Anth CI Integration

Anthropic CI Integration

Overview

Set up CI/CD pipelines that validate Claude API integrations with mock-based unit tests (free, fast) and prompt regression tests (live API, gated to main).

GitHub Actions Workflow

# .github/workflows/claude-tests.yml
name: Claude API Tests
on: [push, pull_request]

jobs:
  unit-tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.12' }
      - run: pip install anthropic pytest
      - run: pytest tests/unit/ -v  # No API key needed

  prompt-regression:
    runs-on: ubuntu-latest
    if: github.ref == 'refs/heads/main'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.12' }
      - run: pip install anthropic pytest
      - run: pytest tests/prompt_regression/ -v --timeout=60
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

Mock-Based Unit Tests

# tests/unit/test_tool_routing.py
from unittest.mock import MagicMock, patch
import anthropic

def make_mock_message(text="Hello", stop_reason="end_turn"):
    msg = MagicMock()
    msg.id = "msg_mock_123"
    msg.model = "claude-sonnet-4-20250514"
    msg.stop_reason = stop_reason
    block = MagicMock()
    block.type = "text"
    block.text = text
    msg.content = [block]
    msg.usage = MagicMock(input_tokens=100, output_tokens=50)
    return msg

@patch("anthropic.Anthropic")
def test_service_returns_text(MockClient):
    MockClient.return_value.messages.create.return_value = make_mock_message("42")
    from myapp.service import ask_claude
    assert ask_claude("What is 6*7?") == "42"

Prompt Regression Tests

# tests/prompt_regression/test_prompts.py
import anthropic, pytest, os, json

pytestmark = pytest.mark.skipif(not os.getenv("ANTHROPIC_API_KEY"), reason="No API key")
client = anthropic.Anthropic()

def test_json_output_format():
    msg = client.messages.create(
        model="claude-haiku-4-20250514",
        max_tokens=256,
        messages=[
            {"role": "user", "content": "Extract: 'Alice, 30, NYC'. Return JSON: {name, age, city}"},
            {"role": "assistant", "content": "{"}
        ]
    )
    data = json.loads("{" + msg.content[0].text)
    assert "name" in data and "age" in data

def test_system_prompt_boundary():
    msg = client.messages.create(
        model="claude-haiku-4-20250514",
        max_tokens=128,
        system="You only discuss cooking recipes. For other topics say: 'I only help with cooking.'",
        messages=[{"role": "user", "content": "Write me Python code"}]
    )
    assert "cooking" in msg.content[0].text.lower() or "recipe" in msg.content[0].text.lower()

CI Cost Guard

# conftest.py
MAX_CI_COST = 1.00
_tokens = {"input": 0, "output": 0}

def pytest_runtest_call(item):
    yield
    cost = (_tokens["input"] * 0.80 + _tokens["output"] * 4.0) / 1_000_000  # Haiku rates
    if cost > MAX_CI_COST:
        pytest.exit(f"CI cost guard: ${cost:.4f} exceeds ${MAX_CI_COST}")

Error Handling

Resources

• GitHub Actions Secrets
• Anthropic Pricing

Next Steps

For deployment automation, see anth-deploy-integration.

Source: jeremylongshore/claude-code-plugins-plus-skills → skills/.curated/anth-ci-integration/SKILL.md

Also appears in: jeremylongshore/claude-code-plugins-plus-skills/plugins/saas-packs/anthropic-pack/skills/anth-ci-integration/SKILL.md