notify: the log names a notification endpoint, not its webhook URL (closes #288)

With debug logging on, each delivery logged the full Slack, Mattermost
or ntfy URL, whose path or query lets anyone who has it post to the
channel or topic. The two debug lines now give the endpoint's name and
the title; sendSlack is told which of Slack or Mattermost it sends to.
A webhook URL that does not parse gave a startup error quoting the
whole URL; it now gives only the reason. Errors from a failed request
come from the transport, not from an HTTP client, and carry no part of
the path or query; a test now checks that too.

Model: opus-5-5

README.md

@@ -104,9 +104,11 @@ notification endpoint set, changes show only on the dashboard; see
   NS change notification above. A domain listed in
   `DNSWATCHER_SKIP_RECORD_NOTIFICATIONS` gets no record change or inconsistency
   notification. A domain with no delegation of its own has these records asked
-  at the servers of the zone it is in, as a hostname has. A nameserver the
-  domain's records were asked at on the previous check but not on this one gets
-  a hostname's NS change notification (see below), unless it was in the domain's
+  at the servers of the zone it is in, as a hostname has. When none of those
+  servers answers, the lookup of its NS record set fails, and they are saved as
+  failed and notified as a hostname's are (see below). A nameserver the domain's
+  records were asked at on the previous check but not on this one gets a
+  hostname's NS change notification (see below), unless it was in the domain's
   delegation on the previous check, as when that delegation is withdrawn. A
   domain that does not exist has none: they are not asked for, and those saved
   by an earlier check are removed without a notification.
@@ -121,7 +123,13 @@ notification endpoint set, changes show only on the dashboard; see
   trace moves from a name to its parent only when the servers asked answer that
   the name has no delegation of its own, or does not exist. When they do not
   answer, the check fails and the hostname's records from the previous check are
-  kept.
+  kept, unless they are the nameservers the previous check saved for the
+  hostname. Each of those is then saved as failed, with the reason, as a
+  domain's nameservers are when none of them answers, so it gets an NS query
+  failure notification, and an NS recovery notification when it answers again
+  (see below). A trace that gets no answer before it reaches them, as when the
+  host running dnswatcher loses its network, fails the check without a
+  notification.
 - Queries **each** authoritative nameserver independently for **all** record
   types: A, AAAA, CNAME, MX, TXT, SRV, CAA, NS.
 - Each record type is a query of its own. When a nameserver answers some types

TODO.md

@@ -10,17 +10,23 @@
 
 # Status
 
-pre-1.0. No git tags. Work lands on `next` by PR. Open work for 1.0 is tracked
-on the 1.0 milestone: https://git.eeqj.de/sneak/dnswatcher/milestone/7
+pre-1.0. Work lands on `next` by PR. Open work for 1.0 is tracked on the 1.0
+milestone: https://git.eeqj.de/sneak/dnswatcher/milestone/7
 
 # Next Step
 
-trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
+1.0 tracking issue: https://git.eeqj.de/sneak/dnswatcher/issues/66
 
 # Completed Steps
 
+- 2026-10-15: the log names a notification endpoint (`slack`, `mattermost`,
+  `ntfy`) and never shows its URL's path or query (closes #288).
+- 2026-10-13: a hostname or a domain whose zone's nameservers all stop answering
+  gets an NS Failure for each, then an NS Recovery (closes #284).
 - 2026-10-13: an IPv6 address is written in brackets before its port, as in
   `[2001:db8::1]:443`, in keys and Port Change notifications (closes #270).
+- 2026-10-13: `TODO.md` names only open issues as next and future steps, and its
+  Status says nothing about git tags (closes #281).
 - 2026-10-13: a port check that finds port 443 closed removes that address's
   certificate entries, so none is left shown as `ok` (closes #265).
 - 2026-10-13: a state file holding `{}`, or leaving out a section, loads with
@@ -203,6 +209,4 @@ trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
 
 # Future Steps
 
-- 1.0 readiness: run it with a real config and read the logs:
-  https://git.eeqj.de/sneak/dnswatcher/issues/66
-- review toward 1.0: https://git.eeqj.de/sneak/dnswatcher/issues/144
+- DNSSEC validation, after 1.0: https://git.eeqj.de/sneak/dnswatcher/issues/59

internal/notify/delivery_test.go

@@ -6,10 +6,12 @@ import (
 	"encoding/json"
 	"errors"
 	"io"
+	"log/slog"
 	"maps"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
+	"slices"
 	"strings"
 	"sync"
 	"testing"
@@ -38,6 +40,13 @@ const (
 	prioUrgent  = "urgent"
 )
 
