Was this page helpful?
pip install claude-agent-sdkquery() 和 ClaudeSDKClient 之間選擇Python SDK 提供兩種與 Claude Code 互動的方式:
| 功能 | query() | ClaudeSDKClient |
|---|---|---|
| 工作階段 | 每次建立新的工作階段 | 重複使用相同的工作階段 |
| 對話 | 單次交換 | 在相同上下文中進行多次交換 |
| 連線 | 自動管理 | 手動控制 |
| 串流輸入 | ✅ 支援 | ✅ 支援 |
| 中斷 | ❌ 不支援 | ✅ 支援 |
| Hooks | ❌ 不支援 | ✅ 支援 |
| 自訂工具 | ❌ 不支援 | ✅ 支援 |
| 繼續聊天 | ❌ 每次建立新工作階段 | ✅ 維持對話 |
| 使用情境 | 一次性任務 | 持續對話 |
query()(每次建立新工作階段)最適合:
ClaudeSDKClient(持續對話)最適合:
query()為每次與 Claude Code 的互動建立新的工作階段。回傳一個非同步迭代器,在訊息到達時逐一產生訊息。每次呼叫 query() 都會重新開始,不保留先前互動的記憶。
async def query(
*,
prompt: str | AsyncIterable[dict[str, Any]],
options: ClaudeAgentOptions | None = None
) -> AsyncIterator[Message]| 參數 | 型別 | 說明 |
|---|---|---|
prompt | str | AsyncIterable[dict] | 輸入提示,可以是字串或用於串流模式的非同步可迭代物件 |
options | ClaudeAgentOptions | None | 選用的配置物件(若為 None 則預設為 ClaudeAgentOptions()) |
回傳一個 AsyncIterator[Message],從對話中逐一產生訊息。
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions
async def main():
options = ClaudeAgentOptions(
system_prompt="You are an expert Python developer",
permission_mode='acceptEdits',
cwd="/home/user/project"
)
async for message in query(
prompt="Create a Python web server",
options=options
):
print(message)
asyncio.run(main())tool()用於定義具有型別安全的 MCP 工具的裝飾器。
def tool(
name: str,
description: str,
input_schema: type | dict[str, Any]
) -> Callable[[Callable[[Any], Awaitable[dict[str, Any]]]], SdkMcpTool[Any]]| 參數 | 型別 | 說明 |
|---|---|---|
name | str | 工具的唯一識別碼 |
description | str | 人類可讀的工具功能說明 |
input_schema | type | dict[str, Any] | 定義工具輸入參數的結構描述(見下方) |
簡單型別對應(推薦):
{"text": str, "count": int, "enabled": bool}JSON Schema 格式(用於複雜驗證):
{
"type": "object",
"properties": {
"text": {"type": "string"},
"count": {"type": "integer", "minimum": 0}
},
"required": ["text"]
}一個裝飾器函式,包裝工具實作並回傳一個 SdkMcpTool 實例。
from claude_agent_sdk import tool
from typing import Any
@tool("greet", "Greet a user", {"name": str})
async def greet(args: dict[str, Any]) -> dict[str, Any]:
return {
"content": [{
"type": "text",
"text": f"Hello, {args['name']}!"
