Moved the WebRTC dependency out of SessionMessagingKit and into the main Session app (it's the only one that used it and it was causing library linker issues in the share extension because it wasn't directly linked)
• Fixed an issue where you could select 0 attachments and go to the "send attachment" screen
• Fixed an issue where returning from the "send attachment" screen wouldn't have the initially selected attachment selected
• Added a uniqueId to the DataSource so instances can be better distinguished from each other (not ideal as the same file would have separate identifiers)
• Fixed some cases where errors weren't being displayed correctly
• Tweaked the "nodeNotFound" error to be a bit more human readable
• Tweaked the BackgroundPoller timeout to have a 5 second buffer instead of a 1 second buffer
• Moved the lastHash pruning into the GarbageCollectionJob instead of the pre-poll fetching to avoid needing to use a write query before polling
• Reworked the Pollers to make their database queries part of the polling stream (and as such, cancellable)
• Fixed an issue where the conversation 'created' timestamp wasn't correctly getting set when creating a group
• Fixed an issue where sending a message to 'Note to Self' may not show the conversation in the conversation list
• Fixed an issue where sharing a message with an attachment might not include the attachment
• Fixed an issue where list paging wouldn't work in some cases after values were inserted into the database after the currently loaded pages
• Added some handling for invalid 'joinedAt' values for groups (seems like we can have an incorrect resolution)
• Fixed an issue where the BackgroundPoller would fail if a single destination failed
- This would suspend the network, then the other pending requests would error and automatically retry, attempting to create a new connection which could loop a number of times rapidly since the network was suspended
• Fixed an issue where the BackgroundPoller could incorrectly try to write to the database after it had been suspended
• Updated the pollers to NOT take the duration of the previous poll into account when scheduling the next poll
• Updated to the latest `libSession` version (a few optimisations/fixes)
• Fixed a minor layout issue with the attribution label on the Path screen
• Updated the GeoLite2 country database data, added some basic localisation to it
• Managed to optimise the size of the GeoLite2 data bundled with the app (10mb -> 8mb)
• Cleaned up the IP2Country logic a little
• Removed some pluralisation from logs (want the logs to be identical outside of numbers)
• Tweaked the PushRegistrationManager to actually timeout
• Tweaked the message request notification behaviour
• Fixed an issue where duplicate message errors would result in the generic notification being shown
• Further notification logging improvements
• Fixed an issue where the notification extension could end up in an invalid state if you delete and create a new account in rapid succession
• Fixed an issue where notification processing errors weren't getting handled correctly resulting in the notification extension timing out
• Stopped the notification extension from trying to download profile images
• Added commit hash to version info
• Tweaked the notification extension logic flow to be more straight forward
• Updated the code to stop sending legacy PNs outside of legacy group conversations
• Updated the logger logic to clean things up and use the local date/time (with time zone info) to ease debugging user reports
• Fixed an issue where messages in a community could incorrectly accept disappearing message settings
• Fixed an issue where duplicate messages could be sent in some cases
• Fixed an issue where the conversation might not scroll to the bottom after sending an attachment
• Fixed an issue where attachment encryption was happening in a db write thread
• Fixed a bug where a disappearing voice message wouldn't stop playing
• Fixed a bug where the conversation screen was never freed from memory
• Fixed an issue with an earlier change where the openGroupManager cache would access itself while modifying itself causing a crash
• Fixed an index out of bounds issue with the mnemonic
• Attempt to fix a crash due to failing to hash SignalAttachment
• Attempt to fix a crash due to list data change inconsistencies
• Ensuring we are shutting down the network when resetting app data
• Updated the broken unit tests
• Fixed an issue where SOGS pollers could be started multiple times
• Avoid checking if blinded conversations exist in the config (will always return false)
• Updated some logs to provide more timing information
• Reworked some of the C API conversions to try to prevent invalid cases
• Tweaked the threading around libSession networking callbacks to minimise Swift code blocking libSession threads
• More logging tweaks
• Fixed an issue where voice messages wouldn't stop playing when deleting a message or leaving a conversation
• Fixed an issue where the notification extension was handling errors and finishing while within a database transaction
• Fixed an issue where the ShareExtension may not have been able to send LinkPreviews
• Fixed an issue where displaying or logging the paths weren't maintaining the correct order
• Tweaked some of the logging behaviours
• Fixed a bad memory crash which could occur when returning from the background
• Fixed an issue where config messages were incorrectly getting double wrapped in protobuf wrappers
• Removed the 'runOnceTransient' behaviour (no longer have jobs that run before the user exists)
• Removed the session id from the message snippet in the conversation list
• Fixed an issue where the SyncPushTokensJob might not run because the paths hadn't been built yet
• Moved the snode cache and path building into libSession (deleted associated logic)
• Moved reachability detection into libSession (remove Reachability dependency)
• Fixed a couple of crashes with using libQuic requests
• Fixed a bug where the MessageRequestFooterView would show buttons on outgoing message requests
• Fixed an issue where the message status wouldn't update to the failed state if the MessageSendJob timed-out
• Fixed an issue where network issues could result in a backlog of TypingIndicator messages that failed to send (don't bother retrying them)
• Fixed an issue where concurrent jobs might not retry correctly if other jobs don't complete or the retry was triggered from the wrong queue
• Fixed an issue where the input view could disappear in some cases
• Reworked the keyboard avoidance in ConversationVC to fix some bugs and simplify the behaviour
• Moved the message request footer UI into it's own view
• Fixed an issue where paths wouldn't get built for a new isntall
• Fixed an issue where a couple of LibSession+Networking errors weren't getting logged correctly
• Fixed a log that could be thrown incorrect for a unique constraint failure
• Fixed an annoying startup warning due to thread priorities
• Moved the 'getSwarm' behaviour into a distinct job to prevent duplicate API calls
• Updated to the latest libSession (fix libQuic crash)
• Updated the JobRunner to support the `runOnceTransient` behaviour and be able to run transient jobs in the app extensions
• Reworked the extension file logging to be written directly to the file in a single operation rather than line-by-line via the logger
• Fixed a bug where community invites has the wrong author
• Fixed a bug where the title on the disappearing messages settings screen was clipping vertically
• Fixed a bug where tapping on the disappearing messages setting subtitle could incorrectly appear in read-only state for admins
• Fixed a log which contained notification content
• Tweaks to extension logging logic
• Fixed an issue where the DisappearingMessagesJob was getting run for every individual message process instead of just once after processing all messages from a poll
• Tweaked the polling logic to split the user, groups and community pollers into separate queues
• Tweaked the logic to restart the open group poller immediately after joining a community (to avoid an edge-case where there could be a long delay before the initial poll is made)
• Tweaked the logic for checking if PNs are susceptible to failure to only dispatch to the main thread once
• Cleaned up some warnings
• Updated the app versioning to be at the project level instead of target level
• Added the ability to define a unique hash for a job for deduplication