后台压缩

from concurrent.futures import Future, ThreadPoolExecutor

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

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

# 请将此值设为接近您实际的输入预算。此处设得较低，以便简短对话也会触发压缩。
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":
        # 精确替换压缩请求中包含的那些消息。
        # 后续轮次保留在该块之后。
        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})

    # 下一个请求也会发送此回复，因此需将其计入。
    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"},
        )

# 在保存之前，先换入仍在生成中的摘要
# 或继续对话。
if pending is not None:
    swap_in(history, pending.result(), sent)
executor.shutdown()