Rate Limit Errors on Claude modelsDegraded Performance
Resolved
Updates
Resolved
After a period of monitoring we have not observed a recurrence of the issue and are considering it resolved.
Monitoring
We've confirmed the traffic filtering rules are applied, with errors dropping to near zero. Claude models should be available now. A permanent fix has been merged and deployment is in progress. We continue monitoring and working on follow-up improvements. More details: https://gitlab.com/gitlab-com/gl-infra/production/-/work_items/21672
Identified
We've applied traffic filtering rules to block the primary source of excess requests to our endpoints. We're seeing a significant drop in rate limit errors and are continuing work on permanent fixes. More details: https://gitlab.com/gitlab-com/gl-infra/production/-/work_items/21672
Investigating
As we continue investigating, we're working on immediate mitigation steps. Additional information can be found in: https://gitlab.com/gitlab-com/gl-infra/production/-/work_items/21672
Investigating
We continue investigating the issue, no material updates to report. Additional information can be found in: https://gitlab.com/gitlab-com/gl-infra/production/-/work_items/21672
Investigating
We are currently investigating an issue with Duo Agent Platform and LLM proxy endpoints hitting rate limits. Users may experience errors using Claude models. We recommend switching to a different model as a workaround.