From the blog
All posts →
9 November 2026 Claude Code can deny permission prompts instead of waiting on them Claude Code 2.1.319 adds the permissions.denyInsteadOfPrompting setting. A tool call that would wait on a permission prompt is denied and the turn continues, in terminal sessions, subagents and teammates.
9 November 2026 Claude Code adds CLAUDE_CODE_DISABLE_FEATURE_FLAGS and changes auto mode when flags are off Claude Code 2.1.319 adds an environment variable that stops feature-flag fetching without turning off telemetry, and changes auto mode so that sessions with flags off no longer fall back to the built-in classifier unless you set CLAUDE_CODE_AUTO_MODE_SERVER=0.
9 November 2026 Claude Code runs MCP tasks in the background Claude Code 2.1.319 supports MCP tasks in the terminal. When an MCP server runs a tool call as a task, Claude Code backgrounds it and reports the result when it finishes. Two environment variables turn this off.
9 November 2026 Claude Code's self-paced /loop now ends if an iteration doesn't reschedule Claude Code 2.1.319 changes self-paced /loop so a turn that finishes without rescheduling ends the loop, instead of getting one fallback wakeup. Set CLAUDE_CODE_LOOP_KEEPALIVE=1 to keep the old behavior.
9 November 2026 Cursor CLI's Grep and Glob now search folders outside the workspace Since Cursor CLI v2026.10.15, Grep and Glob search a folder outside your open workspace when the agent asks for one, instead of quietly searching the workspace and returning results from the wrong place.
9 November 2026 Antigravity CLI replaces Gemini CLI for individual accounts Since June 18, 2026, Gemini CLI no longer serves free or Google AI Pro and Ultra accounts; those users moved to Antigravity CLI. Gemini CLI continues for Gemini Code Assist enterprise customers, and The Loop now tracks Antigravity CLI instead.
5 November 2026 Cursor CLI post-tool hooks now fire for subagents Since Cursor CLI v2026.10.17, postToolUse and postToolUseFailure hooks that match the Task tool run when a subagent finishes or fails, and hooks inside a subagent receive the subagent's own transcript path.
29 October 2026 Claude Code caps concurrent prompt and agent hooks Version 2.1.312 limits prompt and agent hooks to 24 running at a time per session, subagents included, plus 12 that have waited past their event's timeout, and rounds any timeout under one second up to one second.
Built from upstream documentation. A stale badge means the last scheduled refresh could not reach the docs.