+			}{username, uid})
+		}
+	}
+
+	if len(candidates) == 0 {
+		return ""
+	}
+
+	// Find the candidate with the lowest UID (deterministic choice)
+	lowestUID := candidates[0].uid
+	result := candidates[0].name
+	
+	for _, candidate := range candidates[1:] {
+		if candidate.uid < lowestUID {
+			lowestUID = candidate.uid
+			result = candidate.name
+		}
+	}
+
+	return result
+}

discover_user_linux.go

@@ -0,0 +1,238 @@
+//go:build linux
+
+package ctrld
+
+import (
+	"bufio"
+	"context"
+	"os"
+	"os/exec"
+	"strconv"
+	"strings"
+)
+
+// DiscoverMainUser attempts to find the primary user on Linux systems.
+// This is designed to work reliably under RMM deployments where traditional
+// environment variables and session detection may not be available.
+//
+// Priority chain (deterministic, lowest UID wins among candidates):
+// 1. Active users from loginctl list-users
+// 2. Parse /etc/passwd for users with UID >= 1000, prefer admin group members
+// 3. Fallback to lowest UID >= 1000 from /etc/passwd
+func DiscoverMainUser(ctx context.Context) string {
+	logger := ProxyLogger.Load().Debug()
+
+	// Method 1: Check active users via loginctl
+	logger.Msg("attempting to discover user via loginctl")
+	if user := getLoginctlUser(ctx); user != "" {
+		logger.Str("method", "loginctl").Str("user", user).Msg("found user via loginctl")
+		return user
+	}
+
+	// Method 2: Parse /etc/passwd and find admin users first
+	logger.Msg("attempting to discover user via /etc/passwd with admin preference")
+	if user := getPasswdUserWithAdminPreference(ctx); user != "" {
+		logger.Str("method", "passwd+admin").Str("user", user).Msg("found admin user via /etc/passwd")
+		return user
+	}
+
+	// Method 3: Fallback to lowest UID >= 1000 from /etc/passwd
+	logger.Msg("attempting to discover user via /etc/passwd lowest UID")
+	if user := getLowestPasswdUser(ctx); user != "" {
+		logger.Str("method", "passwd").Str("user", user).Msg("found user via /etc/passwd")
+		return user
+	}
+
+	logger.Msg("all user discovery methods failed")
+	return "unknown"
+}
+
+// getLoginctlUser uses loginctl to find active users
+func getLoginctlUser(ctx context.Context) string {
+	cmd := exec.CommandContext(ctx, "loginctl", "list-users", "--no-legend")
+	out, err := cmd.Output()
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to run loginctl list-users")
+		return ""
+	}
+
+	var candidates []struct {
+		name string
+		uid  int
+	}
+
+	lines := strings.Split(string(out), "\n")
+	for _, line := range lines {
+		fields := strings.Fields(line)
+		if len(fields) < 2 {
+			continue
+		}
+
+		uidStr := fields[0]
+		username := fields[1]
+
+		uid, err := strconv.Atoi(uidStr)
+		if err != nil {
+			continue
+		}
+
+		// Only consider regular users (UID >= 1000 on Linux)
+		if uid >= 1000 {
+			candidates = append(candidates, struct {
+				name string
+				uid  int
+			}{username, uid})
+		}
+	}
+
+	if len(candidates) == 0 {
+		return ""
+	}
+
+	// Return user with lowest UID (deterministic choice)
+	lowestUID := candidates[0].uid
+	result := candidates[0].name
+	
+	for _, candidate := range candidates[1:] {
+		if candidate.uid < lowestUID {
+			lowestUID = candidate.uid
+			result = candidate.name
+		}
+	}
+
+	return result
+}
+
+// getPasswdUserWithAdminPreference parses /etc/passwd and prefers admin group members
+func getPasswdUserWithAdminPreference(ctx context.Context) string {
+	users := parsePasswdFile()
+	if len(users) == 0 {
+		return ""
+	}
+
+	var adminUsers []struct {
+		name string
+		uid  int
+	}
+	var regularUsers []struct {
+		name string
+		uid  int
+	}
+
+	// Separate admin and regular users
+	for _, user := range users {
+		if isUserInAdminGroups(ctx, user.name) {
+			adminUsers = append(adminUsers, user)
+		} else {
+			regularUsers = append(regularUsers, user)
+		}
+	}
+
+	// Prefer admin users, then regular users
+	candidates := adminUsers
+	if len(candidates) == 0 {
+		candidates = regularUsers
+	}
+
+	if len(candidates) == 0 {
+		return ""
+	}
+
+	// Return user with lowest UID (deterministic choice)
+	lowestUID := candidates[0].uid
+	result := candidates[0].name
+	
+	for _, candidate := range candidates[1:] {
+		if candidate.uid < lowestUID {
+			lowestUID = candidate.uid
+			result = candidate.name
+		}
+	}
+
+	return result
+}
+
+// getLowestPasswdUser returns the user with lowest UID >= 1000 from /etc/passwd
+func getLowestPasswdUser(ctx context.Context) string {
+	users := parsePasswdFile()
+	if len(users) == 0 {
+		return ""
+	}
+
+	// Return user with lowest UID (deterministic choice)
+	lowestUID := users[0].uid
+	result := users[0].name
+	
+	for _, user := range users[1:] {
+		if user.uid < lowestUID {
+			lowestUID = user.uid
+			result = user.name
+		}
+	}
+
+	return result
+}
+
+// parsePasswdFile parses /etc/passwd and returns users with UID >= 1000
+func parsePasswdFile() []struct {
+	name string
+	uid  int
+} {
+	file, err := os.Open("/etc/passwd")
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to open /etc/passwd")
+		return nil
+	}
+	defer file.Close()
+
+	var users []struct {
+		name string
+		uid  int
+	}
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		fields := strings.Split(line, ":")
+		if len(fields) < 3 {
+			continue
+		}
+
+		username := fields[0]
+		uidStr := fields[2]
+
+		uid, err := strconv.Atoi(uidStr)
+		if err != nil {
+			continue
+		}
+
+		// Only consider regular users (UID >= 1000 on Linux)
+		if uid >= 1000 {
+			users = append(users, struct {
+				name string
+				uid  int
+			}{username, uid})
+		}
+	}
+
+	return users
+}
+
+// isUserInAdminGroups checks if a user is in common admin groups
+func isUserInAdminGroups(ctx context.Context, username string) bool {
+	adminGroups := []string{"sudo", "wheel", "admin"}
+	
+	for _, group := range adminGroups {
+		cmd := exec.CommandContext(ctx, "groups", username)
+		out, err := cmd.Output()
+		if err != nil {
+			continue
+		}
+		
+		if strings.Contains(string(out), group) {
+			return true
+		}
+	}
+	
+	return false
+}

discover_user_others.go

@@ -0,0 +1,13 @@
+//go:build !windows && !linux && !darwin
+
+package ctrld
+
+import "context"
+
+// DiscoverMainUser returns "unknown" for unsupported platforms.
+// This is a stub implementation for platforms where username detection
+// is not yet implemented.
+func DiscoverMainUser(ctx context.Context) string {
+	ProxyLogger.Load().Debug().Msg("username discovery not implemented for this platform")
+	return "unknown"
+}

discover_user_windows.go

@@ -0,0 +1,292 @@
+//go:build windows
+
+package ctrld
+
+import (
+	"context"
+	"strconv"
+	"strings"
+	"syscall"
+	"unsafe"
+
+	"golang.org/x/sys/windows"
+	"golang.org/x/sys/windows/registry"
+)
+
+var (
+	wtsapi32                         = windows.NewLazySystemDLL("wtsapi32.dll")
+	procWTSGetActiveConsoleSessionId = wtsapi32.NewProc("WTSGetActiveConsoleSessionId")
+	procWTSQuerySessionInformation   = wtsapi32.NewProc("WTSQuerySessionInformationW")
+	procWTSFreeMemory                = wtsapi32.NewProc("WTSFreeMemory")
+)
+
+const (
+	WTSUserName = 5
+)
+
+// DiscoverMainUser attempts to find the primary user on Windows systems.
+// This is designed to work reliably under RMM deployments where traditional
+// environment variables and session detection may not be available.
+//
+// Priority chain (deterministic, lowest RID wins among candidates):
+// 1. Active console session user via WTSGetActiveConsoleSessionId
+// 2. Registry ProfileList scan for Administrators group members
+// 3. Fallback to lowest RID from ProfileList
+func DiscoverMainUser(ctx context.Context) string {
+	logger := ProxyLogger.Load().Debug()
+
+	// Method 1: Check active console session
+	logger.Msg("attempting to discover user via active console session")
+	if user := getActiveConsoleUser(ctx); user != "" {
+		logger.Str("method", "console").Str("user", user).Msg("found user via active console session")
+		return user
+	}
+
+	// Method 2: Scan registry for admin users
+	logger.Msg("attempting to discover user via registry with admin preference")
+	if user := getRegistryUserWithAdminPreference(ctx); user != "" {
+		logger.Str("method", "registry+admin").Str("user", user).Msg("found admin user via registry")
+		return user
+	}
+
+	// Method 3: Fallback to lowest RID from registry
+	logger.Msg("attempting to discover user via registry lowest RID")
+	if user := getLowestRegistryUser(ctx); user != "" {
+		logger.Str("method", "registry").Str("user", user).Msg("found user via registry")
+		return user
+	}
+
+	logger.Msg("all user discovery methods failed")
+	return "unknown"
+}
+
+// getActiveConsoleUser gets the username of the active console session
+func getActiveConsoleUser(ctx context.Context) string {
+	// Guard against missing WTS procedures (e.g., Windows Server Core).
+	if err := procWTSGetActiveConsoleSessionId.Find(); err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("WTSGetActiveConsoleSessionId not available, skipping console session check")
+		return ""
+	}
+	sessionId, _, _ := procWTSGetActiveConsoleSessionId.Call()
+	if sessionId == 0xFFFFFFFF { // Invalid session
+		ProxyLogger.Load().Debug().Msg("no active console session found")
+		return ""
+	}
+
+	var buffer uintptr
+	var bytesReturned uint32
+
+	if err := procWTSQuerySessionInformation.Find(); err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("WTSQuerySessionInformationW not available")
+		return ""
+	}
+	ret, _, _ := procWTSQuerySessionInformation.Call(
+		0, // WTS_CURRENT_SERVER_HANDLE
+		sessionId,
+		uintptr(WTSUserName),
+		uintptr(unsafe.Pointer(&buffer)),
+		uintptr(unsafe.Pointer(&bytesReturned)),
+	)
+
+	if ret == 0 {
+		ProxyLogger.Load().Debug().Msg("failed to query session information")
+		return ""
+	}
+	defer procWTSFreeMemory.Call(buffer)
+
+	// Convert buffer to string
+	username := windows.UTF16PtrToString((*uint16)(unsafe.Pointer(buffer)))
+	if username == "" {
+		return ""
+	}
+
+	return username
+}
+
+// getRegistryUserWithAdminPreference scans registry profiles and prefers admin users
+func getRegistryUserWithAdminPreference(ctx context.Context) string {
+	profiles := getRegistryProfiles()
+	if len(profiles) == 0 {
+		return ""
+	}
+
+	var adminProfiles []registryProfile
+	var regularProfiles []registryProfile
+
+	// Separate admin and regular users
+	for _, profile := range profiles {
+		if isUserInAdministratorsGroup(profile.username) {
+			adminProfiles = append(adminProfiles, profile)
+		} else {
+			regularProfiles = append(regularProfiles, profile)
+		}
+	}
+
+	// Prefer admin users, then regular users
+	candidates := adminProfiles
+	if len(candidates) == 0 {
+		candidates = regularProfiles
+	}
+
+	if len(candidates) == 0 {
+		return ""
+	}
+
+	// Return user with lowest RID (deterministic choice)
+	lowestRID := candidates[0].rid
+	result := candidates[0].username
+
+	for _, candidate := range candidates[1:] {
+		if candidate.rid < lowestRID {
+			lowestRID = candidate.rid
+			result = candidate.username
+		}
+	}
+
+	return result
+}
+
+// getLowestRegistryUser returns the user with lowest RID from registry
+func getLowestRegistryUser(ctx context.Context) string {
+	profiles := getRegistryProfiles()
+	if len(profiles) == 0 {
+		return ""
+	}
+
+	// Return user with lowest RID (deterministic choice)
+	lowestRID := profiles[0].rid
+	result := profiles[0].username
+
+	for _, profile := range profiles[1:] {
+		if profile.rid < lowestRID {
+			lowestRID = profile.rid
+			result = profile.username
+		}
+	}
+
+	return result
+}
+
+type registryProfile struct {
+	username string
+	rid      uint32
+	sid      string
+}
+
+// getRegistryProfiles scans the registry ProfileList for user profiles
+func getRegistryProfiles() []registryProfile {
+	key, err := registry.OpenKey(registry.LOCAL_MACHINE, `SOFTWARE\Microsoft\Windows NT\CurrentVersion\ProfileList`, registry.ENUMERATE_SUB_KEYS)
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to open ProfileList registry key")
+		return nil
+	}
+	defer key.Close()
+
+	subkeys, err := key.ReadSubKeyNames(-1)
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("failed to read ProfileList subkeys")
+		return nil
+	}
+
+	var profiles []registryProfile
+
+	for _, subkey := range subkeys {
+		// Only process SIDs that start with S-1-5-21 (domain/local user accounts)
+		if !strings.HasPrefix(subkey, "S-1-5-21-") {
+			continue
+		}
+
+		profileKey, err := registry.OpenKey(key, subkey, registry.QUERY_VALUE)
+		if err != nil {
+			continue
+		}
+
+		profileImagePath, _, err := profileKey.GetStringValue("ProfileImagePath")
+		profileKey.Close()
+		if err != nil {
+			continue
+		}
+
+		// Extract username from profile path (e.g., C:\Users\username)
+		pathParts := strings.Split(profileImagePath, `\`)
+		if len(pathParts) == 0 {
+			continue
+		}
+		username := pathParts[len(pathParts)-1]
+
+		// Extract RID from SID (last component after final hyphen)
+		sidParts := strings.Split(subkey, "-")
+		if len(sidParts) == 0 {
+			continue
+		}
+		ridStr := sidParts[len(sidParts)-1]
+		rid, err := strconv.ParseUint(ridStr, 10, 32)
+		if err != nil {
+			continue
+		}
+
+		// Only consider regular users (RID >= 1000, excludes built-in accounts).
+		// rid == 500 is the default Administrator account (DOMAIN_USER_RID_ADMIN).
+		// See: https://learn.microsoft.com/en-us/windows/win32/secauthz/well-known-sids
+		if rid == 500 || rid >= 1000 {
+			profiles = append(profiles, registryProfile{
+				username: username,
+				rid:      uint32(rid),
+				sid:      subkey,
+			})
+		}
+	}
+
+	return profiles
+}
+
+// isUserInAdministratorsGroup checks if a user is in the Administrators group
+func isUserInAdministratorsGroup(username string) bool {
+	// Open the user account
+	usernamePtr, err := syscall.UTF16PtrFromString(username)
+	if err != nil {
+		return false
+	}
+
+	var userSID *windows.SID
+	var domain *uint16
+	var userSIDSize, domainSize uint32
+	var use uint32
+
+	// First call to get buffer sizes
+	err = windows.LookupAccountName(nil, usernamePtr, userSID, &userSIDSize, domain, &domainSize, &use)
+	if err != nil && err != windows.ERROR_INSUFFICIENT_BUFFER {
+		return false
+	}
+
+	// Allocate buffers and make actual call
+	userSID = (*windows.SID)(unsafe.Pointer(&make([]byte, userSIDSize)[0]))
+	domain = (*uint16)(unsafe.Pointer(&make([]uint16, domainSize)[0]))
+
+	err = windows.LookupAccountName(nil, usernamePtr, userSID, &userSIDSize, domain, &domainSize, &use)
+	if err != nil {
+		return false
+	}
+
+	// Check if user is member of Administrators group (S-1-5-32-544)
+	adminSID, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
+	if err != nil {
+		return false
+	}
+
+	// Open user token (this is a simplified check)
+	var token windows.Token
+	err = windows.OpenProcessToken(windows.CurrentProcess(), windows.TOKEN_QUERY, &token)
+	if err != nil {
+		return false
+	}
+	defer token.Close()
+
+	// Check group membership
+	member, err := token.IsMember(adminSID)
+	if err != nil {
+		return false
+	}
+
+	return member
+}

docs/dns-intercept-mode.md

@@ -0,0 +1,551 @@
+# DNS Intercept Mode
+
+## Overview
+
+DNS intercept mode is an alternative approach to DNS management that uses OS-level packet interception instead of modifying network interface DNS settings. This eliminates race conditions with VPN software, endpoint security tools, and other programs that also manage DNS.
+
+## The Problem
+
+By default, ctrld sets DNS to `127.0.0.1` on network interfaces so all queries go through ctrld's local listener. However, VPN software (F5 BIG-IP, Cisco AnyConnect, Palo Alto GlobalProtect, etc.) also overwrites interface DNS settings, creating conflicts:
+
+1. **DNS Setting War**: ctrld sets DNS to `127.0.0.1`, VPN overwrites to its DNS servers, ctrld's watchdog detects the change and restores `127.0.0.1`, VPN overwrites again — infinitely.
+
+2. **Bypass Window**: During the watchdog polling interval (up to 20 seconds), DNS queries may go to the VPN's DNS servers, bypassing ctrld's filtering profiles (malware blocking, content filtering, etc.).
+
+3. **Resolution Failures**: During the brief moments when DNS is being rewritten, queries may fail entirely, causing intermittent connectivity loss.
+
+## The Solution
+
+DNS intercept mode works at a lower level than interface settings:
+
+- **Windows**: Uses NRPT (Name Resolution Policy Table) to route all DNS queries to `127.0.0.1` (ctrld's listener) via the Windows DNS Client service. In `hard` mode, additionally uses WFP (Windows Filtering Platform) to block all outbound DNS (port 53) except to localhost and private ranges, preventing any bypass. VPN software can set interface DNS freely — NRPT's most-specific-match ensures VPN-specific domains still resolve correctly while ctrld handles everything else.
+
+- **macOS**: Uses pf (packet filter) to redirect all outbound DNS (port 53) traffic to ctrld's listener at `127.0.0.1:53`. Any DNS query, regardless of which DNS server the OS thinks it's using, gets transparently redirected to ctrld.
+
+## Usage
+
+```bash
+# Start ctrld with DNS intercept mode (auto-detects VPN search domains)
+ctrld start --intercept-mode dns --cd <resolver-uid>
+
+# Hard intercept: all DNS through ctrld, no VPN split routing
+ctrld start --intercept-mode hard --cd <resolver-uid>
+
+# Or with a config file
+ctrld start --intercept-mode dns -c /path/to/ctrld.toml
+
+# Run in foreground (debug)
+ctrld run --intercept-mode dns --cd <resolver-uid>
+ctrld run --intercept-mode hard --cd <resolver-uid>
+```
+
+### Intercept Modes
+
+| Flag | DNS Interception | VPN Split Routing | Captive Portal Recovery |
+|------|-----------------|-------------------|------------------------|
+| `--intercept-mode dns` | ✅ WFP/pf | ✅ Auto-detect & forward | ✅ Active |
+| `--intercept-mode hard` | ✅ WFP/pf | ❌ All through ctrld | ✅ Active |
+
+**`--intercept-mode dns`** (recommended): Intercepts all DNS via WFP/pf, but automatically discovers search domains from VPN and virtual network adapters (Tailscale, F5, Cisco AnyConnect, etc.) and forwards matching queries to the DNS server on that interface. This allows VPN internal resources (e.g., `*.corp.local`) to resolve correctly while ctrld handles everything else.
+
+**`--intercept-mode hard`**: Same OS-level interception, but does NOT forward any queries to VPN DNS servers. Every DNS query goes through ctrld's configured upstreams. Use this when you want total DNS control and don't need VPN internal domain resolution. Captive portal recovery still works — network authentication pages are handled automatically.
+
+## How It Works
+
+### Windows (NRPT + WFP)
+
+Windows DNS intercept uses a two-tier architecture with mode-dependent enforcement:
+
+- **`dns` mode**: NRPT only — graceful DNS routing through the Windows DNS Client service. At worst, a VPN overwrites NRPT and queries bypass ctrld temporarily. DNS never breaks.
+- **`hard` mode**: NRPT + WFP — same NRPT routing, plus WFP kernel-level block filters that prevent any outbound DNS bypass. Equivalent enforcement to macOS pf.
+
+#### Why This Design?
+
+WFP can only **block** or **permit** connections — it **cannot redirect** them (redirection requires kernel-mode callout drivers). Without NRPT, WFP blocks outbound DNS but doesn't tell applications where to send queries instead — they see DNS failures. NRPT provides the "positive routing" while WFP provides enforcement.
+
+Separating them into modes means most users get `dns` mode (safe, can never break DNS) while high-security deployments use `hard` mode (full enforcement, same guarantees as macOS pf).
+
+#### Startup Sequence (dns mode)
+
+1. Creates NRPT catch-all registry rule (`.` → `127.0.0.1`) under `HKLM\...\DnsPolicyConfig\CtrldCatchAll`
+2. Triggers Group Policy refresh via `RefreshPolicyEx` (userenv.dll) so DNS Client loads NRPT immediately
+3. Flushes DNS cache to clear stale entries
+4. Starts NRPT health monitor (30s periodic check)
+5. Launches async NRPT probe-and-heal to verify NRPT is actually routing queries
+
+#### Startup Sequence (hard mode)
+
+1. Creates NRPT catch-all rule + GP refresh + DNS flush (same as dns mode)
+2. Opens WFP engine with `RPC_C_AUTHN_DEFAULT` (0xFFFFFFFF)
+3. Cleans up any stale sublayer from a previous unclean shutdown
+4. Creates sublayer with maximum weight (0xFFFF)
+5. Adds **permit** filters (weight 10) for DNS to localhost (`127.0.0.1`/`::1` port 53)
+6. Adds **permit** filters (weight 10) for DNS to RFC1918 + CGNAT subnets (10/8, 172.16/12, 192.168/16, 100.64/10)
+7. Adds **block** filters (weight 1) for all other outbound DNS (port 53 UDP+TCP)
+8. Starts NRPT health monitor (also verifies WFP sublayer in hard mode)
+9. Launches async NRPT probe-and-heal
+
+**Atomic guarantee:** NRPT must succeed before WFP starts. If NRPT fails, WFP is not attempted. If WFP fails, NRPT is rolled back. This prevents DNS blackholes where WFP blocks everything but nothing routes to ctrld.
+
+On shutdown: stops health monitor, removes NRPT rule, flushes DNS, then (hard mode only) removes all WFP filters and closes engine.
+
+#### NRPT Details
+
+The **Name Resolution Policy Table** is a Windows feature (originally for DirectAccess) that tells the DNS Client service to route queries matching specific namespace patterns to specific DNS servers. ctrld adds a catch-all rule:
+
+| Registry Value | Type | Value | Purpose |
+|---|---|---|---|
+| `Name` | REG_MULTI_SZ | `.` | Namespace pattern (`.` = catch-all, matches everything) |
+| `GenericDNSServers` | REG_SZ | `127.0.0.1` | DNS server to use for matching queries |
+| `ConfigOptions` | REG_DWORD | `0x8` | Standard DNS resolution (no DirectAccess) |
+| `Version` | REG_DWORD | `0x2` | NRPT rule version 2 |
+
+**Registry path**: `HKLM\SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig\CtrldCatchAll`
+
+**Group Policy refresh**: The DNS Client service only reads NRPT from registry during Group Policy processing cycles (default: every 90 minutes). ctrld calls `RefreshPolicyEx(bMachine=TRUE, dwOptions=RP_FORCE)` from `userenv.dll` to trigger an immediate refresh. Falls back to `gpupdate /target:computer /force` if the DLL call fails.
+
+#### WFP Filter Architecture
+
+**Filter priority**: Permit filters have weight 10, block filters have weight 1. WFP evaluates higher-weight filters first, so localhost and private-range DNS is always permitted.
+
+**RFC1918 + CGNAT permits**: Static subnet permit filters allow DNS to private IP ranges (10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, 100.64.0.0/10). This means VPN DNS servers on private IPs (Tailscale MagicDNS on 100.100.100.100, corporate VPN DNS on 10.x.x.x, etc.) work without needing dynamic per-server exemptions.
+
+**VPN coexistence**: VPN software can set DNS to whatever it wants on the interface — for public IPs, the WFP block filter prevents those servers from being reached on port 53. For private IPs, the subnet permits allow it. ctrld handles all DNS routing through NRPT and can forward VPN-specific domains to VPN DNS servers through its own upstream mechanism.
+
+#### NRPT Probe and Auto-Heal
+
+`RefreshPolicyEx` returns immediately — it does NOT wait for the DNS Client service to actually load the NRPT rule. On cold machines (first boot, fresh install), the DNS Client may take several seconds to process the policy refresh. During this window, the NRPT rule exists in the registry but isn't active.
+
+ctrld verifies NRPT is actually working by sending a probe DNS query (`_nrpt-probe-<hex>.nrpt-probe.ctrld.test`) through Go's `net.Resolver` (which calls `GetAddrInfoW` → DNS Client → NRPT path). If ctrld receives the probe on its listener, NRPT is active.
+
+**Startup probe (async, non-blocking):** After NRPT setup, an async goroutine probes with escalating remediation: (1) immediate probe, (2) GP refresh + retry, (3) DNS Client service restart + retry, (4) final retry. Only one probe sequence runs at a time.
+
+**DNS Client restart (nuclear option):** If GP refresh alone isn't enough, ctrld restarts the `Dnscache` service to force full NRPT re-initialization. This briefly interrupts all DNS (~100ms) but only fires when NRPT is already not working.
+
+#### NRPT Health Monitor
+
+A dedicated background goroutine (`nrptHealthMonitor`) runs every 30 seconds and now performs active probing:
+
+1. **Registry check:** If the NRPT catch-all rule is missing from the registry, restore it + GP refresh + probe-and-heal
+2. **Active probe:** If the rule exists, send a probe query to verify it's actually routing — catches cases where the registry key is present but DNS Client hasn't loaded it
+3. **(hard mode)** Verify WFP sublayer exists; full restart on loss
+
+This is periodic (not just network-event-driven) because VPN software can clear NRPT at any time. Additionally, `scheduleDelayedRechecks()` (called on network change events) performs immediate NRPT verification at 2s and 4s after changes.
+
+#### Known Caveats
+
+- **`nslookup` bypasses NRPT**: `nslookup.exe` uses its own DNS resolver implementation and does NOT go through the Windows DNS Client service, so it ignores NRPT rules entirely. Use `Resolve-DnsName` (PowerShell) or `ping` to verify DNS resolution through NRPT. This is a well-known Windows behavior, not a ctrld bug.
+- **`RPC_C_AUTHN_DEFAULT`**: `FwpmEngineOpen0` requires `RPC_C_AUTHN_DEFAULT` (0xFFFFFFFF) for the authentication service parameter. Using `RPC_C_AUTHN_NONE` (0) returns `ERROR_NOT_SUPPORTED` on some configurations (e.g., Parallels VMs).
+- **FWP_DATA_TYPE enum**: The `FWP_DATA_TYPE` enum starts at `FWP_EMPTY=0`, making `FWP_UINT8=1`, `FWP_UINT16=2`, etc. Some documentation examples incorrectly start at 0.
+
+### macOS (pf)
+
+1. ctrld writes a pf anchor file at `/etc/pf.anchors/com.controld.ctrld`
+2. Adds the anchor reference to `/etc/pf.conf` (if not present)
+3. Loads the anchor with `pfctl -a com.controld.ctrld -f <file>`
+4. Enables pf with `pfctl -e` (if not already enabled)
+5. The anchor redirects all outbound DNS (port 53) on non-loopback interfaces to `127.0.0.1:53`
+6. On shutdown, the anchor is flushed, the file removed, and references cleaned from `pf.conf`
+
+**ctrld's own traffic**: ctrld's upstream queries use DoH (HTTPS on port 443), not plain DNS on port 53, so the pf redirect does not create a loop for DoH upstreams. **Warning:** If an "os" upstream is configured (which uses plain DNS on port 53 to external servers), the pf redirect will capture ctrld's own outbound queries and create a loop. ctrld will log a warning at startup if this is detected. Use DoH upstreams when DNS intercept mode is active.
+
+## What Changes vs Default Mode
+
+| Behavior | Default Mode | DNS Intercept Mode |
+|----------|-------------|-------------------|
+| Interface DNS settings | Set to `127.0.0.1` | **Not modified** |
+| DNS watchdog | Active (polls every 20s) | **Disabled** |
+| VPN DNS conflict | Race condition possible | **Eliminated** |
+| Profile bypass window | Up to 20 seconds | **Zero** |
+| Requires admin/root | Yes | Yes |
+| Additional OS requirements | None | WFP (Windows), pf (macOS) |
+
+## Logging
+
+DNS intercept mode produces detailed logs for troubleshooting:
+
+```
+DNS intercept: initializing Windows Filtering Platform (WFP)
+DNS intercept: WFP engine opened (handle: 0x1a2b3c)
+DNS intercept: WFP sublayer created (weight: 0xFFFF — maximum priority)
+DNS intercept: added permit filter "Permit DNS to localhost (IPv4/UDP)" (ID: 12345)
+DNS intercept: added block filter "Block outbound DNS (IPv4/UDP)" (ID: 12349)
+DNS intercept: WFP filters active — all outbound DNS (port 53) blocked except to localhost
+```
+
+On macOS:
+```
+DNS intercept: initializing macOS packet filter (pf) redirect
+DNS intercept: wrote pf anchor file: /etc/pf.anchors/com.controld.ctrld
+DNS intercept: loaded pf anchor "com.controld.ctrld"
+DNS intercept: pf anchor "com.controld.ctrld" active with 3 rules
+DNS intercept: pf redirect active — all outbound DNS (port 53) redirected to 127.0.0.1:53
+```
+
+## Troubleshooting
+
+### Windows
+
+```powershell
+# Check NRPT rules (should show CtrldCatchAll with . → 127.0.0.1)
+Get-DnsClientNrptRule
+
+# Check NRPT registry directly
+Get-ChildItem "HKLM:\SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig"
+
+# Force Group Policy refresh (if NRPT not taking effect)
+gpupdate /target:computer /force
+
+# Check if WFP filters are active
+netsh wfp show filters
+
+# Check ctrld's specific filters (look for "ctrld" in output)
+netsh wfp show filters | Select-String "ctrld"
+
+# Test DNS resolution (use Resolve-DnsName, NOT nslookup!)
+# nslookup bypasses DNS Client / NRPT — it will NOT reflect NRPT routing
+Resolve-DnsName example.com
+ping example.com
+
+# If you must use nslookup, specify localhost explicitly:
+nslookup example.com 127.0.0.1
+```
+
+### macOS
+
+```bash
+# Check if pf is enabled
+sudo pfctl -si
+
+# Check ctrld's anchor rules
+sudo pfctl -a com.controld.ctrld -sr
+sudo pfctl -a com.controld.ctrld -sn
+
+# Check pf.conf for anchor reference
+cat /etc/pf.conf | grep ctrld
+
+# Test DNS is going through ctrld
+dig @127.0.0.1 example.com
+```
+
+## Limitations
+
+- **Linux**: Not supported. Linux uses `systemd-resolved` or `/etc/resolv.conf` which don't have the same VPN conflict issues. If needed in the future, `iptables`/`nftables` REDIRECT could be used.
+
+- **Split DNS for VPN internal domains**: In `--intercept-mode dns` mode, VPN search domains are auto-detected from virtual network adapters and forwarded to the VPN's DNS servers automatically. In `--intercept-mode hard` mode, VPN internal domains (e.g., `*.corp.local`) will NOT resolve unless configured as explicit upstream rules in ctrld's configuration.
+
+- **macOS mDNSResponder interaction**: On macOS, ctrld uses a workaround ("mDNSResponder hack") that binds to `0.0.0.0:53` instead of `127.0.0.1:53` and refuses queries from non-localhost sources. In dns-intercept mode, pf's `rdr` rewrites the destination IP to `127.0.0.1:53` but preserves the original source IP (e.g., `192.168.2.73`). The mDNSResponder source-IP check is automatically bypassed in dns-intercept mode because the pf/WFP rules already ensure only legitimate intercepted DNS traffic reaches ctrld's listener.
+
+- **Other WFP/pf users**: If other software (VPN, firewall, endpoint security) also uses WFP or pf for DNS interception, there may be priority conflicts. ctrld uses maximum sublayer weight on Windows and a named anchor on macOS to minimize this risk. See "VPN App Coexistence" below for macOS-specific defenses.
+
+## VPN App Coexistence (macOS)
+
+VPN apps (Windscribe, Cisco AnyConnect, F5 BIG-IP, etc.) often manage pf rules themselves, which can interfere with ctrld's DNS intercept. ctrld uses a multi-layered defense strategy:
+
+### 1. Anchor Priority Enforcement
+
+When injecting our anchor reference into the running pf ruleset, ctrld **prepends** both the `rdr-anchor` and `anchor` references before all other anchors. pf evaluates rules top-to-bottom, so our DNS intercept `quick` rules match port 53 traffic before a VPN app's broader rules in their own anchor.
+
+### 2. Interface-Specific Tunnel Rules
+
+VPN apps commonly add rules like `pass out quick on ipsec0 inet all` that match ALL traffic on the VPN interface. If their anchor is evaluated before ours (e.g., after a ruleset reload), these broad rules capture DNS. ctrld counters this by adding explicit DNS intercept rules for each active tunnel interface (ipsec*, utun*, ppp*, tap*, tun*). These interface-specific rules match port 53 only, so they take priority over the VPN app's broader "all" match even within the same anchor evaluation pass.
+
+### 3. Dynamic Tunnel Interface Detection
+
+The network change monitor (`validInterfacesMap()`) only tracks physical hardware ports (en0, bridge0, etc.) — it doesn't see tunnel interfaces (utun*, ipsec*, etc.) created by VPN software. When a VPN connects and creates a new interface (e.g., utun420 for WireGuard), ctrld detects this through a separate tunnel interface change check and rebuilds the pf anchor to include explicit intercept rules for the new interface. This runs on every network change event, even if no physical interface changed.
+
+### 4. pf Watchdog + Network Change Hooks
+
+A background watchdog (30s interval) plus immediate checks on network change events detect when another program replaces the entire pf ruleset (e.g., Windscribe's `pfctl -f /etc/pf.conf`). When detected, ctrld rebuilds its anchor with up-to-date tunnel interface rules and re-injects the anchor reference at the top of the ruleset. A 2-second delayed re-check catches race conditions where the other program clears rules slightly after the network event.
+
+### 4a. Active Interception Probe (pf Translation State Corruption)
+
+Programs like Parallels Desktop reload `/etc/pf.conf` when creating/destroying virtual network interfaces (bridge100, vmenet0). This can corrupt pf's internal translation engine — rdr rules survive in text form but stop evaluating, causing DNS interception to silently fail while the watchdog reports "intact."
+
+ctrld detects interface appearance/disappearance and spawns an async probe monitor:
+
+1. **Probe mechanism:** A subprocess runs with GID=0 (wheel, not `_ctrld`) and sends a DNS query to the OS resolver. If pf interception is working, the query gets redirected to ctrld (127.0.0.1:53) and is detected in the DNS handler. If broken, it times out after 1s.
+2. **Backoff schedule:** Probes at 0, 0.5, 1, 2, 4 seconds (~8s window) to win the race against async pf reloads by the hypervisor. Only one monitor runs at a time (atomic singleton).
+3. **Auto-heal:** On probe failure, `forceReloadPFMainRuleset()` dumps the running ruleset and pipes it back through `pfctl -f -`, resetting pf's translation engine. VPN-safe because it reassembles from the current running state.
+4. **Watchdog integration:** The 30s watchdog also runs the probe when rule text checks pass, as a safety net for unknown corruption causes.
+
+This approach detects **actual broken DNS** rather than guessing from trigger events, making it robust against future unknown corruption scenarios.
+
+### 5. Proactive DoH Connection Pool Reset
+
+When the watchdog detects a pf ruleset replacement, it force-rebootstraps all upstream transports via `ForceReBootstrap()`. This is necessary because `pfctl -f` flushes the entire pf state table, which kills existing TCP connections (including ctrld's DoH connections to upstream DNS servers like 76.76.2.22:443).
+
+The force-rebootstrap does two things that the lazy `ReBootstrap()` cannot:
+1. **Closes idle connections on the old transport** (`CloseIdleConnections()`), causing in-flight HTTP/2 requests on dead connections to fail immediately instead of waiting for the 5s context deadline
+2. **Creates the new transport synchronously**, so it's ready before any DNS queries arrive post-wipe
+
+Without this, Go's `http.Transport` keeps trying dead connections until each request's context deadline expires (~5s), then the lazy rebootstrap creates a new transport for the *next* request. With force-rebootstrap, the blackout is reduced from ~5s to ~100ms (one fresh TLS handshake).
+
+### 6. Blanket Process Exemption (group _ctrld)
+
+ctrld creates a macOS system group (`_ctrld`) and sets its effective GID at startup via `syscall.Setegid()`. The pf anchor includes a blanket rule:
+
+```
+pass out quick group _ctrld
+```
+
+This exempts **all** outbound traffic from the ctrld process — not just DNS (port 53), but also DoH (TCP 443), DoT (TCP 853), health checks, and any other connections. This is essential because VPN firewalls like Windscribe load `block drop all` rulesets that would otherwise block ctrld's upstream connections even after the pf anchor is restored.
+
+Because ctrld's anchor is prepended before all other anchors, and this rule uses `quick`, it evaluates before any VPN firewall rules. The result: ctrld's traffic is never blocked regardless of what other pf rulesets are loaded.
+
+The per-IP exemptions (OS resolver, VPN DNS) remain as defense-in-depth for the DNS redirect loop prevention — the blanket rule handles everything else.
+
+### 7. Loopback Outbound Pass Rule
+
+When `route-to lo0` redirects a DNS packet to loopback, pf re-evaluates the packet **outbound on lo0**. None of the existing route-to rules match on lo0 (they're all `on ! lo0` or `on utunX`), so without an explicit pass rule, the packet falls through to the main ruleset where VPN firewalls' `block drop all` drops it — before it ever reaches the inbound rdr rule.
+
+```
+pass out quick on lo0 inet proto udp from any to ! 127.0.0.1 port 53
+pass out quick on lo0 inet proto tcp from any to ! 127.0.0.1 port 53
+```
+
+This bridges the route-to → rdr gap: route-to sends outbound on lo0 → this rule passes it → loopback reflects it inbound → rdr rewrites destination to 127.0.0.1:53 → ctrld receives the query. Without this rule, DNS intercept fails whenever a `block drop all` firewall (Windscribe, etc.) is active.
+
+### 8. Response Routing via `reply-to lo0`
+
+After rdr redirects DNS to 127.0.0.1:53, ctrld responds to the original client source IP (e.g., 100.94.163.168 — a VPN tunnel IP). Without intervention, the kernel routes this response through the VPN tunnel interface (utun420) based on its routing table, and the response is lost.
+
+```
+pass in quick on lo0 reply-to lo0 inet proto { udp, tcp } from any to 127.0.0.1 port 53
+```
+
+`reply-to lo0` tells pf to force response packets for this connection back through lo0, overriding the kernel routing table. The response stays local, rdr reverse NAT rewrites the source from 127.0.0.1 back to the original DNS server IP (e.g., 10.255.255.3), and the client process receives a correctly-addressed response.
+
+### 9. VPN DNS Split Routing and Exit Mode Detection
+
+When a VPN like Tailscale MagicDNS is active, two distinct modes require different pf handling:
+
+#### The Problem: DNS Proxy Loop
+
+VPN DNS handlers like Tailscale's MagicDNS run as macOS Network Extensions. MagicDNS
+listens on 100.100.100.100 and forwards queries to internal upstream nameservers
+(e.g., 10.0.0.11, 10.0.0.12) via the VPN tunnel interface (utun13).
+
+Without special handling, pf's generic `pass out quick on ! lo0 route-to lo0` rule
+intercepts MagicDNS's upstream queries on the tunnel interface, routing them back
+to ctrld → which matches VPN DNS split routing → forwards to MagicDNS → loop:
+
+```
+┌──────────────────────────────────────────────────────────────────────┐
+│  THE LOOP (without passthrough rules)                                │
+│                                                                      │
+│  1. dig vpn-internal.example.com                                    │
+│     → pf intercepts → route-to lo0 → rdr → ctrld (127.0.0.1:53)    │
+│                                                                      │
+│  2. ctrld: VPN DNS match → forward to 100.100.100.100:53            │
+│     → group _ctrld exempts → reaches MagicDNS                       │
+│                                                                      │
+│  3. MagicDNS: forward to upstream 10.0.0.11:53 via utun13         │
+│     → pf generic rule matches (utun13 ≠ lo0, 10.0.0.11 ≠ skip)   │
+│     → route-to lo0 → rdr → back to ctrld ← LOOP!                   │
+└──────────────────────────────────────────────────────────────────────┘
+```
+
+#### The Fix: Interface Passthrough + Exit Mode Detection
+
+**Split DNS mode** (VPN handles only specific domains):
+
+ctrld adds passthrough rules for VPN DNS interfaces that let MagicDNS's upstream
+queries flow without interception. A `<vpn_dns>` table contains the VPN DNS server
+IPs (e.g., 100.100.100.100) — traffic TO those IPs is NOT passed through (still
+intercepted by pf → ctrld enforces profile):
+
+```
+table <vpn_dns> { 100.100.100.100 }
+
+# MagicDNS upstream queries (to 10.0.0.11 etc.) — pass through
+pass out quick on utun13 inet proto udp from any to ! <vpn_dns> port 53
+pass out quick on utun13 inet proto tcp from any to ! <vpn_dns> port 53
+
+# Queries TO MagicDNS (100.100.100.100) — not matched above,
+# falls through to generic rule → intercepted → ctrld → profile enforced
+```
+
+```
+┌──────────────────────────────────────────────────────────────────────┐
+│  SPLIT DNS MODE (with passthrough rules)                             │
+│                                                                      │
+│  Non-VPN domain (popads.net):                                        │
+│  dig popads.net → system routes to 100.100.100.100 on utun13        │
+│  → passthrough rule: dest IS in <vpn_dns> → NOT matched             │
+│  → generic rule: route-to lo0 → rdr → ctrld → profile blocks it ✅  │
+│                                                                      │
+│  VPN domain (vpn-internal.example.com):                             │
+│  dig vpn-internal.example.com → pf intercepts → ctrld                          │
+│  → VPN DNS match → forward to 100.100.100.100 (group exempt)        │
+│  → MagicDNS → upstream 10.0.0.11 on utun13                        │
+│  → passthrough rule: dest NOT in <vpn_dns> → MATCHED → passes ✅    │
+│  → 10.0.0.11 returns correct internal answer (10.0.0.113)        │
+└──────────────────────────────────────────────────────────────────────┘
+```
+
+**Exit mode** (all traffic through VPN):
+
+When Tailscale exit node is enabled, MagicDNS becomes the system's **default**
+resolver (not just supplemental). If we added passthrough rules, ALL DNS would
+bypass ctrld — losing profile enforcement.
+
+Exit mode is detected using two independent signals (either triggers exit mode):
+
+**1. Default route detection (primary, most reliable):**
+Uses `netmon.DefaultRouteInterface()` to check if the system's default route
+(0.0.0.0/0) goes through a VPN DNS interface. If `DefaultRouteInterface` matches
+a VPN DNS interface name (e.g., utun13), the VPN owns the default route — it's
+exit mode. This is the ground truth: the routing table directly reflects whether
+all traffic flows through the VPN, regardless of how the VPN presents itself in
+scutil.
+
+**2. scutil flag detection (secondary, fallback):**
+If the VPN DNS server IP appears in a `scutil --dns` resolver entry that has
+**no search domains** and **no Supplemental flag**, it's acting as the system's
+default resolver (exit mode). This catches edge cases where the default route
+hasn't changed yet but scutil already shows the VPN as the default DNS.
+
+```
+# Non-exit mode — default route on en0, 100.100.100.100 is Supplemental:
+$ route -n get 0.0.0.0 | grep interface
+  interface: en0                        ← physical NIC, not VPN
+resolver #1
+  search domain[0] : vpn.example.com
+  nameserver[0] : 100.100.100.100
+  flags    : Supplemental, Request A records
+
+# Exit mode — default route on utun13, 100.100.100.100 is default resolver:
+$ route -n get 0.0.0.0 | grep interface
+  interface: utun13                     ← VPN interface!
+resolver #2
+  nameserver[0] : 100.100.100.100      ← MagicDNS is default
+  flags    : Request A records          ← no Supplemental!
+```
+
+In exit mode, NO passthrough rules are generated. pf intercepts all DNS → ctrld
+enforces its profile on everything. VPN search domains still resolve correctly
+via ctrld's VPN DNS split routing (forwarded to MagicDNS through the group
+exemption).
+
+#### Summary Table
+
+| Scenario | Passthrough | Profile Enforced | VPN Domains |
+|----------|-------------|-----------------|-------------|
+| No VPN | None | ✅ All traffic | N/A |
+| Split DNS (Tailscale non-exit) | ✅ VPN interface | ✅ Non-VPN domains | ✅ Via MagicDNS |
+| Exit mode (Tailscale exit node) | ❌ None | ✅ All traffic | ✅ Via ctrld split routing |
+| Windscribe | None (different flow) | ✅ All traffic | N/A |
+| Hard intercept | None | ✅ All traffic | ❌ Not forwarded |
+
+### Nuclear Option (Future)
+
+If anchor ordering + interface rules prove insufficient, an alternative approach is available: inject DNS intercept rules directly into the **main pf ruleset** (not inside an anchor). Main ruleset rules are evaluated before ALL anchors, making them impossible for another app to override without explicitly removing them. This is more invasive and not currently implemented, but documented here as a known escalation path.
+
+## Known VPN Conflicts
+
+### F5 BIG-IP APM
+
+F5 BIG-IP APM VPN is a known source of DNS conflicts with ctrld (a known support scenario). The conflict occurs because F5's VPN client aggressively manages DNS:
+
+**How the conflict manifests:**
+
+1. ctrld sets system DNS to `127.0.0.1` / `::1` for local forwarding
+2. F5 VPN connects and **overwrites DNS on all interfaces** by prepending its own servers (e.g., `10.20.30.1`, `10.20.30.2`)
+3. F5 enforces split DNS patterns (e.g., `*.corp.example.com`) and activates its DNS Relay Proxy (`F5FltSrv.exe` / `F5FltSrv.sys`)
+4. ctrld's watchdog detects the change and restores `127.0.0.1` — F5 overwrites again
+5. This loop causes intermittent resolution failures, slow responses, and VPN disconnects
+
+**Why `--intercept-mode dns` solves this:**
+
+- ctrld no longer modifies interface DNS settings — there is nothing for F5 to overwrite
+- WFP (Windows) blocks all outbound DNS except to localhost, so F5's prepended DNS servers are unreachable on port 53
+- F5's DNS Relay Proxy (`F5FltSrv`) becomes irrelevant since no queries reach it
+- In `--intercept-mode dns` mode, F5's split DNS domains (e.g., `*.corp.example.com`) are auto-detected from the VPN adapter and forwarded to F5's DNS servers through ctrld's upstream mechanism
+
+**F5-side mitigations (if `--intercept-mode dns` is not available):**
+
+- In APM Network Access DNS settings, enable **"Allow Local DNS Servers"** (`AllowLocalDNSServersAccess = 1`)
+- Disable **"Enforce DNS Name Resolution Order"**
+- Switch to IP-based split tunneling instead of DNS-pattern-based to avoid activating F5's relay proxy
+- Update F5 to version 17.x+ which includes DNS handling fixes (see F5 KB K80231353)
+
+**Additional considerations:**
+
+- CrowdStrike Falcon and similar endpoint security with network inspection can compound the conflict (three-way DNS stomping)
+- F5's relay proxy (`F5FltSrv`) performs similar functions to ctrld — they are in direct conflict when both active
+- The seemingly random failure pattern is caused by timing-dependent race conditions between ctrld's watchdog, F5's DNS enforcement, and (optionally) endpoint security inspection
+
+### Cisco AnyConnect
+
+Cisco AnyConnect exhibits similar DNS override behavior. `--intercept-mode dns` mode prevents the conflict by operating at the packet filter level rather than competing for interface DNS settings.
+
+### Windscribe Desktop App
+
+Windscribe's macOS firewall implementation (`FirewallController_mac`) replaces the entire pf ruleset when connecting/disconnecting via `pfctl -f`, which wipes ctrld's anchor references and flushes the pf state table (killing active DoH connections). ctrld handles this with multiple defenses:
+
+1. **pf watchdog** detects the wipe and restores anchor rules immediately on network change events (or within 30s via periodic check)
+2. **DoH transport force-reset** immediately replaces upstream transports when a pf wipe is detected (closing old connections + creating new ones synchronously), reducing the DNS blackout from ~5s to ~100ms
+3. **Tunnel interface detection** adds explicit intercept rules for Windscribe's WireGuard interface (e.g., utun420) when it appears
+4. **Dual delayed re-checks** (2s + 4s after network event) catch race conditions where VPN apps modify pf rules and DNS settings asynchronously after the initial network change
+5. **Deferred pf restore** waits for VPN to finish its pf modifications before restoring ctrld's rules, preventing the reconnect death spiral
+6. **Blanket group exemption** (`pass out quick group _ctrld`) ensures all ctrld traffic (including DoH on port 443) passes through VPN firewalls like Windscribe's `block drop all`
+
+## 7. VPN DNS Lifecycle
+
+When VPN software connects or disconnects, ctrld must track DNS state changes to ensure correct routing and avoid stale state.
+
+### Network Change Event Flow (macOS)
+
+```
+Network change detected (netmon callback)
+    │
+    ├─ Immediate actions:
+    │   ├─ ensurePFAnchorActive()      — verify/restore pf anchor references
+    │   ├─ checkTunnelInterfaceChanges() — detect new/removed VPN interfaces
+    │   │   ├─ New tunnel → pfStartStabilization() (wait for VPN to finish pf changes)
+    │   │   └─ Removed tunnel → rebuild anchor immediately (with VPN DNS exemptions)
+    │   └─ vpnDNS.Refresh()            — re-discover VPN DNS from scutil --dns
+    │
+    ├─ Delayed re-check at 2s:
+    │   ├─ ensurePFAnchorActive()      — catch async pf wipes
+    │   ├─ checkTunnelInterfaceChanges()
+    │   ├─ InitializeOsResolver()      — clear stale DNS from scutil
+    │   └─ vpnDNS.Refresh()            — clear stale VPN DNS routes
+    │
+    └─ Delayed re-check at 4s:
+        └─ (same as 2s — catches slower VPN teardowns)
+```
+
+### VPN Connect Sequence
+
+1. VPN creates tunnel interface (e.g., utun420)
+2. Network change fires → `checkTunnelInterfaceChanges()` detects new tunnel
+3. **Stabilization mode** activates — suppresses pf restores while VPN modifies rules
+4. Stabilization loop polls `pfctl -sr` hash every 1.5s
+5. When hash stable for 6s → VPN finished → restore ctrld's pf anchor
+6. `vpnDNS.Refresh()` discovers VPN's search domains and DNS servers from `scutil --dns`
+7. Anchor rebuild includes VPN DNS exemptions (so ctrld can reach VPN DNS on port 53)
+
+### VPN Disconnect Sequence
+
+1. VPN removes tunnel interface
+2. Network change fires → `checkTunnelInterfaceChanges()` detects removal
+3. Anchor rebuilt immediately (no stabilization needed for removals)
+4. VPN app may asynchronously wipe pf rules (`pfctl -f /etc/pf.conf`)
+5. VPN app may asynchronously clean up DNS settings from `scutil --dns`
+6. **2s delayed re-check**: restores pf anchor if wiped, refreshes OS resolver
+7. **4s delayed re-check**: catches slower VPN teardowns
+8. `vpnDNS.Refresh()` returns empty → `onServersChanged(nil)` clears stale exemptions
+9. `InitializeOsResolver()` re-reads `scutil --dns` → clears stale LAN nameservers
+
+### Key Design Decisions
+
+- **`buildPFAnchorRules()` receives VPN DNS servers**: All call sites (tunnel rebuild, watchdog restore, stabilization exit) pass `vpnDNS.CurrentServers()` so exemptions are preserved for still-active VPNs.
+- **`onServersChanged` called even when server list is empty**: Ensures stale pf exemptions from a previous VPN session are cleaned up on disconnect.
+- **OS resolver refresh in delayed re-checks**: VPN apps often finish DNS cleanup 1-3s after the network change event. The delayed `InitializeOsResolver()` call ensures stale LAN nameservers (e.g., a VPN's DNS IP (e.g., 10.255.255.3)) don't cause 2s query timeouts.
+- **Ordering: tunnel checks → VPN DNS refresh → delayed re-checks**: Ensures anchor rebuilds from tunnel changes include current VPN DNS exemptions.
+
+## Related
+
+- F5 BIG-IP APM VPN DNS conflict (a known support scenario)

