백그라운드 압축

from concurrent.futures import Future, ThreadPoolExecutor

import anthropic
from anthropic.types.beta import BetaMessage, BetaMessageParam

client = anthropic.Anthropic()
executor = ThreadPoolExecutor(max_workers=1)

# 실제 입력 예산에 가깝게 설정하세요. 여기서는 짧은 대화도 압축되도록 낮게 설정했습니다.
COMPACT_AT_TOKENS = 2500
SYSTEM = "You help design a recipe app's data model. Keep answers short."

QUESTIONS = [
    "What are the main entities in the data model?",
    "Which fields should Recipe have?",
    "Which fields should Ingredient have?",
    "Which fields should RecipeIngredient have?",
    "Which fields should Step have?",
    "Which indexes should these tables have?",
    "Which fields should be required?",
    "Which fields should have default values?",
]


def swap_in(history: list[BetaMessageParam], summary: BetaMessage, sent: int) -> None:
    if summary.stop_reason == "compaction":
        # 압축 요청이 보유했던 메시지만 정확히 교체합니다.
        # 이후 턴은 블록 뒤에 그대로 유지됩니다.
        history[:sent] = [{"role": "assistant", "content": summary.content}]
        print(f"Swapped {sent} messages")


history: list[BetaMessageParam] = []
pending: Future[BetaMessage] | None = None
sent = 0
for turn, question in enumerate(QUESTIONS, start=1):
    if pending is not None and pending.done():
        swap_in(history, pending.result(), sent)
        pending = None

    history.append({"role": "user", "content": question})
    response = client.beta.messages.create(
        model="claude-opus-5-5",
        max_tokens=8192,
        system=SYSTEM,
        betas=["compact-2026-09-04"],
        messages=history,
    )
    history.append({"role": "assistant", "content": response.content})

    # 다음 요청에서는 이 응답도 함께 전송되므로 포함해서 계산하세요.
    conversation_tokens = response.usage.input_tokens + response.usage.output_tokens
    if (
        conversation_tokens > COMPACT_AT_TOKENS
        and turn < len(QUESTIONS)
        and pending is None
    ):
        sent = len(history)
        pending = executor.submit(
            client.beta.messages.create,
            model="claude-opus-5-5",
            max_tokens=4096,
            system=SYSTEM,
            betas=["compact-2026-09-04"],
            messages=history.copy(),
            compaction={"type": "summarize"},
        )

# 저장하기 전에 아직 진행 중인 요약으로 교체합니다
# 또는 대화를 계속합니다.
if pending is not None:
    swap_in(history, pending.result(), sent)
executor.shutdown()