중지 이유 및 폴백

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":
    # 전체 응답 처리
    print(response.content[0].text)

client = anthropic.Anthropic()
# 제한된 토큰으로 요청
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":
    # 응답이 잘렸습니다
    print("Response was cut off at token limit")
    # 계속하려면 추가 요청을 고려하세요

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":
    # 도구를 추출하고 실행합니다
    for block in response.content:
        if block.type == "tool_use":
            result = execute_tool(block.name, block.input)
            # 최종 응답을 위해 결과를 Claude에 반환합니다

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":
    # 응답을 다시 전송하여 대화를 계속합니다
    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":
    # Claude가 응답을 거부했습니다
    print("Claude was unable to process this request")
    # 요청을 다시 표현하거나 수정하는 것을 고려하세요

# 가능한 한 많이 얻기 위해 최대 토큰으로 요청
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":
    # 응답이 max_tokens 이전에 컨텍스트 윈도우 한도에 도달함
    print("Response reached model's context window limit")
    # 응답은 여전히 유효하지만 컨텍스트 윈도우에 의해 제한됨

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:
        # end_turn 및 기타 경우 처리
        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":
            # Claude가 처리를 완료함 - 최종 응답 반환
            return response

        # pause_turn: 역할 교대를 유지하기 위해 전체 메시지 목록을 교체
        messages = [
            {"role": "user", "content": user_query},
            {"role": "assistant", "content": response.content},
        ]

    # 최대 연속 횟수에 도달함 - 마지막 응답 반환
    return response

client = anthropic.Anthropic()

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

    # stop_reason이 포함된 성공 응답 처리
    if response.stop_reason == "max_tokens":
        print("Response was truncated")

except anthropic.APIStatusError as e:
    # 실제 오류 처리
    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":
            # 도구를 실행하고 계속 진행
            tool_results = execute_tools(response.content)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": tool_results})
        else:
            # 최종 응답
            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

        # 중단된 지점부터 계속
        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":
        # 입력 크기를 고려한 최대 가능 토큰 수에 도달함
        print(
            f"Generated {response.usage.output_tokens} tokens (context limit reached)"
        )
    elif response.stop_reason == "max_tokens":
        # 요청한 토큰 수에 정확히 도달함
        print(f"Generated {response.usage.output_tokens} tokens (max_tokens reached)")
    else:
        # 자연스러운 완료
        print(f"Generated {response.usage.output_tokens} tokens (natural completion)")

    return response.content[0].text