Fix: Support iteration and indexing for ModelSimple list responses

[Xyerophyte]

Problem

The DomainsResponse class (and other ModelSimple-based list response models) could not be iterated, causing ApiAttributeError when attempting common operations:

domains = domain_api.DomainApi(api_client).list_domains(id, version)
[domain for domain in domains]  # ❌ ApiAttributeError: DomainsResponse has no attribute '0'

Users had to access the internal _data_store directly, breaking the abstraction.

Root Cause

DomainsResponse inherits from ModelSimple and stores a list in its value attribute. When Python's iteration protocol calls __getitem__(0), the existing implementation only accepted string attribute names, not integer indices.

Solution

Enhanced the ModelSimple class in fastly/model_utils.py with sequence protocol support:

1. __getitem__ - Now accepts integers and slices, delegating to the underlying value list/tuple
2. __iter__ - Returns an iterator over the sequence in value
3. __len__ - Returns the length of the sequence in value

The implementation intelligently handles:

• Lists and tuples as sequences (iterable)
• Dicts and other objects as single items (to avoid iterating dict keys)
• Backward compatibility with existing attribute access

What Now Works

domains = domain_api.DomainApi(api_client).list_domains(id, version)

len(domains)              # ✓ Get count
domains[0]                # ✓ Index access  
domains[1:3]              # ✓ Slicing
list(domains)             # ✓ Convert to list
[d for d in domains]      # ✓ List comprehension
for domain in domains:    # ✓ Iteration
    print(domain)

Testing

• Added comprehensive test suite in tests/test_model_simple_sequence.py
• Tests cover iteration, indexing, slicing, len(), edge cases (empty, single item)
• All tests pass ✓

Documentation

• Updated CHANGELOG.md (v12.0.0 bug fixes section)
• Fix is backward-compatible with existing code

Impact

• Affects all ModelSimple instances that wrap sequences
• Makes list-based response models behave intuitively
• No breaking changes - purely additive functionality

[Copilot]

Pull request overview

This PR updates the Python client’s ModelSimple base class to better support list-style response models (e.g., DomainsResponse) by implementing sequence-like behavior, and adds tests + changelog entry to validate and document the change.

Changes:

• Extend ModelSimple with sequence protocol support (__getitem__ for int/slice, plus __iter__ and __len__) backed by the underlying value.
• Add pytest coverage for iteration, indexing, slicing, and len() on DomainsResponse.
• Document the behavior in the changelog.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 6 comments.

File	Description
fastly/model_utils.py	Adds sequence semantics to ModelSimple to make list-wrapping response models iterable/indexable.
tests/test_model_simple_sequence.py	Introduces tests verifying the new iteration/indexing/slicing/len behavior.
CHANGELOG.md	Notes the ModelSimple sequence behavior change under bug fixes.

---

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

[Copilot]

In the new int/slice error path construction, the list comprehension uses if e, which will drop index 0 (because 0 is falsy). That can lose useful context for callers when model[0] fails. Consider filtering with is not None (or similar) so index 0 is preserved in the path.

[Copilot]

__getitem__ returns v[name] for int/slice names without verifying that value is actually a list/tuple. This is inconsistent with __iter__/__len__, which treat non-(list, tuple) value as a single item; e.g., len(model)==1 but model[0] can still raise. Consider limiting numeric indexing to list/tuple values, or explicitly handling index 0/slices for the single-item case so the sequence semantics stay consistent.

Suggested change

	try:
	return v[name]
	except Exception:
	# normalize to attribute error expected by callers
	raise ApiAttributeError(
	"{0} has no attribute '{1}'".format(
	type(self).__name__, name),
	[e for e in [self._path_to_item, name] if e]
	)
	if isinstance(v, (list, tuple)):
	try:
	return v[name]
	except Exception:
	# normalize to attribute error expected by callers
	raise ApiAttributeError(
	"{0} has no attribute '{1}'".format(
	type(self).__name__, name),
	[e for e in [self._path_to_item, name] if e]
	)
	if isinstance(name, slice):
	return [v][name]
	if name in (0, -1):
	return v
	raise ApiAttributeError(
	"{0} has no attribute '{1}'".format(
	type(self).__name__, name),
	[e for e in [self._path_to_item, name] if e]
	)

[Copilot]

Adding __len__ changes truthiness for ModelSimple instances (Python will use __len__ for bool(model) when __bool__ is not defined). For list-based responses this means empty responses become falsy, which can be a backward-incompatible behavioral change. If that’s not intended, consider defining __bool__ to preserve prior truthiness, or documenting this as a behavior change.

[Copilot]

The __len__ docstring says “otherwise 0”, but the implementation returns 1 for non-(list, tuple) values (treating them as a single item). Update the docstring to match the actual behavior.

[Copilot]

pytest is imported but not used in this test file. Removing the unused import keeps the test module clean and avoids unused-import lint noise (if/when linting is enabled).

Suggested change

import pytest

[Copilot]

The new changelog entry is indented with an extra leading space ( - fix(model): ...), which will render as a nested list item in Markdown. Align it with the other bullets under Bug fixes: (no leading space before -).

Suggested change

	- fix(model): Make `ModelSimple` behave like a sequence when `value` is a list/tuple so generated response models (e.g. `DomainsResponse`) can be iterated, indexed and sized.
	- fix(model): Make `ModelSimple` behave like a sequence when `value` is a list/tuple so generated response models (e.g. `DomainsResponse`) can be iterated, indexed and sized.