Skip to content

langfuse

v3.177.1 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 2d Tracing
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

analytics autogen evaluation langchain large-language-models llama-index
+12 more
llm llm-evaluation llm-observability llmops monitoring observability openai playground prompt-engineering prompt-management self-hosted ycombinator

Summary

AI summary

Updates Improvements / Fixes, mcp, and agents across a mixed release.

Changes in this release

Dependency Low

Bump axios dependency to version 1.16.0.

Bump axios dependency to version 1.16.0.

Source: llm_adapter@2026-06-01

Confidence: high

 —
Bugfix Medium

Normalize fields in queryMetrics tool.

Normalize fields in queryMetrics tool.

Source: llm_adapter@2026-06-01

Confidence: high

 —
Bugfix Medium

Update descriptions for createScore endpoint.

Update descriptions for createScore endpoint.

Source: llm_adapter@2026-06-01

Confidence: high

 —
Bugfix Medium

Prompt retrieval defaults to production environment.

Prompt retrieval defaults to production environment.

Source: llm_adapter@2026-06-01

Confidence: high

 —
Bugfix Medium

Improve description for 'latest' label in MCP.

Improve description for 'latest' label in MCP.

Source: llm_adapter@2026-06-01

Confidence: high

 —
Full changelog

What's Changed

Improvements / Fixes

  • docs(agents): warn against is_deleted filter on ClickHouse reads by @niklassemmler in https://github.com/langfuse/langfuse/pull/13965
  • fix(mcp): Improve description for 'latest' label by @bezbac in https://github.com/langfuse/langfuse/pull/13937
  • fix(mcp): Update score tool descriptions by @bezbac in https://github.com/langfuse/langfuse/pull/13936
  • fix(mcp): Prompt retrieval defaults to production by @bezbac in https://github.com/langfuse/langfuse/pull/13943
  • refactor(web): Align peek view detail components by @bezbac in https://github.com/langfuse/langfuse/pull/13964
  • fix(mcp): Be more liberal in accepting dataset input and output schema by @bezbac in https://github.com/langfuse/langfuse/pull/13938
  • chore(deps): bump axios to 1.16.0 by @nimarb in https://github.com/langfuse/langfuse/pull/13973
  • fix(mcp): Normalize fields in queryMetrics tool by @bezbac in https://github.com/langfuse/langfuse/pull/13942
  • fix(mcp): Update descriptions for createScore by @bezbac in https://github.com/langfuse/langfuse/pull/13945
  • refactor(datasets): Merge dataset services by @bezbac in https://github.com/langfuse/langfuse/pull/13962
  • refactor(code-evaluators): TS and python code formatting to auto-collapse comments by @marliessophie in https://github.com/langfuse/langfuse/pull/13972
  • docs: update readme banners by @jannikmaierhoefer in https://github.com/langfuse/langfuse/pull/13975

Full Changelog: https://github.com/langfuse/langfuse/compare/v3.177.0...v3.177.1

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 langfuse

Get notified when new releases ship.

Sign up free

About langfuse

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. YC W23

All releases →

Related context

Beta — feedback welcome: [email protected]