You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
It would be useful to have a simple performance view that shows where an agent run spent its time, especially the duration of each individual tool call.
I know there have already been requests for per-turn stats and improved tool-call rendering (#2518, #3853), but I’m specifically interested in using the timing data to find performance bottlenecks.
For example, being able to sort tool calls by duration would make it easy to identify slow commands, tests, searches, MCP calls, etc. and optimize them.
Ideally it would also show total model/provider time vs. tool execution time, and distinguish actual tool execution from T3 Code/orchestration overhead where possible.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
It would be useful to have a simple performance view that shows where an agent run spent its time, especially the duration of each individual tool call.
I know there have already been requests for per-turn stats and improved tool-call rendering (#2518, #3853), but I’m specifically interested in using the timing data to find performance bottlenecks.
For example, being able to sort tool calls by duration would make it easy to identify slow commands, tests, searches, MCP calls, etc. and optimize them.
Ideally it would also show total model/provider time vs. tool execution time, and distinguish actual tool execution from T3 Code/orchestration overhead where possible.
All reactions