watcher: follow a watched name's CNAME for port and TLS checks (closes #203)

When a watched name's nameservers answer with a CNAME and no address,
the DNS check asks ResolveIPAddresses for the name, which looks it up
again and follows the chain, and saves the addresses at its end in the
hostname state as cnameAddresses. The port and TLS checks use them.
Before, only the A and AAAA records in the answers were used, so a
CNAME into another zone got no port or TLS checks. When following
fails, the addresses the last check saved are kept. The domain check
now runs the hostname check for the apex instead of a copy of it.

Model: opus-5-5

README.md

@@ -121,22 +121,15 @@ notification endpoint set, changes show only on the dashboard; see
       failed on it, and answers differently is reported on the check where it
       answers. If a pair agrees again and later disagrees, the alert is sent
       again.
-    - **CNAME address change**: For a name whose nameservers answer with a CNAME
-      and no address, the addresses at the end of its CNAME chain differ from
-      those of the previous check, including when there are none now. Nothing is
-      sent when the previous check saved none, or when the previous addresses
-      were kept because the chain could not be followed or none of the name's
-      nameservers answered.
 
 ### TCP Port Monitoring
 
 - For every configured domain and hostname, constructs a deduplicated list of
   the IPv4 and IPv6 addresses in the A and AAAA records its authoritative
   nameservers returned. When they returned a CNAME and no address, the CNAME
-  chain is followed and the addresses at its end are used, and a change in those
-  is notified as a CNAME address change. When the chain cannot be followed, or
-  none of the name's nameservers answered, the addresses the last check found at
-  its end are used.
+  chain is followed and the addresses at its end are used; a change in those
+  sends no notification of its own. When the chain cannot be followed, the
+  addresses the last check found at its end are used.
 - Checks TCP connectivity on ports **80** and **443** for each IP address.
 - Every **1 hour**, re-checks all ports.
 - Any change in port availability triggers a notification:
@@ -183,8 +176,6 @@ includes:
 - **DNS NS changes**: Which domain, which nameservers were added/removed.
 - **NS address changes**: Which domain, which nameserver, its old and new
   addresses.
-- **CNAME address changes**: Which hostname, the old and new addresses at the
-  end of its CNAME chain.
 - **NS query failures**: Which nameserver failed, error type (timeout, SERVFAIL,
   REFUSED, network error), which hostname/domain affected.
 - **NS recoveries**: Which nameserver recovered, which hostname/domain.
@@ -494,10 +485,8 @@ resolves to. A state file without it loads, and the next check fills it in
 without a notification.
 
 `cnameAddresses` lists the sorted addresses at the end of a hostname's CNAME
-chain, found when its nameservers answered with a CNAME and no address, and kept
-from the previous check when the chain cannot be followed or none of the name's
-nameservers answered. It is left out otherwise. A state file without it loads,
-and the next check fills it in without a notification.
+chain, found when its nameservers answered with a CNAME and no address. It is
+left out otherwise.
 
 ---
 
@@ -638,9 +627,7 @@ docker run -d \
       completes.
     - Port and TLS checks always use freshly resolved IP addresses from the DNS
       phase that immediately precedes them — never stale IPs from a previous
-      cycle, with one exception: when a name's CNAME chain cannot be followed,
-      or none of the name's nameservers answered, the addresses the previous
-      cycle found at the end of the chain are used.
+      cycle.
 4. **On change detection**: Send notifications to all configured endpoints,
    update in-memory state, persist to disk.
 5. **Shutdown**: The watcher stops checking and saves the final state to disk,

TODO.md

@@ -21,8 +21,6 @@ trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
 
 - 2026-10-01: a watched name whose nameservers answer with a CNAME and no
   address gets port and TLS checks at the end of its CNAME chain (closes #203).
-- 2026-10-01: a certificate within the expiry warning period is warned about on
-  every TLS check, where some checks used to skip it at random (closes #204).
 - 2026-10-01: a domain's NS set is its delegation from the parent zone's
   servers, not whichever of its own servers answered first (closes #200).
 - 2026-10-01: README has Getting Started, Rationale and TODO sections, and its

