hub 0.166.0 source: the clock-ahead tunnel alarm wg_tunnel_stale/ok (R-1204, operator-only, edge-triggered); D21 + D4 proof evidence

hub/internal/api/host_tunnel_test.go

@@ -0,0 +1,78 @@
+package api
+
+import (
+	"net/http"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.dooplex.hu/admin/felhom-hub/internal/store"
+)
+
+// R-1204: the box's tunnel to ep0 — a future-stamped handshake (the clock ran ahead) or no handshake for 6 h raises
+// wg_tunnel_stale ONCE (edge-triggered from the host's newest tunnel event), and wg_tunnel_ok once when healthy; a
+// healthy tunnel, an inactive one and an older agent are not judged.
+// RED-PROOF: with checkWGTunnel not called from the host-report handler the first count fails (0 events); with
+// wgTunnelStale ignoring handshake_future_s the clock case fails — seen failing 2026-10-22.
+func tunnelReportBody(hostID, wg string) string {
+	b := validReportBody(hostID)
+	i := strings.LastIndex(b, "}")
+	return b[:i] + `,"wireguard":` + wg + b[i:]
+}
+
+func TestR1204_TheClockAheadTunnelAlarmsOnceAndClears(t *testing.T) {
+	h, st, _ := newTestHandler(t)
+	st.SaveCustomerConfig(&store.CustomerConfig{CustomerID: "c1", APIKey: "ckey", RetrievalPassword: "p"})
+	st.UpsertHost(&store.Host{HostID: "h1", CustomerID: "c1", APIKey: "HKEY"})
+	post := func(wg string) {
+		t.Helper()
+		if rr := do(h, http.MethodPost, "/host-report", "HKEY", tunnelReportBody("h1", wg)); rr.Code != http.StatusOK {
+			t.Fatalf("host-report = %d %s", rr.Code, rr.Body.String())
+		}
+	}
+	count := func(typ string) int {
+		evs, _ := st.GetEventsByType("c1", typ, time.Time{})
+		return len(evs)
+	}
+	post(`{"registered":true,"active":true,"last_handshake_age_s":60}`) // healthy
+	post(`{"registered":true,"active":false}`)                          // service down: not judged here
+	if count(eventWGTunnelStale) != 0 {
+		t.Fatal("a healthy or inactive tunnel must not alarm")
+	}
+	post(`{"registered":true,"active":true,"last_handshake_age_s":0,"handshake_future_s":63072000}`) // ran 2 years ahead
+	post(`{"registered":true,"active":true,"last_handshake_age_s":0,"handshake_future_s":63071100}`)
+	if n := count(eventWGTunnelStale); n != 1 {
+		t.Fatalf("wg_tunnel_stale = %d, want exactly 1 (edge-triggered)", n)
+	}
+	evs, _ := st.GetEventsByType("c1", eventWGTunnelStale, time.Time{})
+	if !strings.Contains(evs[0].Message, "Host h1:") || !strings.Contains(evs[0].Message, "FUTURE") {
+		t.Fatalf("the alarm must name the host and the clock cause: %q", evs[0].Message)
+	}
+	post(`{"registered":true,"active":true,"last_handshake_age_s":45}`)
+	post(`{"registered":true,"active":true,"last_handshake_age_s":50}`)
+	if count(eventWGTunnelOK) != 1 {
+		t.Fatalf("wg_tunnel_ok = %d, want 1", count(eventWGTunnelOK))
+	}
+	post(`{"registered":true,"active":true,"last_handshake_age_s":30000}`) // 8 h 20 min with no handshake
+	if count(eventWGTunnelStale) != 2 {
+		t.Fatal("six hours without a handshake while reporting must alarm again")
+	}
+}
+
+func TestR1204_WhatIsJudged(t *testing.T) {
+	i := func(v int64) *int64 { return &v }
+	for _, c := range []struct {
+		w    *hostWireguard
+		want bool
+	}{
+		{nil, false},
+		{&hostWireguard{Registered: true, Active: true, LastHandshakeAgeS: i(120)}, false},
+		{&hostWireguard{Registered: true, Active: true, LastHandshakeAgeS: i(6*3600 + 1)}, true},
+		{&hostWireguard{Registered: true, Active: true, LastHandshakeAgeS: i(0), HandshakeFutureS: i(3600)}, true},
+		{&hostWireguard{Registered: false, Active: true, LastHandshakeAgeS: i(99999)}, false},
+	} {
+		if got, _ := wgTunnelStale(c.w); got != c.want {
+			t.Errorf("%+v: stale=%t, want %t", c.w, got, c.want)
+		}
+	}
+}