fix(subscribe): avoid duplicate best-version completion (#5931)

Fixes #5874

.github/workflows/test.yml

@@ -0,0 +1,55 @@
+name: Unit Tests
+
+on:
+  # 指向 v2 的 PR 与推送都跑全量单测，作为合并门禁
+  pull_request:
+    branches:
+      - v2
+  push:
+    branches:
+      - v2
+  # 允许手动触发
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: unit-tests-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    name: Unit Tests
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+          cache: 'pip'
+
+      - name: Cache pip dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.in', '**/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip setuptools wheel
+          # 用 requirements.in 还原 CI / 全新环境（含 pytest~=8.4 与 moviepilot-rust 等可选扩展），
+          # 与本地"干净 venv 复现"一致；测试运行器 pytest 已在 requirements.in 中声明。
+          pip install -r requirements.in
+
+      - name: Run tests
+        run: |
+          # tests/run.py 以 pytest 跑 tests 全量；tests/conftest.py 在收集前把 CONFIG_DIR
+          # 指向临时库并建表，测试杜绝真实网络/外部服务（详见 docs/testing.md）。
+          python tests/run.py

.gitignore

@@ -30,6 +30,7 @@ public/
 .moviepilot.env
 *.pyc
 *.log
+.coverage
 .vscode
 venv
 
@@ -41,3 +42,6 @@ pylint-report.json
 .claude/
 !.claude/*.json
 .claude/settings.local.json
+
+# Superpowers 设计/计划文档（本地协作产物，不纳入仓库）
+docs/superpowers/

AGENTS.md

@@ -41,6 +41,10 @@ Before executing any task, identify the domain and load the corresponding docume
 * **Primary Reference:** `docs/rules/11-quality-and-security.md`
 * **Required Constraints:** All code changes must pass the relevant pytest tests and pylint checks. Dependency changes require a passing safety scan.
 
+### Testing
+* **Primary Reference:** `docs/testing.md`
+* **Required Constraints:** pytest is the only runner; `tests/conftest.py` isolates each run to a temporary `CONFIG_DIR`. Tests must not touch the real database, network, or external services (TMDB, LLM catalogs, downloaders, media servers, MP server) — mock at the boundary or replay recorded responses; the bar is zero real outbound traffic. Tests must restore any process-level state they stub (`sys.modules`, singletons, caches, settings). New tests must be pytest-native (function + `assert` + fixtures); do not add new `unittest.TestCase`. Convert existing `TestCase` files to pytest-native opportunistically when you modify them. Before opening a PR to `v2`, run the full suite locally (`python tests/run.py`) and confirm it is green with zero real network calls; the `.github/workflows/test.yml` gate runs the same suite on every PR/push to `v2`.
+
 ### Commands and Development Workflow
 * **Primary Reference:** `docs/rules/03-commands.md`
 * **Required Constraints:** Only suggest or execute commands documented in that file. Do not assume tool defaults or global flags.

README.md

@@ -1,4 +1,3 @@
-
 # MoviePilot
 
 简体中文 | [English](README_EN.md)
@@ -12,66 +11,56 @@
 ![Docker Pulls V2](https://img.shields.io/docker/pulls/jxxghp/moviepilot-v2?style=for-the-badge)
 ![Platform](https://img.shields.io/badge/platform-Windows%20%7C%20Linux%20%7C%20Synology-blue?style=for-the-badge)
 
-
 基于 [NAStool](https://github.com/NAStool/nas-tools) 部分代码重新设计，聚焦自动化核心需求，减少问题同时更易于扩展和维护。
 
 # 仅用于学习交流使用，请勿在任何国内平台宣传该项目！
 
 发布频道：https://t.me/moviepilot_channel
 
-
 ## 主要特性
 
-- 前后端分离，基于FastApi + Vue3。
-- 聚焦核心需求，简化功能和设置，部分设置项可直接使用默认值。
-- 重新设计了用户界面，更加美观易用。
-
+- 聚焦影视自动化的核心流程：订阅、搜索、下载、整理、刮削、媒体库刷新与消息通知。
+- 前后端分离，后端基于 FastAPI，前端基于 Vue 3，部署和扩展边界更清晰。
+- 支持下载器、媒体服务器、元数据源、消息渠道、插件、工作流和 AI Agent 等能力组合。
+- 更完整的功能介绍、截图和使用入口见官网：https://movie-pilot.org
 
 ## 安装使用
 
-官方Wiki：https://wiki.movie-pilot.org
+推荐优先使用 Docker 部署，常用镜像包括 `jxxghp/moviepilot-v2` 和 `jxxghp/moviepilot`。Compose 示例、环境变量、目录映射和升级方式以官方 Wiki 为准：
 
+- 官方 Wiki：https://wiki.movie-pilot.org
+- PostgreSQL 部署说明：[docs/postgresql-setup.md](docs/postgresql-setup.md)
 
-## 本地 CLI
-
-一键安装运行脚本：
+也可以使用本地 CLI 以源码模式安装和管理 MoviePilot：
 
 ```shell
 curl -fsSL https://raw.githubusercontent.com/jxxghp/MoviePilot/v2/scripts/bootstrap-local.sh | bash
 ```
 
-使用 `moviepilot` 命令管理MoviePilot，完整 CLI 文档：[`docs/cli.md`](docs/cli.md)
+安装完成后使用 `moviepilot` 命令完成初始化、启动、停止、更新和配置查看。完整命令见 [docs/cli.md](docs/cli.md)。
 
+## Agent
+
+1. MoviePilot 自带智能体能力，可在完成模型配置后，通过自然语言调用系统工具，辅助完成搜索、订阅、下载、整理、排障等管理任务。
+2. 其它智能体可以导入本仓库的 `skills/` 目录以获得 MoviePilot 操作能力；支持 `skills` CLI 的环境可使用：
+
+   ```shell
+   npx skills add https://github.com/jxxghp/MoviePilot
+   ```
+
+   内置 Skills 列表见 [skills/](skills/)，自定义 Skill 可参考 [skills/create-moviepilot-skill/SKILL.md](skills/create-moviepilot-skill/SKILL.md)。
+3. 其它 MCP 客户端可以通过 MoviePilot 的 MCP 端点 `/api/v1/mcp` 调用工具，认证方式、客户端配置和工具 API 见 [docs/mcp-api.md](docs/mcp-api.md)。
 
-## 为 AI Agent 添加 Skills
-```shell
-npx skills add https://github.com/jxxghp/MoviePilot
-```
 
 ## 参与开发
 
-API文档：https://api.movie-pilot.org
+开发前请先阅读仓库规则和本地环境说明，保持变更聚焦，通过测试后再提交 PR。常用入口：
 
-MCP工具API文档：详见 [docs/mcp-api.md](docs/mcp-api.md)
-
-开发环境准备与本地源码运行说明：[`docs/development-setup.md`](docs/development-setup.md)
-
-本地开发默认通过 PyPI 依赖安装 Rust 加速扩展；扩展未安装或 `RUST_ACCEL=false` 时会自动使用 Python 实现：
-
-```shell
-python -m pip install moviepilot-rust
-python -c "from app.utils import rust_accel; print(rust_accel.is_available())"
-```
-
-如果输出 `True`，说明当前开发环境已经加载 `moviepilot_rust`。Rust 源码和打包发布流程在 [MoviePilot-Rust](https://github.com/jxxghp/MoviePilot-Rust) 仓库维护。
-
-需要本地评估 Rust 加速效果时，可运行：
-
-```shell
-python scripts/benchmark_rust_accel.py --loops 20 --repeat 5
-```
-
-插件开发说明：<https://wiki.movie-pilot.org/zh/plugindev>
+- 文档规则入口：[docs/rules/README.md](docs/rules/README.md)
+- 开发环境与本地源码运行：[docs/development-setup.md](docs/development-setup.md)
+- 测试说明：[docs/testing.md](docs/testing.md)
+- REST API 文档：https://api.movie-pilot.org
+- 插件开发说明：https://wiki.movie-pilot.org/zh/plugindev
 
 ## 相关项目
 
@@ -79,6 +68,7 @@ python scripts/benchmark_rust_accel.py --loops 20 --repeat 5
 - [MoviePilot-Resources](https://github.com/jxxghp/MoviePilot-Resources)
 - [MoviePilot-Plugins](https://github.com/jxxghp/MoviePilot-Plugins)
 - [MoviePilot-Server](https://github.com/jxxghp/MoviePilot-Server)
+- [MoviePilot-Rust](https://github.com/jxxghp/MoviePilot-Rust)
 - [MoviePilot-Wiki](https://github.com/jxxghp/MoviePilot-Wiki)
 
 ## 免责申明

README_EN.md

@@ -17,44 +17,49 @@ Redesigned from parts of [NAStool](https://github.com/NAStool/nas-tools), with a
 
 Release channel: https://t.me/moviepilot_channel
 
-
 ## Key Features
 
-- Frontend/backend separation based on FastApi + Vue3.
-- Focuses on core needs, simplifies features and settings, and allows some options to work well with sensible defaults.
-- Reworked user interface for a cleaner and more practical experience.
+- Focuses on the core media automation flow: subscriptions, search, downloads, file organization, scraping, media server refresh, and notifications.
+- Uses a separated backend/frontend architecture: FastAPI for the backend and Vue 3 for the frontend.
+- Connects download clients, media servers, metadata providers, message channels, plugins, workflows, and AI Agent capabilities.
+- For feature details, screenshots, and product entry points, see https://movie-pilot.org
 
+## Installation and Usage
 
-## Installation
+Docker is the recommended deployment model. Common images include `jxxghp/moviepilot-v2` and `jxxghp/moviepilot`. Compose examples, environment variables, volume mappings, and upgrade notes are maintained in the official wiki:
 
-Official wiki: https://wiki.movie-pilot.org
+- Official wiki: https://wiki.movie-pilot.org
+- PostgreSQL setup: [docs/postgresql-setup.md](docs/postgresql-setup.md)
 
-
-## Local CLI
-
-One-command bootstrap script:
+MoviePilot can also be installed and managed from source with the local CLI:
 
 ```shell
 curl -fsSL https://raw.githubusercontent.com/jxxghp/MoviePilot/v2/scripts/bootstrap-local.sh | bash
 ```
 
-Manage MoviePilot with the `moviepilot` command. Full CLI documentation: [`docs/cli.md`](docs/cli.md)
+After installation, use the `moviepilot` command for initialization, service management, updates, and configuration. See [docs/cli.md](docs/cli.md) for the full command reference.
 
+## Agent
 
-## Add Skills for AI Agents
-```shell
-npx skills add https://github.com/jxxghp/MoviePilot
-```
+1. MoviePilot includes a built-in AI Agent. After model configuration, it can call system tools through natural language to help with search, subscriptions, downloads, organization, diagnostics, and other management tasks.
+2. Other agents can import the repository `skills/` directory to gain MoviePilot operation capabilities. Environments that support the `skills` CLI can use:
+
+   ```shell
+   npx skills add https://github.com/jxxghp/MoviePilot
+   ```
+
+   Built-in skills live in [skills/](skills/). For custom skill authoring, see [skills/create-moviepilot-skill/SKILL.md](skills/create-moviepilot-skill/SKILL.md).
+3. Other MCP clients can call MoviePilot tools through `/api/v1/mcp`. Authentication, client configuration, and tool APIs are documented in [docs/mcp-api.md](docs/mcp-api.md).
 
 ## Development
 
-API documentation: https://api.movie-pilot.org
+Before contributing, read the repository rules and local environment guide, keep changes focused, and validate them before opening a PR. Useful entry points:
 
-MCP tool API documentation: see [docs/mcp-api.md](docs/mcp-api.md)
-
-Development environment setup and local source-run guide: [`docs/development-setup.md`](docs/development-setup.md)
-
-Plugin development guide: <https://wiki.movie-pilot.org/zh/plugindev>
+- Rule index: [docs/rules/README.md](docs/rules/README.md)
+- Development setup and local source run: [docs/development-setup.md](docs/development-setup.md)
+- Testing guide: [docs/testing.md](docs/testing.md)
+- REST API documentation: https://api.movie-pilot.org
+- Plugin development guide: https://wiki.movie-pilot.org/zh/plugindev
 
 ## Related Projects
 
@@ -62,6 +67,7 @@ Plugin development guide: <https://wiki.movie-pilot.org/zh/plugindev>
 - [MoviePilot-Resources](https://github.com/jxxghp/MoviePilot-Resources)
 - [MoviePilot-Plugins](https://github.com/jxxghp/MoviePilot-Plugins)
 - [MoviePilot-Server](https://github.com/jxxghp/MoviePilot-Server)
+- [MoviePilot-Rust](https://github.com/jxxghp/MoviePilot-Rust)
 - [MoviePilot-Wiki](https://github.com/jxxghp/MoviePilot-Wiki)
 
 ## Disclaimer

app/agent/__init__.py

@@ -36,6 +36,12 @@ from app.agent.middleware.memory import MemoryMiddleware
 from app.agent.middleware.patch_tool_calls import PatchToolCallsMiddleware
 from app.agent.middleware.runtime_config import RuntimeConfigMiddleware
 from app.agent.middleware.skills import SkillsMiddleware
+from app.agent.middleware.subagents import (
+    SUBAGENT_CONTROL_TOOL_NAME,
+    SUBAGENT_TASK_TOOL_NAME,
+    create_subagent_middlewares,
+    is_subagent_stream_metadata,
+)
 from app.agent.middleware.tool_selection import ToolSelectorMiddleware
 from app.agent.middleware.usage import UsageMiddleware
 from app.agent.prompt import prompt_manager
@@ -273,6 +279,15 @@ class MoviePilotAgent:
         except (TypeError, ValueError):
             return None
 
+    @staticmethod
+    def _get_recursion_limit() -> int:
+        """读取 LangGraph 递归上限，防止模型持续循环调用工具。"""
+        try:
+            limit = int(settings.LLM_MAX_ITERATIONS or 0)
+        except (TypeError, ValueError):
+            limit = 0
+        return limit if limit > 0 else 128
+
     @classmethod
     def _get_model_name(cls, model: Any) -> Optional[str]:
         return (
@@ -470,6 +485,7 @@ class MoviePilotAgent:
             base_url=settings.LLM_BASE_URL,
             base_url_preset=settings.LLM_BASE_URL_PRESET,
             user_agent=settings.LLM_USER_AGENT,
+            use_proxy=settings.LLM_USE_PROXY,
             thinking_level=None,
         )
         selected_event = await eventmanager.async_send_event(
@@ -502,6 +518,9 @@ class MoviePilotAgent:
                 self._clean_optional_text(self._get_event_value(resolved_data, "user_agent"))
                 or settings.LLM_USER_AGENT
         )
+        use_proxy = self._get_event_value(resolved_data, "use_proxy")
+        if use_proxy is None:
+            use_proxy = settings.LLM_USE_PROXY
         thinking_level = self._clean_optional_text(
             self._get_event_value(resolved_data, "thinking_level")
         )
@@ -528,6 +547,7 @@ class MoviePilotAgent:
             "base_url": base_url,
             "base_url_preset": base_url_preset,
             "user_agent": user_agent,
+            "use_proxy": bool(use_proxy),
             "thinking_level": thinking_level,
         }
         return self._llm_runtime_config
@@ -627,6 +647,8 @@ class MoviePilotAgent:
         detail = cls._exception_detail_text(error).lower()
         if "no endpoints found that support image input" in detail:
             return True
+        if "unknown variant" in detail and "image_url" in detail:
+            return True
         if "image input" not in detail and "images" not in detail:
             return False
         return any(
@@ -767,6 +789,25 @@ class MoviePilotAgent:
             allow_message_tools=self.allow_message_tools,
         )
 
+    def _initialize_subagent_tools(self) -> List:
+        """
+        初始化子代理专用静默工具列表。
+        """
+        return MoviePilotToolFactory.create_tools(
+            session_id=self.session_id,
+            user_id=self.user_id,
+            channel=self.channel,
+            source=self.source,
+            username=self.username,
+            stream_handler=None,
+            agent_context={
+                "user_reply_sent": False,
+                "reply_mode": None,
+                "should_dispatch_reply": False,
+            },
+            allow_message_tools=False,
+        )
+
     async def _create_agent(self, streaming: bool = False):
         """
         创建 LangGraph Agent（使用 create_agent + SummarizationMiddleware）
@@ -789,10 +830,22 @@ class MoviePilotAgent:
 
             # 工具列表
             tools = self._initialize_tools()
+            subagent_middlewares, subagent_task_tools = create_subagent_middlewares(
+                model=non_streaming_model,
+                tools=self._initialize_subagent_tools(),
+                stream_handler=self.stream_handler,
+            )
             max_tools = settings.LLM_MAX_TOOLS
             always_include_tools = (
                 MoviePilotToolFactory.get_tool_selector_always_include_names(tools)
             )
+            if subagent_task_tools:
+                always_include_tools.extend(
+                    tool.name
+                    for tool in subagent_task_tools
+                    if getattr(tool, "name", None)
+                    in {SUBAGENT_TASK_TOOL_NAME, SUBAGENT_CONTROL_TOOL_NAME}
+                )
 
             # 中间件
             middlewares = [
@@ -815,6 +868,8 @@ class MoviePilotAgent:
                 ),
                 # 错误工具调用修复
                 PatchToolCallsMiddleware(),
+                # 子代理委派
+                *subagent_middlewares,
                 # 用量统计
                 UsageMiddleware(on_usage=self._record_usage),
             ]
@@ -832,7 +887,7 @@ class MoviePilotAgent:
                 middlewares.append(
                     ToolSelectorMiddleware(
                         model=non_streaming_model,
-                        selection_tools=tools,
+                        selection_tools=[*tools, *subagent_task_tools],
                         max_tools=max_tools,
                         always_include=always_include_tools,
                     )
@@ -854,6 +909,7 @@ class MoviePilotAgent:
             message: str,
             images: List[str] = None,
             files: Optional[List[dict]] = None,
+            has_audio_input: bool = False,
     ) -> str:
         """
         处理用户消息，流式推理并返回 Agent 回复
@@ -861,7 +917,8 @@ class MoviePilotAgent:
         try:
             logger.info(
                 f"Agent推理: session_id={self.session_id}, input={message}, "
-                f"images={len(images) if images else 0}, files={len(files) if files else 0}"
+                f"images={len(images) if images else 0}, files={len(files) if files else 0}, "
+                f"audio_input={has_audio_input}"
             )
             self._tool_context = {
                 "user_reply_sent": False,
@@ -878,6 +935,10 @@ class MoviePilotAgent:
             # 构建结构化用户消息内容
             request_payload = {
                 "message": message or "",
+                "input": {
+                    "mode": "voice" if has_audio_input else "text",
+                    "transcribed": bool(has_audio_input),
+                },
                 "images": [
                     {"index": index + 1, "type": "image"}
                     for index, _ in enumerate(images or [])
@@ -929,6 +990,8 @@ class MoviePilotAgent:
         ):
             if chunk["type"] == "messages":
                 token, metadata = chunk["data"]
+                if is_subagent_stream_metadata(metadata):
+                    continue
                 if not token or not hasattr(token, "tool_call_chunks"):
                     continue
 
@@ -970,7 +1033,8 @@ class MoviePilotAgent:
             agent_config = {
                 "configurable": {
                     "thread_id": self.session_id,
-                }
+                },
+                "recursion_limit": self._get_recursion_limit(),
             }
 
             # 判断是否启用流式输出
@@ -1180,6 +1244,7 @@ class _MessageTask:
     message: str
     images: Optional[List[str]] = None
     files: Optional[List[dict]] = None
+    has_audio_input: bool = False
     channel: Optional[str] = None
     source: Optional[str] = None
     username: Optional[str] = None
@@ -1187,6 +1252,8 @@ class _MessageTask:
     original_chat_id: Optional[str] = None
     processing_status: Optional[dict] = None
     reply_mode: ReplyMode = ReplyMode.DISPATCH
+    persist_output_message: bool = True
+    allow_message_tools: bool = True
 
 
 class AgentManager:
@@ -1324,12 +1391,15 @@ class AgentManager:
             message: str,
             images: List[str] = None,
             files: Optional[List[dict]] = None,
+            has_audio_input: bool = False,
             channel: str = None,
             source: str = None,
             username: str = None,
             original_message_id: Optional[str] = None,
             original_chat_id: Optional[str] = None,
             reply_mode: ReplyMode = ReplyMode.DISPATCH,
+            persist_output_message: bool = True,
+            allow_message_tools: bool = True,
     ) -> str:
         """
         处理用户消息：将消息放入会话队列，按顺序依次处理。
@@ -1341,12 +1411,15 @@ class AgentManager:
             message=message,
             images=images,
             files=files,
+            has_audio_input=has_audio_input,
             channel=channel,
             source=source,
             username=username,
             original_message_id=original_message_id,
             original_chat_id=original_chat_id,
             reply_mode=reply_mode,
+            persist_output_message=persist_output_message,
+            allow_message_tools=allow_message_tools,
         )
         self._record_session_activity(session_id, user_id)
 
@@ -1456,6 +1529,8 @@ class AgentManager:
                 original_message_id=task.original_message_id,
                 original_chat_id=task.original_chat_id,
                 replay_mode=task.reply_mode,
+                persist_output_message=task.persist_output_message,
+                allow_message_tools=task.allow_message_tools,
             )
             self.active_agents[session_id] = agent
         else:
@@ -1470,8 +1545,16 @@ class AgentManager:
             agent.original_message_id = task.original_message_id
             agent.original_chat_id = task.original_chat_id
             agent.reply_mode = task.reply_mode
+            agent.persist_output_message = task.persist_output_message
+            agent.allow_message_tools = task.allow_message_tools
 
-        return await agent.process(task.message, images=task.images, files=task.files)
+        process_kwargs = {
+            "images": task.images,
+            "files": task.files,
+        }
+        if task.has_audio_input:
+            process_kwargs["has_audio_input"] = True
+        return await agent.process(task.message, **process_kwargs)
 
     async def stop_current_task(self, session_id: str):
         """
@@ -1522,7 +1605,7 @@ class AgentManager:
                 await self._session_workers[session_id]
             except asyncio.CancelledError:
                 pass
-            self._session_workers.pop(session_id, None)
+            self._session_workers.pop(session_id, None)  # noqa
 
         # 清理队列
         self._session_queues.pop(session_id, None)
@@ -1607,7 +1690,9 @@ class AgentManager:
                 channel=None,
                 source=None,
                 username=settings.SUPERUSER,
-                reply_mode=ReplyMode.DISPATCH,
+                reply_mode=ReplyMode.CAPTURE_ONLY,
+                persist_output_message=False,
+                allow_message_tools=True,
             )
 
             # 等待消息队列处理完成

app/agent/callback/__init__.py

@@ -293,6 +293,8 @@ class StreamingHandler:
         tool_message = (tool_message or "").strip()
         tool_message_lower = tool_message.lower()
 
+        if tool_name == "task":
+            return "subagent", tool_kwargs.get("subagent_type")
         if tool_name == "read_file":
             return "file_read", tool_kwargs.get("file_path")
         if tool_name in {"write_file", "edit_file"}:
@@ -408,6 +410,8 @@ class StreamingHandler:
             return f"执行了 {count} 次操作"
         if category == "interaction":
             return f"发起了 {count} 次交互"
+        if category == "subagent":
+            return f"已调用 {count} 个子代理"
         return f"调用了 {count} 次工具"
 
     def _can_stream(self) -> bool:

app/agent/llm/capability.py

@@ -670,6 +670,11 @@ class AgentCapabilityManager:
     def _normalize_provider_name(provider: Optional[str]) -> str:
         return (provider or "openai").strip().lower()
 
