停止理由とフォールバック

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
if response.stop_reason == "end_turn":
    # 完全なレスポンスを処理します
    for block in response.content:
        if block.type == "text":
            print(block.text)

client = anthropic.Anthropic()
# トークン数を制限したリクエスト
response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=10,
    messages=[{"role": "user", "content": "Explain quantum physics"}],
)

if response.stop_reason == "max_tokens":
    # レスポンスが途中で切り捨てられました
    print("Response was cut off at token limit")
    # 続きを取得するには、再度リクエストを送信することを検討してください

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    stop_sequences=["END", "STOP"],
    messages=[{"role": "user", "content": "Generate text until you say END"}],
)

if response.stop_reason == "stop_sequence":
    print(f"Stopped at sequence: {response.stop_sequence}")

client = anthropic.Anthropic()
weather_tool = {
    "name": "get_weather",
    "description": "Get the current weather in a given location",
    "input_schema": {
        "type": "object",
        "properties": {
            "location": {"type": "string", "description": "City and state"},
        },
        "required": ["location"],
    },
}


def execute_tool(name, tool_input):
    """Run a tool and return the result."""
    return f"Weather in {tool_input.get('location', 'unknown')}: 72°F"


response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What is the weather in San Francisco?"}],
)

if response.stop_reason == "tool_use":
    # ツールを抽出して実行します
    for block in response.content:
        if block.type == "tool_use":
            result = execute_tool(block.name, block.input)
            # 最終的な応答のために結果を Claude に返します

response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=4096,
    tools=[{"type": "web_search_20250305", "name": "web_search"}],
    messages=[{"role": "user", "content": "Search for latest AI news"}],
)

if response.stop_reason == "pause_turn":
    # レスポンスを送り返して会話を続けます
    messages = [
        {"role": "user", "content": "Search for latest AI news"},
        {"role": "assistant", "content": response.content},
    ]
    continuation = client.messages.create(
        model="claude-opus-5-5",
        max_tokens=4096,
        messages=messages,
        tools=[{"type": "web_search_20250305", "name": "web_search"}],
    )

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "[Unsafe request]"}],
)

if response.stop_reason == "refusal":
    # Claude が応答を拒否しました
    print("Claude was unable to process this request")
    # リクエストの言い換えや修正を検討してください

client = anthropic.Anthropic()

# できるだけ多く取得するため、最大トークン数でリクエストします
response = client.beta.messages.create(
    model="claude-opus-5-5",
    max_tokens=20000,  # Python SDK requires streaming for max_tokens above ~21k
    messages=[
        {"role": "user", "content": "Large input that uses most of context window..."}
    ],
)

if response.stop_reason == "model_context_window_exceeded":
    # max_tokens に達する前にレスポンスがコンテキストウィンドウの上限に達しました
    print("Response reached model's context window limit")
    # レスポンスは有効ですが、コンテキストウィンドウによって制限されています

def handle_response(response):
    match response.stop_reason:
        case "tool_use":
            return handle_tool_use(response)
        case "max_tokens":
            return handle_truncation(response)
        case "model_context_window_exceeded":
            return handle_context_limit(response)
        case "pause_turn":
            return handle_pause(response)
        case "refusal":
            return handle_refusal(response)
        case _:
            # end_turn およびその他のケースを処理します
            return next(
                (block.text for block in response.content if block.type == "text"),
                "",
            )

def handle_truncated_response(response):
    text = next((block.text for block in response.content if block.type == "text"), "")
    if response.stop_reason in ["max_tokens", "model_context_window_exceeded"]:
        if response.stop_reason == "max_tokens":
            note = "[Response truncated due to max_tokens limit]"
        else:
            note = "[Response truncated due to context window limit]"
        return f"{text}\n\n{note}"
    return text

client = anthropic.Anthropic()


def handle_server_tool_conversation(client, user_query, tools, max_requests=5):
    messages = [{"role": "user", "content": user_query}]
    container_id = None

    for _ in range(max_requests):
        response = client.messages.create(
            model="claude-opus-5-5",
            max_tokens=4096,
            messages=messages,
            tools=tools,
            container=container_id,
        )

        if response.stop_reason != "pause_turn":
            # 一時停止していない場合：レスポンスを返します
            return response

        # pause_turn：一時停止したレスポンスをassistantメッセージとして追加し、続行します
        messages.append({"role": "assistant", "content": response.content})

        # ツールがコンテナ内で実行された場合、ファイルを保持するためにそのIDを送り返します
        if response.container:
            container_id = response.container.id

    # max_requests回のリクエスト後も一時停止している場合：最後のレスポンスを返します
    return response


response = handle_server_tool_conversation(
    client,
    "Use the code execution tool to find the 1,000th prime number.",
    [{"type": "code_execution_20250825", "name": "code_execution"}],
)
print(response.stop_reason)

client = anthropic.Anthropic()

try:
    response = client.messages.create(
        model="claude-opus-5-5",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Hello!"}],
    )

    # stop_reason を含む成功レスポンスを処理します
    if response.stop_reason == "max_tokens":
        print("Response was truncated")

except anthropic.APIStatusError as e:
    # 実際のエラーを処理します
    match e.status_code:
        case 429:
            print("Rate limit exceeded")
        case 500:
            print("Server error")

client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-opus-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
) as stream:
    for event in stream:
        if event.type == "message_delta":
            stop_reason = event.delta.stop_reason
            if stop_reason:
                print(f"Stream ended with: {stop_reason}")

def complete_tool_workflow(client, user_query, tools):
    messages = [{"role": "user", "content": user_query}]

    while True:
        response = client.messages.create(
            model="claude-opus-5-5",
            max_tokens=1024,
            messages=messages,
            tools=tools,
        )

        if response.stop_reason == "tool_use":
            # ツールを実行して続行します
            tool_results = execute_tools(response.content)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": tool_results})
        else:
            # 最終レスポンス
            return response

def get_complete_response(client, prompt, max_attempts=3):
    messages = [{"role": "user", "content": prompt}]
    full_response = ""

    for _ in range(max_attempts):
        response = client.messages.create(
            model="claude-opus-5-5", messages=messages, max_tokens=4096
        )

        full_response += next(
            (block.text for block in response.content if block.type == "text"), ""
        )

        if response.stop_reason != "max_tokens":
            break

        # 中断したところから再開します
        messages = [
            {"role": "user", "content": prompt},
            {"role": "assistant", "content": full_response},
            {"role": "user", "content": "Please continue from where you left off."},
        ]

    return full_response

def get_max_possible_tokens(client, prompt):
    """
    Get as many tokens as possible within the model's context window
    without needing to calculate input token count
    """
    response = client.beta.messages.create(
        model="claude-opus-5-5",
        messages=[{"role": "user", "content": prompt}],
        max_tokens=20000,  # Python SDK requires streaming for max_tokens above ~21k
    )

    match response.stop_reason:
        case "model_context_window_exceeded":
            # 入力サイズに対して可能な最大トークン数を取得しました
            print(
                f"Generated {response.usage.output_tokens} tokens (context limit reached)"
            )
        case "max_tokens":
            # 要求どおりのトークン数を取得しました
            print(
                f"Generated {response.usage.output_tokens} tokens (max_tokens reached)"
            )
        case _:
            # 自然な完了です
            print(
                f"Generated {response.usage.output_tokens} tokens (natural completion)"
            )

    return next((block.text for block in response.content if block.type == "text"), "")