fix(hook): tag skills invoked via slash commands#20
Open
milanagm wants to merge 2 commits into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Closes LFE-10759. Fixes #15.
Skills leave two transcript trails: a
Skilltool_use block when Claudeinvokes the skill itself, and a top-level
attributionSkillfield on theassistant rows when the user invokes it as a slash command, which never
produces a tool_use block.
collect_skill_tagsonly read the first trail,so slash-command skill runs shipped without their
skill:<name>tag andwere invisible to tag filtering in Langfuse.
This PR collects both trails, deduped (same skill via both paths tags once).
This PR makes sure to also collect skill tags from subagent JSONL files.
Testing
tests/unit/test_skill_tags.pycovering both invocation paths, both combined, and dedup
via
/slash-commandproducesattributionSkillrows and zeroSkilltool_use blocks
tags=['claude-code'], aftertags=['claude-code', 'skill:greeting-style']