f624971613
chore: fix bunches of type checking errors ( #3213 )
...
* chore(core.utils): 🚨 修正错误Lint
* chore(core.provider): 🚨 修复基类错误Lint
* chore(core.utils): 补全session_get()的重载
* chore(core.provider): 🚨 修正实现错误Lint
* chore(core.platform): 🚨 修正platform基类和webchat的错误Lint
* chore(core.platform): 修正错误实现Lint
* fix(core.provider): 修复循环调用和错误assert
* chore(core.platform): 修复部分实现Lint
* chore(core.provider): 补充Dify.text_chat_stream的参数类型
* chore(core.pipeline): 🚨 修复错误Lint
* fix(core.slack): 补充遗漏导入
* chore(core.utils): 修复错误的session_get声明
* chore(core.platform): 移除Lark adapter import中的wildcard
* chore(core.db): 修复声明和部分逻辑
* chore(core.db): 添加typings，使faiss参数能被正确识别。
* chore(core): 修复声明
* chore(core): 修改声明
* chore: 补充faiss声明
* chore(dashboard): 修改实现，减少报错
* chore(package): 修改部分声明与实现，减少报错
* chore(core): 添加Handler的overload，以去除部分assert同时通过类型检查
* chore(core.pipeline): 修改Pipeline Scheduler的execute，将判断属性改为判断类型，通过静态类型检查
* chore(core.config): 添加类型标注，通过类型检查
* chore(core.message): 为File._download_file添加检查，通过类型检查
* fix: 将断言改为条件判断以实现优雅关闭的容错性
* refactor: 移除 discord 客户端中的 assert，改用 if None 判断并抛出异常
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: DiscordPlatformAdapter 对 self.client.user 为 None 做日志并返回，移除断言
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 增强 Lark 相关空值/异常检查并完善日志输出
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 将断言替换为条件检查并加入日志与错误处理
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* chore: 移除LLM生成的无用注释
* refactor: 使用 File.get_file 替换下载逻辑并移除 assert，提供默认 filename
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: Slack Socket 未初始化抛出运行时异常，图片 URL 判空改为非空判断
* refactor: 将 WeChatPadProAdapter 的断言改为空值判断并添加日志
* refactor: 使用 isinstance 替代断言实现类型判断，便于静态检查
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 去除cast，直接使用字段与字典访问，修正端口解析
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 使用 match-case 重构 ProviderManager 加载并通过类型检查抛出 TypeError
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: group_name_display 时若 group 对象为空则记录错误并返回
* fix: 将 _get_current_persona_id 的 assert 替换成 if guard 并返回 None
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 优化插件目录存在性检查及图片URL非空验证，更新JSON排序配置
* fix: 将 datetime_str 的 assert 替换为显式检查并抛出异常
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 移除 cast，改为运行时检查并在找不到调度器时跳过
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 移除 cast，改用 isinstance 检查 FaissVecDB 并警告
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 删除 typing.cast 导入，并在获取文件绝对路径前校验 file_
* refactor: 移除 typing.cast，简化内容安全检查调用
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 将 PlatformMetadata.id 设为必填并在注册时传入 id，移除 cast
* refactor: 移除 cast，改用 HasInitialize 与 isinstance 进行初始化
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 为 ProviderManager.initialize 增加ID类型判断，避免 None 导致 get 失败
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 为 OTTSProvider 与 AzureNativeProvider 引入 _client 与 client 属性改进上下文管理
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 为 Whisper 自托管源添加模型未初始化校验并直接调用 transcribe
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 移除未使用的 cast 导入并简化 platform_name 赋值
* refactor: 引入 cast 并对 id 使用 cast(str, ...) 提升类型安全
* fix: 将 _id_to_sid 返回改为 str，空值返回空串；对 id 与 message_id 使用 cast
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* refactor: 重构 Discord 处理逻辑：强制 类型转换、优先斜杠指令并优化提及判断
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
* fix: 统一对 id 获取执行 cast，并在微信消息解析失败时抛错
* Revert "fix: 去除cast，直接使用字段与字典访问，修正端口解析"
This reverts commit 1cbfdf9d1baider@aider.chat >
* refactor: 调整 call_handler 泛型、Discord 通道注解及 FishAudioTTS API 请求类型
* refactor: 使用 col(...) 替代列引用并对结果进行 CursorResult 强转
* chore: ruff format
---------
Co-authored-by: aider (openai/gemini-3-pro-high) <aider@aider.chat >
Co-authored-by: Soulter <905617992@qq.com >
2025-12-09 14:13:47 +08:00
aa6d07afcc
refactor: move all internal commands from astrbot plugin to default_command plugin ( #3960 )
...
