Python 3.12.3 -> 3.12.4 breaks use of `create_autospec(X, spec_set=True, name="X")`

[ShapingView]

Bug report

Bug description:

Hello, thanks for the work you do!

My issue: Updating from 3.12.3 to 3.12.4 breaks many elements in my test suite. We use the name= argument to better understand log messages once a test with many objects fails.

This works with 3.12.3, but crashes with 3.12.4. The issue might have been introduced with this fix: 23ba96e

Code example

File autospec_test.py:

import unittest
from unittest.mock import create_autospec

class X: ...

class TestX(unittest.TestCase):
    def test_x(self):
        mock = create_autospec(X, spec_set=True, name="X")


if __name__ == "__main__":
    unittest.main()

Observed behavior

python 3.12.3

python autospec_test.py
.
----------------------------------------------------------------------
Ran 1 test in 0.001s

OK

python 3.12.4

python autospec_test.py
E
======================================================================
ERROR: test_x (__main__.TestX.test_x)
----------------------------------------------------------------------
Traceback (most recent call last):
  File ".../autospec_test.py", line 10, in test_x
    mock = create_autospec(X, spec_set=True, name="X")
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/unittest/mock.py", line 2823, in create_autospec
    mock.configure_mock(**kwargs)
  File "/usr/local/lib/python3.12/unittest/mock.py", line 650, in configure_mock
    setattr(obj, final, val)
  File "/usr/local/lib/python3.12/unittest/mock.py", line 774, in __setattr__
    raise AttributeError("Mock object has no attribute '%s'" % name)
AttributeError: Mock object has no attribute 'name'

----------------------------------------------------------------------
Ran 1 test in 0.003s

FAILED (errors=1)

CPython versions tested on:

3.12

Operating systems tested on:

Linux, (CI pipelines failed on windows, too – didn't test this example, though.)

Linked PRs

• gh-120732: Fix name passing to Mock, when using kwargs to create_autospec #120737
• [3.13] gh-120732: Fix name passing to Mock, when using kwargs to create_autospec (GH-120737) #120760
• [3.12] gh-120732: Fix name passing to Mock, when using kwargs to create_autospec (GH-120737) #120761

[hugovk]

The issue might have been introduced with this fix: 23ba96e

Git bisect also points to the same commit:

23ba96e2433d17e86f4770a64b94aaf9ad22a25b is the first bad commit
commit 23ba96e2433d17e86f4770a64b94aaf9ad22a25b
Author: Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com>
Date:   Thu May 2 20:01:17 2024 +0200

    [3.12] gh-90848: Fixed create_autospec ignoring configure_mock style kwargs (GH-118163) (#118517)

    gh-90848: Fixed create_autospec ignoring configure_mock style kwargs (GH-118163)
    (cherry picked from commit b28a3339e4c63ea3a801dba9bbbc6af5af42c3a0)

    Co-authored-by: infohash <46137868+infohash@users.noreply.github.com>

 Lib/test/test_unittest/testmock/testmock.py          | 13 +++++++++++++
 Lib/unittest/mock.py                                 | 20 ++++++++++++--------
 .../2024-04-22-21-54-12.gh-issue-90848.5jHEEc.rst    |  1 +
 3 files changed, 26 insertions(+), 8 deletions(-)
 create mode 100644 Misc/NEWS.d/next/Library/2024-04-22-21-54-12.gh-issue-90848.5jHEEc.rst
bisect found first bad commit

This is from backport PR #118517, main PR #118163, and issue #90848.

cc @infohash and @cjw296.

[nineteendo]

Can this be closed?