Eliminate Workflow Interruptions with AI-Driven Auto Approval for Routine Terminal Tasks
Automate routine approvals to keep your focus on high-level logic.
Enable the 'Auto Approval' feature to skip manual confirmation for routine, safe agent actions based on LLM-driven risk classification.
The Scenario
You are running a long-running agentic task that involves many file reads and minor edits, and you want to avoid being interrupted for every single routine operation.
Before & after
You must watch the terminal and manually type 'Y' or click 'Approve' for every small file read or terminal command the agent suggests. This adds 5–10 minutes of wait time and distraction per hour.
Enable Auto Approval in Qwen Code settings. The agent uses an LLM classifier to self-approve safe operations, completing them in seconds without bothering you.
The Prompt
/config set auto_approval true
Auto Approval intelligently distinguishes between routine safe actions (like reading a file) and destructive actions (like deleting a directory), only prompting for the latter.
Source
Blog | Qwen Code Docs"Auto Approval uses an LLM classifier to decide whether human confirmation is needed, so routine operations stop interrupting you."
