GithubBackup/MoviePilot
1
0
Fork 0
mirror of https://github.com/jxxghp/MoviePilot.git synced 2026-05-11 18:10:15 +08:00
Code Issues Packages Projects Releases Wiki Activity
7,063 Commits 2 Branches 306 Tags
bae086d8b8dbca8324f2f241e83b63dd4be75c69
Commit Graph

79 Commits

Author SHA1 Message Date
jxxghp
bae086d8b8 更新 __init__.py 2026-04-27 06:57:18 +08:00
jxxghp
221eb21694 refine internal middleware llm usage for streaming agents 
Use a non-streaming model for middleware-only calls so internal outputs do not leak into user streams and model-based middleware stays consistent.
 2026-04-27 06:55:41 +08:00
jxxghp
0277288a41 feat: add agent session usage status reporting 
Track per-session model and token usage so users can inspect context pressure and cumulative usage with /session_status.
 2026-04-26 08:19:05 +08:00
jxxghp
79bfeaf2af 移除工具调用前的流重置，保留模型思考文本可见 2026-04-25 23:12:34 +08:00
jxxghp
ae15eac0f8 feat: normalize internal system user ID in notification dispatch 
- Add SYSTEM_INTERNAL_USER_ID constant and helpers to app.utils.identity
- Ensure internal user ID is normalized to None before dispatching notifications, preventing misrouting to external channels
- Refactor MessageChain to use normalization for all message dispatch methods
- Add tests for internal user ID normalization and notification dispatch behavior
 2026-04-21 14:32:14 +08:00
jxxghp
04c2a1eb18 Add manual AI redo flow 2026-04-15 17:10:18 +08:00
jxxghp
7a5e513f25 feat(agent): support file attachments and local file replies 2026-04-14 15:22:01 +08:00
jxxghp
e5f97cd299 feat(agent): add voice message support with TTS/STT for Telegram and WeChat 
- Integrate voice message handling: detect and extract audio references from Telegram and WeChat messages, route to agent with voice reply preference.
- Add voice provider abstraction and OpenAI-based TTS/STT implementation.
- Implement agent tool `send_voice_message` for generating and sending voice replies, with fallback to text if voice is unavailable.
- Extend agent prompt and context to support voice reply instructions.
- Update notification and message schemas to support audio fields.
- Add Telegram and WeChat voice sending logic, including audio file conversion and temporary media upload for WeChat.
- Add tests for voice helper and agent voice routing.
 2026-04-12 12:30:02 +08:00
jxxghp
bf12a8679d refactor: 移除 agent 批量重试逻辑中的多余 try 块并优化缩进 2026-04-10 15:03:49 +08:00
jxxghp
18906e5ab2 更新 __init__.py 2026-04-09 22:51:37 +08:00
jxxghp
770065d9ed feat(agent): 优化Agent流式输出与工具消息发送逻辑 
- 新增 _should_stream() 方法，根据运行环境决定是否启用流式输出：
  后台模式不启用；渠道支持编辑启用；啰嗦模式开启时也启用
- 非流式模式下使用非流式LLM + ainvoke，避免不必要的流式开销
- 非啰嗦模式下工具调用时不发送任何中间消息（agent文字和工具提示），直接清掉缓冲区
 2026-04-09 22:12:20 +08:00
jxxghp
0c51d79be7 feat(agent): 合并同批次整理失败的agent重试调用，避免重复浪费token 
同一download_hash或同一源目录下的失败记录在5分钟缓冲期内合并为一次agent调用，
批量处理时只识别一次媒体信息后复用到所有文件。
 2026-04-09 07:16:56 +08:00
jxxghp
1e338e48ab fix(agent): 基于langgraph_step过滤中间步骤思考文本，抽离ThinkTagStripper类 
- 利用metadata中的langgraph_step检测工具调用前的中间步骤，非VERBOSE模式下
  自动reset清除模型输出的计划/推理文本（如NEXT STEPS、tool call描述等）
- 将<think>标签流式剥离逻辑抽离为独立的_ThinkTagStripper类，简化主流程
 2026-04-07 12:42:46 +08:00
jxxghp
ac9c9598f4 feat(agent): add tools for querying and updating custom identifiers 2026-04-07 09:00:15 +08:00
jxxghp
8109ffb445 feat(agent): add /stop_agent command for emergency stop of agent reasoning 
Add /stop_agent command that cancels the currently running agent reasoning
task without clearing the session or memory. Unlike /clear_session which
destroys the entire session, this allows users to stop a long-running or
stuck agent process and continue the conversation afterward.
