Skip to content

Agenta

v0.100.2 Breaking

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

Published 8d 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

Summary

AI summary

Updates Fix, feat, and frontend across a mixed release.

Changes in this release

Feature Low

Adds unified `testcase` view.

Adds unified `testcase` view.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Feature Low

Adds bulk trace export for a date range.

Adds bulk trace export for a date range.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Feature Low

Adds evaluation scenario filtering.

Adds evaluation scenario filtering.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Feature Low

Adds batch add traces to annotation queue.

Adds batch add traces to annotation queue.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Bugfix Medium

Fixes OTelLinksResponse.count over-counting and removal of dropped field.

Fixes OTelLinksResponse.count over-counting and removal of dropped field.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Bugfix Medium

Fixes revision commit endpoints silently discarding unknown fields.

Fixes revision commit endpoints silently discarding unknown fields.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Bugfix Low

Resolves free and trial plans issues in web UI.

Resolves free and trial plans issues in web UI.

Source: llm_adapter@2026-05-26

Confidence: high

 —
Full changelog

What's Changed

  • [docs] Update API reference docs by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4408
  • Fix: OTelLinksResponse.count over-counts and writes a removed dropped field by @justin212407 in https://github.com/Agenta-AI/agenta/pull/4346
  • [fix] Resolve small open issues by @junaway in https://github.com/Agenta-AI/agenta/pull/4414
  • Fix: Fix revision commit endpoints silently discard unknown fields in… by @justin212407 in https://github.com/Agenta-AI/agenta/pull/4345
  • feat: unified testcase view by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4394
  • [fix] Resolve free and trial plans in web by @junaway in https://github.com/Agenta-AI/agenta/pull/4444
  • [3840] feat(frontend): Bulk trace export — download all traces for a date range by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4420
  • [FE Feat] Evaluation scenario filtering by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4405
  • [Fe Feat] Batch add traces to annotation queue by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4400

New Contributors

  • @justin212407 made their first contribution in https://github.com/Agenta-AI/agenta/pull/4346

Full Changelog: https://github.com/Agenta-AI/agenta/compare/v0.100.1...v0.100.2

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

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

Beta — feedback welcome: [email protected]