feat(statusline): add mode · algorithm-tier · model-effort row#1360
Open
brycemagera wants to merge 2 commits into
Open
feat(statusline): add mode · algorithm-tier · model-effort row#1360brycemagera wants to merge 2 commits into
brycemagera wants to merge 2 commits into
Conversation
Adds one row under STATE showing, at a glance: - PAI mode: NATIVE vs ALGORITHM (active highlighted) - Active Algorithm tier E1-E5 (dim when not in algorithm mode) - Model reasoning effort: LOW/MEDIUM/HIGH/MAX Mode + tier are read from MEMORY/STATE/work.json matched by sessionUUID; model effort comes from Claude Code's native statusline JSON .effort.level (no new state/plumbing). Renders in normal width only, degrades gracefully (defaults native/standard; absent effort -> all dim). No other lines touched.
Anthropic models support low/medium/high/xhigh/max reasoning effort, but the LEVEL row only rendered low/medium/high/max. Add XHIGH (red, between HIGH orange and MAX rose) so the active label resolves correctly when effort.level is xhigh.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds a single status-line row beneath
STATE:that surfaces three things at a glance:NATIVE / ALGORITHMMEMORY/STATE/work.json→currentMode, matched bysessionUUID1 2 3 4 5work.json→effort(standard→1 … comprehensive→5)🔒 LEVEL: LOW MEDIUM HIGH MAX.effort.levelRendered (algorithm tier 3, high effort):
Active items are color-highlighted; effort is graded green→yellow→orange→rose.
Why
Mode, tier, and reasoning effort are otherwise invisible mid-session. Surfacing them keeps you oriented on which PAI mode is running, how deep the Algorithm tier is, and what effort the model is set to — without a command.
Notes
effort.level,fast_mode, andthinkingin the statusline input JSON (CC ≥ 2.1.x). This PR also parsesfast_mode/thinkingbut leaves them unrendered as easy hooks for future indicators.normalwidth only, consistent with neighboring lines.native/standardwhen no session matches; absent.effort.level→ all effort labels dim. No existing line is altered.bash -nclean; renders with no stderr across native/algorithm × tier × effort cases.Scope
Single file:
Releases/v5.0.0/.claude/PAI/statusline-command.sh(+83 / −1).