Repository navigation
feat(eval): add hashed result provenance records - #1834
Merged
Merged
Conversation
EmersonBraun
force-pushed
the
feat/eval-result-provenance
branch
from
October 8, 2026 06:33
151c17e to
7e9f42f
Compare
Contributor
Lighthouse
Run by |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add a generic result record at
@agentskit/eval/provenancewith suite, frozen case-set, subject revision/digest, runner version, and JSON metrics. Canonical serialization and SHA-256 support deterministic reruns and integrity verification; optional timestamps remain in the envelope but do not enter its content digest.Add precision/recall helpers with explicit zero-denominator behavior, consumer documentation, a versioned record specification, and a minor changeset. Update only eval's public API snapshot entry.
Evidence
pnpm exec turbo run build --filter=@agentskit/eval --concurrency=1: eval plus its two dependencies passed.pnpm --filter @agentskit/eval exec vitest run --coverage --maxWorkers=1: 115 tests passed; 96.95% line coverage (95% required). Includes ESM/CJS and browser/native bundler fixtures.Validation is scoped to eval and direct consumers. No full monorepo suite, production docs build, rendered docs visual review, release, or deployment was performed.
Reuse
Reuse
canonicalJsonandsha256Hexfrom@agentskit/core/hash, the existing shared hash implementation, and existing consumer fixtures. No new dependency, judging pipeline, or storage abstraction is introduced. The universal provenance subpath preserves the existing root bundle budget.The digest checks integrity, not authenticity or the truth of caller-supplied artifact identity. Omitting timestamps gives byte-identical envelopes across reruns.