- 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.
- 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.
- Added functionality to persist sandbox files locally before deletion.
- Introduced methods for retrieving and deleting locally stored sandbox files.
- Updated routes to handle local file downloads and background deletion of sandboxes.
- Enhanced streaming tasks to support sandbox file management.
- Added detailed instructions for prioritizing code execution over text responses in specific scenarios, such as data visualization and file generation.
- Included examples to illustrate correct and incorrect approaches to handling user requests involving code execution.
- Emphasized the importance of printing file paths for user downloads and clarified the handling of sandbox-generated files.
- Added _TimeoutAwareSandbox class to handle per-command timeouts in DaytonaSandbox.
- Updated _find_or_create function to manage sandbox states and restart stopped/archived sandboxes.
- Enhanced get_or_create_sandbox to return the new sandbox class.
- Introduced file download functionality in the frontend, allowing users to download generated files from the sandbox.
- Updated system prompt to include guidelines for sharing generated files.
- delete_linear_issue + delete_notion_page: add db_session.rollback()
in the KB document deletion exception handler so the session is never
left in a PendingRollbackError state after a failed commit, which
would otherwise break all subsequent DB operations in the same request
- delete_linear_issue: include issue identifier (e.g. ENG-42) in the
success message so the caller can confirm which issue was archived
- update_linear_issue: remove redundant label_ids ternary
(x if x is not None else None -> x)
- create_linear_issue: add logger.error on empty-title guard for parity
with the equivalent Notion tool
- update_issue: handle not_indexed KB sync status with a distinct user
message (matches Notion parity)
- delete_issue: fix log message "not found in DB" → "not found in KB"
- LinearConnector.update_issue: return error early when no fields are
provided, preventing a silent no-op mutation and unnecessary KB sync
- Rename delete_from_db → delete_from_kb in delete_notion_page tool and
its frontend component to match the more accurate Linear naming and
keep both tool APIs consistent for the LLM
- Add NotionKBSyncService for immediate KB updates after page changes
- Implement block ID verification to ensure content freshness
- Refactor duplicate block processing logic to shared utils
- Add user-friendly status messages
- Include debug logging for troubleshooting
