Propagate LLM errors in podcast handlers to frontend

- analysis.py: enhance_podcast_idea now re-raises HTTPException (429)
- analysis.py: analyze_podcast_idea already re-raises HTTPException
- research.py: re-raise HTTPException instead of silent fallback
- script.py: re-raise HTTPException instead of generic 500

Ensures 429 errors with usage_info reach frontend for modal display

backend/api/podcast/handlers/script.py

@@ -133,6 +133,8 @@ Guidelines:
             preferred_provider="huggingface",
             flow_type="premium_tool",
         )
+    except HTTPException:
+        raise
     except Exception as exc:
         raise HTTPException(status_code=500, detail=f"Script generation failed: {exc}")