Repository navigation
Conversation
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Loading ordinary input/target records with the default
FieldSpeccurrently passesmetadata=NoneintoSample, which rejects it because metadata must be a dictionary. Initialize a fresh empty dictionary for each record soDictDataLoaderand CSV/JSONL imports accept omitted metadata, matchingSample's default.Add regression coverage for omitted metadata, dictionary isolation between samples and reloads, explicit dictionary/JSON metadata, selected fields, and rejection of null or malformed metadata. Existing benchmark conversion and scoring semantics are unchanged.
Validation:
make dev,make lint, 55 dataset loader/builder tests, 9 default-adapter tests, and the unchangedtests/cli/test_all.py::TestRun::test_ci_litepassed. The smoke test used its built-in mock model and the official 120-record IQuiz dataset cached beforehand; socket connections were blocked during test execution. A separate 10-case offline oracle changed from 4 failures to all passing.Prepared with GPT-6 Astra in Codex. No live model calls were used.