Implementing Conversation Webhook as Azure Function App - actions-on-google

Question

I have an azure function app that I am using as a webhook for my google assistant action. I've tried to follow the documentation for the proper response but I continually get the following error in the simulator when testing my webhook. Is there anything in my response message that looks wrong?
Failed to parse SDKResponse from http_response:
HTTP/1.1 200 OK
Cache-Control: no-cache
Pragma: no-cache
Content-Length: 451
Content-Type: application/json; charset=utf-8
Content-Encoding: gzip
Expires: -1
Vary: Accept-Encoding
Server: Microsoft-IIS/8.0
X-AspNet-Version: 4.0.30319
X-Powered-By: ASP.NET
Date: Sun, 28 May 2017 19:00:13 GMT
{"conversationToken":"cee44ab4-97dd-4e18-99c7-2b8613eb7584","expectUserResponse":true,"expectedInputs":[{"inputPrompt":{"richInitialPrompt":{"items":[{"simpleResponse":{"textToSpeech":"So, you want to become a great swordsman? First, you must learn the proper technique of insult sword fighting. The current difficulty level is Easy. Say 'Tutorial' for some quick instructions. Say 'Start Game' to start the game. Say 'Options' for more options. "}}]}}}]}
Here is the json formatted for readability:
{
"conversationToken": "cee44ab4-97dd-4e18-99c7-2b8613eb7584",
"expectUserResponse": true,
"expectedInputs": [
{
"inputPrompt": {
"richInitialPrompt": {
"items": [
{
"simpleResponse": {
"textToSpeech": "So, you want to become a great swordsman? ... "
}
}
]
}
}
}
]
}
With my latest test, I tried sending the exact example response given on the Fulfillment page instructions and it still fails: https://developers.google.com/actions/components/fulfillment
{
"conversationToken": "{\"state\":null,\"data\":{}}",
"expectUserResponse": true,
"expectedInputs": [
{
"inputPrompt": {
"richInitialPrompt": {
"items": [
{
"simpleResponse": {
"textToSpeech": "Howdy! I can tell you fun facts about almost any number, like 42. What do you have in mind?",
"displayText": "Howdy! I can tell you fun facts about almost any number. What do you have in mind?"
}
}
],
"suggestions": []
}
},
"possibleIntents": [ { "intent": "actions.intent.TEXT" } ]
}
]
}

Answer 1

It looks like you have a slightly invalid entry for your items. The Item object is defined as a union field, indicating that one of the three attributes (simpleResponse, basicCard, or structuredResponse) and its respective value must be set.
So the textToSpeech attribute should not be under the richInitialPrompt.item directly, instead you should have a simpleResponse attribute and, under this, a textToSpeech attribute (or one of the other attributes that make sense for a SimpleResponse object. You must have at least one SimpleResponse (and it must be first), and you may have no more than two.
But the text attached to your second response doesn't make sense in this context. Both responses will be said/shown - not one in case there is a delay in user action.
The v1 protocol had a way to support details of the re-prompt, but I don't see the same thing in v2.
So the JSON should probably look more like:
{
"conversationToken": "fa3bfc17-de0a-4df8-900d-44dbb17b86c6",
"expectUserResponse": true,
"expectedInputs": [
{
"inputPrompt": {
"richInitialPrompt": {
"items": [
"simpleResponse": {
"textToSpeech": "Text for my response"
}
]
}
}
}
]
}