}]
}create_sdk_mcp_server()建立一個在您的 Python 應用程式內執行的程序內 MCP 伺服器。
def create_sdk_mcp_server(
name: str,
version: str = "1.0.0",
tools: list[SdkMcpTool[Any]] | None = None
) -> McpSdkServerConfig| 參數 | 型別 | 預設值 | 說明 |
|---|---|---|---|
name | str | - | 伺服器的唯一識別碼 |
version | str | "1.0.0" | 伺服器版本字串 |
tools | list[SdkMcpTool[Any]] | None | None | 使用 @tool 裝飾器建立的工具函式列表 |
回傳一個 McpSdkServerConfig 物件,可傳遞給 ClaudeAgentOptions.mcp_servers。
from claude_agent_sdk import tool, create_sdk_mcp_server
@tool("add", "Add two numbers", {"a": float, "b": float})
async def add(args):
return {
"content": [{
"type": "text",
"text": f"Sum: {args['a'] + args['b']}"
}]
}
@tool("multiply", "Multiply two numbers", {"a": float, "b": float})
async def multiply(args):
return {
"content": [{
"type": "text",
"text": f"Product: {args['a'] * args['b']}"
}]
}
calculator = create_sdk_mcp_server(
name="calculator",
version="2.0.0",
tools=[add, multiply] # Pass decorated functions
)
# Use with Claude
options = ClaudeAgentOptions(
mcp_servers={"calc": calculator},
allowed_tools=["mcp__calc__add", "mcp__calc__multiply"]
)ClaudeSDKClient在多次交換中維持對話工作階段。 這是 TypeScript SDK 的 query() 函式內部運作方式的 Python 等效實作 - 它建立一個可以繼續對話的客戶端物件。
query() 呼叫之間維持對話上下文@tool 裝飾器建立)和 hooksclass ClaudeSDKClient:
def __init__(self, options: ClaudeAgentOptions | None = None)
async def connect(self, prompt: str | AsyncIterable[dict] | None = None) -> None
async def query(self, prompt: str | AsyncIterable[dict], session_id: str = "default") -> None
async def receive_messages(self) -> AsyncIterator[Message]
async def receive_response(self) -> AsyncIterator[Message]
async def interrupt(self) -> None
async def rewind_files(self, user_message_uuid: str) -> None
async def disconnect(self) -> None| 方法 | 說明 |
|---|---|
__init__(options) | 使用選用配置初始化客戶端 |
connect(prompt) | 使用選用的初始提示或訊息串流連線到 Claude |
query(prompt, session_id) | 在串流模式中發送新請求 |
receive_messages() | 以非同步迭代器接收來自 Claude 的所有訊息 |
receive_response() | 接收訊息直到並包含 ResultMessage |
interrupt() | 發送中斷信號(僅在串流模式中有效) |
rewind_files(user_message_uuid) | 將檔案還原到指定使用者訊息時的狀態。需要 enable_file_checkpointing=True。請參閱檔案檢查點 |
客戶端可以作為非同步上下文管理器使用,以自動管理連線:
async with ClaudeSDKClient() as client:
await client.query("Hello Claude")
async for message in client.receive_response():
print(message)重要: 在迭代訊息時,避免使用
break提前退出,因為這可能導致 asyncio 清理問題。相反,讓迭代自然完成,或使用旗標來追蹤您何時找到所需的內容。
import asyncio
from claude_agent_sdk import ClaudeSDKClient, AssistantMessage, TextBlock, ResultMessage
async def main():
async with ClaudeSDKClient() as client:
# First question
await client.query("What's the capital of France?")
# Process response
async for message in client.receive_response():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(f"Claude: {block.text}")
# Follow-up question - Claude remembers the previous context
await client.query("What's the population of that city?")
async for message in client.receive_response():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(f"Claude: {block.text}")
# Another follow-up - still in the same conversation
await client.query("What are some famous landmarks there?")
async for message in client.receive_response():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(f"Claude: {block.text}")
asyncio.run(main())import asyncio
from claude_agent_sdk import ClaudeSDKClient
async def message_stream():
"""Generate messages dynamically."""
yield {"type": "text", "text": "Analyze the following data:"}
await asyncio.sleep(0.5)
yield {"type": "text", "text": "Temperature: 25°C"}
await asyncio.sleep(0.5)
yield {"type": "text", "text": "Humidity: 60%"}
await asyncio.sleep(0.5)
yield {"type": "text", "text": "What patterns do you see?"}
async def main():
async with ClaudeSDKClient() as client:
# Stream input to Claude
await client.query(message_stream())
# Process response
async for message in client.receive_response():
print(message)
# Follow-up in same session
await client.query("Should we be concerned about these readings?")
async for message in client.receive_response():
print(message)
asyncio.run(main())import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
async def interruptible_task():
options = ClaudeAgentOptions(
allowed_tools=["Bash"],
permission_mode="acceptEdits"
)
async with ClaudeSDKClient(options=options) as client:
# Start a long-running task
await client.query("Count from 1 to 100 slowly")
# Let it run for a bit
await asyncio.sleep(2)
# Interrupt the task
await client.interrupt()
print("Task interrupted!")
# Send a new command
await client.query("Just say hello instead")
async for message in client.receive_response():
# Process the new response
pass
asyncio.run(interruptible_task())from claude_agent_sdk import (
ClaudeSDKClient,
ClaudeAgentOptions
)
from claude_agent_sdk.types import PermissionResultAllow, PermissionResultDeny
async def custom_permission_handler(
tool_name: str,
input_data: dict,
context: dict
) -> PermissionResultAllow | PermissionResultDeny:
"""Custom logic for tool permissions."""
# Block writes to system directories
if tool_name == "Write" and input_data.get("file_path", "").startswith("/system/"):
return PermissionResultDeny(
message="System directory write not allowed",
interrupt=True
)
# Redirect sensitive file operations
if tool_name in ["Write", "Edit"] and "config" in input_data.get("file_path", ""):
safe_path = f"./sandbox/{input_data['file_path']}"
return PermissionResultAllow(
updated_input={**input_data, "file_path": safe_path}
)
# Allow everything else
return PermissionResultAllow(updated_input=input_data)
async def main():
options = ClaudeAgentOptions(
can_use_tool=custom_permission_handler,
allowed_tools=["Read", "Write", "Edit"]
)
async with ClaudeSDKClient(options=options) as client:
await client.query("Update the system config file")
async for message in client.receive_response():
# Will use sandbox path instead
print(message)
asyncio.run(main())SdkMcpTool使用 @tool 裝飾器建立的 SDK MCP 工具定義。
@dataclass
class SdkMcpTool(Generic[T]):
name: str
description: str
input_schema: type[T] | dict[str, Any]
handler: Callable[[T], Awaitable[dict[str, Any]]]| 屬性 | 型別 | 說明 |
|---|---|---|
name | str | 工具的唯一識別碼 |
description | str | 人類可讀的說明 |
input_schema | type[T] | dict[str, Any] | 用於輸入驗證的結構描述 |
handler | Callable[[T], Awaitable[dict[str, Any]]] | 處理工具執行的非同步函式 |
ClaudeAgentOptionsClaude Code 查詢的配置資料類別。
@dataclass
class ClaudeAgentOptions:
tools: list[str] | ToolsPreset | None = None
allowed_tools: list[str] = field(default_factory=list)
system_prompt: str | SystemPromptPreset | None = None
mcp_servers: dict[str, McpServerConfig] | str | Path = field(default_factory=dict)
permission_mode: PermissionMode | None = None
continue_conversation: bool = False
resume: str | None = None
max_turns: int | None = None
max_budget_usd: float | None = None
disallowed_tools: list[str] = field(default_factory=list)
model: str | None = None
fallback_model: str | None = None
betas: list[SdkBeta] = field(default_factory=list)
output_format: OutputFormat | None = None
permission_prompt_tool_name: str | None = None
cwd: str | Path | None = None
cli_path: str | Path | None = None
settings: str | None = None
add_dirs: list[str | Path] = field(default_factory=list)
env: dict[str, str] = field(default_factory=dict)
extra_args: dict[str, str | None] = field(default_factory=dict)
max_buffer_size: int | None = None
debug_stderr: Any = sys.stderr # Deprecated
stderr: Callable[[str], None] | None = None
can_use_tool: CanUseTool | None = None