+// Endpoint names, as the log gives them, used across multiple tests.
+const (
+	endpointNtfy       = "ntfy"
+	endpointSlack      = "slack"
+	endpointMattermost = "mattermost"
+)
+
 // testHost is the hostname used in request construction tests.
 const testHost = "example.com"
 
@@ -1094,6 +1103,172 @@ func TestSendNotificationErrorNamesEndpoint(t *testing.T) {
 	}
 }
 
+// ── webhook URLs kept out of the log ──────────────────────
+
+// webhookPathAndQuery follows the server's address in every
+// endpoint's URL in the tests below. A webhook URL's path or query
+// lets anyone post to the channel or topic, so neither word marked
+// secret in it may reach the log.
+const webhookPathAndQuery = "/hooks/secret-in-path?token=secret-in-query"
+
+// assertNoWebhookSecret fails the test if text holds either word
+// marked secret in webhookPathAndQuery.
+func assertNoWebhookSecret(t *testing.T, text string) {
+	t.Helper()
+
+	for _, secret := range []string{"secret-in-path", "secret-in-query"} {
+		if strings.Contains(text, secret) {
+			t.Errorf("%q from the webhook URL is in:\n%s", secret, text)
+		}
+	}
+}
+
+// logRecord is the part of a JSON log line the tests below read.
+type logRecord struct {
+	Level    string `json:"level"`
+	Msg      string `json:"msg"`
+	Endpoint string `json:"endpoint"`
+	Title    string `json:"title"`
+	Error    string `json:"error"`
+}
+
+// parseLog decodes each line of a JSON log.
+func parseLog(t *testing.T, logs string) []logRecord {
+	t.Helper()
+
+	var records []logRecord
+
+	for line := range strings.Lines(logs) {
+		var record logRecord
+
+		err := json.Unmarshal([]byte(line), &record)
+		if err != nil {
+			t.Fatalf("decoding log line %q: %v", line, err)
+		}
+
+		records = append(records, record)
+	}
+
+	return records
+}
+
+// sendToEachEndpoint sends one notification with the given title to
+// ntfy, Slack and Mattermost, each at baseURL followed by
+// webhookPathAndQuery, and retries a failed delivery once. When
+// every delivery has finished it returns the JSON log written,
+// debug lines included.
+func sendToEachEndpoint(t *testing.T, baseURL, title string) string {
+	t.Helper()
+
+	target, err := url.Parse(baseURL + webhookPathAndQuery)
+	if err != nil {
+		t.Fatalf("parsing webhook URL: %v", err)
+	}
+
+	svc, logs := newLoggingService(http.DefaultTransport)
+	svc.SetNtfyURL(target)
+	svc.SetSlackWebhookURL(target)
+	svc.SetMattermostWebhookURL(target)
+	svc.SetSleepFunc(instantSleep)
+	svc.SetRetryConfig(notify.RetryConfig{
+		MaxRetries: 1,
+		BaseDelay:  time.Millisecond,
+		MaxDelay:   time.Millisecond,
+	})
+
+	svc.SendNotification(context.Background(), title, "m", prioInfo)
+
+	waitForCondition(t, func() bool {
+		return svc.OutstandingDeliveries() == 0
+	})
+
+	return logs.String()
+}
+
+// TestSendNotificationDebugLogOmitsWebhookURL checks that, with debug
+// logging on, a delivery to each endpoint logs the endpoint's name and
+// the title, and no part of the URL's path or query.
+func TestSendNotificationDebugLogOmitsWebhookURL(t *testing.T) {
+	t.Parallel()
+
+	const title = "Port Change"
+
+	srv := httptest.NewServer(
+		http.HandlerFunc(
+			func(w http.ResponseWriter, _ *http.Request) {
+				w.WriteHeader(http.StatusOK)
+			}),
+	)
+	defer srv.Close()
+
+	logs := sendToEachEndpoint(t, srv.URL, title)
+
+	assertNoWebhookSecret(t, logs)
+
+	got := map[string]string{}
+
+	for _, record := range parseLog(t, logs) {
+		if record.Level == slog.LevelDebug.String() {
+			got[record.Endpoint] = record.Title
+		}
+	}
+
+	want := map[string]string{
+		endpointNtfy:       title,
+		endpointSlack:      title,
+		endpointMattermost: title,
+	}
+
+	if !maps.Equal(got, want) {
+		t.Errorf("debug lines' endpoint and title = %v, want %v", got, want)
+	}
+}
+
+// TestSendNotificationErrorLogOmitsWebhookURL checks that a delivery
+// to each endpoint that cannot connect logs the transport's error,
+// which names the refused connection, on its retry line and on its
+// final failure line, and that no line holds any part of the URL's
+// path or query.
+func TestSendNotificationErrorLogOmitsWebhookURL(t *testing.T) {
+	t.Parallel()
+
+	// Closed before anything is sent, so every attempt fails to
+	// connect.
+	srv := httptest.NewServer(http.NotFoundHandler())
+	srv.Close()
+
+	logs := sendToEachEndpoint(t, srv.URL, "t")
+
+	assertNoWebhookSecret(t, logs)
+
+	// For each endpoint, the messages of its lines whose error names
+	// the refused connection, in the order they were logged.
+	got := map[string][]string{}
+
+	for _, record := range parseLog(t, logs) {
+		if strings.Contains(record.Error, "connection refused") {
+			got[record.Endpoint] = append(
+				got[record.Endpoint], record.Msg,
+			)
+		}
+	}
+
+	lines := []string{
+		"notification delivery failed, retrying",
+		"failed to send notification after retries",
+	}
+	want := map[string][]string{
+		endpointNtfy:       lines,
+		endpointSlack:      lines,
+		endpointMattermost: lines,
+	}
+
+	if !maps.EqualFunc(got, want, slices.Equal) {
+		t.Errorf("lines whose error names the refused connection = %v, "+
+			"want %v", got, want)
+	}
+}
+
 // ── SlackPayload JSON marshaling ──────────────────────────
 
