
Announcing our updated Responsible Scaling Policy
Today we are publishing a significant update to our Responsible Scaling Policy (RSP), the risk governance framework we use to mitigate potential catastrophic risks from frontier AI systems.
AI tools for coding: Cursor, Copilot, Claude Code, v0, Bolt

Today we are publishing a significant update to our Responsible Scaling Policy (RSP), the risk governance framework we use to mitigate potential catastrophic risks from frontier AI systems.
What's changed Added MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL) Added new Elicitation and ElicitationRes...
What's changed Increased default maximum output token limits for Claude Opus 4.6 to 64k tokens, and the upper bound for Opus 4.6 and Sonnet 4.6 models to 128k tokens Added allowRead sandbox filesy...
What's changed Added StopFailure hook event that fires when the turn ends due to an API error (rate limit, auth failure, etc.) Added ${CLAUDE_PLUGIN_DATA} variable for plugin persistent state that...
What's changed Added --console flag to claude auth login for Anthropic Console (API billing) authentication Added "Show turn duration" toggle to the /config menu Fixed claude -p hanging when spawn...
What's changed Added rate_limits field to statusline scripts for displaying Claude.ai rate limit usage (5-hour and 7-day windows with used_percentage and resets_at) Added source: 'settings' plugin...
What's changed Added --bare flag for scripted -p calls — skips hooks, LSP, plugin sync, and skill directory walks; requires ANTHROPIC_API_KEY or an apiKeyHelper via --settings (OAuth and keychain ...
What's changed Added managed-settings.d/ drop-in directory alongside managed-settings.json, letting separate teams deploy independent policy fragments that merge alphabetically Added CwdChanged an...
What's changed Added PowerShell tool for Windows as an opt-in preview. Learn more at https://code.claude.com/docs/en/tools-reference#powershell-tool Added ANTHROPIC_DEFAULT_{OPUS,SONNET,HAIKU}_MOD...
What's changed Added CLAUDE_CODE_MCP_SERVER_NAME and CLAUDE_CODE_MCP_SERVER_URL environment variables to MCP headersHelper scripts, allowing one helper to serve multiple servers Added conditional ...
What's changed Added X-Claude-Code-Session-Id header to API requests so proxies can aggregate requests by session without parsing the body Added .jj and .sl to VCS directory exclusion lists so Gre...

We apply online reinforcement learning to Composer, serving model checkpoints to production and using real user interactions as reward signals to ship an improved checkpoint multiple times a day.