Skip to content

langfuse

v3.203.2 Feature

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

Published 24d 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

Broad release touches Chores, web, trace, and agent.

Full changelog

What's Changed

Features

  • feat(agent): Add langfuse skills by @bezbac in https://github.com/langfuse/langfuse/pull/14621
  • feat(agent): Auto-rename conversations by @bezbac in https://github.com/langfuse/langfuse/pull/14592

Fixes

  • fix(ci): run test jobs with NODE_ENV test by @wochinge in https://github.com/langfuse/langfuse/pull/14683
  • fix(assistant): trace rejected tool calls by @nimarb in https://github.com/langfuse/langfuse/pull/14676
  • fix(clickhouse): quote heredoc in dev-tables.sh by @insilications in https://github.com/langfuse/langfuse/pull/14422
  • fix(web): close provider dropdown before opening New LLM Connection dialog (LFE-10615) by @nkabardin in https://github.com/langfuse/langfuse/pull/14693
  • fix(trace): stop v4 tree/search rows overlapping with many scores (LFE-10591) by @nkabardin in https://github.com/langfuse/langfuse/pull/14691
  • fix(v4): show evenly spaced usage chart y-axis ticks by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14699
  • fix(trace): guard markdown rendering against stack overflow on deeply nested payloads (LFE-10604) by @nkabardin in https://github.com/langfuse/langfuse/pull/14690
  • fix(monitors): restore Type/Level filter value options (LFE-10616) by @nkabardin in https://github.com/langfuse/langfuse/pull/14701
  • fix(trace): Improve styling of tool cards for tools with long names by @bezbac in https://github.com/langfuse/langfuse/pull/14688
  • fix(web): render media refs in compact table rows by @wochinge in https://github.com/langfuse/langfuse/pull/14703
  • fix: ensure hasAny* tRPC checks run against readonly events server pool by @sumerman in https://github.com/langfuse/langfuse/pull/14709
  • fix(agent): Refocus input after generation by @bezbac in https://github.com/langfuse/langfuse/pull/14707
  • fix(api-keys): Add details on usage with MCP server by @bezbac in https://github.com/langfuse/langfuse/pull/14705
  • fix(web): allow public trace access in v4 events routes by @Steffen911 in https://github.com/langfuse/langfuse/pull/14717
  • fix(trace): comfortable peek defaults, unify inner-split persistence (LFE-10601) by @nkabardin in https://github.com/langfuse/langfuse/pull/14716
  • fix(search-bar): keep caret in filter on operator pick; blank value stays unarmed (LFE-10501) by @nkabardin in https://github.com/langfuse/langfuse/pull/14714
  • fix(evals): improve code eval error surfacing and retry behavior by @wochinge in https://github.com/langfuse/langfuse/pull/14726
  • fix(worker): add Google AI Studio model fallback by @wochinge in https://github.com/langfuse/langfuse/pull/14728
  • perf(filters): load event filter options lazily, per-facet on demand (LFE-10519) by @nkabardin in https://github.com/langfuse/langfuse/pull/14617

Chores

  • refactor(web): Create & enable require-title-with-truncate eslint rule by @bezbac in https://github.com/langfuse/langfuse/pull/14661
  • chore: fix v4 usage y axis by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14695
  • docs(mcp): clarify trace fetching via observations by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14696
  • docs(mcp): pluralize traces in observations tool by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14697
  • docs(agents): document local database clients by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14698
  • chore(v4): remove CTA banners by @nimarb in https://github.com/langfuse/langfuse/pull/14706
  • chore(storybook): Simplify .mdx stories by @bezbac in https://github.com/langfuse/langfuse/pull/14711
  • feat(worker): add sfdc org id, user auth methods, and sso domain data to core data export by @Steffen911 in https://github.com/langfuse/langfuse/pull/14713
  • feat(worker): add event-propagation stuck health check by @Steffen911 in https://github.com/langfuse/langfuse/pull/14680

New Contributors

  • @insilications made their first contribution in https://github.com/langfuse/langfuse/pull/14422

Full Changelog: https://github.com/langfuse/langfuse/compare/v3.203.1...v3.203.2

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]