v0.103.2

mudler/LocalAIv0.103.2Jun 11, 2026by bekossy

AI Summary

This release introduces several frontend improvements including sticky headers in JSON views, multiple metric support for evaluators, and a decoupled playground chat behavior.

Key Highlights

Code evaluators can now return multiple metrics as a dictionary
Playground chat behavior decoupled from app flag
Sticky collapse headers in PrettyJsonView
Migrated changelog to paginated blog entries

New Features

Multiple metrics for evaluators
Sticky headers in JSON view
Decoupled playground chat

Full Release Notes

## What's Changed
* [release] v0.103.1 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4611
* Migrate changelog from single file to paginated blog entries by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4613
* chore: remove QA scratch files by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4632
* chore(agents): add a What to QA section to the write-pr-description skill by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4635
* feat(sdk): let code evaluators return multiple metrics as a dict by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4626
* fix(frontend): show the evaluator name instead of 'default' in tables by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4634
* feat(frontend): decouple playground chat behavior from the app is_chat flag by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4609
* [AGE-3766] feat(frontend): Make collapse headers sticky in PrettyJsonView by @Sanket2329 in https://github.com/Agenta-AI/agenta/pull/4587
* docs: add Sanket2329 as a contributor for code by @allcontributors[bot] in https://github.com/Agenta-AI/agenta/pull/4640

## New Contributors
* @Sanket2329 made their first contribution in https://github.com/Agenta-AI/agenta/pull/4587

**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.103.1...v0.103.2