- Added `ThirdPartyAgentSubStage` to handle interactions with third-party agent runners (Dify, Coze, Dashscope).
- Refactored `star_request.py` to ensure consistent return types in the `process` method.
- Updated `stage.py` to initialize and utilize the new `AgentRequestSubStage`.
- Modified `ProviderManager` to skip loading agent runner providers.
- Removed `Dify` source implementation as it is now handled by the new agent runner structure.
- Enhanced `DifyAPIClient` to support file uploads via both file path and file data.
- Cleaned up shared preferences handling to simplify session preference retrieval.
- Updated dashboard configuration to reflect changes in agent runner provider selection.
- Refactored conversation commands to accommodate the new agent runner structure and remove direct dependencies on Dify.
- Adjusted main application logic to ensure compatibility with the new conversation management approach.
* refactor: LLM response handling with reasoning content
- Added a `show_reasoning` parameter to `run_agent` to control the display of reasoning content.
- Updated `LLMResponse` to include a `reasoning_content` field for storing reasoning text.
- Modified `WebChatMessageEvent` to handle and send reasoning content in streaming responses.
- Implemented reasoning extraction in various provider sources (e.g., OpenAI, Gemini).
- Updated the chat interface to display reasoning content in a collapsible format.
- Removed the deprecated `thinking_filter` package and its associated logic.
- Updated localization files to include new reasoning-related strings.
* feat: add Groq chat completion provider and associated configurations
* Update astrbot/core/provider/sources/gemini_source.py
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
* feat:add Xinference rerank provider
* feat:add default rerank_api_key option for Xinference provider
* style: format code
* fix: refactor XinferenceRerankProvider initialization for better error handling
* fix: update XinferenceRerankProvider to use async client methods for initialization and reranking
* feat: add launch_model_if_not_running option to XinferenceRerankProvider for better control over model initialization
* chore: remove unused asyncio import from xinference_rerank_source.py
* refactor: mcp server reload mechanism
* fix: wait for client events
* fix: all other mcp servers are terminated when disable selected server
* fix: resolve type hinting issues in MCPClient and FuncCall methods
* perf: optimize mcp server loaders
* perf: improve MCP client connection testing
* perf: improve error message
* perf: clean code
* perf: increase default timeout for MCP connection and reset dialog message on close
---------
Co-authored-by: Raven95676 <Raven95676@gmail.com>
Soulter