 func TestSlackPayloadJSON(t *testing.T) {

internal/notify/export_test.go

@@ -81,7 +81,8 @@ func (svc *Service) SendNtfy(
 	return svc.sendNtfy(ctx, topicURL, title, message, priority)
 }
 
-// SendSlack exports sendSlack for testing.
+// SendSlack exports sendSlack for testing. It sends as the
+// "slack" endpoint.
 func (svc *Service) SendSlack(
 	ctx context.Context,
 	webhookURL *url.URL,
@@ -89,7 +90,7 @@ func (svc *Service) SendSlack(
 	title, message, priority string,
 ) error {
 	return svc.sendSlack(
-		ctx, webhookURL, failed, title, message, priority,
+		ctx, webhookURL, "slack", failed, title, message, priority,
 	)
 }
 

internal/notify/notify.go

@@ -56,6 +56,15 @@ func IsAllowedScheme(scheme string) bool {
 func ValidateWebhookURL(raw string) (*url.URL, error) {
 	u, err := url.ParseRequestURI(raw)
 	if err != nil {
+		// A *url.Error quotes the whole URL, and this error is
+		// logged at startup. A webhook URL's path or query lets
+		// anyone post to the channel or topic, so keep only the
+		// reason.
+		var urlErr *url.Error
+		if errors.As(err, &urlErr) {
+			err = urlErr.Err
+		}
+
 		return nil, fmt.Errorf("invalid URL: %w", err)
 	}
 
@@ -277,7 +286,7 @@ func (svc *Service) dispatchSlack(
 
 	svc.dispatch(ctx, "slack", func(c context.Context) error {
 		return svc.sendSlack(
-			c, svc.slackWebhookURL, ErrSlackFailed,
+			c, svc.slackWebhookURL, "slack", ErrSlackFailed,
 			title, message, priority,
 		)
 	})
@@ -295,8 +304,8 @@ func (svc *Service) dispatchMattermost(
 		ctx, "mattermost",
 		func(c context.Context) error {
 			return svc.sendSlack(
-				c, svc.mattermostWebhookURL, ErrMattermostFailed,
-				title, message, priority,
+				c, svc.mattermostWebhookURL, "mattermost",
+				ErrMattermostFailed, title, message, priority,
 			)
 		},
 	)
@@ -307,9 +316,11 @@ func (svc *Service) sendNtfy(
 	topicURL *url.URL,
 	title, message, priority string,
 ) error {
+	// The topic URL is left out of the log: it lets anyone who has
+	// it read and post to the topic.
 	svc.log.Debug(
 		"sending ntfy notification",
-		"topic", topicURL.String(),
+		"endpoint", "ntfy",
 		"title", title,
 	)
 
