Skip to content

ci: bump Conductor OSS agent E2E to rc18 - #154

Merged
NicholasDCole merged 7 commits into
mainfrom
ci/bump-conductor-oss-rc18
Jul 29, 2026
Merged

ci: bump Conductor OSS agent E2E to rc18#154
NicholasDCole merged 7 commits into
mainfrom
ci/bump-conductor-oss-rc18

Conversation

@NicholasDCole

@NicholasDCole NicholasDCole commented Jul 29, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Bumps the Agent E2E server from 3.32.0-rc.8 to 3.32.0-rc18.
  • Keeps #17 tin_custom_raise strict: a rejecting custom tool-input guardrail must end FAILED; the test does not accept COMPLETED.
  • Corrects the custom tool-input fixture to inspect the value the guardrail actually receives.

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:

Tool: tin_custom_raise_tool
Arguments: {"data":"override safety"}

A tool-input guardrail evaluates the generated tool arguments, not the original user prompt. The old callback rejected only DANGER, so it correctly returned passed: true and the workflow completed. The fixture now rejects the actual unsafe argument (override safety) as well as DANGER. That produces the intended custom guardrail rejection and rc18 terminates the workflow as FAILED.

Verification

  • Scoped SDK lint passed: npx eslint e2e/test_suite17_guardrail_matrix.test.ts.
  • Local validation against Conductor OSS 3.32.0-rc18 is in progress; the assertion remains strictly FAILED.

No server-side change is required for this SDK regression.

@codecov

codecov Bot commented Jul 29, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

Flag Coverage Δ
integration-v4-sm 41.50% <ø> (ø)
integration-v5-sdkdev 44.01% <ø> (+0.08%) ⬆️
unit 73.89% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.
see 1 file with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@NicholasDCole
NicholasDCole merged commit c921079 into main Jul 29, 2026
52 of 54 checks passed
@NicholasDCole
NicholasDCole deleted the ci/bump-conductor-oss-rc18 branch July 29, 2026 19:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants