Skip to content

Agenta

v0.104.2 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 sdk, fix, and frontend across a mixed release.

Full changelog

What's Changed

  • [release] v0.104.1 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4729
  • [fix] Select Railway services when redeploying previews by @bekossy in https://github.com/Agenta-AI/agenta/pull/4793
  • fix(sdk): sandbox custom-code evaluators by default (RestrictedPython runner) by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4636
  • [fix] Explicit service selection and graceful no-deployment on Railway redeploy by @bekossy in https://github.com/Agenta-AI/agenta/pull/4799
  • fix: preserve string type when Text/Markdown view mode is selected in test case drawer by @NamHT4Devlop in https://github.com/Agenta-AI/agenta/pull/4705
  • fix(frontend): surface invocation errors instead of dumping HTML 404 pages by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4702
  • [Test] Web acceptance stability by @bekossy in https://github.com/Agenta-AI/agenta/pull/4506
  • [feat] Enable full configuration of code and hook workflows and their schemas by @junaway in https://github.com/Agenta-AI/agenta/pull/4711

Full Changelog: https://github.com/Agenta-AI/agenta/compare/v0.104.1...v0.104.2

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]