AI Agents · Lesson

Mocking LLM Calls in Tests

unittest.mock, pytest fixtures, and recording/replaying LLM responses.

What Is Mocking?

Mocking replaces a real function or object with a fake version that returns controlled responses. In agent testing, we mock LLM API calls so tests run instantly, cost nothing, and produce predictable results.

Python's unittest.mock module is the standard tool for this.

unittest.mock.patch() Basics

unittest.mock.patch(target) temporarily replaces the named object for the duration of a test. The target is a dotted string pointing to the object as it is imported in the module under test.

from unittest.mock import patch, MagicMock

# The function under test calls openai.chat.completions.create
# We patch it so no real API call is made

def ask_llm(question: str) -> str:
    import openai
    client = openai.OpenAI(api_key='test')
    resp = client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': question}]
    )
    return resp.choices[0].message.content

with patch('openai.OpenAI') as mock_client_class:
    mock_instance = MagicMock()
    mock_client_class.return_value = mock_instance
    mock_instance.chat.completions.create.return_value = MagicMock(
        choices=[MagicMock(message=MagicMock(content='Paris'))]
    )
    result = ask_llm('Capital of France?')
    print(result)  # 'Paris' — no API call made

All lessons in this course

← Back to AI Agents