Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · models-context

Context usageCommon product term

Inspect consumed or remaining context budget during a conversation or run.

Terminology basis: Common product term. OpenAI — ChatGPT desktop slash commands

Context usage: 5 supported, 0 partial, 0 unsupported, 26 unreviewed across 31 cataloged products.

Markdown · JSON

Explore this familyMore in Models and context11 capabilities

Current evidence by product

Can my agent use Context usage?

Read across for the answer. 5 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported5
  • Partial0
  • Unsupported0
  • Unknown26
  • Not applicable0

Web

9 products

Desktop

13 products

CLI

9 products

Unknown means no public evidence has been reviewed for that product and capability. It does not mean unsupported.

How statuses are assigned

Definition and scope

What this capability means

This row asks whether the exact harness shows the operator how much context is in use or remains. An exact token count, a percentage estimate, and a warning shown only at exhaustion are materially different and should be qualified.

The most useful implementations identify contributions from conversation turns, project instructions, tool schemas, retrieved files, images or video, long-term memory, and reserved output. Evidence should also say whether the meter updates before a request, after server-side processing, or only in logs.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

ChatGPTdesktop · current
Supported
Target
current ChatGPT desktop documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/status shows the chat ID, context usage, and rate limits
Evidence
Codex CLIcli · current
Supported
Target
current Codex CLI documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimethe interactive interface displays remaining context as a percentage; the reviewed page does not document a component-by-component breakdown
Evidence
Claude CLIcli · current
Supported
Target
current Claude Code documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/usage and status-line fields expose token usage; /context identifies major context consumers such as MCP definitions
Evidence
Copilot Chatdesktop · current
Supported
Target
current VS Code agent-session documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimethe chat input control shows current usage, exact token count, a category breakdown, and the selected model's available context
Evidence
Copilot CLIcli · current
Supported
Target
current GitHub Copilot CLI context-management documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtime/context displays total usage plus token and percentage breakdowns for context components
Evidence
  1. 1. Evidence checked 2026-08-28: ChatGPT desktop documents /status as showing context usage; the Codex CLI interface documents remaining context in its session footer.
  2. 2. Evidence checked 2026-08-28: Claude Code documents /usage and a configurable status line for current token usage, plus /context for identifying major context consumers.
  3. 3. Evidence checked 2026-08-28: VS Code's context-window control reports token count, percentage usage, category breakdown, and session AI credits for agent chats.
  4. 4. Evidence checked 2026-08-28: GitHub Copilot CLI documents `/context` as a token-usage visualization and breakdown of the current context window.