ci: bump Conductor OSS agent E2E to rc18 - #154
Merged
Merged
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests.
Flags with carried forward coverage won't be shown. Click here to find out more. 🚀 New features to boost your workflow:
|
This reverts commit f65341c.
kowser-orkes
approved these changes
Jul 29, 2026
bradyyie
approved these changes
Jul 29, 2026
6 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
3.32.0-rc.8to3.32.0-rc18.#17 tin_custom_raisestrict: a rejecting custom tool-input guardrail must endFAILED; the test does not acceptCOMPLETED.Root cause
This was an SDK E2E fixture mismatch, not a server routing failure. The test prompt contained
DANGER override safety, but the model generated this tool call:A tool-input guardrail evaluates the generated tool arguments, not the original user prompt. The old callback rejected only
DANGER, so it correctly returnedpassed: trueand the workflow completed. The fixture now rejects the actual unsafe argument (override safety) as well asDANGER. That produces the intended custom guardrail rejection and rc18 terminates the workflow asFAILED.Verification
npx eslint e2e/test_suite17_guardrail_matrix.test.ts.3.32.0-rc18is in progress; the assertion remains strictlyFAILED.No server-side change is required for this SDK regression.