tests: remove the DNS stand-ins from the watcher and resolver tests (closes #159)

The watcher tests used a stand-in resolver and the resolver timeout test
a stand-in DNS client, against the rule that DNS is never mocked.
Watcher tests that look something up in DNS now run the real resolver
against live servers, each attempt on a new watcher. A DNS change is
tested by saving values live DNS never returns (names under .invalid,
192.0.2.1) in the state a check starts from, or by marking a real
nameserver failed. The timeout test queries 192.0.2.1, where nothing
answers. The live-DNS retry and concurrency limit moved from the
resolver tests to internal/livedns, so both packages share them.
NewFromLoggerWithClient had no other use and is gone. TESTING.md now
states the README's rule.

Model: opus-5-5

TODO.md

@@ -10,11 +10,7 @@
 
 # Status
 
-pre-1.0. No git tags. Core resolver work in flight on feature/resolver
-(dirty: internal/resolver/resolver_test.go). Local checkout has diverged
-from origin: origin/main is 8 commits ahead (watcher orchestrator,
-unified TARGETS) and origin/feature/resolver already contains the full
-iterative resolver implementation with hermetic mocked tests.
+pre-1.0. No git tags.
 
 # Next Step
 
@@ -23,13 +19,13 @@ Rationale, Design, TODO, License, Author) if any are still missing.
 
 # Completed Steps
 
-- 2026-09-29: nothing stands in for DNS any more. The watcher tests use the
-  real resolver against live DNS and test changes by preparing the saved
-  state a check starts from; the resolver timeout test queries an address
-  that never answers, and `NewFromLoggerWithClient`, used only by its
-  stand-in client, is gone. The live-DNS retry and concurrency limit moved
-  to `internal/livedns`, which both test packages use. `TESTING.md` states
-  the README's rule (closes #159).
+- 2026-09-29: nothing stands in for DNS any more. Watcher tests that look
+  something up in DNS use the real resolver against live DNS servers and test
+  record and nameserver changes by preparing the saved state a check starts
+  from; the resolver timeout test queries an address that never answers, and
+  `NewFromLoggerWithClient`, used only by its stand-in client, is gone. The
+  live-DNS retry and concurrency limit moved to `internal/livedns`, which both
+  test packages use. `TESTING.md` states the README's rule (closes #159).
 - 2026-09-28: the inconsistency alert is sent once, on the check where two
   nameservers start to disagree or where a nameserver that disagrees first
   appears, instead of on every check while they disagree, and not again after
@@ -268,4 +264,5 @@ Infrastructure notes (from untracked TODO.md):
 - Module path sneak.berlin/go/dnswatcher differs from the git.eeqj.de
   remote intentionally; do not "fix" it
 - Dependencies: github.com/miekg/dns, golang.org/x/net/publicsuffix
-- Tests use live DNS and never mock it (README, "No DNS mocking. Ever.")
+- DNS is never mocked; tests that look something up in DNS query live DNS
+  servers (README, "No DNS mocking. Ever.")

internal/livedns/livedns.go

@@ -1,5 +1,5 @@
-// Package livedns runs the live DNS operations of tests. Every test in
-// this project that needs DNS resolves against the real, live DNS —
+// Package livedns runs the live DNS operations of tests. Tests that
+// look something up in DNS query live DNS servers, never a stand-in —
 // see TESTING.md. Nothing here mocks, fakes, stubs, records or replays
 // DNS, and nothing here skips a test: it only changes *how* the live
 // queries are issued, so that a single dropped UDP packet or one slow

internal/resolver/livedns_test.go

@@ -17,11 +17,12 @@ import (
 // Live DNS test support
 // ----------------------------------------------------------------
 //
-// Every test in this package resolves against the real, live DNS —
-// see TESTING.md. Each live operation below goes through
-// livedns.Retry, which bounds how many resolutions are in flight at
-// once and retries an operation that got no answer (see package
-// livedns).
+// Tests that look something up in DNS query live DNS servers, never a
+// stand-in; logic that works on record data may be tested on that
+// data with no lookup (see TESTING.md). Each live operation below goes
+// through livedns.Retry, which bounds how many resolutions are in
+// flight at once and retries an operation that got no answer (see
+// package livedns).
 //
 // Where an assertion spans several independent nameservers, a quorum
 // is enough: a strict majority answering as expected. A server that

internal/resolver/resolver_test.go

@@ -32,8 +32,8 @@ func newTestResolver(t *testing.T) *resolver.Resolver {
 }
 
 // findOneNSForDomain picks one authoritative nameserver to aim a
-// test at. Live-DNS retry, concurrency and quorum handling live in
-// livedns_test.go.
+// test at. Quorum handling lives in livedns_test.go, and the live-DNS
+// retry and concurrency limit in package livedns.
 func findOneNSForDomain(
 	t *testing.T,
 	r *resolver.Resolver,

internal/watcher/watcher_test.go

@@ -19,9 +19,10 @@ import (
 )
 
 // The watcher looks these names up in live DNS with the real resolver,
-// so tests assert on notifications and saved state, never on the
-// records these zones publish. testHost's addresses stay the same from
-// one check to the next, which the tests that check it twice rely on.
+// so tests assert on what the watcher does with the answers, never on
+// the records these zones publish. testHost's nameservers and addresses
+// stay the same from one check to the next, which the tests that check
+// it twice rely on.
 const (
 	testDomain = "google.com"
 	testHost   = "cloudflare.com"
@@ -38,7 +39,8 @@ const (
 
 // --- Stand-ins for the port checker, TLS checker and notifier ---
 //
-// DNS has none: the watcher uses the real resolver (see TESTING.md).
+// DNS has none: the watchers built here use the real resolver (see
+// TESTING.md).
 
