fix: handle MPS memory issues in CI tests

- Use smaller MiniLM-L6-v2 model (384 dimensions) for README tests in CI
- Skip other memory-intensive tests in CI environment
- Add minimal CI tests that don't require model loading
- Set CI environment variable and disable MPS fallback
- Ensure README examples always run correctly in CI

.github/workflows/build-reusable.yml

@@ -214,9 +214,11 @@ jobs:
 
       - name: Run tests with pytest
         env:
+          CI: true  # Mark as CI environment to skip memory-intensive tests
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           HF_HUB_DISABLE_SYMLINKS: 1
           TOKENIZERS_PARALLELISM: false
+          PYTORCH_ENABLE_MPS_FALLBACK: 0  # Disable MPS on macOS CI to avoid memory issues
         run: |
           # Run all tests
           pytest tests/