Skip to content

[feat]: run auto evaluation from traces#4794

Open
ashrafchowdury wants to merge 14 commits into
refactor/new-evaluation-modal-to-remove-hard-wiresfrom
feat/run-auto-evaluation-from-traces-queries
Open

[feat]: run auto evaluation from traces#4794
ashrafchowdury wants to merge 14 commits into
refactor/new-evaluation-modal-to-remove-hard-wiresfrom
feat/run-auto-evaluation-from-traces-queries

Conversation

@ashrafchowdury

@ashrafchowdury ashrafchowdury commented Jun 22, 2026

Copy link
Copy Markdown
Contributor

What's new??

Run auto evaluation from traces, previously running evaluation on trace were only for the live evaluation. Now we are run auto evaluation from traces as well.

QA scope

Evaluation and Observability

  1. Running evaluations should work as expected (no changes there)
  2. Go to observability and select some traces
  3. Click + Add button and then Run auto evaluation
  4. This should open the create new evaluation modal (the selected tab should be evaluator)
  5. You should be able to see the traces tab and go there and deselect and select the already selected traces from the observability
  6. Run the evaluation and it should work as expected (no changes there)

@dosubot dosubot Bot added the size:XXL This PR changes 1000+ lines, ignoring generated files. label Jun 22, 2026
@vercel

vercel Bot commented Jun 22, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
agenta-documentation Ready Ready Preview, Comment Jun 24, 2026 1:21pm

Request Review

@coderabbitai

coderabbitai Bot commented Jun 22, 2026

Copy link
Copy Markdown

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro Plus

Run ID: f34ac490-07cc-4b04-be1f-8a160a926855

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch feat/run-auto-evaluation-from-traces-queries

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

…o feat/run-auto-evaluation-from-traces-queries
@github-actions

github-actions Bot commented Jun 22, 2026

Copy link
Copy Markdown
Contributor

Railway Preview Environment

Preview URL https://gateway-production-0796.up.railway.app/w
Project agenta-oss-pr-4794
Image tag pr-4794-f2d7912
Status Deployed
Railway logs Open logs
Workflow logs View workflow run
Updated at 2026-06-24T13:48:37.224Z

@ardaerzin ardaerzin self-requested a review June 22, 2026 23:33

@ardaerzin ardaerzin left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

good overall, thanks for the great work @ashrafchowdury.

however we can improve the ux a bit, currently we're silently filling query registry with auto generated "trace-eval" queries

…o feat/run-auto-evaluation-from-traces-queries

# Conflicts:
#	web/oss/src/components/pages/evaluations/NewEvaluation/Components/NewEvaluationModalInner.tsx
#	web/oss/src/components/pages/evaluations/NewEvaluation/Components/SelectEvaluatorSection/SelectEvaluatorSection.tsx
#	web/oss/src/components/pages/evaluations/NewEvaluation/evalSteps/registry.tsx
#	web/oss/src/components/pages/evaluations/NewEvaluation/evalSteps/types.ts
#	web/oss/src/components/pages/evaluations/NewEvaluation/index.tsx
#	web/oss/src/components/pages/evaluations/NewEvaluation/types.ts
#	web/packages/agenta-evaluations/tests/unit/evaluationStepEngine.test.ts
@ashrafchowdury

Copy link
Copy Markdown
Contributor Author

Fixed the issue with the following fixes:

  1. Added alert message on the "New evaluation modal > Trace tab"
  2. Display a toast message upon evaluation creation
  3. Added meta.source when creating a query from the evaluation creation.
  4. Added a new column to the Query registry name source to display the source of the creation
image

…o feat/run-auto-evaluation-from-traces-queries
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature Frontend size:XXL This PR changes 1000+ lines, ignoring generated files.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants