Updated the get_remaining method in CommandArgs to default start_index to 0 instead of 1, ensuring all arguments are included by default when retrieving remaining parameters.
Refactored permission checks in built-in plugins to use the new @require_permission decorator, improving code clarity and consistency. Enhanced permission_decorators to better extract ChatStream and support PlusCommand. Updated PermissionCommand to use permission decorators for all subcommands, improved user mention parsing, and improved feedback messages. Registered a new permission node for sending feeds in MaiZone plugin and updated command registration to use PlusCommand info.
Introduces the PlusCommand system for simplified command development, including new base classes, argument parsing utilities, and registration logic. Updates the plugin system, component registry, and bot message handling to support PlusCommand components alongside traditional commands. Adds documentation and configuration for command prefixes, and provides a developer guide for the new system.
This commit refactors the tool caching system to be more robust, configurable, and easier to use. The caching logic is centralized within the `wrap_tool_executor`, removing the need for boilerplate code within individual tool implementations.
Key changes:
- Adds `enable_cache`, `cache_ttl`, and `semantic_cache_query_key` attributes to `BaseTool` for declarative cache configuration.
- Moves caching logic from a simple history-based lookup and individual tools into a unified handling process in `wrap_tool_executor`.
- The new system leverages the central `tool_cache` manager for both exact and semantic caching based on tool configuration.
- Refactors `WebSurfingTool` and `URLParserTool` to utilize the new declarative caching mechanism, simplifying their code.
Removed the command skip list feature and related code from the anti-injection system, including configuration options, plugin command collection, and management commands. Refactored anti-injector logic to operate directly on message dictionaries and simplified whitelist and message content extraction. Updated response handling to perform anti-injection checks before reply generation, and removed skip list refresh logic from the plugin manager.
Added detailed debug logs for text extraction and LLM detection input in the anti-injector module. Refactored message processing to only use user-added content for detection, avoiding duplicate text. Fixed import paths for command_skip_list in plugin manager and anti_injector_manager to reflect new module structure.
Refactored configuration classes to inherit from a new ValidatedConfigBase using Pydantic for robust validation and error reporting. Updated api_ada_configs.py, config.py, config_base.py, and official_configs.py to replace dataclasses with Pydantic models, add field validation, and improve error messages. This change enhances configuration reliability and developer feedback for misconfigurations. Also includes minor code cleanups and removal of unused variables in other modules.
Cleaned up various files by removing unused or redundant import statements to improve code readability and reduce potential confusion. No functional changes were made.
