Skip to content

Agenta

v0.100.1 Feature

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

Published 12d 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

Affected surfaces

auth

ReleasePort's take

Light signal
editorial:auto 12d

Release v0.100.1 fixes the broken create release branch workflow, restores correct CORS headers, and resolves an Annotations bug where empty links caused mis‑classification.

Why it matters: These bugfixes restore critical CI pipeline functionality, secure API gateway interactions by correcting CORS headers, and prevent erroneous Annotation creation—directly impacting developer productivity and system reliability in the affected surfaces.

Summary

AI summary

Fixed broken create release branch, CORS headers, and Annotations bug.

Changes in this release

Feature Medium

Adds parent slugs to revisions

Adds parent slugs to revisions

Source: llm_adapter@2026-05-22

Confidence: low

 —
Feature Medium

Adds audit logs table UI component

Adds audit logs table UI component

Source: llm_adapter@2026-05-22

Confidence: low

 —
Performance Medium

Increases DEFAULT_MAX_RENDER_DEPTH in BeautifiedJsonView to 100

Increases DEFAULT_MAX_RENDER_DEPTH in BeautifiedJsonView to 100

Source: llm_adapter@2026-05-22

Confidence: low

 —
Bugfix Medium

Fixes broken create release branch workflow

Fixes broken create release branch workflow

Source: llm_adapter@2026-05-22

Confidence: high

 —
Bugfix Medium

Fixes broken CORS headers

Fixes broken CORS headers

Source: llm_adapter@2026-05-22

Confidence: high

 —
Bugfix Medium

Fixes Annotations incorrectly created as Invocations when links={}

Fixes Annotations incorrectly created as Invocations when links={}

Source: llm_adapter@2026-05-22

Confidence: high

 —
Bugfix Medium

Fixes CI by stopping aliasing RAILWAY_API_TOKEN to RAILWAY_TOKEN

Fixes CI by stopping aliasing RAILWAY_API_TOKEN to RAILWAY_TOKEN

Source: llm_adapter@2026-05-22

Confidence: high

 —
Refactor Medium

Disables new behavior behind a feature flag

Disables new behavior behind a feature flag

Source: llm_adapter@2026-05-22

Confidence: low

 —
Refactor Medium

Uses TraceSpanDrillInView for Exception when spanEntityId present

Uses TraceSpanDrillInView for Exception when spanEntityId present

Source: llm_adapter@2026-05-22

Confidence: low

 —
Full changelog

What's Changed

  • [release] v0.100.0 by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4358
  • [docs] Update API reference docs by @github-actions[bot] in https://github.com/Agenta-AI/agenta/pull/4380
  • [fix] Resolve broken create release branch workflow by @junaway in https://github.com/Agenta-AI/agenta/pull/4382
  • [fix] Resolve broken CORS headers by @junaway in https://github.com/Agenta-AI/agenta/pull/4381
  • [fix] Resolve Annotations created as Invocations if links={} by @junaway in https://github.com/Agenta-AI/agenta/pull/4385
  • [feat] Add parent slugs to revisions by @junaway in https://github.com/Agenta-AI/agenta/pull/4388
  • [FE] audit logs table by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4387
  • [FE Chore] Disable new behavior behind a flag by @ardaerzin in https://github.com/Agenta-AI/agenta/pull/4384
  • fix(ci): stop aliasing RAILWAY_API_TOKEN to RAILWAY_TOKEN by @mmabrouk in https://github.com/Agenta-AI/agenta/pull/4392
  • Increase DEFAULT_MAX_RENDER_DEPTH in BeautifiedJsonView to 100 by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4389
  • Use TraceSpanDrillInView for Exception when spanEntityId present by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/4390

Full Changelog: https://github.com/Agenta-AI/agenta/compare/v0.100.0...v0.100.1

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]