Upload 153 files

Dockerfile

@@ -0,0 +1,3 @@
+FROM ghcr.io/zhayujie/chatgpt-on-wechat:latest
+
+ENTRYPOINT ["/entrypoint.sh"]

LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2022 zhayujie
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

app.py

@@ -0,0 +1,57 @@
+# encoding:utf-8
+
+import os
+import signal
+import sys
+
+from channel import channel_factory
+from common.log import logger
+from config import conf, load_config
+from plugins import *
+
+
+def sigterm_handler_wrap(_signo):
+    old_handler = signal.getsignal(_signo)
+
+    def func(_signo, _stack_frame):
+        logger.info("signal {} received, exiting...".format(_signo))
+        conf().save_user_datas()
+        if callable(old_handler):  #  check old_handler
+            return old_handler(_signo, _stack_frame)
+        sys.exit(0)
+
+    signal.signal(_signo, func)
+
+
+def run():
+    try:
+        # load config
+        load_config()
+        # ctrl + c
+        sigterm_handler_wrap(signal.SIGINT)
+        # kill signal
+        sigterm_handler_wrap(signal.SIGTERM)
+
+        # create channel
+        channel_name = conf().get("channel_type", "wx")
+
+        if "--cmd" in sys.argv:
+            channel_name = "terminal"
+
+        if channel_name == "wxy":
+            os.environ["WECHATY_LOG"] = "warn"
+            # os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'
+
+        channel = channel_factory.create_channel(channel_name)
+        if channel_name in ["wx", "wxy", "terminal", "wechatmp", "wechatmp_service", "wechatcom_app"]:
+            PluginManager().load_plugins()
+
+        # startup channel
+        channel.startup()
+    except Exception as e:
+        logger.error("App startup failed!")
+        logger.exception(e)
+
+
+if __name__ == "__main__":
+    run()

bot/baidu/baidu_unit_bot.py

@@ -0,0 +1,36 @@
+# encoding:utf-8
+
+import requests
+
+from bot.bot import Bot
+from bridge.reply import Reply, ReplyType
+
+
+# Baidu Unit对话接口 (可用, 但能力较弱)
+class BaiduUnitBot(Bot):
+    def reply(self, query, context=None):
+        token = self.get_token()
+        url = "https://aip.baidubce.com/rpc/2.0/unit/service/v3/chat?access_token=" + token
+        post_data = (
+            '{"version":"3.0","service_id":"S73177","session_id":"","log_id":"7758521","skill_ids":["1221886"],"request":{"terminal_id":"88888","query":"'
+            + query
+            + '", "hyper_params": {"chat_custom_bot_profile": 1}}}'
+        )
+        print(post_data)
+        headers = {"content-type": "application/x-www-form-urlencoded"}
+        response = requests.post(url, data=post_data.encode(), headers=headers)
+        if response:
+            reply = Reply(
+                ReplyType.TEXT,
+                response.json()["result"]["context"]["SYS_PRESUMED_HIST"][1],
+            )
+            return reply
+
+    def get_token(self):
+        access_key = "YOUR_ACCESS_KEY"
+        secret_key = "YOUR_SECRET_KEY"
+        host = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=" + access_key + "&client_secret=" + secret_key
+        response = requests.get(host)
+        if response:
+            print(response.json())
+            return response.json()["access_token"]

bot/baidu/baidu_wenxin.py

@@ -0,0 +1,104 @@
+# encoding:utf-8
+
+import requests, json
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+from bot.baidu.baidu_wenxin_session import BaiduWenxinSession
+
+BAIDU_API_KEY = conf().get("baidu_wenxin_api_key")
+BAIDU_SECRET_KEY = conf().get("baidu_wenxin_secret_key")
+
+class BaiduWenxinBot(Bot):
+
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(BaiduWenxinSession, model=conf().get("baidu_wenxin_model") or "eb-instant")
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context and context.type:
+            if context.type == ContextType.TEXT:
+                logger.info("[BAIDU] query={}".format(query))
+                session_id = context["session_id"]
+                reply = None
+                if query == "#清除记忆":
+                    self.sessions.clear_session(session_id)
+                    reply = Reply(ReplyType.INFO, "记忆已清除")
+                elif query == "#清除所有":
+                    self.sessions.clear_all_session()
+                    reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+                else:
+                    session = self.sessions.session_query(query, session_id)
+                    result = self.reply_text(session)
+                    total_tokens, completion_tokens, reply_content = (
+                        result["total_tokens"],
+                        result["completion_tokens"],
+                        result["content"],
+                    )
+                    logger.debug(
+                        "[BAIDU] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(session.messages, session_id, reply_content, completion_tokens)
+                    )
+
+                    if total_tokens == 0:
+                        reply = Reply(ReplyType.ERROR, reply_content)
+                    else:
+                        self.sessions.session_reply(reply_content, session_id, total_tokens)
+                        reply = Reply(ReplyType.TEXT, reply_content)
+                return reply
+            elif context.type == ContextType.IMAGE_CREATE:
+                ok, retstring = self.create_img(query, 0)
+                reply = None
+                if ok:
+                    reply = Reply(ReplyType.IMAGE_URL, retstring)
+                else:
+                    reply = Reply(ReplyType.ERROR, retstring)
+                return reply
+
+    def reply_text(self, session: BaiduWenxinSession, retry_count=0):
+        try:
+            logger.info("[BAIDU] model={}".format(session.model))
+            access_token = self.get_access_token()
+            if access_token == 'None':
+                logger.warn("[BAIDU] access token 获取失败")
+                return {
+                    "total_tokens": 0,
+                    "completion_tokens": 0,
+                    "content": 0,
+                    }
+            url = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/" + session.model + "?access_token=" + access_token
+            headers = {
+                'Content-Type': 'application/json'
+            }
+            payload = {'messages': session.messages}
+            response = requests.request("POST", url, headers=headers, data=json.dumps(payload))
+            response_text = json.loads(response.text)
+            logger.info(f"[BAIDU] response text={response_text}")
+            res_content = response_text["result"]
+            total_tokens = response_text["usage"]["total_tokens"]
+            completion_tokens = response_text["usage"]["completion_tokens"]
+            logger.info("[BAIDU] reply={}".format(res_content))
+            return {
+                "total_tokens": total_tokens,
+                "completion_tokens": completion_tokens,
+                "content": res_content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            logger.warn("[BAIDU] Exception: {}".format(e))
+            need_retry = False
+            self.sessions.clear_session(session.session_id)
+            result = {"completion_tokens": 0, "content": "出错了: {}".format(e)}
+            return result
+
+    def get_access_token(self):
+        """
+        使用 AK，SK 生成鉴权签名（Access Token）
+        :return: access_token，或是None(如果错误)
+        """
+        url = "https://aip.baidubce.com/oauth/2.0/token"
+        params = {"grant_type": "client_credentials", "client_id": BAIDU_API_KEY, "client_secret": BAIDU_SECRET_KEY}
+        return str(requests.post(url, params=params).json().get("access_token"))

bot/baidu/baidu_wenxin_session.py

@@ -0,0 +1,53 @@
+from bot.session_manager import Session
+from common.log import logger
+
+"""
+    e.g.  [
+        {"role": "user", "content": "Who won the world series in 2020?"},
+        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
+        {"role": "user", "content": "Where was it played?"}
+    ]
+"""
+
+
+class BaiduWenxinSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="gpt-3.5-turbo"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        # 百度文心不支持system prompt
+        # self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) >= 2:
+                self.messages.pop(0)
+                self.messages.pop(0)
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens, len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+def num_tokens_from_messages(messages, model):
+    """Returns the number of tokens used by a list of messages."""
+    tokens = 0
+    for msg in messages:
+        # 官方token计算规则暂不明确： "大约为 token数为 "中文字 + 其他语种单词数 x 1.3"
+        # 这里先直接根据字数粗略估算吧，暂不影响正常使用，仅在判断是否丢弃历史会话的时候会有偏差
+        tokens += len(msg["content"])
+    return tokens

bot/bot.py

@@ -0,0 +1,17 @@
+"""
+Auto-replay chat robot abstract class
+"""
+
+
+from bridge.context import Context
+from bridge.reply import Reply
+
+
+class Bot(object):
+    def reply(self, query, context: Context = None) -> Reply:
+        """
+        bot auto-reply content
+        :param req: received message
+        :return: reply content
+        """
+        raise NotImplementedError

bot/bot_factory.py

@@ -0,0 +1,42 @@
+"""
+channel factory
+"""
+from common import const
+
+
+def create_bot(bot_type):
+    """
+    create a bot_type instance
+    :param bot_type: bot type code
+    :return: bot instance
+    """
+    if bot_type == const.BAIDU:
+        # 替换Baidu Unit为Baidu文心千帆对话接口
+        # from bot.baidu.baidu_unit_bot import BaiduUnitBot
+        # return BaiduUnitBot()
+        from bot.baidu.baidu_wenxin import BaiduWenxinBot
+        return BaiduWenxinBot()
+
+    elif bot_type == const.CHATGPT:
+        # ChatGPT 网页端web接口
+        from bot.chatgpt.chat_gpt_bot import ChatGPTBot
+        return ChatGPTBot()
+
+    elif bot_type == const.OPEN_AI:
+        # OpenAI 官方对话模型API
+        from bot.openai.open_ai_bot import OpenAIBot
+        return OpenAIBot()
+
+    elif bot_type == const.CHATGPTONAZURE:
+        # Azure chatgpt service https://azure.microsoft.com/en-in/products/cognitive-services/openai-service/
+        from bot.chatgpt.chat_gpt_bot import AzureChatGPTBot
+        return AzureChatGPTBot()
+
+    elif bot_type == const.XUNFEI:
+        from bot.xunfei.xunfei_spark_bot import XunFeiBot
+        return XunFeiBot()
+
+    elif bot_type == const.LINKAI:
+        from bot.linkai.link_ai_bot import LinkAIBot
+        return LinkAIBot()
+    raise RuntimeError

bot/chatgpt/chat_gpt_bot.py

@@ -0,0 +1,193 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+import requests
+
+from bot.bot import Bot
+from bot.chatgpt.chat_gpt_session import ChatGPTSession
+from bot.openai.open_ai_image import OpenAIImage
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.token_bucket import TokenBucket
+from config import conf, load_config
+
+
+# OpenAI对话模型API (可用)
+class ChatGPTBot(Bot, OpenAIImage):
+    def __init__(self):
+        super().__init__()
+        # set the default api_key
+        openai.api_key = conf().get("open_ai_api_key")
+        if conf().get("open_ai_api_base"):
+            openai.api_base = conf().get("open_ai_api_base")
+        proxy = conf().get("proxy")
+        if proxy:
+            openai.proxy = proxy
+        if conf().get("rate_limit_chatgpt"):
+            self.tb4chatgpt = TokenBucket(conf().get("rate_limit_chatgpt", 20))
+
+        self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "gpt-3.5-turbo")
+        self.args = {
+            "model": conf().get("model") or "gpt-3.5-turbo",  # 对话模型的名称
+            "temperature": conf().get("temperature", 0.9),  # 值在[0,1]之间，越大表示回复越具有不确定性
+            # "max_tokens":4096,  # 回复最大的字符数
+            "top_p": conf().get("top_p", 1),
+            "frequency_penalty": conf().get("frequency_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+            "presence_penalty": conf().get("presence_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+            "request_timeout": conf().get("request_timeout", None),  # 请求超时时间，openai接口默认设置为600，对于难问题一般需要较长时间
+            "timeout": conf().get("request_timeout", None),  # 重试超时时间，在这个时间内，将会自动重试
+        }
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[CHATGPT] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[CHATGPT] session query={}".format(session.messages))
+
+            api_key = context.get("openai_api_key")
+            model = context.get("gpt_model")
+            new_args = None
+            if model:
+                new_args = self.args.copy()
+                new_args["model"] = model
+            # if context.get('stream'):
+            #     # reply in stream
+            #     return self.reply_text_stream(query, new_query, session_id)
+
+            reply_content = self.reply_text(session, api_key, args=new_args)
+            logger.debug(
+                "[CHATGPT] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[CHATGPT] reply {} used 0 tokens.".format(reply_content))
+            return reply
+
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, retstring = self.create_img(query, 0)
+            reply = None
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, retstring)
+            else:
+                reply = Reply(ReplyType.ERROR, retstring)
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: ChatGPTSession, api_key=None, args=None, retry_count=0) -> dict:
+        """
+        call openai's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param session_id: session id
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            if conf().get("rate_limit_chatgpt") and not self.tb4chatgpt.get_token():
+                raise openai.error.RateLimitError("RateLimitError: rate limit exceeded")
+            # if api_key == None, the default openai.api_key will be used
+            if args is None:
+                args = self.args
+            response = openai.ChatCompletion.create(api_key=api_key, messages=session.messages, **args)
+            # logger.debug("[CHATGPT] response={}".format(response))
+            # logger.info("[ChatGPT] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
+            return {
+                "total_tokens": response["usage"]["total_tokens"],
+                "completion_tokens": response["usage"]["completion_tokens"],
+                "content": response.choices[0]["message"]["content"],
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if isinstance(e, openai.error.RateLimitError):
+                logger.warn("[CHATGPT] RateLimitError: {}".format(e))
+                result["content"] = "提问太快啦，请休息一下再问我吧"
+                if need_retry:
+                    time.sleep(20)
+            elif isinstance(e, openai.error.Timeout):
+                logger.warn("[CHATGPT] Timeout: {}".format(e))
+                result["content"] = "我没有收到你的消息"
+                if need_retry:
+                    time.sleep(5)
+            elif isinstance(e, openai.error.APIError):
+                logger.warn("[CHATGPT] Bad Gateway: {}".format(e))
+                result["content"] = "请再问我一次"
+                if need_retry:
+                    time.sleep(10)
+            elif isinstance(e, openai.error.APIConnectionError):
+                logger.warn("[CHATGPT] APIConnectionError: {}".format(e))
+                need_retry = False
+                result["content"] = "我连接不到你的网络"
+            else:
+                logger.exception("[CHATGPT] Exception: {}".format(e))
+                need_retry = False
+                self.sessions.clear_session(session.session_id)
+
+            if need_retry:
+                logger.warn("[CHATGPT] 第{}次重试".format(retry_count + 1))
+                return self.reply_text(session, api_key, args, retry_count + 1)
+            else:
+                return result
+
+
+class AzureChatGPTBot(ChatGPTBot):
+    def __init__(self):
+        super().__init__()
+        openai.api_type = "azure"
+        openai.api_version = conf().get("azure_api_version", "2023-06-01-preview")
+        self.args["deployment_id"] = conf().get("azure_deployment_id")
+
+    def create_img(self, query, retry_count=0, api_key=None):
+        api_version = "2022-08-03-preview"
+        url = "{}dalle/text-to-image?api-version={}".format(openai.api_base, api_version)
+        api_key = api_key or openai.api_key
+        headers = {"api-key": api_key, "Content-Type": "application/json"}
+        try:
+            body = {"caption": query, "resolution": conf().get("image_create_size", "256x256")}
+            submission = requests.post(url, headers=headers, json=body)
+            operation_location = submission.headers["Operation-Location"]
+            retry_after = submission.headers["Retry-after"]
+            status = ""
+            image_url = ""
+            while status != "Succeeded":
+                logger.info("waiting for image create..., " + status + ",retry after " + retry_after + " seconds")
+                time.sleep(int(retry_after))
+                response = requests.get(operation_location, headers=headers)
+                status = response.json()["status"]
+            image_url = response.json()["result"]["contentUrl"]
+            return True, image_url
+        except Exception as e:
+            logger.error("create image error: {}".format(e))
+            return False, "图片生成失败"

bot/chatgpt/chat_gpt_session.py

@@ -0,0 +1,100 @@
+from bot.session_manager import Session
+from common.log import logger
+
+"""
+    e.g.  [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Who won the world series in 2020?"},
+        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
+        {"role": "user", "content": "Where was it played?"}
+    ]
+"""
+
+
+class ChatGPTSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="gpt-3.5-turbo"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens, len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+# refer to https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
+def num_tokens_from_messages(messages, model):
+    """Returns the number of tokens used by a list of messages."""
+
+    if model in ["wenxin", "xunfei"]:
+        return num_tokens_by_character(messages)
+
+    import tiktoken
+
+    if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo"]:
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
+    elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
+                   "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k"]:
+        return num_tokens_from_messages(messages, model="gpt-4")
+
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        logger.debug("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+    if model == "gpt-3.5-turbo":
+        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
+        tokens_per_name = -1  # if there's a name, the role is omitted
+    elif model == "gpt-4":
+        tokens_per_message = 3
+        tokens_per_name = 1
+    else:
+        logger.warn(f"num_tokens_from_messages() is not implemented for model {model}. Returning num tokens assuming gpt-3.5-turbo.")
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
+    num_tokens = 0
+    for message in messages:
+        num_tokens += tokens_per_message
+        for key, value in message.items():
+            num_tokens += len(encoding.encode(value))
+            if key == "name":
+                num_tokens += tokens_per_name
+    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
+    return num_tokens
+
+
+def num_tokens_by_character(messages):
+    """Returns the number of tokens used by a list of messages."""
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/linkai/link_ai_bot.py

@@ -0,0 +1,116 @@
+# access LinkAI knowledge base platform
+# docs: https://link-ai.tech/platform/link-app/wechat
+
+import time
+
+import requests
+
+from bot.bot import Bot
+from bot.chatgpt.chat_gpt_session import ChatGPTSession
+from bot.openai.open_ai_image import OpenAIImage
+from bot.session_manager import SessionManager
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+
+
+class LinkAIBot(Bot, OpenAIImage):
+    # authentication failed
+    AUTH_FAILED_CODE = 401
+    NO_QUOTA_CODE = 406
+
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "gpt-3.5-turbo")
+
+    def reply(self, query, context: Context = None) -> Reply:
+        if context.type == ContextType.TEXT:
+            return self._chat(query, context)
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, res = self.create_img(query, 0)
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, res)
+            else:
+                reply = Reply(ReplyType.ERROR, res)
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def _chat(self, query, context, retry_count=0) -> Reply:
+        """
+        发起对话请求
+        :param query: 请求提示词
+        :param context: 对话上下文
+        :param retry_count: 当前递归重试次数
+        :return: 回复
+        """
+        if retry_count >= 2:
+            # exit from retry 2 times
+            logger.warn("[LINKAI] failed after maximum number of retry times")
+            return Reply(ReplyType.ERROR, "请再问我一次吧")
+
+        try:
+            # load config
+            if context.get("generate_breaked_by"):
+                logger.info(f"[LINKAI] won't set appcode because a plugin ({context['generate_breaked_by']}) affected the context")
+                app_code = None
+            else:
+                app_code = context.kwargs.get("app_code") or conf().get("linkai_app_code")
+            linkai_api_key = conf().get("linkai_api_key")
+
+            session_id = context["session_id"]
+
+            session = self.sessions.session_query(query, session_id)
+            model = conf().get("model") or "gpt-3.5-turbo"
+            # remove system message
+            if session.messages[0].get("role") == "system":
+                if app_code or model == "wenxin":
+                    session.messages.pop(0)
+
+            body = {
+                "app_code": app_code,
+                "messages": session.messages,
+                "model": model,     # 对话模型的名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin
+                "temperature": conf().get("temperature"),
+                "top_p": conf().get("top_p", 1),
+                "frequency_penalty": conf().get("frequency_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+                "presence_penalty": conf().get("presence_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+            }
+            logger.info(f"[LINKAI] query={query}, app_code={app_code}, mode={body.get('model')}")
+            headers = {"Authorization": "Bearer " + linkai_api_key}
+
+            # do http request
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
+                                timeout=conf().get("request_timeout", 180))
+            if res.status_code == 200:
+                # execute success
+                response = res.json()
+                reply_content = response["choices"][0]["message"]["content"]
+                total_tokens = response["usage"]["total_tokens"]
+                logger.info(f"[LINKAI] reply={reply_content}, total_tokens={total_tokens}")
+                self.sessions.session_reply(reply_content, session_id, total_tokens)
+                return Reply(ReplyType.TEXT, reply_content)
+
+            else:
+                response = res.json()
+                error = response.get("error")
+                logger.error(f"[LINKAI] chat failed, status_code={res.status_code}, "
+                             f"msg={error.get('message')}, type={error.get('type')}")
+
+                if res.status_code >= 500:
+                    # server error, need retry
+                    time.sleep(2)
+                    logger.warn(f"[LINKAI] do retry, times={retry_count}")
+                    return self._chat(query, context, retry_count + 1)
+
+                return Reply(ReplyType.ERROR, "提问太快啦，请休息一下再问我吧")
+
+        except Exception as e:
+            logger.exception(e)
+            # retry
+            time.sleep(2)
+            logger.warn(f"[LINKAI] do retry, times={retry_count}")
+            return self._chat(query, context, retry_count + 1)

bot/openai/open_ai_bot.py

@@ -0,0 +1,122 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+
+from bot.bot import Bot
+from bot.openai.open_ai_image import OpenAIImage
+from bot.openai.open_ai_session import OpenAISession
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+
+user_session = dict()
+
+
+# OpenAI对话模型API (可用)
+class OpenAIBot(Bot, OpenAIImage):
+    def __init__(self):
+        super().__init__()
+        openai.api_key = conf().get("open_ai_api_key")
+        if conf().get("open_ai_api_base"):
+            openai.api_base = conf().get("open_ai_api_base")
+        proxy = conf().get("proxy")
+        if proxy:
+            openai.proxy = proxy
+
+        self.sessions = SessionManager(OpenAISession, model=conf().get("model") or "text-davinci-003")
+        self.args = {
+            "model": conf().get("model") or "text-davinci-003",  # 对话模型的名称
+            "temperature": conf().get("temperature", 0.9),  # 值在[0,1]之间，越大表示回复越具有不确定性
+            "max_tokens": 1200,  # 回复最大的字符数
+            "top_p": 1,
+            "frequency_penalty": conf().get("frequency_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+            "presence_penalty": conf().get("presence_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+            "request_timeout": conf().get("request_timeout", None),  # 请求超时时间，openai接口默认设置为600，对于难问题一般需要较长时间
+            "timeout": conf().get("request_timeout", None),  # 重试超时时间，在这个时间内，将会自动重试
+            "stop": ["\n\n\n"],
+        }
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context and context.type:
+            if context.type == ContextType.TEXT:
+                logger.info("[OPEN_AI] query={}".format(query))
+                session_id = context["session_id"]
+                reply = None
+                if query == "#清除记忆":
+                    self.sessions.clear_session(session_id)
+                    reply = Reply(ReplyType.INFO, "记忆已清除")
+                elif query == "#清除所有":
+                    self.sessions.clear_all_session()
+                    reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+                else:
+                    session = self.sessions.session_query(query, session_id)
+                    result = self.reply_text(session)
+                    total_tokens, completion_tokens, reply_content = (
+                        result["total_tokens"],
+                        result["completion_tokens"],
+                        result["content"],
+                    )
+                    logger.debug(
+                        "[OPEN_AI] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(str(session), session_id, reply_content, completion_tokens)
+                    )
+
+                    if total_tokens == 0:
+                        reply = Reply(ReplyType.ERROR, reply_content)
+                    else:
+                        self.sessions.session_reply(reply_content, session_id, total_tokens)
+                        reply = Reply(ReplyType.TEXT, reply_content)
+                return reply
+            elif context.type == ContextType.IMAGE_CREATE:
+                ok, retstring = self.create_img(query, 0)
+                reply = None
+                if ok:
+                    reply = Reply(ReplyType.IMAGE_URL, retstring)
+                else:
+                    reply = Reply(ReplyType.ERROR, retstring)
+                return reply
+
+    def reply_text(self, session: OpenAISession, retry_count=0):
+        try:
+            response = openai.Completion.create(prompt=str(session), **self.args)
+            res_content = response.choices[0]["text"].strip().replace("<|endoftext|>", "")
+            total_tokens = response["usage"]["total_tokens"]
+            completion_tokens = response["usage"]["completion_tokens"]
+            logger.info("[OPEN_AI] reply={}".format(res_content))
+            return {
+                "total_tokens": total_tokens,
+                "completion_tokens": completion_tokens,
+                "content": res_content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if isinstance(e, openai.error.RateLimitError):
+                logger.warn("[OPEN_AI] RateLimitError: {}".format(e))
+                result["content"] = "提问太快啦，请休息一下再问我吧"
+                if need_retry:
+                    time.sleep(20)
+            elif isinstance(e, openai.error.Timeout):
+                logger.warn("[OPEN_AI] Timeout: {}".format(e))
+                result["content"] = "我没有收到你的消息"
+                if need_retry:
+                    time.sleep(5)
+            elif isinstance(e, openai.error.APIConnectionError):
+                logger.warn("[OPEN_AI] APIConnectionError: {}".format(e))
+                need_retry = False
+                result["content"] = "我连接不到你的网络"
+            else:
+                logger.warn("[OPEN_AI] Exception: {}".format(e))
+                need_retry = False
+                self.sessions.clear_session(session.session_id)
+
+            if need_retry:
+                logger.warn("[OPEN_AI] 第{}次重试".format(retry_count + 1))
+                return self.reply_text(session, retry_count + 1)
+            else:
+                return result

bot/openai/open_ai_image.py

@@ -0,0 +1,42 @@
+import time
+
+import openai
+import openai.error
+
+from common.log import logger
+from common.token_bucket import TokenBucket
+from config import conf
+
+
+# OPENAI提供的画图接口
+class OpenAIImage(object):
+    def __init__(self):
+        openai.api_key = conf().get("open_ai_api_key")
+        if conf().get("rate_limit_dalle"):
+            self.tb4dalle = TokenBucket(conf().get("rate_limit_dalle", 50))
+
+    def create_img(self, query, retry_count=0, api_key=None):
+        try:
+            if conf().get("rate_limit_dalle") and not self.tb4dalle.get_token():
+                return False, "请求太快了，请休息一下再问我吧"
+            logger.info("[OPEN_AI] image_query={}".format(query))
+            response = openai.Image.create(
+                api_key=api_key,
+                prompt=query,  # 图片描述
+                n=1,  # 每次生成图片的数量
+                size=conf().get("image_create_size", "256x256"),  # 图片大小,可选有 256x256, 512x512, 1024x1024
+            )
+            image_url = response["data"][0]["url"]
+            logger.info("[OPEN_AI] image_url={}".format(image_url))
+            return True, image_url
+        except openai.error.RateLimitError as e:
+            logger.warn(e)
+            if retry_count < 1:
+                time.sleep(5)
+                logger.warn("[OPEN_AI] ImgCreate RateLimit exceed, 第{}次重试".format(retry_count + 1))
+                return self.create_img(query, retry_count + 1)
+            else:
+                return False, "提问太快啦，请休息一下再问我吧"
+        except Exception as e:
+            logger.exception(e)
+            return False, str(e)

bot/openai/open_ai_session.py

@@ -0,0 +1,73 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class OpenAISession(Session):
+    def __init__(self, session_id, system_prompt=None, model="text-davinci-003"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def __str__(self):
+        # 构造对话模型的输入
+        """
+        e.g.  Q: xxx
+              A: xxx
+              Q: xxx
+        """
+        prompt = ""
+        for item in self.messages:
+            if item["role"] == "system":
+                prompt += item["content"] + "<|endoftext|>\n\n\n"
+            elif item["role"] == "user":
+                prompt += "Q: " + item["content"] + "\n"
+            elif item["role"] == "assistant":
+                prompt += "\n\nA: " + item["content"] + "<|endoftext|>\n"
+
+        if len(self.messages) > 0 and self.messages[-1]["role"] == "user":
+            prompt += "A: "
+        return prompt
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 1:
+                self.messages.pop(0)
+            elif len(self.messages) == 1 and self.messages[0]["role"] == "assistant":
+                self.messages.pop(0)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = len(str(self))
+                break
+            elif len(self.messages) == 1 and self.messages[0]["role"] == "user":
+                logger.warn("user question exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(conversation)={}".format(max_tokens, cur_tokens, len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = len(str(self))
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_string(str(self), self.model)
+
+
+# refer to https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
+def num_tokens_from_string(string: str, model: str) -> int:
+    """Returns the number of tokens in a text string."""
+    import tiktoken
+
+    encoding = tiktoken.encoding_for_model(model)
+    num_tokens = len(encoding.encode(string, disallowed_special=()))
+    return num_tokens

bot/session_manager.py

@@ -0,0 +1,91 @@
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from config import conf
+
+
+class Session(object):
+    def __init__(self, session_id, system_prompt=None):
+        self.session_id = session_id
+        self.messages = []
+        if system_prompt is None:
+            self.system_prompt = conf().get("character_desc", "")
+        else:
+            self.system_prompt = system_prompt
+
+    # 重置会话
+    def reset(self):
+        system_item = {"role": "system", "content": self.system_prompt}
+        self.messages = [system_item]
+
+    def set_system_prompt(self, system_prompt):
+        self.system_prompt = system_prompt
+        self.reset()
+
+    def add_query(self, query):
+        user_item = {"role": "user", "content": query}
+        self.messages.append(user_item)
+
+    def add_reply(self, reply):
+        assistant_item = {"role": "assistant", "content": reply}
+        self.messages.append(assistant_item)
+
+    def discard_exceeding(self, max_tokens=None, cur_tokens=None):
+        raise NotImplementedError
+
+    def calc_tokens(self):
+        raise NotImplementedError
+
+
+class SessionManager(object):
+    def __init__(self, sessioncls, **session_args):
+        if conf().get("expires_in_seconds"):
+            sessions = ExpiredDict(conf().get("expires_in_seconds"))
+        else:
+            sessions = dict()
+        self.sessions = sessions
+        self.sessioncls = sessioncls
+        self.session_args = session_args
+
+    def build_session(self, session_id, system_prompt=None):
+        """
+        如果session_id不在sessions中，创建一个新的session并添加到sessions中
+        如果system_prompt不会空，会更新session的system_prompt并重置session
+        """
+        if session_id is None:
+            return self.sessioncls(session_id, system_prompt, **self.session_args)
+
+        if session_id not in self.sessions:
+            self.sessions[session_id] = self.sessioncls(session_id, system_prompt, **self.session_args)
+        elif system_prompt is not None:  # 如果有新的system_prompt，更新并重置session
+            self.sessions[session_id].set_system_prompt(system_prompt)
+        session = self.sessions[session_id]
+        return session
+
+    def session_query(self, query, session_id):
+        session = self.build_session(session_id)
+        session.add_query(query)
+        try:
+            max_tokens = conf().get("conversation_max_tokens", 1000)
+            total_tokens = session.discard_exceeding(max_tokens, None)
+            logger.debug("prompt tokens used={}".format(total_tokens))
+        except Exception as e:
+            logger.debug("Exception when counting tokens precisely for prompt: {}".format(str(e)))
+        return session
+
+    def session_reply(self, reply, session_id, total_tokens=None):
+        session = self.build_session(session_id)
+        session.add_reply(reply)
+        try:
+            max_tokens = conf().get("conversation_max_tokens", 1000)
+            tokens_cnt = session.discard_exceeding(max_tokens, total_tokens)
+            logger.debug("raw total_tokens={}, savesession tokens={}".format(total_tokens, tokens_cnt))
+        except Exception as e:
+            logger.debug("Exception when counting tokens precisely for session: {}".format(str(e)))
+        return session
+
+    def clear_session(self, session_id):
+        if session_id in self.sessions:
+            del self.sessions[session_id]
+
+    def clear_all_session(self):
+        self.sessions.clear()

bot/xunfei/xunfei_spark_bot.py

@@ -0,0 +1,250 @@
+# encoding:utf-8
+
+import requests, json
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bot.baidu.baidu_wenxin_session import BaiduWenxinSession
+from bridge.context import ContextType, Context
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+from common import const
+import time
+import _thread as thread
+import datetime
+from datetime import datetime
+from wsgiref.handlers import format_date_time
+from urllib.parse import urlencode
+import base64
+import ssl
+import hashlib
+import hmac
+import json
+from time import mktime
+from urllib.parse import urlparse
+import websocket
+import queue
+import threading
+import random
+
+# 消息队列 map
+queue_map = dict()
+
+# 响应队列 map
+reply_map = dict()
+
+
+class XunFeiBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.app_id = conf().get("xunfei_app_id")
+        self.api_key = conf().get("xunfei_api_key")
+        self.api_secret = conf().get("xunfei_api_secret")
+        # 默认使用v2.0版本，1.5版本可设置为 general
+        self.domain = "generalv2"
+        # 默认使用v2.0版本，1.5版本可设置为 "ws://spark-api.xf-yun.com/v1.1/chat"
+        self.spark_url = "ws://spark-api.xf-yun.com/v2.1/chat"
+        self.host = urlparse(self.spark_url).netloc
+        self.path = urlparse(self.spark_url).path
+        # 和wenxin使用相同的session机制
+        self.sessions = SessionManager(BaiduWenxinSession, model=const.XUNFEI)
+
+    def reply(self, query, context: Context = None) -> Reply:
+        if context.type == ContextType.TEXT:
+            logger.info("[XunFei] query={}".format(query))
+            session_id = context["session_id"]
+            request_id = self.gen_request_id(session_id)
+            reply_map[request_id] = ""
+            session = self.sessions.session_query(query, session_id)
+            threading.Thread(target=self.create_web_socket, args=(session.messages, request_id)).start()
+            depth = 0
+            time.sleep(0.1)
+            t1 = time.time()
+            usage = {}
+            while depth <= 300:
+                try:
+                    data_queue = queue_map.get(request_id)
+                    if not data_queue:
+                        depth += 1
+                        time.sleep(0.1)
+                        continue
+                    data_item = data_queue.get(block=True, timeout=0.1)
+                    if data_item.is_end:
+                        # 请求结束
+                        del queue_map[request_id]
+                        if data_item.reply:
+                            reply_map[request_id] += data_item.reply
+                        usage = data_item.usage
+                        break
+
+                    reply_map[request_id] += data_item.reply
+                    depth += 1
+                except Exception as e:
+                    depth += 1
+                    continue
+            t2 = time.time()
+            logger.info(f"[XunFei-API] response={reply_map[request_id]}, time={t2 - t1}s, usage={usage}")
+            self.sessions.session_reply(reply_map[request_id], session_id, usage.get("total_tokens"))
+            reply = Reply(ReplyType.TEXT, reply_map[request_id])
+            del reply_map[request_id]
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def create_web_socket(self, prompt, session_id, temperature=0.5):
+        logger.info(f"[XunFei] start connect, prompt={prompt}")
+        websocket.enableTrace(False)
+        wsUrl = self.create_url()
+        ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close,
+                                    on_open=on_open)
+        data_queue = queue.Queue(1000)
+        queue_map[session_id] = data_queue
+        ws.appid = self.app_id
+        ws.question = prompt
+        ws.domain = self.domain
+        ws.session_id = session_id
+        ws.temperature = temperature
+        ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
+
+    def gen_request_id(self, session_id: str):
+        return session_id + "_" + str(int(time.time())) + "" + str(random.randint(0, 100))
+
+    # 生成url
+    def create_url(self):
+        # 生成RFC1123格式的时间戳
+        now = datetime.now()
+        date = format_date_time(mktime(now.timetuple()))
+
+        # 拼接字符串
+        signature_origin = "host: " + self.host + "\n"
+        signature_origin += "date: " + date + "\n"
+        signature_origin += "GET " + self.path + " HTTP/1.1"
+
+        # 进行hmac-sha256进行加密
+        signature_sha = hmac.new(self.api_secret.encode('utf-8'), signature_origin.encode('utf-8'),
+                                 digestmod=hashlib.sha256).digest()
+
+        signature_sha_base64 = base64.b64encode(signature_sha).decode(encoding='utf-8')
+
+        authorization_origin = f'api_key="{self.api_key}", algorithm="hmac-sha256", headers="host date request-line", ' \
+                               f'signature="{signature_sha_base64}"'
+
+        authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')
+
+        # 将请求的鉴权参数组合为字典
+        v = {
+            "authorization": authorization,
+            "date": date,
+            "host": self.host
+        }
+        # 拼接鉴权参数，生成url
+        url = self.spark_url + '?' + urlencode(v)
+        # 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致
+        return url
+
+    def gen_params(self, appid, domain, question):
+        """
+        通过appid和用户的提问来生成请参数
+        """
+        data = {
+            "header": {
+                "app_id": appid,
+                "uid": "1234"
+            },
+            "parameter": {
+                "chat": {
+                    "domain": domain,
+                    "random_threshold": 0.5,
+                    "max_tokens": 2048,
+                    "auditing": "default"
+                }
+            },
+            "payload": {
+                "message": {
+                    "text": question
+                }
+            }
+        }
+        return data
+
+
+class ReplyItem:
+    def __init__(self, reply, usage=None, is_end=False):
+        self.is_end = is_end
+        self.reply = reply
+        self.usage = usage
+
+
+# 收到websocket错误的处理
+def on_error(ws, error):
+    logger.error(f"[XunFei] error: {str(error)}")
+
+
+# 收到websocket关闭的处理
+def on_close(ws, one, two):
+    data_queue = queue_map.get(ws.session_id)
+    data_queue.put("END")
+
+
+# 收到websocket连接建立的处理
+def on_open(ws):
+    logger.info(f"[XunFei] Start websocket, session_id={ws.session_id}")
+    thread.start_new_thread(run, (ws,))
+
+
+def run(ws, *args):
+    data = json.dumps(gen_params(appid=ws.appid, domain=ws.domain, question=ws.question, temperature=ws.temperature))
+    ws.send(data)
+
+
+# Websocket 操作
+# 收到websocket消息的处理
+def on_message(ws, message):
+    data = json.loads(message)
+    code = data['header']['code']
+    if code != 0:
+        logger.error(f'请求错误: {code}, {data}')
+        ws.close()
+    else:
+        choices = data["payload"]["choices"]
+        status = choices["status"]
+        content = choices["text"][0]["content"]
+        data_queue = queue_map.get(ws.session_id)
+        if not data_queue:
+            logger.error(f"[XunFei] can't find data queue, session_id={ws.session_id}")
+            return
+        reply_item = ReplyItem(content)
+        if status == 2:
+            usage = data["payload"].get("usage")
+            reply_item = ReplyItem(content, usage)
+            reply_item.is_end = True
+            ws.close()
+        data_queue.put(reply_item)
+
+
+def gen_params(appid, domain, question, temperature=0.5):
+    """
+    通过appid和用户的提问来生成请参数
+    """
+    data = {
+        "header": {
+            "app_id": appid,
+            "uid": "1234"
+        },
+        "parameter": {
+            "chat": {
+                "domain": domain,
+                "temperature": temperature,
+                "random_threshold": 0.5,
+                "max_tokens": 2048,
+                "auditing": "default"
+            }
+        },
+        "payload": {
+            "message": {
+                "text": question
+            }
+        }
+    }
+    return data

