- Implemented UnifiedWebSocketManager for managing WebSocket connections, including subscription handling and message sending.
- Created unified WebSocket router to handle client messages, including authentication, subscription, and chat session management.
- Added support for logging and plugin progress subscriptions.
- Enhanced error handling and response structure for WebSocket operations.
- Added `inactive_plugins` field to `RunnerReadyPayload` and `ReloadPluginResultPayload` to track plugins that are not activated due to being disabled or unmet dependencies.
- Introduced `InspectPluginConfigPayload` and `InspectPluginConfigResultPayload` for inspecting plugin configuration metadata.
- Implemented `PluginActivationStatus` enum to better represent plugin activation states.
- Updated `_activate_plugin` method to return activation status and handle inactive plugins accordingly.
- Added hooks for send service to allow modification of messages before and after sending.
- Created new runtime routes for listing hook specifications in the WebUI.
- Refactored plugin configuration handling to utilize runtime inspection for better accuracy and flexibility.
- Enhanced error handling and logging for plugin configuration operations.
- 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.
- Added a new `tooling` module to define a unified model for tool declarations, invocations, and execution results, facilitating compatibility between plugins, legacy actions, and MCP tools.
- Implemented `ToolProvider` interface for various tool providers including built-in tools, MCP tools, and plugin runtime tools.
- Enhanced `MCPManager` and `MCPConnection` to support unified tool invocation and execution results.
- Updated `ComponentRegistry` and related classes to accommodate the new tool specifications and descriptions.
- Refactored existing components to utilize the new tooling system, ensuring backward compatibility with legacy actions.
- Improved error handling and logging for tool invocations across different providers.
- Added support for scheduling background tasks to build emoji and image descriptions when not found in cache.
- Improved error handling and logging for emoji and image processing.
- Updated `SessionMessage` processing to allow for optional heavy media analysis and voice transcription.
- Refactored logging messages for better clarity and consistency across various modules.
- Introduced a new function to build outbound log previews for messages, enhancing logging capabilities.
- 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.
