- Added support for new configuration sections: relationship, database, maisaka, mcp, and plugin_runtime.
- Introduced complex field hooks for handling JSON configurations in chat talk value rules, expression learning lists, and more.
- Updated the field hooks to include schema metadata for better UI representation.
- Refactored the bot configuration page to utilize a more dynamic approach for managing section values and state.
- Improved the configuration schema generation to ensure all top-level sections have UI metadata.
- Added tests to validate the new configuration schema and ensure proper functionality of the JSON field hooks.
- Implemented a new dependency pipeline for plugins to manage Python package dependencies, including conflict detection and automatic installation of missing dependencies.
- Introduced an HTML rendering service that utilizes existing browsers to render HTML content as PNG images, with support for various configurations and error handling.
- Introduced MCPHostCallbacks for optional host capabilities like sampling and logging.
- Implemented MCPHostLLMBridge to handle MCP Sampling requests and bridge to LLM service.
- Created models for structured data conversion between MCP SDK and internal data models, including tool content items, prompts, and resources.
- Enhanced error handling and logging for better traceability during sampling operations.
- Refactored model fetching logic to support various authentication methods for OpenAI-compatible APIs.
- Introduced new data models for LLM service requests and responses to standardize interactions across layers.
- Added an adapter base class for unified request execution across different providers.
- Implemented utility functions for building OpenAI-compatible client configurations and request overrides.
