feat: added support for file, voice, and video messages for QQ Official Bot (including WebSocket mode). (#6063)

astrbot/core/platform/sources/qqofficial/qqofficial_message_event.py

@@ -18,7 +18,7 @@ from botpy.types.message import MarkdownPayload, Media
 
 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_temp_path
 from astrbot.core.utils.io import download_image_by_url, file_to_base64
@@ -47,6 +47,10 @@ _patch_qq_botpy_formdata()
 
 class QQOfficialMessageEvent(AstrMessageEvent):
     MARKDOWN_NOT_ALLOWED_ERROR = "不允许发送原生 markdown"
+    IMAGE_FILE_TYPE = 1
+    VIDEO_FILE_TYPE = 2
+    VOICE_FILE_TYPE = 3
+    FILE_FILE_TYPE = 4
 
     def __init__(
         self,
@@ -126,6 +130,9 @@ class QQOfficialMessageEvent(AstrMessageEvent):
             image_base64,
             image_path,
             record_file_path,
+            video_file_source,
+            file_source,
+            file_name,
         ) = await QQOfficialMessageEvent._parse_to_qqofficial(self.send_buffer)
 
         if (
@@ -133,6 +140,8 @@ class QQOfficialMessageEvent(AstrMessageEvent):
             and not image_base64
             and not image_path
             and not record_file_path
+            and not video_file_source
+            and not file_source
         ):
             return None
 
@@ -157,7 +166,7 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                 if image_base64:
                     media = await self.upload_group_and_c2c_image(
                         image_base64,
-                        1,
+                        self.IMAGE_FILE_TYPE,
                         group_openid=source.group_openid,
                     )
                     payload["media"] = media
@@ -165,15 +174,39 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                     payload.pop("markdown", None)
                     payload["content"] = plain_text or None
                 if record_file_path:  # group record msg
-                    media = await self.upload_group_and_c2c_record(
+                    media = await self.upload_group_and_c2c_media(
                         record_file_path,
-                        3,
+                        self.VOICE_FILE_TYPE,
                         group_openid=source.group_openid,
                     )
-                    payload["media"] = media
+                    if media:
-                    payload["msg_type"] = 7
+                        payload["media"] = media
-                    payload.pop("markdown", None)
+                        payload["msg_type"] = 7
-                    payload["content"] = plain_text or None
+                        payload.pop("markdown", None)
+                        payload["content"] = plain_text or None
+                if video_file_source:
+                    media = await self.upload_group_and_c2c_media(
+                        video_file_source,
+                        self.VIDEO_FILE_TYPE,
+                        group_openid=source.group_openid,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                        payload.pop("markdown", None)
+                        payload["content"] = plain_text or None
+                if file_source:
+                    media = await self.upload_group_and_c2c_media(
+                        file_source,
+                        self.FILE_FILE_TYPE,
+                        file_name=file_name,
+                        group_openid=source.group_openid,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                        payload.pop("markdown", None)
+                        payload["content"] = plain_text or None
                 ret = await self._send_with_markdown_fallback(
                     send_func=lambda retry_payload: self.bot.api.post_group_message(
                         group_openid=source.group_openid,  # type: ignore
@@ -187,7 +220,7 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                 if image_base64:
                     media = await self.upload_group_and_c2c_image(
                         image_base64,
-                        1,
+                        self.IMAGE_FILE_TYPE,
                         openid=source.author.user_openid,
                     )
                     payload["media"] = media
@@ -195,15 +228,39 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                     payload.pop("markdown", None)
                     payload["content"] = plain_text or None
                 if record_file_path:  # c2c record
-                    media = await self.upload_group_and_c2c_record(
+                    media = await self.upload_group_and_c2c_media(
                         record_file_path,
-                        3,
+                        self.VOICE_FILE_TYPE,
                         openid=source.author.user_openid,
                     )
-                    payload["media"] = media
+                    if media:
-                    payload["msg_type"] = 7
+                        payload["media"] = media
-                    payload.pop("markdown", None)
+                        payload["msg_type"] = 7
-                    payload["content"] = plain_text or None
+                        payload.pop("markdown", None)
+                        payload["content"] = plain_text or None
+                if video_file_source:
+                    media = await self.upload_group_and_c2c_media(
+                        video_file_source,
+                        self.VIDEO_FILE_TYPE,
+                        openid=source.author.user_openid,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                        payload.pop("markdown", None)
+                        payload["content"] = plain_text or None
+                if file_source:
+                    media = await self.upload_group_and_c2c_media(
+                        file_source,
+                        self.FILE_FILE_TYPE,
+                        file_name=file_name,
+                        openid=source.author.user_openid,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                        payload.pop("markdown", None)
+                        payload["content"] = plain_text or None
                 if stream:
                     ret = await self._send_with_markdown_fallback(
                         send_func=lambda retry_payload: self.post_c2c_message(
@@ -327,16 +384,19 @@ class QQOfficialMessageEvent(AstrMessageEvent):
             ttl=result.get("ttl", 0),
         )
 