docs/known-issues.md

@@ -0,0 +1,42 @@
+# Known Issues
+
+This document outlines known issues with ctrld and their current status, workarounds, and recommendations.
+
+## macOS (Darwin) Issues
+
+### Self-Upgrade Issue on Darwin 15.5
+
+**Issue**: ctrld self-upgrading functionality may not work on macOS Darwin 15.5.
+
+**Status**: Under investigation
+
+**Description**: Users on macOS Darwin 15.5 may experience issues when ctrld attempts to perform automatic self-upgrades. The upgrade process would be triggered, but ctrld won't be upgraded.
+
+**Workarounds**:
+1. **Recommended**: Upgrade your macOS system to Darwin 15.6 or later, which has been tested and verified to work correctly with ctrld self-upgrade functionality.
+2. **Alternative**: Run `ctrld upgrade prod` directly to manually upgrade ctrld to the latest version on Darwin 15.5.
+
+**Affected Versions**: ctrld v1.4.2 and later on macOS Darwin 15.5
+
+**Last Updated**: 05/09/2025
+
+---
+
+## Contributing to Known Issues
+
+If you encounter an issue not listed here, please:
+
+1. Check the [GitHub Issues](https://github.com/Control-D-Inc/ctrld/issues) to see if it's already reported
+2. If not reported, create a new issue with:
+   - Detailed description of the problem
+   - Steps to reproduce
+   - Expected vs actual behavior
+   - System information (OS, version, architecture)
+   - ctrld version
+
+## Issue Status Legend
+
+- **Under investigation**: Issue is confirmed and being analyzed
+- **Workaround available**: Temporary solution exists while permanent fix is developed
+- **Fixed**: Issue has been resolved in a specific version
+- **Won't fix**: Issue is acknowledged but will not be addressed due to technical limitations or design decisions

docs/pf-dns-intercept.md

@@ -0,0 +1,380 @@
+# macOS pf DNS Interception — Technical Reference
+
+## Overview
+
+ctrld uses macOS's built-in packet filter (pf) to intercept all DNS traffic at the kernel level, redirecting it to ctrld's local listeners at `127.0.0.1:53` (IPv4) and `[::1]:53` (IPv6). This operates below interface DNS settings, making it immune to VPN software (F5, Cisco, GlobalProtect, etc.) that overwrites DNS on network interfaces.
+
+## How pf Works (Relevant Basics)
+
+pf is a stateful packet filter built into macOS (and BSD). It processes packets through a pipeline with **strict rule ordering**:
+
+```
+options (set) → normalization (scrub) → queueing → translation (nat/rdr) → filtering (pass/block)
+```
+
+**Anchors** are named rule containers that allow programs to manage their own rules without modifying the global ruleset. Each anchor type must appear in the correct section:
+
+| Anchor Type | Section | Purpose |
+|-------------|---------|---------|
+| `scrub-anchor` | Normalization | Packet normalization |
+| `nat-anchor` | Translation | NAT rules |
+| `rdr-anchor` | Translation | Redirect rules |
+| `anchor` | Filtering | Pass/block rules |
+
+**Critical constraint:** If you place a `rdr-anchor` line after an `anchor` line, pf rejects the entire config with "Rules must be in order."
+
+## Why We Can't Just Use `rdr on ! lo0`
+
+The obvious approach:
+```
+rdr pass on ! lo0 proto udp from any to any port 53 -> 127.0.0.1 port 53
+```
+
+**This doesn't work.** macOS pf `rdr` rules only apply to *forwarded/routed* traffic — packets passing through the machine to another destination. DNS queries originating from the machine itself (locally-originated) are never matched by `rdr` on non-loopback interfaces.
+
+This is a well-known pf limitation on macOS/BSD. It means the VPN client's DNS queries would be redirected (if routed through the machine), but the user's own applications querying DNS directly would not.
+
+## Our Approach: route-to + rdr (Two-Step)
+
+We use a two-step technique to intercept locally-originated DNS:
+
+```
+Step 1: Force outbound DNS through loopback
+  pass out quick on ! lo0 route-to lo0 inet proto udp from any to ! 127.0.0.1 port 53
+
+Step 2: Pass the packet outbound on lo0 (needed when VPN firewalls have "block drop all")
+  pass out quick on lo0 inet proto udp from any to ! 127.0.0.1 port 53 no state
+
+Step 3: Redirect it on loopback to ctrld's listener
+  rdr on lo0 inet proto udp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+
+Step 4: Accept and create state for response routing
+  pass in quick on lo0 reply-to lo0 inet proto { udp, tcp } from any to 127.0.0.1 port 53
+```
+
+> **State handling is critical for VPN firewall coexistence:**
+> - **route-to**: `keep state` (default). State is interface-bound on macOS — doesn't match on lo0.
+> - **pass out lo0**: `no state`. If this created state, it would match inbound on lo0 and bypass rdr.
+> - **rdr**: no `pass` keyword. Packet must go through filter so `pass in` can create response state.
+> - **pass in lo0**: `keep state` (default). Creates the ONLY state on lo0 — handles response routing.
+
+### Packet Flow
+
+```
+Application queries 10.255.255.3:53 (e.g., VPN DNS server)
+    ↓
+Kernel: outbound on en0 (or utun420 for VPN)
+    ↓
+pf filter: "pass out route-to lo0 ... port 53" → redirects to lo0, creates state on en0
+    ↓
+pf filter (outbound lo0): "pass out on lo0 ... no state" → passes, NO state created
+    ↓
+Loopback reflects packet inbound on lo0
+    ↓
+pf rdr (inbound lo0): "rdr on lo0 ... port 53 -> 127.0.0.1:53" → rewrites destination
+    ↓
+pf filter (inbound lo0): "pass in reply-to lo0 ... to 127.0.0.1:53" → creates state + reply route
+    ↓
+ctrld receives query on 127.0.0.1:53
+    ↓
+ctrld resolves via DoH (port 443, exempted by group _ctrld)
+    ↓
+Response from ctrld: 127.0.0.1:53 → 100.94.163.168:54851
+    ↓
+reply-to lo0: forces response through lo0 (without this, kernel routes via utun420 → lost in VPN tunnel)
+    ↓
+pf applies rdr reverse NAT: src 127.0.0.1 → 10.255.255.3
+    ↓
+Application receives response from 10.255.255.3:53 ✓
+```
+
+### Why This Works
+
+1. `route-to lo0` forces the packet onto loopback at the filter stage
+2. `pass out on lo0 no state` gets past VPN "block drop all" without creating state
+3. No state on lo0 means rdr gets fresh evaluation on the inbound pass
+4. `reply-to lo0` on `pass in` forces the response through lo0 — without it, the kernel routes the response to VPN tunnel IPs via the VPN interface and it's lost
+4. `rdr` (without `pass`) redirects then hands off to filter rules
+5. `pass in keep state` creates the response state — the only state on the lo0 path
+6. Traffic already destined for `127.0.0.1` is excluded (`to ! 127.0.0.1`) to prevent loops
+7. ctrld's own upstream queries use DoH (port 443), bypassing port 53 rules entirely
+
+### Why Each State Decision Matters
+
+| Rule | State | Why |
+|------|-------|-----|
+| route-to on en0/utun | keep state | Needed for return routing. Interface-bound, won't match on lo0. |
+| pass out on lo0 | **no state** | If stateful, it would match inbound lo0 → bypass rdr → DNS broken |
+| rdr on lo0 | N/A (no pass) | Must go through filter so pass-in creates response state |
+| pass in on lo0 | keep state + reply-to lo0 | Creates lo0 state. `reply-to` forces response through lo0 (not VPN tunnel). |
+
+## IPv6 DNS Interception
+
+macOS systems with IPv6 nameservers (common — `scutil --dns` often shows an IPv6 nameserver at index 0) send DNS queries over IPv6. Without IPv6 interception, these queries bypass ctrld, causing ~1s delays (the IPv6 query times out, then the app falls back to IPv4).
+
+### Why IPv6 Needs Special Handling
+
+Three problems prevent a simple "mirror the IPv4 rules" approach:
+
+1. **Cross-AF redirect is impossible**: pf cannot `rdr on lo0 inet6 ... -> 127.0.0.1` (redirecting IPv6 to IPv4). ctrld must listen on `[::1]` to handle IPv6 DNS.
+
+2. **`block return` is ineffective for IPv6 DNS**: BSD doesn't deliver ICMPv6 unreachable errors to unconnected UDP sockets (which `dig` and most resolvers use). So `block return out inet6 ... port 53` generates the ICMP error, but the application never receives it — it waits for the full timeout (~1s).
+
+3. **sendmsg from `[::1]` to global unicast fails**: Unlike IPv4 where the kernel allows `sendmsg` from `127.0.0.1` to local private IPs (e.g., `10.x.x.x`), macOS/BSD rejects `sendmsg` from `[::1]` to a global unicast IPv6 address with `EINVAL`. Since pf's `rdr` preserves the original source IP (the machine's global IPv6 address), ctrld's reply would fail.
+
+### Solution: nat + rdr + [::1] Listener
+
+```
+# NAT: rewrite source to ::1 so ctrld can reply
+nat on lo0 inet6 proto udp from ! ::1 to ! ::1 port 53 -> ::1
+nat on lo0 inet6 proto tcp from ! ::1 to ! ::1 port 53 -> ::1
+
+# RDR: redirect destination to ctrld's IPv6 listener
+rdr on lo0 inet6 proto udp from any to ! ::1 port 53 -> ::1 port 53
+rdr on lo0 inet6 proto tcp from any to ! ::1 port 53 -> ::1 port 53
+
+# Filter: route-to forces IPv6 DNS to loopback (mirrors IPv4 rules)
+pass out quick on ! lo0 route-to lo0 inet6 proto udp from any to ! ::1 port 53
+pass out quick on ! lo0 route-to lo0 inet6 proto tcp from any to ! ::1 port 53
+
+# Pass on lo0 without state (mirrors IPv4)
+pass out quick on lo0 inet6 proto udp from any to ! ::1 port 53 no state
+pass out quick on lo0 inet6 proto tcp from any to ! ::1 port 53 no state
+
+# Accept redirected IPv6 DNS with reply-to (mirrors IPv4)
+pass in quick on lo0 reply-to lo0 inet6 proto { udp, tcp } from any to ::1 port 53
+```
+
+### IPv6 Packet Flow
+
+```
+Application queries [2607:f0c8:8000:8210::1]:53 (IPv6 DNS server)
+    ↓
+pf filter: "pass out route-to lo0 inet6 ... port 53" → redirects to lo0
+    ↓
+pf (outbound lo0): "pass out on lo0 inet6 ... no state" → passes
+    ↓
+Loopback reflects packet inbound on lo0
+    ↓
+pf nat: rewrites source 2607:f0c8:...:ec6e → ::1
+pf rdr: rewrites dest [2607:f0c8:8000:8210::1]:53 → [::1]:53
+    ↓
+ctrld receives query from [::1]:port → [::1]:53
+    ↓
+ctrld resolves via DoH, replies to [::1]:port (kernel accepts ::1 → ::1)
+    ↓
+pf reverses both translations:
+  - nat reverse: dest ::1 → 2607:f0c8:...:ec6e (original client)
+  - rdr reverse: src ::1 → 2607:f0c8:8000:8210::1 (original DNS server)
+    ↓
+Application receives response from [2607:f0c8:8000:8210::1]:53 ✓
+```
+
+### Client IP Recovery
+
+The `nat` rewrites the source to `::1`, so ctrld sees the client as `::1` (loopback). The existing `spoofLoopbackIpInClientInfo()` logic detects this and replaces it with the machine's real RFC1918 IPv4 address (e.g., `10.0.10.211`). This is the same mechanism used when queries arrive from `127.0.0.1` — no client identity is lost.
+
+### IPv6 Listener
+
+The `[::1]` listener reuses the existing infrastructure from Windows (where it was added for the same reason — can't suppress IPv6 DNS resolvers from the system config). The `needLocalIPv6Listener()` function gates it, returning `true` on:
+- **Windows**: Always (if IPv6 is available)
+- **macOS**: Only in intercept mode
+
+If the `[::1]` listener fails to bind, it logs a warning and continues — the IPv4 listener is primary.
+
+### nat-anchor Requirement
+
+The `nat` rules in our anchor require a `nat-anchor "com.controld.ctrld"` reference in the main pf ruleset, in addition to the existing `rdr-anchor` and `anchor` references. All pf management functions (inject, remove, verify, watchdog, force-reload) handle all three anchor types.
+
+## Rule Ordering Within the Anchor
+
+pf requires translation rules before filter rules, even within an anchor:
+
+```pf
+# === Translation rules (MUST come first) ===
+rdr on lo0 inet proto udp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+rdr on lo0 inet proto tcp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+
+# === Exemptions (filter phase, scoped to _ctrld group) ===
+pass out quick on ! lo0 inet proto { udp, tcp } from any to <OS_RESOLVER_IP> port 53 group _ctrld
+pass out quick on ! lo0 inet proto { udp, tcp } from any to <VPN_DNS_IP> port 53 group _ctrld
+
+# === Main intercept (filter phase) ===
+pass out quick on ! lo0 route-to lo0 inet proto udp from any to ! 127.0.0.1 port 53
+pass out quick on ! lo0 route-to lo0 inet proto tcp from any to ! 127.0.0.1 port 53
+
+# === Allow redirected traffic on loopback ===
+pass in quick on lo0 reply-to lo0 inet proto { udp, tcp } from any to 127.0.0.1 port 53
+```
+
+### Exemption Mechanism (Group-Scoped)
+
+Some IPs must bypass the redirect:
+
+- **OS resolver nameservers** (e.g., DHCP-assigned DNS): ctrld's recovery/bootstrap path may query these on port 53. Without exemption, these queries loop back to ctrld.
+- **VPN DNS servers**: When ctrld forwards VPN-specific domains (split DNS) to the VPN's internal DNS, those queries must reach the VPN DNS server directly.
+
+Exemptions use `pass out quick` with `group _ctrld` **before** the `route-to` rule. The `group _ctrld` constraint ensures that **only ctrld's own process** can bypass the redirect — other applications cannot circumvent DNS interception by querying the exempted IPs directly. Because pf evaluates filter rules in order and `quick` terminates evaluation, the exempted packet goes directly out the real interface and never hits the `route-to` or `rdr`.
+
+### The `_ctrld` Group
+
+To scope pf exemptions to ctrld's process only, we use a dedicated macOS system group:
+
+1. **Creation**: On startup, `ensureCtrldGroup()` creates a `_ctrld` system group via `dscl` (macOS Directory Services) if it doesn't already exist. The GID is chosen from the 350-450 range to avoid conflicts with Apple's reserved ranges. The function is idempotent.
+
+2. **Process GID**: Before loading pf rules, ctrld sets its effective GID to `_ctrld` via `syscall.Setegid()`. All sockets created by ctrld after this point are tagged with this GID.
+
+3. **pf matching**: Exemption rules include `group _ctrld`, so pf only allows bypass for packets from processes with this effective GID. Other processes querying the same exempt IPs are still redirected to ctrld.
+
+4. **Lifecycle**: The group is **never removed** on shutdown or uninstall. It's a harmless system group, and leaving it avoids race conditions during rapid restart cycles. It is recreated (no-op if exists) on every start.
+
+## Anchor Injection into pf.conf
+
+The trickiest part. macOS only processes anchors declared in the active pf ruleset. We must inject our anchor references into the running config.
+
+### What We Do
+
+1. Read `/etc/pf.conf`
+2. If our anchor reference already exists, reload as-is
+3. Otherwise, inject `nat-anchor "com.controld.ctrld"` and `rdr-anchor "com.controld.ctrld"` in the translation section and `anchor "com.controld.ctrld"` in the filter section
+4. Write to a **temp file** and load with `pfctl -f <tmpfile>`
+5. **We never modify `/etc/pf.conf` on disk** — changes are runtime-only and don't survive reboot (ctrld re-injects on every start)
+
+### Injection Logic
+
+Finding the right insertion point requires understanding the existing pf.conf structure. The algorithm:
+
+1. **Scan** for existing `rdr-anchor`/`nat-anchor`/`binat-anchor` lines (translation section) and `anchor` lines (filter section)
+2. **Insert `rdr-anchor`**:
+   - Before the first existing `rdr-anchor` line (if any exist)
+   - Else before the first `anchor` line (translation must come before filtering)
+   - Else before the first `pass`/`block` line
+   - Last resort: append (but this should never happen with a valid pf.conf)
+3. **Insert `anchor`**:
+   - Before the first existing `anchor` line (if any)
+   - Else before the first `pass`/`block` line
+   - Last resort: append
+
+### Real-World pf.conf Scenarios
+
+We test against these configurations:
+
+#### Default macOS (Sequoia/Sonoma)
+```
+scrub-anchor "com.apple/*"
+nat-anchor "com.apple/*"
+rdr-anchor "com.apple/*"
+anchor "com.apple/*"
+load anchor "com.apple" from "/etc/pf.anchors/com.apple"
+```
+Our `rdr-anchor` goes before `rdr-anchor "com.apple/*"`, our `anchor` goes before `anchor "com.apple/*"`.
+
+#### Little Snitch
+Adds `rdr-anchor "com.obdev.littlesnitch"` and `anchor "com.obdev.littlesnitch"` in the appropriate sections. Our anchors coexist — pf processes multiple anchors in order.
+
+#### Lulu Firewall (Objective-See)
+Adds `anchor "com.objective-see.lulu"`. We insert `rdr-anchor` before it (translation before filtering) and `anchor` before it.
+
+#### Cisco AnyConnect
+Adds `nat-anchor "com.cisco.anyconnect"`, `rdr-anchor "com.cisco.anyconnect"`, `anchor "com.cisco.anyconnect"`. Our anchors insert alongside Cisco's in their respective sections.
+
+#### Minimal pf.conf (no anchors)
+Just `set skip on lo0` and `pass all`. We insert `rdr-anchor` and `anchor` before the `pass` line.
+
+#### Empty pf.conf
+Both anchors appended. This is a degenerate case that shouldn't occur in practice.
+
+## Failure Modes and Safety
+
+### What happens if our injection fails?
+- `ensurePFAnchorReference` returns an error, logged as a warning
+- ctrld continues running but DNS interception may not work
+- The anchor file and rules are cleaned up on shutdown
+- **No damage to existing pf config** — we never modify files on disk
+
+### What happens if ctrld crashes (SIGKILL)?
+- pf anchor rules persist in kernel memory
+- DNS is redirected to 127.0.0.1:53 but nothing is listening → DNS breaks
+- On next `ctrld start`, we detect the stale anchor file, flush the anchor, and start fresh
+- Without ctrld restart: `sudo pfctl -a com.controld.ctrld -F all` manually clears it
+
+### What if another program flushes all pf rules?
+- Our anchor references are removed from the running config
+- DNS interception stops (traffic goes direct again — fails open, not closed)
+- The periodic watchdog (30s) detects missing rules and restores them
+- ctrld continues working for queries sent to 127.0.0.1 directly
+
+### What if another program reloads pf.conf (corrupting translation state)?
+Programs like Parallels Desktop reload `/etc/pf.conf` when creating or destroying
+virtual network interfaces (bridge100, vmenet0). This can corrupt pf's internal
+translation engine — **rdr rules survive in text form but stop evaluating**.
+The watchdog's rule-text checks say "intact" while DNS is silently broken.
+
+**Detection:** ctrld detects interface appearance/disappearance in the network
+change handler and spawns an asynchronous interception probe monitor:
+
+1. A subprocess sends a DNS query WITHOUT the `_ctrld` group GID, so pf
+   intercept rules apply to it
+2. If ctrld receives the query → pf interception is working
+3. If the query times out (1s) → pf translation is broken
+4. On failure: `forceReloadPFMainRuleset()` does `pfctl -f -` with the current
+   running ruleset, resetting pf's translation engine
+
+The monitor probes with exponential backoff (0, 0.5, 1, 2, 4s) to win the race
+against async pf reloads. Only one monitor runs at a time (singleton). The
+watchdog also runs the probe every 30s as a safety net.
+
+The full pf reload is VPN-safe: it reassembles from `pfctl -sr` + `pfctl -sn`
+(the current running state), preserving all existing anchors and rules.
+
+### What if another program adds conflicting rdr rules?
+- pf processes anchors in declaration order
+- If another program redirects port 53 before our anchor, their redirect wins
+- If after, ours wins (first match with `quick` or `rdr pass`)
+- Our maximum-weight sublayer approach on Windows (WFP) doesn't apply to pf — pf uses rule ordering, not weights
+
+### What about `set skip on lo0`?
+Some pf.conf files include `set skip on lo0` which tells pf to skip ALL processing on loopback. **This would break our approach** since both the `rdr on lo0` and `pass in on lo0` rules would be skipped.
+
+**Mitigation:** When injecting anchor references via `ensurePFAnchorReference()`,
+we strip `lo0` from any `set skip on` directives before reloading. The watchdog
+also checks for `set skip on lo0` and triggers a restore if detected. The
+interception probe provides an additional safety net — if `set skip on lo0` gets
+re-applied by another program, the probe will fail and trigger a full reload.
+
+## Cleanup
+
+On shutdown (`stopDNSIntercept`):
+1. `pfctl -a com.controld.ctrld -F all` — flush all rules from our anchor
+2. Remove `/etc/pf.anchors/com.controld.ctrld` anchor file
+3. `pfctl -f /etc/pf.conf` — reload original pf.conf, removing our injected anchor references from the running config
+
+This is clean: no files modified on disk, no residual rules.
+
+## Comparison with Other Approaches
+
+| Approach | Intercepts local DNS? | Survives VPN DNS override? | Risk of loops? | Complexity |
+|----------|----------------------|---------------------------|----------------|------------|
+| `rdr on ! lo0` | ❌ No | Yes | Low | Low |
+| `route-to lo0` + `rdr on lo0` | ✅ Yes | Yes | Medium (need exemptions) | Medium |
+| `/etc/resolver/` | Partial (per-domain only) | No (VPN can overwrite) | Low | Low |
+| `NEDNSProxyProvider` | ✅ Yes | Yes | Low | High (needs app bundle) |
+| NRPT (Windows only) | N/A | Partial | Low | Medium |
+
+We chose `route-to + rdr` as the best balance of effectiveness and deployability (no app bundle needed, no kernel extension, works with existing ctrld binary).
+
+## Key pf Nuances Learned
+
+1. **`rdr` doesn't match locally-originated traffic** — this is the biggest gotcha
+2. **Rule ordering is enforced** — translation before filtering, always
+3. **Anchors must be declared in the main ruleset** — just loading an anchor file isn't enough
+4. **`rdr` without `pass`** — redirected packets must go through filter rules so `pass in keep state` can create response state. `rdr pass` alone is insufficient for response delivery.
+5. **State handling is nuanced** — route-to uses `keep state` (state is floating). `pass out on lo0` must use `no state` (prevents rdr bypass). `pass in on lo0` uses `keep state` + `reply-to lo0` (creates response state AND forces response through loopback instead of VPN tunnel). Getting any of these wrong breaks either the forward or return path.
+6. **`quick` terminates evaluation** — exemption rules must use `quick` and appear before the route-to rule
+7. **Piping to `pfctl -f -` can fail** — special characters in pf.conf content cause issues; use temp files
+8. **`set skip on lo0` would break us** — but it's not in default macOS pf.conf
+9. **`pass out quick` exemptions work with route-to** — they fire in the same phase (filter), so `quick` + rule ordering means exempted packets never hit the route-to rule
+10. **pf cannot cross-AF redirect** — `rdr on lo0 inet6 ... -> 127.0.0.1` is invalid. IPv6 DNS must be handled by an `[::1]` listener.
+11. **`block return` doesn't work for IPv6 DNS** — BSD doesn't deliver ICMPv6 unreachable to unconnected UDP sockets (`sendto`). Apps timeout waiting for a response that never comes.
+12. **sendmsg from `::1` to global unicast fails on macOS** — unlike IPv4 where `127.0.0.1` can send to any local address, `::1` cannot send to the machine's own global IPv6 address. `nat` on lo0 is required to rewrite the source.
+13. **`nat-anchor` is separate from `rdr-anchor`** — pf requires both in the main ruleset for nat and rdr rules in an anchor to be evaluated. `rdr-anchor` alone does not cover nat rules.

docs/runtime-internal-logging.md

@@ -0,0 +1,46 @@
+# Runtime Internal Logging
+
+When no logging is configured (i.e., `log_path` is not set), ctrld automatically enables an internal logging system. This system stores logs in memory to provide troubleshooting information when problems occur.
+
+## Purpose
+
+The runtime internal logging system is designed primarily for **ctrld developers**, not end users. It captures detailed diagnostic information that can be useful for troubleshooting issues when they arise, especially in production environments where explicit logging may not be configured.
+
+## When It's Enabled
+
+Internal logging is automatically enabled when:
+
+- ctrld is running in Control D mode (i.e., `--cd` flag is provided)
+- No log file is configured (i.e., `log_path` is empty or not set)
+
+If a log file is explicitly configured via `log_path`, internal logging will **not** be enabled, as the configured log file serves the logging purpose.
+
+## How It Works
+
+The internal logging system:
+
+- Stores logs in **in-memory buffers** (not written to disk)
+- Captures logs at **debug level** for normal operations and **warn level** for warnings
+- Maintains separate buffers for normal logs and warning logs
+- Automatically manages buffer size to prevent unbounded memory growth
+- Preserves initialization logs even when buffers overflow
+
+## Configuration
+
+**Important**: The `log_level` configuration option does **not** affect the internal logging system. Internal logging always operates at debug level for normal logs and warn level for warnings, regardless of the `log_level` setting in the configuration file.
+
+The `log_level` setting only affects:
+- Console output (when running interactively)
+- File-based logging (when `log_path` is configured)
+
+## Accessing Internal Logs
+
+Internal logs can be accessed through the control server API endpoints. This functionality is intended for developers and support personnel who need to diagnose issues.
+
+## Notes
+
+- Internal logging is **not** a replacement for proper log file configuration in production environments
+- For production deployments, it is recommended to configure `log_path` to enable persistent file-based logging
+- Internal logs are stored in memory and will be lost if the process terminates unexpectedly
+- The internal logging system is automatically disabled when explicit logging is configured
+

docs/username-detection.md

@@ -0,0 +1,126 @@
+# Username Detection in ctrld
+
+## Overview
+
+The ctrld client needs to detect the primary user of a system for telemetry and configuration purposes. This is particularly challenging in RMM (Remote Monitoring and Management) deployments where traditional session-based detection methods fail.
+
+## The Problem
+
+In traditional desktop environments, username detection is straightforward using environment variables like `$USER`, `$LOGNAME`, or `$SUDO_USER`. However, RMM deployments present unique challenges:
+
+- **No active login session**: RMM agents often run as system services without an associated user session
+- **Missing environment variables**: Common user environment variables are not available in service contexts
+- **Root/SYSTEM execution**: The ctrld process may run with elevated privileges, masking the actual user
+
+## Solution Approach
+
+ctrld implements a multi-tier, deterministic username detection system through the `DiscoverMainUser()` function with platform-specific implementations:
+
+### Key Principles
+
+1. **Deterministic selection**: No randomness - always returns the same result for the same system state
+2. **Priority chain**: Multiple detection methods with clear fallback order
+3. **Lowest UID/RID wins**: Among multiple candidates, select the user with the lowest identifier (typically the first user created)
+4. **Fast execution**: All operations complete in <100ms using local system resources
+5. **Debug logging**: Each decision point logs its rationale for troubleshooting
+
+## Platform-Specific Implementation
+
+### macOS (`discover_user_darwin.go`)
+
+**Detection chain:**
+1. **Console owner** (`stat -f %Su /dev/console`) - Most reliable for active GUI sessions
+2. **scutil ConsoleUser** - Alternative session detection via System Configuration framework
+3. **Directory Services scan** (`dscl . list /Users UniqueID`) - Scan all users with UID ≥ 501, select lowest
+
+**Rationale**: macOS systems typically have a primary user who owns the console. Service contexts can still access device ownership information.
+
+### Linux (`discover_user_linux.go`)
+
+**Detection chain:**
+1. **loginctl active users** (`loginctl list-users`) - systemd's session management
+2. **Admin user preference** - Parse `/etc/passwd` for UID ≥ 1000, prefer sudo/wheel/admin group members
+3. **Lowest UID fallback** - From `/etc/passwd`, select user with UID ≥ 1000 and lowest UID
+
+**Rationale**: Linux systems may have multiple regular users. Prioritize users in administrative groups as they're more likely to be primary system users.
+
+### Windows (`discover_user_windows.go`)
+
+**Detection chain:**
+1. **Active console session** (`WTSGetActiveConsoleSessionId` + `WTSQuerySessionInformation`) - Direct Windows API for active user
+2. **Registry admin preference** - Scan `HKLM\SOFTWARE\Microsoft\Windows NT\CurrentVersion\ProfileList`, prefer Administrators group members
+3. **Lowest RID fallback** - From ProfileList, select user with RID ≥ 1000 and lowest RID
+
+**Rationale**: Windows has well-defined APIs for session management. Registry ProfileList provides a complete view of all user accounts when no active session exists.
+
+### Other Platforms (`discover_user_others.go`)
+
+Returns `"unknown"` - placeholder for unsupported platforms.
+
+## Implementation Details
+
+### Error Handling
+
+- Individual detection methods log failures at Debug level and continue to next method
+- Only final failure (all methods failed) is noteworthy
+- Graceful degradation ensures the system continues operating with `"unknown"` user
+
+### Performance Considerations
+
+- Registry/file parsing uses native Go where possible
+- External command execution limited to necessary cases
+- No network calls or blocking operations
+- Timeout context honored for all operations
+
+### Security
+
+- No privilege escalation required
+- Read-only operations on system resources
+- No user data collected beyond username
+- Respects system access controls
+
+## Testing Scenarios
+
+This implementation addresses these common RMM scenarios:
+
+1. **Windows Service context**: No interactive user session, service running as SYSTEM
+2. **Linux systemd service**: No login session, running as root daemon
+3. **macOS LaunchDaemon**: No GUI user context, running as root
+4. **Multi-user systems**: Multiple valid candidates, deterministic selection
+5. **Minimalist systems**: Limited user accounts, fallback to available options
+
+## Metadata Submission Strategy
+
+System metadata (OS, chassis, username, domain) is sent to the Control D API via POST `/utility`. To avoid duplicate submissions and minimize EDR-triggering user discovery, ctrld uses a tiered approach:
+
+### When metadata is sent
+
+| Scenario | Metadata sent? | Username included? |
+|---|---|---|
+| `ctrld start` with `--cd-org` (provisioning via `cdUIDFromProvToken`) | ✅ Full | ✅ Yes |
+| `ctrld run` startup (config validation / processCDFlags) | ✅ Lightweight | ❌ No |
+| Runtime config reload (`doReloadApiConfig`) | ✅ Lightweight | ❌ No |
+| Runtime self-uninstall check | ✅ Lightweight | ❌ No |
+| Runtime deactivation pin refresh | ✅ Lightweight | ❌ No |
+
+Username is only collected and sent once — during initial provisioning via `cdUIDFromProvToken()`. All other API calls use `SystemMetadataRuntime()` which omits username discovery entirely.
+
+### Runtime metadata (`SystemMetadataRuntime`)
+
+Runtime API calls (config reload, self-uninstall check, deactivation pin refresh) use `SystemMetadataRuntime()` which includes OS and chassis info but **skips username discovery**. This avoids:
+
+- **EDR false positives**: Repeated user enumeration (registry scans, WTS queries, loginctl calls) can trigger endpoint detection and response alerts
+- **Unnecessary work**: Username is unlikely to change while the service is running
+
+## Migration Notes
+
+The previous `currentLoginUser()` function has been replaced by `DiscoverMainUser()` with these changes:
+
+- **Removed dependencies**: No longer uses `logname(1)`, environment variables as primary detection
+- **Added platform specificity**: Separate files for each OS with optimized detection logic  
+- **Improved RMM compatibility**: Designed specifically for service/daemon contexts
+- **Maintained compatibility**: Returns same format (string username or "unknown")
+
+## Future Extensions
+
+This architecture allows easy addition of new platforms by creating additional `discover_user_<os>.go` files following the same interface pattern.