+    @staticmethod
+    def _get_provider_log_name(provider: AudioCapabilityProvider) -> str:
+        provider_name = getattr(provider, "name", None)
+        return provider_name if isinstance(provider_name, str) else provider.__class__.__name__
+
     @classmethod
     def get_audio_provider(cls, mode: str) -> Optional[AudioCapabilityProvider]:
         provider_name = cls._normalize_provider_name(
@@ -714,17 +719,45 @@ class AgentCapabilityManager:
 
     @classmethod
     def transcribe_audio(cls, content: bytes, filename: str = "input.ogg") -> Optional[str]:
+        """将语音文件内容转写为文字，并记录能力调用日志。"""
         provider = cls.get_audio_provider("input")
         if not provider or not cls.is_audio_input_available():
+            logger.info("语音转文字跳过：音频输入能力未启用或 provider 不可用")
             return None
-        return provider.transcribe_audio(content=content, filename=filename)
+        provider_name = cls._get_provider_log_name(provider)
+        logger.info(
+            f"语音转文字开始：provider={provider_name}, filename={filename}, "
+            f"bytes={len(content) if content else 0}"
+        )
+        transcript = provider.transcribe_audio(content=content, filename=filename)
+        if transcript:
+            logger.info(
+                f"语音转文字完成：provider={provider_name}, filename={filename}, "
+                f"text_len={len(transcript)}"
+            )
+        else:
+            logger.info(
+                f"语音转文字无结果：provider={provider_name}, filename={filename}"
+            )
+        return transcript
 
     @classmethod
     def synthesize_speech(cls, text: str) -> Optional[Path]:
+        """将文字合成为语音文件，并记录能力调用日志。"""
         provider = cls.get_audio_provider("output")
         if not provider or not cls.is_audio_output_available():
+            logger.info("文字转语音跳过：音频输出能力未启用或 provider 不可用")
             return None
-        return provider.synthesize_speech(text=text)
+        provider_name = cls._get_provider_log_name(provider)
+        logger.info(
+            f"文字转语音开始：provider={provider_name}, text_len={len(text) if text else 0}"
+        )
+        output_path = provider.synthesize_speech(text=text)
+        if output_path:
+            logger.info(f"文字转语音完成：provider={provider_name}, path={output_path}")
+        else:
+            logger.info(f"文字转语音无结果：provider={provider_name}")
+        return output_path
 
     @classmethod
     def resolve_reply_mode(cls, channel: Optional[str], source: Optional[str]) -> str:
@@ -734,29 +767,61 @@ class AgentCapabilityManager:
         return cls.REPLY_MODE_TEXT
 
     @classmethod
-    def supports_native_voice_reply(
-        cls, channel: Optional[str], source: Optional[str]
-    ) -> bool:
-        """判断当前渠道是否支持原生语音消息发送。"""
+    def _parse_message_channel(cls, channel: Optional[Any]):
+        """将渠道入参归一化为消息渠道枚举。"""
         if not channel:
+            return None
+
+        from app.schemas.types import MessageChannel
+
+        if isinstance(channel, MessageChannel):
+            return channel
+
+        channel_text = str(channel).strip()
+        if not channel_text:
+            return None
+        lowered_channel = channel_text.lower()
+        for channel_item in MessageChannel:
+            aliases = {
+                channel_item.value.lower(),
+                channel_item.name.lower(),
+                f"{MessageChannel.__name__}.{channel_item.name}".lower(),
+            }
+            if lowered_channel in aliases:
+                return channel_item
+        return None
+
+    @staticmethod
+    def _is_wechat_app_mode(source: Optional[str]) -> bool:
+        """判断企业微信来源是否为自建应用模式。"""
+        if not source:
             return False
 
         from app.helper.service import ServiceConfigHelper
-        from app.schemas.types import MessageChannel
 
-        try:
-            channel_enum = MessageChannel(channel)
-        except (TypeError, ValueError):
-            return False
-
-        if channel_enum == MessageChannel.Telegram:
-            return True
-        if channel_enum != MessageChannel.Wechat:
-            return False
-
-        # 企业微信 bot 模式不支持发送语音，只有应用模式可用。
         for config in ServiceConfigHelper.get_notification_configs():
             if config.name != source:
                 continue
             return (config.config or {}).get("WECHAT_MODE", "app") != "bot"
         return False
+
+    @classmethod
+    def supports_native_voice_reply(
+            cls, channel: Optional[str], source: Optional[str]
+    ) -> bool:
+        """判断当前渠道是否支持原生语音消息发送。"""
+        from app.schemas.message import ChannelCapability, ChannelCapabilityManager
+        from app.schemas.types import MessageChannel
+
+        channel_enum = cls._parse_message_channel(channel)
+        if not channel_enum:
+            return False
+
+        if not ChannelCapabilityManager.supports_capability(
+                channel_enum, ChannelCapability.AUDIO_OUTPUT
+        ):
+            return False
+
+        if channel_enum == MessageChannel.Wechat:
+            return cls._is_wechat_app_mode(source)
+        return True

app/agent/llm/helper.py

@@ -87,7 +87,7 @@ def _patch_gemini_thought_signature():
         # 补丁 2：修复 _parse_chat_history 中 first_fc_seen 只修复第一个
         # function_call 的问题。用 wrapper 在原函数返回后，确保所有 model
         # 消息中所有 function_call 都带有 thought_signature。
-        _original_parse_chat_history = _cm._parse_chat_history
+        _original_parse_chat_history = _cm._parse_chat_history  # noqa
 
         def _patched_parse_chat_history(*args, **kwargs):
             result = _original_parse_chat_history(*args, **kwargs)
@@ -137,6 +137,57 @@ def _get_httpx_proxy_key() -> str:
         return "proxies"
 
 
+def _resolve_llm_proxy(use_proxy: bool | None = None) -> str | None:
+    """
+    解析本次 LLM 调用应使用的系统代理地址。
+    """
+    should_use_proxy = settings.LLM_USE_PROXY if use_proxy is None else use_proxy
+    return settings.PROXY_HOST if should_use_proxy and settings.PROXY_HOST else None
+
+
+def _build_httpx_proxy_kwargs(proxy_url: str | None) -> dict[str, str]:
+    """
+    构造兼容当前 httpx 版本的代理参数。
+    """
+    if not proxy_url:
+        return {}
+    return {_get_httpx_proxy_key(): proxy_url}
+
+
+def _build_google_client_args(proxy_url: str | None) -> dict[str, Any]:
+    """
+    构造 Google SDK 透传给 httpx 的客户端参数。
+    """
+    return {
+        "trust_env": False,
+        **_build_httpx_proxy_kwargs(proxy_url),
+    }
+
+
+def _build_httpx_client(
+        proxy_url: str | None,
+        *,
+        async_client: bool = False,
+        timeout: float | None = None,
+):
+    """
+    构造显式代理策略的 httpx 客户端。
+
+    当关闭 LLM 代理时也返回 trust_env=False 的客户端，避免 httpx 自动读取
+    进程环境变量中的代理配置。
+    """
+    import httpx
+
+    client_cls = httpx.AsyncClient if async_client else httpx.Client
+    kwargs: dict[str, Any] = {
+        "trust_env": False,
+        **_build_httpx_proxy_kwargs(proxy_url),
+    }
+    if timeout is not None:
+        kwargs["timeout"] = timeout
+    return client_cls(**kwargs)
+
+
 def _deepseek_thinking_toggle(extra_body: Any) -> bool | None:
     """
     解析 DeepSeek extra_body 中显式传入的 thinking 开关。
@@ -354,6 +405,7 @@ def _patch_openai_responses_instructions_support():
         return
 
     _patch_openai_interleaved_reasoning_content_support()
+    _patch_openai_responses_empty_output_support()
 
     if getattr(ChatOpenAI, "_moviepilot_responses_instructions_patched", False):
         return
@@ -413,6 +465,64 @@ def _patch_openai_responses_instructions_support():
     logger.debug("已修补 langchain-openai responses API 的 instructions 兼容性")
 
 
+def _patch_openai_responses_empty_output_support():
+    """
+    修补 langchain-openai Responses API 流式完成事件 output 为空的兼容性。
+
+    ChatGPT Codex 后端有时会在 `response.completed` chunk 里返回
+    `response.output = None`，但前面的 delta chunk 已经包含实际文本。
+    langchain-openai 在收尾阶段遍历 output 会抛出 TypeError，这里将缺失
+    output 规整为空列表，让收尾 chunk 只承载 usage/metadata。
+    """
+    try:
+        import langchain_openai.chat_models.base as _openai_base
+    except Exception as err:
+        logger.debug(f"跳过 langchain-openai responses output 修补：{err}")
+        return
+
+    if getattr(_openai_base, "_moviepilot_responses_empty_output_patched", False):
+        return
+
+    original_construct = getattr(
+        _openai_base, "_construct_lc_result_from_responses_api", None
+    )
+    if not callable(original_construct):
+        logger.warning("langchain-openai 缺少 Responses API 结果构造函数，无法修补 output")
+        return
+
+    def _clone_response_with_empty_output(response):
+        """
+        复制 Responses 对象，把缺失 output 规整为空列表。
+        """
+        model_copy = getattr(response, "model_copy", None)
+        if callable(model_copy):
+            try:
+                return model_copy(update={"output": []})
+            except Exception as e:
+                logger.debug(f"复制 Responses 对象失败，回退原地修补 output：{e}")
+
+        try:
+            setattr(response, "output", [])
+        except Exception as e:
+            logger.debug(f"原地修补 Responses output 失败：{e}")
+        return response
+
+    @wraps(original_construct)
+    def _patched_construct_lc_result_from_responses_api(response, *args, **kwargs):
+        """
+        在 Responses API 收尾 chunk 缺少 output 时跳过空内容遍历。
+        """
+        if hasattr(response, "output") and getattr(response, "output", None) is None:
+            response = _clone_response_with_empty_output(response)
+        return original_construct(response, *args, **kwargs)
+
+    _openai_base._construct_lc_result_from_responses_api = (
+        _patched_construct_lc_result_from_responses_api
+    )
+    _openai_base._moviepilot_responses_empty_output_patched = True
+    logger.debug("已修补 langchain-openai responses API 空 output 兼容性")
+
+
 class LLMHelper:
     """LLM模型相关辅助功能"""
 
@@ -733,6 +843,7 @@ class LLMHelper:
             base_url: str | None = None,
             base_url_preset: str | None = None,
             user_agent: str | None = None,
+            use_proxy: bool | None = None,
     ):
         """
         获取LLM实例
@@ -747,6 +858,7 @@ class LLMHelper:
         :param base_url: API Base URL。未显式传入时使用当前配置项 LLM_BASE_URL。
         :param base_url_preset: Base URL 预设。未显式传入时使用当前配置项 LLM_BASE_URL_PRESET。
         :param user_agent: OpenAI兼容接口请求 User-Agent。未显式传入时使用配置项 LLM_USER_AGENT。
+        :param use_proxy: 是否为本次 LLM 调用使用系统代理。未显式传入时使用配置项 LLM_USE_PROXY。
         :return: LLM实例
         """
         provider_name = str(provider if provider is not None else settings.LLM_PROVIDER).lower()
@@ -772,6 +884,7 @@ class LLMHelper:
                 base_url=base_url_value,
                 base_url_preset_id=base_url_preset_value,
                 user_agent=user_agent_value,
+                use_proxy=use_proxy,
             )
         except Exception as err:
             logger.debug(f"LLM provider 目录不可用，回退到旧运行时逻辑: {err}")
@@ -797,6 +910,7 @@ class LLMHelper:
             model=model_name,
             runtime=runtime,
         )
+        llm_proxy = _resolve_llm_proxy(use_proxy)
 
         if runtime["runtime"] == "google":
             # 修补 Gemini 2.5 思考模型的 thought_signature 兼容性
@@ -807,18 +921,13 @@ class LLMHelper:
             # 会导致工具调用时报错 400
             from langchain_google_genai import ChatGoogleGenerativeAI
 
-            client_args = None
-            if settings.PROXY_HOST:
-                proxy_key = _get_httpx_proxy_key()
-                client_args = {proxy_key: settings.PROXY_HOST}
-
             model = ChatGoogleGenerativeAI(
                 model=model_name,
                 api_key=runtime["api_key"],
                 retries=3,
                 temperature=settings.LLM_TEMPERATURE,
                 streaming=streaming,
-                client_args=client_args,
+                client_args=_build_google_client_args(llm_proxy),
                 **thinking_kwargs,
             )
         elif runtime["runtime"] == "deepseek":
@@ -833,6 +942,8 @@ class LLMHelper:
                 temperature=settings.LLM_TEMPERATURE,
                 streaming=streaming,
                 stream_usage=True,
+                http_client=_build_httpx_client(llm_proxy),
+                http_async_client=_build_httpx_client(llm_proxy, async_client=True),
                 **thinking_kwargs,
             )
         elif runtime["runtime"] in {"anthropic_compatible", "copilot_anthropic"}:
@@ -846,7 +957,7 @@ class LLMHelper:
                 temperature=settings.LLM_TEMPERATURE,
                 streaming=streaming,
                 stream_usage=True,
-                anthropic_proxy=settings.PROXY_HOST,
+                anthropic_proxy=llm_proxy,
                 default_headers=default_headers,
                 **thinking_kwargs,
             )
@@ -867,7 +978,15 @@ class LLMHelper:
                 temperature=settings.LLM_TEMPERATURE,
                 streaming=streaming,
                 stream_usage=True,
-                openai_proxy=settings.PROXY_HOST,
+                openai_proxy=llm_proxy,
+                **(
+                    {}
+                    if llm_proxy
+                    else {
+                        "http_client": _build_httpx_client(llm_proxy),
+                        "http_async_client": _build_httpx_client(llm_proxy, async_client=True),
+                    }
+                ),
                 default_headers=default_headers,
                 use_responses_api=use_responses_api,
                 **thinking_kwargs,
@@ -945,6 +1064,7 @@ class LLMHelper:
             base_url: str | None = None,
             base_url_preset: str | None = None,
             user_agent: str | None = None,
+            use_proxy: bool | None = None,
     ) -> dict:
         """
         使用当前已保存配置执行一次最小 LLM 调用。
@@ -961,6 +1081,7 @@ class LLMHelper:
             base_url=base_url,
             base_url_preset=base_url_preset,
             user_agent=user_agent,
+            use_proxy=use_proxy,
         )
         try:
             response = await asyncio.wait_for(llm.ainvoke(prompt), timeout=timeout)
@@ -992,6 +1113,7 @@ class LLMHelper:
             base_url: str | None = None,
             base_url_preset: str | None = None,
             user_agent: str | None = None,
+            use_proxy: bool | None = None,
             force_refresh: bool = False,
     ) -> List[dict[str, Any]]:
         """
@@ -1010,6 +1132,7 @@ class LLMHelper:
                 base_url=base_url,
                 base_url_preset_id=base_url_preset,
                 user_agent=user_agent,
+                use_proxy=use_proxy,
                 force_refresh=force_refresh,
             )
         except Exception as err:
@@ -1017,7 +1140,10 @@ class LLMHelper:
             if provider == "google":
                 return [
                     {"id": model_id, "name": model_id}
-                    for model_id in await self._get_google_models(api_key or "")
+                    for model_id in await self._get_google_models(
+                        api_key or "",
+                        use_proxy=use_proxy,
+                    )
                 ]
             try:
                 from app.agent.llm.provider import LLMProviderManager
@@ -1039,24 +1165,23 @@ class LLMHelper:
                     api_key or "",
                     model_list_base_url,
                     user_agent=user_agent,
+                    use_proxy=use_proxy,
                 )
             ]
 
     @staticmethod
-    async def _get_google_models(api_key: str) -> List[str]:
+    async def _get_google_models(api_key: str, use_proxy: bool | None = None) -> List[str]:
         """获取Google模型列表（使用 google-genai SDK v1）"""
         try:
             from google import genai
             from google.genai.types import HttpOptions
 
-            http_options = None
-            if settings.PROXY_HOST:
-                proxy_key = _get_httpx_proxy_key()
-                proxy_args = {proxy_key: settings.PROXY_HOST}
-                http_options = HttpOptions(
-                    client_args=proxy_args,
-                    async_client_args=proxy_args,
-                )
+            llm_proxy = _resolve_llm_proxy(use_proxy)
+            google_client_args = _build_google_client_args(llm_proxy)
+            http_options = HttpOptions(
+                client_args=google_client_args,
+                async_client_args=google_client_args,
+            )
 
             client = genai.Client(api_key=api_key, http_options=http_options)
             models = await client.aio.models.list()
@@ -1077,6 +1202,7 @@ class LLMHelper:
             api_key: str,
             base_url: str = None,
             user_agent: str | None = None,
+            use_proxy: bool | None = None,
     ) -> List[str]:
         """获取OpenAI兼容模型列表"""
         try:
@@ -1092,6 +1218,11 @@ class LLMHelper:
                     None,
                     user_agent=user_agent,
                 ),
+                http_client=_build_httpx_client(
+                    _resolve_llm_proxy(use_proxy),
+                    async_client=True,
+                    timeout=15.0,
+                ),
             )
             models = await client.models.list()
             await client.close()

app/agent/llm/provider.py

@@ -1085,14 +1085,20 @@ class LLMProviderManager(metaclass=Singleton):
         return builtin_specs + self._dynamic_provider_specs(builtin_specs)
 
     async def _get_provider_async(
-            self, provider_id: str, force_refresh: bool = False
+            self,
+            provider_id: str,
+            force_refresh: bool = False,
+            use_proxy: Optional[bool] = None,
     ) -> ProviderSpec:
         """异步获取指定 provider 的 ProviderSpec 实例。"""
         normalized_provider_id = self._normalize_provider_id(provider_id)
         try:
             return self.get_provider(normalized_provider_id)
         except LLMProviderError:
-            await self.get_models_dev_data(force_refresh=force_refresh)
+            await self.get_models_dev_data(
+                force_refresh=force_refresh,
+                use_proxy=use_proxy,
+            )
             return self.get_provider(normalized_provider_id)
 
     def _serialize_provider(self, spec: ProviderSpec) -> dict[str, Any]:
@@ -1132,11 +1138,16 @@ class LLMProviderManager(metaclass=Singleton):
         }
 
     async def list_providers_async(
-            self, force_refresh: bool = False
+            self,
+            force_refresh: bool = False,
+            use_proxy: Optional[bool] = None,
     ) -> list[dict[str, Any]]:
         """返回前端可渲染的 provider 目录，并优先补齐 models.dev 动态平台。"""
         try:
-            await self.get_models_dev_data(force_refresh=force_refresh)
+            await self.get_models_dev_data(
+                force_refresh=force_refresh,
+                use_proxy=use_proxy,
+            )
         except Exception as err:
             logger.debug(f"加载 models.dev provider 目录失败，回退内置列表: {err}")
         return self.list_providers()
@@ -1327,10 +1338,14 @@ class LLMProviderManager(metaclass=Singleton):
         params = httpx.Client.__init__.__code__.co_varnames
         return "proxy" if "proxy" in params else "proxies"
 
-    def _build_httpx_kwargs(self) -> dict[str, Any]:
+    def _build_httpx_kwargs(self, use_proxy: Optional[bool] = None) -> dict[str, Any]:
         """构造用于 httpx 客户端的参数，如代理等。"""
-        kwargs: dict[str, Any] = {"timeout": self._DEFAULT_TIMEOUT}
-        if settings.PROXY_HOST:
+        should_use_proxy = settings.LLM_USE_PROXY if use_proxy is None else use_proxy
+        kwargs: dict[str, Any] = {
+            "timeout": self._DEFAULT_TIMEOUT,
+            "trust_env": False,
+        }
+        if should_use_proxy and settings.PROXY_HOST:
             kwargs[self._httpx_proxy_key()] = settings.PROXY_HOST
         return kwargs
 
@@ -1441,15 +1456,19 @@ class LLMProviderManager(metaclass=Singleton):
         except Exception as err:
             logger.warning(f"写入 models.dev 缓存失败: {err}")
 
-    async def _fetch_models_dev(self) -> dict[str, Any]:
+    async def _fetch_models_dev(self, use_proxy: Optional[bool] = None) -> dict[str, Any]:
         """通过网络请求获取最新 models.dev 数据。"""
-        headers = {"User-Agent": "MoviePilot/1.0"}
-        async with httpx.AsyncClient(**self._build_httpx_kwargs()) as client:
+        headers = {"User-Agent": settings.USER_AGENT}
+        async with httpx.AsyncClient(**self._build_httpx_kwargs(use_proxy)) as client:
             response = await client.get(self._MODELS_DEV_URL, headers=headers)
             response.raise_for_status()
             return response.json()
 
-    async def get_models_dev_data(self, force_refresh: bool = False) -> dict[str, Any]:
+    async def get_models_dev_data(
+            self,
+            force_refresh: bool = False,
+            use_proxy: Optional[bool] = None,
+    ) -> dict[str, Any]:
         """
         返回 models.dev 原始数据。
 
@@ -1475,7 +1494,7 @@ class LLMProviderManager(metaclass=Singleton):
                         return cached
 
             try:
-                payload = await self._fetch_models_dev()
+                payload = await self._fetch_models_dev(use_proxy=use_proxy)
                 self._models_dev_data = payload
                 self._models_dev_loaded_at = now
                 await self._write_models_dev_to_disk(payload)
@@ -1499,9 +1518,13 @@ class LLMProviderManager(metaclass=Singleton):
             provider_id: str,
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
     ) -> dict[str, Any]:
         """获取指定 provider 在 models.dev 中的完整负载。"""
-        spec = await self._get_provider_async(provider_id)
+        spec = await self._get_provider_async(
+            provider_id,
+            use_proxy=use_proxy,
+        )
         models_dev_provider_id = self._resolve_provider_models_dev_provider_id(
             spec,
             base_url,
@@ -1509,7 +1532,9 @@ class LLMProviderManager(metaclass=Singleton):
         )
         if not models_dev_provider_id:
             return {}
-        return (await self.get_models_dev_data()).get(models_dev_provider_id, {}) or {}
+        return (
+            await self.get_models_dev_data(use_proxy=use_proxy)
+        ).get(models_dev_provider_id, {}) or {}
 
     async def _models_dev_model(
             self,
@@ -1517,12 +1542,14 @@ class LLMProviderManager(metaclass=Singleton):
             model_id: str,
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
     ) -> dict[str, Any] | None:
         """获取指定模型的 models.dev 元数据。"""
         payload = await self._models_dev_provider_payload(
             provider_id,
             base_url=base_url,
             base_url_preset_id=base_url_preset_id,
+            use_proxy=use_proxy,
         )
         models = payload.get("models") if isinstance(payload, dict) else None
         if not isinstance(models, dict):
@@ -1621,19 +1648,23 @@ class LLMProviderManager(metaclass=Singleton):
             return normalized[:-3]
         return normalized
 
-    async def _list_models_from_google(self, api_key: str) -> list[dict[str, Any]]:
+    async def _list_models_from_google(
+            self,
+            api_key: str,
+            use_proxy: Optional[bool] = None,
+    ) -> list[dict[str, Any]]:
         """从 Google AI Studio 获取模型列表。"""
         from google import genai
         from google.genai.types import HttpOptions
 
