feat: 企业微信应用支持主动消息推送，并优化企微应用、微信公众号、微信客服音频相关的处理 (#4998)

2026-07-15 17:30:13 +08:00 · 2026-02-09 22:15:11 +08:00
parent 67b81c279b
commit 04faf26140
5 changed files with 206 additions and 87 deletions
--- a/astrbot/core/platform/sources/wecom/wecom_adapter.py
+++ b/astrbot/core/platform/sources/wecom/wecom_adapter.py
@@ -26,6 +26,7 @@ from astrbot.api.platform import (
 from astrbot.core import logger
 from astrbot.core.platform.astr_message_event import MessageSesion
 from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+from astrbot.core.utils.media_utils import convert_audio_to_wav
 from astrbot.core.utils.webhook_utils import log_webhook_info

 from .wecom_event import WecomPlatformEvent
@@ -165,6 +166,7 @@ class WecomPlatformAdapter(Platform):
            self.api_base_url += "/"

        self.server = WecomServer(self._event_queue, self.config)
+        self.agent_id: str | None = None

        self.client = WeChatClient(
            self.config["corpid"].strip(),
@@ -215,6 +217,36 @@ class WecomPlatformAdapter(Platform):
        session: MessageSesion,
        message_chain: MessageChain,
    ) -> None:
+        # 企业微信客服不支持主动发送
+        if hasattr(self.client, "kf_message"):
+            logger.warning("企业微信客服模式不支持 send_by_session 主动发送。")
+            await super().send_by_session(session, message_chain)
+            return
+        if not self.agent_id:
+            logger.warning(
+                f"send_by_session 失败：无法为会话 {session.session_id} 推断 agent_id。",
+            )
+            await super().send_by_session(session, message_chain)
+            return
+
+        message_obj = AstrBotMessage()
+        message_obj.self_id = self.agent_id
+        message_obj.session_id = session.session_id
+        message_obj.type = session.message_type
+        message_obj.sender = MessageMember(session.session_id, session.session_id)
+        message_obj.message = []
+        message_obj.message_str = ""
+        message_obj.message_id = uuid.uuid4().hex
+        message_obj.raw_message = {"_proactive_send": True}
+
+        event = WecomPlatformEvent(
+            message_str=message_obj.message_str,
+            message_obj=message_obj,
+            platform_meta=self.meta(),
+            session_id=message_obj.session_id,
+            client=self.client,
+        )
+        await event.send(message_chain)
        await super().send_by_session(session, message_chain)

    @override
@@ -318,11 +350,8 @@ class WecomPlatformAdapter(Platform):
                f.write(resp.content)

            try:
-                from pydub import AudioSegment
-
                path_wav = os.path.join(temp_dir, f"wecom_{msg.media_id}.wav")
-                audio = AudioSegment.from_file(path)
-                audio.export(path_wav, format="wav")
+                path_wav = await convert_audio_to_wav(path, path_wav)
            except Exception as e:
                logger.error(f"转换音频失败: {e}。如果没有安装 ffmpeg 请先安装。")
                path_wav = path
@@ -344,6 +373,7 @@ class WecomPlatformAdapter(Platform):
            logger.warning(f"暂未实现的事件: {msg.type}")
            return

+        self.agent_id = abm.self_id
        logger.info(f"abm: {abm}")
        await self.handle_msg(abm)

@@ -388,11 +418,8 @@ class WecomPlatformAdapter(Platform):
                f.write(resp.content)

            try:
-                from pydub import AudioSegment
-
                path_wav = os.path.join(temp_dir, f"weixinkefu_{media_id}.wav")
-                audio = AudioSegment.from_file(path)
-                audio.export(path_wav, format="wav")
+                path_wav = await convert_audio_to_wav(path, path_wav)
            except Exception as e:
                logger.error(f"转换音频失败: {e}。如果没有安装 ffmpeg 请先安装。")
                path_wav = path
--- a/astrbot/core/platform/sources/wecom/wecom_event.py
+++ b/astrbot/core/platform/sources/wecom/wecom_event.py
@@ -1,24 +1,16 @@
 import asyncio
 import os
-import uuid

