- Enhance message streaming with more precise content and tool call handling
- Add logic to only send and store meaningful assistant messages and tool calls
- Prevent sending empty or redundant messages during stream processing
- Improve tool call and content update tracking in agent stream method
- Optimize message inclusion in recursive thread generation
- Add support for initial non-tool response and subsequent tool-enabled processing
- Implement `PendingToolCall` to manage incremental tool call updates
- Update `Delta` and related types to support more flexible tool call streaming
- Modify agent stream processing to handle tool calls with improved state management
- Add robust handling for tool call deltas and function call arguments
- Move hardcoded agent prompt to a constant `AGENT_PROMPT` in the `agent_thread.rs` file
- Update the prompt's date from January 27, 2025 to February 7, 2025
- Simplify thread initialization by referencing the new constant
- Maintain existing prompt structure and guidelines
- Implement a maximum recursion depth of 30 for agent thread processing
- Add recursion depth tracking to prevent potential infinite loops
- Provide user-friendly message when maximum recursion depth is reached
- Update debug logging to include current recursion depth
- Modify both synchronous and streaming thread processing methods
- Refactor agent stream processing to use a recursive approach for handling tool calls
- Enhance tool execution with more robust error handling and result tracking
- Improve stream chunk processing with detailed state management
- Add support for recursive thread generation based on tool call results
- Implement cloning for LiteLLMClient to support stream processing tasks
- Update search data catalog and file search tools to use consistent JSON response structure
- Enforce strict response format with mandatory "results" key and comprehensive field requirements
- Add explicit guidelines for result composition and handling of empty result sets
- Improve response predictability and parsing reliability for AI-powered search tools
- Add `stream: Some(false)` to file search and data catalog tools
- Make `json_schema` optional in `ResponseFormat` serialization
- Enhance logging in search file tool with debug and warning messages
- Improve error context when parsing LLM JSON responses
- Wrap agent tools in an Arc for safe concurrent access
- Modify tool addition methods to work with Arc-wrapped HashMap
- Ensure thread-safe tool registration and retrieval
- Update stream processing to use Arc-cloned tools reference
- Add comprehensive debug logging for agent thread processing
- Modify agent thread to use user ID for streaming subscription
- Update stream processing to include detailed tool call and content logging
- Improve error handling and visibility in stream processing
- Add user context to agent thread initialization
- Remove redundant tool execution handling in stream processing
- Add `ValueToolExecutor` to convert tool outputs to `serde_json::Value`
- Introduce `IntoValueTool` trait for easy value type conversion
- Update agent tool addition methods to use new value conversion mechanism
- Simplify tool registration by automatically converting tool outputs
- Remove previous manual boxing and type conversion logic
- Add comprehensive dataset search functionality using LLM for intelligent dataset matching
- Implement search across datasets with relevance ranking based on YML content
- Create structured search result output with dataset metadata
- Add robust error handling, logging, and parsing for search operations
- Include test coverage for search result validation
- Enhance tool with flexible query parameter support and detailed response messages
- Add comprehensive file search functionality using LLM for intelligent file matching
- Implement search across metric and dashboard files with relevance ranking
- Create structured search result output with file metadata
- Add robust error handling and logging for search operations
- Include test coverage for search result parsing
- Implement robust line-based content modification for metric and dashboard files
- Add comprehensive error handling and validation for file modifications
- Improve modification tracking with detailed modification results
- Optimize file processing with batch insertion and validation
- Add extensive test coverage for modification and validation logic
- Add generic Output type to ToolExecutor trait
- Update file tools to use strongly-typed output structs
- Modify agent and tool implementations to support generic output
- Improve error handling and result reporting in file-related tools
- Add more detailed status messages for file operations
- Rename file type modules from `metric_file` and `dashboard_file` to `metric_yml` and `dashboard_yml`
- Modify metric files migration to use a verification enum instead of boolean
- Update messages_to_files junction table with UUID primary key and additional timestamp columns
- Adjust database models to support new file and message structures
- Refactor file creation utility to use new model structures
dal