Agenta

v0.102.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo LLM Frameworks

View tool

✓ 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

Run-on mode selector added to the evaluator playground and creation drawer.

Changes in this release

Type	Severity	Summary	CVE
Feature	Medium	Add run-on mode selector for the evaluator playground Add run-on mode selector for the evaluator playground Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Medium	Add run-on modes in the evaluator creation drawer (shared controls) Add run-on modes in the evaluator creation drawer (shared controls) Source: llm_adapter@2026-06-08 Confidence: high	—
Dependency	Low	Add unit tests for @agenta/shared and @agenta/annotation packages Add unit tests for @agenta/shared and @agenta/annotation packages Source: llm_adapter@2026-06-08 Confidence: high	—
Bugfix
Bugfix	Medium	Fix inverted Text/Markdown view in playground message editors Fix inverted Text/Markdown view in playground message editors Source: llm_adapter@2026-06-08 Confidence: high	—
Bugfix	Medium	Re-enable full-page playground for evaluator workflows Re-enable full-page playground for evaluator workflows Source: llm_adapter@2026-06-08 Confidence: high	—
Bugfix	Medium	Render markdown headings by level instead of uppercasing Render markdown headings by level instead of uppercasing Source: llm_adapter@2026-06-08 Confidence: high	—
Bugfix	Medium	Stop PR bot over‑closing on missing checklist and fix reopen loop via CI workflow Stop PR bot over‑closing on missing checklist and fix reopen loop via CI workflow Source: llm_adapter@2026-06-08 Confidence: high	—
Refactor
Refactor	Low	Remove copyright and social-links footer bar from frontend Remove copyright and social-links footer bar from frontend Source: llm_adapter@2026-06-08 Confidence: high	—
Refactor	Low	Auto-close incomplete external PRs via CI workflow Auto-close incomplete external PRs via CI workflow Source: llm_adapter@2026-06-08 Confidence: high	—
Refactor	Low	Exempt private org members from PR contribution check via CI workflow Exempt private org members from PR contribution check via CI workflow Source: llm_adapter@2026-06-08 Confidence: high	—

Full changelog

What's Changed

[release] v0.101.1 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4545
fix(frontend): remove copyright and social-links footer bar by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4550
[fix] Render markdown headings by level instead of uppercasing by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4548
feat(frontend): Run-on mode selector for the evaluator playground by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4553
[FE Fix]: Re-enable full-page playground for evaluator workflows by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4474
[fix] Fix inverted Text/Markdown view in playground message editors by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4554
test(frontend): add unit tests for @agenta/shared and @agenta/annotation packages by @bekossy in https://github.com/Agenta-AI/agenta/pull/4539
ci: auto-close incomplete external PRs by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4579
ci: exempt private org members from PR contribution check by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4580
ci: stop PR bot over-closing on missing checklist + fix reopen loop by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4581
feat(frontend): Run-on modes in the evaluator creation drawer (shared controls) by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4557

Full Changelog: https://github.com/Agenta-AI/agenta/compare/v0.101.1...v0.102.0

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.

About Agenta

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

Agenta

Summary

Changes in this release

What's Changed

Related context

Related tools

Earlier breaking changes