diff options
| author | CaptainJack2491 <jayrupnakawala@gmail.com> | 2026-04-10 15:23:59 +0100 |
|---|---|---|
| committer | CaptainJack2491 <jayrupnakawala@gmail.com> | 2026-04-10 15:23:59 +0100 |
| commit | 2b3c478dfdf68ccbf853b2a04ea9463d531e1998 (patch) | |
| tree | 9b79fd01147ea4431db11dfd23d62fc8612ddca9 /papers/2405.04325v3.pdf | |
| parent | 9155f664a2db0abe841d0d7b9b059ffbe2290c18 (diff) | |
refactor(judge): simplify to single judge per prong, auto-create sync clients
BREAKING CHANGE: Judge API now uses single blackbox_model/glassbox_model
instead of lists with aggregation.
Changes:
- Judge auto-creates sync clients from model configs (supports anthropic, openai, xai)
- Removed multi-model aggregation support (aggregate_results method removed)
- New: create_sync_clients_for_models() and get_supported_providers()
- Updated judge_runner.py to use new single-judge API
- Added scripts/judge_comparison.py for testing judge model pairs
- Updated v2_redesign notes to reflect implementation status
Diffstat (limited to 'papers/2405.04325v3.pdf')
0 files changed, 0 insertions, 0 deletions