bridge/bridge.py

@@ -0,0 +1,66 @@
+from bot.bot_factory import create_bot
+from bridge.context import Context
+from bridge.reply import Reply
+from common import const
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+from translate.factory import create_translator
+from voice.factory import create_voice
+
+
+@singleton
+class Bridge(object):
+    def __init__(self):
+        self.btype = {
+            "chat": const.CHATGPT,
+            "voice_to_text": conf().get("voice_to_text", "openai"),
+            "text_to_voice": conf().get("text_to_voice", "google"),
+            "translate": conf().get("translate", "baidu"),
+        }
+        model_type = conf().get("model")
+        if model_type in ["text-davinci-003"]:
+            self.btype["chat"] = const.OPEN_AI
+        if conf().get("use_azure_chatgpt", False):
+            self.btype["chat"] = const.CHATGPTONAZURE
+        if model_type in ["wenxin"]:
+            self.btype["chat"] = const.BAIDU
+        if model_type in ["xunfei"]:
+            self.btype["chat"] = const.XUNFEI
+        if conf().get("use_linkai") and conf().get("linkai_api_key"):
+            self.btype["chat"] = const.LINKAI
+        self.bots = {}
+
+    def get_bot(self, typename):
+        if self.bots.get(typename) is None:
+            logger.info("create bot {} for {}".format(self.btype[typename], typename))
+            if typename == "text_to_voice":
+                self.bots[typename] = create_voice(self.btype[typename])
+            elif typename == "voice_to_text":
+                self.bots[typename] = create_voice(self.btype[typename])
+            elif typename == "chat":
+                self.bots[typename] = create_bot(self.btype[typename])
+            elif typename == "translate":
+                self.bots[typename] = create_translator(self.btype[typename])
+        return self.bots[typename]
+
+    def get_bot_type(self, typename):
+        return self.btype[typename]
+
+    def fetch_reply_content(self, query, context: Context) -> Reply:
+        return self.get_bot("chat").reply(query, context)
+
+    def fetch_voice_to_text(self, voiceFile) -> Reply:
+        return self.get_bot("voice_to_text").voiceToText(voiceFile)
+
+    def fetch_text_to_voice(self, text) -> Reply:
+        return self.get_bot("text_to_voice").textToVoice(text)
+
+    def fetch_translate(self, text, from_lang="", to_lang="en") -> Reply:
+        return self.get_bot("translate").translate(text, from_lang, to_lang)
+
+    def reset_bot(self):
+        """
+        重置bot路由
+        """
+        self.__init__()

bridge/context.py

@@ -0,0 +1,63 @@
+# encoding:utf-8
+
+from enum import Enum
+
+
+class ContextType(Enum):
+    TEXT = 1  # 文本消息
+    VOICE = 2  # 音频消息
+    IMAGE = 3  # 图片消息
+    IMAGE_CREATE = 10  # 创建图片命令
+    JOIN_GROUP = 20  # 加入群聊
+    PATPAT = 21  # 拍了拍
+
+    def __str__(self):
+        return self.name
+
+
+class Context:
+    def __init__(self, type: ContextType = None, content=None, kwargs=dict()):
+        self.type = type
+        self.content = content
+        self.kwargs = kwargs
+
+    def __contains__(self, key):
+        if key == "type":
+            return self.type is not None
+        elif key == "content":
+            return self.content is not None
+        else:
+            return key in self.kwargs
+
+    def __getitem__(self, key):
+        if key == "type":
+            return self.type
+        elif key == "content":
+            return self.content
+        else:
+            return self.kwargs[key]
+
+    def get(self, key, default=None):
+        try:
+            return self[key]
+        except KeyError:
+            return default
+
+    def __setitem__(self, key, value):
+        if key == "type":
+            self.type = value
+        elif key == "content":
+            self.content = value
+        else:
+            self.kwargs[key] = value
+
+    def __delitem__(self, key):
+        if key == "type":
+            self.type = None
+        elif key == "content":
+            self.content = None
+        else:
+            del self.kwargs[key]
+
+    def __str__(self):
+        return "Context(type={}, content={}, kwargs={})".format(self.type, self.content, self.kwargs)

bridge/reply.py

@@ -0,0 +1,25 @@
+# encoding:utf-8
+
+from enum import Enum
+
+
+class ReplyType(Enum):
+    TEXT = 1  # 文本
+    VOICE = 2  # 音频文件
+    IMAGE = 3  # 图片文件
+    IMAGE_URL = 4  # 图片URL
+
+    INFO = 9
+    ERROR = 10
+
+    def __str__(self):
+        return self.name
+
+
+class Reply:
+    def __init__(self, type: ReplyType = None, content=None):
+        self.type = type
+        self.content = content
+
+    def __str__(self):
+        return "Reply(type={}, content={})".format(self.type, self.content)

channel/channel.py

@@ -0,0 +1,43 @@
+"""
+Message sending channel abstract class
+"""
+
+from bridge.bridge import Bridge
+from bridge.context import Context
+from bridge.reply import *
+
+
+class Channel(object):
+    NOT_SUPPORT_REPLYTYPE = [ReplyType.VOICE, ReplyType.IMAGE]
+
+    def startup(self):
+        """
+        init channel
+        """
+        raise NotImplementedError
+
+    def handle_text(self, msg):
+        """
+        process received msg
+        :param msg: message object
+        """
+        raise NotImplementedError
+
+    # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息
+    def send(self, reply: Reply, context: Context):
+        """
+        send message to user
+        :param msg: message content
+        :param receiver: receiver channel account
+        :return:
+        """
+        raise NotImplementedError
+
+    def build_reply_content(self, query, context: Context = None) -> Reply:
+        return Bridge().fetch_reply_content(query, context)
+
+    def build_voice_to_text(self, voice_file) -> Reply:
+        return Bridge().fetch_voice_to_text(voice_file)
+
+    def build_text_to_voice(self, text) -> Reply:
+        return Bridge().fetch_text_to_voice(text)

channel/channel_factory.py

@@ -0,0 +1,36 @@
+"""
+channel factory
+"""
+
+
+def create_channel(channel_type):
+    """
+    create a channel instance
+    :param channel_type: channel type code
+    :return: channel instance
+    """
+    if channel_type == "wx":
+        from channel.wechat.wechat_channel import WechatChannel
+
+        return WechatChannel()
+    elif channel_type == "wxy":
+        from channel.wechat.wechaty_channel import WechatyChannel
+
+        return WechatyChannel()
+    elif channel_type == "terminal":
+        from channel.terminal.terminal_channel import TerminalChannel
+
+        return TerminalChannel()
+    elif channel_type == "wechatmp":
+        from channel.wechatmp.wechatmp_channel import WechatMPChannel
+
+        return WechatMPChannel(passive_reply=True)
+    elif channel_type == "wechatmp_service":
+        from channel.wechatmp.wechatmp_channel import WechatMPChannel
+
+        return WechatMPChannel(passive_reply=False)
+    elif channel_type == "wechatcom_app":
+        from channel.wechatcom.wechatcomapp_channel import WechatComAppChannel
+
+        return WechatComAppChannel()
+    raise RuntimeError

channel/chat_channel.py

@@ -0,0 +1,367 @@
+import os
+import re
+import threading
+import time
+from asyncio import CancelledError
+from concurrent.futures import Future, ThreadPoolExecutor
+
+from bridge.context import *
+from bridge.reply import *
+from channel.channel import Channel
+from common.dequeue import Dequeue
+from common.log import logger
+from config import conf
+from plugins import *
+
+try:
+    from voice.audio_convert import any_to_wav
+except Exception as e:
+    pass
+
+
+# 抽象类, 它包含了与消息通道无关的通用处理逻辑
+class ChatChannel(Channel):
+    name = None  # 登录的用户名
+    user_id = None  # 登录的用户id
+    futures = {}  # 记录每个session_id提交到线程池的future对象, 用于重置会话时把没执行的future取消掉，正在执行的不会被取消
+    sessions = {}  # 用于控制并发，每个session_id同时只能有一个context在处理
+    lock = threading.Lock()  # 用于控制对sessions的访问
+    handler_pool = ThreadPoolExecutor(max_workers=8)  # 处理消息的线程池
+
+    def __init__(self):
+        _thread = threading.Thread(target=self.consume)
+        _thread.setDaemon(True)
+        _thread.start()
+
+    # 根据消息构造context，消息内容相关的触发项写在这里
+    def _compose_context(self, ctype: ContextType, content, **kwargs):
+        context = Context(ctype, content)
+        context.kwargs = kwargs
+        # context首次传入时，origin_ctype是None,
+        # 引入的起因是：当输入语音时，会嵌套生成两个context，第一步语音转文本，第二步通过文本生成文字回复。
+        # origin_ctype用于第二步文本回复时，判断是否需要匹配前缀，如果是私聊的语音，就不需要匹配前缀
+        if "origin_ctype" not in context:
+            context["origin_ctype"] = ctype
+        # context首次传入时，receiver是None，根据类型设置receiver
+        first_in = "receiver" not in context
+        # 群名匹配过程，设置session_id和receiver
+        if first_in:  # context首次传入时，receiver是None，根据类型设置receiver
+            config = conf()
+            cmsg = context["msg"]
+            user_data = conf().get_user_data(cmsg.from_user_id)
+            context["openai_api_key"] = user_data.get("openai_api_key")
+            context["gpt_model"] = user_data.get("gpt_model")
+            if context.get("isgroup", False):
+                group_name = cmsg.other_user_nickname
+                group_id = cmsg.other_user_id
+
+                group_name_white_list = config.get("group_name_white_list", [])
+                group_name_keyword_white_list = config.get("group_name_keyword_white_list", [])
+                if any(
+                    [
+                        group_name in group_name_white_list,
+                        "ALL_GROUP" in group_name_white_list,
+                        check_contain(group_name, group_name_keyword_white_list),
+                    ]
+                ):
+                    group_chat_in_one_session = conf().get("group_chat_in_one_session", [])
+                    session_id = cmsg.actual_user_id
+                    if any(
+                        [
+                            group_name in group_chat_in_one_session,
+                            "ALL_GROUP" in group_chat_in_one_session,
+                        ]
+                    ):
+                        session_id = group_id
+                else:
+                    return None
+                context["session_id"] = session_id
+                context["receiver"] = group_id
+            else:
+                context["session_id"] = cmsg.other_user_id
+                context["receiver"] = cmsg.other_user_id
+            e_context = PluginManager().emit_event(EventContext(Event.ON_RECEIVE_MESSAGE, {"channel": self, "context": context}))
+            context = e_context["context"]
+            if e_context.is_pass() or context is None:
+                return context
+            if cmsg.from_user_id == self.user_id and not config.get("trigger_by_self", True):
+                logger.debug("[WX]self message skipped")
+                return None
+
+        # 消息内容匹配过程，并处理content
+        if ctype == ContextType.TEXT:
+            if first_in and "」\n- - - - - - -" in content:  # 初次匹配 过滤引用消息
+                logger.debug("[WX]reference query skipped")
+                return None
+
+            if context.get("isgroup", False):  # 群聊
+                # 校验关键字
+                match_prefix = check_prefix(content, conf().get("group_chat_prefix"))
+                match_contain = check_contain(content, conf().get("group_chat_keyword"))
+                flag = False
+                if match_prefix is not None or match_contain is not None:
+                    flag = True
+                    if match_prefix:
+                        content = content.replace(match_prefix, "", 1).strip()
+                if context["msg"].is_at:
+                    logger.info("[WX]receive group at")
+                    if not conf().get("group_at_off", False):
+                        flag = True
+                    pattern = f"@{re.escape(self.name)}(\u2005|\u0020)"
+                    subtract_res = re.sub(pattern, r"", content)
+                    if subtract_res == content and context["msg"].self_display_name:
+                        # 前缀移除后没有变化，使用群昵称再次移除
+                        pattern = f"@{re.escape(context['msg'].self_display_name)}(\u2005|\u0020)"
+                        subtract_res = re.sub(pattern, r"", content)
+                    content = subtract_res
+                if not flag:
+                    if context["origin_ctype"] == ContextType.VOICE:
+                        logger.info("[WX]receive group voice, but checkprefix didn't match")
+                    return None
+            else:  # 单聊
+                match_prefix = check_prefix(content, conf().get("single_chat_prefix", [""]))
+                if match_prefix is not None:  # 判断如果匹配到自定义前缀，则返回过滤掉前缀+空格后的内容
+                    content = content.replace(match_prefix, "", 1).strip()
+                elif context["origin_ctype"] == ContextType.VOICE:  # 如果源消息是私聊的语音消息，允许不匹配前缀，放宽条件
+                    pass
+                else:
+                    return None
+            content = content.strip()
+            img_match_prefix = check_prefix(content, conf().get("image_create_prefix"))
+            if img_match_prefix:
+                content = content.replace(img_match_prefix, "", 1)
+                context.type = ContextType.IMAGE_CREATE
+            else:
+                context.type = ContextType.TEXT
+            context.content = content.strip()
+            if "desire_rtype" not in context and conf().get("always_reply_voice") and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE:
+                context["desire_rtype"] = ReplyType.VOICE
+        elif context.type == ContextType.VOICE:
+            if "desire_rtype" not in context and conf().get("voice_reply_voice") and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE:
+                context["desire_rtype"] = ReplyType.VOICE
+
+        return context
+
+    def _handle(self, context: Context):
+        if context is None or not context.content:
+            return
+        logger.debug("[WX] ready to handle context: {}".format(context))
+        # reply的构建步骤
+        reply = self._generate_reply(context)
+
+        logger.debug("[WX] ready to decorate reply: {}".format(reply))
+        # reply的包装步骤
+        reply = self._decorate_reply(context, reply)
+
+        # reply的发送步骤
+        self._send_reply(context, reply)
+
+    def _generate_reply(self, context: Context, reply: Reply = Reply()) -> Reply:
+        e_context = PluginManager().emit_event(
+            EventContext(
+                Event.ON_HANDLE_CONTEXT,
+                {"channel": self, "context": context, "reply": reply},
+            )
+        )
+        reply = e_context["reply"]
+        if not e_context.is_pass():
+            logger.debug("[WX] ready to handle context: type={}, content={}".format(context.type, context.content))
+            if e_context.is_break():
+                context["generate_breaked_by"] = e_context["breaked_by"]
+            if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE:  # 文字和图片消息
+                reply = super().build_reply_content(context.content, context)
+            elif context.type == ContextType.VOICE:  # 语音消息
+                cmsg = context["msg"]
+                cmsg.prepare()
+                file_path = context.content
+                wav_path = os.path.splitext(file_path)[0] + ".wav"
+                try:
+                    any_to_wav(file_path, wav_path)
+                except Exception as e:  # 转换失败，直接使用mp3，对于某些api，mp3也可以识别
+                    logger.warning("[WX]any to wav error, use raw path. " + str(e))
+                    wav_path = file_path
+                # 语音识别
+                reply = super().build_voice_to_text(wav_path)
+                # 删除临时文件
+                try:
+                    os.remove(file_path)
+                    if wav_path != file_path:
+                        os.remove(wav_path)
+                except Exception as e:
+                    pass
+                    # logger.warning("[WX]delete temp file error: " + str(e))
+
+                if reply.type == ReplyType.TEXT:
+                    new_context = self._compose_context(ContextType.TEXT, reply.content, **context.kwargs)
+                    if new_context:
+                        reply = self._generate_reply(new_context)
+                    else:
+                        return
+            elif context.type == ContextType.IMAGE:  # 图片消息，当前无默认逻辑
+                pass
+            else:
+                logger.error("[WX] unknown context type: {}".format(context.type))
+                return
+        return reply
+
+    def _decorate_reply(self, context: Context, reply: Reply) -> Reply:
+        if reply and reply.type:
+            e_context = PluginManager().emit_event(
+                EventContext(
+                    Event.ON_DECORATE_REPLY,
+                    {"channel": self, "context": context, "reply": reply},
+                )
+            )
+            reply = e_context["reply"]
+            desire_rtype = context.get("desire_rtype")
+            if not e_context.is_pass() and reply and reply.type:
+                if reply.type in self.NOT_SUPPORT_REPLYTYPE:
+                    logger.error("[WX]reply type not support: " + str(reply.type))
+                    reply.type = ReplyType.ERROR
+                    reply.content = "不支持发送的消息类型: " + str(reply.type)
+
+                if reply.type == ReplyType.TEXT:
+                    reply_text = reply.content
+                    if desire_rtype == ReplyType.VOICE and ReplyType.VOICE not in self.NOT_SUPPORT_REPLYTYPE:
+                        reply = super().build_text_to_voice(reply.content)
+                        return self._decorate_reply(context, reply)
+                    if context.get("isgroup", False):
+                        reply_text = "@" + context["msg"].actual_user_nickname + "\n" + reply_text.strip()
+                        reply_text = conf().get("group_chat_reply_prefix", "") + reply_text + conf().get("group_chat_reply_suffix", "")
+                    else:
+                        reply_text = conf().get("single_chat_reply_prefix", "") + reply_text + conf().get("single_chat_reply_suffix", "")
+                    reply.content = reply_text
+                elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+                    reply.content = "[" + str(reply.type) + "]\n" + reply.content
+                elif reply.type == ReplyType.IMAGE_URL or reply.type == ReplyType.VOICE or reply.type == ReplyType.IMAGE:
+                    pass
+                else:
+                    logger.error("[WX] unknown reply type: {}".format(reply.type))
+                    return
+            if desire_rtype and desire_rtype != reply.type and reply.type not in [ReplyType.ERROR, ReplyType.INFO]:
+                logger.warning("[WX] desire_rtype: {}, but reply type: {}".format(context.get("desire_rtype"), reply.type))
+            return reply
+
+    def _send_reply(self, context: Context, reply: Reply):
+        if reply and reply.type:
+            e_context = PluginManager().emit_event(
+                EventContext(
+                    Event.ON_SEND_REPLY,
+                    {"channel": self, "context": context, "reply": reply},
+                )
+            )
+            reply = e_context["reply"]
+            if not e_context.is_pass() and reply and reply.type:
+                logger.debug("[WX] ready to send reply: {}, context: {}".format(reply, context))
+                self._send(reply, context)
+
+    def _send(self, reply: Reply, context: Context, retry_cnt=0):
+        try:
+            self.send(reply, context)
+        except Exception as e:
+            logger.error("[WX] sendMsg error: {}".format(str(e)))
+            if isinstance(e, NotImplementedError):
+                return
+            logger.exception(e)
+            if retry_cnt < 2:
+                time.sleep(3 + 3 * retry_cnt)
+                self._send(reply, context, retry_cnt + 1)
+
+    def _success_callback(self, session_id, **kwargs):  # 线程正常结束时的回调函数
+        logger.debug("Worker return success, session_id = {}".format(session_id))
+
+    def _fail_callback(self, session_id, exception, **kwargs):  # 线程异常结束时的回调函数
+        logger.exception("Worker return exception: {}".format(exception))
+
+    def _thread_pool_callback(self, session_id, **kwargs):
+        def func(worker: Future):
+            try:
+                worker_exception = worker.exception()
+                if worker_exception:
+                    self._fail_callback(session_id, exception=worker_exception, **kwargs)
+                else:
+                    self._success_callback(session_id, **kwargs)
+            except CancelledError as e:
+                logger.info("Worker cancelled, session_id = {}".format(session_id))
+            except Exception as e:
+                logger.exception("Worker raise exception: {}".format(e))
+            with self.lock:
+                self.sessions[session_id][1].release()
+
+        return func
+
+    def produce(self, context: Context):
+        session_id = context["session_id"]
+        with self.lock:
+            if session_id not in self.sessions:
+                self.sessions[session_id] = [
+                    Dequeue(),
+                    threading.BoundedSemaphore(conf().get("concurrency_in_session", 4)),
+                ]
+            if context.type == ContextType.TEXT and context.content.startswith("#"):
+                self.sessions[session_id][0].putleft(context)  # 优先处理管理��令
+            else:
+                self.sessions[session_id][0].put(context)
+
+    # 消费者函数，单独线程，用于从消息队列中取出消息并处理
+    def consume(self):
+        while True:
+            with self.lock:
+                session_ids = list(self.sessions.keys())
+                for session_id in session_ids:
+                    context_queue, semaphore = self.sessions[session_id]
+                    if semaphore.acquire(blocking=False):  # 等线程处理完毕才能删除
+                        if not context_queue.empty():
+                            context = context_queue.get()
+                            logger.debug("[WX] consume context: {}".format(context))
+                            future: Future = self.handler_pool.submit(self._handle, context)
+                            future.add_done_callback(self._thread_pool_callback(session_id, context=context))
+                            if session_id not in self.futures:
+                                self.futures[session_id] = []
+                            self.futures[session_id].append(future)
+                        elif semaphore._initial_value == semaphore._value + 1:  # 除了当前，没有任务再申请到信号量，说明所有任务都处理完毕
+                            self.futures[session_id] = [t for t in self.futures[session_id] if not t.done()]
+                            assert len(self.futures[session_id]) == 0, "thread pool error"
+                            del self.sessions[session_id]
+                        else:
+                            semaphore.release()
+            time.sleep(0.1)
+
+    # 取消session_id对应的所有任务，只能取消排队的消息和已提交线程池但未执行的任务
+    def cancel_session(self, session_id):
+        with self.lock:
+            if session_id in self.sessions:
+                for future in self.futures[session_id]:
+                    future.cancel()
+                cnt = self.sessions[session_id][0].qsize()
+                if cnt > 0:
+                    logger.info("Cancel {} messages in session {}".format(cnt, session_id))
+                self.sessions[session_id][0] = Dequeue()
+
+    def cancel_all_session(self):
+        with self.lock:
+            for session_id in self.sessions:
+                for future in self.futures[session_id]:
+                    future.cancel()
+                cnt = self.sessions[session_id][0].qsize()
+                if cnt > 0:
+                    logger.info("Cancel {} messages in session {}".format(cnt, session_id))
+                self.sessions[session_id][0] = Dequeue()
+
+
+def check_prefix(content, prefix_list):
+    if not prefix_list:
+        return None
+    for prefix in prefix_list:
+        if content.startswith(prefix):
+            return prefix
+    return None
+
+
+def check_contain(content, keyword_list):
+    if not keyword_list:
+        return None
+    for ky in keyword_list:
+        if content.find(ky) != -1:
+            return True
+    return None

