Release v2.5.1

Merge pull request #523 from RockChinQ/feat-prompt-preprocess-event
[Feat] 新增PromptPreprocessing事件
2025-11-25 19:37:36 +08:00 · 2023-07-31 18:12:59 +08:00 · 2023-07-31 17:55:06 +08:00 · 2023-07-31 17:53:33 +08:00 · 2023-07-31 17:46:30 +08:00 · 2023-07-31 17:27:28 +08:00
44 changed files with 1591 additions and 489 deletions
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -1,34 +0,0 @@
-// For format details, see https://aka.ms/devcontainer.json. For config options, see the
-// README at: https://github.com/devcontainers/templates/tree/main/src/python
-{
-	"name": "QChatGPT 3.10",
-	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
-	"image": "mcr.microsoft.com/devcontainers/python:0-3.10",
-
-	// Features to add to the dev container. More info: https://containers.dev/features.
-	// "features": {},
-
-	// Use 'forwardPorts' to make a list of ports inside the container available locally.
-	// "forwardPorts": [],
-
-	// Use 'postCreateCommand' to run commands after the container is created.
-	// "postCreateCommand": "pip3 install --user -r requirements.txt",
-
-	// Configure tool-specific properties.
-	// "customizations": {},
-	"customizations": {
-		"codespaces": {
-		  "repositories": {
-			"RockChinQ/QChatGPT": {
-			  "permissions": "write-all"
-			},
-			"RockChinQ/revLibs": {
-			  "permissions": "write-all"
-			}
-		  }
-		}
-	  }
-
-	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
-	// "remoteUser": "root"
-}
--- a/.github/workflows/sync-wiki.yml
+++ b/.github/workflows/sync-wiki.yml
@@ -1,7 +1,14 @@
 name: Update Wiki

 on:
+  pull_request:
+    branches:
+      - master
+    paths:
+      - 'res/wiki/**'
  push:
+    branches:
+      - master
    paths:
      - 'res/wiki/**'

@@ -23,11 +30,16 @@ jobs:
    - name: Copy res/wiki content to wiki
      run: |
        cp -r res/wiki/* wiki/
+    - name: Check for changes
+      run: |
+        cd wiki
+        if git diff --quiet; then
+          echo "No changes to commit."
+          exit 0
+        fi
    - name: Commit and Push Changes
      run: |
        cd wiki
-        if git diff --name-only; then
-          git add .
-          git commit -m "Update wiki"
-          git push
-        fi
+        git add .
+        git commit -m "Update wiki"
+        git push
--- a/.github/workflows/update-cmdpriv-template.yml
+++ b/.github/workflows/update-cmdpriv-template.yml
@@ -26,7 +26,7 @@ jobs:
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
-        python -m pip install --upgrade  yiri-mirai openai colorlog func_timeout dulwich Pillow
+        python -m pip install --upgrade  yiri-mirai openai colorlog func_timeout dulwich Pillow CallingGPT tiktoken

    - name: Copy Scripts
      run: |
--- a/.gitignore
+++ b/.gitignore
@@ -25,3 +25,4 @@ bin/
 .vscode
 test_*
 venv/
+hugchat.json
--- a/README.md
+++ b/README.md
@@ -7,18 +7,23 @@
 [English](README_en.md) | 简体中文

 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT?style=flat-square)](https://github.com/RockChinQ/QChatGPT/releases/latest)
+![Wakapi Count](https://wakapi.dev/api/badge/RockChinQ/interval:any/project:QChatGPT)

-> 2023/4/27 正在对纯Python实现的QQ登录框架、YAML配置文件、异步编程等功能进行概念验证，欢迎体验[LightQChat](https://github.com/RockChinQ/LightQChat)项目  
+
+> 2023/7/29 支持使用GPT的Function Calling功能实现类似ChatGPT Plugin的效果，请见[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)  
 > 2023/4/24 支持使用go-cqhttp登录QQ，请查看[此文档](https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE)  
 > 2023/3/18 现已支持GPT-4 API（内测），请查看`config-template.py`中的`completion_api_params`  
 > 2023/3/15 逆向库已支持New Bing，使用方法查看[插件文档](https://github.com/RockChinQ/revLibs)  

+
+**QChatGPT需要Python版本>=3.9**
 - 到[项目Wiki](https://github.com/RockChinQ/QChatGPT/wiki)可了解项目详细信息
 - 官方交流、答疑群: 656285629  
  - **进群提问前请您`确保`已经找遍文档和issue均无法解决**  
- 社区群（内有一键部署包、图形化界面等资源）: 362515018
+- 社区群（内有一键部署包、图形化界面等资源）: 891448839
 - QQ频道机器人见[QQChannelChatGPT](https://github.com/Soulter/QQChannelChatGPT)
 - 欢迎各种形式的贡献，请查看[贡献指引](CONTRIBUTING.md)
+- 购买ChatGPT账号: [此链接](http://fk.kimi.asia)

 ## 🍺模型适配一览

@@ -33,7 +38,7 @@
 - ChatGPT网页版GPT-3.5模型, 由[插件](https://github.com/RockChinQ/revLibs)接入
 - ChatGPT网页版GPT-4模型, 目前需要ChatGPT Plus订阅, 由[插件](https://github.com/RockChinQ/revLibs)接入
 - New Bing逆向库, 由[插件](https://github.com/RockChinQ/revLibs)接入
- HuggingChat, 由[插件](https://github.com/RockChinQ/revLibs)接入, 无需账号，仅支持英文
+- HuggingChat, 由[插件](https://github.com/RockChinQ/revLibs)接入, 仅支持英文

 ### 故事续写

@@ -107,6 +112,7 @@
 <summary>✅支持插件加载🧩</summary>

  - 自行实现插件加载器及相关支持
+  - 支持GPT的Function Calling功能
  - 详细查看[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
 </details>
 <details>
@@ -161,6 +167,9 @@

 ### - 注册OpenAI账号

+<details>
+<summary>点此查看步骤</summary>
+
 > 若您要直接使用非OpenAI的模型（如New Bing），可跳过此步骤，直接进行之后的部署，完成后按照相关插件的文档进行配置即可

 参考以下文章自行注册
@@ -171,6 +180,8 @@
 注册成功后请前往[个人中心查看](https://beta.openai.com/account/api-keys)api_key  
 完成注册后，使用以下自动化或手动部署步骤

+</details>
+
 ### - 自动化部署

 <details>
@@ -231,7 +242,7 @@ cd QChatGPT
 2. 安装依赖

 ```bash
-pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk
+pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk CallingGPT tiktoken
 ```

 3. 运行一次主程序，生成配置文件
@@ -271,21 +282,16 @@ python3 main.py
 详见[Wiki插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)  
 开发教程见[Wiki插件开发页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91)

+⭐我们已经支持了[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)，请查看[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)  
+
 <details>
 <summary>查看插件列表</summary>

-### 示例插件
+[所有插件列表](https://github.com/stars/RockChinQ/lists/qchatgpt-%E6%8F%92%E4%BB%B6)，欢迎提出issue以提交新的插件

-在`tests/plugin_examples`目录下，将其整个目录复制到`plugins`目录下即可使用
-
- `cmdcn` - 主程序指令中文形式
- `hello_plugin` - 在收到消息`hello`时回复相应消息
- `urlikethisijustsix` - 收到冒犯性消息时回复相应消息
-
-### 更多
-
-欢迎提交新的插件
+### 部分插件

+- [WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin) - 让机器人能联网！！
 - [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版接入此项目，关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E3%80%81ChatGPT%E7%BD%91%E9%A1%B5%E7%89%88%E3%80%81ChatGPT-API%E5%8C%BA%E5%88%AB)
 - [Switcher](https://github.com/RockChinQ/Switcher) - 支持通过指令切换使用的模型
 - [hello_plugin](https://github.com/RockChinQ/hello_plugin) - `hello_plugin` 的储存库形式，插件开发模板
--- a/README_en.md
+++ b/README_en.md
@@ -7,6 +7,7 @@
 English | [简体中文](README.md)

 [![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT?style=flat-square)](https://github.com/RockChinQ/QChatGPT/releases/latest)
+![Wakapi Count](https://wakapi.dev/api/badge/RockChinQ/interval:any/project:QChatGPT)

 - Refer to [Wiki](https://github.com/RockChinQ/QChatGPT/wiki) to get further information.  
 - Official QQ group: 656285629  
@@ -27,7 +28,7 @@ English | [简体中文](README.md)
 - ChatGPT website edition (GPT-3.5), see [revLibs plugin](https://github.com/RockChinQ/revLibs)
 - ChatGPT website edition (GPT-4), ChatGPT plus subscription required, see [revLibs plugin](https://github.com/RockChinQ/revLibs)
 - New Bing, see [revLibs plugin](https://github.com/RockChinQ/revLibs)
- HuggingChat, see [revLibs plugin](https://github.com/RockChinQ/revLibs), no accounts required, English only
+- HuggingChat, see [revLibs plugin](https://github.com/RockChinQ/revLibs), English only

 ### Story

--- a/config-template.py
+++ b/config-template.py
@@ -195,16 +195,22 @@ encourage_sponsor_at_start = True
 # 注意：较大的prompt_submit_length会导致OpenAI账户额度消耗更快
 prompt_submit_length = 2048

+# 是否在token超限报错时自动重置会话
+# 可在tips.py中编辑提示语
+auto_reset = True
+
 # OpenAI补全API的参数
 # 请在下方填写模型，程序自动选择接口
 # 现已支持的模型有：
 # 
 #    'gpt-4'
-#    'gpt-4-0314'
+#    'gpt-4-0613'
 #    'gpt-4-32k'
-#    'gpt-4-32k-0314'
+#    'gpt-4-32k-0613'
 #    'gpt-3.5-turbo'
-#    'gpt-3.5-turbo-0301'
+#    'gpt-3.5-turbo-16k'
+#    'gpt-3.5-turbo-0613'
+#    'gpt-3.5-turbo-16k-0613'
 #    'text-davinci-003'
 #    'text-davinci-002'
 #    'code-davinci-002'
--- a/main.py
+++ b/main.py
@@ -47,7 +47,7 @@ def init_db():

 def ensure_dependencies():
    import pkg.utils.pkgmgr as pkgmgr
-    pkgmgr.run_pip(["install", "openai", "Pillow", "nakuru-project-idk", "--upgrade",
+    pkgmgr.run_pip(["install", "openai", "Pillow", "nakuru-project-idk", "CallingGPT", "tiktoken", "--upgrade",
                    "-i", "https://pypi.tuna.tsinghua.edu.cn/simple",
                    "--trusted-host", "pypi.tuna.tsinghua.edu.cn"])

@@ -134,127 +134,144 @@ def start(first_time_init=False):

    known_exception_caught = False
    try:
-
-        sh = reset_logging()
-        pkg.utils.context.context['logger_handler'] = sh
-
-        # 检查是否设置了管理员
-        if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
-            # logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
-            while True:
-                try:
-                    config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
-                    # 写入到文件
-
-                    # 读取文件
-                    config_file_str = ""
-                    with open("config.py", "r", encoding="utf-8") as f:
-                        config_file_str = f.read()
-                    # 替换
-                    config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
-                    # 写入
-                    with open("config.py", "w", encoding="utf-8") as f:
-                        f.write(config_file_str)
-
-                    print("管理员QQ已设置，如需修改请修改config.py中的admin_qq字段")
-                    time.sleep(4)
-                    break
-                except ValueError:
-                    print("请输入数字")
-
-        import pkg.openai.manager
-        import pkg.database.manager
-        import pkg.openai.session
-        import pkg.qqbot.manager
-        import pkg.openai.dprompt
-        import pkg.qqbot.cmds.aamgr
-        
        try:
-            pkg.openai.dprompt.register_all()
-            pkg.qqbot.cmds.aamgr.register_all()
-            pkg.qqbot.cmds.aamgr.apply_privileges()
-        except Exception as e:
-            logging.error(e)
-            traceback.print_exc()

-        # 配置openai api_base
-        if "reverse_proxy" in config.openai_config and config.openai_config["reverse_proxy"] is not None:
+            sh = reset_logging()
+            pkg.utils.context.context['logger_handler'] = sh
+
+            # 检查是否设置了管理员
+            if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
+                # logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
+                while True:
+                    try:
+                        config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
+                        # 写入到文件
+
+                        # 读取文件
+                        config_file_str = ""
+                        with open("config.py", "r", encoding="utf-8") as f:
+                            config_file_str = f.read()
+                        # 替换
+                        config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
+                        # 写入
+                        with open("config.py", "w", encoding="utf-8") as f:
+                            f.write(config_file_str)
+
+                        print("管理员QQ已设置，如需修改请修改config.py中的admin_qq字段")
+                        time.sleep(4)
+                        break
+                    except ValueError:
+                        print("请输入数字")
+
+            import pkg.openai.manager
+            import pkg.database.manager
+            import pkg.openai.session
+            import pkg.qqbot.manager
+            import pkg.openai.dprompt
+            import pkg.qqbot.cmds.aamgr
+            
+            try:
+                pkg.openai.dprompt.register_all()
+                pkg.qqbot.cmds.aamgr.register_all()
+                pkg.qqbot.cmds.aamgr.apply_privileges()
+            except Exception as e:
+                logging.error(e)
+                traceback.print_exc()
+
+            # 配置OpenAI proxy
            import openai
-            openai.api_base = config.openai_config["reverse_proxy"]
+            openai.proxy = None  # 先重置，因为重载后可能需要清除proxy
+            if "http_proxy" in config.openai_config and config.openai_config["http_proxy"] is not None:
+                openai.proxy = config.openai_config["http_proxy"]

