Merge Pull Request #774 into master

.gitignore

@@ -1,5 +1,6 @@
 .DS_Store
 .idea
+.vscode
 .wechaty/
 __pycache__/
 venv*

app.py

@@ -36,7 +36,7 @@ def run():
             # os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'
 
         channel = channel_factory.create_channel(channel_name)
-        if channel_name in ['wx','wxy','wechatmp','terminal']:
+        if channel_name in ['wx','wxy','terminal','wechatmp','wechatmp_service']:
             PluginManager().load_plugins()
 
         # startup channel

channel/channel_factory.py

@@ -19,5 +19,8 @@ def create_channel(channel_type):
         return TerminalChannel()
     elif channel_type == 'wechatmp':
         from channel.wechatmp.wechatmp_channel import WechatMPChannel
-        return WechatMPChannel()
+        return WechatMPChannel(passive_reply = True)
+    elif channel_type == 'wechatmp_service':
+        from channel.wechatmp.wechatmp_channel import WechatMPChannel
+        return WechatMPChannel(passive_reply = False)
     raise RuntimeError

channel/wechatmp/README.md

@@ -1,10 +1,11 @@
-# 个人微信公众号channel
+# 微信公众号channel
 
-鉴于个人微信号在服务器上通过itchat登录有封号风险，这里新增了个人微信公众号channel，提供无风险的服务。
-但是由于个人微信公众号的众多接口限制，目前支持的功能有限，实现简陋，提供了一个最基本的文本对话服务，支持加载插件，优化了命令格式，支持私有api_key。暂未实现图片输入输出、语音输入输出等交互形式。
-如有公众号是企业主体且可以通过微信认证，即可获得更多接口，解除大多数限制。欢迎大家提供更多的支持。
+鉴于个人微信号在服务器上通过itchat登录有封号风险，这里新增了微信公众号channel，提供无风险的服务。
+目前支持订阅号（个人）和服务号（企业）两种类型的公众号，它们的主要区别就是被动回复和主动回复。
+个人微信订阅号有许多接口限制，目前仅支持最基本的文本对话和语音输入，支持加载插件，支持私有api_key。
+暂未实现图片输入输出、语音输出等交互形式。
 