-    async def upload_group_and_c2c_record(
+    async def upload_group_and_c2c_media(
         self,
         file_source: str,
         file_type: int,
         srv_send_msg: bool = False,
+        file_name: str | None = None,
         **kwargs,
     ) -> Media | None:
         """上传媒体文件"""
         # 构建基础payload
         payload = {"file_type": file_type, "srv_send_msg": srv_send_msg}
+        if file_name:
+            payload["file_name"] = file_name
 
         # 处理文件数据
         if os.path.exists(file_source):
@@ -416,6 +476,9 @@ class QQOfficialMessageEvent(AstrMessageEvent):
         image_base64 = None  # only one img supported
         image_file_path = None
         record_file_path = None
+        video_file_source = None
+        file_source = None
+        file_name = None
         for i in message.chain:
             if isinstance(i, Plain):
                 plain_text += i.text
@@ -454,6 +517,30 @@ class QQOfficialMessageEvent(AstrMessageEvent):
                     except Exception as e:
                         logger.error(f"处理语音时出错: {e}")
                         record_file_path = None
+            elif isinstance(i, Video) and not video_file_source:
+                if i.file.startswith("file:///"):
+                    video_file_source = i.file[8:]
+                else:
+                    video_file_source = i.file
+            elif isinstance(i, File) and not file_source:
+                file_name = i.name
+                if i.file_:
+                    file_path = i.file_
+                    if file_path.startswith("file:///"):
+                        file_path = file_path[8:]
+                    elif file_path.startswith("file://"):
+                        file_path = file_path[7:]
+                    file_source = file_path
+                elif i.url:
+                    file_source = i.url
             else:
                 logger.debug(f"qq_official 忽略 {i.type}")
-        return plain_text, image_base64, image_file_path, record_file_path
+        return (
+            plain_text,
+            image_base64,
+            image_file_path,
+            record_file_path,
+            video_file_source,
+            file_source,
+            file_name,
+        )

astrbot/core/platform/sources/qqofficial/qqofficial_platform_adapter.py

@@ -3,8 +3,10 @@ from __future__ import annotations
 import asyncio
 import logging
 import os
+import random
 import time
-from typing import cast
+from types import SimpleNamespace
+from typing import Any, cast
 
 import botpy
 import botpy.message
@@ -12,7 +14,7 @@ from botpy import Client
 
 from astrbot import logger
 from astrbot.api.event import MessageChain
-from astrbot.api.message_components import At, File, Image, Plain
+from astrbot.api.message_components import At, File, Image, Plain, Record, Video
 from astrbot.api.platform import (
     AstrBotMessage,
     MessageMember,
@@ -46,6 +48,7 @@ class botClient(Client):
         )
         abm.group_id = cast(str, message.group_openid)
         abm.session_id = abm.group_id
+        self.platform.remember_session_scene(abm.session_id, "group")
         self._commit(abm)
 
     # 收到频道消息
@@ -56,6 +59,7 @@ class botClient(Client):
         )
         abm.group_id = message.channel_id
         abm.session_id = abm.group_id
+        self.platform.remember_session_scene(abm.session_id, "channel")
         self._commit(abm)
 
