ml_switcheroo.testing.bisector
==============================

.. py:module:: ml_switcheroo.testing.bisector

.. autoapi-nested-parse::

   Semantics Bisector: Automated Spec Repair.

   This module implements a feedback loop ("Bisector") that attempts to fix failing
   verification tests by incrementally relaxing the constraints in the ODL specifications.
   It closes the loop between Testing and Definition.

   Capabilities:

   1.  **Tolerance Relaxation**: If a test fails on numeric comparison, the bisector
       retries with looser `rtol`/`atol` values.
   2.  **Suggestion Generation**: Returns a mutated OperationDef dict that passes tests,
       which can be used to patch the Knowledge Base.



Classes
-------

.. autoapisummary::

   ml_switcheroo.testing.bisector.SemanticsBisector


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

.. py:class:: SemanticsBisector(runner: ml_switcheroo.testing.runner.EquivalenceRunner)

   Automated tool to find working constraints for an operation.

   Iterates through progressively relaxed constraints (e.g., tolerances) to find
   a configuration where the operation passes verification across frameworks.


   .. py:attribute:: runner


   .. py:attribute:: logger


   .. py:method:: propose_fix(op_name: str, op_def: Dict[str, Any]) -> Optional[Dict[str, Any]]

      Attempts to satisfy verification by mutating verification parameters.

      Strategies:
      1. Increase tolerances (1e-3 -> 1e-2 -> 1e-1).

      :param op_name: Name of the operation.
      :param op_def: The definition dictionary from SemanticsManager.

      :returns: A patched version of op_def if a fix was found, else None.
      :rtype: Dict