Fail loudly on half-set metrics auth credentials (closes #205) (#216)

internal/config/config.go

@@ -71,6 +71,16 @@ var ErrInvalidPort = errors.New("invalid port")
 // nor a bare IP address.
 var ErrInvalidCIDR = errors.New("invalid CIDR")
 
+// ErrIncompleteMetricsAuth is returned when exactly one of
+// METRICS_USERNAME and METRICS_PASSWORD carries a value. Neither
+// fallback is acceptable: serving /metrics on the username alone
+// publishes an endpoint whose password is the empty string, and
+// silently leaving it unmounted withholds an endpoint the operator
+// asked for. Half-set is a configuration error, so startup fails.
+var ErrIncompleteMetricsAuth = errors.New(
+	"incomplete metrics credentials",
+)
+
 //nolint:revive // ConfigParams is a standard fx naming convention.
 type ConfigParams struct {
 	fx.In
@@ -128,6 +138,21 @@ func (c *Config) IsProd() bool {
 	return c.Environment == EnvironmentProd
 }
 
+// MetricsAuthEnabled reports whether /metrics is served behind basic
+// auth. It is the only answer to that question in the codebase: the
+// route mount, the Prometheus recording middleware and the startup
+// log's hasMetricsAuth field all read this one method, so the log
+// cannot report auth as off while the route is mounted.
+//
+// It requires both credentials rather than the username alone.
+// loadFromEnv already rejects a half-set pair, but a Config built in
+// code bypasses that, and the failure mode this guards is an endpoint
+// mounted with a credential map whose only password is the empty
+// string.
+func (c *Config) MetricsAuthEnabled() bool {
+	return c.MetricsUsername != "" && c.MetricsPassword != ""
+}
+
 // envString returns the value of the named environment variable,
 // or an empty string if not set.
 func envString(key string) string {
@@ -329,6 +354,30 @@ func envPrefixList(key string) ([]netip.Prefix, error) {
 	return prefixes, nil
 }
 
+// resolveMetricsAuth reads the /metrics basic-auth credentials and
+// rejects a half-set pair, naming both variables either way. The
+// error carries neither value: the password is a secret.
+func resolveMetricsAuth() (string, string, error) {
+	username := envString("METRICS_USERNAME")
+	password := envString("METRICS_PASSWORD")
+
+	if (username == "") == (password == "") {
+		return username, password, nil
+	}
+
+	set, empty := "METRICS_USERNAME", "METRICS_PASSWORD"
+	if username == "" {
+		set, empty = empty, set
+	}
+
+	return "", "", fmt.Errorf(
+		"%w: %s is set but %s is empty; METRICS_USERNAME and "+
+			"METRICS_PASSWORD must both be set to serve /metrics, "+
+			"or both be empty to leave it unmounted",
+		ErrIncompleteMetricsAuth, set, empty,
+	)
+}
+
 // resolveEnvironment reads WEBHOOKER_ENVIRONMENT, defaulting to
 // dev, and rejects unrecognised values.
 func resolveEnvironment() (string, error) {
@@ -406,13 +455,18 @@ func loadFromEnv() (*Config, error) {
 		return nil, err
 	}
 
+	metricsUsername, metricsPassword, err := resolveMetricsAuth()
+	if err != nil {
+		return nil, err
+	}
+
 	return &Config{
 		DataDir:                envString("DATA_DIR"),
 		Debug:                  debug,
 		MaintenanceMode:        maintenanceMode,
 		Environment:            environment,
-		MetricsUsername:        envString("METRICS_USERNAME"),
-		MetricsPassword:        envString("METRICS_PASSWORD"),
+		MetricsUsername:        metricsUsername,
+		MetricsPassword:        metricsPassword,
 		Port:                   port,
 		SentryDSN:              envString("SENTRY_DSN"),
 		RetentionSweepInterval: retentionSweepInterval,
@@ -512,8 +566,7 @@ func New(lc fx.Lifecycle, params ConfigParams) (*Config, error) {
 		"receiverRateLimit", s.ReceiverRateLimit,
 		"trustedProxies", len(s.TrustedProxies),
 		"hasSentryDSN", s.SentryDSN != "",
-		"hasMetricsAuth",
-		s.MetricsUsername != "" && s.MetricsPassword != "",
+		"hasMetricsAuth", s.MetricsAuthEnabled(),
 	)
 
 	s.warnSharedRateLimitBucket(log)