* perf: support extended thinking for Anthropic, DeepSeek reasoning mode, and Gemini text part thought signatures to improve multi-turn reasoning performance.
* chore: remove verbose
* perf
* refactor: remove special tools handling for deepseek-reasoner model in openai source
* fix: improve error handling and logging in InternalAgentSubStage processing
* refactor: remove unused reasoning content from Gemini source processing
* refactor: enhance modality determination logic in useProviderSources
Co-authored-by: kawayiYokami <289104862@qq.com>
* fix: handle None values in _extract_usage to prevent TypeError
Some LLM providers (especially API proxies) may return None for
prompt_tokens and completion_tokens in the usage response. This
causes a TypeError when attempting arithmetic operations.
Added null checks with fallback to 0 for both prompt_tokens and
completion_tokens before performing calculations.
* refactor: use explicit None check and reuse cached variable
- Use `is None` instead of `or 0` to avoid masking unexpected falsy values
- Reuse `cached` variable for `input_cached` to avoid redundant calculation
* ruff format
---------
Co-authored-by: Soulter <905617992@qq.com>
- Expanded model name checks to include specific Gemini 2.5 and 3 variants, ensuring correct configuration for thinking parameters based on the model used.
- Introduced logging warnings in ProviderManager and Context classes when a provider ID is not found, indicating potential issues due to ID modifications.
- Updated the ProviderPage.vue to advise against modifying provider IDs, highlighting possible configuration impacts.
* feat: supports thinking level of google gemini
- Updated google-genai version to >=1.56.0 in pyproject.toml and requirements.txt.
- Changed model configuration from "gemini-1.5-flash" to "gemini-3-flash-preview" in default.py.
- Enhanced thinking configuration handling in gemini_source.py to support new parameters for Gemini 3 models.
* fix: standardize thinking level configuration in default.py and gemini_source.py
- Updated the thinking level values in default.py to uppercase for consistency.
- Enhanced gemini_source.py to validate the thinking level and default to "HIGH" if an invalid value is provided.
* feat: enhance tool call handling and UI integration for tool calls render
- Added support for tool call messages in the agent runner and webchat event handling.
- Implemented JSON message component for structured tool call data.
- Updated chat route to save tool call information in message history.
- Enhanced frontend to display tool call details in a collapsible format, including status and results.
- Introduced elapsed time tracking for ongoing tool calls in the chat interface.
* fix: improve message handling in agent run utility and tool loop runner
- Refactored message sending logic in `astr_agent_run_util.py` to use `msg_chain` directly for better clarity.
- Added a check in `tool_loop_agent_runner.py` to ensure `tool_call_result_blocks` is not empty before yielding the last tool call result, preventing potential errors.
* refactor: enhance message structure and UI for chat components
- Updated message handling in `MessageList.vue` to support structured message parts, including plain text, images, audio, and files.
- Improved the `Chat.vue` component styles for better visual consistency.
- Refactored message parsing logic in `useMessages.ts` to accommodate new message formats and ensure proper rendering of embedded content.
- Removed deprecated tool call handling from the message structure, streamlining the message display process.
* chore: ruff format
* feat: implement agent statistics tracking and display in chat
- Added `AgentStats` and `TokenUsage` data classes to track agent performance metrics.
- Enhanced `ToolLoopAgentRunner` to collect and update agent statistics during execution.
- Integrated agent statistics sending to webchat for real-time updates.
- Updated chat route to save and display agent statistics in message history.
- Improved frontend components to visualize agent statistics, including token usage and duration metrics.
* fix: improve message handling in Telegram event and agent run utility
- Updated message sending logic in `astr_agent_run_util.py` to send the correct message chain for tool calls.
- Enhanced `tg_event.py` to edit messages during streaming breaks, improving message management and user experience.
- Added error handling for message editing failures to ensure robustness.
* chore: ruff format
- Added icons for 'modelstack', 'tokenpony', and 'compshare' in providerUtils.js.
- Updated ProviderPage.vue to display the correct count of displayed provider sources.
- Enhanced the logic for displaying provider sources to include placeholders for unselected templates.
- Improved the display name for provider sources to show template keys for placeholders.
- Adjusted styles for better layout and overflow handling in provider source list and cards.
- Refactored source selection logic to handle placeholder sources correctly.
- Updated error handling in provider testing to provide clearer messages.
- Updated the `test` method in all provider classes to remove return values and raise exceptions for failure cases, enhancing clarity and consistency.
- Adjusted related logic in the dashboard and command routes to align with the new `test` method behavior, simplifying error handling.
- Added a `test` method to each provider class to standardize availability checks.
- Updated the dashboard and command routes to utilize the new `test` method for provider reachability verification, simplifying the logic and improving maintainability.
- Removed redundant reachability check logic from the command handler.
- Introduced a reload lock to prevent concurrent reloads of providers.
- Added logging to indicate when a provider is disabled and when providers are being synchronized with the configuration.
- Refactored the reload method to improve clarity and maintainability.
Co-authored-by: anka <1350989414@qq.com>
- Implemented CozeAPIClient for file upload, image download, chat messaging, and context management.
- Developed DashscopeAgentRunner for handling requests to the Dashscope API with streaming support.
- Created DifyAgentRunner to manage interactions with the Dify API, including file uploads and workflow execution.
- Introduced DifyAPIClient for making asynchronous requests to the Dify API.
- Updated third-party agent imports to reflect new module structure.
- 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.
* feat: enhance parameter type handling in LLM tool registration with JSON schema support
* refactor: remove debug print statement from FunctionToolManager
* 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>