-## 使用方法
+## 使用方法（订阅号，服务号类似）
 
 在开始部署前，你需要一个拥有公网IP的服务器，以提供微信服务器和我们自己服务器的连接。或者你需要进行内网穿透，否则微信服务器无法将消息发送给我们的服务器。
 
@@ -21,8 +22,10 @@ pip3 install web.py
 相关的服务器验证代码已经写好，你不需要再添加任何代码。你只需要在本项目根目录的`config.json`中添加
 ```
 "channel_type": "wechatmp", 
-"wechatmp_token": "your Token", 
-"wechatmp_port": 8080,
+"wechatmp_token": "Token",  # 微信公众平台的Token
+"wechatmp_port": 8080,      # 微信公众平台的端口,需要端口转发到80或443
+"wechatmp_app_id": "",      # 微信公众平台的appID，仅服务号需要
+"wechatmp_app_secret": "",  # 微信公众平台的appsecret，仅服务号需要
 ``` 
 然后运行`python3 app.py`启动web服务器。这里会默认监听8080端口，但是微信公众号的服务器配置只支持80/443端口，有两种方法来解决这个问题。第一个是推荐的方法，使用端口转发命令将80端口转发到8080端口（443同理，注意需要支持SSL，也就是https的访问，在`wechatmp_channel.py`需要修改相应的证书路径）：
 ```
@@ -35,12 +38,17 @@ sudo iptables-save > /etc/iptables/rules.v4
 随后在[微信公众平台](https://mp.weixin.qq.com)启用服务器，关闭手动填写规则的自动回复，即可实现ChatGPT的自动回复。
 
 ## 个人微信公众号的限制
-由于目前测试的公众号不是企业主体，所以没有客服接口，因此公众号无法主动发出消息，只能被动回复。而微信官方对被动回复有5秒的时间限制，最多重试2次，因此最多只有15秒的自动回复时间窗口。因此如果问题比较复杂或者我们的服务器比较忙，ChatGPT的回答就没办法及时回复给用户。为了解决这个问题，这里做了回答缓存，它需要你在回复超时后，再次主动发送任意文字（例如1）来尝试拿到回答缓存。为了优化使用体验，目前设置了两分钟（120秒）的timeout，用户在至多两分钟后即可得到查询到回复或者错误原因。
+由于人微信公众号不能通过微信认证，所以没有客服接口，因此公众号无法主动发出消息，只能被动回复。而微信官方对被动回复有5秒的时间限制，最多重试2次，因此最多只有15秒的自动回复时间窗口。因此如果问题比较复杂或者我们的服务器比较忙，ChatGPT的回答就没办法及时回复给用户。为了解决这个问题，这里做了回答缓存，它需要你在回复超时后，再次主动发送任意文字（例如1）来尝试拿到回答缓存。为了优化使用体验，目前设置了两分钟（120秒）的timeout，用户在至多两分钟后即可得到查询到回复或者错误原因。
 
 另外，由于微信官方的限制，自动回复有长度限制。因此这里将ChatGPT的回答拆分，分成每段600字回复（限制大约在700字）。
 
 ## 私有api_key
 公共api有访问频率限制（免费账号每分钟最多20次ChatGPT的API调用），这在服务多人的时候会遇到问题。因此这里多加了一个设置私有api_key的功能。目前通过godcmd插件的命令来设置私有api_key。
 
 ## 测试范围
-目前在`RoboStyle`这个公众号上进行了测试，感兴趣的可以关注并体验。开启了godcmd, Banwords, role, dungeon, finish这五个插件，其他的插件还没有测试。百度的接口暂未测试。语音对话没有测试。图片直接以链接形式回复（没有临时素材上传接口的权限）。
+目前在`RoboStyle`这个公众号上进行了测试(基于[wechatmp-stable分支](https://github.com/JS00000/chatgpt-on-wechat/tree/wechatmp-stable),而[master分支](https://github.com/zhayujie/chatgpt-on-wechat)含有最新功能，但是稳定性有待测试)，感兴趣的可以关注并体验。开启了godcmd, Banwords, role, dungeon, finish这五个插件，其他的插件还没有测试。百度的接口暂未测试。语音对话没有测试。图片直接以链接形式回复（没有临时素材上传接口的权限）。
+
+## TODO
+* 服务号交互完善
+* 服务号使用临时素材接口，提供图片回复能力
+* 插件测试

channel/wechatmp/ServiceAccount.py

@@ -0,0 +1,51 @@
+import web
+import time
+import channel.wechatmp.reply as reply
+import channel.wechatmp.receive as receive
+from config import conf
+from common.log import logger
+from bridge.context import *
+from channel.wechatmp.common import * 
+from channel.wechatmp.wechatmp_channel import WechatMPChannel
+
+# This class is instantiated once per query
+class Query():
+
+    def GET(self):
+        return verify_server(web.input())
+
+    def POST(self):
+        # Make sure to return the instance that first created, @singleton will do that. 
+        channel_instance = WechatMPChannel()
+        try:
+            webData = web.data()
+            # logger.debug("[wechatmp] Receive request:\n" + webData.decode("utf-8"))
+            wechatmp_msg = receive.parse_xml(webData)
+            if wechatmp_msg.msg_type == 'text':
+                from_user = wechatmp_msg.from_user_id
+                message = wechatmp_msg.content.decode("utf-8")
+                message_id = wechatmp_msg.msg_id
+
+                logger.info("[wechatmp] {}:{} Receive post query {} {}: {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), from_user, message_id, message))
+                context = channel_instance._compose_context(ContextType.TEXT, message, isgroup=False, msg=wechatmp_msg)
+                if context:
+                    # set private openai_api_key
+                    # if from_user is not changed in itchat, this can be placed at chat_channel
+                    user_data = conf().get_user_data(from_user)
+                    context['openai_api_key'] = user_data.get('openai_api_key') # None or user openai_api_key
+                    channel_instance.produce(context)
+                # The reply will be sent by channel_instance.send() in another thread
+                return "success"
+
+            elif wechatmp_msg.msg_type == 'event':
+                logger.info("[wechatmp] Event {} from {}".format(wechatmp_msg.Event, wechatmp_msg.from_user_id))
+                content = subscribe_msg()
+                replyMsg = reply.TextMsg(wechatmp_msg.from_user_id, wechatmp_msg.to_user_id, content)
+                return replyMsg.send()
+            else:
+                logger.info("暂且不处理")
+                return "success"
+        except Exception as exc:
+            logger.exception(exc)
+            return exc
+

channel/wechatmp/SubscribeAccount.py

@@ -0,0 +1,165 @@
+import web
+import time
+import channel.wechatmp.reply as reply
+import channel.wechatmp.receive as receive
+from config import conf
+from common.log import logger
+from bridge.context import *
+from channel.wechatmp.common import * 
+from channel.wechatmp.wechatmp_channel import WechatMPChannel
+
+# This class is instantiated once per query
+class Query():
+
+    def GET(self):
+        return verify_server(web.input())
+
+    def POST(self):
+        # Make sure to return the instance that first created, @singleton will do that. 
+        channel = WechatMPChannel()
+        try:
+            query_time = time.time()
+            webData = web.data()
+            logger.debug("[wechatmp] Receive request:\n" + webData.decode("utf-8"))
+            wechatmp_msg = receive.parse_xml(webData)
+            if wechatmp_msg.msg_type == 'text':
+                from_user = wechatmp_msg.from_user_id
+                to_user = wechatmp_msg.to_user_id
+                message = wechatmp_msg.content.decode("utf-8")
+                message_id = wechatmp_msg.msg_id
+
+                logger.info("[wechatmp] {}:{} Receive post query {} {}: {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), from_user, message_id, message))
+                supported = True
+                if "【收到不支持的消息类型，暂无法显示】" in message:
+                    supported = False # not supported, used to refresh
+                cache_key = from_user
+
+                reply_text = ""
+                # New request
+                if cache_key not in channel.cache_dict and cache_key not in channel.running:
+                    # The first query begin, reset the cache
+                    context = channel._compose_context(ContextType.TEXT, message, isgroup=False, msg=wechatmp_msg)
+                    logger.debug("[wechatmp] context: {} {}".format(context, wechatmp_msg))
+                    if message_id in channel.received_msgs: # received and finished
+                        return 
+                    if supported and context:
+                        # set private openai_api_key
+                        # if from_user is not changed in itchat, this can be placed at chat_channel
+                        user_data = conf().get_user_data(from_user)
+                        context['openai_api_key'] = user_data.get('openai_api_key') # None or user openai_api_key
+                        channel.received_msgs[message_id] = wechatmp_msg
+                        channel.running.add(cache_key)
+                        channel.produce(context)
+                    else:
+                        trigger_prefix = conf().get('single_chat_prefix',[''])[0]
+                        if trigger_prefix or not supported:
+                            if trigger_prefix:
+                                content = textwrap.dedent(f"""\
+                                    请输入'{trigger_prefix}'接你想说的话跟我说话。
+                                    例如:
+                                    {trigger_prefix}你好，很高兴见到你。""")
+                            else:
+                                content = textwrap.dedent("""\
+                                    你好，很高兴见到你。
+                                    请跟我说话吧。""")
+                        else:
+                            logger.error(f"[wechatmp] unknown error")
+                            content = textwrap.dedent("""\
+                                未知错误，请稍后再试""")
+                        replyMsg = reply.TextMsg(wechatmp_msg.from_user_id, wechatmp_msg.to_user_id, content)
+                        return replyMsg.send()
+                    channel.query1[cache_key] = False
+                    channel.query2[cache_key] = False
+                    channel.query3[cache_key] = False
+                # Request again
+                elif cache_key in channel.running and channel.query1.get(cache_key) == True and channel.query2.get(cache_key) == True and channel.query3.get(cache_key) == True:
+                    channel.query1[cache_key] = False  #To improve waiting experience, this can be set to True.
+                    channel.query2[cache_key] = False  #To improve waiting experience, this can be set to True.
+                    channel.query3[cache_key] = False
+                elif cache_key in channel.cache_dict:
+                    # Skip the waiting phase
+                    channel.query1[cache_key] = True
+                    channel.query2[cache_key] = True
+                    channel.query3[cache_key] = True
+
+                assert not (cache_key in channel.cache_dict and cache_key in channel.running)
+
+                if channel.query1.get(cache_key) == False:
+                    # The first query from wechat official server
+                    logger.debug("[wechatmp] query1 {}".format(cache_key))
+                    channel.query1[cache_key] = True
+                    cnt = 0
+                    while cache_key not in channel.cache_dict and cnt < 45:
+                        cnt = cnt + 1
+                        time.sleep(0.1)
+                    if cnt == 45:
+                        # waiting for timeout (the POST query will be closed by wechat official server)
+                        time.sleep(1)
+                        # and do nothing
+                        return
+                    else:
+                        pass
+                elif channel.query2.get(cache_key) == False:
+                    # The second query from wechat official server
+                    logger.debug("[wechatmp] query2 {}".format(cache_key))
+                    channel.query2[cache_key] = True
+                    cnt = 0
+                    while cache_key not in channel.cache_dict and cnt < 45:
+                        cnt = cnt + 1
+                        time.sleep(0.1)
+                    if cnt == 45:
+                        # waiting for timeout (the POST query will be closed by wechat official server)
+                        time.sleep(1)
+                        # and do nothing
+                        return
+                    else:
+                        pass
+                elif channel.query3.get(cache_key) == False:
+                    # The third query from wechat official server
+                    logger.debug("[wechatmp] query3 {}".format(cache_key))
+                    channel.query3[cache_key] = True
+                    cnt = 0
+                    while cache_key not in channel.cache_dict and cnt < 40:
+                        cnt = cnt + 1
+                        time.sleep(0.1)
+                    if cnt == 40:
+                        # Have waiting for 3x5 seconds
+                        # return timeout message
+                        reply_text = "【正在思考中，回复任意文字尝试获取回复】"
+                        logger.info("[wechatmp] Three queries has finished For {}: {}".format(from_user, message_id))
+                        replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
+                        return replyPost
+                    else:
+                        pass
+
+                if float(time.time()) - float(query_time) > 4.8:
+                    reply_text = "【正在思考中，回复任意文字尝试获取回复】"
+                    logger.info("[wechatmp] Timeout for {} {}, return".format(from_user, message_id))
+                    replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
+                    return replyPost
+
+                if cache_key in channel.cache_dict:
+                    content = channel.cache_dict[cache_key]
+                    if len(content.encode('utf8'))<=MAX_UTF8_LEN:
+                        reply_text = channel.cache_dict[cache_key]
+                        channel.cache_dict.pop(cache_key)
+                    else:
+                        continue_text = "\n【未完待续，回复任意文字以继续】"
+                        splits = split_string_by_utf8_length(content, MAX_UTF8_LEN - len(continue_text.encode('utf-8')), max_split= 1)
+                        reply_text = splits[0] + continue_text
+                        channel.cache_dict[cache_key] = splits[1]
+                logger.info("[wechatmp] {}:{} Do send {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), reply_text))
+                replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
+                return replyPost
+
+            elif wechatmp_msg.msg_type == 'event':
+                logger.info("[wechatmp] Event {} from {}".format(wechatmp_msg.content, wechatmp_msg.from_user_id))
+                content = subscribe_msg()
+                replyMsg = reply.TextMsg(wechatmp_msg.from_user_id, wechatmp_msg.to_user_id, content)
+                return replyMsg.send()
+            else:
+                logger.info("暂且不处理")
+                return "success"
+        except Exception as exc:
+            logger.exception(exc)
+            return exc

channel/wechatmp/common.py

@@ -0,0 +1,63 @@
+from config import conf
+import hashlib
+import textwrap
+
+MAX_UTF8_LEN = 2048
+
+class WeChatAPIException(Exception):
+    pass
+
+
+def verify_server(data):
+    try:
+        if len(data) == 0:
+            return "None"
+        signature = data.signature
+        timestamp = data.timestamp
+        nonce = data.nonce
+        echostr = data.echostr
+        token = conf().get('wechatmp_token') #请按照公众平台官网\基本配置中信息填写
+
+        data_list = [token, timestamp, nonce]
+        data_list.sort()
+        sha1 = hashlib.sha1()
+        # map(sha1.update, data_list) #python2
+        sha1.update("".join(data_list).encode('utf-8'))
+        hashcode = sha1.hexdigest()
+        print("handle/GET func: hashcode, signature: ", hashcode, signature)
+        if hashcode == signature:
+            return echostr
+        else:
+            return ""
+    except Exception as Argument:
+        return Argument
+
+def subscribe_msg():
+    trigger_prefix = conf().get('single_chat_prefix',[''])[0]
+    msg = textwrap.dedent(f"""\
+                    感谢您的关注！
+                    这里是ChatGPT，可以自由对话。
+                    资源有限，回复较慢，请勿着急。
+                    支持通用表情输入。
+                    暂时不支持图片输入。
+                    支持图片输出，画字开头的问题将回复图片链接。
+                    支持角色扮演和文字冒险两种定制模式对话。
+                    输入'{trigger_prefix}#帮助' 查看详细指令。""")
+    return msg
+
+
+def split_string_by_utf8_length(string, max_length, max_split=0):
+    encoded = string.encode('utf-8')
+    start, end = 0, 0
+    result = []
+    while end < len(encoded):
+        if max_split > 0 and len(result) >= max_split:
+            result.append(encoded[start:].decode('utf-8'))
+            break
+        end = start + max_length
+        # 如果当前字节不是 UTF-8 编码的开始字节，则向前查找直到找到开始字节为止
+        while end < len(encoded) and (encoded[end] & 0b11000000) == 0b10000000:
+            end -= 1
+        result.append(encoded[start:end].decode('utf-8'))
+        start = end
+    return result