 2026-04-07 07:32:35 +08:00
jxxghp
d7a5c32b08 feat: 整理失败时AI智能体自动重试 
- 新增 delete_transfer_history 工具供智能体删除失败历史记录
- 新增 transfer-failed-retry 技能引导智能体执行重试流程
- 新增 AI_AGENT_RETRY_TRANSFER 配置项控制是否启用
- AgentManager 新增 retry_failed_transfer() 方法创建独立会话执行重试
- 整理失败和媒体未识别时自动触发智能体重试
 2026-04-03 13:33:27 +08:00
jxxghp
244112be5c fix: 智能体唤醒后消息发送问题 2026-04-02 19:23:40 +08:00
jxxghp
1f526adbe7 feat: add NotificationType for Agent messages 2026-04-02 19:13:05 +08:00
jxxghp
9c51f73a72 feat(telegram): 优化Telegram文件下载与base64转换逻辑，重构消息发送相关代码 
- 新增 TelegramModule.download_file_to_base64 方法，统一文件下载与base64编码
- Telegram 客户端新增 download_file 方法，简化文件下载流程
- 消息图片下载逻辑调整为通过模块方法调用，移除冗余静态方法
- 修复部分参数格式与空格风格，提升代码一致性
- 优化长消息发送异常处理与代码结构
 2026-03-30 10:28:40 +08:00
jxxghp
2d358e376c refactor: 移除多余的局部导入 2026-03-29 09:59:22 +08:00
jxxghp
b349aa2693 feat(agent): 支持图片消息处理 2026-03-29 09:56:53 +08:00
jxxghp
296d815e3e refactor: 移除异步pop操作 2026-03-28 12:42:26 +08:00
jxxghp
6806900436 refactor: Update agent package initialization and imports. 2026-03-28 07:58:47 +08:00
jxxghp
f859d99d91 fix current_date 2026-03-27 21:55:09 +08:00
jxxghp
8d7ff2bd1d feat(agent): 新增AI_AGENT_VERBOSE开关，控制工具调用过程回复及提示词输出 2026-03-27 20:12:01 +08:00
jxxghp
e7d14691df 优化记忆结构 2026-03-26 22:29:09 +08:00
jxxghp
740b0a1396 fix 2026-03-26 12:42:54 +08:00
jxxghp
7d0c790185 fix: agent过滤模型思考/推理内容，不输出thinking到用户 2026-03-26 12:37:45 +08:00
jxxghp
83bf59dd4d feat: 新增 ActivityLogMiddleware，自动记录每次交互的活动日志并注入系统提示词 2026-03-26 03:32:20 +08:00
jxxghp
d5d6442e1d feat: 新增 moviepilot-api 技能，支持全量 REST API 调用；技能中间件自动同步内置技能到用户目录 2026-03-26 03:10:30 +08:00
jxxghp
a6f16dcf8f feat: 同一会话消息排队顺序处理，不同会话互不影响 2026-03-25 22:01:35 +08:00
jxxghp
d38b6dfc0a fix: 优化心跳提示词，后台任务只生成执行结果摘要 2026-03-25 18:18:34 +08:00
jxxghp
0a4091d93c fix: 后台任务使用非流式执行，仅发送模型最后一条回复 2026-03-25 18:15:19 +08:00
jxxghp
0399ab73cf feat: 后台任务(定时唤醒)跳过流式输出，仅广播最终结果 2026-03-25 17:10:48 +08:00
jxxghp
94c75eb1c7 feat: 智能体增加定时任务(Jobs)管理和心跳唤醒机制 
- 新增 JobsMiddleware 中间件，支持通过 JOB.md 文件管理长期/重复性任务
- 智能体可创建一次性(once)和重复性(recurring)任务，自动跟踪执行状态
- 新增心跳唤醒机制，定时调度器周期性唤醒智能体检查并执行待处理任务
- 新增 AI_AGENT_JOB_INTERVAL 配置项控制检查间隔，默认24小时
- 每次心跳使用独立会话，执行完毕后清理资源
 2026-03-25 13:02:20 +08:00
jxxghp
e6e50d7f0a fix: 修复Agent流式输出时回复消息未记录到数据库的问题 2026-03-25 07:01:17 +08:00
jxxghp
e82494c444 feat(agent): support skills 2026-03-24 08:48:27 +08:00
jxxghp
309b7b8a77 feat: 新增 LLM_MAX_TOOLS 配置项，支持按需启用 LLMToolSelectorMiddleware 2026-03-23 23:45:32 +08:00
jxxghp
6f4df912d8 更新 __init__.py 2026-03-23 22:33:18 +08:00
PKC278
4cbf1a886e fix: 移除AI智能体初始化中错误的await 2026-03-23 22:16:34 +08:00
jxxghp
faa046eea4 更新 __init__.py 2026-03-23 21:31:46 +08:00
jxxghp
873e3832b6 更新 __init__.py 2026-03-23 20:18:05 +08:00
jxxghp
4bc67dc816 feat(agent): Telegram与Agent相互时支持流式输出 2026-03-23 19:13:51 +08:00
jxxghp
9b00a5f3f1 refactor: Update agent stream processing to support 'v2' chunk format and prevent emitting empty content. 2026-03-23 17:23:44 +08:00
jxxghp
565e10b6a5 add LLMToolSelectorMiddleware 2026-03-23 08:16:19 +08:00
Aqr-K
41f53d39a0 Fix agent memory (#5607) 2026-03-23 04:30:46 +08:00
jxxghp
30b332ac7e feat: Introduce MemoryMiddleware and PatchToolCallsMiddleware to the agent, and add EditFileTool and WriteFileTool for file manipulation. 2026-03-22 23:35:34 +08:00
jxxghp
5739ca7f97 fix agent bug 2026-03-22 22:02:54 +08:00
jxxghp
5cded77387 feat(agent): upgrade langchain to v1.0+ 2026-03-22 21:41:12 +08:00
jxxghp
ea4e0dd764 feat(agent): upgrade langchain to v1.0+ 2026-03-22 21:07:45 +08:00