mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-06-17 11:14:19 +00:00
feat: Implement WebSocket long connection client for WeChat Work AI Bot (#2054)
* feat: Implement WebSocket long connection client for WeChat Work AI Bot - Added WecomBotWsClient to handle WebSocket connections for receiving messages and sending replies. - Introduced a new migration (dbm022) to add 'enable-webhook' field to existing wecombot adapter configs, ensuring backward compatibility. - Updated WecomBotAdapter to support both WebSocket and webhook modes based on the new configuration. - Enhanced YAML configuration for WecomBot to include 'enable-webhook' and 'Secret' fields, adjusting requirements accordingly. - Incremented database version to 22 to reflect schema changes. * fix:db enable-webhook is false * fix:add logic * fix:Removed an unnecessary configuration check * fix: migration * fix: update migration * fix:migration
This commit is contained in:
fdc310
@@ -199,6 +199,253 @@ class StreamSessionManager:
|
||||
self._msg_index.pop(msg_id, None)
|
||||
|
||||
|
||||
async def download_encrypted_file(download_url: str, encoding_aes_key: str, logger: EventLogger) -> Optional[str]:
|
||||
"""Download an AES-encrypted file from WeChat Work and return as data URI.
|
||||
|
||||
Args:
|
||||
download_url: The encrypted file download URL.
|
||||
encoding_aes_key: The AES key used for decryption (base64-encoded, without trailing '=').
|
||||
logger: Logger instance.
|
||||
|
||||
Returns:
|
||||
A data URI string (e.g. 'data:image/jpeg;base64,...') or None on failure.
|
||||
"""
|
||||
if not download_url:
|
||||
return None
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.get(download_url)
|
||||
if response.status_code != 200:
|
||||
await logger.error(f'failed to get file: {response.text}')
|
||||
return None
|
||||
encrypted_bytes = response.content
|
||||
|
||||
aes_key = base64.b64decode(encoding_aes_key + '=')
|
||||
iv = aes_key[:16]
|
||||
|
||||
cipher = AES.new(aes_key, AES.MODE_CBC, iv)
|
||||
decrypted = cipher.decrypt(encrypted_bytes)
|
||||
|
||||
pad_len = decrypted[-1]
|
||||
decrypted = decrypted[:-pad_len]
|
||||
|
||||
if decrypted.startswith(b'\xff\xd8'):
|
||||
mime_type = 'image/jpeg'
|
||||
elif decrypted.startswith(b'\x89PNG'):
|
||||
mime_type = 'image/png'
|
||||
elif decrypted.startswith((b'GIF87a', b'GIF89a')):
|
||||
mime_type = 'image/gif'
|
||||
elif decrypted.startswith(b'BM'):
|
||||
mime_type = 'image/bmp'
|
||||
elif decrypted.startswith(b'II*\x00') or decrypted.startswith(b'MM\x00*'):
|
||||
mime_type = 'image/tiff'
|
||||
else:
|
||||
mime_type = 'application/octet-stream'
|
||||
|
||||
base64_str = base64.b64encode(decrypted).decode('utf-8')
|
||||
return f'data:{mime_type};base64,{base64_str}'
|
||||
|
||||
|
||||
async def parse_wecom_bot_message(
|
||||
msg_json: dict[str, Any], encoding_aes_key: str, logger: EventLogger
|
||||
) -> dict[str, Any]:
|
||||
"""Parse a decrypted WeChat Work AI Bot message JSON into a unified message dict.
|
||||
|
||||
This is the shared message parsing logic used by both webhook and WebSocket modes.
|
||||
|
||||
Args:
|
||||
msg_json: The decrypted message JSON from WeChat Work.
|
||||
encoding_aes_key: AES key for file decryption.
|
||||
logger: Logger instance.
|
||||
|
||||
Returns:
|
||||
A dict suitable for constructing a WecomBotEvent.
