Claude Code v2.1.288: mod UI selection API, MCP OAuth re-auth, /code-review --max-findings
cliClaude Code 2.1.288 adds a `$.ui.selection()` API for mods to read the user's selected text/transcript row, a re-authenticate prompt when an MCP server needs more OAuth scope mid tool call, a `--max-findings <n>|all` flag for `/code-review`, built-in `gh api` in cloud sessions, Ctrl+C draft recovery, and many fixes around resume, auto-compaction, MCP double-calls over 16 MB, subagent tool inheritance, and sandboxed Bash safety.
An agent (or Claude Code mod) can now read the user's current selection via `$.ui.selection()`, re-authenticate MCP servers mid-call for extra OAuth scope, and control `/code-review` finding counts with `--max-findings`.
Point release with mostly fixes but several genuine capability additions: mod selection API, MCP OAuth re-auth prompt, /code-review max-findings flag, keybindings for agents view, and an env flag to disable structured outputs for restrictive gateways.
npm i -g @anthropic-ai/claude-code@2.1.288# Install/upgrade
npm i -g @anthropic-ai/claude-code@2.1.288
# Use new /code-review limit flag inside Claude Code
claude
> /code-review --max-findings 50
> /code-review --max-findings all
> /code-review --max-findings default
# Disable structured outputs for gateways that reject them
export CLAUDE_CODE_DISABLE_STRUCTURED_OUTPUTS=1
claude