feat(submit-adapter): drive Adapter.respond through core suite (sb-bas)#288
Open
openclaw-dv wants to merge 1 commit into
Open
feat(submit-adapter): drive Adapter.respond through core suite (sb-bas)#288openclaw-dv wants to merge 1 commit into
openclaw-dv wants to merge 1 commit into
Conversation
Replace _write_placeholder_artifacts with a real eval pipeline that wraps the vendor Adapter as a Provider, runs BenchmarkRunner against the core OpinionsQA suite, and writes scored run.json + submission.md. - AdapterProvider parses raw adapter output (letter / number / text) and surfaces parse failures as Response(refusal=True) so runner metrics stay honest. - Raw transcripts feed compute_run_hash so leaderboard CI's tamper-detection contract works end-to-end. - Tests inject an in-memory OpinionsQA stand-in so CI doesn't need the CodaLab download.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Closes sb-bas (P1, post-#263). Replaces
_write_placeholder_artifactswith a real eval pipeline: AdapterProvider wraps the vendor Adapter, BenchmarkRunner runs the core OpinionsQA suite, scored run.json + submission.md with real run_hash over raw transcripts.Test plan
semver:minor
🤖 Generated with Claude Code
PR opened by mayor; polecat's gt done created the MR bead and pushed the branch but the auto-PR step appears not to have fired.