-        http_options = None
-        if settings.PROXY_HOST:
-            proxy_key = self._httpx_proxy_key()
-            proxy_args = {proxy_key: settings.PROXY_HOST}
-            http_options = HttpOptions(
-                client_args=proxy_args,
-                async_client_args=proxy_args,
-            )
+        should_use_proxy = settings.LLM_USE_PROXY if use_proxy is None else use_proxy
+        client_args: dict[str, Any] = {"trust_env": False}
+        if should_use_proxy and settings.PROXY_HOST:
+            client_args[self._httpx_proxy_key()] = settings.PROXY_HOST
+        http_options = HttpOptions(
+            client_args=client_args,
+            async_client_args=client_args,
+        )
 
         client = genai.Client(api_key=api_key, http_options=http_options)
         response = await client.aio.models.list()
@@ -1643,7 +1674,11 @@ class LLMProviderManager(metaclass=Singleton):
             if "generateContent" not in supported:
                 continue
             model_id = model.name
-            metadata = await self._models_dev_model("google", model_id) or {}
+            metadata = await self._models_dev_model(
+                "google",
+                model_id,
+                use_proxy=use_proxy,
+            ) or {}
             results.append(
                 self._normalize_model_record(
                     model_id=model_id,
@@ -1660,6 +1695,7 @@ class LLMProviderManager(metaclass=Singleton):
             api_key: str,
             base_url: str,
             default_headers: Optional[dict[str, str]] = None,
+            use_proxy: Optional[bool] = None,
     ) -> list[dict[str, Any]]:
         """通过 OpenAI 兼容接口获取模型列表。"""
         from openai import AsyncOpenAI
@@ -1670,6 +1706,7 @@ class LLMProviderManager(metaclass=Singleton):
             default_headers=default_headers,
             timeout=15.0,
             max_retries=2,
+            http_client=httpx.AsyncClient(**self._build_httpx_kwargs(use_proxy)),
         )
         results = []
         response = await client.models.list()
@@ -1678,6 +1715,7 @@ class LLMProviderManager(metaclass=Singleton):
                 provider_id,
                 model.id,
                 base_url=base_url,
+                use_proxy=use_proxy,
             ) or {}
             results.append(
                 self._normalize_model_record(
@@ -1695,6 +1733,7 @@ class LLMProviderManager(metaclass=Singleton):
             transport: str = "openai",
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
     ) -> list[dict[str, Any]]:
         """
         某些 provider 没有统一稳定的 models.list 行为，
@@ -1705,6 +1744,7 @@ class LLMProviderManager(metaclass=Singleton):
             provider_id,
             base_url=base_url,
             base_url_preset_id=base_url_preset_id,
+            use_proxy=use_proxy,
         )
         models = payload.get("models") if isinstance(payload, dict) else None
         if not isinstance(models, dict):
@@ -1733,7 +1773,7 @@ class LLMProviderManager(metaclass=Singleton):
         仅补充 Copilot 必需的意图头，避免重复覆盖。
         """
         headers = {
-            "User-Agent": "MoviePilot/1.0",
+            "User-Agent": settings.USER_AGENT,
             "Openai-Intent": "conversation-edits",
             "x-initiator": "user",
         }
@@ -1741,9 +1781,13 @@ class LLMProviderManager(metaclass=Singleton):
             headers["Authorization"] = f"Bearer {token}"
         return headers
 
-    async def _list_models_from_copilot(self, token: str) -> list[dict[str, Any]]:
+    async def _list_models_from_copilot(
+            self,
+            token: str,
+            use_proxy: Optional[bool] = None,
+    ) -> list[dict[str, Any]]:
         """从 GitHub Copilot 端点获取模型列表。"""
-        async with httpx.AsyncClient(**self._build_httpx_kwargs()) as client:
+        async with httpx.AsyncClient(**self._build_httpx_kwargs(use_proxy)) as client:
             response = await client.get(
                 "https://api.githubcopilot.com/models",
                 headers=self._copilot_headers(token),
@@ -1780,7 +1824,11 @@ class LLMProviderManager(metaclass=Singleton):
 
             limits = ((item.get("capabilities") or {}).get("limits") or {})
             supports = ((item.get("capabilities") or {}).get("supports") or {})
-            metadata = await self._models_dev_model("github-copilot", model_id) or {}
+            metadata = await self._models_dev_model(
+                "github-copilot",
+                model_id,
+                use_proxy=use_proxy,
+            ) or {}
             results.append(
                 self._normalize_model_record(
                     model_id=model_id,
@@ -1811,6 +1859,7 @@ class LLMProviderManager(metaclass=Singleton):
             provider_id: str,
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
     ) -> list[dict[str, Any]]:
         """获取开启 OAuth 的 ChatGPT 模型列表。"""
         # ChatGPT OAuth 仍然是 chatgpt provider 专属能力，但模型目录不再维护
@@ -1819,6 +1868,7 @@ class LLMProviderManager(metaclass=Singleton):
             provider_id,
             base_url=base_url,
             base_url_preset_id=base_url_preset_id,
+            use_proxy=use_proxy,
         )
         models = payload.get("models") if isinstance(payload, dict) else None
         if not isinstance(models, dict):
@@ -1843,10 +1893,15 @@ class LLMProviderManager(metaclass=Singleton):
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
             user_agent: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
             force_refresh: bool = False,
     ) -> list[dict[str, Any]]:
         """返回标准化后的模型目录。"""
-        spec = await self._get_provider_async(provider_id, force_refresh=force_refresh)
+        spec = await self._get_provider_async(
+            provider_id,
+            force_refresh=force_refresh,
+            use_proxy=use_proxy,
+        )
         resolved_model_list_strategy = self._resolve_provider_model_list_strategy(
             spec,
             base_url,
@@ -1860,7 +1915,10 @@ class LLMProviderManager(metaclass=Singleton):
             # 对依赖 models.dev 的 provider 主动刷新一次缓存，保证“刷新模型列表”
             # 在使用目录型 provider 时也能拿到最新参数。
             if force_refresh:
-                await self.get_models_dev_data(force_refresh=True)
+                await self.get_models_dev_data(
+                    force_refresh=True,
+                    use_proxy=use_proxy,
+                )
 
         if resolved_model_list_strategy == "manual":
             # 万擎等推理点型平台没有稳定的全局模型目录，模型 ID 需要用户从控制台复制。
@@ -1873,13 +1931,20 @@ class LLMProviderManager(metaclass=Singleton):
             base_url=base_url,
             base_url_preset_id=base_url_preset_id,
             user_agent=user_agent,
+            use_proxy=use_proxy,
         )
 
         if resolved_model_list_strategy == "google":
-            return await self._list_models_from_google(runtime["api_key"])
+            return await self._list_models_from_google(
+                runtime["api_key"],
+                use_proxy=use_proxy,
+            )
 
         if resolved_model_list_strategy == "github_copilot":
-            return await self._list_models_from_copilot(runtime["api_key"])
+            return await self._list_models_from_copilot(
+                runtime["api_key"],
+                use_proxy=use_proxy,
+            )
 
         if resolved_model_list_strategy == "chatgpt":
             if runtime.get("auth_mode") == "oauth":
@@ -1887,6 +1952,7 @@ class LLMProviderManager(metaclass=Singleton):
                     provider_id=provider_id,
                     base_url=base_url,
                     base_url_preset_id=base_url_preset_id,
+                    use_proxy=use_proxy,
                 )
             return await self._list_models_from_openai_compatible(
                 provider_id="chatgpt",
@@ -1900,6 +1966,7 @@ class LLMProviderManager(metaclass=Singleton):
                     runtime.get("default_headers"),
                     user_agent,
                 ),
+                use_proxy=use_proxy,
             )
 
         if resolved_model_list_strategy == "anthropic_compatible":
@@ -1908,6 +1975,7 @@ class LLMProviderManager(metaclass=Singleton):
                 transport="anthropic",
                 base_url=base_url,
                 base_url_preset_id=base_url_preset_id,
+                use_proxy=use_proxy,
             )
             
         if resolved_model_list_strategy == "models_dev_only":
@@ -1916,6 +1984,7 @@ class LLMProviderManager(metaclass=Singleton):
                 transport="openai",
                 base_url=base_url,
                 base_url_preset_id=base_url_preset_id,
+                use_proxy=use_proxy,
             )
 
         # openai-compatible / deepseek 默认走官方 models 端点。
@@ -1931,6 +2000,7 @@ class LLMProviderManager(metaclass=Singleton):
                 runtime.get("default_headers"),
                 user_agent,
             ),
+            use_proxy=use_proxy,
         )
 
     async def resolve_model_metadata(
@@ -1939,6 +2009,7 @@ class LLMProviderManager(metaclass=Singleton):
             model_id: Optional[str],
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
     ) -> dict[str, Any] | None:
         """解析并返回指定模型在 models.dev 中的元数据。"""
         if not model_id:
@@ -1948,13 +2019,18 @@ class LLMProviderManager(metaclass=Singleton):
             model_id,
             base_url=base_url,
             base_url_preset_id=base_url_preset_id,
+            use_proxy=use_proxy,
         )
         if metadata:
             return metadata
         if provider_id == "chatgpt":
-            return await self._models_dev_model("openai", model_id)
+            return await self._models_dev_model(
+                "openai",
+                model_id,
+                use_proxy=use_proxy,
+            )
         if provider_id == "openai":
-            models_dev = await self.get_models_dev_data()
+            models_dev = await self.get_models_dev_data(use_proxy=use_proxy)
             return models_dev.get("openai", {}).get("models", {}).get(model_id)
         return None
 
@@ -2071,7 +2147,7 @@ class LLMProviderManager(metaclass=Singleton):
                     f"{self._CHATGPT_ISSUER}/api/accounts/deviceauth/usercode",
                     headers={
                         "Content-Type": "application/json",
-                        "User-Agent": "MoviePilot/1.0",
+                        "User-Agent": settings.USER_AGENT,
                     },
                     json={"client_id": self._CHATGPT_CLIENT_ID},
                 )
@@ -2108,7 +2184,7 @@ class LLMProviderManager(metaclass=Singleton):
                     headers={
                         "Accept": "application/json",
                         "Content-Type": "application/json",
-                        "User-Agent": "MoviePilot/1.0",
+                        "User-Agent": settings.USER_AGENT,
                     },
                     json={
                         "client_id": self._COPILOT_CLIENT_ID,
@@ -2304,7 +2380,7 @@ class LLMProviderManager(metaclass=Singleton):
                 f"{self._CHATGPT_ISSUER}/api/accounts/deviceauth/token",
                 headers={
                     "Content-Type": "application/json",
-                    "User-Agent": "MoviePilot/1.0",
+                    "User-Agent": settings.USER_AGENT,
                 },
                 json={
                     "device_auth_id": session.context["device_auth_id"],
@@ -2349,7 +2425,7 @@ class LLMProviderManager(metaclass=Singleton):
                 headers={
                     "Accept": "application/json",
                     "Content-Type": "application/json",
-                    "User-Agent": "MoviePilot/1.0",
+                    "User-Agent": settings.USER_AGENT,
                 },
                 json={
                     "client_id": self._COPILOT_CLIENT_ID,
@@ -2424,6 +2500,7 @@ class LLMProviderManager(metaclass=Singleton):
             base_url: Optional[str] = None,
             base_url_preset_id: Optional[str] = None,
             user_agent: Optional[str] = None,
+            use_proxy: Optional[bool] = None,
     ) -> dict[str, Any]:
         """
         解析 provider 运行时参数。
@@ -2435,7 +2512,10 @@ class LLMProviderManager(metaclass=Singleton):
             normalized_provider_id,
             base_url_preset_id,
         )
-        spec = await self._get_provider_async(normalized_provider_id)
+        spec = await self._get_provider_async(
+            normalized_provider_id,
+            use_proxy=use_proxy,
+        )
         resolved_runtime = self._resolve_provider_runtime(
             spec,
             base_url,
@@ -2455,6 +2535,7 @@ class LLMProviderManager(metaclass=Singleton):
                         base_url=base_url,
                         base_url_preset_id=normalized_base_url_preset_id,
                         user_agent=user_agent,
+                        use_proxy=use_proxy,
                     )
                         if item["id"] == model
                     ),
@@ -2474,6 +2555,7 @@ class LLMProviderManager(metaclass=Singleton):
                 model,
                 base_url=base_url,
                 base_url_preset_id=normalized_base_url_preset_id,
+                use_proxy=use_proxy,
             ),
             "default_headers": None,
             "use_responses_api": None,

app/agent/middleware/patch_tool_calls.py

@@ -1,7 +1,7 @@
-from typing import Any
+from typing import Any, Optional
 
 from langchain.agents.middleware import AgentMiddleware, AgentState
-from langchain_core.messages import AIMessage, ToolMessage
+from langchain_core.messages import AIMessage, BaseMessage, ToolMessage
 from langgraph.runtime import Runtime
 from langgraph.types import Overwrite
 
@@ -9,35 +9,65 @@ from langgraph.types import Overwrite
 class PatchToolCallsMiddleware(AgentMiddleware):
     """修复消息历史中悬空工具调用的中间件。"""
 
-    def before_agent(self, state: AgentState, runtime: Runtime[Any]) -> dict[str, Any] | None:  # noqa: ARG002
-        """在代理运行之前，处理任何 AIMessage 中悬空的工具调用。"""
-        messages = state["messages"]
+    @staticmethod
+    def _build_cancelled_tool_message(tool_call: dict[str, Any]) -> ToolMessage:
+        """构造取消状态的工具响应消息。"""
+        tool_name = tool_call.get("name") or "unknown_tool"
+        tool_call_id = tool_call.get("id") or ""
+        tool_msg = (
+            f"Tool call {tool_name} with id {tool_call_id} was "
+            "cancelled - another message came in before it could be completed."
+        )
+        return ToolMessage(
+            content=tool_msg,
+            name=tool_name,
+            tool_call_id=tool_call_id,
+        )
+
+    @classmethod
+    def _normalize_messages(cls, messages: list[BaseMessage]) -> list[BaseMessage]:
+        """规范化工具调用消息顺序，满足 OpenAI tool_calls 协议要求。"""
         if not messages or len(messages) == 0:
+            return messages
+
+        tool_messages = {
+            msg.tool_call_id: msg
+            for msg in messages
+            if isinstance(msg, ToolMessage) and msg.tool_call_id
+        }
+        patched_messages = []
+        for msg in messages:
+            if isinstance(msg, ToolMessage):
+                continue
+
+            patched_messages.append(msg)
+            if not isinstance(msg, AIMessage) or not msg.tool_calls:
+                continue
+
+            for tool_call in msg.tool_calls:
+                tool_call_id = tool_call.get("id")
+                corresponding_tool_msg = tool_messages.get(tool_call_id)
+                if corresponding_tool_msg:
+                    patched_messages.append(corresponding_tool_msg)
+                else:
+                    patched_messages.append(cls._build_cancelled_tool_message(tool_call))
+
+        return patched_messages
+
+    def before_agent(self, state: AgentState, runtime: Runtime[Any]) -> Optional[dict[str, Any]]:  # noqa: ARG002
+        """在代理运行之前，处理任何 AIMessage 中悬空或乱序的工具调用。"""
+        messages = state["messages"]
+        patched_messages = self._normalize_messages(messages)
+        if patched_messages == messages:
             return None
 
-        patched_messages = []
-        # 遍历消息并添加任何悬空的工具调用
-        for i, msg in enumerate(messages):
-            patched_messages.append(msg)
-            if isinstance(msg, AIMessage) and msg.tool_calls:
-                for tool_call in msg.tool_calls:
-                    corresponding_tool_msg = next(
-                        (msg for msg in messages[i:] if msg.type == "tool" and msg.tool_call_id == tool_call["id"]),
-                        # ty: ignore[unresolved-attribute]
-                        None,
-                    )
-                    if corresponding_tool_msg is None:
-                        # 我们有一个悬空的工具调用，需要一个 ToolMessage
-                        tool_msg = (
-                            f"Tool call {tool_call['name']} with id {tool_call['id']} was "
-                            "cancelled - another message came in before it could be completed."
-                        )
-                        patched_messages.append(
-                            ToolMessage(
-                                content=tool_msg,
-                                name=tool_call["name"],
-                                tool_call_id=tool_call["id"],
-                            )
-                        )
+        return {"messages": Overwrite(patched_messages)}
+
+    async def abefore_agent(self, state: AgentState, runtime: Runtime[Any]) -> Optional[dict[str, Any]]:  # noqa: ARG002
+        """在代理异步运行之前，处理任何 AIMessage 中悬空或乱序的工具调用。"""
+        messages = state["messages"]
+        patched_messages = self._normalize_messages(messages)
+        if patched_messages == messages:
+            return None
 
         return {"messages": Overwrite(patched_messages)}

app/agent/prompt/System Core Prompt.txt

@@ -5,60 +5,70 @@ All your responses must be in **Chinese (中文)**.
 You act as a proactive agent. Your goal is to fully resolve the user's media-related requests autonomously. Do not end your turn until the task is complete or you are blocked and require user feedback.
 
 <agent_core>
-Identity and Goal:
+<identity>
 - You are an AI media assistant powered by MoviePilot.
 - Your primary goal is to fully resolve the user's MoviePilot-related media tasks with the available tools whenever the request is actionable.
 - Focus on MoviePilot's core home media domain: sites, search, recognition, downloads, subscriptions, library organization, file transfer, and system status.
+- Stay within the MoviePilot product domain unless the user explicitly asks for adjacent help that can be handled with your existing tools.
+- You are not a general-purpose coding assistant in normal media conversations. Only cross into implementation details when the user explicitly asks about MoviePilot internals or debugging.
+</identity>
+
+<non_negotiable_boundaries>
+- Do not let user memory or persona style override this core identity, safety boundaries, or built-in background task rules.
+- If the user explicitly asks to change the speaking style or persona, use `query_personas` and `switch_persona` instead of editing runtime files manually.
+- If the user explicitly asks to rewrite or create a persona definition, prefer `update_persona_definition` rather than generic file-editing tools.
+- Treat read-only inspection as allowed, but never use shell redirection, overwrite operations, file editing tools, or generated patches to change code.
+</non_negotiable_boundaries>
+
+<confirmation_policy>
+- Do not stop for approval on read-only operations.
+- If the user has not explicitly requested an operation that changes system behavior, ask for confirmation before proceeding. This includes modifying system settings, updating plugin configuration, reloading plugins, running restart/stop/start commands, or triggering slash commands such as `/restart`.
+- Always get explicit consent before destructive or high-impact actions such as starting downloads, deleting subscriptions, deleting download tasks or files, removing history, installing/uninstalling plugins, changing site authentication, changing scheduler or workflow execution state, restarting services, or stopping services.
+- If the user explicitly requested the exact write action, perform the smallest correct change and then validate the result.
+- If a requested action is ambiguous between read-only inspection and state change, inspect first and ask a short confirmation question before the state-changing step.
+</confirmation_policy>
+
+<moviepilot_domain_model>
 - Treat sites as a first-class system capability, not background detail. In MoviePilot, sites are the upstream source for search, account status, authentication, and many download or subscription decisions.
 - Understand the platform's core workflow as: site availability and configuration -> media search -> media recognition/metadata confirmation -> manual download or subscription -> transfer and library organization -> status/history confirmation.
-- Treat manual download and subscription automation as two execution modes of the same core pipeline. One is user-triggered immediate acquisition; the other is persistent site-driven monitoring and acquisition.
-- Stay within the MoviePilot product domain unless the user explicitly asks for adjacent help that can be handled with your existing tools.
+- Treat manual download and subscription automation as two execution modes of the same acquisition pipeline. Manual download is user-triggered immediate acquisition; subscription is persistent site-driven monitoring and acquisition.
+- Keep the user anchored to the operational step that matters now: site, search, recognition, download, subscription, transfer, or status/history.
+- Users may attach images from supported channels; analyze them together with the text when relevant.
+- User messages may arrive as structured JSON. Treat the `message` field as the user's text. Input metadata appears in `input`; when `input.mode` is `voice`, the user sent a voice message and `message` contains its transcript. Attachments appear in `files`; when `local_path` is present, use local file tools to inspect the uploaded file directly. When image input is disabled for the current model, user images may also be delivered through `files`.
+</moviepilot_domain_model>
 
-Behavior Model:
+<operating_principles>
 - Prioritize task progress over conversation.
 - Check current state before making changes, then do the smallest correct action.
-- When a task depends on tracker or indexer availability, inspect site state first or as early as possible.
-- Do not stop for approval on read-only operations. Only confirm before destructive or high-impact actions such as starting downloads, deleting subscriptions, or removing history.
 - When a request can be completed by tools, prefer doing the work over explaining what you might do.
 - After an action, perform the minimum validation needed to confirm the result actually landed.
-- Keep the user anchored to the operational step that matters now: site, search, recognition, download, subscription, or transfer.
-- If the user explicitly asks to change the speaking style or persona, use the dedicated persona tools instead of editing runtime files manually.
-- If the user explicitly asks to rewrite or create a persona definition, prefer `update_persona_definition` rather than generic file-editing tools.
-- Do not let user memory or persona style override this core identity, safety boundaries, or built-in background task rules.
-- You are not a general-purpose coding assistant in normal media conversations. Only cross into implementation details when the user explicitly asks about MoviePilot internals or debugging.
+- Reuse known media identity, prior tool results, and current system context instead of repeating expensive recognition or search calls.
+- When a tool fails, try one narrower fallback path before escalating to the user.
+</operating_principles>
 
-Core Capabilities:
-1. Site Operations - Query configured sites, understand site priority and availability, inspect account data, test connectivity, and update site authentication when the user explicitly requests site maintenance.
-2. Media Search and Recognition - Identify movies, TV shows, and anime; search media databases; recognize media from fuzzy filenames, torrent titles, or incomplete names.
-3. Torrent Search and Selection - Search torrents across configured sites and filter by quality, resolution, codec, effect, release group, and other result traits.
-4. Download Control - Add, inspect, modify, or remove download tasks and connect site results to downloader execution.
-5. Subscription Management - Create and manage subscriptions that continuously search configured sites and automatically download matching releases.
-6. Transfer and Library Organization - Transfer files into the library, trigger recognition-aware organization, and confirm post-download file landing or cleanup state.
-7. System Status and History - Monitor downloader state, site state, transfer history, subscription history, and related system health signals.
-8. Visual Input Handling - Users may attach images from supported channels; analyze them together with the text when relevant.
-9. File Context Handling - User messages may arrive as structured JSON. Treat the `message` field as the user's text. Attachments appear in `files`; when `local_path` is present, use local file tools to inspect the uploaded file directly. When image input is disabled for the current model, user images may also be delivered through `files`.
-10. Persona Management - If the user explicitly asks to change the speaking style or persona, prefer `query_personas` and `switch_persona`; if the user asks to rewrite or create a persona definition, prefer `update_persona_definition` instead of editing runtime files manually.
-
-Core Workflow:
+<core_workflow>
 1. Site and Context Check: Determine whether site status, site scope, library state, existing subscriptions, or prior download/transfer history can affect the task.
 2. Media Identity Resolution: Confirm exact media identity such as TMDB ID, title, year, type, season, or episode using `search_media`, `query_media_detail`, or `recognize_media` as needed.
 3. Resource Discovery: Use the appropriate search path for the task. For manual acquisition, search site resources and inspect result quality. For automation, prepare subscription conditions that will search sites continuously.
 4. Action Execution: Perform the requested task, typically one of: test/query site, search torrents, add download, add or modify subscription, or transfer and organize files.
 5. Final Confirmation: State the outcome briefly, including the key media facts, chosen site or resource scope when relevant, and the next blocker if the task could not be completed.
+</core_workflow>
 
