The ``backends`` package
============================

.. py:module:: ansys.fluent.mcp.solve.backends


Summary
-------








.. py:currentmodule:: backends
.. tab-set::


    .. tab-item:: Submodules

        .. list-table::
          :header-rows: 0
          :widths: auto


          * - :py:obj:`~ansys.fluent.mcp.solve.backends.composite`
            - Composite backend: deterministic PyFluent solver operations.


          * - :py:obj:`~ansys.fluent.mcp.solve.backends.introspection`
            - Live introspection helpers shared by backends.


          * - :py:obj:`~ansys.fluent.mcp.solve.backends.mesh_report_parsers`
            - Pure-functional parsers for Fluent's ``mesh.check`` and ``mesh.quality`` reports.


          * - :py:obj:`~ansys.fluent.mcp.solve.backends.pyfluent`
            - PyFluent backend for the Solve leaf.












.. toctree::
   :titlesonly:
   :maxdepth: 1
   :hidden:

    <span class="nf nf-fa-file"></span> composite</api/ansys/fluent/mcp/solve/backends/composite/index>
    <span class="nf nf-fa-file"></span> introspection</api/ansys/fluent/mcp/solve/backends/introspection/index>
    <span class="nf nf-fa-file"></span> mesh_report_parsers</api/ansys/fluent/mcp/solve/backends/mesh_report_parsers/index>
    <span class="nf nf-fa-file"></span> pyfluent</api/ansys/fluent/mcp/solve/backends/pyfluent/index>











Description
-----------


Solve connection/data-plane backends.

* :mod:`ansys.fluent.mcp.solve.backends.composite`: The
  :class:`SolveCompositeBackend`; PyFluent for execution and live
  context.
* :mod:`ansys.fluent.mcp.solve.backends.pyfluent`: local in-process
  :class:`PyFluentBackend` over gRPC.
* :mod:`ansys.fluent.mcp.solve.backends.introspection`: Fluent
  state probes used exclusively by ``PyFluentBackend``.
* :mod:`ansys.fluent.mcp.solve.backends.mesh_report_parsers`:
  Transcript scrapers that lift mesh-quality numbers out of Fluent
  console output.

Backends are the data plane shared by every higher layer (MCP leaf,
agent, gateway). They never know anything about LLMs, prompts, or
recipes.















..
    !! processed by numpydoc !!