fix: add preflight check and --bare for claude CLI client#44
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Following up to PR #43 to add the
--bareflag to avoid injecting CLAUDE.md files, project memory, rules, and other local context into every LLM-as-judge scoring call, and potentially affecting scoring outputs.However, in testing, it turns out
--barealso strips auth, thus negating the benefit of adding theclaude-cliclient. So I'm removing the--bareflag for now, and have instead added documentation to the README and other relevant spots to indicate that when usingclaude-cli, the additional context can affect scoring.I've also filed a request on the Claude Code repo requesting a bare-like flag that retains auth but strips other context: anthropics/claude-code#38022
This PR does add a preflight check for the "claude" binary before executing LLM-as-judge scoring.