Use tenant-scoped dubbed audio paths with safe file resolution

backend/api/podcast/handlers/dubbing.py

@@ -29,16 +29,45 @@ from ..models import (
     VoiceCloneResult,
 )
 from services.dubbing import AudioDubbingService
+from ..constants import get_podcast_media_read_dirs, get_podcast_media_dir
 
 router = APIRouter()
 
 _dubbing_executor = ThreadPoolExecutor(max_workers=4, thread_name_prefix="podcast_dubbing")
 
-DUBBED_AUDIO_DIR = Path(__file__).resolve().parents[3] / "data" / "media" / "dubbed_audio"
+_DUBBED_AUDIO_SUBDIR = Path("dubbed_audio")
+_LEGACY_DUBBED_AUDIO_DIR = Path(__file__).resolve().parents[3] / "data" / "media" / "dubbed_audio"
 
 
-def _ensure_dubbed_audio_dir():
+def _get_dubbed_audio_dir(user_id: str, *, ensure_exists: bool = False) -> Path:
-    DUBBED_AUDIO_DIR.mkdir(parents=True, exist_ok=True)
+    """Resolve tenant-scoped dubbed audio directory under podcast audio media."""
+    base_dir = get_podcast_media_dir("audio", user_id, ensure_exists=ensure_exists)
+    dubbed_dir = (base_dir / _DUBBED_AUDIO_SUBDIR).resolve()
+    if ensure_exists:
+        dubbed_dir.mkdir(parents=True, exist_ok=True)
+    return dubbed_dir
+
+
+def _resolve_dubbed_audio_file(filename: str, user_id: str) -> Path:
+    """Resolve dubbed audio with traversal-safe checks (tenant first, then legacy fallback)."""
+    clean_filename = filename.split("?", 1)[0].strip()
+    if not clean_filename:
+        raise HTTPException(status_code=400, detail="Invalid filename")
+
+    candidate_dirs: list[Path] = []
+    for base_dir in get_podcast_media_read_dirs("audio", user_id):
+        candidate_dirs.append((base_dir / _DUBBED_AUDIO_SUBDIR).resolve())
+    candidate_dirs.append(_LEGACY_DUBBED_AUDIO_DIR.resolve())
+
+    for target_dir in candidate_dirs:
+        candidate = (target_dir / clean_filename).resolve()
+        if not str(candidate).startswith(str(target_dir)):
+            logger.error(f"[Podcast][Dubbing] Attempted path traversal: {filename}")
+            raise HTTPException(status_code=403, detail="Invalid audio path")
+        if candidate.exists():
+            return candidate
+
+    raise HTTPException(status_code=404, detail="Audio file not found")
 
 
 def _execute_dubbing_task(
@@ -62,9 +91,8 @@ def _execute_dubbing_task(
             message="Starting audio dubbing..."
         )
         
-        _ensure_dubbed_audio_dir()
+        dubbed_audio_dir = _get_dubbed_audio_dir(user_id, ensure_exists=True)
-        
+        service = AudioDubbingService(output_dir=dubbed_audio_dir)
-        service = AudioDubbingService(output_dir=DUBBED_AUDIO_DIR)
         
         def progress_callback(progress: float, message: str):
             task_manager.update_task_status(
@@ -136,9 +164,8 @@ def _execute_voice_clone_task(
             message="Starting voice cloning..."
         )
         
-        _ensure_dubbed_audio_dir()
+        dubbed_audio_dir = _get_dubbed_audio_dir(user_id, ensure_exists=True)
-        
+        service = AudioDubbingService(output_dir=dubbed_audio_dir)
-        service = AudioDubbingService(output_dir=DUBBED_AUDIO_DIR)
         
         task_manager.update_task_status(
             task_id, "processing", progress=30.0,
@@ -301,12 +328,7 @@ async def serve_dubbed_audio(
     """
     user_id = require_authenticated_user(current_user)
     
-    _ensure_dubbed_audio_dir()
+    audio_path = _resolve_dubbed_audio_file(filename, user_id)
-    
-    audio_path = DUBBED_AUDIO_DIR / filename
-    
-    if not audio_path.exists():
-        raise HTTPException(status_code=404, detail="Audio file not found")
     
     return FileResponse(
         path=audio_path,
@@ -327,7 +349,8 @@ async def estimate_dubbing_cost(
     """
     user_id = require_authenticated_user(current_user)
     
-    service = AudioDubbingService(output_dir=DUBBED_AUDIO_DIR)
+    dubbed_audio_dir = _get_dubbed_audio_dir(user_id, ensure_exists=True)
+    service = AudioDubbingService(output_dir=dubbed_audio_dir)
     
     cost_estimate = service.estimate_cost(
         audio_duration_seconds=request.audio_duration_seconds,
@@ -479,12 +502,12 @@ async def serve_voice_audio(
     """
     user_id = require_authenticated_user(current_user)
     
-    _ensure_dubbed_audio_dir()
+    try:
-    
+        audio_path = _resolve_dubbed_audio_file(filename, user_id)
-    audio_path = DUBBED_AUDIO_DIR / filename
+    except HTTPException as exc:
-    
+        if exc.status_code == 404:
-    if not audio_path.exists():
+            raise HTTPException(status_code=404, detail="Voice audio file not found") from exc
-        raise HTTPException(status_code=404, detail="Voice audio file not found")
+        raise
     
     return FileResponse(
         path=audio_path,

backend/app.py

@@ -48,9 +48,6 @@ load_dotenv(backend_dir / '.env')  # backend/.env
 load_dotenv(project_root / '.env')  # root .env (fallback)
 load_dotenv()  # CWD .env (fallback)
 