     # 收到私聊消息
@@ -67,6 +71,7 @@ class botClient(Client):
             MessageType.FRIEND_MESSAGE,
         )
         abm.session_id = abm.sender.user_id
+        self.platform.remember_session_scene(abm.session_id, "friend")
         self._commit(abm)
 
     # 收到 C2C 消息
@@ -76,9 +81,11 @@ class botClient(Client):
             MessageType.FRIEND_MESSAGE,
         )
         abm.session_id = abm.sender.user_id
+        self.platform.remember_session_scene(abm.session_id, "friend")
         self._commit(abm)
 
     def _commit(self, abm: AstrBotMessage) -> None:
+        self.platform.remember_session_message_id(abm.session_id, abm.message_id)
         self.platform.commit_event(
             QQOfficialMessageEvent(
                 abm.message_str,
@@ -124,6 +131,9 @@ class QQOfficialPlatformAdapter(Platform):
 
         self.client.set_platform(self)
 
+        self._session_last_message_id: dict[str, str] = {}
+        self._session_scene: dict[str, str] = {}
+
         self.test_mode = os.environ.get("TEST_MODE", "off") == "on"
 
     async def send_by_session(
@@ -131,14 +141,185 @@ class QQOfficialPlatformAdapter(Platform):
         session: MessageSesion,
         message_chain: MessageChain,
     ) -> None:
-        raise NotImplementedError("QQ 机器人官方 API 适配器不支持 send_by_session")
+        await self._send_by_session_common(session, message_chain)
+
+    async def _send_by_session_common(
+        self,
+        session: MessageSesion,
+        message_chain: MessageChain,
+    ) -> None:
+        (
+            plain_text,
+            image_base64,
+            image_path,
+            record_file_path,
+            video_file_source,
+            file_source,
+            file_name,
+        ) = await QQOfficialMessageEvent._parse_to_qqofficial(message_chain)
+        if (
+            not plain_text
+            and not image_path
+            and not image_base64
+            and not record_file_path
+            and not video_file_source
+            and not file_source
+        ):
+            return
+
+        msg_id = self._session_last_message_id.get(session.session_id)
+        if not msg_id:
+            logger.warning(
+                "[QQOfficial] No cached msg_id for session: %s, skip send_by_session",
+                session.session_id,
+            )
+            return
+
+        payload: dict[str, Any] = {"content": plain_text, "msg_id": msg_id}
+        ret: Any = None
+        send_helper = SimpleNamespace(bot=self.client)
+
+        if session.message_type == MessageType.GROUP_MESSAGE:
+            scene = self._session_scene.get(session.session_id)
+            if scene == "group":
+                payload["msg_seq"] = random.randint(1, 10000)
+                if image_base64:
+                    media = await QQOfficialMessageEvent.upload_group_and_c2c_image(
+                        send_helper,  # type: ignore
+                        image_base64,
+                        QQOfficialMessageEvent.IMAGE_FILE_TYPE,
+                        group_openid=session.session_id,
+                    )
+                    payload["media"] = media
+                    payload["msg_type"] = 7
+                if record_file_path:
+                    media = await QQOfficialMessageEvent.upload_group_and_c2c_media(
+                        send_helper,  # type: ignore
+                        record_file_path,
+                        QQOfficialMessageEvent.VOICE_FILE_TYPE,
+                        group_openid=session.session_id,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                if video_file_source:
+                    media = await QQOfficialMessageEvent.upload_group_and_c2c_media(
+                        send_helper,  # type: ignore
+                        video_file_source,
+                        QQOfficialMessageEvent.VIDEO_FILE_TYPE,
+                        group_openid=session.session_id,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                if file_source:
+                    media = await QQOfficialMessageEvent.upload_group_and_c2c_media(
+                        send_helper,  # type: ignore
+                        file_source,
+                        QQOfficialMessageEvent.FILE_FILE_TYPE,
+                        file_name=file_name,
