* perf: improve tool calls in reasoning and multiple tool calls display
- Updated LiveChatRoute and OpenApiRoute to replace manual message accumulation with BotMessageAccumulator.
- Simplified message saving logic by using build_bot_history_content and collect_plain_text_from_message_parts.
- Enhanced message processing to handle various message types (plain, image, record, file, video) more efficiently.
- Improved reasoning handling by extracting thinking parts and displaying them correctly in the UI components.
- Refactored message normalization and reasoning extraction logic in useMessages composable for better clarity and maintainability.
- Updated ChatMessageList, MessageList, StandaloneChat, and ReasoningBlock components to accommodate new message structure and rendering logic.
* feat(chat): reasoning activity panel
- Introduced a new ReasoningSidebar component for displaying reasoning details.
- Refactored MessageList and StandaloneChat components to utilize renderBlocks for improved message part handling.
- Added ReasoningTimeline component to visualize reasoning steps.
- Updated message handling logic to differentiate between thinking and content blocks.
- Enhanced localization for reasoning-related terms in English, Russian, and Chinese.
- Improved styling for various components to ensure consistency and readability.
* Update astrbot/dashboard/routes/chat.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix: handle reasoning_content when completion_text is empty (kimi-for-coding thinking mode)
* fix: use elif for result_chain/completion_text to avoid duplication, keep reasoning_content independent per review feedback
---------
Co-authored-by: Blueteemo <Blueteemo@users.noreply.github.com>
* fix: add ConnectionError and OSError to retry decorator for QQ Official API
* fix: remove redundant ConnectionError and add asyncio.TimeoutError per review feedback
* fix: rename decorator back to _qqofficial_retry
---------
Co-authored-by: Blueteemo <Blueteemo@users.noreply.github.com>
* feat: add inline message editing and regeneration functionality for webui
- Implemented inline editing for user messages in the chat component.
- Added a regenerate menu for retrying messages with different models.
- Enhanced message handling to include llm_checkpoint_id for better tracking.
- Updated localization files to include new actions for retrying and model selection.
- Introduced tests for checkpoint message handling and chat route functionality.
* feat: thread mode in webui
* feat: enhance message editing functionality to allow only the latest user message to be edited
* feat: add error handling and user feedback for thread creation in chat component
* feat: add thread count display and localization support in chat component
* feat: add RefsSidebar component and integrate reference management in chat UI
* feat: improve message editing validation and cleanup for bot messages
* feat: enhance checkpoint message handling with binding and dumping functionality
* feat: update FileReadTool description to mention image and PDF support
Add explicit mention of image (OCR) and PDF (text extraction) support
to the FileReadTool description for better discoverability.
* feat: update FileReadTool description to include support for docx and epub files; change base64 decoding to utf-8
* feat: enhance ToolLoopAgentRunner to support image and audio modalities; add context sanitization logic
* fix: accept both str and re.Pattern in RegexFilter
RegexFilter.__init__ now handles compiled re.Pattern objects by
extracting .pattern for regex_str, preventing TypeError during
JSON serialization in the dashboard plugin API.
* perf: 精简代码
* fix: prevent path traversal in backup importer (CWE-22)
Validate that all file write targets resolve within their expected
base directories before writing. This prevents crafted backup ZIP
files from writing to arbitrary filesystem locations via malicious
path values in attachment records, media file paths, or directory
entries.
* fix: use Path.is_relative_to for robust path containment check
* fix: add explicit strict=False to Path.resolve() calls
* style: format backup importer
---------
Co-authored-by: 邹永赫 <1259085392@qq.com>
* feat: add EPUB parsing support for knowledge base and file reader
* feat: update supported file formats for document upload in knowledge base
* feat: enhance EPUB parser to support spine order and generic containers
* makeitdown parse epub
* update parser
* fix
Improve robustness of tool call handling in OpenAI completions and agent tool loop by avoiding premature filtering and surfacing clearer errors when tools are missing.
* Refactor tool call argument handling in openai_source.py
* Improve error logging for missing tools
Log available tools when a specified tool is not found.
* fix: prevent Telegram media group exceptions from being silently swallowed
process_media_group() is invoked by APScheduler via add_job(). If
convert_message() or handle_msg() raises (e.g. get_file() network
timeout, file download failure), APScheduler catches the exception
internally and only logs it through its own logger, which is often
not configured in AstrBot. The result is that the media group
silently disappears with no trace in the application logs.
Two changes:
- Wrap the body of process_media_group() in try/except so failures
are logged through AstrBot's own logger with full traceback.
- Register an EVENT_JOB_ERROR listener on the scheduler as a
safety net, so any future scheduled job that throws will also
surface in the logs.
Fixes#7512
* ruff format
---------
Co-authored-by: Soulter <905617992@qq.com>
* feat: implement FTS5 support in DocumentStorage and SparseRetriever with tokenizer enhancements
* feat: optimize FTS row handling in DocumentStorage and update query tokenization in SparseRetriever
* feat: add MiniMax Token Plan provider with hardcoded model list (fix#7585)
- Add new provider 'minimax_token_plan' for MiniMax Token Plan users
- Inherit ProviderAnthropic to reuse all chat/completion logic
- Hardcode api_base to https://api.minimaxi.com/anthropic
- get_models() returns hardcoded list: MiniMax-M2.7, M2.5, M2.1, M2
- Highspeed models excluded (require premium tier)
- Reason for hardcoding: Token Plan API does not expose /models endpoint
- Fixes: https://github.com/AstrBotDevs/AstrBot/issues/7585
* fix: remove api_base from config template and add model validation
- Remove api_base from default_config_tmpl (always overridden, misleading)
- Add model validation against MINIMAX_TOKEN_PLAN_MODELS
- Raise clear ValueError if user configures an unsupported model
Addressed Sourcery AI review comments.
* fix: use custom_headers for Bearer token auth instead of auth_header
MiniMax Token Plan requires Authorization: Bearer <token> header.
Use custom_headers to inject the correct auth header instead of
the non-functional auth_header key.
Addressed Gemini Code Assist review comment.
* fix: update MiniMax Token Plan provider adapter and documentation to English
* feat: add MiniMax Token Plan configuration and icon support
* feat: remove default configuration template from MiniMax Token Plan provider adapter
---------
Co-authored-by: Soulter <905617992@qq.com>
