Google Actions - how to add testers before final deployment - actions-on-google

someone knows how to add testers to an action on google package?
So other users can test the implementation on their Google Home devices?
Thanks!

Today you must use the developer's account to test except for the case of account linking where testers can put their own credentials in for that specific step, and test any functionality that relies on that. I am told by the Actions on Google support team that providing a mechanism for testers (with different accounts than the developer) to access Actions/agents prior to deployment is the number 1 requested feature "by far" so hopefully we will see it down the road.

Yes. Make sure everything under "Directory information" is filled out. Then go to the "Release" tab under "Deploy", and click on Alpha (which allows a quicker deploy for up to 20 users without review). Click "Submit for Alpha", and ensure you meet the requirements to check the checkboxes there. After that, you can press "Manage alpha testers" under the Alpha pane, where you can generate a link or add email addresses.
(screenshots anyone?)

Related

Not able to test Google Action

I am not able to test the Google Action. I'm getting an error:
The Web & App Activity permission is enabled, but the administrator of your Google account does not allow that. Please reach out to the administrator to change the preference.
But My team members are able to test it and we have the same privileges. I can't test it. I am not able to the "Account Linking" also.
In order to use Actions on Google or the Assistant, you will need your account's activity controls for "Web & App Activity" to be enabled.
You seem to be using a GSuite account, so this change may not be possible to toggle by yourself. In a work or school environment, the ability to change certain settings may be restricted by whoever manages the accounts. Depending on the scale you may be able to get the IT department to enable this setting.
Porting the project over to a standard GMail account will allow you to test the Action without this restriction.

I want my actions to not use any type of account linking

I want to publish this action but everytime I submit for production it shows the same message for denial. I don't want account linking of any type for my actions. Please help me in this problem.
It seems by mistake you have enabled Account Linking in your action.
If you don't want any kind of authentication or linking in your actions, check Account Linking section under Develop menu and clear it.
If it is linked you will get an option to clear it at the right side of the panel.
If you want Account Linking than you need to provide atleast one login credentials in testing credentials section.

Can I have a "semi-private" google action?

I'm attempting to write a google action that is only intended for use by me and my immediate family. I have it working currently in the simulator, and on my device, but I haven't "released" it yet.
This may be a result of it being still in the testing phase, but it seems to be able to be invoked only by my google account. Everything I do with the action works, but neither my wife nor kids can use it; they just get "I don't understand".
What do I have to do to allow other voice-recognized google accounts to be able to use my action?
This is intentional - your Action is currently in a "development" state. While you can permit it to other developers, this isn't a great approach.
You can "release" it into an Alpha channel and let a limited number of accounts have access to the Alpha channel version. This isn't quite a "private" action, but it doesn't require review from Google, and it does let you limit which accounts have access to it. Once they're in the Alpha channel, they can activate the Action just like public Actions.

Sorry, this action is not available in simulation

My test invocation name is "Mrs Tang", so i input "Talk to Mrs Tang", but it responds "Sorry, this action is not available in simulation"...
Does anybody know How can I resolve this error?
According to the doc:
Turn on the Web & App Activity, Device Information, and Voice & Audio
Activity permissions on the Activity controls page for your Google
account. You need to do this to use the Actions Simulator, which lets
you test your actions on the web without a hardware device.
And I had do what Jeremy Gordon suggested. To add a second google account in the GCP IAM console with a viewer action permission and then login with this second google account in an incognito window for the web simulator to work.
I had a related problem (I could test with my main developer account, but not my test credentials). I eventually got it working with the non-primary account.
The missing link for me was that when I was viewing the simulator, I was actually signed in to two accounts, my primary google account (developer account, shows up in the main frame of the page, upper right corner), and the account I authorized when 'starting' the simulator (email address shows up in the simulator frame), which was my test credentials. The second test account repeatedly gave me the "Sorry, this action is not supported in simulation" message, until I:
1) Added the test account as a Conversation API Viewer & Client in GCP IAM console
2) Visited the 'create link' (the one that comes up when you click share) in an incognito window, and signed into the secondary account there such that I was signed into only one account in that incognito window.
After that, invocations connected to the app.
Make sure you are logged into the same account you used to deploy the test action and that the deployment has been done within the past half hour or so. If you have not set all the information on the Actions on Google Console, you may need to use the invocation phrase "Talk to my test app".
I think sometimes I run into the same error. I get past it by toggling the Active switch off and on.
Same problem I encountered. You must be logged in via the secondary google account. Do logout from the account and login via the account that is paired with api.ai.
why I can't use google action in web simulator
I got this to work by saying "talk to my test app" or typing it in to the simulator prompt, that triggered my app to start in the simulator.
I had the same problem. I needed to set the location first (it defaults to Google-Headquaters), if you are in some other region (like in germany as i am).
Then go on with "Mit meiner Test-App sprechen" (Talk to my test app), or whatever it is in your language!
I did not get this message on my invocation, but on my my second input:"Sorry, this action is not available for your app.".
It turns out the simulator had left the conversation right after the invocation (and it did mention that in the small print).
This happened because I returned a FinalResponse for the invocation. And a final response is pretty final, it will terminate your conversation.
So, after a FinalResponse you can only get back in your action/conversation by a new invocation or a deep link. If you want to suggest questions/inputs, then you should return ExpectedInputs.
You might need to turn on Web & App Activity to let group members use some Google Assistant features.(if you are using organizational account)
https://support.google.com/assistant/answer/7219584?hl=en
If you are using any organization's Google Accounts then there might be an access issue. So use your own personal Gmail account.
Take a look here, organization's might not be given you access. So use your personal Gmail and follow the Docs, you will able to create your agent/ actions and able to test it with simulator as well as in android device.
At time of testing the Google Action you need to set the location to the country which you selected while developing or submitting your Google Action.
By default US is selected in testing but if your action is for one particular country only then you need to select that. You can see in image the field where you can select location

iPhone Developer account: Multiple Admins?

I am doing some dev work for a client. She has a Dev License should would like to put the app under but since she is non-technical it has been frustrating since she has to be the one to submit the final app.
Is there a way for a Dev License to have multiple Admins? I have it configured so I am a developer but as such I cannot do the Distribution License. Only she can do that. Is there a fix?
If you have a good relationship to your client, you might want to ask her for her login details so you can do it yourself.
There is one other possibility though: For a similar problem I was given the advice to build & archive my app and send the archive to the client. He could then resign the app using his certs, which would eliminate the need for him to do all the building stuff, not to mention it will spare you to surrender your source code. However, this will not eliminate the need for your client to enter all the meta information and so forth while uploading the app.
For the necessary steps to resign an app, see this answer.
To answer your original question: Each developer account has exactly one Team Agent. So you need some kind of workaround anyway.
There is only one administrative or Team leader per developer account. So you really need to plan on the policy for sharing use of that account from the beginning, if the required activities of the agent need to be split up among multiple parties, if you can't have one party capable of doing everything.
A shared account can be created from the beginning (either by the owner or the developer). I recommend an ADC account be created just for this purpose, instead of just using the owner's personal account and email address ( e.g. instead of mary.smith#sample.com, create and use iosdeveloper#sample.com for enrolling as an iOS developer. )
Account credentials can be "loaned" (perhaps with password changes after use).
You can be given remote access (VNC/RDP) into the owners PC or Mac (or more secure yet, a VM session) as or after they log in.
You can talk the owner though the process over the phone (or video chat, etc.).
Or, the owner can learn how to get certificates, and build or resign and submit apps themselves, perhaps using a comprehensive script.