 // mockPortChecker reports every port open until closed is set.
 type mockPortChecker struct {
@@ -173,9 +175,8 @@ func defaultTestConfig(t *testing.T) *config.Config {
 
 // checkOnce runs the watcher's checks once and returns an error when a
 // configured name has no hostname state saved by this check, or that
-// state holds no address. The watcher saves a name's hostname state
-// only when all of the name's lookups succeed, so this means either
-// live DNS did not answer or the watcher did not save what it got.
+// state holds no address. Either live DNS gave no answer for the name,
+// or the watcher saved no fresh result for it.
 func checkOnce(
 	ctx context.Context,
 	w *watcher.Watcher,
@@ -202,46 +203,42 @@ func checkOnce(
 	return nil
 }
 
-// runFirstCheck builds a watcher, lets prepare set up the saved state
-// and stand-ins it starts from, and runs its checks once against live
-// DNS. When live DNS does not answer, the watcher is thrown away and
-// built again, so a failed attempt leaves nothing behind in the state
-// or the notifications.
-func runFirstCheck(
+// runChecks builds a watcher, lets prepare set up the saved state and
+// stand-ins it starts from, and runs its checks once against live DNS.
+// If change is not nil, change then alters the saved state or stand-ins
+// and the checks run a second time. When either check finds no fresh
+// address for a name (see checkOnce), the watcher is thrown away and
+// all of this runs again on a new one, so a failed attempt leaves
+// nothing behind in the saved state, the stand-ins or the notifications.
+func runChecks(
 	t *testing.T,
 	cfg *config.Config,
-	prepare func(deps *testDeps),
-) (*watcher.Watcher, *testDeps) {
+	prepare, change func(deps *testDeps),
+) *testDeps {
 	t.Helper()
 
-	var (
-		w    *watcher.Watcher
-		deps *testDeps
-	)
+	var deps *testDeps
+
+	livedns.Retry(t, "watcher checks", func(ctx context.Context) error {
+		var w *watcher.Watcher
 
-	livedns.Retry(t, "first check", func(ctx context.Context) error {
 		w, deps = newTestWatcher(t, cfg)
 
 		if prepare != nil {
 			prepare(deps)
 		}
 
+		err := checkOnce(ctx, w, deps)
+		if err != nil || change == nil {
+			return err
+		}
+
+		change(deps)
+
 		return checkOnce(ctx, w, deps)
 	})
 
-	return w, deps
-}
-
-// runCheck runs the watcher's checks once more against live DNS,
-// repeating them while live DNS does not answer. A failed lookup keeps
-// the name's saved records, so a repeat compares against the same
-// saved state.
-func runCheck(t *testing.T, w *watcher.Watcher, deps *testDeps) {
-	t.Helper()
-
-	livedns.Retry(t, "check", func(ctx context.Context) error {
-		return checkOnce(ctx, w, deps)
-	})
+	return deps
 }
 
 // addresses returns the A and AAAA values saved for a hostname.
@@ -299,7 +296,7 @@ func TestFirstRunBaseline(t *testing.T) {
 	cfg.Domains = []string{testDomain}
 	cfg.Hostnames = []string{testHost}
 
-	_, deps := runFirstCheck(t, cfg, nil)
+	deps := runChecks(t, cfg, nil, nil)
 
 	assertNoNotifications(t, deps)
 	assertStatePopulated(t, deps)
@@ -351,7 +348,7 @@ func TestDomainPortAndTLSChecks(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Domains = []string{testDomain}
 
-	_, deps := runFirstCheck(t, cfg, nil)
+	deps := runChecks(t, cfg, nil, nil)
 
 	snap := deps.state.GetSnapshot()
 
@@ -391,11 +388,11 @@ func TestNSChangeDetection(t *testing.T) {
 	cfg.Domains = []string{testDomain}
 
 	// The saved state lists nameservers that live DNS does not.
-	_, deps := runFirstCheck(t, cfg, func(deps *testDeps) {
+	deps := runChecks(t, cfg, func(deps *testDeps) {
 		deps.state.SetDomainState(testDomain, &state.DomainState{
 			Nameservers: []string{oldNS1, oldNS2},
 		})
-	})
+	}, nil)
 
 	assertNotified(t, deps, "NS Change: "+testDomain, "warning")
 