docs/wfp-dns-intercept.md

@@ -0,0 +1,449 @@
+# Windows DNS Intercept — Technical Reference
+
+## Overview
+
+On Windows, DNS intercept mode uses a two-layer architecture:
+
+- **`dns` mode (default)**: NRPT only — graceful DNS routing via the Windows DNS Client service
+- **`hard` mode**: NRPT + WFP — full enforcement with kernel-level block filters
+
+This dual-mode design ensures that `dns` mode can never break DNS (at worst, a VPN
+overwrites NRPT and queries bypass ctrld temporarily), while `hard` mode provides
+the same enforcement guarantees as macOS pf.
+
+## Architecture: dns vs hard Mode
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│                     dns mode (NRPT only)                        │
+│                                                                 │
+│  App DNS query → DNS Client service → NRPT lookup               │
+│     → "." catch-all matches → forward to 127.0.0.1 (ctrld)    │
+│                                                                 │
+│  If VPN clears NRPT: health monitor re-adds within 30s         │
+│  Worst case: queries go to VPN DNS until NRPT restored          │
+│  DNS never breaks — graceful degradation                        │
+└─────────────────────────────────────────────────────────────────┘
+
+┌─────────────────────────────────────────────────────────────────┐
+│                     hard mode (NRPT + WFP)                      │
+│                                                                 │
+│  App DNS query → DNS Client service → NRPT → 127.0.0.1 (ctrld)│
+│                                                                 │
+│  Bypass attempt (raw 8.8.8.8:53) → WFP BLOCK filter            │
+│  VPN DNS on private IP → WFP subnet PERMIT filter → allowed    │
+│                                                                 │
+│  NRPT must be active before WFP starts (atomic guarantee)       │
+│  If NRPT fails → WFP not started (avoids DNS blackhole)         │
+│  If WFP fails → NRPT rolled back (all-or-nothing)              │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+## NRPT (Name Resolution Policy Table)
+
+### What It Does
+
+NRPT is a Windows feature (originally for DirectAccess) that tells the DNS Client
+service to route queries matching specific namespace patterns to specific DNS servers.
+ctrld adds a catch-all rule that routes ALL DNS to `127.0.0.1`:
+
+| Registry Value | Type | Value | Purpose |
+|---|---|---|---|
+| `Name` | REG_MULTI_SZ | `.` | Namespace (`.` = catch-all) |
+| `GenericDNSServers` | REG_SZ | `127.0.0.1` | Target DNS server |
+| `ConfigOptions` | REG_DWORD | `0x8` | Standard DNS resolution |
+| `Version` | REG_DWORD | `0x2` | NRPT rule version 2 |
+| `Comment` | REG_SZ | `` | Empty (matches PowerShell behavior) |
+| `DisplayName` | REG_SZ | `` | Empty (matches PowerShell behavior) |
+| `IPSECCARestriction` | REG_SZ | `` | Empty (matches PowerShell behavior) |
+
+### Registry Paths — GP vs Local (Critical)
+
+Windows NRPT has two registry paths with **all-or-nothing** precedence:
+
+| Path | Name | Mode |
+|---|---|---|
+| `HKLM\SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig` | **GP path** | Group Policy mode |
+| `HKLM\SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig` | **Local path** | Local/service store mode |
+
+**Precedence rule**: If ANY rules exist in the GP path (from IT policy, VPN, MDM,
+or our own earlier builds), DNS Client enters "GP mode" and **ignores ALL local-path
+rules entirely**. This is not per-rule — it's a binary switch.
+
+**Consequence**: On non-domain-joined (WORKGROUP) machines, `RefreshPolicyEx` is
+unreliable. If we write to the GP path, DNS Client enters GP mode but the rules
+never activate — resulting in `Get-DnsClientNrptPolicy` returning empty even though
+`Get-DnsClientNrptRule` shows the rule in registry.
+
+ctrld uses an adaptive strategy (matching [Tailscale's approach](https://github.com/tailscale/tailscale/blob/main/net/dns/nrpt_windows.go)):
+
+1. **Always write to the local path** using a deterministic GUID key name
+   (`{B2E9A3C1-7F4D-4A8E-9D6B-5C1E0F3A2B8D}`). This is the baseline that works
+   on all non-domain machines.
+2. **Check if other software has GP NRPT rules** (`otherGPRulesExist()`). If
+   foreign GP rules are present (IT policy, VPN), DNS Client is already in GP mode
+   and our local rule would be invisible — so we also write to the GP path.
+3. **If no foreign GP rules exist**, clean any stale ctrld GP rules and delete
+   the empty GP parent key. This ensures DNS Client stays in "local mode" where
+   the local-path rule activates immediately via `paramchange`.
+
+### VPN Coexistence
+
+NRPT uses most-specific-match. VPN NRPT rules for specific domains (e.g.,
+`*.corp.local` → `10.20.30.1`) take priority over ctrld's `.` catch-all.
+This means VPN split DNS works naturally — VPN-specific domains go to VPN DNS,
+everything else goes to ctrld. No exemptions or special handling needed.
+
+### DNS Client Notification
+
+After writing NRPT rules, DNS Client must be notified to reload:
+
+1. **`paramchange`**: `sc control dnscache paramchange` — signals DNS Client to
+   re-read configuration. Works for local-path rules on most machines.
+2. **`RefreshPolicyEx`**: `RefreshPolicyEx(bMachine=TRUE, dwOptions=RP_FORCE)` from
+   `userenv.dll` — triggers GP refresh for GP-path rules. Unreliable on non-domain
+   machines (WORKGROUP). Fallback: `gpupdate /target:computer /force`.
+3. **DNS cache flush**: `DnsFlushResolverCache` from `dnsapi.dll` or `ipconfig /flushdns`
+   — clears stale cached results from before NRPT was active.
+
+### DNS Cache Flush
+
+After NRPT changes, stale DNS cache entries could bypass the new routing. ctrld flushes:
+
+1. **Primary**: `DnsFlushResolverCache` from `dnsapi.dll`
+2. **Fallback**: `ipconfig /flushdns` (subprocess)
+
+### Known Limitation: nslookup
+
+`nslookup.exe` implements its own DNS resolver and does NOT use the Windows DNS Client
+service. It ignores NRPT entirely. Use `Resolve-DnsName` (PowerShell) or `ping` to
+verify DNS resolution through NRPT. This is a well-known Windows behavior.
+
+## WFP (Windows Filtering Platform) — hard Mode Only
+
+### Filter Stack
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│  Sublayer: "ctrld DNS Intercept" (weight 0xFFFF — max priority) │
+│                                                                 │
+│  ┌─ Permit Filters (weight 10) ─────────────────────────────┐   │
+│  │  • IPv4/UDP to 127.0.0.1:53     → PERMIT                │   │
+│  │  • IPv4/TCP to 127.0.0.1:53     → PERMIT                │   │
+│  │  • IPv6/UDP to ::1:53           → PERMIT                │   │
+│  │  • IPv6/TCP to ::1:53           → PERMIT                │   │
+│  │  • RFC1918 + CGNAT subnets:53   → PERMIT (VPN DNS)      │   │
+│  │  • VPN DNS exemptions (dynamic) → PERMIT                │   │
+│  └──────────────────────────────────────────────────────────┘   │
+│                                                                 │
+│  ┌─ Block Filters (weight 1) ───────────────────────────────┐   │
+│  │  • All IPv4/UDP to *:53         → BLOCK                  │   │
+│  │  • All IPv4/TCP to *:53         → BLOCK                  │   │
+│  │  • All IPv6/UDP to *:53         → BLOCK                  │   │
+│  │  • All IPv6/TCP to *:53         → BLOCK                  │   │
+│  └──────────────────────────────────────────────────────────┘   │
+│                                                                 │
+│  Filter evaluation: higher weight wins → permits checked first  │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+### Why WFP Can't Work Alone
+
+WFP operates at the connection authorization layer (`FWPM_LAYER_ALE_AUTH_CONNECT`).
+It can only **block** or **permit** connections — it **cannot redirect** them.
+Redirection requires kernel-mode callout drivers (`FwpsCalloutRegister` in
+`fwpkclnt.lib`) using `FWPM_LAYER_ALE_CONNECT_REDIRECT_V4/V6`, which are not
+accessible from userspace.
+
+Without NRPT, WFP blocks outbound DNS but doesn't tell applications where to send
+queries instead — they just see DNS failures. This is why `hard` mode requires NRPT
+to be active first, and why WFP is rolled back if NRPT setup fails.
+
+### Sublayer Priority
+
+Weight `0xFFFF` (maximum) ensures ctrld's filters take priority over any other WFP
+sublayers from VPN software, endpoint security, or Windows Defender Firewall.
+
+### RFC1918 + CGNAT Subnet Permits
+
+Static permit filters for private IP ranges (10.0.0.0/8, 172.16.0.0/12,
+192.168.0.0/16, 100.64.0.0/10) allow VPN DNS servers on private IPs to work
+without dynamic per-server exemptions. This covers Tailscale MagicDNS
+(100.100.100.100), corporate VPN DNS (10.x.x.x), and similar.
+
+### VPN DNS Exemption Updates
+
+When `vpnDNSManager.Refresh()` discovers VPN DNS servers on public IPs:
+
+1. Delete all existing VPN permit filters (by stored IDs)
+2. For each VPN DNS server IP:
+   - IPv4: `addWFPPermitIPFilter()` on `ALE_AUTH_CONNECT_V4`
+   - IPv6: `addWFPPermitIPv6Filter()` on `ALE_AUTH_CONNECT_V6`
+   - Both UDP and TCP for each IP
+3. Store new filter IDs for next cleanup cycle
+
+**In `dns` mode, VPN DNS exemptions are skipped** — there are no WFP block
+filters to exempt from.
+
+### Session Lifecycle
+
+**Startup (hard mode):**
+```
+1. Add NRPT catch-all rule + GP refresh + DNS flush
+2. FwpmEngineOpen0() with RPC_C_AUTHN_DEFAULT (0xFFFFFFFF)
+3. Delete stale sublayer (crash recovery)
+4. FwpmSubLayerAdd0() — weight 0xFFFF
+5. Add 4 localhost permit filters
+6. Add 4 block filters
+7. Add RFC1918 + CGNAT subnet permits
+8. Start NRPT health monitor goroutine
+```
+
+**Startup (dns mode):**
+```
+1. Add NRPT catch-all rule + GP refresh + DNS flush
+2. Start NRPT health monitor goroutine
+3. (No WFP — done)
+```
+
+**Shutdown:**
+```
+1. Stop NRPT health monitor
+2. Remove NRPT catch-all rule + DNS flush
+3. (hard mode only) Clean up all WFP filters, sublayer, close engine
+```
+
+**Crash Recovery:**
+On startup, `FwpmSubLayerDeleteByKey0` removes any stale sublayer from a previous
+unclean shutdown, including all its child filters (deterministic GUID ensures we
+only clean up our own).
+
+## NRPT Probe and Auto-Heal
+
+### The Problem: Async GP Refresh Race
+
+`RefreshPolicyEx` triggers a Group Policy refresh but returns immediately — it does
+NOT wait for the DNS Client service to actually reload NRPT from the registry. On
+cold machines (first boot, fresh install, long sleep), the DNS Client may take
+several seconds to process the policy refresh. During this window, NRPT rules exist
+in the registry but the DNS Client hasn't loaded them — queries bypass ctrld.
+
+### The Solution: Active Probing
+
+After writing NRPT to the registry, ctrld sends a probe DNS query through the
+Windows DNS Client path to verify NRPT is actually working:
+
+1. Generate a unique probe domain: `_nrpt-probe-<hex>.nrpt-probe.ctrld.test`
+2. Send it via Go's `net.Resolver` (calls `GetAddrInfoW` → DNS Client → NRPT)
+3. If NRPT is active, DNS Client routes it to 127.0.0.1 → ctrld receives it
+4. ctrld's DNS handler recognizes the probe prefix and signals success
+5. If the probe times out (2s), NRPT isn't loaded yet → retry with remediation
+
+### Startup Probe (Async)
+
+After NRPT setup, an async goroutine runs the probe-and-heal sequence without
+blocking startup:
+
+```
+Probe attempt 1 (2s timeout)
+  ├─ Success → "NRPT verified working", done
+  └─ Timeout → GP refresh + DNS flush, sleep 1s
+       Probe attempt 2 (2s timeout)
+         ├─ Success → done
+         └─ Timeout → Restart DNS Client service (nuclear), sleep 2s
+              Re-add NRPT + GP refresh + DNS flush
+              Probe attempt 3 (2s timeout)
+                ├─ Success → done
+                └─ Timeout → GP refresh + DNS flush, sleep 4s
+                     Probe attempt 4 (2s timeout)
+                       ├─ Success → done
+                       └─ Timeout → log error, continue
+```
+
+### DNS Client Restart (Nuclear Option)
+
+If GP refresh alone isn't enough, ctrld restarts the Windows DNS Client service
+(`Dnscache`). This forces the DNS Client to fully re-initialize, including
+re-reading all NRPT rules from the registry. This is the equivalent of macOS
+`forceReloadPFMainRuleset()`.
+
+**Trade-offs:**
+- Briefly interrupts ALL DNS resolution (few hundred ms during restart)
+- Clears the system DNS cache (all apps need to re-resolve)
+- VPN NRPT rules survive (they're in registry, re-read on restart)
+- Enterprise security tools may log the service restart event
+
+This only fires as attempt #3 after two GP refresh attempts fail — at that point
+DNS isn't working through ctrld anyway, so a brief DNS blip is acceptable.
+
+### Health Monitor Integration
+
+The 30s periodic health monitor now does actual probing, not just registry checks:
+
+```
+Every 30s:
+    ├─ Registry check: nrptCatchAllRuleExists()?
+    │   ├─ Missing → re-add + GP refresh + flush + probe-and-heal
+    │   └─ Present → probe to verify it's actually routing
+    │       ├─ Probe success → OK
+    │       └─ Probe failure → probe-and-heal cycle
+    │
+    └─ (hard mode only) Check: wfpSublayerExists()?
+        ├─ Missing → full restart (stopDNSIntercept + startDNSIntercept)
+        └─ Present → OK
+```
+
+**Singleton guard:** Only one probe-and-heal sequence runs at a time (atomic bool).
+The startup probe and health monitor cannot overlap.
+
+**Why periodic, not just network-event?** VPN software or Group Policy updates can
+clear NRPT at any time, not just during network changes. A 30s periodic check ensures
+recovery within a bounded window.
+
+**Hard mode safety:** The health monitor verifies NRPT before checking WFP. If NRPT
+is gone, it's restored first. WFP is never running without NRPT — this prevents
+DNS blackholes where WFP blocks everything but NRPT isn't routing to ctrld.
+
+## DNS Flow Diagrams
+
+### Normal Resolution (both modes)
+
+```
+App → DNS Client → NRPT lookup → "." matches → 127.0.0.1 → ctrld
+    → Control D DoH (port 443, not affected by WFP port-53 rules)
+    → response flows back
+```
+
+### VPN Split DNS (both modes)
+
+```
+App → DNS Client → NRPT lookup:
+    VPN domain (*.corp.local) → VPN's NRPT rule wins → VPN DNS server
+    Everything else → ctrld's "." catch-all → 127.0.0.1 → ctrld
+        → VPN domain match → forward to VPN DNS (port 53)
+        → (hard mode: WFP subnet permit allows private IP DNS)
+```
+
+### Bypass Attempt (hard mode only)
+
+```
+App → raw socket to 8.8.8.8:53 → WFP ALE_AUTH_CONNECT → BLOCK
+```
+
+In `dns` mode, this query would succeed (no WFP) — the tradeoff for never
+breaking DNS.
+
+## Key Differences from macOS (pf)
+
+| Aspect | macOS (pf) | Windows dns mode | Windows hard mode |
+|--------|-----------|------------------|-------------------|
+| **Routing** | `rdr` redirect | NRPT policy | NRPT policy |
+| **Enforcement** | `route-to` + block rules | None (graceful) | WFP block filters |
+| **Can break DNS?** | Yes (pf corruption) | No | Yes (if NRPT lost) |
+| **VPN coexistence** | Watchdog + stabilization | NRPT most-specific-match | Same + WFP permits |
+| **Bypass protection** | pf catches all packets | None | WFP catches all connections |
+| **Recovery** | Probe + auto-heal | Health monitor re-adds | Full restart on sublayer loss |
+
+## WFP API Notes
+
+### Struct Layouts
+
+WFP C API structures are manually defined in Go (`golang.org/x/sys/windows` doesn't
+include WFP types). Field alignment must match the C ABI exactly — any mismatch
+causes access violations or silent corruption.
+
+### FWP_DATA_TYPE Enum
+
+```
+FWP_EMPTY    = 0
+FWP_UINT8    = 1
+FWP_UINT16   = 2
+FWP_UINT32   = 3
+FWP_UINT64   = 4
+...
+```
+
+**⚠️** Some documentation examples incorrectly start at 1. The enum starts at 0
+(`FWP_EMPTY`), making all subsequent values offset by 1 from what you might expect.
+
+### GC Safety
+
+When passing Go heap objects to WFP syscalls via `unsafe.Pointer`, use
+`runtime.KeepAlive()` to prevent garbage collection during the call:
+
+```go
+conditions := make([]fwpmFilterCondition0, 3)
+filter.filterCondition = &conditions[0]
+r1, _, _ := procFwpmFilterAdd0.Call(...)
+runtime.KeepAlive(conditions)
+```
+
+### Authentication
+
+`FwpmEngineOpen0` requires `RPC_C_AUTHN_DEFAULT` (0xFFFFFFFF) for the authentication
+service parameter. `RPC_C_AUTHN_NONE` (0) returns `ERROR_NOT_SUPPORTED` on some
+configurations (e.g., Parallels VMs).
+
+### Elevation
+
+WFP requires admin/SYSTEM privileges. `FwpmEngineOpen0` fails with HRESULT 0x32
+when run non-elevated. Services running as SYSTEM have this automatically.
+
+## Debugging
+
+### Check NRPT Rules
+
+```powershell
+# PowerShell — show active NRPT rules
+Get-DnsClientNrptRule
+
+# Check registry directly
+Get-ChildItem "HKLM:\SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig"
+```
+
+### Check WFP Filters (hard mode)
+
+```powershell
+# Show all WFP filters (requires admin) — output is XML
+netsh wfp show filters
+
+# Search for ctrld's filters
+Select-String "ctrld" filters.xml
+```
+
+### Verify DNS Resolution
+
+```powershell
+# Use Resolve-DnsName, NOT nslookup (nslookup bypasses NRPT)
+Resolve-DnsName example.com
+ping example.com
+
+# If you must use nslookup, specify localhost:
+nslookup example.com 127.0.0.1
+
+# Force GP refresh (if NRPT not loading)
+gpupdate /target:computer /force
+
+# Verify service registration
+sc qc ctrld
+```
+
+### Service Verification
+
+After install, verify the Windows service is correctly registered:
+
+```powershell
+# Check binary path and start type
+sc qc ctrld
+
+# Should show:
+#   BINARY_PATH_NAME: "C:\...\ctrld.exe" run --cd xxxxx --intercept-mode dns
+#   START_TYPE: AUTO_START
+```
+
+## Related
+
+- [DNS Intercept Mode Overview](dns-intercept-mode.md) — cross-platform documentation
+- [pf DNS Intercept](pf-dns-intercept.md) — macOS technical reference
+- [Microsoft WFP Documentation](https://docs.microsoft.com/en-us/windows/win32/fwp/windows-filtering-platform-start-page)
+- [Microsoft NRPT Documentation](https://docs.microsoft.com/en-us/previous-versions/windows/it-pro/windows-server-2012-r2-and-2012/dn593632(v=ws.11))

doh.go

@@ -85,6 +85,10 @@ type dohResolver struct {
 
 // Resolve performs DNS query with given DNS message using DOH protocol.
 func (r *dohResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	if err := validateMsg(msg); err != nil {
+		return nil, err
+	}
+
 	data, err := msg.Pack()
 	if err != nil {
 		return nil, err
@@ -122,11 +126,6 @@ func (r *dohResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, erro
 	}
 	if err != nil {
 		err = wrapUrlError(err)
-		if r.isDoH3 {
-			if closer, ok := c.Transport.(io.Closer); ok {
-				closer.Close()
-			}
-		}
 		return nil, fmt.Errorf("could not perform request: %w", err)
 	}
 	defer resp.Body.Close()

doq.go

@@ -5,8 +5,10 @@ package ctrld
 import (
 	"context"
 	"crypto/tls"
+	"errors"
 	"io"
 	"net"
+	"runtime"
 	"time"
 
 	"github.com/miekg/dns"
@@ -18,27 +20,74 @@ type doqResolver struct {
 }
 
 func (r *doqResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
-	endpoint := r.uc.Endpoint
-	tlsConfig := &tls.Config{NextProtos: []string{"doq"}}
-	ip := r.uc.BootstrapIP
-	if ip == "" {
-		dnsTyp := uint16(0)
-		if msg != nil && len(msg.Question) > 0 {
-			dnsTyp = msg.Question[0].Qtype
-		}
-		ip = r.uc.bootstrapIPForDNSType(dnsTyp)
+	if err := validateMsg(msg); err != nil {
+		return nil, err
 	}
-	tlsConfig.ServerName = r.uc.Domain
-	_, port, _ := net.SplitHostPort(endpoint)
-	endpoint = net.JoinHostPort(ip, port)
-	return resolve(ctx, msg, endpoint, tlsConfig)
+
+	// Get the appropriate connection pool based on DNS type and IP stack
+	dnsTyp := uint16(0)
+	if msg != nil && len(msg.Question) > 0 {
+		dnsTyp = msg.Question[0].Qtype
+	}
+
+	pool := r.uc.doqTransport(dnsTyp)
+	if pool == nil {
+		return nil, errors.New("DoQ connection pool is not available")
+	}
+
+	return pool.Resolve(ctx, msg)
 }
 
-func resolve(ctx context.Context, msg *dns.Msg, endpoint string, tlsConfig *tls.Config) (*dns.Msg, error) {
-	// DoQ quic-go server returns io.EOF error after running for a long time,
-	// even for a good stream. So retrying the query for 5 times before giving up.
-	for i := 0; i < 5; i++ {
-		answer, err := doResolve(ctx, msg, endpoint, tlsConfig)
+const doqPoolSize = 16
+
+// doqConnPool manages a pool of QUIC connections for DoQ queries using a buffered channel.
+type doqConnPool struct {
+	uc        *UpstreamConfig
+	addrs     []string
+	port      string
+	tlsConfig *tls.Config
+	conns     chan *doqConn
+}
+
+type doqConn struct {
+	conn *quic.Conn
+}
+
+func newDOQConnPool(uc *UpstreamConfig, addrs []string) *doqConnPool {
+	_, port, _ := net.SplitHostPort(uc.Endpoint)
+	if port == "" {
+		port = "853"
+	}
+
+	tlsConfig := &tls.Config{
+		NextProtos: []string{"doq"},
+		RootCAs:    uc.certPool,
+		ServerName: uc.Domain,
+	}
+
+	pool := &doqConnPool{
+		uc:        uc,
+		addrs:     addrs,
+		port:      port,
+		tlsConfig: tlsConfig,
+		conns:     make(chan *doqConn, doqPoolSize),
+	}
+
+	// Use SetFinalizer here because we need to call a method on the pool itself.
+	// AddCleanup would require passing the pool as arg (which panics) or capturing
+	// it in a closure (which prevents GC). SetFinalizer is appropriate for this case.
+	runtime.SetFinalizer(pool, func(p *doqConnPool) {
+		p.CloseIdleConnections()
+	})
+
+	return pool
+}
+
+// Resolve performs a DNS query using a pooled QUIC connection.
+func (p *doqConnPool) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	// Retry logic for io.EOF errors (as per original implementation)
+	for range 5 {
+		answer, err := p.doResolve(ctx, msg)
 		if err == io.EOF {
 			continue
 		}
@@ -47,57 +96,72 @@ func resolve(ctx context.Context, msg *dns.Msg, endpoint string, tlsConfig *tls.
 		}
 		return answer, nil
 	}
-	return nil, &quic.ApplicationError{ErrorCode: quic.ApplicationErrorCode(quic.InternalError), ErrorMessage: quic.InternalError.Message()}
+	return nil, &quic.ApplicationError{
+		ErrorCode:    quic.ApplicationErrorCode(quic.InternalError),
+		ErrorMessage: quic.InternalError.Message(),
+	}
 }
 
-func doResolve(ctx context.Context, msg *dns.Msg, endpoint string, tlsConfig *tls.Config) (*dns.Msg, error) {
-	session, err := quic.DialAddr(ctx, endpoint, tlsConfig, nil)
+func (p *doqConnPool) doResolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	conn, err := p.getConn(ctx)
 	if err != nil {
 		return nil, err
 	}
-	defer session.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
 
+	// Pack the DNS message
 	msgBytes, err := msg.Pack()
 	if err != nil {
+		p.putConn(conn, false)
 		return nil, err
 	}
 
-	stream, err := session.OpenStream()
+	// Open a new stream for this query
+	stream, err := conn.OpenStream()
 	if err != nil {
+		p.putConn(conn, false)
 		return nil, err
 	}
 
+	// Set deadline
 	deadline, ok := ctx.Deadline()
 	if !ok {
 		deadline = time.Now().Add(5 * time.Second)
 	}
 	_ = stream.SetDeadline(deadline)
 
+	// Write message length (2 bytes) followed by message
 	var msgLen = uint16(len(msgBytes))
 	var msgLenBytes = []byte{byte(msgLen >> 8), byte(msgLen & 0xFF)}
 	if _, err := stream.Write(msgLenBytes); err != nil {
+		stream.Close()
+		p.putConn(conn, false)
 		return nil, err
 	}
 
 	if _, err := stream.Write(msgBytes); err != nil {
+		stream.Close()
+		p.putConn(conn, false)
 		return nil, err
 	}
 
+	// Read response
 	buf, err := io.ReadAll(stream)
+	stream.Close()
+
+	// Return connection to pool (mark as potentially bad if error occurred)
+	isGood := err == nil && len(buf) > 0
+	p.putConn(conn, isGood)
+
 	if err != nil {
 		return nil, err
 	}
 
-	_ = stream.Close()
-
-	// io.ReadAll hide the io.EOF error returned by quic-go server.
-	// Once we figure out why quic-go server sends io.EOF after running
-	// for a long time, we can have a better way to handle this. For now,
-	// make sure io.EOF error returned, so the caller can handle it cleanly.
+	// io.ReadAll hides io.EOF error, so check for empty buffer
 	if len(buf) == 0 {
 		return nil, io.EOF
 	}
 
+	// Unpack DNS response (skip 2-byte length prefix)
 	answer := new(dns.Msg)
 	if err := answer.Unpack(buf[2:]); err != nil {
 		return nil, err
@@ -105,3 +169,99 @@ func doResolve(ctx context.Context, msg *dns.Msg, endpoint string, tlsConfig *tl
 	answer.SetReply(msg)
 	return answer, nil
 }
+
+// getConn gets a QUIC connection from the pool or creates a new one.
+// A connection is taken from the channel while in use; putConn returns it.
+func (p *doqConnPool) getConn(ctx context.Context) (*quic.Conn, error) {
+	for {
+		select {
+		case dc := <-p.conns:
+			if dc.conn != nil && dc.conn.Context().Err() == nil {
+				return dc.conn, nil
+			}
+			if dc.conn != nil {
+				dc.conn.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
+			}
+		default:
+			_, conn, err := p.dialConn(ctx)
+			if err != nil {
+				return nil, err
+			}
+			return conn, nil
+		}
+	}
+}
+
+// putConn returns a connection to the pool for reuse by other goroutines.
+func (p *doqConnPool) putConn(conn *quic.Conn, isGood bool) {
+	if !isGood || conn == nil || conn.Context().Err() != nil {
+		if conn != nil {
+			conn.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
+		}
+		return
+	}
+	dc := &doqConn{conn: conn}
+	select {
+	case p.conns <- dc:
+	default:
+		// Channel full, close the connection
+		dc.conn.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
+	}
+}
+
+// dialConn creates a new QUIC connection using parallel dialing like DoH3.
+func (p *doqConnPool) dialConn(ctx context.Context) (string, *quic.Conn, error) {
+	logger := ProxyLogger.Load()
+
+	// If we have a bootstrap IP, use it directly
+	if p.uc.BootstrapIP != "" {
+		addr := net.JoinHostPort(p.uc.BootstrapIP, p.port)
+		Log(ctx, logger.Debug(), "Sending DoQ request to: %s", addr)
+		udpConn, err := net.ListenUDP("udp", nil)
+		if err != nil {
+			return "", nil, err
+		}
+		remoteAddr, err := net.ResolveUDPAddr("udp", addr)
+		if err != nil {
+			udpConn.Close()
+			return "", nil, err
+		}
+		conn, err := quic.DialEarly(ctx, udpConn, remoteAddr, p.tlsConfig, nil)
+		if err != nil {
+			udpConn.Close()
+			return "", nil, err
+		}
+		return addr, conn, nil
+	}
+
+	// Use parallel dialing like DoH3
+	dialAddrs := make([]string, len(p.addrs))
+	for i := range p.addrs {
+		dialAddrs[i] = net.JoinHostPort(p.addrs[i], p.port)
+	}
+
+	pd := &quicParallelDialer{}
+	conn, err := pd.Dial(ctx, dialAddrs, p.tlsConfig, nil)
+	if err != nil {
+		return "", nil, err
+	}
+
+	addr := conn.RemoteAddr().String()
+	Log(ctx, logger.Debug(), "Sending DoQ request to: %s", addr)
+	return addr, conn, nil
+}
+
+// CloseIdleConnections closes all connections in the pool.
+// Connections currently checked out (in use) are not closed.
+func (p *doqConnPool) CloseIdleConnections() {
+	for {
+		select {
+		case dc := <-p.conns:
+			if dc.conn != nil {
+				dc.conn.CloseWithError(quic.ApplicationErrorCode(quic.NoError), "")
+			}
+		default:
+			return
+		}
+	}
+}

doq_test.go

@@ -142,7 +142,7 @@ func (s *testQUICServer) serve(t *testing.T) {
 }
 
 // handleConnection manages an individual QUIC connection by accepting and handling incoming streams in separate goroutines.
-func (s *testQUICServer) handleConnection(t *testing.T, conn quic.Connection) {
+func (s *testQUICServer) handleConnection(t *testing.T, conn *quic.Conn) {
 	for {
 		stream, err := conn.AcceptStream(context.Background())
 		if err != nil {
@@ -154,7 +154,7 @@ func (s *testQUICServer) handleConnection(t *testing.T, conn quic.Connection) {
 }
 
 // handleStream processes a single QUIC stream, reads DNS messages, generates a response, and sends it back to the client.
-func (s *testQUICServer) handleStream(t *testing.T, stream quic.Stream) {
+func (s *testQUICServer) handleStream(t *testing.T, stream *quic.Stream) {
 	defer stream.Close()
 
 	// Read length (2 bytes)

dot.go

@@ -3,7 +3,11 @@ package ctrld
 import (
 	"context"
 	"crypto/tls"
+	"errors"
+	"io"
 	"net"
+	"runtime"
+	"time"
 
 	"github.com/miekg/dns"
 )
@@ -13,30 +17,275 @@ type dotResolver struct {
 }
 
 func (r *dotResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
-	// The dialer is used to prevent bootstrapping cycle.
-	// If r.endpoint is set to dns.controld.dev, we need to resolve
-	// dns.controld.dev first. By using a dialer with custom resolver,
-	// we ensure that we can always resolve the bootstrap domain
-	// regardless of the machine DNS status.
-	dialer := newDialer(net.JoinHostPort(controldPublicDns, "53"))
+	if err := validateMsg(msg); err != nil {
+		return nil, err
+	}
+
 	dnsTyp := uint16(0)
 	if msg != nil && len(msg.Question) > 0 {
 		dnsTyp = msg.Question[0].Qtype
 	}
-	tcpNet, _ := r.uc.netForDNSType(dnsTyp)
-	dnsClient := &dns.Client{
-		Net:       tcpNet,
-		Dialer:    dialer,
-		TLSConfig: &tls.Config{RootCAs: r.uc.certPool},
-	}
-	endpoint := r.uc.Endpoint
-	if r.uc.BootstrapIP != "" {
-		dnsClient.TLSConfig.ServerName = r.uc.Domain
-		dnsClient.Net = "tcp-tls"
-		_, port, _ := net.SplitHostPort(endpoint)
-		endpoint = net.JoinHostPort(r.uc.BootstrapIP, port)
+
+	pool := r.uc.dotTransport(dnsTyp)
+	if pool == nil {
+		return nil, errors.New("DoT client pool is not available")
 	}
 
-	answer, _, err := dnsClient.ExchangeContext(ctx, msg, endpoint)
-	return answer, wrapCertificateVerificationError(err)
+	return pool.Resolve(ctx, msg)
+}
+
+const dotPoolSize = 16
+
+// dotConnPool manages a pool of TCP/TLS connections for DoT queries using a buffered channel.
+type dotConnPool struct {
+	uc        *UpstreamConfig
+	addrs     []string
+	port      string
+	tlsConfig *tls.Config
+	dialer    *net.Dialer
+	conns     chan *dotConn
+}
+
+type dotConn struct {
+	conn *tls.Conn
+}
+
+func newDOTClientPool(uc *UpstreamConfig, addrs []string) *dotConnPool {
+	_, port, _ := net.SplitHostPort(uc.Endpoint)
+	if port == "" {
+		port = "853"
+	}
+
+	// The dialer is used to prevent bootstrapping cycle.
+	// If endpoint is set to dns.controld.dev, we need to resolve
+	// dns.controld.dev first. By using a dialer with custom resolver,
+	// we ensure that we can always resolve the bootstrap domain
+	// regardless of the machine DNS status.
+	dialer := newDialer(net.JoinHostPort(controldPublicDns, "53"))
+
+	tlsConfig := &tls.Config{
+		RootCAs: uc.certPool,
+	}
+
+	if uc.BootstrapIP != "" {
+		tlsConfig.ServerName = uc.Domain
+	}
+
+	pool := &dotConnPool{
+		uc:        uc,
+		addrs:     addrs,
+		port:      port,
+		tlsConfig: tlsConfig,
+		dialer:    dialer,
+		conns:     make(chan *dotConn, dotPoolSize),
+	}
+
+	// Use SetFinalizer here because we need to call a method on the pool itself.
+	// AddCleanup would require passing the pool as arg (which panics) or capturing
+	// it in a closure (which prevents GC). SetFinalizer is appropriate for this case.
+	runtime.SetFinalizer(pool, func(p *dotConnPool) {
+		p.CloseIdleConnections()
+	})
+
+	return pool
+}
+
+// Resolve performs a DNS query using a pooled TCP/TLS connection.
+func (p *dotConnPool) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	if msg == nil {
+		return nil, errors.New("nil DNS message")
+	}
+
+	conn, err := p.getConn(ctx)
+	if err != nil {
+		return nil, wrapCertificateVerificationError(err)
+	}
+
+	client := dns.Client{Net: "tcp-tls"}
+	answer, _, err := client.ExchangeWithConnContext(ctx, msg, &dns.Conn{Conn: conn})
+	isGood := err == nil
+	p.putConn(conn, isGood)
+
+	if err != nil {
+		return nil, wrapCertificateVerificationError(err)
+	}
+
+	return answer, nil
+}
+
+// getConn gets a TCP/TLS connection from the pool or creates a new one.
+// A connection is taken from the channel while in use; putConn returns it.
+func (p *dotConnPool) getConn(ctx context.Context) (net.Conn, error) {
+	for {
+		select {
+		case dc := <-p.conns:
+			if dc.conn != nil && isAlive(dc.conn) {
+				return dc.conn, nil
+			}
+			if dc.conn != nil {
+				dc.conn.Close()
+			}
+		default:
+			_, conn, err := p.dialConn(ctx)
+			if err != nil {
+				return nil, err
+			}
+			return conn, nil
+		}
+	}
+}
+
+// putConn returns a connection to the pool for reuse by other goroutines.
+func (p *dotConnPool) putConn(conn net.Conn, isGood bool) {
+	if !isGood || conn == nil {
+		if conn != nil {
+			conn.Close()
+		}
+		return
+	}
+	dc := &dotConn{conn: conn.(*tls.Conn)}
+	select {
+	case p.conns <- dc:
+	default:
+		// Channel full, close the connection
+		dc.conn.Close()
+	}
+}
+
+// dialConn creates a new TCP/TLS connection.
+func (p *dotConnPool) dialConn(ctx context.Context) (string, *tls.Conn, error) {
+	logger := ProxyLogger.Load()
+	var endpoint string
+
+	if p.uc.BootstrapIP != "" {
+		endpoint = net.JoinHostPort(p.uc.BootstrapIP, p.port)
+		Log(ctx, logger.Debug(), "Sending DoT request to: %s", endpoint)
+		conn, err := p.dialer.DialContext(ctx, "tcp", endpoint)
+		if err != nil {
+			return "", nil, err
+		}
+		tlsConn := tls.Client(conn, p.tlsConfig)
+		if err := tlsConn.HandshakeContext(ctx); err != nil {
+			conn.Close()
+			return "", nil, err
+		}
+		return endpoint, tlsConn, nil
+	}
+
+	// Try bootstrap IPs in parallel
+	if len(p.addrs) > 0 {
+		type result struct {
+			conn *tls.Conn
+			addr string
+			err  error
+		}
+
+		ch := make(chan result, len(p.addrs))
+		done := make(chan struct{})
+		defer close(done)
+
+		for _, addr := range p.addrs {
+			go func(addr string) {
+				endpoint := net.JoinHostPort(addr, p.port)
+				conn, err := p.dialer.DialContext(ctx, "tcp", endpoint)
+				if err != nil {
+					select {
+					case ch <- result{conn: nil, addr: endpoint, err: err}:
+					case <-done:
+					}
+					return
+				}
+				tlsConfig := p.tlsConfig.Clone()
+				tlsConfig.ServerName = p.uc.Domain
+				tlsConn := tls.Client(conn, tlsConfig)
+				if err := tlsConn.HandshakeContext(ctx); err != nil {
+					conn.Close()
+					select {
+					case ch <- result{conn: nil, addr: endpoint, err: err}:
+					case <-done:
+					}
+					return
+				}
+				select {
+				case ch <- result{conn: tlsConn, addr: endpoint, err: nil}:
+				case <-done:
+					if conn != nil {
+						conn.Close()
+					}
+				}
+			}(addr)
+		}
+
+		errs := make([]error, 0, len(p.addrs))
+		for range len(p.addrs) {
+			select {
+			case res := <-ch:
+				if res.err == nil && res.conn != nil {
+					Log(ctx, logger.Debug(), "Sending DoT request to: %s", res.addr)
+					return res.addr, res.conn, nil
+				}
+				if res.err != nil {
+					errs = append(errs, res.err)
+				}
+			case <-ctx.Done():
+				return "", nil, ctx.Err()
+			}
+		}
+
+		return "", nil, errors.Join(errs...)
+	}
+
+	// Fallback to endpoint resolution
+	endpoint = p.uc.Endpoint
+	Log(ctx, logger.Debug(), "Sending DoT request to: %s", endpoint)
+	conn, err := p.dialer.DialContext(ctx, "tcp", endpoint)
+	if err != nil {
+		return "", nil, err
+	}
+	tlsConn := tls.Client(conn, p.tlsConfig)
+	if err := tlsConn.HandshakeContext(ctx); err != nil {
+		conn.Close()
+		return "", nil, err
+	}
+	return endpoint, tlsConn, nil
+}
+
+// CloseIdleConnections closes all connections in the pool.
+// Connections currently checked out (in use) are not closed.
+func (p *dotConnPool) CloseIdleConnections() {
+	for {
+		select {
+		case dc := <-p.conns:
+			if dc.conn != nil {
+				dc.conn.Close()
+			}
+		default:
+			return
+		}
+	}
+}
+
+func isAlive(c *tls.Conn) bool {
+	// Set a very short deadline for the read
+	c.SetReadDeadline(time.Now().Add(1 * time.Millisecond))
+
+	// Try to read 1 byte without consuming it (using a small buffer)
+	one := make([]byte, 1)
+	_, err := c.Read(one)
+
+	// Reset the deadline for future operations
+	c.SetReadDeadline(time.Time{})
+
+	if err == io.EOF {
+		return false // Connection is definitely closed
+	}
+
+	// If we get a timeout, it means no data is waiting,
+	// but the connection is likely still "up."
+	var netErr net.Error
+	if errors.As(err, &netErr) && netErr.Timeout() {
+		return true
+	}
+
+	return err == nil
 }

go.mod

@@ -1,12 +1,11 @@
 module github.com/Control-D-Inc/ctrld
 
-go 1.23.0
-
-toolchain go1.23.7
+go 1.24
 
 require (
 	github.com/Masterminds/semver/v3 v3.2.1
 	github.com/ameshkov/dnsstamps v1.0.3
+	github.com/brunogui0812/sysprofiler v0.5.0
 	github.com/coreos/go-systemd/v22 v22.5.0
 	github.com/cuonglm/osinfo v0.0.0-20230921071424-e0e1b1e0bbbf
 	github.com/docker/go-units v0.5.0
@@ -17,6 +16,7 @@ require (
 	github.com/hashicorp/golang-lru/v2 v2.0.1
 	github.com/illarion/gonotify/v2 v2.0.3
 	github.com/insomniacslk/dhcp v0.0.0-20231206064809-8c70d406f6d2
+	github.com/jaypipes/ghw v0.21.0
 	github.com/jaytaylor/go-hostsfile v0.0.0-20220426042432-61485ac1fa6c
 	github.com/josharian/native v1.1.1-0.20230202152459-5c7d0dd6ab86
 	github.com/kardianos/service v1.2.1
@@ -29,16 +29,16 @@ require (
 	github.com/prometheus/client_golang v1.19.1
 	github.com/prometheus/client_model v0.5.0
 	github.com/prometheus/prom2json v1.3.3
-	github.com/quic-go/quic-go v0.48.2
+	github.com/quic-go/quic-go v0.57.1
 	github.com/rs/zerolog v1.28.0
-	github.com/spf13/cobra v1.8.1
-	github.com/spf13/pflag v1.0.5
+	github.com/spf13/cobra v1.9.1
+	github.com/spf13/pflag v1.0.6
 	github.com/spf13/viper v1.16.0
-	github.com/stretchr/testify v1.9.0
-	github.com/vishvananda/netlink v1.2.1-beta.2
-	golang.org/x/net v0.38.0
-	golang.org/x/sync v0.12.0
-	golang.org/x/sys v0.31.0
+	github.com/stretchr/testify v1.11.1
+	github.com/vishvananda/netlink v1.3.1
+	golang.org/x/net v0.43.0
+	golang.org/x/sync v0.16.0
+	golang.org/x/sys v0.35.0
 	golang.zx2c4.com/wireguard/windows v0.5.3
 	tailscale.com v1.74.0
 )
@@ -54,13 +54,13 @@ require (
 	github.com/go-ole/go-ole v1.3.0 // indirect
 	github.com/go-playground/locales v0.14.0 // indirect
 	github.com/go-playground/universal-translator v0.18.0 // indirect
-	github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 // indirect
 	github.com/golang/protobuf v1.5.4 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
-	github.com/google/pprof v0.0.0-20240409012703-83162a5b38cd // indirect
 	github.com/google/uuid v1.6.0 // indirect
+	github.com/groob/plist v0.0.0-20200425180238-0f631f258c01 // indirect
 	github.com/hashicorp/hcl v1.0.0 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
+	github.com/jaypipes/pcidb v1.1.1 // indirect
 	github.com/jsimonetti/rtnetlink v1.4.0 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
@@ -74,32 +74,33 @@ require (
 	github.com/mdlayher/packet v1.1.2 // indirect
 	github.com/mdlayher/socket v0.5.0 // indirect
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
-	github.com/onsi/ginkgo/v2 v2.9.5 // indirect
 	github.com/pierrec/lz4/v4 v4.1.21 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/common v0.48.0 // indirect
 	github.com/prometheus/procfs v0.12.0 // indirect
-	github.com/quic-go/qpack v0.5.1 // indirect
+	github.com/quic-go/qpack v0.6.0 // indirect
 	github.com/rivo/uniseg v0.4.4 // indirect
 	github.com/rogpeppe/go-internal v1.11.0 // indirect
+	github.com/spakin/awk v1.0.0 // indirect
 	github.com/spf13/afero v1.9.5 // indirect
 	github.com/spf13/cast v1.6.0 // indirect
 	github.com/spf13/jwalterweatherman v1.1.0 // indirect
 	github.com/subosito/gotenv v1.4.2 // indirect
 	github.com/u-root/uio v0.0.0-20240118234441-a3c409a6018e // indirect
-	github.com/vishvananda/netns v0.0.4 // indirect
-	go.uber.org/mock v0.4.0 // indirect
+	github.com/vishvananda/netns v0.0.5 // indirect
+	github.com/yusufpapurcu/wmi v1.2.4 // indirect
 	go4.org/mem v0.0.0-20220726221520-4f986261bf13 // indirect
 	go4.org/netipx v0.0.0-20231129151722-fdeea329fbba // indirect
-	golang.org/x/crypto v0.36.0 // indirect
+	golang.org/x/crypto v0.41.0 // indirect
 	golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842 // indirect
-	golang.org/x/mod v0.19.0 // indirect
-	golang.org/x/text v0.23.0 // indirect
-	golang.org/x/tools v0.23.0 // indirect
+	golang.org/x/mod v0.27.0 // indirect
+	golang.org/x/text v0.28.0 // indirect
+	golang.org/x/tools v0.36.0 // indirect
 	google.golang.org/protobuf v1.33.0 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
+	howett.net/plist v1.0.2-0.20250314012144-ee69052608d9 // indirect
 )
 
 replace github.com/mr-karan/doggo => github.com/Windscribe/doggo v0.0.0-20220919152748-2c118fc391f8

go.sum

@@ -50,6 +50,8 @@ github.com/ameshkov/dnsstamps v1.0.3 h1:Srzik+J9mivH1alRACTbys2xOxs0lRH9qnTA7Y1O
 github.com/ameshkov/dnsstamps v1.0.3/go.mod h1:Ii3eUu73dx4Vw5O4wjzmT5+lkCwovjzaEZZ4gKyIH5A=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
+github.com/brunogui0812/sysprofiler v0.5.0 h1:AUekplOKG/VKH6sPSBRxsKOA9Uv5OsI8qolXM73dXPU=
+github.com/brunogui0812/sysprofiler v0.5.0/go.mod h1:lLd7gvylgd4nsTSC8exq1YY6qhLWXkgnalxjVzdlbEM=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -64,7 +66,7 @@ github.com/cncf/udpa/go v0.0.0-20200629203442-efcf912fb354/go.mod h1:WmhPx2Nbnht
 github.com/cncf/udpa/go v0.0.0-20201120205902-5459f2c99403/go.mod h1:WmhPx2Nbnhtbo57+VJT5O0JRkEi1Wbu0z5j0R8u5Hbk=
 github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs=
 github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
-github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
+github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/cuonglm/osinfo v0.0.0-20230921071424-e0e1b1e0bbbf h1:40DHYsri+d1bnroFDU2FQAeq68f3kAlOzlQ93kCf26Q=
 github.com/cuonglm/osinfo v0.0.0-20230921071424-e0e1b1e0bbbf/go.mod h1:G45410zMgmnSjLVKCq4f6GpbYAzoP2plX9rPwgx6C24=
@@ -91,8 +93,7 @@ github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2
 github.com/go-gl/glfw/v3.3/glfw v0.0.0-20200222043503-6f7a984d4dc4/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
 github.com/go-json-experiment/json v0.0.0-20231102232822-2e55bd4e08b0 h1:ymLjT4f35nQbASLnvxEde4XOBL+Sn7rFuV+FOJqkljg=
 github.com/go-json-experiment/json v0.0.0-20231102232822-2e55bd4e08b0/go.mod h1:6daplAwHHGbUGib4990V3Il26O0OC4aRyvewaaAihaA=
-github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
-github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
 github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
 github.com/go-playground/assert/v2 v2.0.1 h1:MsBgLAaY856+nPRTKrp3/OZK38U/wa0CcBYNjji3q3A=
@@ -103,8 +104,6 @@ github.com/go-playground/universal-translator v0.18.0 h1:82dyy6p4OuJq4/CByFNOn/j
 github.com/go-playground/universal-translator v0.18.0/go.mod h1:UvRDBj+xPUEGrFYl+lu/H90nyDXpg0fqeB/AQUGNTVA=
 github.com/go-playground/validator/v10 v10.11.1 h1:prmOlTVv+YjZjmRmNSF3VmspqJIxJWXmqUsHwfTRRkQ=
 github.com/go-playground/validator/v10 v10.11.1/go.mod h1:i+3WkQ1FvaUjjxh1kSvIA4dMGDBiPU55YFDl0WbKdWU=
-github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI=
-github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/godbus/dbus/v5 v5.1.1-0.20230522191255-76236955d466 h1:sQspH8M4niEijh3PFscJRLDnkL547IeP7kpPe3uUhEg=
 github.com/godbus/dbus/v5 v5.1.1-0.20230522191255-76236955d466/go.mod h1:ZiQxhyQ+bbbfxUKVvjfO498oPYvtYhZzycal3G/NHmU=
@@ -162,8 +161,6 @@ github.com/google/pprof v0.0.0-20200708004538-1a94d8640e99/go.mod h1:ZgVRPoUq/hf
 github.com/google/pprof v0.0.0-20201023163331-3e6fc7fc9c4c/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20201203190320-1bf35d6f28c2/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20201218002935-b9804c9f04c2/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
-github.com/google/pprof v0.0.0-20240409012703-83162a5b38cd h1:gbpYu9NMq8jhDVbvlGkMFWCjLFlqqEZjEmObmhUy6Vo=
-github.com/google/pprof v0.0.0-20240409012703-83162a5b38cd/go.mod h1:kf6iHlnVGwgKolg33glAes7Yg/8iWP8ukqeldJSO7jw=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
@@ -171,6 +168,8 @@ github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+
 github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
 github.com/googleapis/google-cloud-go-testing v0.0.0-20200911160855-bcd43fbb19e8/go.mod h1:dvDLG8qkwmyD9a/MJJN3XJcT3xFxOKAvTZGvuZmac9g=
+github.com/groob/plist v0.0.0-20200425180238-0f631f258c01 h1:0T3XGXebqLj7zSVLng9wX9axQzTEnvj/h6eT7iLfUas=
+github.com/groob/plist v0.0.0-20200425180238-0f631f258c01/go.mod h1:itkABA+w2cw7x5nYUS/pLRef6ludkZKOigbROmCTaFw=
 github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/golang-lru v0.5.1/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/golang-lru/v2 v2.0.1 h1:5pv5N1lT1fjLg2VQ5KWc7kmucp2x/kvFOnxuVTqZ6x4=
@@ -187,8 +186,13 @@ github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/insomniacslk/dhcp v0.0.0-20231206064809-8c70d406f6d2 h1:9K06NfxkBh25x56yVhWWlKFE8YpicaSfHwoV8SFbueA=
 github.com/insomniacslk/dhcp v0.0.0-20231206064809-8c70d406f6d2/go.mod h1:3A9PQ1cunSDF/1rbTq99Ts4pVnycWg+vlPkfeD2NLFI=
+github.com/jaypipes/ghw v0.21.0 h1:ClG2xWtYY0c1ud9jZYwVGdSgfCI7AbmZmZyw3S5HHz8=
+github.com/jaypipes/ghw v0.21.0/go.mod h1:GPrvwbtPoxYUenr74+nAnWbardIZq600vJDD5HnPsPE=
+github.com/jaypipes/pcidb v1.1.1 h1:QmPhpsbmmnCwZmHeYAATxEaoRuiMAJusKYkUncMC0ro=
+github.com/jaypipes/pcidb v1.1.1/go.mod h1:x27LT2krrUgjf875KxQXKB0Ha/YXLdZRVmw6hH0G7g8=
 github.com/jaytaylor/go-hostsfile v0.0.0-20220426042432-61485ac1fa6c h1:kbTQ8oGf+BVFvt/fM+ECI+NbZDCqoi0vtZTfB2p2hrI=
 github.com/jaytaylor/go-hostsfile v0.0.0-20220426042432-61485ac1fa6c/go.mod h1:k6+89xKz7BSMJ+DzIerBdtpEUeTlBMugO/hcVSzahog=
+github.com/jessevdk/go-flags v1.4.0/go.mod h1:4FA24M0QyGHXBuZZK/XkWh8h0e1EYbRYJSGM75WSRxI=
 github.com/josharian/native v1.0.1-0.20221213033349-c1e37c09b531/go.mod h1:7X/raswPFr05uY3HiLlYeyQntB6OO7E/d2Cu7qoaN2w=
 github.com/josharian/native v1.1.1-0.20230202152459-5c7d0dd6ab86 h1:elKwZS1OcdQ0WwEDBeqxKwb7WB62QX8bvZ/FJnVXIfk=
 github.com/josharian/native v1.1.1-0.20230202152459-5c7d0dd6ab86/go.mod h1:aFAMtuldEgx/4q7iSGazk22+IcgvtiC+HIimFO9XlS8=
@@ -242,10 +246,6 @@ github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyua
 github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
 github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
 github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
-github.com/onsi/ginkgo/v2 v2.9.5 h1:+6Hr4uxzP4XIUyAkg61dWBw8lb/gc4/X5luuxN/EC+Q=
-github.com/onsi/ginkgo/v2 v2.9.5/go.mod h1:tvAoo1QUJwNEU2ITftXTpR7R1RbCzoZUOs3RonqW57k=
-github.com/onsi/gomega v1.27.6 h1:ENqfyGeS5AX/rlXDd/ETokDz93u0YufY1Pgxuy/PvWE=
-github.com/onsi/gomega v1.27.6/go.mod h1:PIQNjfQwkP3aQAH7lf7j87O/5FiNr+ZR8+ipb+qQlhg=
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
 github.com/pierrec/lz4/v4 v4.1.14/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
@@ -269,10 +269,10 @@ github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k
 github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
 github.com/prometheus/prom2json v1.3.3 h1:IYfSMiZ7sSOfliBoo89PcufjWO4eAR0gznGcETyaUgo=
 github.com/prometheus/prom2json v1.3.3/go.mod h1:Pv4yIPktEkK7btWsrUTWDDDrnpUrAELaOCj+oFwlgmc=
-github.com/quic-go/qpack v0.5.1 h1:giqksBPnT/HDtZ6VhtFKgoLOWmlyo9Ei6u9PqzIMbhI=
-github.com/quic-go/qpack v0.5.1/go.mod h1:+PC4XFrEskIVkcLzpEkbLqq1uCoxPhQuvK5rH1ZgaEg=
-github.com/quic-go/quic-go v0.48.2 h1:wsKXZPeGWpMpCGSWqOcqpW2wZYic/8T3aqiOID0/KWE=
-github.com/quic-go/quic-go v0.48.2/go.mod h1:yBgs3rWBOADpga7F+jJsb6Ybg1LSYiQvwWlLX+/6HMs=
+github.com/quic-go/qpack v0.6.0 h1:g7W+BMYynC1LbYLSqRt8PBg5Tgwxn214ZZR34VIOjz8=
+github.com/quic-go/qpack v0.6.0/go.mod h1:lUpLKChi8njB4ty2bFLX2x4gzDqXwUpaO1DP9qMDZII=
+github.com/quic-go/quic-go v0.57.1 h1:25KAAR9QR8KZrCZRThWMKVAwGoiHIrNbT72ULHTuI10=
+github.com/quic-go/quic-go v0.57.1/go.mod h1:ly4QBAjHA2VhdnxhojRsCUOeJwKYg+taDlos92xb1+s=
 github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.4.4 h1:8TfxU8dW6PdqD27gjM8MVNuicgxIjxpm4K7x4jp8sis=
 github.com/rivo/uniseg v0.4.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
@@ -284,16 +284,18 @@ github.com/rogpeppe/go-internal v1.11.0 h1:cWPaGQEPrBb5/AsnsZesgZZ9yb1OQ+GOISoDN
 github.com/rogpeppe/go-internal v1.11.0/go.mod h1:ddIwULY96R17DhadqLgMfk9H9tvdUzkipdSkR5nkCZA=
 github.com/rs/xid v1.6.0/go.mod h1:7XoLgs4eV+QndskICGsho+ADou8ySMSjJKDIan90Nz0=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/spakin/awk v1.0.0 h1:5ulBVgJhdN3XoFGNVv/MOHOIUfPVPvMCIlLH6O6ZqU4=
+github.com/spakin/awk v1.0.0/go.mod h1:e7FnxcIEcRqdKwStPYWonox4n9DpharWk+3nnn1IqJs=
 github.com/spf13/afero v1.9.5 h1:stMpOSZFs//0Lv29HduCmli3GUfpFoF3Y1Q/aXj/wVM=
 github.com/spf13/afero v1.9.5/go.mod h1:UBogFpq8E9Hx+xc5CNTTEpTnuHVmXDwZcZcE1eb/UhQ=
 github.com/spf13/cast v1.6.0 h1:GEiTHELF+vaR5dhz3VqZfFSzZjYbgeKDpBxQVS4GYJ0=
 github.com/spf13/cast v1.6.0/go.mod h1:ancEpBxwJDODSW/UG4rDrAqiKolqNNh2DX3mk86cAdo=
-github.com/spf13/cobra v1.8.1 h1:e5/vxKd/rZsfSJMUX1agtjeTDf+qv1/JdBF8gg5k9ZM=
-github.com/spf13/cobra v1.8.1/go.mod h1:wHxEcudfqmLYa8iTfL+OuZPbBZkmvliBWKIezN3kD9Y=
+github.com/spf13/cobra v1.9.1 h1:CXSaggrXdbHK9CF+8ywj8Amf7PBRmPCOJugH954Nnlo=
+github.com/spf13/cobra v1.9.1/go.mod h1:nDyEzZ8ogv936Cinf6g1RU9MRY64Ir93oCnqb9wxYW0=
 github.com/spf13/jwalterweatherman v1.1.0 h1:ue6voC5bR5F8YxI5S67j9i582FU4Qvo2bmqnqMYADFk=
 github.com/spf13/jwalterweatherman v1.1.0/go.mod h1:aNWZUN0dPAAO/Ljvb5BEdw96iTZ0EXowPYD95IqWIGo=
-github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
-github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/spf13/pflag v1.0.6 h1:jFzHGLGAlb3ruxLB8MhbI6A8+AQX/2eW4qeyNZXNp2o=
+github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 github.com/spf13/viper v1.16.0 h1:rGGH0XDZhdUOryiDWjmIvUSWpbNqisK8Wk0Vyefw8hc=
 github.com/spf13/viper v1.16.0/go.mod h1:yg78JgCJcbrQOvV9YLXgkLaZqUidkY9K+Dd1FofRzQg=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
@@ -309,29 +311,30 @@ github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 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 v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
-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/subosito/gotenv v1.4.2 h1:X1TuBLAMDFbaTAChgCBLu3DU3UPyELpnF2jjJ2cz/S8=
 github.com/subosito/gotenv v1.4.2/go.mod h1:ayKnFf/c6rvx/2iiLrJUk1e6plDbT3edrFNGqEflhK0=
 github.com/u-root/uio v0.0.0-20240118234441-a3c409a6018e h1:BA9O3BmlTmpjbvajAwzWx4Wo2TRVdpPXZEeemGQcajw=
 github.com/u-root/uio v0.0.0-20240118234441-a3c409a6018e/go.mod h1:eLL9Nub3yfAho7qB0MzZizFhTU2QkLeoVsWdHtDW264=
-github.com/vishvananda/netlink v1.2.1-beta.2 h1:Llsql0lnQEbHj0I1OuKyp8otXp0r3q0mPkuhwHfStVs=
-github.com/vishvananda/netlink v1.2.1-beta.2/go.mod h1:twkDnbuQxJYemMlGd4JFIcuhgX83tXhKS2B/PRMpOho=
-github.com/vishvananda/netns v0.0.0-20200728191858-db3c7e526aae/go.mod h1:DD4vA1DwXk04H54A1oHXtwZmA0grkVMdPxx/VGLCah0=
-github.com/vishvananda/netns v0.0.4 h1:Oeaw1EM2JMxD51g9uhtC0D7erkIjgmj8+JZc26m1YX8=
-github.com/vishvananda/netns v0.0.4/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
+github.com/vishvananda/netlink v1.3.1 h1:3AEMt62VKqz90r0tmNhog0r/PpWKmrEShJU0wJW6bV0=
+github.com/vishvananda/netlink v1.3.1/go.mod h1:ARtKouGSTGchR8aMwmkzC0qiNPrrWO5JS/XMVl45+b4=
+github.com/vishvananda/netns v0.0.5 h1:DfiHV+j8bA32MFM7bfEunvT8IAqQ/NzSJHtcmW5zdEY=
+github.com/vishvananda/netns v0.0.5/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
 github.com/yuin/goldmark v1.1.25/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.1.32/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/yusufpapurcu/wmi v1.2.4 h1:zFUKzehAFReQwLys1b/iSMl+JQGSCSjtVqQn9bBrPo0=
+github.com/yusufpapurcu/wmi v1.2.4/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
 go.opencensus.io v0.22.3/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
 go.opencensus.io v0.22.4/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
 go.opencensus.io v0.22.5/go.mod h1:5pWMHQbX5EPX2/62yrJeAkowc+lfs/XD7Uxpq3pI6kk=
-go.uber.org/mock v0.4.0 h1:VcM4ZOtdbR4f6VXfiOpwpVJDL6lCReaZ6mw31wqh7KU=
-go.uber.org/mock v0.4.0/go.mod h1:a6FSlNadKUHUa9IP5Vyt1zh4fC7uAwxMutEAscFbkZc=
+go.uber.org/mock v0.5.2 h1:LbtPTcP8A5k9WPXj54PPPbjcI4Y6lhyOZXn+VS7wNko=
+go.uber.org/mock v0.5.2/go.mod h1:wLlUxC2vVTPTaE3UD51E0BGOAElKrILxhVSDYQLld5o=
 go4.org/mem v0.0.0-20220726221520-4f986261bf13 h1:CbZeCBZ0aZj8EfVgnqQcYZgf0lpZ3H9rmp5nkDTAst8=
 go4.org/mem v0.0.0-20220726221520-4f986261bf13/go.mod h1:reUoABIJ9ikfM5sgtSF3Wushcza7+WeD01VB9Lirh3g=
 go4.org/netipx v0.0.0-20231129151722-fdeea329fbba h1:0b9z3AuHCjxk0x/opv64kcgZLBseWJUpBw5I82+2U4M=
@@ -346,8 +349,8 @@ golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b/go.mod h1:T9bdIzuCu7OtxOm
 golang.org/x/crypto v0.0.0-20211209193657-4570a0811e8b/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20211215153901-e495a2d5b3d3/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
 golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
-golang.org/x/crypto v0.36.0 h1:AnAEvhDddvBdpY+uR+MyHmuZzzNqXSe/GvuDeob5L34=
-golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc=
+golang.org/x/crypto v0.41.0 h1:WKYxWedPGCTVVl5+WHSSrOBT0O8lx32+zxmHxijgXp4=
+golang.org/x/crypto v0.41.0/go.mod h1:pO5AFd7FA68rFak7rOAGVuygIISepHftHnr8dr6+sUc=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
@@ -383,8 +386,8 @@ golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.1/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.19.0 h1:fEdghXQSo20giMthA7cd28ZC+jts4amQ3YMXiP5oMQ8=
-golang.org/x/mod v0.19.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
+golang.org/x/mod v0.27.0 h1:kb+q2PyFnEADO2IEF935ehFUXlWiNjJWtRNgBLSfbxQ=
+golang.org/x/mod v0.27.0/go.mod h1:rWI627Fq0DEoudcK+MBkNkCe0EetEaDSwJJkCcjpazc=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -417,8 +420,8 @@ golang.org/x/net v0.0.0-20201209123823-ac852fbbde11/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20201224014010-6772e930b67b/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
-golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
+golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -438,8 +441,8 @@ golang.org/x/sync v0.0.0-20200317015054-43a5402ce75a/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw=
-golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sync v0.16.0 h1:ycBJEhp9p4vXvUZNszeOq0kGTPghopOL8q0fq3vstxw=
+golang.org/x/sync v0.16.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -449,6 +452,7 @@ golang.org/x/sys v0.0.0-20190507160741-ecd444e8653b/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20190606165138-5da285871e9c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190624142023-c5567b49c5d0/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190726091711-fc99dfbffb4e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191001151750-bb3f8db39f24/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -457,7 +461,6 @@ golang.org/x/sys v0.0.0-20200113162924-86b910548bc1/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200122134326-e047566fdf82/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200202164722-d101bd2416d5/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200212091648-12a6c2dcc1e4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200217220822-9197077df867/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200223170610-d5e6a3e2c0ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200302150141-5c8b2ff67527/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -466,7 +469,6 @@ golang.org/x/sys v0.0.0-20200501052902-10377860bb8e/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200511232937-7e40ca221e25/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200515095857-1151b9dac4a9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200523222454-059865788121/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200728102440-3e129f6d46b1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200803210538-64077c9b5642/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200905004654-be1d3432aa8f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -485,11 +487,13 @@ golang.org/x/sys v0.0.0-20220622161953-175b2fd9d664/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220817070843-5a390386f1f2/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.1.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.4.1-0.20230131160137-e7d7f63158de/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik=
-golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/sys v0.35.0 h1:vz1N37gP5bs89s7He8XuIYXpyY0+QlsKmzipCbUtyxI=
+golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -500,13 +504,13 @@ golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
-golang.org/x/text v0.23.0 h1:D71I7dUrlY+VX0gQShAThNGHFxZ13dGLBHQLVl1mJlY=
-golang.org/x/text v0.23.0/go.mod h1:/BLNzu4aZCJ1+kcD0DNRotWKage4q2rGVAg4o22unh4=
+golang.org/x/text v0.28.0 h1:rhazDwis8INMIwQ4tpjLDzUhx6RlXqZNPEM0huQojng=
+golang.org/x/text v0.28.0/go.mod h1:U8nCwOR8jO/marOQ0QbDiOngZVEBB7MAiitBuMjXiNU=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
-golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
+golang.org/x/time v0.12.0 h1:ScB/8o8olJvc+CQPWrK3fPZNfh7qgwCrY0zJmoEQLSE=
+golang.org/x/time v0.12.0/go.mod h1:CDIdPxbZBQxdj6cxyCIdrNogrJKMJ7pr37NYpMcMDSg=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
@@ -554,8 +558,8 @@ golang.org/x/tools v0.0.0-20201208233053-a543418bbed2/go.mod h1:emZCQorbCU4vsT4f
 golang.org/x/tools v0.0.0-20210105154028-b0ab187a4818/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210108195828-e2f9c7f1fc8e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.0/go.mod h1:xkSsbof2nBLbhDlRMhhhyNLN/zl3eTqcnHD5viDpcZ0=
-golang.org/x/tools v0.23.0 h1:SGsXPZ+2l4JsgaCKkx+FQ9YZ5XEtA1GZYuoDjenLjvg=
-golang.org/x/tools v0.23.0/go.mod h1:pnu6ufv6vQkll6szChhK3C3L/ruaIv5eBeztNG8wtsI=
+golang.org/x/tools v0.36.0 h1:kWS0uv/zsvHEle1LbV5LE8QujrxB3wfQyxHfhOk0Qkg=
+golang.org/x/tools v0.36.0/go.mod h1:WBDiHKJK8YgLHlcQPYQzNCkUxUypCaa5ZegCVutKm+s=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -671,6 +675,8 @@ honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWh
 honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
 honnef.co/go/tools v0.0.1-2020.1.3/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
 honnef.co/go/tools v0.0.1-2020.1.4/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
+howett.net/plist v1.0.2-0.20250314012144-ee69052608d9 h1:eeH1AIcPvSc0Z25ThsYF+Xoqbn0CI/YnXVYoTLFdGQw=
+howett.net/plist v1.0.2-0.20250314012144-ee69052608d9/go.mod h1:fyFX5Hj5tP1Mpk8obqA9MZgXT416Q5711SDT7dQLTLk=
 rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=
 rsc.io/quote/v3 v3.1.0/go.mod h1:yEA65RcK8LyAZtP9Kv3t0HmxON59tX3rD+tICJqUlj0=
 rsc.io/sampler v1.3.0/go.mod h1:T1hPZKmBbMNahiBKFy5HrXp6adAjACjK9JXDnKaTXpA=

internal/clientinfo/dhcp_lease_files.go

@@ -16,4 +16,5 @@ var clientInfoFiles = map[string]ctrld.LeaseFileFormat{
 	"/var/dhcpd/var/db/dhcpd.leases":           ctrld.IscDhcpd, // Pfsense
 	"/home/pi/.router/run/dhcp/dnsmasq.leases": ctrld.Dnsmasq,  // Firewalla
 	"/var/lib/kea/dhcp4.leases":                ctrld.KeaDHCP4, // Pfsense
+	"/var/db/dnsmasq.leases":                   ctrld.Dnsmasq,  // OPNsense
 }

internal/clientinfo/mdns.go

@@ -74,7 +74,6 @@ func (m *mdns) lookupIPByHostname(name string, v6 bool) string {
 		if value == name {
 			if addr, err := netip.ParseAddr(key.(string)); err == nil && addr.Is6() == v6 {
 				ip = addr.String()
-				//lint:ignore S1008 This is used for readable.
 				if addr.IsLoopback() { // Continue searching if this is loopback address.
 					return true
 				}

internal/clientinfo/ptr_lookup.go

@@ -104,7 +104,6 @@ func (p *ptrDiscover) lookupIPByHostname(name string, v6 bool) string {
 		if value == name {
 			if addr, err := netip.ParseAddr(key.(string)); err == nil && addr.Is6() == v6 {
 				ip = addr.String()
-				//lint:ignore S1008 This is used for readable.
 				if addr.IsLoopback() { // Continue searching if this is loopback address.
 					return true
 				}
@@ -120,8 +119,7 @@ func (p *ptrDiscover) lookupIPByHostname(name string, v6 bool) string {
 // is reachable, set p.serverDown to false, so p.lookupHostname can continue working.
 func (p *ptrDiscover) checkServer() {
 	bo := backoff.NewBackoff("ptrDiscover", func(format string, args ...any) {}, time.Minute*5)
-	m := new(dns.Msg)
-	m.SetQuestion(".", dns.TypeNS)
+	m := (&ctrld.UpstreamConfig{}).VerifyMsg()
 	ping := func() error {
 		ctx, cancel := context.WithTimeout(context.Background(), time.Second)
 		defer cancel()

internal/controld/config.go

@@ -10,7 +10,6 @@ import (
 	"io"
 	"net"
 	"net/http"
-	"os"
 	"runtime"
 	"strings"
 	"time"
@@ -71,14 +70,23 @@ func (u ErrorResponse) Error() string {
 }
 
 type utilityRequest struct {
-	UID      string `json:"uid"`
-	ClientID string `json:"client_id,omitempty"`
+	UID      string            `json:"uid"`
+	ClientID string            `json:"client_id,omitempty"`
+	Metadata map[string]string `json:"metadata"`
 }
 
 // UtilityOrgRequest contains request data for calling Org API.
 type UtilityOrgRequest struct {
-	ProvToken string `json:"prov_token"`
-	Hostname  string `json:"hostname"`
+	ProvToken string            `json:"prov_token"`
+	Hostname  string            `json:"hostname"`
+	Metadata  map[string]string `json:"metadata"`
+}
+
+// ResolverConfigRequest contains request data for fetching resolver config.
+type ResolverConfigRequest struct {
+	RawUID   string
+	Version  string
+	Metadata map[string]string
 }
 
 // LogsRequest contains request data for sending runtime logs to API.
@@ -88,26 +96,41 @@ type LogsRequest struct {
 }
 
 // FetchResolverConfig fetch Control D config for given uid.
-func FetchResolverConfig(rawUID, version string, cdDev bool) (*ResolverConfig, error) {
-	uid, clientID := ParseRawUID(rawUID)
-	req := utilityRequest{UID: uid}
-	if clientID != "" {
-		req.ClientID = clientID
+func FetchResolverConfig(req *ResolverConfigRequest, cdDev bool) (*ResolverConfig, error) {
+	uid, clientID := ParseRawUID(req.RawUID)
+	uReq := utilityRequest{
+		UID:      uid,
+		Metadata: req.Metadata,
 	}
-	body, _ := json.Marshal(req)
-	return postUtilityAPI(version, cdDev, false, bytes.NewReader(body))
+	if clientID != "" {
+		uReq.ClientID = clientID
+	}
+	body, _ := json.Marshal(uReq)
+	return postUtilityAPI(req.Version, cdDev, false, bytes.NewReader(body))
 }
 
-// FetchResolverUID fetch resolver uid from provision token.
+// FetchResolverUID fetch resolver uid from a given request.
 func FetchResolverUID(req *UtilityOrgRequest, version string, cdDev bool) (*ResolverConfig, error) {
 	if req == nil {
 		return nil, errors.New("invalid request")
 	}
-	hostname := req.Hostname
-	if hostname == "" {
-		hostname, _ = os.Hostname()
+	if req.Hostname == "" {
+		hostname, _ := preferredHostname()
+		ctrld.ProxyLogger.Load().Debug().Msgf("Using system hostname: %s", hostname)
+		req.Hostname = hostname
 	}
-	body, _ := json.Marshal(UtilityOrgRequest{ProvToken: req.ProvToken, Hostname: hostname})
+
+	// Include all hostname sources in metadata so the API can pick the
+	// best one if the primary looks generic (e.g., "Mac", "Mac.lan").
+	if req.Metadata == nil {
+		req.Metadata = make(map[string]string)
+	}
+	for k, v := range hostnameHints() {
+		req.Metadata["hostname_"+k] = v
+	}
+	ctrld.ProxyLogger.Load().Debug().Msgf("Sending UID request to ControlD API")
+
+	body, _ := json.Marshal(req)
 	return postUtilityAPI(version, cdDev, false, bytes.NewReader(body))
 }
 

internal/controld/controld_test.go

@@ -3,10 +3,13 @@
 package controld
 
 import (
+	"context"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+
+	"github.com/Control-D-Inc/ctrld"
 )
 
 func TestFetchResolverConfig(t *testing.T) {
@@ -20,11 +23,18 @@ func TestFetchResolverConfig(t *testing.T) {
 		{"valid dev", "p2", true, false},
 		{"invalid uid", "abcd1234", false, true},
 	}
+
+	ctx := context.Background()
 	for _, tc := range tests {
 		tc := tc
 		t.Run(tc.name, func(t *testing.T) {
 			t.Parallel()
-			got, err := FetchResolverConfig(tc.uid, "dev-test", tc.dev)
+			req := &ResolverConfigRequest{
+				RawUID:   tc.uid,
+				Version:  "dev-test",
+				Metadata: ctrld.SystemMetadata(ctx),
+			}
+			got, err := FetchResolverConfig(ctx, req, tc.dev)
 			require.False(t, (err != nil) != tc.wantErr, err)
 			if !tc.wantErr {
 				assert.NotEmpty(t, got.DOH)

internal/controld/hostname_darwin.go

@@ -0,0 +1,44 @@
+package controld
+
+import (
+	"os"
+	"os/exec"
+	"strings"
+)
+
+// preferredHostname returns the best available hostname on macOS.
+// It prefers scutil --get ComputerName which is the user-configured name
+// from System Settings → General → About → Name. This is immune to
+// DHCP/network state that can cause os.Hostname() and even LocalHostName
+// to return generic names like "Mac.lan" on Sequoia with Private Wi-Fi
+// Address enabled.
+//
+// Fallback chain: ComputerName → LocalHostName → os.Hostname()
+func preferredHostname() (string, error) {
+	for _, key := range []string{"ComputerName", "LocalHostName"} {
+		if out, err := exec.Command("scutil", "--get", key).Output(); err == nil {
+			if name := strings.TrimSpace(string(out)); name != "" {
+				return name, nil
+			}
+		}
+	}
+	return os.Hostname()
+}
+
+// hostnameHints returns all available hostname sources on macOS for
+// diagnostic/fallback purposes. The API can use these to pick the
+// best hostname if the primary one looks generic (e.g., "Mac").
+func hostnameHints() map[string]string {
+	hints := make(map[string]string)
+	for _, key := range []string{"ComputerName", "LocalHostName", "HostName"} {
+		if out, err := exec.Command("scutil", "--get", key).Output(); err == nil {
+			if name := strings.TrimSpace(string(out)); name != "" {
+				hints[key] = name
+			}
+		}
+	}
+	if h, err := os.Hostname(); err == nil {
+		hints["os.Hostname"] = h
+	}
+	return hints
+}

internal/controld/hostname_others.go

@@ -0,0 +1,19 @@
+//go:build !darwin
+
+package controld
+
+import "os"
+
+// preferredHostname returns the system hostname on non-Darwin platforms.
+func preferredHostname() (string, error) {
+	return os.Hostname()
+}
+
+// hostnameHints returns available hostname sources for diagnostic purposes.
+func hostnameHints() map[string]string {
+	hints := make(map[string]string)
+	if h, err := os.Hostname(); err == nil {
+		hints["os.Hostname"] = h
+	}
+	return hints
+}

internal/router/dnsmasq/conf.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"io"
 	"os"
+	"path/filepath"
 	"strings"
 )
 
@@ -28,3 +29,62 @@ func interfaceNameFromReader(r io.Reader) (string, error) {
 	}
 	return "", errors.New("not found")
 }
+
+// AdditionalConfigFiles returns a list of Dnsmasq configuration files found in the "/tmp/etc" directory.
+func AdditionalConfigFiles() []string {
+	if paths, err := filepath.Glob("/tmp/etc/dnsmasq-*.conf"); err == nil {
+		return paths
+	}
+	return nil
+}
+
+// AdditionalLeaseFiles returns a list of lease file paths corresponding to the Dnsmasq configuration files.
+func AdditionalLeaseFiles() []string {
+	cfgFiles := AdditionalConfigFiles()
+	if len(cfgFiles) == 0 {
+		return nil
+	}
+	leaseFiles := make([]string, 0, len(cfgFiles))
+	for _, cfgFile := range cfgFiles {
+		if leaseFile := leaseFileFromConfigFileName(cfgFile); leaseFile != "" {
+			leaseFiles = append(leaseFiles, leaseFile)
+
+		} else {
+			leaseFiles = append(leaseFiles, defaultLeaseFileFromConfigPath(cfgFile))
+		}
+	}
+	return leaseFiles
+}
+
+// leaseFileFromConfigFileName retrieves the DHCP lease file path by reading and parsing the provided configuration file.
+func leaseFileFromConfigFileName(cfgFile string) string {
+	if f, err := os.Open(cfgFile); err == nil {
+		return leaseFileFromReader(f)
+	}
+	return ""
+}
+
+// leaseFileFromReader parses the given io.Reader for the "dhcp-leasefile" configuration and returns its value as a string.
+func leaseFileFromReader(r io.Reader) string {
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := scanner.Text()
+		if strings.HasPrefix(line, "#") {
+			continue
+		}
+		before, after, found := strings.Cut(line, "=")
+		if !found {
+			continue
+		}
+		if before == "dhcp-leasefile" {
+			return after
+		}
+	}
+	return ""
+}
+
+// defaultLeaseFileFromConfigPath generates the default lease file path based on the provided configuration file path.
+func defaultLeaseFileFromConfigPath(path string) string {
+	name := filepath.Base(path)
+	return filepath.Join("/var/lib/misc", strings.TrimSuffix(name, ".conf")+".leases")
+}

internal/router/dnsmasq/conf_test.go

@@ -1,6 +1,7 @@
 package dnsmasq
 
 import (
+	"io"
 	"strings"
 	"testing"
 )
@@ -44,3 +45,49 @@ interface=eth0
 		})
 	}
 }
+
+func Test_leaseFileFromReader(t *testing.T) {
+	tests := []struct {
+		name     string
+		in       io.Reader
+		expected string
+	}{
+		{
+			"default",
+			strings.NewReader(`
+dhcp-script=/sbin/dhcpc_lease
+dhcp-leasefile=/var/lib/misc/dnsmasq-1.leases
+script-arp
+`),
+			"/var/lib/misc/dnsmasq-1.leases",
+		},
+		{
+			"non-default",
+			strings.NewReader(`
+dhcp-script=/sbin/dhcpc_lease
+dhcp-leasefile=/tmp/var/lib/misc/dnsmasq-1.leases
+script-arp
+`),
+			"/tmp/var/lib/misc/dnsmasq-1.leases",
+		},
+		{
+			"missing",
+			strings.NewReader(`
+dhcp-script=/sbin/dhcpc_lease
+script-arp
+`),
+			"",
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := leaseFileFromReader(tc.in); got != tc.expected {
+				t.Errorf("leaseFileFromReader() = %v, want %v", got, tc.expected)
+			}
+		})
+	}
+
+}

internal/router/dnsmasq/dnsmasq.go

@@ -4,6 +4,7 @@ import (
 	"errors"
 	"html/template"
 	"net"
+	"os"
 	"path/filepath"
 	"strings"
 
@@ -26,9 +27,13 @@ max-cache-ttl=0
 {{- end}}
 `
 
-const MerlinConfPath = "/tmp/etc/dnsmasq.conf"
-const MerlinJffsConfPath = "/jffs/configs/dnsmasq.conf"
-const MerlinPostConfPath = "/jffs/scripts/dnsmasq.postconf"
+const (
+	MerlinConfPath     = "/tmp/etc/dnsmasq.conf"
+	MerlinJffsConfDir  = "/jffs/configs"
+	MerlinJffsConfPath = "/jffs/configs/dnsmasq.conf"
+	MerlinPostConfPath = "/jffs/scripts/dnsmasq.postconf"
+)
+
 const MerlinPostConfMarker = `# GENERATED BY ctrld - EOF`
 const MerlinPostConfTmpl = `# GENERATED BY ctrld - DO NOT MODIFY
 
@@ -159,3 +164,27 @@ func FirewallaSelfInterfaces() []*net.Interface {
 	}
 	return ifaces
 }
+
+const (
+	ubios43ConfPath = "/run/dnsmasq.dhcp.conf.d"
+	ubios42ConfPath = "/run/dnsmasq.conf.d"
+	ubios43PidFile  = "/run/dnsmasq-main.pid"
+	ubios42PidFile  = "/run/dnsmasq.pid"
+	UbiosConfName   = "zzzctrld.conf"
+)
+
+// UbiosConfPath returns the appropriate configuration path based on the system's directory structure.
+func UbiosConfPath() string {
+	if st, _ := os.Stat(ubios43ConfPath); st != nil && st.IsDir() {
+		return ubios43ConfPath
+	}
+	return ubios42ConfPath
+}
+
+// UbiosPidFile returns the appropriate dnsmasq pid file based on the system's directory structure.
+func UbiosPidFile() string {
+	if st, _ := os.Stat(ubios43PidFile); st != nil && !st.IsDir() {
+		return ubios43PidFile
+	}
+	return ubios42PidFile
+}

internal/router/edgeos/edgeos.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"os"
 	"os/exec"
+	"path/filepath"
 	"strings"
 
 	"github.com/kardianos/service"
@@ -181,7 +182,7 @@ func ContentFilteringEnabled() bool {
 // DnsShieldEnabled reports whether DNS Shield is enabled.
 // See: https://community.ui.com/releases/UniFi-OS-Dream-Machines-3-2-7/251dfc1e-f4dd-4264-a080-3be9d8b9e02b
 func DnsShieldEnabled() bool {
-	buf, err := os.ReadFile("/var/run/dnsmasq.conf.d/dns.conf")
+	buf, err := os.ReadFile(filepath.Join(dnsmasq.UbiosConfPath(), "dns.conf"))
 	if err != nil {
 		return false
 	}

internal/router/merlin/merlin.go

@@ -6,6 +6,7 @@ import (
 	"io"
 	"os"
 	"os/exec"
+	"path/filepath"
 	"strings"
 	"time"
 	"unicode"
@@ -20,10 +21,18 @@ import (
 
 const Name = "merlin"
 
+// nvramKvMap is a map of NVRAM key-value pairs used to configure and manage Merlin-specific settings.
 var nvramKvMap = map[string]string{
 	"dnspriv_enable": "0", // Ensure Merlin native DoT disabled.
 }
 
+// dnsmasqConfig represents configuration paths for dnsmasq operations in Merlin firmware.
+type dnsmasqConfig struct {
+	confPath     string
+	jffsConfPath string
+}
+
+// Merlin represents a configuration handler for setting up and managing ctrld on Merlin routers.
 type Merlin struct {
 	cfg *ctrld.Config
 }
@@ -33,18 +42,22 @@ func New(cfg *ctrld.Config) *Merlin {
 	return &Merlin{cfg: cfg}
 }
 
+// ConfigureService configures the service based on the provided configuration. It returns an error if the configuration fails.
 func (m *Merlin) ConfigureService(config *service.Config) error {
 	return nil
 }
 
+// Install sets up the necessary configurations and services required for the Merlin instance to function properly.
 func (m *Merlin) Install(_ *service.Config) error {
 	return nil
 }
 
+// Uninstall removes the ctrld-related configurations and services from the Merlin router and reverts to the original state.
 func (m *Merlin) Uninstall(_ *service.Config) error {
 	return nil
 }
 
+// PreRun prepares the Merlin instance for operation by waiting for essential services and directories to become available.
 func (m *Merlin) PreRun() error {
 	// Wait NTP ready.
 	_ = m.Cleanup()
@@ -66,6 +79,7 @@ func (m *Merlin) PreRun() error {
 	return nil
 }
 
+// Setup initializes and configures the Merlin instance for use, including setting up dnsmasq and necessary nvram settings.
 func (m *Merlin) Setup() error {
 	if m.cfg.FirstListener().IsDirectDnsListener() {
 		return nil
@@ -79,35 +93,10 @@ func (m *Merlin) Setup() error {
 		return err
 	}
 
-	// Copy current dnsmasq config to /jffs/configs/dnsmasq.conf,
-	// Then we will run postconf script on this file.
-	//
-	// Normally, adding postconf script is enough. However, we see
-	// reports on some Merlin devices that postconf scripts does not
-	// work, but manipulating the config directly via /jffs/configs does.
-	src, err := os.Open(dnsmasq.MerlinConfPath)
-	if err != nil {
-		return fmt.Errorf("failed to open dnsmasq config: %w", err)
-	}
-	defer src.Close()
-
-	dst, err := os.Create(dnsmasq.MerlinJffsConfPath)
-	if err != nil {
-		return fmt.Errorf("failed to create %s: %w", dnsmasq.MerlinJffsConfPath, err)
-	}
-	defer dst.Close()
-
-	if _, err := io.Copy(dst, src); err != nil {
-		return fmt.Errorf("failed to copy current dnsmasq config: %w", err)
-	}
-	if err := dst.Close(); err != nil {
-		return fmt.Errorf("failed to save %s: %w", dnsmasq.MerlinJffsConfPath, err)
-	}
-
-	// Run postconf script on /jffs/configs/dnsmasq.conf directly.
-	cmd := exec.Command("/bin/sh", dnsmasq.MerlinPostConfPath, dnsmasq.MerlinJffsConfPath)
-	if out, err := cmd.CombinedOutput(); err != nil {
-		return fmt.Errorf("failed to run post conf: %s: %w", string(out), err)
+	for _, cfg := range getDnsmasqConfigs() {
+		if err := m.setupDnsmasq(cfg); err != nil {
+			return fmt.Errorf("failed to setup dnsmasq: config: %s, error: %w", cfg.confPath, err)
+		}
 	}
 
 	// Restart dnsmasq service.
@@ -122,6 +111,7 @@ func (m *Merlin) Setup() error {
 	return nil
 }
 
+// Cleanup restores the original dnsmasq and nvram configurations and restarts dnsmasq if necessary.
 func (m *Merlin) Cleanup() error {
 	if m.cfg.FirstListener().IsDirectDnsListener() {
 		return nil
@@ -143,9 +133,11 @@ func (m *Merlin) Cleanup() error {
 	if err := os.WriteFile(dnsmasq.MerlinPostConfPath, merlinParsePostConf(buf), 0750); err != nil {
 		return err
 	}
-	// Remove /jffs/configs/dnsmasq.conf file.
-	if err := os.Remove(dnsmasq.MerlinJffsConfPath); err != nil && !os.IsNotExist(err) {
-		return err
+
+	for _, cfg := range getDnsmasqConfigs() {
+		if err := m.cleanupDnsmasqJffs(cfg); err != nil {
+			return fmt.Errorf("failed to cleanup jffs dnsmasq: config: %s, error: %w", cfg.confPath, err)
+		}
 	}
 	// Restart dnsmasq service.
 	if err := restartDNSMasq(); err != nil {
@@ -154,6 +146,54 @@ func (m *Merlin) Cleanup() error {
 	return nil
 }
 
+// setupDnsmasq sets up dnsmasq configuration by writing postconf, copying configuration, and running a postconf script.
+func (m *Merlin) setupDnsmasq(cfg *dnsmasqConfig) error {
+	src, err := os.Open(cfg.confPath)
+	if os.IsNotExist(err) {
+		return nil // nothing to do if conf file does not exist.
+	}
+	if err != nil {
+		return fmt.Errorf("failed to open dnsmasq config: %w", err)
+	}
+	defer src.Close()
+
+	// Copy current dnsmasq config to cfg.jffsConfPath,
+	// Then we will run postconf script on this file.
+	//
+	// Normally, adding postconf script is enough. However, we see
+	// reports on some Merlin devices that postconf scripts does not
+	// work, but manipulating the config directly via /jffs/configs does.
+	dst, err := os.Create(cfg.jffsConfPath)
+	if err != nil {
+		return fmt.Errorf("failed to create %s: %w", cfg.jffsConfPath, err)
+	}
+	defer dst.Close()
+
+	if _, err := io.Copy(dst, src); err != nil {
+		return fmt.Errorf("failed to copy current dnsmasq config: %w", err)
+	}
+	if err := dst.Close(); err != nil {
+		return fmt.Errorf("failed to save %s: %w", cfg.jffsConfPath, err)
+	}
+
+	// Run postconf script on cfg.jffsConfPath directly.
+	cmd := exec.Command("/bin/sh", dnsmasq.MerlinPostConfPath, cfg.jffsConfPath)
+	if out, err := cmd.CombinedOutput(); err != nil {
+		return fmt.Errorf("failed to run post conf: %s: %w", string(out), err)
+	}
+	return nil
+}
+
+// cleanupDnsmasqJffs removes the JFFS configuration file specified in the given dnsmasqConfig, if it exists.
+func (m *Merlin) cleanupDnsmasqJffs(cfg *dnsmasqConfig) error {
+	// Remove cfg.jffsConfPath file.
+	if err := os.Remove(cfg.jffsConfPath); err != nil && !os.IsNotExist(err) {
+		return err
+	}
+	return nil
+}
+
+// writeDnsmasqPostconf writes the requireddnsmasqConfigs post-configuration for dnsmasq to enable custom DNS settings with ctrld.
 func (m *Merlin) writeDnsmasqPostconf() error {
 	buf, err := os.ReadFile(dnsmasq.MerlinPostConfPath)
 	// Already setup.
@@ -179,6 +219,8 @@ func (m *Merlin) writeDnsmasqPostconf() error {
 	return os.WriteFile(dnsmasq.MerlinPostConfPath, []byte(data), 0750)
 }
 
+// restartDNSMasq restarts the dnsmasq service by executing the appropriate system command using "service".
+// Returns an error if the command fails or if there is an issue processing the command output.
 func restartDNSMasq() error {
 	if out, err := exec.Command("service", "restart_dnsmasq").CombinedOutput(); err != nil {
 		return fmt.Errorf("restart_dnsmasq: %s, %w", string(out), err)
@@ -186,6 +228,22 @@ func restartDNSMasq() error {
 	return nil
 }
 
+// getDnsmasqConfigs retrieves a list of dnsmasqConfig containing configuration and JFFS paths for dnsmasq operations.
+func getDnsmasqConfigs() []*dnsmasqConfig {
+	cfgs := []*dnsmasqConfig{
+		{dnsmasq.MerlinConfPath, dnsmasq.MerlinJffsConfPath},
+	}
+	for _, path := range dnsmasq.AdditionalConfigFiles() {
+		jffsConfPath := filepath.Join(dnsmasq.MerlinJffsConfDir, filepath.Base(path))
+		cfgs = append(cfgs, &dnsmasqConfig{path, jffsConfPath})
+	}
+
+	return cfgs
+}
+
+// merlinParsePostConf parses the dnsmasq post configuration by removing content after the MerlinPostConfMarker, if present.
+// If no marker is found, the original buffer is returned unmodified.
+// Returns nil if the input buffer is empty.
 func merlinParsePostConf(buf []byte) []byte {
 	if len(buf) == 0 {
 		return nil
@@ -197,6 +255,7 @@ func merlinParsePostConf(buf []byte) []byte {
 	return buf
 }
 
+// waitDirExists waits until the specified directory exists, polling its existence every second.
 func waitDirExists(dir string) {
 	for {
 		if _, err := os.Stat(dir); !os.IsNotExist(err) {

internal/router/service_ubios.go

@@ -13,14 +13,13 @@ import (
 	"time"
 
 	"github.com/kardianos/service"
+
+	"github.com/Control-D-Inc/ctrld/internal/router/dnsmasq"
 )
 
 // This is a copy of https://github.com/kardianos/service/blob/v1.2.1/service_sysv_linux.go,
 // with modification for supporting ubios v1 init system.
 
