This release adds 5 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+5 more
Summary
AI summaryAdds prompts UX improvements, ambiguous dataset assignment, copy_from coordination on createOrUpdateDatasetItems, online evaluation smoke test, and multi‑environment support per prompt version.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Improves prompts UX across playground, traces, and library. Improves prompts UX across playground, traces, and library. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Feature | Medium |
Assigns ambiguous datasets to their dominant project automatically. Assigns ambiguous datasets to their dominant project automatically. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Feature | Medium |
Copies coordinates on createOrUpdateDatasetItems and applies dataset item changes. Copies coordinates on createOrUpdateDatasetItems and applies dataset item changes. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Feature | Medium |
Adds Online Evaluation smoke test with LLM-judge and Python rule. Adds Online Evaluation smoke test with LLM-judge and Python rule. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Feature | Medium |
Supports multiple environments per prompt version. Supports multiple environments per prompt version. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Refactor | Low |
Retires config patterns and adds prompt-usage detection in snapshot. Retires config patterns and adds prompt-usage detection in snapshot. Source: llm_adapter@2026-05-28 Confidence: high |
— |
| Refactor | Low |
Updates automatically generated OpenAPI spec and Fern code in SDK documentation. Updates automatically generated OpenAPI spec and Fern code in SDK documentation. Source: llm_adapter@2026-05-28 Confidence: low |
— |
Full changelog
What's Changed
- [OPIK-6457] [FE] feat: prompts UX improvements across playground, traces, and library by @aadereiko in https://github.com/comet-ml/opik/pull/6771
- [OPIK-6465] [SDK] refactor(runner): retire config patterns, add prompt-usage detection in snapshot by @petrotiurin in https://github.com/comet-ml/opik/pull/6801
- [OPIK-6701] [BE] feat: assign ambiguous datasets to their dominant project by @andrescrz in https://github.com/comet-ml/opik/pull/6884
- [OPIK-6696] [BE] feat(datasets): copy_from coords on createOrUpdateDatasetItems + applyDatasetItemChanges by @JetoPistola in https://github.com/comet-ml/opik/pull/6867
- [OPIK-6597] [QA] feat: Online Evaluation smoke (LLM-judge + Python rule) by @AndreiCautisanu in https://github.com/comet-ml/opik/pull/6874
- [OPIK-6626] [BE] feat: support multiple environments per prompt version by @BorisTkachenko in https://github.com/comet-ml/opik/pull/6873
- [NA] [SDK] [DOCS] Update automatically OpenAPI spec and Fern code by @CometActions in https://github.com/comet-ml/opik/pull/6888
Full Changelog: https://github.com/comet-ml/opik/compare/2.0.49...2.0.50
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 opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Related context
Related tools
Earlier breaking changes
- v2.0.38 Split stats query and gate legacy feedback_scores UNION in BE.
Beta — feedback welcome: [email protected]