Add 80% limit warning, stop repeat notifications, fix review findings

Notifications:
- Warn once when a counter reaches warn_percent of its limit, through
  separate warn_*_url endpoints.
- Write ntf/ markers so a lost Redis reply cannot re-send a breach.
- Retry only when the request never left or the web app answered 429/5xx.

Fixes:
- Retry transactions Redis rejected; treat pool timeouts as definite.
- Install the signal handler before startup work.
- Stop logging the login suffix; redact notify URL credentials.
- Reject corrupt or empty CDBs, truncated hash tables included.
- Require a Sentinel password, refuse example placeholders, and default
  admin_addr to localhost.
- Normalise /counters domains, count on the arrival day, log rejections,
  hide internals in errors and exit 1 on a failed drain.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

cmd/migadu_counters/main.go

@@ -44,6 +44,9 @@ var (
 	date    = "unknown"
 )
 
+// beforeStartup lets tests act right after the signal handler is installed.
+var beforeStartup func()
+
 func main() {
 	os.Exit(run(os.Args[1:], os.Stdout, os.Stderr, nil))
 }
@@ -63,6 +66,18 @@ func run(args []string, stdout, stderr io.Writer, sigs <-chan os.Signal) int {
 		return 0
 	}
 
+	// Installed before anything slow: a SIGHUP's default action is to kill the
+	// process. Signals that arrive during startup wait in the channel.
+	if sigs == nil {
+		ch := make(chan os.Signal, 8)
+		signal.Notify(ch, syscall.SIGHUP, syscall.SIGTERM, syscall.SIGINT)
+		defer signal.Stop(ch)
+		sigs = ch
+	}
+	if beforeStartup != nil {
+		beforeStartup()
+	}
+
 	path, err := config.Discover(*configPath)
 	if err != nil {
 		fmt.Fprintln(stderr, err)
@@ -93,12 +108,6 @@ func run(args []string, stdout, stderr io.Writer, sigs <-chan os.Signal) int {
 	}
 	a.Serve(apiLn, adminLn)
 
-	if sigs == nil {
-		ch := make(chan os.Signal, 2)
-		signal.Notify(ch, syscall.SIGHUP, syscall.SIGTERM, syscall.SIGINT)
-		defer signal.Stop(ch)
-		sigs = ch
-	}
 	for {
 		select {
 		case sig := <-sigs:
@@ -115,6 +124,7 @@ func run(args []string, stdout, stderr io.Writer, sigs <-chan os.Signal) int {
 			cancel()
 			if err != nil {
 				fmt.Fprintf(stderr, "shutdown: %v\n", err)
+				return 1
 			}
 			return 0
 		case err := <-a.fatal:
@@ -166,6 +176,11 @@ func newApp(cfg *config.Config) (*app, error) {
 		logWriter.Close()
 		return nil, err
 	}
+	if db.Count() == 0 {
+		db.Close()
+		logWriter.Close()
+		return nil, fmt.Errorf("domains db %s holds no records", cfg.DomainsCDB)
+	}
 	a.db.Store(db)
 	logger.Info("domains db loaded", "path", cfg.DomainsCDB, "domains", db.Count(), "max_cached_domains", cfg.MaxCachedDomains)
 
@@ -209,6 +224,7 @@ func newApp(cfg *config.Config) (*app, error) {
 
 	a.notifier = notify.New(notify.Config{
 		OrgURL: cfg.Notify.OrgURL, AddressURL: cfg.Notify.AddressURL, DomainURL: cfg.Notify.DomainURL,
+		WarnOrgURL: cfg.Notify.WarnOrgURL, WarnAddressURL: cfg.Notify.WarnAddressURL, WarnDomainURL: cfg.Notify.WarnDomainURL,
 		User: cfg.Notify.User, Password: cfg.Notify.Password, Timeout: cfg.Notify.Timeout(),
 	}, server.NotifyHooks(tx, a.m))
 
@@ -220,8 +236,9 @@ func newApp(cfg *config.Config) (*app, error) {
 			}
 			return db.Lookup(domain)
 		}),
-		Exempt:    cfg.ExemptSet(),
-		CountJunk: cfg.CountJunk,
+		Exempt:      cfg.ExemptSet(),
+		CountJunk:   cfg.CountJunk,
+		WarnPercent: cfg.Notify.EffectiveWarnPercent(),
 	}
 	a.srv = server.New(server.Deps{
 		AuthToken:      cfg.AuthToken,

cmd/migadu_counters/main_test.go

@@ -415,3 +415,50 @@ func TestRun_SignalLoop(t *testing.T) {
 		t.Errorf("log:\n%s", e.logs())
 	}
 }
+
+// A SIGHUP while the daemon starts must not kill it, and the reload it asked
+// for runs once the daemon is ready.
+func TestRun_SIGHUPDuringStartupIsQueued(t *testing.T) {
+	e := newEnv(t, "")
+	beforeStartup = func() { syscall.Kill(os.Getpid(), syscall.SIGHUP) }
+	t.Cleanup(func() { beforeStartup = nil })
+	done := make(chan int, 1)
+	var out, errb bytes.Buffer
+	go func() { done <- run([]string{"-config", e.cfgPath}, &out, &errb, nil) }()
+
+	deadline := time.Now().Add(5 * time.Second)
+	for !strings.Contains(e.logs(), "domains db reloaded") {
+		if time.Now().After(deadline) {
+			t.Fatalf("the early SIGHUP was not honoured; log:\n%s", e.logs())
+		}
+		time.Sleep(20 * time.Millisecond)
+	}
+	syscall.Kill(os.Getpid(), syscall.SIGTERM)
+	select {
+	case code := <-done:
+		if code != 0 {
+			t.Errorf("exit code %d, stderr %q", code, errb.String())
+		}
+	case <-time.After(15 * time.Second):
+		t.Fatal("run did not return after SIGTERM")
+	}
+}
+
+func TestNewApp_EmptyCDBIsFatal(t *testing.T) {
+	e := newEnv(t, "")
+	w, err := cdb.Create(e.cdbPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := w.Close(); err != nil {
+		t.Fatal(err)
+	}
+	cfg, err := config.Load(e.cfgPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if a, err := newApp(cfg); err == nil {
+		a.Shutdown(context.Background())
+		t.Fatal("an empty domains db must be fatal at startup")
+	}
+}