From 7181675c4a78cfa18fde9b294af789659b1fbb0e Mon Sep 17 00:00:00 2001
From: jochens <jschoubben@gmail.com>
Date: Fri, 2 Oct 2026 18:15:11 +0200
Subject: [PATCH] A joining machine dials the bus once the hub has answered its
 tunnel

Issuing the token sends the hub its new peer, and the hub applies it on
its own time; a bus dialled before then timed out naming the bus. The
first tunnel now waits for a handshake with the hub, and says so in the
tunnel's words when there is none (novox/hq ADR 0169).
---
 cmd/mesh-host/join_tunnel.go      | 36 ++++++++++++++++++++++++++++++-
 cmd/mesh-host/join_tunnel_test.go | 27 +++++++++++++++++++++++
 2 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/cmd/mesh-host/join_tunnel.go b/cmd/mesh-host/join_tunnel.go
index d72c64a..3a20318 100644
--- a/cmd/mesh-host/join_tunnel.go
+++ b/cmd/mesh-host/join_tunnel.go
@@ -8,6 +8,7 @@ import (
 	"os/exec"
 	"path/filepath"
 	"strings"
+	"time"
 
 	"github.com/novox/mesh-host/internal/apply"
 	"github.com/novox/mesh-host/internal/identity"
@@ -115,5 +116,38 @@ func bringTheTunnelUp(ctx context.Context, t *identity.TokenTunnel, keyPath stri
 		return fmt.Errorf("the first tunnel would not start (%s): %v %s", tunnelUnit, err, strings.TrimSpace(out))
 	}
 	fmt.Printf("the tunnel to the hub is up: %s, through %s\n", t.Address, t.HubEndpoint)
-	return nil
+	return waitForTheHub(ctx, run, handshakeWithin)
+}
+
+// handshakeWithin is how long the hub has to answer the first tunnel. Issuing the token sent the hub
+// this machine as a peer; the hub applies that on its own time, and a bus dialled before it has is a
+// timeout that names the bus rather than the tunnel.
+var handshakeWithin = 90 * time.Second
+
+// waitForTheHub waits until the tunnel has shaken hands with the hub, so the bus is dialled over a
+// tunnel that answers — and says so in the tunnel's own words when it does not.
+func waitForTheHub(ctx context.Context, run apply.Runner, within time.Duration) error {
+	deadline := time.Now().Add(within)
+	for {
+		out, err := run(ctx, "wg", "show", "mesh0", "latest-handshakes")
+		if err == nil {
+			for _, line := range strings.Split(strings.TrimSpace(out), "\n") {
+				fields := strings.Fields(line)
+				if len(fields) == 2 && fields[1] != "0" {
+					fmt.Println("the hub answered the tunnel")
+					return nil
+				}
+			}
+		}
+		if time.Now().After(deadline) {
+			return fmt.Errorf("the hub has not answered the tunnel in %s: the token may be another machine's, "+
+				"the hub may not have been sent this machine as a peer, or its tunnel's port is not reachable "+
+				"from here", within)
+		}
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-time.After(2 * time.Second):
+		}
+	}
 }
diff --git a/cmd/mesh-host/join_tunnel_test.go b/cmd/mesh-host/join_tunnel_test.go
index 146fc7e..6f6757b 100644
--- a/cmd/mesh-host/join_tunnel_test.go
+++ b/cmd/mesh-host/join_tunnel_test.go
@@ -7,6 +7,7 @@ import (
 	"path/filepath"
 	"strings"
 	"testing"
+	"time"
 
 	"github.com/novox/mesh-host/internal/identity"
 )
@@ -67,6 +68,9 @@ func TestTheFirstTunnelIsTheMeshsInterfaceWithTheHubAsItsPeer(t *testing.T) {
 	t.Cleanup(func() { tunnelConfigPath = "/etc/wireguard/mesh0.conf" })
 	var ran []string
 	run := func(_ context.Context, name string, args ...string) (string, error) {
+		if name == "wg" {
+			return "HUBKEY\t1759400000\n", nil
+		}
 		ran = append(ran, name+" "+strings.Join(args, " "))
 		return "", nil
 	}
@@ -110,3 +114,26 @@ func captureStdout(t *testing.T, fn func()) string {
 	out, _ := io.ReadAll(r)
 	return string(out)
 }
+
+// The bus is dialled only once the hub has answered the tunnel, and a hub that never does is said
+// as the tunnel's fault rather than the bus's.
+func TestTheBusWaitsForTheHubToAnswer(t *testing.T) {
+	asked := 0
+	answersOnThird := func(_ context.Context, name string, args ...string) (string, error) {
+		asked++
+		if asked < 3 {
+			return "HUBKEY\t0\n", nil
+		}
+		return "HUBKEY\t1759400000\n", nil
+	}
+	captureStdout(t, func() {
+		if err := waitForTheHub(context.Background(), answersOnThird, time.Minute); err != nil {
+			t.Fatal(err)
+		}
+	})
+	never := func(context.Context, string, ...string) (string, error) { return "HUBKEY\t0\n", nil }
+	err := waitForTheHub(context.Background(), never, 0)
+	if err == nil || !strings.Contains(err.Error(), "has not answered the tunnel") {
+		t.Fatalf("a hub that never answered was not said: %v", err)
+	}
+}