Judge matchers must not block the vitest worker - #196
Merged
Conversation
toSatisfyCriterion and toScoreAtLeast ran the in-sandbox judge with spawnSync, freezing the worker's event loop for the length of a model run. The worker answers the main process over an RPC channel whose per-call timeout is birpc's default 60 seconds, hardcoded — no vitest option or env var reaches it. Any judge slower than that left an in-flight call like onTaskUpdate unanswered, and when the loop finally unblocked, the expired timer fired first: an unhandled "[vitest-worker]: Timeout calling" error and a non-zero exit for a file whose every assertion had passed. A green eval recorded as red, more often the slower the judge model, and invisible on genuinely failing runs since those were already red. The judge now runs via async spawn and the matchers are async, so the loop keeps servicing the RPC channel however long the judge takes; the sandbox timeout remains the real bound. Judge calls must be awaited, which every published example already shows — the await is load-bearing now, since vitest does not track a custom matcher's promise and an un-awaited call floats free of its test. toContainText is deterministic and stays sync. Verified three ways: unit tests with a fake runner, including an event-loop liveness test that fails against the old implementation; and a 70-second judge under vitest 3 in the harness's generated-config shape, where the old helper exits 1 with the RPC timeout despite its test passing and the new one exits 0.
gaojude
marked this pull request as ready for review
August 25, 2026 15:58
devjiwonchoi
approved these changes
Aug 25, 2026
Merged
gaojude
added a commit
to vercel/next-evals-oss
that referenced
this pull request
Aug 25, 2026
Picks up the async judge matchers (vercel-labs/agent-eval#196) and the vitest reinstall guard (vercel-labs/agent-eval#195), moving the harness onto the 2.x line. Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
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
2 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.
A judge run slower than 60 seconds made vitest fail the file even when every assertion passed — the worker's RPC heartbeat shares the event loop the sync matchers were blocking, and its timeout is hardcoded. The matchers now run the judge async, so the eval's own duration no longer decides its result.