{ "type": "tool_use", "id": "toolu_01A09q90qw90lq917835lq9", "name": "str_replace_editor", "input": { "command": "insert", "path": "primes.py", "insert_line": 0, "new_str": "\"\"\"Module for working with prime numbers.\n\nThis module provides functions to check if a number is prime\nand to generate a list of prime numbers up to a given limit.\n\"\"\"\n" }}
此範例演示 Claude 4 模型如何使用文字編輯工具修復 Python 檔案中的語法錯誤。首先，您的應用程式向 Claude 提供文字編輯工具和修復語法錯誤的提示：
curl https://api.anthropic.com/v1/messages \ -H "content-type: application/json" \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -d '{ "model": "claude-sonnet-4-5", "max_tokens": 1024, "tools": [ { "type": "text_editor_20250728", "name": "str_replace_based_edit_tool" } ], "messages": [ { "role": "user", "content": "There'\''s a syntax error in my primes.py file. Can you help me fix it?" } ] }'
Claude 將首先使用文字編輯工具檢視檔案：
{ "id": "msg_01XAbCDeFgHiJkLmNoPQrStU", "model": "claude-sonnet-4-5", "stop_reason": "tool_use", "role": "assistant", "content": [ { "type": "text", "text": "I'll help you fix the syntax error in your primes.py file. First, let me take a look at the file to identify the issue." }, { "type": "tool_use", "id": "toolu_01AbCdEfGhIjKlMnOpQrStU", "name": "str_replace_based_edit_tool", "input": { "command": "view", "path": "primes.py" } } ]}
您的應用程式應該讀取檔案並將其內容返回給 Claude：
curl https://api.anthropic.com/v1/messages \ -H "content-type: application/json" \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -d '{ "model": "claude-sonnet-4-5", "max_tokens": 1024, "tools": [ { "type": "text_editor_20250728", "name": "str_replace_based_edit_tool" } ], "messages": [ { "role": "user", "content": "There'\''s a syntax error in my primes.py file. Can you help me fix it?" }, { "role": "assistant", "content": [ { "type": "text", "text": "I'\''ll help you fix the syntax error in your primes.py file. First, let me take a look at the file to identify the issue." }, { "type": "tool_use", "id": "toolu_01AbCdEfGhIjKlMnOpQrStU", "name": "str_replace_based_edit_tool", "input": { "command": "view", "path": "primes.py" } } ] }, { "role": "user", "content": [ { "type": "tool_result", "tool_use_id": "toolu_01AbCdEfGhIjKlMnOpQrStU", "content": "1: def is_prime(n):\n2: \"\"\"Check if a number is prime.\"\"\"\n3: if n <= 1:\n4: return False\n5: if n <= 3:\n6: return True\n7: if n % 2 == 0 or n % 3 == 0:\n8: return False\n9: i = 5\n10: while i * i <= n:\n11: if n % i == 0 or n % (i + 2) == 0:\n12: return False\n13: i += 6\n14: return True\n15: \n16: def get_primes(limit):\n17: \"\"\"Generate a list of prime numbers up to the given limit.\"\"\"\n18: primes = []\n19: for num in range(2, limit + 1)\n20: if is_prime(num):\n21: primes.append(num)\n22: return primes\n23: \n24: def main():\n25: \"\"\"Main function to demonstrate prime number generation.\"\"\"\n26: limit = 100\n27: prime_list = get_primes(limit)\n28: print(f\"Prime numbers up to {limit}:\")\n29: print(prime_list)\n30: print(f\"Found {len(prime_list)} prime numbers.\")\n31: \n32: if __name__ == \"__main__\":\n33: main()" } ] } ] }'
{ "id": "msg_01VwXyZAbCdEfGhIjKlMnO", "model": "claude-sonnet-4-5", "stop_reason": "tool_use", "role": "assistant", "content": [ { "type": "text", "text": "I found the syntax error in your primes.py file. In the `get_primes` function, there is a missing colon (:) at the end of the for loop line. Let me fix that for you." }, { "type": "tool_use", "id": "toolu_01PqRsTuVwXyZAbCdEfGh", "name": "str_replace_based_edit_tool", "input": { "command": "str_replace", "path": "primes.py", "old_str": " for num in range(2, limit + 1)", "new_str": " for num in range(2, limit + 1):" } } ]}
您的應用程式應該進行編輯並返回結果：
response = client.messages.create( model="claude-sonnet-4-5", max_tokens=1024, tools=[ { "type": "text_editor_20250728", "name": "str_replace_based_edit_tool" } ], messages=[ # Previous messages... { "role": "assistant", "content": [ { "type": "text", "text": "I found the syntax error in your primes.py file. In the `get_primes` function, there is a missing colon (:) at the end of the for loop line. Let me fix that for you." }, { "type": "tool_use", "id": "toolu_01PqRsTuVwXyZAbCdEfGh", "name": "str_replace_based_edit_tool", "input": { "command": "str_replace", "path": "primes.py", "old_str": " for num in range(2, limit + 1)", "new_str": " for num in range(2, limit + 1):" } } ] }, { "role": "user", "content": [ { "type": "tool_result", "tool_use_id": "toolu_01PqRsTuVwXyZAbCdEfGh", "content": "Successfully replaced text at exactly one location." } ] } ])
