- Introduced a shielded async session context manager to ensure safe session closure during cancellations.
- Updated various database operations to utilize the new shielded session, preventing orphaned connections.
- Added environment variables to optimize glibc memory management, improving overall application performance.
- Implemented a function to trim the native heap, allowing for better memory reclamation on Linux systems.
- Added proper session closure to prevent connection leaks during streaming.
- Implemented a fresh session for cleanup tasks to ensure data integrity.
- Enhanced error handling during session operations to improve robustness.
- Removed unnecessary session parameters from function signatures for clarity.
- Introduced a mechanism to identify degenerate queries that lack meaningful search signals, improving search accuracy.
- Implemented a fallback method for browsing recent documents when queries are degenerate, ensuring relevant results are returned.
- Added limits on the number of chunks fetched per document to optimize performance and prevent excessive data loading.
- Updated the ConnectorService to allow for reusable query embeddings, enhancing efficiency in search operations.
- Enhanced LLM router service to support context window fallbacks, improving robustness during context window limitations.
- Increased maximum file upload limit from 10 to 50 to improve user experience.
- Implemented batch processing for document uploads to avoid proxy timeouts, splitting files into manageable chunks.
- Enhanced garbage collection in chat streaming functions to prevent memory leaks and improve performance.
- Added memory delta tracking in system snapshots for better monitoring of resource usage.
- Updated LLM router and service configurations to prevent unbounded internal accumulation and improve efficiency.
- 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.
- 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 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.
- Updated the embedding dimension in test configurations to use the value from the application config, enhancing maintainability and consistency across tests.
- Removed commented-out testing configuration from .env.example to streamline the file.
- Updated markers in pyproject.toml to remove the e2e test marker, clarifying the purpose of the remaining markers.
- Introduced a TaskDispatcher abstraction to decouple the upload endpoint from Celery, allowing for easier testing with synchronous implementations.
- Updated the create_documents_file_upload function to utilize the new dispatcher for task management.
- Removed direct Celery task imports from the upload function, enhancing modularity.
- Added integration tests for document upload, including page limit enforcement and file size restrictions.
Keeps the deletion of Dockerfile.allinone, docker-compose.yml (root), and
scripts/docker/entrypoint-allinone.sh from fix/docker. Ports the Daytona
sandbox env vars added by upstream/dev into docker/docker-compose.yml and
docker/docker-compose.dev.yml instead.
Made-with: Cursor
- Introduced a new test class to verify that uploaded documents appear in search results once their status is ready.
- Implemented assertions to ensure the uploaded document's ID is present in the search response.
