agent-diff 0.1.7

Python SDK for Agent Diff - test AI agents and train models against replicas of services

Agent Diff Python SDK

Python SDK for testing AI agents against isolated replicas of production services.

Installation

uv add agent-diff

Environments

Create isolated, ephemeral replicas of services:

env = client.init_env(
    templateService="slack",
    templateName="slack_default",
    impersonateUserId="U123",
    ttlSeconds=3600
)

# Access environment details
env.environmentId
env.environmentUrl
env.expiresAt

# Delete when done
client.delete_env(env.environmentId)

Templates

List and create environment templates:

# List available templates
templates = client.list_templates()

# Create custom template - you can populate the replica via API and turn it into a template with custom data
custom = client.create_template_from_environment(
    environmentId=env.environmentId,
    service="slack",
    name="my_template",
    description="Custom template",
    visibility="private"  # "private" means only you can view the template
)

Code Execution Proxies

SDK provides code execution proxies that automatically intercept API calls and route them to isolated test environments. This enables agents with code execution capabilities to interact with service replicas without any code changes.

How It Works

When your agent executes Python or Bash code:

1. The executor wraps your code with interception logic
2. API calls to https://slack.com/api/* → http://localhost:8000/api/env/{env_id}/services/slack/api/*
3. API calls to https://api.linear.app/* → http://localhost:8000/api/env/{env_id}/services/linear/*
4. Your agent sees real API responses from the isolated environment

Available Executors

PythonExecutorProxy

Intercepts Python requests and urllib libraries:

from agent_diff import PythonExecutorProxy, create_openai_tool

python_executor = PythonExecutorProxy(env.environmentId, base_url=client.base_url)
python_tool = create_openai_tool(python_executor)

# Works with OpenAI Agents SDK, LangChain, smolagents
agent = Agent(
    model="gpt-4o",
    tools=[python_tool],
    instructions="Use execute_python tool to interact with Slack API at https://slack.com/api/*. Authentication is automatic."
)
agent.run("Send a Slack message to #general")

BashExecutorProxy

Intercepts curl commands:

from agent_diff import BashExecutorProxy, create_openai_tool

bash_executor = BashExecutorProxy(env.environmentId, base_url=client.base_url)
bash_tool = create_openai_tool(bash_executor)

agent = Agent(
    model="gpt-4o",
    tools=[bash_tool],
    instructions="Use execute_bash tool with curl to interact with Slack API at https://slack.com/api/*. Authentication is automatic."
)
agent.run("Use curl to post a message to Slack")

Framework Support

Create tools for popular agent frameworks:

from agent_diff import create_openai_tool, create_langchain_tool, create_smolagents_tool

# OpenAI Agents SDK
openai_tool = create_openai_tool(python_executor)

# LangChain
langchain_tool = create_langchain_tool(python_executor)

# HuggingFace smolagents
smolagents_tool = create_smolagents_tool(python_executor)

Direct Execution

For custom frameworks or direct usage:

python_executor = PythonExecutorProxy(env.environmentId, base_url=client.base_url)

result = python_executor.execute("""
import requests
response = requests.post('https://slack.com/api/chat.postMessage', json={
    'channel': '#general',
    'text': 'Hello from Agent Diff!'
})
print(response.json())
""")

if result["status"] == "success":
    print(result["stdout"])
else:
    print(result["stderr"])

Test Suites & Evaluations

To run evaluations:

suite = client.get_test_suite("slack-bench")
# Returns: {"tests": [{"id": "...", "prompt": "Send hello to #general"}, ...]}


evaluation_results = []

for test in suite['tests']:
    prompt = test['prompt']
    test_id = test['id']

    env = client.init_env(testId=test_id)
    run = client.start_run(envId=env.environmentId, testId=test_id)

    # Create executor with automatic API interception
    python_executor = PythonExecutorProxy(env.environmentId, base_url=client.base_url)
    python_tool = create_openai_tool(python_executor)

    # Run your agent with the tool
    agent = Agent(
        model="gpt-4o",
        tools=[python_tool],
        instructions="Use execute_python to interact with Slack at https://slack.com/api/*. Authentication is automatic."
    )
    response = agent.run(prompt)

    evaluation_result = client.evaluate_run(run.runId)  # Returns score, runId, status and Score (0/1)

    evaluation_results.append(evaluation_result)

    client.delete_env(envId=env.environmentId)

License

MIT License - see LICENSE file for details.