バックグラウンドでのコンパクション

from concurrent.futures import Future, ThreadPoolExecutor

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

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

# 実際の入力予算に近い値を設定してください。ここでは短い会話でもコンパクションされるよう低くしています。
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":
        # コンパクションリクエストが保持していたメッセージだけを正確に置き換えます。
        # 以降のターンはブロックの後ろに残ります。
        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})

    # 次のリクエストではこの応答も送信されるため、カウントに含めます。
    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"},
        )

# 保存する前に、まだ生成中の要約に差し替えます
# または会話を続行します。
if pending is not None:
    swap_in(history, pending.result(), sent)
executor.shutdown()