🤖 refactor: Prevent Vertex AI from Setting Parameter Defaults

[danny-avila]

Summary

The VertexAI client was setting defaults for model parameters that was adversely affecting generation, namely with a limited amount of maxOutputTokens

• Updated @librechat/agents package from version 2.0.0 to 2.0.1 for improved functionality
• Enhanced VertexAI client initialization by explicitly setting client parameters instead of relying on defaults
• Improved stream handling by properly typing the client and managing chunk text processing
• Implemented robust metadata processing by filtering out NaN values and ensuring proper concatenation
• Removed unnecessary default configurations and legacy maxRetries setting
• Refined the client initialization process for both VertexAI and GenAI implementations

Change Type

• Bug fix (non-breaking change which fixes an issue)
• Documentation update

Checklist

• My code adheres to this project's style guidelines
• I have performed a self-review of my own code
• I have commented in any complex areas of my code
• I have made pertinent documentation changes
• My changes do not introduce new warnings
• Local unit tests pass with my changes