fix: youtube transcript API and missing datasets dependency

- Changed YouTubeTranscriptApi.get_transcript to .fetch (API changed)
- Added datasets>=4.4.0 to pyproject.toml (was missing)

Co-Authored-By: Claude <noreply@anthropic.com>

pyproject.toml

@@ -36,6 +36,7 @@ dependencies = [
     "gradio[oauth]>=5.0.0",
     "pandas>=2.2.0",
     "tenacity>=9.1.2",
+    "datasets>=4.4.0",
     "groq>=1.0.0",
 ]
 

src/tools/youtube.py

@@ -111,7 +111,7 @@ def get_youtube_transcript(video_id: str) -> Dict[str, Any]:
         logger.info(f"Fetching transcript for video: {video_id}")
 
         # Get transcript (auto-detect language, prefer English)
-        transcript_list = YouTubeTranscriptApi.get_transcript(
+        transcript_list = YouTubeTranscriptApi.fetch(
             video_id,
             languages=['en', 'en-US', 'en-GB']
         )