Fix: Avatar/media path resolution and voice clone dependencies

- Remove nltk dependency from step4_assets by inlining _extract_user_id
- Add graceful error handling for step4_assets in podcast-only mode
- Fix media_utils.py to use tenant-aware get_podcast_media_read_dirs()
- Resolves avatar image 404 during scene image generation

backend/api/onboarding_utils/step4_asset_routes.py

@@ -9,8 +9,21 @@ from fastapi.responses import FileResponse
 from sqlalchemy.orm import Session
 from pydantic import BaseModel
 from loguru import logger
-from .step4_persona_routes import _extract_user_id
 from middleware.auth_middleware import get_current_user
+
+
+def _extract_user_id(user: Dict[str, Any]) -> str:
+    """Extract a stable user ID from Clerk-authenticated user payloads.
+    Prefers 'clerk_user_id' or 'id', falls back to 'user_id', else 'unknown'.
+    """
+    if not isinstance(user, dict):
+        return 'unknown'
+    return (
+        user.get('clerk_user_id')
+        or user.get('id')
+        or user.get('user_id')
+        or 'unknown'
+    )
 import base64
 import os
 from pathlib import Path

backend/app.py

@@ -426,13 +426,15 @@ if PODCAST_ONLY_DEMO_MODE:
     podcast_routers = [r for r in CORE_ROUTER_REGISTRY if "podcast" in r.get("features", set())]
     logger.info(f"[PODCAST-ONLY] Found {len(podcast_routers)} podcast routers: {[r['name'] for r in podcast_routers]}")
     
-    # Force include step4_assets for voice cloning
+    # Try to include step4_assets for voice cloning (may fail if nltk not installed)
     step4_entry = next((r for r in CORE_ROUTER_REGISTRY if r.get("name") == "step4_assets"), None)
     if step4_entry:
         try:
-            logger.info(f"[PODCAST-ONLY] Forcing load of step4_assets for voice cloning")
+            logger.info(f"[PODCAST-ONLY] Attempting to load step4_assets for voice cloning")
             router = router_manager._load_router_from_registry(step4_entry)
             router_manager.include_router_safely(router, step4_entry["name"], step4_entry.get("include_kwargs"))
+        except ImportError as e:
+            logger.warning(f"[PODCAST-ONLY] Skipping step4_assets (missing optional dependency): {e}")
         except Exception as e:
             logger.error(f"[PODCAST-ONLY] Failed to mount step4_assets: {e}")
     

backend/utils/media_utils.py

@@ -97,13 +97,22 @@ def resolve_media_path(media_url_or_path: str) -> Optional[Path]:
             # Prioritize YouTube paths
             pass # Already first in list
         elif "/api/podcast/" in media_url_or_path:
-            # Prioritize Podcast paths
+            # Prioritize Podcast paths: use centralized podcast media resolution
-            search_paths = [
+            try:
-                PODCAST_AVATARS_DIR / filename,
+                # Import the centralized function that checks tenant workspace first
-                PODCAST_IMAGES_DIR / filename,
+                from api.podcast.constants import get_podcast_media_read_dirs
-                YOUTUBE_AVATARS_DIR / filename,
+                podcast_dirs = get_podcast_media_read_dirs("image")
-                YOUTUBE_IMAGES_DIR / filename
+                search_paths = []
-            ]
+                for pod_dir in podcast_dirs:
+                    # Add both avatar and image subdirectories
+                    search_paths.append(pod_dir / "avatars" / filename)
+                    search_paths.append(pod_dir / filename)
+            except ImportError:
+                # Fallback if podcast constants not available
+                search_paths = [
+                    PODCAST_AVATARS_DIR / filename,
+                    PODCAST_IMAGES_DIR / filename,
+                ]
             
         # Iterate and find first existing file
         for path in search_paths: