opik

v2.0.60 Feature

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

Published 1mo Error & Performance Tracking

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

evaluation hacktoberfest2025 langchain llama-index llm llm-evaluation

+5 more

llm-observability llmops openai playground prompt-engineering

Summary

AI summary

Add evaluate_resume to SDK and UI for resuming interrupted evaluations.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds ability to evaluate experiment traces from UI. Adds ability to evaluate experiment traces from UI. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Medium	Adds evaluate_resume method to SDK for continuing interrupted evaluations. Adds evaluate_resume method to SDK for continuing interrupted evaluations. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Low	Implements MCP OAuth 2.1 foundations (schema, config, domain, persistence, service). Implements MCP OAuth 2.1 foundations (schema, config, domain, persistence, service). Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Low	Adds E2E failure investigation tooling (/comet:investigate-e2e-failure + debugging‑e2e‑tests skill). Adds E2E failure investigation tooling (/comet:investigate-e2e-failure + debugging‑e2e‑tests skill). Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix	Low	Fixes JSLinter issue in frontend code. Fixes JSLinter issue in frontend code. Source: llm_adapter@2026-06-10 Confidence: high	—
Refactor	Low	Reverts thread time range change in ThreadDetailsPanel traces query. Reverts thread time range change in ThreadDetailsPanel traces query. Source: llm_adapter@2026-06-10 Confidence: high	—

Full changelog

What's Changed

[NA] [QA] docs: self-serve E2E test authoring (/add-e2e-test + writing-e2e-tests skill) by @AndreiCautisanu in https://github.com/comet-ml/opik/pull/6992
[NA] [BE][FE] chore: sync provider model definitions by @CometActions in https://github.com/comet-ml/opik/pull/7001
[OPIK-6737] [FE] Add Ability to Evaluate Experiment Traces from UI by @yaricom in https://github.com/comet-ml/opik/pull/6999
[NA] [FE] JSLinter fix by @yaricom in https://github.com/comet-ml/opik/pull/7005
[OPIK-5269] [SDK] feat: add evaluate_resume to continue interrupted evaluations by @alexkuzmik in https://github.com/comet-ml/opik/pull/6941
[OPIK-5269] [DOCS] docs: add page on resuming interrupted evaluations by @alexkuzmik in https://github.com/comet-ml/opik/pull/6950
[OPIK-6385] [FE] revert: thread time range in ThreadDetailsPanel traces query by @andriidudar in https://github.com/comet-ml/opik/pull/7007
[OPIK-6666] [BE] feat: MCP OAuth 2.1 foundations (PR 1/7) — schema, config, domain, persistence, service by @LifeXplorer in https://github.com/comet-ml/opik/pull/6979
[NA] [QA] feat: E2E failure investigation tooling (/comet:investigate-e2e-failure + debugging-e2e-tests skill) by @AndreiCautisanu in https://github.com/comet-ml/opik/pull/7003

Full Changelog: https://github.com/comet-ml/opik/compare/2.0.59...2.0.60

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 opik

Get notified when new releases ship.

About opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

All releases →

Related context

Related tools

Earlier breaking changes

v2.0.63 Span search now supports last_updated_at and created_at filter parameters.
v2.0.57 Make enum-fix migration rollback empty for in‑place column changes
v2.0.38 Split stats query and gate legacy feedback_scores UNION in BE.