haive.agents.conversation.directed.agent
========================================

.. py:module:: haive.agents.conversation.directed.agent

.. autoapi-nested-parse::

   Directed conversation agent where participants respond to mentions and direct questions.
   from typing import Any
   Uses structured output models for robust speaker selection and interaction tracking.



Classes
-------

.. autoapisummary::

   haive.agents.conversation.directed.agent.DirectedConversation
   haive.agents.conversation.directed.agent.DirectedConversationConfig
   haive.agents.conversation.directed.agent.InteractionPattern
   haive.agents.conversation.directed.agent.MentionType
   haive.agents.conversation.directed.agent.SpeakerMention
   haive.agents.conversation.directed.agent.SpeakerSelectionResult


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

.. py:class:: DirectedConversation

   Bases: :py:obj:`haive.agents.conversation.base.agent.BaseConversationAgent`


   Directed conversation where agents respond to mentions and questions.

   Uses structured output models for robust speaker selection and tracking.
   Participants speak when:
   - They are directly mentioned (@name)
   - A question is directed at them
   - They haven't spoken in a while (configurable)


   .. py:method:: create_classroom(teacher_name = 'Teacher', student_names = None, topic = "Today's lesson", config = None, **kwargs)
      :classmethod:


      Create a classroom-style directed conversation.

      :param teacher_name: Name of the teacher
      :param student_names: List of student names
      :param topic: Lesson topic
      :param config: Optional configuration for directed conversation
      :param \*\*kwargs: Additional conversation arguments



   .. py:method:: get_conversation_state_schema()

      Use extended state schema.



   .. py:method:: process_response(state)

      Track interaction patterns using structured models.



   .. py:method:: select_speaker(state)

      Select speaker based on mentions and context using structured models.



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

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


   Configuration for directed conversation behavior.

   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.


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

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


   Track interaction patterns between speakers.

   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.


.. py:class:: MentionType

   Bases: :py:obj:`str`, :py:obj:`enum.Enum`


   Types of mentions detected in messages.

   Initialize self.  See help(type(self)) for accurate signature.


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

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


   Structured representation of a speaker mention.

   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.


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

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


   Structured output for speaker selection logic.

   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.