internal/watcher/cname_test.go

@@ -85,115 +85,3 @@ func TestCNAMEThatCannotBeFollowedKeepsPrevious(t *testing.T) {
 		)
 	}
 }
-
-// TestCNAMEWhoseNameserversAllFailedKeepsPrevious checks a name none of
-// whose nameservers answered. The addresses the previous check saved
-// from following its CNAME are kept, and nothing is looked up: the
-// watcher has no resolver.
-func TestCNAMEWhoseNameserversAllFailedKeepsPrevious(t *testing.T) {
-	t.Parallel()
-
-	w := watcher.NewForTest(nil, nil, nil, nil, nil, nil)
-
-	current := saved(map[string]*state.NameserverRecordState{
-		nsA: failed(), nsB: failed(),
-	})
-	prev := cnameState(oldIP)
-
-	w.ResolveCNAMEAddresses(t.Context(), host, current, prev)
-
-	if !slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
-		t.Errorf(
-			"saved %v, want %v",
-			current.CNAMEAddresses, prev.CNAMEAddresses,
-		)
-	}
-}
-
-// cnameState builds the state a check leaves behind for a name whose
-// nameserver answered with a CNAME and no address, when following the
-// CNAME found these addresses.
-func cnameState(addresses ...string) *state.HostnameState {
-	hs := hostnameState(map[string]map[string][]string{
-		nsA: {"CNAME": {"target.example.org."}},
-	})
-	hs.CNAMEAddresses = addresses
-
-	return hs
-}
-
-func TestCNAMEAddressChangeAlerts(t *testing.T) {
-	t.Parallel()
-
-	// Each case is the state saved by the previous check and by the
-	// current one. The name's records are the same in both.
-	tests := []struct {
-		name          string
-		prev, current *state.HostnameState
-		want          int
-	}{
-		{
-			"same addresses",
-			cnameState(ip1, ip2), cnameState(ip1, ip2), 0,
-		},
-		{
-			"same addresses in another order",
-			cnameState(ip2, ip1), cnameState(ip1, ip2), 0,
-		},
-		{
-			"address replaced",
-			cnameState(ip1), cnameState(ip2), 1,
-		},
-		{
-			"address added",
-			cnameState(ip1), cnameState(ip1, ip2), 1,
-		},
-		{
-			"no address at the end of the chain now",
-			cnameState(ip1), cnameState(), 1,
-		},
-		{
-			"state file from before addresses were saved",
-			cnameState(), cnameState(ip1), 0,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			notifier := &mockNotifier{}
-			w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
-
-			w.DetectHostnameChanges(t.Context(), host, tt.prev, tt.current)
-
-			got := len(notifier.getNotifications())
-			if got != tt.want {
-				t.Errorf("sent %d notifications, want %d", got, tt.want)
-			}
-		})
-	}
-}
-
-func TestCNAMEAddressChangeAlertNamesHostnameAndAddresses(t *testing.T) {
-	t.Parallel()
-
-	notifier := &mockNotifier{}
-	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
-
-	w.DetectHostnameChanges(
-		t.Context(), host, cnameState(ip1), cnameState(ip2, ip3),
-	)
-
-	want := notification{
-		Title: "CNAME Address Change: " + host,
-		Message: "Hostname: " + host +
-			"\nOld: " + ip1 + "\nNew: " + ip2 + ", " + ip3,
-		Priority: "warning",
-	}
-
-	got := notifier.getNotifications()
-	if len(got) != 1 || got[0] != want {
-		t.Errorf("sent %v, want %v", got, want)
-	}
-}

internal/watcher/export_test.go

@@ -20,14 +20,15 @@ func NewForTest(
 	n Notifier,
 ) *Watcher {
 	return &Watcher{
-		log:       slog.Default(),
-		config:    cfg,
-		state:     st,
-		resolver:  res,
-		portCheck: pc,
-		tlsCheck:  tc,
-		notify:    n,
-		firstRun:  true,
+		log:            slog.Default(),
+		config:         cfg,
+		state:          st,
+		resolver:       res,
+		portCheck:      pc,
+		tlsCheck:       tc,
+		notify:         n,
+		firstRun:       true,
+		expiryNotified: make(map[string]time.Time),
 	}
 }
 
@@ -80,11 +81,6 @@ func (w *Watcher) CheckAllPorts(ctx context.Context) {
 	w.checkAllPorts(ctx)
 }
 
-// RunTLSChecks exports runTLSChecks for testing.
-func (w *Watcher) RunTLSChecks(ctx context.Context) {
-	w.runTLSChecks(ctx)
-}
-
 // BuildHostnameState exports buildHostnameState for testing.
 func BuildHostnameState(
 	results map[string]*resolver.NameserverResponse,

internal/watcher/watcher.go

@@ -7,6 +7,7 @@ import (
 	"slices"
 	"sort"
 	"strings"
+	"sync"
 	"time"
 
 	"go.uber.org/fx"
@@ -48,16 +49,18 @@ type Params struct {
 
 // Watcher orchestrates all monitoring checks on a schedule.
 type Watcher struct {
-	log       *slog.Logger
-	config    *config.Config
-	state     *state.State
-	resolver  DNSResolver
-	portCheck PortChecker
-	tlsCheck  TLSChecker
-	notify    Notifier
-	cancel    context.CancelFunc
-	done      chan struct{} // closed when Run returns
-	firstRun  bool
+	log              *slog.Logger
+	config           *config.Config
+	state            *state.State
+	resolver         DNSResolver
+	portCheck        PortChecker
+	tlsCheck         TLSChecker
+	notify           Notifier
+	cancel           context.CancelFunc
+	done             chan struct{} // closed when Run returns
+	firstRun         bool
+	expiryNotifiedMu sync.Mutex
+	expiryNotified   map[string]time.Time
 }
 
 // New creates a new Watcher instance wired into the fx lifecycle.
@@ -66,14 +69,15 @@ func New(
 	params Params,
 ) (*Watcher, error) {
 	w := &Watcher{
-		log:       params.Logger.Get(),
-		config:    params.Config,
-		state:     params.State,
-		resolver:  params.Resolver,
-		portCheck: params.PortCheck,
-		tlsCheck:  params.TLSCheck,
-		notify:    params.Notify,
-		firstRun:  true,
+		log:            params.Logger.Get(),
+		config:         params.Config,
+		state:          params.State,
+		resolver:       params.Resolver,
+		portCheck:      params.PortCheck,
+		tlsCheck:       params.TLSCheck,
+		notify:         params.Notify,
+		firstRun:       true,
+		expiryNotified: make(map[string]time.Time),
 	}
 
 	lifecycle.Append(fx.Hook{
@@ -395,30 +399,17 @@ func (w *Watcher) checkHostname(
 // resolveCNAMEAddresses saves in current the addresses at the end of
 // hostname's CNAME chain, when the nameservers' answers in current hold
 // a CNAME and no address. ResolveIPAddresses looks the name up again
-// and follows the chain. The addresses saved in prev, which may be nil,
-// are kept when none of the name's nameservers answered, and when the
-// chain cannot be followed, as when no nameserver of a zone in it
-// answers.
+// and follows the chain. When it fails, as when no nameserver of a zone
+// in the chain answers, the addresses saved in prev, which may be nil,
+// are kept.
 func (w *Watcher) resolveCNAMEAddresses(
 	ctx context.Context,
 	hostname string,
 	current, prev *state.HostnameState,
 ) {
-	var prevAddresses []string
-	if prev != nil {
-		prevAddresses = prev.CNAMEAddresses
-	}
-
-	answered := false
 	hasCNAME := false
 
 	for _, nsState := range current.RecordsByNameserver {
-		if nsState.Status != statusOK {
-			continue
-		}
-
-		answered = true
-
 		if len(nsState.Records["A"]) > 0 || len(nsState.Records["AAAA"]) > 0 {
 			return
 		}
@@ -428,12 +419,6 @@ func (w *Watcher) resolveCNAMEAddresses(
 		}
 	}
 
-	if !answered {
-		current.CNAMEAddresses = prevAddresses
-
-		return
-	}
-
 	if !hasCNAME {
 		return
 	}
@@ -446,7 +431,9 @@ func (w *Watcher) resolveCNAMEAddresses(
 			"error", err,
 		)
 
-		current.CNAMEAddresses = prevAddresses
+		if prev != nil {
+			current.CNAMEAddresses = prev.CNAMEAddresses
+		}
 