-        # 主启动流程
-        database = pkg.database.manager.DatabaseManager()
+            # 配置openai api_base
+            if "reverse_proxy" in config.openai_config and config.openai_config["reverse_proxy"] is not None:
+                openai.api_base = config.openai_config["reverse_proxy"]

-        database.initialize_database()
+            # 主启动流程
+            database = pkg.database.manager.DatabaseManager()

-        openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])
+            database.initialize_database()

-        # 加载所有未超时的session
-        pkg.openai.session.load_sessions()
+            openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])

-        # 初始化qq机器人
-        qqbot = pkg.qqbot.manager.QQBotManager(first_time_init=first_time_init)
+            # 加载所有未超时的session
+            pkg.openai.session.load_sessions()

-        # 加载插件
-        import pkg.plugin.host
-        pkg.plugin.host.load_plugins()
+            # 初始化qq机器人
+            qqbot = pkg.qqbot.manager.QQBotManager(first_time_init=first_time_init)

-        pkg.plugin.host.initialize_plugins()
+            # 加载插件
+            import pkg.plugin.host
+            pkg.plugin.host.load_plugins()

-        if first_time_init:  # 不是热重载之后的启动,则启动新的bot线程
+            pkg.plugin.host.initialize_plugins()

-            import mirai.exceptions
+            if first_time_init:  # 不是热重载之后的启动,则启动新的bot线程

-            def run_bot_wrapper():
-                global known_exception_caught
-                try:
-                    logging.info("使用账号: {}".format(qqbot.bot_account_id))
-                    qqbot.adapter.run_sync()
-                except TypeError as e:
-                    if str(e).__contains__("argument 'debug'"):
-                        logging.error(
-                            "连接bot失败:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/82".format(e))
-                        known_exception_caught = True
-                    elif str(e).__contains__("As of 3.10, the *loop*"):
-                        logging.error(
-                            "Websockets版本过低:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/5".format(e))
-                        known_exception_caught = True
+                import mirai.exceptions

-                except websockets.exceptions.InvalidStatus as e:
-                    logging.error(
-                        "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
-                            e))
-                    known_exception_caught = True
-                except mirai.exceptions.NetworkError as e:
-                    logging.error("连接mirai-api-http失败:{}, 请检查是否已按照文档启动mirai".format(e))
-                    known_exception_caught = True
-                except Exception as e:
-                    if str(e).__contains__("404"):
+                def run_bot_wrapper():
+                    global known_exception_caught
+                    try:
+                        logging.info("使用账号: {}".format(qqbot.bot_account_id))
+                        qqbot.adapter.run_sync()
+                    except TypeError as e:
+                        if str(e).__contains__("argument 'debug'"):
+                            logging.error(
+                                "连接bot失败:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/82".format(e))
+                            known_exception_caught = True
+                        elif str(e).__contains__("As of 3.10, the *loop*"):
+                            logging.error(
+                                "Websockets版本过低:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/5".format(e))
+                            known_exception_caught = True
+
+                    except websockets.exceptions.InvalidStatus as e:
                        logging.error(
                            "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
                                e))
                        known_exception_caught = True
-                    elif str(e).__contains__("signal only works in main thread"):
-                        logging.error(
-                            "hypercorn异常:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/86".format(
-                                e))
+                    except mirai.exceptions.NetworkError as e:
+                        logging.error("连接mirai-api-http失败:{}, 请检查是否已按照文档启动mirai".format(e))
                        known_exception_caught = True
-                    elif str(e).__contains__("did not receive a valid HTTP"):
-                        logging.error(
-                            "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
-                                e))
-                    else:
-                        import traceback
-                        traceback.print_exc()
-                        logging.error(
-                            "捕捉到未知异常:{}, 请前往 https://github.com/RockChinQ/QChatGPT/issues 查找或提issue".format(e))
-                        known_exception_caught = True
-                        raise e
-                finally:
-                    time.sleep(12)
-            threading.Thread(
-                target=run_bot_wrapper
-            ).start()
+                    except Exception as e:
+                        if str(e).__contains__("404"):
+                            logging.error(
+                                "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
+                                    e))
+                            known_exception_caught = True
+                        elif str(e).__contains__("signal only works in main thread"):
+                            logging.error(
+                                "hypercorn异常:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/86".format(
+                                    e))
+                            known_exception_caught = True
+                        elif str(e).__contains__("did not receive a valid HTTP"):
+                            logging.error(
+                                "mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
+                                    e))
+                        else:
+                            import traceback
+                            traceback.print_exc()
+                            logging.error(
+                                "捕捉到未知异常:{}, 请前往 https://github.com/RockChinQ/QChatGPT/issues 查找或提issue".format(e))
+                            known_exception_caught = True
+                            raise e
+                    finally:
+                        time.sleep(12)
+                threading.Thread(
+                    target=run_bot_wrapper
+                ).start()
+        except Exception as e:
+            traceback.print_exc()
+            if isinstance(e, KeyboardInterrupt):
+                logging.info("程序被用户中止")
+                sys.exit(0)
+            elif isinstance(e, SyntaxError):
+                logging.error("配置文件存在语法错误，请检查配置文件：\n1. 是否存在中文符号\n2. 是否已按照文件中的说明填写正确")
+                sys.exit(1)
+            else:
+                logging.error("初始化失败:{}".format(e))
+                sys.exit(1)
    finally:
        # 判断若是Windows，输出选择模式可能会暂停程序的警告
        if os.name == 'nt':
--- a/override-all.json
+++ b/override-all.json
@@ -53,6 +53,7 @@
    "inappropriate_message_tips": "[百度云]请珍惜机器人，当前返回内容不合规",
    "encourage_sponsor_at_start": true,
    "prompt_submit_length": 2048,
+    "auto_reset": true,
    "completion_api_params": {
        "model": "gpt-3.5-turbo",
        "temperature": 0.9,
--- a/pkg/openai/api/init.py
+++ b/pkg/openai/api/init.py
--- a/pkg/openai/api/chat_completion.py
+++ b/pkg/openai/api/chat_completion.py
@@ -0,0 +1,200 @@
+import openai
+import json
+import logging
+
+from .model import RequestBase
+
+from ..funcmgr import get_func_schema_list, execute_function, get_func, get_func_schema, ContentFunctionNotFoundError
+
+
+class ChatCompletionRequest(RequestBase):
+    """调用ChatCompletion接口的请求类。
+    
+    此类保证每一次返回的角色为assistant的信息的finish_reason一定为stop。
+    若有函数调用响应，本类的返回瀑布是：函数调用请求->函数调用结果->...->assistant的信息->stop。
+    """
+    model: str
+    messages: list[dict[str, str]]
+    kwargs: dict
+
+    stopped: bool = False
+
+    pending_func_call: dict = None
+
+    pending_msg: str
+
+    def flush_pending_msg(self):
+        self.append_message(
+            role="assistant",
+            content=self.pending_msg
+        )
+        self.pending_msg = ""
+
+    def append_message(self, role: str, content: str, name: str=None):
+        msg = {
+            "role": role,
+            "content": content
+        }
+
+        if name is not None:
+            msg['name'] = name
+
+        self.messages.append(msg)
+
+    def __init__(
+        self,
+        model: str,
+        messages: list[dict[str, str]],
+        **kwargs
+    ):
+        self.model = model
+        self.messages = messages.copy()
+
+        self.kwargs = kwargs
+
+        self.req_func = openai.ChatCompletion.acreate
+
+        self.pending_func_call = None
+
+        self.stopped = False
+
+        self.pending_msg = ""
+
+    def __iter__(self):
+        return self
+
+    def __next__(self) -> dict:
+        if self.stopped:
+            raise StopIteration()
+
+        if self.pending_func_call is None:  # 没有待处理的函数调用请求
+
+            args = {
+                "model": self.model,
+                "messages": self.messages,
+            }
+
+            funcs = get_func_schema_list()
+
+            if len(funcs) > 0:
+                args['functions'] = funcs
+
+            # 拼接kwargs
+            args = {**args, **self.kwargs}
+
+            resp = self._req(**args)
+
+            choice0 = resp["choices"][0]
+
+            # 如果不是函数调用，且finish_reason为stop，则停止迭代
+            if 'function_call' not in choice0['message'] and choice0["finish_reason"] == "stop":
+                self.stopped = True
+            
+            if 'function_call' in choice0['message']:
+                self.pending_func_call = choice0['message']['function_call']
+
+                # self.append_message(
+                #     role="assistant",
+                #     content="function call: "+json.dumps(self.pending_func_call, ensure_ascii=False)
+                # )
+
+                return {
+                    "id": resp["id"],
+                    "choices": [
+                        {
+                            "index": choice0["index"],
+                            "message": {
+                                "role": "assistant",
+                                "type": "function_call",
+                                "content": None,
+                                "function_call": choice0['message']['function_call']
+                            },
+                            "finish_reason": "function_call"
+                        }
+                    ],
+                    "usage": resp["usage"]
+                }
+            else:
+
+                # self.pending_msg += choice0['message']['content']
+                # 普通回复一定处于最后方，故不用再追加进内部messages
+
+                return {
+                    "id": resp["id"],
+                    "choices": [
+                        {
+                            "index": choice0["index"],
+                            "message": {
+                                "role": "assistant",
+                                "type": "text",
+                                "content": choice0['message']['content']
+                            },
+                            "finish_reason": "stop"
+                        }
+                    ],
+                    "usage": resp["usage"]
+                }
+        else:  # 处理函数调用请求
+
+            cp_pending_func_call = self.pending_func_call.copy()
+            
+            self.pending_func_call = None
+
+            func_name = cp_pending_func_call['name']
+            arguments = {}
+
+            try:
+
+                try:
+                    arguments = json.loads(cp_pending_func_call['arguments'])
+                # 若不是json格式的异常处理
+                except json.decoder.JSONDecodeError:
+                    # 获取函数的参数列表
+                    func_schema = get_func_schema(func_name)
+
+                    arguments = {
+                        func_schema['parameters']['required'][0]: cp_pending_func_call['arguments']
+                    }
+                
+                logging.info("执行函数调用: name={}, arguments={}".format(func_name, arguments))
+
+                # 执行函数调用
+                ret = ""
+                try:
+                    ret = execute_function(func_name, arguments)
+
+                    logging.info("函数执行完成。")
+                except Exception as e:
+                    ret = "error: execute function failed: {}".format(str(e))
+                    logging.error("函数执行失败: {}".format(str(e)))
+
+                self.append_message(
+                    role="function",
+                    content=json.dumps(ret, ensure_ascii=False),
+                    name=func_name
+                )
+
+                return {
+                    "id": -1,
+                    "choices": [
+                        {
+                            "index": -1,
+                            "message": {
+                                "role": "function",
+                                "type": "function_return",
+                                "function_name": func_name,
+                                "content": json.dumps(ret, ensure_ascii=False)
+                            },
+                            "finish_reason": "function_return"
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 0,
+                        "completion_tokens": 0,
+                        "total_tokens": 0
+                    }
+                }
+
+            except ContentFunctionNotFoundError:
+                raise Exception("没有找到函数: {}".format(func_name))
+
--- a/pkg/openai/api/completion.py
+++ b/pkg/openai/api/completion.py
@@ -0,0 +1,111 @@
+import openai
+
+from .model import RequestBase
+
+
+class CompletionRequest(RequestBase):
+    """调用Completion接口的请求类。
+    
+    调用方可以一直next completion直到finish_reason为stop。
+    """
+
+    model: str
+    prompt: str
+    kwargs: dict
+
+    stopped: bool = False
+
+    def __init__(
+        self,
+        model: str,
+        messages: list[dict[str, str]],
+        **kwargs
+    ):
+        self.model = model
+        self.prompt = ""
+        
+        for message in messages:
+            self.prompt += message["role"] + ": " + message["content"] + "\n"
+        
+        self.prompt += "assistant: "
+
+        self.kwargs = kwargs
+
+        self.req_func = openai.Completion.acreate
+
+    def __iter__(self):
+        return self
+
+    def __next__(self) -> dict:
+        """调用Completion接口，返回生成的文本
+        
+        {
+            "id": "id",
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "type": "text",
+                        "content": "message"
+                    },
+                    "finish_reason": "reason"
+                }
+            ],
+            "usage": {
+                "prompt_tokens": 10,
+                "completion_tokens": 20,
+                "total_tokens": 30
+            }
+        }
+        """
+
+        if self.stopped:
+            raise StopIteration()
+
+        resp = self._req(
+            model=self.model,
+            prompt=self.prompt,
+            **self.kwargs
+        )
+
+        if resp["choices"][0]["finish_reason"] == "stop":
+            self.stopped = True
+
+        choice0 = resp["choices"][0]
+
+        self.prompt += choice0["text"]
+
+        return {
+            "id": resp["id"],
+            "choices": [
+                {
+                    "index": choice0["index"],
+                    "message": {
+                        "role": "assistant",
+                        "type": "text",
+                        "content": choice0["text"]
+                    },
+                    "finish_reason": choice0["finish_reason"]
+                }
+            ],
+            "usage": resp["usage"]
+        }
+        
+if __name__ == "__main__":
+    import os
+
+    openai.api_key = os.environ["OPENAI_API_KEY"]
+
+    for resp in CompletionRequest(
+        model="text-davinci-003",
+        messages=[
+            {
+                "role": "user",
+                "content": "Hello, who are you?"
+            }
+        ]
+    ):
+        print(resp)
+        if resp["choices"][0]["finish_reason"] == "stop":
+            break
--- a/pkg/openai/api/model.py
+++ b/pkg/openai/api/model.py
@@ -0,0 +1,51 @@
+# 定义不同接口请求的模型
+import threading
+import asyncio
+import logging
+
+import openai
+
+
+class RequestBase:
+
+    req_func: callable
+
+    def __init__(self, *args, **kwargs):
+        raise NotImplementedError
+
+    def _req(self, **kwargs):
+        """处理代理问题"""
+
+        ret: dict = {}
+        exception: Exception = None
+
+        async def awrapper(**kwargs):
+            nonlocal ret, exception
+
+            try:
+                ret = await self.req_func(**kwargs)
+                logging.debug("接口请求返回：%s", str(ret))
+                return ret
+            except Exception as e:
+                exception = e
+            
+        loop = asyncio.new_event_loop()
+
+        thr = threading.Thread(
+            target=loop.run_until_complete,
+            args=(awrapper(**kwargs),)
+        )
+
+        thr.start()
+        thr.join()
+
+        if exception is not None:
+            raise exception
+
+        return ret
+
+    def __iter__(self):
+        raise self
+
+    def __next__(self):
+        raise NotImplementedError
--- a/pkg/openai/funcmgr.py
+++ b/pkg/openai/funcmgr.py
@@ -0,0 +1,47 @@
+# 封装了function calling的一些支持函数
+import logging
+
+
+from pkg.plugin import host
+
+
+class ContentFunctionNotFoundError(Exception):
+    pass
+
+
+def get_func_schema_list() -> list:
+    """从plugin包中的函数结构中获取并处理成受GPT支持的格式"""
+    if not host.__enable_content_functions__:
+        return []
+
+    schemas = []
+
+    for func in host.__callable_functions__:
+        if func['enabled']:
+            fun_cp = func.copy()
+
+            del fun_cp['enabled']
+
+            schemas.append(fun_cp)
+
+    return schemas
+
+def get_func(name: str) -> callable:
+    if name not in host.__function_inst_map__:
+        raise ContentFunctionNotFoundError("没有找到内容函数: {}".format(name))
+
+    return host.__function_inst_map__[name]
+
+def get_func_schema(name: str) -> dict:
+    for func in host.__callable_functions__:
+        if func['name'] == name:
+            return func
+    raise ContentFunctionNotFoundError("没有找到内容函数: {}".format(name))
+
+def execute_function(name: str, kwargs: dict) -> any:
+    """执行函数调用"""
+
+    logging.debug("executing function: name='{}', kwargs={}".format(name, kwargs))
+
+    func = get_func(name)
+    return func(**kwargs)
--- a/pkg/openai/manager.py
+++ b/pkg/openai/manager.py
@@ -5,7 +5,9 @@ import openai
 import pkg.openai.keymgr
 import pkg.utils.context
 import pkg.audit.gatherer
-from pkg.openai.modelmgr import ModelRequest, create_openai_model_request
+from pkg.openai.modelmgr import select_request_cls
+
+from pkg.openai.api.model import RequestBase


