OpenTelemetry로 통합하는 Agent 평가

def _flush_telemetry():
    from opentelemetry import trace as _trace
    from opentelemetry._logs import get_logger_provider as _get_lp
    for provider in (_trace.get_tracer_provider(), _get_lp()):
        flush = getattr(provider, "force_flush", None)
        if flush:
            flush()

@app.entrypoint
async def invoke(payload, context):
    prompt = payload.get("prompt", "")
    try:
        result = await run_agent(prompt)
    finally:
        _flush_telemetry()
    return str(result)

from bedrock_agentcore.evaluation import EvaluationClient
from bedrock_agentcore.evaluation.client import ReferenceInputs
from datetime import timedelta

ec = EvaluationClient(region_name=REGION)
# The client resolves each evaluator's level (SESSION, TRACE, or TOOL_CALL)
# automatically, so no level configuration is needed here.
results = ec.run(
    evaluator_ids=[
        "Builtin.GoalSuccessRate",
        "Builtin.Correctness",
        "Builtin.Helpfulness",
        CUSTOM_RESPONSE_QUALITY_ID,
        CUSTOM_SESSION_COMPLETENESS_ID,
    ],
    agent_id=AGENT_ID,
    session_id=SESSION_ID,
    look_back_time=timedelta(hours=1),
    reference_inputs=ReferenceInputs(
        assertions=ASSERTIONS,
        expected_trajectory=EXPECTED_TRAJECTORY,
        expected_response=EXPECTED_RESPONSES[-1],
    ),
)