-
Notifications
You must be signed in to change notification settings - Fork 21
Add matrix testing for Python 3.12-3.14 with experimental 3.14 support #722
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Co-authored-by: ilaflott <6273252+ilaflott@users.noreply.github.com>
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## use-numpy-v2 #722 +/- ##
=============================================
Coverage 82.77% 82.77%
=============================================
Files 68 68
Lines 4529 4529
=============================================
Hits 3749 3749
Misses 780 780
Flags with carried forward coverage won't be shown. Click here to find out more. Continue to review full report in Codecov by Sentry.
🚀 New features to boost your workflow:
|
|
Co-authored-by: ilaflott <6273252+ilaflott@users.noreply.github.com>
Updated the workflow to:
The workflow now runs 3 jobs instead of 6, focusing on Python version compatibility. (commit 65975cb) |
Removed Python 3.14 from the testing matrix and related checks.
Describe your changes
Implements matrix testing strategy in CI pipeline to validate compatibility across Python versions:
Matrix dimensions:
Workflow changes (
.github/workflows/create_test_conda_env.yml):fail-fast: falseto test all Python versionscontinue-on-error: true- failures won't block CIThis enables detection of Python version-specific issues across the supported version range while allowing development to continue without blocking on potential Python 3.14 incompatibilities.
Issue ticket number and link (if applicable)
Related to investigation of CDO/python-cdo numerical differences with numpy>=2
Checklist before requesting a review
💡 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.