Add LM Model selector (0.6B/1.7B/4B) with auto-download

- Add lmModel parameter through full chain (types, API, routes, service)
- Add LM Model dropdown in Advanced Settings (defaults to 0.6B)
- Pass lmModel and lmBackend to format/enhance endpoint
- Update format_sample.py to accept --lm-model and --lm-backend args
- Auto-download model from HuggingFace if not present locally
- Persist model selection in localStorage
- Improve format route error logging with exit code and stdout/stderr

Fixes #9

services/api.ts

@@ -234,6 +234,7 @@ export interface GenerationParams {
   lmTopP?: number;
   lmNegativePrompt?: string;
   lmBackend?: 'pt' | 'vllm';
+  lmModel?: string;
 
   // Expert Parameters
   referenceAudioUrl?: string;
@@ -317,6 +318,8 @@ export const generateApi = {
     temperature?: number;
     topK?: number;
     topP?: number;
+    lmModel?: string;
+    lmBackend?: string;
   }, token: string): Promise<{
     success: boolean;
     caption?: string;