Raise TypeError for boolean dtype subtraction to match NumPy behavior

[Copilot]

Pytato silently accepted boolean array subtraction, whereas NumPy raises a TypeError. This adds the same guard to match NumPy semantics.

import numpy as np
import pytato as pt

a_np = np.array([False, True])
a_np - a_np  # TypeError: numpy boolean subtract, the `-` operator, is not supported...

a_pt = pt.make_data_wrapper(a_np)
a_pt - a_pt  # Previously returned an IndexLambda; now raises TypeError

Changes

• pytato/array.py: __sub__ and __rsub__ now check if _np_result_dtype would yield bool_ and raise TypeError with NumPy's canonical message. Added _BOOL_DTYPE module-level constant to avoid repeated dtype object construction.
• test/test_pytato.py: Added test_boolean_subtract_raises covering array - array, array - scalar, and scalar - array boolean cases, plus positive cases confirming non-boolean subtraction and bool - int (result is int) still work.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Subtraction of array with boolean dtypes should not be allowed.</issue_title>
<issue_description>```python

import numpy as np
import pytato as pt
a_np = np.array([False, True])
a_np - a_np
Traceback (most recent call last):
File "", line 1, in
a_np - a_np
~~~~~^~~~~~
TypeError: numpy boolean subtract, the - operator, is not supported, use the bitwise_xor, the ^ operator, or the logical_xor function instead.
a_pt = pt.make_data_wrapper(a_np)
a_pt - a_pt
IndexLambda(shape=(2), dtype='bool', expr=Sum((Subscript(Variable('_in0'), (Variable('_0'),)), Product((-1, Subscript(Variable('_in1'), (Variable('_0'),)))))), bindings={'_in0': DataWrapper(axes=(Axis(tags=frozenset())), tags={}, non_equality_tags={}, data=array([False, True]), shape=(2)), '_in1': DataWrapper(axes=(Axis(tags=frozenset())), tags={}, non_equality_tags={}, data=array([False, True]), shape=(2))})

We should follow Numpy and raise TypeError as well.</issue_description>

## Comments on the Issue (you are @copilot in this section)

<comments>
</comments>

• Fixes Subtraction of array with boolean dtypes should not be allowed. #643

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

[Copilot]

Pull request overview

This PR ensures pytato raises TypeError for boolean dtype subtraction, matching NumPy's behavior. When both operands resolve to bool_ via np.result_type, the - operator now raises a TypeError with the canonical NumPy error message, instead of silently producing a boolean IndexLambda.

Changes:

• Add _BOOL_DTYPE module-level constant in array.py and guard __sub__/__rsub__ with a dtype check.
• Add test_boolean_subtract_raises covering array–array, array–scalar, scalar–array, and positive cases.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
pytato/array.py	Adds _BOOL_DTYPE constant and dtype guard in __sub__/__rsub__ to raise TypeError for boolean subtraction.
test/test_pytato.py	Adds test_boolean_subtract_raises with three error cases and two positive cases verifying the new behavior.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.