openai / openai/codex

Improvements to the information provided by the command /status

Open
#40,916 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI enhancement rate-limits TUI
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of Codex CLI is running?

codex-cli 0.149.1

What subscription do you have?

Plus

Which model were you using?

gpt-5.6-sol

What platform is your computer?

Windows 11

What terminal emulator and version are you using (if applicable)?

Powershell through Visual Studio

Codex doctor report

What issue are you seeing?

› Currently, /status primarily shows remaining usage as a percentage for the 5-hour and weekly
limits, along with reset times. This makes it very difficult to understand how much capacity is
actually available or how expensive individual Codex operations are.

I would like to see:

  • The actual number of usage points/credits remaining and the total allowance, in addition to the
    percentage.

  • The usage cost of each completed Codex turn or command.

  • How much that operation deducted from both the 5-hour and weekly allowance.

  • Ideally, total usage consumed during the current session.

For example:

5-hour allowance:

38,420 / 45,000 remaining (85.4%)

Weekly allowance:

184,200 / 220,000 remaining (83.7%)

Last operation:

1,742 points consumed

Without this information, users cannot meaningfully budget their Codex usage. A percentage alone
tells us how depleted the allowance is, but not what any particular task costs.

The current experience is similar to receiving a monthly stipend but only being told what percentage
of it remains, while shopping in a store where none of the items display prices.

Even video games generally expose both the player's available resource pool and the cost of an action
before or after that resource is consumed. Codex should provide at least that level of transparency,
particularly because different development tasks can consume dramatically different amounts of the
available allowance.

This would make it much easier to decide whether there is enough capacity remaining to begin a large
implementation, run a comprehensive audit/test cycle, or save the remaining allowance for smaller
work.

• I’m using the OpenAI product guidance skill because this is feedback about Codex’s /status and usage
reporting. I’ll check whether exact point totals or per-operation costs are currently documented, then
give you a concise, actionable version of the request.

• Explored
└ Read SKILL.md

• Searched the web for site:developers.openai.com/codex usage limits status 5-hour weekly credits

• Searched the web for Codex usage limits 5-hour weekly status credits site:developers.openai.com

• Searched the web

────────────────────────────────────────────────────────────────────────────────────────────────────────

• This is a well-founded product request. The key improvement is not merely displaying more digits; it
is exposing a stable unit of consumption so users can estimate future work.

A useful /status response should include:

5-hour allowance
38,420 / 45,000 remaining (85.4%)
Resets in 2h 14m

Weekly allowance
184,200 / 220,000 remaining (83.7%)
Resets Monday at 00:00

Last turn
1,742 usage points
5-hour deduction: 1,742
Weekly deduction: 1,742

Current session
8,936 usage points consumed

Ideally, each completed turn would also show a breakdown such as model work, tool calls, delegated
agents, and retries—provided those categories genuinely affect the allowance.

The official documentation describes API pricing in tokens and API rate limits in RPM/TPM, but that is
distinct from Codex product-plan usage windows. I could not find official documentation exposing the
underlying 5-hour/weekly point totals or per-turn deductions. Consequently, percentages cannot
currently be translated reliably into credits, tokens, or API cost. OpenAI model and rate-limit
documentation (https://developers.openai.com/api/docs/models/gpt-5-codex)

The strongest requirements for a feature request are:

  • Show remaining and total units for every allowance window.
  • Show the exact deduction after each turn.
  • Show cumulative session consumption.
  • Define what a “usage point” represents, or explicitly describe it as a normalized internal unit.
  • Preserve percentages and reset times for quick scanning.
  • Expose the same information through /status and any graphical usage page.
  • Make usage data machine-readable so clients can display budgets and warnings.
  • If exact totals cannot be disclosed, show normalized units with a fixed total such as 100,000 per
    allowance rather than percentages alone.

That would make usage planning possible without requiring disclosure of proprietary model-cost
calculations.

What steps can reproduce the bug?

Uploaded thread: 01a036dc-0640-7412-87bb-9c6b24325551

What is the expected behavior?

I would like to see:

  • The actual number of usage points/credits remaining and the total allowance, in addition to the
    percentage.

  • The usage cost of each completed Codex turn or command.

  • How much that operation deducted from both the 5-hour and weekly allowance.

  • Ideally, total usage consumed during the current session.

For example:

5-hour allowance:

38,420 / 45,000 remaining (85.4%)

Weekly allowance:

184,200 / 220,000 remaining (83.7%)

Last operation:

1,742 points consumed

Without this information, users cannot meaningfully budget their Codex usage. A percentage alone
tells us how depleted the allowance is, but not what any particular task costs.

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 at the /status command entry point and review the uploaded thread 01a036dc-0640-7412-87bb-9c6b24325551 for the current usage-reporting context. Define what usage units and deductions are available before scoping the change. Done means /status reports remaining and total allowances, per-operation consumption, session usage, and reset information as requested.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
cli
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.