revert: replace actions/upload-artifact@v3 with actions/upload-artifact@v4

[lklimek]

Reverts #2359

In #2359, we changed to upload-artifacts v4 without updating the logic to address the following breaking change:

Breaking Changes

Uploading to the same named Artifact multiple times.

Due to how Artifacts are created in this new version, it is no longer possible to upload to the same named Artifact multiple times. You must either split the uploads into multiple Artifacts with different names, or only upload once. Otherwise you will encounter an error.

Summary by CodeRabbit

• New Features

  • Introduced a new input parameter only_drive for specifying Drive image builds.

• Bug Fixes

  • Enhanced conditional logic for steps in the release process based on artifact existence.

• Chores

  • Updated action versions for upload-artifact and download-artifact from v4 to v3 in multiple workflows.

[coderabbitai]

Walkthrough

The pull request includes updates to two GitHub Actions workflow files: .github/workflows/release-docker-image.yml and .github/workflows/release.yml. The changes involve downgrading the versions of the upload-artifact and download-artifact actions from v4 to v3. Additionally, the release.yml workflow introduces a new input parameter only_drive and modifies the release-npm job to include conditional steps based on artifact existence. These updates enhance the configurability and streamline the release process without altering the overall control flow.

Changes

File Path	Change Summary
.github/workflows/release-docker-image.yml	- Updated upload-artifact from v4 to v3 in build-image job. - Updated download-artifact from v4 to v3 in publish-manifest job.
.github/workflows/release.yml	- Added new input parameter only_drive for workflow_dispatch. - Modified release-npm job to include conditional steps based on artifact existence. - Updated actions/upload-artifact from v4 to v3 in release-dashmate-packages job.

Possibly related PRs

• ci: docker image always released as -dev #2358: This PR modifies the .github/workflows/release-docker-image.yml file, which is directly related to the main PR that also changes this file, specifically updating action versions for Docker image releases.

Suggested reviewers

• QuantumExplorer
• shumkov

Poem

In the workflow's dance, we twirl and sway,
With artifacts checked, we pave the way.
From v4 to v3, a gentle glide,
A new only_drive to help us decide.
Hopping along, our builds take flight,
In the land of code, everything feels right! 🐇✨

---

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 40ae73f and 00bdcc2.

📒 Files selected for processing (2)

• .github/workflows/release-docker-image.yml (1 hunks)
• .github/workflows/release.yml (1 hunks)

🧰 Additional context used

🪛 actionlint (1.7.4)

.github/workflows/release.yml

285-285: the runner of "actions/upload-artifact@v3" action is too old to run on GitHub Actions. update the action's version to fix this issue

(action)

.github/workflows/release-docker-image.yml

83-83: the runner of "actions/upload-artifact@v3" action is too old to run on GitHub Actions. update the action's version to fix this issue

(action)

🔇 Additional comments (3)

.github/workflows/release-docker-image.yml (1)

Line range hint 83-87: LGTM: Downgrade to v3 is appropriate

The downgrade from upload-artifact@v4 to v3 is correct as this workflow potentially needs to upload multiple digests to the same artifact name when building for different platforms (amd64/arm64). Version 4 would fail in this scenario due to its restriction on multiple uploads to the same named artifact.

🧰 Tools

🪛 actionlint (1.7.4)

83-83: the runner of "actions/upload-artifact@v3" action is too old to run on GitHub Actions. update the action's version to fix this issue

(action)

.github/workflows/release.yml (2)

Line range hint 285-290: LGTM: Consistent downgrade to v3

The downgrade from upload-artifact@v4 to v3 is consistent with the changes in the docker image workflow. The conditional if: github.event_name != 'release' ensures this step only runs for non-release events, preventing duplicate uploads.

🧰 Tools

🪛 actionlint (1.7.4)

282-282: shellcheck reported issue in this script: SC2086:info:1:1: Double quote to prevent globbing and word splitting

(shellcheck)

---

285-285: the runner of "actions/upload-artifact@v3" action is too old to run on GitHub Actions. update the action's version to fix this issue

(action)

---

Line range hint 8-11: LGTM: Well-structured workflow input parameter

The new only_drive parameter is a good addition that allows for more granular control over the release process. It's properly integrated with conditional job execution throughout the workflow.

🧰 Tools

🪛 actionlint (1.7.4)

282-282: shellcheck reported issue in this script: SC2086:info:1:1: Double quote to prevent globbing and word splitting

(shellcheck)

---

285-285: the runner of "actions/upload-artifact@v3" action is too old to run on GitHub Actions. update the action's version to fix this issue

(action)

---

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Experiment)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[lklimek]

Closed in favor of #2389