使用 Claude 構建

處理停止原因

當您向 Messages API 發送請求時，Claude 的回應包含一個 stop_reason 欄位，指示模型為何停止生成回應。理解這些值對於建構能適當處理不同回應類型的穩健應用程式至關重要。

有關 API 回應中 stop_reason 的詳細資訊，請參閱 Messages API 參考文件。

什麼是 stop_reason？

stop_reason 欄位是每個成功的 Messages API 回應的一部分。與表示處理請求失敗的錯誤不同，stop_reason 告訴您 Claude 為何成功完成了回應生成。

Example response

{
  "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
  }
}

停止原因值

end_turn

最常見的停止原因。表示 Claude 自然地完成了回應。

if response.stop_reason == "end_turn":
    # Process the complete response
    print(response.content[0].text)

end_turn 的空回應

有時 Claude 會返回一個空回應（恰好 2-3 個 token，沒有內容），且 stop_reason: "end_turn"。這通常發生在 Claude 判斷助手回合已完成時，特別是在工具結果之後。

常見原因：

在工具結果之後立即添加文字區塊（Claude 學會期望使用者總是在工具結果後插入文字，因此它結束回合以遵循該模式）
將 Claude 已完成的回應發送回去而不添加任何內容（Claude 已經決定完成了，所以它會保持完成狀態）

如何防止空回應：

# INCORRECT: Adding text immediately after tool_result
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"  # Don't add text after tool_result
        }
    ]}
]

# CORRECT: Send tool results directly without additional text
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"
        }
    ]}  # Just the tool_result, no additional text
]

# If you still get empty responses after fixing the above:
def handle_empty_response(client, messages):
    response = client.messages.create(
        model="claude-opus-4-6",
        max_tokens=1024,
        messages=messages
    )

    # Check if response is empty
    if (response.stop_reason == "end_turn" and
        not response.content:

        # INCORRECT: Don't just retry with the empty response
        # This won't work because Claude already decided it's done

        # CORRECT: Add a continuation prompt in a NEW user message
        messages.append({"role": "user", "content": "Please continue"})

        response = client.messages.create(
            model="claude-opus-4-6",
            max_tokens=1024,
            messages=messages
        )

    return response

最佳實踐：

永遠不要在工具結果之後立即添加文字區塊 - 這會教導 Claude 在每次工具使用後期望使用者輸入
不要在不修改的情況下重試空回應 - 簡單地將空回應發送回去不會有幫助
將繼續提示作為最後手段 - 僅在上述修復無法解決問題時使用

max_tokens

Claude 停止是因為達到了您在請求中指定的 max_tokens 限制。

# Request with limited tokens
response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=10,
    messages=[{"role": "user", "content": "Explain quantum physics"}]
)

if response.stop_reason == "max_tokens":
    # Response was truncated
    print("Response was cut off at token limit")
    # Consider making another request to continue

stop_sequence

Claude 遇到了您的自訂停止序列之一。

response = client.messages.create(
    model="claude-opus-4-6",
    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}")

tool_use

Claude 正在呼叫工具並期望您執行它。

對於大多數工具使用實作，我們建議使用 tool runner，它會自動處理工具執行、結果格式化和對話管理。

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    tools=[weather_tool],
    messages=[{"role": "user", "content": "What's the weather?"}]
)

if response.stop_reason == "tool_use":
    # Extract and execute the tool
    for content in response.content:
        if content.type == "tool_use":
            result = execute_tool(content.name, content.input)
            # Return result to Claude for final response

pause_turn

當 Claude 需要暫停長時間運行的操作時，與網路搜尋等伺服器工具一起使用。

response = client.messages.create(
    model="claude-opus-4-6",
    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":
    # Continue the conversation
    messages = [
        {"role": "user", "content": original_query},
        {"role": "assistant", "content": response.content}
    ]
    continuation = client.messages.create(
        model="claude-opus-4-6",
        messages=messages,
        tools=[{"type": "web_search_20250305", "name": "web_search"}]
    )

refusal

Claude 因安全考量而拒絕生成回應。

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "[Unsafe request]"}]
)

if response.stop_reason == "refusal":
    # Claude declined to respond
    print("Claude was unable to process this request")
    # Consider rephrasing or modifying the request

如果您在使用 Claude Sonnet 4.5 或 Opus 4.1 時頻繁遇到 refusal 停止原因，您可以嘗試將 API 呼叫更新為使用 Sonnet 4（claude-sonnet-4-20250514），它有不同的使用限制。了解更多關於理解 Sonnet 4.5 的 API 安全過濾器。

要了解更多關於 Claude Sonnet 4.5 的 API 安全過濾器觸發的拒絕，請參閱理解 Sonnet 4.5 的 API 安全過濾器。

model_context_window_exceeded

Claude 停止是因為達到了模型的上下文視窗限制。這允許您在不知道確切輸入大小的情況下請求最大可能的 token 數。

# Request with maximum tokens to get as much as possible
response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=64000,  # Model's maximum output tokens
    messages=[{"role": "user", "content": "Large input that uses most of context window..."}]
)

if response.stop_reason == "model_context_window_exceeded":
    # Response hit context window limit before max_tokens
    print("Response reached model's context window limit")
    # The response is still valid but was limited by context window

此停止原因在 Sonnet 4.5 及更新模型中預設可用。對於較早的模型，請使用 beta 標頭 model-context-window-exceeded-2025-08-26 來啟用此行為。