feat(gwm): add validated DAM-GK research baseline #289
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # ============================================================================= | ||
|
Check failure on line 1 in .github/workflows/cd-staging.yml
|
||
| # CD Pipeline — Staging Deployment + Evaluation | ||
| # | ||
| # Triggered: After merge to main (post CI pass) | ||
| # Phase 2 of 3-phase CI/CD (per Google AgentOps whitepaper) | ||
| # ============================================================================= | ||
| name: CD - Staging | ||
| on: | ||
| push: | ||
| branches: [main] | ||
| workflow_dispatch: | ||
| jobs: | ||
| deploy-staging: | ||
| name: Deploy to Staging | ||
| runs-on: ubuntu-latest | ||
| services: | ||
| postgres: | ||
| image: postgis/postgis:16-3.4 | ||
| env: | ||
| POSTGRES_DB: gis_agent_staging | ||
| POSTGRES_USER: postgres | ||
| POSTGRES_PASSWORD: staging_password | ||
| ports: | ||
| - 5432:5432 | ||
| options: >- | ||
| --health-cmd "pg_isready -U postgres" | ||
| --health-interval 10s | ||
| --health-timeout 5s | ||
| --health-retries 5 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - name: Set up Python 3.13 | ||
| uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: '3.13' | ||
| - name: Install dependencies | ||
| run: | | ||
| pip install -r requirements.txt | ||
| pip install pytest | ||
| - name: Run full test suite (staging validation) | ||
| env: | ||
| POSTGRES_HOST: localhost | ||
| POSTGRES_PORT: 5432 | ||
| POSTGRES_DATABASE: gis_agent_staging | ||
| POSTGRES_USER: postgres | ||
| POSTGRES_PASSWORD: staging_password | ||
| DEPLOY_ENV: staging | ||
| run: | | ||
| python -m pytest data_agent/ \ | ||
| --ignore=data_agent/test_knowledge_agent.py \ | ||
| -q --tb=short --junitxml=staging-test-results.xml | ||
| - name: Upload staging test results | ||
| uses: actions/upload-artifact@v4 | ||
| if: always() | ||
| with: | ||
| name: staging-test-results | ||
| path: staging-test-results.xml | ||
| evaluate-staging: | ||
| name: Agent Evaluation (Staging) | ||
| needs: deploy-staging | ||
| runs-on: ubuntu-latest | ||
| if: ${{ vars.GOOGLE_API_KEY != '' || secrets.GOOGLE_API_KEY != '' }} | ||
| services: | ||
| postgres: | ||
| image: postgis/postgis:16-3.4 | ||
| env: | ||
| POSTGRES_DB: gis_agent_staging | ||
| POSTGRES_USER: postgres | ||
| POSTGRES_PASSWORD: staging_password | ||
| ports: | ||
| - 5432:5432 | ||
| options: >- | ||
| --health-cmd "pg_isready -U postgres" | ||
| --health-interval 10s | ||
| --health-timeout 5s | ||
| --health-retries 5 | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - name: Set up Python 3.13 | ||
| uses: actions/setup-python@v5 | ||
| with: | ||
| python-version: '3.13' | ||
| - name: Install dependencies | ||
| run: pip install -r requirements.txt | ||
| - name: Run agent evaluation | ||
| env: | ||
| GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }} | ||
| GOOGLE_GENAI_USE_VERTEXAI: ${{ vars.GOOGLE_GENAI_USE_VERTEXAI }} | ||
| GOOGLE_CLOUD_PROJECT: ${{ vars.GOOGLE_CLOUD_PROJECT }} | ||
| GOOGLE_CLOUD_LOCATION: ${{ vars.GOOGLE_CLOUD_LOCATION || 'global' }} | ||
| POSTGRES_HOST: localhost | ||
| POSTGRES_PORT: 5432 | ||
| POSTGRES_DATABASE: gis_agent_staging | ||
| POSTGRES_USER: postgres | ||
| POSTGRES_PASSWORD: staging_password | ||
| DEPLOY_ENV: staging | ||
| run: | | ||
| python data_agent/run_evaluation.py --num-runs 2 2>&1 | tee eval-output.log | ||
| echo "Evaluation complete" | ||
| - name: Record eval results to history | ||
| if: always() | ||
| env: | ||
| POSTGRES_HOST: localhost | ||
| POSTGRES_PORT: 5432 | ||
| POSTGRES_DATABASE: gis_agent_staging | ||
| POSTGRES_USER: postgres | ||
| POSTGRES_PASSWORD: staging_password | ||
| run: | | ||
| python -c " | ||
| from data_agent.eval_history import ensure_eval_table, record_eval_result | ||
| import json, os | ||
| ensure_eval_table() | ||
| summary_path = 'eval_results/eval_summary.json' | ||
| if os.path.exists(summary_path): | ||
| with open(summary_path) as f: | ||
| s = json.load(f) | ||
| for pipeline, verdict in s.get('pipeline_verdicts', {}).items(): | ||
| record_eval_result( | ||
| pipeline=pipeline, | ||
| overall_score=s.get('pass_rate', 0), | ||
| pass_rate=s.get('pass_rate', 0), | ||
| verdict=verdict, | ||
| ) | ||
| print(f'Recorded eval results: {s.get(\"pipeline_verdicts\", {})}') | ||
| " | ||
| - name: Upload evaluation results | ||
| uses: actions/upload-artifact@v4 | ||
| if: always() | ||
| with: | ||
| name: staging-eval-results | ||
| path: | | ||
| eval_results/ | ||
| eval-output.log | ||
| staging-approval: | ||
| name: Staging Sign-off | ||
| needs: [deploy-staging, evaluate-staging] | ||
| runs-on: ubuntu-latest | ||
| if: always() && needs.deploy-staging.result == 'success' | ||
| environment: staging # Requires manual approval in GitHub | ||
| steps: | ||
| - name: Staging validated | ||
| run: | | ||
| echo "✅ Staging validation complete." | ||
| echo "Tests: ${{ needs.deploy-staging.result }}" | ||
| echo "Eval: ${{ needs.evaluate-staging.result }}" | ||
| echo "Ready for production deployment." | ||
