[client] Resume peer reconnection when the network comes back

Ticks taken while the OS reported no network were skipped, but they still
advanced the exponential backoff, so a peer could be tens of seconds from its
next attempt by the time connectivity returned. Recovery then depended on a
signal or relay event, which never arrives when both stayed up across the
outage, e.g. a short airplane mode toggle over Wi-Fi. A peer parked in ICE
hourly mode stayed there for the same reason.

React to the offline-to-online transition directly: re-arm the reconnect
ticker and reset the ICE retry state, so the peer retries at once. Add
netstate.Changed for callers that own a select loop and cannot block in Wait.

client/internal/peer/guard/guard.go

@@ -104,12 +104,13 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 	iceState := &iceRetryState{log: g.log}
 	defer iceState.reset()
 
+	netChanged := g.netState.Changed()
+
 	for {
 		select {
 		case <-tickerChannel:
-			// skip attempts while the OS reports no usable network; the ticker
-			// keeps running so other events remain responsive, and the guard
-			// resumes via the signal/relay reconnect events once network returns
+			// skip attempts while the OS reports no usable network; the
+			// netChanged case below resumes the loop once it returns
 			if !g.netState.IsOnline() {
 				continue
 			}
@@ -149,6 +150,23 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 			tickerChannel = ticker.C
 			iceState.reset()
 
+		case <-netChanged:
+			// Re-arm for the next transition before acting on this one.
+			netChanged = g.netState.Changed()
+			if !g.netState.IsOnline() {
+				continue
+			}
+			// Ticks skipped while offline drove the backoff towards its
+			// maximum without ever attempting, and left the ICE budget
+			// frozen — possibly in hourly mode. Recover on our own so the
+			// peer does not depend on a signal or relay event that never
+			// comes when both stayed up across the outage.
+			g.log.Debugf("network is back, reset reconnection ticker")
+			ticker.Stop()
+			ticker = g.newReconnectTicker(ctx)
+			tickerChannel = ticker.C
+			iceState.reset()
+
 		case <-ctx.Done():
 			g.log.Debugf("context is done, stop reconnect loop")
 			return

client/internal/peer/guard/guard_netstate_test.go

@@ -0,0 +1,98 @@
+package guard
+
+import (
+	"context"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the
+// backoff must be able to grow well past the outage, as it does in production
+// where the timeout is seconds to minutes.
+func newTestGuardWithNetState(status connStatusFunc, netState *netstate.State) *Guard {
+	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
+	return NewGuard(log.WithField("test", "guard"), status, 30*time.Second, srw, netState)
+}
+
+// TestGuard_RecoversAfterOfflineToOnline covers a peer that stays disconnected
+// across a network outage while neither signal nor relay reports an event —
+// both stayed up, as on a short airplane mode toggle over Wi-Fi.
+//
+// Every tick taken while offline is skipped, but it still advances the
+// exponential backoff, so by the time the network returns the next tick can be
+// tens of seconds away. Without an explicit reaction to the transition the
+// peer waits out that interval for a recovery that could start immediately.
+func TestGuard_RecoversAfterOfflineToOnline(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	// Start from the reconnect ticker (800ms initial interval), the state a
+	// peer is in after it loses its connection.
+	go g.Start(ctx, func() { attempts.Add(1) })
+	g.SetRelayedConnDisconnected()
+
+	// Let the backoff climb: 0.8s, 1.6s, 3.2s, 6.4s ... every tick is skipped
+	// while offline, but each one doubles the wait for the next.
+	netState.Set(false)
+	time.Sleep(8 * time.Second)
+
+	offlineAttempts := attempts.Load()
+	if offlineAttempts != 0 {
+		t.Fatalf("callback ran %d times while offline, want 0", offlineAttempts)
+	}
+
+	netState.Set(true)
+
+	// The next organic tick is now several seconds out, so anything within
+	// this window can only come from reacting to the transition itself.
+	select {
+	case <-time.After(2 * time.Second):
+		t.Fatal("peer was not retried within 2s of the network coming back, " +
+			"with neither a signal nor a relay event to fall back on")
+	case <-pollUntil(func() bool { return attempts.Load() > 0 }):
+	}
+}
+
+// TestGuard_OfflineTransitionDoesNotRetry checks the other direction: going
+// offline must not itself trigger an attempt.
+func TestGuard_OfflineTransitionDoesNotRetry(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go g.Start(ctx, func() { attempts.Add(1) })
+
+	netState.Set(false)
+	time.Sleep(5 * time.Second)
+
+	if got := attempts.Load(); got != 0 {
+		t.Fatalf("callback ran %d times after going offline, want 0", got)
+	}
+}
+
+func pollUntil(cond func() bool) <-chan struct{} {
+	done := make(chan struct{})
+	go func() {
+		for {
+			if cond() {
+				close(done)
+				return
+			}
+			time.Sleep(10 * time.Millisecond)
+		}
+	}()
+	return done
+}

client/netstate/netstate.go

@@ -61,6 +61,20 @@ func (s *State) IsOnline() bool {
 	return s.online
 }
 
+// Changed returns a channel closed on the next availability transition, for
+// callers that already own a select loop and cannot block in Wait. Re-read it
+// after every fire: each transition installs a fresh channel. On a nil
+// receiver — no State injected — it returns nil, which blocks forever in a
+// select, so the caller simply never observes a transition.
+func (s *State) Changed() <-chan struct{} {
+	if s == nil {
+		return nil
+	}
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.changed
+}
+
 // Wait blocks while the network is offline. It reports whether it had to
 // wait, so callers can reset their backoff after an outage. It returns early
 // with the context error when ctx is done. On a nil receiver — no State