Is your feature request related to a problem?
The console currently uses the v1 evaluation API, which lacks the features and speed of v2. The new v2 API offers significant improvements, including a better scoring system and additional functionalities that are not currently represented in the UI.
Describe the solution you'd like
- Transition dataset upload, run trigger, and improve-prompt to the v2 endpoints
- Update scoring UI to reflect the three judge metrics, verdicts, and overall summary
- Introduce v2-specific controls: per-run duplication override and prompt-iteration loop
Is your feature request related to a problem?
The console currently uses the v1 evaluation API, which lacks the features and speed of v2. The new v2 API offers significant improvements, including a better scoring system and additional functionalities that are not currently represented in the UI.
Describe the solution you'd like