Dropped the auto-incrementing id from the SnodeReceivedMessageInfo
Changed the 'key, hash' from a uniqueKey to a primaryKey to allow "upsert" behaviours to work
Added inline errors & warnings (regex could use some work to remove invalid cases)
Added a build step to validate the strings are included in the app and it's extensions
Fixed an issue where tapping a remote notification wasn't opening the conversation
Fixed an issue where the Share Extension could fail due to not having a snode pool loaded
Fixed an issue where the Theme may not be applied at the right time in the Share extension
Sorted out some more threading issues
Removed a redundant SyncPushTokensJob run
Fixed an issue where the NotificationServiceExtension could incorrectly setup the database before setting up it's context
Fixed a few warnings
Removed a bunch of legacy code
Refactored the MainAppContext from Objective C into Swift
Removed the YapDatabase CocoaPod
Removed logic to migrate from YapDatabase to GRDB
Removed the logic to check for legacy config messages during onboarding
Added a database error for when a migration is no longer supported
Cleaned up the Dependencies so that tests can run synchronously without having to custom set queues as much
Sorted out the crypto and network dependencies to avoid needing weird dependency inheritance
Fixed the flaky tests so they are no longer flaky
Fixed some unexpected JobRunner behaviours
Updated the CI config to use a local build directory for derivedData (now works with build tweaks)
Added the XCBeautify pod (so the CI doesn't need to separately install something)
Updated the CI build script to use XCBeautify
Fixed some broken unit tests
Added code to throttle the 'markAsRead' logic when scrolling to 100ms
Added a launch counter so we will always get error logs on launch if the database is suspended
Updated the logging to also indicate whether it's the DBWrite queue
Moved a couple of Atomic mutations outside of DB write closure on the off chance they are blocking
Removed the 'readPublisherFlatMap/writePublisherFlatMap' functions as they easily resulted in behaviours which held up database threads
Tweaked the logic around starting the open group pollers to avoid an unlikely atomic lock blocks
Updated some logic to avoid accessing database read threads for longer than needed
Updated the OpenGroupManager to only update the 'seqNo' value for valid messages
Cleaned up some double Atomic wrapped instances which had some weird access behaviours
Fixed an issue where a database read thread could have been started within a database write thread
Fixed an issue where the ReplaySubject might not emit values in some cases
Fixed a busted version comparison
Fixed an issue where the config dump population wasn't setting the 'created' timestamp for contacts
Fixed an issue where the 'SyncPushTokensJob' could run logic on the wrong thread
Fixed a bug where the 'scroll to bottom' button wouldn't initial be visible in some cases
Fixed a bug where the 'scroll to bottom' button would fade out when there were subsequent pages
Fixed a bug where an open group image might not get downloaded in some cases
Fixed an issue where we would incorrectly append a wildcard character to the end of a search term that ended in a quotation mark
Finished refactoring the OpenGroupAPI to use PreparedSendData
Added copy for an unrecoverable startup case
Added some additional logs to better debug ValueObservation query errors
Increased the pageSize to 20 on iPad devices (to prevent it immediately loading a second page)
Cleaned up a bunch of threading logic (try to avoid overriding subscribe/receive threads specified at subscription)
Consolidated the 'sendMessage' and 'sendAttachments' functions
Updated the various frameworks to use 'DAWRF with DSYM' to allow for better debugging during debug mode (at the cost of a longer build time)
Updated the logic to optimistically insert messages when sending to avoid any database write delays
Updated the logic to avoid sending notifications for messages which are already marked as read by the config
Fixed an issue where multiple paths could incorrectly get built at the same time in some cases
Fixed an issue where other job queues could be started before the blockingQueue finishes
Fixed a potential bug with the snode version comparison (was just a string comparison which would fail when getting to double-digit values)
Fixed a bug where you couldn't remove the last reaction on a message
Fixed the broken media message zoom animations
Fixed a bug where the last message read in a conversation wouldn't be correctly detected as already read
Fixed a bug where the QuoteView had no line limits (resulting in the '@You' mention background highlight being incorrectly positioned in the quote preview)
Fixed a bug where a large number of configSyncJobs could be scheduled (only one would run at a time but this could result in performance impacts)
Added an 'all' namespace to make the "delete from all" behaviour more explicit
Defaulted the ConfigDump 'timestampMs' database column to 0
Updated the 'conversationInConfig' logic to support the note to self conversation
Forced the user config feature to be on (for testing)
Fixed a bug where triggering the 'Delete for everyone' functionality would incorrectly try to delete from the recipient swarm (not possible)
Fixed a bug where the 'profileNamePublisher' could only be set once resulting in potential issues if you try to restore different accounts within the same session
Re-added the limit to the number of reactions to display before collapsing to make it consistent with the designs and other platforms
Updated the SnodeAPI to ensure that when it retries it will actually select a new snode
Added some more logs to libSession build script and tweaked the stdout location
Added shadow threads to the GarbageCollectionJob
Changed the seed node retries to 2 because it's likely we will swap to another seed node pretty quickly which could resolve the issue
Fixed a bug where the user could get kicked from a draft conversation if they get a contacts update before sending a message
Fixed a bug where message status or media message download statuses would trigger the conversation to jump to the bottom
Updated to the latest libSession version
Updated the 'hidden' logic to be based on a negative 'priority' value
Added an index on the Quote table to speed up conversation query
Fixed an odd behaviour with GRDB and Combine (simplified the interface as well)
Fixed an issue where migrations could fail
Morgan Pretty
Ryan ZHAO
ryanzhao