最後，Claude 將提供完整的修復說明：
{ "id": "msg_01IjKlMnOpQrStUvWxYzAb", "model": "claude-sonnet-4-5", "stop_reason": "end_turn", "role": "assistant", "content": [ { "type": "text", "text": "I've fixed the syntax error in your primes.py file. The issue was in the `get_primes` function at line 19. There was a missing colon (:) at the end of the for loop line.\n\nHere's what I changed:\n\nFrom:\n```python\nfor num in range(2, limit + 1)\n```\n\nTo:\n```python\nfor num in range(2, limit + 1):\n```\n\nIn Python, a colon is required at the end of statements that start a new code block, such as for loops, if statements, function definitions, etc. Without the colon, Python raises a syntax error because it doesn't know where the code block begins.\n\nYour code should now run correctly. The function will properly generate a list of prime numbers up to the specified limit." } ]}
此範例演示 Claude Sonnet 3.7 如何使用文字編輯工具修復 Python 檔案中的語法錯誤。首先，您的應用程式向 Claude 提供文字編輯工具和修復語法錯誤的提示：
import anthropicclient = anthropic.Anthropic()response = client.messages.create( model="claude-3-7-sonnet-20250219", max_tokens=1024, tools=[ { "type": "text_editor_20250124", "name": "str_replace_editor" } ], messages=[ { "role": "user", "content": "There's a syntax error in my primes.py file. Can you help me fix it?" } ])print(response)
Claude Sonnet 3.7 範例遵循與上面 Claude 4 範例相同的格式，使用相同的工具呼叫和回應，但使用 text_editor_20250124 工具類型和 str_replace_editor 名稱。
文字編輯工具實現為無模式工具。使用此工具時，您不需要像其他工具那樣提供輸入模式；模式內置於 Claude 的模型中，無法修改。工具類型取決於模型版本：
Claude 4：type: "text_editor_20250728"
Claude Sonnet 3.7：type: "text_editor_20250124"
1
初始化您的編輯器實現
建立幫助函數來處理檔案操作，如讀取、寫入和修改檔案。考慮實現備份功能以從錯誤中恢復。
2
處理編輯器工具呼叫
建立一個函數，根據命令類型處理來自 Claude 的工具呼叫：
def handle_editor_tool(tool_call, model_version): input_params = tool_call.input command = input_params.get('command', '') file_path = input_params.get('path', '') if command == 'view': # Read and return file contents pass elif command == 'str_replace': # Replace text in file pass elif command == 'create': # Create new file pass elif command == 'insert': # Insert text at location pass elif command == 'undo_edit': # Check if it's a Claude 4 model if 'str_replace_based_edit_tool' in model_version: return {"error": "undo_edit command is not supported in Claude 4"} # Restore from backup for Claude 3.7 pass
3
實現安全措施
添加驗證和安全檢查：
驗證檔案路徑以防止目錄遍歷
在進行變更前建立備份
優雅地處理錯誤
實現權限檢查
4
處理 Claude 的回應
從 Claude 的回應中提取並處理工具呼叫：
# Process tool use in Claude's responsefor content in response.content: if content.type == "tool_use": # Execute the tool based on command result = handle_editor_tool(content) # Return result to Claude tool_result = { "type": "tool_result", "tool_use_id": content.id, "content": result }
{ "role": "user", "content": [ { "type": "tool_result", "tool_use_id": "toolu_01A09q90qw90lq917835lq9", "content": "Error: Found 3 matches for replacement text. Please provide more context to make a unique match.", "is_error": true } ]}
替換文字無匹配
如果 Claude 的 str_replace 命令與檔案中的任何文字都不匹配，返回適當的錯誤訊息：
{ "role": "user", "content": [ { "type": "tool_result", "tool_use_id": "toolu_01A09q90qw90lq917835lq9", "content": "Error: No match found for replacement. Please check your text and try again.", "is_error": true } ]}
在應用程式中實現備份系統，在允許 Claude 編輯檔案之前建立檔案副本，特別是對於重要或生產程式碼。
def backup_file(file_path): """Create a backup of a file before editing.""" backup_path = f"{file_path}.backup" if os.path.exists(file_path): with open(file_path, 'r') as src, open(backup_path, 'w') as dst: dst.write(src.read())
def safe_replace(file_path, old_text, new_text): """Replace text only if there's exactly one match.""" with open(file_path, 'r') as f: content = f.read() count = content.count(old_text) if count == 0: return "Error: No match found" elif count > 1: return f"Error: Found {count} matches" else: new_content = content.replace(old_text, new_text) with open(file_path, 'w') as f: f.write(new_content) return "Successfully replaced text"
驗證變更
Claude 對檔案進行變更後，通過執行測試或檢查程式碼是否仍按預期工作來驗證變更。
def verify_changes(file_path): """Run tests or checks after making changes.""" try: # For Python files, check for syntax errors if file_path.endswith('.py'): import ast with open(file_path, 'r') as f: ast.parse(f.read()) return "Syntax check passed" except Exception as e: return f"Verification failed: {str(e)}"
The text editor tool uses the same pricing structure as other tools used with Claude. It follows the standard input and output token pricing based on the Claude model you’re using.In addition to the base tokens, the following additional input tokens are needed for the text editor tool:
