Claude Code 2.1.269
Version 2.1.269 adds a plugin eval command, output style switching in headless sessions, and higher Workflow agent concurrency.
Claude Code 2.1.269 adds a command for testing plugins: claude plugin eval runs a plugin's eval suite against Claude Code and returns scored, reproducible results as a JSON and HTML report.
- /output-style [name] now lists and switches output styles, including over Remote Control and in cloud or other headless sessions.
- When the Bash tool handles file edits, its result can now include a diff of the files a command changed, controlled by the bashEditDiffEnabled setting.
- A new spinner tip points to /focus, a view showing just the prompt, a one-line work summary, and the response.
- CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS raises the Workflow tool's per-run concurrent agent limit, from 1 to as high as 256, for inference-bound fan-outs.
The release also fixes the prompt cache being partially invalidated on the turn after a response was cut off at the output-token limit and automatically resumed.
Claude Code
Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud.
View Claude Code →