Skip to main content

​
CodeAgent Parameters

​
Core Settings

  • task: Task description string that defines what the agent should accomplish
  • llm: LLM instance for code generation (required: ChatBrowserUse)
  • browser: Browser session object for automation
  • tools: Registry of tools the agent can call
  • max_steps (default: 20): Maximum number of execution steps before termination
  • max_failures (default: 8): Maximum consecutive errors before termination
  • max_validations (default: 0): Maximum number of times to run the validator agent (default: 0)

​
Vision & Processing

  • use_vision (default: "auto"): Vision mode - "auto" includes screenshot tool but only uses vision when requested, True always includes screenshots, False never includes screenshots and excludes screenshot tool
  • page_extraction_llm: Separate LLM model for page content extraction. You can choose a small & fast model because it only needs to extract text from the page (default: same as llm)

​
Actions & Behavior

  • use_thinking (default: True): Controls whether the agent uses its internal “thinking” field for explicit reasoning steps

​
File & Data Management

  • available_file_paths: List of file paths the agent can access
  • sensitive_data: Dictionary of sensitive data to handle carefully

​
Advanced Options

  • calculate_cost (default: False): Calculate and track API costs (see … to track costs)