gave connection_pattern a "node" argument to support ops with

doc/extending/op.txt

@@ -98,7 +98,7 @@ following methods:
   lifetime of self.  Op instances should be immutable in this
   sense.
 
-.. function:: connection_pattern():
+.. function:: connection_pattern( node ):
 
   Optional method; sometimes needed for gradient.grad to
   work correctly.
@@ -109,6 +109,10 @@ following methods:
   elements of inputs[input_idx] have an effect on the elements of
   outputs[output_idx].
 
+  The ``node'' parameter is needed to determine the number of
+  inputs. Some ops such as Subtensor take a variable number of
+  inputs.
+
   If no connection_pattern is specified, gradient.grad will
   assume that all inputs have some elements connected to some
   elements of all outputs.

theano/gradient.py

@@ -526,7 +526,7 @@ def _populate_var_to_node_to_idx(outputs, wrt):
         # that does type checking and supplies the default value
         # if the method is not implemented
         if hasattr(node.op,'connection_pattern'):
-            connection_pattern = node.op.connection_pattern()
+            connection_pattern = node.op.connection_pattern(node)
 
             if not isinstance(connection_pattern, list):
                 raise TypeError("Op.connection_pattern should return " + \