Nick

The display text is supplemental, and there is no way to force the response. One alternative is to enable HTML output and then parse the HTML for the text.

The [`--display true`](https://github.com/googlesamples/assistant-sdk-python/blob/master/google-assistant-sdk/googlesamples/assistant/grpc/pushtotalk.py#L255) which you [can then get](https://github.com/googlesamples/assistant-sdk-python/blob/master/google-assistant-sdk/googlesamples/assistant/grpc/pushtotalk.py#L175).

There's no structured representation of this screen information.

You should take a look at which account is logged into `gactions`. It looks like it's not the same account which owns the project, or you've never authorized with gactions...

Is there a reason to change the default?

Are you using the Assistant SDK library or the Assistant SDK service? There are some limitations to assigning rooms for devices, and features that would necessitate room assignments are probably...

Either way, features that you'd get from room assignments aren't available right now.

Are you using the library or the service api?

If you're doing pushtotalk, you may see that by default it uses silence detection to determine when to end the API request. It stops recording when it gets the [END_OF_UTTERANCE](https://github.com/googlesamples/assistant-sdk-python/blob/master/google-assistant-sdk/googlesamples/assistant/grpc/pushtotalk.py#L141)...

Which version of the `google-assistant-library` are you using?