Skip to content

Agenta

v0.100.7 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 5d LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents evaluation llm-as-a-judge llm-evaluation llm-framework llm-monitoring
+9 more
llm-observability llm-platform llm-playground llm-tools llmops observability prompt-engineering prompt-management rag-evaluation

ReleasePort's take

Moderate signal
editorial:auto 5d

Release v0.100.7 patches several UI bugs and adds minor features while introducing a breaking change that renames the providers table Status column to API Key.

Why it matters: The rename (severity 70) requires updating any code or scripts referencing the old 'Status' column name; all other fixes address functional regressions in invites, data retrieval, UI displays, and evaluation processing.

Summary

AI summary

Fixes broken OSS invites, data corruption on retrieval, and adds API Key column for providers.

Changes in this release

Breaking High

Renames providers table Status column to API Key.

Renames providers table Status column to API Key.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Feature Low

Adds Markdown / Text switch in playground configs.

Adds Markdown / Text switch in playground configs.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Feature Low

Preserves playground chat history across commits.

Preserves playground chat history across commits.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Fixes broken OSS invites from non-default projects.

Fixes broken OSS invites from non-default projects.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Resolves data corruption related to retrieval.

Resolves data corruption related to retrieval.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Fixes missing trace in scenario drawer.

Fixes missing trace in scenario drawer.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Filters evaluation scenario display names correctly.

Filters evaluation scenario display names correctly.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Fixes evaluation scenario output cells in comparison mode.

Fixes evaluation scenario output cells in comparison mode.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Refreshes prompts page table after prompt creation.

Refreshes prompts page table after prompt creation.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Bugfix Medium

Resolves issues from null data in live evaluations.

Resolves issues from null data in live evaluations.

Source: llm_adapter@2026-05-29

Confidence: high

 —
Full changelog

What's Changed

  • [Fe fix] Evaluation scenarios filter display names by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4485
  • [fix] Resolve broken oss invites from non-default projects by @junaway in https://github.com/Agenta-AI/agenta/pull/4461
  • [FE Fix] Fix evaluation scenario output cells in comparison mode by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4486
  • [fix] Resolve issues from null data in live evaluations by @junaway in https://github.com/Agenta-AI/agenta/pull/4462
  • [FE Fix]: Rename providers table Status column to API Key by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4488
  • [FE Fix]: Refresh prompts page table after prompt creation by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4490
  • [FE fix] Scenario drawer missing trace by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4483
  • [fix] Resolve data corruption related to retrieval by @junaway in https://github.com/Agenta-AI/agenta/pull/4476
  • [FE Fix]: Markdown / Text switch in playground configs by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4482
  • [AGE-3785] fix(frontend): preserve playground chat history across commits by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4468

Full Changelog: https://github.com/Agenta-AI/agenta/compare/v0.100.6...v0.100.7

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

Beta — feedback welcome: [email protected]