Add 'replaceTrack' method to API, make all replace track operations local (use same ssrcs so no need for source-add/source-remove)

* M1: device change now uses new flow.  fundamentally "works" but may be corner cases/side effects to other flows. haven't touched ffox yet

* M1a: fixed a bug where the ssrc info of the new stream wasn't being set correctly, causing problems with video mute/unmute

* M1b: fix firefox.  changing camera, video mute/unmute looks good

* M1c: 'replaceStream' processing is not integrated with the same queue as all of the other o/a-related events.

* fix typo, some deprecated code cleanup

* move the rfc4145 fix to traceablepeerconnection::createanswer so both the new and old o/a flows leverage it.  also cleanup some now-unused code and change more functions to arrow functions so we can get rid of 'var self = this' workarounds.

* get rid of separately-mainted local description in JingleSessionPC.  keep TraceablePeerConnection as the source of truth for the local sdp and have JingleSessionPC retrieve it from there.

* change the code in the old modifySources shim to use the _renegotiate method so both old and new flows use that method.

* split out the remote change processing from the local change processing to better set us up for individual remote and local modification queues

* move the setOfferCycle flow off of the old shim and into the new flow.  also removes the new for this this.jingleOfferIq member

* move addRemoteStream (nee addSource) to the new flow.  gets rid of the need for the this.addssrc member.

* move remove remote stream over to the new flow.  gets rid of the need for the this.removessrc member variable

* temporary '_processRemoteChange' method is no longer needed, as all remote changes are processed directly (rather than setting member variables and calling a catch-all method which checks each member to see what needs to be done)

* M2: add 'sdp-consistency' in an attempt to separate out the restoration of the same ssrcs (also requires the changes i've made to sdp-simulcast, currently in my brian/rework branch @90aceaddb1eec4d15026efac82c140579c7af2b3, as well as a commit in jitsi-meet to change the toggle-screenshare flows over to use the new 'replace' chain).  as of this point video mute, change device and toggle screenshare all happen as local operatons.  there is a bug when starting as video muted i need to look into, and i haven't checked firefox yet.

* fix the bug with start-as-video-muted (relies on commit f1d8d3c831 in brian/overual sdp-simulcast branch)

* some code cleanup, marked some TODO list items.  got addStream off of the old shim and onto the new flow

* change removeStream over to the new flow and off of the shim.  shim is now removed!

* fix a bug when muting a stream.  remove some logic from addstream/removestream that i don't think makes sense, and move the source-remove parsing logic into a helper

* move the source-add/source-remove processing into the atomic queued operation since it looks at sdp.

* remove unused code used for old ssrc replacement logic

* get rid of the need for TraceablePeerConnection::addStreamNoSideEffects

* get rid of need for TraceablePeerConnection::removeStreamNoSideEffects

* distinguish XXXStream and XXXStreamToPeerConnection (was XXXStreamNoSideEffects)

* remove shim methods for add/removeRemoteStream

* fix a bug when adding local media for the first time

* replace the old 'dispose' method with the new one

* address feedback comments.  update version of sdp-simulcast.

* update sdp-simulcast version

* add missing semicolons

* move sdpconsistency to es6 style

* restore JitsiConference::removeTrack, restore JitsiLocalTrack::dispose back to how it was (doing o/a if necessary)--we get around this on replace by not disposing the track until after we do the replace)

* change removeTrack and addTrack to leverage replaceStream

* fix removeTrack to return the promise, handle an already-disposed track

* add more documentation

* remove unnecessary semicolon

* update sdp-simulcast version

* address PR feedback

* remove usage of @type in method js docs

* address (more) pr feedback.  upgrades to a new sdp-simulcast version which fixes an issue in smoke tests

* more PR feedback, and clean up the success/error handling done for the work functions.

* tweak the error propagation

Fixes calling of leave in kick.

Introduce JingleSessionState constants. Make the invalid JingleSession
rejection an explicit action taken by the JitsiConference.

Our JSHint configuration is not extensive and we have excluded multiple
files from linting. Additionally, we have seen JSHint to be unable to
parse newer ECMAScript features such as the object spread operator
(proposal).

On the other hand, we have seen ESLint to beautifully work on React and
React Native source code in addition to ES2015 and later. Introduce
ESLint alongside JSHint as an intermediate step to eventually switching
from JSHint to ESLint.

As our source code does not fully follow even the JSHint rules we have,
it is very difficult to introduce ESLint with many rules. At the
beginning, introduce it with as little rules as possible. Morever,
ESLint is able to automatically fix certain rule offenders so once we
have ESLint merged we can incrementally add new rules while keeping our
commits' modification on as little subjects as possible.

JitsiConference passed in the constructor and adding all events happen inside the feature.

By default talk while muted detection is disabled.

The timeout will be configurable though
'peerDisconnectedThroughRtcTimeout' conference config option. It has
not been document in the public API on purpose.

The event is triggered when the notification about the user's connection
status change arrives from the JVB.

This currently fixes problem for participants joining in a room with other participants and trying to send initial value of selected local participant will throw an error. And fixes a potential problem if the UI can select participants before their video is available, before session initiated, can make local state with jvb inconsistent. Also if we want to have multiple selected endpoints or pinned participants and this is done before session-initiate caching should be done before creating data channel (currently selecting multiple is not possible).

Use 'sendToAll' for 'session.restart' and 'session.terminate' events.

Not doing so will cause issues when trying to mute after
'session-terminate', because the PeerConnection is closed and should not
be used anymore.

When call ends the PeerConnection is closed and the SSRCs stored in
the local track will not match those assigned the PeerConnection when
it's reopened for new session. This will confuse SSRC replacement logic.
We need to reset those SSRCs and re-register 'ssrcHandler' listener to
get the new ones.

The event is triggered when Jicofo sends 'session-terminate' and our
PeerConnection is closed.