13 Commits

Author	SHA1	Message	Date
Weilong Liao	93a6152eee	feat: add temporary extra user content parts (#7976) ... * feat: add temporary extra user content parts * fix: 3.10	2026-05-03 22:11:24 +08:00
Soulter	36d6f3b67e	feat: add inline message editing and regeneration functionality for webui (#7673) ... * 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	2026-04-22 11:51:12 +08:00
鸦羽	eca3ede7b0	fix: dedupe preset messages (#4961)	2026-02-08 22:18:13 +08:00
Soulter	66e2f49c11	perf: support extended thinking for Anthropic, DeepSeek reasoning mode, and Gemini text part thought signatures to improve multi-turn reasoning performance. (#4240) ... * 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>	2025-12-29 14:22:30 +08:00
Soulter	bd1b0a2836	perf: drop unnecessary none-value fields in tool call loop (#4213)	2025-12-26 21:12:34 +08:00
Soulter	0299aa6e4c	fix: validation error for ToolCall.extra_content in specific upstream model providers (#4102) ... * fix: validation error for ToolCall.extra_content in specific upstream model providers * fix: handle missing extra_content gracefully in ToolCall serialization	2025-12-18 11:55:49 +08:00
Soulter	26f863ba81	Revert "fix: omit empty content field for the LLM request after tool calls ar…" (#4068) ... This reverts commit f78a90218e.	2025-12-16 20:22:13 +08:00
sctop	f78a90218e	fix: omit empty content field for the LLM request after tool calls are completed (#4008) ... * fix: omit content field for the LLM request after tool calls are completed and content is empy string or none * chore: ruff format --------- Co-authored-by: Soulter <905617992@qq.com>	2025-12-16 20:11:11 +08:00
Soulter	c13c51f499	fix: assistant message validation error when tool_call exists but content not exists (#3862) ... * fix: assistant message validation error when tool_call exists but content not exists * fix: enhance content validation in Message model to allow None for assistant role with tool_calls	2025-11-30 23:42:37 +08:00
Soulter	4087bbb512	perf: set content attribute optional to AssistantMessageSegment for enhanced message handling ... fixes: #3843	2025-11-30 00:32:00 +08:00
Soulter	afb56cf707	feat: add supports for gemini-3 series thought signature (#3698) ... * feat: add supports for gemini-3 series thought signature * feat: refactor tools_call_extra_content to use a dictionary for better structure	2025-11-19 18:54:56 +08:00
piexian	6cf169f4f2	fix: ImageURLPart typo (#3665) ... * 修复新版本更新对不上格式的问题 entities.py生成的格式：{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}} ImageURLPart期望的格式：{"type": "image_url", "image_url": "data:image/jpeg;base64,..."} * Revert "修复新版本更新对不上格式的问题" This reverts commit 28b4791391. * fix(core.agent): 修复ImageURLPart的声明，修复pydantic校验失败的问题。 --------- Co-authored-by: piexian <piexian@users.noreply.github.com> Co-authored-by: Dt8333 <lb0016@foxmail.com>	2025-11-17 09:52:31 +08:00
Soulter	50144ddcae	refactor: revise LLM message schema and fix the reload logic when using dataclass-based LLM Tool registration (#3234) ... * refactor: llm message schema * feat: implement MCPTool and local LLM tools with enhanced context handling * refactor: reorganize imports and enhance docstrings for clarity * refactor: enhance ContentPart validation and add message pair handling in ConversationManager * chore: ruff format * refactor: remove debug print statement from payloads in ProviderOpenAIOfficial * Update astrbot/core/agent/tool.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update astrbot/core/agent/message.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update astrbot/core/agent/message.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update astrbot/core/agent/tool.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update astrbot/core/pipeline/process_stage/method/llm_request.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update astrbot/core/agent/message.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * refactor: enhance documentation and import mcp in tool.py; update call method return type * fix: 修复以数据类的方式注册 tool 时的插件重载机制问题 * refactor: change role attributes to use Literal types for message segments * fix: add support for 'decorator_handler' method in call_local_llm_tool * fix: handle None prompt in text_chat method and ensure context is properly formatted --------- Co-authored-by: LIghtJUNction <lightjunction.me@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-11-02 18:12:20 +08:00