* feat: Set degradation preference on video senders
Use 'maintain-framerate' for camera tracks and 'maintain-resolution' for desktop tracks

* ref: apply cached video contraints and degradation preference on unmute
Since the sender encodings are available only after the renegotiation is complete (on chrome/safari), constraints/preferences have to be applied after renegotiation is complete.

- Use getDisplayMedia on browsers where it is supported.
- desktopSharingChromeDisabled and desktopSharingFirefoxDisabled will no longer be supported.

Refactors the way send/receive video constraints are managed and puts the high level
logic in a separate module. See QualityController.js for high level overview on how
the constraints are managed now.

Adds events to JitsiConference fired whenever it starts new jvb/p2p session.

Adds event to JingleSessionPC.js when remote party signals receive max frame height.
Also adds signaling of the local recv preference for the p2p mode(only existed for JVB).

mostly removing the 'tmp' variable. Renaming 'media' to 'sdp'
in some places.

Pass a value for Opus' maxaveragebitrate parameter to Jicofo
iff opusMaxAvgBitrate is set as configuration option.

not used elsewhere. Also the common term for this is munging
these days.

using more specific selectors

We switched to using replaceTrack for Firefox and Safari in the unified-plan rewrite

When screensharing is stopped on FF from the sharing indicator (available in FF nightly), we are currently not detecting it.
Firefox fires a track 'ended' event as opposed to Chrome which fires a mediastream 'inactive' event as well.

to test the mapping of fmtp lines which are not key=value pairs

* fix: Fix shuffling turn servers.

In the Fisher-Yates shuffle we want to choose 0 <= j <= i. The existing
implementation always swaps the two elements in a 2-element array.

* feat: Add an option to allow turn/udp for the videobridge PC.

Remove unused code, we always use replaceTrack in unified plan

There are cases when using tenants subdomain) where we would pass a capital letters in the muc component.

* Initial impl of lobby rooms.

* Fixes tests to check the new fulljid added to MUC_MEMBER_JOINED.

* Updates few of the comments, renaming some functions.

* Renames disableLobby ChatRoom option to enableLobby.

* Fixes a comment.

* Moves setMembersOnly method to ChatRoom.

* Fixes counting members, to exclude jicofo.

* Moves setLobbyRoomJid earlier and renames a method.

Rename _maybeEnableDisable to maybeJoinLeaveLobbyRoom.

* Drops using custom roomconfig lobbypassword field and reuse room lock.

* Handles destroying the lobby room.

* Handles clear lobby room on destroy for moderators.

We do not try to leave the lobby room as it is server-side destroyed and we handle that. The only case of leaving a lobby room is when request to join room is being approved.

* Join main room if lobby is disabled while waiting.

* Adds MEMBERS_ONLY_CHANGED conference event.

* fix: Make sure we leave lobby if main room is joined.

* fix: Setting password when joining locked room.

* fix: Fixes case where we enable lobby for already locked room.

* fix: Fixes case where we enable lobby and then lock room.

* fix: Fixes lint.

* ref: Removes shared password for lobby.

This functionality is handled by the lock room password and handled there.
Removes duplication and unnecessary complicated API for lobby room.

* fix: Fixes comments.

This behavior got altered when we correctly update the reference we keep of MediaStreamTrack in JitsiLocalTrack when effects are applied

* fix: Skips sending an extra presence on join.

* Renames the variable names.

Add RFC 4588 to the list of advertised features on Firefox.
Use RtxModifier only for cases when simulcast is achieved through SDP munging
This will ensure that RTX is negotiated whenever it is offered by the browser.

which landed in
  https://bugs.chromium.org/p/chromium/issues/detail?id=1069295#c4

In preparation for turning on RTX on Firefox: add only the primary ssrcs to the SIM group if FID groups are present

removes the SDES mapping. This is a leftover of the time when
Chrome only supported SDES and shouldn't be required anymore.

This has become obsolete thanks to ES6 arrow functions

derived from the participant id in addition to the salt, separated by a null
byte to avoid ambiguity attacks along the lines of
  (someRoom, someParticipant)
  (someRoo, mSomeParticipant)

removing an old FIXME

as suggested during the community call recently

See: https://chromium.googlesource.com/external/webrtc/+/refs/heads/master/pc/ice_server_parsing.cc#299

moves the cryptography bit to a datastructure which allows per-sender keys.
Does not yet use per-sender keys.

Also fixes lots of lint errors in the worker.

currently unused, will allow moving to per-participant keys

This will make sure we get 30 fps for screenshare on p2p connections

follow-up from #1146. Very high level but this should cover the relevant code paths.

The jingle offer was taken from a current focus offer with a few bits removed:
* ssrc-info element
* web-socket element inside transport
* rtcp-mux element inside transport
* bridge-session element
* bundle element (removed in focus already)

and make the code use arrow functions with named parameters in .each()/.map.

Make sure we inject the encoding function on RTCRtpsenders when tracks are replaced on the peerconnection.
Update the MediaStreamTrack on the JitsiLocalTrack when effects are applied or removed so that
we can find the RTCRtpSender using the MediaStreamTrack

This adds the 'codec' object to the RTP stats passed out of lib-jitsi-meet.

Switches from using JitsiConference.isJvbConnectionInterrupted
flag to peerconnection's ICE state. The interrupted
flag is not set if the connection fails initially.

Standard audio constraints need to be passed to gUM for audio input device selection
to work properly on Safari.
Safari doesn't support permissions query, add a workaround for that.

...to prevent a crash. The functionality that depends on it
is not required by ProxyConnectionPC.

Audio fails on Safari when we try to re-use audio m-lines whose direction has been set to 'inactive'
when the remote source left the conference.
Disable noisy mic detection on Safari as this causes audio input to fail on Safari on iPadOS