Approval

Require human approval before sensitive actions

Approval mode requires human confirmation before agents execute sensitive operations.

Quick Start

1. Configure Approval with AutonomyConfig

   use praisonai::AutonomyConfig;
   
   // Create config that requires approval (default)
   let config = AutonomyConfig::new();
   // require_approval is true by default
   
   // Or disable approval
   let no_approval = AutonomyConfig::new()
       .no_approval();
   
   println!("Approval required: {}", config.require_approval);  // true
   println!("Approval required: {}", no_approval.require_approval);  // false

2. Block Dangerous Tools

   use praisonai::AutonomyConfig;
   
   let config = AutonomyConfig::new()
       .block_tool("delete_file")
       .block_tool("rm_directory")
       .max_actions(10);  // Pause after 10 autonomous actions

3. Allow Specific Tools

   use praisonai::{AutonomyConfig, AutonomyLevel};
   
   let config = AutonomyConfig::new()
       .level(AutonomyLevel::Limited)
       .allow_tool("read_file")
       .allow_tool("search")
       .allow_tool("list_dir");

How It Works

AutonomyConfig

Configuration for agent autonomy and approval behavior.

pub struct AutonomyConfig {
    pub level: AutonomyLevel,
    pub require_approval: bool,
    pub max_actions: Option<usize>,
    pub allowed_tools: Vec<String>,
    pub blocked_tools: Vec<String>,
}

Methods

Configuration Options

| [] | Tools allowed autonomously | | blocked_tools | Vec

| []` | Tools never run autonomously |

Best Practices

Related