OpenAI Agents SDK

pip install agentx-python openai-agents

from agentx import AgentX
from agents import Agent, Runner, function_tool

client = AgentX.from_env()

@function_tool
def get_policy(topic: str) -> str:
    """Look up a company policy by topic."""
    db = {
        "cancel": "Go to Account → Subscription → Cancel.",
        "refund": "Full refund within 30 days.",
    }
    return db.get(topic.lower(), "No policy found.")

agent = Agent(
    name="support-agent",
    instructions="You are a helpful support agent. Use get_policy to look up policies.",
    tools=[get_policy],
)

def openai_agents_eval(case):
    result = Runner.run_sync(agent, case.query)
    return {"output": result.final_output}

run_context = (
    client.evaluations
    # "openai-agents" isn't a valid EvaluationSubject.framework value (see note below), so "other"
    # is the correct value here, distinct from what you pass to tracer.trace(framework=...).
    .run(dataset_id="...", subject={"kind": "custom_agent", "displayName": "Support Agent", "framework": "other"})
    .execute(openai_agents_eval)
    .finalize()
)
print(f"Average rating: {run_context.average_rating:.2f}")

from agentx import AgentX
from agents import Agent, Runner

client = AgentX.from_env()

agent = Agent(name="support-agent", instructions="You are a helpful support agent.")

def openai_agents_eval(case):
    with client.tracer.trace(
        "openai-agents-call",
        input={"query": case.query},
        framework="openai-agents",
        sync=True,
        monitor=False,  # the run's judge already scores this case
    ) as span:
        result = Runner.run_sync(agent, case.query)
        span.output = result.final_output

    return {
        "output": result.final_output,
        "trace_id": span.trace_id,
    }