* refactor: move all internal commands from astrbot plugin to default_command plugin
* ruff check
* feat: add config
* ruff check
2025-12-08 22:17:32 +08:00
37566182b0
feat: segment reply supports segmentation words ( #3959 )
...
* feat: segment reply supports segmentation words
* chore: ruff format
* feat: enhance segmented reply processing by refining word extraction logic
* ruff format
2025-12-08 00:27:17 +08:00
5d856900ef
perf: some UI/UX fixes, change Console to Platform Logs ( #3873 )
...
* refactor: 统一‘平台日志’文案
* perf: 优化自动滚动开关键操作逻辑
* perf: add tooltips to save and code editor buttons
2025-12-05 16:02:20 +08:00
2ba0460f19
feat: introduce file extract capability ( #3870 )
...
* feat: introduce file extract capability
powered by MoonshotAI
* fix: correct indentation in default configuration file
* fix: add error handling for file extract application in InternalAgentSubStage
* fix: update file name handling in InternalAgentSubStage to correctly associate file names with extracted content
* feat: add condition settings for local agent runner in default configuration
* fix: enhance file naming logic in File component and update prompt handling in InternalAgentSubStage
2025-12-01 18:12:39 +08:00
a7fdc98b29
fix: third party agent runner cannot run properly when using non-default config file
...
fix : #3815
2025-11-29 23:45:12 +08:00
85b7f104df
fix: remove unnecessary provider check ( #3846 )
...
fixes : #3815
2025-11-29 23:15:19 +08:00
5c5515d462
fix: segmented reply regex error handling ( #3771 )
...
* fix: segmented reply regex error handling
closes : #3761
* fix: improve regex handling for segmented replies to support multiline input
* fix: update regex handling in ResultDecorateStage to use findall for segmented replies
* fix: update error logging message for segmented reply regex handling
2025-11-24 22:00:59 +08:00
39eb367866
perf: improve file structure
...
- 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.
2025-11-24 14:00:16 +08:00
a6dc458212
feat(third-party-agent): implement streaming response handling and enhance agent execution flow
2025-11-23 23:03:56 +08:00
910ec6c695
feat: implement third party agent sub stage and refactor provider management
...
- 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.
2025-11-23 20:18:51 +08:00
c7a58252fe
feat: supports knowledge base agentic search ( #3667 )
...
* feat: supports knowledge base agentic search
* fix: correct formatting of system prompt in knowledge base results
2025-11-17 17:29:18 +08:00
e200835074
refactor: remove unused Message import and context_model initialization in LLMRequestSubStage
2025-11-15 21:36:54 +08:00
5a11d8f0ee
refactor: LLM response handling with reasoning content ( #3632 )
...
* 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>
2025-11-15 21:31:03 +08:00
b062e83d54
refactor: remove redundant session lock management from message sending logic in RespondStage ( #3645 )
...
fixes : #3644
Co-authored-by: Dt8333 <lb0016@foxmail.com >
2025-11-15 21:30:05 +08:00
17422ba9c3
feat: introduce messages field in agent RunContext
2025-11-15 21:15:20 +08:00
d19945009f
refactor: decople the agent impl part and introduce some helper context method to call llm
2025-11-14 19:17:24 +08:00
3957861878
refactor: streamline llm processing logic ( #3607 )
...
* refactor: streamline llm processing logic
* perf: merge-nested-ifs
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
* fix: ruff format
* refactor: remove unnecessary debug logs in FunctionToolExecutor and LLMRequestSubStage
---------
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
2025-11-13 10:08:57 +08:00
6ac43c600e
perf: improve streaming fallback strategy for streaming-unsupported platform ( #3547 )
...
* feat: 修改tool_loop_agent_runner，新增stream_to_general属性。
Co-authored-by: aider (openai/gemini-2.5-flash-preview) <aider@aider.chat >
* refactor: 优化text_chat_stream，直接yield完整信息
Co-authored-by: aider (openai/gemini-2.5-flash-preview) <aider@aider.chat >
* feat(core): ✨ 添加streaming_fallback选项，允许进行流式请求和非流式输出
添加了streaming_fallback配置，默认为false。在PlatformMetadata中新增字段用于标识是否支持真流式输出。在LLMRequest中添加判断是否启用Fallback。
#3431 #2793 #3014
* refactor(core): 将stream_to_general移出toolLoopAgentRunner
* refactor(core.platform): 修改metadata中的属性名称
* fix: update streaming provider settings descriptions and add conditions
* fix: update streaming configuration to use unsupported_streaming_strategy and adjust related logic
* fix: remove support_streaming_message flag from WecomAIBotAdapter registration
* fix: update hint for non-streaming platform handling in configuration
* fix(core.pipeline): Update astrbot/core/pipeline/process_stage/method/llm_request.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* fix(core.pipeline): Update astrbot/core/pipeline/process_stage/method/llm_request.py
---------
Co-authored-by: aider (openai/gemini-2.5-flash-preview) <aider@aider.chat >
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
Co-authored-by: Soulter <905617992@qq.com >
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-11-12 18:01:20 +08:00
6d00717655
feat: add streaming support with toggle in chat interface and adjust layout for mobile
2025-11-09 21:57:30 +08:00
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
e190bbeeed
Optimize string concatenation in loops: replace += with list.join() ( #3246 )
...
