fix(tests): reduce flakiness in guardrail redact output test #1505
+139
−6
Conversation
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
dbschmigelski
temporarily deployed
to
auto-approve
GitHub Actions
Inactive
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
- Add retry_on_flaky decorator to handle LLM non-determinism - Change response2 prompt from "Reply with only: OK" to a math question to prevent model from referencing blocked word from conversation history - Update system prompt to explicitly instruct not mentioning the word - Add tenacity dependency for retry functionality
dbschmigelski
force-pushed
the
tests/add-test-retry
branch
from
ba3ed97 to
57325c7
Compare
dbschmigelski
had a problem deploying
to
auto-approve
GitHub Actions
Failure
dbschmigelski
temporarily deployed
to
auto-approve
GitHub Actions
Inactive
pgrayy
reviewed
Jan 20, 2026
pgrayy
reviewed
Jan 20, 2026
dbschmigelski
temporarily deployed
to
auto-approve
GitHub Actions
Inactive
Unshure
previously approved these changes
Jan 20, 2026
pgrayy
previously approved these changes
Jan 20, 2026
dbschmigelski
temporarily deployed
to
auto-approve
GitHub Actions
Inactive
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Description
Our integ tests have been flaky for some time. This PR will improve robustness by introducing a retry annotation. We will sparingly use this. Another place we will is on certain integ tests where model providers have been flaky.
retry_on_flakydecorator to handle flaky integration tests caused by LLM non-determinismtest_guardrail_output_intervention_redact_outputwhich was failing ~90% of runs due to the model referencing "CACTUS" from conversation historyDocumentation PR
N/A
Type of Change
Bug fix
Testing
How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli
hatch run prepareChecklist
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.