1 Commits

Author SHA1 Message Date
clawbot
82fd68a41b fix: deduplicate TLS expiry warnings to prevent notification spam (closes #18)
Some checks failed
Check / check (pull_request) Failing after 5m31s
checkTLSExpiry fired every monitoring cycle with no deduplication,
causing notification spam for expiring certificates. Added an
in-memory map tracking the last notification time per domain/IP
pair, suppressing re-notification within the TLS check interval.

Added TestTLSExpiryWarningDedup to verify deduplication works.
2026-02-21 00:54:59 -08:00
4 changed files with 109 additions and 43 deletions

View File

@@ -13,7 +13,7 @@ import (
) )
const ( const (
queryTimeoutDuration = 700 * time.Millisecond queryTimeoutDuration = 5 * time.Second
maxRetries = 2 maxRetries = 2
maxDelegation = 20 maxDelegation = 20
timeoutMultiplier = 2 timeoutMultiplier = 2
@@ -291,17 +291,8 @@ func (r *Resolver) resolveNSIPs(
return ips return ips
} }
// publicResolvers returns well-known public recursive DNS resolvers. // resolveNSRecursive queries for NS records using recursive
func publicResolvers() []string { // resolution as a fallback for intercepted environments.
return []string{
"1.1.1.1", // Cloudflare
"8.8.8.8", // Google
"9.9.9.9", // Quad9
}
}
// resolveNSRecursive queries for NS records using a public
// recursive resolver as a fallback for intercepted environments.
func (r *Resolver) resolveNSRecursive( func (r *Resolver) resolveNSRecursive(
ctx context.Context, ctx context.Context,
domain string, domain string,
@@ -311,7 +302,7 @@ func (r *Resolver) resolveNSRecursive(
msg.SetQuestion(domain, dns.TypeNS) msg.SetQuestion(domain, dns.TypeNS)
msg.RecursionDesired = true msg.RecursionDesired = true
for _, ip := range publicResolvers() { for _, ip := range rootServerList()[:3] {
if checkCtx(ctx) != nil { if checkCtx(ctx) != nil {
return nil, ErrContextCanceled return nil, ErrContextCanceled
} }
@@ -332,8 +323,7 @@ func (r *Resolver) resolveNSRecursive(
return nil, ErrNoNameservers return nil, ErrNoNameservers
} }
// resolveARecord resolves a hostname to IPv4 addresses using // resolveARecord resolves a hostname to IPv4 addresses.
// public recursive resolvers.
func (r *Resolver) resolveARecord( func (r *Resolver) resolveARecord(
ctx context.Context, ctx context.Context,
hostname string, hostname string,
@@ -343,7 +333,7 @@ func (r *Resolver) resolveARecord(
msg.SetQuestion(hostname, dns.TypeA) msg.SetQuestion(hostname, dns.TypeA)
msg.RecursionDesired = true msg.RecursionDesired = true
for _, ip := range publicResolvers() { for _, ip := range rootServerList()[:3] {
if checkCtx(ctx) != nil { if checkCtx(ctx) != nil {
return nil, ErrContextCanceled return nil, ErrContextCanceled
} }

View File

@@ -156,8 +156,8 @@ func (s *State) Load() error {
// Save writes the current state to disk atomically. // Save writes the current state to disk atomically.
func (s *State) Save() error { func (s *State) Save() error {
s.mu.Lock() s.mu.RLock()
defer s.mu.Unlock() defer s.mu.RUnlock()
s.snapshot.LastUpdated = time.Now().UTC() s.snapshot.LastUpdated = time.Now().UTC()

View File

@@ -6,6 +6,7 @@ import (
"log/slog" "log/slog"
"sort" "sort"
"strings" "strings"
"sync"
"time" "time"
"go.uber.org/fx" "go.uber.org/fx"
@@ -49,6 +50,8 @@ type Watcher struct {
notify Notifier notify Notifier
cancel context.CancelFunc cancel context.CancelFunc
firstRun bool firstRun bool
expiryNotifiedMu sync.Mutex
expiryNotified map[string]time.Time
} }
// New creates a new Watcher instance wired into the fx lifecycle. // New creates a new Watcher instance wired into the fx lifecycle.
@@ -65,6 +68,7 @@ func New(
tlsCheck: params.TLSCheck, tlsCheck: params.TLSCheck,
notify: params.Notify, notify: params.Notify,
firstRun: true, firstRun: true,
expiryNotified: make(map[string]time.Time),
} }
lifecycle.Append(fx.Hook{ lifecycle.Append(fx.Hook{
@@ -108,6 +112,7 @@ func NewForTest(
tlsCheck: tc, tlsCheck: tc,
notify: n, notify: n,
firstRun: true, firstRun: true,
expiryNotified: make(map[string]time.Time),
} }
} }
@@ -691,6 +696,22 @@ func (w *Watcher) checkTLSExpiry(
return 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( msg := fmt.Sprintf(
"Host: %s\nIP: %s\nCN: %s\n"+ "Host: %s\nIP: %s\nCN: %s\n"+
"Expires: %s (%.0f days)", "Expires: %s (%.0f days)",

View File

@@ -506,6 +506,61 @@ func TestTLSExpiryWarning(t *testing.T) {
} }
} }
func TestTLSExpiryWarningDedup(t *testing.T) {
t.Parallel()
cfg := defaultTestConfig(t)
cfg.Hostnames = []string{"www.example.com"}
cfg.TLSInterval = 24 * time.Hour
w, deps := newTestWatcher(t, cfg)
deps.resolver.allRecords["www.example.com"] = map[string]map[string][]string{
"ns1.example.com.": {"A": {"1.2.3.4"}},
}
deps.resolver.ipAddresses["www.example.com"] = []string{
"1.2.3.4",
}
deps.portChecker.results["1.2.3.4:80"] = true
deps.portChecker.results["1.2.3.4:443"] = true
deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
CommonName: "www.example.com",
Issuer: "DigiCert",
NotAfter: time.Now().Add(3 * 24 * time.Hour),
SubjectAlternativeNames: []string{
"www.example.com",
},
}
ctx := t.Context()
// First run = baseline, no notifications
w.RunOnce(ctx)
// Second run should fire one expiry warning
w.RunOnce(ctx)
// Third run should NOT fire another warning (dedup)
w.RunOnce(ctx)
notifications := deps.notifier.getNotifications()
expiryCount := 0
for _, n := range notifications {
if n.Title == "TLS Expiry Warning: www.example.com" {
expiryCount++
}
}
if expiryCount != 1 {
t.Errorf(
"expected exactly 1 expiry warning (dedup), got %d",
expiryCount,
)
}
}
func TestGracefulShutdown(t *testing.T) { func TestGracefulShutdown(t *testing.T) {
t.Parallel() t.Parallel()