I'm just going through an exercise of upgrading an internal app with very old versions to slightly less old and ran into some breakage relating to #88 which I think requires a code change here.

class NotificationGroupSerializer(serializers.ModelSerializer):
    class Meta:
        model = models.NotificationGroup
        exclude = ()

    members = GM2MSerializerField(queryset=autocomplete.QuerySetSequence(User.objects.all(), Group.objects.all()))

This worked fine in django 2.2 and drf 3.9. Having bumped upto django 3.2 and drf 3.15.2 (I'm still working on getting current), openapi schema generation started failing with infinite recursion errors.

Re-reading the QSS docs, I discover I need to specify model when creating the QuerySetSequence for some functionality to work. Changing the above to

    members = GM2MSerializerField(queryset=autocomplete.QuerySetSequence(User.objects.all(), Group.objects.all(), model=User))

Then starts failing with

  File "/home/brobert/.virtualenvs/myapp/lib64/python3.9/site-packages/rest_framework/fields.py", line 652, in <dictcomp>
    key: (copy.deepcopy(value, memo) if (key not in ('validators', 'regex')) else value)
  File "/usr/lib64/python3.9/copy.py", line 172, in deepcopy
    y = _reconstruct(x, memo, *rv)
  File "/usr/lib64/python3.9/copy.py", line 270, in _reconstruct
    state = deepcopy(state, memo)
  File "/usr/lib64/python3.9/copy.py", line 146, in deepcopy
    y = copier(x, memo)
  File "/usr/lib64/python3.9/copy.py", line 230, in _deepcopy_dict
    y[deepcopy(key, memo)] = deepcopy(value, memo)
  File "/usr/lib64/python3.9/copy.py", line 161, in deepcopy
    rv = reductor(4)
TypeError: __getstate__() missing 1 required positional argument: 'self'

reductor is a reference to __reduce_ex__. After a bit of digging, I followed the definition of User.__reduce__, which lead me to the the inherited Model.__reduce__ from django's base Model class:

    def __reduce__(self):
        data = self.__getstate__()
        data[DJANGO_VERSION_PICKLE_KEY] = django.__version__
        class_id = self._meta.app_label, self._meta.object_name
        return model_unpickle, (class_id,), data

Meanwhile in #88, QSS' ProxyModel had been changed to:

class ProxyModel:
    """
    Wrapper for generating DoesNotExist exceptions without modifying
    the provided model. This is needed by DRF as the views only handle
    the specific exception by the model.
    """

    def __init__(self, model=None):
        self._model = model

        # Define DoesNotExist for abstract models.
        if self._model and not self._model._meta.abstract:
            self.DoesNotExist = model.DoesNotExist
        else:
            self.DoesNotExist = ObjectDoesNotExist

    def __getattr__(self, name):
        return getattr(self._model, name)

Long story short, this code assumes getattr will only ever be called to get DoesNotExist, and that it's safe to proxy calls for getattr on an instance to the class. I don't fully understand what DRF is doing such that I end up with getattr invoked on the ProxyModel instance, but it appears to have gone wrong because getattr was expecting to be called on an instance of User and actually got invoked on the User class itself.

From the context of #88 I think this __getattr__ override exists solely to return a valid DoesNotExist exception object. In which case a quick hack of the following resolves the crashes:

    def __getattr__(self, name):
        if name == 'DoesNotExist':
            return getattr(self._model, name)
        return super().__getattr__(self, name)

This proxies the request for the DoesNotExist object to the model, and relies on the default behaviour for anything else.

I'm not sure if this is the right thing to do in all cases; can someone more familiar with this codebase than me sanity check?