@@ -411,17 +408,16 @@ func TestRecordChangeDetection(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	w, deps := runFirstCheck(t, cfg, nil)
+	// Between the checks, save for every nameserver an address live DNS
+	// never returns.
+	deps := runChecks(t, cfg, nil, func(deps *testDeps) {
+		hs, _ := deps.state.GetHostnameState(testHost)
+		for _, nsState := range hs.RecordsByNameserver {
+			nsState.Records = map[string][]string{"A": {oldIP}}
+		}
 
-	// Save, for every nameserver, an address live DNS never returns.
-	hs, _ := deps.state.GetHostnameState(testHost)
-	for _, nsState := range hs.RecordsByNameserver {
-		nsState.Records = map[string][]string{"A": {oldIP}}
-	}
-
-	deps.state.SetHostnameState(testHost, hs)
-
-	runCheck(t, w, deps)
+		deps.state.SetHostnameState(testHost, hs)
+	})
 
 	assertNotified(t, deps, "Record Change: "+testHost, "warning")
 }
@@ -432,13 +428,12 @@ func TestPortStateChange(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	w, deps := runFirstCheck(t, cfg, nil)
-
-	deps.portChecker.mu.Lock()
-	deps.portChecker.closed = true
-	deps.portChecker.mu.Unlock()
-
-	runCheck(t, w, deps)
+	// Between the checks, every port closes.
+	deps := runChecks(t, cfg, nil, func(deps *testDeps) {
+		deps.portChecker.mu.Lock()
+		deps.portChecker.closed = true
+		deps.portChecker.mu.Unlock()
+	})
 
 	hs, _ := deps.state.GetHostnameState(testHost)
 	assertNotified(
@@ -458,7 +453,7 @@ func TestTLSExpiryWarning(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	_, deps := runFirstCheck(t, cfg, expiresInThreeDays)
+	deps := runChecks(t, cfg, expiresInThreeDays, nil)
 
 	assertNotified(t, deps, "TLS Expiry Warning: "+testHost, "warning")
 }
@@ -470,18 +465,19 @@ func TestTLSExpiryWarningDedup(t *testing.T) {
 	cfg.Hostnames = []string{testHost}
 	cfg.TLSInterval = 24 * time.Hour
 
-	w, deps := runFirstCheck(t, cfg, expiresInThreeDays)
-
 	title := "TLS Expiry Warning: " + testHost
 
-	warnings := countNotifications(deps, title)
-	if warnings == 0 {
-		t.Fatal("expected expiry warnings from the first check")
-	}
-
 	// The second check comes within the TLS interval of the first,
 	// so it must not warn again.
-	runCheck(t, w, deps)
+	var warnings int
+
+	deps := runChecks(t, cfg, expiresInThreeDays, func(deps *testDeps) {
+		warnings = countNotifications(deps, title)
+	})
+
+	if warnings == 0 {
+		t.Fatal("expected expiry warnings from the first check")
+	}
 
 	got := countNotifications(deps, title)
 	if got != warnings {
@@ -529,7 +525,7 @@ func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
 	cfg.Hostnames = []string{testHost}
 
 	// The saved state says the last check found testHost at oldIP.
-	_, deps := runFirstCheck(t, cfg, func(deps *testDeps) {
+	deps := runChecks(t, cfg, func(deps *testDeps) {
 		deps.state.SetHostnameState(testHost, &state.HostnameState{
 			RecordsByNameserver: map[string]*state.NameserverRecordState{
 				oldNS1: {
@@ -538,7 +534,7 @@ func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
 				},
 			},
 		})
-	})
+	}, nil)
 
 	snap := deps.state.GetSnapshot()
 
@@ -669,23 +665,21 @@ func TestNSFailureAndRecovery(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	w, deps := runFirstCheck(t, cfg, nil)
+	// Between the checks, save every nameserver the first check found
+	// as failed, and add, as answering, one that live DNS does not list.
+	deps := runChecks(t, cfg, nil, func(deps *testDeps) {
+		hs, _ := deps.state.GetHostnameState(testHost)
+		for _, nsState := range hs.RecordsByNameserver {
+			nsState.Status = "error"
+		}
 
-	// Save every nameserver the first check found as failed, and add
-	// one that live DNS does not list as having answered.
-	hs, _ := deps.state.GetHostnameState(testHost)
-	for _, nsState := range hs.RecordsByNameserver {
-		nsState.Status = "error"
-	}
+		hs.RecordsByNameserver[oldNS1] = &state.NameserverRecordState{
+			Records: map[string][]string{"A": {oldIP}},
+			Status:  "ok",
+		}
 
-	hs.RecordsByNameserver[oldNS1] = &state.NameserverRecordState{
-		Records: map[string][]string{"A": {oldIP}},
-		Status:  "ok",
-	}
-
-	deps.state.SetHostnameState(testHost, hs)
-
-	runCheck(t, w, deps)
+		deps.state.SetHostnameState(testHost, hs)
+	})
 
 	assertNotified(t, deps, "NS Failure: "+testHost, "error")
 	assertNotified(t, deps, "NS Recovery: "+testHost, "success")