What variant of Codex are you using?
App
What feature would you like to see?
It would be useful to have a simple performance/timing view directly in the Codex app that shows where an agent run spent its time.
In particular, I’d like to see how much time was spent on model/inference vs. tool calls, and the duration of each individual tool call. This would make it easy to identify slow commands, tests, searches, MCP calls, etc. and optimize them.
Ideally it would also distinguish actual tool execution time from Codex overhead/waiting where possible, so a command that runs in 100 ms but takes Codex 5 seconds end-to-end doesn’t look like a slow command.
Something as simple as a per-turn breakdown with a sortable list of tool calls and their durations would already be very useful.
Additional information
No response
What variant of Codex are you using?
App
What feature would you like to see?
It would be useful to have a simple performance/timing view directly in the Codex app that shows where an agent run spent its time.
In particular, I’d like to see how much time was spent on model/inference vs. tool calls, and the duration of each individual tool call. This would make it easy to identify slow commands, tests, searches, MCP calls, etc. and optimize them.
Ideally it would also distinguish actual tool execution time from Codex overhead/waiting where possible, so a command that runs in 100 ms but takes Codex 5 seconds end-to-end doesn’t look like a slow command.
Something as simple as a per-turn breakdown with a sortable list of tool calls and their durations would already be very useful.
Additional information
No response