+                        group_openid=session.session_id,
+                    )
+                    if media:
+                        payload["media"] = media
+                        payload["msg_type"] = 7
+                ret = await self.client.api.post_group_message(
+                    group_openid=session.session_id,
+                    **payload,
+                )
+            else:
+                if image_path:
+                    payload["file_image"] = image_path
+                ret = await self.client.api.post_message(
+                    channel_id=session.session_id,
+                    **payload,
+                )
+
+        elif session.message_type == MessageType.FRIEND_MESSAGE:
+            payload["msg_seq"] = random.randint(1, 10000)
+            if image_base64:
+                media = await QQOfficialMessageEvent.upload_group_and_c2c_image(
+                    send_helper,  # type: ignore
+                    image_base64,
+                    QQOfficialMessageEvent.IMAGE_FILE_TYPE,
+                    openid=session.session_id,
+                )
+                payload["media"] = media
+                payload["msg_type"] = 7
+            if record_file_path:
+                media = await QQOfficialMessageEvent.upload_group_and_c2c_media(
+                    send_helper,  # type: ignore
+                    record_file_path,
+                    QQOfficialMessageEvent.VOICE_FILE_TYPE,
+                    openid=session.session_id,
+                )
+                if media:
+                    payload["media"] = media
+                    payload["msg_type"] = 7
+            if video_file_source:
+                media = await QQOfficialMessageEvent.upload_group_and_c2c_media(
+                    send_helper,  # type: ignore
+                    video_file_source,
+                    QQOfficialMessageEvent.VIDEO_FILE_TYPE,
+                    openid=session.session_id,
+                )
+                if media:
+                    payload["media"] = media
+                    payload["msg_type"] = 7
+            if file_source:
+                media = await QQOfficialMessageEvent.upload_group_and_c2c_media(
+                    send_helper,  # type: ignore
+                    file_source,
+                    QQOfficialMessageEvent.FILE_FILE_TYPE,
+                    file_name=file_name,
+                    openid=session.session_id,
+                )
+                if media:
+                    payload["media"] = media
+                    payload["msg_type"] = 7
+
+            ret = await QQOfficialMessageEvent.post_c2c_message(
+                send_helper,  # type: ignore
+                openid=session.session_id,
+                **payload,
+            )
+        else:
+            logger.warning(
+                "[QQOfficial] Unsupported message type for send_by_session: %s",
+                session.message_type,
+            )
+            return
+
+        sent_message_id = self._extract_message_id(ret)
+        if sent_message_id:
+            self.remember_session_message_id(session.session_id, sent_message_id)
+        await super().send_by_session(session, message_chain)
+
+    def remember_session_message_id(self, session_id: str, message_id: str) -> None:
+        if not session_id or not message_id:
+            return
+        self._session_last_message_id[session_id] = message_id
+
+    def remember_session_scene(self, session_id: str, scene: str) -> None:
+        if not session_id or not scene:
+            return
+        self._session_scene[session_id] = scene
+
+    def _extract_message_id(self, ret: Any) -> str | None:
+        if isinstance(ret, dict):
+            message_id = ret.get("id")
+            return str(message_id) if message_id else None
+        message_id = getattr(ret, "id", None)
+        if message_id:
+            return str(message_id)
+        return None
 
     def meta(self) -> PlatformMetadata:
         return PlatformMetadata(
             name="qq_official",
             description="QQ 机器人官方 API 适配器",
             id=cast(str, self.config.get("id")),
-            support_proactive_message=False,
+            support_proactive_message=True,
         )
 
