Skip to content

langfuse

v3.186.0 Feature

This release adds 5 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

Features added across blob-storage, datasets, media, session, scores, agents, monitors and fixes/improvements in experiments, annotation, batch-export, worker, api, anthropic, agent plus performance tweak; chores update CI, deps, docs.

Full changelog

What's Changed

Features

  • feat(blob-storage): block legacy export source for new Cloud exporters by @niklassemmler in https://github.com/langfuse/langfuse/pull/14044
  • feat(datasets): make default UI tab in datasets detail page by @marliessophie in https://github.com/langfuse/langfuse/pull/14223
  • feat(media): add upload rate limit budget by @hassiebp in https://github.com/langfuse/langfuse/pull/14226
  • feat(session): add root observation filter to session detail by @hassiebp in https://github.com/langfuse/langfuse/pull/14220
  • feat(scores): add api_version to ClickHouse log_comment tags by @niklassemmler in https://github.com/langfuse/langfuse/pull/14233
  • feat(agents): add housekeeping skill by @hassiebp in https://github.com/langfuse/langfuse/pull/14252
  • feat(agent): Show sources for agent answers by @bezbac in https://github.com/langfuse/langfuse/pull/14218
  • feat(monitors): add in-progress leading window to live preview by @marksalpeter in https://github.com/langfuse/langfuse/pull/14251

Fixes / Improvments

  • fix(experiments): add dataset selector to run experiments form by @marliessophie in https://github.com/langfuse/langfuse/pull/14204
  • fix(datasets): update id documentation and validation to enforce max length of 255 characters by @marliessophie in https://github.com/langfuse/langfuse/pull/14205
  • fix(annotation): support adding trace-level scores when in FP by @marliessophie in https://github.com/langfuse/langfuse/pull/13587
  • fix(batch-export): read observations from events table for v4 users by @niklassemmler in https://github.com/langfuse/langfuse/pull/14216
  • fix(worker): resolve app default export under tsx ESM interop by @sumerman in https://github.com/langfuse/langfuse/pull/14219
  • fix(api): don't let scores value operator override timestamp filters by @niklassemmler in https://github.com/langfuse/langfuse/pull/14217
  • fix(anthropic): remove default disabled thinking for fable and mythos by @hassiebp in https://github.com/langfuse/langfuse/pull/14221
  • fix(agent): Small improvements by @bezbac in https://github.com/langfuse/langfuse/pull/14248
  • perf(api): add redundant timestamp bound to scores v3 cursor for index pruning (LFE-10208) by @niklassemmler in https://github.com/langfuse/langfuse/pull/14230

Chores

  • ci: Add workflow to label PRs with merge conflicts by @bezbac in https://github.com/langfuse/langfuse/pull/13976
  • chore(deps): bump grpc-js to 1.14.4 by @nimarb in https://github.com/langfuse/langfuse/pull/14244
  • docs(agents): update weekly production review skill by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14253
  • chore: one more place to fix 422 alerting by @sumerman in https://github.com/langfuse/langfuse/pull/14255
  • chore(deps): bump esbuild to 0.28.1 by @nimarb in https://github.com/langfuse/langfuse/pull/14247
  • docs(agents): add weekly review alert load table by @maxdeichmann in https://github.com/langfuse/langfuse/pull/14256

Full Changelog: https://github.com/langfuse/langfuse/compare/v3.185.0...v3.186.0

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]