|
||||
"""
|
||||
message_data: dict[str, Any] = {}
|
||||
|
||||
msg_type = msg_json.get('msgtype', '')
|
||||
if msg_type:
|
||||
message_data['msgtype'] = msg_type
|
||||
|
||||
if msg_json.get('chattype', '') == 'single':
|
||||
message_data['type'] = 'single'
|
||||
elif msg_json.get('chattype', '') == 'group':
|
||||
message_data['type'] = 'group'
|
||||
|
||||
max_inline_file_size = 5 * 1024 * 1024
|
||||
|
||||
async def _safe_download(url: str):
|
||||
if not url:
|
||||
return None
|
||||
return await download_encrypted_file(url, encoding_aes_key, logger)
|
||||
|
||||
if msg_type == 'text':
|
||||
message_data['content'] = msg_json.get('text', {}).get('content')
|
||||
elif msg_type == 'markdown':
|
||||
message_data['content'] = msg_json.get('markdown', {}).get('content') or msg_json.get('text', {}).get(
|
||||
'content', ''
|
||||
)
|
||||
elif msg_type == 'image':
|
||||
picurl = msg_json.get('image', {}).get('url', '')
|
||||
base64_data = await _safe_download(picurl)
|
||||
if base64_data:
|
||||
message_data['picurl'] = base64_data
|
||||
message_data['images'] = [base64_data]
|
||||
elif msg_type == 'voice':
|
||||
voice_info = msg_json.get('voice', {}) or {}
|
||||
download_url = voice_info.get('url')
|
||||
message_data['voice'] = {
|
||||
'url': download_url,
|
||||
'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
|
||||
'filesize': voice_info.get('filesize') or voice_info.get('size'),
|
||||
'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
|
||||
}
|
||||
if voice_info.get('content'):
|
||||
message_data['content'] = voice_info.get('content')
|
||||
if (message_data['voice'].get('filesize') or 0) <= max_inline_file_size:
|
||||
voice_base64 = await _safe_download(download_url)
|
||||
if voice_base64:
|
||||
message_data['voice']['base64'] = voice_base64
|
||||
elif msg_type == 'video':
|
||||
video_info = msg_json.get('video', {}) or {}
|
||||
download_url = video_info.get('url')
|
||||
video_data = {
|
||||
'url': download_url,
|
||||
'filesize': video_info.get('filesize') or video_info.get('size'),
|
||||
'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
|
||||
'md5sum': video_info.get('md5sum') or video_info.get('md5'),
|
||||
'filename': video_info.get('filename') or video_info.get('name'),
|
||||
}
|
||||
if (video_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
video_base64 = await _safe_download(download_url)
|
||||
if video_base64:
|
||||
video_data['base64'] = video_base64
|
||||
message_data['video'] = video_data
|
||||
elif msg_type == 'file':
|
||||
file_info = msg_json.get('file', {}) or {}
|
||||
download_url = file_info.get('url') or file_info.get('fileurl')
|
||||
file_data = {
|
||||
'filename': file_info.get('filename') or file_info.get('name'),
|
||||
'filesize': file_info.get('filesize') or file_info.get('size'),
|
||||
'md5sum': file_info.get('md5sum') or file_info.get('md5'),
|
||||
'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
|
||||
'download_url': download_url,
|
||||
'extra': file_info,
|
||||
}
|
||||
if (file_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
file_base64 = await _safe_download(download_url)
|
||||
if file_base64:
|
||||
file_data['base64'] = file_base64
|
||||
message_data['file'] = file_data
|
||||
elif msg_type == 'link':
|
||||
message_data['link'] = msg_json.get('link', {})
|
||||
if not message_data.get('content'):
|
||||
title = message_data['link'].get('title', '')
|
||||
desc = message_data['link'].get('description') or message_data['link'].get('digest', '')
|
||||
message_data['content'] = '\n'.join(filter(None, [title, desc]))
|
||||
elif msg_type == 'mixed':
|
||||
items = msg_json.get('mixed', {}).get('msg_item', [])
|
||||
texts = []
|
||||
images = []
|
||||
files = []
|
||||
voices = []
|
||||
videos = []
|
||||
links = []
|
||||
for item in items:
|
||||
item_type = item.get('msgtype')
|
||||
if item_type == 'text':
|
||||
texts.append(item.get('text', {}).get('content', ''))
|
||||
elif item_type == 'image':
|
||||
img_url = item.get('image', {}).get('url')
|
||||
base64_data = await _safe_download(img_url)
|
||||
if base64_data:
|
||||
images.append(base64_data)
|
||||
elif item_type == 'file':
|
||||
file_info = item.get('file', {}) or {}
|
||||
download_url = file_info.get('url') or file_info.get('fileurl')
|
||||
file_data = {
|
||||
'filename': file_info.get('filename') or file_info.get('name'),
|
||||
'filesize': file_info.get('filesize') or file_info.get('size'),
|
||||
'md5sum': file_info.get('md5sum') or file_info.get('md5'),
|
||||
'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
|
||||
'download_url': download_url,
|
||||
'extra': file_info,
|
||||
}
|
||||
if (file_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
file_base64 = await _safe_download(download_url)
|
||||
if file_base64:
|
||||
file_data['base64'] = file_base64
|
||||
files.append(file_data)
|
||||
elif item_type == 'voice':
|
||||
voice_info = item.get('voice', {}) or {}
|
||||
download_url = voice_info.get('url')
|
||||
voice_data = {
|
||||
'url': download_url,
|
||||
'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
|
||||
'filesize': voice_info.get('filesize') or voice_info.get('size'),
|
||||
'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
|
||||
}
|
||||
if voice_info.get('content'):
|
||||
texts.append(voice_info.get('content'))
|
||||
if (voice_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
voice_base64 = await _safe_download(download_url)
|
||||
if voice_base64:
|
||||
voice_data['base64'] = voice_base64
|
||||
voices.append(voice_data)
|
||||
elif item_type == 'video':
|
||||
video_info = item.get('video', {}) or {}
|
||||
download_url = video_info.get('url')
|
||||
video_data = {
|
||||
'url': download_url,
|
||||
'filesize': video_info.get('filesize') or video_info.get('size'),
|
||||
'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
|
||||
'md5sum': video_info.get('md5sum') or video_info.get('md5'),
|
||||
'filename': video_info.get('filename') or video_info.get('name'),
|
||||
}
|
||||
if (video_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
video_base64 = await _safe_download(download_url)
|
||||
if video_base64:
|
||||
video_data['base64'] = video_base64
|
||||
videos.append(video_data)
|
||||
elif item_type == 'link':
|
||||
links.append(item.get('link', {}))
|
||||
|
||||
if texts:
|
||||
message_data['content'] = ' '.join(texts)
|
||||
if images:
|
||||
message_data['images'] = images
|
||||
message_data['picurl'] = images[0]
|
||||
if files:
|
||||
message_data['files'] = files
|
||||
message_data['file'] = files[0]
|
||||
if voices:
|
||||
message_data['voices'] = voices
|
||||
message_data['voice'] = voices[0]
|
||||
if videos:
|
||||
message_data['videos'] = videos
|
||||
message_data['video'] = videos[0]
|
||||
if links:
|
||||
message_data['link'] = links[0]
|
||||
if items:
|
||||
message_data['attachments'] = items
|
||||
else:
|
||||
message_data['raw_msg'] = msg_json
|
||||
|
||||
from_info = msg_json.get('from', {})
|
||||
message_data['userid'] = from_info.get('userid', '')
|
||||
message_data['username'] = from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
|
||||
|
||||
if msg_json.get('chattype', '') == 'group':
|
||||
message_data['chatid'] = msg_json.get('chatid', '')
|
||||
message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
|
||||
|
||||
message_data['msgid'] = msg_json.get('msgid', '')
|
||||
|
||||
if msg_json.get('aibotid'):
|
||||
message_data['aibotid'] = msg_json.get('aibotid', '')
|
||||
|
||||
return message_data
|
||||
|
||||
|
||||
class WecomBotClient:
|
||||
def __init__(self, Token: str, EnCodingAESKey: str, Corpid: str, logger: EventLogger, unified_mode: bool = False):
|
||||
"""企业微信智能机器人客户端。
|
||||
@@ -455,196 +702,7 @@ class WecomBotClient:
|
||||
return await self._handle_post_initial_response(msg_json, nonce)
|
||||
|
||||
async def get_message(self, msg_json):
|
||||
message_data = {}
|
||||
|
||||
msg_type = msg_json.get('msgtype', '')
|
||||
if msg_type:
|
||||
message_data['msgtype'] = msg_type
|
||||
|
||||
if msg_json.get('chattype', '') == 'single':
|
||||
message_data['type'] = 'single'
|
||||
elif msg_json.get('chattype', '') == 'group':
|
||||
message_data['type'] = 'group'
|
||||
|
||||
max_inline_file_size = 5 * 1024 * 1024 # avoid decoding very large payloads by default
|
||||
|
||||
async def _safe_download(url: str):
|
||||
if not url:
|
||||
return None
|
||||
return await self.download_url_to_base64(url, self.EnCodingAESKey)
|
||||
|
||||
if msg_type == 'text':
|
||||
message_data['content'] = msg_json.get('text', {}).get('content')
|
||||
elif msg_type == 'markdown':
|
||||
message_data['content'] = msg_json.get('markdown', {}).get('content') or msg_json.get('text', {}).get(
