resolver: a reply marked recursion available from a root server's address stops the lookup (closes #300)

dnswatcher never asks for recursion and a root server never offers it,
so a reply marked recursion available from a root server's address
came from a resolver on the network answering in its place. The first
such reply, a refusal included, now stops the lookup at once with the
existing "this network intercepts DNS queries", naming the address,
and no other root server is asked, whether or not that resolver had
the name cached. queryDNS now returns a refused reply along with
ErrRefused, so the mark on a refusal can be seen. A refusal without
the mark is passed over and counted as before.

On such a network dnswatcher and its tests fail with that error, by
design. A live test passes public resolvers as the root servers and
expects it.

Model: opus-5-5

README.md

@@ -565,13 +565,13 @@ A root server never offers recursion, so a reply marked "recursion available"
 from a root server's address came from a recursive resolver on the network
 answering in its place, as on a network where a router rule, a VPN or a DNS
 filter sends all DNS to one resolver. The first such reply from a root server's
-address stops the lookup at once with the error "this network intercepts DNS
-queries", and no other root server is asked. A lookup that every root server
-refuses fails with the same error. Every lookup starts at the root servers, so
-on such a network every lookup fails with that error, whether or not that
-resolver has the name cached, and dnswatcher's tests fail there too. That is by
-design: nothing asks again another way or otherwise works around the
-interception.
+address, a refusal included, stops the lookup at once with the error "this
+network intercepts DNS queries", naming that address, and no other root server
+is asked. A lookup that every root server refuses without that mark fails with
+the same error. Every lookup starts at the root servers, so on such a network
+every lookup fails with that error, whether or not that resolver has the name
+cached, and dnswatcher's tests fail there too. That is by design: nothing asks
+again another way or otherwise works around the interception.
 
 A watched name's records are stored as its nameservers return them, CNAME
 included. When they return a CNAME and no address, the chain of every CNAME

TODO.md

@@ -20,9 +20,9 @@ milestone: https://git.eeqj.de/sneak/dnswatcher/milestone/7
 # Completed Steps
 
 - 2026-10-16: the first reply marked "recursion available" from a root server's
-  address stops the lookup with "this network intercepts DNS queries", so on a
-  network that sends DNS to a resolver dnswatcher and its tests fail, by design
-  (closes #300).
+  address, a refusal included, stops the lookup with "this network intercepts
+  DNS queries", so on a network that sends DNS to a resolver dnswatcher and its
+  tests fail, by design (closes #300).
 - 2026-10-15: a query its caller's context ends before it is sent records no
   reason about the nameserver, and a try the context's deadline cuts short is a
   timeout, so a nameserver whose only failures were timeouts is `timeout`, not a

internal/resolver/errors.go

@@ -54,11 +54,12 @@ var (
 	)
 
 	// ErrIntercepted is returned when a root server's address gave a
-	// reply marked recursion available, which ends the lookup at once,
-	// or when every root server refused a query. Root servers do
-	// neither, so those replies came from something on the network
-	// answering in their place. On such a network dnswatcher fails with
-	// it, by design: nothing works around the interception.
+	// reply marked recursion available, a refusal included, which ends
+	// the lookup at once, or when every root server refused a query.
+	// Root servers do neither, so those replies came from something on
+	// the network answering in their place. On such a network
+	// dnswatcher fails with it, by design: nothing works around the
+	// interception.
 	ErrIntercepted = errors.New("this network intercepts DNS queries")
 
 	// ErrCNAMEDepthExceeded is returned when a CNAME chain

internal/resolver/iterative.go

@@ -115,7 +115,8 @@ func (r *Resolver) retryTCP(
 }
 
 // queryDNS sends a DNS query to a specific server IP, never asking it
-// for recursion. A reply of REFUSED is returned as ErrRefused.
+// for recursion. A reply of REFUSED is returned together with
+// ErrRefused, so that the caller can still read the reply's flags.
 func (r *Resolver) queryDNS(
 	ctx context.Context,
 	serverIP string,
@@ -139,7 +140,7 @@ func (r *Resolver) queryDNS(
 	}
 
 	if resp.Rcode == dns.RcodeRefused {
-		return nil, fmt.Errorf(
+		return resp, fmt.Errorf(
 			"query %s @%s: %w", name, serverIP, ErrRefused,
 		)
 	}
@@ -284,14 +285,15 @@ func shuffled(
 }
 
 // queryServers asks servers, the servers of zone, about name in a random
-// order until one gives a usable reply. A server that times out, refuses
-// or gives a reply that is not usable is passed over for the next. When
-// every server refused, the error says so, and when they are the root
-// servers it is ErrIntercepted. When they are the root servers, the
-// first reply marked recursion available also ends the lookup with
-// ErrIntercepted, naming the address it came from, and no other root
-// server is asked: root servers offer no recursion, so that reply came
-// from something on the network answering in their place.
+// order until one gives a usable reply. When they are the root servers,
+// the first reply marked recursion available, a refusal included, ends
+// the lookup with ErrIntercepted, naming the address it came from, and
+// no other root server is asked: root servers offer no recursion, so
+// that reply came from something on the network answering in their
+// place. Otherwise a server that times out, refuses or gives a reply
+// that is not usable is passed over for the next. When every server
+// refused, the error says so, and when they are the root servers it is
+// ErrIntercepted.
 func (r *Resolver) queryServers(
 	ctx context.Context,
 	servers []string,
@@ -308,8 +310,10 @@ func (r *Resolver) queryServers(
 			return nil, ErrContextCanceled
 		}
 
