feat(agent): add voice message support with TTS/STT for Telegram and WeChat

- Integrate voice message handling: detect and extract audio references from Telegram and WeChat messages, route to agent with voice reply preference.
- Add voice provider abstraction and OpenAI-based TTS/STT implementation.
- Implement agent tool `send_voice_message` for generating and sending voice replies, with fallback to text if voice is unavailable.
- Extend agent prompt and context to support voice reply instructions.
- Update notification and message schemas to support audio fields.
- Add Telegram and WeChat voice sending logic, including audio file conversion and temporary media upload for WeChat.
- Add tests for voice helper and agent voice routing.

app/agent/tools/base.py

@@ -31,6 +31,7 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
     _username: Optional[str] = PrivateAttr(default=None)
     _stream_handler: Optional[StreamingHandler] = PrivateAttr(default=None)
     _require_admin: bool = PrivateAttr(default=False)
+    _agent_context: dict = PrivateAttr(default_factory=dict)
 
     def __init__(self, session_id: str, user_id: str, **kwargs):
         super().__init__(**kwargs)
@@ -142,6 +143,12 @@ class MoviePilotTool(BaseTool, metaclass=ABCMeta):
         """
         self._stream_handler = stream_handler
 
+    def set_agent_context(self, agent_context: Optional[dict]):
+        """
+        设置与当前 Agent 共享的上下文。
+        """
+        self._agent_context = agent_context or {}
+
     async def _check_permission(self) -> Optional[str]:
         """
         检查用户权限：

app/agent/tools/factory.py

@@ -30,6 +30,7 @@ from app.agent.tools.impl.search_torrents import SearchTorrentsTool
 from app.agent.tools.impl.get_search_results import GetSearchResultsTool
 from app.agent.tools.impl.search_web import SearchWebTool
 from app.agent.tools.impl.send_message import SendMessageTool
+from app.agent.tools.impl.send_voice_message import SendVoiceMessageTool
 from app.agent.tools.impl.query_schedulers import QuerySchedulersTool
 from app.agent.tools.impl.run_scheduler import RunSchedulerTool
 from app.agent.tools.impl.query_workflows import QueryWorkflowsTool
@@ -72,6 +73,7 @@ class MoviePilotToolFactory:
         source: str = None,
         username: str = None,
         stream_handler: Callable = None,
+        agent_context: dict = None,
     ) -> List[MoviePilotTool]:
         """
         创建MoviePilot工具列表
@@ -117,6 +119,7 @@ class MoviePilotToolFactory:
             QueryTransferHistoryTool,
             TransferFileTool,
             SendMessageTool,
+            SendVoiceMessageTool,
             QuerySchedulersTool,
             RunSchedulerTool,
             QueryWorkflowsTool,
@@ -138,6 +141,7 @@ class MoviePilotToolFactory:
             tool = ToolClass(session_id=session_id, user_id=user_id)
             tool.set_message_attr(channel=channel, source=source, username=username)
             tool.set_stream_handler(stream_handler=stream_handler)
+            tool.set_agent_context(agent_context=agent_context)
             tools.append(tool)
 
         # 加载插件提供的工具
@@ -161,6 +165,7 @@ class MoviePilotToolFactory:
                         channel=channel, source=source, username=username
                     )
                     tool.set_stream_handler(stream_handler=stream_handler)
+                    tool.set_agent_context(agent_context=agent_context)
                     tools.append(tool)
                     plugin_tools_count += 1
                     logger.debug(

app/agent/tools/impl/send_voice_message.py

@@ -0,0 +1,96 @@
+"""发送语音消息工具。"""
+
+import asyncio
+from typing import Optional, Type
+
+from pydantic import BaseModel, Field
+
+from app.agent.tools.base import MoviePilotTool, ToolChain
+from app.core.config import settings
+from app.helper.voice import VoiceHelper
+from app.helper.service import ServiceConfigHelper
+from app.log import logger
+from app.schemas import Notification, NotificationType
+from app.schemas.types import MessageChannel
+
+
+class SendVoiceMessageInput(BaseModel):
+    """发送语音消息工具输入。"""
+
+    explanation: str = Field(
+        ...,
+        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",
+    )
+
+
+class SendVoiceMessageTool(MoviePilotTool):
+    name: str = "send_voice_message"
+    description: str = (
+        "Send a voice reply to the current user. Prefer this when the user sent a voice message "
+        "or when spoken playback is more natural. On channels without voice support or when TTS "
+        "is unavailable, it automatically falls back to sending the same content as plain text."
+    )
+    args_schema: Type[BaseModel] = SendVoiceMessageInput
+    require_admin: bool = False
+
+    def get_tool_message(self, **kwargs) -> Optional[str]:
+        message = kwargs.get("message") or ""
+        if len(message) > 40:
+            message = message[:40] + "..."
+        return f"正在发送语音回复: {message}"
+
+    def _supports_real_voice_reply(self) -> bool:
+        channel = self._channel or ""
+        if channel == MessageChannel.Telegram.value:
+            return True
+        if channel != MessageChannel.Wechat.value:
+            return False
+        for config in ServiceConfigHelper.get_notification_configs():
+            if config.name != self._source:
+                continue
+            return (config.config or {}).get("WECHAT_MODE", "app") != "bot"
+        return False
+
+    async def run(self, message: str, **kwargs) -> str:
+        if not message:
+            return "语音回复内容不能为空"
+
+        voice_path = None
+        used_voice = False
+        channel = self._channel or ""
+        if self._supports_real_voice_reply() and VoiceHelper.is_available("tts"):
+            voice_file = await asyncio.to_thread(VoiceHelper.synthesize_speech, message)
+            if voice_file:
+                voice_path = str(voice_file)
+                used_voice = True
+
+        logger.info(
+            "执行工具: %s, channel=%s, use_voice=%s, text_len=%s",
+            self.name,
+            channel,
+            used_voice,
+            len(message),
+        )
+
+        await ToolChain().async_post_message(
+            Notification(
+                channel=self._channel,
+                source=self._source,
+                mtype=NotificationType.Agent,
+                userid=self._user_id,
+                username=self._username,
+                text=message,
+                voice_path=voice_path,
+                voice_caption=message if settings.AI_VOICE_REPLY_WITH_TEXT else None,
+            )
+        )
+        self._agent_context["user_reply_sent"] = True
+        self._agent_context["reply_mode"] = "voice" if used_voice else "text_fallback"
+
+        if used_voice:
+            return "语音回复已发送"
+        return "当前未使用语音通道，已自动回退为文字回复"