@@ -372,12 +383,15 @@ type SlackAttachment struct {
 }
 
 // sendSlack posts to a Slack or Mattermost incoming webhook, which
-// take the same payload. An HTTP error status is returned wrapped in
-// failed, ErrSlackFailed or ErrMattermostFailed, so the error names
-// the endpoint.
+// take the same payload. endpoint, "slack" or "mattermost", names
+// the webhook in the log in place of its URL, which lets anyone who
+// has it post to the channel. An HTTP error status is returned
+// wrapped in failed, ErrSlackFailed or ErrMattermostFailed, so the
+// error names the endpoint.
 func (svc *Service) sendSlack(
 	ctx context.Context,
 	webhookURL *url.URL,
+	endpoint string,
 	failed error,
 	title, message, priority string,
 ) error {
@@ -388,7 +402,7 @@ func (svc *Service) sendSlack(
 
 	svc.log.Debug(
 		"sending webhook notification",
-		"url", webhookURL.String(),
+		"endpoint", endpoint,
 		"title", title,
 	)
 

internal/notify/notify_test.go

@@ -79,6 +79,23 @@ func TestValidateWebhookURLInvalid(t *testing.T) {
 	}
 }
 
+// TestValidateWebhookURLErrorOmitsURL checks that the error for a
+// webhook URL that does not parse, here because a carriage return
+// was left at its end, leaves out the URL's path and query: the
+// error is logged at startup.
+func TestValidateWebhookURLErrorOmitsURL(t *testing.T) {
+	t.Parallel()
+
+	_, err := notify.ValidateWebhookURL(
+		"https://hooks.example.com" + webhookPathAndQuery + "\r",
+	)
+	if err == nil {
+		t.Fatal("expected an error for a URL ending in a carriage return")
+	}
+
+	assertNoWebhookSecret(t, err.Error())
+}
+
 func TestIsAllowedScheme(t *testing.T) {
 	t.Parallel()
 

internal/resolver/errors.go

@@ -2,6 +2,23 @@ package resolver
 
 import "errors"
 
+// NoAnswerError is returned when the walk to a name's nameservers
+// reached a zone through a referral and none of that zone's
+// nameservers, Nameservers as the referral names them, answered. Err
+// says why they did not.
+type NoAnswerError struct {
+	Nameservers []string
+	Err         error
+}
+
+func (e *NoAnswerError) Error() string {
+	return e.Err.Error()
+}
+
+func (e *NoAnswerError) Unwrap() error {
+	return e.Err
+}
+
 // Sentinel errors returned by the resolver.
 var (
 	// ErrNoNameservers is returned when no authoritative NS

internal/resolver/export_test.go

@@ -31,9 +31,11 @@ func NewWithQueryTimeout(log *slog.Logger, timeout time.Duration) *Resolver {
 func (r *Resolver) FollowDelegation(
 	ctx context.Context,
 	domain string,
+	zone string,
+	nameservers []string,
 	servers []string,
 ) ([]string, error) {
-	return r.followDelegation(ctx, domain, servers)
+	return r.followDelegation(ctx, domain, zone, nameservers, servers)
 }
 
 // FindAuthoritativeNameserversFrom exports findAuthoritativeNameservers

internal/resolver/iterative.go

@@ -204,20 +204,24 @@ func glueIPs(nsNames []string, glue map[string][]net.IP) []string {
 	return ips
 }
 
-// followDelegation follows referrals from servers, the root servers, to
-// domain and returns the NS set of domain's delegation. When the servers
-// of the zone domain is in answer that domain does not exist, the error
-// is ErrNXDomain. When they answer that it has no delegation of its own,
+// followDelegation follows referrals to domain from servers, the
+// addresses of the servers of zone, and returns the NS set of domain's
+// delegation. nameservers are the names a referral gave the servers of
+// zone; the walk to a name's nameservers starts at the root servers, the
+// servers of zone ".", which no referral names. When the servers of the
+// zone domain is in answer that domain does not exist, the error is
+// ErrNXDomain. When they answer that it has no delegation of its own,
 // because it is not the zone's apex, the set is empty and there is no
-// error. Any other error means that no such answer came.
+// error. Any other error means that no such answer came; it is a
+// *NoAnswerError when the servers that did not answer are those of a
+// zone a referral named.
 func (r *Resolver) followDelegation(
 	ctx context.Context,
 	domain string,
+	zone string,
+	nameservers []string,
 	servers []string,
 ) ([]string, error) {
-	// servers are the root servers, the servers of zone ".".
-	zone := "."
-
 	var withoutAddresses []string
 