|
||||
'content', ''
|
||||
)
|
||||
elif msg_type == 'image':
|
||||
picurl = msg_json.get('image', {}).get('url', '')
|
||||
base64_data = await _safe_download(picurl)
|
||||
if base64_data:
|
||||
message_data['picurl'] = base64_data
|
||||
message_data['images'] = [base64_data]
|
||||
elif msg_type == 'voice':
|
||||
voice_info = msg_json.get('voice', {}) or {}
|
||||
download_url = voice_info.get('url')
|
||||
message_data['voice'] = {
|
||||
'url': download_url,
|
||||
'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
|
||||
'filesize': voice_info.get('filesize') or voice_info.get('size'),
|
||||
'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
|
||||
}
|
||||
# 企业微信智能转写文本（如果已有）直接复用，避免重复转写
|
||||
if voice_info.get('content'):
|
||||
message_data['content'] = voice_info.get('content')
|
||||
if (message_data['voice'].get('filesize') or 0) <= max_inline_file_size:
|
||||
voice_base64 = await _safe_download(download_url)
|
||||
if voice_base64:
|
||||
message_data['voice']['base64'] = voice_base64
|
||||
elif msg_type == 'video':
|
||||
video_info = msg_json.get('video', {}) or {}
|
||||
download_url = video_info.get('url')
|
||||
video_data = {
|
||||
'url': download_url,
|
||||
'filesize': video_info.get('filesize') or video_info.get('size'),
|
||||
'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
|
||||
'md5sum': video_info.get('md5sum') or video_info.get('md5'),
|
||||
'filename': video_info.get('filename') or video_info.get('name'),
|
||||
}
|
||||
if (video_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
video_base64 = await _safe_download(download_url)
|
||||
if video_base64:
|
||||
video_data['base64'] = video_base64
|
||||
message_data['video'] = video_data
|
||||
elif msg_type == 'file':
|
||||
file_info = msg_json.get('file', {}) or {}
|
||||
download_url = file_info.get('url') or file_info.get('fileurl')
|
||||
file_data = {
|
||||
'filename': file_info.get('filename') or file_info.get('name'),
|
||||
'filesize': file_info.get('filesize') or file_info.get('size'),
|
||||
'md5sum': file_info.get('md5sum') or file_info.get('md5'),
|
||||
'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
|
||||
'download_url': download_url,
|
||||
'extra': file_info,
|
||||
}
|
||||
if (file_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
file_base64 = await _safe_download(download_url)
|
||||
if file_base64:
|
||||
file_data['base64'] = file_base64
|
||||
message_data['file'] = file_data
|
||||
elif msg_type == 'link':
|
||||
message_data['link'] = msg_json.get('link', {})
|
||||
if not message_data.get('content'):
|
||||
title = message_data['link'].get('title', '')
|
||||
desc = message_data['link'].get('description') or message_data['link'].get('digest', '')
|
||||
message_data['content'] = '\n'.join(filter(None, [title, desc]))
|
||||
elif msg_type == 'mixed':
|
||||
items = msg_json.get('mixed', {}).get('msg_item', [])
|
||||
texts = []
|
||||
images = []
|
||||
files = []
|
||||
voices = []
|
||||
videos = []
|
||||
links = []
|
||||
for item in items:
|
||||
item_type = item.get('msgtype')
|
||||
if item_type == 'text':
|
||||
texts.append(item.get('text', {}).get('content', ''))
|
||||
elif item_type == 'image':
|
||||
img_url = item.get('image', {}).get('url')
|
||||
base64_data = await _safe_download(img_url)
|
||||
if base64_data:
|
||||
images.append(base64_data)
|
||||
elif item_type == 'file':
|
||||
file_info = item.get('file', {}) or {}
|
||||
download_url = file_info.get('url') or file_info.get('fileurl')
|
||||
file_data = {
|
||||
'filename': file_info.get('filename') or file_info.get('name'),
|
||||
'filesize': file_info.get('filesize') or file_info.get('size'),
|
||||
'md5sum': file_info.get('md5sum') or file_info.get('md5'),
|
||||
'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
|
||||
'download_url': download_url,
|
||||
'extra': file_info,
|
||||
}
|
||||
if (file_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
file_base64 = await _safe_download(download_url)
|
||||
if file_base64:
|
||||
file_data['base64'] = file_base64
|
||||
files.append(file_data)
|
||||
elif item_type == 'voice':
|
||||
voice_info = item.get('voice', {}) or {}
|
||||
download_url = voice_info.get('url')
|
||||
voice_data = {
|
||||
'url': download_url,
|
||||
'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
|
||||
'filesize': voice_info.get('filesize') or voice_info.get('size'),
|
||||
'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
|
||||
}
|
||||
if voice_info.get('content'):
|
||||
texts.append(voice_info.get('content'))
|
||||
if (voice_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
voice_base64 = await _safe_download(download_url)
|
||||
if voice_base64:
|
||||
voice_data['base64'] = voice_base64
|
||||
voices.append(voice_data)
|
||||
elif item_type == 'video':
|
||||
video_info = item.get('video', {}) or {}
|
||||
download_url = video_info.get('url')
|
||||
video_data = {
|
||||
'url': download_url,
|
||||
'filesize': video_info.get('filesize') or video_info.get('size'),
|
||||
'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
|
||||
'md5sum': video_info.get('md5sum') or video_info.get('md5'),
|
||||
'filename': video_info.get('filename') or video_info.get('name'),
|
||||
}
|
||||
if (video_data.get('filesize') or 0) <= max_inline_file_size:
|
||||
video_base64 = await _safe_download(download_url)
|
||||
if video_base64:
|
||||
video_data['base64'] = video_base64
|
||||
videos.append(video_data)
|
||||
elif item_type == 'link':
|
||||
links.append(item.get('link', {}))
|
||||
|
||||
if texts:
|
||||
message_data['content'] = ' '.join(texts) # 拼接所有 text
|
||||
if images:
|
||||
message_data['images'] = images
|
||||
message_data['picurl'] = images[0] # 只保留第一个 image
|
||||
if files:
|
||||
message_data['files'] = files
|
||||
message_data['file'] = files[0]
|
||||
if voices:
|
||||
message_data['voices'] = voices
|
||||
message_data['voice'] = voices[0]
|
||||
if videos:
|
||||
message_data['videos'] = videos
|
||||
message_data['video'] = videos[0]
|
||||
if links:
|
||||
message_data['link'] = links[0]
|
||||
if items:
|
||||
message_data['attachments'] = items
|
||||
else:
|
||||
message_data['raw_msg'] = msg_json
|
||||
|
||||
# Extract user information
|
||||
from_info = msg_json.get('from', {})
|
||||
message_data['userid'] = from_info.get('userid', '')
|
||||
message_data['username'] = (
|
||||
from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
|
||||
)
|
||||
|
||||
# Extract chat/group information
|
||||
if msg_json.get('chattype', '') == 'group':
|
||||
message_data['chatid'] = msg_json.get('chatid', '')
|
||||
# Try to get group name if available
|
||||
message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
|
||||
|
||||
message_data['msgid'] = msg_json.get('msgid', '')
|
||||
|
||||
if msg_json.get('aibotid'):
|
||||
message_data['aibotid'] = msg_json.get('aibotid', '')
|
||||
|
||||
return message_data
|
||||
return await parse_wecom_bot_message(msg_json, self.EnCodingAESKey, self.logger)
|
||||
|
||||
async def _handle_message(self, event: wecombotevent.WecomBotEvent):
|
||||
"""
|
||||
@@ -712,39 +770,7 @@ class WecomBotClient:
|
||||
return decorator
|
||||
|
||||
async def download_url_to_base64(self, download_url, encoding_aes_key):
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.get(download_url)
|
||||
if response.status_code != 200:
|
||||
await self.logger.error(f'failed to get file: {response.text}')
|
||||
return None
|
||||
|
||||
encrypted_bytes = response.content
|
||||
|
||||
aes_key = base64.b64decode(encoding_aes_key + '=') # base64 补齐
|
||||
iv = aes_key[:16]
|
||||
|
||||
cipher = AES.new(aes_key, AES.MODE_CBC, iv)
|
||||
decrypted = cipher.decrypt(encrypted_bytes)
|
||||
|
||||
pad_len = decrypted[-1]
|
||||
decrypted = decrypted[:-pad_len]
|
||||
|
||||
if decrypted.startswith(b'\xff\xd8'): # JPEG
|
||||
mime_type = 'image/jpeg'
|
||||
elif decrypted.startswith(b'\x89PNG'): # PNG
|
||||
mime_type = 'image/png'
|
||||
elif decrypted.startswith((b'GIF87a', b'GIF89a')): # GIF
|
||||
mime_type = 'image/gif'
|
||||
elif decrypted.startswith(b'BM'): # BMP
|
||||
mime_type = 'image/bmp'
|
||||
elif decrypted.startswith(b'II*\x00') or decrypted.startswith(b'MM\x00*'): # TIFF
|
||||
mime_type = 'image/tiff'
|
||||
else:
|
||||
mime_type = 'application/octet-stream'
|
||||
|
||||
# 转 base64
|
||||
base64_str = base64.b64encode(decrypted).decode('utf-8')
|
||||
return f'data:{mime_type};base64,{base64_str}'
|
||||
return await download_encrypted_file(download_url, encoding_aes_key, self.logger)
|
||||
|
||||
async def run_task(self, host: str, port: int, *args, **kwargs):
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user