- Implemented dynamic SameSite and Secure cookie settings based on the backend URL context.
- Enhanced cookie handling to ensure proper functionality in cross-domain scenarios.
- Introduced AI File Sorting functionality to automatically organize documents into a smart folder hierarchy based on source, date, and topic.
- Updated README.md to include the new feature.
- Enhanced homepage components with new illustrations and descriptions for AI File Sorting.
- Refactored rate limiting logic to extract real client IPs more accurately.
- Changed assertions in `test_llamacloud_basic_uses_cost_effective_tier` to check for `parse_page_with_llm` instead of `cost_effective` tier.
- Updated `test_llamacloud_premium_uses_agentic_plus_tier` to verify `parse_page_with_agent` instead of `agentic_plus` tier.
- Ensured that `tier` is no longer included in the call arguments.
- Enhanced Azure Document Intelligence parser to raise an error for empty or whitespace-only content.
- Updated LLMRouterService to log premium model strings more clearly.
- Added automatic encoding detection for file reading in document processors.
- Improved error handling for empty markdown content extraction in file processors.
- Refactored DocumentUploadTab component for better accessibility and user interaction.
- Introduced a `ProcessingMode` enum to differentiate between basic and premium processing modes.
- Updated `EtlRequest` to include a `processing_mode` field, defaulting to basic.
- Enhanced ETL pipeline services to utilize the selected processing mode for Azure Document Intelligence and LlamaCloud parsing.
- Modified various routes and services to handle processing mode, affecting document upload and indexing tasks.
- Improved error handling and logging to include processing mode details.
- Added tests to validate processing mode functionality and its impact on ETL operations.
Updated the create, delete, and update functions in Linear and Notion tools to utilize the new request_approval utility for handling user approvals. This change improves code consistency and simplifies decision handling by directly merging parameters from the approval response.
Updated the create, delete, and update functions in Jira and OneDrive tools to utilize the new request_approval utility for handling user approvals. This change improves code consistency and simplifies decision handling by directly merging parameters from the approval response.
Updated the create, delete, and update functions in Google Calendar and Google Drive tools to utilize the new request_approval utility for handling user approvals. This change enhances code consistency and simplifies decision handling by directly merging parameters from the approval response.
Updated the create, send, update, and trash functions in Gmail tools to utilize the new request_approval utility for handling user approvals. This change improves code consistency and simplifies decision handling by directly merging parameters from the approval response.
Updated the create, delete, and update functions in Confluence and Dropbox tools to utilize the new request_approval utility for handling user approvals. This change enhances code consistency and simplifies decision handling by merging parameters directly from the approval response.
Updated the deduplication mechanism in the DedupHITLToolCallsMiddleware to utilize a comprehensive list of native HITL tools. The deduplication keys are now dynamically populated from both hardcoded values and metadata from StructuredTool instances. Additionally, integrated HITL approval into MCP tool creation, ensuring all tools are gated by user approval, with the ability to bypass for trusted tools.
This new module provides a `request_approval()` function that streamlines the process of requesting user approval for sensitive actions, including decision parsing and parameter merging. It enhances the interaction with tools by allowing for user modifications and handling trusted tools seamlessly.