 	for range maxDelegation {
@@ -228,6 +232,12 @@ func (r *Resolver) followDelegation(
 		resp, err := r.queryZone(
 			ctx, servers, withoutAddresses, zone, domain, dns.TypeNS, 0,
 		)
+
+		// A query that ctx cut short says nothing about the servers.
+		if err != nil && len(nameservers) > 0 && checkCtx(ctx) == nil {
+			return nil, &NoAnswerError{Nameservers: nameservers, Err: err}
+		}
+
 		if err != nil {
 			return nil, err
 		}
@@ -256,6 +266,7 @@ func (r *Resolver) followDelegation(
 			return r.resolveNSIterative(ctx, domain)
 		}
 
+		nameservers = authNS
 		servers, withoutAddresses = referralNameservers(resp)
 		zone = referralZone(resp)
 	}
@@ -626,7 +637,8 @@ func (r *Resolver) resolveARecord(
 // them. When the servers asked answer that the name has no delegation
 // of its own, or does not exist, it tries each parent name in turn, so
 // it returns the nameservers of the zone the name is in. When they do
-// not answer, it returns the error and tries no parent name.
+// not answer, it returns the error and tries no parent name; when a
+// referral named them, the error is a *NoAnswerError naming them.
 func (r *Resolver) FindAuthoritativeNameservers(
 	ctx context.Context,
 	domain string,
@@ -655,7 +667,7 @@ func (r *Resolver) findAuthoritativeNameservers(
 
 		candidate := strings.Join(labels[i:], ".") + "."
 
-		nsNames, err := r.followDelegation(ctx, candidate, servers)
+		nsNames, err := r.followDelegation(ctx, candidate, ".", nil, servers)
 		if err != nil && !errors.Is(err, ErrNXDomain) {
 			return nil, err
 		}
@@ -1067,7 +1079,7 @@ func (r *Resolver) LookupNS(
 	}
 
 	return r.followDelegation(
-		ctx, dns.Fqdn(strings.ToLower(domain)), rootServerList(),
+		ctx, dns.Fqdn(strings.ToLower(domain)), ".", nil, rootServerList(),
 	)
 }
 

internal/resolver/resolver_test.go

@@ -121,7 +121,9 @@ func TestFindAuthoritativeNameservers_DelegatedSubdomain(
 // delegation of its own, so the lookup returns that walk's error, about
 // www.google.com, and tries no parent name: trying google.com and com
 // would end in ErrNoNameservers, or in the error of a walk for one of
-// them.
+// them. The servers that did not answer are those the walk started at,
+// which no referral named, so the error is no NoAnswerError, as when
+// the host running dnswatcher has lost its network.
 func TestFindAuthoritativeNameservers_NoAnswer(t *testing.T) {
 	t.Parallel()
 
@@ -134,6 +136,9 @@ func TestFindAuthoritativeNameservers_NoAnswer(t *testing.T) {
 	require.NotErrorIs(t, err, resolver.ErrNoNameservers)
 	assert.Contains(t, err.Error(), "query www.google.com. @"+noAnswerAddress)
 	assert.Empty(t, nameservers)
+
+	var noAnswer *resolver.NoAnswerError
+	assert.NotErrorAs(t, err, &noAnswer)
 }
 
 func TestFindAuthoritativeNameservers_ReturnsSorted(
@@ -954,12 +959,34 @@ func TestFollowDelegation_NoAnswer(t *testing.T) {
 	r := resolver.NewWithQueryTimeout(slog.Default(), 100*time.Millisecond)
 
 	nameservers, err := r.FollowDelegation(
-		t.Context(), "google.com.", []string{noAnswerAddress},
+		t.Context(), "google.com.", ".", nil, []string{noAnswerAddress},
 	)
 	require.Error(t, err)
 	assert.Empty(t, nameservers)
 }
 
