處理停止原因

{
  "id": "msg_01234",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Here's the answer to your question..."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 100,
    "output_tokens": 50
  }
}

if response.stop_reason == "end_turn":
    # 處理完整回應
    print(response.content[0].text)

# 錯誤：在 tool_result 後立即添加文字
messages = [
    {"role": "user", "content": "Calculate the sum of 1234 and 5678"},
    {"role": "assistant", "content": [
        {
            "type": "tool_use",
            "id": "toolu_123",
            "name": "calculator",
            "input": {"operation": "add", "a": 1234, "b": 5678}
        }
    ]},
    {"role": "user", "content": [
        {
            "type": "tool_result",
            "tool_use_id": "toolu_123",
            "content": "6912"
        },
        {
            "type": "text",
            "text": "Here's the result"  # 不要在 tool_result 後添加文字
        }
    ]}
]

# 正確：直接發送工具結果而不添加額外文字
messages = [
    {"role": "user", "content": "Calculate the sum of 1234 and 5678"},
    {"role": "assistant", "content": [
        {
            "type": "tool_use",
            "id": "toolu_123",
            "name": "calculator",
            "input": {"operation": "add", "a": 1234, "b": 5678}
        }
    ]},
    {"role": "user", "content": [
        {
            "type": "tool_result",
            "tool_use_id": "toolu_123",
            "content": "6912"
        }
    ]}  # 只有 tool_result，沒有額外文字
]

# 如果修復上述問題後仍然得到空回應：
def handle_empty_response(client, messages):
    response = client.messages.create(
        model="claude-sonnet-4-20250514",
        max_tokens=1024,
        messages=messages
    )

    # 檢查回應是否為空
    if (response.stop_reason == "end_turn" and
        not response.content):

        # 錯誤：不要只是用空回應重試
        # 這不會起作用，因為 Claude 已經決定它完成了

        # 正確：在新的使用者訊息中添加繼續提示
        messages.append({"role": "user", "content": "Please continue"})

        response = client.messages.create(
            model="claude-sonnet-4-20250514",
            max_tokens=1024,
            messages=messages
        )

    return response

# 有限 token 的請求
response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=10,
    messages=[{"role": "user", "content": "Explain quantum physics"}]
)

if response.stop_reason == "max_tokens":
    # 回應被截斷
    print("Response was cut off at token limit")
    # 考慮發出另一個請求以繼續

response = client.messages.create(
    model="claude-sonnet-4-5",
    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}")

response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What's the weather?"}]
)

if response.stop_reason == "tool_use":
    # 提取並執行工具
    for content in response.content:
        if content.type == "tool_use":
            result = execute_tool(content.name, content.input)
            # 將結果返回給 Claude 以獲得最終回應

response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    tools=[{"type": "web_search_20250305", "name": "web_search"}],
    messages=[{"role": "user", "content": "Search for latest AI news"}]
)

if response.stop_reason == "pause_turn":
    # 繼續對話
    messages = [
        {"role": "user", "content": original_query},
        {"role": "assistant", "content": response.content}
    ]
    continuation = client.messages.create(
        model="claude-sonnet-4-5",
        messages=messages,
        tools=[{"type": "web_search_20250305", "name": "web_search"}]
    )

response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "[Unsafe request]"}]
)

if response.stop_reason == "refusal":
    # Claude 拒絕回應
    print("Claude was unable to process this request")
    # 考慮重新措辭或修改請求

# 請求最大 token 以獲得盡可能多的內容
response = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=64000,  # 模型的最大輸出 token
    messages=[{"role": "user", "content": "Large input that uses most of context window..."}]
)

if response.stop_reason == "model_context_window_exceeded":
    # 回應在 max_tokens 之前達到上下文視窗限制
    print("Response reached model's context window limit")
    # 回應仍然有效，但受到上下文視窗限制

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:
        # 處理 end_turn 和其他情況
        return response.content[0].text

def handle_truncated_response(response):
    if response.stop_reason in ["max_tokens", "model_context_window_exceeded"]:
        # 選項 1：警告使用者特定限制
        if response.stop_reason == "max_tokens":
            message = "[Response truncated due to max_tokens limit]"
        else:
            message = "[Response truncated due to context window limit]"
        return f"{response.content[0].text}\n\n{message}"

        # 選項 2：繼續生成
        messages = [
            {"role": "user", "content": original_prompt},
            {"role": "assistant", "content": response.content[0].text}
        ]
        continuation = client.messages.create(
            model="claude-sonnet-4-5",
            max_tokens=1024,
            messages=messages + [{"role": "user", "content": "Please continue"}]
        )
        return response.content[0].text + continuation.content[0].text

def handle_paused_conversation(initial_response, max_retries=3):
    response = initial_response
    messages = [{"role": "user", "content": original_query}]
    
    for attempt in range(max_retries):
        if response.stop_reason != "pause_turn":
            break
            
        messages.append({"role": "assistant", "content": response.content})
        response = client.messages.create(
            model="claude-sonnet-4-5",
            messages=messages,
            tools=original_tools
        )
    
    return response

try:
    response = client.messages.create(...)
    
    # 處理帶有 stop_reason 的成功回應
    if response.stop_reason == "max_tokens":
        print("Response was truncated")
    
except anthropic.APIError as e:
    # 處理實際錯誤
    if e.status_code == 429:
        print("Rate limit exceeded")
    elif e.status_code == 500:
        print("Server error")

with client.messages.stream(...) 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-sonnet-4-5",
            messages=messages,
            tools=tools
        )
        
        if response.stop_reason == "tool_use":
            # 執行工具並繼續
            tool_results = execute_tools(response.content)
            messages.append({"role": "assistant", "content": response.content})
            messages.append({"role": "user", "content": tool_results})
        else:
            # 最終回應
            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-sonnet-4-5",
            messages=messages,
            max_tokens=4096
        )

        full_response += response.content[0].text

        if response.stop_reason != "max_tokens":
            break

        # 從中斷的地方繼續
        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):
    """
    在模型的上下文視窗內獲得盡可能多的 token
    而無需計算輸入 token 數量
    """
    response = client.messages.create(
        model="claude-sonnet-4-5",
        messages=[{"role": "user", "content": prompt}],
        max_tokens=64000  # 設定為模型的最大輸出 token
    )

    if response.stop_reason == "model_context_window_exceeded":
        # 在給定輸入大小的情況下獲得了最大可能的 token
        print(f"Generated {response.usage.output_tokens} tokens (context limit reached)")
    elif response.stop_reason == "max_tokens":
        # 獲得了確切請求的 token
        print(f"Generated {response.usage.output_tokens} tokens (max_tokens reached)")
    else:
        # 自然完成
        print(f"Generated {response.usage.output_tokens} tokens (natural completion)")

    return response.content[0].text