I have the problem that the google home/assitant action console simulators response and request tab are not working. At least when I am using a custom action.json.
For me I am not sure if all have this problem or only some. That are using an custom action sdk. Or is it a problem only because something of my action.json is maybe not 100% correct configured.
here is the action.json:
{
"actions": [
{
"description": "Default Welcome Intent",
"name": "MAIN",
"fulfillment": {
"conversationName": "testApp"
},
"intent": {
"name": "actions.intent.MAIN",
"trigger": {
"queryPatterns": [
"open special manager",
"open s p m"
]
}
}
}
],
"types": [],
"conversations": {
"testApp": {
"name": "testApp",
"url": "https://572e66a2.ngrok.io/",
"fulfillmentApiVersion": 2,
"in_dialog_intents": [
{
"name": "actions.intent.NO_INPUT"
},
{
"name": "actions.intent.SIGN_IN"
}
]
}
}
here is a picture of the request:
As you can see it is only the dummy content in request tab anyway if the chat is working.
The response tab is completly empty. But the messages and voice is correctly working. Also on my google home.
Does anybody have an idea? I will add of course more debug informations if necessary. Can it be trouble with the response or request messages from my server?
But actually the messages, they are working...
Related
I am building a Google Assistant action without using Dialogflow instead using our own NLG / NLU , i am using gactions cli to upload my action file, all works fine , while i am able to test in simulator as well on my phone,
I am unable to submit for Alpha / Beta testing, all i see is those buttons disabled and its saying i do not have any action (as i am not using dialogflow).
How can i submit action for Alpha/Beta testing?
It looks like you haven't defined any actions in the action package (the file you upload using the gactions tool). Unfortunately "action" has several meanings here. One is the app itself, another is the things it can do via 'intents'.
Try adding the main intent to your action package:
{
"actions": [
{
"description": "Default Welcome Intent",
"name": "MAIN",
"fulfillment": {
"conversationName": "HelloWorld"
},
"intent": {
"name": "actions.intent.MAIN",
"trigger": {
"queryPatterns": [
"Open hello world"
]
}
}
}
]
}
The conversationName field must be the same as the one you define under conversations in the same file.
"conversations": {
"HelloWorld": {
"name": "HelloWorld",
"url": "https://myapp.example.com",
"fulfillmentApiVersion": 2,
}
}
Sometimes Google Assistant does not answer me even though I receive correct response from the fulfillment. That happens only when I use voice command, by using keyboard it always works fine.
What I receive instead of the response
It's just 'thinking'.
After using conv.close('You've punched-in into demo as Jack'); in DialogFlow history I can see following response:
{
"queryText": "Jack",
"fulfillmentMessages": [
{
"text": {
"text": [
"[{\"type\":0,\"speech\":\"\"}]"
]
}
}
],
"webhookPayload": {
"google": {
"userStorage": "{\"data\":{}}",
"richResponse": {
"items": [
{
"simpleResponse": {
"textToSpeech": "You've punched-in into demo as Jack"
}
}
]
},
"expectUserResponse": false
}
},
"outputContexts": [
...
],
"intent": {
"id": "96f93154-0ae4-4bb4-91c3-c1b796d7cda3",
"displayName": "punch-in"
},
"intentDetectionConfidence": 1,
"languageCode": "en"
}
Does any one experienced such issue?
Noticed on Galaxy S7, Android 6.0.1.
actions-on-google v.2.2.0
That mostly happens to me when the internet connection is not good. With voice, there is an extra layer of Voice to Text conversion. Same latency issue might be causing the issue in your case.
The google assistant team resolved the issues I created to them, and after that the issues is not reproduced.
I decided to upgrade my Google Assistant action to use "dialogFlow V2 API" and my webhook returns an object like this
{
"fulfillmentText": "Testing",
"fulfillmentMessages": [
{
"text": {
"text": [
"fulfillmentMessages text attribute"
]
}
}
],
"payload": {
"google": {
"richResponse": {
"items": [
{
"mediaResponse": {
"mediaType": "AUDIO",
"mediaObjects": [
{
"name": "mediaResponse name",
"description": "mediaResponse description",
"largeImage": {
"url": "https://.../640x480.jpg"
},
"contentUrl": "https://.../20183832714.mp3"
}
]
},
"simpleResponse": {
"textToSpeech": "simpleResponse: testing",
"ssml": "simpleResponse: ssml",
"displayText": "simpleResponse displayText"
}
}
]
}
}
},
"source": "webhook-play-sample"
}
But I get an error message saying my action it is not available, is mediaResponse supported by V2?, should I format my object differently?, also, when I remove "mediaResponse" object works just fine and the assistant will speak the simpleResponse part.