-// Keep in sync with ubios.ubiosDNSMasqConfigPath
-const ubiosDNSMasqConfigPath = "/run/dnsmasq.conf.d/zzzctrld.conf"
-
 type ubiosSvc struct {
 	i        service.Interface
 	platform string
@@ -86,7 +85,7 @@ func (s *ubiosSvc) Install() error {
 	}{
 		s.Config,
 		path,
-		ubiosDNSMasqConfigPath,
+		filepath.Join(dnsmasq.UbiosConfPath(), dnsmasq.UbiosConfName),
 	}
 
 	if err := s.template().Execute(f, to); err != nil {

internal/router/ubios/ubios.go

@@ -3,6 +3,7 @@ package ubios
 import (
 	"bytes"
 	"os"
+	"path/filepath"
 	"strconv"
 
 	"github.com/kardianos/service"
@@ -12,19 +13,19 @@ import (
 	"github.com/Control-D-Inc/ctrld/internal/router/edgeos"
 )
 
-const (
-	Name                      = "ubios"
-	ubiosDNSMasqConfigPath    = "/run/dnsmasq.conf.d/zzzctrld.conf"
-	ubiosDNSMasqDnsConfigPath = "/run/dnsmasq.conf.d/dns.conf"
-)
+const Name = "ubios"
 
 type Ubios struct {
-	cfg *ctrld.Config
+	cfg             *ctrld.Config
+	dnsmasqConfPath string
 }
 
 // New returns a router.Router for configuring/setup/run ctrld on Ubios routers.
 func New(cfg *ctrld.Config) *Ubios {
-	return &Ubios{cfg: cfg}
+	return &Ubios{
+		cfg:             cfg,
+		dnsmasqConfPath: filepath.Join(dnsmasq.UbiosConfPath(), dnsmasq.UbiosConfName),
+	}
 }
 
 func (u *Ubios) ConfigureService(config *service.Config) error {
@@ -59,7 +60,7 @@ func (u *Ubios) Setup() error {
 	if err != nil {
 		return err
 	}
-	if err := os.WriteFile(ubiosDNSMasqConfigPath, []byte(data), 0600); err != nil {
+	if err := os.WriteFile(u.dnsmasqConfPath, []byte(data), 0600); err != nil {
 		return err
 	}
 	// Restart dnsmasq service.
@@ -74,7 +75,7 @@ func (u *Ubios) Cleanup() error {
 		return nil
 	}
 	// Remove the custom dnsmasq config
-	if err := os.Remove(ubiosDNSMasqConfigPath); err != nil {
+	if err := os.Remove(u.dnsmasqConfPath); err != nil {
 		return err
 	}
 	// Restart dnsmasq service.
@@ -85,7 +86,7 @@ func (u *Ubios) Cleanup() error {
 }
 
 func restartDNSMasq() error {
-	buf, err := os.ReadFile("/run/dnsmasq.pid")
+	buf, err := os.ReadFile(dnsmasq.UbiosPidFile())
 	if err != nil {
 		return err
 	}

internal/system/chassis_darwin.go

@@ -0,0 +1,25 @@
+package system
+
+import (
+	"errors"
+	"fmt"
+
+	"github.com/brunogui0812/sysprofiler"
+)
+
+// GetChassisInfo retrieves hardware information including machine model type and vendor from the system profiler.
+func GetChassisInfo() (*ChassisInfo, error) {
+	hardwares, err := sysprofiler.Hardware()
+	if err != nil {
+		return nil, fmt.Errorf("failed to get hardware info: %w", err)
+	}
+	if len(hardwares) == 0 {
+		return nil, errors.New("no hardware info found")
+	}
+	hardware := hardwares[0]
+	info := &ChassisInfo{
+		Type:   hardware.MachineModel,
+		Vendor: "Apple Inc.",
+	}
+	return info, nil
+}

internal/system/chassis_others.go

@@ -0,0 +1,20 @@
+//go:build !darwin
+
+package system
+
+import "github.com/jaypipes/ghw"
+
+// GetChassisInfo retrieves hardware information including machine model type and vendor from the system profiler.
+func GetChassisInfo() (*ChassisInfo, error) {
+	// Disable warnings from ghw, since these are undesirable but recoverable errors.
+	// With warnings enabled, ghw will emit unnecessary log messages.
+	chassis, err := ghw.Chassis(ghw.WithDisableWarnings())
+	if err != nil {
+		return nil, err
+	}
+	info := &ChassisInfo{
+		Type:   chassis.TypeDescription,
+		Vendor: chassis.Vendor,
+	}
+	return info, nil
+}

internal/system/metadata.go

@@ -0,0 +1,7 @@
+package system
+
+// ChassisInfo represents the structural framework of a device, specifying its type and manufacturer information.
+type ChassisInfo struct {
+	Type   string
+	Vendor string
+}

internal/system/metadata_others.go

@@ -0,0 +1,8 @@
+//go:build !windows
+
+package system
+
+// GetActiveDirectoryDomain returns AD domain name of this computer.
+func GetActiveDirectoryDomain() (string, error) {
+	return "", nil
+}

internal/system/metadata_windows.go

@@ -0,0 +1,74 @@
+package system
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"log"
+	"os"
+	"strings"
+	"unsafe"
+
+	"github.com/microsoft/wmi/pkg/base/host"
+	hh "github.com/microsoft/wmi/pkg/hardware/host"
+	"golang.org/x/sys/windows"
+)
+
+// GetActiveDirectoryDomain returns AD domain name of this computer.
+func GetActiveDirectoryDomain() (string, error) {
+	log.SetOutput(io.Discard)
+	defer log.SetOutput(os.Stderr)
+
+	// 1) Check environment variable
+	envDomain := os.Getenv("USERDNSDOMAIN")
+	if envDomain != "" {
+		return strings.TrimSpace(envDomain), nil
+	}
+
+	// 2) Query WMI via the microsoft/wmi library
+	whost := host.NewWmiLocalHost()
+	cs, err := hh.GetComputerSystem(whost)
+	if cs != nil {
+		defer cs.Close()
+	}
+	if err != nil {
+		return "", err
+	}
+	pod, err := cs.GetPropertyPartOfDomain()
+	if err != nil {
+		return "", err
+	}
+	if pod {
+		domainVal, err := cs.GetPropertyDomain()
+		if err != nil {
+			return "", fmt.Errorf("failed to get domain property: %w", err)
+		}
+		domainName := strings.TrimSpace(fmt.Sprintf("%v", domainVal))
+		if domainName == "" {
+			return "", errors.New("machine does not appear to have a domain set")
+		}
+		return domainName, nil
+	}
+	return "", nil
+}
+
+// DomainJoinedStatus returns the domain joined status of the current computer.
+//
+// NETSETUP_JOIN_STATUS constants from Microsoft Windows API
+// See: https://learn.microsoft.com/en-us/windows/win32/api/lmjoin/ne-lmjoin-netsetup_join_status
+//
+// NetSetupUnknownStatus         uint32 = 0 // The status is unknown
+// NetSetupUnjoined              uint32 = 1 // The computer is not joined to a domain or workgroup
+// NetSetupWorkgroupName         uint32 = 2 // The computer is joined to a workgroup
+// NetSetupDomainName            uint32 = 3 // The computer is joined to a domain
+func DomainJoinedStatus() (uint32, error) {
+	var domain *uint16
+	var status uint32
+
+	if err := windows.NetGetJoinInformation(nil, &domain, &status); err != nil {
+		return 0, fmt.Errorf("failed to get domain join status: %w", err)
+	}
+	defer windows.NetApiBufferFree((*byte)(unsafe.Pointer(domain)))
+
+	return status, nil
+}

metadata.go

@@ -0,0 +1,61 @@
+package ctrld
+
+import (
+	"context"
+
+	"github.com/cuonglm/osinfo"
+
+	"github.com/Control-D-Inc/ctrld/internal/system"
+)
+
+const (
+	metadataOsKey                = "os"
+	metadataChassisTypeKey       = "chassis_type"
+	metadataChassisVendorKey     = "chassis_vendor"
+	metadataUsernameKey          = "username"
+	metadataDomainOrWorkgroupKey = "domain_or_workgroup"
+	metadataDomainKey            = "domain"
+)
+
+var (
+	chassisType   string
+	chassisVendor string
+)
+
+// SystemMetadata collects full system metadata including username discovery.
+// Use for initial provisioning and first-run config validation where full
+// device identification is needed.
+func SystemMetadata(ctx context.Context) map[string]string {
+	return systemMetadata(ctx, true)
+}
+
+// SystemMetadataRuntime collects system metadata without username discovery.
+// Use for runtime API calls (config reload, self-uninstall check, deactivation
+// pin refresh) to avoid repeated user enumeration that can trigger EDR alerts.
+func SystemMetadataRuntime(ctx context.Context) map[string]string {
+	return systemMetadata(ctx, false)
+}
+
+func systemMetadata(ctx context.Context, includeUsername bool) map[string]string {
+	m := make(map[string]string)
+	oi := osinfo.New()
+	m[metadataOsKey] = oi.String()
+	if chassisType == "" && chassisVendor == "" {
+		if ci, err := system.GetChassisInfo(); err == nil {
+			chassisType, chassisVendor = ci.Type, ci.Vendor
+		}
+	}
+	m[metadataChassisTypeKey] = chassisType
+	m[metadataChassisVendorKey] = chassisVendor
+	if includeUsername {
+		m[metadataUsernameKey] = DiscoverMainUser(ctx)
+	}
+	m[metadataDomainOrWorkgroupKey] = partOfDomainOrWorkgroup(ctx)
+	domain, err := system.GetActiveDirectoryDomain()
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("Failed to get active directory domain name")
+	}
+	m[metadataDomainKey] = domain
+
+	return m
+}

metadata_others.go

@@ -0,0 +1,10 @@
+//go:build !windows
+
+package ctrld
+
+import "context"
+
+// partOfDomainOrWorkgroup checks if the computer is part of a domain or workgroup and returns "true" or "false".
+func partOfDomainOrWorkgroup(ctx context.Context) string {
+	return "false"
+}

metadata_test.go

@@ -0,0 +1,15 @@
+package ctrld
+
+import (
+	"context"
+	"os"
+	"testing"
+)
+
+func Test_metadata(t *testing.T) {
+	m := SystemMetadata(context.Background())
+	t.Logf("metadata: %v", m)
+	t.Logf("SUDO_USER: %s", os.Getenv("SUDO_USER"))
+	t.Logf("LOGNAME: %s", os.Getenv("LOGNAME"))
+	t.Logf("USER: %s", os.Getenv("USER"))
+}

metadata_windows.go

@@ -0,0 +1,22 @@
+package ctrld
+
+import (
+	"context"
+
+	"github.com/Control-D-Inc/ctrld/internal/system"
+)
+
+// partOfDomainOrWorkgroup checks if the computer is part of a domain or workgroup and returns "true" or "false".
+func partOfDomainOrWorkgroup(ctx context.Context) string {
+	status, err := system.DomainJoinedStatus()
+	if err != nil {
+		ProxyLogger.Load().Debug().Err(err).Msg("Failed to get domain join status")
+		return "false"
+	}
+	switch status {
+	case 2, 3:
+		return "true"
+	default:
+		return "false"
+	}
+}

nameservers_linux.go

@@ -5,9 +5,12 @@ import (
 	"bytes"
 	"encoding/hex"
 	"net"
+	"net/netip"
 	"os"
 	"strings"
 
+	"tailscale.com/net/netmon"
+
 	"github.com/Control-D-Inc/ctrld/internal/dns/resolvconffile"
 )
 
@@ -128,3 +131,25 @@ func virtualInterfaces() set {
 	}
 	return s
 }
+
+// validInterfacesMap returns a set containing non virtual interfaces.
+// TODO: deduplicated with cmd/cli/net_linux.go in v2.
+func validInterfaces() set {
+	m := make(map[string]struct{})
+	vis := virtualInterfaces()
+	netmon.ForeachInterface(func(i netmon.Interface, prefixes []netip.Prefix) {
+		if _, existed := vis[i.Name]; existed {
+			return
+		}
+		m[i.Name] = struct{}{}
+	})
+	// Fallback to default route interface if found nothing.
+	if len(m) == 0 {
+		defaultRoute, err := netmon.DefaultRoute()
+		if err != nil {
+			return m
+		}
+		m[defaultRoute.InterfaceName] = struct{}{}
+	}
+	return m
+}

nameservers_windows.go

@@ -8,6 +8,7 @@ import (
 	"net"
 	"os"
 	"strings"
+	"sync"
 	"syscall"
 	"time"
 	"unsafe"
@@ -17,26 +18,48 @@ import (
 	"github.com/microsoft/wmi/pkg/base/query"
 	"github.com/microsoft/wmi/pkg/constant"
 	"github.com/microsoft/wmi/pkg/hardware/network/netadapter"
+	"github.com/miekg/dns"
 	"golang.org/x/sys/windows"
 	"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
 	"tailscale.com/net/netmon"
+
+	"github.com/Control-D-Inc/ctrld/internal/system"
 )
 
 const (
-	maxDNSAdapterRetries                 = 5
-	retryDelayDNSAdapter                 = 1 * time.Second
-	defaultDNSAdapterTimeout             = 10 * time.Second
-	minDNSServers                        = 1 // Minimum number of DNS servers we want to find
-	NetSetupUnknown               uint32 = 0
-	NetSetupWorkgroup             uint32 = 1
-	NetSetupDomain                uint32 = 2
-	NetSetupCloudDomain           uint32 = 3
-	DS_FORCE_REDISCOVERY                 = 0x00000001
-	DS_DIRECTORY_SERVICE_REQUIRED        = 0x00000010
-	DS_BACKGROUND_ONLY                   = 0x00000100
-	DS_IP_REQUIRED                       = 0x00000200
-	DS_IS_DNS_NAME                       = 0x00020000
-	DS_RETURN_DNS_NAME                   = 0x40000000
+	maxDNSAdapterRetries     = 5
+	retryDelayDNSAdapter     = 1 * time.Second
+	defaultDNSAdapterTimeout = 10 * time.Second
+	minDNSServers            = 1 // Minimum number of DNS servers we want to find
+
+	DS_FORCE_REDISCOVERY          = 0x00000001
+	DS_DIRECTORY_SERVICE_REQUIRED = 0x00000010
+	DS_BACKGROUND_ONLY            = 0x00000100
+	DS_IP_REQUIRED                = 0x00000200
+	DS_IS_DNS_NAME                = 0x00020000
+	DS_RETURN_DNS_NAME            = 0x40000000
+
+	// AD DC retry constants
+	dcRetryInitialDelay = 1 * time.Second
+	dcRetryMaxDelay     = 30 * time.Second
+	dcRetryMaxAttempts  = 10
+
+	// DsGetDcName error codes
+	errNoSuchDomain   uintptr = 1355
+	errNoLogonServers uintptr = 1311
+	errDCNotFound     uintptr = 1004
+	errRPCUnavailable uintptr = 1722
+	errConnReset      uintptr = 10054
+	errNetUnreachable uintptr = 1231
+)
+
+var (
+	dcRetryMu     sync.Mutex
+	dcRetryCancel context.CancelFunc
+
+	// Lazy-loaded netapi32 for DsGetDcNameW calls.
+	netapi32DLL  = windows.NewLazySystemDLL("netapi32.dll")
+	dsGetDcNameW = netapi32DLL.NewProc("DsGetDcNameW")
 )
 
 type DomainControllerInfo struct {
@@ -110,6 +133,9 @@ func dnsFromAdapter() []string {
 func getDNSServers(ctx context.Context) ([]string, error) {
 	logger := *ProxyLogger.Load()
 
+	// Cancel any in-flight DC retry from a previous network state.
+	cancelDCRetry()
+
 	// Check context before making the call
 	if ctx.Err() != nil {
 		return nil, ctx.Err()
@@ -129,72 +155,75 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 
 	// Try to get domain controller info if domain-joined
 	var dcServers []string
+	var adDomain string
 	isDomain := checkDomainJoined()
 	if isDomain {
-		domainName, err := getLocalADDomain()
+		domainName, err := system.GetActiveDirectoryDomain()
 		if err != nil {
-			Log(context.Background(), logger.Debug(),
+			Log(ctx, logger.Debug(),
 				"Failed to get local AD domain: %v", err)
 		} else {
+			adDomain = domainName
 			// Load netapi32.dll
-			netapi32 := windows.NewLazySystemDLL("netapi32.dll")
-			dsDcName := netapi32.NewProc("DsGetDcNameW")
-
 			var info *DomainControllerInfo
 			flags := uint32(DS_RETURN_DNS_NAME | DS_IP_REQUIRED | DS_IS_DNS_NAME)
 
 			domainUTF16, err := windows.UTF16PtrFromString(domainName)
 			if err != nil {
-				Log(context.Background(), logger.Debug(),
-					"Failed to convert domain name to UTF16: %v", err)
+				Log(ctx, logger.Debug(), "Failed to convert domain name to UTF16: %v", err)
 			} else {
-				Log(context.Background(), logger.Debug(),
+				Log(ctx, logger.Debug(),
 					"Attempting to get DC for domain: %s with flags: 0x%x", domainName, flags)
 
 				// Call DsGetDcNameW with domain name
-				ret, _, err := dsDcName.Call(
+				ret, _, err := dsGetDcNameW.Call(
 					0,                                    // ComputerName - can be NULL
 					uintptr(unsafe.Pointer(domainUTF16)), // DomainName
 					0,                                    // DomainGuid - not needed
 					0,                                    // SiteName - not needed
 					uintptr(flags),                       // Flags
-					uintptr(unsafe.Pointer(&info))) // DomainControllerInfo - output
+					uintptr(unsafe.Pointer(&info)))       // DomainControllerInfo - output
 
 				if ret != 0 {
 					switch ret {
-					case 1355: // ERROR_NO_SUCH_DOMAIN
-						Log(context.Background(), logger.Debug(),
+					case errNoSuchDomain:
+						Log(ctx, logger.Debug(),
 							"Domain not found: %s (%d)", domainName, ret)
-					case 1311: // ERROR_NO_LOGON_SERVERS
-						Log(context.Background(), logger.Debug(),
+					case errNoLogonServers:
+						Log(ctx, logger.Debug(),
 							"No logon servers available for domain: %s (%d)", domainName, ret)
-					case 1004: // ERROR_DC_NOT_FOUND
-						Log(context.Background(), logger.Debug(),
+					case errDCNotFound:
+						Log(ctx, logger.Debug(),
 							"Domain controller not found for domain: %s (%d)", domainName, ret)
-					case 1722: // RPC_S_SERVER_UNAVAILABLE
-						Log(context.Background(), logger.Debug(),
+					case errRPCUnavailable:
+						Log(ctx, logger.Debug(),
 							"RPC server unavailable for domain: %s (%d)", domainName, ret)
 					default:
-						Log(context.Background(), logger.Debug(),
+						Log(ctx, logger.Debug(),
 							"Failed to get domain controller info for domain %s: %d, %v", domainName, ret, err)
 					}
+					// Start background retry for transient DC errors.
+					if isTransientDCError(ret) {
+						Log(ctx, logger.Info(),
+							"AD DC detection failed with transient error %d for %s, starting background retry", ret, domainName)
+						startDCRetry(domainName)
+					}
 				} else if info != nil {
 					defer windows.NetApiBufferFree((*byte)(unsafe.Pointer(info)))
 
 					if info.DomainControllerAddress != nil {
 						dcAddr := windows.UTF16PtrToString(info.DomainControllerAddress)
 						dcAddr = strings.TrimPrefix(dcAddr, "\\\\")
-						Log(context.Background(), logger.Debug(),
+						Log(ctx, logger.Debug(),
 							"Found domain controller address: %s", dcAddr)
 
 						if ip := net.ParseIP(dcAddr); ip != nil {
 							dcServers = append(dcServers, ip.String())
-							Log(context.Background(), logger.Debug(),
+							Log(ctx, logger.Debug(),
 								"Added domain controller DNS servers: %v", dcServers)
 						}
 					} else {
-						Log(context.Background(), logger.Debug(),
-							"No domain controller address found")
+						Log(ctx, logger.Debug(), "No domain controller address found")
 					}
 				}
 			}
@@ -209,7 +238,7 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 	// Collect all local IPs
 	for _, aa := range aas {
 		if aa.OperStatus != winipcfg.IfOperStatusUp {
-			Log(context.Background(), logger.Debug(),
+			Log(ctx, logger.Debug(),
 				"Skipping adapter %s - not up, status: %d", aa.FriendlyName(), aa.OperStatus)
 			continue
 		}
@@ -217,24 +246,25 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 		// Skip if software loopback or other non-physical types
 		// This is to avoid the "Loopback Pseudo-Interface 1" issue we see on windows
 		if aa.IfType == winipcfg.IfTypeSoftwareLoopback {
-			Log(context.Background(), logger.Debug(),
-				"Skipping %s (software loopback)", aa.FriendlyName())
+			Log(ctx, logger.Debug(), "Skipping %s (software loopback)", aa.FriendlyName())
 			continue
 		}
 
-		Log(context.Background(), logger.Debug(),
-			"Processing adapter %s", aa.FriendlyName())
+		Log(ctx, logger.Debug(), "Processing adapter %s", aa.FriendlyName())
 
 		for a := aa.FirstUnicastAddress; a != nil; a = a.Next {
 			ip := a.Address.IP().String()
 			addressMap[ip] = struct{}{}
-			Log(context.Background(), logger.Debug(),
-				"Added local IP %s from adapter %s", ip, aa.FriendlyName())
+			Log(ctx, logger.Debug(), "Added local IP %s from adapter %s", ip, aa.FriendlyName())
 		}
 	}
 
 	validInterfacesMap := validInterfaces()
 
+	if isDomain && adDomain == "" {
+		Log(ctx, logger.Warn(), "The machine is joined domain, but domain name is empty")
+	}
+	checkDnsSuffix := isDomain && adDomain != ""
 	// Collect DNS servers
 	for _, aa := range aas {
 		if aa.OperStatus != winipcfg.IfOperStatusUp {
@@ -244,23 +274,33 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 		// Skip if software loopback or other non-physical types
 		// This is to avoid the "Loopback Pseudo-Interface 1" issue we see on windows
 		if aa.IfType == winipcfg.IfTypeSoftwareLoopback {
-			Log(context.Background(), logger.Debug(),
-				"Skipping %s (software loopback)", aa.FriendlyName())
+			Log(ctx, logger.Debug(), "Skipping %s (software loopback)", aa.FriendlyName())
 			continue
 		}
 
-		// if not in the validInterfacesMap, skip
-		if _, ok := validInterfacesMap[aa.FriendlyName()]; !ok {
-			Log(context.Background(), logger.Debug(),
-				"Skipping %s (not in validInterfacesMap)", aa.FriendlyName())
+		_, valid := validInterfacesMap[aa.FriendlyName()]
+		if !valid && checkDnsSuffix {
+			for suffix := aa.FirstDNSSuffix; suffix != nil; suffix = suffix.Next {
+				// For non-physical adapters but have the DNS suffix that matches the domain name,
+				// (or vice versa) consider it valid. This can happen when remote VPN machines.
+				ds := strings.TrimSpace(suffix.String())
+				if dns.IsSubDomain(adDomain, ds) || dns.IsSubDomain(ds, adDomain) {
+					Log(ctx, logger.Debug(), "Found valid interface %s with DNS suffix %s", aa.FriendlyName(), suffix.String())
+					valid = true
+					break
+				}
+			}
+		}
+		// if not a valid interface, skip it
+		if !valid {
+			Log(ctx, logger.Debug(), "Skipping %s (not in validInterfacesMap)", aa.FriendlyName())
 			continue
 		}
 
 		for dns := aa.FirstDNSServerAddress; dns != nil; dns = dns.Next {
 			ip := dns.Address.IP()
 			if ip == nil {
-				Log(context.Background(), logger.Debug(),
-					"Skipping nil IP from adapter %s", aa.FriendlyName())
+				Log(ctx, logger.Debug(), "Skipping nil IP from adapter %s", aa.FriendlyName())
 				continue
 			}
 
@@ -293,28 +333,23 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 		if !seen[dcServer] {
 			seen[dcServer] = true
 			ns = append(ns, dcServer)
-			Log(context.Background(), logger.Debug(),
-				"Added additional domain controller DNS server: %s", dcServer)
+			Log(ctx, logger.Debug(), "Added additional domain controller DNS server: %s", dcServer)
 		}
 	}
 
 	// if we have static DNS servers saved for the current default route, we should add them to the list
 	drIfaceName, err := netmon.DefaultRouteInterface()
 	if err != nil {
-		Log(context.Background(), logger.Debug(),
-			"Failed to get default route interface: %v", err)
+		Log(ctx, logger.Debug(), "Failed to get default route interface: %v", err)
 	} else {
 		drIface, err := net.InterfaceByName(drIfaceName)
 		if err != nil {
-			Log(context.Background(), logger.Debug(),
-				"Failed to get interface by name %s: %v", drIfaceName, err)
+			Log(ctx, logger.Debug(), "Failed to get interface by name %s: %v", drIfaceName, err)
 		} else {
 			staticNs, file := SavedStaticNameservers(drIface)
-			Log(context.Background(), logger.Debug(),
-				"static dns servers from %s: %v", file, staticNs)
+			Log(ctx, logger.Debug(), "static dns servers from %s: %v", file, staticNs)
 			if len(staticNs) > 0 {
-				Log(context.Background(), logger.Debug(),
-					"Adding static DNS servers from %s: %v", drIfaceName, staticNs)
+				Log(ctx, logger.Debug(), "Adding static DNS servers from %s: %v", drIfaceName, staticNs)
 				ns = append(ns, staticNs...)
 			}
 		}
@@ -324,8 +359,7 @@ func getDNSServers(ctx context.Context) ([]string, error) {
 		return nil, fmt.Errorf("no valid DNS servers found")
 	}
 
-	Log(context.Background(), logger.Debug(),
-		"DNS server discovery completed, count=%d, servers=%v (including %d DC servers)",
+	Log(ctx, logger.Debug(), "DNS server discovery completed, count=%d, servers=%v (including %d DC servers)",
 		len(ns), ns, len(dcServers))
 	return ns, nil
 }
@@ -340,72 +374,153 @@ func currentNameserversFromResolvconf() []string {
 func checkDomainJoined() bool {
 	logger := *ProxyLogger.Load()
 
-	var domain *uint16
-	var status uint32
-
-	err := windows.NetGetJoinInformation(nil, &domain, &status)
+	status, err := system.DomainJoinedStatus()
 	if err != nil {
-		Log(context.Background(), logger.Debug(),
-			"Failed to get domain join status: %v", err)
+		logger.Debug().Msgf("Failed to get domain joined status: %v", err)
 		return false
 	}
-	defer windows.NetApiBufferFree((*byte)(unsafe.Pointer(domain)))
-
-	domainName := windows.UTF16PtrToString(domain)
-	Log(context.Background(), logger.Debug(),
-		"Domain join status: domain=%s status=%d (Unknown=0, Workgroup=1, Domain=2, CloudDomain=3)",
-		domainName, status)
-
-	// Consider domain or cloud domain as domain-joined
-	isDomain := status == NetSetupDomain || status == NetSetupCloudDomain
-	Log(context.Background(), logger.Debug(),
-		"Is domain joined? status=%d, traditional=%v, cloud=%v, result=%v",
-		status,
-		status == NetSetupDomain,
-		status == NetSetupCloudDomain,
-		isDomain)
+	isDomain := status == syscall.NetSetupDomainName
+	logger.Debug().Msg("Domain join status: (UnknownStatus=0, Unjoined=1, WorkgroupName=2, DomainName=3)")
+	logger.Debug().Msgf("Is domain joined? status=%d, result=%v", status, isDomain)
 
 	return isDomain
 }
 
-// getLocalADDomain uses Microsoft's WMI wrappers (github.com/microsoft/wmi/pkg/*)
-// to query the Domain field from Win32_ComputerSystem instead of a direct go-ole call.
-func getLocalADDomain() (string, error) {
-	log.SetOutput(io.Discard)
-	defer log.SetOutput(os.Stderr)
-	// 1) Check environment variable
-	envDomain := os.Getenv("USERDNSDOMAIN")
-	if envDomain != "" {
-		return strings.TrimSpace(envDomain), nil
+// isTransientDCError returns true if the DsGetDcName error code indicates
+// a transient failure that may succeed on retry.
+func isTransientDCError(code uintptr) bool {
+	switch code {
+	case errConnReset, errRPCUnavailable, errNoLogonServers, errDCNotFound, errNetUnreachable:
+		return true
+	default:
+		return false
 	}
+}
 
-	// 2) Query WMI via the microsoft/wmi library
-	whost := host.NewWmiLocalHost()
-	q := query.NewWmiQuery("Win32_ComputerSystem")
-	instances, err := instance.GetWmiInstancesFromHost(whost, string(constant.CimV2), q)
-	if instances != nil {
-		defer instances.Close()
+// cancelDCRetry cancels any in-flight DC retry goroutine.
+func cancelDCRetry() {
+	dcRetryMu.Lock()
+	defer dcRetryMu.Unlock()
+	if dcRetryCancel != nil {
+		dcRetryCancel()
+		dcRetryCancel = nil
 	}
+}
+
+// startDCRetry spawns a background goroutine that retries DsGetDcName with
+// exponential backoff. On success it appends the DC IP to the OS resolver.
+func startDCRetry(domainName string) {
+	dcRetryMu.Lock()
+	// Cancel any previous retry.
+	if dcRetryCancel != nil {
+		dcRetryCancel()
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	dcRetryCancel = cancel
+	dcRetryMu.Unlock()
+
+	go func() {
+		logger := *ProxyLogger.Load()
+		delay := dcRetryInitialDelay
+
+		for attempt := 1; attempt <= dcRetryMaxAttempts; attempt++ {
+			select {
+			case <-ctx.Done():
+				Log(context.Background(), logger.Debug(), "AD DC retry cancelled for domain %s", domainName)
+				return
+			case <-time.After(delay):
+			}
+
+			Log(ctx, logger.Debug(),
+				"AD DC retry attempt %d/%d for domain %s (delay was %v)",
+				attempt, dcRetryMaxAttempts, domainName, delay)
+
+			dcIP, errCode := tryGetDCAddress(domainName)
+			if dcIP != "" {
+				Log(context.Background(), logger.Info(),
+					"AD DC retry succeeded: found DC at %s for domain %s (attempt %d)",
+					dcIP, domainName, attempt)
+				if AppendOsResolverNameservers([]string{dcIP}) {
+					Log(context.Background(), logger.Info(),
+						"Added DC %s to OS resolver nameservers", dcIP)
+				} else {
+					Log(context.Background(), logger.Warn(),
+						"AD DC retry: OS resolver not initialized, DC IP %s was not added", dcIP)
+				}
+				return
+			}
+
+			// Permanent error or unexpected empty result — stop retrying.
+			if errCode != 0 && !isTransientDCError(errCode) {
+				Log(context.Background(), logger.Debug(),
+					"AD DC retry stopping: permanent error %d for domain %s", errCode, domainName)
+				return
+			}
+			if errCode == 0 {
+				// DsGetDcName returned success but no usable address — don't retry.
+				Log(context.Background(), logger.Debug(),
+					"AD DC retry stopping: DsGetDcName returned no address for domain %s", domainName)
+				return
+			}
+
+			// Exponential backoff.
+			delay *= 2
+			if delay > dcRetryMaxDelay {
+				delay = dcRetryMaxDelay
+			}
+		}
+
+		Log(ctx, logger.Warn(),
+			"AD DC retry exhausted %d attempts for domain %s", dcRetryMaxAttempts, domainName)
+	}()
+}
+
+// tryGetDCAddress attempts a single DsGetDcName call and returns the DC IP on success,
+// or empty string and the error code on failure.
+func tryGetDCAddress(domainName string) (string, uintptr) {
+	logger := *ProxyLogger.Load()
+
+	var info *DomainControllerInfo
+	// Use DS_FORCE_REDISCOVERY on retries to bypass the DC locator cache,
+	// which may have cached the initial transient failure.
+	flags := uint32(DS_RETURN_DNS_NAME | DS_IP_REQUIRED | DS_IS_DNS_NAME | DS_FORCE_REDISCOVERY)
+
+	domainUTF16, err := windows.UTF16PtrFromString(domainName)
 	if err != nil {
-		return "", fmt.Errorf("WMI query failed: %v", err)
+		Log(context.Background(), logger.Debug(),
+			"Failed to convert domain name to UTF16: %v", err)
+		return "", 0
 	}
 
-	// If no results, return an error
-	if len(instances) == 0 {
-		return "", fmt.Errorf("no rows returned from Win32_ComputerSystem")
+	ret, _, _ := dsGetDcNameW.Call(
+		0,
+		uintptr(unsafe.Pointer(domainUTF16)),
+		0,
+		0,
+		uintptr(flags),
+		uintptr(unsafe.Pointer(&info)))
+
+	if ret != 0 {
+		Log(context.Background(), logger.Debug(),
+			"DsGetDcName retry failed for %s: error %d", domainName, ret)
+		return "", ret
 	}
 
-	// We only care about the first row
-	domainVal, err := instances[0].GetProperty("Domain")
-	if err != nil {
-		return "", fmt.Errorf("machine does not appear to have a domain set: %v", err)
+	if info == nil {
+		return "", 0
+	}
+	defer windows.NetApiBufferFree((*byte)(unsafe.Pointer(info)))
+
+	if info.DomainControllerAddress == nil {
+		return "", 0
 	}
 
-	domainName := strings.TrimSpace(fmt.Sprintf("%v", domainVal))
-	if domainName == "" {
-		return "", fmt.Errorf("machine does not appear to have a domain set")
+	dcAddr := windows.UTF16PtrToString(info.DomainControllerAddress)
+	dcAddr = strings.TrimPrefix(dcAddr, "\\\\")
+	if ip := net.ParseIP(dcAddr); ip != nil {
+		return ip.String(), 0
 	}
-	return domainName, nil
+	return "", 0
 }
 
 // validInterfaces returns a list of all physical interfaces.

net_darwin.go

@@ -0,0 +1,35 @@
+package ctrld
+
+import (
+	"bufio"
+	"bytes"
+	"io"
+	"os/exec"
+	"strings"
+)
+
+// validInterfaces returns a set of all valid hardware ports.
+// TODO: deduplicated with cmd/cli/net_darwin.go in v2.
+func validInterfaces() map[string]struct{} {
+	b, err := exec.Command("networksetup", "-listallhardwareports").Output()
+	if err != nil {
+		return nil
+	}
+	return parseListAllHardwarePorts(bytes.NewReader(b))
+}
+
+// parseListAllHardwarePorts parses output of "networksetup -listallhardwareports"
+// and returns map presents all hardware ports.
+func parseListAllHardwarePorts(r io.Reader) map[string]struct{} {
+	m := make(map[string]struct{})
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := scanner.Text()
+		after, ok := strings.CutPrefix(line, "Device: ")
+		if !ok {
+			continue
+		}
+		m[after] = struct{}{}
+	}
+	return m
+}

net_darwin_test.go

@@ -1,4 +1,4 @@
-package cli
+package ctrld
 
 import (
 	"maps"

net_others.go

@@ -0,0 +1,15 @@
+//go:build !darwin && !windows && !linux
+
+package ctrld
+
+import "tailscale.com/net/netmon"
+
+// validInterfaces returns a set containing only default route interfaces.
+// TODO: deuplicated with cmd/cli/net_others.go in v2.
+func validInterfaces() map[string]struct{} {
+	defaultRoute, err := netmon.DefaultRoute()
+	if err != nil {
+		return nil
+	}
+	return map[string]struct{}{defaultRoute.InterfaceName: {}}
+}

resolver.go

@@ -234,6 +234,79 @@ type publicResponse struct {
 	server string
 }
 
+// OsResolverNameservers returns the current OS resolver nameservers (host:port format).
+// Returns nil if the OS resolver has not been initialized.
+func OsResolverNameservers() []string {
+	resolverMutex.Lock()
+	r := or
+	resolverMutex.Unlock()
+	if r == nil {
+		return nil
+	}
+	var nss []string
+	if lan := r.lanServers.Load(); lan != nil {
+		nss = append(nss, *lan...)
+	}
+	if pub := r.publicServers.Load(); pub != nil {
+		nss = append(nss, *pub...)
+	}
+	return nss
+}
+
+// AppendOsResolverNameservers adds additional nameservers to the existing OS resolver
+// without reinitializing it. This is used for late-arriving nameservers such as AD
+// domain controller IPs discovered via background retry.
+// Returns true if nameservers were actually added.
+func AppendOsResolverNameservers(servers []string) bool {
+	if len(servers) == 0 {
+		return false
+	}
+	resolverMutex.Lock()
+	defer resolverMutex.Unlock()
+	if or == nil {
+		return false
+	}
+
+	// Collect existing nameservers to avoid duplicates.
+	existing := make(map[string]bool)
+	if lan := or.lanServers.Load(); lan != nil {
+		for _, s := range *lan {
+			existing[s] = true
+		}
+	}
+	if pub := or.publicServers.Load(); pub != nil {
+		for _, s := range *pub {
+			existing[s] = true
+		}
+	}
+
+	var added bool
+	for _, s := range servers {
+		// Normalize to host:port format.
+		if _, _, err := net.SplitHostPort(s); err != nil {
+			s = net.JoinHostPort(s, "53")
+		}
+		if existing[s] {
+			continue
+		}
+		existing[s] = true
+		added = true
+
+		ip, _, _ := net.SplitHostPort(s)
+		addr, _ := netip.ParseAddr(ip)
+		if isLanAddr(addr) {
+			lan := or.lanServers.Load()
+			newLan := append(append([]string{}, (*lan)...), s)
+			or.lanServers.Store(&newLan)
+		} else {
+			pub := or.publicServers.Load()
+			newPub := append(append([]string{}, (*pub)...), s)
+			or.publicServers.Store(&newPub)
+		}
+	}
+	return added
+}
+
 // SetDefaultLocalIPv4 updates the stored local IPv4.
 func SetDefaultLocalIPv4(ip net.IP) {
 	Log(context.Background(), ProxyLogger.Load().Debug(), "SetDefaultLocalIPv4: %s", ip)
@@ -291,6 +364,9 @@ const hotCacheTTL = time.Second
 // for a short period (currently 1 second), reducing unnecessary traffics
 // sent to upstreams.
 func (o *osResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	if err := validateMsg(msg); err != nil {
+		return nil, err
+	}
 	if len(msg.Question) == 0 {
 		return nil, errors.New("no question found")
 	}
@@ -509,6 +585,10 @@ type legacyResolver struct {
 }
 
 func (r *legacyResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	if err := validateMsg(msg); err != nil {
+		return nil, err
+	}
+
 	// See comment in (*dotResolver).resolve method.
 	dialer := newDialer(net.JoinHostPort(controldPublicDns, "53"))
 	dnsTyp := uint16(0)
@@ -534,6 +614,9 @@ func (r *legacyResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, e
 type dummyResolver struct{}
 
 func (d dummyResolver) Resolve(ctx context.Context, msg *dns.Msg) (*dns.Msg, error) {
+	if err := validateMsg(msg); err != nil {
+		return nil, err
+	}
 	ans := new(dns.Msg)
 	ans.SetReply(msg)
 	return ans, nil
@@ -729,10 +812,15 @@ func newResolverWithNameserver(nameservers []string) *osResolver {
 	return r
 }
 
-// Rfc1918Addresses returns the list of local interfaces private IP addresses
+// Rfc1918Addresses returns the list of local physical interfaces private IP addresses
 func Rfc1918Addresses() []string {
+	vis := validInterfaces()
 	var res []string
 	netmon.ForeachInterface(func(i netmon.Interface, prefixes []netip.Prefix) {
+		// Skip virtual interfaces.
+		if _, existed := vis[i.Name]; !existed {
+			return
+		}
 		addrs, _ := i.Addrs()
 		for _, addr := range addrs {
 			ipNet, ok := addr.(*net.IPNet)
@@ -764,3 +852,13 @@ func isLanAddr(addr netip.Addr) bool {
 		addr.IsLinkLocalUnicast() ||
 		tsaddr.CGNATRange().Contains(addr)
 }
+
+func validateMsg(msg *dns.Msg) error {
+	if msg == nil {
+		return errors.New("nil DNS message")
+	}
+	if len(msg.Question) == 0 {
+		return errors.New("no question found")
+	}
+	return nil
+}

resolver_test.go

@@ -282,6 +282,35 @@ func Test_Edns0_CacheReply(t *testing.T) {
 	}
 }
 
+// https://github.com/Control-D-Inc/ctrld/issues/255
+func Test_legacyResolverWithBigExtraSection(t *testing.T) {
+	lanPC, err := net.ListenPacket("udp", "127.0.0.1:0") // 127.0.0.1 is considered LAN (loopback)
+	if err != nil {
+		t.Fatalf("failed to listen on LAN address: %v", err)
+	}
+	lanServer, lanAddr, err := runLocalPacketConnTestServer(t, lanPC, bigExtraSectionHandler())
+	if err != nil {
+		t.Fatalf("failed to run LAN test server: %v", err)
+	}
+	defer lanServer.Shutdown()
+
+	uc := &UpstreamConfig{
+		Name:     "Legacy",
+		Type:     ResolverTypeLegacy,
+		Endpoint: lanAddr,
+	}
+	uc.Init()
+	r, err := NewResolver(uc)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = r.Resolve(context.Background(), uc.VerifyMsg())
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
 func Test_upstreamTypeFromEndpoint(t *testing.T) {
 	tests := []struct {
 		name         string
@@ -370,6 +399,68 @@ func countHandler(call *atomic.Int64) dns.HandlerFunc {
 	}
 }
 
