Real-World Usage

Examples

Practical examples and configurations for common use cases.

What's Available

🤖

AI MR Review

Automated code review on merge requests using AI

GitLab CI

GitHub Actions

👋

Human-in-Loop Approval

Two-stage approval with Slack notification and manual trigger

GitLab CI

Slack

Approval

🔔

Push Notification

Notify your team on every push to main/master

GitLab CI

GitHub Actions

Slack

📊

Jira Integration

Create Jira issues from CI events using subprocess modules

GitLab CI

Jira

GitLab CI Configurations

AI-Powered MR Review

Automated code review using AI on merge requests

stages:
  - review

ai-mr-review:
  stage: review
  image: ghcr.io/rajitk13/shiro-automation:latest
  variables:
    GITLAB_TOKEN: $GL_TOKEN
  script:
    - shiro run -workflow .shiro/workflows/code-review.json -config .shiro/config.yaml -state-store gitlab
  artifacts:
    paths:
      - .shiro/state/
    expire_in: 1 day
  only:
    - merge_requests

This workflow automatically reviews merge requests using AI, providing feedback on code quality and potential issues.

GitLab CI

Workflow Definitions

Simple Test Workflow

Basic workflow with print steps

{
  "name": "simple-test",
  "description": "Simple test workflow using print module",
  "steps": [
    {
      "id": "test_info",
      "type": "print",
      "config": {
        "message": "Starting simple test workflow",
        "level": "info"
      }
    },
    {
      "id": "test_debug",
      "type": "print",
      "config": {
        "message": "Debug: Testing variable resolution",
        "level": "debug"
      }
    },
    {
      "id": "test_complete",
      "type": "print",
      "config": {
        "message": "Test workflow completed successfully!",
        "level": "info"
      }
    }
  ]
}

Configuration Examples

AI Provider Configuration

Configure multiple AI providers in config.yaml

models:
  # Ollama local models
  codellama:
    type: ollama
    model: codellama:34b
    base_url: http://localhost:11434

  # OpenAI-compatible providers
  gpt-4:
    type: openai
    model: gpt-4
    base_url: https://api.openai.com/v1
    api_key: "{"{env.OPENAI_API_KEY}"}"

  # Gemini (Google AI Studio)
  gemini:
    type: gemini
    model: gemini-1.5-pro
    api_key: "{"{env.GEMINI_API_KEY}"}"
    api_type: "google-ai-studio"

  # Custom OpenAI-compatible endpoint
  custom-llm:
    type: openai
    model: custom-model
    base_url: http://localhost:8000/v1
    api_key: "sk-custom-key"