 class OpenAIInteract:
@@ -33,45 +35,31 @@ class OpenAIInteract:

        pkg.utils.context.set_openai_manager(self)

-    # 请求OpenAI Completion
-    def request_completion(self, prompts) -> tuple[str, int]:
-        """请求补全接口回复
-
-        Parameters:
-            prompts (str): 提示语
-
-        Returns:
-            str: 回复
+    def request_completion(self, messages: list):
+        """请求补全接口回复=
        """
-
+        # 选择接口请求类
        config = pkg.utils.context.get_config()

-        # 根据模型选择使用的接口
-        ai: ModelRequest = create_openai_model_request(
-            config.completion_api_params['model'],
-            'user',
-            config.openai_config["http_proxy"] if "http_proxy" in config.openai_config else None
-        )
-        ai.request(
-            prompts,
-            **config.completion_api_params
-        )
-        response = ai.get_response()
+        request: RequestBase

-        logging.debug("OpenAI response: %s", response)
+        model: str = config.completion_api_params['model']

-        # 记录使用量
-        current_round_token = 0
-        if 'model' in config.completion_api_params:
-            self.audit_mgr.report_text_model_usage(config.completion_api_params['model'],
-                                                   ai.get_total_tokens())
-            current_round_token = ai.get_total_tokens()
-        elif 'engine' in config.completion_api_params:
-            self.audit_mgr.report_text_model_usage(config.completion_api_params['engine'],
-                                                   response['usage']['total_tokens'])
-            current_round_token = response['usage']['total_tokens']
+        cp_parmas = config.completion_api_params.copy()
+        del cp_parmas['model']

-        return ai.get_message(), current_round_token
+        request = select_request_cls(model, messages, cp_parmas)
+
+        # 请求接口
+        for resp in request:
+
+            if resp['usage']['total_tokens'] > 0:
+                self.audit_mgr.report_text_model_usage(
+                    model,
+                    resp['usage']['total_tokens']
+                )
+
+            yield resp

    def request_image(self, prompt) -> dict:
        """请求图片接口回复
--- a/pkg/openai/modelmgr.py
+++ b/pkg/openai/modelmgr.py
@@ -7,6 +7,11 @@ Completion - text-davinci-003 等模型
 """
 import openai, logging, threading, asyncio
 import openai.error as aiE
+import tiktoken
+
+from pkg.openai.api.model import RequestBase
+from pkg.openai.api.completion import CompletionRequest
+from pkg.openai.api.chat_completion import ChatCompletionRequest

 COMPLETION_MODELS = {
    'text-davinci-003',
@@ -20,11 +25,14 @@ COMPLETION_MODELS = {

 CHAT_COMPLETION_MODELS = {
    'gpt-3.5-turbo',
-    'gpt-3.5-turbo-0301',
+    'gpt-3.5-turbo-16k',
+    'gpt-3.5-turbo-0613',
+    'gpt-3.5-turbo-16k-0613',
+    # 'gpt-3.5-turbo-0301',
    'gpt-4',
-    'gpt-4-0314',
+    'gpt-4-0613',
    'gpt-4-32k',
-    'gpt-4-32k-0314'
+    'gpt-4-32k-0613'
 }

 EDIT_MODELS = {
@@ -36,153 +44,76 @@ IMAGE_MODELS = {
 }


-class ModelRequest:
-    """模型接口请求父类"""
-
-    can_chat = False
-    runtime: threading.Thread = None
-    ret = {}
-    proxy: str = None
-    request_ready = True
-    error_info: str = "若在没有任何错误的情况下看到这句话，请带着配置文件上报Issues"
-
-    def __init__(self, model_name, user_name, request_fun, http_proxy:str = None, time_out = None):
-        self.model_name = model_name
-        self.user_name = user_name
-        self.request_fun = request_fun
-        self.time_out = time_out
-        if http_proxy != None:
-            self.proxy = http_proxy
-            openai.proxy = self.proxy
-            self.request_ready = False
-
-    async def __a_request__(self, **kwargs):
-        """异步请求"""
-
-        try:
-            self.ret: dict = await self.request_fun(**kwargs)
-            self.request_ready = True
-        except aiE.APIConnectionError as e:
-            self.error_info = "{}\n请检查网络连接或代理是否正常".format(e)
-            raise ConnectionError(self.error_info)
-        except ValueError as e:
-            self.error_info = "{}\n该错误可能是由于http_proxy格式设置错误引起的"
-        except Exception as e:
-            self.error_info = "{}\n由于请求异常产生的未知错误，请查看日志".format(e)
-            raise type(e)(self.error_info)
-
-    def request(self, **kwargs):
-        """向接口发起请求"""
-
-        if self.proxy != None: #异步请求
-            self.request_ready = False
-            loop = asyncio.new_event_loop()
-            self.runtime = threading.Thread(
-                target=loop.run_until_complete,
-                args=(self.__a_request__(**kwargs),)
-            )
-            self.runtime.start()
-        else: #同步请求
-            self.ret = self.request_fun(**kwargs)
-
-    def __msg_handle__(self, msg):
-        """将prompt dict转换成接口需要的格式"""
-        return msg
-    
-    def ret_handle(self):
-        '''
-        API消息返回处理函数
-        若重写该方法，应检查异步线程状态，或在需要检查处super该方法
-        '''
-        if self.runtime != None and isinstance(self.runtime, threading.Thread):
-            self.runtime.join(self.time_out)
-        if self.request_ready:
-            return
-        raise Exception(self.error_info)
-
-    def get_total_tokens(self):
-        try:
-            return self.ret['usage']['total_tokens']
-        except:
-            return 0
-
-    def get_message(self):
-        return self.message
-
-    def get_response(self):
-        return self.ret
-
-
-class ChatCompletionModel(ModelRequest):
-    """ChatCompletion接口的请求实现"""
-
-    Chat_role = ['system', 'user', 'assistant']
-    def __init__(self, model_name, user_name, http_proxy:str = None, **kwargs):
-        if http_proxy == None:
-            request_fun = openai.ChatCompletion.create
-        else:
-            request_fun = openai.ChatCompletion.acreate
-        self.can_chat = True
-        super().__init__(model_name, user_name, request_fun, http_proxy, **kwargs)
-
-    def request(self, prompts, **kwargs):
-        prompts = self.__msg_handle__(prompts)
-        kwargs['messages'] = prompts
-        super().request(**kwargs)
-        self.ret_handle()
-
-    def __msg_handle__(self, msgs):
-        temp_msgs = []
-        # 把msgs拷贝进temp_msgs
-        for msg in msgs:
-            temp_msgs.append(msg.copy())
-        return temp_msgs
-
-    def get_message(self):
-        return self.ret["choices"][0]["message"]['content'] #需要时直接加载加快请求速度，降低内存消耗
-
-
-class CompletionModel(ModelRequest):
-    """Completion接口的请求实现"""
-
-    def __init__(self, model_name, user_name, http_proxy:str = None, **kwargs):
-        if http_proxy == None:
-            request_fun = openai.Completion.create
-        else:
-            request_fun = openai.Completion.acreate
-        super().__init__(model_name, user_name, request_fun, http_proxy, **kwargs)
-
-    def request(self, prompts, **kwargs):
-        prompts = self.__msg_handle__(prompts)
-        kwargs['prompt'] = prompts
-        super().request(**kwargs)
-        self.ret_handle()
-
-    def __msg_handle__(self, msgs):
-        prompt = ''
-        for msg in msgs:
-            prompt = prompt + "{}: {}\n".format(msg['role'], msg['content'])
-        # for msg in msgs:
-        #     if msg['role'] == 'assistant':
-        #         prompt = prompt + "{}\n".format(msg['content'])
-        #     else:
-        #         prompt = prompt + "{}:{}\n".format(msg['role'] , msg['content'])
-        prompt = prompt + "assistant: "
-        return prompt
-
-    def get_message(self):
-        return self.ret["choices"][0]["text"]
-
-
-def create_openai_model_request(model_name: str, user_name: str = 'user', http_proxy:str = None) -> ModelRequest:
-    """使用给定的模型名称创建模型请求对象"""
+def select_request_cls(model_name: str, messages: list, args: dict) -> RequestBase:
    if model_name in CHAT_COMPLETION_MODELS:
-        model = ChatCompletionModel(model_name, user_name, http_proxy)
+        return ChatCompletionRequest(model_name, messages, **args)
    elif model_name in COMPLETION_MODELS:
-        model = CompletionModel(model_name, user_name, http_proxy)
-    else :
-        log = "找不到模型[{}]，请检查配置文件".format(model_name)
-        logging.error(log)
-        raise IndexError(log)
-    logging.debug("使用接口[{}]创建模型请求[{}]".format(model.__class__.__name__, model_name))
-    return model
+        return CompletionRequest(model_name, messages, **args)
+    raise ValueError("不支持模型[{}]，请检查配置文件".format(model_name))
+
+
+def count_chat_completion_tokens(messages: list, model: str) -> int:
+    """Return the number of tokens used by a list of messages."""
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+    if model in {
+        "gpt-3.5-turbo-0613",
+        "gpt-3.5-turbo-16k-0613",
+        "gpt-4-0314",
+        "gpt-4-32k-0314",
+        "gpt-4-0613",
+        "gpt-4-32k-0613",
+        }:
+        tokens_per_message = 3
+        tokens_per_name = 1
+    elif model == "gpt-3.5-turbo-0301":
+        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 "gpt-3.5-turbo" in model:
+        # print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
+        return count_chat_completion_tokens(messages, model="gpt-3.5-turbo-0613")
+    elif "gpt-4" in model:
+        # print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
+        return count_chat_completion_tokens(messages, model="gpt-4-0613")
+    else:
+        raise NotImplementedError(
+            f"""count_chat_completion_tokens() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
+        )
+    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 count_completion_tokens(messages: list, model: str) -> int:
+
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+
+    text = ""
+
+    for message in messages:
+        text += message['role'] + message['content'] + "\n"
+
+    text += "assistant: "
+
+    return len(encoding.encode(text))
+
+
+def count_tokens(messages: list, model: str):
+    if model in CHAT_COMPLETION_MODELS:
+        return count_chat_completion_tokens(messages, model)
+    elif model in COMPLETION_MODELS:
+        return count_completion_tokens(messages, model)
+    raise ValueError("不支持模型[{}]，请检查配置文件".format(model))
--- a/pkg/openai/pricing.bak.py
+++ b/pkg/openai/pricing.bak.py
@@ -1,28 +0,0 @@
-# 计费模块
-# 已弃用 https://github.com/RockChinQ/QChatGPT/issues/81
-
-import logging
-
-pricing = {
-    "base": {  # 文字模型单位是1000字符
-        "text-davinci-003": 0.02,
-    },
-    "image": {
-        "256x256": 0.016,
-        "512x512": 0.018,
-        "1024x1024": 0.02,
-    }
-}
-
-
-def language_base_price(model, text):
-    salt_rate = 0.93
-    length = ((len(text.encode('utf-8')) - len(text)) / 2 + len(text)) * salt_rate
-    logging.debug("text length: %d" % length)
-
-    return pricing["base"][model] * length / 1000
-
-
-def image_price(size):
-    logging.debug("image size: %s" % size)
-    return pricing["image"][size]
--- a/pkg/openai/session.py
+++ b/pkg/openai/session.py
@@ -16,6 +16,8 @@ import pkg.utils.context
 import pkg.plugin.host as plugin_host
 import pkg.plugin.models as plugin_models

