Skip to content

Agenta

v0.103.1 Feature

This release adds 2 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

Redesigned the Evaluation Run Configuration tab and entity reference chips in the frontend.

Changes in this release

Feature Low

Redesigns entity reference chips with identifier hovercard.

Redesigns entity reference chips with identifier hovercard.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Feature Low

Rebuilds eval run Configuration tab as summary rail with sections.

Rebuilds eval run Configuration tab as summary rail with sections.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Bugfix Medium

Fixes playground drafts retention when connecting a test set.

Fixes playground drafts retention when connecting a test set.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Bugfix Medium

Fixes deployment "Last modified" to show deployed revision date.

Fixes deployment "Last modified" to show deployed revision date.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Bugfix Low

Fixes passing prompt‑referenced testset columns to playground evaluators.

Fixes passing prompt‑referenced testset columns to playground evaluators.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Full changelog

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

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]