+func mustRR(s string) dns.RR {
+	r, err := dns.NewRR(s)
+	if err != nil {
+		panic(err)
+	}
+	return r
+}
+
+func bigExtraSectionHandler() dns.HandlerFunc {
+	return func(w dns.ResponseWriter, msg *dns.Msg) {
+		m := &dns.Msg{
+			Answer: []dns.RR{
+				mustRR(".			7149	IN	NS	m.root-servers.net."),
+				mustRR(".			7149	IN	NS	c.root-servers.net."),
+				mustRR(".			7149	IN	NS	e.root-servers.net."),
+				mustRR(".			7149	IN	NS	j.root-servers.net."),
+				mustRR(".			7149	IN	NS	g.root-servers.net."),
+				mustRR(".			7149	IN	NS	k.root-servers.net."),
+				mustRR(".			7149	IN	NS	l.root-servers.net."),
+				mustRR(".			7149	IN	NS	d.root-servers.net."),
+				mustRR(".			7149	IN	NS	h.root-servers.net."),
+				mustRR(".			7149	IN	NS	b.root-servers.net."),
+				mustRR(".			7149	IN	NS	a.root-servers.net."),
+				mustRR(".			7149	IN	NS	f.root-servers.net."),
+				mustRR(".			7149	IN	NS	i.root-servers.net."),
+			},
+			Extra: []dns.RR{
+				mustRR("m.root-servers.net.	656	IN	A	202.12.27.33"),
+				mustRR("m.root-servers.net.	656	IN	AAAA	2001:dc3::35"),
+				mustRR("c.root-servers.net.	656	IN	A	192.33.4.12"),
+				mustRR("c.root-servers.net.	656	IN	AAAA	2001:500:2::c"),
+				mustRR("e.root-servers.net.	656	IN	A	192.203.230.10"),
+				mustRR("e.root-servers.net.	656	IN	AAAA	2001:500:a8::e"),
+				mustRR("j.root-servers.net.	656	IN	A	192.58.128.30"),
+				mustRR("j.root-servers.net.	656	IN	AAAA	2001:503:c27::2:30"),
+				mustRR("g.root-servers.net.	656	IN	A	192.112.36.4"),
+				mustRR("g.root-servers.net.	656	IN	AAAA	2001:500:12::d0d"),
+				mustRR("k.root-servers.net.	656	IN	A	193.0.14.129"),
+				mustRR("k.root-servers.net.	656	IN	AAAA	2001:7fd::1"),
+				mustRR("l.root-servers.net.	656	IN	A	199.7.83.42"),
+				mustRR("l.root-servers.net.	656	IN	AAAA	2001:500:9f::42"),
+				mustRR("d.root-servers.net.	656	IN	A	199.7.91.13"),
+				mustRR("d.root-servers.net.	656	IN	AAAA	2001:500:2d::d"),
+				mustRR("h.root-servers.net.	656	IN	A	198.97.190.53"),
+				mustRR("h.root-servers.net.	656	IN	AAAA	2001:500:1::53"),
+				mustRR("b.root-servers.net.	656	IN	A	170.247.170.2"),
+				mustRR("b.root-servers.net.	656	IN	AAAA	2801:1b8:10::b"),
+				mustRR("a.root-servers.net.	656	IN	A	198.41.0.4"),
+				mustRR("a.root-servers.net.	656	IN	AAAA	2001:503:ba3e::2:30"),
+				mustRR("f.root-servers.net.	656	IN	A	192.5.5.241"),
+				mustRR("f.root-servers.net.	656	IN	AAAA	2001:500:2f::f"),
+				mustRR("i.root-servers.net.	656	IN	A	192.36.148.17"),
+				mustRR("i.root-servers.net.	656	IN	AAAA	2001:7fe::53"),
+			},
+		}
+
+		m.Compress = true
+		m.SetReply(msg)
+		w.WriteMsg(m)
+	}
+}
+
 func generateEdns0ClientCookie() string {
 	cookie := make([]byte, 8)
 	if _, err := rand.Read(cookie); err != nil {

scripts/nrpt-diag.ps1

@@ -0,0 +1,132 @@
+#Requires -RunAsAdministrator
+<#
+.SYNOPSIS
+    NRPT diagnostic script for ctrld DNS intercept troubleshooting.
+.DESCRIPTION
+    Captures the full NRPT state: registry keys (both GP and direct paths),
+    effective policy, active rules, DNS Client service status, and resolver
+    config. Run as Administrator.
+.EXAMPLE
+    .\nrpt-diag.ps1
+    .\nrpt-diag.ps1 | Out-File nrpt-diag-output.txt
+#>
+
+$ErrorActionPreference = 'SilentlyContinue'
+
+Write-Host "=== NRPT Diagnostic Report ===" -ForegroundColor Cyan
+Write-Host "Date: $(Get-Date -Format 'yyyy-MM-dd HH:mm:ss')"
+Write-Host "Computer: $env:COMPUTERNAME"
+Write-Host "OS: $((Get-CimInstance Win32_OperatingSystem).Caption) $((Get-CimInstance Win32_OperatingSystem).BuildNumber)"
+Write-Host ""
+
+# --- 1. DNS Client Service ---
+Write-Host "=== 1. DNS Client (Dnscache) Service ===" -ForegroundColor Yellow
+$svc = Get-Service Dnscache
+Write-Host "Status: $($svc.Status)  StartType: $($svc.StartType)"
+Write-Host ""
+
+# --- 2. GP Path (Policy store) ---
+$gpPath = "HKLM:\SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig"
+Write-Host "=== 2. GP Path: $gpPath ===" -ForegroundColor Yellow
+$gpKey = Get-Item $gpPath 2>$null
+if ($gpKey) {
+    Write-Host "Key EXISTS"
+    $subkeys = Get-ChildItem $gpPath 2>$null
+    if ($subkeys) {
+        foreach ($sk in $subkeys) {
+            Write-Host ""
+            Write-Host "  Subkey: $($sk.PSChildName)" -ForegroundColor Green
+            foreach ($prop in $sk.Property) {
+                $val = $sk.GetValue($prop)
+                $kind = $sk.GetValueKind($prop)
+                Write-Host "    $prop ($kind) = $val"
+            }
+        }
+    } else {
+        Write-Host "  ** EMPTY (no subkeys) — this blocks NRPT activation! **" -ForegroundColor Red
+    }
+} else {
+    Write-Host "Key does NOT exist (clean state)"
+}
+Write-Host ""
+
+# --- 3. Direct Path (Service store) ---
+$directPath = "HKLM:\SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig"
+Write-Host "=== 3. Direct Path: $directPath ===" -ForegroundColor Yellow
+$directKey = Get-Item $directPath 2>$null
+if ($directKey) {
+    Write-Host "Key EXISTS"
+    $subkeys = Get-ChildItem $directPath 2>$null
+    if ($subkeys) {
+        foreach ($sk in $subkeys) {
+            Write-Host ""
+            Write-Host "  Subkey: $($sk.PSChildName)" -ForegroundColor Green
+            foreach ($prop in $sk.Property) {
+                $val = $sk.GetValue($prop)
+                $kind = $sk.GetValueKind($prop)
+                Write-Host "    $prop ($kind) = $val"
+            }
+        }
+    } else {
+        Write-Host "  ** EMPTY (no subkeys) **" -ForegroundColor Red
+    }
+} else {
+    Write-Host "Key does NOT exist"
+}
+Write-Host ""
+
+# --- 4. Effective NRPT Rules (what Windows sees) ---
+Write-Host "=== 4. Get-DnsClientNrptRule ===" -ForegroundColor Yellow
+$rules = Get-DnsClientNrptRule 2>$null
+if ($rules) {
+    $rules | Format-List Name, Version, Namespace, NameServers, NameEncoding, DnsSecEnabled
+} else {
+    Write-Host "(none)"
+}
+Write-Host ""
+
+# --- 5. Effective NRPT Policy (what DNS Client actually applies) ---
+Write-Host "=== 5. Get-DnsClientNrptPolicy ===" -ForegroundColor Yellow
+$policy = Get-DnsClientNrptPolicy 2>$null
+if ($policy) {
+    $policy | Format-List Namespace, NameServers, NameEncoding, QueryPolicy
+} else {
+    Write-Host "(none — DNS Client is NOT honoring any NRPT rules)" -ForegroundColor Red
+}
+Write-Host ""
+
+# --- 6. Interface DNS servers ---
+Write-Host "=== 6. Interface DNS Configuration ===" -ForegroundColor Yellow
+Get-DnsClientServerAddress -AddressFamily IPv4 | Where-Object { $_.ServerAddresses } |
+    Format-Table InterfaceAlias, InterfaceIndex, ServerAddresses -AutoSize
+Write-Host ""
+
+# --- 7. DNS resolution test ---
+Write-Host "=== 7. DNS Resolution Test ===" -ForegroundColor Yellow
+Write-Host "Resolve-DnsName example.com (uses DNS Client / NRPT):"
+try {
+    $result = Resolve-DnsName example.com -Type A -DnsOnly -ErrorAction Stop
+    $result | Format-Table Name, Type, IPAddress -AutoSize
+} catch {
+    Write-Host "  FAILED: $_" -ForegroundColor Red
+}
+Write-Host ""
+Write-Host "nslookup example.com 127.0.0.1 (direct to ctrld, bypasses NRPT):"
+$ns = nslookup example.com 127.0.0.1 2>&1
+$ns | ForEach-Object { Write-Host "  $_" }
+Write-Host ""
+
+# --- 8. Domain join status ---
+Write-Host "=== 8. Domain Status ===" -ForegroundColor Yellow
+$cs = Get-CimInstance Win32_ComputerSystem
+Write-Host "Domain: $($cs.Domain)  PartOfDomain: $($cs.PartOfDomain)"
+Write-Host ""
+
+# --- 9. Group Policy NRPT ---
+Write-Host "=== 9. GP Result (NRPT section) ===" -ForegroundColor Yellow
+Write-Host "(Running gpresult — may take a few seconds...)"
+$gp = gpresult /r 2>&1
+$gp | Select-String -Pattern "DNS|NRPT|Policy" | ForEach-Object { Write-Host "  $_" }
+Write-Host ""
+
+Write-Host "=== End of Diagnostic Report ===" -ForegroundColor Cyan

test-scripts/README.md

@@ -0,0 +1,47 @@
+# DNS Intercept Test Scripts
+
+Manual test scripts for verifying DNS intercept mode behavior. These require root/admin privileges and a running ctrld instance.
+
+## Structure
+
+```
+test-scripts/
+├── darwin/
+│   ├── test-recovery-bypass.sh     # Captive portal recovery simulation
+│   ├── test-dns-intercept.sh       # Basic pf intercept verification
+│   ├── test-pf-group-exemption.sh  # Group-based pf exemption test
+│   ├── validate-pf-rules.sh        # Dry-run pf rule validation
+│   ├── diag-lo0-capture.sh         # Capture DNS on lo0 for pf debugging
+│   ├── diag-pf-poll.sh             # Poll pf rules/states every 2s
+│   └── diag-vpn-connect.sh         # VPN connect/disconnect diagnostic
+└── windows/
+    ├── test-recovery-bypass.ps1    # Captive portal recovery simulation
+    └── test-dns-intercept.ps1      # Basic WFP intercept verification
+```
+
+## Prerequisites
+
+- ctrld running with `--intercept-mode dns` (or `--intercept-mode hard`)
+- Verbose logging: `-v 1 --log /tmp/dns.log` (macOS) or `--log C:\temp\dns.log` (Windows)
+- Root (macOS) or Administrator (Windows)
+- For recovery tests: disconnect VPNs (e.g., Tailscale) that provide alternative routes
+
+## Recovery Bypass Test
+
+Simulates a captive portal by blackholing ctrld's upstream DoH IPs and cycling wifi. Verifies that ctrld's recovery bypass activates, discovers DHCP nameservers, and forwards queries to them until the upstream recovers.
+
+### macOS
+```bash
+sudo bash test-scripts/darwin/test-recovery-bypass.sh en0
+```
+
+### Windows (PowerShell as Administrator)
+```powershell
+.\test-scripts\windows\test-recovery-bypass.ps1 -WifiAdapter "Wi-Fi"
+```
+
+## Safety
+
+All scripts clean up on exit (including Ctrl+C):
+- **macOS**: Removes route blackholes, re-enables wifi
+- **Windows**: Removes firewall rules, re-enables adapter

test-scripts/darwin/diag-lo0-capture.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+# diag-lo0-capture.sh — Capture DNS on lo0 to see where the pf chain breaks
+# Usage: sudo bash diag-lo0-capture.sh
+# Run while VPN + ctrld are both active, then dig from another terminal
+
+set -u
+PCAP="/tmp/lo0-dns-$(date +%s).pcap"
+echo "=== lo0 DNS Packet Capture ==="
+echo "Capturing to: $PCAP"
+echo ""
+
+# Show current rules (verify build)
+echo "--- ctrld anchor rdr rules ---"
+pfctl -a com.controld.ctrld -sn 2>/dev/null
+echo ""
+echo "--- ctrld anchor filter rules (lo0 only) ---"
+pfctl -a com.controld.ctrld -sr 2>/dev/null | grep lo0
+echo ""
+
+# Check pf state table for port 53 before
+echo "--- port 53 states BEFORE dig ---"
+pfctl -ss 2>/dev/null | grep ':53' | head -10
+echo "(total: $(pfctl -ss 2>/dev/null | grep -c ':53'))"
+echo ""
+
+# Start capture on lo0
+echo "Starting tcpdump on lo0 port 53..."
+echo ">>> In another terminal, run: dig example.com"
+echo ">>> Then press Ctrl-C here"
+echo ""
+tcpdump -i lo0 -n -v port 53 -w "$PCAP" 2>&1 &
+TCPDUMP_PID=$!
+
+# Also show live output
+tcpdump -i lo0 -n port 53 2>&1 &
+LIVE_PID=$!
+
+# Wait for Ctrl-C
+trap "kill $TCPDUMP_PID $LIVE_PID 2>/dev/null; echo ''; echo '--- port 53 states AFTER dig ---'; pfctl -ss 2>/dev/null | grep ':53' | head -20; echo '(total: '$(pfctl -ss 2>/dev/null | grep -c ':53')')'; echo ''; echo 'Capture saved to: $PCAP'; echo 'Read with: tcpdump -r $PCAP -n -v'; exit 0" INT
+wait

test-scripts/darwin/diag-pf-poll.sh

@@ -0,0 +1,62 @@
+#!/bin/bash
+# diag-pf-poll.sh — Polls pf rules, options, states, and DNS every 2s
+# Usage: sudo bash diag-pf-poll.sh | tee /tmp/pf-poll.log
+# Steps: 1) Run script  2) Connect VPN  3) Start ctrld  4) Ctrl-C when done
+
+set -u
+LOG="/tmp/pf-poll-$(date +%s).log"
+echo "=== PF Poll Diagnostic — logging to $LOG ==="
+echo "Press Ctrl-C to stop"
+echo ""
+
+poll() {
+    local ts=$(date '+%H:%M:%S.%3N')
+    echo "======== [$ts] POLL ========"
+
+    # 1. pf options — looking for "set skip on lo0"
+    echo "--- pf options ---"
+    pfctl -so 2>/dev/null | grep -i skip || echo "(no skip rules)"
+
+    # 2. Main ruleset anchors — where is ctrld relative to block drop all?
+    echo "--- main filter rules (summary) ---"
+    pfctl -sr 2>/dev/null | head -30
+
+    # 3. Main NAT/rdr rules
+    echo "--- main nat/rdr rules (summary) ---"
+    pfctl -sn 2>/dev/null | head -20
+
+    # 4. ctrld anchor content
+    echo "--- ctrld anchor (filter) ---"
+    pfctl -a com.apple.internet-sharing/ctrld -sr 2>/dev/null || echo "(no anchor)"
+    echo "--- ctrld anchor (nat/rdr) ---"
+    pfctl -a com.apple.internet-sharing/ctrld -sn 2>/dev/null || echo "(no anchor)"
+
+    # 5. State count for rdr target (10.255.255.3) and loopback
+    echo "--- states summary ---"
+    local total=$(pfctl -ss 2>/dev/null | wc -l | tr -d ' ')
+    local rdr=$(pfctl -ss 2>/dev/null | grep -c '10\.255\.255\.3' || true)
+    local lo0=$(pfctl -ss 2>/dev/null | grep -c 'lo0' || true)
+    echo "total=$total rdr_target=$rdr lo0=$lo0"
+
+    # 6. Quick DNS test (1s timeout)
+    echo "--- DNS tests ---"
+    local direct=$(dig +short +time=1 +tries=1 example.com @127.0.0.1 2>&1 | head -1)
+    local system=$(dig +short +time=1 +tries=1 example.com 2>&1 | head -1)
+    echo "direct @127.0.0.1: $direct"
+    echo "system DNS:        $system"
+
+    # 7. VPN tunnel interface
+    echo "--- tunnel interfaces ---"
+    ifconfig -l | tr ' ' '\n' | grep -E '^utun' | while read iface; do
+        echo -n "$iface: "
+        ifconfig "$iface" 2>/dev/null | grep 'inet ' | awk '{print $2}' || echo "no ip"
+    done
+
+    echo ""
+}
+
+# Main loop
+while true; do
+    poll 2>&1 | tee -a "$LOG"
+    sleep 2
+done

test-scripts/darwin/diag-vpn-connect.sh

@@ -0,0 +1,183 @@
+#!/bin/bash
+# diag-vpn-connect.sh — Diagnostic script for testing ctrld dns-intercept
+# during VPN VPN connection on macOS.
+#
+# Usage: sudo ./diag-vpn-connect.sh
+#
+# Run this BEFORE connecting VPN. It polls every 0.5s and captures:
+#   1. pf anchor state (are ctrld anchors present?)
+#   2. pf state table entries (rdr interception working?)
+#   3. ctrld log events (watchdog, rebootstrap, errors)
+#   4. scutil DNS resolver state
+#   5. Active tunnel interfaces
+#   6. dig test query results
+#
+# Output goes to /tmp/diag-vpn-<timestamp>/
+# Press Ctrl-C to stop. A summary is printed at the end.
+
+set -e
+
+if [ "$(id -u)" -ne 0 ]; then
+    echo "ERROR: Must run as root (sudo)"
+    exit 1
+fi
+
+CTRLD_LOG="${CTRLD_LOG:-/tmp/dns.log}"
+TIMESTAMP=$(date +%Y%m%d-%H%M%S)
+OUTDIR="/tmp/diag-vpn-${TIMESTAMP}"
+mkdir -p "$OUTDIR"
+
+echo "=== VPN + ctrld DNS Intercept Diagnostic ==="
+echo "Output: $OUTDIR"
+echo "ctrld log: $CTRLD_LOG"
+echo ""
+echo "1. Start this script"
+echo "2. Connect VPN"
+echo "3. Wait ~30 seconds"
+echo "4. Try: dig popads.net / dig @127.0.0.1 popads.net"
+echo "5. Ctrl-C to stop and see summary"
+echo ""
+echo "Polling every 0.5s... Press Ctrl-C to stop."
+echo ""
+
+# Track ctrld log position
+if [ -f "$CTRLD_LOG" ]; then
+    LOG_START_LINE=$(wc -l < "$CTRLD_LOG")
+else
+    LOG_START_LINE=0
+fi
+
+ITER=0
+DIG_FAIL=0
+DIG_OK=0
+ANCHOR_MISSING=0
+ANCHOR_PRESENT=0
+PF_WIPE_COUNT=0
+FORCE_REBOOT_COUNT=0
+LAST_TUNNEL_IFACES=""
+
+cleanup() {
+    echo ""
+    echo "=== Stopping diagnostic ==="
+
+    # Capture final state
+    echo "--- Final pf state ---" > "$OUTDIR/final-pfctl.txt"
+    pfctl -sa 2>/dev/null >> "$OUTDIR/final-pfctl.txt" 2>&1 || true
+
+    echo "--- Final scutil ---" > "$OUTDIR/final-scutil.txt"
+    scutil --dns >> "$OUTDIR/final-scutil.txt" 2>&1 || true
+
+    # Extract ctrld log events since start
+    if [ -f "$CTRLD_LOG" ]; then
+        tail -n +$((LOG_START_LINE + 1)) "$CTRLD_LOG" > "$OUTDIR/ctrld-events.log" 2>/dev/null || true
+
+        # Extract key events
+        echo "--- Watchdog events ---" > "$OUTDIR/summary-watchdog.txt"
+        grep -i "watchdog\|anchor.*missing\|anchor.*restored\|force-reset\|re-bootstrapping\|force re-bootstrapping" "$OUTDIR/ctrld-events.log" >> "$OUTDIR/summary-watchdog.txt" 2>/dev/null || true
+
+        echo "--- Errors ---" > "$OUTDIR/summary-errors.txt"
+        grep '"level":"error"' "$OUTDIR/ctrld-events.log" >> "$OUTDIR/summary-errors.txt" 2>/dev/null || true
+
+        echo "--- Network changes ---" > "$OUTDIR/summary-network.txt"
+        grep -i "Network change\|tunnel interface\|Ignoring interface" "$OUTDIR/ctrld-events.log" >> "$OUTDIR/summary-network.txt" 2>/dev/null || true
+
+        echo "--- Transport resets ---" > "$OUTDIR/summary-transport.txt"
+        grep -i "re-bootstrap\|force.*bootstrap\|dialing to\|connected to" "$OUTDIR/ctrld-events.log" >> "$OUTDIR/summary-transport.txt" 2>/dev/null || true
+
+        # Count key events
+        PF_WIPE_COUNT=$(grep -c "anchor.*missing\|restoring pf" "$OUTDIR/ctrld-events.log" 2>/dev/null || echo 0)
+        FORCE_REBOOT_COUNT=$(grep -c "force re-bootstrapping\|force-reset" "$OUTDIR/ctrld-events.log" 2>/dev/null || echo 0)
+        DEADLINE_COUNT=$(grep -c "context deadline exceeded" "$OUTDIR/ctrld-events.log" 2>/dev/null || echo 0)
+        FALLBACK_COUNT=$(grep -c "OS resolver retry query successful" "$OUTDIR/ctrld-events.log" 2>/dev/null || echo 0)
+    fi
+
+    echo ""
+    echo "========================================="
+    echo "         DIAGNOSTIC SUMMARY"
+    echo "========================================="
+    echo "Duration: $ITER iterations (~$((ITER / 2))s)"
+    echo ""
+    echo "pf Anchor Status:"
+    echo "  Present: $ANCHOR_PRESENT times"
+    echo "  Missing: $ANCHOR_MISSING times"
+    echo ""
+    echo "dig Tests (popads.net):"
+    echo "  Success: $DIG_OK"
+    echo "  Failed:  $DIG_FAIL"
+    echo ""
+    echo "ctrld Log Events:"
+    echo "  pf wipes detected:      $PF_WIPE_COUNT"
+    echo "  Force rebootstraps:     $FORCE_REBOOT_COUNT"
+    echo "  Context deadline errors: ${DEADLINE_COUNT:-0}"
+    echo "  OS resolver fallbacks:   ${FALLBACK_COUNT:-0}"
+    echo ""
+    echo "Last tunnel interfaces: ${LAST_TUNNEL_IFACES:-none}"
+    echo ""
+    echo "Files saved to: $OUTDIR/"
+    echo "  final-pfctl.txt        — full pfctl -sa at exit"
+    echo "  final-scutil.txt       — scutil --dns at exit"
+    echo "  ctrld-events.log       — ctrld log during test"
+    echo "  summary-watchdog.txt   — watchdog events"
+    echo "  summary-errors.txt     — errors"
+    echo "  summary-transport.txt  — transport reset events"
+    echo "  timeline.log           — per-iteration state"
+    echo "========================================="
+    exit 0
+}
+
+trap cleanup INT TERM
+
+while true; do
+    ITER=$((ITER + 1))
+    NOW=$(date '+%H:%M:%S.%3N' 2>/dev/null || date '+%H:%M:%S')
+
+    # 1. Check pf anchor presence
+    ANCHOR_STATUS="MISSING"
+    if pfctl -sr 2>/dev/null | grep -q "com.controld.ctrld"; then
+        ANCHOR_STATUS="PRESENT"
+        ANCHOR_PRESENT=$((ANCHOR_PRESENT + 1))
+    else
+        ANCHOR_MISSING=$((ANCHOR_MISSING + 1))
+    fi
+
+    # 2. Check tunnel interfaces
+    TUNNEL_IFACES=$(ifconfig -l 2>/dev/null | tr ' ' '\n' | grep -E '^(utun|ipsec|ppp|tap|tun)' | \
+        while read iface; do
+            # Only list interfaces that are UP and have an IP
+            if ifconfig "$iface" 2>/dev/null | grep -q "inet "; then
+                echo -n "$iface "
+            fi
+        done)
+    TUNNEL_IFACES=$(echo "$TUNNEL_IFACES" | xargs)  # trim
+    if [ -n "$TUNNEL_IFACES" ]; then
+        LAST_TUNNEL_IFACES="$TUNNEL_IFACES"
+    fi
+
+    # 3. Count rdr states (three-part = intercepted)
+    RDR_COUNT=$(pfctl -ss 2>/dev/null | grep -c "127.0.0.1:53 <-" || echo 0)
+
+    # 4. Quick dig test (0.5s timeout)
+    DIG_RESULT="SKIP"
+    if [ $((ITER % 4)) -eq 0 ]; then  # every 2 seconds
+        if dig +time=1 +tries=1 popads.net A @127.0.0.1 +short >/dev/null 2>&1; then
+            DIG_RESULT="OK"
+            DIG_OK=$((DIG_OK + 1))
+        else
+            DIG_RESULT="FAIL"
+            DIG_FAIL=$((DIG_FAIL + 1))
+        fi
+    fi
+
+    # 5. Check latest ctrld log for recent errors
+    RECENT_ERR=""
+    if [ -f "$CTRLD_LOG" ]; then
+        RECENT_ERR=$(tail -5 "$CTRLD_LOG" 2>/dev/null | grep -o '"message":"[^"]*deadline[^"]*"' | tail -1 || true)
+    fi
+
+    # Output timeline
+    LINE="[$NOW] anchor=$ANCHOR_STATUS rdr_states=$RDR_COUNT tunnels=[$TUNNEL_IFACES] dig=$DIG_RESULT $RECENT_ERR"
+    echo "$LINE"
+    echo "$LINE" >> "$OUTDIR/timeline.log"
+
+    sleep 0.5
+done

test-scripts/darwin/test-dns-intercept.sh

@@ -0,0 +1,556 @@
+#!/bin/bash
+# =============================================================================
+# DNS Intercept Mode Test Script — macOS (pf)
+# =============================================================================
+# Run as root: sudo bash test-dns-intercept-mac.sh
+#
+# Tests the dns-intercept feature end-to-end with validation at each step.
+# Logs are read from /tmp/dns.log (ctrld log location on test machine).
+#
+# Manual steps marked with [MANUAL] require human interaction.
+# =============================================================================
+
+set -euo pipefail
+
+CTRLD_LOG="/tmp/dns.log"
+PF_ANCHOR="com.controld.ctrld"
+PASS=0
+FAIL=0
+WARN=0
+RESULTS=()
+
+# Colors
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+CYAN='\033[0;36m'
+BOLD='\033[1m'
+NC='\033[0m'
+
+header() { echo -e "\n${CYAN}${BOLD}━━━ $1 ━━━${NC}"; }
+info()   { echo -e "  ${BOLD}ℹ${NC}  $1"; }
+pass()   { echo -e "  ${GREEN}✅ PASS${NC}: $1"; PASS=$((PASS+1)); RESULTS+=("PASS: $1"); }
+fail()   { echo -e "  ${RED}❌ FAIL${NC}: $1"; FAIL=$((FAIL+1)); RESULTS+=("FAIL: $1"); }
+warn()   { echo -e "  ${YELLOW}⚠️  WARN${NC}: $1"; WARN=$((WARN+1)); RESULTS+=("WARN: $1"); }
+manual() { echo -e "  ${YELLOW}[MANUAL]${NC} $1"; }
+separator() { echo -e "${CYAN}─────────────────────────────────────────────────────${NC}"; }
+
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        echo -e "${RED}This script must be run as root (sudo).${NC}"
+        exit 1
+    fi
+}
+
+wait_for_key() {
+    echo -e "\n  Press ${BOLD}Enter${NC} to continue..."
+    read -r
+}
+
+# Grep recent log entries (last N lines)
+log_grep() {
+    local pattern="$1"
+    local lines="${2:-200}"
+    tail -n "$lines" "$CTRLD_LOG" 2>/dev/null | grep -i "$pattern" 2>/dev/null || true
+}
+
+log_grep_count() {
+    local pattern="$1"
+    local lines="${2:-200}"
+    tail -n "$lines" "$CTRLD_LOG" 2>/dev/null | grep -ci "$pattern" 2>/dev/null || echo "0"
+}
+
+# =============================================================================
+# TEST SECTIONS
+# =============================================================================
+
+test_prereqs() {
+    header "0. Prerequisites"
+
+    if command -v pfctl &>/dev/null; then
+        pass "pfctl available"
+    else
+        fail "pfctl not found"
+        exit 1
+    fi
+
+    if [[ -f "$CTRLD_LOG" ]]; then
+        pass "ctrld log exists at $CTRLD_LOG"
+    else
+        warn "ctrld log not found at $CTRLD_LOG — log checks will be skipped"
+    fi
+
+    if command -v dig &>/dev/null; then
+        pass "dig available"
+    else
+        fail "dig not found — install bind tools"
+        exit 1
+    fi
+
+    info "Default route interface: $(route -n get default 2>/dev/null | grep interface | awk '{print $2}' || echo 'unknown')"
+    info "Current DNS servers:"
+    scutil --dns | grep "nameserver\[" | head -5 | sed 's/^/    /'
+}
+
+test_pf_state() {
+    header "1. PF State Validation"
+
+    # Is pf enabled?
+    local pf_status
+    pf_status=$(pfctl -si 2>&1 | grep "Status:" || true)
+    if echo "$pf_status" | grep -q "Enabled"; then
+        pass "pf is enabled"
+    else
+        fail "pf is NOT enabled (status: $pf_status)"
+    fi
+
+    # Is our anchor referenced in the running ruleset?
+    local sr_match sn_match
+    sr_match=$(pfctl -sr 2>&1 | grep "$PF_ANCHOR" || true)
+    sn_match=$(pfctl -sn 2>&1 | grep "$PF_ANCHOR" || true)
+
+    if [[ -n "$sr_match" ]]; then
+        pass "anchor '$PF_ANCHOR' found in filter rules (pfctl -sr)"
+        info "  $sr_match"
+    else
+        fail "anchor '$PF_ANCHOR' NOT in filter rules — main ruleset doesn't reference it"
+    fi
+
+    if [[ -n "$sn_match" ]]; then
+        pass "rdr-anchor '$PF_ANCHOR' found in NAT rules (pfctl -sn)"
+        info "  $sn_match"
+    else
+        fail "rdr-anchor '$PF_ANCHOR' NOT in NAT rules — redirect won't work"
+    fi
+
+    # Check anchor rules
+    separator
+    info "Anchor filter rules (pfctl -a '$PF_ANCHOR' -sr):"
+    local anchor_sr
+    anchor_sr=$(pfctl -a "$PF_ANCHOR" -sr 2>&1 | grep -v "ALTQ" || true)
+    if [[ -n "$anchor_sr" ]]; then
+        echo "$anchor_sr" | sed 's/^/    /'
+        # Check for route-to rules
+        if echo "$anchor_sr" | grep -q "route-to"; then
+            pass "route-to lo0 rules present (needed for local traffic interception)"
+        else
+            warn "No route-to rules found — local DNS may not be intercepted"
+        fi
+    else
+        fail "No filter rules in anchor"
+    fi
+
+    info "Anchor redirect rules (pfctl -a '$PF_ANCHOR' -sn):"
+    local anchor_sn
+    anchor_sn=$(pfctl -a "$PF_ANCHOR" -sn 2>&1 | grep -v "ALTQ" || true)
+    if [[ -n "$anchor_sn" ]]; then
+        echo "$anchor_sn" | sed 's/^/    /'
+        if echo "$anchor_sn" | grep -q "rdr.*lo0.*port = 53"; then
+            pass "rdr rules on lo0 present (redirect DNS to ctrld)"
+        else
+            warn "rdr rules don't match expected pattern"
+        fi
+    else
+        fail "No redirect rules in anchor"
+    fi
+
+    # Check anchor file exists
+    if [[ -f "/etc/pf.anchors/$PF_ANCHOR" ]]; then
+        pass "Anchor file exists: /etc/pf.anchors/$PF_ANCHOR"
+    else
+        fail "Anchor file missing: /etc/pf.anchors/$PF_ANCHOR"
+    fi
+
+    # Check pf.conf was NOT modified
+    if grep -q "$PF_ANCHOR" /etc/pf.conf 2>/dev/null; then
+        warn "pf.conf contains '$PF_ANCHOR' reference — should NOT be modified on disk"
+    else
+        pass "pf.conf NOT modified on disk (anchor injected at runtime only)"
+    fi
+}
+
+test_dns_interception() {
+    header "2. DNS Interception Tests"
+
+    # Mark position in log
+    local log_lines_before=0
+    if [[ -f "$CTRLD_LOG" ]]; then
+        log_lines_before=$(wc -l < "$CTRLD_LOG")
+    fi
+
+    # Test 1: Query to external resolver should be intercepted
+    info "Test: dig @8.8.8.8 example.com (should be intercepted by ctrld)"
+    local dig_result
+    dig_result=$(dig @8.8.8.8 example.com +short +timeout=5 2>&1 || true)
+
+    if [[ -n "$dig_result" ]] && ! echo "$dig_result" | grep -q "timed out"; then
+        pass "dig @8.8.8.8 returned result: $dig_result"
+    else
+        fail "dig @8.8.8.8 failed or timed out"
+    fi
+
+    # Check if ctrld logged the query
+    sleep 1
+    if [[ -f "$CTRLD_LOG" ]]; then
+        local intercepted
+        intercepted=$(tail -n +$((log_lines_before+1)) "$CTRLD_LOG" | grep -c "example.com" || echo "0")
+        if [[ "$intercepted" -gt 0 ]]; then
+            pass "ctrld logged the intercepted query for example.com"
+        else
+            fail "ctrld did NOT log query for example.com — interception may not be working"
+        fi
+    fi
+
+    # Check dig reports ctrld answered (not 8.8.8.8)
+    local full_dig
+    full_dig=$(dig @8.8.8.8 example.com +timeout=5 2>&1 || true)
+    local server_line
+    server_line=$(echo "$full_dig" | grep "SERVER:" || true)
+    info "dig SERVER line: $server_line"
+    if echo "$server_line" | grep -q "127.0.0.1"; then
+        pass "Response came from 127.0.0.1 (ctrld intercepted)"
+    elif echo "$server_line" | grep -q "8.8.8.8"; then
+        fail "Response came from 8.8.8.8 directly — NOT intercepted"
+    else
+        warn "Could not determine response server from dig output"
+    fi
+
+    separator
+
+    # Test 2: Query to another external resolver
+    info "Test: dig @1.1.1.1 cloudflare.com (should also be intercepted)"
+    local dig2
+    dig2=$(dig @1.1.1.1 cloudflare.com +short +timeout=5 2>&1 || true)
+    if [[ -n "$dig2" ]] && ! echo "$dig2" | grep -q "timed out"; then
+        pass "dig @1.1.1.1 returned result"
+    else
+        fail "dig @1.1.1.1 failed or timed out"
+    fi
+
+    separator
+
+    # Test 3: Query to localhost should work (not double-redirected)
+    info "Test: dig @127.0.0.1 example.org (direct to ctrld, should NOT be redirected)"
+    local dig3
+    dig3=$(dig @127.0.0.1 example.org +short +timeout=5 2>&1 || true)
+    if [[ -n "$dig3" ]] && ! echo "$dig3" | grep -q "timed out"; then
+        pass "dig @127.0.0.1 works (no loop)"
+    else
+        fail "dig @127.0.0.1 failed — possible redirect loop"
+    fi
+
+    separator
+
+    # Test 4: System DNS resolution
+    info "Test: host example.net (system resolver, should go through ctrld)"
+    local host_result
+    host_result=$(host example.net 2>&1 || true)
+    if echo "$host_result" | grep -q "has address"; then
+        pass "System DNS resolution works via host command"
+    else
+        fail "System DNS resolution failed"
+    fi
+
+    separator
+
+    # Test 5: TCP DNS query
+    info "Test: dig @9.9.9.9 example.com +tcp (TCP DNS should also be intercepted)"
+    local dig_tcp
+    dig_tcp=$(dig @9.9.9.9 example.com +tcp +short +timeout=5 2>&1 || true)
+    if [[ -n "$dig_tcp" ]] && ! echo "$dig_tcp" | grep -q "timed out"; then
+        pass "TCP DNS query intercepted and resolved"
+    else
+        warn "TCP DNS query failed (may not be critical if UDP works)"
+    fi
+}
+
+test_non_dns_unaffected() {
+    header "3. Non-DNS Traffic Unaffected"
+
+    # HTTPS should work fine
+    info "Test: curl https://example.com (HTTPS port 443 should NOT be affected)"
+    local curl_result
+    curl_result=$(curl -s -o /dev/null -w "%{http_code}" --max-time 10 https://example.com 2>&1 || echo "000")
+    if [[ "$curl_result" == "200" ]] || [[ "$curl_result" == "301" ]] || [[ "$curl_result" == "302" ]]; then
+        pass "HTTPS works (HTTP $curl_result)"
+    else
+        fail "HTTPS failed (HTTP $curl_result) — pf may be affecting non-DNS traffic"
+    fi
+
+    # SSH-style connection test (port 22 should be unaffected)
+    info "Test: nc -z -w5 github.com 22 (SSH port should NOT be affected)"
+    if nc -z -w5 github.com 22 2>/dev/null; then
+        pass "SSH port reachable (non-DNS traffic unaffected)"
+    else
+        warn "SSH port unreachable (may be firewall, not necessarily our fault)"
+    fi
+}
+
+test_ctrld_log_health() {
+    header "4. ctrld Log Health Check"
+
+    if [[ ! -f "$CTRLD_LOG" ]]; then
+        warn "Skipping log checks — $CTRLD_LOG not found"
+        return
+    fi
+
+    # Check for intercept initialization
+    if log_grep "DNS intercept.*initializing" 500 | grep -q "."; then
+        pass "DNS intercept initialization logged"
+    else
+        fail "No DNS intercept initialization in recent logs"
+    fi
+
+    # Check for successful anchor load
+    if log_grep "pf anchor.*active" 500 | grep -q "."; then
+        pass "PF anchor reported as active"
+    else
+        fail "PF anchor not reported as active"
+    fi
+
+    # Check for anchor reference injection
+    if log_grep "anchor reference active" 500 | grep -q "."; then
+        pass "Anchor reference injected into running ruleset"
+    else
+        fail "Anchor reference NOT injected — this is the critical step"
+    fi
+
+    # Check for errors
+    separator
+    info "Recent errors/warnings in ctrld log:"
+    local errors
+    errors=$(log_grep '"level":"error"' 500)
+    if [[ -n "$errors" ]]; then
+        echo "$errors" | tail -5 | sed 's/^/    /'
+        warn "Errors found in recent logs (see above)"
+    else
+        pass "No errors in recent logs"
+    fi
+
+    local warnings
+    warnings=$(log_grep '"level":"warn"' 500 | grep -v "skipping self-upgrade" || true)
+    if [[ -n "$warnings" ]]; then
+        echo "$warnings" | tail -5 | sed 's/^/    /'
+        info "(warnings above may be expected)"
+    fi
+
+    # Check for recovery bypass state
+    if log_grep "recoveryBypass\|recovery bypass\|prepareForRecovery" 500 | grep -q "."; then
+        info "Recovery bypass activity detected in logs"
+        log_grep "recovery" 500 | tail -3 | sed 's/^/    /'
+    fi
+
+    # Check for VPN DNS detection
+    if log_grep "VPN DNS" 500 | grep -q "."; then
+        info "VPN DNS activity in logs:"
+        log_grep "VPN DNS" 500 | tail -5 | sed 's/^/    /'
+    else
+        info "No VPN DNS activity (expected if no VPN is connected)"
+    fi
+}
+
+test_pf_counters() {
+    header "5. PF Statistics & Counters"
+
+    info "PF info (pfctl -si):"
+    pfctl -si 2>&1 | grep -v "ALTQ" | head -15 | sed 's/^/    /'
+
+    info "PF state table entries:"
+    pfctl -ss 2>&1 | grep -c "." | sed 's/^/    States: /'
+
+    # Count evaluations of our anchor
+    info "Anchor-specific stats (if available):"
+    local anchor_info
+    anchor_info=$(pfctl -a "$PF_ANCHOR" -si 2>&1 | grep -v "ALTQ" || true)
+    if [[ -n "$anchor_info" ]]; then
+        echo "$anchor_info" | head -10 | sed 's/^/    /'
+    else
+        info "  (no per-anchor stats available)"
+    fi
+}
+
+test_cleanup_on_stop() {
+    header "6. Cleanup Validation (After ctrld Stop)"
+
+    manual "Stop ctrld now (Ctrl+C or 'ctrld stop'), then press Enter"
+    wait_for_key
+
+    # Check anchor is flushed
+    local anchor_rules_after
+    anchor_rules_after=$(pfctl -a "$PF_ANCHOR" -sr 2>&1 | grep -v "ALTQ" | grep -v "^$" || true)
+    if [[ -z "$anchor_rules_after" ]]; then
+        pass "Anchor filter rules flushed after stop"
+    else
+        fail "Anchor filter rules still present after stop"
+        echo "$anchor_rules_after" | sed 's/^/    /'
+    fi
+
+    local anchor_rdr_after
+    anchor_rdr_after=$(pfctl -a "$PF_ANCHOR" -sn 2>&1 | grep -v "ALTQ" | grep -v "^$" || true)
+    if [[ -z "$anchor_rdr_after" ]]; then
+        pass "Anchor redirect rules flushed after stop"
+    else
+        fail "Anchor redirect rules still present after stop"
+    fi
+
+    # Check anchor file removed
+    if [[ ! -f "/etc/pf.anchors/$PF_ANCHOR" ]]; then
+        pass "Anchor file removed after stop"
+    else
+        fail "Anchor file still exists: /etc/pf.anchors/$PF_ANCHOR"
+    fi
+
+    # Check pf.conf is clean
+    if ! grep -q "$PF_ANCHOR" /etc/pf.conf 2>/dev/null; then
+        pass "pf.conf is clean (no ctrld references)"
+    else
+        fail "pf.conf still has ctrld references after stop"
+    fi
+
+    # DNS should work normally without ctrld
+    info "Test: dig example.com (should resolve via system DNS)"
+    local dig_after
+    dig_after=$(dig example.com +short +timeout=5 2>&1 || true)
+    if [[ -n "$dig_after" ]] && ! echo "$dig_after" | grep -q "timed out"; then
+        pass "DNS works after ctrld stop"
+    else
+        fail "DNS broken after ctrld stop — cleanup may have failed"
+    fi
+}
+
+test_restart_resilience() {
+    header "7. Restart Resilience"
+
+    manual "Start ctrld again with --dns-intercept, then press Enter"
+    wait_for_key
+
+    sleep 3
+
+    # Re-run pf state checks
+    local sr_match sn_match
+    sr_match=$(pfctl -sr 2>&1 | grep "$PF_ANCHOR" || true)
+    sn_match=$(pfctl -sn 2>&1 | grep "$PF_ANCHOR" || true)
+
+    if [[ -n "$sr_match" ]] && [[ -n "$sn_match" ]]; then
+        pass "Anchor references restored after restart"
+    else
+        fail "Anchor references NOT restored after restart"
+    fi
+
+    # Quick interception test
+    local dig_after_restart
+    dig_after_restart=$(dig @8.8.8.8 example.com +short +timeout=5 2>&1 || true)
+    if [[ -n "$dig_after_restart" ]] && ! echo "$dig_after_restart" | grep -q "timed out"; then
+        pass "DNS interception works after restart"
+    else
+        fail "DNS interception broken after restart"
+    fi
+}
+
+test_network_change() {
+    header "8. Network Change Recovery"
+
+    info "This test verifies recovery after network changes."
+    manual "Switch Wi-Fi networks (or disconnect/reconnect Ethernet), then press Enter"
+    wait_for_key
+
+    sleep 5
+
+    # Check pf rules still active
+    local sr_after sn_after
+    sr_after=$(pfctl -sr 2>&1 | grep "$PF_ANCHOR" || true)
+    sn_after=$(pfctl -sn 2>&1 | grep "$PF_ANCHOR" || true)
+
+    if [[ -n "$sr_after" ]] && [[ -n "$sn_after" ]]; then
+        pass "Anchor references survived network change"
+    else
+        fail "Anchor references lost after network change"
+    fi
+
+    # Check interception still works
+    local dig_after_net
+    dig_after_net=$(dig @8.8.8.8 example.com +short +timeout=10 2>&1 || true)
+    if [[ -n "$dig_after_net" ]] && ! echo "$dig_after_net" | grep -q "timed out"; then
+        pass "DNS interception works after network change"
+    else
+        fail "DNS interception broken after network change"
+    fi
+
+    # Check logs for recovery bypass activity
+    if [[ -f "$CTRLD_LOG" ]]; then
+        local recovery_logs
+        recovery_logs=$(log_grep "recovery\|network change\|network monitor" 100)
+        if [[ -n "$recovery_logs" ]]; then
+            info "Recovery/network change log entries:"
+            echo "$recovery_logs" | tail -5 | sed 's/^/    /'
+        fi
+    fi
+}
+
+# =============================================================================
+# SUMMARY
+# =============================================================================
+
+print_summary() {
+    header "TEST SUMMARY"
+    echo ""
+    for r in "${RESULTS[@]}"; do
+        if [[ "$r" == PASS* ]]; then
+            echo -e "  ${GREEN}✅${NC} ${r#PASS: }"
+        elif [[ "$r" == FAIL* ]]; then
+            echo -e "  ${RED}❌${NC} ${r#FAIL: }"
+        elif [[ "$r" == WARN* ]]; then
+            echo -e "  ${YELLOW}⚠️${NC}  ${r#WARN: }"
+        fi
+    done
+    echo ""
+    separator
+    echo -e "  ${GREEN}Passed: $PASS${NC}  |  ${RED}Failed: $FAIL${NC}  |  ${YELLOW}Warnings: $WARN${NC}"
+    separator
+
+    if [[ $FAIL -gt 0 ]]; then
+        echo -e "\n  ${RED}${BOLD}Some tests failed.${NC} Check output above for details."
+        echo -e "  Useful debug commands:"
+        echo -e "    pfctl -a '$PF_ANCHOR' -sr      # anchor filter rules"
+        echo -e "    pfctl -a '$PF_ANCHOR' -sn      # anchor redirect rules"
+        echo -e "    pfctl -sr | grep controld       # main ruleset references"
+        echo -e "    tail -100 $CTRLD_LOG            # recent ctrld logs"
+    else
+        echo -e "\n  ${GREEN}${BOLD}All tests passed!${NC}"
+    fi
+}
+
+# =============================================================================
+# MAIN
+# =============================================================================
+
+echo -e "${BOLD}╔═══════════════════════════════════════════════════════╗${NC}"
+echo -e "${BOLD}║  ctrld DNS Intercept Mode — macOS Test Suite         ║${NC}"
+echo -e "${BOLD}║  Tests pf-based DNS interception (route-to + rdr)    ║${NC}"
+echo -e "${BOLD}╚═══════════════════════════════════════════════════════╝${NC}"
+
+check_root
+
+echo ""
+echo "Make sure ctrld is running with --dns-intercept before starting."
+echo "Log location: $CTRLD_LOG"
+wait_for_key
+
+test_prereqs
+test_pf_state
+test_dns_interception
+test_non_dns_unaffected
+test_ctrld_log_health
+test_pf_counters
+
+separator
+echo ""
+echo "The next tests require manual steps (stop/start ctrld, network changes)."
+echo "Press Enter to continue, or Ctrl+C to skip and see results so far."
+wait_for_key
+
+test_cleanup_on_stop
+test_restart_resilience
+test_network_change
+
+print_summary

test-scripts/darwin/test-pf-group-exemption.sh

@@ -0,0 +1,147 @@
+#!/bin/bash
+# Test: pf group-based exemption for DNS intercept
+# Run as root: sudo bash test-pf-group-exemption.sh
+
+set -e
+
+GROUP_NAME="_ctrld"
+ANCHOR="com.controld.test"
+TEST_DNS="1.1.1.1"
+
+echo "=== Step 1: Create test group ==="
+if dscl . -read /Groups/$GROUP_NAME PrimaryGroupID &>/dev/null; then
+    echo "Group $GROUP_NAME already exists"
+else
+    # Find an unused GID in 350-450 range
+    USED_GIDS=$(dscl . -list /Groups PrimaryGroupID 2>/dev/null | awk '{print $2}' | sort -n)
+    GROUP_ID=""
+    for gid in $(seq 350 450); do
+        if ! echo "$USED_GIDS" | grep -q "^${gid}$"; then
+            GROUP_ID=$gid
+            break
+        fi
+    done
+    if [ -z "$GROUP_ID" ]; then
+        echo "ERROR: Could not find unused GID in 350-450 range"
+        exit 1
+    fi
+    dscl . -create /Groups/$GROUP_NAME
+    dscl . -create /Groups/$GROUP_NAME PrimaryGroupID $GROUP_ID
+    dscl . -create /Groups/$GROUP_NAME RealName "Control D DNS Intercept"
+    echo "Created group $GROUP_NAME (GID $GROUP_ID)"
+fi
+
+ACTUAL_GID=$(dscl . -read /Groups/$GROUP_NAME PrimaryGroupID | awk '{print $2}')
+echo "GID: $ACTUAL_GID"
+
+echo ""
+echo "=== Step 2: Enable pf ==="
+pfctl -e 2>&1 || true
+
+echo ""
+echo "=== Step 3: Set up pf anchor with group exemption ==="
+
+cat > /tmp/pf-group-test-anchor.conf << RULES
+# Translation: redirect DNS on loopback to our listener
+rdr pass on lo0 inet proto udp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+rdr pass on lo0 inet proto tcp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+
+# Exemption: only group _ctrld can talk to $TEST_DNS directly
+pass out quick on ! lo0 inet proto { udp, tcp } from any to $TEST_DNS port 53 group $GROUP_NAME
+
+# Intercept everything else
+pass out quick on ! lo0 route-to lo0 inet proto udp from any to ! 127.0.0.1 port 53
+pass out quick on ! lo0 route-to lo0 inet proto tcp from any to ! 127.0.0.1 port 53
+pass in quick on lo0 inet proto { udp, tcp } from any to 127.0.0.1 port 53
+RULES
+
+pfctl -a $ANCHOR -f /tmp/pf-group-test-anchor.conf 2>/dev/null
+echo "Loaded anchor $ANCHOR"
+
+# Inject anchor refs into running ruleset
+NAT_RULES=$(pfctl -sn 2>/dev/null | grep -v "ALTQ" | grep -v "^$")
+FILTER_RULES=$(pfctl -sr 2>/dev/null | grep -v "ALTQ" | grep -v "^$")
+SCRUB_RULES=$(echo "$FILTER_RULES" | grep "^scrub" || true)
+PURE_FILTER=$(echo "$FILTER_RULES" | grep -v "^scrub" | grep -v "com.controld.test" || true)
+CLEAN_NAT=$(echo "$NAT_RULES" | grep -v "com.controld.test" || true)
+
+{
+    [ -n "$SCRUB_RULES" ] && echo "$SCRUB_RULES"
+    [ -n "$CLEAN_NAT" ] && echo "$CLEAN_NAT"
+    echo "rdr-anchor \"$ANCHOR\""
+    echo "anchor \"$ANCHOR\""
+    [ -n "$PURE_FILTER" ] && echo "$PURE_FILTER"
+} | pfctl -f - 2>/dev/null
+
+echo "Injected anchor references (no duplicates)"
+
+echo ""
+echo "=== Step 4: Verify rules ==="
+echo "NAT rules:"
+pfctl -sn 2>/dev/null | grep -v ALTQ
+echo ""
+echo "Anchor filter rules:"
+pfctl -a $ANCHOR -sr 2>/dev/null | grep -v ALTQ
+echo ""
+echo "Anchor NAT rules:"
+pfctl -a $ANCHOR -sn 2>/dev/null | grep -v ALTQ
+
+echo ""
+echo "=== Step 5: Build setgid test binary ==="
+# We need a binary that runs with effective group _ctrld.
+# sudo -g doesn't work on macOS, so we use a setgid binary.
+cat > /tmp/test-dns-group.c << 'EOF'
+#include <unistd.h>
+int main() {
+    char *args[] = {"dig", "+short", "+timeout=3", "+tries=1", "@1.1.1.1", "popads.net", NULL};
+    execvp("dig", args);
+    return 1;
+}
+EOF
+cc -o /tmp/test-dns-group /tmp/test-dns-group.c
+chgrp $GROUP_NAME /tmp/test-dns-group
+chmod g+s /tmp/test-dns-group
+echo "Built setgid binary /tmp/test-dns-group (group: $GROUP_NAME)"
+
+echo ""
+echo "=== Step 6: Test as regular user (should be INTERCEPTED) ==="
+echo "Running: dig @$TEST_DNS popads.net (as root / group wheel — no group exemption)"
+echo "If nothing listens on 127.0.0.1:53, this should timeout."
+DIG_RESULT=$(dig +short +timeout=3 +tries=1 @$TEST_DNS popads.net 2>&1 || true)
+echo "Result: ${DIG_RESULT:-TIMEOUT/INTERCEPTED}"
+
+echo ""
+echo "=== Step 7: Test as group _ctrld (should BYPASS) ==="
+echo "Running: setgid binary (effective group: $GROUP_NAME)"
+BYPASS_RESULT=$(/tmp/test-dns-group 2>&1 || true)
+echo "Result: ${BYPASS_RESULT:-TIMEOUT/BLOCKED}"
+
+echo ""
+echo "=== Results ==="
+PASS=true
+if [[ -z "$DIG_RESULT" || "$DIG_RESULT" == *"timed out"* || "$DIG_RESULT" == *"connection refused"* ]]; then
+    echo "✅ Regular query INTERCEPTED (redirected away from $TEST_DNS)"
+else
+    echo "❌ Regular query NOT intercepted — got: $DIG_RESULT"
+    PASS=false
+fi
+
+if [[ -n "$BYPASS_RESULT" && "$BYPASS_RESULT" != *"timed out"* && "$BYPASS_RESULT" != *"connection refused"* && "$BYPASS_RESULT" != *"TIMEOUT"* ]]; then
+    echo "✅ Group _ctrld query BYPASSED — got: $BYPASS_RESULT"
+else
+    echo "❌ Group _ctrld query was also intercepted — got: ${BYPASS_RESULT:-TIMEOUT}"
+    PASS=false
+fi
+
+if $PASS; then
+    echo ""
+    echo "🎉 GROUP EXEMPTION WORKS — this approach is viable for dns-intercept mode"
+fi
+
+echo ""
+echo "=== Cleanup ==="
+pfctl -a $ANCHOR -F all 2>/dev/null
+pfctl -f /etc/pf.conf 2>/dev/null
+rm -f /tmp/pf-group-test-anchor.conf /tmp/test-dns-group /tmp/test-dns-group.c
+echo "Cleaned up. Group $GROUP_NAME left in place."
+echo "To remove: sudo dscl . -delete /Groups/$GROUP_NAME"

test-scripts/darwin/test-recovery-bypass.sh

@@ -0,0 +1,301 @@
+#!/bin/bash
+# test-recovery-bypass.sh — Test DNS intercept recovery bypass (captive portal simulation)
+#
+# Simulates a captive portal by:
+#   1. Discovering ctrld's upstream IPs from active connections
+#   2. Blackholing ALL of them via route table
+#   3. Cycling wifi to trigger network change → recovery flow
+#   4. Verifying recovery bypass forwards to OS/DHCP resolver
+#   5. Unblocking and verifying normal operation resumes
+#
+# SAFE: Uses route add/delete + networksetup — cleaned up on exit (including Ctrl+C).
+#
+# Usage: sudo bash test-recovery-bypass.sh [wifi_interface]
+#   wifi_interface defaults to en0
+#
+# Prerequisites:
+#   - ctrld running with --dns-intercept and -v 1 --log /tmp/dns.log
+#   - Run as root (sudo)
+
+set -euo pipefail
+
+WIFI_IFACE="${1:-en0}"
+CTRLD_LOG="/tmp/dns.log"
+BLOCKED_IPS=()
+
+RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; CYAN='\033[0;36m'; NC='\033[0m'
+log()  { echo -e "${CYAN}[$(date +%H:%M:%S)]${NC} $*"; }
+pass() { echo -e "${GREEN}[PASS]${NC} $*"; }
+fail() { echo -e "${RED}[FAIL]${NC} $*"; }
+warn() { echo -e "${YELLOW}[WARN]${NC} $*"; }
+
+# ── Safety: always clean up on exit ──────────────────────────────────────────
+cleanup() {
+    echo ""
+    log "═══ CLEANUP ═══"
+
+    # Ensure wifi is on
+    log "Ensuring wifi is on..."
+    networksetup -setairportpower "$WIFI_IFACE" on 2>/dev/null || true
+
+    # Remove all blackhole routes
+    for ip in "${BLOCKED_IPS[@]}"; do
+        route delete -host "$ip" 2>/dev/null && log "Removed route for $ip" || true
+    done
+
+    log "Cleanup complete. Internet should be restored."
+    log "(If not, run: sudo networksetup -setairportpower $WIFI_IFACE on)"
+}
+trap cleanup EXIT INT TERM
+
+# ── Pre-checks ───────────────────────────────────────────────────────────────
+if [[ $EUID -ne 0 ]]; then
+    echo "Run as root: sudo bash $0 $*"
+    exit 1
+fi
+
+if [[ ! -f "$CTRLD_LOG" ]]; then
+    fail "ctrld log not found at $CTRLD_LOG"
+    echo "Start ctrld with: ctrld run --dns-intercept --cd <uid> -v 1 --log $CTRLD_LOG"
+    exit 1
+fi
+
+# Check wifi interface exists
+if ! networksetup -getairportpower "$WIFI_IFACE" >/dev/null 2>&1; then
+    fail "Wifi interface $WIFI_IFACE not found"
+    echo "Try: networksetup -listallhardwareports"
+    exit 1
+fi
+
+log "═══════════════════════════════════════════════════════════"
+log "  Recovery Bypass Test (Captive Portal Simulation)"
+log "═══════════════════════════════════════════════════════════"
+log "Wifi interface: $WIFI_IFACE"
+log "ctrld log:      $CTRLD_LOG"
+echo ""
+
+# ── Phase 1: Discover upstream IPs ──────────────────────────────────────────
+log "Phase 1: Discovering ctrld upstream IPs from active connections"
+
+# Find ctrld's established connections (DoH uses port 443)
+CTRLD_CONNS=$(lsof -i -n -P 2>/dev/null | grep -i ctrld | grep ESTABLISHED || true)
+if [[ -z "$CTRLD_CONNS" ]]; then
+    warn "No established ctrld connections found via lsof"
+    warn "Trying: ss/netstat fallback..."
+    CTRLD_CONNS=$(netstat -an 2>/dev/null | grep "\.443 " | grep ESTABLISHED || true)
+fi
+
+echo "$CTRLD_CONNS" | head -10 | while read -r line; do
+    log "  $line"
+done
+
+# Extract unique remote IPs from ctrld connections
+UPSTREAM_IPS=()
+while IFS= read -r ip; do
+    [[ -n "$ip" ]] && UPSTREAM_IPS+=("$ip")
+done < <(echo "$CTRLD_CONNS" | grep -oE '[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | sort -u | while read -r ip; do
+    # Filter out local/private IPs — we only want the upstream DoH server IPs
+    if [[ ! "$ip" =~ ^(127\.|10\.|192\.168\.|172\.(1[6-9]|2[0-9]|3[01])\.) ]]; then
+        echo "$ip"
+    fi
+done)
+
+# Also try to resolve known Control D DoH endpoints
+for host in dns.controld.com freedns.controld.com; do
+    for ip in $(dig +short "$host" 2>/dev/null || true); do
+        if [[ "$ip" =~ ^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            UPSTREAM_IPS+=("$ip")
+        fi
+    done
+done
+
+# Deduplicate
+UPSTREAM_IPS=($(printf '%s\n' "${UPSTREAM_IPS[@]}" | sort -u))
+
+if [[ ${#UPSTREAM_IPS[@]} -eq 0 ]]; then
+    fail "Could not discover any upstream IPs!"
+    echo "Check: lsof -i -n -P | grep ctrld"
+    exit 1
+fi
+
+log "Found ${#UPSTREAM_IPS[@]} upstream IP(s):"
+for ip in "${UPSTREAM_IPS[@]}"; do
+    log "  $ip"
+done
+echo ""
+
+# ── Phase 2: Baseline check ─────────────────────────────────────────────────
+log "Phase 2: Baseline — verify DNS works normally"
+BASELINE=$(dig +short +timeout=5 example.com @127.0.0.1 2>/dev/null || true)
+if [[ -z "$BASELINE" ]]; then
+    fail "DNS not working before test!"
+    exit 1
+fi
+pass "Baseline: example.com → $BASELINE"
+
+LOG_LINES_BEFORE=$(wc -l < "$CTRLD_LOG" | tr -d ' ')
+log "Log position: line $LOG_LINES_BEFORE"
+echo ""
+
+# ── Phase 3: Block all upstream IPs ─────────────────────────────────────────
+log "Phase 3: Blackholing all upstream IPs"
+for ip in "${UPSTREAM_IPS[@]}"; do
+    route delete -host "$ip" 2>/dev/null || true  # clean slate
+    route add -host "$ip" 127.0.0.1 2>/dev/null
+    BLOCKED_IPS+=("$ip")
+    log "  Blocked: $ip → 127.0.0.1"
+done
+pass "All ${#UPSTREAM_IPS[@]} upstream IPs blackholed"
+echo ""
+
+# ── Phase 4: Cycle wifi to trigger network change ───────────────────────────
+log "Phase 4: Cycling wifi to trigger network change event"
+log "  Turning wifi OFF..."
+networksetup -setairportpower "$WIFI_IFACE" off
+sleep 3
+
+log "  Turning wifi ON..."
+networksetup -setairportpower "$WIFI_IFACE" on
+
+log "  Waiting for wifi to reconnect (up to 15s)..."
+WIFI_UP=false
+for i in $(seq 1 15); do
+    # Check if we have an IP on the wifi interface
+    IF_IP=$(ipconfig getifaddr "$WIFI_IFACE" 2>/dev/null || true)
+    if [[ -n "$IF_IP" ]]; then
+        WIFI_UP=true
+        pass "Wifi reconnected: $WIFI_IFACE → $IF_IP"
+        break
+    fi
+    sleep 1
+done
+
+if [[ "$WIFI_UP" == "false" ]]; then
+    fail "Wifi did not reconnect in 15s!"
+    warn "Cleaning up and exiting..."
+    exit 1
+fi
+
+log "  Waiting 5s for ctrld network monitor to fire..."
+sleep 5
+echo ""
+
+# ── Phase 5: Query and watch for recovery ────────────────────────────────────
+log "Phase 5: Sending queries — upstream is blocked, recovery should activate"
+log "  (ctrld should detect upstream failure → enable recovery bypass → use DHCP DNS)"
+echo ""
+
+RECOVERY_DETECTED=false
+BYPASS_ACTIVE=false
+DNS_DURING_BYPASS=false
+QUERY_COUNT=0
+
+for i in $(seq 1 30); do
+    QUERY_COUNT=$((QUERY_COUNT + 1))
+    RESULT=$(dig +short +timeout=3 "example.com" @127.0.0.1 2>/dev/null || true)
+
+    if [[ -n "$RESULT" ]]; then
+        log "  Query #$QUERY_COUNT: example.com → $RESULT ✓"
+    else
+        log "  Query #$QUERY_COUNT: example.com → FAIL ✗"
+    fi
+
+    # Check logs
+    NEW_LOGS=$(tail -n +$((LOG_LINES_BEFORE + 1)) "$CTRLD_LOG" 2>/dev/null || true)
+
+    if [[ "$RECOVERY_DETECTED" == "false" ]] && echo "$NEW_LOGS" | grep -qiE "enabling DHCP bypass|triggering recovery|No healthy"; then
+        echo ""
+        pass "🎯 Recovery flow triggered!"
+        RECOVERY_DETECTED=true
+        echo "$NEW_LOGS" | grep -iE "recovery|bypass|DHCP|No healthy|network change" | tail -8 | while read -r line; do
+            echo "  📋 $line"
+        done
+        echo ""
+    fi
+
+    if [[ "$BYPASS_ACTIVE" == "false" ]] && echo "$NEW_LOGS" | grep -qi "Recovery bypass active"; then
+        pass "🔄 Recovery bypass is forwarding queries to OS/DHCP resolver"
+        BYPASS_ACTIVE=true
+    fi
+
+    if [[ "$RECOVERY_DETECTED" == "true" && -n "$RESULT" ]]; then
+        pass "✅ DNS resolves during recovery bypass: example.com → $RESULT"
+        DNS_DURING_BYPASS=true
+        break
+    fi
+
+    sleep 2
+done
+
+# ── Phase 6: Show all recovery-related log entries ──────────────────────────
+echo ""
+log "Phase 6: All recovery-related ctrld log entries"
+log "────────────────────────────────────────────────"
+NEW_LOGS=$(tail -n +$((LOG_LINES_BEFORE + 1)) "$CTRLD_LOG" 2>/dev/null || true)
+RELEVANT=$(echo "$NEW_LOGS" | grep -iE "recovery|bypass|DHCP|unhealthy|upstream.*fail|No healthy|network change|network monitor|OS resolver" || true)
+if [[ -n "$RELEVANT" ]]; then
+    echo "$RELEVANT" | head -40 | while read -r line; do
+        echo "  $line"
+    done
+else
+    warn "No recovery-related log entries found!"
+    log "Last 15 lines of ctrld log:"
+    tail -15 "$CTRLD_LOG" | while read -r line; do
+        echo "  $line"
+    done
+fi
+
+# ── Phase 7: Unblock and verify full recovery ───────────────────────────────
+echo ""
+log "Phase 7: Unblocking upstream IPs"
+for ip in "${BLOCKED_IPS[@]}"; do
+    route delete -host "$ip" 2>/dev/null && log "  Unblocked: $ip" || true
+done
+BLOCKED_IPS=()  # clear so cleanup doesn't double-delete
+pass "All upstream IPs unblocked"
+
+log "Waiting for ctrld to recover (up to 30s)..."
+LOG_LINES_UNBLOCK=$(wc -l < "$CTRLD_LOG" | tr -d ' ')
+RECOVERY_COMPLETE=false
+
+for i in $(seq 1 15); do
+    dig +short +timeout=3 example.com @127.0.0.1 >/dev/null 2>&1 || true
+    POST_LOGS=$(tail -n +$((LOG_LINES_UNBLOCK + 1)) "$CTRLD_LOG" 2>/dev/null || true)
+
+    if echo "$POST_LOGS" | grep -qiE "recovery complete|disabling DHCP bypass|Upstream.*recovered"; then
+        RECOVERY_COMPLETE=true
+        pass "ctrld recovered — normal operation resumed"
+        echo "$POST_LOGS" | grep -iE "recovery|recovered|bypass|disabling" | head -5 | while read -r line; do
+            echo "  📋 $line"
+        done
+        break
+    fi
+    sleep 2
+done
+
+[[ "$RECOVERY_COMPLETE" == "false" ]] && warn "Recovery completion not detected (may need more time)"
+
+# Final check
+echo ""
+log "Phase 8: Final DNS verification"
+sleep 2
+FINAL=$(dig +short +timeout=5 example.com @127.0.0.1 2>/dev/null || true)
+if [[ -n "$FINAL" ]]; then
+    pass "DNS working: example.com → $FINAL"
+else
+    fail "DNS not resolving"
+fi
+
+# ── Summary ──────────────────────────────────────────────────────────────────
+echo ""
+log "═══════════════════════════════════════════════════════════"
+log "  Test Summary"
+log "═══════════════════════════════════════════════════════════"
+[[ "$RECOVERY_DETECTED" == "true" ]]  && pass "Recovery bypass activated" || fail "Recovery bypass NOT activated"
+[[ "$BYPASS_ACTIVE" == "true" ]]      && pass "Queries forwarded to OS/DHCP resolver" || warn "OS resolver forwarding not confirmed"
+[[ "$DNS_DURING_BYPASS" == "true" ]]  && pass "DNS resolved during bypass (proof of OS resolver leak)" || warn "DNS during bypass not confirmed"
+[[ "$RECOVERY_COMPLETE" == "true" ]]  && pass "Normal operation resumed after unblock" || warn "Recovery completion not confirmed"
+[[ -n "${FINAL:-}" ]]                && pass "DNS functional at end of test" || fail "DNS broken at end of test"
+echo ""
+log "Full log since test: tail -n +$LOG_LINES_BEFORE $CTRLD_LOG"
+log "Recovery entries:    tail -n +$LOG_LINES_BEFORE $CTRLD_LOG | grep -i recovery"

test-scripts/darwin/validate-pf-rules.sh

@@ -0,0 +1,272 @@
+#!/bin/bash
+# validate-pf-rules.sh
+# Standalone test of the pf redirect rules for dns-intercept mode.
+# Does NOT require ctrld. Loads the pf anchor, validates interception, cleans up.
+# Run as root (sudo).
+
+set -e
+
+GREEN='\033[0;32m'; RED='\033[0;31m'; YELLOW='\033[1;33m'; CYAN='\033[0;36m'; NC='\033[0m'
+ok()   { echo -e "${GREEN}[OK]${NC} $1"; }
+fail() { echo -e "${RED}[FAIL]${NC} $1"; FAILURES=$((FAILURES+1)); }
+warn() { echo -e "${YELLOW}[WARN]${NC} $1"; }
+FAILURES=0
+
+ANCHOR="com.controld.ctrld.test"
+ANCHOR_FILE="/tmp/pf-dns-intercept-test.conf"
+# Use a local DNS listener to prove redirect works (python one-liner)
+LISTENER_PID=""
+
+cleanup() {
+    echo ""
+    echo -e "${CYAN}--- Cleanup ---${NC}"
+    # Remove anchor rules
+    pfctl -a "$ANCHOR" -F all 2>/dev/null && echo "     Flushed anchor $ANCHOR" || true
+    # Remove anchor file
+    rm -f "$ANCHOR_FILE" "/tmp/pf-combined-test.conf" && echo "     Removed temp files" || true
+    # Reload original pf.conf to remove anchor reference
+    pfctl -f /etc/pf.conf 2>/dev/null && echo "     Reloaded original pf.conf" || true
+    # Kill test listener
+    if [ -n "$LISTENER_PID" ]; then
+        kill "$LISTENER_PID" 2>/dev/null && echo "     Stopped test DNS listener" || true
+    fi
+    echo "     Cleanup complete"
+}
+trap cleanup EXIT
+
+resolve() {
+    dig "@${1}" "$2" A +short +timeout=3 +tries=1 2>/dev/null | grep -E '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+' | head -1
+}
+
+echo -e "${CYAN}=== pf DNS Redirect Rule Validation ===${NC}"
+echo "     This loads the exact pf rules from the dns-intercept MR,"
+echo "     starts a tiny DNS listener on 127.0.0.1:53, and verifies"
+echo "     that queries to external IPs get redirected."
+echo ""
+
+# 0. Check we're root
+if [ "$(id -u)" -ne 0 ]; then
+    fail "Must run as root (sudo)"
+    exit 1
+fi
+
+# 1. Start a minimal DNS listener on 127.0.0.1:53
+# Uses socat to echo a fixed response — enough to prove redirect works.
+# If port 53 is already in use (mDNSResponder), we'll use that instead.
+echo "--- Step 1: DNS Listener on 127.0.0.1:53 ---"
+if lsof -i :53 -sTCP:LISTEN 2>/dev/null | grep -q "." || lsof -i UDP:53 2>/dev/null | grep -q "."; then
+    ok "Something already listening on port 53 (likely mDNSResponder or ctrld)"
+    HAVE_LISTENER=true
+else
+    # Start a simple Python DNS proxy that forwards to 1.1.1.1
+    python3 -c "
+import socket, threading, sys
+def proxy(data, addr, sock):
+    try:
+        s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+        s.settimeout(3)
+        s.sendto(data, ('1.1.1.1', 53))
+        resp, _ = s.recvfrom(4096)
+        sock.sendto(resp, addr)
+        s.close()
+    except: pass
+
+sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+sock.bind(('127.0.0.1', 53))
+print('READY', flush=True)
+while True:
+    data, addr = sock.recvfrom(4096)
+    threading.Thread(target=proxy, args=(data, addr, sock), daemon=True).start()
+" &
+    LISTENER_PID=$!
+    sleep 1
+    if kill -0 "$LISTENER_PID" 2>/dev/null; then
+        ok "Started test DNS proxy on 127.0.0.1:53 (PID $LISTENER_PID, forwards to 1.1.1.1)"
+        HAVE_LISTENER=true
+    else
+        fail "Could not start DNS listener on port 53 — port may be in use"
+        HAVE_LISTENER=false
+    fi
+fi
+echo ""
+
+# 2. Verify baseline: direct query to 8.8.8.8 works (before pf rules)
+echo "--- Step 2: Baseline (before pf rules) ---"
+IP=$(resolve "8.8.8.8" "example.com")
+if [ -n "$IP" ]; then
+    ok "Direct DNS to 8.8.8.8 works (baseline): $IP"
+else
+    warn "Direct DNS to 8.8.8.8 failed — may be blocked by existing firewall"
+fi
+echo ""
+
+# 3. Write and load the pf anchor (exact rules from MR)
+echo "--- Step 3: Load pf Anchor Rules ---"
+TEST_UPSTREAM="1.1.1.1"
+cat > "$ANCHOR_FILE" << PFRULES
+# ctrld DNS Intercept Mode (test anchor)
+# Two-step: route-to lo0 + rdr on lo0
+#
+# In production, ctrld uses DoH (port 443) for upstreams so they're not
+# affected by port 53 rules. For this test, we exempt our upstream ($TEST_UPSTREAM)
+# explicitly — same mechanism ctrld uses for OS resolver exemptions.
+
+# --- Translation rules (rdr) ---
+rdr pass on lo0 inet proto udp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+rdr pass on lo0 inet proto tcp from any to ! 127.0.0.1 port 53 -> 127.0.0.1 port 53
+
+# --- Filtering rules (pass) ---
+# Exempt test upstream (in production: ctrld uses DoH, so this isn't needed).
+pass out quick on ! lo0 inet proto { udp, tcp } from any to $TEST_UPSTREAM port 53
+
+# Force remaining outbound DNS through loopback for interception.
+pass out quick on ! lo0 route-to lo0 inet proto udp from any to ! 127.0.0.1 port 53 no state
+pass out quick on ! lo0 route-to lo0 inet proto tcp from any to ! 127.0.0.1 port 53 no state
+
+# Allow redirected traffic through on loopback.
+pass in quick on lo0 inet proto { udp, tcp } from any to 127.0.0.1 port 53 no state
+PFRULES
+
+ok "Wrote anchor file: $ANCHOR_FILE"
+cat "$ANCHOR_FILE" | sed 's/^/     /'
+echo ""
+
+# Load anchor
+OUTPUT=$(pfctl -a "$ANCHOR" -f "$ANCHOR_FILE" 2>&1) || {
+    fail "Failed to load anchor: $OUTPUT"
+    exit 1
+}
+ok "Loaded anchor: $ANCHOR"
+
+# Inject anchor references into running pf config.
+# pf enforces strict rule ordering: options, normalization, queueing, translation, filtering.
+# We must insert rdr-anchor with other rdr-anchors and anchor with other anchors.
+TMPCONF="/tmp/pf-combined-test.conf"
+python3 -c "
+import sys
+lines = open('/etc/pf.conf').read().splitlines()
+anchor = '$ANCHOR'
+rdr_ref = 'rdr-anchor \"' + anchor + '\"'
+anchor_ref = 'anchor \"' + anchor + '\"'
+out = []
+rdr_done = False
+anc_done = False
+for line in lines:
+    s = line.strip()
+    # Insert our rdr-anchor before the first existing rdr-anchor
+    if not rdr_done and s.startswith('rdr-anchor'):
+        out.append(rdr_ref)
+        rdr_done = True
+    # Insert our anchor before the first existing anchor (filter-phase)
+    if not anc_done and s.startswith('anchor') and not s.startswith('anchor \"com.apple'):
+        out.append(anchor_ref)
+        anc_done = True
+    out.append(line)
+# Fallback if no existing anchors found
+if not rdr_done:
+    # Insert before first non-comment, non-blank after any 'set' or 'scrub' lines
+    out.insert(0, rdr_ref)
+if not anc_done:
+    out.append(anchor_ref)
+open('$TMPCONF', 'w').write('\n'.join(out) + '\n')
+" || { fail "Failed to build combined pf config"; exit 1; }
+
+INJECT_OUT=$(pfctl -f "$TMPCONF" 2>&1) || {
+    fail "Failed to inject anchor reference: $INJECT_OUT"
+    rm -f "$TMPCONF"
+    exit 1
+}
+rm -f "$TMPCONF"
+ok "Injected anchor references into running pf ruleset"
+
+# Enable pf
+pfctl -e 2>/dev/null || true
+
+# Show loaded rules
+echo ""
+echo "     Active NAT rules:"
+pfctl -a "$ANCHOR" -sn 2>/dev/null | sed 's/^/       /'
+echo "     Active filter rules:"
+pfctl -a "$ANCHOR" -sr 2>/dev/null | sed 's/^/       /'
+echo ""
+
+# 4. Test: DNS to 8.8.8.8 should now be redirected to 127.0.0.1:53
+echo "--- Step 4: Redirect Test ---"
+if [ "$HAVE_LISTENER" = true ]; then
+    IP=$(resolve "8.8.8.8" "example.com" 5)
+    if [ -n "$IP" ]; then
+        ok "DNS to 8.8.8.8 redirected through 127.0.0.1:53: $IP"
+    else
+        fail "DNS to 8.8.8.8 failed — redirect may not be working"
+    fi
+
+    # Also test another random IP
+    IP2=$(resolve "9.9.9.9" "example.com" 5)
+    if [ -n "$IP2" ]; then
+        ok "DNS to 9.9.9.9 also redirected: $IP2"
+    else
+        fail "DNS to 9.9.9.9 failed"
+    fi
+else
+    warn "No listener on port 53 — cannot test redirect"
+fi
+echo ""
+
+# 5. Test: DNS to 127.0.0.1 still works (not double-redirected)
+echo "--- Step 5: Localhost DNS (no loop) ---"
+if [ "$HAVE_LISTENER" = true ]; then
+    IP=$(resolve "127.0.0.1" "example.com" 5)
+    if [ -n "$IP" ]; then
+        ok "DNS to 127.0.0.1 works normally (not caught by redirect): $IP"
+    else
+        fail "DNS to 127.0.0.1 failed — possible redirect loop"
+    fi
+fi
+echo ""
+
+# 6. Simulate VPN DNS override
+echo "--- Step 6: VPN DNS Override Simulation ---"
+IFACE=$(route -n get default 2>/dev/null | awk '/interface:/{print $2}')
+SVC=""
+for try_svc in "Wi-Fi" "Ethernet" "Thunderbolt Ethernet"; do
+    if networksetup -getdnsservers "$try_svc" 2>/dev/null >/dev/null; then
+        SVC="$try_svc"
+        break
+    fi
+done
+
+if [ -n "$SVC" ] && [ "$HAVE_LISTENER" = true ]; then
+    ORIG_DNS=$(networksetup -getdnsservers "$SVC" 2>/dev/null || echo "")
+    echo "     Service: $SVC"
+    echo "     Current DNS: $ORIG_DNS"
+
+    networksetup -setdnsservers "$SVC" 10.50.10.77
+    dscacheutil -flushcache 2>/dev/null || true
+    killall -HUP mDNSResponder 2>/dev/null || true
+    echo "     Set DNS to 10.50.10.77 (simulating F5 VPN)"
+    sleep 2
+
+    IP=$(resolve "10.50.10.77" "google.com" 5)
+    if [ -n "$IP" ]; then
+        ok "Query to fake VPN DNS (10.50.10.77) redirected to ctrld: $IP"
+    else
+        fail "Query to fake VPN DNS failed"
+    fi
+
+    # Restore
+    if echo "$ORIG_DNS" | grep -q "There aren't any DNS Servers"; then
+        networksetup -setdnsservers "$SVC" Empty
+    else
+        networksetup -setdnsservers "$SVC" $ORIG_DNS
+    fi
+    echo "     Restored DNS"
+else
+    warn "Skipping VPN simulation (no service found or no listener)"
+fi
+
+echo ""
+if [ "$FAILURES" -eq 0 ]; then
+    echo -e "${GREEN}=== All tests passed ===${NC}"
+else
+    echo -e "${RED}=== $FAILURES test(s) failed ===${NC}"
+fi

test-scripts/windows/test-dns-intercept.ps1

@@ -0,0 +1,544 @@
+# =============================================================================
+# DNS Intercept Mode Test Script — Windows (WFP)
+# =============================================================================
+# Run as Administrator: powershell -ExecutionPolicy Bypass -File test-dns-intercept-win.ps1
+#
+# Tests the dns-intercept feature end-to-end with validation at each step.
+# Logs are read from C:\tmp\dns.log (ctrld log location on test machine).
+#
+# Manual steps marked with [MANUAL] require human interaction.
+# =============================================================================
+
+$ErrorActionPreference = "Continue"
+
+$CtrldLog = "C:\tmp\dns.log"
+$WfpSubLayerName = "ctrld DNS Intercept"
+$Pass = 0
+$Fail = 0
+$Warn = 0
+$Results = @()
+
+# --- Helpers ---
+
+function Header($text) { Write-Host "`n━━━ $text ━━━" -ForegroundColor Cyan }
+function Info($text)   { Write-Host "  ℹ  $text" }
+function Manual($text) { Write-Host "  [MANUAL] $text" -ForegroundColor Yellow }
+function Separator()   { Write-Host "─────────────────────────────────────────────────────" -ForegroundColor Cyan }
+
+function Pass($text) {
+    Write-Host "  ✅ PASS: $text" -ForegroundColor Green
+    $script:Pass++
+    $script:Results += "PASS: $text"
+}
+
+function Fail($text) {
+    Write-Host "  ❌ FAIL: $text" -ForegroundColor Red
+    $script:Fail++
+    $script:Results += "FAIL: $text"
+}
+
+function Warn($text) {
+    Write-Host "  ⚠️  WARN: $text" -ForegroundColor Yellow
+    $script:Warn++
+    $script:Results += "WARN: $text"
+}
+
+function WaitForKey {
+    Write-Host "`n  Press Enter to continue..." -NoNewline
+    Read-Host
+}
+
+function LogGrep($pattern, $lines = 200) {
+    if (Test-Path $CtrldLog) {
+        Get-Content $CtrldLog -Tail $lines -ErrorAction SilentlyContinue |
+            Select-String -Pattern $pattern -ErrorAction SilentlyContinue
+    }
+}
+
+function LogGrepCount($pattern, $lines = 200) {
+    $matches = LogGrep $pattern $lines
+    if ($matches) { return @($matches).Count } else { return 0 }
+}
+
+# --- Check Admin ---
+
+function Check-Admin {
+    $identity = [Security.Principal.WindowsIdentity]::GetCurrent()
+    $principal = New-Object Security.Principal.WindowsPrincipal($identity)
+    if (-not $principal.IsInRole([Security.Principal.WindowsBuiltInRole]::Administrator)) {
+        Write-Host "This script must be run as Administrator." -ForegroundColor Red
+        exit 1
+    }
+}
+
+# =============================================================================
+# TEST SECTIONS
+# =============================================================================
+
+function Test-Prereqs {
+    Header "0. Prerequisites"
+
+    if (Get-Command nslookup -ErrorAction SilentlyContinue) {
+        Pass "nslookup available"
+    } else {
+        Fail "nslookup not found"
+    }
+
+    if (Get-Command netsh -ErrorAction SilentlyContinue) {
+        Pass "netsh available"
+    } else {
+        Fail "netsh not found"
+    }
+
+    if (Test-Path $CtrldLog) {
+        Pass "ctrld log exists at $CtrldLog"
+    } else {
+        Warn "ctrld log not found at $CtrldLog — log checks will be skipped"
+    }
+
+    # Show current DNS config
+    Info "Current DNS servers:"
+    Get-DnsClientServerAddress -AddressFamily IPv4 |
+        Where-Object { $_.ServerAddresses.Count -gt 0 } |
+        Format-Table InterfaceAlias, ServerAddresses -AutoSize |
+        Out-String | ForEach-Object { $_.Trim() } | Write-Host
+}
+
+function Test-WfpState {
+    Header "1. WFP State Validation"
+
+    # Export WFP filters and check for ctrld's sublayer/filters
+    $wfpExport = "$env:TEMP\wfp_filters.xml"
+    Info "Exporting WFP filters (this may take a few seconds)..."
+
+    try {
+        netsh wfp show filters file=$wfpExport 2>$null | Out-Null
+
+        if (Test-Path $wfpExport) {
+            $wfpContent = Get-Content $wfpExport -Raw -ErrorAction SilentlyContinue
+
+            # Check for ctrld sublayer
+            if ($wfpContent -match "ctrld") {
+                Pass "WFP filters contain 'ctrld' references"
+
+                # Count filters
+                $filterMatches = ([regex]::Matches($wfpContent, "ctrld")).Count
+                Info "Found $filterMatches 'ctrld' references in WFP export"
+            } else {
+                Fail "No 'ctrld' references found in WFP filters"
+            }
+
+            # Check for DNS port 53 filters
+            if ($wfpContent -match "port.*53" -or $wfpContent -match "0x0035") {
+                Pass "Port 53 filter conditions found in WFP"
+            } else {
+                Warn "Could not confirm port 53 filters in WFP export"
+            }
+
+            Remove-Item $wfpExport -ErrorAction SilentlyContinue
+        } else {
+            Warn "WFP export file not created"
+        }
+    } catch {
+        Warn "Could not export WFP filters: $_"
+    }
+
+    Separator
+
+    # Alternative: Check via PowerShell WFP cmdlets if available
+    Info "Checking WFP via netsh wfp show state..."
+    $wfpState = netsh wfp show state 2>$null
+    if ($wfpState) {
+        Info "WFP state export completed (check $env:TEMP for details)"
+    }
+
+    # Check Windows Firewall service is running
+    $fwService = Get-Service -Name "mpssvc" -ErrorAction SilentlyContinue
+    if ($fwService -and $fwService.Status -eq "Running") {
+        Pass "Windows Firewall service (BFE/WFP) is running"
+    } else {
+        Fail "Windows Firewall service not running — WFP won't work"
+    }
+
+    # Check BFE (Base Filtering Engine)
+    $bfeService = Get-Service -Name "BFE" -ErrorAction SilentlyContinue
+    if ($bfeService -and $bfeService.Status -eq "Running") {
+        Pass "Base Filtering Engine (BFE) is running"
+    } else {
+        Fail "BFE not running — WFP requires this service"
+    }
+}
+
+function Test-DnsInterception {
+    Header "2. DNS Interception Tests"
+
+    # Mark log position
+    $logLinesBefore = 0
+    if (Test-Path $CtrldLog) {
+        $logLinesBefore = @(Get-Content $CtrldLog -ErrorAction SilentlyContinue).Count
+    }
+
+    # Test 1: Query to external resolver should be intercepted
+    Info "Test: nslookup example.com 8.8.8.8 (should be intercepted by ctrld)"
+    $result = $null
+    try {
+        $result = nslookup example.com 8.8.8.8 2>&1 | Out-String
+    } catch { }
+
+    if ($result -and $result -match "\d+\.\d+\.\d+\.\d+") {
+        Pass "nslookup @8.8.8.8 returned a result"
+
+        # Check which server answered
+        if ($result -match "Server:\s+(\S+)") {
+            $server = $Matches[1]
+            Info "Answered by server: $server"
+            if ($server -match "127\.0\.0\.1|localhost") {
+                Pass "Response came from localhost (ctrld intercepted)"
+            } elseif ($server -match "8\.8\.8\.8") {
+                Fail "Response came from 8.8.8.8 directly — NOT intercepted"
+            }
+        }
+    } else {
+        Fail "nslookup @8.8.8.8 failed or returned no address"
+    }
+
+    # Check ctrld logged it
+    Start-Sleep -Seconds 1
+    if (Test-Path $CtrldLog) {
+        $newLines = Get-Content $CtrldLog -ErrorAction SilentlyContinue |
+            Select-Object -Skip $logLinesBefore
+        $intercepted = $newLines | Select-String "example.com" -ErrorAction SilentlyContinue
+        if ($intercepted) {
+            Pass "ctrld logged the intercepted query for example.com"
+        } else {
+            Fail "ctrld did NOT log query for example.com"
+        }
+    }
+
+    Separator
+
+    # Test 2: Another external resolver
+    Info "Test: nslookup cloudflare.com 1.1.1.1 (should also be intercepted)"
+    try {
+        $result2 = nslookup cloudflare.com 1.1.1.1 2>&1 | Out-String
+        if ($result2 -match "\d+\.\d+\.\d+\.\d+") {
+            Pass "nslookup @1.1.1.1 returned result"
+        } else {
+            Fail "nslookup @1.1.1.1 failed"
+        }
+    } catch {
+        Fail "nslookup @1.1.1.1 threw exception"
+    }
+
+    Separator
+
+    # Test 3: Query to localhost should work (no loop)
+    Info "Test: nslookup example.org 127.0.0.1 (direct to ctrld, no loop)"
+    try {
+        $result3 = nslookup example.org 127.0.0.1 2>&1 | Out-String
+        if ($result3 -match "\d+\.\d+\.\d+\.\d+") {
+            Pass "nslookup @127.0.0.1 works (no loop)"
+        } else {
+            Fail "nslookup @127.0.0.1 failed — possible loop"
+        }
+    } catch {
+        Fail "nslookup @127.0.0.1 exception — possible loop"
+    }
+
+    Separator
+
+    # Test 4: System DNS via Resolve-DnsName
+    Info "Test: Resolve-DnsName example.net (system resolver)"
+    try {
+        $result4 = Resolve-DnsName example.net -Type A -ErrorAction Stop
+        if ($result4) {
+            Pass "System DNS resolution works (Resolve-DnsName)"
+        }
+    } catch {
+        Fail "System DNS resolution failed: $_"
+    }
+
+    Separator
+
+    # Test 5: TCP DNS
+    Info "Test: nslookup -vc example.com 9.9.9.9 (TCP DNS)"
+    try {
+        $result5 = nslookup -vc example.com 9.9.9.9 2>&1 | Out-String
+        if ($result5 -match "\d+\.\d+\.\d+\.\d+") {
+            Pass "TCP DNS query intercepted and resolved"
+        } else {
+            Warn "TCP DNS query may not have been intercepted"
+        }
+    } catch {
+        Warn "TCP DNS test inconclusive"
+    }
+}
+
+function Test-NonDnsUnaffected {
+    Header "3. Non-DNS Traffic Unaffected"
+
+    # HTTPS
+    Info "Test: Invoke-WebRequest https://example.com (HTTPS should NOT be affected)"
+    try {
+        $web = Invoke-WebRequest -Uri "https://example.com" -UseBasicParsing -TimeoutSec 10 -ErrorAction Stop
+        if ($web.StatusCode -eq 200) {
+            Pass "HTTPS works (HTTP 200)"
+        } else {
+            Pass "HTTPS returned HTTP $($web.StatusCode)"
+        }
+    } catch {
+        Fail "HTTPS failed: $_"
+    }
+
+    # Test non-53 port connectivity
+    Info "Test: Test-NetConnection to github.com:443 (non-DNS port)"
+    try {
+        $nc = Test-NetConnection -ComputerName "github.com" -Port 443 -WarningAction SilentlyContinue
+        if ($nc.TcpTestSucceeded) {
+            Pass "Port 443 reachable (non-DNS traffic unaffected)"
+        } else {
+            Warn "Port 443 unreachable (may be firewall)"
+        }
+    } catch {
+        Warn "Test-NetConnection failed: $_"
+    }
+}
+
+function Test-CtrldLogHealth {
+    Header "4. ctrld Log Health Check"
+
+    if (-not (Test-Path $CtrldLog)) {
+        Warn "Skipping log checks — $CtrldLog not found"
+        return
+    }
+
+    # Check for WFP initialization
+    if (LogGrepCount "initializing Windows Filtering Platform" 500) {
+        Pass "WFP initialization logged"
+    } else {
+        Fail "No WFP initialization in recent logs"
+    }
+
+    # Check for successful WFP engine open
+    if (LogGrepCount "WFP engine opened" 500) {
+        Pass "WFP engine opened successfully"
+    } else {
+        Fail "WFP engine open not found in logs"
+    }
+
+    # Check for sublayer creation
+    if (LogGrepCount "WFP sublayer created" 500) {
+        Pass "WFP sublayer created"
+    } else {
+        Fail "WFP sublayer creation not logged"
+    }
+
+    # Check for filter creation
+    $filterCount = LogGrepCount "added WFP.*filter" 500
+    if ($filterCount -gt 0) {
+        Pass "WFP filters added ($filterCount filter log entries)"
+    } else {
+        Fail "No WFP filter creation logged"
+    }
+
+    # Check for permit-localhost filters
+    if (LogGrepCount "permit.*localhost\|permit.*127\.0\.0\.1" 500) {
+        Pass "Localhost permit filters logged"
+    } else {
+        Warn "Localhost permit filters not explicitly logged"
+    }
+
+    Separator
+
+    # Check for errors
+    Info "Recent errors in ctrld log:"
+    $errors = LogGrep '"level":"error"' 500
+    if ($errors) {
+        $errors | Select-Object -Last 5 | ForEach-Object { Write-Host "    $_" }
+        Warn "Errors found in recent logs"
+    } else {
+        Pass "No errors in recent logs"
+    }
+
+    # Warnings (excluding expected ones)
+    $warnings = LogGrep '"level":"warn"' 500 | Where-Object {
+        $_ -notmatch "skipping self-upgrade"
+    }
+    if ($warnings) {
+        Info "Warnings:"
+        $warnings | Select-Object -Last 5 | ForEach-Object { Write-Host "    $_" }
+    }
+
+    # VPN DNS detection
+    $vpnLogs = LogGrep "VPN DNS" 500
+    if ($vpnLogs) {
+        Info "VPN DNS activity:"
+        $vpnLogs | Select-Object -Last 5 | ForEach-Object { Write-Host "    $_" }
+    } else {
+        Info "No VPN DNS activity (expected if no VPN connected)"
+    }
+}
+
+function Test-CleanupOnStop {
+    Header "5. Cleanup Validation (After ctrld Stop)"
+
+    Manual "Stop ctrld now (ctrld stop or Ctrl+C), then press Enter"
+    WaitForKey
+
+    Start-Sleep -Seconds 2
+
+    # Check WFP filters are removed
+    $wfpExport = "$env:TEMP\wfp_after_stop.xml"
+    try {
+        netsh wfp show filters file=$wfpExport 2>$null | Out-Null
+        if (Test-Path $wfpExport) {
+            $content = Get-Content $wfpExport -Raw -ErrorAction SilentlyContinue
+            if ($content -match "ctrld") {
+                Fail "WFP still contains 'ctrld' filters after stop"
+            } else {
+                Pass "WFP filters cleaned up after stop"
+            }
+            Remove-Item $wfpExport -ErrorAction SilentlyContinue
+        }
+    } catch {
+        Warn "Could not verify WFP cleanup"
+    }
+
+    # DNS should work normally
+    Info "Test: nslookup example.com (should work via system DNS)"
+    try {
+        $result = nslookup example.com 2>&1 | Out-String
+        if ($result -match "\d+\.\d+\.\d+\.\d+") {
+            Pass "DNS works after ctrld stop"
+        } else {
+            Fail "DNS broken after ctrld stop"
+        }
+    } catch {
+        Fail "DNS exception after ctrld stop"
+    }
+}
+
+function Test-RestartResilience {
+    Header "6. Restart Resilience"
+
+    Manual "Start ctrld again with --dns-intercept, then press Enter"
+    WaitForKey
+
+    Start-Sleep -Seconds 3
+
+    # Quick interception test
+    Info "Test: nslookup example.com 8.8.8.8 (should be intercepted after restart)"
+    try {
+        $result = nslookup example.com 8.8.8.8 2>&1 | Out-String
+        if ($result -match "\d+\.\d+\.\d+\.\d+") {
+            Pass "DNS interception works after restart"
+        } else {
+            Fail "DNS interception broken after restart"
+        }
+    } catch {
+        Fail "DNS test failed after restart"
+    }
+
+    # Check WFP filters restored
+    if (LogGrepCount "WFP engine opened" 100) {
+        Pass "WFP re-initialized after restart"
+    }
+}
+
+function Test-NetworkChange {
+    Header "7. Network Change Recovery"
+
+    Info "This test verifies recovery after network changes."
+    Manual "Switch Wi-Fi networks, or disable/re-enable network adapter, then press Enter"
+    WaitForKey
+
+    Start-Sleep -Seconds 5
+
+    # Test interception still works
+    Info "Test: nslookup example.com 8.8.8.8 (should still be intercepted)"
+    try {
+        $result = nslookup example.com 8.8.8.8 2>&1 | Out-String
+        if ($result -match "\d+\.\d+\.\d+\.\d+") {
+            Pass "DNS interception works after network change"
+        } else {
+            Fail "DNS interception broken after network change"
+        }
+    } catch {
+        Fail "DNS test failed after network change"
+    }
+
+    # Check logs for recovery/network events
+    if (Test-Path $CtrldLog) {
+        $recoveryLogs = LogGrep "recovery|network change|network monitor" 100
+        if ($recoveryLogs) {
+            Info "Recovery/network log entries:"
+            $recoveryLogs | Select-Object -Last 5 | ForEach-Object { Write-Host "    $_" }
+        }
+    }
+}
+
+# =============================================================================
+# SUMMARY
+# =============================================================================
+
+function Print-Summary {
+    Header "TEST SUMMARY"
+    Write-Host ""
+    foreach ($r in $Results) {
+        if ($r.StartsWith("PASS")) {
+            Write-Host "  ✅ $($r.Substring(6))" -ForegroundColor Green
+        } elseif ($r.StartsWith("FAIL")) {
+            Write-Host "  ❌ $($r.Substring(6))" -ForegroundColor Red
+        } elseif ($r.StartsWith("WARN")) {
+            Write-Host "  ⚠️  $($r.Substring(6))" -ForegroundColor Yellow
+        }
+    }
+    Write-Host ""
+    Separator
+    Write-Host "  Passed: $Pass  |  Failed: $Fail  |  Warnings: $Warn"
+    Separator
+
+    if ($Fail -gt 0) {
+        Write-Host "`n  Some tests failed. Debug commands:" -ForegroundColor Red
+        Write-Host "    netsh wfp show filters          # dump all WFP filters"
+        Write-Host "    Get-Content $CtrldLog -Tail 100 # recent ctrld logs"
+        Write-Host "    Get-DnsClientServerAddress       # current DNS config"
+        Write-Host "    netsh wfp show state             # WFP state dump"
+    } else {
+        Write-Host "`n  All tests passed!" -ForegroundColor Green
+    }
+}
+
+# =============================================================================
+# MAIN
+# =============================================================================
+
+Write-Host "╔═══════════════════════════════════════════════════════╗" -ForegroundColor White
+Write-Host "║  ctrld DNS Intercept Mode — Windows Test Suite       ║" -ForegroundColor White
+Write-Host "║  Tests WFP-based DNS interception                    ║" -ForegroundColor White
+Write-Host "╚═══════════════════════════════════════════════════════╝" -ForegroundColor White
+
+Check-Admin
+
+Write-Host ""
+Write-Host "Make sure ctrld is running with --dns-intercept before starting."
+Write-Host "Log location: $CtrldLog"
+WaitForKey
+
+Test-Prereqs
+Test-WfpState
+Test-DnsInterception
+Test-NonDnsUnaffected
+Test-CtrldLogHealth
+
+Separator
+Write-Host ""
+Write-Host "The next tests require manual steps (stop/start ctrld, network changes)."
+Write-Host "Press Enter to continue, or Ctrl+C to skip and see results so far."
+WaitForKey
+
+Test-CleanupOnStop
+Test-RestartResilience
+Test-NetworkChange
+
+Print-Summary