+from pkg.openai.modelmgr import count_tokens
+
 # 运行时保存的所有session
 sessions = {}

@@ -83,7 +85,7 @@ def load_sessions():


 # 获取指定名称的session，如果不存在则创建一个新的
-def get_session(session_name: str):
+def get_session(session_name: str) -> 'Session':
    global sessions
    if session_name not in sessions:
        sessions[session_name] = Session(session_name)
@@ -107,9 +109,6 @@ class Session:
    prompt = []
    """使用list来保存会话中的回合"""

-    token_counts = []
-    """每个回合的token数量"""
-
    default_prompt = []
    """本session的默认prompt"""

@@ -195,7 +194,7 @@ class Session:

    # 请求回复
    # 这个函数是阻塞的
-    def append(self, text: str) -> str:
+    def append(self, text: str=None) -> str:
        """向session中添加一条消息，返回接口回复"""

        self.last_interact_timestamp = int(time.time())
@@ -215,29 +214,92 @@ class Session:
        config = pkg.utils.context.get_config()
        max_length = config.prompt_submit_length

-        prompts, counts = self.cut_out(text, max_length)
+        local_default_prompt = self.default_prompt.copy()
+        local_prompt = self.prompt.copy()
+
+        # 触发PromptPreProcessing事件
+        args = {
+            'session_name': self.name,
+            'default_prompt': self.default_prompt,
+            'prompt': self.prompt,
+            'text_message': text,
+        }
+
+        event = pkg.plugin.host.emit(plugin_models.PromptPreProcessing, **args)
+        
+        if event.get_return_value('default_prompt') is not None:
+            local_default_prompt = event.get_return_value('default_prompt')
+        
+        if event.get_return_value('prompt') is not None:
+            local_prompt = event.get_return_value('prompt')
+
+        if event.get_return_value('text_message') is not None:
+            text = event.get_return_value('text_message')
+
+        prompts, _ = self.cut_out(text, max_length, local_default_prompt, local_prompt)
+
+        res_text = ""
+
+        pending_msgs = []
+
+        total_tokens = 0
+
+        for resp in pkg.utils.context.get_openai_manager().request_completion(prompts):
+            if resp['choices'][0]['message']['type'] == 'text':  # 普通回复
+                res_text += resp['choices'][0]['message']['content']
+
+                total_tokens += resp['usage']['total_tokens']
+
+                pending_msgs.append(
+                    {
+                        "role": "assistant",
+                        "content": resp['choices'][0]['message']['content']
+                    }
+                )
+
+            elif resp['choices'][0]['message']['type'] == 'function_call':
+                # self.prompt.append(
+                #     {
+                #         "role": "assistant",
+                #         "content": "function call: "+json.dumps(resp['choices'][0]['message']['function_call'])
+                #     }
+                # )
+
+                total_tokens += resp['usage']['total_tokens']
+            elif resp['choices'][0]['message']['type'] == 'function_return':
+                # self.prompt.append(
+                #     {
+                #         "role": "function",
+                #         "name": resp['choices'][0]['message']['function_name'],
+                #         "content": json.dumps(resp['choices'][0]['message']['content'])
+                #     }
+                # )
+
+                # total_tokens += resp['usage']['total_tokens']
+                pass
+

-        # 计算请求前的prompt数量
-        total_token_before_query = 0
-        for token_count in counts:
-            total_token_before_query += token_count

        # 向API请求补全
-        message, total_token = pkg.utils.context.get_openai_manager().request_completion(
-            prompts,
-        )
+        # message, total_token = pkg.utils.context.get_openai_manager().request_completion(
+        #     prompts,
+        # )

        # 成功获取，处理回复
-        res_test = message
-        res_ans = res_test.strip()
+        # res_test = message
+        res_ans = res_text.strip()

        # 将此次对话的双方内容加入到prompt中
-        self.prompt.append({'role': 'user', 'content': text})
-        self.prompt.append({'role': 'assistant', 'content': res_ans})
+        # self.prompt.append({'role': 'user', 'content': text})
+        # self.prompt.append({'role': 'assistant', 'content': res_ans})
+        if text:
+            self.prompt.append({'role': 'user', 'content': text})
+        # 添加pending_msgs
+        self.prompt += pending_msgs

        # 向token_counts中添加本回合的token数量
-        self.token_counts.append(total_token-total_token_before_query)
-        logging.debug("本回合使用token: {}, session counts: {}".format(total_token-total_token_before_query, self.token_counts))
+        # self.token_counts.append(total_tokens-total_token_before_query)
+        # logging.debug("本回合使用token: {}, session counts: {}".format(total_tokens-total_token_before_query, self.token_counts))

        if self.just_switched_to_exist_session:
            self.just_switched_to_exist_session = False
@@ -261,7 +323,7 @@ class Session:
        return question

    # 构建对话体
-    def cut_out(self, msg: str, max_tokens: int) -> tuple[list, list]:
+    def cut_out(self, msg: str, max_tokens: int, default_prompt: list, prompt: list) -> tuple[list, list]:
        """将现有prompt进行切割处理，使得新的prompt长度不超过max_tokens

        :return: (新的prompt, 新的token_counts)
@@ -274,42 +336,35 @@ class Session:

        # 包装目前的对话回合内容
        changable_prompts = []
-        changable_counts = []
-        # 倒着来, 遍历prompt的步长为2, 遍历tokens_counts的步长为1
-        changable_index = len(self.prompt) - 1
-        token_count_index = len(self.token_counts) - 1

-        packed_tokens = 0
+        use_model = pkg.utils.context.get_config().completion_api_params['model']

-        while changable_index >= 0 and token_count_index >= 0:
-            if packed_tokens + self.token_counts[token_count_index] > max_tokens:
+        ptr = len(prompt) - 1
+
+        # 直接从后向前扫描拼接，不管是否是整回合
+        while ptr >= 0:
+            if count_tokens(prompt[ptr:ptr+1]+changable_prompts, use_model) > max_tokens:
                break

-            changable_prompts.insert(0, self.prompt[changable_index])
-            changable_prompts.insert(0, self.prompt[changable_index - 1])
-            changable_counts.insert(0, self.token_counts[token_count_index])
-            packed_tokens += self.token_counts[token_count_index]
+            changable_prompts.insert(0, prompt[ptr])

-            changable_index -= 2
-            token_count_index -= 1
+            ptr -= 1

        # 将default_prompt和changable_prompts合并
-        result_prompt = self.default_prompt + changable_prompts
+        result_prompt = default_prompt + changable_prompts

        # 添加当前问题
-        result_prompt.append(
-            {
-                'role': 'user',
-                'content': msg
-            }
-        )
+        if msg:
+            result_prompt.append(
+                {
+                    'role': 'user',
+                    'content': msg
+                }
+            )

-        logging.debug('cut_out: {}\nchangable section tokens: {}\npacked counts: {}\nsession counts: {}'.format(json.dumps(result_prompt, ensure_ascii=False, indent=4),
-                                                                             packed_tokens,
-                                                                             changable_counts,
-                                                                             self.token_counts))
+        logging.debug("cut_out: {}".format(json.dumps(result_prompt, ensure_ascii=False, indent=4)))

-        return result_prompt, changable_counts
+        return result_prompt, count_tokens(changable_prompts, use_model)

    # 持久化session
    def persistence(self):
@@ -327,7 +382,7 @@ class Session:
                                    json.dumps(self.prompt), json.dumps(self.default_prompt), json.dumps(self.token_counts))

    # 重置session
-    def reset(self, explicit: bool = False, expired: bool = False, schedule_new: bool = True, use_prompt: str = None):
+    def reset(self, explicit: bool = False, expired: bool = False, schedule_new: bool = True, use_prompt: str = None, persist: bool = False):
        if self.prompt:
            self.persistence()
            if explicit:
@@ -345,7 +400,8 @@ class Session:
            if expired:
                pkg.utils.context.get_database_manager().set_session_expired(self.name, self.create_timestamp)

-        self.default_prompt = self.get_default_prompt(use_prompt)
+        if not persist:  # 不要求保持default prompt
+            self.default_prompt = self.get_default_prompt(use_prompt)
        self.prompt = []
        self.token_counts = []
        self.create_timestamp = int(time.time())
--- a/pkg/plugin/host.py
+++ b/pkg/plugin/host.py
@@ -16,6 +16,8 @@ import pkg.qqbot.adapter as msadapter

 from mirai import Mirai

+from CallingGPT.session.session import Session
+
 __plugins__ = {}
 """插件列表

@@ -42,6 +44,15 @@ __plugins__ = {}
 __plugins_order__ = []
 """插件顺序"""

+__enable_content_functions__ = True
+"""是否启用内容函数"""
+
+__callable_functions__ = []
+"""供GPT调用的函数结构"""
+
+__function_inst_map__: dict[str, callable] = {}
+"""函数名:实例 映射"""
+

 def generate_plugin_order():
    """根据__plugin__生成插件初始顺序，无视是否启用"""
@@ -102,6 +113,10 @@ def load_plugins():
    # 加载插件顺序
    settings.load_settings()

+    # 输出已注册的内容函数列表
+    logging.debug("registered content functions: {}".format(__callable_functions__))
+    logging.debug("function instance map: {}".format(__function_inst_map__))
+

 def initialize_plugins():
    """初始化插件"""
@@ -251,7 +266,7 @@ class EventContext:
            self.__return_value__[key] = []
        self.__return_value__[key].append(ret)

-    def get_return(self, key: str):
+    def get_return(self, key: str) -> list:
        """获取key的所有返回值"""
        if key in self.__return_value__:
            return self.__return_value__[key]
@@ -300,7 +315,9 @@ class PluginHost:
    """插件宿主"""

    def __init__(self):
+        """初始化插件宿主"""
        context.set_plugin_host(self)
+        self.calling_gpt_session = Session([])

    def get_runtime_context(self) -> context:
        """获取运行时上下文（pkg.utils.context模块的对象）
--- a/pkg/plugin/models.py
+++ b/pkg/plugin/models.py
@@ -132,18 +132,64 @@ KeySwitched = "key_switched"
        key_list: list[str] api-key列表
 """

+PromptPreProcessing = "prompt_pre_processing"
+"""每回合调用接口前对prompt进行预处理时触发，此事件不支持阻止默认行为
+    kwargs:
+        session_name: str 会话名称(<launcher_type>_<launcher_id>)
+        default_prompt: list 此session使用的情景预设内容
+        prompt: list 此session现有的prompt内容
+        text_message: str 用户发送的消息文本
+    
+    returns (optional):
+        default_prompt: list 修改后的情景预设内容
+        prompt: list 修改后的prompt内容
+        text_message: str 修改后的消息文本
+"""

