コンパクション

client = anthropic.Anthropic()

messages = [{"role": "user", "content": "Help me build a website"}]

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

# レスポンス（コンパクションブロックを含む）を追加して会話を継続します
messages.append({"role": "assistant", "content": response.content})

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [
            {
                "type": "compact_20260112",
                "trigger": {"type": "input_tokens", "value": 150000},
            }
        ]
    },
)

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [
            {
                "type": "compact_20260112",
                "instructions": "Focus on preserving code snippets, variable names, and technical decisions.",
            }
        ]
    },
)

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [{"type": "compact_20260112", "pause_after_compaction": True}]
    },
)

# コンパクションによって一時停止が発生したかを確認
if response.stop_reason == "compaction":
    # レスポンスにはコンパクションブロックのみが含まれる
    messages.append({"role": "assistant", "content": response.content})

    # リクエストを継続
    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-5",
        max_tokens=4096,
        messages=messages,
        context_management={"edits": [{"type": "compact_20260112"}]},
    )

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
TRIGGER_THRESHOLD = 100_000
TOTAL_TOKEN_BUDGET = 3_000_000
n_compactions = 0

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={
        "edits": [
            {
                "type": "compact_20260112",
                "trigger": {"type": "input_tokens", "value": TRIGGER_THRESHOLD},
                "pause_after_compaction": True,
            }
        ]
    },
)

if response.stop_reason == "compaction":
    n_compactions += 1
    messages.append({"role": "assistant", "content": response.content})

    # 消費された合計トークン数を推定し、予算超過の場合はまとめを促す
    if n_compactions * TRIGGER_THRESHOLD >= TOTAL_TOKEN_BUDGET:
        messages.append(
            {
                "role": "user",
                "content": "Please wrap up your current work and summarize the final state.",
            }
        )

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)
# コンパクションブロックを含むレスポンスを受け取った後
messages.append({"role": "assistant", "content": response.content})

# 会話を続ける
messages.append({"role": "user", "content": "Now add error handling"})

response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]

with client.beta.messages.stream(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
) as stream:
    for event in stream:
        if event.type == "content_block_start":
            if event.content_block.type == "compaction":
                print("Compaction started...")
            elif event.content_block.type == "text":
                print("Text response started...")

        elif event.type == "content_block_delta":
            if event.delta.type == "compaction_delta":
                print(f"Compaction complete: {len(event.delta.content or '')} chars")
            elif event.delta.type == "text_delta":
                print(event.delta.text, end="", flush=True)

    # 最終的に蓄積されたメッセージを取得
    message = stream.get_final_message()
    messages.append({"role": "assistant", "content": message.content})

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
response = client.beta.messages.create(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    max_tokens=4096,
    system=[
        {
            "type": "text",
            "text": "You are a helpful coding assistant...",
            "cache_control": {
                "type": "ephemeral"
            },  # Cache the system prompt separately
        }
    ],
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

client = anthropic.Anthropic()
messages = [{"role": "user", "content": "Hello, Claude"}]
count_response = client.beta.messages.count_tokens(
    betas=["compact-2026-01-12"],
    model="claude-opus-5",
    messages=messages,
    context_management={"edits": [{"type": "compact_20260112"}]},
)

print(f"Current tokens: {count_response.input_tokens}")
print(f"Original tokens: {count_response.context_management.original_input_tokens}")

client = anthropic.Anthropic()

messages: list[dict] = []


def chat(user_message: str) -> str:
    messages.append({"role": "user", "content": user_message})

    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-5",
        max_tokens=4096,
        messages=messages,
        context_management={
            "edits": [
                {
                    "type": "compact_20260112",
                    "trigger": {"type": "input_tokens", "value": 100000},
                }
            ]
        },
    )

    # レスポンスを追加（コンパクションブロックは自動的に含まれます）
    messages.append({"role": "assistant", "content": response.content})

    # テキストコンテンツを返す
    return next(block.text for block in response.content if block.type == "text")


# 長い会話を実行する
print(chat("Help me build a Python web scraper"))
print(chat("Add support for JavaScript-rendered pages"))
print(chat("Now add rate limiting and error handling"))
# 会話が必要な限りchat()を呼び出し続ける

from typing import Any

client = anthropic.Anthropic()

messages: list[dict[str, Any]] = []


def chat(user_message: str) -> str:
    messages.append({"role": "user", "content": user_message})

    response = client.beta.messages.create(
        betas=["compact-2026-01-12"],
        model="claude-opus-5",
        max_tokens=4096,
        messages=messages,
        context_management={
            "edits": [
                {
                    "type": "compact_20260112",
                    "trigger": {"type": "input_tokens", "value": 100000},
                    "pause_after_compaction": True,
                }
            ]
        },
    )

    # コンパクションが発生して一時停止したかどうかを確認
    if response.stop_reason == "compaction":
        # レスポンスからコンパクションブロックを取得
        compaction_block = response.content[0]

        # 直前のやり取り + 現在のユーザーメッセージ(3件)を保持
        # コンパクションブロックの後に含めることで保持する
        preserved_messages = messages[-3:] if len(messages) >= 3 else messages

        # 新しいメッセージリストを構築:コンパクション + 保持したメッセージ
        new_assistant_content = [compaction_block]
        messages_after_compaction = [
            {"role": "assistant", "content": new_assistant_content}
        ] + preserved_messages

        # コンパクションされたコンテキスト + 保持したメッセージでリクエストを継続
        response = client.beta.messages.create(
            betas=["compact-2026-01-12"],
            model="claude-opus-5",
            max_tokens=4096,
            messages=messages_after_compaction,
            context_management={"edits": [{"type": "compact_20260112"}]},
        )

        # コンパクションを反映するようにメッセージリストを更新
        messages.clear()
        messages.extend(messages_after_compaction)

    # 最終レスポンスを追加
    messages.append({"role": "assistant", "content": response.content})

    # テキストコンテンツを返す
    return next(block.text for block in response.content if block.type == "text")


# 長い会話を実行
print(chat("Help me build a Python web scraper"))
print(chat("Add support for JavaScript-rendered pages"))
print(chat("Now add rate limiting and error handling"))
# 会話が必要とする限りchat()を呼び出し続ける