feat: add disabled_skills config and --no-skills CLI flag#216
Merged
Conversation
Add support for controlling which skills are loaded during evals: - New `disabled_skills` config field in eval YAML - Use `["*"]` to disable all skills - List specific skill names to exclude individual skills - New `--no-skills` CLI flag to disable all skills from the command line - `AllSkillsDisabled()` and `FilteredSkillPaths()` helper methods on Config - Conditional skill loading in CopilotEngine (skips getSkillDirs/buildSkillSystemMessage) - Early return in validateRequiredSkills when all skills disabled - Updated eval.schema.json, CLI reference, schema reference, and eval-yaml guide - 14 new test cases covering all disabled_skills scenarios Closes #126 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
b31ac9b to
9c023ac
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Implements #126 — allows users to control which skills are loaded during evals, including a "none" option to disable all skills.
Changes
New config field:
disabled_skills["*"]disables all skill loading entirely["noisy-skill"]) exclude individual skill directoriesskill_directoriesentriesNew CLI flag:
--no-skillsdisabled_skills: ["*"]in YAMLskill_directoriesconfigured in the eval specImplementation details:
Config.AllSkillsDisabled()— checks for wildcard disable orskill_directories: ["none"]Config.FilteredSkillPaths()— returns skill paths with disabled entries removedExecutionRequest.NoSkills— signals CopilotEngine to skipgetSkillDirs()andbuildSkillSystemMessage()validateRequiredSkills()— early returns when all skills disabledTesting
14 new test cases across 3 test functions:
TestConfig_AllSkillsDisabled(6 subtests)TestConfig_FilteredSkillPaths(6 subtests)TestBenchmarkSpec_DisabledSkillsDeserialization(2 subtests)All existing tests pass. Docs site builds cleanly.
Usage
# CLI flag waza run eval.yaml --no-skillsWorking as Linus (Backend Developer)
Closes #126