This roll moves Juggler component registration to a new system that
is used in XPCOM: this is what both RemoteAgent and Marionette use.
Drive-by: we now have to explicitly pass default values to dispatched
mouse events to avoid a `MOZ_ASSERT` trigger inside a drag service
native code.
Manual conflict resolutions: ab3ed0cb2c
* nsIScreencastServiceClient is not thread safe refcounted so we make nsScreencastService::Session a thread safe refcounted object and keep it alive while there are inflight frames. Once such frames get handled on the main thread we check if the session has been stopped.
* Removed mCaptureCallbackCs in favor of atomic counter (mClient is not accessed only on the main thread).
* HeadlessWindowCapturer now holds RefPtr to the headless window object to avoid use after free when clearing it as a listener on the widget.
* ScreencastEncoder is not ref counted anymore.
Pretty-diff: 5f5042ff1e
* `clip` option is always passed from the client code
* with this change, we can no longer capture screenshot of a blinking
caret; the browser-side API doesn't have this capability.
In this case, there's no protocol version that we can extract for
nsIHttpChannel.
The code that does the redirect is here: 7f3d9fce41/docshell/base/nsDocShell.cpp (L6079-L6095)
To trigger this codepath, we'd need to run test inside a special
docker container that has https server running on the 443 port. We lack
infrastructure for this kind of tests (but it'll be cool to have it).
References #11118
When firefox is automated + interacted with manually, input composition
might get stolen from Text Input Processor.
Re-requiring TIP every time seems to fix this.
References #5460
Both `libyuv::I420Copy` and `libyuv::I420Scale` support image cropping
by offsetting coordinates inside planes, but offsets must be even
numbers.
References #7998
Notable changes:
- javaScriptEnabled moved to the browser side.
- enabling new UI since it no longer helps to fix screencast
Review branch: https://github.com/aslushnikov/juggler/tree/roll-to-91-0-b10
Note: this will have 2 screencast tests failing. Investigation is in a follow-up.
When Firefox decides to perform an http->https redirect based on HSTS
information, it issues an "internal" redirect and cancels the http request.
Since there is no response for the http request, we forge 307 redirect
in this case, following Chromium lead.
The relevant code is in nsHttpChannel::StartRedirectChannelToHttps.