This action was re-created this Mid March 2018 and I read about May deadline and that is why I decide to upgrade to V2, do you think I should go back to V1, I know I will have to delete it and re-created but that is fine. This is a link to the JSON object I see in the debug tab. Thanks once again
I set "API V2" in my action dialogFlow console, this is a screenshot of that setting
Here is an screenshoot of my action's integration -> Google Assistant
Thanks Allen, Yes I do have "expectUserResponse": false, I added the suggestion object you recommended but, unfortunately nothing changed, I am still getting this error
Simulator debug tag details
First of all - this is not a problem with Dialogflow V2. You also seem to be confusing the sunset of Actions on Google V1 with the release of Dialogflow V2 - they are two different creatures completely. If your project was using AoG V1, there would be a setting on the Actions integration screen, and thee isn't.
It is fine if you want to move to Dialogflow V2, but it isn't required. Media definitely works under Dialogflow V2.
The array of items must include a simpleResponse item first, before any of the other items in the RichResponse. (You also shouldn't include both ssml and textToSpeech - just one of them.) You also don't need the fulfillmentText and fulfillmentMessages components, since those are provided by the richResponse.
You also need to include suggestions chips unless you have set expectUserResponse to false. Somewhere in the simulator debug is probably a block that says
{
"name": "MalformedResponse",
"debugInfo": "expected_inputs[0].input_prompt.rich_initial_prompt: Suggestions must be provided if media_response is used..",
"subDebugEntryList": []
}
So something more like this should work:
{
"payload": {
"google": {
"richResponse": {
"items": [
{
"simpleResponse": {
"textToSpeech": "simpleResponse: testing",
"displayText": "simpleResponse displayText"
},
"mediaResponse": {
"mediaType": "AUDIO",
"mediaObjects": [
{
"name": "mediaResponse name",
"description": "mediaResponse description",
"largeImage": {
"url": "https://.../640x480.jpg"
},
"contentUrl": "https://.../20183832714.mp3"
}
]
}
}
]
"suggestions": [
{
"title": "This"
},
{
"title": "That"
}
]
}
}
},
"source": "webhook-play-sample"
}
As I don't know why suggested, using Postman.
Per docs, have succesfully POSTed the configuration to facebook APIs:
which is not supposed to be anyways locale specific. Even I don't see here
Localization: Developers can now provide text in multiple languages (or entirely different menus) for each local your bot's users may come from.
Like my brother, I have tried almost everything so far
This looks like some crazy bug. Is there some work around to add a simplest persistent menu?
Wasted 2 hours on this issue. Until I realised you have to delete the conversation then refresh facebook with ignore cache (ctrl+shift+r in chrome) and then it will show.
The FB API document states that the API link to hit for applying persistent menu to the page specific bot is:
https://graph.facebook.com/v2.6/me/messenger_profile?access_token=<PAGE_ACCESS_TOKEN>
Notice the me after version number i.e v2.6 in this specific case. However, this did not worked for a lot of people
There is small change in the API link to hit:
graph.facebook.com/v2.6/Page ID/messenger_profile?access_token=PAGE ACCESS TOKEN
Notice that me is replaced with the fb Page Id.
And the sample payload can still be the same:
{
"get_started": {
"payload": "Get started"
},
"persistent_menu": [
{
"locale": "default",
"composer_input_disabled": false,
"call_to_actions": [
{
"title": "Stop notifications",
"type": "nested",
"call_to_actions": [
{
"title": "For 1 week",
"type": "postback",
"payload": "For_1_week"
},
{
"title": "For 1 month",
"type": "postback",
"payload": "For_1_month"
},
{
"title": "For 1 year",
"type": "postback",
"payload": "For_1_year"
}
]
},
{
"title": "fresh jobs",
"type": "postback",
"payload": "fresh jobs"
},
{
"title": "More",
"type": "nested",
"call_to_actions": [
{
"title": "like us",
"type": "web_url",
"url": "https://www.facebook.com/nordible/"
},
{
"title": "blog",
"type": "web_url",
"url": "http://xameeramir.github.io/"
}
]
}
]
}
]
}
Notice that it is mandatory to configure get_started button before setting up the persistent_menu.
I have created an actions SDK app which I can view in my google assistant. On clicking account linkage is complete with Auth2.0, but SYNC intent is not getting triggered and app just shows a message "Something went wrong".
My action.json :
{
"actions": [{
"name": "actions.devices",
"fulfillment": {
"conversationName": "automation"
}
}],
"conversations": {
"automation" :
{
"name": "automation",
"url": "MY_APPLICATION_ENDPOINT"
}
}
}