hooks: dict[HookEvent, list[HookMatcher]] | None = None
user: str | None = None
include_partial_messages: bool = False
fork_session: bool = False
agents: dict[str, AgentDefinition] | None = None
setting_sources: list[SettingSource] | None = None
max_thinking_tokens: int | None = None| 屬性 | 型別 | 預設值 | 說明 |
|---|---|---|---|
tools | list[str] | ToolsPreset | None | None | 工具配置。使用 {"type": "preset", "preset": "claude_code"} 來取得 Claude Code 的預設工具 |
allowed_tools | list[str] | [] | 允許的工具名稱列表 |
system_prompt | str | SystemPromptPreset | None | None | 系統提示配置。傳入字串作為自訂提示,或使用 {"type": "preset", "preset": "claude_code"} 來取得 Claude Code 的系統提示。加入 以擴展預設值 |
OutputFormat結構化輸出驗證的配置。
class OutputFormat(TypedDict):
type: Literal["json_schema"]
schema: dict[str, Any]| 欄位 | 必填 | 說明 |
|---|---|---|
type | 是 | 必須為 "json_schema" 以進行 JSON Schema 驗證 |
schema | 是 | 用於輸出驗證的 JSON Schema 定義 |
SystemPromptPreset使用 Claude Code 預設系統提示並可選擇附加內容的配置。
class SystemPromptPreset(TypedDict):
type: Literal["preset"]
preset: Literal["claude_code"]
append: NotRequired[str]| 欄位 | 必填 | 說明 |
|---|---|---|
type | 是 | 必須為 "preset" 以使用預設系統提示 |
preset | 是 | 必須為 "claude_code" 以使用 Claude Code 的系統提示 |
append | 否 | 附加到預設系統提示的額外指令 |
SettingSource控制 SDK 從哪些檔案系統配置來源載入設定。
SettingSource = Literal["user", "project", "local"]| 值 | 說明 | 位置 |
|---|---|---|
"user" | 全域使用者設定 | ~/.claude/settings.json |
"project" | 共享專案設定(版本控制) | .claude/settings.json |
"local" | 本地專案設定(gitignored) | .claude/settings.local.json |
當 setting_sources 被省略或為 None 時,SDK 不會載入任何檔案系統設定。這為 SDK 應用程式提供了隔離性。
載入所有檔案系統設定(舊版行為):
# Load all settings like SDK v0.0.x did
from claude_agent_sdk import query, ClaudeAgentOptions
async for message in query(
prompt="Analyze this code",
options=ClaudeAgentOptions(
setting_sources=["user", "project", "local"] # Load all settings
)
):
print(message)僅載入特定設定來源:
# Load only project settings, ignore user and local
async for message in query(
prompt="Run CI checks",
options=ClaudeAgentOptions(
setting_sources=["project"] # Only .claude/settings.json
)
):
print(message)測試和 CI 環境:
# Ensure consistent behavior in CI by excluding local settings
async for message in query(
prompt="Run tests",
options=ClaudeAgentOptions(
setting_sources=["project"], # Only team-shared settings
permission_mode="bypassPermissions"
)
):
print(message)僅 SDK 應用程式:
# Define everything programmatically (default behavior)
# No filesystem dependencies - setting_sources defaults to None
async for message in query(
prompt="Review this PR",
options=ClaudeAgentOptions(
# setting_sources=None is the default, no need to specify
agents={ /* ... */ },
mcp_servers={ /* ... */ },
allowed_tools=["Read", "Grep", "Glob"]
)
):
print(message)載入 CLAUDE.md 專案指令:
# Load project settings to include CLAUDE.md files
async for message in query(
prompt="Add a new feature following project conventions",
options=ClaudeAgentOptions(
system_prompt={
"type": "preset",
"preset": "claude_code" # Use Claude Code's system prompt
},
