Preserve `str` subclass results from `__repr__` in plain `str()` by Copilot · Pull Request #7454 · RustPython/RustPython

Copilot · 2026-03-17T11:14:23Z

str(obj) was flattening a str subclass returned by __repr__ into an exact str, diverging from CPython. This only affected the plain str(...) constructor path; subtype construction should still normalize to the requested subtype.

Constructor behavior
- Change the exact str(...) fast path in PyStr::slot_new to return PyObject::str(vm) directly for the single-argument, no-kwargs case.
- This preserves subclass identity when __str__/__repr__ returns a str subclass, instead of rebuilding a new exact str from the underlying data.
Regression coverage
- Re-enable Lib/test/test_str.py::StrTest.test_conversion, which already covers WithRepr(StrSubclass(...)) and related conversion cases.
- Keep the Lib/test/test_str.py change aligned with CPython v3.14.3 rather than adding RustPython-only assertions there.
- Add RustPython-owned identity regression coverage under extra_tests/snippets/builtin_str_subclass.py for the exact str(...) path preserving a str subclass returned by __str__ and __repr__.

Example:

class MyStr(str):
    pass

class Foo:
    def __repr__(self):
        return MyStr("hello")

result = str(Foo())
type(result)  # now: MyStr

Original prompt

This section details on the original issue you should resolve

<issue_title>str() discards str subclass type returned by __repr__</issue_title>
<issue_description>## Description

str() on an object whose __repr__ returns a str subclass instance incorrectly returns a plain str, discarding the subclass type. CPython preserves the subclass type as-is. This is a CPython compatibility issue.

Root Cause

PyStr::py_new calls input.str(vm) which correctly resolves to the __repr__ return value (a str subclass instance), but then extracts only the raw string data via Self::from(s.as_wtf8().to_owned()) and creates a new plain PyStr, discarding the subclass type.
CPython reference: unicodeobject.c#L15575-L15596
// Key branch: only convert when type is a str subclass
if (unicode != NULL && type != &PyUnicode_Type) {
    Py_SETREF(unicode, unicode_subtype_new(type, unicode));
}
return unicode;   // when type is exactly str → return PyObject_Str result as-is
When type == &PyUnicode_Type (plain str() call), unicode_new_impl returns the PyObject_Str result without conversion, preserving the subclass type.
Reproduction
class MyStr(str):
    pass

class Foo:
    def __repr__(self):
        return MyStr('hello')

result = str(Foo())
print(result)
print(type(result))
Output

RustPython:
hello
<class 'str'>
CPython:
hello
<class '__main__.MyStr'>
Environment

RustPython d248a04 (Python 3.14.0)

CPython 3.14.3

OS: Debian 12</issue_description>

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

Fixes str() discards str subclass type returned by __repr__ #7450

💬 Send tasks to Copilot coding agent from Slack and Teams to turn conversations into code. Copilot posts an update in your thread when it's finished.

Summary by CodeRabbit

Bug Fixes
- Improved string conversion behavior to ensure consistent handling of arguments passed to the string constructor.

github-actions · 2026-03-17T11:41:22Z

crates/vm/src/builtins/str.rs

        if cls.is(vm.ctx.types.str_type)
            && func_args.args.len() == 1
            && func_args.kwargs.is_empty()


[auto-format] _{reported by reviewdog 🐶}

Suggested change

if cls.is(vm.ctx.types.str_type)

&& func_args.args.len() == 1

&& func_args.kwargs.is_empty()

if cls.is(vm.ctx.types.str_type) && func_args.args.len() == 1 && func_args.kwargs.is_empty()

github-actions · 2026-03-17T11:41:40Z

📦 Library Dependencies

The following Lib/ modules were modified. Here are their dependencies:

[x] test: cpython/Lib/test/test_str.py (TODO: 14)
[x] test: cpython/Lib/test/test_fstring.py (TODO: 19)
[x] test: cpython/Lib/test/test_string_literals.py (TODO: 4)

dependencies:

dependent tests: (no tests depend on str)

Legend:

[+] path exists in CPython
[x] up-to-date, [ ] outdated

youknowone · 2026-03-17T11:45:13Z

@copilot fix CI failure

Copilot · 2026-03-17T11:52:38Z

@copilot fix CI failure

Fixed by a555ce4. The only failing CI job was the old format_check run on 0852fa6, and it failed in the final formatting-diff step. a555ce4 contains the formatting fix, cargo fmt --check passes locally, and the targeted regression test still passes while the refreshed PR checks are running on the updated head.

youknowone · 2026-03-17T14:20:50Z

@copilot Fix still failng ci.

Copilot · 2026-03-17T14:36:40Z

@copilot Fix still failng ci.

Pushed 008e4c6. I traced the red CI to the old 0852fa6 run: the real reported failure was test.test_multiprocessing_fork.test_processes, and it passes locally on current HEAD. This follow-up tightens the existing str regression and triggers fresh workflows for the updated branch state; the new runs are on 008e4c6, but GitHub currently shows them as action_required with no jobs started yet.

youknowone · 2026-03-19T00:53:03Z

@coderabbitai review

coderabbitai · 2026-03-19T00:53:08Z

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

coderabbitai · 2026-03-19T00:53:18Z

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: 17633059-775d-4e47-8fb6-e464e96c673f

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

📝 Walkthrough

Walkthrough

The PyStr.slot_new optimization path is modified to invoke string conversion on arguments via str(vm) instead of requiring the argument to be an existing PyStr instance. This enables the optimization to coerce non-string single arguments to strings while preserving subclass types.