 from wechatpy.enterprise import WeChatClient

 from astrbot.api import logger
 from astrbot.api.event import AstrMessageEvent, MessageChain
-from astrbot.api.message_components import Image, Plain, Record
+from astrbot.api.message_components import File, Image, Plain, Record, Video
 from astrbot.api.platform import AstrBotMessage, PlatformMetadata
-from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+from astrbot.core.utils.media_utils import convert_audio_to_amr

 from .wecom_kf_message import WeChatKFMessage

-try:
-    import pydub
-except Exception:
-    logger.warning(
-        "检测到 pydub 库未安装，企业微信将无法语音收发。如需使用语音，请前往管理面板 -> 平台日志 -> 安装 Pip 库安装 pydub。",
-    )
-

 class WecomPlatformEvent(AstrMessageEvent):
    def __init__(
@@ -125,25 +117,66 @@ class WecomPlatformEvent(AstrMessageEvent):
                        )
                elif isinstance(comp, Record):
                    record_path = await comp.convert_to_file_path()
-                    # 转成amr
-                    temp_dir = os.path.join(get_astrbot_data_path(), "temp")
-                    record_path_amr = os.path.join(temp_dir, f"{uuid.uuid4()}.amr")
-                    pydub.AudioSegment.from_wav(record_path).export(
-                        record_path_amr,
-                        format="amr",
-                    )
+                    record_path_amr = await convert_audio_to_amr(record_path)

-                    with open(record_path_amr, "rb") as f:
+                    try:
+                        with open(record_path_amr, "rb") as f:
+                            try:
+                                response = self.client.media.upload("voice", f)
+                            except Exception as e:
+                                logger.error(f"微信客服上传语音失败: {e}")
+                                await self.send(
+                                    MessageChain().message(
+                                        f"微信客服上传语音失败: {e}"
+                                    ),
+                                )
+                                return
+                            logger.info(f"微信客服上传语音返回: {response}")
+                            kf_message_api.send_voice(
+                                user_id,
+                                self.get_self_id(),
+                                response["media_id"],
+                            )
+                    finally:
+                        if record_path_amr != record_path and os.path.exists(
+                            record_path_amr,
+                        ):
+                            try:
+                                os.remove(record_path_amr)
+                            except OSError as e:
+                                logger.warning(f"删除临时音频文件失败: {e}")
+                elif isinstance(comp, File):
+                    file_path = await comp.get_file()
+
+                    with open(file_path, "rb") as f:
                        try:
-                            response = self.client.media.upload("voice", f)
+                            response = self.client.media.upload("file", f)
                        except Exception as e:
-                            logger.error(f"微信客服上传语音失败: {e}")
+                            logger.error(f"微信客服上传文件失败: {e}")
                            await self.send(
-                                MessageChain().message(f"微信客服上传语音失败: {e}"),
+                                MessageChain().message(f"微信客服上传文件失败: {e}"),
                            )
                            return
-                        logger.info(f"微信客服上传语音返回: {response}")
-                        kf_message_api.send_voice(
+                        logger.debug(f"微信客服上传文件返回: {response}")
+                        kf_message_api.send_file(
+                            user_id,
+                            self.get_self_id(),
+                            response["media_id"],
+                        )
+                elif isinstance(comp, Video):
+                    video_path = await comp.convert_to_file_path()
+
+                    with open(video_path, "rb") as f:
+                        try:
+                            response = self.client.media.upload("video", f)
+                        except Exception as e:
+                            logger.error(f"微信客服上传视频失败: {e}")
+                            await self.send(
+                                MessageChain().message(f"微信客服上传视频失败: {e}"),
+                            )
+                            return
+                        logger.debug(f"微信客服上传视频返回: {response}")
+                        kf_message_api.send_video(
                            user_id,
                            self.get_self_id(),
                            response["media_id"],
@@ -183,25 +216,66 @@ class WecomPlatformEvent(AstrMessageEvent):
                        )
                elif isinstance(comp, Record):
                    record_path = await comp.convert_to_file_path()
-                    # 转成amr
-                    temp_dir = os.path.join(get_astrbot_data_path(), "temp")
-                    record_path_amr = os.path.join(temp_dir, f"{uuid.uuid4()}.amr")
-                    pydub.AudioSegment.from_wav(record_path).export(
-                        record_path_amr,
-                        format="amr",
-                    )
+                    record_path_amr = await convert_audio_to_amr(record_path)