     @staticmethod
@@ -158,7 +339,10 @@ class QQOfficialPlatformAdapter(Platform):
             return
 
         for attachment in attachments:
-            content_type = cast(str, getattr(attachment, "content_type", "") or "")
+            content_type = cast(
+                str,
+                getattr(attachment, "content_type", "") or "",
+            ).lower()
             url = QQOfficialPlatformAdapter._normalize_attachment_url(
                 cast(str | None, getattr(attachment, "url", None))
             )
@@ -174,7 +358,32 @@ class QQOfficialPlatformAdapter(Platform):
                     or getattr(attachment, "name", None)
                     or "attachment",
                 )
-                msg.append(File(name=filename, file=url, url=url))
+                ext = os.path.splitext(filename)[1].lower()
+                image_exts = {".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp"}
+                audio_exts = {
+                    ".mp3",
+                    ".wav",
+                    ".ogg",
+                    ".m4a",
+                    ".amr",
+                    ".silk",
+                }
+                video_exts = {
+                    ".mp4",
+                    ".mov",
+                    ".avi",
+                    ".mkv",
+                    ".webm",
+                }
+
+                if content_type.startswith("audio") or ext in audio_exts:
+                    msg.append(Record.fromURL(url))
+                elif content_type.startswith("video") or ext in video_exts:
+                    msg.append(Video.fromURL(url))
+                elif content_type.startswith("image") or ext in image_exts:
+                    msg.append(Image.fromURL(url))
+                else:
+                    msg.append(File(name=filename, file=url, url=url))
 
     @staticmethod
     def _parse_from_qqofficial(

astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_adapter.py

@@ -1,7 +1,5 @@
 import asyncio
 import logging
-import random
-from types import SimpleNamespace
 from typing import Any, cast
 
 import botpy
@@ -15,7 +13,6 @@ from astrbot.core.platform.astr_message_event import MessageSesion
 from astrbot.core.utils.webhook_utils import log_webhook_info
 
 from ...register import register_platform_adapter
-from ..qqofficial.qqofficial_message_event import QQOfficialMessageEvent
 from ..qqofficial.qqofficial_platform_adapter import QQOfficialPlatformAdapter
 from .qo_webhook_event import QQOfficialWebhookMessageEvent
 from .qo_webhook_server import QQOfficialWebhook
@@ -123,95 +120,11 @@ class QQOfficialWebhookPlatformAdapter(Platform):
         session: MessageSesion,
         message_chain: MessageChain,
     ) -> None:
-        (
+        await QQOfficialPlatformAdapter._send_by_session_common(
-            plain_text,
+            cast(Any, self),
-            image_base64,
+            session,
-            image_path,
+            message_chain,
-            record_file_path,
+        )
-        ) = await QQOfficialMessageEvent._parse_to_qqofficial(message_chain)
-        if not plain_text and not image_path:
-            return
-
-        msg_id = self._session_last_message_id.get(session.session_id)
-        if not msg_id:
-            logger.warning(
-                "[QQOfficialWebhook] No cached msg_id for session: %s, skip send_by_session",
-                session.session_id,
-            )
-            return
-
-        payload: dict[str, Any] = {"content": plain_text, "msg_id": msg_id}
-        ret: Any = None
-        send_helper = SimpleNamespace(bot=self.client)
-        if session.message_type == MessageType.GROUP_MESSAGE:
-            scene = self._session_scene.get(session.session_id)
-            if scene == "group":
-                payload["msg_seq"] = random.randint(1, 10000)
-                if image_base64:
-                    media = await QQOfficialMessageEvent.upload_group_and_c2c_image(
-                        send_helper,  # type: ignore
-                        image_base64,
-                        1,
-                        group_openid=session.session_id,
-                    )
-                    payload["media"] = media
-                    payload["msg_type"] = 7
-                if record_file_path:
-                    media = await QQOfficialMessageEvent.upload_group_and_c2c_record(
-                        send_helper,  # type: ignore
-                        record_file_path,
-                        3,
-                        group_openid=session.session_id,
-                    )
-                    payload["media"] = media
-                    payload["msg_type"] = 7
-                ret = await self.client.api.post_group_message(
-                    group_openid=session.session_id,
-                    **payload,
-                )
-            else:
-                if image_path:
-                    payload["file_image"] = image_path
-                ret = await self.client.api.post_message(
-                    channel_id=session.session_id,
-                    **payload,
-                )
-        elif session.message_type == MessageType.FRIEND_MESSAGE:
-            payload["msg_seq"] = random.randint(1, 10000)
-            if image_base64:
-                media = await QQOfficialMessageEvent.upload_group_and_c2c_image(
-                    send_helper,  # type: ignore
-                    image_base64,
-                    1,
-                    openid=session.session_id,
-                )
-                payload["media"] = media
-                payload["msg_type"] = 7
-            if record_file_path:
-                media = await QQOfficialMessageEvent.upload_group_and_c2c_record(
-                    send_helper,  # type: ignore
-                    record_file_path,
-                    3,
-                    openid=session.session_id,
-                )
-                payload["media"] = media
-                payload["msg_type"] = 7
-            ret = await QQOfficialMessageEvent.post_c2c_message(
-                send_helper,  # type: ignore
-                openid=session.session_id,
-                **payload,
-            )
-        else:
-            logger.warning(
-                "[QQOfficialWebhook] Unsupported message type for send_by_session: %s",
-                session.message_type,
-            )
-            return
-
-        sent_message_id = self._extract_message_id(ret)
-        if sent_message_id:
-            self.remember_session_message_id(session.session_id, sent_message_id)
-        await super().send_by_session(session, message_chain)
 
     def remember_session_message_id(self, session_id: str, message_id: str) -> None:
         if not session_id or not message_id:

docs/en/platform/qqofficial/webhook.md

@@ -7,17 +7,17 @@
 
 ## Supported Basic Message Types
 
-> Version v4.15.0.
+> Version v4.19.6.
 
 | Message Type | Receive | Send | Notes |
 | --- | --- | --- | --- |
 | Text | Yes | Yes | |
 | Image | Yes | Yes | |
-| Voice | No | No | |
+| Voice | Yes | Yes | |
-| Video | No | No | |
+| Video | Yes | Yes | |
-| File | No | No | |
+| File | Yes | Yes | |
 
-Proactive message push: Not supported.
+Proactive message push: Supported.
 
 ## Apply for a Bot
 

docs/en/platform/qqofficial/websockets.md

@@ -2,17 +2,17 @@
 
 ## Supported Basic Message Types
 
-> Version v4.15.0.
+> Version v4.19.6.
 
 | Message Type | Receive | Send | Notes |
 | --- | --- | --- | --- |
 | Text | Yes | Yes | |
 | Image | Yes | Yes | |
-| Voice | No | No | |
+| Voice | Yes | Yes | |
-| Video | No | No | |
+| Video | Yes | Yes | |
-| File | No | No | |
+| File | Yes | Yes | |
 
-Proactive message push: Not supported.
+Proactive message push: Supported.
 
 ## Quick Deployment Steps
 

docs/zh/platform/qqofficial/webhook.md

@@ -10,17 +10,17 @@
 
 ## 支持的基本消息类型
 
-> 版本 v4.15.0。
+> 版本 v4.19.6。
 
 | 消息类型 | 是否支持接收 | 是否支持发送 | 备注 |
 | --- | --- | --- | --- |
 | 文本 | 是 | 是 | |
 | 图片 | 是 | 是 | |
-| 语音 | 否 | 否 | |
+| 语音 | 是 | 是 | |
-| 视频 | 否 | 否 | |
+| 视频 | 是 | 是 | |
-| 文件 | 否 | 否 | |
+| 文件 | 是 | 是 | |
 
-主动消息推送：不支持。
+主动消息推送：支持。
 
 ## 申请一个机器人
 

docs/zh/platform/qqofficial/websockets.md

@@ -3,17 +3,17 @@
 
 ## 支持的基本消息类型
 
-> 版本 v4.15.0。
+> 版本 v4.19.6。
 
 | 消息类型 | 是否支持接收 | 是否支持发送 | 备注 |
 | --- | --- | --- | --- |
 | 文本 | 是 | 是 | |
 | 图片 | 是 | 是 | |
-| 语音 | 否 | 否 | |
+| 语音 | 是 | 是 | |
-| 视频 | 否 | 否 | |
+| 视频 | 是 | 是 | |
-| 文件 | 否 | 否 | |
+| 文件 | 是 | 是 | |
 
-主动消息推送：不支持。
+主动消息推送：支持。
 
 ## 快速部署通道