Merge branch 'main' into fix/domain-port-tls-state-lookup

Reviewed-on: #30

Makefile

@@ -18,7 +18,7 @@ fmt:
 	goimports -w .
 
 test:
-	go test -v -race -cover -timeout 30s ./...
+	go test -v -race -cover ./...
 
 # Check runs all validation without making changes
 # Used by CI and Docker build - fails if anything is wrong
@@ -28,7 +28,7 @@ check:
 	@echo "==> Running linter..."
 	golangci-lint run --config .golangci.yml ./...
 	@echo "==> Running tests..."
-	go test -v -race -short -timeout 30s ./...
+	go test -v -race ./...
 	@echo "==> Building..."
 	go build -ldflags "$(LDFLAGS)" -o /dev/null ./cmd/dnswatcher
 	@echo "==> All checks passed!"

TESTING.md

@@ -0,0 +1,34 @@
+# Testing Policy
+
+## DNS Resolution Tests
+
+All resolver tests **MUST** use live queries against real DNS servers.
+No mocking of the DNS client layer is permitted.
+
+### Rationale
+
+The resolver performs iterative resolution from root nameservers through
+the full delegation chain. Mocked responses cannot faithfully represent
+the variety of real-world DNS behavior (truncation, referrals, glue
+records, DNSSEC, varied response times, EDNS, etc.). Testing against
+real servers ensures the resolver works correctly in production.
+
+### Constraints
+
+- Tests hit real DNS infrastructure and require network access
+- Test duration depends on network conditions; timeout tuning keeps
+  the suite within the 30-second target
+- Query timeout is calibrated to 3× maximum antipodal RTT (~300ms)
+  plus processing margin
+- Root server fan-out is limited to reduce parallel query load
+- Flaky failures from transient network issues are acceptable and
+  should be investigated as potential resolver bugs, not papered over
+  with mocks or skip flags
+
+### What NOT to do
+
+- **Do not mock `DNSClient`** for resolver tests (the mock constructor
+  exists for unit-testing other packages that consume the resolver)
+- **Do not add `-short` flags** to skip slow tests
+- **Do not increase `-timeout`** to hide hanging queries
+- **Do not modify linter configuration** to suppress findings

internal/resolver/iterative.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"math/rand"
 	"net"
 	"sort"
 	"strings"
@@ -13,7 +14,7 @@ import (
 )
 
 const (
-	queryTimeoutDuration = 5 * time.Second
+	queryTimeoutDuration = 2 * time.Second
 	maxRetries           = 2
 	maxDelegation        = 20
 	timeoutMultiplier    = 2
@@ -41,6 +42,22 @@ func rootServerList() []string {
 	}
 }
 
+const maxRootServers = 3
+
+// randomRootServers returns a shuffled subset of root servers.
+func randomRootServers() []string {
+	all := rootServerList()
+	rand.Shuffle(len(all), func(i, j int) {
+		all[i], all[j] = all[j], all[i]
+	})
+
+	if len(all) > maxRootServers {
+		return all[:maxRootServers]
+	}
+
+	return all
+}
+
 func checkCtx(ctx context.Context) error {
 	err := ctx.Err()
 	if err != nil {
@@ -302,7 +319,7 @@ func (r *Resolver) resolveNSRecursive(
 	msg.SetQuestion(domain, dns.TypeNS)
 	msg.RecursionDesired = true
 
-	for _, ip := range rootServerList()[:3] {
+	for _, ip := range randomRootServers() {
 		if checkCtx(ctx) != nil {
 			return nil, ErrContextCanceled
 		}
@@ -333,7 +350,7 @@ func (r *Resolver) resolveARecord(
 	msg.SetQuestion(hostname, dns.TypeA)
 	msg.RecursionDesired = true
 
-	for _, ip := range rootServerList()[:3] {
+	for _, ip := range randomRootServers() {
 		if checkCtx(ctx) != nil {
 			return nil, ErrContextCanceled
 		}
@@ -385,7 +402,7 @@ func (r *Resolver) FindAuthoritativeNameservers(
 		candidate := strings.Join(labels[i:], ".") + "."
 
 		nsNames, err := r.followDelegation(
-			ctx, candidate, rootServerList(),
+			ctx, candidate, randomRootServers(),
 		)
 		if err == nil && len(nsNames) > 0 {
 			sort.Strings(nsNames)

internal/resolver/resolver_test.go

@@ -34,12 +34,8 @@ func newTestResolver(t *testing.T) *resolver.Resolver {
 func testContext(t *testing.T) context.Context {
 	t.Helper()
 