+// TestFollowDelegation_NoAnswerAfterReferral starts the walk for
+// www.example.net at the servers of example.net as a referral names
+// them, ns1.example.net and ns2.example.net, at 192.0.2.1, where nothing
+// answers. The error is a NoAnswerError naming them, which the watcher
+// compares with the nameservers it saved for the name.
+func TestFollowDelegation_NoAnswerAfterReferral(t *testing.T) {
+	t.Parallel()
+
+	r := resolver.NewWithQueryTimeout(slog.Default(), 100*time.Millisecond)
+	nameservers := []string{"ns1.example.net.", "ns2.example.net."}
+
+	_, err := r.FollowDelegation(
+		t.Context(), "www.example.net.", "example.net.", nameservers,
+		[]string{noAnswerAddress},
+	)
+
+	var noAnswer *resolver.NoAnswerError
+	require.ErrorAs(t, err, &noAnswer)
+	assert.Equal(t, nameservers, noAnswer.Nameservers)
+	assert.Contains(t, err.Error(), "query www.example.net. @"+noAnswerAddress)
+}
+
 // TestResolveNSIterative_NoDelegationOfItsOwn walks to the nameservers
 // of www.google.com as the fallback walk does. As in
 // TestLookupNS_NoDelegationOfItsOwn, the set is empty, with no error.

internal/watcher/export_test.go

@@ -122,6 +122,34 @@ func (w *Watcher) RunTLSChecks(ctx context.Context) {
 	w.runTLSChecks(ctx)
 }
 
+// CheckHostnameResult exports checkHostnameResult for testing.
+func (w *Watcher) CheckHostnameResult(
+	ctx context.Context,
+	hostname string,
+	results map[string]*resolver.NameserverResponse,
+	err error,
+) bool {
+	return w.checkHostnameResult(ctx, hostname, results, err)
+}
+
+// CheckDomainResult exports checkDomainResult for testing.
+func (w *Watcher) CheckDomainResult(
+	ctx context.Context,
+	domain string,
+	nameservers []string,
+	err error,
+) {
+	w.checkDomainResult(ctx, domain, nameservers, err)
+}
+
+// FailedNameservers exports failedNameservers for testing.
+func FailedNameservers(
+	err error,
+	prev *state.HostnameState,
+) map[string]*resolver.NameserverResponse {
+	return failedNameservers(err, prev)
+}
+
 // BuildHostnameState exports buildHostnameState for testing.
 func BuildHostnameState(
 	results map[string]*resolver.NameserverResponse,

internal/watcher/interfaces.go

@@ -20,7 +20,10 @@ type DNSResolver interface {
 	) ([]string, error)
 
 	// LookupAllRecords queries all record types for a hostname,
-	// returning each nameserver's response keyed by nameserver.
+	// returning each nameserver's response keyed by nameserver. When
+	// the walk to the nameservers reached a zone through a referral and
+	// none of that zone's nameservers answered, the error is a
+	// *resolver.NoAnswerError naming them.
 	LookupAllRecords(
 		ctx context.Context,
 		hostname string,

internal/watcher/ipv6_test.go

@@ -16,7 +16,8 @@ import (
 // certificate keys and the Port Change notification write the address
 // in brackets, so its last group cannot be read as the port, and the
 // second port checks keep the certificate entry, whose address they read
-// back from its key. Nothing is looked up.
+// back from its key. When a last port check finds port 443 closed, the
+// certificate entry is removed. Nothing is looked up.
 func TestIPv6AddressInBrackets(t *testing.T) {
 	t.Parallel()
 
@@ -70,4 +71,13 @@ Port now open`
 	if len(got) != 1 || got[0].Title != title || got[0].Message != want {
 		t.Errorf("sent %v, want one %q with message:\n%s", got, title, want)
 	}
+
+	deps.portChecker.closed = true
+
+	w.CheckAllPorts(t.Context())
+
+	gotCerts = slices.Sorted(maps.Keys(deps.state.GetSnapshot().Certificates))
+	if len(gotCerts) != 0 {
+		t.Errorf("certificate entries %v with port 443 closed, want none", gotCerts)
+	}
 }

internal/watcher/nsfailure_test.go

@@ -2,6 +2,7 @@ package watcher_test
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"log/slog"
 	"strings"
@@ -14,6 +15,10 @@ import (
 	"sneak.berlin/go/dnswatcher/internal/watcher"
 )
 
+// errNoReply is why a walk that got no reply from a zone's servers
+// failed.
+var errNoReply = errors.New("all servers failed: i/o timeout")
+
 // answered is what a check saves for a nameserver that answered with
 // these records.
 func answered(records map[string][]string) *state.NameserverRecordState {
@@ -183,6 +188,134 @@ func TestNSFailureAlertNamesHostnameNameserverAndReason(t *testing.T) {
 	}
 }
 
