Unknown Member Boolean Cast Fix

[jonhopper-dataengineers]

• Fixed unknown_member macro: added explicit ::boolean casts for is_current, is_deleted, and generic boolean columns to ensure correct type inference in Snowflake when generating unknown member rows.

[sourcery-ai]

Reviewer's Guide

Adds a GitHub Actions workflow that, on pushes to main or manual dispatch, reads the dbt project version, checks for an existing git tag, extracts the corresponding changelog section, and creates a GitHub release using the GitHub CLI if the tag does not yet exist.

Sequence diagram for the new GitHub release workflow

sequenceDiagram
    actor Developer
    participant GitHubActions as GitHub_Actions_Workflow
    participant Git as git_repo
    participant Python as python_scripts
    participant GHCLI as gh_cli

    Developer->>GitHub_Actions_Workflow: push to main or workflow_dispatch
    GitHub_Actions_Workflow->>GitHub_Actions_Workflow: actions/checkout

    GitHub_Actions_Workflow->>Python: Extract version from dbt_project.yml
    Python-->>GitHub_Actions_Workflow: version output

    GitHub_Actions_Workflow->>Git: git rev-parse --verify refs/tags/version
    alt tag exists
        Git-->>GitHub_Actions_Workflow: tag found
        GitHub_Actions_Workflow->>GitHub_Actions_Workflow: skip Extract changelog for this version
        GitHub_Actions_Workflow->>GitHub_Actions_Workflow: skip Create GitHub release
    else tag does not exist
        Git-->>GitHub_Actions_Workflow: tag not found
        GitHub_Actions_Workflow->>Python: Extract changelog for this version
        Python-->>GitHub_Actions_Workflow: title and /tmp/release_notes.md
        GitHub_Actions_Workflow->>GHCLI: gh release create version
        GHCLI-->>GitHub_Actions_Workflow: GitHub release created
    end

Loading

File-Level Changes

Change	Details	Files
Introduce an automated tag-and-release GitHub Actions workflow driven by dbt_project.yml and CHANGELOG.md.	Add a workflow triggered on pushes to main and manual dispatch with contents: write permission. Checkout the full git history and extract the project version from dbt_project.yml using a Python + PyYAML snippet. Check for an existing git tag matching the extracted version and short-circuit the job when it is present to ensure idempotency. Parse CHANGELOG.md with a Python script to isolate the section corresponding to the current version, deriving a release title and notes file. Create a GitHub release via the gh CLI using the extracted version as the tag, the parsed title, and the generated notes file, targeting the current commit SHA.	.github/workflows/release.yml

---

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.

[sourcery-ai]

Hey - I've found 2 issues, and left some high level feedback:

• The Extract version from dbt_project.yml step assumes PyYAML is installed (import yaml), which is not guaranteed on GitHub-hosted runners; consider either adding an explicit installation step or parsing the version with a tool that’s already available (e.g., yq or simple grep/sed).
• In the changelog extraction step, if the requested version header is missing from CHANGELOG.md the script will silently produce an empty title/notes; it would be safer to detect this case and fail the workflow with a clear error message rather than creating a release with incomplete metadata.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The `Extract version from dbt_project.yml` step assumes PyYAML is installed (`import yaml`), which is not guaranteed on GitHub-hosted runners; consider either adding an explicit installation step or parsing the version with a tool that’s already available (e.g., `yq` or simple `grep/sed`).
- In the changelog extraction step, if the requested version header is missing from `CHANGELOG.md` the script will silently produce an empty title/notes; it would be safer to detect this case and fail the workflow with a clear error message rather than creating a release with incomplete metadata.

## Individual Comments

### Comment 1
<location path=".github/workflows/release.yml" line_range="21-26" />
<code_context>
+        with:
+          fetch-depth: 0
+
+      - name: Extract version from dbt_project.yml
+        id: version
+        run: |
+          VERSION=$(python3 -c "import yaml; print(yaml.safe_load(open('dbt_project.yml'))['version'])")
+          echo "version=$VERSION" >> "$GITHUB_OUTPUT"
+          echo "Detected version: $VERSION"
+
+      - name: Check if tag already exists
</code_context>
<issue_to_address>
**issue (bug_risk):** Avoid relying on an uninstalled PyYAML dependency on the runner

This step imports `yaml`, which depends on PyYAML and is not installed by default on `ubuntu-latest`, so the workflow can fail unless another step installs it. To make this more robust, either use a tool already available on the runner (e.g., `yq`, `grep`, `sed`) to read `dbt_project.yml`, or add an explicit step to install PyYAML before running this command.
</issue_to_address>

### Comment 2
<location path=".github/workflows/release.yml" line_range="39-48" />
<code_context>
+      - name: Extract changelog for this version
</code_context>
<issue_to_address>
**suggestion (bug_risk):** Fail fast when the changelog entry for the version is missing

If `CHANGELOG.md` lacks a header for the detected version, this step will still succeed and produce an empty `TITLE`/release notes, resulting in a release with incomplete metadata. Consider checking `found == False` (or an empty `title`) and exiting with a non-zero status so the workflow fails when the changelog is not updated.
</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.}