Regression: Codex Desktop has no persistent context/token usage indicator

Open
#33,407 2 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
42/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Quiet
Tech stack
rust
Domain
desktop

Research direction

The payload names no Desktop files or tests. Start by comparing the Desktop task/status controls with the existing CLI/TUI status UI, then trace where model, context, compaction, and token totals are exposed. Done means a persistent or opt-in Desktop indicator distinguishes context occupancy from cumulative totals and warns about compaction.

Written by the indexing model from the issue text.

Description

app bug context rate-limits

Summary

Codex Desktop no longer shows a persistent, user-visible context and token usage indicator comparable to the Codex CLI/TUI status display.

The information is operationally important in long-running tasks: users need to know the active model, current context-window pressure/remaining budget, cumulative input and output token totals, and when compaction is approaching or has occurred.

Environment

  • Codex Desktop: 26.707.9981.0
  • Codex CLI installed locally: 0.144.4
  • OS: Windows
  • Model available in the CLI: gpt-5.6-sol

Steps to reproduce

  1. Open Codex Desktop.
  2. Start or open any task.
  3. Look near the composer, model selector, and task/status controls.
  4. There is no persistent context/token usage indicator or tooltip.

Actual behavior

The Desktop UI does not expose the live context-window usage, remaining context, input/output token totals, or a persistent model/status display. The CLI/TUI provides this information through its status UI, but the Desktop app does not provide an equivalent passive display.

Expected behavior

Restore an opt-in or always-visible Desktop status indicator, ideally near the composer or model selector, with:

  • Active model/provider
  • Current context usage and remaining effective context window
  • Cumulative input, cached-input, and output token totals
  • Clear separation between current context-window occupancy and cumulative session/thread totals
  • Compaction status or a warning before automatic compaction

This is not merely a cosmetic preference; without the indicator, users cannot reliably decide when to compact, fork, or start a new task before context pressure affects work quality.

Related reports

Similar reports were filed as #23794, #23591, and #18201. This report confirms that the problem persists in a newer Desktop build.

Dominant language
Rust
Stars
125k
Forks
19.5k
Avg merge
1m
Merged PRs (30d)
1k

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.

More from openai/codex

All issues in openai/codex

Similar issues

More Rust issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.