vastai-project/
  src/
    vastai_client.py      # API client wrapper
    job_runner.py          # Job orchestration logic
    instance_manager.py   # Instance lifecycle management
  docker/
    Dockerfile            # GPU workload image
    requirements.txt      # Python dependencies for GPU job
  tests/
    test_client.py        # Unit tests with mocked API
    test_job_runner.py    # Integration tests
    conftest.py           # Shared fixtures and mocks
  scripts/
    test-connection.sh    # Quick API verification
    benchmark-gpu.py      # GPU benchmark script
  .env.development        # Dev API key (low spending limit)
  .env.production         # Prod API key (gitignored)

# tests/conftest.py
import pytest
from unittest.mock import MagicMock

@pytest.fixture
def mock_vast_client():
    client = MagicMock()
    client.search_offers.return_value = {
        "offers": [
            {"id": 12345, "gpu_name": "RTX_4090", "gpu_ram": 24,
             "dph_total": 0.22, "reliability2": 0.99,
             "inet_down": 500, "ssh_host": "test.host", "ssh_port": 22},
        ]
    }
    client.create_instance.return_value = {"new_contract": 67890}
    client.show_instances.return_value = [
        {"id": 67890, "actual_status": "running",
         "ssh_host": "test.host", "ssh_port": 22}
    ]
    return client

# Build and test your GPU image locally (CPU mode)
docker build -t my-training:dev -f docker/Dockerfile .
docker run --rm my-training:dev python -c "import torch; print('OK')"

# Test training script in CPU mode
docker run --rm -v $(pwd)/data:/workspace/data my-training:dev \
  python train.py --epochs 1 --batch-size 4 --device cpu --dry-run

#!/bin/bash
set -euo pipefail
echo "Testing Vast.ai connection..."
vastai show user 2>/dev/null && echo "  CLI auth: OK" || echo "  CLI auth: FAIL"
BALANCE=$(vastai show user --raw 2>/dev/null | python3 -c "import sys,json; print(json.load(sys.stdin).get('balance',0))")
echo "  Balance: \$$BALANCE"
echo "Connection verified."

# 1. Edit Docker image and training code locally
# 2. Test locally with CPU mode
docker build -t my-training:dev . && docker run --rm my-training:dev python train.py --dry-run
# 3. Push image to registry
docker tag my-training:dev ghcr.io/yourorg/training:dev && docker push ghcr.io/yourorg/training:dev
# 4. Rent cheapest GPU for real test
vastai create instance OFFER_ID --image ghcr.io/yourorg/training:dev --disk 20
# 5. Monitor, verify, destroy
vastai show instances && vastai destroy instance INSTANCE_ID