Auto mode now asks or denies calls the server cannot check when telemetry or flags are off, unless CLAUDE_CODE_AUTO_MODE_SERVER=0. New permissions.denyInsteadOfPrompting enables unattended runs without hanging on prompts. MCP tasks now background automatically.
Key takeaways · AI-distilled
Claude Code v2.1.319 changes auto mode with telemetry or feature flags off, including behind LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → gateways: calls the server can't check are asked about or denied, with no fallback to the built-in classifier. CLAUDE_CODE_AUTO_MODE_SERVER=0 keeps the classifier.
The release closes several permission and sandboxAn isolated environment where AI-generated code or agent actions run without being able to touch anything real.Full definition → holes: a crafted environment prefix that could hide part of a Bash command from permission checks, a sed command that could skip the check in accept-edits and auto mode, and a sandbox escape when creating a worktree.
A new permissions.denyInsteadOfPrompting setting denies any tool call that would wait on a permission prompt and lets the turn continue, in terminal sessions, subagents and teammates instead of waiting on an answer.
When an MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → server runs a tool call as a task, Claude Code now moves it to the background right away and tells Claude the result when it finishes. CLAUDE_CODE_DISABLE_MCP_TASK_BACKGROUND makes it wait instead; CLAUDE_CODE_DISABLE_MCP_TASKS=1 turns tasks off.
Self-paced /loop now ends when a turn finishes without rescheduling, instead of scheduling a fallback wakeup. Setting CLAUDE_CODE_LOOP_KEEPALIVE=1 keeps the old behavior.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
