Call RTCRtpTransceiver#setCodecPreferences with the preferrred codec order before every createOffer/createAnswer. This ensures that the codec preference is enforced even when there is no local description available yet while the preferred codec is being set immediately after media session creation.

The 'signalingstatechange' event for 'stable' is fired after the 'iceconnectionstatechange' event for 'completed' is fired on chrome in Unified plan. This prevents the client from switching the media connection to the p2p connection once the ice connection for p2p gets established.

Add a preifx to logs for idenitifying the type of TPC/jingleSessionPC.

This can be controlled through the config.js  option 'enableUnifiedOnChrome'.

Avoid configuring the encodings on Chromium/Safari until simulcast is configured for the newly added track using SDP munging which happens during the renegotiation.

Avoid configuring the encodings on chromium immediately after replace track since the encoding params are read-only until the renegotation is done.

* fix(xmpp): use text parameter instead of attr for message

bug: msg with elementName != 'body' ->
   Cannot read property 'appendChild' of null

fix leads to another problem - there is some magic in the 'c' function:
"This function moves the current element pointer to the child,
unless text is provided"

apply the same magic here. will be removed in the next commit

* fix(xmpp): do not rely on internals of Strophe.c

* squash: Fixes tests.

Co-authored-by: damencho <damencho@jitsi.org>

The direction was marked as 'inactive' only on Firefox as Safari had audio issues when an inactive mid is re-used. Chrome (in unified-plan) needs the direction of the mid in remote desc to be set to 'inactive' for a 'removetrack' to be fired on the associated media stream whenever a remote source is removed.

This is needed only for JVB connections. Add unit tests for LocalSdpMunger.

If the msid attribute is missing, then remove the ssrc from the transformed description so that a source-remove is signaled to Jicofo. This happens when the direction of the transceiver (or m-line) is set to 'inactive' or 'recvonly' on Firefox. Not signaling these source updates creates issues with remote track handling on the other endpoints in the call.

This fixes the issue where TRACK_REMOVED event is not fired when a remote track is removed from the peerconnection.
Fixes https://github.com/jitsi/lib-jitsi-meet/issues/1612 and https://github.com/jitsi/jitsi-meet/issues/8482.

There is a known issue with Firefox where the BWE gets halved on every renegotiation causing the low upload bitrates from the Firefox clients.

Fixes https://github.com/jitsi/docker-jitsi-meet/issues/1048

Get the correct media type when generating the source identifier.

* feat: Audio/Video moderation.

* squash: Fix docs.

* squash: Adds some warning logs when execution is rejected.

* squash: Changes a field name in the message for adding jid to whitelist.

* squash: Send to participants only message about approval.

Skips sending the whole list.

* squash: Fixes tests.

* squash: Adds more logs.

* feat: Separates enable/disable by media type.

Adds actor to the messages to inform who enabled it.

* squash: Fixes log line.

* squash: Fixes comments.

* squash: Fixes log messages.

* squash: Fixes comments.

When a msid attribute is missing in the 'a=ssrc' line, use the local endpoint id as an indentifier. Move this generation logic to LocalSdpMunger. Also suppress notifying Jicfo of a ssrc change on Firefox when the change is a result of the media being suspended on the jvb connection.

Get rid of noisy logs related to SDP transformations which are redundant. Fix formatting and add missing information.

If the application is using the new receiver constraints, propagate the height constraint to the p2p session as well.

Do not send old format constraints if no constraints are set before the channel is initialized.

In certain cases, when RTCPeerconnection#addTrack is used, the browser doesn't produce the streamid in the 'a=msid' line which is being used by Jicofo as a unique identifier for the associated ssrc. Whenever the msid is missing in the local description, generate an ID using the local endpoint id.

Do not try to configure encodings on the sender until they are available. This fixes an issue on Chrome (running in unified-plan mode) where unmuting the local source throws a 'Read-only field modified in setParameters()' error.

SDP utility classes are spread across RTC and XMPP directories now, moving these class files to a 'sdp' directory.

Switch to returning a Promise for getStats. Reset frame rate stat to 0 when video is suspended as a result of endpoint falling out of last-n.

* Fix: sysMessageHandler not deleted

#1589

* Update xmpp.js

Fixes the case where the old format height constraint is sent on join for a jvb media session.

Use the new receiver constraints unless it is explicitly disabled through config.js.

Drops the custom type breaking xmpp protocol.

Fixes https://github.com/jitsi/lib-jitsi-meet/issues/1571.

Disable simulcast for low fps screenshare and enable it for high fps screenshare. testing.capScreenshareBitrate config.js setting has now been deprecated.

* squash: Extracts parsing disco info in utility method.

* squash: Extracts parsing disco info identities and features in utility method.

* squash: Skip disco-info on reconnection.

Doing disco info queries only once.
If the call is longer than 24-hours turn credentials may be expired.

* feat: Adds handler for early messages with conference info data.

* feat: JiConOp handling for shard name.

* squash: Drops unneeded check.

* squash: Changes message type to service-info.

* squash: Moves utility parseDiscoInfo out of the Caps class.

* fix: high CPU on Chrome with low fps screen sharing

It turns out that if 5 fps is set on the track constraints,
Chrome will capture the original video in 30 fps and only
further down the pipeline will downsample it to 5 fps.
This results in very high CPU usage. Specify max FPS in
getDisplayMedia to fix the problem.

Getting rid of track.applyConstraints should also fix another
issue on Firefox where it reports 0x0 screen size after this call.

* ref(RTCUtils): remove trackOptions

* remove extra &&

This will reduce the numbers of transport-info IQs sent by the client.

Get rid of the browser specific keys and use the standard spec-compliant fields for stats.
Get the resolution/fps for remote streams from 'inbound-rtp' stats. Use the 'track' stats for the local resolution/fps since these take the active simulcast streams into account.