-# Feature flags (read early so app wiring can rely on a single source of truth)
-PODCAST_ONLY_DEMO_MODE = os.getenv("PODCAST_ONLY_DEMO_MODE", "false").lower() == "true"
-
 # Set up clean logging for end users
 from logging_config import setup_clean_logging
 setup_clean_logging()
@@ -408,62 +405,48 @@ async def analyze_urls_ai_endpoint(request: AnalyzeURLsRequest, current_user: di
     """Run AI-powered SEO analysis on selected URLs."""
     return await analyze_urls_ai(request, current_user)
 
-# Centralized mode helpers for router wiring.
+# Include platform analytics router
-# Keep all mode decisions in this section to avoid scattered env checks.
+from routers.platform_analytics import router as platform_analytics_router
-def is_podcast_only_demo_mode() -> bool:
+app.include_router(platform_analytics_router)
-    return PODCAST_ONLY_DEMO_MODE
+# Include Bing Analytics Storage router to expose storage-backed endpoints
+from routers.bing_analytics_storage import router as bing_analytics_storage_router
+app.include_router(bing_analytics_storage_router)
+app.include_router(images_router)
+app.include_router(image_studio_router)
+app.include_router(product_marketing_router)
+app.include_router(campaign_creator_router)
 
+# Include content assets router
+from api.content_assets.router import router as content_assets_router
+app.include_router(content_assets_router)
 
-def should_include_non_podcast_routers() -> bool:
+# Include Podcast Maker router
-    return not is_podcast_only_demo_mode()
-
-
-# Include Podcast Maker router (available in all modes)
 from api.podcast.router import router as podcast_router
 app.include_router(podcast_router)
 
-if should_include_non_podcast_routers():
+# Include YouTube Creator Studio router
-    # Include platform analytics router
+from api.youtube.router import router as youtube_router
-    from routers.platform_analytics import router as platform_analytics_router
+app.include_router(youtube_router, prefix="/api")
-    app.include_router(platform_analytics_router)
 
-    # Include Bing Analytics Storage router to expose storage-backed endpoints
+# Include research configuration router
-    from routers.bing_analytics_storage import router as bing_analytics_storage_router
+app.include_router(research_config_router, prefix="/api/research", tags=["research"])
-    app.include_router(bing_analytics_storage_router)
-    app.include_router(images_router)
-    app.include_router(image_studio_router)
-    app.include_router(product_marketing_router)
-    app.include_router(campaign_creator_router)
 
-    # Include content assets router
+# Include Research Engine router (standalone AI research module)
-    from api.content_assets.router import router as content_assets_router
+from api.research.router import router as research_engine_router
-    app.include_router(content_assets_router)
+app.include_router(research_engine_router, tags=["Research Engine"])
 
-    # Include YouTube Creator Studio router
+# Scheduler dashboard routes
-    from api.youtube.router import router as youtube_router
+from api.scheduler_dashboard import router as scheduler_dashboard_router
-    app.include_router(youtube_router, prefix="/api")
+app.include_router(scheduler_dashboard_router)
+app.include_router(oauth_token_monitoring_router)
 
-    # Include research configuration router
+# Autonomous Agents API routes (Phase 3A)
-    app.include_router(research_config_router, prefix="/api/research", tags=["research"])
+from api.agents_api import router as agents_router
+app.include_router(agents_router)
 
-    # Include Research Engine router (standalone AI research module)
+# Today workflow routes
-    from api.research.router import router as research_engine_router
+from api.today_workflow import router as today_workflow_router
-    app.include_router(research_engine_router, tags=["Research Engine"])
+app.include_router(today_workflow_router)
-
-    # Scheduler dashboard routes
-    from api.scheduler_dashboard import router as scheduler_dashboard_router
-    app.include_router(scheduler_dashboard_router)
-    app.include_router(oauth_token_monitoring_router)
-
-    # Autonomous Agents API routes (Phase 3A)
-    from api.agents_api import router as agents_router
-    app.include_router(agents_router)
-
-    # Today workflow routes
-    from api.today_workflow import router as today_workflow_router
-    app.include_router(today_workflow_router)
-else:
-    logger.info("PODCAST_ONLY_DEMO_MODE is enabled: non-podcast routers are not registered.")
 
 # Setup frontend serving using modular utilities
 frontend_serving.setup_frontend_serving()

backend/start_alwrity_backend.py

@@ -298,11 +298,6 @@ def main():
     parser.add_argument("--dev", action="store_true", help="Enable development mode (auto-reload)")
     parser.add_argument("--production", action="store_true", help="Enable production mode (optimized for deployment)")
     parser.add_argument("--verbose", action="store_true", help="Enable verbose logging for debugging")
-    parser.add_argument(
-        "--podcast-only-demo",
-        action="store_true",
-        help="Enable podcast-only demo mode (sets PODCAST_ONLY_DEMO_MODE=true before app startup)",
-    )
     args = parser.parse_args()
     
     # Determine mode
@@ -312,8 +307,6 @@ def main():
     
     # Set global verbose flag for utilities
     os.environ["ALWRITY_VERBOSE"] = "true" if verbose_mode else "false"
-    if args.podcast_only_demo:
-        os.environ["PODCAST_ONLY_DEMO_MODE"] = "true"
     
     print("[*] ALwrity Backend Server")
     print("=" * 40)
@@ -321,8 +314,6 @@ def main():
     print(f"Auto-reload: {'ENABLED' if enable_reload else 'DISABLED'}")
     if verbose_mode:
         print("Verbose logging: ENABLED")
-    if args.podcast_only_demo:
-        print("Podcast-only demo mode: ENABLED")
     print("=" * 40)
     
     # Check if we're in the right directory