Skip to content

langfuse

v3.194.0 Feature

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

Published 1mo 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

Added model price audit dry run to agents, fixed max turns checks in ci-model-price-audit and ci-model-prices, and introduced a metric for ingestion failure projects.

Full changelog

What's Changed

  • fix(ci-model-price-audit): max turns check by @hassiebp in https://github.com/langfuse/langfuse/pull/14410
  • fix(ci-model-prices): max turns check by @hassiebp in https://github.com/langfuse/langfuse/pull/14411
  • fix(agents): add model price audit dry run by @hassiebp in https://github.com/langfuse/langfuse/pull/14412
  • feat(worker): blob export raw-passthrough path (LFE-10402) by @niklassemmler in https://github.com/langfuse/langfuse/pull/14400
  • chore: introduing a metric indicating how many projects are experiencing ingestion failures by @sumerman in https://github.com/langfuse/langfuse/pull/14403
  • fix(agents): avoid boolean dry-run choice by @hassiebp in https://github.com/langfuse/langfuse/pull/14413
  • chore(pricing): update default model prices by @langfuse-bot in https://github.com/langfuse/langfuse/pull/14414

New Contributors

  • @langfuse-bot made their first contribution in https://github.com/langfuse/langfuse/pull/14414

Full Changelog: https://github.com/langfuse/langfuse/compare/v3.193.0...v3.194.0

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

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]