There were a few logs related to bad memory access within libSession and the `toLibSession` convention which we'd originally setup made me nervous as C-friendly objects would be allocated in Swift and then assigned to C struct properties but I'm not sure how the memory would actually behave in this case.
This updated approach unfortunately involves a bunch of duplicate code within 'TypeConversion+Utilities' (and some horrible type aliases for tuples) but as a result we now have compile-time safe 'get' and 'set' functions for any C struct which conforms to `CAccessible` and `CMutable`. The other nice benefit about this change is that the new `set` functions copy memory across into the C structs so we can have more confidence that the memory ownership has shifted to the libSession side of things.
• 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)
Properly fixed the busted migration issue
Updated to the latest version of Quick and Nimble (unit testing libraries)
Updated the tests based on the above
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)
Updated the JobRunner to support dependency injection
Updated the DataExtractionNotification to take a 'sentTimestamp' when created to reduce the chance for duplicates being sent
Fixed an issue where checking current and pending jobs wasn't including blocking jobs
Fixed an issue where the 'hasPendingOrRunningJob' check didn't actually include running jobs
Fixed some odd behaviours with job dependencies
Fixed an incorrect failure count check
Morgan Pretty