root 462d81868f Overhaul history: scores visible, optimization history, full run tracking
Archive list improvements:
- Score column added to run list (color-coded: green 7+, amber 5+, red)
- OPT badge on runs generated by optimization (shows parent run)
- quality_score, score_method, tags, source, parent_run now in list query

Detail panel score display:
- Large color-coded score badge in header (e.g., "8.0/10" in green)
- Shows scoring method (auto/thumbs up/thumbs down)
- Persistent — visible every time you open the detail, not just once

Full optimization history section:
- Shows all optimization runs with timestamps, scores, call counts
- Each run lists ranked variations with strategy, mode, score
- Winner highlighted with star and green border
- "View" button opens any variation's full detail
- "Use" button on winner sends prompt to composer via sessionStorage
- Always loads from /api/optimize-history — no stale data

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-29 07:32:50 -05:00
Description
LLM Team UI - Full-stack local AI orchestration platform
9.2 MiB
Languages
Python 97.4%
Shell 2.6%