setting_sources=["project"], # Required to load CLAUDE.md from project
allowed_tools=["Read", "Write", "Edit"]
)
):
print(message)當載入多個來源時,設定會按以下優先順序合併(從高到低):
.claude/settings.local.json).claude/settings.json)~/.claude/settings.json)程式化選項(如 agents、allowed_tools)始終覆蓋檔案系統設定。
AgentDefinition以程式方式定義的子代理配置。
@dataclass
class AgentDefinition:
description: str
prompt: str
tools: list[str] | None = None
model: Literal["sonnet", "opus", "haiku", "inherit"] | None = None| 欄位 | 必填 | 說明 |
|---|---|---|
description | 是 | 描述何時使用此代理的自然語言說明 |
tools | 否 | 允許的工具名稱陣列。若省略,則繼承所有工具 |
prompt | 是 | 代理的系統提示 |
model | 否 | 此代理的模型覆蓋。若省略,則使用主模型 |
PermissionMode控制工具執行的權限模式。
PermissionMode = Literal[
"default", # Standard permission behavior
"acceptEdits", # Auto-accept file edits
"plan", # Planning mode - no execution
"bypassPermissions" # Bypass all permission checks (use with caution)
]CanUseTool工具權限回呼函式的型別別名。
CanUseTool = Callable[
[str, dict[str, Any], ToolPermissionContext],
Awaitable[PermissionResult]
]回呼接收:
tool_name:被呼叫的工具名稱input_data:工具的輸入參數context:包含額外資訊的 ToolPermissionContext回傳 PermissionResult(PermissionResultAllow 或 PermissionResultDeny)。
ToolPermissionContext傳遞給工具權限回呼的上下文資訊。
@dataclass
class ToolPermissionContext:
signal: Any | None = None # Future: abort signal support
suggestions: list[PermissionUpdate] = field(default_factory=list)| 欄位 | 型別 | 說明 |
|---|---|---|
signal | Any | None | 保留供未來中止信號支援使用 |
suggestions | list[PermissionUpdate] | 來自 CLI 的權限更新建議 |
PermissionResult權限回呼結果的聯合型別。
PermissionResult = PermissionResultAllow | PermissionResultDenyPermissionResultAllow表示應允許工具呼叫的結果。
@dataclass
class PermissionResultAllow:
behavior: Literal["allow"] = "allow"
updated_input: dict[str, Any] | None = None
updated_permissions: list[PermissionUpdate] | None = None| 欄位 | 型別 | 預設值 | 說明 |
|---|---|---|---|
behavior | Literal["allow"] | "allow" | 必須為 "allow" |
updated_input | dict[str, Any] | None | None | 用於替代原始輸入的修改後輸入 |
updated_permissions | list[PermissionUpdate] | None | None | 要套用的權限更新 |
PermissionResultDeny表示應拒絕工具呼叫的結果。
@dataclass
class PermissionResultDeny:
behavior: Literal["deny"] = "deny"
message: str = ""
interrupt: bool = False| 欄位 | 型別 | 預設值 | 說明 |
|---|---|---|---|
behavior | Literal["deny"] | "deny" | 必須為 "deny" |
message | str | "" | 說明工具被拒絕原因的訊息 |
interrupt | bool | False | 是否中斷目前的執行 |
PermissionUpdate以程式方式更新權限的設定。
@dataclass
class PermissionUpdate:
type: Literal[
"addRules",
"replaceRules",
"removeRules",
"setMode",
"addDirectories",
"removeDirectories",
]
rules: list[PermissionRuleValue] | None = None
behavior: Literal["allow", "deny", "ask"] | None = None
mode: PermissionMode | None = None
directories: list[str] | None = None
destination: Literal["userSettings", "projectSettings", "localSettings", "session"] | None = None| 欄位 | 型別 | 說明 |
|---|---|---|
type | Literal[...] | 權限更新操作的類型 |
rules | list[PermissionRuleValue] | None | 用於新增/替換/移除操作的規則 |
behavior | Literal["allow", "deny", "ask"] | None | 基於規則操作的行為 |
mode | PermissionMode | None | setMode 操作的模式 |
