Agent 하니스·루프·그래프 엔지니어링 비교

def run_loop(agent, task, max_attempts=5):
    for attempt in range(max_attempts):
        output = agent.act(task)
        passed, feedback = verify(output, task.spec)
        if passed:
            return output
        task.context.append(feedback)  # specific, not vague
    return escalate_to_human(task, output)

def verify(output, spec):
    # deterministic check beats "does this look right?"
    if spec.type == "code":
        return run_tests(output), "tests failed: see diff"
    return validate_schema(output, spec.schema)

# model.py
import os
from anthropic import Anthropic

client = Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

def call_model(prompt: str) -> str:
    resp = client.messages.create(
        model="claude-sonnet-5",
        max_tokens=1024,
        messages=[
            {"role": "user", "content": prompt}
        ],
    )
    return resp.content[0].text

def fix_once(file):
    passed, log = run_tests(file)
    if passed:
        return True
    code = open(file).read()
    prompt = (f"This code fails its test:
{code}

"
              f"Test output:
{log}
"
              "Return only the fixed code, nothing else.")
    open(file, "w").write(call_model(prompt))
    passed, _ = run_tests(file)
    return passed

def run_loop(file, max_attempts=5):
    for attempt in range(max_attempts):
        passed, log = run_tests(file)
        if passed:
            return attempt
        code = open(file).read()
        prompt = f"Fix this failing code:
{code}

Test failure:
{log}"
        open(file, "w").write(call_model(prompt))
    return None

from concurrent.futures import ThreadPoolExecutor

with ThreadPoolExecutor(max_workers=3) as pool:
    results = list(pool.map(coder_node, FILES))
print(results)
print("full suite passes:", reviewer_node())