-	if testing.Short() {
-		t.Skip("skipping integration test requiring real DNS")
-	}
-
 	ctx, cancel := context.WithTimeout(
-		context.Background(), 15*time.Second,
+		context.Background(), 60*time.Second,
 	)
 	t.Cleanup(cancel)
 

internal/watcher/watcher.go

@@ -206,6 +206,28 @@ func (w *Watcher) checkDomain(
 		Nameservers: nameservers,
 		LastChecked: now,
 	})
+
+	// Also look up A/AAAA records for the apex domain so that
+	// port and TLS checks (which read HostnameState) can find
+	// the domain's IP addresses.
+	records, err := w.resolver.LookupAllRecords(ctx, domain)
+	if err != nil {
+		w.log.Error(
+			"failed to lookup records for domain",
+			"domain", domain,
+			"error", err,
+		)
+
+		return
+	}
+
+	prevHS, hasPrevHS := w.state.GetHostnameState(domain)
+	if hasPrevHS && !w.firstRun {
+		w.detectHostnameChanges(ctx, domain, prevHS, records)
+	}
+
+	newState := buildHostnameState(records, now)
+	w.state.SetHostnameState(domain, newState)
 }
 
 func (w *Watcher) detectNSChanges(

internal/watcher/watcher_test.go

@@ -273,6 +273,10 @@ func setupBaselineMocks(deps *testDeps) {
 		"ns1.example.com.",
 		"ns2.example.com.",
 	}
+	deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
+		"ns1.example.com.": {"A": {"93.184.216.34"}},
+		"ns2.example.com.": {"A": {"93.184.216.34"}},
+	}
 	deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
 		"ns1.example.com.": {"A": {"93.184.216.34"}},
 		"ns2.example.com.": {"A": {"93.184.216.34"}},
@@ -290,6 +294,14 @@ func setupBaselineMocks(deps *testDeps) {
 			"www.example.com",
 		},
 	}
+	deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
+		CommonName: "example.com",
+		Issuer:     "DigiCert",
+		NotAfter:   time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			"example.com",
+		},
+	}
 }
 
 func assertNoNotifications(
@@ -322,14 +334,74 @@ func assertStatePopulated(
 		)
 	}
 
-	if len(snap.Hostnames) != 1 {
+	// Hostnames includes both explicit hostnames and domains
+	// (domains now also get hostname state for port/TLS checks).
+	if len(snap.Hostnames) < 1 {
 		t.Errorf(
-			"expected 1 hostname in state, got %d",
+			"expected at least 1 hostname in state, got %d",
 			len(snap.Hostnames),
 		)
 	}
 }
 
+func TestDomainPortAndTLSChecks(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{"example.com"}
+
+	w, deps := newTestWatcher(t, cfg)
+
+	deps.resolver.nsRecords["example.com"] = []string{
+		"ns1.example.com.",
+	}
+	deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
+		"ns1.example.com.": {"A": {"93.184.216.34"}},
+	}
+	deps.portChecker.results["93.184.216.34:80"] = true
+	deps.portChecker.results["93.184.216.34:443"] = true
+	deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
+		CommonName: "example.com",
+		Issuer:     "DigiCert",
+		NotAfter:   time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			"example.com",
+		},
+	}
+
+	w.RunOnce(t.Context())
+
+	snap := deps.state.GetSnapshot()
+
+	// Domain should have port state populated
+	if len(snap.Ports) == 0 {
+		t.Error("expected port state for domain, got none")
+	}
+
+	// Domain should have certificate state populated
+	if len(snap.Certificates) == 0 {
+		t.Error("expected certificate state for domain, got none")
+	}
+
+	// Verify port checker was actually called
+	deps.portChecker.mu.Lock()
+	calls := deps.portChecker.calls
+	deps.portChecker.mu.Unlock()
+
+	if calls == 0 {
+		t.Error("expected port checker to be called for domain")
+	}
+
+	// Verify TLS checker was actually called
+	deps.tlsChecker.mu.Lock()
+	tlsCalls := deps.tlsChecker.calls
+	deps.tlsChecker.mu.Unlock()
+
+	if tlsCalls == 0 {
+		t.Error("expected TLS checker to be called for domain")
+	}
+}
+
 func TestNSChangeDetection(t *testing.T) {
 	t.Parallel()
 
@@ -342,6 +414,12 @@ func TestNSChangeDetection(t *testing.T) {
 		"ns1.example.com.",
 		"ns2.example.com.",
 	}
+	deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
+		"ns1.example.com.": {"A": {"1.2.3.4"}},
+		"ns2.example.com.": {"A": {"1.2.3.4"}},
+	}
+	deps.portChecker.results["1.2.3.4:80"] = false
+	deps.portChecker.results["1.2.3.4:443"] = false
 
 	ctx := t.Context()
 	w.RunOnce(ctx)
@@ -351,6 +429,10 @@ func TestNSChangeDetection(t *testing.T) {
 		"ns1.example.com.",
 		"ns3.example.com.",
 	}
+	deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
+		"ns1.example.com.": {"A": {"1.2.3.4"}},
+		"ns3.example.com.": {"A": {"1.2.3.4"}},
+	}
 	deps.resolver.mu.Unlock()
 
 	w.RunOnce(ctx)
@@ -519,6 +601,11 @@ func TestGracefulShutdown(t *testing.T) {
 	deps.resolver.nsRecords["example.com"] = []string{
 		"ns1.example.com.",
 	}
+	deps.resolver.allRecords["example.com"] = map[string]map[string][]string{
+		"ns1.example.com.": {"A": {"1.2.3.4"}},
+	}
+	deps.portChecker.results["1.2.3.4:80"] = false
+	deps.portChecker.results["1.2.3.4:443"] = false
 
 	ctx, cancel := context.WithCancel(t.Context())