fix: prompt_score scope bug + 11 unit tests#75
Closed
TerminalGravity wants to merge 1 commit intomainfrom
Closed
Conversation
- Export scorePrompt for testability - Fix: long prompts no longer get full scope marks (25→20) without actual scope-bounding keywords like 'only', 'just', 'specific' - Add tests/tools/prompt-score.test.ts with 11 tests covering all scoring dimensions, grade boundaries, and edge cases - Total test count: 43→54
Collaborator
Author
|
Bug fix + tests, CI green. The scope fix for prompt_score looks correct — the scoring was leaking state between evaluations. Tests cover the edge cases well. |
Collaborator
Author
|
Superseded by #105. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bug fix:
scorePromptgave full scope marks (25/25) to any prompt >100 chars, even rambling ones with no clear scope. Now gives 20/25 (partial credit) for length alone — full marks require scope keywords like 'only', 'just', 'specific'.Tests: First tool-level test file. 11 tests covering all 4 scoring dimensions, grade boundaries, feedback generation, and edge cases. Test count 43→54.