Skip to main content
Menu
LangSmith

Incident

Partial ingestion failures for traces with large payloads

Partial outage Lasted 16h 37m · started · LangSmith's page

DWN-7933072dd1

Level
confirmed
Worst impact
Partial outage
Down Index
57of 100

What to do

  • Check whether your product depends on LangSmith. Check your stack

    Drop a package.json, lockfile, Terraform or a list of domains at down.guide to see every provider you depend on.
  • Confirm your retries, queues and scheduled jobs caught up after the 16h 37m it lasted.

    Anything that failed between 2026-08-06 15:03 UTC and 2026-08-07 07:40 UTC may need a replay.
  • Subscribe to LangSmith's feed to hear about the next one first. RSS feed

    https://down.guide/feed?provider=langsmith works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Root cause

The full fix took an extraordinarily long time to release due to an outage at our CI provider.

Category: Deploy or config change

Read the postmortem

Updates from LangSmith 4

  1. identified

    Traces including large payloads might currently fail to be ingested or can be delayed. We are working on a fix.

    provider

  2. identified

    Updated affected regions

    provider

  3. monitoring

    The service is temporarily patched. Large payloads are now ingested normally.

    provider

  4. resolved

    The full fix took an extraordinarily long time to release due to an outage at our CI provider. In the meantime, the mitigation we had deployed mitigated the problem.

    provider

Reports count in aggregate; nothing about you is shown.

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.

Questions about DWN-7933072dd1

Is LangSmith still down?

No, this incident was resolved 2026-08-07 07:40 UTC. For LangSmith's live state, see https://down.guide/providers/langsmith.

How long did it last?

16h 37m, from 2026-08-06 15:03 UTC to 2026-08-07 07:40 UTC, by the times LangSmith posted.

What caused it?

Deploy or config change. LangSmith wrote: "The full fix took an extraordinarily long time to release due to an outage at our CI provider." The postmortem: https://global.status.smith.langchain.com/incidents/01KZBSKVD5VBN0TD0K8143WHWB

Where does this come from?

LangSmith's official status page, https://global.status.smith.langchain.com/gcp-us, quoted verbatim. down.guide's own probes, reports and social counts are labeled as ours.