This release includes 1 breaking change for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+12 more
ReleasePort's take
Light signalThis 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 summaryUpdates agents, fix, and Fix across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| 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
prettyby @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
About Agenta
LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.
Related context
Related tools
Earlier breaking changes
- v0.100.7 Renames providers table Status column to API Key.
Beta — feedback welcome: [email protected]