run
Method
This is a method of the Agent class in the agent module.Execute agent silently and return structured result. Production-friendly execution. Always uses silent mode with no streaming or verbose display, regardless of TTY status. Use this for programmatic, scripted, or automated usage where you want just the result.
Signature
Parameters
The input prompt to process **kwargs: Additional arguments: - stream (bool): Force streaming if True. Default: False - output (str): Output preset override (rarely needed)
Returns
The agent’s response as a string
Usage
Uses
substitute_variableschat
Notes
Unlike .start() which enables verbose output in TTY for interactive use, .run() is always silent. This makes it suitable for:- Production pipelines
- Automated scripts
- Background processing
- API endpoints
Used By
Agent.run_untilrequire_approvalHookRunner.execute_syncMCPToolRunner.runTask.execute_callback_sync
Source
View on GitHub
praisonaiagents/agent/agent.py at line 5926
