together-ci-integration

# Together AI CI Integration ## Overview Set up CI/CD for Together AI inference integrations: run unit tests with mocked completion and embedding responses on every PR, validate live API connectivity for model inference on merge to main. Together AI provides an OpenAI-compatible API for 100+ open-source models including Llama, Mixtral, and FLUX, so CI pipelines verify prompt formatting, response parsing, model selection logic, and fine-tuning job management. ## GitHub Actions Workflow ```yaml # .github/workflows/together-ci.yml name: Together AI CI on: pull_request: paths: ['src/together/**', 'tests/**'] push: branches: [main] jobs: unit-tests: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: actions/setup-node@v4 with: { node-version: '20' } - run: npm ci - run: npm test -- --reporter=verbose integration-tests: if: github.ref == 'refs/heads/main' needs: unit-tests runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: actions/setup-node@v4 with: { node-version: '20' } - run: npm ci - run: npm run test:integration env: TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }} ``` ## Mock-Based Unit Tests ```typescript // tests/together-service.test.ts import { describe, it, expect, vi } from 'vitest'; import { generateCompletion, createEmbedding } from '../src/together-service'; vi.mock('../src/together-client', () => ({ Toge...