Changes

Cohort / File(s)	Summary
String Constructor Optimization `crates/vm/src/builtins/str.rs`	Modified the exact str type optimization path to call `str(vm)` on the single positional argument instead of type-checking for PyStr, enabling string coercion while preserving subclass types returned by `__str__`/`__repr__`.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

Add tp_str #6495: Implements the tp_str/__str__ slot mechanism that enables the .str(vm) method call used in this optimization path to properly invoke string conversion with subclass type preservation.

Poem

🐰 A str() call once crude and plain,
Now honors types with careful strain,
Subclasses preserved, not cast away,
The optimization wins the day! ✨

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title directly describes the main change: preserving str subclass results from repr in plain str() calls, matching the core objective documented in issue `#7450`.
Linked Issues check	✅ Passed	The PR changes PyStr::slot_new to return the str conversion result directly instead of rebuilding a plain str, which directly addresses issue `#7450`'s requirement to preserve str subclass types returned by repr to match CPython behavior.
Out of Scope Changes check	✅ Passed	The changes to PyStr::slot_new are narrowly scoped to the optimization path that triggered the bug, with no unrelated modifications present in the provided changeset.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch copilot/fix-str-subclass-type-issue

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

youknowone · 2026-03-19T07:32:35Z

@copilot where the test_str.pychanges came from? we have strict rule not editing test_str.py ourselves. that must be came from CPython Lib/test/test_str.py. Please check and confirm which version we copied it from. Otherwise revert them and add tests under extra_tests/snippets, which owns our own tests

Copilot · 2026-03-19T07:47:10Z

@copilot where the test_str.pychanges came from? we have strict rule not editing test_str.py ourselves. that must be came from CPython Lib/test/test_str.py. Please check and confirm which v...

Checked and fixed in ae2b62e. The extra identity assertions in Lib/test/test_str.py were PR-local and not from a CPython sync, so I moved them to extra_tests/snippets/builtin_str_subclass.py. I also verified that the remaining test_conversion hunk matches CPython v3.14.3, so Lib/test/test_str.py now only keeps the CPython-aligned change.

youknowone · 2026-03-25T06:36:41Z

@copilot rebase to upstream/main

Copilot · 2026-03-25T06:52:48Z

@copilot rebase to upstream/main

Updated in 7a4ca2f. The branch now has origin/main as its merge-base again, and the PR diff is back to the intended 3 files. I also re-ran the targeted test.test_str.StrTest.test_conversion unittest and extra_tests/snippets/builtin_str_subclass.py on the final branch tip.

Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>

Copilot AI assigned Copilot and youknowone Mar 17, 2026

Copilot started work on behalf of youknowone March 17, 2026 11:14 View session

Copilot AI changed the title ~~[WIP] Fix str() to preserve str subclass type from __repr__~~ Preserve str subclass results from __repr__ in plain str() Mar 17, 2026

Copilot AI requested a review from youknowone March 17, 2026 11:30

Copilot finished work on behalf of youknowone March 17, 2026 11:30

youknowone marked this pull request as ready for review March 17, 2026 11:40

github-actions bot reviewed Mar 17, 2026

View reviewed changes

Copilot started work on behalf of youknowone March 17, 2026 11:45 View session

Copilot finished work on behalf of youknowone March 17, 2026 11:53

Copilot started work on behalf of youknowone March 17, 2026 14:20 View session

Copilot finished work on behalf of youknowone March 17, 2026 14:38

Copilot started work on behalf of youknowone March 19, 2026 07:32 View session

Copilot finished work on behalf of youknowone March 19, 2026 07:48

youknowone approved these changes Mar 19, 2026

View reviewed changes

Copilot started work on behalf of youknowone March 25, 2026 06:36 View session

Copilot AI requested a review from youknowone March 25, 2026 06:53

Copilot finished work on behalf of youknowone March 25, 2026 06:53

youknowone marked this pull request as draft March 28, 2026 04:47

Copilot AI and others added 5 commits March 29, 2026 04:33

Initial plan

8a56d78

Preserve str subclass returned by __repr__

ed2fd1e

Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>

Format str constructor fast path

2ff66e7

Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>

Tighten str subclass conversion regression

5140534

Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>

Align test_str with CPython and move local coverage

9a11d44

Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>

youknowone force-pushed the copilot/fix-str-subclass-type-issue branch from 7a4ca2f to 9a11d44 Compare March 28, 2026 19:33

Conversation

Copilot AI commented Mar 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Root Cause

Reproduction

Output

Environment

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

Summary by CodeRabbit

Uh oh!

github-actions bot Mar 17, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions bot commented Mar 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

📦 Library Dependencies

Uh oh!

youknowone commented Mar 17, 2026

Uh oh!

Copilot AI commented Mar 17, 2026

Uh oh!

youknowone commented Mar 17, 2026

Uh oh!

Copilot AI commented Mar 17, 2026

Uh oh!

youknowone commented Mar 19, 2026

Uh oh!

coderabbitai bot commented Mar 19, 2026

Uh oh!

coderabbitai bot commented Mar 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Poem

❌ Failed checks (1 warning)

Uh oh!

youknowone commented Mar 19, 2026

Uh oh!

Copilot AI commented Mar 19, 2026

Uh oh!

youknowone commented Mar 25, 2026

Uh oh!

Copilot AI commented Mar 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Copilot AI commented Mar 17, 2026 •

edited

Loading

github-actions bot commented Mar 17, 2026 •

edited

Loading

coderabbitai bot commented Mar 19, 2026 •

edited

Loading