docs: Document custom app harnesses#50
Merged
Merged
Conversation
Add a custom application harness recipe that shows the existing harness-first run and prompt contract for LLM-backed judges. Clarify when scenario-owned rubric criteria should live on inputValue instead of per-run metadata. Fixes GH-48 Co-Authored-By: OpenAI Codex <codex@openai.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Document the custom app harness path for eval authors who are not using first-party runtime adapters. The package README now shows an app/integration harness that returns a normalized HarnessRun, exposes harness.prompt, and scores with a judge that calls ctx.harness.prompt.
Criteria Location
Clarify that scenario-owned rubric criteria belong on inputValue, while metadata is for per-run expectations or harness configuration outside the scenario payload. The same guidance now appears in the package README, root README, custom judge docs, and JudgeContext doc comment.
Validated with
pnpm exec biome lint packages/vitest-evals/src/judges/types.ts,pnpm exec biome format packages/vitest-evals/src/judges/types.ts, andgit diff --check.Fixes GH-48