KEP-3562: [OptimizationJob] Add End-to-End (E2E) integration tests for OptimizationJob workflow
- Dominant language
- Go
- Stars
- 2.2k
- Forks
- 1.1k
- Avg merge
- 3d 22h
- Merged PRs (30d)
- 39
Description
### What you would like to be added?
Context:
Unit and webhook tests cover static validation and defaulting in [KEP-3562](https://github.com/kubeflow/trainer/pull/3565).
Problem:
We need real cluster tests to verify the interactions between the `OptimizationJob` controller, mutating/validating webhooks, the gRPC Optuna container, and the underlying `TrainJob` instances.
Future Goals:
- Add E2E test suites
- Validate complete job execution cycles: creation -> trial generation -> metric evaluation -> job completion.
- Test failure scenarios (e.g., failing trial recovery, gRPC timeout handling).
Relates to KEP-3562 Master Tracking [Issue](https://github.com/kubeflow/trainer/issues/3562).
### Why is this needed?
E2E tests catch integration bugs in CI/CD pipelines before code is merged, ensuring long-term stability of the OptimizationJob controller.
### Love this feature?
Give it a 👍 We prioritize the features with most 👍
Contributor guide
Assessment
This issue has not been assessed yet.