- Improved in-memory rate limiting by evicting timestamps outside the current window and cleaning up empty keys.
- Updated LLM router service to cache context profiles and avoid redundant computations.
- Introduced cache eviction logic for MCP tools and sandbox instances to manage memory usage effectively.
- Added garbage collection triggers in chat streaming functions to reclaim resources promptly.
- improved search_knowledgebase_tool
- Added new endpoint to batch-fetch comments for multiple messages, reducing the number of API calls.
- Introduced CommentBatchRequest and CommentBatchResponse schemas for handling batch requests and responses.
- Updated chat_comments_service to validate message existence and permissions before fetching comments.
- Enhanced frontend with useBatchCommentsPreload hook to optimize comment loading for assistant messages.
- Introduced RequestPerfMiddleware to log request performance metrics, including slow request thresholds.
- Updated various services and retrievers to utilize the new performance logging utility for better tracking of execution times.
- Enhanced existing methods with detailed performance logs for operations such as embedding, searching, and indexing.
- Removed deprecated logging setup in stream_new_chat and replaced it with the new performance logger.
- Changed meeting link from Calendly to Cal.com for scheduling.
- Updated email contact from eric@surfsense.com to rohan@surfsense.com in multiple components.
- Revised text in the contact form to reflect the new scheduling options.
- Introduced dynamic character budget calculation for document formatting based on model's context window.
- Updated `format_documents_for_context` to respect character limits and improve output quality.
- Added `max_input_tokens` parameter to various functions to facilitate context-aware processing.
- Enhanced error handling for context overflow in LLM router service.
- Introduced should_summarize parameter in TaskDispatcher and CeleryTaskDispatcher to control summary generation.
- Updated InlineTaskDispatcher to support the new parameter for document processing.
- Replaced direct embedding calls with a utility function across various components to streamline embedding logic.
- Added enable_summary flag to several models and routes to control summary generation behavior.
- Introduced SidebarSeparator component for improved sidebar organization.
- Updated layout configuration to utilize the new SidebarSeparator in the documentation layout.
- Introduced slow callback logging in FastAPI to identify blocking calls.
- Added performance logging for agent creation and tool loading processes.
- Implemented caching for MCP tools to reduce redundant server calls.
- Enhanced sandbox management with in-process caching for improved efficiency.
- Refactored several functions for better readability and performance tracking.
- Updated tests to ensure proper functionality of new features and optimizations.
