feat: add support for graphql-core 3.3.x

[bellini666]

Summary by Sourcery

Add compatibility with graphql-core 3.3.x while retaining support for 3.2.x and update tooling accordingly.

New Features:

• Support graphql-core 3.3.x in the optimizer field selection logic.

Enhancements:

• Introduce version detection utilities for graphql-core to conditionally adapt behavior.
• Add pytest helpers to skip tests based on the installed graphql-core major.minor version.
• Expand CI test matrix to run against both graphql-core 3.2.x and 3.3.x.
• Update the ruff pre-commit hook to a newer version.

[sourcery-ai]

Reviewer's Guide

Adds conditional support for graphql-core 3.3.x while preserving compatibility with 3.2.x, including version feature flags, updated field selection logic, test skips, and CI matrix changes.

File-Level Changes

Change	Details	Files
Update optimizer field selection logic to handle graphql-core 3.3.x API while keeping graphql-core 3.2.x behavior.	Branch _get_selections based on graphql-core version using IS_GQL_32 flag. For graphql-core 3.2.x, continue to call collect_sub_fields with the original argument list. For graphql-core 3.3.x, construct FieldDetails instances from info.field_nodes and call collect_subfields with info.operation and the field group. Convert the graphql-core 3.3.x FieldDetails-based grouped_field_set back into the expected dict[str, list[FieldNode]] shape for the rest of the optimizer.	strawberry_django/optimizer.py
Introduce graphql-core version detection utilities and use them to conditionally skip tests.	Add IS_GQL_33 and IS_GQL_32 flags based on graphql-core version_info. Create skip_if_gql_32 and skip_if_gql_33 pytest helpers to skip tests depending on installed graphql-core version. Wire the new skip helpers into tests via conftest imports.	strawberry_django/utils/__init__.py tests/conftest.py
Extend CI test matrix and dependencies to cover graphql-core 3.2.x and 3.3.x and bump linting tooling.	Add gql-core dimension to GitHub Actions matrix with values 3.2 and 3.3 and exclude incompatible combinations implicitly via existing matrix rules. Install the appropriate graphql-core version in CI based on the matrix value, pinning 3.2.x to <3.3.0 and 3.3.x to >=3.3.0a11. Update ruff-pre-commit hook revision to v0.14.13. Refresh uv.lock to reflect the new dependencies and tooling versions.	.github/workflows/tests.yml .pre-commit-config.yaml uv.lock

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[botberry]

Thanks for adding the RELEASE.md file!

Below is the changelog that will be used for the release.

---

Add support for graphql-core 3.3.x (currently in alpha) alongside existing 3.2.x support.

This release was contributed by @bellini666 in #850

[sourcery-ai]

Hey - I've found 1 issue, and left some high level feedback:

• The new _get_selections logic branches on IS_GQL_32 but relies on multiple # pyright: ignore comments; consider tightening the typing (e.g. explicit imports/aliases, narrowed types, or helper wrapper functions) so these ignores are unnecessary and future changes to graphql-core APIs are easier to catch statically.
• Instead of defining IS_GQL_33 and IS_GQL_32 = not IS_GQL_33, you may want to use explicit version-range checks (e.g. >=3.2,<3.3 and >=3.3) so that behavior remains well-defined if graphql-core 4.x or a later 3.x minor release is installed.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The new `_get_selections` logic branches on `IS_GQL_32` but relies on multiple `# pyright: ignore` comments; consider tightening the typing (e.g. explicit imports/aliases, narrowed types, or helper wrapper functions) so these ignores are unnecessary and future changes to `graphql-core` APIs are easier to catch statically.
- Instead of defining `IS_GQL_33` and `IS_GQL_32 = not IS_GQL_33`, you may want to use explicit version-range checks (e.g. `>=3.2,<3.3` and `>=3.3`) so that behavior remains well-defined if `graphql-core` 4.x or a later 3.x minor release is installed.

## Individual Comments

### Comment 1
<location> `tests/conftest.py:13` </location>
<code_context>

 import strawberry_django
 from strawberry_django.optimizer import DjangoOptimizerExtension
+from strawberry_django.utils import IS_GQL_32, IS_GQL_33
 from tests.utils import GraphQLTestClient

</code_context>

<issue_to_address>
**issue (testing):** Missing tests that validate the behavior of the suite under both graphql-core 3.2.x and 3.3.x, especially around the optimizer selection logic.

You’ve introduced `IS_GQL_32`/`IS_GQL_33` into the test setup, but there are no tests that actually assert the optimizer’s behavior under each version. Since `_get_selections` now branches on these flags, please add a parametrized test that runs once under 3.2.x and once under 3.3.x, confirming that: (1) 3.2.x preserves the current behavior, and (2) 3.3.x with `collect_subfields` + `FieldDetails` yields the same effective selection set (including fragments/variables).
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[codecov]

Codecov Report

❌ Patch coverage is 77.27273% with 5 lines in your changes missing coverage. Please review.
✅ Project coverage is 91.30%. Comparing base (9b1655f) to head (51d431d).

Files with missing lines	Patch %	Lines
strawberry_django/utils/gql_compat.py	72.22%	5 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #850      +/-   ##
==========================================
- Coverage   91.38%   91.30%   -0.08%     
==========================================
  Files          45       47       +2     
  Lines        4421     4441      +20     
==========================================
+ Hits         4040     4055      +15     
- Misses        381      386       +5     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.