Stream WhisperX uploads safely

internal/config/validate.go

@@ -395,11 +395,11 @@ func validateWhisperX(cfg WhisperXConfig) error {
 		return fmt.Errorf("pipeline.whisperx.transcribe_url is required")
 	}
 	u, err := url.Parse(cfg.TranscribeURL)
-	if err != nil || u.Scheme == "" || u.Host == "" {
+	if err != nil || !u.IsAbs() || u.Host == "" || (strings.ToLower(u.Scheme) != "http" && strings.ToLower(u.Scheme) != "https") {
 		if err != nil {
-			return fmt.Errorf("pipeline.whisperx.transcribe_url must be a valid URL: %w", err)
+			return fmt.Errorf("pipeline.whisperx.transcribe_url must be an absolute http or https URL: %w", err)
 		}
-		return fmt.Errorf("pipeline.whisperx.transcribe_url must be a valid URL")
+		return fmt.Errorf("pipeline.whisperx.transcribe_url must be an absolute http or https URL")
 	}
 	if err := validateDuration("pipeline.whisperx.timeout", cfg.Timeout); err != nil {
 		return err

internal/config/validation_duration_test.go

@@ -39,6 +39,33 @@ func TestValidateDurationsRequirePositiveValues(t *testing.T) {
 	}
 }
 
+func TestValidateWhisperXRequiresAbsoluteHTTPSEndpoint(t *testing.T) {
+	retries := 0
+	concurrency := 1
+	base := WhisperXConfig{
+		Language:    "en",
+		Timeout:     "1s",
+		Retries:     &retries,
+		RetryDelay:  "0s",
+		Concurrency: &concurrency,
+	}
+
+	for _, endpoint := range []string{"ftp://example.com/transcribe", "file:///tmp/transcribe", "//example.com/transcribe", "https:/missing-host"} {
+		cfg := base
+		cfg.TranscribeURL = endpoint
+		if err := validateWhisperX(cfg); err == nil || !strings.Contains(err.Error(), "absolute http or https URL") {
+			t.Errorf("validateWhisperX(%q) error = %v, want HTTP(S) endpoint validation", endpoint, err)
+		}
+	}
+	for _, endpoint := range []string{"http://example.com/transcribe", "https://example.com/transcribe"} {
+		cfg := base
+		cfg.TranscribeURL = endpoint
+		if err := validateWhisperX(cfg); err != nil {
+			t.Errorf("validateWhisperX(%q) error = %v", endpoint, err)
+		}
+	}
+}
+
 func TestValidateNotariusTimeoutRequiresPositiveValue(t *testing.T) {
 	for _, value := range []string{"0s", "-1ms"} {
 		t.Run(value, func(t *testing.T) {