Major changes:
- Remove fake OPRO evaluation (no more fake 0.5 scores)
- Add simple refinement based on user selection
- New endpoint: POST /opro/refine (selected + rejected instructions)
- Update prompt generation to focus on comprehensive coverage instead of style variety
- All generated instructions now start with role definition (你是一个...)
- Update README to reflect new approach and API endpoints
Technical details:
- Added refine_based_on_selection() in prompt_utils.py
- Added refine_instruction_candidates() in user_prompt_optimizer.py
- Added OPRORefineReq model and /opro/refine endpoint in api.py
- Updated frontend handleContinueOptimize() to use new refinement flow
- Changed prompt requirements from 'different styles' to 'comprehensive coverage'
- Added role definition requirement as first item in all prompt templates
- Add session layer above runs to group related optimization tasks
- Sessions use first task description as name instead of 'Session 1'
- Simplified sidebar: show sessions without expansion
- Add '+ 新建任务' button in header to create runs within session
- Fix: reload sessions after creating new run
- Add debugging logs for candidate generation
- Backend: auto-update session name with first task description
