issue: #441649 (closed)
Related to &12224 (comment 1770963792)
Currently there is no metric to measure time spent by code completions request between Rails and AI gateway (latency added by sending request from Rails to AI gateway). We could use same approach as with rails queue duration: add timestamp to request headers and then calculate difference on AI gateway side similar to https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/middleware/rails_queue_duration.rb#L16
This assumes that time is accurate both on Rails and AI gateway server (in case of self-managed servers this may not be true).
Please evaluate this MR against the MR acceptance checklist. It helps you analyze changes to reduce risks in quality, performance, reliability, security, and maintainability.
Screenshots are required for UI changes, and strongly recommended for all other merge requests.
Before | After |
---|---|
Numbered steps to set up and validate the change are strongly suggested.
Related to #441649 (closed)