channel/chat_message.py

@@ -0,0 +1,85 @@
+"""
+本类表示聊天消息，用于对itchat和wechaty的消息进行统一的封装。
+
+填好必填项(群聊6个，非群聊8个)，即可接入ChatChannel，并支持插件，参考TerminalChannel
+
+ChatMessage
+msg_id: 消息id (必填)
+create_time: 消息创建时间
+
+ctype: 消息类型 : ContextType (必填)
+content: 消息内容, 如果是声音/图片，这里是文件路径 (必填)
+
+from_user_id: 发送者id (必填)
+from_user_nickname: 发送者昵称
+to_user_id: 接收者id (必填)
+to_user_nickname: 接收者昵称
+
+other_user_id: 对方的id，如果你是发送者，那这个就是接收者id，如果你是接收者，那这个就是发送者id，如果是群消息，那这一直是群id (必填)
+other_user_nickname: 同上
+
+is_group: 是否是群消息 (群聊必填)
+is_at: 是否被at
+
+- (群消息时，一般会存在实际发送者，是群内某个成员的id和昵称，下列项仅在群消息时存在)
+actual_user_id: 实际发送者id (群聊必填)
+actual_user_nickname：实际发送者昵称
+self_display_name: 自身的展示名，设置群昵称时，该字段表示群昵称
+
+_prepare_fn: 准备函数，用于准备消息的内容，比如下载图片等,
+_prepared: 是否已经调用过准备函数
+_rawmsg: 原始消息对象
+
+"""
+
+
+class ChatMessage(object):
+    msg_id = None
+    create_time = None
+
+    ctype = None
+    content = None
+
+    from_user_id = None
+    from_user_nickname = None
+    to_user_id = None
+    to_user_nickname = None
+    other_user_id = None
+    other_user_nickname = None
+    my_msg = False
+    self_display_name = None
+
+    is_group = False
+    is_at = False
+    actual_user_id = None
+    actual_user_nickname = None
+
+    _prepare_fn = None
+    _prepared = False
+    _rawmsg = None
+
+    def __init__(self, _rawmsg):
+        self._rawmsg = _rawmsg
+
+    def prepare(self):
+        if self._prepare_fn and not self._prepared:
+            self._prepared = True
+            self._prepare_fn()
+
+    def __str__(self):
+        return "ChatMessage: id={}, create_time={}, ctype={}, content={}, from_user_id={}, from_user_nickname={}, to_user_id={}, to_user_nickname={}, other_user_id={}, other_user_nickname={}, is_group={}, is_at={}, actual_user_id={}, actual_user_nickname={}".format(
+            self.msg_id,
+            self.create_time,
+            self.ctype,
+            self.content,
+            self.from_user_id,
+            self.from_user_nickname,
+            self.to_user_id,
+            self.to_user_nickname,
+            self.other_user_id,
+            self.other_user_nickname,
+            self.is_group,
+            self.is_at,
+            self.actual_user_id,
+            self.actual_user_nickname,
+        )

channel/terminal/terminal_channel.py

@@ -0,0 +1,92 @@
+import sys
+
+from bridge.context import *
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel, check_prefix
+from channel.chat_message import ChatMessage
+from common.log import logger
+from config import conf
+
+
+class TerminalMessage(ChatMessage):
+    def __init__(
+        self,
+        msg_id,
+        content,
+        ctype=ContextType.TEXT,
+        from_user_id="User",
+        to_user_id="Chatgpt",
+        other_user_id="Chatgpt",
+    ):
+        self.msg_id = msg_id
+        self.ctype = ctype
+        self.content = content
+        self.from_user_id = from_user_id
+        self.to_user_id = to_user_id
+        self.other_user_id = other_user_id
+
+
+class TerminalChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = [ReplyType.VOICE]
+
+    def send(self, reply: Reply, context: Context):
+        print("\nBot:")
+        if reply.type == ReplyType.IMAGE:
+            from PIL import Image
+
+            image_storage = reply.content
+            image_storage.seek(0)
+            img = Image.open(image_storage)
+            print("<IMAGE>")
+            img.show()
+        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+            import io
+
+            import requests
+            from PIL import Image
+
+            img_url = reply.content
+            pic_res = requests.get(img_url, stream=True)
+            image_storage = io.BytesIO()
+            for block in pic_res.iter_content(1024):
+                image_storage.write(block)
+            image_storage.seek(0)
+            img = Image.open(image_storage)
+            print(img_url)
+            img.show()
+        else:
+            print(reply.content)
+        print("\nUser:", end="")
+        sys.stdout.flush()
+        return
+
+    def startup(self):
+        context = Context()
+        logger.setLevel("WARN")
+        print("\nPlease input your question:\nUser:", end="")
+        sys.stdout.flush()
+        msg_id = 0
+        while True:
+            try:
+                prompt = self.get_input()
+            except KeyboardInterrupt:
+                print("\nExiting...")
+                sys.exit()
+            msg_id += 1
+            trigger_prefixs = conf().get("single_chat_prefix", [""])
+            if check_prefix(prompt, trigger_prefixs) is None:
+                prompt = trigger_prefixs[0] + prompt  # 给没触发的消息加上触发前缀
+
+            context = self._compose_context(ContextType.TEXT, prompt, msg=TerminalMessage(msg_id, prompt))
+            if context:
+                self.produce(context)
+            else:
+                raise Exception("context is None")
+
+    def get_input(self):
+        """
+        Multi-line input function
+        """
+        sys.stdout.flush()
+        line = input()
+        return line

channel/wechat/wechat_channel.py

@@ -0,0 +1,210 @@
+# encoding:utf-8
+
+"""
+wechat channel
+"""
+
+import io
+import json
+import os
+import threading
+import time
+
+import requests
+
+from bridge.context import *
+from bridge.reply import *
+from channel.chat_channel import ChatChannel
+from channel.wechat.wechat_message import *
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from common.singleton import singleton
+from common.time_check import time_checker
+from config import conf, get_appdata_dir
+from lib import itchat
+from lib.itchat.content import *
+
+
+@itchat.msg_register([TEXT, VOICE, PICTURE, NOTE])
+def handler_single_msg(msg):
+    try:
+        cmsg = WechatMessage(msg, False)
+    except NotImplementedError as e:
+        logger.debug("[WX]single message {} skipped: {}".format(msg["MsgId"], e))
+        return None
+    WechatChannel().handle_single(cmsg)
+    return None
+
+
+@itchat.msg_register([TEXT, VOICE, PICTURE, NOTE], isGroupChat=True)
+def handler_group_msg(msg):
+    try:
+        cmsg = WechatMessage(msg, True)
+    except NotImplementedError as e:
+        logger.debug("[WX]group message {} skipped: {}".format(msg["MsgId"], e))
+        return None
+    WechatChannel().handle_group(cmsg)
+    return None
+
+
+def _check(func):
+    def wrapper(self, cmsg: ChatMessage):
+        msgId = cmsg.msg_id
+        if msgId in self.receivedMsgs:
+            logger.info("Wechat message {} already received, ignore".format(msgId))
+            return
+        self.receivedMsgs[msgId] = True
+        create_time = cmsg.create_time  # 消息时间戳
+        if conf().get("hot_reload") == True and int(create_time) < int(time.time()) - 60:  # 跳过1分钟前的历史消息
+            logger.debug("[WX]history message {} skipped".format(msgId))
+            return
+        if cmsg.my_msg and not cmsg.is_group:
+            logger.debug("[WX]my message {} skipped".format(msgId))
+            return
+        return func(self, cmsg)
+
+    return wrapper
+
+
+# 可用的二维码生成接口
+# https://api.qrserver.com/v1/create-qr-code/?size=400×400&data=https://www.abc.com
+# https://api.isoyu.com/qr/?m=1&e=L&p=20&url=https://www.abc.com
+def qrCallback(uuid, status, qrcode):
+    # logger.debug("qrCallback: {} {}".format(uuid,status))
+    if status == "0":
+        try:
+            from PIL import Image
+
+            img = Image.open(io.BytesIO(qrcode))
+            _thread = threading.Thread(target=img.show, args=("QRCode",))
+            _thread.setDaemon(True)
+            _thread.start()
+        except Exception as e:
+            pass
+
+        import qrcode
+
+        url = f"https://login.weixin.qq.com/l/{uuid}"
+
+        qr_api1 = "https://api.isoyu.com/qr/?m=1&e=L&p=20&url={}".format(url)
+        qr_api2 = "https://api.qrserver.com/v1/create-qr-code/?size=400×400&data={}".format(url)
+        qr_api3 = "https://api.pwmqr.com/qrcode/create/?url={}".format(url)
+        qr_api4 = "https://my.tv.sohu.com/user/a/wvideo/getQRCode.do?text={}".format(url)
+        print("You can also scan QRCode in any website below:")
+        print(qr_api3)
+        print(qr_api4)
+        print(qr_api2)
+        print(qr_api1)
+
+        qr = qrcode.QRCode(border=1)
+        qr.add_data(url)
+        qr.make(fit=True)
+        qr.print_ascii(invert=True)
+
+
+@singleton
+class WechatChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+        self.receivedMsgs = ExpiredDict(60 * 60)
+
+    def startup(self):
+        itchat.instance.receivingRetryCount = 600  # 修改断线超时时间
+        # login by scan QRCode
+        hotReload = conf().get("hot_reload", False)
+        status_path = os.path.join(get_appdata_dir(), "itchat.pkl")
+        itchat.auto_login(
+            enableCmdQR=2,
+            hotReload=hotReload,
+            statusStorageDir=status_path,
+            qrCallback=qrCallback,
+        )
+        self.user_id = itchat.instance.storageClass.userName
+        self.name = itchat.instance.storageClass.nickName
+        logger.info("Wechat login success, user_id: {}, nickname: {}".format(self.user_id, self.name))
+        # start message listener
+        itchat.run()
+
+    # handle_* 系列函数处理收到的消息后构造Context，然后传入produce函数中处理Context和发送回复
+    # Context包含了消息的所有信息，包括以下属性
+    #   type 消息类型, 包括TEXT、VOICE、IMAGE_CREATE
+    #   content 消息内容，如果是TEXT类型，content就是文本内容，如果是VOICE类型，content就是语音文件名，如果是IMAGE_CREATE类型，content就是图片生成命令
+    #   kwargs 附加参数字典，包含以下的key：
+    #        session_id: 会话id
+    #        isgroup: 是否是群聊
+    #        receiver: 需要回复的对象
+    #        msg: ChatMessage消息对象
+    #        origin_ctype: 原始消息类型，语音转文字后，私聊时如果匹配前缀失败，会根据初始消息是否是语音来放宽触发规则
+    #        desire_rtype: 希望回复类���，默认是文本回复，设置为ReplyType.VOICE是语音回复
+
+    @time_checker
+    @_check
+    def handle_single(self, cmsg: ChatMessage):
+        if cmsg.ctype == ContextType.VOICE:
+            if conf().get("speech_recognition") != True:
+                return
+            logger.debug("[WX]receive voice msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.IMAGE:
+            logger.debug("[WX]receive image msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.PATPAT:
+            logger.debug("[WX]receive patpat msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.TEXT:
+            logger.debug("[WX]receive text msg: {}, cmsg={}".format(json.dumps(cmsg._rawmsg, ensure_ascii=False), cmsg))
+        else:
+            logger.debug("[WX]receive msg: {}, cmsg={}".format(cmsg.content, cmsg))
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=False, msg=cmsg)
+        if context:
+            self.produce(context)
+
+    @time_checker
+    @_check
+    def handle_group(self, cmsg: ChatMessage):
+        if cmsg.ctype == ContextType.VOICE:
+            if conf().get("group_speech_recognition") != True:
+                return
+            logger.debug("[WX]receive voice for group msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.IMAGE:
+            logger.debug("[WX]receive image for group msg: {}".format(cmsg.content))
+        elif cmsg.ctype in [ContextType.JOIN_GROUP, ContextType.PATPAT]:
+            logger.debug("[WX]receive note msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.TEXT:
+            # logger.debug("[WX]receive group msg: {}, cmsg={}".format(json.dumps(cmsg._rawmsg, ensure_ascii=False), cmsg))
+            pass
+        else:
+            logger.debug("[WX]receive group msg: {}".format(cmsg.content))
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=True, msg=cmsg)
+        if context:
+            self.produce(context)
+
+    # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息
+    def send(self, reply: Reply, context: Context):
+        receiver = context["receiver"]
+        if reply.type == ReplyType.TEXT:
+            itchat.send(reply.content, toUserName=receiver)
+            logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
+        elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+            itchat.send(reply.content, toUserName=receiver)
+            logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
+        elif reply.type == ReplyType.VOICE:
+            itchat.send_file(reply.content, toUserName=receiver)
+            logger.info("[WX] sendFile={}, receiver={}".format(reply.content, receiver))
+        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+            img_url = reply.content
+            logger.debug(f"[WX] start download image, img_url={img_url}")
+            pic_res = requests.get(img_url, stream=True)
+            image_storage = io.BytesIO()
+            size = 0
+            for block in pic_res.iter_content(1024):
+                size += len(block)
+                image_storage.write(block)
+            logger.info(f"[WX] download image success, size={size}, img_url={img_url}")
+            image_storage.seek(0)
+            itchat.send_image(image_storage, toUserName=receiver)
+            logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver))
+        elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
+            image_storage = reply.content
+            image_storage.seek(0)
+            itchat.send_image(image_storage, toUserName=receiver)
+            logger.info("[WX] sendImage, receiver={}".format(receiver))

