Enhance HistoryTable Component with Infinite Scroll and Cache Management

- Updated HistoryTable to implement infinite scrolling for loading history items dynamically.
- Introduced state management for accumulated history and total item count.
- Added Intersection Observer for triggering additional data fetches when scrolling.
- Implemented cache clearing functionality in the backend to manage voice prompt caches effectively.
- Improved loading indicators and user feedback for data fetching states.
- Refactored code for better readability and maintainability.

backend/backends/mlx_backend.py

@@ -175,7 +175,13 @@ class MLXTTSBackend:
             if cached_prompt is not None:
                 # Return cached prompt (should be dict format)
                 if isinstance(cached_prompt, dict):
-                    return cached_prompt, True
+                    # Validate that the cached audio file still exists
+                    cached_audio_path = cached_prompt.get("ref_audio") or cached_prompt.get("ref_audio_path")
+                    if cached_audio_path and Path(cached_audio_path).exists():
+                        return cached_prompt, True
+                    else:
+                        # Cached file no longer exists, invalidate cache
+                        print(f"Cached audio file not found: {cached_audio_path}, regenerating prompt")
         
         # MLX voice prompt format - store audio path and text
         # The model will process this during generation
@@ -263,6 +269,13 @@ class MLXTTSBackend:
             ref_audio = voice_prompt.get("ref_audio") or voice_prompt.get("ref_audio_path")
             ref_text = voice_prompt.get("ref_text", "")
             
+            # Validate that the audio file exists
+            if ref_audio and not Path(ref_audio).exists():
+                print(f"Warning: Audio file not found: {ref_audio}")
+                print("This may be due to a cached voice prompt referencing a deleted temp file.")
+                print("Regenerating without voice prompt.")
+                ref_audio = None
+            
             # Check if model supports voice cloning via generate method
             # MLX API may support ref_audio parameter directly
             try:

backend/backends/pytorch_backend.py

@@ -196,6 +196,8 @@ class PyTorchTTSBackend:
                 # Cache stores as torch.Tensor but actual prompt is dict
                 # Convert if needed
                 if isinstance(cached_prompt, dict):
+                    # For PyTorch backend, the dict should contain tensors, not file paths
+                    # So we can safely return it
                     return cached_prompt, True
                 elif isinstance(cached_prompt, torch.Tensor):
                     # Legacy cache format - convert to dict

backend/main.py

@@ -27,6 +27,7 @@ from . import database, models, profiles, history, tts, transcribe, config, expo
 from .database import get_db, Generation as DBGeneration, VoiceProfile as DBVoiceProfile
 from .utils.progress import get_progress_manager
 from .utils.tasks import get_task_manager
+from .utils.cache import clear_voice_prompt_cache
 from .platform_detect import get_backend_type
 
 app = FastAPI(
@@ -1495,6 +1496,19 @@ async def delete_model(model_name: str):
         raise HTTPException(status_code=500, detail=f"Failed to delete model: {str(e)}")
 
 
+@app.post("/cache/clear")
+async def clear_cache():
+    """Clear all voice prompt caches (memory and disk)."""
+    try:
+        deleted_count = clear_voice_prompt_cache()
+        return {
+            "message": f"Voice prompt cache cleared successfully",
+            "files_deleted": deleted_count,
+        }
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Failed to clear cache: {str(e)}")
+
+
 # ============================================
 # TASK MANAGEMENT
 # ============================================

backend/profiles.py

@@ -22,6 +22,7 @@ from .database import (
 )
 from .utils.audio import validate_reference_audio, load_audio, save_audio
 from .utils.images import validate_image, process_avatar
+from .utils.cache import _get_cache_dir
 from .tts import get_tts_model
 from . import config
 
@@ -345,23 +346,27 @@ async def create_voice_prompt_for_profile(
             reference_texts,
         )
 
-        # Save combined audio temporarily
-        import tempfile
-        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp:
-            save_audio(combined_audio, tmp.name, 24000)
-            tmp_path = tmp.name
+        # Save combined audio to cache directory (persistent)
+        # Create a hash of sample IDs to identify this specific combination
+        import hashlib
+        sample_ids_str = "-".join(sorted([s.id for s in samples]))
+        combination_hash = hashlib.md5(sample_ids_str.encode()).hexdigest()[:12]
+        
+        # Store in cache directory
+        cache_dir = _get_cache_dir()
+        cache_dir.mkdir(parents=True, exist_ok=True)
+        combined_path = cache_dir / f"combined_{profile_id}_{combination_hash}.wav"
+        
+        # Save combined audio
+        save_audio(combined_audio, str(combined_path), 24000)
 
-        try:
-            # Create prompt from combined audio
-            voice_prompt, _ = await tts_model.create_voice_prompt(
-                tmp_path,
-                combined_text,
-                use_cache=use_cache,
-            )
-            return voice_prompt
-        finally:
-            # Clean up temp file
-            Path(tmp_path).unlink(missing_ok=True)
+        # Create prompt from combined audio
+        voice_prompt, _ = await tts_model.create_voice_prompt(
+            str(combined_path),
+            combined_text,
+            use_cache=use_cache,
+        )
+        return voice_prompt
 
 
 async def upload_avatar(

backend/utils/cache.py

@@ -88,3 +88,28 @@ def cache_voice_prompt(
     # Store on disk (torch.save can handle both dicts and tensors)
     cache_file = _get_cache_dir() / f"{cache_key}.prompt"
     torch.save(voice_prompt, cache_file)
+
+
+def clear_voice_prompt_cache() -> int:
+    """
+    Clear all voice prompt caches (memory and disk).
+    
+    Returns:
+        Number of cache files deleted
+    """
+    # Clear memory cache
+    _memory_cache.clear()
+    
+    # Clear disk cache
+    cache_dir = _get_cache_dir()
+    deleted_count = 0
+    
+    if cache_dir.exists():
+        for cache_file in cache_dir.glob("*.prompt"):
+            try:
+                cache_file.unlink()
+                deleted_count += 1
+            except Exception as e:
+                print(f"Failed to delete cache file {cache_file}: {e}")
+    
+    return deleted_count