The client will reject P2P session-initiate if the conditions which
allow for P2P session to start are not met(there more or less than 2
human participants in the call).

We had several reports that googSuspendBelowMinBitrate misbehaves, we had been running for a while with that disabled for the bridge, but it was causing problems and for p2p.

If DTLS fingerprint remains unchanged after ice-restart there will be no
media flow even thought the ICE connection will be re-established.
That's because JVB has all layers re-initialized from scratch, but
the WebRTC stack will keep the current state of the DTLS layer.

Reset the DTLS layer by setting an all zeros fingerprint on the hacky
offer/answer cycle which is currently done in order to reset the data
channels and the sequence number counters on the RTP receivers.

The event TRACK_VIDEOTYPE_CHANGED passes only the video type
along, not the track.

To be sure we always report room name in small case and as mobile and jigasi report this way it will take time for them to adopt which leads to wrong stats.

This commit refactors 592f72a63c. It adds
the video type in the event and it also does a better job at managing
and properly cleaning up the state map.

Move time since last success error detail to
the _getConnectionFailedReasonDetails method and use it on all
connection failed events.

React Native also supports it now.

If it's good enough for Google Meet it's good enough for us :-)

This functionality is being brought back for apps
that use ljm for its prosody logic but not for
video conferencing, ie Jitsi-Meet Spot. The desired
use is for Spot-TVs to be identifiable by their
jid alone and for the resource to be the part
that identifies them.

* Adds confID to JitsiConference option and enables callstats siteID.

* Simplifies siteID logic and use '/' as default when there is no tenant.

The version change is invoked from add/remove features which controls whether to submit the presence.

* Always uses 8 hex digits for the MUC nickname/endpoint ID.

* squash: Fix a comment and add the full JID to the log.

* squash: Fixes the compilation and style.

They contain no information about the failure (this is available in the onclose
event) and the event references the WS object itself, which causes hangs on
mobile.

Add 'timeSinceLastSuccess' to the details of connection dropped event.

Also do not execute any peerconnection callbacks like
'oniceconnectionstatechange', 'onicecandidate' etc. after close.

Attempts to fix this race condition:
1. Web client joins a conference.
2. Electron client joins the same conference.
3. Web client requests capabilities of Electron
   using version 1111.
4. Electron adds remote control capability,
   settings its version to 2222.
5. Electron responds to web client's requests
   but with features of 2222.
6. Web client caches request under 1111.
7. Any future calls to get features for a client
   with version 1111 will incorrect include the
   remote control capability.

Attempts to fix the following issue:
1. Electron user starts the conference join process.
2. Electron user adds remote control capability and
   attempts to send presence.
3. Electron user presence send is blocked because the
   conference has not been joined.
4. Electron user joins the conference.
5. The remote control capability is not emitted until
   some other presence change triggers another
   presence send. Until then, other uses will not see
   remote control option available for the electron
   user.

* Updates kicked event to inform local and remote kicks and who it affects

* Parses actor from MuteIQ and adds participant info to mute track event.

* Fixes emitting both events.

* Fixes comments.

The idea is to not show the frozen video indication for intermittent
failures which can be confusing to users.