Co-authored-by: Saúl Ibarra Corretgé <saghul@jitsi.org>
Co-authored-by: zycwind <391321232@qq.com>

There is no need for setting the availability of desktop sharing anymore. It can
now be detected on the spot.

The reson for the previous code was that way back when browser extensions were
needed, it was possible to start a conference without desktopo sharing support
and get it afterwards. This is no longer the case.

…if they are reported as a feature request, of course.

We sometimes see "error   Top-level error, please report:
                  /usr/lib/prosody/util/serialization.lua:38: Can't serialize table: table has multiple references".
This also slows down restarting prosody.

Co-authored-by: Saúl Ibarra Corretgé <saghul@jitsi.org>

chore(deps) lib-jitsi-meet@latest

This fixes an issue where lastN is not bumped to 1 on an audio-only client when a screenshare source is added to the call.

Take into account the start muted values stored in local storage.

Participants that join video muted do not have video tracks attached. Fixes https://github.com/jitsi/jitsi-meet/issues/7942.

It must be served from the same origin, so we need to bypass the CDN we use for
meet.jit.si. See the code comments for the rationale on the workaround.

lib-jitsi-meet@latest

https://github.com/jitsi/jitsi-meet/issues/7911#issuecomment-714323255

Looks like the base it's still applied, so use a full URL.

We typically use a base URL for static assets using a CDN so loading the worker
from there won't work since it's a different origin. Using a URL relative to the
origin of the page will make it be loaded from the right place.

Add methods for start/stop recording in addition to the commands that we already have.

Tavram/twa

Make it a 512 square and specify its purpose as just "maskable" since this can't
go anywhere.

Through several avatar work iterations it's no longer used.

I don't know how to modify built-in MediaStreamTrack type, so ignore the error.

...so that the text is more readable in the presenter mode. Chrome by
default uses 'detail' for screen sharing. I went with the 'text' here,
because the docs[1] say "may take advantage of encoder tools that
optimize for text rendering." - whether that's good specifically for
the presenter mode I don't know. It looked good for me when tested
on Chrome.

https://www.w3.org/TR/mst-content-hint/

Since the external API now sets preferredWidth/preferredHeight for resizing the large video, we don't need to add chat width to the computed window width when the chat window is closed.
Fixes https://github.com/jitsi/jitsi-meet/issues/7889