+// TestZoneNameserversAllStopAnswering runs three checks of host from
+// the point where its lookup has returned. On the first, nsA and nsB,
+// the nameservers of its zone, answer. On the second, the lookup fails
+// with the error the walk to them returns when neither answers (see
+// the resolver's TestFollowDelegation_NoAnswerAfterReferral), given
+// here because no live zone has nameservers that never answer. For a
+// hostname it is the lookup of its records that fails, and for a domain
+// with no delegation of its own the lookup of its delegation. Both are
+// saved as failed, with the reason, and each gets an NS Failure. On the
+// third, both answer, and each gets an NS Recovery. A domain's records
+// are checked as a hostname's, so its first and third checks are too.
+func TestZoneNameserversAllStopAnswering(t *testing.T) {
+	t.Parallel()
+
+	records := map[string][]string{"A": {ip1}}
+	bothAnswer := map[string]*resolver.NameserverResponse{
+		nsA: response(records), nsB: response(records),
+	}
+	noAnswer := &resolver.NoAnswerError{
+		Nameservers: []string{nsA, nsB}, Err: errNoReply,
+	}
+
+	tests := []struct {
+		name     string
+		isDomain bool
+	}{
+		{"hostname", false},
+		{"domain with no delegation of its own", true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			cfg := defaultTestConfig(t)
+			if tt.isDomain {
+				cfg.Domains = []string{host}
+			} else {
+				cfg.Hostnames = []string{host}
+			}
+
+			// The watcher is given each lookup's result, so it has no
+			// resolver.
+			deps := newTestDeps(t, cfg)
+			w := watcher.NewForTest(
+				cfg, deps.state, nil,
+				deps.portChecker, deps.tlsChecker, deps.notifier,
+			)
+			w.SetFirstRun(false)
+
+			w.CheckHostnameResult(t.Context(), host, bothAnswer, nil)
+
+			if tt.isDomain {
+				w.CheckDomainResult(t.Context(), host, nil, noAnswer)
+			} else {
+				w.CheckHostnameResult(t.Context(), host, nil, noAnswer)
+			}
+
+			current, _ := deps.state.GetHostnameState(host)
+
+			for _, ns := range []string{nsA, nsB} {
+				got := current.RecordsByNameserver[ns]
+				if got.Status != failed().Status || got.Error != errNoReply.Error() {
+					t.Errorf(
+						"%s saved with status %q, error %q; want %q, %q",
+						ns, got.Status, got.Error, failed().Status, errNoReply,
+					)
+				}
+			}
+
+			if n := countNotifications(deps, "NS Failure: "+host); n != 2 {
+				t.Errorf("sent %d NS Failure notifications, want 2", n)
+			}
+
+			w.CheckHostnameResult(t.Context(), host, bothAnswer, nil)
+
+			if n := countNotifications(deps, "NS Recovery: "+host); n != 2 {
+				t.Errorf("sent %d NS Recovery notifications, want 2", n)
+			}
+		})
+	}
+}
+
+// TestFailedNameserversOnlyForThoseOfThePreviousCheck gives
+// FailedNameservers lookup errors after a check in which nsA and nsB
+// answered. Only an error that names both makes them failed.
+func TestFailedNameserversOnlyForThoseOfThePreviousCheck(t *testing.T) {
+	t.Parallel()
+
+	records := map[string][]string{"A": {ip1}}
+	bothAnswered := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(records), nsB: answered(records),
+	})
+	noAnswer := func(nameservers ...string) error {
+		return &resolver.NoAnswerError{Nameservers: nameservers, Err: errNoReply}
+	}
+
+	tests := []struct {
+		name       string
+		err        error
+		prev       *state.HostnameState
+		wantFailed bool
+	}{
+		{"both did not answer", noAnswer(nsA, nsB), bothAnswered, true},
+		{
+			"the servers of a parent zone did not answer",
+			noAnswer(nsC), bothAnswered, false,
+		},
+		{
+			"the zone's delegation lists only nsA now",
+			noAnswer(nsA), bothAnswered, false,
+		},
+		{"no root server answered", errNoReply, bothAnswered, false},
+		{"no previous check", noAnswer(nsA, nsB), nil, false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			got := watcher.FailedNameservers(tt.err, tt.prev)
+			if (got != nil) != tt.wantFailed {
+				t.Errorf("returned %v, want failed: %v", got, tt.wantFailed)
+			}
+		})
+	}
+}
+
 // TestNameserverThatNeverAnswers asks a nameserver address where
 // nothing answers, 192.0.2.1, and checks what the watcher saves for it.
 // The deadline outlasts the resolver's first two-second try, as in the

internal/watcher/watcher.go

@@ -291,12 +291,25 @@ func (w *Watcher) logFailedLookup(
 	w.log.Error(msg, args...)
 }
 