+		// queryDNS returns a refusal together with its reply, so a
+		// refusal's mark is checked here too.
 		resp, err := r.queryDNS(ctx, ip, name, qtype)
-		if err == nil && zone == "." && resp.RecursionAvailable {
+		if resp != nil && zone == "." && resp.RecursionAvailable {
 			return nil, fmt.Errorf(
 				"query %s @%s: reply marked recursion available, "+
 					"so not from a root server: %w",

internal/resolver/resolver_test.go

@@ -851,59 +851,70 @@ func TestQueryServers_NotEveryRootServerRefused(t *testing.T) {
 }
 
 // TestQueryServers_RecursiveResolversAsRootServers passes public
-// recursive resolvers of four operators to QueryServers as the servers
-// of the root zone, as a network that sends every DNS query to a
-// resolver would. Their replies are marked recursion available, which
-// no root server's is: SERVFAIL, or an answer from a resolver's cache,
-// as 1.1.1.1 gives for com., which would be used if a root server gave
-// it. The first such reply ends the lookup with ErrIntercepted, naming
-// the resolver that gave it. A resolver that refuses or gives no reply
-// is passed over for the next, so one of them answering is enough.
+// recursive resolvers to QueryServers as the servers of the root zone,
+// as a network that sends every DNS query to a resolver would. Their
+// replies are marked recursion available, which no root server's is:
+// SERVFAIL, REFUSED, or an answer from a resolver's cache, as 1.1.1.1
+// gives for com., which would be used if a root server gave it. The
+// first such reply ends the lookup with ErrIntercepted, naming the
+// resolver that gave it. In the first group the replies differ; every
+// resolver in the second refuses a query that does not ask for
+// recursion, as 9.9.9.9 does, so there a refusal ends the lookup
+// instead of being passed over. Each group has resolvers of four
+// operators, and a resolver that gives no reply is passed over for the
+// next, so one of them answering is enough.
 func TestQueryServers_RecursiveResolversAsRootServers(t *testing.T) {
 	t.Parallel()
 
 	r := newTestResolver(t)
-	resolvers := []string{
-		"1.1.1.1", "8.8.8.8", "9.9.9.9", "208.67.222.222",
+	groups := [][]string{
+		{"1.1.1.1", "8.8.8.8", "9.9.9.9", "208.67.222.222"},
+		{"64.6.64.6", "185.222.222.222", "4.2.2.1", "94.140.14.14"},
 	}
 
-	for _, name := range []string{"com.", "desec.io."} {
-		var err error
+	for _, resolvers := range groups {
+		for _, name := range []string{"com.", "desec.io."} {
+			var err error
 
-		livednstest.Retry(
-			t,
-			"QueryServers(public recursive resolvers as root servers, "+
-				name+")",
-			func(ctx context.Context) error {
-				_, err = r.QueryServers(ctx, resolvers, ".", name, dns.TypeNS)
-
-				// When no resolver gave a reply marked recursion
-				// available, each refused or gave no reply at all, so
-				// the attempt is tried again.
-				if err != nil &&
-					!strings.Contains(err.Error(), "marked recursion available") {
-					return fmt.Errorf(
-						"%w: %w", livednstest.ErrNoAnswer, err,
+			livednstest.Retry(
+				t,
+				"QueryServers("+strings.Join(resolvers, ", ")+
+					" as root servers, "+name+")",
+				func(ctx context.Context) error {
+					_, err = r.QueryServers(
+						ctx, resolvers, ".", name, dns.TypeNS,
 					)
-				}
 
-				return nil
-			},
-		)
+					// When no resolver gave a reply marked recursion
+					// available, none may have replied at all, so the
+					// attempt is tried again.
+					if err != nil && !strings.Contains(
+						err.Error(), "marked recursion available",
+					) {
+						return fmt.Errorf(
+							"%w: %w", livednstest.ErrNoAnswer, err,
+						)
+					}
 
-		require.ErrorIs(t, err, resolver.ErrIntercepted)
-
-		// The error names the resolver whose reply ended the lookup.
-		messages := make([]string, 0, len(resolvers))
-		for _, ip := range resolvers {
-			messages = append(messages,
-				"query "+name+" @"+ip+": reply marked recursion "+
-					"available, so not from a root server: "+
-					"this network intercepts DNS queries",
+					return nil
+				},
 			)
-		}
 
-		require.Contains(t, messages, err.Error())
+			require.ErrorIs(t, err, resolver.ErrIntercepted)
+
+			// The error names the resolver whose reply ended the
+			// lookup.
+			messages := make([]string, 0, len(resolvers))
+			for _, ip := range resolvers {
+				messages = append(messages,
+					"query "+name+" @"+ip+": reply marked recursion "+
+						"available, so not from a root server: "+
+						"this network intercepts DNS queries",
+				)
+			}
+
+			require.Contains(t, messages, err.Error())
+		}
 	}
 }