Improve the auto-AI-review pipeline

https://gitlab.com/sid6i7/beyondchats-node/-/blob/main/scripts/ai-review.py?ref_type=heads We use this script to automatically review MRs but it has several issues: - AI often gives positive feedback instead of flaws - AI doesnt consider context of the entire file: suggests "check if xyz is imported" - Would it be possible for the AI to generate unit test cases to test functions changed/added and actually run these?? Might be possible via tool calling