[Refactor] drop misleading auto_activate field on SkillRecommendation#26
Open
NickCrew wants to merge 1 commit into
Open
[Refactor] drop misleading auto_activate field on SkillRecommendation#26NickCrew wants to merge 1 commit into
NickCrew wants to merge 1 commit into
Conversation
…endation Skill activation was deprecated in favour of progressive disclosure — skills are surfaced via descriptions in context rather than being activated. The auto_activate bool was set at construction time but never read by any consumer (the skill formatter groups by confidence tier; the [AUTO] badge in cmd_suggest belongs to AgentRecommendation, not SkillRecommendation). Removing the field eliminates a truth-in-advertising hazard where users might infer high-confidence skills would be silently turned on for them. Follow-up to 6f854cd feat(skills): add project-signature pre-filter. Agent activation path (cmd_ai.py, intelligence/base.py) is unchanged.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Skill activation was deprecated in favour of progressive disclosure — skills are surfaced via descriptions in context rather than being explicitly activated. The
auto_activate: boolfield onSkillRecommendationwas a vestige of that older model:skill_recommender.py)_print_skill_recommendations) groups results into High/Medium/Low confidence tiers and never referenced this field[AUTO]badge incmd_suggest.pybelongs to_print_agent_recommendations/AgentRecommendation, not the skill pathA user reading
cortex suggest --skillscould reasonably infer that[AUTO]means a skill will be turned on for them. Nothing happens. This PR removes the field for truth-in-advertising.Agent activation path is untouched.
cmd_ai.py,intelligence/base.py(AgentRecommendation.auto_activate),watch.pydaemon — all unchanged.Follow-up to 6f854cd
feat(skills): add project-signature pre-filter.Changes
auto_activate: boolfield fromSkillRecommendationdataclass (skill_recommender.py:32)auto_activate=…constructor kwargs (rule-based, agent-based, semantic, and pattern-based recommendation strategies)cmd_suggest.py— the[AUTO]badge there was already correctly scoped toAgentRecommendationSkillRecommendation.auto_activateTest plan
pytest tests/unit/test_cmd_suggest.py— 31 passedpytest tests/unit/— 273 passed, 3 pre-existing failures (missingpsutil/richdeps, unrelated to this change)mypy --strict claude_ctx_py/skill_recommender.py claude_ctx_py/cmd_suggest.py— all errors in pre-existing TUI modules, none in touched filesgrep -rn auto_activate claude_ctx_py/cmd_ai.py— agent path unchangedGenerated by Claude Code