Fix flaky tests in resource-constrained CI environments#130
Fix flaky tests in resource-constrained CI environments#130Copilot wants to merge 2 commits intobugfix/flakey-testsfrom
Conversation
|
|
1 similar comment
|
|
- Add small delay after unsubscribe operations to allow processing - Add delays in test initialization and cleanup to prevent interference - Helps tests pass reliably in resource-bound CI environments Co-authored-by: niemyjski <1020579+niemyjski@users.noreply.github.com>
|
Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details. Warning Firewall rules blocked me from connecting to one or more addresses (expand for details)I tried to connect to the following addresses, but was blocked by firewall rules:
If you need me to access, download, or install something from one of these locations, you can either:
|
Tests pass locally but fail intermittently in CI due to resource contention during Redis pub/sub operations and rapid test execution.
Changes
FireAndForgetunsubscribe operations inRedisMessageBusandRedisQueueto allow completion before disposalFlushAll) and teardown to prevent state interference between testsContext
Resource-bound CI runners execute pub/sub operations slower than local environments. Without processing time, unsubscribe operations initiated with
FireAndForgetdon't complete before the next test starts, causing:Strategic delays (70ms overhead per test) allow async operations to settle without impacting local development velocity.
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.