haive.agents.reasoning_and_critique.reflection.config
=====================================================

.. py:module:: haive.agents.reasoning_and_critique.reflection.config

.. autoapi-nested-parse::

   Configuration for the Reflection Agent.



Classes
-------

.. autoapisummary::

   haive.agents.reasoning_and_critique.reflection.config.ReflectionAgentConfig
   haive.agents.reasoning_and_critique.reflection.config.ReflectionConfig


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

.. py:class:: ReflectionAgentConfig

   Bases: :py:obj:`haive.agents.simple.config.SimpleAgentConfig`


   Configuration for an agent that uses reflection to improve responses.


   .. py:method:: from_aug_llm(aug_llm, name = None, **kwargs)
      :classmethod:


      Create a ReflectionAgentConfig from an existing AugLLMConfig.



   .. py:method:: from_scratch(system_prompt = None, model = 'gpt-4o', temperature = 0.7, name = None, **kwargs)
      :classmethod:


      Create a ReflectionAgentConfig from scratch.



.. py:class:: ReflectionConfig(/, **data)

   Bases: :py:obj:`pydantic.BaseModel`


   Configuration specific to the reflection mechanism.

   Create a new model by parsing and validating input data from keyword arguments.

   Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
   validated to form a valid model.

   `self` is explicitly positional-only to allow `self` as a field name.