feat(verify): honour a disabled tester role so the LLM tester is no longer the fallback for a failed verification (AGT-4679) - #820
Merged
Conversation
…onger the fallback for a failed verification (AGT-4679)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
runTesterWithVerificationtakesllmFallback. Withfalse, a deterministic infrastructure failure is rethrown (the attempt ends asinfra_error) and a repository with no deterministic command gets a passing result that says nothing was verified. The LLM tester is never asked.PairPipeline.runTesterpassesllmFallback: roles.tester.enabled !== false, so only an explicitenabled: falseturns it off. Default behaviour is unchanged.LLM tester is disabled, no verdictinstead offalling back to LLM testerin that case.Why
tester.enabled: falsewas already configured, but every verification that hit the 300 s pytest cap still fell back to the LLM tester (tester stages of 764 s and 814 s observed). The disabled role was not honoured.Tests
deterministicTester.test.ts: no command +llmFallback: falsereturns the unverified result and never calls the fallback; the default still calls it.pairPipeline.verify.test.ts: infra failure with the tester role disabled ends asinfra_errorwithoutrunTester; no command with the role disabled passes withoutrunTester.