abacusai.rsi_task_run_history
=============================

.. py:module:: abacusai.rsi_task_run_history


Classes
-------

.. autoapisummary::

   abacusai.rsi_task_run_history.RsiTaskRunHistory


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

.. py:class:: RsiTaskRunHistory(client, objective=None, metricName=None, direction=None, baselineValue=None, minSample=None, noiseFloor=None, lifecycle=None, totalCount=None, gradedCount=None, limit=None, offset=None, iterations=None, trend=None, sourceDeploymentConversationId=None, workdir=None)

   Bases: :py:obj:`abacusai.return_class.AbstractApiClass`


   Run history of a recursively self-improving (RSI) daemon task

   :param client: An authenticated API Client instance
   :type client: ApiClient
   :param objective: The user's natural-language objective the task improves at.
   :type objective: str
   :param metricName: The name of the measured metric.
   :type metricName: str
   :param direction: Whether the metric should 'increase' or 'decrease'.
   :type direction: str
   :param baselineValue: The metric value measured at task setup.
   :type baselineValue: float
   :param minSample: Minimum sample size required to grade a run.
   :type minSample: int
   :param noiseFloor: Absolute metric band treated as no change.
   :type noiseFloor: float
   :param lifecycle: The lifecycle of the daemon task.
   :type lifecycle: str
   :param totalCount: Total number of runs with an iteration record.
   :type totalCount: int
   :param gradedCount: Number of runs whose iteration record has been graded (closed).
   :type gradedCount: int
   :param limit: The page size used for the iterations list.
   :type limit: int
   :param offset: The offset used for the iterations list.
   :type offset: int
   :param iterations: One page of per-run records, newest first (iteration_index, status, value_before, value_after, delta, n_sample, verdict, change_summary, measured_at, failure_reason, run_record, created_at, run_lifecycle).
   :type iterations: list
   :param trend: Compact full history for charting, oldest first (index, value, verdict; the in-flight run appears last with pending=true at its comparison baseline).
   :type trend: list
   :param sourceDeploymentConversationId: The conversation whose filesystem holds the RSI workdir (for fetching run records).
   :type sourceDeploymentConversationId: str
   :param workdir: The RSI working directory on that filesystem.
   :type workdir: str


   .. py:attribute:: objective
      :value: None



   .. py:attribute:: metric_name
      :value: None



   .. py:attribute:: direction
      :value: None



   .. py:attribute:: baseline_value
      :value: None



   .. py:attribute:: min_sample
      :value: None



   .. py:attribute:: noise_floor
      :value: None



   .. py:attribute:: lifecycle
      :value: None



   .. py:attribute:: total_count
      :value: None



   .. py:attribute:: graded_count
      :value: None



   .. py:attribute:: limit
      :value: None



   .. py:attribute:: offset
      :value: None



   .. py:attribute:: iterations
      :value: None



   .. py:attribute:: trend
      :value: None



   .. py:attribute:: source_deployment_conversation_id
      :value: None



   .. py:attribute:: workdir
      :value: None



   .. py:attribute:: deprecated_keys


   .. py:method:: __repr__()


   .. py:method:: to_dict()

      Get a dict representation of the parameters in this class

      :returns: The dict value representation of the class parameters
      :rtype: dict