Причины остановки и резервные варианты

client = anthropic.Anthropic()

response = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
if response.stop_reason == "end_turn":
    # Обработка полного ответа
    print(response.content[0].text)

client = anthropic.Anthropic()
# Запрос с ограниченным числом токенов
response = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=10,
    messages=[{"role": "user", "content": "Explain quantum physics"}],
)

if response.stop_reason == "max_tokens":
    # Ответ был усечён
    print("Response was cut off at token limit")
    # Рассмотрите возможность отправить ещё один запрос для продолжения

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-opus-4-8",
    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):
    """Execute a tool and return the result."""
    return f"Weather in {tool_input.get('location', 'unknown')}: 72°F"


response = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What is the weather in San Francisco?"}],
)

if response.stop_reason == "tool_use":
    # Извлечь и выполнить инструмент
    for block in response.content:
        if block.type == "tool_use":
            result = execute_tool(block.name, block.input)
            # Вернуть результат Claude для окончательного ответа

response = client.messages.create(
    model="claude-opus-4-8",
    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":
    # Продолжите диалог, отправив ответ обратно
    messages = [
        {"role": "user", "content": "Search for latest AI news"},
        {"role": "assistant", "content": response.content},
    ]
    continuation = client.messages.create(
        model="claude-opus-4-8",
        max_tokens=4096,
        messages=messages,
        tools=[{"type": "web_search_20250305", "name": "web_search"}],
    )

client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "[Unsafe request]"}],
)

if response.stop_reason == "refusal":
    # Claude отказался отвечать
    print("Claude was unable to process this request")
    # Попробуйте переформулировать или изменить запрос

# Запрос с максимальным числом токенов, чтобы получить как можно больше
response = client.beta.messages.create(
    model="claude-opus-4-8",
    max_tokens=20000,  # Python SDK requires streaming for max_tokens above ~21k (Opus 4.8 supports 128k with streaming)
    messages=[
        {"role": "user", "content": "Large input that uses most of context window..."}
    ],
)

if response.stop_reason == "model_context_window_exceeded":
    # Ответ достиг предела контекстного окна раньше, чем max_tokens
    print("Response reached model's context window limit")
    # Ответ по-прежнему корректен, но был ограничен контекстным окном

def handle_response(response):
    if response.stop_reason == "tool_use":
        return handle_tool_use(response)
    elif response.stop_reason == "max_tokens":
        return handle_truncation(response)
    elif response.stop_reason == "model_context_window_exceeded":
        return handle_context_limit(response)
    elif response.stop_reason == "pause_turn":
        return handle_pause(response)
    elif response.stop_reason == "refusal":
        return handle_refusal(response)
    else:
        # Обработка end_turn и других случаев
        return response.content[0].text

def handle_truncated_response(response):
    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"{response.content[0].text}\n\n{note}"
    return response.content[0].text

def handle_server_tool_conversation(client, user_query, tools, max_continuations=5):
    """
    Handle server tool conversations that may require multiple continuations.

    The server runs a sampling loop when executing server tools. If the loop
    reaches its iteration limit, the API returns pause_turn. Continue the
    conversation by sending the response back to let Claude finish.
    """
    messages = [{"role": "user", "content": user_query}]

    for _ in range(max_continuations):
        response = client.messages.create(
            model="claude-opus-4-8", max_tokens=4096, messages=messages, tools=tools
        )

        if response.stop_reason != "pause_turn":
            # Claude завершил обработку — возвращаем итоговый ответ
            return response

        # pause_turn: заменяем весь список сообщений, чтобы сохранить чередование ролей
        messages = [
            {"role": "user", "content": user_query},
            {"role": "assistant", "content": response.content},
        ]

    # Достигнут максимум продолжений — возвращаем последний ответ
    return response

client = anthropic.Anthropic()

try:
    response = client.messages.create(
        model="claude-opus-4-8",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Hello!"}],
    )

    # Обработка успешного ответа со stop_reason
    if response.stop_reason == "max_tokens":
        print("Response was truncated")

except anthropic.APIStatusError as e:
    # Обработка фактических ошибок
    if e.status_code == 429:
        print("Rate limit exceeded")
    elif e.status_code == 500:
        print("Server error")

client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-opus-4-8",
    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-4-8", max_tokens=1024, messages=messages, tools=tools
        )

        if response.stop_reason == "tool_use":
            # Выполнить инструменты и продолжить
            tool_results = execute_tools(response.content)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": tool_results})
        else:
            # Окончательный ответ
            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-4-8", messages=messages, max_tokens=4096
        )

        full_response += response.content[0].text

        if response.stop_reason != "max_tokens":
            break

        # Продолжить с места остановки
        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-4-8",
        messages=[{"role": "user", "content": prompt}],
        max_tokens=20000,  # Python SDK requires streaming for max_tokens above ~21k
    )

    if response.stop_reason == "model_context_window_exceeded":
        # Получено максимально возможное число токенов при данном размере входных данных
        print(
            f"Generated {response.usage.output_tokens} tokens (context limit reached)"
        )
    elif response.stop_reason == "max_tokens":
        # Получено ровно запрошенное число токенов
        print(f"Generated {response.usage.output_tokens} tokens (max_tokens reached)")
    else:
        # Естественное завершение
        print(f"Generated {response.usage.output_tokens} tokens (natural completion)")

    return response.content[0].text