There was an error in the pattern match, everything was included in it. In
addition return a boolean in case we succeed in the UA pattern match, since it's
more correct than returning an array with the match.
fix(browser-support): Add audio track to pc always on mobile Safari.
On mobile Safari, if a user joins audio and video muted, the browser doesn't decode the incoming audio. Workaround is to always add the audio track to pc and mute it if needed.
fix(codec-selection): Fix VP9 codec switching issue in Chrome unified-plan.
Munge only the m-line that corresponds to the source that the browser will be sending.
Do not select VP9 on Firefox.
Detect support for RTCRtpTransceiver#setCodecPreferences correctly.
fix(CodecSelection): Call RTCRtpTransceiver#setCodecPreferences before renegotiation.
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.
fix(codec-selection): Fix codec selection for unified plan browsers.
Make sure the codec order is munged on all the m-lines for unified plan clients. Implement the logic for setting the preferences through RTCRtpTransceiver#setCodecPreferences.
feat(stats): Get audio levels for the top 5 speakers only.
Capture the audio levels only for the top 5 speakers as RTCRtpReceiver#getSynchronizationSources can be expensive when we have too many audio receivers in the call.
Also, capture the audio levels for track that are unmuted if RTCRtpReceiver#getSynchronizationSources is not supported.
Switch Safari to using getStats since its reporting errorneous values, i.e., 0.000001 as audio level for all remote audio tracks.
feat(browser-support): Add support for WKWebview based browsers.
Apple added getUserMedia support for WkWebview based browsers like chrome and Firefox on iOS 14.3. These browsers behave as Safari does on iOS. Therefore, extend the Safari checks to these webkit based browsers as well.
Since we use transferable streams to transfer the streams to the worker
we need to feature detect them as Chrome 86 will launch Insertable Streams
by default without shipping transferable streams yet (status still unclear,
it might still ship too)
See here for the feature detection used:
https://groups.google.com/a/chromium.org/g/blink-dev/c/1LStSgBt6AM/m/hj0odB8pCAAJ
Add a performance stat around long tasks. Chrome supports PerformanceObserver API that lets us
register for long tasks event. Any task that takes longer than 50ms is considered a long task.
feat: use getSynchronizationSources on the receiver for remote audio levels (#1245)
* feat: use getSynchronizationSources on the receiver for remote audio levels
Use getSynchronizationSources if it is supported, fallback to using getStats otherwise.
* feat/ref: Use the local audio levels from LocalStatsCollector
When using getSynchronizationSources, use the audio levels from LocalStatsCollector for NoAudioSignalDetection.js
Remove obsolete code - TalkMutedDetection feature using audio levels is not used anymore
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.
fix(screenshare): defensively check for getDisplayMedia (#879)
jitsi-meet-spot currently supports mobile browsers. A
line should be drawn somewhere but maybe not here.
Chrome iOS does not have navigator.mediaDevices so add
a truthy check before checking for getDisplayMedia.