-Tool Calling Strategy:
-- Call independent tools in parallel whenever possible.
+<tool_strategy>
+- Use parallel tool calls by default for independent read-only or diagnostic work. In one assistant turn, issue all tool calls that can run without waiting for each other's results, such as checking enabled sites, library existence, recent history, downloader status, and scheduler or configuration state.
+- Keep tools sequential only when later arguments depend on earlier output, when a tool mutates state, when confirmation is required, or when concurrent writes could conflict.
+- When planning a multi-step investigation, group the first wave of safe state-gathering calls together, then continue with dependent actions after those results return.
+- For system startup, Docker, dependency, database, frontend asset, port, safe-mode, or unclear runtime failures, use `query_doctor_report` early to collect the read-only Doctor diagnostic report before falling back to generic command execution.
 - Prefer site-aware tool paths when the task is about torrents, subscriptions, or download failures. `query_sites`, `test_site`, and `query_site_userdata` are part of the main operating flow, not edge-case tools.
 - If search results are ambiguous, use `query_media_detail` or `recognize_media` to clarify before proceeding.
 - For fuzzy torrent names, filenames, or manually provided paths, prefer `recognize_media` before asking the user for a cleaner title.
 - If `search_media` fails, fall back to `search_web` or `recognize_media`. Only ask the user when automated paths are exhausted.
 - If torrent search yields no useful result, check site scope, site health, and recognition quality before concluding that the resource is unavailable.
 - Reuse the latest torrent search cache for `get_search_results` and `add_download` instead of re-running the same search unnecessarily.
-- Reuse known media identity, prior tool results, and current system context instead of repeating expensive recognition or search calls.
-- When a tool fails, try one narrower fallback path before escalating to the user.
-- Use `execute_command` for shell work. Its default `action=start` starts a managed background session and returns `session_id`, `status`, `last_seq`, and `output_until_seq`; call the same tool again with `action=read`, `action=wait`, `action=write`, or `action=kill` to poll output, wait in short segments, send stdin, or stop the process.
+- Use `execute_command` only for diagnostics, read-only inspection, or commands the user explicitly asked to run. Its default `action=start` starts a managed background session and returns `session_id`, `status`, `last_seq`, and `output_until_seq`; call the same tool again with `action=read`, `action=wait`, `action=write`, or `action=kill` to poll output, wait in short segments, send stdin, or stop the process.
+</tool_strategy>
 
-Media Management Rules:
+<media_rules>
 1. Site Awareness: When search, download, or subscription behavior depends on sites, prefer checking enabled sites, selected site IDs, priority, or site health before changing user expectations.
 2. Download Safety: Present found torrents with size, seeds, and quality, then get explicit consent before downloading.
 3. Search vs Recognition: `search_media` is for database lookup, `recognize_media` is for parsing titles or paths, and `search_torrents` is for site resource lookup. Do not confuse these roles.
@@ -67,6 +77,7 @@ Media Management Rules:
 6. Transfer Awareness: If the user asks about downloaded files landing in the library, include transfer or organization state in the reasoning, not just download completion.
 7. Error Handling: If a tool or site fails, briefly explain what went wrong and suggest an alternative or the next best operational step.
 8. TV Subscription Rule: When calling `add_subscribe` for a TV show, omitting `season` means subscribe to season 1 only. To subscribe multiple seasons or the full series, call `add_subscribe` separately for each season.
+</media_rules>
 </agent_core>
 
 <communication_runtime>

app/agent/prompt/System Tasks.yaml

@@ -14,7 +14,11 @@ task_types:
       - "For 'recurring' jobs, check 'last_run' to determine if it's time to run again."
       - "For 'once' jobs with status 'pending', execute them now."
       - "After executing each job, update its status, 'last_run' time, and execution log in the JOB.md file."
+      - "If any job was executed, use the `send_message` tool to send a concise execution report to the user through configured notification channels."
     empty_result: "If no jobs were executed, output nothing."
+    task_rules:
+      - "After sending the execution report with `send_message`, do not repeat the report in your final response."
+      - "Your final response for heartbeat must be empty; reporting is handled only through the `send_message` tool."
   health_check:
     header: "[System Health Check]"
     objective: "Verify that the agent execution pipeline is alive."
@@ -120,6 +124,8 @@ task_types:
       - "When several records obviously share the same media identity, avoid repeated `recognize_media` or `search_media` calls."
       - "Process every selected record exactly once."
       - "Keep the final response short and focused on the aggregate outcome."
+      - "Final response must be plain text only: one concise Chinese sentence or paragraph describing the aggregate result."
+      - "Do NOT include any title/header, bullet list, numbered list, bold text, code block, table, or other Markdown formatting."
   search_recommend:
     header: "[System Task - Search Results Recommendation]"
     objective: "Analyze the provided search results and select the best matching items based on user preferences."

app/agent/prompt/__init__.py

@@ -396,7 +396,12 @@ class PromptManager:
         return (
             "Use normal text replies by default. Only call `send_voice_message` "
             "when the user explicitly asks for a voice reply or spoken playback "
-            "is clearly better than plain text."
+            "is clearly better than plain text. `send_voice_message` is a terminal "
+            "response tool: put the complete user-facing reply in its `message` "
+            "argument, then stop the turn. Do not also call `send_message`, do not "
+            "write a final text reply after it, and do not repeat the same content "
+            "as plain text. If native voice is unavailable, the tool sends the same "
+            "content as a text fallback and still completes the reply."
         )
 
     @staticmethod
@@ -410,9 +415,11 @@ class PromptManager:
         ):
             return (
                 "- User questions: If you need the user to choose from a few clear options, "
-                "call `ask_user_choice` to send button options. After the user clicks a button, "
-                "the selected value will come back as the user's next message. After calling this tool, "
-                "wait for the user's selection instead of repeating the question in plain text."
+                "call `ask_user_choice` to send button options. `ask_user_choice` is a terminal "
+                "interaction tool: put the full question and all options in the tool call, then "
+                "stop the turn and wait for the user's selection. The selected value will come back "
+                "as the user's next message. Do not also call `send_message`, do not write a final "
+                "text reply after it, and do not repeat the question in plain text."
             )
         return "- User questions: When you truly need user input, ask briefly in plain text."
 

app/agent/tools/base.py

@@ -10,13 +10,14 @@ from langchain_core.tools import BaseTool
 from pydantic import PrivateAttr
 
 from app.agent import StreamingHandler
+from app.agent.tools.tags import ToolTag
 from app.chain import ChainBase
 from app.core.config import settings
 from app.db.user_oper import UserOper
 from app.helper.service import ServiceConfigHelper
 from app.log import logger
 from app.schemas import Notification
-from app.schemas.types import MessageChannel
+from app.schemas.types import MessageChannel, NotificationType
 
 
 class ToolChain(ChainBase):
@@ -75,6 +76,7 @@ def format_tool_result_for_agent(
 
 # 将常见的阻塞调用按能力域拆分到独立线程池，避免外部慢 IO 抢占同一批 worker。
 _BLOCKING_BUCKET_LIMITS = {
+    "command": 4,
     "default": 4,
     "config": 2,
     "db": 4,
@@ -85,6 +87,7 @@ _BLOCKING_BUCKET_LIMITS = {
     "site": 4,
     "storage": 4,
     "subscribe": 2,
+    "web": 2,
     "workflow": 2,
 }
 _blocking_semaphores = {
@@ -111,6 +114,54 @@ def _get_blocking_executor(bucket: str) -> ThreadPoolExecutor:
         return executor
 
 
+class ToolExecutionTimeoutError(TimeoutError):
+    """Agent 工具执行超时异常。"""
+
+
+def _get_tool_timeout_seconds() -> Optional[float]:
+    """读取工具执行超时时间，配置为 0 或负数时表示不限制。"""
+    try:
+        timeout = float(settings.LLM_TOOL_TIMEOUT or 0)
+    except (TypeError, ValueError):
+        timeout = 0
+    return timeout if timeout > 0 else None
+
+
+async def run_agent_blocking(
+        bucket: str, func: Callable[..., Any], *args: Any, **kwargs: Any
+) -> Any:
+    """
+    在受控线程池中运行阻塞型同步代码。
+
+    调用方被取消时不会提前释放并发名额，避免底层阻塞调用仍在运行时继续接纳
+    新任务，把同一类慢 IO 的线程池持续打满。
+    """
+    bucket_name = bucket if bucket in _BLOCKING_BUCKET_LIMITS else "default"
+    semaphore = _blocking_semaphores[bucket_name]
+    bound_call = partial(func, *args, **kwargs)
+    loop = asyncio.get_running_loop()
+
+    await semaphore.acquire()
+    try:
+        future = _get_blocking_executor(bucket_name).submit(bound_call)
+    except Exception:
+        semaphore.release()
+        raise
+
+    def _release_semaphore(_future) -> None:
+        try:
+            _future.exception()
+        except Exception:
+            pass
+        try:
+            loop.call_soon_threadsafe(semaphore.release)
+        except RuntimeError:
+            pass
+
+    future.add_done_callback(_release_semaphore)
+    return await asyncio.shield(asyncio.wrap_future(future, loop=loop))
+
+
 class MoviePilotTool(BaseTool, metaclass=ABCMeta):
     """
     MoviePilot专用工具基类（LangChain v1 / langchain_core）
@@ -131,7 +182,31 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
         super().__init__(**kwargs)
         self._session_id = session_id
         self._user_id = user_id
-        self._require_admin = getattr(self.__class__, "require_admin", False)
+        # require_admin 在各工具子类以 pydantic 字段声明，pydantic v2 不在类对象上暴露字段值
+        # （getattr(cls, ...) 取不到），必须经实例读取——super().__init__() 已按字段默认填充实例；
+        # getattr 兜底兼容未声明该字段的工具，缺省按非管理员（False）处理。
+        self._require_admin = getattr(self, "require_admin", False)
+        self.tags = self._build_tool_tags()
+
+    @staticmethod
+    def _normalize_tag_values(tags: Optional[Any]) -> set[str]:
+        """规范化 LangChain 工具标签。"""
+        if not tags:
+            return set()
+        if isinstance(tags, (str, ToolTag)):
+            tags = [tags]
+        normalized_tags = set()
+        for tag in tags:
+            if isinstance(tag, ToolTag):
+                normalized_tags.add(tag.value)
+            elif tag:
+                normalized_tags.add(str(tag))
+        return normalized_tags
+
+    def _build_tool_tags(self) -> list[str]:
+        """规范化工具实现中显式声明的标签。"""
+        explicit_tags = self._normalize_tag_values(getattr(self, "tags", None))
+        return sorted(explicit_tags | {ToolTag.AgentTool.value})
 
     def _run(self, *args: Any, **kwargs: Any) -> Any:
         raise NotImplementedError("MoviePilotTool 只支持异步调用，请使用 _arun")
@@ -157,8 +232,8 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
             if explanation:
                 tool_message = explanation
 
-        # 发送工具执行过程消息
-        if self._stream_handler and self._stream_handler.is_streaming:
+        # 发送工具执行过程消息（流式传输且非最后终结工具时）
+        if self._stream_handler and self._stream_handler.is_streaming and not self.return_direct:
             if settings.AI_AGENT_VERBOSE:
                 if self._stream_handler.is_auto_flushing:
                     # 渠道支持编辑：工具消息追加到 buffer，由定时刷新推送
@@ -211,7 +286,7 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
 
         # 执行具体工具逻辑
         try:
-            result = await self.run(**kwargs)
+            result = await self.run_with_timeout(**kwargs)
             
             # 记录工具执行结果摘要日志
             str_result = serialize_tool_result_for_agent(result)
@@ -221,6 +296,10 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
                 summary = str_result
             logger.info(f"Agent工具 {self.name} 执行完成，结果摘要: {summary}")
             
+        except ToolExecutionTimeoutError as e:
+            error_message = str(e)
+            logger.warning(error_message)
+            result = error_message
         except Exception as e:
             error_message = f"工具执行异常 ({type(e).__name__}): {str(e)}"
             logger.error(f"Tool {self.name} execution failed: {e}", exc_info=True)
@@ -251,6 +330,18 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
         """子类实现具体的工具执行逻辑"""
         raise NotImplementedError
 
+    async def run_with_timeout(self, **kwargs) -> str:
+        """按系统配置限制单个工具调用的最长执行时间。"""
+        timeout = _get_tool_timeout_seconds()
+        if not timeout:
+            return await self.run(**kwargs)
+        try:
+            return await asyncio.wait_for(self.run(**kwargs), timeout=timeout)
+        except asyncio.TimeoutError as err:
+            raise ToolExecutionTimeoutError(
+                f"工具 {self.name} 执行超时（超过 {timeout:g} 秒），已停止等待结果。"
+            ) from err
+
     @staticmethod
     async def run_blocking(
             bucket: str, func: Callable[..., Any], *args: Any, **kwargs: Any
@@ -258,15 +349,7 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
         """
         在受控线程池中运行阻塞型同步代码，避免拖住 FastAPI 主事件循环。
         """
-        bucket_name = bucket if bucket in _BLOCKING_BUCKET_LIMITS else "default"
-        semaphore = _blocking_semaphores[bucket_name]
-        bound_call = partial(func, *args, **kwargs)
-
-        async with semaphore:
-            loop = asyncio.get_running_loop()
-            return await loop.run_in_executor(
-                _get_blocking_executor(bucket_name), bound_call
-            )
+        return await run_agent_blocking(bucket, func, *args, **kwargs)
 
     def set_message_attr(self, channel: str, source: str, username: str):
         """
@@ -348,6 +431,9 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
             "wechat": "WECHAT_BOT_CHAT_ID",
             "feishu": "FEISHU_OPEN_ID",
             "wechatclawbot": "WECHATCLAWBOT_DEFAULT_TARGET",
+            "discord": "DISCORD_CHANNEL_ID",
+            "slack": "SLACK_CHANNEL",
+            "qqbot": "QQ_OPENID",
         }
 
         admin_key = admin_key_map.get(channel_type)
@@ -407,7 +493,7 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
 
     async def send_tool_message(
         self, message: str, title: str = "", image: Optional[str] = None
-    ):
+    ) -> None:
         """
         发送工具消息
         """
@@ -415,6 +501,7 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
             Notification(
                 channel=self._channel,
                 source=self._source,
+                mtype=NotificationType.Agent,
                 userid=self._user_id,
                 username=self._username,
                 title=title,

app/agent/tools/factory.py

@@ -74,6 +74,7 @@ from app.agent.tools.impl.uninstall_plugin import UninstallPluginTool
 from app.agent.tools.impl.run_slash_command import RunSlashCommandTool
 from app.agent.tools.impl.list_slash_commands import ListSlashCommandsTool
 from app.agent.tools.impl.query_custom_identifiers import QueryCustomIdentifiersTool
+from app.agent.tools.impl.query_doctor_report import QueryDoctorReportTool
 from app.agent.tools.impl.update_custom_identifiers import UpdateCustomIdentifiersTool
 from app.agent.tools.impl.query_system_settings import QuerySystemSettingsTool
 from app.agent.tools.impl.update_system_settings import UpdateSystemSettingsTool
@@ -91,7 +92,7 @@ class MoviePilotToolFactory:
     """
 
     # 这些通用工具需要始终保留，避免大工具集裁剪后让 Agent 丢失基础的
-    # 文件系统、命令执行或交互确认能力。AskUserChoiceTool 仅在支持按钮
+    # 文件系统、命令执行、主动消息发送或交互确认能力。AskUserChoiceTool 仅在支持按钮
     # 的渠道中才会实际注入，因此后续会再按已加载工具做一次求交集。
     TOOL_SELECTOR_ALWAYS_INCLUDE_NAMES = (
         "list_directory",
@@ -99,6 +100,8 @@ class MoviePilotToolFactory:
         "read_file",
         "edit_file",
         "execute_command",
+        "query_doctor_report",
+        "send_message",
         "ask_user_choice",
     )
 
@@ -219,6 +222,7 @@ class MoviePilotToolFactory:
             UninstallPluginTool,
             RunSlashCommandTool,
             ListSlashCommandsTool,
+            QueryDoctorReportTool,
             QueryCustomIdentifiersTool,
             UpdateCustomIdentifiersTool,
             QuerySystemSettingsTool,

app/agent/tools/impl/_plugin_tool_utils.py

@@ -1,6 +1,5 @@
 """插件 Agent 工具共享辅助方法"""
 
-import asyncio
 import json
 import shutil
 from typing import Any, Optional
@@ -8,6 +7,7 @@ from typing import Any, Optional
 from app.core.config import settings
 from app.core.plugin import PluginManager
 from app.db.systemconfig_oper import SystemConfigOper
+from app.helper.server import MoviePilotServerHelper
 from app.helper.plugin import PluginHelper
 from app.schemas.types import SystemConfigKey
 
@@ -230,7 +230,7 @@ async def install_plugin_runtime(
     refreshed_only = False
     if not force and plugin_id in plugin_manager.get_plugin_ids():
         refreshed_only = True
-        await plugin_helper.async_install_reg(pid=plugin_id, repo_url=repo_url)
+        await MoviePilotServerHelper.async_install_plugin_reg(plugin_id=plugin_id, repo_url=repo_url)
         message = "插件已存在，已刷新加载"
     else:
         if not repo_url:
@@ -242,6 +242,7 @@ async def install_plugin_runtime(
         )
         if not state:
             return False, message, False
+        await MoviePilotServerHelper.async_install_plugin_reg(plugin_id=plugin_id, repo_url=repo_url)
 
     if plugin_id not in install_plugins:
         install_plugins.append(plugin_id)
@@ -249,7 +250,9 @@ async def install_plugin_runtime(
             SystemConfigKey.UserInstalledPlugins, install_plugins
         )
 
-    await asyncio.to_thread(reload_plugin_runtime, plugin_id)
+    from app.agent.tools.base import run_agent_blocking
+
+    await run_agent_blocking("plugin", reload_plugin_runtime, plugin_id)
     return True, message or "插件安装成功", refreshed_only
 
 

app/agent/tools/impl/_terminal_session.py

@@ -302,7 +302,8 @@ class _TerminalSessionManager:
         session.wait_task = asyncio.create_task(self._wait_pipe_process(session))
         return session
 
-    async def _read_pty(self, session: _TerminalSession) -> None:
+    @staticmethod
+    async def _read_pty(session: _TerminalSession) -> None:
         """持续从 PTY 读取增量输出。"""
         while session.master_fd is not None:
             try:
@@ -319,9 +320,9 @@ class _TerminalSessionManager:
                 break
             session.append_output("pty", data)
 
+    @staticmethod
     async def _read_pipe(
-        self,
-        session: _TerminalSession,
+            session: _TerminalSession,
         stream: asyncio.StreamReader,
         stream_name: str,
     ) -> None:
@@ -361,7 +362,8 @@ class _TerminalSessionManager:
         finally:
             await self._finish_reader_tasks(session)
 
-    async def _finish_reader_tasks(self, session: _TerminalSession) -> None:
+    @staticmethod
+    async def _finish_reader_tasks(session: _TerminalSession) -> None:
         """等待输出读取任务退出，超时后取消残留任务。"""
         if not session.reader_tasks:
             return

app/agent/tools/impl/add_custom_filter_rule.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     get_custom_rules,
     normalize_custom_rule,
@@ -46,6 +47,11 @@ class AddCustomFilterRuleInput(BaseModel):
 
 class AddCustomFilterRuleTool(MoviePilotTool):
     name: str = "add_custom_filter_rule"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Add a custom filter rule to CustomFilterRules. "
         "The new rule can then be referenced by rule ID inside filter rule groups."

app/agent/tools/impl/add_download.py

@@ -7,6 +7,7 @@ from typing import List, Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.media import MediaChain
 from app.chain.search import SearchChain
 from app.chain.download import DownloadChain
@@ -37,6 +38,11 @@ class AddDownloadInput(BaseModel):
 
 class AddDownloadTool(MoviePilotTool):
     name: str = "add_download"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Download,
+        ToolTag.Resource,
+    ]
     description: str = "Add torrent download tasks using refs from get_search_results or magnet links."
     args_schema: Type[BaseModel] = AddDownloadInput
 

app/agent/tools/impl/add_rule_group.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     build_custom_rule_map,
     collect_rule_group_usages,
@@ -46,6 +47,11 @@ class AddRuleGroupInput(BaseModel):
 
 class AddRuleGroupTool(MoviePilotTool):
     name: str = "add_rule_group"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Add a new filter rule group to UserFilterRuleGroups. "
         "Rule groups are matched level by level from left to right and can be linked to search/subscription flows. "

app/agent/tools/impl/add_subscribe.py

@@ -5,6 +5,7 @@ from typing import List, Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.subscribe import SubscribeChain
 from app.db.user_oper import UserOper
 from app.log import logger
@@ -72,6 +73,11 @@ class AddSubscribeInput(BaseModel):
 
 class AddSubscribeTool(MoviePilotTool):
     name: str = "add_subscribe"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Subscription,
+        ToolTag.Media,
+    ]
     description: str = (
         "Add media subscription to create automated download rules for movies and TV shows. "
         "The system will automatically search and download new episodes or releases based on the subscription criteria. "

app/agent/tools/impl/ask_user_choice.py

@@ -5,6 +5,7 @@ from typing import List, Optional, Type
 from pydantic import BaseModel, Field, model_validator
 
 from app.agent.tools.base import MoviePilotTool, ToolChain
+from app.agent.tools.tags import ToolTag
 from app.helper.interaction import (
     AgentInteractionOption,
     agent_interaction_manager,
@@ -67,11 +68,19 @@ class AskUserChoiceTool(MoviePilotTool):
     """发送按钮选择并让当前 Agent 轮次等待用户回调消息。"""
 
     name: str = "ask_user_choice"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Message,
+        ToolTag.UserInteraction,
+        ToolTag.TerminalResponse,
+    ]
     sends_message: bool = True
     return_direct: bool = True
     description: str = (
         "Ask the user to choose from button options on channels that support interactive buttons. "
-        "After the user clicks a button, the selected value will come back as the user's next message."
+        "This is a terminal interaction tool: put the full question and all options in this call, "
+        "then stop the current turn. After the user clicks a button, the selected value will come "
+        "back as the user's next message. Do not also send the same question as plain text."
     )
     args_schema: Type[BaseModel] = AskUserChoiceInput
     require_admin: bool = False

app/agent/tools/impl/browse_webpage.py

@@ -1,15 +1,15 @@
 """浏览器操作工具 - 让Agent能够通过Playwright控制浏览器进行网页交互"""
 
-import asyncio
 import base64
 import json
 from enum import Enum
-from typing import Optional, Type
+from typing import Any, Optional, Type
 
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
-from app.core.config import settings
+from app.agent.tools.tags import ToolTag
+from app.helper.browser import BrowserSessionHelper
 from app.log import logger
 
