Skip to content

Agenta

v0.101.1 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

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

ReleasePort's take

Light signal
editorial:auto 1mo

This release fixes several UI and annotation bugs and refactors documentation; it also introduces a breaking identifier rename from `beautified` to `pretty`.

Why it matters: The high‑severity (70) breaking change renames the API/frontend identifier `beautified` to `pretty`, requiring immediate code updates for affected integrations.

Summary

AI summary

Updates agents, fix, and Fix across a mixed release.

Changes in this release

Breaking High

Renames `beautified` to `pretty`.

Renames `beautified` to `pretty`.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Fixes broken annotations with numeric versions.

Fixes broken annotations with numeric versions.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Fixes broken evaluator playground with chat prompts.

Fixes broken evaluator playground with chat prompts.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Fixes dark mode rendering issues.

Fixes dark mode rendering issues.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Ensures consistent workflow type colors.

Ensures consistent workflow type colors.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Wires testset connection into workflow drawer playground.

Wires testset connection into workflow drawer playground.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Prevents duplication of testcases when saving from annotation queue.

Prevents duplication of testcases when saving from annotation queue.

Source: llm_adapter@2026-06-04

Confidence: high

Bugfix Medium

Enhances JSON object handling and rendering in testset UI.

Enhances JSON object handling and rendering in testset UI.

Source: llm_adapter@2026-06-04

Confidence: high

Refactor Low

Compartmentalizes AGENTS.md into scoped files and skills.

Compartmentalizes AGENTS.md into scoped files and skills.

Source: llm_adapter@2026-06-04

Confidence: high

Full changelog

What's Changed

  • chore(agents): compartmentalize AGENTS.md into scoped files and skills by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4543
  • [fix] Resolve broken annotations with numeric versions by @junaway in https://github.com/Agenta-AI/agenta/pull/4529
  • [fix] Resolve broken evaluator playground with chat prompts by @junaway in https://github.com/Agenta-AI/agenta/pull/4530
  • fix: rename beautified to pretty by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4532
  • Fix/dark mode by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4546
  • Fix: Consistent workflow type colors by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4534
  • [FE Fix] Wire testset connection into workflow drawer playground by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4450
  • [FE Fix] Stop duplicating testcases when saving back from annotation queue by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4537
  • fix(frontend): enhance JSON object handling and rendering in testset by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4510

Full Changelog: https://github.com/Agenta-AI/agenta/compare/v0.101.0...v0.101.1

Breaking Changes

  • rename `beautified` flag/option to `pretty`

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

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

  • v0.100.7 Renames providers table Status column to API Key.

Beta — feedback welcome: [email protected]