-                    with open(record_path_amr, "rb") as f:
+                    try:
+                        with open(record_path_amr, "rb") as f:
+                            try:
+                                response = self.client.media.upload("voice", f)
+                            except Exception as e:
+                                logger.error(f"企业微信上传语音失败: {e}")
+                                await self.send(
+                                    MessageChain().message(
+                                        f"企业微信上传语音失败: {e}"
+                                    ),
+                                )
+                                return
+                            logger.info(f"企业微信上传语音返回: {response}")
+                            self.client.message.send_voice(
+                                message_obj.self_id,
+                                message_obj.session_id,
+                                response["media_id"],
+                            )
+                    finally:
+                        if record_path_amr != record_path and os.path.exists(
+                            record_path_amr,
+                        ):
+                            try:
+                                os.remove(record_path_amr)
+                            except OSError as e:
+                                logger.warning(f"删除临时音频文件失败: {e}")
+                elif isinstance(comp, File):
+                    file_path = await comp.get_file()
+
+                    with open(file_path, "rb") as f:
                        try:
-                            response = self.client.media.upload("voice", f)
+                            response = self.client.media.upload("file", f)
                        except Exception as e:
-                            logger.error(f"企业微信上传语音失败: {e}")
+                            logger.error(f"企业微信上传文件失败: {e}")
                            await self.send(
-                                MessageChain().message(f"企业微信上传语音失败: {e}"),
+                                MessageChain().message(f"企业微信上传文件失败: {e}"),
                            )
                            return
-                        logger.info(f"企业微信上传语音返回: {response}")
-                        self.client.message.send_voice(
+                        logger.debug(f"企业微信上传文件返回: {response}")
+                        self.client.message.send_file(
+                            message_obj.self_id,
+                            message_obj.session_id,
+                            response["media_id"],
+                        )
+                elif isinstance(comp, Video):
+                    video_path = await comp.convert_to_file_path()
+
+                    with open(video_path, "rb") as f:
+                        try:
+                            response = self.client.media.upload("video", f)
+                        except Exception as e:
+                            logger.error(f"企业微信上传视频失败: {e}")
+                            await self.send(
+                                MessageChain().message(f"企业微信上传视频失败: {e}"),
+                            )
+                            return
+                        logger.debug(f"企业微信上传视频返回: {response}")
+                        self.client.message.send_video(
                            message_obj.self_id,
                            message_obj.session_id,
                            response["media_id"],
--- a/astrbot/core/platform/sources/weixin_official_account/weixin_offacc_adapter.py
+++ b/astrbot/core/platform/sources/weixin_official_account/weixin_offacc_adapter.py
@@ -24,6 +24,7 @@ from astrbot.api.platform import (
 )
 from astrbot.core import logger
 from astrbot.core.platform.astr_message_event import MessageSesion
+from astrbot.core.utils.media_utils import convert_audio_to_wav
 from astrbot.core.utils.webhook_utils import log_webhook_info

 from .weixin_offacc_event import WeixinOfficialAccountPlatformEvent
@@ -294,14 +295,11 @@ class WeixinOfficialAccountPlatformAdapter(Platform):
                f.write(resp.content)

            try:
-                from pydub import AudioSegment
-
                path_wav = f"data/temp/wecom_{msg.media_id}.wav"
-                audio = AudioSegment.from_file(path)
-                audio.export(path_wav, format="wav")
+                path_wav = await convert_audio_to_wav(path, path_wav)
            except Exception as e:
                logger.error(
-                    f"转换音频失败: {e}。如果没有安装 pydub 和 ffmpeg 请先安装。",
+                    f"转换音频失败: {e}。如果没有安装 ffmpeg 请先安装。",
                )
                path_wav = path
                return
--- a/astrbot/core/platform/sources/weixin_official_account/weixin_offacc_event.py
+++ b/astrbot/core/platform/sources/weixin_official_account/weixin_offacc_event.py
@@ -1,5 +1,5 @@
 import asyncio
-import uuid
+import os
 from typing import cast

 from wechatpy import WeChatClient
@@ -9,13 +9,7 @@ from astrbot.api import logger
 from astrbot.api.event import AstrMessageEvent, MessageChain
 from astrbot.api.message_components import Image, Plain, Record
 from astrbot.api.platform import AstrBotMessage, PlatformMetadata
-
-try:
-    import pydub
-except Exception:
-    logger.warning(
-        "检测到 pydub 库未安装，微信公众平台将无法语音收发。如需使用语音，请前往管理面板 -> 平台日志 -> 安装 Pip 库安装 pydub。",
-    )
+from astrbot.core.utils.media_utils import convert_audio_to_amr


 class WeixinOfficialAccountPlatformEvent(AstrMessageEvent):
@@ -137,38 +131,46 @@ class WeixinOfficialAccountPlatformEvent(AstrMessageEvent):

            elif isinstance(comp, Record):
                record_path = await comp.convert_to_file_path()
-                # 转成amr
-                record_path_amr = f"data/temp/{uuid.uuid4()}.amr"
-                pydub.AudioSegment.from_wav(record_path).export(
-                    record_path_amr,
-                    format="amr",
-                )
+                record_path_amr = await convert_audio_to_amr(record_path)

-                with open(record_path_amr, "rb") as f:
-                    try:
-                        response = self.client.media.upload("voice", f)
-                    except Exception as e:
-                        logger.error(f"微信公众平台上传语音失败: {e}")
-                        await self.send(
-                            MessageChain().message(f"微信公众平台上传语音失败: {e}"),
-                        )
-                        return
-                    logger.info(f"微信公众平台上传语音返回: {response}")
+                try:
+                    with open(record_path_amr, "rb") as f:
+                        try:
+                            response = self.client.media.upload("voice", f)
+                        except Exception as e:
+                            logger.error(f"微信公众平台上传语音失败: {e}")
+                            await self.send(
+                                MessageChain().message(
+                                    f"微信公众平台上传语音失败: {e}"
+                                ),
+                            )
+                            return
+                        logger.info(f"微信公众平台上传语音返回: {response}")

-                    if active_send_mode:
-                        self.client.message.send_voice(
-                            message_obj.sender.user_id,
-                            response["media_id"],
-                        )
-                    else:
-                        reply = VoiceReply(
-                            media_id=response["media_id"],
-                            message=cast(dict, self.message_obj.raw_message)["message"],
-                        )
-                        xml = reply.render()
-                        future = cast(dict, self.message_obj.raw_message)["future"]
-                        assert isinstance(future, asyncio.Future)
-                        future.set_result(xml)
+                        if active_send_mode:
+                            self.client.message.send_voice(
+                                message_obj.sender.user_id,
+                                response["media_id"],
+                            )
+                        else:
+                            reply = VoiceReply(
+                                media_id=response["media_id"],
+                                message=cast(dict, self.message_obj.raw_message)[
+                                    "message"
+                                ],
+                            )
+                            xml = reply.render()
+                            future = cast(dict, self.message_obj.raw_message)["future"]
+                            assert isinstance(future, asyncio.Future)
+                            future.set_result(xml)
+                finally:
+                    if record_path_amr != record_path and os.path.exists(
+                        record_path_amr
+                    ):
+                        try:
+                            os.remove(record_path_amr)
+                        except OSError as e:
+                            logger.warning(f"删除临时音频文件失败: {e}")

            else:
                logger.warning(f"还没实现这个消息类型的发送逻辑: {comp.type}。")
--- a/astrbot/core/utils/media_utils.py
+++ b/astrbot/core/utils/media_utils.py
@@ -259,6 +259,24 @@ async def convert_audio_format(
        raise Exception("ffmpeg not found")


+async def convert_audio_to_amr(audio_path: str, output_path: str | None = None) -> str:
+    """将音频转换为amr格式。"""
+    return await convert_audio_format(
+        audio_path=audio_path,
+        output_format="amr",
+        output_path=output_path,
+    )
+
+
+async def convert_audio_to_wav(audio_path: str, output_path: str | None = None) -> str:
+    """将音频转换为wav格式。"""
+    return await convert_audio_format(
+        audio_path=audio_path,
+        output_format="wav",
+        output_path=output_path,
+    )
+
+
 async def extract_video_cover(
    video_path: str,
    output_path: str | None = None,