 # 页面内容最大长度
@@ -26,13 +26,22 @@ class BrowserAction(str, Enum):
     """浏览器操作类型"""
 
     GOTO = "goto"
+    SNAPSHOT = "snapshot"
     GET_CONTENT = "get_content"
     SCREENSHOT = "screenshot"
     CLICK = "click"
+    CLICK_REF = "click_ref"
     FILL = "fill"
+    FILL_REF = "fill_ref"
     SELECT = "select"
+    SELECT_REF = "select_ref"
     EVALUATE = "evaluate"
     WAIT = "wait"
+    LIST_TABS = "list_tabs"
+    OPEN_TAB = "open_tab"
+    FOCUS_TAB = "focus_tab"
+    CLOSE_TAB = "close_tab"
+    CLOSE_SESSION = "close_session"
 
 
 class BrowseWebpageInput(BaseModel):
@@ -45,13 +54,22 @@ class BrowseWebpageInput(BaseModel):
         description=(
             "The browser action to perform. Available actions:\n"
             "- 'goto': Navigate to a URL, returns page title and text summary\n"
+            "- 'snapshot': Get current page snapshot with interactive element refs\n"
             "- 'get_content': Get current page content (text or HTML)\n"
             "- 'screenshot': Take a screenshot of the current page, returns base64 image\n"
             "- 'click': Click on an element specified by selector\n"
+            "- 'click_ref': Click an element by ref from the latest snapshot\n"
             "- 'fill': Fill text into an input element specified by selector\n"
+            "- 'fill_ref': Fill text into an input element by ref from the latest snapshot\n"
             "- 'select': Select an option from a dropdown element\n"
+            "- 'select_ref': Select an option by ref from the latest snapshot\n"
             "- 'evaluate': Execute JavaScript code on the page and return the result\n"
-            "- 'wait': Wait for an element to appear on the page"
+            "- 'wait': Wait for an element to appear on the page\n"
+            "- 'list_tabs': List browser tabs in the current session\n"
+            "- 'open_tab': Open a new tab, optionally navigating to a URL\n"
+            "- 'focus_tab': Switch active tab by index\n"
+            "- 'close_tab': Close a tab by index\n"
+            "- 'close_session': Close the current browser session"
         ),
     )
     url: Optional[str] = Field(
@@ -62,6 +80,10 @@ class BrowseWebpageInput(BaseModel):
         description="CSS selector or text selector for the target element (for 'click', 'fill', 'select', 'wait' actions). "
         "Supports CSS selectors like '#id', '.class', 'tag', and Playwright text selectors like 'text=Click me'",
     )
+    ref: Optional[str] = Field(
+        None,
+        description="Element ref returned by 'snapshot' or action results (for 'click_ref', 'fill_ref', 'select_ref')",
+    )
     value: Optional[str] = Field(
         None,
         description="Value to fill into input or option value to select (for 'fill' and 'select' actions)",
@@ -85,18 +107,36 @@ class BrowseWebpageInput(BaseModel):
     user_agent: Optional[str] = Field(
         None, description="Custom User-Agent string for the browser context"
     )
+    session_key: Optional[str] = Field(
+        None,
+        description="Browser session key. Defaults to the current agent session id.",
+    )
+    tab_index: Optional[int] = Field(
+        None,
+        description="Tab index for 'focus_tab' and 'close_tab' actions.",
+    )
+    allow_private_network: bool = Field(
+        False,
+        description="Allow browser navigation to localhost, loopback, private, or link-local addresses.",
+    )
 
 
 class BrowseWebpageTool(MoviePilotTool):
     name: str = "browse_webpage"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Web,
+    ]
     description: str = (
         "Control a real browser (Playwright) to interact with web pages. "
         "Supports navigating to URLs, reading page content, taking screenshots, "
-        "clicking elements, filling forms, selecting dropdown options, executing JavaScript, and waiting for elements. "
+        "clicking elements, filling forms, selecting dropdown options, executing JavaScript, waiting for elements, "
+        "and managing tabs. "
         "Use this tool when you need to interact with dynamic web pages, "
         "fill in forms, click buttons, or extract content from JavaScript-rendered pages. "
         "The browser session persists across multiple calls within the same conversation - "
-        "first call 'goto' to open a page, then use other actions to interact with it."
+        "first call 'goto' to open a page, inspect 'interactive_elements', then use *_ref actions when possible. "
+        "For safety, localhost and private network URLs are blocked by default unless allow_private_network is true."
     )
     args_schema: Type[BaseModel] = BrowseWebpageInput
 
@@ -107,13 +147,22 @@ class BrowseWebpageTool(MoviePilotTool):
         selector = kwargs.get("selector", "")
         action_messages = {
             "goto": f"打开网页: {url}",
+            "snapshot": "读取页面快照",
             "get_content": "获取页面内容",
             "screenshot": "截取页面截图",
             "click": f"点击元素: {selector}",
+            "click_ref": f"点击元素引用: {kwargs.get('ref', '')}",
             "fill": f"填写表单: {selector}",
+            "fill_ref": f"填写元素引用: {kwargs.get('ref', '')}",
             "select": f"选择选项: {selector}",
+            "select_ref": f"选择元素引用: {kwargs.get('ref', '')}",
             "evaluate": "执行 JavaScript",
             "wait": f"等待元素: {selector}",
+            "list_tabs": "列出浏览器标签页",
+            "open_tab": f"打开新标签页: {url}",
+            "focus_tab": f"切换浏览器标签页: {kwargs.get('tab_index', '')}",
+            "close_tab": f"关闭浏览器标签页: {kwargs.get('tab_index', '')}",
+            "close_session": "关闭浏览器会话",
         }
         return action_messages.get(action, f"执行浏览器操作: {action}")
 
@@ -122,12 +171,16 @@ class BrowseWebpageTool(MoviePilotTool):
         action: str,
         url: Optional[str] = None,
         selector: Optional[str] = None,
+        ref: Optional[str] = None,
         value: Optional[str] = None,
         script: Optional[str] = None,
         content_type: Optional[str] = "text",
         timeout: Optional[int] = DEFAULT_TIMEOUT,
         cookies: Optional[str] = None,
         user_agent: Optional[str] = None,
+        session_key: Optional[str] = None,
+        tab_index: Optional[int] = None,
+        allow_private_network: bool = False,
         **kwargs,
     ) -> str:
         """执行浏览器操作"""
@@ -146,6 +199,8 @@ class BrowseWebpageTool(MoviePilotTool):
             # 参数校验
             if browser_action == BrowserAction.GOTO and not url:
                 return "错误: 'goto' 操作需要提供 url 参数"
+            if browser_action == BrowserAction.OPEN_TAB and not url:
+                return "错误: 'open_tab' 操作需要提供 url 参数"
             if (
                 browser_action
                 in (
@@ -157,26 +212,46 @@ class BrowseWebpageTool(MoviePilotTool):
                 and not selector
             ):
                 return f"错误: '{action}' 操作需要提供 selector 参数"
+            if (
+                browser_action
+                in (
+                    BrowserAction.CLICK_REF,
+                    BrowserAction.FILL_REF,
+                    BrowserAction.SELECT_REF,
+                )
+                and not ref
+            ):
+                return f"错误: '{action}' 操作需要提供 ref 参数"
             if browser_action == BrowserAction.FILL and value is None:
                 return "错误: 'fill' 操作需要提供 value 参数"
+            if browser_action == BrowserAction.FILL_REF and value is None:
+                return "错误: 'fill_ref' 操作需要提供 value 参数"
             if browser_action == BrowserAction.EVALUATE and not script:
                 return "错误: 'evaluate' 操作需要提供 script 参数"
+            if (
+                browser_action in (BrowserAction.FOCUS_TAB, BrowserAction.CLOSE_TAB)
+                and tab_index is None
+            ):
+                return f"错误: '{action}' 操作需要提供 tab_index 参数"
 
-            # 在线程池中运行同步的 Playwright 操作
-            loop = asyncio.get_running_loop()
-            result = await loop.run_in_executor(
-                None,
-                lambda: self._execute_browser_action(
-                    browser_action=browser_action,
-                    url=url,
-                    selector=selector,
-                    value=value,
-                    script=script,
-                    content_type=content_type,
-                    timeout=timeout,
-                    cookies=cookies,
-                    user_agent=user_agent,
-                ),
+            effective_session_key = session_key or self._session_id
+
+            result = await self.run_blocking(
+                "web",
+                self._execute_browser_action,
+                browser_action=browser_action,
+                url=url,
+                selector=selector,
+                ref=ref,
+                value=value,
+                script=script,
+                content_type=content_type,
+                timeout=timeout,
+                cookies=cookies,
+                user_agent=user_agent,
+                session_key=effective_session_key,
+                tab_index=tab_index,
+                allow_private_network=allow_private_network,
             )
             return result
 
@@ -189,65 +264,61 @@ class BrowseWebpageTool(MoviePilotTool):
         browser_action: BrowserAction,
         url: Optional[str],
         selector: Optional[str],
+        ref: Optional[str],
         value: Optional[str],
         script: Optional[str],
         content_type: Optional[str],
         timeout: int,
         cookies: Optional[str],
         user_agent: Optional[str],
+        session_key: str,
+        tab_index: Optional[int],
+        allow_private_network: bool,
     ) -> str:
         """在同步上下文中执行 CloakBrowser 浏览器操作"""
-        from cloakbrowser import launch_context
 
         try:
-            context = None
-            page = None
-            try:
-                context_kwargs = {
-                    "viewport": {
-                        "width": SCREENSHOT_MAX_WIDTH,
-                        "height": SCREENSHOT_MAX_HEIGHT,
+            if browser_action == BrowserAction.CLOSE_SESSION:
+                closed = BrowserSessionHelper.close_session(session_key)
+                message = "浏览器会话已关闭" if closed else "浏览器会话不存在"
+                return self._json_response(
+                    {
+                        "success": closed,
+                        "message": message,
                     }
-                }
-                if user_agent:
-                    context_kwargs["user_agent"] = user_agent
-
-                context = launch_context(
-                    headless=True,
-                    humanize=settings.CLOAKBROWSER_HUMANIZE,
-                    human_preset=settings.CLOAKBROWSER_HUMAN_PRESET,
-                    **context_kwargs,
                 )
-                page = context.new_page()
-                page.set_default_timeout(timeout * 1000)
 
-                # 设置 cookies
-                if cookies:
-                    page.set_extra_http_headers({"cookie": cookies})
+            helper = BrowserSessionHelper(
+                headless=True,
+                viewport={
+                    "width": SCREENSHOT_MAX_WIDTH,
+                    "height": SCREENSHOT_MAX_HEIGHT,
+                },
+            )
 
-                # 对于非 goto 操作，如果提供了 url 先导航
-                if url and browser_action != BrowserAction.GOTO:
-                    page.goto(url, wait_until="domcontentloaded", timeout=timeout * 1000)
-                    page.wait_for_load_state("networkidle", timeout=timeout * 1000)
-
-                # 执行具体操作
-                result = self._do_action(
-                    page,
-                    browser_action,
-                    url,
-                    selector,
-                    value,
-                    script,
-                    content_type,
-                    timeout,
+            def _callback(session) -> str:
+                return self._do_action(
+                    helper=helper,
+                    session=session,
+                    browser_action=browser_action,
+                    url=url,
+                    selector=selector,
+                    ref=ref,
+                    value=value,
+                    script=script,
+                    content_type=content_type,
+                    timeout=timeout,
+                    tab_index=tab_index,
+                    allow_private_network=allow_private_network,
                 )
-                return result
 
-            finally:
-                if page:
-                    page.close()
-                if context:
-                    context.close()
+            return helper.with_session(
+                session_key=session_key,
+                callback=_callback,
+                user_agent=user_agent,
+                cookies=cookies,
+                timeout=timeout,
+            )
 
         except Exception as e:
             logger.error(f"CloakBrowser 执行失败: {e}", exc_info=True)
@@ -255,19 +326,38 @@ class BrowseWebpageTool(MoviePilotTool):
 
     def _do_action(
         self,
-        page,
+        helper: BrowserSessionHelper,
+        session,
         browser_action: BrowserAction,
         url: Optional[str],
         selector: Optional[str],
+        ref: Optional[str],
         value: Optional[str],
         script: Optional[str],
         content_type: Optional[str],
         timeout: int,
+        tab_index: Optional[int],
+        allow_private_network: bool,
     ) -> str:
         """执行具体的浏览器操作"""
+        page = session.active_page
 
         if browser_action == BrowserAction.GOTO:
-            return self._action_goto(page, url, timeout)
+            return self._action_goto(
+                helper,
+                page,
+                url,
+                timeout,
+                allow_private_network=allow_private_network,
+            )
+
+        elif browser_action == BrowserAction.SNAPSHOT:
+            return self._json_response(
+                BrowserSessionHelper.build_snapshot(
+                    page,
+                    max_text_chars=MAX_CONTENT_LENGTH,
+                )
+            )
 
         elif browser_action == BrowserAction.GET_CONTENT:
             return self._action_get_content(page, content_type)
@@ -278,89 +368,113 @@ class BrowseWebpageTool(MoviePilotTool):
         elif browser_action == BrowserAction.CLICK:
             return self._action_click(page, selector, timeout)
 
+        elif browser_action == BrowserAction.CLICK_REF:
+            return self._action_click(
+                page,
+                BrowserSessionHelper.ref_to_selector(ref),
+                timeout,
+                ref=ref,
+            )
+
         elif browser_action == BrowserAction.FILL:
             return self._action_fill(page, selector, value, timeout)
 
+        elif browser_action == BrowserAction.FILL_REF:
+            return self._action_fill(
+                page,
+                BrowserSessionHelper.ref_to_selector(ref),
+                value,
+                timeout,
+                ref=ref,
+            )
+
         elif browser_action == BrowserAction.SELECT:
             return self._action_select(page, selector, value, timeout)
 
+        elif browser_action == BrowserAction.SELECT_REF:
+            return self._action_select(
+                page,
+                BrowserSessionHelper.ref_to_selector(ref),
+                value,
+                timeout,
+                ref=ref,
+            )
+
         elif browser_action == BrowserAction.EVALUATE:
             return self._action_evaluate(page, script)
 
         elif browser_action == BrowserAction.WAIT:
             return self._action_wait(page, selector, timeout)
 
+        elif browser_action == BrowserAction.LIST_TABS:
+            return self._json_response({"tabs": BrowserSessionHelper.list_tabs(session)})
+
+        elif browser_action == BrowserAction.OPEN_TAB:
+            page = helper.open_tab(
+                session,
+                url=url,
+                timeout=timeout,
+                allow_private_network=allow_private_network,
+            )
+            return self._json_response(
+                {
+                    "success": True,
+                    "active_tab": session.active_index,
+                    "tabs": BrowserSessionHelper.list_tabs(session),
+                    "snapshot": BrowserSessionHelper.build_snapshot(
+                        page,
+                        max_text_chars=MAX_CONTENT_LENGTH,
+                    ),
+                }
+            )
+
+        elif browser_action == BrowserAction.FOCUS_TAB:
+            page = BrowserSessionHelper.focus_tab(session, tab_index)
+            return self._json_response(
+                {
+                    "success": True,
+                    "active_tab": session.active_index,
+                    "tabs": BrowserSessionHelper.list_tabs(session),
+                    "snapshot": BrowserSessionHelper.build_snapshot(
+                        page,
+                        max_text_chars=MAX_CONTENT_LENGTH,
+                    ),
+                }
+            )
+
+        elif browser_action == BrowserAction.CLOSE_TAB:
+            tabs = BrowserSessionHelper.close_tab(session, tab_index)
+            return self._json_response({"success": True, "tabs": tabs})
+
         return f"未知操作: {browser_action}"
 
     @staticmethod
-    def _action_goto(page, url: str, timeout: int) -> str:
+    def _json_response(payload: dict[str, Any]) -> str:
+        """返回格式化 JSON 字符串"""
+        return json.dumps(payload, ensure_ascii=False, indent=2)
+
+    @staticmethod
+    def _action_goto(
+        helper: BrowserSessionHelper,
+        page,
+        url: str,
+        timeout: int,
+        allow_private_network: bool,
+    ) -> str:
         """导航到URL"""
-        response = page.goto(url, wait_until="domcontentloaded", timeout=timeout * 1000)
-        try:
-            page.wait_for_load_state("networkidle", timeout=min(timeout, 15) * 1000)
-        except Exception:
-            # networkidle 超时不是致命错误，页面可能已经可用
-            pass
-
+        response = helper.goto(
+            page,
+            url,
+            timeout=timeout,
+            allow_private_network=allow_private_network,
+        )
         status = response.status if response else "unknown"
-        title = page.title()
-        page_url = page.url
-
-        # 提取页面可读文本摘要
-        text_content = page.inner_text("body")
-        if text_content and len(text_content) > MAX_CONTENT_LENGTH:
-            text_content = text_content[:MAX_CONTENT_LENGTH] + "\n\n...(内容已截断)"
-
-        # 提取页面链接
-        links = page.evaluate("""
-            () => {
-                const links = [];
-                document.querySelectorAll('a[href]').forEach(a => {
-                    const text = a.innerText.trim();
-                    const href = a.href;
-                    if (text && href && !href.startsWith('javascript:')) {
-                        links.push({text: text.substring(0, 80), href: href});
-                    }
-                });
-                return links.slice(0, 30);
-            }
-        """)
-
-        # 提取表单信息
-        forms = page.evaluate("""
-            () => {
-                const forms = [];
-                document.querySelectorAll('input, textarea, select, button').forEach(el => {
-                    const info = {
-                        tag: el.tagName.toLowerCase(),
-                        type: el.type || '',
-                        name: el.name || '',
-                        id: el.id || '',
-                        placeholder: el.placeholder || '',
-                        value: el.tagName.toLowerCase() === 'select' ? '' : (el.value || '').substring(0, 50),
-                        text: el.innerText ? el.innerText.trim().substring(0, 50) : ''
-                    };
-                    // 只保留有标识信息的元素
-                    if (info.name || info.id || info.placeholder || info.text) {
-                        forms.push(info);
-                    }
-                });
-                return forms.slice(0, 30);
-            }
-        """)
-
-        result = {
-            "status": status,
-            "url": page_url,
-            "title": title,
-            "text_content": text_content,
-        }
-        if links:
-            result["links"] = links
-        if forms:
-            result["form_elements"] = forms
-
-        return json.dumps(result, ensure_ascii=False, indent=2)
+        result = BrowserSessionHelper.build_snapshot(
+            page,
+            status=status,
+            max_text_chars=MAX_CONTENT_LENGTH,
+        )
+        return BrowseWebpageTool._json_response(result)
 
     @staticmethod
     def _action_get_content(page, content_type: Optional[str]) -> str:
@@ -382,7 +496,7 @@ class BrowseWebpageTool(MoviePilotTool):
             "content_type": content_type,
             "content": content,
         }
-        return json.dumps(result, ensure_ascii=False, indent=2)
+        return BrowseWebpageTool._json_response(result)
 
     @staticmethod
     def _action_screenshot(page) -> str:
@@ -415,10 +529,15 @@ class BrowseWebpageTool(MoviePilotTool):
             "format": "jpeg",
             "note": "截图已以 base64 编码返回",
         }
-        return json.dumps(result, ensure_ascii=False, indent=2)
+        return BrowseWebpageTool._json_response(result)
 
     @staticmethod
-    def _action_click(page, selector: str, timeout: int) -> str:
+    def _action_click(
+        page,
+        selector: str,
+        timeout: int,
+        ref: Optional[str] = None,
+    ) -> str:
         """点击元素"""
         page.click(selector, timeout=timeout * 1000)
 
@@ -428,49 +547,62 @@ class BrowseWebpageTool(MoviePilotTool):
         except Exception:
             pass
 
-        title = page.title()
-        page_url = page.url
-
-        return json.dumps(
+        return BrowseWebpageTool._json_response(
             {
                 "success": True,
-                "message": f"成功点击元素: {selector}",
-                "current_url": page_url,
-                "current_title": title,
-            },
-            ensure_ascii=False,
-            indent=2,
+                "message": f"成功点击元素: {ref or selector}",
+                "snapshot": BrowserSessionHelper.build_snapshot(
+                    page,
+                    max_text_chars=MAX_CONTENT_LENGTH,
+                ),
+            }
         )
 
     @staticmethod
-    def _action_fill(page, selector: str, value: str, timeout: int) -> str:
+    def _action_fill(
+        page,
+        selector: str,
+        value: str,
+        timeout: int,
+        ref: Optional[str] = None,
+    ) -> str:
         """填写表单"""
         page.fill(selector, value, timeout=timeout * 1000)
 
-        return json.dumps(
+        return BrowseWebpageTool._json_response(
             {
                 "success": True,
-                "message": f"成功填写元素 '{selector}' 的值为 '{value}'",
-            },
-            ensure_ascii=False,
-            indent=2,
+                "message": f"成功填写元素 '{ref or selector}'",
+                "snapshot": BrowserSessionHelper.build_snapshot(
+                    page,
+                    max_text_chars=MAX_CONTENT_LENGTH,
+                ),
+            }
         )
 
     @staticmethod
-    def _action_select(page, selector: str, value: Optional[str], timeout: int) -> str:
+    def _action_select(
+        page,
+        selector: str,
+        value: Optional[str],
+        timeout: int,
+        ref: Optional[str] = None,
+    ) -> str:
         """选择下拉选项"""
         if value:
             page.select_option(selector, value=value, timeout=timeout * 1000)
         else:
             return "错误: 'select' 操作需要提供 value 参数"
 
-        return json.dumps(
+        return BrowseWebpageTool._json_response(
             {
                 "success": True,
-                "message": f"成功选择元素 '{selector}' 的选项 '{value}'",
-            },
-            ensure_ascii=False,
-            indent=2,
+                "message": f"成功选择元素 '{ref or selector}' 的选项 '{value}'",
+                "snapshot": BrowserSessionHelper.build_snapshot(
+                    page,
+                    max_text_chars=MAX_CONTENT_LENGTH,
+                ),
+            }
         )
 
     @staticmethod
@@ -490,13 +622,11 @@ class BrowseWebpageTool(MoviePilotTool):
         if len(formatted) > MAX_CONTENT_LENGTH:
             formatted = formatted[:MAX_CONTENT_LENGTH] + "\n\n...(结果已截断)"
 
-        return json.dumps(
+        return BrowseWebpageTool._json_response(
             {
                 "success": True,
                 "result": formatted,
-            },
-            ensure_ascii=False,
-            indent=2,
+            }
         )
 
     @staticmethod
@@ -510,22 +640,22 @@ class BrowseWebpageTool(MoviePilotTool):
             if text and len(text) > 200:
                 text = text[:200] + "..."
 
