[BUG] Context usage panel: “Usage” column label is misleading next to “Free space”
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 64/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- typescript
- Domain
- cli
Research direction
Start by locating the /context panel and the code that labels its last column and renders the “Free space” row. Check how the displayed percentages are calculated and compare them with the header’s usage figure. Done means the column label or free space presentation no longer makes available context look like used context.
Written by the indexing model from the issue text.
Description
Preflight Checklist
- I have searched existing issues and this hasn't been reported yet
- This is a single bug report (please file separate reports for different bugs)
- I am using the latest version of Claude Code
What's Wrong?
Title: Context usage panel: "Usage" column label is misleading next to "Free space"
Description:
In the /context panel, the last column is labeled "Usage". Every row shows a percentage of the total context window, including "Free space", which reads "85.1%". At a glance this looks like 85% of the context has been used, when it's actually 85% still available. The real usage (12%) only appears in the header.
Environment: Claude Code, model claude-opus-5-5, 1M context window. Screenshot attached.
What Should Happen?
Suggestion:
Rename the column to something neutral, like "% of total" or "Share". Alternatively, show "Free space" separately from the used categories, for example as a summary line ("851k tokens available").
Error Messages/Logs
Steps to Reproduce
- Open Claude Code (VS Code extension) and start a session with claude-opus-5-5 (1M context window)
- Have a short conversation so some context is used (~115k tokens in my case)
- Open the "Context usage" panel (click the context indicator, or run /context)
- Look at the "USAGE" column: the "Free space" row shows "85.1%"
- Compare with the header, which shows the real usage: "115.8k / 1.0M tokens (12%)"
Result: because the column is labeled "USAGE", the 85.1% next to "Free space" reads at first glance as "85% used", while it actually means 85% still available.
Claude Model
Opus
Is this a regression?
Yes, this worked in a previous version
Last Working Version
No response
Claude Code Version
2.1.322.
Platform
Other
Operating System
Windows
Terminal/Shell
PowerShell
Additional Information
No response
- Dominant language
- TypeScript
- Stars
- 156k
- Forks
- 25k
- Avg merge
- 12h 27m
- Merged PRs (30d)
- 4
Getting set up
Starts the project's dev container in your browser, under your own GitHub account.
- No Dockerfile or Docker Compose file
- No pull request template
- No contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from anthropics/claude-code
-
area:agent-sdk area:docs documentation enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
anthropics/claude-code#110914 ·
-
area:tui bug has repro platform:linux regression
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
anthropics/claude-code#110876 ·
-
area:desktop area:ui bug platform:macos
Difficulty 2/5 1-3 hours Newbie friendliness 61/100
anthropics/claude-code#110835 ·
-
area:hooks area:plugins area:skills enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
anthropics/claude-code#110517 ·
-
area:installation enhancement platform:windows
Difficulty 1/5 Under an hour Newbie friendliness 84/100
anthropics/claude-code#110491 ·
All issues in anthropics/claude-code
Similar issues
-
bot:ai-assisted component:platform-js status:untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
midnightntwrk/platform-js#69 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
Picolab/pico-engine#668 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
Maintainers usually reply within 1 day
-
ai-driven-qa bug claude Cosmetic
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
Maintainers usually reply within 1 day
-
needs verification
Difficulty 2/5 1-3 hours Newbie friendliness 64/100
Maintainers usually reply within 13 days