RTCUtils.enumerateDevices was being called earlier than the RTCUtils.init which assigned that function

By looking at the replaceTrack usages it's possible for it to be called with both new and old tracks null/undefined.

When a second remote track of the same mediatype is received for an endpoint, remove the existing track before creating the new remote track.

* Added video mute participant

* Trigger mute event

* Optimized mute type checks

* Fixed event name

* Fixed some linter issues

* Fixed more linter issues

* And even more linter issues fixed

* And more linter fixes

* Added media type to analytics event

When E2EE is disabled we need just set the last key to `false`. When decoding we
need to check if the last key is not false, otherwise we might try to decrypt
the unencrypted video frames, thus resulting in breakage.

- After ratchet do not set it as new key for current index. Set it to correct position in crypto ring.

* feat: Drops unused code about handling incoming caps changes.

* fix: Drop using private fields outside JitsiParticipant.

There were cases where the bridge was sending the same constraint multiple times causing redundant calls to getParameters/setParameters on the RTCRtpSender.

Translate the 'LastNChangedEvent', 'SelectedEndpointsChangedEvent' and 'ReceiverVideoConstraint' messages into the new 'ReceiverVideoConstraints' message that invokes the new bandwidth allocation algorithm in the bridge that is described here - https://github.com/jitsi/jitsi-videobridge/blob/master/doc/allocation.md. useNewBandwidthAllocationStrategy=true in config.js will invoke the translation in the client.

Fire PERMISSION_PROMPT_IS_SHOWN when none of the devices have a label
Fire a new SLOW_GET_USER_MEDIA event if the timeout for getUserMedia is exceeded

Update JitsiMeetJS.createLocalTracks to include the options for firing the above events
in the provided options argument. Deprecate the firePermissionPromptIsShownEvent flag in
method's signature

All the send video constraints for the client, i.e., what simulcast streams will be enabled based on constraints received on the bridge channel, will be handled by the SendVideoController class.
The receive video constraints like lastN, selectEndpoints and receive video resolution will be handled by the ReceiveVideoController class.

* fix: Save guards _features to be always empty and nver undefined.

* fix: Ignore caps changes relaying only on features in presence.

"Pinned" endpoints are deprecated, use "selected" instead.

Make sure screenshare w/ presenter gets the full 2500 Kbps bitrate.

The max bitrate for VP9 is enforced by adding the b=AS:<limit> line in the SDP since there is no way to configure the max. bitrates for the individual SVC streams using RTCRtpSender.setParameters.

Force the client to reload when the bridge that is handling the media goes down.
This mitigates issues seen on the bridge because of a client re-joining the call with the same endpointId, BWE issues, etc.
This behavior is configurable through 'enableForcedReload' setting in config.js.

On Firefox it throws:
DOMException: AudioContext.createMediaStreamSource: Connecting AudioNodes from AudioContexts with different sample-rate is currently not supported.

RN doesn't support RTCRtpSender yet. Therefore, media is suspended on RN by changing the media direction in the SDP whenever the client receives an ideal height of 0 for sender constraints on the bridge channel.

After ICE failure and subsequent recovery of the media connection to the bridge using session-terminate, the local connection status needs to updated when ICE connection is established on the new peerconnection. The local connectivity status will be shown as Lost otherwise.

* Support the urn:xmpp:extdisco:2 namespace specified by XEP-0125

* squash: Fix lint errors and drop unused code.

Co-authored-by: Jasper Hugo <jasper@jasperhugo.com>

Fixes https://github.com/jitsi/lib-jitsi-meet/issues/1466

* feat: Detects shard changed when using websockets.

* squash: Simplifies code.

* squash: Rename method.

* squash: Skips checking for shard changed on the initial connection.

Determine the preferred codec for a given endpoint based on the config.js settings and the codecs supported by the endpoint.
The preferred codec is published in presence and then used by the other endpoints in the call during join/leave to determine
if the codec needs to be changed on the fly. Different codecs can be configuered for p2p/jvb connections.
The preferredCodec/disabledCodec settings under videoQuality will have precedence over the older settins like preferH264/disableH264.

The jid received is the main jid in internal representation with [tenant]roomname@domain.com and we cannot compare it directly to roomname@conference.tenant.domain.com.

* fix: Drops unused parameter of join and sendPresence.

* feat: Skips using disco-info for features.

Uses presence to publish features added externally.
Recognizes jigasi participants using a specific presence extension used by jigasi.

* squash: Fixes tests.

* squash: Adds e2ee to the features in presence.

* squash: Fix function name and docs.

* squash: Drops detecting jigasi from initiator.

Using the newly added presence features.

* squash: Drops unused var.

* squash: Fix comments.

* squash: Adds a constant and for E2EEE feature.

which should include the colon in order not to match something like
  a=simulcast-is-cool

in order to not match a=msid-somethingelse, a=ridiculous and similar

Explicitly check if all the encodings report the same scaleResolutionDownBy value before trying to ensure they match the expected values. This makes Chrome VP9 work again.

Due to no timeout value passed the disconnection was not detected.

Now stores the time of the raw input when ping is received. Before this change we were storing the Date.now and comparing to _getTimeSinceLastServerResponse and we needed small adjustment of values as it may lead to no pings sent.

* fix: Always query the main domain for features.

* squash: Always use the main domain for turn credentials and ping.

* squash: Fix tests.