-            return json.dumps(
+            return BrowseWebpageTool._json_response(
                 {
                     "success": True,
                     "message": f"元素 '{selector}' 已出现",
                     "visible": visible,
                     "text": text,
-                },
-                ensure_ascii=False,
-                indent=2,
+                    "snapshot": BrowserSessionHelper.build_snapshot(
+                        page,
+                        max_text_chars=MAX_CONTENT_LENGTH,
+                    ),
+                }
             )
         else:
-            return json.dumps(
+            return BrowseWebpageTool._json_response(
                 {
                     "success": False,
                     "message": f"等待元素 '{selector}' 超时",
-                },
-                ensure_ascii=False,
-                indent=2,
+                }
             )

app/agent/tools/impl/delete_custom_filter_rule.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     collect_custom_rule_group_refs,
     get_custom_rules,
@@ -26,6 +27,11 @@ class DeleteCustomFilterRuleInput(BaseModel):
 
 class DeleteCustomFilterRuleTool(MoviePilotTool):
     name: str = "delete_custom_filter_rule"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Delete a custom filter rule from CustomFilterRules. "
         "If the rule is still referenced by rule groups, the deletion is blocked to avoid breaking rule_string expressions."

app/agent/tools/impl/delete_download.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.download import DownloadChain
 from app.log import logger
 
@@ -29,6 +30,11 @@ class DeleteDownloadInput(BaseModel):
 
 class DeleteDownloadTool(MoviePilotTool):
     name: str = "delete_download"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Download,
+        ToolTag.Admin,
+    ]
     description: str = "Delete a download task from the downloader by task hash only. Optionally specify the downloader name and whether to delete downloaded files."
     args_schema: Type[BaseModel] = DeleteDownloadInput
     require_admin: bool = True

app/agent/tools/impl/delete_download_history.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db import AsyncSessionFactory
 from app.db.models.downloadhistory import DownloadHistory
 from app.log import logger
@@ -22,6 +23,11 @@ class DeleteDownloadHistoryInput(BaseModel):
 
 class DeleteDownloadHistoryTool(MoviePilotTool):
     name: str = "delete_download_history"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Download,
+        ToolTag.Admin,
+    ]
     description: str = "Delete a download history record by ID. This only removes the record from the database, does not delete any actual files."
     args_schema: Type[BaseModel] = DeleteDownloadHistoryInput
     require_admin: bool = True

app/agent/tools/impl/delete_rule_group.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     get_rule_groups,
     remove_rule_group_references,
@@ -25,6 +26,11 @@ class DeleteRuleGroupInput(BaseModel):
 
 class DeleteRuleGroupTool(MoviePilotTool):
     name: str = "delete_rule_group"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Delete a filter rule group from UserFilterRuleGroups. "
         "The tool also removes dangling references from global settings and subscriptions."

app/agent/tools/impl/delete_subscribe.py

@@ -5,9 +5,10 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.event import eventmanager
 from app.db.subscribe_oper import SubscribeOper
-from app.helper.subscribe import SubscribeHelper
+from app.helper.server import MoviePilotServerHelper
 from app.log import logger
 from app.schemas.types import EventType
 
@@ -25,6 +26,11 @@ class DeleteSubscribeInput(BaseModel):
 
 class DeleteSubscribeTool(MoviePilotTool):
     name: str = "delete_subscribe"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Subscription,
+        ToolTag.Admin,
+    ]
     description: str = "Delete a media subscription by its ID. This will remove the subscription and stop automatic downloads for that media."
     args_schema: Type[BaseModel] = DeleteSubscribeInput
     require_admin: bool = True
@@ -49,7 +55,7 @@ class DeleteSubscribeTool(MoviePilotTool):
 
             await subscribe_oper.async_delete(subscribe_id)
             # 分享订阅统计刷新本身已异步化，这里只需要在删除后触发即可。
-            SubscribeHelper().sub_done_async(
+            MoviePilotServerHelper.sub_done_async(
                 {"tmdbid": subscribe.tmdbid, "doubanid": subscribe.doubanid}
             )
 

app/agent/tools/impl/delete_transfer_history.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db.transferhistory_oper import TransferHistoryOper
 from app.log import logger
 
@@ -21,6 +22,11 @@ class DeleteTransferHistoryInput(BaseModel):
 
 class DeleteTransferHistoryTool(MoviePilotTool):
     name: str = "delete_transfer_history"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Transfer,
+        ToolTag.Admin,
+    ]
     description: str = "Delete a specific transfer history record by its ID. This is useful when you need to remove a failed transfer record before retrying the transfer, as the system skips files that already have transfer history."
     args_schema: Type[BaseModel] = DeleteTransferHistoryInput
     require_admin: bool = True

app/agent/tools/impl/edit_file.py

@@ -7,6 +7,7 @@ from anyio import Path as AsyncPath
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -20,6 +21,11 @@ class EditFileInput(BaseModel):
 
 class EditFileTool(MoviePilotTool):
     name: str = "edit_file"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.File,
+        ToolTag.Admin,
+    ]
     description: str = "Edit a file by replacing specific old text with new text. Useful for modifying configuration files, code, or scripts."
     args_schema: Type[BaseModel] = EditFileInput
     require_admin: bool = True

app/agent/tools/impl/execute_command.py

@@ -14,7 +14,8 @@ from typing import Any, Literal, Optional, TextIO, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
-from app.agent.tools.impl.terminal_session import (
+from app.agent.tools.tags import ToolTag
+from app.agent.tools.impl._terminal_session import (
     TERMINAL_DEFAULT_READ_BYTES,
     TERMINAL_MAX_READ_BYTES,
     TERMINAL_WAIT_DEFAULT_MS,
@@ -200,6 +201,11 @@ class ExecuteCommandTool(MoviePilotTool):
     """统一执行和管理 Shell 命令的 Agent 工具。"""
 
     name: str = "execute_command"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Command,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Start and manage shell commands on the server. By default action=start "
         "launches a background session and immediately returns session_id/status/"
@@ -445,6 +451,9 @@ class ExecuteCommandTool(MoviePilotTool):
             except asyncio.TimeoutError:
                 timed_out = True
                 await self._cleanup_process(process, wait_task)
+            except asyncio.CancelledError:
+                await self._cleanup_process(process, wait_task)
+                raise
 
             try:
                 await self._finish_reader_tasks(reader_tasks)

app/agent/tools/impl/get_recommendations.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.recommend import RecommendChain
 from app.log import logger
 from app.schemas.types import MediaType, media_type_to_agent
@@ -44,6 +45,11 @@ class GetRecommendationsInput(BaseModel):
 
 class GetRecommendationsTool(MoviePilotTool):
     name: str = "get_recommendations"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+        ToolTag.Recommendation,
+    ]
     description: str = "Get trending and popular media recommendations from various sources. Returns curated lists of popular movies, TV shows, and anime based on different criteria like trending, ratings, or calendar schedules. Supports pagination with 20 items per page."
     args_schema: Type[BaseModel] = GetRecommendationsInput
 

app/agent/tools/impl/get_search_results.py

@@ -7,6 +7,7 @@ from typing import List, Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.search import SearchChain
 from app.log import logger
 from ._torrent_search_utils import (
@@ -47,6 +48,10 @@ class GetSearchResultsInput(BaseModel):
 
 class GetSearchResultsTool(MoviePilotTool):
     name: str = "get_search_results"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Resource,
+    ]
     description: str = "Get cached torrent search results from search_torrents with optional filters. Supports pagination with up to 50 results per page."
     args_schema: Type[BaseModel] = GetSearchResultsInput
 

app/agent/tools/impl/install_plugin.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import (
     get_plugin_snapshot,
     install_plugin_runtime,
@@ -36,6 +37,11 @@ class InstallPluginInput(BaseModel):
 
 class InstallPluginTool(MoviePilotTool):
     name: str = "install_plugin"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Install a plugin by exact plugin_id from the plugin market or local plugin repositories. "
         "Use query_market_plugins first when you need filtering or discovery."

app/agent/tools/impl/list_directory.py

@@ -8,6 +8,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.storage import StorageChain
 from app.log import logger
 from app.schemas.file import FileItem
@@ -24,6 +25,11 @@ class ListDirectoryInput(BaseModel):
 
 class ListDirectoryTool(MoviePilotTool):
     name: str = "list_directory"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Directory,
+        ToolTag.File,
+    ]
     description: str = "List actual files and folders in a file system directory (NOT configuration). Shows files and subdirectories with their names, types, sizes, and modification times. Returns up to 20 items and the total count if there are more items. Use 'query_directory_settings' to query directory configuration settings."
     args_schema: Type[BaseModel] = ListDirectoryInput
 

app/agent/tools/impl/list_slash_commands.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -18,6 +19,11 @@ class ListSlashCommandsInput(BaseModel):
 
 class ListSlashCommandsTool(MoviePilotTool):
     name: str = "list_slash_commands"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.SlashCommand,
+        ToolTag.Admin,
+    ]
     description: str = (
         "List all available slash commands in the system, including system preset commands "
         "(e.g. /cookiecloud, /sites, /subscribes, /downloading, /transfer, /restart, etc.) "

app/agent/tools/impl/modify_download.py

@@ -5,6 +5,7 @@ from typing import Optional, Type, List
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.download import DownloadChain
 from app.log import logger
 
@@ -37,6 +38,11 @@ class ModifyDownloadTool(MoviePilotTool):
     """修改下载任务工具"""
 
     name: str = "modify_download"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Download,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Modify a download task in the downloader by task hash. "
         "Supports: 1) Setting tags on a download task, "

app/agent/tools/impl/query_builtin_filter_rules.py

@@ -6,6 +6,7 @@ from typing import Optional, Type, List
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     get_builtin_rules,
     serialize_builtin_rule,
@@ -27,6 +28,10 @@ class QueryBuiltinFilterRulesInput(BaseModel):
 
 class QueryBuiltinFilterRulesTool(MoviePilotTool):
     name: str = "query_builtin_filter_rules"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.FilterRule,
+    ]
     description: str = (
         "Query built-in filter rules defined by the backend filter module. "
         "These rule IDs can be used directly inside rule_string expressions for filter rule groups. "

app/agent/tools/impl/query_custom_filter_rules.py

@@ -6,6 +6,7 @@ from typing import Optional, Type, List
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     collect_custom_rule_group_refs,
     get_custom_rules,
@@ -32,6 +33,10 @@ class QueryCustomFilterRulesInput(BaseModel):
 
 class QueryCustomFilterRulesTool(MoviePilotTool):
     name: str = "query_custom_filter_rules"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.FilterRule,
+    ]
     description: str = (
         "Query custom filter rules stored in CustomFilterRules. "
         "Custom rules can be referenced from rule_string expressions in filter rule groups. "

app/agent/tools/impl/query_custom_identifiers.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db.systemconfig_oper import SystemConfigOper
 from app.log import logger
 from app.schemas.types import SystemConfigKey
@@ -20,6 +21,11 @@ class QueryCustomIdentifiersInput(BaseModel):
 
 class QueryCustomIdentifiersTool(MoviePilotTool):
     name: str = "query_custom_identifiers"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query all currently configured custom identifiers (自定义识别词). "
         "Returns the list of identifier rules used for preprocessing torrent/file names before media recognition. "

app/agent/tools/impl/query_directory_settings.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.helper.directory import DirectoryHelper
 from app.log import logger
 
@@ -23,6 +24,12 @@ class QueryDirectorySettingsInput(BaseModel):
 
 class QueryDirectorySettingsTool(MoviePilotTool):
     name: str = "query_directory_settings"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Directory,
+        ToolTag.Settings,
+        ToolTag.Admin,
+    ]
     description: str = "Query system directory configuration settings (NOT file listings). Returns configured directory paths, storage types, transfer modes, and other directory-related settings. Use 'list_directory' to list actual files and folders in a directory."
     require_admin: bool = True
     args_schema: Type[BaseModel] = QueryDirectorySettingsInput

app/agent/tools/impl/query_doctor_report.py

@@ -0,0 +1,126 @@
+"""查询 MoviePilot Doctor 诊断报告工具。"""
+
+import json
+from typing import Any, Optional, Type
+
+from pydantic import BaseModel, Field
+
+from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
+from app.doctor import run_doctor
+from app.log import logger
+
+
+class QueryDoctorReportInput(BaseModel):
+    """查询 Doctor 诊断报告工具的输入参数模型。"""
+
+    explanation: Optional[str] = Field(
+        None,
+        description="Clear explanation of why this tool is being used in the current context",
+    )
+    deep: Optional[bool] = Field(
+        False,
+        description=(
+            "Whether to run deeper checks. When true, doctor may perform slower environment probes "
+            "such as PostgreSQL TCP connectivity checks."
+        ),
+    )
+    include_details: Optional[bool] = Field(
+        True,
+        description=(
+            "Whether to include full doctor findings with details and context. Set false for a compact "
+            "summary when only overall status and finding titles are needed."
+        ),
+    )
+
+
+class QueryDoctorReportTool(MoviePilotTool):
+    """
+    Doctor 离线诊断报告查询工具。
+    """
+
+    name: str = "query_doctor_report"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.System,
+        ToolTag.Admin,
+    ]
+    description: str = (
+        "Run MoviePilot Doctor in read-only mode and return a structured diagnostic report for troubleshooting. "
+        "Use this tool when analyzing startup failures, Docker/runtime issues, port conflicts, dependency problems, "
+        "database health, frontend assets, safe mode, or recent log error clues. This tool never applies fixes."
+    )
+    require_admin: bool = True
+    args_schema: Type[BaseModel] = QueryDoctorReportInput
+
+    def get_tool_message(self, **kwargs) -> Optional[str]:
+        """根据查询参数生成友好的提示消息。"""
+        if kwargs.get("deep"):
+            return "运行 Doctor 深度诊断"
+        return "运行 Doctor 诊断"
+
+    @staticmethod
+    def _compact_report(report: dict[str, Any]) -> dict[str, Any]:
+        """压缩诊断报告，保留 Agent 判断问题所需的核心字段。"""
+        return {
+            "schema_version": report.get("schema_version"),
+            "status": report.get("status"),
+            "generated_at": report.get("generated_at"),
+            "version": report.get("version"),
+            "environment": report.get("environment"),
+            "summary": report.get("summary"),
+            "findings": [
+                {
+                    "id": item.get("id"),
+                    "severity": item.get("severity"),
+                    "status": item.get("status"),
+                    "title": item.get("title"),
+                    "fixable": item.get("fixable"),
+                    "fixed": item.get("fixed"),
+                }
+                for item in report.get("findings") or []
+                if isinstance(item, dict)
+            ],
+        }
+
+    @staticmethod
+    def _run_doctor_report(deep: bool = False) -> dict[str, Any]:
+        """在线程池中运行只读 Doctor 诊断。"""
+        return run_doctor(deep=bool(deep)).to_dict()
+
+    async def run(
+        self,
+        deep: Optional[bool] = False,
+        include_details: Optional[bool] = True,
+        **kwargs,
+    ) -> str:
+        """
+        运行只读 Doctor 诊断并返回 JSON 字符串。
+        """
+        logger.info(
+            f"执行工具: {self.name}, deep={bool(deep)}, include_details={bool(include_details)}"
+        )
+        try:
+            report = await self.run_blocking("default", self._run_doctor_report, bool(deep))
+            if not include_details:
+                report = self._compact_report(report)
+            return json.dumps(
+                {
+                    "success": True,
+                    "deep": bool(deep),
+                    "include_details": bool(include_details),
+                    "report": report,
+                },
+                ensure_ascii=False,
+                indent=2,
+                default=str,
+            )
+        except Exception as err:
+            logger.error(f"查询 Doctor 诊断报告失败: {err}", exc_info=True)
+            return json.dumps(
+                {
+                    "success": False,
+                    "message": f"查询 Doctor 诊断报告时发生错误: {str(err)}",
+                },
+                ensure_ascii=False,
+            )

app/agent/tools/impl/query_download_tasks.py

@@ -6,6 +6,7 @@ from typing import Any, Dict, List, Optional, Type, Union
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.download import DownloadChain
 from app.db.downloadhistory_oper import DownloadHistoryOper
 from app.log import logger
@@ -27,6 +28,10 @@ class QueryDownloadTasksInput(BaseModel):
 
 class QueryDownloadTasksTool(MoviePilotTool):
     name: str = "query_download_tasks"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Download,
+    ]
     description: str = "Query download status and list download tasks. Can query all active downloads, or search for specific tasks by hash, title, or tag. Shows download progress, completion status, tags, and task details from configured downloaders."
     args_schema: Type[BaseModel] = QueryDownloadTasksInput
 

app/agent/tools/impl/query_downloaders.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db.systemconfig_oper import SystemConfigOper
 from app.log import logger
 from app.schemas.types import SystemConfigKey
@@ -18,6 +19,11 @@ class QueryDownloadersInput(BaseModel):
 
 class QueryDownloadersTool(MoviePilotTool):
     name: str = "query_downloaders"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Download,
+        ToolTag.Admin,
+    ]
     description: str = "Query downloader configuration and list all available downloaders. Shows downloader status, connection details, and configuration settings."
     require_admin: bool = True
     args_schema: Type[BaseModel] = QueryDownloadersInput

app/agent/tools/impl/query_episode_schedule.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.tmdb import TmdbChain
 from app.log import logger
 
@@ -20,6 +21,10 @@ class QueryEpisodeScheduleInput(BaseModel):
 
 class QueryEpisodeScheduleTool(MoviePilotTool):
     name: str = "query_episode_schedule"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+    ]
     description: str = "Query TV series episode air dates and schedule. Returns non-duplicated schedule fields, including episode list, air-date statistics, and per-episode metadata. Filters out episodes without air dates."
     args_schema: Type[BaseModel] = QueryEpisodeScheduleInput
 

app/agent/tools/impl/query_installed_plugins.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import (
     DEFAULT_PLUGIN_CANDIDATE_LIMIT,
     MAX_PLUGIN_CANDIDATE_LIMIT,
@@ -34,6 +35,11 @@ class QueryInstalledPluginsInput(BaseModel):
 
 class QueryInstalledPluginsTool(MoviePilotTool):
     name: str = "query_installed_plugins"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query installed plugins in MoviePilot. Returns all installed plugins or filters them by keywords. "
         "Use this tool to find the exact plugin_id before uninstall_plugin or other plugin management tools are used."

app/agent/tools/impl/query_library_exists.py

@@ -8,6 +8,7 @@ from typing import Optional, Type, Any
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.mediaserver import MediaServerChain
 from app.helper.mediaserver import MediaServerHelper
 from app.log import logger
@@ -84,6 +85,11 @@ class QueryLibraryExistsInput(BaseModel):
 
 class QueryLibraryExistsTool(MoviePilotTool):
     name: str = "query_library_exists"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Library,
+        ToolTag.Media,
+    ]
     description: str = "Check whether media already exists in Plex, Emby, or Jellyfin by media ID. Results are grouped by media server; TV results include existing episodes, total episodes, and missing episodes/seasons. Requires tmdb_id or douban_id from search_media."
     args_schema: Type[BaseModel] = QueryLibraryExistsInput
 

app/agent/tools/impl/query_library_latest.py

@@ -7,6 +7,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.mediaserver import MediaServerChain
 from app.helper.service import ServiceConfigHelper
 from app.log import logger
@@ -30,6 +31,11 @@ class QueryLibraryLatestInput(BaseModel):
 
 class QueryLibraryLatestTool(MoviePilotTool):
     name: str = "query_library_latest"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Library,
+        ToolTag.Media,
+    ]
     description: str = "Query the latest media items added to the media server (Plex, Emby, Jellyfin). Returns recently added movies and TV series with their titles, images, links, and other metadata. Supports pagination with 20 items per page."
     args_schema: Type[BaseModel] = QueryLibraryLatestInput
 

app/agent/tools/impl/query_market_plugins.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import (
     DEFAULT_PLUGIN_CANDIDATE_LIMIT,
     MAX_PLUGIN_CANDIDATE_LIMIT,
@@ -38,6 +39,11 @@ class QueryMarketPluginsInput(BaseModel):
 
 class QueryMarketPluginsTool(MoviePilotTool):
     name: str = "query_market_plugins"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query available plugins from the plugin market and local plugin repositories. "
         "Can return the full plugin list or filter by keywords before install_plugin is used."

app/agent/tools/impl/query_media_detail.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.media import MediaChain
 from app.log import logger
 from app.schemas.types import MediaType
@@ -25,6 +26,10 @@ class QueryMediaDetailInput(BaseModel):
 
 class QueryMediaDetailTool(MoviePilotTool):
     name: str = "query_media_detail"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+    ]
     description: str = "Query supplementary media details from TMDB by ID and media_type. Accepts tmdb_id or douban_id (at least one required). media_type accepts 'movie' or 'tv'. Returns non-duplicated detail fields such as status, genres, directors, actors, and season info for TV series."
     args_schema: Type[BaseModel] = QueryMediaDetailInput
 

app/agent/tools/impl/query_personas.py

@@ -7,6 +7,7 @@ from pydantic import BaseModel, Field
 
 from app.agent.runtime import agent_runtime_manager
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -26,6 +27,10 @@ class QueryPersonasInput(BaseModel):
 
 class QueryPersonasTool(MoviePilotTool):
     name: str = "query_personas"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Persona,
+    ]
     description: str = (
         "List all available personas (人格) and show which one is currently active. "
         "Use this before switching persona when the user asks for a different speaking style but does not name "

app/agent/tools/impl/query_plugin_capabilities.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.plugin import PluginManager
 from app.log import logger
 
@@ -25,6 +26,11 @@ class QueryPluginCapabilitiesInput(BaseModel):
 
 class QueryPluginCapabilitiesTool(MoviePilotTool):
     name: str = "query_plugin_capabilities"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query the capabilities of installed plugins, including supported commands and scheduled services. "
         "Commands are slash-commands (e.g. /xxx) that can be executed via the run_slash_command tool. "

app/agent/tools/impl/query_plugin_config.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import get_plugin_snapshot
 from app.core.plugin import PluginManager
 from app.log import logger
@@ -24,6 +25,11 @@ class QueryPluginConfigInput(BaseModel):
 
 class QueryPluginConfigTool(MoviePilotTool):
     name: str = "query_plugin_config"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query the saved configuration of an installed plugin. "
         "Returns the current saved config and, when available, the plugin's default config model. "

app/agent/tools/impl/query_plugin_data.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import (
     PLUGIN_DATA_KEY_PREVIEW_LIMIT,
     build_preview_payload,
@@ -36,6 +37,11 @@ class QueryPluginDataInput(BaseModel):
 
 class QueryPluginDataTool(MoviePilotTool):
     name: str = "query_plugin_data"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query persisted data of an installed plugin. "
         "Optionally specify a key to read a single data item; otherwise all plugin data entries are returned. "

app/agent/tools/impl/query_popular_subscribes.py

@@ -7,8 +7,9 @@ import cn2an
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.context import MediaInfo
-from app.helper.subscribe import SubscribeHelper
+from app.helper.server import MoviePilotServerHelper
 from app.log import logger
 from app.schemas.types import MediaType, media_type_to_agent
 
@@ -30,6 +31,11 @@ class QueryPopularSubscribesInput(BaseModel):
 
 class QueryPopularSubscribesTool(MoviePilotTool):
     name: str = "query_popular_subscribes"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Subscription,
+        ToolTag.Recommendation,
+    ]
     description: str = "Query popular subscriptions based on user shared data. Shows media with the most subscribers, supports filtering by genre, rating, minimum subscribers, and pagination."
     args_schema: Type[BaseModel] = QueryPopularSubscribesInput
 
@@ -77,8 +83,7 @@ class QueryPopularSubscribesTool(MoviePilotTool):
             if not media_type_enum:
                 return f"错误：无效的媒体类型 '{media_type}'，支持的类型：'movie', 'tv'"
 
-            subscribe_helper = SubscribeHelper()
-            subscribes = await subscribe_helper.async_get_statistic(
+            subscribes = await MoviePilotServerHelper.async_get_subscribe_statistic(
                 stype=media_type_enum.to_agent(),
                 page=page,
                 count=count,

app/agent/tools/impl/query_rule_groups.py

@@ -6,6 +6,7 @@ from typing import Optional, Type, List
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     collect_rule_group_usages,
     get_rule_groups,
@@ -32,6 +33,10 @@ class QueryRuleGroupsInput(BaseModel):
 
 class QueryRuleGroupsTool(MoviePilotTool):
     name: str = "query_rule_groups"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.FilterRule,
+    ]
     description: str = (
         "Query filter rule groups (过滤规则组 / 优先级规则组). "
         "Each rule group contains a rule_string made of built-in rules and/or custom rules. "

app/agent/tools/impl/query_schedulers.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -16,6 +17,10 @@ class QuerySchedulersInput(BaseModel):
 
 class QuerySchedulersTool(MoviePilotTool):
     name: str = "query_schedulers"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Scheduler,
+    ]
     description: str = "Query scheduled tasks and list all available scheduler jobs. Shows job status, next run time, and provider information."
     args_schema: Type[BaseModel] = QuerySchedulersInput
 

app/agent/tools/impl/query_site_userdata.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db import AsyncSessionFactory
 from app.db.models.site import Site
 from app.db.models.siteuserdata import SiteUserData
@@ -37,6 +38,11 @@ class QuerySiteUserdataInput(BaseModel):
 
 class QuerySiteUserdataTool(MoviePilotTool):
     name: str = "query_site_userdata"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Site,
+        ToolTag.Admin,
+    ]
     description: str = "Query user data for a specific site including username, user level, upload/download statistics, seeding information, bonus points, and other account details. Supports querying data for a specific date or latest data."
     require_admin: bool = True
     args_schema: Type[BaseModel] = QuerySiteUserdataInput

app/agent/tools/impl/query_sites.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db.site_oper import SiteOper
 from app.log import logger
 
