openai / openai/codex

Codex App: Add per-tool timing and performance breakdown

Open
#40,087 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

app enhancement performance tool-calls
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

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

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the Codex App entry points for agent-run views and the existing timing or tool-call data. Define how a per-turn breakdown can show model/inference time, individual tool durations, and Codex overhead separately where possible. Done means the app presents a sortable list of tool calls with durations and an overall performance breakdown.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
desktop, observability
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.