Degraded LLMaJ execution in EU
Steady throughput for the last 30 minutes. Delay < 5min.
The latest update from Langfuse.
State
Resolved
Started
76 d ago
2026-08-18 12:06 UTC
Lasted
1 h 19 min
until 2026-08-18 13:25 UTC
Worst impact
Degraded
Timeline
4 updatesInvestigating
21 min 26%
Identified
20 min 26%
Monitoring
38 min 48%
Updates
Times in UTCAs posted by Langfuse
Steady throughput for the last 30 minutes. Delay < 5min.
our autoscaling responded slower than expected, but responded nonetheless. the backlog is draining
evaluation throughput was overwhelmed by a slow tenant/model workload, with lock-expiry retries multiplying work; the concurrent worker rollout prolonged the incident.
Eval execution in EU region is taking longer than usual
Langfuse in the last 90 days
Full historyIncidents in 90 days
17
Days with an incident
15
Median duration
1 h 12 min
This incident
About the median
Other Langfuse incidents
All incidentsLangfuse·Slow trace data retirival across API and UI in EU
should be finally resolved
Langfuse·Degraded performance in Halo (Langfuse Assistant)
Issue with Langfuse Halo (assistant) is fixed.
Langfuse·Degraded data serving in EU
Have been stable
Langfuse·Degraded public API performance
Problematic workload was identified and isolated.
Langfuse·Degraded ingestion for 20 projects
All projects ingesting as normal
Follow Langfuse
Your coding agent knows when Langfuse is down, and tells you when a failure is theirs, not yours. You can also get Langfuse incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "langfuse" and tell me if Langfuse has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.live/feed.xml?providers=langfuse/feed subscribe https://outages.live/feed.xml?providers=langfuseFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane