UPSTREAM: <carry>: Fix flags passed to test-experimental-e2e#723
UPSTREAM: <carry>: Fix flags passed to test-experimental-e2e#723tmshort wants to merge 3 commits into
Conversation
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughMakefile edits in ChangesOpenshift Makefile — E2E targets
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes 🚥 Pre-merge checks | ✅ 12✅ Passed checks (12 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Comment |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: tmshort The full list of commands accepted by this bot can be found here. The pull request process is described here DetailsNeeds approval from an approver in each of these files:
Approvers can indicate their approval by writing |
|
/test openshift-e2e-aws-techpreview |
0c7d0b1 to
7aa1838
Compare
|
/test openshift-e2e-aws-techpreview |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@openshift/Makefile`:
- Around line 47-48: Replace the short-circuit in the Makefile target
test-experimental-e2e (remove the "/bin/true" line) and restore the real
command(s) that run the experimental e2e suite so the target actually executes
tests; ensure the restored command invokes the same test runner used elsewhere
(e.g., the existing e2e script or binary) and passes the corrected flags/ENV
used for experimental runs so CI executes the suite instead of always
succeeding.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository: openshift/coderabbit/.coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: c1ad50ea-2428-4502-86f2-c79d425a54c2
📒 Files selected for processing (1)
openshift/Makefile
| test-experimental-e2e: ## Run the experimental e2e tests. | ||
| $(DIR)/operator-controller/build-test-registry.sh $(E2E_REGISTRY_NAMESPACE) $(E2E_REGISTRY_NAME) | ||
| cd $(DIR)/../; \ | ||
| go test $(DOWNSTREAM_EXPERIMENTAL_E2E_FLAGS) ./test/experimental-e2e/...; | ||
| /bin/true # keep - because it's triggered, but always succeed |
There was a problem hiding this comment.
Restore real test execution in test-experimental-e2e
Line 48 makes this target always pass, which bypasses experimental e2e coverage and can mask regressions in CI. If the goal is to fix flags, this should still run the suite with corrected flags instead of short-circuiting.
Suggested fix
.PHONY: test-experimental-e2e
test-experimental-e2e: ## Run the experimental e2e tests.
- /bin/true # keep - because it's triggered, but always succeed
+ $(DIR)/operator-controller/build-test-registry.sh $(E2E_REGISTRY_NAMESPACE) $(E2E_REGISTRY_NAME)
+ cd $(DIR)/../; \
+ go test $(DOWNSTREAM_E2E_FLAGS) ./test/experimental-e2e/... --k8s.cli=oc🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@openshift/Makefile` around lines 47 - 48, Replace the short-circuit in the
Makefile target test-experimental-e2e (remove the "/bin/true" line) and restore
the real command(s) that run the experimental e2e suite so the target actually
executes tests; ensure the restored command invokes the same test runner used
elsewhere (e.g., the existing e2e script or binary) and passes the corrected
flags/ENV used for experimental runs so CI executes the suite instead of always
succeeding.
There was a problem hiding this comment.
This is intentional. The experimental e2e test now looks at the deployments featuregates to determine which features to test. So, having a separate test for experimental is redundant. It will eventually be removed, but right now it's still invoked, and if it were removed, it would cause the CI to fail.
There was a problem hiding this comment.
@tmshort, thanks for the context — that makes sense. Since the experimental e2e functionality has been folded into the regular e2e suite (driven by deployment feature gates), keeping this target as a no-op prevents CI failures while the trigger is still wired up. My concern no longer applies.
✏️ Learnings added
Learnt from: tmshort
Repo: openshift/operator-framework-operator-controller PR: 723
File: openshift/Makefile:47-48
Timestamp: 2026-05-11T18:39:21.641Z
Learning: In `openshift/Makefile`, the `test-experimental-e2e` target is intentionally set to `/bin/true` (always succeed). The experimental e2e tests now look at deployment feature gates to determine which features to test, making a separate experimental test target redundant. The target is kept as a no-op to avoid CI failures while the CI job still invokes it; it will be removed once CI stops triggering it.
Note: Learnings are effective only in the context of similar code segments. To apply general coding guidelines, please configure review instructions. You can manage existing learnings in the app.
7aa1838 to
d36da45
Compare
|
/test openshift-e2e-aws-techpreview |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@openshift/Makefile`:
- Around line 46-49: The Go test command in the Makefile uses the misspelled
flag "-tieout" which should be "-timeout"; update the invocation (the go test
line that includes $(DOWNSTREAM_E2E_FLAGS) and $(DOWNSTREAM_E2E_TIMEOUT)) to use
"-timeout=$(DOWNSTREAM_E2E_TIMEOUT)" so the Go test timeout is applied and the
make test-e2e target no longer fails due to an unknown flag.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository: openshift/coderabbit/.coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 83c75b64-475b-430d-885d-47b1d524fd27
📒 Files selected for processing (1)
openshift/Makefile
d36da45 to
c79c8d7
Compare
|
/test openshift-e2e-aws-techpreview |
c79c8d7 to
e073781
Compare
|
/test openshift-e2e-aws-techpreview |
e073781 to
2687456
Compare
|
/test openshift-e2e-aws-techpreview |
Signed-off-by: Todd Short <tshort@redhat.com>
2687456 to
f17a6e4
Compare
|
/test openshift-e2e-aws-techpreview |
Takes advantage of changes made to isolate test runs to execute as many tests in parallel as possible. For tests that must be run serially, the @serial tag has been added to the beginning of relevant feature file(s). Signed-off-by: Daniel Franz <dfranz@redhat.com> Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
|
@tmshort: The following tests failed, say
Full PR test history. Your PR dashboard. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
|
/test openshift-e2e-aws-techpreview |
Summary by CodeRabbit