feat(agent): add audio message extraction and download support for Slack, QQ, Discord, SynologyChat, and VoceChat

app/modules/vocechat/__init__.py

@@ -21,6 +21,20 @@ class VoceChatModule(_ModuleBase, _MessageBase[VoceChat]):
         ".tiff",
         ".svg",
     )
+    _AUDIO_SUFFIXES = (
+        ".mp3",
+        ".m4a",
+        ".wav",
+        ".ogg",
+        ".oga",
+        ".opus",
+        ".aac",
+        ".amr",
+        ".flac",
+        ".mpga",
+        ".mpeg",
+        ".webm",
+    )
 
     def init_module(self) -> None:
         """
@@ -118,6 +132,7 @@ class VoceChatModule(_ModuleBase, _MessageBase[VoceChat]):
             content_type = detail.get("content_type") or ""
             content = detail.get("content")
             images = self._extract_images(detail)
+            audio_refs = self._extract_audio_refs(detail)
             text = None
             if content_type in ("text/plain", "text/markdown") and isinstance(content, str):
                 text = content
@@ -132,14 +147,15 @@ class VoceChatModule(_ModuleBase, _MessageBase[VoceChat]):
                 userid = f"UID#{msg_body.get('from_uid')}"
 
             # 处理消息内容
-            if (text or images) and userid:
+            if (text or images or audio_refs) and userid:
                 logger.info(
                     f"收到来自 {client_config.name} 的VoceChat消息："
-                    f"userid={userid}, text={text}, images={len(images) if images else 0}"
+                    f"userid={userid}, text={text}, images={len(images) if images else 0}, "
+                    f"audios={len(audio_refs) if audio_refs else 0}"
                 )
                 return CommingMessage(channel=MessageChannel.VoceChat, source=client_config.name,
                                       userid=userid, username=userid, text=text or "",
-                                      images=images)
+                                      images=images, audio_refs=audio_refs)
         except Exception as err:
             logger.error(f"VoceChat消息处理发生错误：{str(err)}")
         return None
@@ -182,6 +198,37 @@ class VoceChatModule(_ModuleBase, _MessageBase[VoceChat]):
             return [f"vocechat://file/{quote(file_path, safe='')}"]
         return None
 
+    @classmethod
+    def _extract_audio_refs(cls, detail: dict) -> Optional[List[str]]:
+        content_type = detail.get("content_type") or ""
+        if content_type != "vocechat/file":
+            return None
+        properties = detail.get("properties") or {}
+        mime_type = (
+            properties.get("content_type")
+            or properties.get("mime_type")
+            or properties.get("contentType")
+            or ""
+        ).lower()
+        file_path = (
+            properties.get("path")
+            or properties.get("file_path")
+            or properties.get("storage_path")
+            or detail.get("content")
+        )
+        file_name = (
+            properties.get("name")
+            or properties.get("filename")
+            or (str(file_path).rsplit("/", 1)[-1] if file_path else "")
+        ).lower()
+
+        is_audio = mime_type.startswith("audio/") or file_name.endswith(cls._AUDIO_SUFFIXES)
+        if not is_audio:
+            return None
+        if isinstance(file_path, str) and file_path:
+            return [f"vocechat://file/{quote(file_path, safe='')}"]
+        return None
+
     def post_message(self, message: Notification, **kwargs) -> None:
         """
         发送消息
@@ -255,3 +302,22 @@ class VoceChatModule(_ModuleBase, _MessageBase[VoceChat]):
             return None
         file_path = unquote(image_ref.replace("vocechat://file/", "", 1))
         return client.download_file_to_data_url(file_path)
+
+    def download_vocechat_file_bytes(self, file_ref: str, source: str) -> Optional[bytes]:
+        """
+        下载 VoceChat 文件并返回原始字节
+        """
+        if not file_ref or not file_ref.startswith("vocechat://file/"):
+            return None
+        client_config = self.get_config(source)
+        if not client_config:
+            return None
+        client: VoceChat = self.get_instance(client_config.name)
+        if not client:
+            return None
+        file_path = unquote(file_ref.replace("vocechat://file/", "", 1))
+        file_data = client.download_file(file_path)
+        if file_data:
+            content, _ = file_data
+            return content
+        return None