v0.103.1

lyogavin/airllmv0.103.1Jun 10, 2026by bekossy

AI Summary

A frontend-focused update including UI redesigns, improved evaluation configurations, and dark mode support.

Key Highlights

Redesigned entity reference chips with identifier hovercards.
Rebuilt evaluation run Configuration tab as summary rail + sections.
Added dark mode changelog entry.

New Features

Entity reference chips redesign.
Playground evaluator improvements for testset columns.
Preservation of playground drafts when connecting test sets.
Documentation update for dark mode.

Full Release Notes

## What's Changed
* [release] v0.103.0 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4584
* fix(frontend): pass prompt-referenced testset columns to playground evaluators by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4601
* [#4592] fix(frontend): deployment "Last modified" shows the deployed revision date by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4593
* feat(frontend): rebuild eval run Configuration tab as summary rail + sections by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4606
* feat(frontend): redesign entity reference chips with identifier hovercard by @bekossy in https://github.com/Agenta-AI/agenta/pull/4615
* docs: add dark mode changelog entry and announcement by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4618
* fix(frontend): keep playground drafts when connecting a test set by @bekossy in https://github.com/Agenta-AI/agenta/pull/4622


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.103.0...v0.103.1