Don't count tool waits in output speed - #530
Open
Adam-Dalloul wants to merge 2 commits into
Open
Conversation
Contributor
Author
|
Pulled it off the status bar. Average tok/s now lives in Session Details and on the Token Usage page. |
The live tok/s reading was averaging in time spent waiting on tools, so a fast model looked slow whenever a command was running. Pause the clock while a tool is in flight, hold the last generating rate, and keep a session average of tokens over generating time only. Show that average in Session Details, the composer token popover, and the bottom-left status bar.
Keep the live generating rate off the status bar. Persist the average on the session itself (Session Details) and on the Token Usage page: a generation-time headline plus tok/s on each heaviest-session row.
Adam-Dalloul
force-pushed
the
feat/generating-only-output-speed
branch
from
August 22, 2026 16:29
7f97572 to
fe74cbd
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The live tok/s number was folding in time spent waiting on tools, so a fast model looked slow whenever a command was running.
This pauses the clock while a tool is in flight, holds the last generating rate, and keeps a session average of tokens over generating time only. That average shows up in Session Details, the composer token popover, and the bottom-left status bar.
A slow stream with no tool still counts the quiet gaps, so a trickle is not reported as fast.