directories | list[str] | None |
SdkBetaSDK 測試版功能的字面值型別。
SdkBeta = Literal["context-1m-2025-08-07"]與 ClaudeAgentOptions 中的 betas 欄位一起使用以啟用測試版功能。
McpSdkServerConfig使用 create_sdk_mcp_server() 建立的 SDK MCP 伺服器設定。
class McpSdkServerConfig(TypedDict):
type: Literal["sdk"]
name: str
instance: Any # MCP Server instanceMcpServerConfigMCP 伺服器設定的聯合型別。
McpServerConfig = McpStdioServerConfig | McpSSEServerConfig | McpHttpServerConfig | McpSdkServerConfigMcpStdioServerConfigclass McpStdioServerConfig(TypedDict):
type: NotRequired[Literal["stdio"]] # Optional for backwards compatibility
command: str
args: NotRequired[list[str]]
env: NotRequired[dict[str, str]]McpSSEServerConfigclass McpSSEServerConfig(TypedDict):
type: Literal["sse"]
url: str
headers: NotRequired[dict[str, str]]McpHttpServerConfigclass McpHttpServerConfig(TypedDict):
type: Literal["http"]
url: str
headers: NotRequired[dict[str, str]]SdkPluginConfig在 SDK 中載入外掛程式的設定。
class SdkPluginConfig(TypedDict):
type: Literal["local"]
path: str| 欄位 | 型別 | 說明 |
|---|---|---|
type | Literal["local"] | 必須為 "local"(目前僅支援本地外掛程式) |
path | str | 外掛程式目錄的絕對或相對路徑 |
範例:
plugins=[
{"type": "local", "path": "./my-plugin"},
{"type": "local", "path": "/absolute/path/to/plugin"}
]有關建立和使用外掛程式的完整資訊,請參閱外掛程式。
Message所有可能訊息的聯合型別。
Message = UserMessage | AssistantMessage | SystemMessage | ResultMessage | StreamEventUserMessage使用者輸入訊息。
@dataclass
class UserMessage:
content: str | list[ContentBlock]AssistantMessage包含內容區塊的助理回應訊息。
@dataclass
class AssistantMessage:
content: list[ContentBlock]
model: strSystemMessage包含中繼資料的系統訊息。
@dataclass
class SystemMessage:
subtype: str
data: dict[str, Any]ResultMessage包含成本和使用量資訊的最終結果訊息。
@dataclass
class ResultMessage:
subtype: str
duration_ms: int
duration_api_ms: int
is_error: bool
num_turns: int
session_id: str
total_cost_usd: float | None = None
usage: dict[str, Any] | None = None
result: str | None = None
structured_output: Any = NoneStreamEvent串流期間部分訊息更新的串流事件。僅在 ClaudeAgentOptions 中設定 include_partial_messages=True 時才會接收。
@dataclass
class StreamEvent:
uuid: str
session_id: str
event: dict[str, Any] # The raw Anthropic API stream event
parent_tool_use_id: str | None = None| 欄位 | 型別 | 說明 |
|---|---|---|
uuid | str | 此事件的唯一識別碼 |
session_id | str | 工作階段識別碼 |
event | dict[str, Any] | 原始 Anthropic API 串流事件資料 |
parent_tool_use_id | str | None | 如果此事件來自子代理,則為父工具使用 ID |
ContentBlock所有內容區塊的聯合型別。
ContentBlock = TextBlock | ThinkingBlock | ToolUseBlock | ToolResultBlockTextBlock文字內容區塊。
@dataclass
class TextBlock:
text: strThinkingBlock思考內容區塊(適用於具有思考能力的模型)。
@dataclass
class ThinkingBlock:
thinking: str
signature: strToolUseBlock工具使用請求區塊。
@dataclass
class ToolUseBlock:
id: str
name: str
input: dict[str, Any]ToolResultBlock工具執行結果區塊。
@dataclass
class ToolResultBlock:
tool_use_id: str
content: str | list[dict[str, Any]] | None = None
is_error: bool | None = NoneClaudeSDKError所有 SDK 錯誤的基礎例外類別。
class ClaudeSDKError(Exception):
"""Base error for Claude SDK."""CLINotFoundError當 Claude Code CLI 未安裝或找不到時引發。
