Repository navigation
Fix/chat response metrics - #682
Merged
Merged
Conversation
The Responses stream carries neither value, so fill them from the server's analytics row for the request, matched by token counts. Drop the redundant tok/s from the Decode label.
Peak memory regressed only on the Responses path added with compaction; leave it to a server-side fix rather than matching analytics rows.
lucasnewman
approved these changes
Oct 7, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I was testing prefill for previous prompt prs(#679) and saw that decode mispelling and prefill tok/s can be wired in from what server exposed.
verified the prefill numbers match what is already exposed in Dashboard