+// checkDomain looks up domain's delegation and checks domain with it
+// (see checkDomainResult).
 func (w *Watcher) checkDomain(
 	ctx context.Context,
 	domain string,
 ) {
 	nameservers, err := w.resolver.LookupNS(ctx, domain)
 
+	w.checkDomainResult(ctx, domain, nameservers, err)
+}
+
+// checkDomainResult finishes a check of domain from nameservers and err,
+// what the lookup of its delegation returned.
+func (w *Watcher) checkDomainResult(
+	ctx context.Context,
+	domain string,
+	nameservers []string,
+	err error,
+) {
 	// A domain that does not exist has no nameservers.
 	nxdomain := errors.Is(err, resolver.ErrNXDomain)
 	if nxdomain {
@@ -311,6 +324,12 @@ func (w *Watcher) checkDomain(
 			"error", err,
 		)
 
+		// For a domain with no delegation of its own, the servers that
+		// did not answer can be those of the zone it is in, at which
+		// its records are asked. They are then saved as failed, as a
+		// hostname's are.
+		w.checkHostnameResult(ctx, domain, nil, err)
+
 		return
 	}
 
@@ -464,8 +483,8 @@ func (w *Watcher) detectNSAddressChanges(
 	}
 }
 
-// checkHostname checks hostname's records and reports whether it saved
-// them; it does not when their lookup fails.
+// checkHostname looks up hostname's records and checks them (see
+// checkHostnameResult). It reports whether it saved them.
 func (w *Watcher) checkHostname(
 	ctx context.Context,
 	hostname string,
@@ -478,12 +497,31 @@ func (w *Watcher) checkHostname(
 			"hostname", hostname,
 			"error", err,
 		)
-
-		return false
 	}
 
+	return w.checkHostnameResult(ctx, hostname, results, err)
+}
+
+// checkHostnameResult finishes a check of hostname from results and err,
+// what the lookup of its records returned, and reports whether it saved
+// them. When the lookup failed, it saves nothing, unless the nameservers
+// that did not answer are those of the previous check (see
+// failedNameservers).
+func (w *Watcher) checkHostnameResult(
+	ctx context.Context,
+	hostname string,
+	results map[string]*resolver.NameserverResponse,
+	err error,
+) bool {
 	prev, _ := w.state.GetHostnameState(hostname)
 
+	if err != nil {
+		results = failedNameservers(err, prev)
+		if results == nil {
+			return false
+		}
+	}
+
 	w.updateHostnameState(
 		ctx, hostname, buildHostnameState(results, prev, time.Now().UTC()),
 	)
@@ -491,6 +529,40 @@ func (w *Watcher) checkHostname(
 	return true
 }
 
+// failedNameservers returns a failed response for each nameserver in
+// prev, a name's state from the previous check, with err as the reason,
+// when err says that the walk to the name's nameservers reached their
+// zone and none of them answered. For any other error, as when the walk
+// got no answer before it reached their zone, or when prev is nil, it
+// returns nil.
+func failedNameservers(
+	err error,
+	prev *state.HostnameState,
+) map[string]*resolver.NameserverResponse {
+	var noAnswer *resolver.NoAnswerError
+	if !errors.As(err, &noAnswer) || prev == nil {
+		return nil
+	}
+
+	saved := slices.Sorted(maps.Keys(prev.RecordsByNameserver))
+	if !slices.Equal(noAnswer.Nameservers, saved) {
+		return nil
+	}
+
+	results := make(map[string]*resolver.NameserverResponse)
+
+	for _, ns := range saved {
+		results[ns] = &resolver.NameserverResponse{
+			Nameserver: ns,
+			Records:    make(map[string][]string),
+			Status:     resolver.StatusError,
+			Error:      err.Error(),
+		}
+	}
+
+	return results
+}
+
 // updateHostnameState finishes a check of hostname from newState, built
 // from its nameservers' answers: it follows the CNAME in them, notifies
 // what changed since the previous check, and saves newState.
@@ -790,7 +862,7 @@ func (w *Watcher) detectRecordChanges(
 // saved delegation, which detectNSChanges notifies when they are removed
 // from it. checkDomain saves a new delegation only after this runs, and
 // only together with the records, so the saved delegation and the
-// records in prev come from the same check.
+// nameservers in prev come from the same check.
 func (w *Watcher) detectNSDisappearances(
 	ctx context.Context,
 	hostname string,