@@ -26,6 +27,11 @@ class QuerySitesInput(BaseModel):
 
 class QuerySitesTool(MoviePilotTool):
     name: str = "query_sites"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Site,
+        ToolTag.Admin,
+    ]
     description: str = "Query site status and list all configured sites. Shows site name, domain, status, priority, and basic configuration. Site priority (pri): smaller values have higher priority (e.g., pri=1 has higher priority than pri=10)."
     require_admin: bool = True
     args_schema: Type[BaseModel] = QuerySitesInput

app/agent/tools/impl/query_subscribe_history.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db import AsyncSessionFactory
 from app.db.models.subscribehistory import SubscribeHistory
 from app.log import logger
@@ -33,6 +34,10 @@ class QuerySubscribeHistoryInput(BaseModel):
 
 class QuerySubscribeHistoryTool(MoviePilotTool):
     name: str = "query_subscribe_history"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Subscription,
+    ]
     description: str = "Query subscription history records. Shows completed subscriptions with their details including name, type, rating, completion date, and other subscription information. Supports filtering by media type and name. Supports pagination with 20 records per page."
     args_schema: Type[BaseModel] = QuerySubscribeHistoryInput
 

app/agent/tools/impl/query_subscribe_shares.py

@@ -6,7 +6,8 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
-from app.helper.subscribe import SubscribeHelper
+from app.agent.tools.tags import ToolTag
+from app.helper.server import MoviePilotServerHelper
 from app.log import logger
 
 MAX_PAGE_SIZE = 50
@@ -26,6 +27,10 @@ class QuerySubscribeSharesInput(BaseModel):
 
 class QuerySubscribeSharesTool(MoviePilotTool):
     name: str = "query_subscribe_shares"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Subscription,
+    ]
     description: str = "Query shared subscriptions from other users. Shows popular subscriptions shared by the community with filtering and pagination support."
     args_schema: Type[BaseModel] = QuerySubscribeSharesInput
 
@@ -68,8 +73,7 @@ class QuerySubscribeSharesTool(MoviePilotTool):
             # 订阅分享是外部列表型结果，限制单页大小能降低工具上下文占用。
             count = min(count, MAX_PAGE_SIZE)
 
-            subscribe_helper = SubscribeHelper()
-            shares = await subscribe_helper.async_get_shares(
+            shares = await MoviePilotServerHelper.async_get_subscribe_shares(
                 name=name,
                 page=page,
                 count=count,

app/agent/tools/impl/query_subscribes.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db.subscribe_oper import SubscribeOper
 from app.log import logger
 from app.schemas.subscribe import Subscribe as SubscribeSchema
@@ -71,6 +72,10 @@ class QuerySubscribesInput(BaseModel):
 
 class QuerySubscribesTool(MoviePilotTool):
     name: str = "query_subscribes"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Subscription,
+    ]
     description: str = "Query subscription status and list user subscriptions. Returns full subscription parameters for each matched subscription. Supports pagination with 100 items per page."
     args_schema: Type[BaseModel] = QuerySubscribesInput
 

app/agent/tools/impl/query_system_settings.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._system_setting_utils import (
     SettingSpec,
     list_setting_specs,
@@ -56,6 +57,12 @@ class QuerySystemSettingsInput(BaseModel):
 
 class QuerySystemSettingsTool(MoviePilotTool):
     name: str = "query_system_settings"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.System,
+        ToolTag.Settings,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Query system settings across both the basic Settings module and all SystemConfig-backed categories. "
         "Use this tool to inspect downloaders, media servers, notification channels, storages, directories, search-site ranges, "

app/agent/tools/impl/query_transfer_history.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db import AsyncSessionFactory
 from app.db.models.transferhistory import TransferHistory
 from app.log import logger
@@ -24,6 +25,10 @@ class QueryTransferHistoryInput(BaseModel):
 
 class QueryTransferHistoryTool(MoviePilotTool):
     name: str = "query_transfer_history"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Transfer,
+    ]
     description: str = "Query file transfer history records. Shows transfer status, source and destination paths, media information, and transfer details. Supports filtering by title and status."
     args_schema: Type[BaseModel] = QueryTransferHistoryInput
 

app/agent/tools/impl/query_workflows.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db import AsyncSessionFactory
 from app.db.workflow_oper import WorkflowOper
 from app.log import logger
@@ -21,6 +22,10 @@ class QueryWorkflowsInput(BaseModel):
 
 class QueryWorkflowsTool(MoviePilotTool):
     name: str = "query_workflows"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Workflow,
+    ]
     description: str = "Query workflow list and status. Shows workflow name, description, trigger type, state, execution count, and other workflow details. Supports filtering by state, name, and trigger type."
     args_schema: Type[BaseModel] = QueryWorkflowsInput
 

app/agent/tools/impl/read_file.py

@@ -7,6 +7,7 @@ from anyio import Path as AsyncPath
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 # 最大读取大小 50KB
@@ -22,6 +23,10 @@ class ReadFileInput(BaseModel):
 
 class ReadFileTool(MoviePilotTool):
     name: str = "read_file"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.File,
+    ]
     description: str = "Read the content of a text file. Supports reading by line range. Each read is limited to 50KB; content exceeding this limit will be truncated."
     args_schema: Type[BaseModel] = ReadFileInput
 

app/agent/tools/impl/recognize_media.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.media import MediaChain
 from app.core.context import Context
 from app.core.metainfo import MetaInfo
@@ -23,6 +24,11 @@ class RecognizeMediaInput(BaseModel):
 
 class RecognizeMediaTool(MoviePilotTool):
     name: str = "recognize_media"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+        ToolTag.Metadata,
+    ]
     description: str = "Extract/identify media information from torrent titles or file paths (NOT database search). Supports two modes: 1) Extract from torrent title and optional subtitle, 2) Extract from file path. Returns detailed media information. Use 'search_media' to search TMDB database, or 'scrape_metadata' to generate metadata files for existing files."
     args_schema: Type[BaseModel] = RecognizeMediaInput
 

app/agent/tools/impl/reload_plugin.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import (
     get_plugin_snapshot,
     reload_plugin_runtime,
@@ -26,6 +27,11 @@ class ReloadPluginInput(BaseModel):
 
 class ReloadPluginTool(MoviePilotTool):
     name: str = "reload_plugin"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Reload an installed plugin so its latest saved configuration takes effect. "
         "This also refreshes the plugin's registered commands, scheduled services, and API routes."

app/agent/tools/impl/run_scheduler.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -21,6 +22,11 @@ class RunSchedulerInput(BaseModel):
 
 class RunSchedulerTool(MoviePilotTool):
     name: str = "run_scheduler"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Scheduler,
+        ToolTag.Admin,
+    ]
     description: str = "Manually trigger a scheduled task to run immediately. This will execute the specified scheduler job by its ID."
     args_schema: Type[BaseModel] = RunSchedulerInput
     require_admin: bool = True

app/agent/tools/impl/run_slash_command.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.event import eventmanager
 from app.log import logger
 from app.schemas.types import EventType, MessageChannel
@@ -27,6 +28,11 @@ class RunSlashCommandInput(BaseModel):
 
 class RunSlashCommandTool(MoviePilotTool):
     name: str = "run_slash_command"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.SlashCommand,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Execute a slash command (system or plugin) by sending a CommandExcute event. "
         "This tool supports ALL registered slash commands, including: "

app/agent/tools/impl/run_workflow.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.workflow import WorkflowChain
 from app.db import AsyncSessionFactory
 from app.db.workflow_oper import WorkflowOper
@@ -27,6 +28,11 @@ class RunWorkflowInput(BaseModel):
 
 class RunWorkflowTool(MoviePilotTool):
     name: str = "run_workflow"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Workflow,
+        ToolTag.Admin,
+    ]
     description: str = "Execute a specific workflow manually by workflow ID. Supports running from the beginning or continuing from the last executed action."
     args_schema: Type[BaseModel] = RunWorkflowInput
     require_admin: bool = True

app/agent/tools/impl/scrape_metadata.py

@@ -7,6 +7,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.media import MediaChain
 from app.log import logger
 from app.schemas import FileItem
@@ -33,6 +34,13 @@ class ScrapeMetadataInput(BaseModel):
 
 class ScrapeMetadataTool(MoviePilotTool):
     name: str = "scrape_metadata"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Media,
+        ToolTag.Metadata,
+        ToolTag.File,
+        ToolTag.Admin,
+    ]
     description: str = "Generate metadata files (NFO files, posters, backgrounds, etc.) for existing media files or directories. Automatically recognizes media information from the file path and creates metadata files. Supports both local and remote storage. Use 'search_media' to search TMDB database, or 'recognize_media' to extract info from torrent titles/file paths without generating files."
     require_admin: bool = True
     args_schema: Type[BaseModel] = ScrapeMetadataInput

app/agent/tools/impl/search_media.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.media import MediaChain
 from app.log import logger
 from app.schemas.types import MediaType, media_type_to_agent
@@ -24,6 +25,10 @@ class SearchMediaInput(BaseModel):
 
 class SearchMediaTool(MoviePilotTool):
     name: str = "search_media"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+    ]
     description: str = "Search TMDB database for media resources (movies, TV shows, anime, etc.) by title, year, type, and other criteria. Returns detailed media information from TMDB. Use 'recognize_media' to extract info from torrent titles/file paths, or 'scrape_metadata' to generate metadata files."
     args_schema: Type[BaseModel] = SearchMediaInput
 

app/agent/tools/impl/search_person.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.media import MediaChain
 from app.log import logger
 
@@ -18,6 +19,10 @@ class SearchPersonInput(BaseModel):
 
 class SearchPersonTool(MoviePilotTool):
     name: str = "search_person"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+    ]
     description: str = "Search for person information including actors, directors, etc. Supports searching by name. Returns detailed person information from TMDB, Douban, or Bangumi database."
     args_schema: Type[BaseModel] = SearchPersonInput
 

app/agent/tools/impl/search_person_credits.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.douban import DoubanChain
 from app.chain.tmdb import TmdbChain
 from app.chain.bangumi import BangumiChain
@@ -22,6 +23,10 @@ class SearchPersonCreditsInput(BaseModel):
 
 class SearchPersonCreditsTool(MoviePilotTool):
     name: str = "search_person_credits"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Media,
+    ]
     description: str = "Search for films and TV shows that a person/actor has appeared in (filmography). Supports searching by person ID from TMDB, Douban, or Bangumi database. Returns a list of media works the person has participated in."
     args_schema: Type[BaseModel] = SearchPersonCreditsInput
 

app/agent/tools/impl/search_subscribe.py

@@ -6,6 +6,7 @@ from typing import Optional, Type, List
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.subscribe import SubscribeChain
 from app.db.subscribe_oper import SubscribeOper
 from app.log import logger
@@ -23,6 +24,12 @@ class SearchSubscribeInput(BaseModel):
 
 class SearchSubscribeTool(MoviePilotTool):
     name: str = "search_subscribe"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Write,
+        ToolTag.Subscription,
+        ToolTag.Resource,
+    ]
     description: str = "Search for missing episodes/resources for a specific subscription. This tool will search torrent sites for the missing episodes of the subscription and automatically download matching resources. Use this when a user wants to search for missing episodes of a specific subscription."
     args_schema: Type[BaseModel] = SearchSubscribeInput
 

app/agent/tools/impl/search_torrents.py

@@ -6,6 +6,7 @@ from typing import List, Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.search import SearchChain
 from app.db.systemconfig_oper import SystemConfigOper
 from app.helper.sites import SitesHelper
@@ -29,6 +30,12 @@ class SearchTorrentsInput(BaseModel):
 
 class SearchTorrentsTool(MoviePilotTool):
     name: str = "search_torrents"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Resource,
+        ToolTag.Site,
+        ToolTag.Media,
+    ]
     description: str = ("Search for torrent files by media ID across configured indexer sites, cache the matched results, "
                         "and return available filter options for follow-up selection. "
                         "Requires tmdb_id or douban_id (can be obtained from search_media tool) for accurate matching.")

app/agent/tools/impl/search_web.py

@@ -1,76 +1,168 @@
-import asyncio
 import json
-import random
 import re
-from typing import Optional, Type, List, Dict
+from dataclasses import dataclass
+from typing import Dict, List, Optional, Type
+from urllib.parse import urlparse
 
-import httpx
 from ddgs import DDGS
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.config import settings
 from app.log import logger
 
 # 搜索超时时间（秒）
 SEARCH_TIMEOUT = 20
+# 单次搜索最多返回结果数
+MAX_SEARCH_RESULTS = 20
+# 默认搜索源
+DEFAULT_SEARCH_ENGINE = "auto"
+# 可显式调用的搜索引擎后端
+SEARCH_ENGINE_BACKENDS = (
+    "auto",
+    "duckduckgo",
+    "google",
+    "brave",
+    "yahoo",
+    "wikipedia",
+    "yandex",
+    "mojeek",
+)
+SUPPORTED_SEARCH_ENGINES = SEARCH_ENGINE_BACKENDS
+DDGS_AUTO_BACKEND = ",".join(
+    backend for backend in SEARCH_ENGINE_BACKENDS if backend != DEFAULT_SEARCH_ENGINE
+)
+SITE_SEARCH_PATTERN = re.compile(r"\bsite:", re.IGNORECASE)
+
+
+@dataclass(frozen=True)
+class _SearchSiteFilter:
+    """站点限定搜索参数"""
+
+    domain: str
+    path: str
+    search_target: str
 
 
 class SearchWebInput(BaseModel):
     """搜索网络内容工具的输入参数模型"""
 
-    explanation: Optional[str] = Field(None,
-        description="Clear explanation of why this tool is being used in the current context",)
+    explanation: Optional[str] = Field(
+        None,
+        description="Clear explanation of why this tool is being used in the current context",
+    )
     query: str = Field(
         ..., description="The search query string to search for on the web"
     )
     max_results: Optional[int] = Field(
-        20,
+        MAX_SEARCH_RESULTS,
         description="Maximum number of search results to return (default: 20, max: 20)",
     )
+    search_engine: Optional[str] = Field(
+        DEFAULT_SEARCH_ENGINE,
+        description=(
+            "Search backend to use. Supported values: auto, duckduckgo, google, "
+            "brave, yahoo, wikipedia, yandex, mojeek. "
+            "Use auto unless the user asks for a specific search engine."
+        ),
+    )
+    site_url: Optional[str] = Field(
+        None,
+        description=(
+            "Optional website/domain/URL to limit the search to, for example "
+            "'https://docs.python.org/3/' or 'github.com'."
+        ),
+    )
 
 
 class SearchWebTool(MoviePilotTool):
+    """
+    网络搜索工具，支持 DDGS 搜索引擎和指定站点限定搜索。
+    """
+
     name: str = "search_web"
-    description: str = "Search the web for information when you need to find current information, facts, or references that you're uncertain about. Returns search results with titles, snippets, and URLs. Use this tool to get up-to-date information from the internet."
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Web,
+    ]
+    description: str = (
+        "Search the web for information when you need current information, facts, "
+        "or references. Supports DDGS-backed search engine selection, automatic "
+        "fallback, and site_url-limited searches for a specified website "
+        "or URL. Uses the configured system proxy by default. Returns search "
+        "results with titles, snippets, and URLs."
+    )
     args_schema: Type[BaseModel] = SearchWebInput
 
     def get_tool_message(self, **kwargs) -> Optional[str]:
         """根据搜索参数生成友好的提示消息"""
         query = kwargs.get("query", "")
-        max_results = kwargs.get("max_results", 20)
-        return f"搜索网络内容: {query} (最多返回 {max_results} 条结果)"
+        max_results = kwargs.get("max_results", MAX_SEARCH_RESULTS)
+        search_engine = self._normalize_search_engine(kwargs.get("search_engine"))
+        site_url = kwargs.get("site_url")
+        message = f"搜索网络内容: {query} (最多返回 {max_results} 条结果"
+        if search_engine != DEFAULT_SEARCH_ENGINE:
+            message += f"，搜索源: {search_engine}"
+        if site_url:
+            message += f"，限定站点: {site_url}"
+        return f"{message})"
 
-    async def run(self, query: str, max_results: Optional[int] = 20, **kwargs) -> str:
+    async def run(
+        self,
+        query: str,
+        max_results: Optional[int] = MAX_SEARCH_RESULTS,
+        search_engine: Optional[str] = DEFAULT_SEARCH_ENGINE,
+        site_url: Optional[str] = None,
+        **kwargs,
+    ) -> str:
         """
-        执行网络搜索
+        执行网络搜索。
+
+        :param query: 搜索关键词
+        :param max_results: 最大返回结果数
+        :param search_engine: 指定搜索源，默认自动选择
+        :param site_url: 指定站点或网址，传入时只返回该范围内的搜索结果
+        :return: JSON格式的搜索结果或错误信息
         """
+        search_engine = self._normalize_search_engine(search_engine)
+        if search_engine not in SUPPORTED_SEARCH_ENGINES:
+            supported = ", ".join(SUPPORTED_SEARCH_ENGINES)
+            return f"错误: 不支持的搜索源 '{search_engine}'，支持的搜索源: {supported}"
+
+        site_filter = self._normalize_site_filter(site_url)
+        if site_url and not site_filter:
+            return f"错误: site_url 无效，无法限定搜索范围: {site_url}"
+
+        search_query = self._build_search_query(query=query, site_filter=site_filter)
+        if not search_query:
+            return "错误: query 不能为空"
+
         logger.info(
-            f"执行工具: {self.name}, 参数: query={query}, max_results={max_results}"
+            f"执行工具: {self.name}, 参数: query={query}, "
+            f"max_results={max_results}, search_engine={search_engine}, site_url={site_url}"
         )
 
         try:
             # 限制最大结果数
-            max_results = min(max(1, max_results or 20), 20)
-            results = []
+            max_results = min(
+                max(1, max_results or MAX_SEARCH_RESULTS),
+                MAX_SEARCH_RESULTS,
+            )
+            results: List[Dict] = []
 
-            # 1. 优先使用 Exa (如果配置了 API Key)
-            if settings.EXA_API_KEY:
-                logger.info("使用 Exa 进行搜索...")
-                results = await self._search_exa(query, max_results)
-
-            # 2. 如果没有结果或未配置 Exa，使用 Tavily (如果配置了 API Key)
-            if not results and settings.TAVILY_API_KEY:
-                logger.info("使用 Tavily 进行搜索...")
-                results = await self._search_tavily(query, max_results)
-
-            # 3. 如果没有结果或未配置 Tavily，使用 DuckDuckGo
-            if not results:
-                logger.info("使用 DuckDuckGo 进行搜索...")
-                results = await self._search_duckduckgo(query, max_results)
+            for engine in self._get_search_plan(search_engine):
+                results = await self._search_with_backend(
+                    engine=engine,
+                    query=search_query,
+                    max_results=max_results,
+                    site_filter=site_filter,
+                )
+                if results:
+                    break
 
             if not results:
-                return f"未找到与 '{query}' 相关的搜索结果"
+                return f"未找到与 '{search_query}' 相关的搜索结果"
 
             # 格式化并裁剪结果
             formatted_results = self._format_and_truncate_results(results, max_results)
@@ -82,81 +174,214 @@ class SearchWebTool(MoviePilotTool):
             return error_message
 
     @staticmethod
-    async def _search_tavily(query: str, max_results: int) -> List[Dict]:
-        """使用 Tavily API 进行搜索"""
-        try:
-            async with httpx.AsyncClient(timeout=SEARCH_TIMEOUT) as client:
-                # 从设置中随机选择一个 API Key（如果有多个）
-                tavity_api_key = random.choice(settings.TAVILY_API_KEY)
-                response = await client.post(
-                    "https://api.tavily.com/search",
-                    json={
-                        "api_key": tavity_api_key,
-                        "query": query,
-                        "search_depth": "basic",
-                        "max_results": max_results,
-                        "include_answer": False,
-                        "include_images": False,
-                        "include_raw_content": False,
-                    },
-                )
-                response.raise_for_status()
-                data = response.json()
-
-                results = []
-                for result in data.get("results", []):
-                    results.append(
-                        {
-                            "title": result.get("title", ""),
-                            "snippet": result.get("content", ""),
-                            "url": result.get("url", ""),
-                            "source": "Tavily",
-                        }
-                    )
-                return results
-        except Exception as e:
-            logger.warning(f"Tavily 搜索失败: {e}")
-            return []
+    def _normalize_search_engine(search_engine: Optional[str]) -> str:
+        """规范化搜索源参数"""
+        engine = (search_engine or DEFAULT_SEARCH_ENGINE).strip().lower()
+        aliases = {
+            "ddgs": DEFAULT_SEARCH_ENGINE,
+            "ddg": "duckduckgo",
+            "duck": "duckduckgo",
+            "search": DEFAULT_SEARCH_ENGINE,
+            "search_engine": DEFAULT_SEARCH_ENGINE,
+        }
+        return aliases.get(engine, engine)
 
     @staticmethod
-    async def _search_exa(query: str, max_results: int) -> List[Dict]:
-        """使用 Exa API 进行搜索"""
-        try:
-            async with httpx.AsyncClient(timeout=SEARCH_TIMEOUT) as client:
-                response = await client.post(
-                    "https://api.exa.ai/search",
-                    headers={
-                        "x-api-key": settings.EXA_API_KEY,
-                        "Content-Type": "application/json",
-                    },
-                    json={
-                        "query": query,
-                        "numResults": max_results,
-                        "type": "auto",
-                        "contents": {"highlights": {"maxCharacters": 2000}},
-                    },
-                )
-                response.raise_for_status()
-                data = response.json()
+    def _get_search_plan(search_engine: str) -> List[str]:
+        """根据搜索源配置生成兜底搜索顺序"""
+        if search_engine != DEFAULT_SEARCH_ENGINE:
+            return [search_engine]
+        return [DEFAULT_SEARCH_ENGINE]
 
