What this error means
Claude Code /context reports 200K context for claude-sonnet-4-6 instead of 1M (registry-stale bug) is a Claude Code failure pattern reported for developers trying to fix claude code /context command showing 200k instead of 1m context window for claude-sonnet-4-6. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
anthropics/claude-code issue #58710: Claude Code v2.1.140 shows /context reporting 200K for claude-sonnet-4-6 instead of expected 1M. Same registry-stale bug previously fixed for Opus 4.7. Affects Windows native build.
Common causes
- Claude Code users paying for Max plan expect 1M context with Sonnet 4.6 (per changelog 2.1.49), but /context shows only 200K. This is a registry-stale bug previously fixed for Opus 4.7 in v2.1.117 but not for Sonnet 4.6.
- anthropics/claude-code issue #58710: Claude Code v2.1.140 shows /context reporting 200K for claude-sonnet-4-6 instead of expected 1M. Same registry-stale bug previously fixed for Opus 4.7. Affects Windows native build.
Quick fixes
- Confirm the exact error signature matches
Claude Code /context reports 200K context for claude-sonnet-4-6 instead of 1M (registry-stale bug). - Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
- Compare the failing environment with a known working setup, then change one configuration value at a time.
Platform/tool-specific checks
- Verify the command, editor, extension, or API client that produced the error.
- Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
- Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- Keep the working fix documented for the team or deployment environment.
How to prevent it
- Keep provider/tool configuration documented.
- Record non-secret diagnostics such as tool version, provider name, model name, and command path.
- Add a lightweight check before CI or production workflows depend on the tool.