Code assistantsclaude.com12 published changes
Users can now enforce a maximum effort level globally or per model, with the ability to select lower levels as needed. Affects organizations managing Claude Code settings.
Users can now force all subagents to use a specific model via CLAUDE_CODE_SUBAGENT_MODEL_FORCE, overriding per-spawn and agent-definition model overrides.
Users now have access to Claude Fable 5.1 (claude-fable-5-1) as the default Fable model with 1M context window, priced at $10/$50 per Mtok with $0.25/Mtok cache reads for improved performance.
Mac users running Bash commands will no longer encounter 'task output swap refused' errors when task directories are moved or linked.
Users will see when their session or weekly spend limits reset when they reach their monthly limit.
Users can now set a default model for new sessions via environment variable, with /model picker still allowing overrides that persist across restarts
Developers using MCP with pre-registered OAuth clients like Slack can now successfully authenticate without redirect URI mismatches.
Users on Pro, Max, and Team plans will no longer see a misleading note about auto mode pricing in first-use notices.
Resolved a security vulnerability where crafted Bash commands could evade permission checks
Users must now explicitly invoke /verify and /code-review commands instead of Claude running them automatically, giving users more control over when these skills execute.
Developers can now use message.uuid, client_request_id, and tool_source attributes in OpenTelemetry logs to correlate messages and track tool origins.
Fixed critical security issues including permission check bypasses in PowerShell, file-descriptor redirect handling, and auto-approval vulnerabilities in bash permission checks.