-def on(event: str):
+
+def on(*args, **kwargs):
    """注册事件监听器
-    :param
-        event: str 事件名称
    """
-    return Plugin.on(event)
+    return Plugin.on(*args, **kwargs)
+
+def func(*args, **kwargs):
+    """注册内容函数，声明此函数为一个内容函数，在对话中将发送此函数给GPT以供其调用
+    此函数可以具有任意的参数，但必须按照[此文档](https://github.com/RockChinQ/CallingGPT/wiki/1.-Function-Format#function-format)
+    所述的格式编写函数的docstring。
+    此功能仅支持在使用gpt-3.5或gpt-4系列模型时使用。
+    """
+    return Plugin.func(*args, **kwargs)


 __current_registering_plugin__ = ""


+def require_ver(ge: str, le: str="v999.9.9") -> bool:
+    """插件版本要求装饰器
+
+    Args:
+        ge (str): 最低版本要求
+        le (str, optional): 最高版本要求
+
+    Returns:
+        bool: 是否满足要求, False时为无法获取版本号，True时为满足要求，报错为不满足要求
+    """
+    qchatgpt_version = ""
+    
+    from pkg.utils.updater import get_current_tag, compare_version_str
+
+    try:
+        qchatgpt_version = get_current_tag()  # 从updater模块获取版本号
+    except:
+        return False
+
+    if compare_version_str(qchatgpt_version, ge) < 0 or \
+        (compare_version_str(qchatgpt_version, le) > 0):
+        raise Exception("QChatGPT 版本不满足要求，某些功能（可能是由插件提供的）无法正常使用。（要求版本：{}-{}，但当前版本：{}）".format(ge, le, qchatgpt_version))
+
+    return True
+
+
 class Plugin:
    """插件基类"""

@@ -176,6 +222,34 @@ class Plugin:

        return wrapper

+    @classmethod
+    def func(cls, name: str=None):
+        """内容函数装饰器
+        """
+        global __current_registering_plugin__
+        from CallingGPT.entities.namespace import get_func_schema
+
+        def wrapper(func):
+
+            function_schema = get_func_schema(func)
+            function_schema['name'] = __current_registering_plugin__ + '-' + (func.__name__ if name is None else name)
+
+            function_schema['enabled'] = True
+
+            host.__function_inst_map__[function_schema['name']] = function_schema['function']
+
+            del function_schema['function']
+
+            # logging.debug("registering content function: p='{}', f='{}', s={}".format(__current_registering_plugin__, func, function_schema))
+
+            host.__callable_functions__.append(
+                function_schema
+            )
+
+            return func
+
+        return wrapper
+

 def register(name: str, description: str, version: str, author: str):
    """注册插件, 此函数作为装饰器使用
--- a/pkg/plugin/settings.py
+++ b/pkg/plugin/settings.py
@@ -8,7 +8,10 @@ import logging
 def wrapper_dict_from_runtime_context() -> dict:
    """从变量中包装settings.json的数据字典"""
    settings = {
-        "order": []
+        "order": [],
+        "functions": {
+            "enabled": host.__enable_content_functions__
+        }
    }

    for plugin_name in host.__plugins_order__:
@@ -22,6 +25,11 @@ def apply_settings(settings: dict):
    if "order" in settings:
        host.__plugins_order__ = settings["order"]

+    if "functions" in settings:
+        if "enabled" in settings["functions"]:
+            host.__enable_content_functions__ = settings["functions"]["enabled"]
+            # logging.debug("set content function enabled: {}".format(host.__enable_content_functions__))
+

 def dump_settings():
    """保存settings.json数据"""
@@ -78,6 +86,17 @@ def load_settings():
            settings["order"].append(plugin_name)
            settings_modified = True

+    if "functions" not in settings:
+        settings["functions"] = {
+            "enabled": host.__enable_content_functions__
+        }
+        settings_modified = True
+    elif "enabled" not in settings["functions"]:
+        settings["functions"]["enabled"] = host.__enable_content_functions__
+        settings_modified = True
+
+    logging.info("已全局{}内容函数。".format("启用" if settings["functions"]["enabled"] else "禁用"))
+
    apply_settings(settings)

    if settings_modified:
--- a/pkg/plugin/switch.py
+++ b/pkg/plugin/switch.py
@@ -28,6 +28,11 @@ def apply_switch(switch: dict):
    for plugin_name in switch:
        host.__plugins__[plugin_name]["enabled"] = switch[plugin_name]["enabled"]

+        # 查找此插件的所有内容函数
+        for func in host.__callable_functions__:
+            if func['name'].startswith(plugin_name + '-'):
+                func['enabled'] = switch[plugin_name]["enabled"]
+

 def dump_switch():
    """保存开关数据"""
--- a/pkg/qqbot/cmds/funcs/func.py
+++ b/pkg/qqbot/cmds/funcs/func.py
@@ -0,0 +1,28 @@
+from ..aamgr import AbstractCommandNode, Context
+import logging
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="func",
+    description="管理内容函数",
+    usage="!func",
+    aliases=[],
+    privilege=1
+)
+class FuncCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        from pkg.plugin.models import host
+
+        reply = []
+
+        reply_str = "当前已加载的内容函数：\n\n"
+
+        index = 1
+        for func in host.__callable_functions__:
+            reply_str += "{}. {}{}:\n{}\n\n".format(index, ("(已禁用) " if not func['enabled'] else ""), func['name'], func['description'])
+
+        reply = [reply_str]
+
+        return True, reply
--- a/pkg/qqbot/cmds/plugin/plugin.py
+++ b/pkg/qqbot/cmds/plugin/plugin.py
@@ -12,7 +12,7 @@ import pkg.utils.updater as updater
    description="插件管理",
    usage="!plugin\n!plugin get <插件仓库地址>\n!plugin update\n!plugin del <插件名>\n!plugin on <插件名>\n!plugin off <插件名>",
    aliases=[],
-    privilege=2
+    privilege=1
 )
 class PluginCommand(AbstractCommandNode):
    @classmethod
@@ -188,6 +188,11 @@ class PluginOnOffCommand(AbstractCommandNode):
            plugin_name = ctx.crt_params[0]
            if plugin_name in plugin_list:
                plugin_list[plugin_name]['enabled'] = new_status
+
+                for func in plugin_host.__callable_functions__:
+                    if func['name'].startswith(plugin_name+"-"):
+                        func['enabled'] = new_status
+
                plugin_switch.dump_switch()
                reply = ["[bot]已{}插件: {}".format("启用" if new_status else "禁用", plugin_name)]
            else:
--- a/pkg/qqbot/cmds/session/continue.py
+++ b/pkg/qqbot/cmds/session/continue.py
@@ -0,0 +1,27 @@
+from ..aamgr import AbstractCommandNode, Context
+
+
+@AbstractCommandNode.register(
+    parent=None,
+    name="continue",
+    description="继续未完成的响应",
+    usage="!continue",
+    aliases=[],
+    privilege=1
+)
+class ContinueCommand(AbstractCommandNode):
+    @classmethod
+    def process(cls, ctx: Context) -> tuple[bool, list]:
+        import pkg.openai.session
+        import config
+        session_name = ctx.session_name
+
+        reply = []
+
+        session = pkg.openai.session.get_session(session_name)
+
+        text = session.append()
+
+        reply = [text]
+
+        return True, reply
--- a/pkg/qqbot/cmds/system/cconfig.py
+++ b/pkg/qqbot/cmds/system/cconfig.py
@@ -8,7 +8,7 @@ def config_operation(cmd, params):
    config = pkg.utils.context.get_config()
    reply_str = ""
    if len(params) == 0:
-        reply = ["[bot]err:请输入配置项"]
+        reply = ["[bot]err:请输入!cmd cfg查看使用方法"]
    else:
        cfg_name = params[0]
        if cfg_name == 'all':
@@ -26,45 +26,61 @@ def config_operation(cmd, params):
                    else:
                        reply_str += "{}: {}\n".format(cfg, getattr(config, cfg))
            reply = [reply_str]
-        elif cfg_name in dir(config):
-            if len(params) == 1:
-                # 按照配置项类型进行格式化
-                if isinstance(getattr(config, cfg_name), str):
-                    reply_str = "[bot]配置项{}: \"{}\"\n".format(cfg_name, getattr(config, cfg_name))
-                elif isinstance(getattr(config, cfg_name), dict):
-                    reply_str = "[bot]配置项{}: {}\n".format(cfg_name,
-                                                             json.dumps(getattr(config, cfg_name),
-                                                                        ensure_ascii=False, indent=4))
-                else:
-                    reply_str = "[bot]配置项{}: {}\n".format(cfg_name, getattr(config, cfg_name))
-                reply = [reply_str]
-            else:
-                cfg_value = " ".join(params[1:])
-                # 类型转换，如果是json则转换为字典
-                if cfg_value == 'true':
-                    cfg_value = True
-                elif cfg_value == 'false':
-                    cfg_value = False
-                elif cfg_value.isdigit():
-                    cfg_value = int(cfg_value)
-                elif cfg_value.startswith('{') and cfg_value.endswith('}'):
-                    cfg_value = json.loads(cfg_value)
-                else:
-                    try:
-                        cfg_value = float(cfg_value)
-                    except ValueError:
-                        pass
-
-                # 检查类型是否匹配
-                if isinstance(getattr(config, cfg_name), type(cfg_value)):
-                    setattr(config, cfg_name, cfg_value)
-                    pkg.utils.context.set_config(config)
-                    reply = ["[bot]配置项{}修改成功".format(cfg_name)]
-                else:
-                    reply = ["[bot]err:配置项{}类型不匹配".format(cfg_name)]
-
        else:
-            reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
+            cfg_entry_path = cfg_name.split('.')
+
+            try:
+                if len(params) == 1:
+                    cfg_entry = getattr(config, cfg_entry_path[0])
+                    if len(cfg_entry_path) > 1:
+                        for i in range(1, len(cfg_entry_path)):
+                            cfg_entry = cfg_entry[cfg_entry_path[i]]
+
+                    if isinstance(cfg_entry, str):
+                        reply_str = "[bot]配置项{}: \"{}\"\n".format(cfg_name, cfg_entry)
+                    elif isinstance(cfg_entry, dict):
+                        reply_str = "[bot]配置项{}: {}\n".format(cfg_name,
+                                                                 json.dumps(cfg_entry,
+                                                                            ensure_ascii=False, indent=4))
+                    else:
+                        reply_str = "[bot]配置项{}: {}\n".format(cfg_name, cfg_entry)
+                    reply = [reply_str]
+                else:
+                    cfg_value = " ".join(params[1:])
+                    # 类型转换，如果是json则转换为字典
+                    # if cfg_value == 'true':
+                    #     cfg_value = True
+                    # elif cfg_value == 'false':
+                    #     cfg_value = False
+                    # elif cfg_value.isdigit():
+                    #     cfg_value = int(cfg_value)
+                    # elif cfg_value.startswith('{') and cfg_value.endswith('}'):
+                    #     cfg_value = json.loads(cfg_value)
+                    # else:
+                    #     try:
+                    #         cfg_value = float(cfg_value)
+                    #     except ValueError:
+                    #         pass
+                    cfg_value = eval(cfg_value)
+
+                    cfg_entry = getattr(config, cfg_entry_path[0])
+                    if len(cfg_entry_path) > 1:
+                        for i in range(1, len(cfg_entry_path) - 1):
+                            cfg_entry = cfg_entry[cfg_entry_path[i]]
+                        if isinstance(cfg_entry[cfg_entry_path[-1]], type(cfg_value)):
+                            cfg_entry[cfg_entry_path[-1]] = cfg_value
+                            reply = ["[bot]配置项{}修改成功".format(cfg_name)]
+                        else:
+                            reply = ["[bot]err:配置项{}类型不匹配".format(cfg_name)]
+                    else:
+                        setattr(config, cfg_entry_path[0], cfg_value)
+                        reply = ["[bot]配置项{}修改成功".format(cfg_name)]
+            except AttributeError:
+                reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
+            except ValueError:
+                reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
+        # else:
+        #     reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]

    return reply

--- a/pkg/qqbot/manager.py
+++ b/pkg/qqbot/manager.py
@@ -102,6 +102,9 @@ class QQBotManager:

    enable_banlist = False

+    enable_private = True
+    enable_group = True
+
    ban_person = []
    ban_group = []

@@ -242,6 +245,11 @@ class QQBotManager:
            self.ban_group = banlist.group
            logging.info("加载禁用列表: person: {}, group: {}".format(self.ban_person, self.ban_group))

+            if hasattr(banlist, "enable_private"):
+                self.enable_private = banlist.enable_private
+            if hasattr(banlist, "enable_group"):
+                self.enable_group = banlist.enable_group
+
        config = pkg.utils.context.get_config()
        if os.path.exists("sensitive.json") \
                and config.sensitive_word_filter is not None \
@@ -269,7 +277,9 @@ class QQBotManager:
        import config
        reply = ''

