This adds the ability to configure hiding the logo on the deep linking page.
HIDE_DEEP_LINKING_LOGO defaults to false in the config.
The implementation also defaults to showing the logo if HIDE_DEEP_LINKING_LOGO
is missing from the config.

Add a config option with the default value of 2, which will cap the max recv video quality to SD if there's more than 2 participants in the conference while in the tile view mode.

Adds 'lastNLimits' config value which allows to define last N value per number of participants.
See config.js for more details.

* Adding responsive to jitsi logo, buttons and hiding some part of the interface
* moving media types thresholds to variables and apply only to screen
* hide chrome extension banner on very small view
* Hide filmstrip only on desktop narrow windows

Display name for lobby operations notifications are taken from the list of knocking participants which is available only to moderators. In case of not all moderators the notifications were broken.

call TOGGLE_CHAT action when chat modal is closed to correctly update chat isOpen state

Must match the lib-jitsi-meet counterpart.

Fixes: https://github.com/jitsi/jitsi-meet/issues/7384

* feat(blur): terminate blur web worker when disabled

Fixes: https://github.com/jitsi/jitsi-meet/issues/7373

Use the same moderator semantics when adding items into the remote video menu as when showing/hiding the items themselves.

This way autocomplete and keyboards work correctly.

* Update JitsiStreamPresenterEffect.js
Create/terminate the Web Worker on effect start/stop so that we don't leak them.

Fixes crash on mobile due to chained imports.

Despite running Android 8.1, they don't support Picture-in-Picture.

Makes the tiles consistent as the participant view is equally sized and the
avatar is always centered in the tile.

Signed-off-by: Michael Telatynski <7t3chguy@gmail.com>

Moves the logic from all different places into single state
listener to combine all inputs into a single output.

Adds an extra 'options' argument to the register method which
allows to use deep equality instead of a shallow one when comparing
the current and the previous selections.

* Integrate rtcstats

* expcetion handling / clean up

* order imports

* config fix

* remove mock amplitude handler

* additional comments

* lint fix

* address code review

* move rtcstats middleware

* link to jitsi rtcstats package

* address code review

* address code review / add ws onclose handler

* add display name / bump rtcstats version

* resolve import error

Part of [1] replaces a `setPreferredVideoQuality` call with a
`setMaxReceiverVideoQuality` call. The change was part of a bigger
changeset that adds logic that tries to adjust the max based on reduced
ui turned on or off and allow to set prefered through the config.

However, by calling `setMaxReceiverVideoQuality` instead of
`setPreferredVideoQuality`, the new feature overrides the lower
resolution requested by tile-view earlier in some occasions.

This PR reverts back to using `setPreferredVideoQuality` instead of
`setMaxReceiverVideoQuality` as this achieves the same result without
overwriting the max set by the tile-view.

NOTE that this is a quick-fix and all the handling related to setting
the receive resolution will be reworked soon.

[1]: 7d513738d2

Showing the modal earlier is weird because it will be closed as soon as we
connect. Also, we don't know if we are going to be alone until we join.