* Initial plan
* Fix string concatenation performance issues in loops
Co-authored-by: LIghtJUNction <106986785+LIghtJUNction@users.noreply.github.com >
* Address code review feedback: Fix plugin list logic and add comment
Co-authored-by: LIghtJUNction <106986785+LIghtJUNction@users.noreply.github.com >
* Improve comment clarity for at_parts accumulation
Co-authored-by: LIghtJUNction <106986785+LIghtJUNction@users.noreply.github.com >
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com >
Co-authored-by: LIghtJUNction <106986785+LIghtJUNction@users.noreply.github.com >
2025-11-02 13:00:59 +08:00
0b7fc29ac4
style: add ruff lint module of isort and pyupgrade, and some ruff check fix ( #3214 )
...
Co-authored-by: Dt8333 <25431943+Dt8333@users.noreply.github.com >
Co-authored-by: Soulter <905617992@qq.com >
2025-11-01 13:26:19 +08:00
8ae2a556e4
feat: remove tips from knowledge base creation form and add persistent hints for field modifications
2025-10-25 15:06:07 +08:00
82cf4ed909
fix: 使用ruff格式化文件代码
2025-10-25 14:10:26 +08:00
6cb5527894
feat: 添加会话知识库配置的 API 接口，支持获取、设置和删除会话配置，优化知识库选择界面
2025-10-25 13:52:57 +08:00
b1b53ab983
Merge remote-tracking branch 'origin/master' into lwl-dev/knowledge-base
2025-10-24 21:48:47 +08:00
38e3f27899
feat: update knowledge base retrieval configuration and UI adjustments
2025-10-24 15:06:07 +08:00
3c58d96db5
feat: add configuration for final knowledge base retrieval count and update related components
2025-10-24 14:45:07 +08:00
59df244173
improve
2025-10-23 21:20:41 +08:00
65bc5efa19
feat: 集成知识库管理器，优化知识库上下文注入流程，移除冗余代码
2025-10-22 21:59:00 +08:00
36ffcf3cc3
fix: typing error
2025-10-21 10:56:44 +08:00
361d78247b
fix(core): 修复人格预设对话的重复注入 ( #3088 )
...
备份Context避免供应商适配器移除Context内字段导致将预设会话存入历史。深拷贝人格预设会话防止运行时被意外修改。
#3063
2025-10-19 20:13:57 +08:00
98a75e923d
feat: 集成知识库到核心生命周期和消息流水线
...
- 在 AstrBotCoreLifecycle 中初始化知识库管理器
- 将知识库注入器添加到消息处理上下文
- 在消息流水线中添加 KBEnhanceStage（知识库增强阶段）
- 实现会话删除时的知识库配置级联清理机制
- 添加会话管理器的回调注册机制，支持零侵入扩展
2025-10-19 18:41:34 +08:00
9ab652641d
feat: 支持配置工具调用超时时间并适配 ModelScope 的 MCP Server 配置 ( #3039 )
...
* feat: 支持配置工具调用超时时间并适配 ModelScope 的 MCP Server 配置。
closes : #2939
* fix: Remove unnecessary blank lines in _quick_test_mcp_connection function
2025-10-15 12:06:57 +08:00
80fccc90b7
feat: 支持接入企业微信智能机器人平台 ( #3034 )
...
* stage
* stage
* feat: 支持图片收发
* feat: add support for wecom_ai_bot in getPlatformIcon function
2025-10-14 23:20:56 +08:00
7191d28ada
fix: 启动了 TTS 但未配置 TTS 模型时，At 和 Reply 发送人无效
...
fixes : #2996
2025-10-10 12:11:03 +08:00
1413d6b5fe
fix: 让事件钩子被暂停时跳出循环，而不是继续执行 ( #2989 )
2025-10-09 15:01:45 +08:00
d951b99718
fix: 发送阶段将 Plain 为空的消息段移除
2025-10-03 00:45:07 +08:00
a8437d9331
feat: 支持在 Telegram 和飞书下请求 LLM 前预表态功能 ( #2737 )
...