-        if event.sender.id == self.bot_account_id:
+        if not self.enable_private:
+            logging.debug("已在banlist.py中禁用所有私聊")
+        elif event.sender.id == self.bot_account_id:
            pass
        else:
            if Image in event.message_chain:
@@ -342,8 +352,10 @@ class QQBotManager:
                replys = [tips_custom.replys_message]

            return replys
-
-        if Image in event.message_chain:
+        
+        if not self.enable_group:
+            logging.debug("已在banlist.py中禁用所有群聊")
+        elif Image in event.message_chain:
            pass
        else:
            if At(self.bot_account_id) in event.message_chain and response_at(event.group.id):
--- a/pkg/qqbot/message.py
+++ b/pkg/qqbot/message.py
@@ -114,8 +114,12 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
                reply = handle_exception("{}会话调用API失败:{}".format(session_name, e),
                                         "[bot]err:RateLimitError,请重试或联系作者，或等待修复")
        except openai.error.InvalidRequestError as e:
-            reply = handle_exception("{}API调用参数错误:{}\n".format(
-                             session_name, e), "[bot]err:API调用参数错误，请联系管理员，或等待修复")
+            if config.auto_reset and "This model's maximum context length is" in str(e):
+                session.reset(persist=True)
+                reply = [tips_custom.session_auto_reset_message]
+            else:
+                reply = handle_exception("{}API调用参数错误:{}\n".format(
+                                session_name, e), "[bot]err:API调用参数错误，请联系管理员，或等待修复")
        except openai.error.ServiceUnavailableError as e:
            reply = handle_exception("{}API调用服务不可用:{}".format(session_name, e), "[bot]err:API调用服务不可用，请重试或联系管理员，或等待修复")
        except Exception as e:
--- a/pkg/qqbot/process.py
+++ b/pkg/qqbot/process.py
@@ -74,7 +74,7 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
    import config
    if config.income_msg_check:
        if mgr.reply_filter.is_illegal(text_message):
-            return MessageChain(Plain("[bot] 你的提问中有不合适的内容, 请更换措辞~"))
+            return MessageChain(Plain("[bot] 消息中存在不合适的内容, 请更换措辞"))

    pkg.openai.session.get_session(session_name).acquire_response_lock()

--- a/pkg/utils/constants.py
+++ b/pkg/utils/constants.py
--- a/pkg/utils/updater.py
+++ b/pkg/utils/updater.py
@@ -34,13 +34,18 @@ def pull_latest(repo_path: str) -> bool:
    return True


-def is_newer_ignored_bugfix_ver(new_tag: str, old_tag: str):
-    """判断版本是否更新，忽略第四位版本"""
+def is_newer(new_tag: str, old_tag: str):
+    """判断版本是否更新，忽略第四位版本和第一位版本"""
    if new_tag == old_tag:
        return False

    new_tag = new_tag.split(".")
    old_tag = old_tag.split(".")
+    
+    # 判断主版本是否相同
+    if new_tag[0] != old_tag[0]:
+        return False
+
    if len(new_tag) < 4:
        return True

@@ -73,6 +78,34 @@ def get_current_tag() -> str:
    return current_tag


+def compare_version_str(v0: str, v1: str) -> int:
+    """比较两个版本号"""
+
+    # 删除版本号前的v
+    if v0.startswith("v"):
+        v0 = v0[1:]
+    if v1.startswith("v"):
+        v1 = v1[1:]
+
+    v0:list = v0.split(".")
+    v1:list = v1.split(".")
+
+    # 如果两个版本号节数不同，把短的后面用0补齐
+    if len(v0) < len(v1):
+        v0.extend(["0"]*(len(v1)-len(v0)))
+    elif len(v0) > len(v1):
+        v1.extend(["0"]*(len(v0)-len(v1)))
+
+    # 从高位向低位比较
+    for i in range(len(v0)):
+        if int(v0[i]) > int(v1[i]):
+            return 1
+        elif int(v0[i]) < int(v1[i]):
+            return -1
+    
+    return 0
+
+
 def update_all(cli: bool = False) -> bool:
    """检查更新并下载源码"""
    current_tag = get_current_tag()
@@ -97,7 +130,7 @@ def update_all(cli: bool = False) -> bool:
    else:
        print("更新日志: {}".format(rls_notes))

-    if latest_rls == {} and not is_newer_ignored_bugfix_ver(latest_tag_name, current_tag):  # 没有新版本
+    if latest_rls == {} and not is_newer(latest_tag_name, current_tag):  # 没有新版本
        return False

    # 下载最新版本的zip到temp目录
@@ -254,7 +287,7 @@ def is_new_version_available() -> bool:
            latest_tag_name = rls['tag_name']
            break

-    return is_newer_ignored_bugfix_ver(latest_tag_name, current_tag)
+    return is_newer(latest_tag_name, current_tag)


 def get_rls_notes() -> list:
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,10 +1,12 @@
-requests~=2.28.1
-openai~=0.27.6
+requests~=2.31.0
+openai~=0.27.8
 dulwich~=0.21.5
 colorlog~=6.6.0
-yiri-mirai~=0.2.7
+yiri-mirai
 websockets
 urllib3~=1.26.10
 func_timeout~=4.3.5
 Pillow
-nakuru-project-idk
+nakuru-project-idk
+CallingGPT
+tiktoken
--- a/res/announcement.json
+++ b/res/announcement.json
@@ -4,5 +4,11 @@
        "time": "2023-04-24 16:05:20",
        "timestamp": 1682323520,
        "content": "现已支持使用go-cqhttp替换mirai作为QQ登录框架, 请更新并查看 https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE"
+    },
+    {
+        "id": 1,
+        "time": "2023-05-21 17:33:18",
+        "timestamp": 1684661598,
+        "content": "NewBing不再需要鉴权，若您正在使用revLibs逆向库插件，请立即使用!plugin update revLibs命令更新插件到最新版。"
    }
 ]
--- a/res/screenshots/webwlkr_plugin.png
+++ b/res/screenshots/webwlkr_plugin.png
--- a/res/templates/banlist-template.py
+++ b/res/templates/banlist-template.py
@@ -1,3 +1,13 @@
+# 是否处理群聊消息
+# 为False时忽略所有群聊消息
+# 优先级高于下方禁用列表
+enable_group = True
+
+# 是否处理私聊消息
+# 为False时忽略所有私聊消息
+# 优先级高于下方禁用列表
+enable_private = True
+
 # 是否启用禁用列表
 enable = True

--- a/res/templates/cmdpriv-template.json
+++ b/res/templates/cmdpriv-template.json
@@ -1,12 +1,14 @@
 {
    "comment": "以下为命令权限，请设置到cmdpriv.json中。关于此功能的说明，请查看：https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%91%BD%E4%BB%A4%E6%9D%83%E9%99%90%E6%8E%A7%E5%88%B6",
    "draw": 1,
-    "plugin": 2,
+    "func": 1,
+    "plugin": 1,
    "plugin.get": 2,
    "plugin.update": 2,
    "plugin.del": 2,
    "plugin.off": 2,
    "plugin.on": 2,
+    "continue": 1,
    "default": 1,
    "default.set": 2,
    "del": 1,
--- a/res/wiki/功能使用.md
+++ b/res/wiki/功能使用.md
@@ -180,6 +180,7 @@
 !draw <提示语>     进行绘图
 !version          查看当前版本并检查更新
 !resend           重新回复上一个问题
+!continue         继续响应未完成的回合（通常用于内容函数继续调用）
 !plugin           用法请查看插件使用页的`管理`章节
 !default          查看可用的情景预设值
 ```
@@ -225,7 +226,7 @@
 格式: `!cfg <配置项名称> <配置项新值>`  
 以修改`default_prompt`示例
 ```
-!cfg default_prompt 我是Rock Chin
+!cfg default_prompt "我是Rock Chin"
 ```

 输出示例
@@ -243,7 +244,15 @@
 ```
 !~all
 !~default_prompt
-!~default_prompt 我是Rock Chin
+!~default_prompt "我是Rock Chin"
+```
+
+5. 配置项名称支持使用点号(.)拼接以索引子配置项
+
+例如: `openai_config.api_key`将索引`config`字典中的`openai_config`字典中的`api_key`字段，可以通过这个方式查看或修改此子配置项
+
+```
+!~openai_config.api_key
 ```

 </details>
@@ -367,4 +376,5 @@ prompt_submit_length = <模型单次请求token数上限> - 情景预设中token

 ### 加入黑名单

-编辑`banlist.py`，设置`enable = True`，并在其中的`person`或`group`列表中加入要封禁的人或群聊，修改完成后重启程序或进行热重载
+- 支持禁用所有`私聊`或`群聊`，请查看`banlist.py`中的`enable_private`和`enable_group`字段
+- 编辑`banlist.py`，设置`enable = True`，并在其中的`person`或`group`列表中加入要封禁的人或群聊，修改完成后重启程序或进行热重载
--- a/res/wiki/插件使用-内容函数.md
+++ b/res/wiki/插件使用-内容函数.md
@@ -0,0 +1,24 @@
+> 说白了就是ChatGPT官方插件那种东西
+
+内容函数是基于[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)实现的，这是一种嵌入对话中，由GPT自动调用的函数。  
+
+例如我们为GPT提供一个函数`access_the_web`，并提供其详细的描述以及其参数的描述，那么当我们在与GPT对话时涉及类似以下内容时：
+
+```
+Q: 请搜索一下github上有那些QQ机器人项目？
+Q: 请为我搜索一些不错的云服务商网站？
+Q：阅读并总结这篇文章：https://zhuanlan.zhihu.com/p/607570830
+Q：搜一下清远今天天气如何
+```
+
+GPT将会回复一个对`access_the_web`的函数调用请求，QChatGPT将自动处理执行该调用，并返回结果给GPT使其生成新的回复。
+
+当然，函数调用功能不止局限于网络访问，还可以实现图片处理、科学计算、行程规划等需要调用函数的功能，理论上我们可以通过内容函数实现与`ChatGPT Plugins`相同的功能。
+
+- 您需要使用`v2.5.0`以上的版本才能加载包含内容函数的插件
+- 您需要同时在`config.py`中的`completion_api_params`中设置`model`为支持函数调用的模型，推荐使用`gpt-3.5-turbo-16k`
+- 使用此功能可能会造成难以预期的账号余额消耗，请关注
+
+## QChatGPT的一些不错的内容函数插件
+
+- [WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin) - 让机器人能联网！！
--- a/res/wiki/插件使用.md
+++ b/res/wiki/插件使用.md
@@ -4,6 +4,8 @@ QChatGPT 插件使用Wiki

 `plugins`目录下的所有`.py`程序都将被加载，除了`__init__.py`之外的模块支持热加载

+> 插件分为`行为插件`和`内容插件`两种，行为插件由主程序运行中的事件驱动，内容插件由GPT生成的内容驱动，请查看内容插件页
+
 ## 安装

 ### 储存库克隆(推荐)
@@ -33,6 +35,8 @@ QChatGPT 插件使用Wiki
 !plugin del <插件名>       删除插件(需要管理员权限)
 !plugin on <插件名>        启用插件(需要管理员权限)
 !plugin off <插件名>       禁用插件(需要管理员权限)
+
+!func                      列出所有内容函数
 ```

 ### 控制插件执行顺序
@@ -42,4 +46,9 @@ QChatGPT 插件使用Wiki
 ### 启用或关闭插件

 无需卸载即可管理插件的开关  
-编辑`plugins`目录下的`switch.json`文件，将相应的插件的`enabled`字段设置为`true/false(开/关)`，之后重启程序或执行热重载即可控制插件开关
+编辑`plugins`目录下的`switch.json`文件，将相应的插件的`enabled`字段设置为`true/false(开/关)`，之后重启程序或执行热重载即可控制插件开关
+
+### 控制全局内容函数开关
+
+内容函数是基于[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)实现的，这是一种嵌入对话中，由GPT自动调用的函数。  
+每个插件可以自行注册内容函数，您可以在`plugins`目录下的`settings.json`中设置`functions`下的`enabled`为`true`或`false`控制这些内容函数的启用或禁用。
--- a/res/wiki/插件开发.md
+++ b/res/wiki/插件开发.md
@@ -113,6 +113,199 @@ class HelloPlugin(Plugin):
 - 一个目录内可以存放多个Python程序文件，以独立出插件的各个功能，便于开发者管理，但不建议在一个目录内注册多个插件
 - 插件需要的依赖库请在插件目录下的`requirements.txt`中指定，程序从储存库获取此插件时将自动安装依赖

