feat: add Vitest workspace verifier adapter#1480
Merged
Merged
Conversation
Deploying agentv with
|
| Latest commit: |
23ce574
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://25f57dd0.agentv.pages.dev |
| Branch Preview URL: | https://feat-sdk-deterministic-grade.agentv.pages.dev |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
AgentV deterministic workspace graders can now use normal Vitest verifier files and have each
it(...)outcome mapped into AgentVcode-graderassertions. The common path no longer needs a per-evalverify-*.mjsordefineVitestWorkspaceGrader()wrapper: eval YAML can call AgentV's built-in adapter directly withagentv eval vitest <verifier.test.ts>.This keeps framework-specific behavior out of core evaluator types while moving the stdin/stdout, workspace path, Vitest JSON reporter, score aggregation, and hidden-verifier copy/cleanup plumbing into AgentV-owned adapter glue.
What Changed
runVitestWorkspaceGrader(),defineVitestWorkspaceGrader(), andvitestReportToCodeGraderResult().agentv eval vitestas a code-grader protocol adapter for plain Vitest verifier files.examples/features/vitest-workspace-grader/so the only grader file isgraders/welcome-banner.test.ts; the eval calls the built-in adapter directly.Verification
bun --filter @agentv/sdk testbun --filter @agentv/sdk typecheckbun --filter @agentv/sdk lintbun --filter @agentv/sdk buildbun --filter agentv testbun --filter agentv typecheckbun --filter agentv lintbun --filter agentv buildbun run buildbun run validate:examplesbun apps/cli/src/cli.ts eval examples/features/vitest-workspace-grader/evals/dataset.eval.yaml --target mock_agentpasses at 100%; JSONL shows 4 Vitest tests mapped to 4 AgentV assertions.Tracker
Related: EntityProcess/agentv-beads#11. Beads worktree redirect was repaired separately; notes were pushed for
av-bv4.16,av-bv4.17, andav-bv4.19.av-bv4.18remains the dogfood follow-up for moving the next-evals welcome-banner case to the built-in Vitest path once this AgentV branch is merged/released or otherwise available to that repo.