Implement production pipeline for ADK multi-agent system with LiteLLM integration, chaos testing, Vertex AI, and Terraform IaC

.env.example

@@ -0,0 +1,65 @@
+# Environment Configuration
+ENVIRONMENT=development
+LOG_LEVEL=INFO
+
+# LLM API Keys
+GEMINI_API_KEY=your-gemini-api-key-here
+OPENAI_API_KEY=your-openai-api-key-here
+ANTHROPIC_API_KEY=your-anthropic-api-key-here
+MISTRAL_API_KEY=your-mistral-api-key-here
+
+# Google Cloud
+GOOGLE_PROJECT_ID=your-gcp-project-id
+GOOGLE_REGION=us-central1
+GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
+
+# Database Configuration
+POSTGRES_HOST=postgres
+POSTGRES_PORT=5432
+POSTGRES_DB=rag7_db
+POSTGRES_USER=rag7_user
+POSTGRES_PASSWORD=your-secure-password-here
+
+# Redis Configuration
+REDIS_HOST=redis
+REDIS_PORT=6379
+REDIS_PASSWORD=
+REDIS_DB=0
+
+# Qdrant Vector Database
+QDRANT_HOST=qdrant
+QDRANT_PORT=6333
+QDRANT_API_KEY=
+
+# LiteLLM Configuration
+LITELLM_PROXY_URL=http://litellm-proxy:4000
+LITELLM_MASTER_KEY=your-litellm-master-key
+LITELLM_CACHE_TYPE=redis
+LITELLM_CACHE_HOST=redis:6379
+
+# Monitoring
+PROMETHEUS_URL=http://prometheus:9090
+GRAFANA_URL=http://grafana:3000
+JAEGER_ENDPOINT=http://jaeger:14268/api/traces
+
+# Application Configuration
+APP_HOST=0.0.0.0
+APP_PORT=8080
+METRICS_PORT=9090
+WORKERS=4
+MAX_AGENTS=10
+
+# Rate Limiting
+RATE_LIMIT_RPM=60
+RATE_LIMIT_TPM=100000
+
+# Circuit Breaker
+CIRCUIT_BREAKER_FAILURE_THRESHOLD=5
+CIRCUIT_BREAKER_TIMEOUT=60
+CIRCUIT_BREAKER_RECOVERY_TIMEOUT=30
+
+# Deployment
+DEPLOYMENT_ENV=dev
+CLOUD_RUN_SERVICE_NAME=rag7-agent-api
+GKE_CLUSTER_NAME=rag7-cluster
+GKE_NAMESPACE=rag7-dev

.github/CODEOWNERS

@@ -0,0 +1,36 @@
+# Code Owners
+# These owners will be requested for review when someone opens a pull request.
+
+# Default owners for everything in the repo
+*                       @Stacey77
+
+# Source code
+/src/                   @Stacey77
+
+# Tests
+/tests/                 @Stacey77
+
+# CI/CD workflows
+/.github/workflows/     @Stacey77
+
+# Deployment configurations
+/deploy/                @Stacey77
+
+# Documentation
+/docs/                  @Stacey77
+*.md                    @Stacey77
+
+# Infrastructure as Code
+/deploy/terraform/      @Stacey77
+
+# Kubernetes manifests
+/deploy/gke/            @Stacey77
+
+# Monitoring and observability
+/monitoring/            @Stacey77
+
+# Dependencies
+requirements*.txt       @Stacey77
+pyproject.toml          @Stacey77
+Dockerfile              @Stacey77
+docker-compose*.yml     @Stacey77

.github/dependabot.yml

@@ -0,0 +1,50 @@
+version: 2
+updates:
+  # Python dependencies
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+      time: "09:00"
+    open-pull-requests-limit: 10
+    reviewers:
+      - "Stacey77"
+    labels:
+      - "dependencies"
+      - "python"
+    commit-message:
+      prefix: "chore"
+      include: "scope"
+
+  # Docker dependencies
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+      time: "09:00"
+    open-pull-requests-limit: 5
+    reviewers:
+      - "Stacey77"
+    labels:
+      - "dependencies"
+      - "docker"
+    commit-message:
+      prefix: "chore"
+
+  # GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "monday"
+      time: "09:00"
+    open-pull-requests-limit: 5
+    reviewers:
+      - "Stacey77"
+    labels:
+      - "dependencies"
+      - "github-actions"
+    commit-message:
+      prefix: "chore"

.github/workflows/chaos-testing.yml

@@ -0,0 +1,78 @@
+name: Chaos Testing
+
+on:
+  schedule:
+    - cron: '0 2 * * 0'  # Weekly on Sunday at 2 AM UTC
+  workflow_dispatch:
+
+jobs:
+  chaos-tests:
+    name: Run Chaos Engineering Tests
+    runs-on: ubuntu-latest
+    environment: staging
+
+    services:
+      redis:
+        image: redis:7-alpine
+        ports:
+          - 6379:6379
+
+      postgres:
+        image: postgres:15-alpine
+        env:
+          POSTGRES_DB: rag7_test
+          POSTGRES_USER: test_user
+          POSTGRES_PASSWORD: test_password
+        ports:
+          - 5432:5432
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt -r requirements-dev.txt
+
+      - name: Run chaos tests
+        run: |
+          pytest tests/orchestration/ -v -m chaos --tb=short
+        env:
+          ENVIRONMENT: staging
+          REDIS_HOST: localhost
+          POSTGRES_HOST: localhost
+
+      - name: Generate chaos test report
+        if: always()
+        run: |
+          echo "# Chaos Testing Report" > chaos-report.md
+          echo "Date: $(date)" >> chaos-report.md
+          echo "" >> chaos-report.md
+          echo "## Test Results" >> chaos-report.md
+          pytest tests/orchestration/ -m chaos --tb=line --quiet >> chaos-report.md 2>&1 || true
+
+      - name: Upload chaos test report
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: chaos-test-report
+          path: chaos-report.md
+
+      - name: Notify on failure
+        if: failure()
+        uses: actions/github-script@v7
+        with:
+          script: |
+            github.rest.issues.create({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              title: 'Chaos Testing Failed',
+              body: 'The weekly chaos testing run has failed. Please investigate.',
+              labels: ['chaos-testing', 'needs-investigation']
+            })