Repository navigation
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #299.
Top-program prompts currently describe every metric as “Performs well on”, including zero scores and error messages. Change the default fragment to
Metric:so these entries report values without asserting good performance.Metric values and formatting, explicit
key_features, and custom fragment overrides are preserved. This changes only the default label, not fitness or selection logic.Validation (Python 3.12.13):
PromptSampler.build_prompt()without model calls; all four metric regression cases failed before the change and passed afterward.python -m unittest tests.test_prompt_sampler -v: 4 tests passed.OPENAI_API_KEY=test-key-for-unit-tests python -m unittest discover -s tests -p 'test_*.py' -v: 861 tests, 2 skipped, no failures.git diff --checkpassed for the changes.Codex assisted with issue investigation, implementation, and testing. No model-quality benchmark was run.