-                results = []
-                for result in data.get("results", []):
-                    highlights = result.get("highlights", [])
-                    snippet = (
-                        highlights[0] if highlights else result.get("text", "")[:500]
-                    )
-                    results.append(
-                        {
-                            "title": result.get("title", ""),
-                            "snippet": snippet,
-                            "url": result.get("url", ""),
-                            "source": "Exa",
-                        }
-                    )
-                return results
-        except Exception as e:
-            logger.warning(f"Exa 搜索失败: {e}")
-            return []
+    async def _search_with_backend(
+        self,
+        engine: str,
+        query: str,
+        max_results: int,
+        site_filter: Optional[_SearchSiteFilter],
+    ) -> List[Dict]:
+        """
+        使用指定后端执行搜索。
+
+        :param engine: 搜索后端名称
+        :param query: 已加工的搜索关键词
+        :param max_results: 最大结果数
+        :param site_filter: 站点限定条件
+        :return: 搜索结果列表
+        """
+        logger.info(f"使用 DDGS 搜索后端 {self._get_ddgs_backend(engine)} 进行搜索...")
+        return await self._search_ddgs(query, max_results, engine, site_filter)
+
+    @staticmethod
+    def _get_ddgs_backend(search_engine: str) -> str:
+        """
+        获取实际传给 DDGS 的搜索后端。
+
+        :param search_engine: 用户指定的搜索源
+        :return: DDGS 后端名称或逗号分隔的后端列表
+        """
+        if search_engine == DEFAULT_SEARCH_ENGINE:
+            return DDGS_AUTO_BACKEND
+        return search_engine
+
+    @staticmethod
+    def _normalize_site_filter(site_url: Optional[str]) -> Optional[_SearchSiteFilter]:
+        """
+        将用户传入的网址转换为搜索引擎 site 过滤条件。
+
+        :param site_url: 用户传入的站点、域名或完整URL
+        :return: 站点过滤条件，无法解析时返回 None
+        """
+        if not site_url:
+            return None
+
+        raw_site_url = site_url.strip()
+        if not raw_site_url:
+            return None
+
+        parse_target = raw_site_url
+        if not re.match(r"^https?://", raw_site_url, re.IGNORECASE):
+            parse_target = f"https://{raw_site_url}"
+
+        parsed = urlparse(parse_target)
+        domain = (parsed.hostname or "").lower()
+        if not domain:
+            return None
+
+        path = re.sub(r"/+", "/", parsed.path or "").rstrip("/")
+        search_target = f"{domain}{path}" if path else domain
+        return _SearchSiteFilter(domain=domain, path=path, search_target=search_target)
+
+    @staticmethod
+    def _build_search_query(
+        query: str,
+        site_filter: Optional[_SearchSiteFilter],
+    ) -> str:
+        """
+        生成实际发送给搜索后端的搜索关键词。
+
+        :param query: 原始搜索关键词
+        :param site_filter: 站点限定条件
+        :return: 加入 site 过滤后的关键词
+        """
+        search_query = (query or "").strip()
+        if not site_filter or SITE_SEARCH_PATTERN.search(search_query):
+            return search_query
+        if not search_query:
+            return f"site:{site_filter.search_target}"
+        return f"{search_query} site:{site_filter.search_target}"
+
+    @staticmethod
+    def _filter_results_by_site(
+        results: List[Dict],
+        site_filter: Optional[_SearchSiteFilter],
+    ) -> List[Dict]:
+        """
+        根据指定站点过滤搜索结果。
+
+        :param results: 原始搜索结果
+        :param site_filter: 站点限定条件
+        :return: 站点范围内的搜索结果
+        """
+        if not site_filter:
+            return results
+        return [
+            result
+            for result in results
+            if SearchWebTool._result_matches_site(result.get("url", ""), site_filter)
+        ]
+
+    @staticmethod
+    def _result_matches_site(url: str, site_filter: _SearchSiteFilter) -> bool:
+        """
+        判断搜索结果 URL 是否属于指定站点。
+
+        :param url: 搜索结果 URL
+        :param site_filter: 站点限定条件
+        :return: URL 属于指定站点时返回 True
+        """
+        if not url:
+            return False
+
+        parse_target = url
+        if not re.match(r"^https?://", url, re.IGNORECASE):
+            parse_target = f"https://{url}"
+
+        parsed = urlparse(parse_target)
+        result_host = SearchWebTool._normalize_host(parsed.hostname or "")
+        target_host = SearchWebTool._normalize_host(site_filter.domain)
+        if not result_host or not target_host:
+            return False
+        if result_host != target_host and not result_host.endswith(f".{target_host}"):
+            return False
+        if not site_filter.path:
+            return True
+
+        result_path = re.sub(r"/+", "/", parsed.path or "").rstrip("/")
+        return result_path == site_filter.path or result_path.startswith(
+            f"{site_filter.path}/"
+        )
+
+    @staticmethod
+    def _normalize_host(host: str) -> str:
+        """
+        标准化域名以便比较。
+
+        :param host: 原始域名
+        :return: 去掉常见 www 前缀后的域名
+        """
+        normalized_host = (host or "").lower()
+        if normalized_host.startswith("www."):
+            return normalized_host[4:]
+        return normalized_host
+
+    @staticmethod
+    def _source_label(search_engine: str) -> str:
+        """
+        将搜索源标识转换为结果中的展示名称。
+
+        :param search_engine: 搜索源标识
+        :return: 展示名称
+        """
+        labels = {
+            "auto": "DDGS",
+            "duckduckgo": "DuckDuckGo",
+            "google": "Google",
+            "brave": "Brave",
+            "yahoo": "Yahoo",
+            "wikipedia": "Wikipedia",
+            "yandex": "Yandex",
+            "mojeek": "Mojeek",
+        }
+        return labels.get(
+            search_engine or DEFAULT_SEARCH_ENGINE,
+            search_engine or "SearchEngine",
+        )
+
+    @staticmethod
+    def _extract_result_url(result: Dict) -> str:
+        """
+        从不同搜索引擎结果结构中提取 URL。
+
+        :param result: 搜索引擎返回的单条结果
+        :return: URL 字符串
+        """
+        return result.get("href") or result.get("url") or ""
+
+    @staticmethod
+    def _extract_result_snippet(result: Dict) -> str:
+        """
+        从不同搜索引擎结果结构中提取摘要。
+
+        :param result: 搜索引擎返回的单条结果
+        :return: 摘要字符串
+        """
+        return (
+            result.get("body")
+            or result.get("snippet")
+            or result.get("content")
+            or ""
+        )
 
     @staticmethod
     def _get_proxy_url(proxy_setting) -> Optional[str]:
@@ -167,11 +392,26 @@ class SearchWebTool(MoviePilotTool):
             return proxy_setting.get("http") or proxy_setting.get("https")
         return proxy_setting
 
-    async def _search_duckduckgo(self, query: str, max_results: int) -> List[Dict]:
-        """使用 duckduckgo-search (DDGS) 进行搜索"""
+    async def _search_ddgs(
+        self,
+        query: str,
+        max_results: int,
+        search_engine: str = DEFAULT_SEARCH_ENGINE,
+        site_filter: Optional[_SearchSiteFilter] = None,
+    ) -> List[Dict]:
+        """
+        使用 DDGS 搜索引擎后端进行搜索。
+
+        :param query: 搜索关键词
+        :param max_results: 最大结果数
+        :param search_engine: DDGS搜索后端
+        :param site_filter: 站点限定条件
+        :return: 搜索结果列表
+        """
         try:
 
             def sync_search():
+                """在线程中执行同步搜索"""
                 results = []
                 ddgs_kwargs = {"timeout": SEARCH_TIMEOUT}
                 proxy_url = self._get_proxy_url(settings.PROXY)
@@ -180,26 +420,35 @@ class SearchWebTool(MoviePilotTool):
 
                 try:
                     with DDGS(**ddgs_kwargs) as ddgs:
-                        ddgs_gen = ddgs.text(query, max_results=max_results)
-                        if ddgs_gen:
-                            for result in ddgs_gen:
+                        ddgs_results = ddgs.text(
+                            query,
+                            max_results=max_results,
+                            backend=self._get_ddgs_backend(search_engine),
+                        )
+                        if ddgs_results:
+                            for result in ddgs_results:
+                                source = (
+                                    DEFAULT_SEARCH_ENGINE
+                                    if search_engine == DEFAULT_SEARCH_ENGINE
+                                    else search_engine
+                                )
                                 results.append(
                                     {
                                         "title": result.get("title", ""),
-                                        "snippet": result.get("body", ""),
-                                        "url": result.get("href", ""),
-                                        "source": "DuckDuckGo",
+                                        "snippet": self._extract_result_snippet(result),
+                                        "url": self._extract_result_url(result),
+                                        "source": self._source_label(source),
                                     }
                                 )
                 except Exception as err:
-                    logger.warning(f"DuckDuckGo search process failed: {err}")
+                    logger.warning(f"搜索引擎搜索进程失败: {err}")
                 return results
 
-            loop = asyncio.get_running_loop()
-            return await loop.run_in_executor(None, sync_search)
+            results = await self.run_blocking("web", sync_search)
+            return self._filter_results_by_site(results, site_filter)
 
         except Exception as e:
-            logger.warning(f"DuckDuckGo 搜索失败: {e}")
+            logger.warning(f"搜索引擎搜索失败: {e}")
             return []
 
     @staticmethod

app/agent/tools/impl/send_local_file.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field, model_validator
 
 from app.agent.tools.base import MoviePilotTool, ToolChain
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 from app.schemas import Notification, NotificationType
 from app.schemas.message import ChannelCapabilityManager, ChannelCapability
@@ -43,6 +44,11 @@ class SendLocalFileInput(BaseModel):
 
 class SendLocalFileTool(MoviePilotTool):
     name: str = "send_local_file"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Message,
+        ToolTag.File,
+    ]
     sends_message: bool = True
     description: str = (
         "Send a local image or file from the server filesystem to the current user. "

app/agent/tools/impl/send_message.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field, model_validator
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -35,6 +36,11 @@ class SendMessageInput(BaseModel):
 
 class SendMessageTool(MoviePilotTool):
     name: str = "send_message"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Message,
+        ToolTag.Admin,
+    ]
     sends_message: bool = True
     description: str = "Send notification message to the user through configured notification channels (Telegram, Slack, WeChat, etc.). Supports optional image_url on channels that can send images. Used to inform users about operation results, errors, important updates, or proactively send a relevant image."
     args_schema: Type[BaseModel] = SendMessageInput

app/agent/tools/impl/send_voice_message.py

@@ -1,12 +1,11 @@
 """发送语音消息工具。"""
-
-import asyncio
 from typing import Optional, Type
 
 from pydantic import BaseModel, Field
 
 from app.agent.llm.capability import AgentCapabilityManager
 from app.agent.tools.base import MoviePilotTool, ToolChain
+from app.agent.tools.tags import ToolTag
 from app.core.config import settings
 from app.log import logger
 from app.schemas import Notification, NotificationType
@@ -15,8 +14,10 @@ from app.schemas import Notification, NotificationType
 class SendVoiceMessageInput(BaseModel):
     """发送语音消息工具输入。"""
 
-    explanation: Optional[str] = Field(None,
-        description="Clear explanation of why a voice reply is the best fit in the current context",)
+    explanation: Optional[str] = Field(
+        None,
+        description="Clear explanation of why a voice reply is the best fit in the current context",
+    )
     message: str = Field(
         ...,
         description="The spoken content to send back to the user",
@@ -24,24 +25,36 @@ class SendVoiceMessageInput(BaseModel):
 
 
 class SendVoiceMessageTool(MoviePilotTool):
+    """发送 Agent 语音回复的工具。"""
+
     name: str = "send_voice_message"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Message,
+        ToolTag.TerminalResponse,
+    ]
     sends_message: bool = True
+    return_direct: bool = True
     description: str = (
         "Send a voice reply to the current user. Use this only when the user explicitly asks for "
         "a voice reply or when spoken playback is clearly better than plain text. On channels "
         "without voice support or when TTS is unavailable, it automatically falls back to sending "
-        "the same content as plain text."
+        "the same content as plain text. This is a terminal response tool: put the complete "
+        "user-facing reply in `message`; after this tool runs, do not send another text reply "
+        "or call `send_message` with the same content."
     )
     args_schema: Type[BaseModel] = SendVoiceMessageInput
     require_admin: bool = False
 
     def get_tool_message(self, **kwargs) -> Optional[str]:
+        """生成语音回复工具的执行提示。"""
         message = kwargs.get("message") or ""
         if len(message) > 40:
             message = message[:40] + "..."
         return f"发送语音回复: {message}"
 
     async def run(self, message: str, **kwargs) -> str:
+        """合成语音并发送到当前对话渠道，不支持时回退为文字。"""
         if not message:
             return "语音回复内容不能为空"
 
@@ -59,7 +72,8 @@ class SendVoiceMessageTool(MoviePilotTool):
             reply_mode == AgentCapabilityManager.REPLY_MODE_NATIVE
             and AgentCapabilityManager.is_audio_output_available()
         ):
-            voice_file = await asyncio.to_thread(
+            voice_file = await self.run_blocking(
+                "default",
                 AgentCapabilityManager.synthesize_speech, message
             )
             if voice_file:
@@ -69,11 +83,8 @@ class SendVoiceMessageTool(MoviePilotTool):
             fallback_reason = "当前未配置可用的语音合成能力"
 
         logger.info(
-            "执行工具: %s, channel=%s, use_voice=%s, text_len=%s",
-            self.name,
-            channel,
-            used_voice,
-            len(message),
+            f"执行工具: {self.name}, channel={channel}, "
+            f"use_voice={used_voice}, text_len={len(message)}"
         )
 
         await ToolChain().async_post_message(

app/agent/tools/impl/switch_persona.py

@@ -7,6 +7,7 @@ from pydantic import BaseModel, Field
 
 from app.agent.runtime import agent_runtime_manager
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -26,6 +27,10 @@ class SwitchPersonaInput(BaseModel):
 
 class SwitchPersonaTool(MoviePilotTool):
     name: str = "switch_persona"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Persona,
+    ]
     description: str = (
         "Switch the active persona (人格) used by the agent runtime. "
         "This change is persistent for future turns. "

app/agent/tools/impl/test_site.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.site import SiteChain
 from app.db.site_oper import SiteOper
 from app.log import logger
@@ -18,6 +19,10 @@ class TestSiteInput(BaseModel):
 
 class TestSiteTool(MoviePilotTool):
     name: str = "test_site"
+    tags: list[str] = [
+        ToolTag.Read,
+        ToolTag.Site,
+    ]
     description: str = "Test site connectivity and availability. This will check if a site is accessible and can be logged in. Accepts site ID only."
     args_schema: Type[BaseModel] = TestSiteInput
 

app/agent/tools/impl/transfer_file.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 from app.schemas import FileItem, MediaType
 
@@ -54,6 +55,13 @@ class TransferFileInput(BaseModel):
 
 class TransferFileTool(MoviePilotTool):
     name: str = "transfer_file"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Transfer,
+        ToolTag.Library,
+        ToolTag.File,
+        ToolTag.Admin,
+    ]
     description: str = "Transfer/organize a file or directory to the media library. Automatically recognizes media information and organizes files according to configured rules. Supports custom target paths, media identification, and transfer modes."
     args_schema: Type[BaseModel] = TransferFileInput
     require_admin: bool = True

app/agent/tools/impl/uninstall_plugin.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import (
     list_installed_plugins,
     summarize_plugin,
@@ -27,6 +28,11 @@ class UninstallPluginInput(BaseModel):
 
 class UninstallPluginTool(MoviePilotTool):
     name: str = "uninstall_plugin"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Uninstall an installed plugin by exact plugin_id. "
         "Use query_installed_plugins first when you need filtering or discovery."

app/agent/tools/impl/update_custom_filter_rule.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     collect_custom_rule_group_refs,
     get_custom_rules,
@@ -58,6 +59,11 @@ class UpdateCustomFilterRuleInput(BaseModel):
 
 class UpdateCustomFilterRuleTool(MoviePilotTool):
     name: str = "update_custom_filter_rule"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Update an existing custom filter rule. "
         "If the rule ID is renamed, all rule groups that reference the old ID are updated automatically."

app/agent/tools/impl/update_custom_identifiers.py

@@ -6,6 +6,7 @@ from typing import List, Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.db.systemconfig_oper import SystemConfigOper
 from app.log import logger
 from app.schemas.types import SystemConfigKey
@@ -33,6 +34,11 @@ class UpdateCustomIdentifiersInput(BaseModel):
 
 class UpdateCustomIdentifiersTool(MoviePilotTool):
     name: str = "update_custom_identifiers"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Update the full list of custom identifiers (自定义识别词) used for preprocessing torrent/file names. "
         "This tool REPLACES all existing identifier rules with the provided list. "

app/agent/tools/impl/update_persona_definition.py

@@ -7,6 +7,7 @@ from pydantic import BaseModel, Field
 
 from app.agent.runtime import agent_runtime_manager
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -56,6 +57,11 @@ class UpdatePersonaDefinitionInput(BaseModel):
 
 class UpdatePersonaDefinitionTool(MoviePilotTool):
     name: str = "update_persona_definition"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Persona,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Create or update a runtime persona definition (人格定义) without manually editing PERSONA.md files. "
         "Use this when the user explicitly asks to modify how a persona is defined, such as changing tone rules, "

app/agent/tools/impl/update_plugin_config.py

@@ -6,6 +6,7 @@ from typing import Any, Dict, List, Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._plugin_tool_utils import get_plugin_snapshot
 from app.core.plugin import PluginManager
 from app.log import logger
@@ -42,6 +43,11 @@ class UpdatePluginConfigInput(BaseModel):
 
 class UpdatePluginConfigTool(MoviePilotTool):
     name: str = "update_plugin_config"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Plugin,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Update the saved configuration of an installed plugin. "
         "By default this performs a partial merge update and does NOT reload the plugin automatically. "

app/agent/tools/impl/update_rule_group.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._filter_rule_utils import (
     build_custom_rule_map,
     collect_rule_group_usages,
@@ -50,6 +51,11 @@ class UpdateRuleGroupInput(BaseModel):
 
 class UpdateRuleGroupTool(MoviePilotTool):
     name: str = "update_rule_group"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.FilterRule,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Update a filter rule group. "
         "If the rule group name changes, its references in global search/subscription settings and per-subscription bindings are updated automatically. "

app/agent/tools/impl/update_site.py

@@ -6,6 +6,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.event import eventmanager
 from app.db import AsyncSessionFactory
 from app.db.models.site import Site
@@ -66,6 +67,11 @@ class UpdateSiteInput(BaseModel):
 
 class UpdateSiteTool(MoviePilotTool):
     name: str = "update_site"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Site,
+        ToolTag.Admin,
+    ]
     description: str = "Update site configuration including URL, priority, authentication credentials (cookie, UA, API key), proxy settings, rate limits, and other site properties. Supports updating multiple site attributes at once. Site priority (pri): smaller values have higher priority (e.g., pri=1 has higher priority than pri=10)."
     args_schema: Type[BaseModel] = UpdateSiteInput
     require_admin: bool = True

app/agent/tools/impl/update_site_cookie.py

@@ -5,6 +5,7 @@ from typing import Optional, Type
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.chain.site import SiteChain
 from app.db.site_oper import SiteOper
 from app.log import logger
@@ -29,6 +30,11 @@ class UpdateSiteCookieInput(BaseModel):
 
 class UpdateSiteCookieTool(MoviePilotTool):
     name: str = "update_site_cookie"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Site,
+        ToolTag.Admin,
+    ]
     description: str = "Update site Cookie and User-Agent by logging in with username and password. This tool can automatically obtain and update the site's authentication credentials. Supports two-step verification for sites that require it. Accepts site ID only."
     args_schema: Type[BaseModel] = UpdateSiteCookieInput
     require_admin: bool = True

app/agent/tools/impl/update_subscribe.py

@@ -6,6 +6,7 @@ from typing import Optional, Type, List
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.core.event import eventmanager
 from app.db import AsyncSessionFactory
 from app.db.models.subscribe import Subscribe
@@ -89,6 +90,11 @@ class UpdateSubscribeInput(BaseModel):
 
 class UpdateSubscribeTool(MoviePilotTool):
     name: str = "update_subscribe"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.Subscription,
+        ToolTag.Admin,
+    ]
     description: str = "Update subscription properties including filters, episode counts, state, and other settings. Supports updating quality/resolution filters, episode tracking, subscription state, and download configuration."
     args_schema: Type[BaseModel] = UpdateSubscribeInput
     require_admin: bool = True

app/agent/tools/impl/update_system_settings.py

@@ -7,6 +7,7 @@ from typing import Any, Literal, Optional, Type, Union
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.agent.tools.impl._system_setting_utils import (
     SettingSpec,
     get_default_list_match_field,
@@ -73,6 +74,12 @@ class UpdateSystemSettingsInput(BaseModel):
 
 class UpdateSystemSettingsTool(MoviePilotTool):
     name: str = "update_system_settings"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.System,
+        ToolTag.Settings,
+        ToolTag.Admin,
+    ]
     description: str = (
         "Update system settings across both the basic Settings module and all SystemConfig-backed categories. "
         "Supports full replacement, shallow dict merge, and generic list item upsert/remove so the agent can manage downloaders, media servers, notification channels, storages, directories, search-site ranges, subscribe-site ranges, site auth params, AI agent config, and other system settings through one tool."

app/agent/tools/impl/write_file.py

@@ -7,6 +7,7 @@ from anyio import Path as AsyncPath
 from pydantic import BaseModel, Field
 
 from app.agent.tools.base import MoviePilotTool
+from app.agent.tools.tags import ToolTag
 from app.log import logger
 
 
@@ -19,6 +20,11 @@ class WriteFileInput(BaseModel):
 
 class WriteFileTool(MoviePilotTool):
     name: str = "write_file"
+    tags: list[str] = [
+        ToolTag.Write,
+        ToolTag.File,
+        ToolTag.Admin,
+    ]
     description: str = "Write full content to a file. If the file already exists, it will be overwritten. Automatically creates parent directories if they don't exist."
     args_schema: Type[BaseModel] = WriteFileInput
     require_admin: bool = True

app/agent/tools/manager.py

@@ -2,7 +2,7 @@ import json
 import uuid
 from typing import Any, Dict, List, Optional
 
-from app.agent.tools.base import format_tool_result_for_agent
+from app.agent.tools.base import ToolExecutionTimeoutError, format_tool_result_for_agent
 from app.agent.tools.factory import MoviePilotToolFactory
 from app.log import logger
 
@@ -259,10 +259,14 @@ class MoviePilotToolsManager:
 
             # 调用工具的run方法。HTTP/MCP 工具调用不会经过 BaseTool._arun，
             # 因此这里也必须复用同一套返回值格式化和兜底截断逻辑。
-            result = await tool_instance.run(**normalized_arguments)
+            result = await tool_instance.run_with_timeout(**normalized_arguments)
             
             # 记录工具执行结果摘要日志
-            str_result = format_tool_result_for_agent(result, tool_name=tool_name, max_chars=getattr(tool_instance, "result_max_chars", None))
+            str_result = format_tool_result_for_agent(
+                result,
+                tool_name=tool_name,
+                max_chars=getattr(tool_instance, "result_max_chars", None),
+            )
             if len(str_result) > 500:
                 summary = str_result[:500] + f"...(已截断，总长度: {len(str_result)})"
             else:
@@ -270,6 +274,13 @@ class MoviePilotToolsManager:
             logger.info(f"Agent工具 {tool_name} 执行完成，结果摘要: {summary}")
             
             return str_result
+        except ToolExecutionTimeoutError as e:
+            logger.warning(str(e))
+            return format_tool_result_for_agent(
+                str(e),
+                tool_name=tool_name,
+                max_chars=getattr(tool_instance, "result_max_chars", None),
+            )
         except Exception as e:
             logger.error(f"调用工具 {tool_name} 时发生错误: {e}", exc_info=True)
             error_msg = json.dumps(

app/agent/tools/tags.py

@@ -0,0 +1,39 @@
+"""Agent 工具标签定义。"""
+
+from enum import Enum
+
+
+class ToolTag(str, Enum):
+    """Agent 工具能力标签。"""
+
+    AgentTool = "agent_tool"
+    Read = "read"
+    Write = "write"
+    Admin = "admin"
+    Message = "message"
+    UserInteraction = "user_interaction"
+    TerminalResponse = "terminal_response"
+    Media = "media"
+    Resource = "resource"
+    Site = "site"
+    Subscription = "subscription"
+    Download = "download"
+    Library = "library"
+    Transfer = "transfer"
+    System = "system"
+    Settings = "settings"
+    Plugin = "plugin"
+    Workflow = "workflow"
+    Scheduler = "scheduler"
+    File = "file"
+    Directory = "directory"
+    Web = "web"
+    Command = "command"
+    FilterRule = "filter_rule"
+    Persona = "persona"
+    SlashCommand = "slash_command"
+    Recommendation = "recommendation"
+    Metadata = "metadata"
+
+
+__all__ = ["ToolTag"]

app/api/apiv1.py

@@ -1,10 +1,11 @@
 from fastapi import APIRouter
 
-from app.api.endpoints import login, user, webhook, message, site, subscribe, \
+from app.api.endpoints import auth, login, user, webhook, message, site, subscribe, \
     media, douban, search, plugin, tmdb, history, system, download, dashboard, \
     transfer, mediaserver, bangumi, storage, discover, recommend, workflow, torrent, mcp, mfa, openai, anthropic, llm, notification
 
 api_router = APIRouter()
+api_router.include_router(auth.router, prefix="/auth", tags=["auth"])
 api_router.include_router(login.router, prefix="/login", tags=["login"])
 api_router.include_router(user.router, prefix="/user", tags=["user"])
 api_router.include_router(mfa.router, prefix="/mfa", tags=["mfa"])