Treat blank OpenAI-compatible tool call arguments as an empty dict so parameterless tools such as finish can execute with providers that return an empty string. Also trim model identifiers during config normalization to avoid leading whitespace leaking into requests and snapshots.
- Updated `uni_message_sender.py` to allow for private messaging by removing the mandatory group ID and adding user ID handling.
- Enhanced chat history retrieval and clearing functions in `routes.py` and `service.py` to support both group and private chat scenarios.
- Introduced a new `ChatScrollContext` for managing message scrolling and highlighting in the chat UI.
- Created a `ListItemEditorHookFactory` for rendering a rich UI editor for list items in configuration settings, replacing the previous JSON text display.
- Improved message serialization for consistent display in chat history.
- Added detailed logging for chat history operations and error handling.
Co-authored-by: Copilot <copilot@github.com>
- 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.
