haive.agents.simple.config
==========================

.. py:module:: haive.agents.simple.config

.. autoapi-nested-parse::

   Configuration for SimpleAgent with comprehensive schema handling.

   This module defines the configuration class for SimpleAgent with explicit
   input/output schema support, schema composition integration, and improved
   mapping capabilities.



Classes
-------

.. autoapisummary::

   haive.agents.simple.config.SimpleAgentConfig


Module Contents
---------------

.. py:class:: SimpleAgentConfig

   Bases: :py:obj:`haive.core.engine.agent.agent.AgentConfig`


   Configuration for a simple single-node agent with comprehensive schema handling.

   This config supports:
   - Explicit input/output schemas
   - Auto-derived state schema
   - Structured output models
   - Intelligent input/output mappings


   .. py:method:: from_aug_llm(aug_llm, name = None, id = None, input_schema = None, output_schema = None, state_schema = None, **kwargs)
      :classmethod:


      Create a SimpleAgentConfig from an existing AugLLMConfig.

      :param aug_llm: Existing AugLLMConfig to use
      :param name: Optional agent name
      :param id: Optional unique identifier
      :param input_schema: Optional explicit input schema
      :param output_schema: Optional explicit output schema
      :param state_schema: Optional explicit state schema
      :param \*\*kwargs: Additional kwargs for the config

      :returns: SimpleAgentConfig instance



   .. py:method:: from_scratch(system_prompt = 'You are a helpful assistant.', model = 'gpt-4o', temperature = 0.7, structured_output_model = None, name = None, id = None, input_schema = None, output_schema = None, state_schema = None, **kwargs)
      :classmethod:


      Create a SimpleAgentConfig from scratch with a new AugLLMConfig.

      :param system_prompt: System prompt for the LLM
      :param model: Model identifier to use
      :param temperature: Generation temperature
      :param structured_output_model: Optional model for structured outputs
      :param name: Optional agent name
      :param id: Optional unique identifier
      :param input_schema: Optional explicit input schema
      :param output_schema: Optional explicit output schema
      :param state_schema: Optional explicit state schema
      :param \*\*kwargs: Additional kwargs for the config

      :returns: SimpleAgentConfig instance



   .. py:method:: validate_engine(v)
      :classmethod:


      Ensure engine is an AugLLMConfig instance.



   .. py:method:: validate_mappings(v, info)
      :classmethod:


      Validate mappings if provided.



   .. py:method:: with_structured_output(output_model, system_prompt = None, model = 'gpt-4o', temperature = 0.2, name = None, **kwargs)
      :classmethod:


      Create a SimpleAgentConfig with structured output capabilities.

      :param output_model: Pydantic model for structured output
      :param system_prompt: Optional system prompt (default derived from model)
      :param model: Model identifier
      :param temperature: Generation temperature (lower for structured outputs)
      :param name: Optional agent name
      :param \*\*kwargs: Additional kwargs for the config

      :returns: SimpleAgentConfig with structured output capability