Skip to content
Agents tracked: 502 Releases (7d): 613 Agent status: 4 with issuesSince last limit reset: Claude 7d · Codex 5d For AI agents: Markdown Updated Nov 18, 2026

Langfuse known issues, errors and fixes

What Langfuse users report right now: 1 open problem, 1 fixed and 1 answered question, from its GitHub repository, written up by AgentGid. Workarounds and fix versions come only from official sources. Checked Nov 12, 2026.

← Langfuse: pricing, features and usage · All user reports

Open Oct 5, 2026

Users report that the dashboard's User consumption card shows a 'Total cost' that adds up only the top 20 users, so it undercounts when more users have costs; one report shows $46.43 against $92.36 across 479 users. The issue is open.

Reported on GitHub · 6 👍

Security Fixed in 4.70.1 Oct 22, 2026

Users report that Langfuse's self-hosted Docker images shipped Node.js 24.21.0, without Node's October 2026 security release (24.22.1). Version 4.70.1 moved to Node 24.22.1; when 4.72.0 went back to Red Hat's Node package, the team said it applies the needed security patches to that package itself.

Reported on GitHub · 5 👍 · fix source

Questions Langfuse users ask

Answered from the official documentation.

Can I put a unit, such as characters, into usage_details when sending usage to Langfuse over OpenTelemetry?

The docs treat usage_details as counts per usage type: every key is its own bucket, and total is the sum of the buckets. Prices in a model definition are set per usage type and must match the usage_details keys exactly, so a non-token unit goes into the key name (for example input_characters), together with a custom model definition priced on those keys.

Source · Source · Where it was asked

Reports are users' accounts from public GitHub issues and discussions, not AgentGid tests. AgentGid writes each one in its own words; statuses, fix versions and workarounds come from the project's own pages, release notes and maintainers.