Skip to content

Agenta

v0.103.2 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-builder agent-observability agent-orchestration agent-workspace agentic-ai agentic-workflow
+12 more
agents ai-agent ai-agents ai-automation ai-workflow-builder background-agents harness human-in-the-loop llm-evaluation llm-observability mcp self-hosted

Summary

AI summary

Updates frontend, chore, and agents across a mixed release.

Changes in this release

Feature Medium

Migrate changelog from single file to paginated blog entries

Migrate changelog from single file to paginated blog entries

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Medium

Decouple playground chat behavior from the app is_chat flag in frontend

Decouple playground chat behavior from the app is_chat flag in frontend

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Medium

Make collapse headers sticky in PrettyJsonView frontend component

Make collapse headers sticky in PrettyJsonView frontend component

Source: llm_adapter@2026-06-11

Confidence: high

 —
Feature Low

Let code evaluators return multiple metrics as a dict in SDK

Let code evaluators return multiple metrics as a dict in SDK

Source: granite4.1:30b@2026-06-11-audit

Confidence: low

 —
Bugfix Medium

Show the evaluator name instead of 'default' in frontend tables

Show the evaluator name instead of 'default' in frontend tables

Source: llm_adapter@2026-06-11

Confidence: high

 —
Refactor Low

Remove QA scratch files from repository

Remove QA scratch files from repository

Source: llm_adapter@2026-06-11

Confidence: high

 —
Full changelog

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

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Agenta

Get notified when new releases ship.

Sign up free

About Agenta

LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.

All releases →

Related context

Earlier breaking changes

  • v0.101.1 Renames `beautified` to `pretty`.
  • v0.100.7 Renames providers table Status column to API Key.

Beta — feedback welcome: [email protected]