channel/wechat/wechat_message.py

@@ -0,0 +1,84 @@
+import re
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from common.tmp_dir import TmpDir
+from lib import itchat
+from lib.itchat.content import *
+
+
+class WechatMessage(ChatMessage):
+    def __init__(self, itchat_msg, is_group=False):
+        super().__init__(itchat_msg)
+        self.msg_id = itchat_msg["MsgId"]
+        self.create_time = itchat_msg["CreateTime"]
+        self.is_group = is_group
+
+        if itchat_msg["Type"] == TEXT:
+            self.ctype = ContextType.TEXT
+            self.content = itchat_msg["Text"]
+        elif itchat_msg["Type"] == VOICE:
+            self.ctype = ContextType.VOICE
+            self.content = TmpDir().path() + itchat_msg["FileName"]  # content直接存临时目录路径
+            self._prepare_fn = lambda: itchat_msg.download(self.content)
+        elif itchat_msg["Type"] == PICTURE and itchat_msg["MsgType"] == 3:
+            self.ctype = ContextType.IMAGE
+            self.content = TmpDir().path() + itchat_msg["FileName"]  # content直接存临时目录路径
+            self._prepare_fn = lambda: itchat_msg.download(self.content)
+        elif itchat_msg["Type"] == NOTE and itchat_msg["MsgType"] == 10000:
+            if is_group and ("加入群聊" in itchat_msg["Content"] or "加入了群聊" in itchat_msg["Content"]):
+                self.ctype = ContextType.JOIN_GROUP
+                self.content = itchat_msg["Content"]
+                # 这里只能得到nickname， actual_user_id还是机器人的id
+                if "加入了群聊" in itchat_msg["Content"]:
+                    self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[-1]
+                elif "加入群聊" in itchat_msg["Content"]:
+                    self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
+            elif "拍了拍我" in itchat_msg["Content"]:
+                self.ctype = ContextType.PATPAT
+                self.content = itchat_msg["Content"]
+                if is_group:
+                    self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
+            else:
+                raise NotImplementedError("Unsupported note message: " + itchat_msg["Content"])
+        else:
+            raise NotImplementedError("Unsupported message type: Type:{} MsgType:{}".format(itchat_msg["Type"], itchat_msg["MsgType"]))
+
+        self.from_user_id = itchat_msg["FromUserName"]
+        self.to_user_id = itchat_msg["ToUserName"]
+
+        user_id = itchat.instance.storageClass.userName
+        nickname = itchat.instance.storageClass.nickName
+
+        # 虽然from_user_id和to_user_id用的少，但是为了保持一致性，还是要填充一下
+        # 以下很繁琐，一句话总结：能填的都填了。
+        if self.from_user_id == user_id:
+            self.from_user_nickname = nickname
+        if self.to_user_id == user_id:
+            self.to_user_nickname = nickname
+        try:  # 陌生人时候, User字段可能不存在
+            # my_msg 为True是表示是自己发送的消息
+            self.my_msg = itchat_msg["ToUserName"] == itchat_msg["User"]["UserName"] and \
+                          itchat_msg["ToUserName"] != itchat_msg["FromUserName"]
+            self.other_user_id = itchat_msg["User"]["UserName"]
+            self.other_user_nickname = itchat_msg["User"]["NickName"]
+            if self.other_user_id == self.from_user_id:
+                self.from_user_nickname = self.other_user_nickname
+            if self.other_user_id == self.to_user_id:
+                self.to_user_nickname = self.other_user_nickname
+            if itchat_msg["User"].get("Self"):
+                # 自身的展示名，当设置了群昵称时，该字段表示群昵称
+                self.self_display_name = itchat_msg["User"].get("Self").get("DisplayName")
+        except KeyError as e:  # 处理偶尔没有对方信息的情况
+            logger.warn("[WX]get other_user_id failed: " + str(e))
+            if self.from_user_id == user_id:
+                self.other_user_id = self.to_user_id
+            else:
+                self.other_user_id = self.from_user_id
+
+        if self.is_group:
+            self.is_at = itchat_msg["IsAt"]
+            self.actual_user_id = itchat_msg["ActualUserName"]
+            if self.ctype not in [ContextType.JOIN_GROUP, ContextType.PATPAT]:
+                self.actual_user_nickname = itchat_msg["ActualNickName"]

channel/wechat/wechaty_channel.py

@@ -0,0 +1,129 @@
+# encoding:utf-8
+
+"""
+wechaty channel
+Python Wechaty - https://github.com/wechaty/python-wechaty
+"""
+import asyncio
+import base64
+import os
+import time
+
+from wechaty import Contact, Wechaty
+from wechaty.user import Message
+from wechaty_puppet import FileBox
+
+from bridge.context import *
+from bridge.context import Context
+from bridge.reply import *
+from channel.chat_channel import ChatChannel
+from channel.wechat.wechaty_message import WechatyMessage
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+
+try:
+    from voice.audio_convert import any_to_sil
+except Exception as e:
+    pass
+
+
+@singleton
+class WechatyChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+
+    def startup(self):
+        config = conf()
+        token = config.get("wechaty_puppet_service_token")
+        os.environ["WECHATY_PUPPET_SERVICE_TOKEN"] = token
+        asyncio.run(self.main())
+
+    async def main(self):
+        loop = asyncio.get_event_loop()
+        # 将asyncio的loop传入处理线程
+        self.handler_pool._initializer = lambda: asyncio.set_event_loop(loop)
+        self.bot = Wechaty()
+        self.bot.on("login", self.on_login)
+        self.bot.on("message", self.on_message)
+        await self.bot.start()
+
+    async def on_login(self, contact: Contact):
+        self.user_id = contact.contact_id
+        self.name = contact.name
+        logger.info("[WX] login user={}".format(contact))
+
+    # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息
+    def send(self, reply: Reply, context: Context):
+        receiver_id = context["receiver"]
+        loop = asyncio.get_event_loop()
+        if context["isgroup"]:
+            receiver = asyncio.run_coroutine_threadsafe(self.bot.Room.find(receiver_id), loop).result()
+        else:
+            receiver = asyncio.run_coroutine_threadsafe(self.bot.Contact.find(receiver_id), loop).result()
+        msg = None
+        if reply.type == ReplyType.TEXT:
+            msg = reply.content
+            asyncio.run_coroutine_threadsafe(receiver.say(msg), loop).result()
+            logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
+        elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
+            msg = reply.content
+            asyncio.run_coroutine_threadsafe(receiver.say(msg), loop).result()
+            logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
+        elif reply.type == ReplyType.VOICE:
+            voiceLength = None
+            file_path = reply.content
+            sil_file = os.path.splitext(file_path)[0] + ".sil"
+            voiceLength = int(any_to_sil(file_path, sil_file))
+            if voiceLength >= 60000:
+                voiceLength = 60000
+                logger.info("[WX] voice too long, length={}, set to 60s".format(voiceLength))
+            # 发送语音
+            t = int(time.time())
+            msg = FileBox.from_file(sil_file, name=str(t) + ".sil")
+            if voiceLength is not None:
+                msg.metadata["voiceLength"] = voiceLength
+            asyncio.run_coroutine_threadsafe(receiver.say(msg), loop).result()
+            try:
+                os.remove(file_path)
+                if sil_file != file_path:
+                    os.remove(sil_file)
+            except Exception as e:
+                pass
+            logger.info("[WX] sendVoice={}, receiver={}".format(reply.content, receiver))
+        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+            img_url = reply.content
+            t = int(time.time())
+            msg = FileBox.from_url(url=img_url, name=str(t) + ".png")
+            asyncio.run_coroutine_threadsafe(receiver.say(msg), loop).result()
+            logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver))
+        elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
+            image_storage = reply.content
+            image_storage.seek(0)
+            t = int(time.time())
+            msg = FileBox.from_base64(base64.b64encode(image_storage.read()), str(t) + ".png")
+            asyncio.run_coroutine_threadsafe(receiver.say(msg), loop).result()
+            logger.info("[WX] sendImage, receiver={}".format(receiver))
+
+    async def on_message(self, msg: Message):
+        """
+        listen for message event
+        """
+        try:
+            cmsg = await WechatyMessage(msg)
+        except NotImplementedError as e:
+            logger.debug("[WX] {}".format(e))
+            return
+        except Exception as e:
+            logger.exception("[WX] {}".format(e))
+            return
+        logger.debug("[WX] message:{}".format(cmsg))
+        room = msg.room()  # 获取消息来自的群聊. 如果消息不是来自群聊, 则返回None
+        isgroup = room is not None
+        ctype = cmsg.ctype
+        context = self._compose_context(ctype, cmsg.content, isgroup=isgroup, msg=cmsg)
+        if context:
+            logger.info("[WX] receiveMsg={}, context={}".format(cmsg, context))
+            self.produce(context)

channel/wechat/wechaty_message.py

@@ -0,0 +1,89 @@
+import asyncio
+import re
+
+from wechaty import MessageType
+from wechaty.user import Message
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from common.tmp_dir import TmpDir
+
+
+class aobject(object):
+    """Inheriting this class allows you to define an async __init__.
+
+    So you can create objects by doing something like `await MyClass(params)`
+    """
+
+    async def __new__(cls, *a, **kw):
+        instance = super().__new__(cls)
+        await instance.__init__(*a, **kw)
+        return instance
+
+    async def __init__(self):
+        pass
+
+
+class WechatyMessage(ChatMessage, aobject):
+    async def __init__(self, wechaty_msg: Message):
+        super().__init__(wechaty_msg)
+
+        room = wechaty_msg.room()
+
+        self.msg_id = wechaty_msg.message_id
+        self.create_time = wechaty_msg.payload.timestamp
+        self.is_group = room is not None
+
+        if wechaty_msg.type() == MessageType.MESSAGE_TYPE_TEXT:
+            self.ctype = ContextType.TEXT
+            self.content = wechaty_msg.text()
+        elif wechaty_msg.type() == MessageType.MESSAGE_TYPE_AUDIO:
+            self.ctype = ContextType.VOICE
+            voice_file = await wechaty_msg.to_file_box()
+            self.content = TmpDir().path() + voice_file.name  # content直接存临时目录路径
+
+            def func():
+                loop = asyncio.get_event_loop()
+                asyncio.run_coroutine_threadsafe(voice_file.to_file(self.content), loop).result()
+
+            self._prepare_fn = func
+
+        else:
+            raise NotImplementedError("Unsupported message type: {}".format(wechaty_msg.type()))
+
+        from_contact = wechaty_msg.talker()  # 获取消息的发送者
+        self.from_user_id = from_contact.contact_id
+        self.from_user_nickname = from_contact.name
+
+        # group中的from和to，wechaty跟itchat含义不一样
+        # wecahty: from是消息实际发送者, to:所在群
+        # itchat: 如果是你发送群消息，from和to是你自己和所在群，如果是别人发群消息，from和to是所在群和你自己
+        # 但这个差别不影响逻辑，group中只使用到：1.用from来判断是否是自己发的，2.actual_user_id来判断实际发送用户
+
+        if self.is_group:
+            self.to_user_id = room.room_id
+            self.to_user_nickname = await room.topic()
+        else:
+            to_contact = wechaty_msg.to()
+            self.to_user_id = to_contact.contact_id
+            self.to_user_nickname = to_contact.name
+
+        if self.is_group or wechaty_msg.is_self():  # 如果是群消息，other_user设置为群，如果是私聊消息，而且自己发的，就设置成对方。
+            self.other_user_id = self.to_user_id
+            self.other_user_nickname = self.to_user_nickname
+        else:
+            self.other_user_id = self.from_user_id
+            self.other_user_nickname = self.from_user_nickname
+
+        if self.is_group:  # wechaty群聊中，实际发送用户就是from_user
+            self.is_at = await wechaty_msg.mention_self()
+            if not self.is_at:  # 有时候复制粘贴的消息，不算做@，但是内容里面会有@xxx，这里做一下兼容
+                name = wechaty_msg.wechaty.user_self().name
+                pattern = f"@{re.escape(name)}(\u2005|\u0020)"
+                if re.search(pattern, self.content):
+                    logger.debug(f"wechaty message {self.msg_id} include at")
+                    self.is_at = True
+
+            self.actual_user_id = self.from_user_id
+            self.actual_user_nickname = self.from_user_nickname

channel/wechatcom/README.md

@@ -0,0 +1,85 @@
+# 企业微信应用号channel
+
+企业微信官方提供了客服、应用等API，本channel使用的是企业微信的自建应用API的能力。
+
+因为未来可能还会开发客服能力，所以本channel的类型名叫作`wechatcom_app`。
+
+`wechatcom_app` channel支持插件系统和图片声音交互等能力，除了无法加入群聊，作为个人使用的私人助理已绰绰有余。
+
+## 开始之前
+
+- 在企业中确认自己拥有在企业内自建应用的权限。
+- 如果没有权限或者是个人用户，也可创建未认证的企业。操作方式：登录手机企业微信，选择`创建/加入企业`来创建企业，类型请选择企业，企业名称可随意填写。
+    未认证的企业有100人的服务人数上限，其他功能与认证企业没有差异。
+
+本channel需安装的依赖与公众号一致，需要安装`wechatpy`和`web.py`，它们包含在`requirements-optional.txt`中。
+
+此外，如果你是`Linux`系统，除了`ffmpeg`还需要安装`amr`编码器，否则会出现找不到编码器的错误，无法正常使用语音功能。
+
+- Ubuntu/Debian
+
+```bash
+apt-get install libavcodec-extra
+```
+
+- Alpine
+
+需自行编译`ffmpeg`，在编译参数里加入`amr`编码器的支持
+
+## 使用方法
+
+1.查看企业ID
+
+- 扫码登陆[企业微信后台](https://work.weixin.qq.com)
+- 选择`我的企业`，点击`企业信息`，记住该`企业ID`
+
+2.创建自建应用
+
+- 选择应用管理, 在自建区选创建应用来创建企业自建应用
+- 上传应用logo，填写应用名称等项
+- 创建应用后进入应用详情页面，记住`AgentId`和`Secert`
+
+3.配置应用
+
+- 在详情页点击`企业可信IP`的配置(没看到可以不管)，填入你服务器的公网IP，如果不知道可以先不填
+- 点击`接收消息`下的启用API接收消息
+- `URL`填写格式为`http://url:port/wxcomapp`，`port`是程序监听的端口，默认是9898
+    如果是未认证的企业，url可直接使用服务器的IP。如果是认证企业，需要使用备案的域名，可使用二级域名。
+- `Token`可随意填写，停留在这个页面
+- 在程序根目录`config.json`中增加配置（**去掉注释**），`wechatcomapp_aes_key`是当前页面的`wechatcomapp_aes_key`
+
+```python
+    "channel_type": "wechatcom_app",
+    "wechatcom_corp_id": "",  # 企业微信公司的corpID
+    "wechatcomapp_token": "",  # 企业微信app的token
+    "wechatcomapp_port": 9898,  # 企业微信app的服务端口, 不需要端口转发
+    "wechatcomapp_secret": "",  # 企业微信app的secret
+    "wechatcomapp_agent_id": "",  # 企业微信app的agent_id
+    "wechatcomapp_aes_key": "",  # 企业微信app的aes_key
+```
+
+- 运行程序，在页面中点击保存，保存成功说明验证成功
+
+4.连接个人微信
+
+选择`我的企业`，点击`微信插件`，下面有个邀请关注的二维码。微信扫码后，即可在微信中看到对应企业，在这里你便可以和机器人沟通。
+
+向机器人发送消息，如果日志里出现报错:
+
+```bash
+Error code: 60020, message: "not allow to access from your ip, ...from ip: xx.xx.xx.xx"
+```
+
+意思是IP不可信，需要参考上一步的`企业可信IP`配置，把这里的IP加进去。
+
+~~### Railway部署方式~~（2023-06-08已失效）
+
+~~公众号不能在`Railway`上部署，但企业微信应用[可以](https://railway.app/template/-FHS--?referralCode=RC3znh)!~~
+
+~~填写配置后，将部署完成后的网址```**.railway.app/wxcomapp```，填写在上一步的URL中。发送信息后观察日志，把报错的IP加入到可信IP。（每次重启后都需要加入可信IP）~~
+
+## 测试体验
+
+AIGC开放社区中已经部署了多个可免费使用的Bot，扫描下方的二维码会自动邀请你来体验。
+
+<img width="200" src="../../docs/images/aigcopen.png">

