haive.agents.reasoning_and_critique.tot.agent
=============================================

.. py:module:: haive.agents.reasoning_and_critique.tot.agent

.. autoapi-nested-parse::

   Tree of Thoughts (ToT) agent implementation.

   This module implements the Tree of Thoughts algorithm as a Haive agent.



Classes
-------

.. autoapisummary::

   haive.agents.reasoning_and_critique.tot.agent.ToTAgent


Functions
---------

.. autoapisummary::

   haive.agents.reasoning_and_critique.tot.agent.compose_evaluator_runnable
   haive.agents.reasoning_and_critique.tot.agent.compose_generator_runnable
   haive.agents.reasoning_and_critique.tot.agent.create_evaluator_engine
   haive.agents.reasoning_and_critique.tot.agent.create_generator_engine


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

.. py:class:: ToTAgent(config)

   Bases: :py:obj:`haive.core.engine.agent.agent.Agent`\ [\ :py:obj:`haive.agents.reasoning_and_critique.tot.config.TOTAgentConfig`\ ], :py:obj:`Generic`\ [\ :py:obj:`T`\ ]


   Tree of Thoughts agent implementation.

   This agent implements the Tree of Thoughts search algorithm, which:
   1. Generates candidate solutions
   2. Scores the candidates
   3. Selects the best candidates for further exploration
   4. Repeats until a satisfactory solution is found or max depth reached

   The implementation supports parallel processing of candidates through beam search.

   Initialize the ToT agent.

   :param config: Configuration for the ToT agent


   .. py:method:: setup_workflow()

      Set up the Tree of Thoughts workflow.

      Graph structure:
      - Sequential mode:
        START -> generate -> evaluate_all -> select -> (loop or END)
      - Parallel mode:
        START -> generate -> [evaluate_candidate * N] -> collect -> select -> (loop or END)



.. py:function:: compose_evaluator_runnable(engine, use_structured_output=False)

   Create evaluator runnable.


.. py:function:: compose_generator_runnable(engine, use_structured_output=False)

   Create generator runnable.


.. py:function:: create_evaluator_engine(engine, use_structured_output=False, output_model=None)

   Create evaluator engine configuration.


.. py:function:: create_generator_engine(engine, use_structured_output=False, output_model=None)

   Create generator engine configuration.