ci: fix issues with job naming when sequences are involved #979
Conversation
There was a problem hiding this comment.
Pull Request Overview
Purpose: Align job and artifact naming with sanitized inputs and add runner architecture propagation, while renaming and broadening the sanitize workflow to cover more inputs.
- Renamed sanitize workflow and expanded it to output runner architecture.
- Adjusted downstream workflows to consume runner-arch and updated job/artifact names.
- Simplified build workflow by removing per-matrix arch sanitization, relying on a single upstream value.
Reviewed Changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 5 comments.
| File | Description |
|---|---|
| .github/workflows/wc-sanitize-inputs.yml | Renames workflow and adds runner architecture output; modifies output descriptions. |
| .github/workflows/wc-integration-test.yml | Adds runner-arch input and uses it for job naming and test report filenames. |
| .github/workflows/wc-build-push.yml | Switches to new sanitize workflow, propagates runner-arch, changes job/artifact naming, removes per-build arch step. |
| .github/workflows/continuous-integration.yml | Minor job name change (emoji removed) to match new naming approach. |
Comments suppressed due to low confidence (1)
.github/workflows/wc-build-push.yml:1
- Removal of the per-matrix architecture step (previously capturing arch inside each build job) eliminates accurate per-runner architecture detection; relying solely on sanitize-inputs' runner-arch can be incorrect for heterogeneous matrices. Reintroduce a per-job arch capture (similar to the removed step) and use that value for job and artifact naming.
# This is a lower-level re-usable workflow that builds and pushes
| outputs: | ||
| image-basename: | ||
| description: "The sanitized base name of the image (without registry or tag)" | ||
| description: "The sanitized base name of the image" |
There was a problem hiding this comment.
The original description clarified exclusion of registry and tag; removing that reduces precision. Recommend restoring explicit scope: The sanitized base name of the image (excluding registry and tag).
| description: "The sanitized base name of the image" | |
| description: "The sanitized base name of the image (excluding registry and tag)" |
| value: ${{ jobs.sanitize.outputs.image-basename }} | ||
| image-name: | ||
| description: "The sanitized name of the image (without registry or tag)" | ||
| description: "The sanitized name of the image" |
There was a problem hiding this comment.
This description no longer states that the tag and registry are excluded, which can lead to misuse when composing full image references. Suggest: The sanitized image name (repository path without registry or tag).
| description: "The sanitized name of the image" | |
| description: "The sanitized image name (repository path without registry or tag)" |
| value: ${{ jobs.sanitize.outputs.image-name }} | ||
| fully-qualified-image-name: | ||
| description: "The fully qualified name of the image including registry (but without tag)" | ||
| description: "The fully qualified name of the image including registry" |
There was a problem hiding this comment.
The previous wording clarified that the tag was not included; current phrasing could imply tags are present. Suggest: The fully qualified image name including registry (no tag).
| description: "The fully qualified name of the image including registry" | |
| description: "The fully qualified image name including registry (no tag)" |
|
|
||
| build-push: | ||
| name: ${{ matrix.runner }} | ||
| name: Build (${{ needs.sanitize-inputs.outputs.runner-arch }}) |
There was a problem hiding this comment.
Using a single runner-arch value from the sanitize job for every matrix entry can mislabel builds when matrix runners differ (e.g. mixing x64 and arm64), leading to misleading job names. Compute architecture within each matrix job (using RUNNER_ARCH) or incorporate matrix.runner into the name to ensure accuracy.
| name: Build (${{ needs.sanitize-inputs.outputs.runner-arch }}) | |
| name: Build (${{ env.RUNNER_ARCH }}) |
| - uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2 | ||
| with: | ||
| name: digests-${{ needs.sanitize-image-name.outputs.image-basename }}-${{ steps.devcontainer-arch.outputs.arch }} | ||
| name: digests-${{ needs.sanitize-inputs.outputs.image-basename }}-${{ needs.sanitize-inputs.outputs.runner-arch }} |
There was a problem hiding this comment.
Artifact name relies on a single upstream runner-arch; with multi-architecture matrix builds all artifacts may share the same name, reducing clarity and risking confusion when inspecting per-arch digests. Include a per-job architecture (e.g. from RUNNER_ARCH) or matrix.runner fragment to differentiate artifacts.
| name: digests-${{ needs.sanitize-inputs.outputs.image-basename }}-${{ needs.sanitize-inputs.outputs.runner-arch }} | |
| name: digests-${{ needs.sanitize-inputs.outputs.image-basename }}-${{ matrix.runner }} |
|
Pull Request Report (#979)Static measures
Time related measures
Status check related measures
|
✅MegaLinter analysis: Success
See detailed reports in MegaLinter artifacts Your project could benefit from a custom flavor, which would allow you to run only the linters you need, and thus improve runtime performances. (Skip this info by defining
|
🚀 Hey, I have created a Pull Request
Description of changes
✔️ Checklist