• Prerequisites
  • Install Docker and set the socket file path
• Use GitLab Duo Workflow in VS Code
• Use cURL to run GitLab Duo Workflow against a CI/CD pipeline
• The context Duo Workflow is aware of
• Current limitations
• Troubleshooting
• Give feedback

GitLab Duo Workflow

Automate tasks and help increase productivity in your development workflow by using GitLab Duo Workflow.

GitLab Duo Workflow, as part of your IDE, takes the information you provide and uses AI to walk you through an implementation plan.

GitLab Duo Workflow supports a wide variety of use cases. Here are a few examples:

• Bootstrapping a new project
• Writing tests
• Fixing a failed pipeline
• Implementing a proof of concept for an existing issue
• Commenting on a Merge Request with suggestions
• Optimize GitLab CI

These are examples of known GitLab Duo Workflow that have successfully executed, but it can be used for many more use cases.

Prerequisites

Before you can use GitLab Duo Workflow in VS Code:

1. Install the GitLab Workflow extension for VS Code. Minimum version 5.8.0.
2. In VS Code, set the Docker socket file path.

Install Docker and set the socket file path

1. Download the script. This downloads Docker, Colima, pulls workflow generic image and updates VS code settings to update Docker context for Duo Workflow. You will need to Authenticate with the GitLab container registry to pull the generic workflow image. You can run the script with --dry-run flag to know the dependencies that will be installed with the script.

2. Run the script.

        chmod +x duo_workflow_runtime.sh
        ./duo_workflow_runtime.sh
   

Use GitLab Duo Workflow in VS Code

To use GitLab Duo Workflow:

1. In VS Code, open the GitLab project.
   • The namespace must have an Ultimate subscription.
   • You must check out the branch for the code you would like to change.
2. Access the Command Palette:
   • On Mac: Cmd + Shift + P
   • On Windows and Linux: Ctrl + P.
3. Type Duo Workflow and select GitLab: Show Duo Workflow.
4. In the Duo Workflow panel, type your command, along with the merge request ID and project ID. Copy-paste is not currently possible.
   • Merge request ID: In GitLab, the ID is in the merge request URL.
   • Project ID: In GitLab, the ID is on the project overview page. In the upper-right corner, select the vertical ellipsis () to view it.

Use cURL to run GitLab Duo Workflow against a CI/CD pipeline

Instead of running GitLab Workflow in VS Code, you can use a cURL command. See the handbook for details.

1. Create a personal access token with the api scope, or create an OAuth access token with the ai_workflows scope.

2. Start GitLab Workflow in a CI/CD pipeline by using the following cURL request.

   curl POST --verbose \
      --header "Authorization: Bearer $YOUR_GITLAB_PAT" \
      --header "Content-Type: application/json" \
      --data '{
         "project_id": "$PROJECT_ID_FOR_RUNNING_WORKFLOW_AGAINST",
         "start_workflow": true,
         "goal": "Fix the pipeline for merge request X in project Y."
      }' \
      --location 'https://gitlab.com/api/v4/ai/duo_workflows/workflows'
   

The response should be the pipeline ID. To view the pipeline execution, go to:

https://gitlab.com/$namespace/$project/-/pipelines/$pipeline_id

The context Duo Workflow is aware of

GitLab Duo Workflow is aware of the context you’re working in, specifically:

In addition, Duo Workflow has read-only access to:

• The GitLab API for fetching project and merge request information.
• Merge request’s CI pipeline trace to locate errors in the pipeline job execution.

Current limitations

Duo Workflow has the following limitations:

• No copy and paste functionality. For details, see issue 380.
• No theme support.
• Project-specific workflow execution only.

Troubleshooting

If you encounter issues:

1. Check that your open project in VS Code corresponds to the GitLab project you want to interact with.
2. Ensure that you’ve checked out the branch as well.
3. Check your Docker and Docker socket configuration:
   1. Follow the setup instructions again.

   2. If using Colima and encountering issues, try restarting it:

      colima stop
      colima start
      

   3. For permission issues, ensure your operating system user has the necessary Docker permissions.
4. Check the Language Server logs:
   1. To open the logs in VS Code, select View > Output. In the output panel at the bottom, in the top-right corner, select GitLab Workflow or GitLab Language Server from the list.
   2. Review for errors, warnings, connection issues, or authentication problems.
   3. For more output in the logs, open the settings:
      • On Mac: Cmd + ,
      • On Windows and Linux: Ctrl + ,
   4. Search for the setting GitLab: Debug and enable it.
5. Examine the Duo Workflow Service production LangSmith trace.

Give feedback

Duo Workflow is an experiment and your feedback is crucial. To report issues or suggest improvements, complete this survey.