Skip to main content

​
run_autonomous

Method
This is a method of the Agent class in the agent module.
Run an autonomous task execution loop. This method executes a task autonomously, using the agent’s tools and capabilities to complete the task. It handles:
  • Progressive escalation based on task complexity
  • Doom loop detection and recovery
  • Iteration limits and timeouts
  • Completion detection (keyword-based or promise-based)
  • Optional context clearing between iterations

​
Signature

def run_autonomous(prompt: str, max_iterations: Optional[int], timeout_seconds: Optional[float], completion_promise: Optional[str], clear_context: bool) -> Any

​
Parameters

​
prompt
str
required
The task to execute
​
max_iterations
Optional
Override max iterations (default from config)
​
timeout_seconds
Optional
Timeout in seconds (default: no timeout)
​
completion_promise
Optional
Optional string that signals completion when wrapped in <promise>TEXT</promise> tags in the response
​
clear_context
bool
default:"False"
Whether to clear chat history between iterations (forces agent to rely on external state like files)

​
Returns

​
Returns
Any
AutonomyResult with success status, output, and metadata

​
Exceptions

If autonomy is not enabled

​
Usage

agent = Agent(instructions="...", autonomy=True)
    result = agent.run_autonomous(
        "Refactor the auth module",
        completion_promise="DONE",
        clear_context=True
    )
    if result.success:
        print(result.output)