* ✨ feat(platform): 为 Telegram 和飞书添加消息表情回应功能
支持在收到命令时自动添加表情回应，提升用户交互体验
新增平台特异配置项，允许自定义启用状态和表情列表
* Update astrbot/core/platform/astr_message_event.py
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
* style: ruff format
* fix: 优化平台特异配置的预回应表情处理逻辑
---------
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
Co-authored-by: Soulter <905617992@qq.com >
2025-09-30 17:29:34 +08:00
50f74f5ba2
fix: 修复"开启 TTS 时同时输出语音和文字内容"功能不可用的问题 ( #2900 )
...
fixes : #2844
2025-09-28 10:48:57 +08:00
c2a34475f1
feat: 支持删除指定会话以及部分会话管理优化 ( #2895 )
...
* feat: add toast notification system with snackbar component
* feat: add session deletion functionality
* feat: support batch operations for updating session persona, provider, LLM, and TTS statuses
fix : #2263
* feat: 修复对话状态关闭，删除对话管理库会导致对话无法恢复
fixes : #2309
2025-09-27 20:36:30 +08:00
a69195a02b
fix: webchat streaming queue interrupted after user closing tab ( #2892 )
...
* feat: add toast notification system with snackbar component
* feat: enhance chat functionality with conversation running state and notifications
* fix: update bot message avatar rendering during streaming
* feat: implement conversation tracking context manager for webchat
* fix: update conversation tracking to remove conversation ID on exit
2025-09-27 17:57:12 +08:00
ccb380ce06
feat: 支持接入 Coze ( #2858 )
...
* feat: 适配 coze 供应商
1. 支持文件上传
2. 支持多模态
3. 支持流式传输
4. 支持 API 端的上下文保存历史记录
5. 支持类似 dify 的 forget 接口
* style: format code
* fix: type checking error
* fix: 修复:
1. 使用coze api端的上下文时, 现在不会重复传递上下文
2. 使用 AstrBot 的上下文时, 正确处理其中的图片信息
3. 上传图片时, 提供一个非持久化的缓存避免重复上传(在解析上下文并将文件转化为file_id传递给coze api时, 如果没有缓存会导致很多的网络资源浪费)
4. 修复reset等指令不能正确重置上下文的问题
* fix: 移除某些地方多余的针对 dify 的断言, 以兼容 Coze
* style: 修改配置项显示/webchat平台对于非预期的类型的处理
* fix: 让conversation_id放到请求中正确的位置
* refactor: extract coze api client
* refactor: improve image processing logic in ProviderCoze
* chore: remove file ext guessing
---------
Co-authored-by: Soulter <905617992@qq.com >
2025-09-27 14:23:29 +08:00
09d1f96603
fix: 修复 /alter_cmd 指令无法控制指令组、子指令组和子指令组下子指令的问题 ( #2873 )
...
* fix: revert changes in command_group.py at 782c03625431943+Dt8333@users.noreply.github.com >
Co-authored-by: Soulter <905617992@qq.com >
2025-09-26 14:16:50 +08:00
9177bb660f
fix: improve error handling in run_agent for streaming responses
2025-09-23 10:34:24 +08:00
80a86f5b1b
fix: 修复 astrbot.core.star 等包下的 type checking error ( #2787 )
...
* fix: 修复 astrbot.core.star 等包下的 type checking error
* refactor: improve type checking and annotations
* chore: ruff format
2025-09-21 18:10:04 +08:00
a8f874bf05
fix: 修复分段回复时，引用消息单独发送导致第一条消息内容为空的问题 ( #2757 )
2025-09-16 10:45:39 +08:00
7740e1e131
ci: add ci stage of code format checking ( #2750 )
...
* style: ruff format
* ci(dashboard-ci): ensure GitHub Release action only runs on push events
* ci(code-format): ruff format and ruff check
2025-09-14 18:05:58 +08:00
b31b520c7c
feat: 支持管理 T2I 模版 ( #2638 )
...
* feat:添加t2i模板管理后端api,移除config.py中重复功能
* feat: 添加T2I模板管理功能前端，支持模板的创建、应用和重置
* refactor: 修复错误的保存逻辑，将t2i注册时打印路由信息部分移到基类实现
* remove:移除了路由注册时的打印
* chore: format code
* fix: update input variant from solo to outlined for better UI consistency
---------
Co-authored-by: Soulter <905617992@qq.com >
2025-09-07 00:14:28 +08:00
Dt8333
Soulter
Oscar Shaw
Soulter
Copilot
LIghtJUNction
lxfight
ctrlkk
Seayon
anka
RC-CHN