在 Botframework 中为 Google 上的操作创建自定义适配器

Question

我目前正在用 Typescript 编写自定义适配器以将 Google Assistant 连接到 Microsoft 的 Botframework。在此适配器中，我试图通过网络调用捕获 Google 助理对话对象并使用我的机器人更改它。

目前，我的机器人正在做的唯一一件事就是在 Google 上接收来自 Actions 的请求并将请求正文解析为 ActionsOnGoogleConversation 对象。在此之后，我调用 conv.ask() 来尝试在两个服务之间进行简单的对话。

Api端点：

app.post("/api/google", (req, res) => {
  googleAdapter.processActivity(req, res, async (context) => {
    await bot.run(context);
  });
});

适配器 processActivity 函数：

public async processActivity(req: WebRequest, res: WebResponse, logic: (context: TurnContext) => Promise<void>): Promise<void> {
    const body = req.body;
    let conv = new ActionsSdkConversation();
    Object.assign(conv, body);
    res.status(200);
    res.send(conv.ask("Boo"));
  };

当我尝试开始对话时，我在 Google 控制台上的操作中收到以下错误。

UnparseableJsonResponse

API Version 2: Failed to parse JSON response string with 'INVALID_ARGUMENT' error: "availableSurfaces: Cannot find field." HTTP Status Code: 200.

我已经检查了响应，我可以在 AoG 控制台中找到一个名为 availableSurfaces 的字段，当我使用 Postman 调用我的机器人时。

回复：

{
  "responses": [
    "Boo"
  ],
  "expectUserResponse": true,
  "digested": false,
  "noInputs": [],
  "speechBiasing": [],
  "_responded": true,
  "_ordersv3": false,
  "request": {},
  "headers": {},
  "_init": {},
  "sandbox": false,
  "input": {},
  "surface": {
    "capabilities": [
      {
        "name": "actions.capability.MEDIA_RESPONSE_AUDIO"
      },
      {
        "name": "actions.capability.AUDIO_OUTPUT"
      },
      {
        "name": "actions.capability.ACCOUNT_LINKING"
      },
      {
        "name": "actions.capability.SCREEN_OUTPUT"
      }
    ]
  },
  "available": {
    "surfaces": {
      "list": [],
      "capabilities": {
        "surfaces": []
      }
    }
  },
  "user": {
    "locale": "en-US",
    "lastSeen": "2019-11-14T12:40:52Z",
    "userStorage": "{\"data\":{\"userId\":\"c1a4b8ab-06bb-4270-80f5-958cfdff57bd\"}}",
    "userVerificationStatus": "VERIFIED"
  },
  "arguments": {
    "parsed": {
      "input": {},
      "list": []
    },
    "status": {
      "input": {},
      "list": []
    },
    "raw": {
      "list": [],
      "input": {}
    }
  },
  "device": {},
  "screen": false,
  "body": {},
  "version": 2,
  "action": "",
  "intent": "",
  "parameters": {},
  "contexts": {
    "input": {},
    "output": {}
  },
  "incoming": {
    "parsed": []
  },
  "query": "",
  "data": {},
  "conversation": {
    "conversationId": "ABwppHEky66Iy1-qJ_4g08i3Z1HNHe2aDTrVTqY4otnNmdOgY2CC0VDbyt9lIM-_WkJA8emxbMPVxS5uutYHW2BzRQ",
    "type": "NEW"
  },
  "inputs": [
    {
      "intent": "actions.intent.MAIN",
      "rawInputs": [
        {
          "inputType": "VOICE",
          "query": "Talk to My test app"
        }
      ]
    }
  ],
  "availableSurfaces": [
    {
      "capabilities": [
        {
          "name": "actions.capability.AUDIO_OUTPUT"
        },
        {
          "name": "actions.capability.SCREEN_OUTPUT"
        },
        {
          "name": "actions.capability.WEB_BROWSER"
        }
      ]
    }
  ]
}

有谁知道这可能是什么原因造成的？我个人认为创建 ActionsSdkConversation 可能是原因，但我没有找到任何使用 Google Assistant 而不从 standard intent handeling setup.

获取 conv 对象的示例

Answer 1

所以我设法通过改变方法来修复它，而不是有一个适合 bot 框架结构的 API 点，我将它改为 AoG 的 intenthandler。

Google 控制器

export class GoogleController {

  public endpoint: GoogleEndpoint;
  private adapter: GoogleAssistantAdapter;
  private bot: SampleBot;

constructor(bot: SampleBot) {
    this.bot = bot;
    this.adapter = new GoogleAssistantAdapter();
    this.endpoint = actionssdk();
    this.setupIntents(this.endpoint);
};

private setupIntents(endpoint: GoogleEndpoint) {

    endpoint.intent(GoogleIntentTypes.Start, (conv: ActionsSdkConversation) => {
      this.sendMessageToBotFramework(conv);
    });

    endpoint.intent(GoogleIntentTypes.Text, conv => {
      this.sendMessageToBotFramework(conv);
    });
  };

  private sendMessageToBotFramework(conv: ActionsSdkConversation) {
    this.adapter.processActivity(conv, async (context) => {
      await this.bot.run(context);
    });
  };
};

interface GoogleEndpoint extends OmniHandler, BaseApp , ActionsSdkApp <{}, {}, ActionsSdkConversation<{}, {}>>  {};

一旦 conv 对象在适配器中，我就使用 conv 对象创建一个 activity 机器人用来做它的事情并使用 context.turnState()[= 将其保存在状态中15=]

适配器进程活动

  public async processActivity(conv: ActionsSdkConversation, logic: (context: TurnContext) => Promise<void>): Promise<ActionsSdkConversation> {

    const activty = this.createActivityFromGoogleConversation(conv);
    const context = this.createContext(activty);
    context.turnState.set("httpBody", conv);
    await this.runMiddleware(context, logic);

    const result = context.turnState.get("httpBody");
    return result;
  };

机器人

export class SampleBot extends ActivityHandler {

  constructor() {
    super();

    this.onMessage(async (context, next) => {
      await context.sendActivity(`You said: ${context.activity.text}`);
      await next();
    });
}

机器人发送响应后，我使用结果修改 conv 对象，将其保存，然后 return 在 processActivity() 中。

private createGoogleConversationFromActivity(activity: Partial<Activity>, context: TurnContext) {

    const conv = context.turnState.get("httpBody");

    if (activity.speak) {
      const response = new SimpleResponse({
        text: activity.text,
        speech: activity.speak
      });

      conv.ask(response);
    } else {

      if (!activity.text) {
        throw Error("Activity text cannot be undefined");
      };

      conv.ask(activity.text);
    };

    context.turnState.set("httpBody", conv);
    return;
  };

这导致了 Google 助手和 Bot Framework 之间的简单对话。

在 Botframework 中为 Google 上的操作创建自定义适配器

Creating a custom adapter in Botframework for Actions on Google

botframework

actions-on-google