GitLab's Duo Agent Platform and LLM proxy endpoints experienced rate limiting issues that caused errors when users attempted to access Claude models for 12.4 hours. The incident was resolved by implementing traffic filtering rules to block excessive requests, which reduced rate limit errors to near zero and restored Claude model availability. A permanent fix was deployed with continued monitoring for follow-up improvements.
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.
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
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
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
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
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6020 services available
Integrations with