test-scripts/windows/test-recovery-bypass.ps1

@@ -0,0 +1,289 @@
+# test-recovery-bypass.ps1 — Test DNS intercept recovery bypass (captive portal simulation)
+#
+# Simulates a captive portal by:
+#   1. Discovering ctrld's upstream IPs from active connections
+#   2. Blocking them via Windows Firewall rules
+#   3. Disabling/re-enabling the wifi adapter to trigger network change
+#   4. Verifying recovery bypass forwards to OS/DHCP resolver
+#   5. Removing firewall rules and verifying normal operation resumes
+#
+# SAFE: Uses named firewall rules that are cleaned up on exit.
+#
+# Usage (run as Administrator):
+#   .\test-recovery-bypass.ps1 [-WifiAdapter "Wi-Fi"] [-CtrldLog "C:\temp\dns.log"]
+#
+# Prerequisites:
+#   - ctrld running with --dns-intercept and -v 1 --log C:\temp\dns.log
+#   - Run as Administrator
+
+param(
+    [string]$WifiAdapter = "Wi-Fi",
+    [string]$CtrldLog = "C:\temp\dns.log",
+    [int]$BlockDurationSec = 60
+)
+
+$ErrorActionPreference = "Stop"
+$FwRulePrefix = "ctrld-test-recovery-block"
+$BlockedIPs = @()
+
+function Log($msg)  { Write-Host "[$(Get-Date -Format 'HH:mm:ss')] $msg" -ForegroundColor Cyan }
+function Pass($msg) { Write-Host "[PASS] $msg" -ForegroundColor Green }
+function Fail($msg) { Write-Host "[FAIL] $msg" -ForegroundColor Red }
+function Warn($msg) { Write-Host "[WARN] $msg" -ForegroundColor Yellow }
+
+# ── Safety: cleanup function ─────────────────────────────────────────────────
+function Cleanup {
+    Log "═══ CLEANUP ═══"
+
+    # Ensure wifi is enabled
+    Log "Ensuring wifi adapter is enabled..."
+    try { Enable-NetAdapter -Name $WifiAdapter -Confirm:$false -ErrorAction SilentlyContinue } catch {}
+
+    # Remove all test firewall rules
+    Log "Removing test firewall rules..."
+    Get-NetFirewallRule -DisplayName "$FwRulePrefix*" -ErrorAction SilentlyContinue |
+        Remove-NetFirewallRule -ErrorAction SilentlyContinue
+    Log "Cleanup complete."
+}
+
+# Register cleanup on script exit
+$null = Register-EngineEvent -SourceIdentifier PowerShell.Exiting -Action { Cleanup } -ErrorAction SilentlyContinue
+trap { Cleanup; break }
+
+# ── Pre-checks ───────────────────────────────────────────────────────────────
+$isAdmin = ([Security.Principal.WindowsPrincipal][Security.Principal.WindowsIdentity]::GetCurrent()).IsInRole([Security.Principal.WindowsBuiltInRole]::Administrator)
+if (-not $isAdmin) {
+    Fail "Run as Administrator!"
+    exit 1
+}
+
+if (-not (Test-Path $CtrldLog)) {
+    Fail "ctrld log not found at $CtrldLog"
+    Write-Host "Start ctrld with: ctrld run --dns-intercept --cd <uid> -v 1 --log $CtrldLog"
+    exit 1
+}
+
+# Check wifi adapter exists
+$adapter = Get-NetAdapter -Name $WifiAdapter -ErrorAction SilentlyContinue
+if (-not $adapter) {
+    Fail "Wifi adapter '$WifiAdapter' not found"
+    Write-Host "Available adapters:"
+    Get-NetAdapter | Format-Table Name, Status, InterfaceDescription
+    exit 1
+}
+
+Log "═══════════════════════════════════════════════════════════"
+Log "  Recovery Bypass Test (Captive Portal Simulation)"
+Log "═══════════════════════════════════════════════════════════"
+Log "Wifi adapter: $WifiAdapter"
+Log "ctrld log:    $CtrldLog"
+Write-Host ""
+
+# ── Phase 1: Discover upstream IPs ──────────────────────────────────────────
+Log "Phase 1: Discovering ctrld upstream IPs from active connections"
+
+$ctrldConns = Get-NetTCPConnection -OwningProcess (Get-Process ctrld* -ErrorAction SilentlyContinue).Id -ErrorAction SilentlyContinue |
+    Where-Object { $_.State -eq "Established" -and $_.RemotePort -eq 443 }
+
+$upstreamIPs = @()
+if ($ctrldConns) {
+    $upstreamIPs = $ctrldConns | Select-Object -ExpandProperty RemoteAddress -Unique |
+        Where-Object { $_ -notmatch "^(127\.|10\.|192\.168\.|172\.(1[6-9]|2[0-9]|3[01])\.)" }
+
+    foreach ($conn in $ctrldConns) {
+        Log "  $($conn.LocalAddress):$($conn.LocalPort) -> $($conn.RemoteAddress):$($conn.RemotePort)"
+    }
+}
+
+# Also resolve known Control D endpoints
+foreach ($host_ in @("dns.controld.com", "freedns.controld.com")) {
+    try {
+        $resolved = Resolve-DnsName $host_ -Type A -ErrorAction SilentlyContinue
+        $resolved | ForEach-Object { if ($_.IPAddress) { $upstreamIPs += $_.IPAddress } }
+    } catch {}
+}
+
+$upstreamIPs = $upstreamIPs | Sort-Object -Unique
+
+if ($upstreamIPs.Count -eq 0) {
+    Fail "Could not discover any upstream IPs!"
+    exit 1
+}
+
+Log "Found $($upstreamIPs.Count) upstream IP(s):"
+foreach ($ip in $upstreamIPs) { Log "  $ip" }
+Write-Host ""
+
+# ── Phase 2: Baseline ───────────────────────────────────────────────────────
+Log "Phase 2: Baseline — verify DNS works normally"
+$baseline = Resolve-DnsName example.com -Server 127.0.0.1 -Type A -ErrorAction SilentlyContinue
+if ($baseline) {
+    Pass "Baseline: example.com -> $($baseline[0].IPAddress)"
+} else {
+    Fail "DNS not working!"
+    exit 1
+}
+
+$logLinesBefore = (Get-Content $CtrldLog).Count
+Log "Log position: line $logLinesBefore"
+Write-Host ""
+
+# ── Phase 3: Block upstream IPs via Windows Firewall ────────────────────────
+Log "Phase 3: Blocking upstream IPs via Windows Firewall"
+foreach ($ip in $upstreamIPs) {
+    $ruleName = "$FwRulePrefix-$ip"
+    # Remove existing rule if any
+    Remove-NetFirewallRule -DisplayName $ruleName -ErrorAction SilentlyContinue
+    # Block outbound to this IP
+    New-NetFirewallRule -DisplayName $ruleName -Direction Outbound -Action Block `
+        -RemoteAddress $ip -Protocol TCP -RemotePort 443 `
+        -Description "Temporary test rule for ctrld recovery bypass test" | Out-Null
+    $BlockedIPs += $ip
+    Log "  Blocked: $ip (outbound TCP 443)"
+}
+Pass "All $($upstreamIPs.Count) upstream IPs blocked"
+Write-Host ""
+
+# ── Phase 4: Cycle wifi ─────────────────────────────────────────────────────
+Log "Phase 4: Cycling wifi to trigger network change event"
+Log "  Disabling $WifiAdapter..."
+Disable-NetAdapter -Name $WifiAdapter -Confirm:$false
+Start-Sleep -Seconds 3
+
+Log "  Enabling $WifiAdapter..."
+Enable-NetAdapter -Name $WifiAdapter -Confirm:$false
+
+Log "  Waiting for wifi to reconnect (up to 20s)..."
+$wifiUp = $false
+for ($i = 0; $i -lt 20; $i++) {
+    $status = (Get-NetAdapter -Name $WifiAdapter).Status
+    if ($status -eq "Up") {
+        # Check for IP
+        $ipAddr = (Get-NetIPAddress -InterfaceAlias $WifiAdapter -AddressFamily IPv4 -ErrorAction SilentlyContinue).IPAddress
+        if ($ipAddr) {
+            $wifiUp = $true
+            Pass "Wifi reconnected: $WifiAdapter -> $ipAddr"
+            break
+        }
+    }
+    Start-Sleep -Seconds 1
+}
+
+if (-not $wifiUp) {
+    Fail "Wifi did not reconnect in 20s!"
+    Cleanup
+    exit 1
+}
+
+Log "  Waiting 5s for ctrld network monitor..."
+Start-Sleep -Seconds 5
+Write-Host ""
+
+# ── Phase 5: Query and watch for recovery ────────────────────────────────────
+Log "Phase 5: Sending queries — upstream blocked, recovery should activate"
+Write-Host ""
+
+$recoveryDetected = $false
+$bypassActive = $false
+$dnsDuringBypass = $false
+
+for ($q = 1; $q -le 30; $q++) {
+    $result = $null
+    try {
+        $result = Resolve-DnsName "example.com" -Server 127.0.0.1 -Type A -DnsOnly -ErrorAction SilentlyContinue
+    } catch {}
+
+    if ($result) {
+        Log "  Query #$q`: example.com -> $($result[0].IPAddress) ✓"
+    } else {
+        Log "  Query #$q`: example.com -> FAIL ✗"
+    }
+
+    # Check ctrld log for recovery
+    $newLogs = Get-Content $CtrldLog | Select-Object -Skip $logLinesBefore
+    $logText = $newLogs -join "`n"
+
+    if (-not $recoveryDetected -and ($logText -match "enabling DHCP bypass|triggering recovery|No healthy")) {
+        Write-Host ""
+        Pass "🎯 Recovery flow triggered!"
+        $recoveryDetected = $true
+    }
+
+    if (-not $bypassActive -and ($logText -match "Recovery bypass active")) {
+        Pass "🔄 Recovery bypass forwarding to OS/DHCP resolver"
+        $bypassActive = $true
+    }
+
+    if ($recoveryDetected -and $result) {
+        Pass "✅ DNS resolves during recovery: example.com -> $($result[0].IPAddress)"
+        $dnsDuringBypass = $true
+        break
+    }
+
+    Start-Sleep -Seconds 2
+}
+
+# ── Phase 6: Show log entries ────────────────────────────────────────────────
+Write-Host ""
+Log "Phase 6: Recovery-related ctrld log entries"
+Log "────────────────────────────────────────────"
+$newLogs = Get-Content $CtrldLog | Select-Object -Skip $logLinesBefore
+$relevant = $newLogs | Where-Object { $_ -match "recovery|bypass|DHCP|unhealthy|upstream.*fail|No healthy|network change|OS resolver" }
+if ($relevant) {
+    $relevant | Select-Object -First 30 | ForEach-Object { Write-Host "  $_" }
+} else {
+    Warn "No recovery-related log entries found"
+    Get-Content $CtrldLog | Select-Object -Last 10 | ForEach-Object { Write-Host "  $_" }
+}
+
+# ── Phase 7: Unblock and verify ─────────────────────────────────────────────
+Write-Host ""
+Log "Phase 7: Removing firewall blocks"
+Get-NetFirewallRule -DisplayName "$FwRulePrefix*" -ErrorAction SilentlyContinue |
+    Remove-NetFirewallRule -ErrorAction SilentlyContinue
+$BlockedIPs = @()
+Pass "Firewall rules removed"
+
+Log "Waiting for recovery (up to 30s)..."
+$logLinesUnblock = (Get-Content $CtrldLog).Count
+$recoveryComplete = $false
+
+for ($i = 0; $i -lt 15; $i++) {
+    try { Resolve-DnsName example.com -Server 127.0.0.1 -Type A -DnsOnly -ErrorAction SilentlyContinue } catch {}
+    $postLogs = (Get-Content $CtrldLog | Select-Object -Skip $logLinesUnblock) -join "`n"
+    if ($postLogs -match "recovery complete|disabling DHCP bypass|Upstream.*recovered") {
+        $recoveryComplete = $true
+        Pass "ctrld recovered — normal operation resumed"
+        break
+    }
+    Start-Sleep -Seconds 2
+}
+
+if (-not $recoveryComplete) { Warn "Recovery completion not detected (may need more time)" }
+
+# ── Phase 8: Final check ────────────────────────────────────────────────────
+Write-Host ""
+Log "Phase 8: Final DNS verification"
+Start-Sleep -Seconds 2
+$final = Resolve-DnsName example.com -Server 127.0.0.1 -Type A -ErrorAction SilentlyContinue
+if ($final) {
+    Pass "DNS working: example.com -> $($final[0].IPAddress)"
+} else {
+    Fail "DNS not resolving"
+}
+
+# ── Summary ──────────────────────────────────────────────────────────────────
+Write-Host ""
+Log "═══════════════════════════════════════════════════════════"
+Log "  Test Summary"
+Log "═══════════════════════════════════════════════════════════"
+if ($recoveryDetected) { Pass "Recovery bypass activated" } else { Fail "Recovery bypass NOT activated" }
+if ($bypassActive)     { Pass "Queries forwarded to OS/DHCP" } else { Warn "OS resolver forwarding not confirmed" }
+if ($dnsDuringBypass)  { Pass "DNS resolved during bypass" } else { Warn "DNS during bypass not confirmed" }
+if ($recoveryComplete) { Pass "Normal operation resumed" } else { Warn "Recovery completion not confirmed" }
+if ($final)            { Pass "DNS functional at end of test" } else { Fail "DNS broken at end of test" }
+Write-Host ""
+Log "Full log: Get-Content $CtrldLog | Select-Object -Skip $logLinesBefore"
+
+# Cleanup runs via trap
+Cleanup

vpn_dns_config.go

@@ -0,0 +1,11 @@
+package ctrld
+
+// VPNDNSConfig represents DNS configuration discovered from a VPN interface.
+// Used by the dns-intercept mode to detect VPN split DNS settings and
+// route matching queries to VPN DNS servers automatically.
+type VPNDNSConfig struct {
+	InterfaceName string   // VPN adapter name (e.g., "F5 Networks VPN")
+	Servers       []string // DNS server IPs (e.g., ["10.20.30.1"])
+	Domains       []string // Search/match domains (e.g., ["corp.example.com"])
+	IsExitMode    bool     // True if this VPN is also the system default resolver (exit node mode)
+}

vpn_dns_darwin.go

@@ -0,0 +1,243 @@
+//go:build darwin
+
+package ctrld
+
+import (
+	"bufio"
+	"context"
+	"net"
+	"os/exec"
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+// DiscoverVPNDNS discovers DNS servers and search domains from VPN interfaces on macOS.
+// Parses `scutil --dns` output to find VPN resolver configurations.
+func DiscoverVPNDNS(ctx context.Context) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+
+	Log(ctx, logger.Debug(), "Discovering VPN DNS configurations on macOS")
+
+	cmd := exec.CommandContext(ctx, "scutil", "--dns")
+	output, err := cmd.Output()
+	if err != nil {
+		Log(ctx, logger.Error().Err(err), "Failed to execute scutil --dns")
+		return nil
+	}
+
+	return parseScutilOutput(ctx, string(output))
+}
+
+// parseScutilOutput parses the output of `scutil --dns` to extract VPN DNS configurations.
+func parseScutilOutput(ctx context.Context, output string) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+
+	Log(ctx, logger.Debug(), "Parsing scutil --dns output")
+
+	resolverBlockRe := regexp.MustCompile(`resolver #(\d+)`)
+	searchDomainRe := regexp.MustCompile(`search domain\[\d+\] : (.+)`)
+	// Matches singular "domain : value" entries (e.g., Tailscale per-domain resolvers).
+	singleDomainRe := regexp.MustCompile(`^domain\s+:\s+(.+)`)
+	nameserverRe := regexp.MustCompile(`nameserver\[\d+\] : (.+)`)
+	ifIndexRe := regexp.MustCompile(`if_index : (\d+) \((.+)\)`)
+
+	var vpnConfigs []VPNDNSConfig
+	var currentResolver *resolverInfo
+	var allResolvers []resolverInfo
+
+	scanner := bufio.NewScanner(strings.NewReader(output))
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+
+		if match := resolverBlockRe.FindStringSubmatch(line); match != nil {
+			if currentResolver != nil {
+				allResolvers = append(allResolvers, *currentResolver)
+			}
+			resolverNum, _ := strconv.Atoi(match[1])
+			currentResolver = &resolverInfo{
+				Number: resolverNum,
+			}
+			continue
+		}
+
+		if currentResolver == nil {
+			continue
+		}
+
+		if match := searchDomainRe.FindStringSubmatch(line); match != nil {
+			domain := strings.TrimSpace(match[1])
+			if domain != "" {
+				currentResolver.Domains = append(currentResolver.Domains, domain)
+			}
+			continue
+		}
+
+		// Parse singular "domain : value" (used by Tailscale per-domain resolvers).
+		if match := singleDomainRe.FindStringSubmatch(line); match != nil {
+			domain := strings.TrimSpace(match[1])
+			if domain != "" {
+				currentResolver.Domains = append(currentResolver.Domains, domain)
+			}
+			continue
+		}
+
+		if match := nameserverRe.FindStringSubmatch(line); match != nil {
+			server := strings.TrimSpace(match[1])
+			if ip := net.ParseIP(server); ip != nil && !ip.IsLoopback() {
+				currentResolver.Servers = append(currentResolver.Servers, server)
+			}
+			continue
+		}
+
+		if match := ifIndexRe.FindStringSubmatch(line); match != nil {
+			currentResolver.InterfaceName = strings.TrimSpace(match[2])
+			continue
+		}
+
+		if strings.HasPrefix(line, "flags") {
+			if idx := strings.Index(line, ":"); idx >= 0 {
+				currentResolver.Flags = strings.TrimSpace(line[idx+1:])
+			}
+			continue
+		}
+	}
+
+	if currentResolver != nil {
+		allResolvers = append(allResolvers, *currentResolver)
+	}
+
+	for _, resolver := range allResolvers {
+		if isSplitDNSResolver(ctx, &resolver) {
+			ifaceName := resolver.InterfaceName
+
+			// When scutil doesn't provide if_index (common with Tailscale MagicDNS
+			// per-domain resolvers), look up the outbound interface from the routing
+			// table. This is needed for interface-scoped pf exemptions — without the
+			// interface name, we can't generate rules that let the VPN's Network
+			// Extension handle DNS queries from all processes.
+			if ifaceName == "" && len(resolver.Servers) > 0 {
+				if routeIface := resolveInterfaceForIP(ctx, resolver.Servers[0]); routeIface != "" {
+					ifaceName = routeIface
+					Log(ctx, logger.Debug(), "Resolver #%d: resolved interface %q from routing table for %s",
+						resolver.Number, routeIface, resolver.Servers[0])
+				}
+			}
+
+			config := VPNDNSConfig{
+				InterfaceName: ifaceName,
+				Servers:       resolver.Servers,
+				Domains:       resolver.Domains,
+			}
+
+			vpnConfigs = append(vpnConfigs, config)
+
+			Log(ctx, logger.Debug(), "Found VPN DNS config - Interface: %s, Servers: %v, Domains: %v",
+				config.InterfaceName, config.Servers, config.Domains)
+		}
+	}
+
+	// Detect exit mode: if a VPN DNS server IP also appears as the system's default
+	// resolver (no search domains, no Supplemental flag), the VPN is routing ALL traffic
+	// (not just specific domains). In exit mode, ctrld must continue intercepting DNS
+	// on the VPN interface to enforce its profile on all queries.
+	defaultResolverIPs := make(map[string]bool)
+	for _, resolver := range allResolvers {
+		if len(resolver.Servers) > 0 && len(resolver.Domains) == 0 &&
+			!strings.Contains(resolver.Flags, "Supplemental") &&
+			!strings.Contains(resolver.Flags, "Scoped") {
+			for _, server := range resolver.Servers {
+				defaultResolverIPs[server] = true
+			}
+		}
+	}
+	for i := range vpnConfigs {
+		for _, server := range vpnConfigs[i].Servers {
+			if defaultResolverIPs[server] {
+				vpnConfigs[i].IsExitMode = true
+				Log(ctx, logger.Info(), "VPN DNS config on %s detected as EXIT MODE — server %s is also the system default resolver",
+					vpnConfigs[i].InterfaceName, server)
+				break
+			}
+		}
+	}
+
+	Log(ctx, logger.Debug(), "VPN DNS discovery completed: found %d VPN interfaces", len(vpnConfigs))
+	return vpnConfigs
+}
+
+// resolveInterfaceForIP uses the macOS routing table to determine which network
+// interface would be used to reach the given IP address. This is a fallback for
+// when scutil --dns doesn't include if_index in the resolver entry (common with
+// Tailscale MagicDNS per-domain resolvers).
+//
+// Runs: route -n get <ip> and parses the "interface:" line from the output.
+// Returns empty string on any error (callers should treat as "unknown interface").
+func resolveInterfaceForIP(ctx context.Context, ip string) string {
+	logger := *ProxyLogger.Load()
+
+	cmd := exec.CommandContext(ctx, "route", "-n", "get", ip)
+	output, err := cmd.Output()
+	if err != nil {
+		Log(ctx, logger.Debug(), "route -n get %s failed: %v", ip, err)
+		return ""
+	}
+
+	// Parse "interface: utun11" from route output.
+	for _, line := range strings.Split(string(output), "\n") {
+		line = strings.TrimSpace(line)
+		if strings.HasPrefix(line, "interface:") {
+			iface := strings.TrimSpace(strings.TrimPrefix(line, "interface:"))
+			if iface != "" && iface != "lo0" {
+				return iface
+			}
+		}
+	}
+	return ""
+}
+
+type resolverInfo struct {
+	Number        int
+	InterfaceName string
+	Servers       []string
+	Domains       []string
+	Flags         string // Raw flags line (e.g., "Supplemental, Request A records")
+}
+
+// isSplitDNSResolver reports whether a scutil --dns resolver entry represents a
+// split DNS configuration that ctrld should forward to. Any resolver with both
+// non-loopback DNS servers and search domains qualifies — this covers VPN adapters
+// (F5, Tailscale, Cisco AnyConnect, etc.) and any other virtual interface that
+// registers search domains (e.g., corporate proxies, containers).
+//
+// We intentionally avoid heuristics about interface names or domain suffixes:
+// if an interface declares "these domains resolve via these servers," we honor it.
+// The only exclusions are mDNS entries (bare ".local" without an interface binding).
+//
+// Note: loopback servers are already filtered out during parsing in parseScutilOutput.
+func isSplitDNSResolver(ctx context.Context, resolver *resolverInfo) bool {
+	logger := *ProxyLogger.Load()
+
+	// Must have both DNS servers and search domains to be a useful split DNS route.
+	if len(resolver.Servers) == 0 || len(resolver.Domains) == 0 {
+		Log(ctx, logger.Debug(), "Resolver #%d: skipping — no servers (%d) or no domains (%d)",
+			resolver.Number, len(resolver.Servers), len(resolver.Domains))
+		return false
+	}
+
+	// Skip multicast DNS entries. scutil --dns shows a resolver for ".local" that
+	// handles mDNS — it has no interface binding and the sole domain is "local".
+	// Real VPN entries with ".local" suffix (e.g., "corp.example.com") will have an
+	// interface name or additional domains.
+	if len(resolver.Domains) == 1 {
+		domain := strings.ToLower(strings.TrimSpace(resolver.Domains[0]))
+		if domain == "local" || domain == ".local" {
+			Log(ctx, logger.Debug(), "Resolver #%d: skipping — mDNS resolver", resolver.Number)
+			return false
+		}
+	}
+
+	Log(ctx, logger.Debug(), "Resolver #%d: split DNS resolver — interface: %q, servers: %v, domains: %v",
+		resolver.Number, resolver.InterfaceName, resolver.Servers, resolver.Domains)
+	return true
+}

vpn_dns_linux.go

@@ -0,0 +1,211 @@
+//go:build linux
+
+package ctrld
+
+import (
+	"bufio"
+	"context"
+	"net"
+	"os/exec"
+	"regexp"
+	"strings"
+)
+
+// DiscoverVPNDNS discovers DNS servers and search domains from VPN interfaces on Linux.
+// Uses resolvectl status to find per-link DNS configurations.
+func DiscoverVPNDNS(ctx context.Context) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+
+	Log(ctx, logger.Debug(), "Discovering VPN DNS configurations on Linux")
+
+	if configs := parseResolvectlStatus(ctx); len(configs) > 0 {
+		return configs
+	}
+
+	Log(ctx, logger.Debug(), "resolvectl not available or no results, trying fallback method")
+	return parseVPNInterfacesDNS(ctx)
+}
+
+func parseResolvectlStatus(ctx context.Context) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+
+	cmd := exec.CommandContext(ctx, "resolvectl", "status")
+	output, err := cmd.Output()
+	if err != nil {
+		Log(ctx, logger.Debug(), "Failed to execute resolvectl status: %v", err)
+		return nil
+	}
+
+	Log(ctx, logger.Debug(), "Parsing resolvectl status output")
+
+	linkRe := regexp.MustCompile(`^Link (\d+) \((.+)\):`)
+	dnsServersRe := regexp.MustCompile(`^\s+DNS Servers?: (.+)`)
+	dnsDomainsRe := regexp.MustCompile(`^\s+DNS Domain: (.+)`)
+
+	var vpnConfigs []VPNDNSConfig
+	var currentLink *linkInfo
+
+	scanner := bufio.NewScanner(strings.NewReader(string(output)))
+	for scanner.Scan() {
+		line := scanner.Text()
+
+		if match := linkRe.FindStringSubmatch(line); match != nil {
+			if currentLink != nil && isVPNLink(ctx, currentLink) {
+				config := VPNDNSConfig{
+					InterfaceName: currentLink.InterfaceName,
+					Servers:       currentLink.Servers,
+					Domains:       currentLink.Domains,
+				}
+				vpnConfigs = append(vpnConfigs, config)
+
+				Log(ctx, logger.Debug(), "Found VPN DNS config - Interface: %s, Servers: %v, Domains: %v",
+					config.InterfaceName, config.Servers, config.Domains)
+			}
+
+			currentLink = &linkInfo{
+				InterfaceName: strings.TrimSpace(match[2]),
+			}
+			continue
+		}
+
+		if currentLink == nil {
+			continue
+		}
+
+		if match := dnsServersRe.FindStringSubmatch(line); match != nil {
+			serverList := strings.TrimSpace(match[1])
+			for _, server := range strings.Fields(serverList) {
+				if ip := net.ParseIP(server); ip != nil && !ip.IsLoopback() {
+					currentLink.Servers = append(currentLink.Servers, server)
+				}
+			}
+			continue
+		}
+
+		if match := dnsDomainsRe.FindStringSubmatch(line); match != nil {
+			domainList := strings.TrimSpace(match[1])
+			for _, domain := range strings.Fields(domainList) {
+				domain = strings.TrimSpace(domain)
+				if domain != "" {
+					currentLink.Domains = append(currentLink.Domains, domain)
+				}
+			}
+			continue
+		}
+	}
+
+	if currentLink != nil && isVPNLink(ctx, currentLink) {
+		config := VPNDNSConfig{
+			InterfaceName: currentLink.InterfaceName,
+			Servers:       currentLink.Servers,
+			Domains:       currentLink.Domains,
+		}
+		vpnConfigs = append(vpnConfigs, config)
+
+		Log(ctx, logger.Debug(), "Found VPN DNS config - Interface: %s, Servers: %v, Domains: %v",
+			config.InterfaceName, config.Servers, config.Domains)
+	}
+
+	Log(ctx, logger.Debug(), "resolvectl parsing completed: found %d VPN interfaces", len(vpnConfigs))
+	return vpnConfigs
+}
+
+func parseVPNInterfacesDNS(ctx context.Context) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+
+	Log(ctx, logger.Debug(), "Using fallback method to detect VPN DNS")
+
+	interfaces, err := net.Interfaces()
+	if err != nil {
+		Log(ctx, logger.Error().Err(err), "Failed to get network interfaces")
+		return nil
+	}
+
+	var vpnConfigs []VPNDNSConfig
+
+	for _, iface := range interfaces {
+		if !isVPNInterfaceName(iface.Name) {
+			continue
+		}
+		if iface.Flags&net.FlagUp == 0 {
+			continue
+		}
+
+		Log(ctx, logger.Debug(), "Found potential VPN interface: %s", iface.Name)
+		Log(ctx, logger.Debug(), "Fallback DNS detection not implemented for interface: %s", iface.Name)
+	}
+
+	Log(ctx, logger.Debug(), "Fallback method completed: found %d VPN interfaces", len(vpnConfigs))
+	return vpnConfigs
+}
+
+type linkInfo struct {
+	InterfaceName string
+	Servers       []string
+	Domains       []string
+}
+
+func isVPNLink(ctx context.Context, link *linkInfo) bool {
+	logger := *ProxyLogger.Load()
+
+	if len(link.Servers) == 0 || len(link.Domains) == 0 {
+		Log(ctx, logger.Debug(), "Link %s: insufficient config (servers: %d, domains: %d)",
+			link.InterfaceName, len(link.Servers), len(link.Domains))
+		return false
+	}
+
+	if isVPNInterfaceName(link.InterfaceName) {
+		Log(ctx, logger.Debug(), "Link %s: identified as VPN based on interface name", link.InterfaceName)
+		return true
+	}
+
+	hasRoutingDomain := false
+	for _, domain := range link.Domains {
+		if strings.HasPrefix(domain, "~") {
+			hasRoutingDomain = true
+			break
+		}
+	}
+
+	if hasRoutingDomain {
+		Log(ctx, logger.Debug(), "Link %s: identified as VPN based on routing domain", link.InterfaceName)
+		return true
+	}
+
+	hasPrivateDNS := false
+	for _, server := range link.Servers {
+		if ip := net.ParseIP(server); ip != nil && ip.IsPrivate() {
+			hasPrivateDNS = true
+			break
+		}
+	}
+
+	hasVPNDomains := false
+	for _, domain := range link.Domains {
+		domain = strings.ToLower(strings.TrimPrefix(domain, "~"))
+		if strings.HasSuffix(domain, ".local") ||
+			strings.HasSuffix(domain, ".corp") ||
+			strings.HasSuffix(domain, ".internal") ||
+			strings.Contains(domain, "vpn") {
+			hasVPNDomains = true
+			break
+		}
+	}
+
+	if hasPrivateDNS && hasVPNDomains {
+		Log(ctx, logger.Debug(), "Link %s: identified as VPN based on private DNS + VPN domains", link.InterfaceName)
+		return true
+	}
+
+	Log(ctx, logger.Debug(), "Link %s: not identified as VPN link", link.InterfaceName)
+	return false
+}
+
+func isVPNInterfaceName(name string) bool {
+	name = strings.ToLower(name)
+	return strings.HasPrefix(name, "tun") ||
+		strings.HasPrefix(name, "tap") ||
+		strings.HasPrefix(name, "ppp") ||
+		strings.HasPrefix(name, "vpn") ||
+		strings.Contains(name, "vpn")
+}

vpn_dns_others.go

@@ -0,0 +1,15 @@
+//go:build !windows && !darwin && !linux
+
+package ctrld
+
+import (
+	"context"
+)
+
+// DiscoverVPNDNS is a stub implementation for unsupported platforms.
+// Returns nil to indicate no VPN DNS configurations found.
+func DiscoverVPNDNS(ctx context.Context) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+	Log(ctx, logger.Debug(), "VPN DNS discovery not implemented for this platform")
+	return nil
+}

vpn_dns_windows.go

@@ -0,0 +1,130 @@
+//go:build windows
+
+package ctrld
+
+import (
+	"context"
+	"strings"
+	"syscall"
+
+	"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
+)
+
+// DiscoverVPNDNS discovers DNS servers and search domains from non-physical (VPN) interfaces.
+// Only called when dnsIntercept is active.
+func DiscoverVPNDNS(ctx context.Context) []VPNDNSConfig {
+	logger := *ProxyLogger.Load()
+
+	Log(ctx, logger.Debug(), "Discovering VPN DNS configurations on Windows")
+
+	flags := winipcfg.GAAFlagIncludeGateways | winipcfg.GAAFlagIncludePrefix
+	aas, err := winipcfg.GetAdaptersAddresses(syscall.AF_UNSPEC, flags)
+	if err != nil {
+		Log(ctx, logger.Error().Err(err), "Failed to get adapters addresses")
+		return nil
+	}
+
+	Log(ctx, logger.Debug(), "Found %d network adapters", len(aas))
+
+	// Get valid (physical/hardware) interfaces to filter them out
+	validInterfacesMap := validInterfaces()
+
+	var vpnConfigs []VPNDNSConfig
+
+	for _, aa := range aas {
+		if aa.OperStatus != winipcfg.IfOperStatusUp {
+			Log(ctx, logger.Debug(), "Skipping adapter %s - not up, status: %d",
+				aa.FriendlyName(), aa.OperStatus)
+			continue
+		}
+
+		if aa.IfType == winipcfg.IfTypeSoftwareLoopback {
+			Log(ctx, logger.Debug(), "Skipping %s (software loopback)", aa.FriendlyName())
+			continue
+		}
+
+		// INVERT the validInterfaces filter: we want non-physical/non-hardware adapters
+		_, isValidPhysical := validInterfacesMap[aa.FriendlyName()]
+		if isValidPhysical {
+			Log(ctx, logger.Debug(), "Skipping %s (physical/hardware adapter)", aa.FriendlyName())
+			continue
+		}
+
+		// Skip adapters that have no routable unicast addresses. An adapter
+		// with only link-local (fe80::) or APIPA (169.254.x.x) addresses is
+		// not actually connected — its DNS servers are stale. This prevents
+		// picking up e.g. Tailscale's adapter when the app is installed but
+		// disconnected (OperStatus reports Up but only APIPA addresses exist).
+		hasRoutableAddr := false
+		for a := aa.FirstUnicastAddress; a != nil; a = a.Next {
+			ip := a.Address.IP()
+			if ip == nil {
+				continue
+			}
+			if !ip.IsLinkLocalUnicast() {
+				hasRoutableAddr = true
+				break
+			}
+		}
+		if !hasRoutableAddr {
+			Log(ctx, logger.Debug(), "Skipping %s - no routable addresses (likely disconnected)", aa.FriendlyName())
+			continue
+		}
+
+		var servers []string
+		for dns := aa.FirstDNSServerAddress; dns != nil; dns = dns.Next {
+			ip := dns.Address.IP()
+			if ip == nil {
+				continue
+			}
+
+			ipStr := ip.String()
+			if ip.IsLoopback() {
+				continue
+			}
+
+			servers = append(servers, ipStr)
+		}
+
+		// Check adapter-specific (connection-specific) DNS suffix first,
+		// since we want to map per-adapter DNS servers to per-adapter suffixes.
+		// This is what most traditional VPNs set (F5, Cisco AnyConnect, GlobalProtect).
+		var domains []string
+		if connSuffix := strings.TrimSpace(aa.DNSSuffix()); connSuffix != "" {
+			domains = append(domains, connSuffix)
+			Log(ctx, logger.Debug(), "Using connection-specific DNS suffix for %s: %s",
+				aa.FriendlyName(), connSuffix)
+		}
+
+		// Then check supplemental DNS suffix list (used by Tailscale and
+		// VPN clients that register search domains via the DNS Client API).
+		for suffix := aa.FirstDNSSuffix; suffix != nil; suffix = suffix.Next {
+			domain := strings.TrimSpace(suffix.String())
+			if domain != "" {
+				domains = append(domains, domain)
+			}
+		}
+
+		// Accept VPN adapters with DNS servers even without domains.
+		// Domain-less configs still provide useful DNS server IPs that
+		// can serve existing split-rules and OS resolver queries.
+		if len(servers) > 0 {
+			config := VPNDNSConfig{
+				InterfaceName: aa.FriendlyName(),
+				Servers:       servers,
+				Domains:       domains,
+			}
+
+			vpnConfigs = append(vpnConfigs, config)
+
+			Log(ctx, logger.Debug(), "Found VPN DNS config - Interface: %s, Servers: %v, Domains: %v",
+				config.InterfaceName, config.Servers, config.Domains)
+		} else {
+			Log(ctx, logger.Debug(), "Skipping %s - no DNS servers found",
+				aa.FriendlyName())
+		}
+	}
+
+	Log(ctx, logger.Debug(), "VPN DNS discovery completed: found %d VPN interfaces", len(vpnConfigs))
+	return vpnConfigs
+}