[Release] anthropics/claude-code v2.1.80: v2.1.80

Claude Code v2.1.80 introduces rate limit visibility in statusline scripts, inline plugin marketplace sourcing via settings.json, and enhanced effort level control through frontmatter. The release fixes critical issues with parallel tool results restoration, voice mode WebSocket failures, and API proxy compatibility. Performance improvements include ~80 MB memory savings on large repositories and better responsiveness for file autocomplete and UI interactions.

Key Points

• •Added `rate_limits` field to statusline scripts showing Claude.ai rate limit usage with 5-hour and 7-day windows, including `used_percentage` and `resets_at` timestamps
• •Introduced `source: 'settings'` plugin marketplace source to declare plugin entries directly in settings.json instead of external marketplace
• •Added `effort` frontmatter support for skills and slash commands to override model effort level at invocation time
• •Fixed `--resume` flag dropping parallel tool results — sessions now properly restore all tool_use/tool_result pairs instead of showing placeholders
• •Resolved voice mode WebSocket failures caused by Cloudflare bot detection on non-browser TLS fingerprints
• •Fixed 400 errors when using fine-grained tool streaming through API proxies, Bedrock, or Vertex AI
• •Added CLI tool usage detection to plugin tips alongside existing file pattern matching for smarter plugin recommendations
• •Improved startup performance by reducing memory usage ~80 MB on large repositories (250k+ files)
• •Enhanced UI responsiveness: Tab/arrow keys now work in `/sandbox` tab switching, `/permissions` tab navigation, and background tasks panel
• •Fixed managed settings (`enabledPlugins`, `permissions.defaultMode`, policy env vars) not applying at startup when `remote-settings.json` was cached

Workflow Diagram

Concepts