channel/wechatcom/wechatcomapp_channel.py

@@ -0,0 +1,178 @@
+# -*- coding=utf-8 -*-
+import io
+import os
+import time
+
+import requests
+import web
+from wechatpy.enterprise import create_reply, parse_message
+from wechatpy.enterprise.crypto import WeChatCrypto
+from wechatpy.enterprise.exceptions import InvalidCorpIdException
+from wechatpy.exceptions import InvalidSignatureException, WeChatClientException
+
+from bridge.context import Context
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel
+from channel.wechatcom.wechatcomapp_client import WechatComAppClient
+from channel.wechatcom.wechatcomapp_message import WechatComAppMessage
+from common.log import logger
+from common.singleton import singleton
+from common.utils import compress_imgfile, fsize, split_string_by_utf8_length
+from config import conf, subscribe_msg
+from voice.audio_convert import any_to_amr, split_audio
+
+MAX_UTF8_LEN = 2048
+
+
+@singleton
+class WechatComAppChannel(ChatChannel):
+    NOT_SUPPORT_REPLYTYPE = []
+
+    def __init__(self):
+        super().__init__()
+        self.corp_id = conf().get("wechatcom_corp_id")
+        self.secret = conf().get("wechatcomapp_secret")
+        self.agent_id = conf().get("wechatcomapp_agent_id")
+        self.token = conf().get("wechatcomapp_token")
+        self.aes_key = conf().get("wechatcomapp_aes_key")
+        print(self.corp_id, self.secret, self.agent_id, self.token, self.aes_key)
+        logger.info(
+            "[wechatcom] init: corp_id: {}, secret: {}, agent_id: {}, token: {}, aes_key: {}".format(self.corp_id, self.secret, self.agent_id, self.token, self.aes_key)
+        )
+        self.crypto = WeChatCrypto(self.token, self.aes_key, self.corp_id)
+        self.client = WechatComAppClient(self.corp_id, self.secret)
+
+    def startup(self):
+        # start message listener
+        urls = ("/wxcomapp", "channel.wechatcom.wechatcomapp_channel.Query")
+        app = web.application(urls, globals(), autoreload=False)
+        port = conf().get("wechatcomapp_port", 9898)
+        web.httpserver.runsimple(app.wsgifunc(), ("0.0.0.0", port))
+
+    def send(self, reply: Reply, context: Context):
+        receiver = context["receiver"]
+        if reply.type in [ReplyType.TEXT, ReplyType.ERROR, ReplyType.INFO]:
+            reply_text = reply.content
+            texts = split_string_by_utf8_length(reply_text, MAX_UTF8_LEN)
+            if len(texts) > 1:
+                logger.info("[wechatcom] text too long, split into {} parts".format(len(texts)))
+            for i, text in enumerate(texts):
+                self.client.message.send_text(self.agent_id, receiver, text)
+                if i != len(texts) - 1:
+                    time.sleep(0.5)  # 休眠0.5秒，防止发送过快乱序
+            logger.info("[wechatcom] Do send text to {}: {}".format(receiver, reply_text))
+        elif reply.type == ReplyType.VOICE:
+            try:
+                media_ids = []
+                file_path = reply.content
+                amr_file = os.path.splitext(file_path)[0] + ".amr"
+                any_to_amr(file_path, amr_file)
+                duration, files = split_audio(amr_file, 60 * 1000)
+                if len(files) > 1:
+                    logger.info("[wechatcom] voice too long {}s > 60s , split into {} parts".format(duration / 1000.0, len(files)))
+                for path in files:
+                    response = self.client.media.upload("voice", open(path, "rb"))
+                    logger.debug("[wechatcom] upload voice response: {}".format(response))
+                    media_ids.append(response["media_id"])
+            except WeChatClientException as e:
+                logger.error("[wechatcom] upload voice failed: {}".format(e))
+                return
+            try:
+                os.remove(file_path)
+                if amr_file != file_path:
+                    os.remove(amr_file)
+            except Exception:
+                pass
+            for media_id in media_ids:
+                self.client.message.send_voice(self.agent_id, receiver, media_id)
+                time.sleep(1)
+            logger.info("[wechatcom] sendVoice={}, receiver={}".format(reply.content, receiver))
+        elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+            img_url = reply.content
+            pic_res = requests.get(img_url, stream=True)
+            image_storage = io.BytesIO()
+            for block in pic_res.iter_content(1024):
+                image_storage.write(block)
+            sz = fsize(image_storage)
+            if sz >= 10 * 1024 * 1024:
+                logger.info("[wechatcom] image too large, ready to compress, sz={}".format(sz))
+                image_storage = compress_imgfile(image_storage, 10 * 1024 * 1024 - 1)
+                logger.info("[wechatcom] image compressed, sz={}".format(fsize(image_storage)))
+            image_storage.seek(0)
+            try:
+                response = self.client.media.upload("image", image_storage)
+                logger.debug("[wechatcom] upload image response: {}".format(response))
+            except WeChatClientException as e:
+                logger.error("[wechatcom] upload image failed: {}".format(e))
+                return
+
+            self.client.message.send_image(self.agent_id, receiver, response["media_id"])
+            logger.info("[wechatcom] sendImage url={}, receiver={}".format(img_url, receiver))
+        elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
+            image_storage = reply.content
+            sz = fsize(image_storage)
+            if sz >= 10 * 1024 * 1024:
+                logger.info("[wechatcom] image too large, ready to compress, sz={}".format(sz))
+                image_storage = compress_imgfile(image_storage, 10 * 1024 * 1024 - 1)
+                logger.info("[wechatcom] image compressed, sz={}".format(fsize(image_storage)))
+            image_storage.seek(0)
+            try:
+                response = self.client.media.upload("image", image_storage)
+                logger.debug("[wechatcom] upload image response: {}".format(response))
+            except WeChatClientException as e:
+                logger.error("[wechatcom] upload image failed: {}".format(e))
+                return
+            self.client.message.send_image(self.agent_id, receiver, response["media_id"])
+            logger.info("[wechatcom] sendImage, receiver={}".format(receiver))
+
+
+class Query:
+    def GET(self):
+        channel = WechatComAppChannel()
+        params = web.input()
+        logger.info("[wechatcom] receive params: {}".format(params))
+        try:
+            signature = params.msg_signature
+            timestamp = params.timestamp
+            nonce = params.nonce
+            echostr = params.echostr
+            echostr = channel.crypto.check_signature(signature, timestamp, nonce, echostr)
+        except InvalidSignatureException:
+            raise web.Forbidden()
+        return echostr
+
+    def POST(self):
+        channel = WechatComAppChannel()
+        params = web.input()
+        logger.info("[wechatcom] receive params: {}".format(params))
+        try:
+            signature = params.msg_signature
+            timestamp = params.timestamp
+            nonce = params.nonce
+            message = channel.crypto.decrypt_message(web.data(), signature, timestamp, nonce)
+        except (InvalidSignatureException, InvalidCorpIdException):
+            raise web.Forbidden()
+        msg = parse_message(message)
+        logger.debug("[wechatcom] receive message: {}, msg= {}".format(message, msg))
+        if msg.type == "event":
+            if msg.event == "subscribe":
+                reply_content = subscribe_msg()
+                if reply_content:
+                    reply = create_reply(reply_content, msg).render()
+                    res = channel.crypto.encrypt_message(reply, nonce, timestamp)
+                    return res
+        else:
+            try:
+                wechatcom_msg = WechatComAppMessage(msg, client=channel.client)
+            except NotImplementedError as e:
+                logger.debug("[wechatcom] " + str(e))
+                return "success"
+            context = channel._compose_context(
+                wechatcom_msg.ctype,
+                wechatcom_msg.content,
+                isgroup=False,
+                msg=wechatcom_msg,
+            )
+            if context:
+                channel.produce(context)
+        return "success"

channel/wechatcom/wechatcomapp_client.py

@@ -0,0 +1,21 @@
+import threading
+import time
+
+from wechatpy.enterprise import WeChatClient
+
+
+class WechatComAppClient(WeChatClient):
+    def __init__(self, corp_id, secret, access_token=None, session=None, timeout=None, auto_retry=True):
+        super(WechatComAppClient, self).__init__(corp_id, secret, access_token, session, timeout, auto_retry)
+        self.fetch_access_token_lock = threading.Lock()
+
+    def fetch_access_token(self):  # 重载父类方法，加锁避免多线程重复获取access_token
+        with self.fetch_access_token_lock:
+            access_token = self.session.get(self.access_token_key)
+            if access_token:
+                if not self.expires_at:
+                    return access_token
+                timestamp = time.time()
+                if self.expires_at - timestamp > 60:
+                    return access_token
+            return super().fetch_access_token()

channel/wechatcom/wechatcomapp_message.py

@@ -0,0 +1,52 @@
+from wechatpy.enterprise import WeChatClient
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from common.tmp_dir import TmpDir
+
+
+class WechatComAppMessage(ChatMessage):
+    def __init__(self, msg, client: WeChatClient, is_group=False):
+        super().__init__(msg)
+        self.msg_id = msg.id
+        self.create_time = msg.time
+        self.is_group = is_group
+
+        if msg.type == "text":
+            self.ctype = ContextType.TEXT
+            self.content = msg.content
+        elif msg.type == "voice":
+            self.ctype = ContextType.VOICE
+            self.content = TmpDir().path() + msg.media_id + "." + msg.format  # content直接存临时目录路径
+
+            def download_voice():
+                # 如果响应状态码是200，则将响应内容写入本地文件
+                response = client.media.download(msg.media_id)
+                if response.status_code == 200:
+                    with open(self.content, "wb") as f:
+                        f.write(response.content)
+                else:
+                    logger.info(f"[wechatcom] Failed to download voice file, {response.content}")
+
+            self._prepare_fn = download_voice
+        elif msg.type == "image":
+            self.ctype = ContextType.IMAGE
+            self.content = TmpDir().path() + msg.media_id + ".png"  # content直接存临时目录路径
+
+            def download_image():
+                # 如果响应状态码是200，则将响应内容写入本地文件
+                response = client.media.download(msg.media_id)
+                if response.status_code == 200:
+                    with open(self.content, "wb") as f:
+                        f.write(response.content)
+                else:
+                    logger.info(f"[wechatcom] Failed to download image file, {response.content}")
+
+            self._prepare_fn = download_image
+        else:
+            raise NotImplementedError("Unsupported message type: Type:{} ".format(msg.type))
+
+        self.from_user_id = msg.source
+        self.to_user_id = msg.target
+        self.other_user_id = msg.source

channel/wechatmp/README.md

@@ -0,0 +1,100 @@
+# 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，这里新增了微信公众号channel，提供无风险的服务。
+目前支持订阅号和服务号两种类型的公众号，它们都支持文本交互，语音和图片输入。其中个人主体的微信订阅号由于无法通过微信认证，存在回复时间限制，每天的图片和声音回复次数也有限制。
+
+## 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。
+
+此外，需要在我们的服务器上安装python的web框架web.py和wechatpy。
+以ubuntu为例(在ubuntu 22.04上测试):
+```
+pip3 install web.py
+pip3 install wechatpy
+```
+
+然后在[微信公众平台](https://mp.weixin.qq.com)注册一个自己的公众号，类型选择订阅号，主体为个人即可。
+
+然后根据[接入指南](https://developers.weixin.qq.com/doc/offiaccount/Basic_Information/Access_Overview.html)的说明，在[微信公众平台](https://mp.weixin.qq.com)的“设置与开发”-“基本配置”-“服务器配置”中填写服务器地址`URL`和令牌`Token`。`URL`填写格式为`http://url/wx`，可使用IP（成功几率看脸），`Token`是你自己编的一个特定的令牌。消息加解密方式如果选择了需要加密的模式，需要在配置中填写`wechatmp_aes_key`。
+
+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",     # 如果通过了微信认证，将"wechatmp"替换为"wechatmp_service"，可极大的优化使用体验
+"wechatmp_token": "xxxx",       # 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": "xxxx",      # 微信公众平台的appID
+"wechatmp_app_secret": "xxxx",  # 微信公众平台的appsecret
+"wechatmp_aes_key": "",         # 微信公众平台的EncodingAESKey，加密模式需要
+"single_chat_prefix": [""],     # 推荐设置，任意对话都可以触发回复，不添加前缀
+"single_chat_reply_prefix": "", # 推荐设置，回复不设置前缀
+"plugin_trigger_prefix": "&",   # 推荐设置，在手机微信客户端中，$%^等符号与中文连在一起时会自动显示一段较大的间隔，用户体验不好。请不要使用管理员指令前缀"#"，这会造成未知问题。
+```
+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：
+```
+sudo iptables -t nat -A PREROUTING -p tcp --dport 80 -j REDIRECT --to-port 8080
+sudo iptables-save > /etc/iptables/rules.v4
+```
+第二个方法是让python程序直接监听80端口，在配置文件中设置`"wechatmp_port": 80` ，在linux上需要使用`sudo python3 app.py`启动程序。然而这会导致一系列环境和权限问题，因此不是推荐的方法。
+
+443端口同理，注意需要支持SSL，也就是https的访问，在`wechatmp_channel.py`中需要修改相应的证书路径。
+
+程序启动并监听端口后，在刚才的“服务器配置”中点击`提交`即可验证你的服务器。
+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。
+
+之后需要在公众号开发信息下将本机IP加入到IP白名单。
+
+不然在启用后，发送语音、图片等消息可能会遇到如下报错：
+```
+'errcode': 40164, 'errmsg': 'invalid ip xx.xx.xx.xx not in whitelist rid
+```
+
+
+## 个人微信公众号的限制
+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的回答进行了拆分，以满足限制。
+
+## 私有api_key
+公共api有访问频率限制（免费账号每分钟最多3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。
+
+## 语音输入
+利用微信自带的语音识别功能，提供语音输入能力。需要在公众号管理页面的“设置与开发”->“接口权限”页面开启“接收语音识别结果”。
+
+## 语音回复
+请在配置文件中添加以下词条：
+```
+  "voice_reply_voice": true,
+```
+这样公众号将会用语音回复语音消息，实现语音对话。
+
+默认的语音合成引擎是`google`，它是免费使用的。
+
+如果要选择其他的语音合成引擎，请添加以下配置项：
+```
+"text_to_voice": "pytts"
+```
+
+pytts是本地的语音合成引擎。还支持baidu,azure，这些你需要自行配置相关的依赖和key。
+
+如果使用pytts，在ubuntu上需要安装如下依赖：
+```
+sudo apt update
+sudo apt install espeak
+sudo apt install ffmpeg
+python3 -m pip install pyttsx3
+```
+不是很建议开启pytts语音回复，因为它是离线本地计算，算的慢会拖垮服务器，且声音不好听。
+
+## 图片回复
+现在认证公众号和非认证公众号都可以实现的图片和语音回复。但是非认证公众号使用了永久素材接口，每天有1000次的调用上限（每个月有10次重置机会，程序中已设定遇到上限会自动重置），且永久素材库存也有上限。因此对于非认证公众号，我们会在回复图片或者语音消息后的10秒内从永久素材库存内删除该素材。
+
+## 测试
+目前在`RoboStyle`这个公众号上进行了测试（基于[wechatmp分支](https://github.com/JS00000/chatgpt-on-wechat/tree/wechatmp)），感兴趣的可以关注并体验。开启了godcmd, Banwords, role, dungeon, finish这五个插件，其他的插件还没有详尽测试。百度的接口暂未测试。[wechatmp-stable分支](https://github.com/JS00000/chatgpt-on-wechat/tree/wechatmp-stable)是较稳定的上个版本，但也缺少最新的功能支持。
+
+## TODO
+ - [x] 语音输入
+ - [x] 图片输入
+ - [x] 使用临时素材接口提供认证公众号的图片和语音回复
+ - [x] 使用永久素材接口提供未认证公众号的图片和语音回复
+ - [ ] 高并发支持

channel/wechatmp/active_reply.py

@@ -0,0 +1,75 @@
+import time
+
+import web
+from wechatpy import parse_message
+from wechatpy.replies import create_reply
+
+from bridge.context import *
+from bridge.reply import *
+from channel.wechatmp.common import *
+from channel.wechatmp.wechatmp_channel import WechatMPChannel
+from channel.wechatmp.wechatmp_message import WeChatMPMessage
+from common.log import logger
+from config import conf, subscribe_msg
+
+
+# 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.
+        try:
+            args = web.input()
+            verify_server(args)
+            channel = WechatMPChannel()
+            message = web.data()
+            encrypt_func = lambda x: x
+            if args.get("encrypt_type") == "aes":
+                logger.debug("[wechatmp] Receive encrypted post data:\n" + message.decode("utf-8"))
+                if not channel.crypto:
+                    raise Exception("Crypto not initialized, Please set wechatmp_aes_key in config.json")
+                message = channel.crypto.decrypt_message(message, args.msg_signature, args.timestamp, args.nonce)
+                encrypt_func = lambda x: channel.crypto.encrypt_message(x, args.nonce, args.timestamp)
+            else:
+                logger.debug("[wechatmp] Receive post data:\n" + message.decode("utf-8"))
+            msg = parse_message(message)
+            if msg.type in ["text", "voice", "image"]:
+                wechatmp_msg = WeChatMPMessage(msg, client=channel.client)
+                from_user = wechatmp_msg.from_user_id
+                content = wechatmp_msg.content
+                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,
+                        content,
+                    )
+                )
+                if msg.type == "voice" and wechatmp_msg.ctype == ContextType.TEXT and conf().get("voice_reply_voice", False):
+                    context = channel._compose_context(wechatmp_msg.ctype, content, isgroup=False, desire_rtype=ReplyType.VOICE, msg=wechatmp_msg)
+                else:
+                    context = channel._compose_context(wechatmp_msg.ctype, content, isgroup=False, msg=wechatmp_msg)
+                if context:
+                    channel.produce(context)
+                # The reply will be sent by channel.send() in another thread
+                return "success"
+            elif msg.type == "event":
+                logger.info("[wechatmp] Event {} from {}".format(msg.event, msg.source))
+                if msg.event in ["subscribe", "subscribe_scan"]:
+                    reply_text = subscribe_msg()
+                    if reply_text:
+                        replyPost = create_reply(reply_text, msg)
+                        return encrypt_func(replyPost.render())
+                else:
+                    return "success"
+            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 +1,27 @@
+import web
+from wechatpy.crypto import WeChatCrypto
+from wechatpy.exceptions import InvalidSignatureException
+from wechatpy.utils import check_signature
+
+from config import conf
+
+MAX_UTF8_LEN = 2048
+
+
+class WeChatAPIException(Exception):
+    pass
+
+
+def verify_server(data):
+    try:
+        signature = data.signature
+        timestamp = data.timestamp
+        nonce = data.nonce
+        echostr = data.get("echostr", None)
+        token = conf().get("wechatmp_token")  # 请按照公众平台官网\基本配置中信息填写
+        check_signature(token, signature, timestamp, nonce)
+        return echostr
+    except InvalidSignatureException:
+        raise web.Forbidden("Invalid signature")
+    except Exception as e:
+        raise web.Forbidden(str(e))

channel/wechatmp/passive_reply.py

@@ -0,0 +1,209 @@
+import asyncio
+import time
+
+import web
+from wechatpy import parse_message
+from wechatpy.replies import ImageReply, VoiceReply, create_reply
+import textwrap
+from bridge.context import *
+from bridge.reply import *
+from channel.wechatmp.common import *
+from channel.wechatmp.wechatmp_channel import WechatMPChannel
+from channel.wechatmp.wechatmp_message import WeChatMPMessage
+from common.log import logger
+from common.utils import split_string_by_utf8_length
+from config import conf, subscribe_msg
+
+
+# This class is instantiated once per query
+class Query:
+    def GET(self):
+        return verify_server(web.input())
+
+    def POST(self):
+        try:
+            args = web.input()
+            verify_server(args)
+            request_time = time.time()
+            channel = WechatMPChannel()
+            message = web.data()
+            encrypt_func = lambda x: x
+            if args.get("encrypt_type") == "aes":
+                logger.debug("[wechatmp] Receive encrypted post data:\n" + message.decode("utf-8"))
+                if not channel.crypto:
+                    raise Exception("Crypto not initialized, Please set wechatmp_aes_key in config.json")
+                message = channel.crypto.decrypt_message(message, args.msg_signature, args.timestamp, args.nonce)
+                encrypt_func = lambda x: channel.crypto.encrypt_message(x, args.nonce, args.timestamp)
+            else:
+                logger.debug("[wechatmp] Receive post data:\n" + message.decode("utf-8"))
+            msg = parse_message(message)
+            if msg.type in ["text", "voice", "image"]:
+                wechatmp_msg = WeChatMPMessage(msg, client=channel.client)
+                from_user = wechatmp_msg.from_user_id
+                content = wechatmp_msg.content
+                message_id = wechatmp_msg.msg_id
+
+                supported = True
+                if "【收到不支持的消息类型，暂无法显示】" in content:
+                    supported = False  # not supported, used to refresh
+
+                # New request
+                if (
+                    from_user not in channel.cache_dict
+                    and from_user not in channel.running
+                    or content.startswith("#")
+                    and message_id not in channel.request_cnt  # insert the godcmd
+                ):
+                    # The first query begin
+                    if msg.type == "voice" and wechatmp_msg.ctype == ContextType.TEXT and conf().get("voice_reply_voice", False):
+                        context = channel._compose_context(wechatmp_msg.ctype, content, isgroup=False, desire_rtype=ReplyType.VOICE, msg=wechatmp_msg)
+                    else:
+                        context = channel._compose_context(wechatmp_msg.ctype, content, isgroup=False, msg=wechatmp_msg)
+                    logger.debug("[wechatmp] context: {} {} {}".format(context, wechatmp_msg, supported))
+
+                    if supported and context:
+                        channel.running.add(from_user)
+                        channel.produce(context)
+                    else:
+                        trigger_prefix = conf().get("single_chat_prefix", [""])[0]
+                        if trigger_prefix or not supported:
+                            if trigger_prefix:
+                                reply_text = 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:
+                                reply_text = textwrap.dedent(
+                                    """\
+                                    你好，很高兴见到你。
+                                    请跟我说话吧。"""
+                                )
+                        else:
+                            logger.error(f"[wechatmp] unknown error")
+                            reply_text = textwrap.dedent(
+                                """\
+                                未知错误，请稍后再试"""
+                            )
+
+                        replyPost = create_reply(reply_text, msg)
+                        return encrypt_func(replyPost.render())
+
+                # Wechat official server will request 3 times (5 seconds each), with the same message_id.
+                # Because the interval is 5 seconds, here assumed that do not have multithreading problems.
+                request_cnt = channel.request_cnt.get(message_id, 0) + 1
+                channel.request_cnt[message_id] = request_cnt
+                logger.info(
+                    "[wechatmp] Request {} from {} {} {}:{}\n{}".format(
+                        request_cnt, from_user, message_id, web.ctx.env.get("REMOTE_ADDR"), web.ctx.env.get("REMOTE_PORT"), content
+                    )
+                )
+
+                task_running = True
+                waiting_until = request_time + 4
+                while time.time() < waiting_until:
+                    if from_user in channel.running:
+                        time.sleep(0.1)
+                    else:
+                        task_running = False
+                        break
+
+                reply_text = ""
+                if task_running:
+                    if request_cnt < 3:
+                        # waiting for timeout (the POST request will be closed by Wechat official server)
+                        time.sleep(2)
+                        # and do nothing, waiting for the next request
+                        return "success"
+                    else:  # request_cnt == 3:
+                        # return timeout message
+                        reply_text = "【正在思考中，回复任意文字尝试获取回复】"
+                        replyPost = create_reply(reply_text, msg)
+                        return encrypt_func(replyPost.render())
+
+                # reply is ready
+                channel.request_cnt.pop(message_id)
+
+                # no return because of bandwords or other reasons
+                if from_user not in channel.cache_dict and from_user not in channel.running:
+                    return "success"
+
+                # Only one request can access to the cached data
+                try:
+                    (reply_type, reply_content) = channel.cache_dict.pop(from_user)
+                except KeyError:
+                    return "success"
+
+                if reply_type == "text":
+                    if len(reply_content.encode("utf8")) <= MAX_UTF8_LEN:
+                        reply_text = reply_content
+                    else:
+                        continue_text = "\n【未完待续，回复任意文字以继续】"
+                        splits = split_string_by_utf8_length(
+                            reply_content,
+                            MAX_UTF8_LEN - len(continue_text.encode("utf-8")),
+                            max_split=1,
+                        )
+                        reply_text = splits[0] + continue_text
+                        channel.cache_dict[from_user] = ("text", splits[1])
+
+                    logger.info(
+                        "[wechatmp] Request {} do send to {} {}: {}\n{}".format(
+                            request_cnt,
+                            from_user,
+                            message_id,
+                            content,
+                            reply_text,
+                        )
+                    )
+                    replyPost = create_reply(reply_text, msg)
+                    return encrypt_func(replyPost.render())
+
+                elif reply_type == "voice":
+                    media_id = reply_content
+                    asyncio.run_coroutine_threadsafe(channel.delete_media(media_id), channel.delete_media_loop)
+                    logger.info(
+                        "[wechatmp] Request {} do send to {} {}: {} voice media_id {}".format(
+                            request_cnt,
+                            from_user,
+                            message_id,
+                            content,
+                            media_id,
+                        )
+                    )
+                    replyPost = VoiceReply(message=msg)
+                    replyPost.media_id = media_id
+                    return encrypt_func(replyPost.render())
+
+                elif reply_type == "image":
+                    media_id = reply_content
+                    asyncio.run_coroutine_threadsafe(channel.delete_media(media_id), channel.delete_media_loop)
+                    logger.info(
+                        "[wechatmp] Request {} do send to {} {}: {} image media_id {}".format(
+                            request_cnt,
+                            from_user,
+                            message_id,
+                            content,
+                            media_id,
+                        )
+                    )
+                    replyPost = ImageReply(message=msg)
+                    replyPost.media_id = media_id
+                    return encrypt_func(replyPost.render())
+
+            elif msg.type == "event":
+                logger.info("[wechatmp] Event {} from {}".format(msg.event, msg.source))
+                if msg.event in ["subscribe", "subscribe_scan"]:
+                    reply_text = subscribe_msg()
+                    if reply_text:
+                        replyPost = create_reply(reply_text, msg)
+                        return encrypt_func(replyPost.render())
+                else:
+                    return "success"
+            else:
+                logger.info("暂且不处理")
+            return "success"
+        except Exception as exc:
+            logger.exception(exc)
+            return exc

channel/wechatmp/wechatmp_channel.py

@@ -0,0 +1,216 @@
+# -*- coding: utf-8 -*-
+import asyncio
+import imghdr
+import io
+import os
+import threading
+import time
+
+import requests
+import web
+from wechatpy.crypto import WeChatCrypto
+from wechatpy.exceptions import WeChatClientException
+
+from bridge.context import *
+from bridge.reply import *
+from channel.chat_channel import ChatChannel
+from channel.wechatmp.common import *
+from channel.wechatmp.wechatmp_client import WechatMPClient
+from common.log import logger
+from common.singleton import singleton
+from common.utils import split_string_by_utf8_length
+from config import conf
+from voice.audio_convert import any_to_mp3
+
+# If using SSL, uncomment the following lines, and modify the certificate path.
+# from cheroot.server import HTTPServer
+# from cheroot.ssl.builtin import BuiltinSSLAdapter
+# HTTPServer.ssl_adapter = BuiltinSSLAdapter(
+#         certificate='/ssl/cert.pem',
+#         private_key='/ssl/cert.key')
+
+
+@singleton
+class WechatMPChannel(ChatChannel):
+    def __init__(self, passive_reply=True):
+        super().__init__()
+        self.passive_reply = passive_reply
+        self.NOT_SUPPORT_REPLYTYPE = []
+        appid = conf().get("wechatmp_app_id")
+        secret = conf().get("wechatmp_app_secret")
+        token = conf().get("wechatmp_token")
+        aes_key = conf().get("wechatmp_aes_key")
+        self.client = WechatMPClient(appid, secret)
+        self.crypto = None
+        if aes_key:
+            self.crypto = WeChatCrypto(token, aes_key, appid)
+        if self.passive_reply:
+            # Cache the reply to the user's first message
+            self.cache_dict = dict()
+            # Record whether the current message is being processed
+            self.running = set()
+            # Count the request from wechat official server by message_id
+            self.request_cnt = dict()
+            # The permanent media need to be deleted to avoid media number limit
+            self.delete_media_loop = asyncio.new_event_loop()
+            t = threading.Thread(target=self.start_loop, args=(self.delete_media_loop,))
+            t.setDaemon(True)
+            t.start()
+
+    def startup(self):
+        if self.passive_reply:
+            urls = ("/wx", "channel.wechatmp.passive_reply.Query")
+        else:
+            urls = ("/wx", "channel.wechatmp.active_reply.Query")
+        app = web.application(urls, globals(), autoreload=False)
+        port = conf().get("wechatmp_port", 8080)
+        web.httpserver.runsimple(app.wsgifunc(), ("0.0.0.0", port))
+
+    def start_loop(self, loop):
+        asyncio.set_event_loop(loop)
+        loop.run_forever()
+
+    async def delete_media(self, media_id):
+        logger.debug("[wechatmp] permanent media {} will be deleted in 10s".format(media_id))
+        await asyncio.sleep(10)
+        self.client.material.delete(media_id)
+        logger.info("[wechatmp] permanent media {} has been deleted".format(media_id))
+
+    def send(self, reply: Reply, context: Context):
+        receiver = context["receiver"]
+        if self.passive_reply:
+            if reply.type == ReplyType.TEXT or reply.type == ReplyType.INFO or reply.type == ReplyType.ERROR:
+                reply_text = reply.content
+                logger.info("[wechatmp] text cached, receiver {}\n{}".format(receiver, reply_text))
+                self.cache_dict[receiver] = ("text", reply_text)
+            elif reply.type == ReplyType.VOICE:
+                try:
+                    voice_file_path = reply.content
+                    with open(voice_file_path, "rb") as f:
+                        # support: <2M, <60s, mp3/wma/wav/amr
+                        response = self.client.material.add("voice", f)
+                        logger.debug("[wechatmp] upload voice response: {}".format(response))
+                        # 根据文件大小估计一个微信自动审核的时间，审核结束前返回将会导致语音无法播放，这个估计有待验证
+                        f_size = os.fstat(f.fileno()).st_size
+                        time.sleep(1.0 + 2 * f_size / 1024 / 1024)
+                        # todo check media_id
+                except WeChatClientException as e:
+                    logger.error("[wechatmp] upload voice failed: {}".format(e))
+                    return
+                media_id = response["media_id"]
+                logger.info("[wechatmp] voice uploaded, receiver {}, media_id {}".format(receiver, media_id))
+                self.cache_dict[receiver] = ("voice", media_id)
+
+            elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+                img_url = reply.content
+                pic_res = requests.get(img_url, stream=True)
+                image_storage = io.BytesIO()
+                for block in pic_res.iter_content(1024):
+                    image_storage.write(block)
+                image_storage.seek(0)
+                image_type = imghdr.what(image_storage)
+                filename = receiver + "-" + str(context["msg"].msg_id) + "." + image_type
+                content_type = "image/" + image_type
+                try:
+                    response = self.client.material.add("image", (filename, image_storage, content_type))
+                    logger.debug("[wechatmp] upload image response: {}".format(response))
+                except WeChatClientException as e:
+                    logger.error("[wechatmp] upload image failed: {}".format(e))
+                    return
+                media_id = response["media_id"]
+                logger.info("[wechatmp] image uploaded, receiver {}, media_id {}".format(receiver, media_id))
+                self.cache_dict[receiver] = ("image", media_id)
+            elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
+                image_storage = reply.content
+                image_storage.seek(0)
+                image_type = imghdr.what(image_storage)
+                filename = receiver + "-" + str(context["msg"].msg_id) + "." + image_type
+                content_type = "image/" + image_type
+                try:
+                    response = self.client.material.add("image", (filename, image_storage, content_type))
+                    logger.debug("[wechatmp] upload image response: {}".format(response))
+                except WeChatClientException as e:
+                    logger.error("[wechatmp] upload image failed: {}".format(e))
+                    return
+                media_id = response["media_id"]
+                logger.info("[wechatmp] image uploaded, receiver {}, media_id {}".format(receiver, media_id))
+                self.cache_dict[receiver] = ("image", media_id)
+        else:
+            if reply.type == ReplyType.TEXT or reply.type == ReplyType.INFO or reply.type == ReplyType.ERROR:
+                reply_text = reply.content
+                texts = split_string_by_utf8_length(reply_text, MAX_UTF8_LEN)
+                if len(texts) > 1:
+                    logger.info("[wechatmp] text too long, split into {} parts".format(len(texts)))
+                for i, text in enumerate(texts):
+                    self.client.message.send_text(receiver, text)
+                    if i != len(texts) - 1:
+                        time.sleep(0.5)  # 休眠0.5秒，防止发送过快乱序
+                logger.info("[wechatmp] Do send text to {}: {}".format(receiver, reply_text))
+            elif reply.type == ReplyType.VOICE:
+                try:
+                    file_path = reply.content
+                    file_name = os.path.basename(file_path)
+                    file_type = os.path.splitext(file_name)[1]
+                    if file_type == ".mp3":
+                        file_type = "audio/mpeg"
+                    elif file_type == ".amr":
+                        file_type = "audio/amr"
+                    else:
+                        mp3_file = os.path.splitext(file_path)[0] + ".mp3"
+                        any_to_mp3(file_path, mp3_file)
+                        file_path = mp3_file
+                        file_name = os.path.basename(file_path)
+                        file_type = "audio/mpeg"
+                    logger.info("[wechatmp] file_name: {}, file_type: {} ".format(file_name, file_type))
+                    # support: <2M, <60s, AMR\MP3
+                    response = self.client.media.upload("voice", (file_name, open(file_path, "rb"), file_type))
+                    logger.debug("[wechatmp] upload voice response: {}".format(response))
+                except WeChatClientException as e:
+                    logger.error("[wechatmp] upload voice failed: {}".format(e))
+                    return
+                self.client.message.send_voice(receiver, response["media_id"])
+                logger.info("[wechatmp] Do send voice to {}".format(receiver))
+            elif reply.type == ReplyType.IMAGE_URL:  # 从网络下载图片
+                img_url = reply.content
+                pic_res = requests.get(img_url, stream=True)
+                image_storage = io.BytesIO()
+                for block in pic_res.iter_content(1024):
+                    image_storage.write(block)
+                image_storage.seek(0)
+                image_type = imghdr.what(image_storage)
+                filename = receiver + "-" + str(context["msg"].msg_id) + "." + image_type
+                content_type = "image/" + image_type
+                try:
+                    response = self.client.media.upload("image", (filename, image_storage, content_type))
+                    logger.debug("[wechatmp] upload image response: {}".format(response))
+                except WeChatClientException as e:
+                    logger.error("[wechatmp] upload image failed: {}".format(e))
+                    return
+                self.client.message.send_image(receiver, response["media_id"])
+                logger.info("[wechatmp] Do send image to {}".format(receiver))
+            elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
+                image_storage = reply.content
+                image_storage.seek(0)
+                image_type = imghdr.what(image_storage)
+                filename = receiver + "-" + str(context["msg"].msg_id) + "." + image_type
+                content_type = "image/" + image_type
+                try:
+                    response = self.client.media.upload("image", (filename, image_storage, content_type))
+                    logger.debug("[wechatmp] upload image response: {}".format(response))
+                except WeChatClientException as e:
+                    logger.error("[wechatmp] upload image failed: {}".format(e))
+                    return
+                self.client.message.send_image(receiver, response["media_id"])
+                logger.info("[wechatmp] Do send image to {}".format(receiver))
+        return
+
+    def _success_callback(self, session_id, context, **kwargs):  # 线程异常结束时的回调函数
+        logger.debug("[wechatmp] Success to generate reply, msgId={}".format(context["msg"].msg_id))
+        if self.passive_reply:
+            self.running.remove(session_id)
+
+    def _fail_callback(self, session_id, exception, context, **kwargs):  # 线程异常结束时的回调函数
+        logger.exception("[wechatmp] Fail to generate reply to user, msgId={}, exception={}".format(context["msg"].msg_id, exception))
+        if self.passive_reply:
+            assert session_id not in self.cache_dict
+            self.running.remove(session_id)

