feat(test): add per-skill eval behavior specs#85
Open
mvanhorn wants to merge 1 commit intogarrytan:mainfrom
Open
feat(test): add per-skill eval behavior specs#85mvanhorn wants to merge 1 commit intogarrytan:mainfrom
mvanhorn wants to merge 1 commit intogarrytan:mainfrom
Conversation
Phase 1 of garrytan#24. Adds structural behavior assertions for each skill - deterministic, free (no API cost), and fast. Each skill gets a JSON spec defining patterns its output must exhibit (e.g., review must have CRITICAL/INFORMATIONAL sections, retro must contain metrics). The behavior-checker module runs assertions against captured output text. Includes 14 unit tests covering all assertion types: pattern_exists, pattern_absent, section_exists, min_sections, regex, case-insensitive. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
behavior-checker.tsmodule with 4 assertion types:pattern_exists,pattern_absent,section_exists,min_sectionsImplements Phase 1 of #24. Each skill gets a JSON spec defining patterns its output must exhibit (e.g., review must have CRITICAL/INFORMATIONAL sections, retro must contain quantitative metrics). Assertions are deterministic, free (no API cost), and fast. The behavior-checker module is designed to wire into the existing E2E test suite via
checkBehaviors(capturedOutput, spec).Test plan
bun test test/behavior-checker.test.tspasses (14 tests, 83 assertions)bun run gen:skill-docs --dry-runpasses (SKILL.md freshness)skill-e2e.test.tsto run after E2E tests (follow-up)