+## 🪝内容函数
+
+通过[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)实现的`内容函数`，这是一种嵌入对话中，由GPT自动调用的函数。
+
+> 您的插件比一定必须包含内容函数，请先查看内容函数页了解此功能
+
+<details>
+<summary>示例：联网插件</summary>
+
+加载含有联网功能的内容函数的插件[WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin)，向机器人询问在线内容
+
+```
+# 控制台输出
+[2023-07-29 17:37:18.698] message.py (26) - [INFO] : [person_1010553892]发送消息:介绍一下这个项目：https://git...
+[2023-07-29 17:37:21.292] util.py (67) - [INFO] : message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=1902 request_id=941afc13b2e1bba1e7877b92a970cdea response_code=200
+[2023-07-29 17:37:21.293] chat_completion.py (159) - [INFO] : 执行函数调用: name=Webwlkr-access_the_web, arguments={'url': 'https://github.com/RockChinQ/QChatGPT', 'brief_len': 512}
+[2023-07-29 17:37:21.848] chat_completion.py (164) - [INFO] : 函数执行完成。
+```
+
+![Webwlkr插件](https://github.com/RockChinQ/QChatGPT/blob/master/res/screenshots/webwlkr_plugin.png?raw=true)
+
+</details>
+
+### 内容函数编写步骤
+
+1️⃣ 请先按照上方步骤编写您的插件基础结构，现在请删除（当然你也可以不删，只是为了简洁）上述插件内容的诸个由`@on`装饰的类函数
+
+<details>
+<summary>删除后的结构</summary>
+
+```python
+from pkg.plugin.models import *
+from pkg.plugin.host import EventContext, PluginHost
+
+"""
+在收到私聊或群聊消息"hello"时，回复"hello, <发送者id>!"或"hello, everyone!"
+"""
+
+
+# 注册插件
+@register(name="Hello", description="hello world", version="0.1", author="RockChinQ")
+class HelloPlugin(Plugin):
+
+    # 插件加载时触发
+    # plugin_host (pkg.plugin.host.PluginHost) 提供了与主程序交互的一些方法，详细请查看其源码
+    def __init__(self, plugin_host: PluginHost):
+        pass
+
+    # 插件卸载时触发
+    def __del__(self):
+        pass
+```
+
+</details>
+
+2️⃣ 现在我们将以下函数添加到刚刚删除的函数的位置
+
+```Python
+
+# 要添加的函数
+
+@func(name="access_the_web")  # 设置函数名称
+def _(url: str):
+    """Call this function to search about the question before you answer any questions.
+    - Do not search through baidu.com at any time.
+    - If you need to search somthing, visit https://www.google.com/search?q=xxx.
+    - If user ask you to open a url (start with http:// or https://), visit it directly.
+    - Summary the plain content result by yourself, DO NOT directly output anything in the result you got.
+
+    Args:
+        url(str): url to visit
+
+    Returns:
+        str: plain text content of the web page
+    """
+    import requests
+    from bs4 import BeautifulSoup
+    # 你需要先使用
+    # pip install beautifulsoup4
+    # 安装依赖
+
+    r = requests.get(
+        url,
+        timeout=10,
+        headers={
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.183"
+        }
+    )
+    soup = BeautifulSoup(r.text, 'html.parser')
+
+    s = soup.get_text()
+
+    # 删除多余的空行或仅有\t和空格的行
+    s = re.sub(r'\n\s*\n', '\n', s)
+
+    if len(s) >= 512:  # 截取获取到的网页纯文本内容的前512个字
+        return s[:512]
+
+    return s
+
+```
+<details>
+<summary>现在这个文件内容应该是这样</summary>
+
+```python
+from pkg.plugin.models import *
+from pkg.plugin.host import EventContext, PluginHost
+
+"""
+在收到私聊或群聊消息"hello"时，回复"hello, <发送者id>!"或"hello, everyone!"
+"""
+
+
+# 注册插件
+@register(name="Hello", description="hello world", version="0.1", author="RockChinQ")
+class HelloPlugin(Plugin):
+
+    # 插件加载时触发
+    # plugin_host (pkg.plugin.host.PluginHost) 提供了与主程序交互的一些方法，详细请查看其源码
+    def __init__(self, plugin_host: PluginHost):
+        pass
+
+    @func(name="access_the_web")
+    def _(url: str):
+        """Call this function to search about the question before you answer any questions.
+        - Do not search through baidu.com at any time.
+        - If you need to search somthing, visit https://www.google.com/search?q=xxx.
+        - If user ask you to open a url (start with http:// or https://), visit it directly.
+        - Summary the plain content result by yourself, DO NOT directly output anything in the result you got.
+
+        Args:
+            url(str): url to visit
+
+        Returns:
+            str: plain text content of the web page
+        """
+        import requests
+        from bs4 import BeautifulSoup
+        # 你需要先使用
+        # pip install beautifulsoup4
+        # 安装依赖
+
+        r = requests.get(
+            url,
+            timeout=10,
+            headers={
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.183"
+            }
+        )
+        soup = BeautifulSoup(r.text, 'html.parser')
+
+        s = soup.get_text()
+
+        # 删除多余的空行或仅有\t和空格的行
+        s = re.sub(r'\n\s*\n', '\n', s)
+
+        if len(s) >= 512:  # 截取获取到的网页纯文本内容的前512个字
+            return s[:512]
+
+        return s
+
+    # 插件卸载时触发
+    def __del__(self):
+        pass
+```
+
+</details>
+
+#### 请注意：
+
+- 函数的注释必须严格按照要求的格式进行书写，具体格式请查看[此文档](https://github.com/RockChinQ/CallingGPT/wiki/1.-Function-Format#function-format)
+- 内容函数和`以@on装饰的行为函数`可以同时存在于同一个插件，并同时受到`switch.json`中的插件开关的控制
+- 务必确保您使用的模型支持函数调用功能，可以到`config.py`的`completion_api_params`中修改模型，推荐使用`gpt-3.5-turbo-16k`
+
+3️⃣ 现在您的程序已具备网络访问功能，重启程序，询问机器人有关在线的内容或直接发送文章链接请求其总结。
+
+- 这仅仅是一个示例，需要更高效的网络访问能力支持插件，请查看[WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin)
+
+## 🔒版本要求
+
+若您的插件对主程序的版本有要求，可以使用以下函数进行断言，若不符合版本，此函数将报错并打断此函数所在的流程：
+
+```python
+require_ver("v2.5.1")  # 要求最低版本为 v2.5.1
+```
+
+```python
+require_ver("v2.5.1", "v2.6.0")  # 要求最低版本为 v2.5.1, 同时要求最高版本为 v2.6.0
+```
+
+- 此函数在主程序`v2.5.1`中加入
+- 此函数声明在`pkg.plugin.models`模块中，在插件示例代码最前方已引入此模块所有内容，故可直接使用
+
 ## 📄API参考

 ### 说明
@@ -257,6 +450,20 @@ KeySwitched = "key_switched"
        key_name: str 切换成功的api-key名称
        key_list: list[str] api-key列表
 """
+
+PromptPreProcessing = "prompt_pre_processing"  # 于v2.5.1加入
+"""每回合调用接口前对prompt进行预处理时触发，此事件不支持阻止默认行为
+    kwargs:
+        session_name: str 会话名称(<launcher_type>_<launcher_id>)
+        default_prompt: list 此session使用的情景预设内容
+        prompt: list 此session现有的prompt内容
+        text_message: str 用户发送的消息文本
+    
+    returns (optional):
+        default_prompt: list 修改后的情景预设内容
+        prompt: list 修改后的prompt内容
+        text_message: str 修改后的消息文本
+"""
 ```

 ### host: PluginHost 详解
--- a/tests/bs_test/bs_test.py
+++ b/tests/bs_test/bs_test.py
@@ -0,0 +1,42 @@
+
+import requests
+from bs4 import BeautifulSoup
+import os
+import random
+import sys
+
+
+user_agents = [
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1.2 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1 Safari/537.36',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0'
+]
+
+r = requests.get(
+    sys.argv[1],
+    headers={
+        "User-Agent": random.choice(user_agents)
+    }    
+)
+soup = BeautifulSoup(r.text, 'html.parser')
+# print(soup.get_text())
+
+raw = soup.get_text()
+
+import re
+
+# strip每一行
+# raw = '\n'.join([line.strip() for line in raw.split('\n')])
+
+# # 删除所有空行或只有空格的行
+# raw = re.sub(r'\n\s*\n', '\n', raw)
+
+
+print(raw)
--- a/tests/ssh_client_test/ssh_client.py
+++ b/tests/ssh_client_test/ssh_client.py
@@ -0,0 +1,57 @@
+import os
+import sys
+import paramiko
+import time
+import select
+
+
+class sshClient:
+    #创建一个ssh客户端，和服务器连接上，准备发消息
+    def __init__(self,host,port,user,password):
+        self.trans = paramiko.Transport((host, port))
+        self.trans.start_client()
+        self.trans.auth_password(username=user, password=password)
+        self.channel = self.trans.open_session()
+        self.channel.get_pty()
+        self.channel.invoke_shell()
+
+    #给服务器发送一个命令
+    def sendCmd(self,cmd):
+        self.channel.sendall(cmd)
+        
+    #接收的时候，有时候服务器处理的比较慢，需要设置一个延时等待一下。
+    def recvResponse(self,timeout):
+        data=b''
+        while True:
+            try:
+                #使用select，不断的读取数据，直到没有多余的数据了，超时返回。
+                readable,w,e= select.select([self.channel],[],[],timeout)
+                if self.channel in readable:
+                    data = self.channel.recv(1024)
+                else:
+                    sys.stdout.write(data.decode())
+                    sys.stdout.flush()
+                    return data.decode()
+            except TimeoutError:
+                sys.stdout.write(data.decode())
+                sys.stdout.flush()
+                return data.decode
+    #关闭客户端
+    def close(self):
+        self.channel.close()
+        self.trans.close()
+
+host='host'
+port=22#your port
+user='root'
+pwd='pass'
+
+ssh = sshClient(host,port,user,pwd)
+response = ssh.recvResponse(1)
+response = ssh.sendCmd("ls\n")
+ssh.sendCmd("cd /home\n")
+response = ssh.recvResponse(1)
+ssh.sendCmd("ls\n")
+response = ssh.recvResponse(1)
+
+ssh.close()
--- a/tests/token_test/tiktoken_test.py
+++ b/tests/token_test/tiktoken_test.py
@@ -0,0 +1,124 @@
+import tiktoken
+import openai
+import json
+import os
+
+
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+
+def encode(text: str, model: str):
+    import tiktoken
+    enc = tiktoken.get_encoding("cl100k_base")
+    assert enc.decode(enc.encode("hello world")) == "hello world"
+
+    # To get the tokeniser corresponding to a specific model in the OpenAI API:
+    enc = tiktoken.encoding_for_model(model)
+
+    return enc.encode(text)
+
+
+# def ask(prompt: str, model: str = "gpt-3.5-turbo"):
+#     # To get the tokeniser corresponding to a specific model in the OpenAI API:
+#     enc = tiktoken.encoding_for_model(model)
+    
+#     resp = openai.ChatCompletion.create(
+#         model=model,
+#         messages=[
+#             {
+#                 "role": "user",
+#                 "content": prompt
+#             }
+#         ]
+#     )
+
+#     return enc.encode(prompt), enc.encode(resp['choices'][0]['message']['content']), resp
+
+def ask(
+    messages: list,
+    model: str = "gpt-3.5-turbo"
+):
+    enc = tiktoken.encoding_for_model(model)
+
+    resp = openai.ChatCompletion.create(
+        model=model,
+        messages=messages
+    )
+
+    txt = ""
+
+    for r in messages:
+        txt += r['role'] + r['content'] + "\n"
+    
+    txt += "assistant: "
+
+    return enc.encode(txt), enc.encode(resp['choices'][0]['message']['content']), resp
+
+
+def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
+    """Return the number of tokens used by a list of messages."""
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+    if model in {
+        "gpt-3.5-turbo-0613",
+        "gpt-3.5-turbo-16k-0613",
+        "gpt-4-0314",
+        "gpt-4-32k-0314",
+        "gpt-4-0613",
+        "gpt-4-32k-0613",
+        }:
+        tokens_per_message = 3
+        tokens_per_name = 1
+    elif model == "gpt-3.5-turbo-0301":
+        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 "gpt-3.5-turbo" in model:
+        print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
+    elif "gpt-4" in model:
+        print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
+        return num_tokens_from_messages(messages, model="gpt-4-0613")
+    else:
+        raise NotImplementedError(
+            f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
+        )
+    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
+
+messages = [
+    {
+        "role": "user",
+        "content": "你叫什么名字？"
+    },{
+        "role": "assistant",
+        "content": "我是AI助手，没有具体的名字。你可以叫我GPT-3。有什么可以帮到你的吗？"
+    },{
+        "role": "user",
+        "content": "你是由谁开发的？"
+    },{
+        "role": "assistant",
+        "content": "我是由OpenAI开发的，一家人工智能研究实验室。OpenAI的使命是促进人工智能的发展，使其为全人类带来积极影响。我是由OpenAI团队使用GPT-3模型训练而成的。"
+    },{
+        "role": "user",
+        "content": "很高兴见到你。"
+    }
+]
+
+
+pro, rep, resp=ask(messages)
+
+print(len(pro), len(rep))
+print(resp)
+print(resp['choices'][0]['message']['content'])
+
+print(num_tokens_from_messages(messages, model="gpt-3.5-turbo"))
--- a/tips-custom-template.py
+++ b/tips-custom-template.py
@@ -30,5 +30,8 @@ command_admin_message = "[bot]err:权限不足： "
 command_err_message = "[bot]err:指令不存在："

 # 会话重置提示
-command_reset_message = "[bot]:会话已重置"
-command_reset_name_message = "[bot]:会话已重置，使用场景预设:"
+command_reset_message = "[bot]会话已重置"
+command_reset_name_message = "[bot]会话已重置，使用场景预设:"
+
+# 会话自动重置时的提示
+session_auto_reset_message = "[bot]会话token超限，已自动重置，请重新发送消息"
Author	SHA1	Message	Date
RockChinQ	b0cca0a4c2	Release v2.5.1	2023-07-31 18:12:59 +08:00
Junyan Qin	a2bda85a9c	Merge pull request #523 from RockChinQ/feat-prompt-preprocess-event [Feat] 新增PromptPreprocessing事件	2023-07-31 17:55:06 +08:00
RockChinQ	20677cff86	doc(wiki): 插件开发页增加版本断言说明	2023-07-31 17:53:33 +08:00
RockChinQ	c8af5d8445	feat: 添加版本断言函数require_ver	2023-07-31 17:46:30 +08:00
RockChinQ	2dbe984539	doc(wiki): 添加事件wiki说明	2023-07-31 17:27:28 +08:00
RockChinQ	6b8fa664f1	feat: 新增PromptPreprocessing事件	2023-07-31 17:21:09 +08:00
RockChinQ	2b9612e933	chore: 提交部分测试文件	2023-07-31 16:24:39 +08:00
RockChinQ	749d0219fb	chore: 删除弃用模块	2023-07-31 16:23:31 +08:00
Junyan Qin	a11a152bd7	ci: 解决sync-wiki.yml异常退出问题	2023-07-31 15:41:37 +08:00
Junyan Qin	fc803a3742	Merge pull request #522 from RockChinQ/feat-generating-stop-case [Feat] 新增!continue命令	2023-07-31 15:34:30 +08:00
GitHub Actions Bot	13a1e15f24	Update cmdpriv-template.json	2023-07-31 07:24:14 +00:00
RockChinQ	3f41b94da5	feat: 完善命令文档	2023-07-31 15:23:42 +08:00
RockChinQ	0fb5bfda20	ci: 添加tiktoken依赖	2023-07-31 15:20:23 +08:00
RockChinQ	dc1fd73ebb	feat: 添加continue命令	2023-07-31 15:17:49 +08:00
Junyan Qin	161b694f71	Merge pull request #521 from RockChinQ/fix-usage-not-reported [Fix] text的使用量未上报	2023-07-31 14:31:48 +08:00
RockChinQ	45d1c89e45	fix: text的使用量未上报	2023-07-31 14:28:48 +08:00
Junyan Qin	e26664aa51	Merge pull request #520 from RockChinQ/feat-accurately-calculate-tokens feat: 使用tiktoken计算tokens数	2023-07-31 12:16:10 +08:00
RockChinQ	e29691efbd	feat: 使用tiktoken计算tokens数	2023-07-31 11:59:22 +08:00
RockChinQ	6d45327882	debug: 接口底层添加返回数据debug信息	2023-07-31 10:37:45 +08:00
RockChinQ	fbd41eef49	chore: 删除devcontainer.json	2023-07-31 10:37:14 +08:00
Junyan Qin	0a30c88322	doc(README.md): 插件列表	2023-07-31 00:07:39 +08:00
Junyan Qin	4f5af0e8c8	Merge pull request #518 from RockChinQ/fix-cannot-disable-funcs-dynamically [Fix] plugin启用禁用命令对内容函数不生效	2023-07-30 23:56:01 +08:00
RockChinQ	df3f0fd159	fix: plugin启用禁用命令对内容函数不生效	2023-07-30 23:54:56 +08:00
RockChinQ	f2493c79dd	doc(wiki): 添加联网内容函数提问示例	2023-07-29 19:34:47 +08:00
RockChinQ	a86a035b6b	doc: 更新README.md	2023-07-29 19:26:28 +08:00
RockChinQ	7995793bfd	doc(wiki): 添加内容函数页	2023-07-29 19:24:56 +08:00
RockChinQ	a56b340646	Release v2.5.0	2023-07-29 18:59:25 +08:00
Junyan Qin	7473cdfe16	Merge pull request #513 from RockChinQ/feat-function-calling-integration [Feat] 支持GPT的函数调用功能	2023-07-29 18:57:29 +08:00
RockChinQ	24273ac158	doc: README添加内容函数相关内容	2023-07-29 18:55:18 +08:00
RockChinQ	fe6275000e	doc(wiki): 更新wiki插件页	2023-07-29 18:40:49 +08:00
RockChinQ	5fbf369f82	doc(wiki): 更新插件页	2023-07-29 18:37:03 +08:00
Junyan Qin	4400475ffa	chore: 添加Webwlkr插件示例	2023-07-29 17:41:56 +08:00
GitHub Actions Bot	796eb7c95d	Update cmdpriv-template.json	2023-07-29 09:30:22 +00:00
RockChinQ	89a01378e7	ci: 跑工作流	2023-07-29 17:29:52 +08:00
RockChinQ	f4735e5e30	ci(cmd_priv): 添加CallingGPT依赖	2023-07-29 17:28:11 +08:00
RockChinQ	f1bb3045aa	feat: 添加func命令	2023-07-29 17:26:07 +08:00
RockChinQ	96e474a555	feat: 插件开关对其内容函数生效	2023-07-29 17:10:47 +08:00
RockChinQ	833d29b101	typo: enable->enabled	2023-07-29 16:55:01 +08:00
RockChinQ	dce6734ba2	feat: 改为推荐使用func()装饰器注册内容函数	2023-07-29 16:51:19 +08:00
RockChinQ	0481167dc6	feat: 改为在start流程设置openai.proxy	2023-07-29 16:36:31 +08:00
RockChinQ	a002f93f7b	chore: 删除过时代码	2023-07-29 16:30:09 +08:00
RockChinQ	3c894fe70e	feat: chat_completion的函数开关支持	2023-07-29 16:29:16 +08:00
RockChinQ	8c69b8a1d9	feat: 内容函数全局开关支持	2023-07-29 16:28:18 +08:00
Junyan Qin	a9dae05303	doc(README.md): 修改社区群群号	2023-07-29 13:31:58 +08:00
RockChinQ	ae6994e241	feat(contentPlugin): 完成基本的内容函数调用功能	2023-07-28 19:03:02 +08:00
Rock Chin	caa72fa40c	feat: 在插件层面初步支持内容函数	2023-07-27 14:27:36 +08:00
Junyan Qin	46cc9220c3	Merge pull request #506 from RockChinQ/perf-persist-dprompt-when-auto-reset [Perf] 在session自动重置时保留非default的prompt	2023-07-07 17:53:29 +08:00
Rock Chin	ddb56d7a8e	fix: reset命令错误的逻辑	2023-07-07 17:49:43 +08:00
Rock Chin	a0267416d7	fix: 修复reset逻辑导致的无法初始化情景预设问题	2023-07-07 16:37:05 +08:00
Rock Chin	56e1ef3602	fix: 修复reset可能引起的bug	2023-07-07 16:35:37 +08:00
Rock Chin	b4fc1057d1	perf: 在session自动重置时保留非default的prompt (#494 )	2023-07-06 23:09:39 +08:00
Rock Chin	06037df607	ci: 仅在master分支运行sync-wiki工作流	2023-06-20 22:42:18 +08:00
Rock Chin	dce134d08d	Release v2.4.7	2023-06-16 19:43:13 +08:00
Junyan Qin	cca471d068	Merge pull request #500 from RockChinQ/perf-more-model-support Perf more model support	2023-06-16 19:40:29 +08:00
Rock Chin	ddb211b74a	feat: 支持新的模型	2023-06-16 19:35:26 +08:00
Rock Chin	cef70751ff	chore: 修改配置文件说明	2023-06-16 19:35:06 +08:00
JunYan Qin	2d2219fc6e	更新 README.md	2023-06-13 11:59:30 +08:00
JunYan Qin	514a6b4192	更新 README.md	2023-06-13 11:59:07 +08:00
JunYan Qin	7a552b3434	Merge pull request #496 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.8 chore(deps): update openai requirement from ~=0.27.7 to ~=0.27.8	2023-06-12 23:20:02 +08:00
dependabot[bot]	ecebd1b0e0	chore(deps): update openai requirement from ~=0.27.7 to ~=0.27.8 Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version. - [Release notes](https://github.com/openai/openai-python/releases) - [Commits](https://github.com/openai/openai-python/compare/v0.27.7...v0.27.8) --- updated-dependencies: - dependency-name: openai dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>	2023-06-12 09:01:51 +00:00
Rock Chin	8dc34d2a88	doc(README.md): 添加卖号网站	2023-06-12 14:13:36 +08:00
Rock Chin	d52644ceec	doc: 更新README.md	2023-06-12 12:24:59 +08:00
Rock Chin	3052510591	Release v2.4.6	2023-06-08 14:01:18 +08:00
Rock Chin	777a5617db	Merge pull request #492 from RockChinQ/feat-ignore-major-vernum [Feat] 更新时忽略主版本号不同的版本	2023-06-08 14:00:32 +08:00
Rock Chin	e17c1087e9	feat(updater.py): 更新时忽略主版本号不同的版本	2023-06-08 13:57:24 +08:00
Rock Chin	633695175a	Merge pull request #491 from RockChinQ/feat-tokens-auto-reset [Feat] token超限报错时自动重置会话	2023-06-08 13:49:49 +08:00
Rock Chin	9e78bf3d21	perf: 更严格的重置条件判断	2023-06-08 13:49:20 +08:00
Rock Chin	43aa68a55d	feat: 支持在token超限时自动重置会话	2023-06-08 13:45:54 +08:00
Rock Chin	b8308f8c57	Merge branch 'feat-tokens-auto-reset' of https://github.com/RockChinQ/QChatGPT into feat-tokens-auto-reset	2023-06-08 13:43:36 +08:00
Rock Chin	466bfbddeb	perf: 提示语格式	2023-06-08 13:43:33 +08:00
GitHub Actions	b6da07b225	Update override-all.json	2023-06-08 05:20:55 +00:00
Rock Chin	2f2159239a	chore: 添加开关和提示语配置项	2023-06-08 13:20:33 +08:00
Rock Chin	67d1ca8a65	Merge pull request #490 from RockChinQ/feat-global-group-private-enable [Feat] 支持设置全局群聊/私聊消息禁用	2023-06-07 23:49:53 +08:00
Rock Chin	497a393e83	doc: 修改wiki	2023-06-07 23:49:09 +08:00
Rock Chin	782c0e22ea	feat: 支持设置全局群聊、私聊禁用	2023-06-07 23:47:13 +08:00
Rock Chin	2932fc6dfd	chore(banlist-template.py): 添加配置项	2023-06-07 23:23:21 +08:00
Rock Chin	0a9eab2113	chore(requirements.txt): 更新requests版本	2023-06-06 09:37:00 +08:00
Rock Chin	50a673a8ec	doc: 添加插件列表list	2023-06-05 22:37:19 +08:00
Rock Chin	9e25d0f9e4	Release v2.4.5	2023-05-31 18:31:25 +08:00
Rock Chin	23cd7be711	Merge pull request #487 from RockChinQ/feat-banlist-syntax-check feat: 初始化流程异常处理	2023-05-31 18:25:46 +08:00
Rock Chin	025b9e33f1	feat: 初始化流程异常处理	2023-05-31 18:24:01 +08:00
Rock Chin	bab2f64913	doc(README_en.md): 添加wakapi计时	2023-05-29 11:12:07 +08:00
Rock Chin	b00e09aa9c	doc: 添加wakapi计时	2023-05-29 11:10:49 +08:00
Rock Chin	0b109fdc7a	Merge pull request #479 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.7 chore(deps): update openai requirement from ~=0.27.6 to ~=0.27.7	2023-05-22 17:13:50 +08:00
dependabot[bot]	018fea2ddb	chore(deps): update openai requirement from ~=0.27.6 to ~=0.27.7 Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version. - [Release notes](https://github.com/openai/openai-python/releases) - [Commits](https://github.com/openai/openai-python/compare/v0.27.6...v0.27.7) --- updated-dependencies: - dependency-name: openai dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>	2023-05-22 09:05:00 +00:00
Rock Chin	f8a3cc4352	doc: 折起OpenAI注册步骤	2023-05-21 18:25:35 +08:00
Rock Chin	6ab853acc1	doc: 修改关于HuggingChat的说明	2023-05-21 17:50:35 +08:00
Rock Chin	e825dea02f	chore: 排除hugchat.json	2023-05-21 17:47:42 +08:00
Rock Chin	cf8740d16e	Merge branch 'master' of https://github.com/RockChinQ/QChatGPT	2023-05-21 17:33:47 +08:00
Rock Chin	9c4809e26f	chore: 发布revLibs相关公告	2023-05-21 17:33:44 +08:00
Rock Chin	0a232fd9ef	Merge pull request #477 from RockChinQ/feature-detailed-cfg-cmd [Feat] 支持使用!cfg指令修改子配置项	2023-05-21 15:59:59 +08:00
Rock Chin	23016a0791	doc: 更新wiki说明	2023-05-21 15:58:21 +08:00
Rock Chin	cdcc67ff23	feat(!cfg): 使用eval()函数进行类型转换	2023-05-21 15:53:56 +08:00
Rock Chin	92274bfc34	feat(!cfg): 支持使用点号索引子配置项	2023-05-21 15:49:56 +08:00