feat(statusline): show reasoning effort level alongside model name - #31
Draft
yulonglin wants to merge 1 commit into
Draft
feat(statusline): show reasoning effort level alongside model name#31yulonglin wants to merge 1 commit into
yulonglin wants to merge 1 commit into
Conversation
Claude Code sends an effort.level field (low/medium/high/xhigh) in the statusline stdin JSON for models that support configurable reasoning effort. Append it to the model name bracket in both implementations: [Sonnet 5 · high] instead of just [Sonnet 5]. Falls back to the plain model name when effort is absent (older models, or models without configurable effort). - claude/statusline.sh: bash fallback - tools/claude-tools/src/statusline.rs: Rust primary, rebuilt for linux-x86_64 with checksums regenerated Claude-Session: https://claude.ai/code/session_019m9jsBpvKn79DC1vGnWeF6
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
[Sonnet 5 · high], for models that support configurable effort (falls back to plain[Model Name]otherwise).claude/statusline.sh(bash fallback) andtools/claude-tools/src/statusline.rs(Rust primary).effort.levelfield was reverse-engineered from the installed Claude Code CLI binary (2.1.216) — it's a top-leveleffort: {level: "low"|"medium"|"high"|"xhigh"}sibling tomodel/cost/context_windowin the statusline stdin JSON, sent only for models that support configurable effort.claude-toolsforlinux-x86_64and regeneratedtools/claude-tools/SHA256SUMSto match.Test plan
effortpresentclaude/statusline.shend-to-end against sample stdin JSON, both with and withouteffortpresent — output matches Rust implementation exactly ([Sonnet 5 · high]/[Haiku 4.5])custom_bins/claude-tools-linux-x86_64checksum matches the newly built binaryhttps://claude.ai/code/session_019m9jsBpvKn79DC1vGnWeF6