Skip to content

Evaluation: Fix judge run display #272

Description

@AkhileshNegi

Is your feature request related to a problem?
v2 runs do not compute cosine similarity and do not interact with Langfuse. However, the run cards and detail view still display cosine columns and Langfuse trace links, which are empty or broken for judge runs.

Describe the solution you'd like

  • Implement a check for is_judge_run in EvalRunCard, EvalRunsList, and the run detail page
  • Remove cosine similarity summary and per-item cosine columns for judge runs
  • Hide Langfuse trace links for judge runs while retaining the native score_trace_url path
  • Keep the rendering path for v1 unchanged
Original issue

Is your feature request related to a problem?
v2 runs compute no cosine similarity and never touch Langfuse. The run cards and detail view still render cosine columns and Langfuse trace links, which will show up empty or broken for judge runs.

Describe the solution you'd like

  • Branch on is_judge_run in EvalRunCard, EvalRunsList and the run detail page
  • Hide cosine similarity summary and per-item cosine columns for judge runs
  • Hide Langfuse trace links for judge runs; keep the native score_trace_url path
  • Leave the v1 rendering path unchanged

Parent: #265

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions