ProjectTech4DevAI / ProjectTech4DevAI/kaapi-frontend

Evaluation: Fix judge run display

Open
#272 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
TypeScript
Stars
1
Forks
0
Avg merge
10h 40m
Merged PRs (30d)
4

Description

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

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating EvalRunCard, EvalRunsList, and the run detail page, then trace how is_judge_run and score_trace_url are provided to them. Verify the existing v1 rendering path before updating the judge-run branches. Done means judge runs hide cosine summaries, per-item cosine columns, and Langfuse links while retaining native score_trace_url links; v1 output remains unchanged.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
frontend
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Clearly specified
Newbie friendliness
76/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.