channel/wechatmp/wechatmp_client.py

@@ -0,0 +1,49 @@
+import threading
+import time
+
+from wechatpy.client import WeChatClient
+from wechatpy.exceptions import APILimitedException
+
+from channel.wechatmp.common import *
+from common.log import logger
+
+
+class WechatMPClient(WeChatClient):
+    def __init__(self, appid, secret, access_token=None, session=None, timeout=None, auto_retry=True):
+        super(WechatMPClient, self).__init__(appid, secret, access_token, session, timeout, auto_retry)
+        self.fetch_access_token_lock = threading.Lock()
+        self.clear_quota_lock = threading.Lock()
+        self.last_clear_quota_time = -1
+
+    def clear_quota(self):
+        return self.post("clear_quota", data={"appid": self.appid})
+
+    def clear_quota_v2(self):
+        return self.post("clear_quota/v2", params={"appid": self.appid, "appsecret": self.secret})
+
+    def fetch_access_token(self):  # 重载父类方法，加锁避免多线程重复获取access_token
+        with self.fetch_access_token_lock:
+            access_token = self.session.get(self.access_token_key)
+            if access_token:
+                if not self.expires_at:
+                    return access_token
+                timestamp = time.time()
+                if self.expires_at - timestamp > 60:
+                    return access_token
+            return super().fetch_access_token()
+
+    def _request(self, method, url_or_endpoint, **kwargs):  # 重载父类方法，遇到API限流时，清除quota后重试
+        try:
+            return super()._request(method, url_or_endpoint, **kwargs)
+        except APILimitedException as e:
+            logger.error("[wechatmp] API quata has been used up. {}".format(e))
+            if self.last_clear_quota_time == -1 or time.time() - self.last_clear_quota_time > 60:
+                with self.clear_quota_lock:
+                    if self.last_clear_quota_time == -1 or time.time() - self.last_clear_quota_time > 60:
+                        self.last_clear_quota_time = time.time()
+                        response = self.clear_quota_v2()
+                        logger.debug("[wechatmp] API quata has been cleard, {}".format(response))
+                return super()._request(method, url_or_endpoint, **kwargs)
+            else:
+                logger.error("[wechatmp] last clear quota time is {}, less than 60s, skip clear quota")
+                raise e

channel/wechatmp/wechatmp_message.py

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-#
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from common.log import logger
+from common.tmp_dir import TmpDir
+
+
+class WeChatMPMessage(ChatMessage):
+    def __init__(self, msg, client=None):
+        super().__init__(msg)
+        self.msg_id = msg.id
+        self.create_time = msg.time
+        self.is_group = False
+
+        if msg.type == "text":
+            self.ctype = ContextType.TEXT
+            self.content = msg.content
+        elif msg.type == "voice":
+            if msg.recognition == None:
+                self.ctype = ContextType.VOICE
+                self.content = TmpDir().path() + msg.media_id + "." + msg.format  # content直接存临时目录路径
+
+                def download_voice():
+                    # 如果响应状态码是200，则将响应内容写入本地文件
+                    response = client.media.download(msg.media_id)
+                    if response.status_code == 200:
+                        with open(self.content, "wb") as f:
+                            f.write(response.content)
+                    else:
+                        logger.info(f"[wechatmp] Failed to download voice file, {response.content}")
+
+                self._prepare_fn = download_voice
+            else:
+                self.ctype = ContextType.TEXT
+                self.content = msg.recognition
+        elif msg.type == "image":
+            self.ctype = ContextType.IMAGE
+            self.content = TmpDir().path() + msg.media_id + ".png"  # content直接存临时目录路径
+
+            def download_image():
+                # 如果响应状态码是200，则将响应内容写入本地文件
+                response = client.media.download(msg.media_id)
+                if response.status_code == 200:
+                    with open(self.content, "wb") as f:
+                        f.write(response.content)
+                else:
+                    logger.info(f"[wechatmp] Failed to download image file, {response.content}")
+
+            self._prepare_fn = download_image
+        else:
+            raise NotImplementedError("Unsupported message type: Type:{} ".format(msg.type))
+
+        self.from_user_id = msg.source
+        self.to_user_id = msg.target
+        self.other_user_id = msg.source

common/const.py

@@ -0,0 +1,11 @@
+# bot_type
+OPEN_AI = "openAI"
+CHATGPT = "chatGPT"
+BAIDU = "baidu"
+XUNFEI = "xunfei"
+CHATGPTONAZURE = "chatGPTOnAzure"
+LINKAI = "linkai"
+
+VERSION = "1.3.0"
+
+MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "xunfei"]

common/dequeue.py

@@ -0,0 +1,33 @@
+from queue import Full, Queue
+from time import monotonic as time
+
+
+# add implementation of putleft to Queue
+class Dequeue(Queue):
+    def putleft(self, item, block=True, timeout=None):
+        with self.not_full:
+            if self.maxsize > 0:
+                if not block:
+                    if self._qsize() >= self.maxsize:
+                        raise Full
+                elif timeout is None:
+                    while self._qsize() >= self.maxsize:
+                        self.not_full.wait()
+                elif timeout < 0:
+                    raise ValueError("'timeout' must be a non-negative number")
+                else:
+                    endtime = time() + timeout
+                    while self._qsize() >= self.maxsize:
+                        remaining = endtime - time()
+                        if remaining <= 0.0:
+                            raise Full
+                        self.not_full.wait(remaining)
+            self._putleft(item)
+            self.unfinished_tasks += 1
+            self.not_empty.notify()
+
+    def putleft_nowait(self, item):
+        return self.putleft(item, block=False)
+
+    def _putleft(self, item):
+        self.queue.appendleft(item)

common/expired_dict.py

@@ -0,0 +1,42 @@
+from datetime import datetime, timedelta
+
+
+class ExpiredDict(dict):
+    def __init__(self, expires_in_seconds):
+        super().__init__()
+        self.expires_in_seconds = expires_in_seconds
+
+    def __getitem__(self, key):
+        value, expiry_time = super().__getitem__(key)
+        if datetime.now() > expiry_time:
+            del self[key]
+            raise KeyError("expired {}".format(key))
+        self.__setitem__(key, value)
+        return value
+
+    def __setitem__(self, key, value):
+        expiry_time = datetime.now() + timedelta(seconds=self.expires_in_seconds)
+        super().__setitem__(key, (value, expiry_time))
+
+    def get(self, key, default=None):
+        try:
+            return self[key]
+        except KeyError:
+            return default
+
+    def __contains__(self, key):
+        try:
+            self[key]
+            return True
+        except KeyError:
+            return False
+
+    def keys(self):
+        keys = list(super().keys())
+        return [key for key in keys if key in self]
+
+    def items(self):
+        return [(key, self[key]) for key in self.keys()]
+
+    def __iter__(self):
+        return self.keys().__iter__()

common/log.py

@@ -0,0 +1,38 @@
+import logging
+import sys
+
+
+def _reset_logger(log):
+    for handler in log.handlers:
+        handler.close()
+        log.removeHandler(handler)
+        del handler
+    log.handlers.clear()
+    log.propagate = False
+    console_handle = logging.StreamHandler(sys.stdout)
+    console_handle.setFormatter(
+        logging.Formatter(
+            "[%(levelname)s][%(asctime)s][%(filename)s:%(lineno)d] - %(message)s",
+            datefmt="%Y-%m-%d %H:%M:%S",
+        )
+    )
+    file_handle = logging.FileHandler("run.log", encoding="utf-8")
+    file_handle.setFormatter(
+        logging.Formatter(
+            "[%(levelname)s][%(asctime)s][%(filename)s:%(lineno)d] - %(message)s",
+            datefmt="%Y-%m-%d %H:%M:%S",
+        )
+    )
+    log.addHandler(file_handle)
+    log.addHandler(console_handle)
+
+
+def _get_logger():
+    log = logging.getLogger("log")
+    _reset_logger(log)
+    log.setLevel(logging.INFO)
+    return log
+
+
+# 日志句柄
+logger = _get_logger()

common/package_manager.py

@@ -0,0 +1,36 @@
+import time
+
+import pip
+from pip._internal import main as pipmain
+
+from common.log import _reset_logger, logger
+
+
+def install(package):
+    pipmain(["install", package])
+
+
+def install_requirements(file):
+    pipmain(["install", "-r", file, "--upgrade"])
+    _reset_logger(logger)
+
+
+def check_dulwich():
+    needwait = False
+    for i in range(2):
+        if needwait:
+            time.sleep(3)
+            needwait = False
+        try:
+            import dulwich
+
+            return
+        except ImportError:
+            try:
+                install("dulwich")
+            except:
+                needwait = True
+    try:
+        import dulwich
+    except ImportError:
+        raise ImportError("Unable to import dulwich")

common/singleton.py

@@ -0,0 +1,9 @@
+def singleton(cls):
+    instances = {}
+
+    def get_instance(*args, **kwargs):
+        if cls not in instances:
+            instances[cls] = cls(*args, **kwargs)
+        return instances[cls]
+
+    return get_instance

common/sorted_dict.py

@@ -0,0 +1,65 @@
+import heapq
+
+
+class SortedDict(dict):
+    def __init__(self, sort_func=lambda k, v: k, init_dict=None, reverse=False):
+        if init_dict is None:
+            init_dict = []
+        if isinstance(init_dict, dict):
+            init_dict = init_dict.items()
+        self.sort_func = sort_func
+        self.sorted_keys = None
+        self.reverse = reverse
+        self.heap = []
+        for k, v in init_dict:
+            self[k] = v
+
+    def __setitem__(self, key, value):
+        if key in self:
+            super().__setitem__(key, value)
+            for i, (priority, k) in enumerate(self.heap):
+                if k == key:
+                    self.heap[i] = (self.sort_func(key, value), key)
+                    heapq.heapify(self.heap)
+                    break
+            self.sorted_keys = None
+        else:
+            super().__setitem__(key, value)
+            heapq.heappush(self.heap, (self.sort_func(key, value), key))
+            self.sorted_keys = None
+
+    def __delitem__(self, key):
+        super().__delitem__(key)
+        for i, (priority, k) in enumerate(self.heap):
+            if k == key:
+                del self.heap[i]
+                heapq.heapify(self.heap)
+                break
+        self.sorted_keys = None
+
+    def keys(self):
+        if self.sorted_keys is None:
+            self.sorted_keys = [k for _, k in sorted(self.heap, reverse=self.reverse)]
+        return self.sorted_keys
+
+    def items(self):
+        if self.sorted_keys is None:
+            self.sorted_keys = [k for _, k in sorted(self.heap, reverse=self.reverse)]
+        sorted_items = [(k, self[k]) for k in self.sorted_keys]
+        return sorted_items
+
+    def _update_heap(self, key):
+        for i, (priority, k) in enumerate(self.heap):
+            if k == key:
+                new_priority = self.sort_func(key, self[key])
+                if new_priority != priority:
+                    self.heap[i] = (new_priority, key)
+                    heapq.heapify(self.heap)
+                    self.sorted_keys = None
+                break
+
+    def __iter__(self):
+        return iter(self.keys())
+
+    def __repr__(self):
+        return f"{type(self).__name__}({dict(self)}, sort_func={self.sort_func.__name__}, reverse={self.reverse})"

common/time_check.py

@@ -0,0 +1,42 @@
+import hashlib
+import re
+import time
+
+import config
+from common.log import logger
+
+
+def time_checker(f):
+    def _time_checker(self, *args, **kwargs):
+        _config = config.conf()
+        chat_time_module = _config.get("chat_time_module", False)
+        if chat_time_module:
+            chat_start_time = _config.get("chat_start_time", "00:00")
+            chat_stopt_time = _config.get("chat_stop_time", "24:00")
+            time_regex = re.compile(r"^([01]?[0-9]|2[0-4])(:)([0-5][0-9])$")  # 时间匹配，包含24:00
+
+            starttime_format_check = time_regex.match(chat_start_time)  # 检查停止时间格式
+            stoptime_format_check = time_regex.match(chat_stopt_time)  # 检查停止时间格式
+            chat_time_check = chat_start_time < chat_stopt_time  # 确定启动时间<停止时间
+
+            # 时间格式检查
+            if not (starttime_format_check and stoptime_format_check and chat_time_check):
+                logger.warn("时间格式不正确,请在config.json中修改您的CHAT_START_TIME/CHAT_STOP_TIME,否则可能会影响您正常使用,开始({})-结束({})".format(starttime_format_check, stoptime_format_check))
+            if chat_start_time > "23:59":
+                logger.error("启动时间可能存在问题，请修改!")
+
+            # 服务时间检查
+            now_time = time.strftime("%H:%M", time.localtime())
+            if chat_start_time <= now_time <= chat_stopt_time:  # 服务时间内，正常返回回答
+                f(self, *args, **kwargs)
+                return None
+            else:
+                if args[0]["Content"] == "#更新配置":  # 不在服务时间内也可以更新配置
+                    f(self, *args, **kwargs)
+                else:
+                    logger.info("非服务时间内,不接受访问")
+                    return None
+        else:
+            f(self, *args, **kwargs)  # 未开启时间模块则直接回答
+
+    return _time_checker

common/tmp_dir.py

@@ -0,0 +1,18 @@
+import os
+import pathlib
+
+from config import conf
+
+
+class TmpDir(object):
+    """A temporary directory that is deleted when the object is destroyed."""
+
+    tmpFilePath = pathlib.Path("./tmp/")
+
+    def __init__(self):
+        pathExists = os.path.exists(self.tmpFilePath)
+        if not pathExists:
+            os.makedirs(self.tmpFilePath)
+
+    def path(self):
+        return str(self.tmpFilePath) + "/"

common/token_bucket.py

@@ -0,0 +1,45 @@
+import threading
+import time
+
+
+class TokenBucket:
+    def __init__(self, tpm, timeout=None):
+        self.capacity = int(tpm)  # 令牌桶容量
+        self.tokens = 0  # 初始令牌数为0
+        self.rate = int(tpm) / 60  # 令牌每秒生成速率
+        self.timeout = timeout  # 等待令牌超时时间
+        self.cond = threading.Condition()  # 条件变量
+        self.is_running = True
+        # 开启令牌生成线程
+        threading.Thread(target=self._generate_tokens).start()
+
+    def _generate_tokens(self):
+        """生成令牌"""
+        while self.is_running:
+            with self.cond:
+                if self.tokens < self.capacity:
+                    self.tokens += 1
+                self.cond.notify()  # 通知获取令牌的线程
+            time.sleep(1 / self.rate)
+
+    def get_token(self):
+        """获取令牌"""
+        with self.cond:
+            while self.tokens <= 0:
+                flag = self.cond.wait(self.timeout)
+                if not flag:  # 超时
+                    return False
+            self.tokens -= 1
+        return True
+
+    def close(self):
+        self.is_running = False
+
+
+if __name__ == "__main__":
+    token_bucket = TokenBucket(20, None)  # 创建一个每分钟生产20个tokens的令牌桶
+    # token_bucket = TokenBucket(20, 0.1)
+    for i in range(3):
+        if token_bucket.get_token():
+            print(f"第{i+1}次请求成功")
+    token_bucket.close()

common/utils.py

@@ -0,0 +1,51 @@
+import io
+import os
+
+from PIL import Image
+
+
+def fsize(file):
+    if isinstance(file, io.BytesIO):
+        return file.getbuffer().nbytes
+    elif isinstance(file, str):
+        return os.path.getsize(file)
+    elif hasattr(file, "seek") and hasattr(file, "tell"):
+        pos = file.tell()
+        file.seek(0, os.SEEK_END)
+        size = file.tell()
+        file.seek(pos)
+        return size
+    else:
+        raise TypeError("Unsupported type")
+
+
+def compress_imgfile(file, max_size):
+    if fsize(file) <= max_size:
+        return file
+    file.seek(0)
+    img = Image.open(file)
+    rgb_image = img.convert("RGB")
+    quality = 95
+    while True:
+        out_buf = io.BytesIO()
+        rgb_image.save(out_buf, "JPEG", quality=quality)
+        if fsize(out_buf) <= max_size:
+            return out_buf
+        quality -= 5
+
+
+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 = min(start + max_length, len(encoded))
+        # 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