feat: add reference replay runner#8
Merged
Conversation
drewstone
force-pushed
the
feat/reference-replay-runner
branch
from
9343d8b to
814a103
Compare
drewstone
force-pushed
the
feat/reference-replay-runner
branch
from
814a103 to
f380eb4
Compare
4 tasks
9 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the execution layer around the reference replay scorer so downstream products can run hidden-reference evals end to end.\n\nChanges:\n- add ReferenceReplayCase, execution scenario, adapter, run, and run record types\n- add runReferenceReplay with hidden references, per-case scoring, failure capture, and full run scoring\n- add in-memory and JSONL run stores\n- add run-to-run promotion decision helper\n- cover adapter reference hiding, persistence, JSONL round-trip, failure capture, and promotion behavior\n\nVerification:\n- pnpm test -- tests/reference-replay.test.ts\n- pnpm typecheck\n- pnpm build