- Introduced LLM Provider declarations in plugin manifests, allowing plugins to specify their LLM capabilities.
- Implemented validation for LLM Provider declarations to prevent duplicates and conflicts.
- Enhanced the PluginRunner to handle LLM Provider invocation requests, enabling plugins to interact with LLM Providers seamlessly.
- Added a ClientRegistry to manage LLM Provider registrations and ensure no conflicts arise between different plugins.
- Created a PluginLLMClient to facilitate communication with LLM Providers through the plugin runtime.
- Developed tests to ensure proper registration and conflict handling of LLM Providers.
- 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.
- 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 a new method `validate_plugin_config` in `PluginRuntimeManager` to validate plugin configurations at runtime.
- Implemented the `_normalize_plugin_config` method in `PluginRunner` to normalize and persist plugin configurations.
- Enhanced the `PluginRunner` to handle configuration validation requests and return normalized configurations.
- Updated the WebUI routes to utilize runtime validation for plugin configurations, ensuring that configurations are validated and normalized before saving.
- Added tests for runtime configuration validation and normalization processes, including handling of invalid configurations.
- 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.
- Introduced HookHandlerEntry to manage hook processing with attributes like hook name, mode, order, timeout, and error policy.
- Implemented normalization methods for hook attributes to ensure valid configurations.
- Updated ComponentRegistry to support retrieval of hook handlers based on hook names, with sorting by mode and order.
- Refactored HookDispatcher to handle invocation of hooks, separating blocking and non-blocking handlers, and managing execution results.
- Added support for registering hook specifications and invoking hooks across supervisors in PluginRuntimeManager.
- Removed deprecated workflow step handling from PluginRunner, streamlining hook invocation responses.
- Updated the PluginMeta class to utilize a strongly typed PluginManifest, improving type safety and clarity.
- Refactored dependency extraction logic to streamline the handling of plugin dependencies.
- Modified the PluginLoader to accommodate new manifest versioning and validation processes.
- Enhanced the PluginRunner to work with a dictionary for external available plugins, allowing for version mapping.
- Updated built-in plugins' manifest files to version 2, adding URLs and SDK versioning for better integration and documentation.
- Improved error handling and logging for plugin loading and dependency resolution processes.
- Updated `calculate_session_id` method in `SessionUtils` to include optional `account_id` and `scope` parameters for more granular session ID generation.
- Added new environment variables in `plugin_runtime` for external plugin dependencies and global configuration snapshots.
- Introduced methods in `RuntimeComponentManagerProtocol` for loading and reloading plugins globally, accommodating external dependencies.
- Enhanced `PluginRunnerSupervisor` to manage external available plugin IDs during plugin reloads.
- Implemented dependency extraction and management in `PluginRuntimeManager` to handle cross-supervisor dependencies.
- Added tests for session ID calculation and message registration in `ChatManager` to ensure correct behavior with new parameters.
- Add test for fallback to bot account in platform IO route metadata when context message is absent.
- Improve PlatformIOManager to avoid duplicate driver entries and streamline fallback driver handling.
- Refactor OutboundTracker to support tracking by both internal message ID and driver ID, enhancing the uniqueness of pending records.
- Introduce dynamic API capabilities in RuntimeComponent, allowing plugins to replace their dynamic API lists.
- Update APIRegistry to manage dynamic APIs more effectively, including registration and toggling of API statuses.
- Implement authorization checks for dynamic API capabilities to ensure proper permissions.
- Restrict direct calls to certain host RPC methods from plugins for enhanced security.
- Refactor send_service to ensure fallback to current platform account when no context message is available.
- Add support for configuration reload scopes in the plugin runtime.
- Implement validation for SDK plugins to ensure required lifecycle methods are overridden.
- Update the configuration update handling to include scope information.
- Introduce tests for expression auto-check task and NapCat adapter SDK integration.
- Refactor configuration management to support callbacks with variable arguments.
- Improve plugin loading and error handling for configuration updates.
- Ensure that plugins can manage their own configuration updates effectively.
- Added APIEntry and APIRegistry classes for managing plugin APIs.
- Updated PluginRunnerSupervisor to include API registry and methods for invoking APIs.
- Enhanced PluginRuntimeManager to support API registration and invocation.
- Created tests for API registration, invocation, and visibility between plugins.
- Refactored component handling to distinguish between runtime components and APIs.
- Removed unused core action mirror functionality from PluginRunnerSupervisor.
- Simplified action and command execution logic in send_service.py.
- Introduced ComponentQueryService for unified component querying in plugin runtime.
- Enhanced message component handling with new binary component support.
- Improved message sequence construction and detection of outbound message flags.
- Updated methods for sending messages to streamline the process and improve readability.
- Removed UniversalMessageSender from group_generator.py and private_generator.py.
- Updated PlatformIOManager to manage legacy send drivers and ensure send pipeline readiness.
- Enhanced LegacyPlatformDriver to utilize prepared messages for sending.
- Refactored send_service to unify message sending logic and integrate with Platform IO.
- Added regression tests for Platform IO legacy driver and send service functionality.
- Changed the message sending method to return DeliveryBatch instead of DeliveryReceipt in integration.py.
- Removed AdapterDeclarationPayload and related references from envelope.py, replacing them with MessageGatewayStateUpdatePayload and MessageGatewayStateUpdateResultPayload.
- Updated runner_main.py to remove adapter-related logic and methods, focusing on message gateway functionality.
- Added tests for message gateway runtime state synchronization and action bridge functionality in test files.