 		return
 	}
@@ -497,37 +484,6 @@ func (w *Watcher) detectHostnameChanges(
 	w.detectNSDisappearances(ctx, hostname, prev, current)
 	w.detectNSFailures(ctx, hostname, prev, current)
 	w.detectInconsistencies(ctx, hostname, prev, current)
-	w.detectCNAMEAddressChanges(ctx, hostname, prev, current)
-}
-
-// detectCNAMEAddressChanges notifies when the addresses at the end of
-// hostname's CNAME chain differ from those the previous check saved,
-// including when there are none now. When the previous check saved
-// none, as in a state file from before they were saved, nothing is
-// compared.
-func (w *Watcher) detectCNAMEAddressChanges(
-	ctx context.Context,
-	hostname string,
-	prev, current *state.HostnameState,
-) {
-	old, cur := prev.CNAMEAddresses, current.CNAMEAddresses
-	if len(old) == 0 || sliceEqual(old, cur) {
-		return
-	}
-
-	msg := fmt.Sprintf(
-		"Hostname: %s\nOld: %s\nNew: %s",
-		hostname,
-		strings.Join(old, ", "),
-		strings.Join(cur, ", "),
-	)
-
-	w.notify.SendNotification(
-		ctx,
-		"CNAME Address Change: "+hostname,
-		msg,
-		"warning",
-	)
 }
 
 // detectRecordChanges compares each nameserver's records with those of
@@ -1108,6 +1064,22 @@ func (w *Watcher) checkTLSExpiry(
 		return
 	}
 
+	// Deduplicate expiry warnings: don't re-notify for the same
+	// hostname within the TLS check interval.
+	dedupKey := fmt.Sprintf("expiry:%s:%s", hostname, ip)
+
+	w.expiryNotifiedMu.Lock()
+
+	lastNotified, seen := w.expiryNotified[dedupKey]
+	if seen && time.Since(lastNotified) < w.config.TLSInterval {
+		w.expiryNotifiedMu.Unlock()
+
+		return
+	}
+
+	w.expiryNotified[dedupKey] = time.Now()
+	w.expiryNotifiedMu.Unlock()
+
 	msg := fmt.Sprintf(
 		"Host: %s\nIP: %s\nCN: %s\n"+
 			"Expires: %s (%.0f days)",

internal/watcher/watcher_test.go

@@ -616,54 +616,33 @@ func TestTLSExpiryWarning(t *testing.T) {
 	assertNotified(t, deps, "TLS Expiry Warning: "+testHost, "warning")
 }
 
-// TestTLSExpiryWarningEachCheck runs the TLS checks three times in a
-// row on hostname and port state built here, for a certificate that
-// expires within the warning period. Each check warns once, whether the
-// TLS interval is a nanosecond, shorter than the time between two
-// checks, or a day, longer than it.
-func TestTLSExpiryWarningEachCheck(t *testing.T) {
+func TestTLSExpiryWarningDedup(t *testing.T) {
 	t.Parallel()
 
-	title := "TLS Expiry Warning: " + host
+	cfg := defaultTestConfig(t)
+	cfg.Hostnames = []string{testHost}
+	cfg.TLSInterval = 24 * time.Hour
 
-	for _, interval := range []time.Duration{time.Nanosecond, 24 * time.Hour} {
-		t.Run(interval.String(), func(t *testing.T) {
-			t.Parallel()
+	title := "TLS Expiry Warning: " + testHost
 
-			cfg := defaultTestConfig(t)
-			cfg.Hostnames = []string{host}
-			cfg.TLSInterval = interval
+	// The second check comes within the TLS interval of the first,
+	// so it must not warn again.
+	var warnings int
 
-			// The TLS checks read the saved hostname and port state and
-			// look nothing up, so the watcher has no resolver.
-			deps := newTestDeps(t, cfg)
-			w := watcher.NewForTest(
-				cfg, deps.state, nil,
-				deps.portChecker, deps.tlsChecker, deps.notifier,
-			)
+	deps := runChecks(t, cfg, expiresInThreeDays, func(deps *testDeps) {
+		warnings = countNotifications(deps, title)
+	})
 
-			expiresInThreeDays(deps)
-			deps.state.SetHostnameState(host, saved(
-				map[string]*state.NameserverRecordState{
-					nsA: answered(map[string][]string{"A": {ip1}}),
-				},
-			))
-			deps.state.SetPortState(ip1+":443", &state.PortState{
-				Open: true, Hostnames: []string{host},
-			})
+	if warnings == 0 {
+		t.Fatal("expected expiry warnings from the first check")
+	}
 
-			for check := 1; check <= 3; check++ {
-				w.RunTLSChecks(t.Context())
-
-				got := countNotifications(deps, title)
-				if got != check {
-					t.Fatalf(
-						"after check %d: %d expiry warnings, want %d",
-						check, got, check,
-					)
-				}
-			}
-		})
+	got := countNotifications(deps, title)
+	if got != warnings {
+		t.Errorf(
+			"expected %d expiry warnings (dedup), got %d",
+			warnings, got,
+		)
 	}
 }