Fix rls draft workflow

[miroslavpojer]

Overview

Fix duplicities in release draft workflow.

Release Notes

• Enhance release draft workflow by adding infra-repo-ref input and refining tag creation process

Summary by CodeRabbit

• Chores
  • Improved release workflow: revamped tag creation to produce annotated tags with metadata and ensure the new tag reference is created reliably.
  • Streamlined draft release step: standardized tag-name inputs, adjusted release naming and prerelease setting, and ensured inputs propagate correctly across steps.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

Walkthrough

Replaced lightweight tag creation with annotated tag creation (including message and tagger metadata), changed tag ref creation to use the annotated tag object's SHA, reconnected the draft-release step to use github.event.inputs.tag-name and set prerelease: false, and preserved token/env propagation between steps.

Changes

Cohort / File(s)	Summary
GitHub Actions release workflow .github/workflows/release_draft.yml	Replaced standalone lightweight tag step with annotated tag creation (message, tagger name/email/date), use tagObject.data.sha to create the tag ref, switched inputs to read core.getInput('tag-name') and github.event.inputs.tag-name, re-added draft release step with prerelease: false, and adjusted step naming and input wiring.

Sequence Diagram(s)

sequenceDiagram
  autonumber
  participant Runner as Actions Runner
  participant REST as GitHub REST API
  participant Repo as Git Data (refs/tags)

  Runner->>REST: create annotated tag (message, tagger metadata)
  REST-->>Runner: returns tagObject (with .data.sha)
  Runner->>REST: create ref using tagObject.data.sha -> refs/tags/{tag-name}
  Runner->>REST: create draft release with tag-name (prerelease: false)
  note right of REST `#DFF2E1`: Steps use token from workflow inputs/env

Loading

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• Fix Aquasec alerts #60: Modifies the same release_draft.yml workflow and tag creation/draft-release handling.

Suggested reviewers

• benedeki
• lsulak
• salamonpavel

Poem

🐰 I hopped through YAML, swift and spry,

I stitched a tag with name and why.
A SHA was born, a ref took flight,
The draft now waits — not prerelease tonight. 🏷️

Pre-merge checks and finishing touches

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Title check	❓ Inconclusive	The title 'Fix rls draft workflow' is vague and uses an abbreviation ('rls') that lacks clarity about the specific issue being addressed.	Expand the title to be more descriptive, such as 'Fix tag creation duplicities in release draft workflow' or similar, to clearly convey the main change.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description check	✅ Passed	The description covers the Overview and Release Notes sections from the template, but the Related section with issue reference is missing.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch feature/fix-release-draft-workflow

---

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

• X
• Mastodon
• Reddit
• LinkedIn

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

[github-actions]

JaCoCo 'balta' module code coverage report - scala 2.12.18

Overall Project	67.11%	🍏

There is no coverage information present for the Files changed

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 38581e7 and cb293cf.

📒 Files selected for processing (1)

• .github/workflows/release_draft.yml

🔇 Additional comments (3)

.github/workflows/release_draft.yml (3)

134-134: LGTM: Explicit input reference improves clarity.

Using github.event.inputs.tag-name directly is more explicit and consistent with the tag_name field on line 136.

---

138-138: LGTM: Explicit prerelease flag improves clarity.

Explicitly setting prerelease: false documents the intended behavior and is a good practice, even if it matches the default value.

---

95-127: > Likely an incorrect or invalid review comment.

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

.github/workflows/release_draft.yml (1)

91-124: Annotated tag creation looks good; consider adding error handling.

The switch to annotated tags with proper metadata (message, tagger info) is a best practice for releases. The use of tagObject.data.sha at line 118 correctly creates a reference to the tag object rather than directly to the commit.

However, if createTag succeeds but createRef fails (e.g., network issue, race condition), an orphaned tag object will remain in the repository. Consider wrapping the two API calls in a try-catch and cleaning up on failure.

🔎 Suggested error handling pattern

         script: |
           const tag = core.getInput('tag-name')
           const ref = `refs/tags/${tag}`;
           const sha = context.sha; // The SHA of the commit to tag
           const tagMessage = `${tag} released by GitHub Action`;
+          
+          try {
+            const tagObject = await github.rest.git.createTag({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              tag: tag,
+              message: tagMessage,
+              object: sha,
+              type: 'commit',
+              tagger: {
+                name: context.actor,
+                email: `${context.actor}@users.noreply.github.com`,
+                date: new Date().toISOString()
+              }
+            });

-          const tagObject = await github.rest.git.createTag({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            tag: tag,
-            message: tagMessage,
-            object: sha,
-            type: 'commit',
-            tagger: {
-              name: context.actor,
-              email: `${context.actor}@users.noreply.github.com`,
-              date: new Date().toISOString()
-            }
-          });

-          await github.rest.git.createRef({
-            owner: context.repo.owner,
-            repo: context.repo.repo,
-            ref: ref,
-            sha: tagObject.data.sha
-          });
+            await github.rest.git.createRef({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              ref: ref,
+              sha: tagObject.data.sha
+            });

-          console.log(`Tag created: ${tag}`);
+            console.log(`Tag created: ${tag}`);
+          } catch (error) {
+            core.setFailed(`Failed to create tag: ${error.message}`);
+            throw error;
+          }

📜 Review details

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between cb293cf and 38384f1.

📒 Files selected for processing (1)

• .github/workflows/release_draft.yml

🔇 Additional comments (1)

.github/workflows/release_draft.yml (1)

130-134: LGTM! Draft release configuration is correct.

The draft release step correctly references the tag created in the previous step via github.event.inputs.tag-name, and setting prerelease: false is appropriate for this workflow.