opik

v2.1.27 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 12d 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

Added ClickHouse partition‑health observability metrics.

Changes in this release

Type	Severity	Summary	CVE
Feature	Low	Adds ClickHouse partition-health observability metrics. Adds ClickHouse partition-health observability metrics. Source: llm_adapter@2026-07-14 Confidence: high	—
Feature	Low	Introduces single‑run optimization overview in the frontend. Introduces single‑run optimization overview in the frontend. Source: llm_adapter@2026-07-14 Confidence: high	—
Bugfix	Medium	Tolerates extra OpenAI usage keys and excludes litellm 1.92.* versions. Tolerates extra OpenAI usage keys and excludes litellm 1.92.* versions. Source: llm_adapter@2026-07-14 Confidence: high	—

Full changelog

What's Changed

[OPIK-6887] [BE] test: add partition-pruning and partition-stability staging gates by @andrescrz in https://github.com/comet-ml/opik/pull/7464
[NA] [SDK] fix: tolerate extra openai usage keys and exclude litellm 1.92.* by @alexkuzmik in https://github.com/comet-ml/opik/pull/7465
[OPIK-6904] Add ClickHouse partition-health observability metrics by @thiagohora in https://github.com/comet-ml/opik/pull/7458
[OPIK-7043] [FE] Single-run optimization overview by @awkoy in https://github.com/comet-ml/opik/pull/7310

Full Changelog: https://github.com/comet-ml/opik/compare/2.1.26...2.1.27

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.