class CLINotFoundError(CLIConnectionError):
def __init__(self, message: str = "Claude Code not found", cli_path: str | None = None):
"""
Args:
message: Error message (default: "Claude Code not found")
cli_path: Optional path to the CLI that was not found
"""CLIConnectionError當連線至 Claude Code 失敗時引發。
class CLIConnectionError(ClaudeSDKError):
"""Failed to connect to Claude Code."""ProcessError當 Claude Code 程序失敗時引發。
class ProcessError(ClaudeSDKError):
def __init__(self, message: str, exit_code: int | None = None, stderr: str | None = None):
self.exit_code = exit_code
self.stderr = stderrCLIJSONDecodeError當 JSON 解析失敗時引發。
class CLIJSONDecodeError(ClaudeSDKError):
def __init__(self, line: str, original_error: Exception):
"""
Args:
line: The line that failed to parse
original_error: The original JSON decode exception
"""
self.line = line
self.original_error = original_error有關使用 Hook 的完整指南,包括範例和常見模式,請參閱 Hook 指南。
HookEvent支援的 Hook 事件型別。請注意,由於設定限制,Python SDK 不支援 SessionStart、SessionEnd 和 Notification Hook。
HookEvent = Literal[
"PreToolUse", # Called before tool execution
"PostToolUse", # Called after tool execution
"UserPromptSubmit", # Called when user submits a prompt
"Stop", # Called when stopping execution
"SubagentStop", # Called when a subagent stops
"PreCompact" # Called before message compaction
]HookCallbackHook 回呼函式的型別定義。
HookCallback = Callable[
[dict[str, Any], str | None, HookContext],
Awaitable[dict[str, Any]]
]參數:
input_data:Hook 特定的輸入資料(請參閱 Hook 指南)tool_use_id:可選的工具使用識別碼(用於工具相關的 Hook)context:包含額外資訊的 Hook 上下文回傳一個可能包含以下內容的字典:
decision:"block" 以阻止該動作systemMessage:要新增到記錄中的系統訊息hookSpecificOutput:Hook 特定的輸出資料HookContext傳遞給 Hook 回呼的上下文資訊。
@dataclass
class HookContext:
signal: Any | None = None # Future: abort signal supportHookMatcher用於將 Hook 匹配到特定事件或工具的設定。
@dataclass
class HookMatcher:
matcher: str | None = None # Tool name or pattern to match (e.g., "Bash", "Write|Edit")
hooks: list[HookCallback] = field(default_factory=list) # List of callbacks to execute
timeout: float | None = None # Timeout in seconds for all hooks in this matcher (default: 60)HookInput所有 Hook 輸入型別的聯合型別。實際型別取決於 hook_event_name 欄位。
HookInput = (
PreToolUseHookInput
| PostToolUseHookInput
| UserPromptSubmitHookInput
| StopHookInput
| SubagentStopHookInput
| PreCompactHookInput
)BaseHookInput所有 Hook 輸入型別中存在的基礎欄位。
class BaseHookInput(TypedDict):
session_id: str
transcript_path: str
cwd: str
permission_mode: NotRequired[str]| 欄位 | 型別 | 說明 |
|---|---|---|
session_id | str | 目前工作階段識別碼 |
transcript_path | str | 工作階段記錄檔案的路徑 |
cwd | str | 目前工作目錄 |
permission_mode | str(可選) | 目前的權限模式 |
PreToolUseHookInputPreToolUse Hook 事件的輸入資料。
class PreToolUseHookInput(BaseHookInput):
hook_event_name: Literal["PreToolUse"]
tool_name: str
tool_input: dict[str, Any]| 欄位 | 型別 | 說明 |
|---|---|---|
hook_event_name | Literal["PreToolUse"] | 始終為 "PreToolUse" |
tool_name | str | 即將執行的工具名稱 |
tool_input | dict[str, Any] | 工具的輸入參數 |
PostToolUseHookInputPostToolUse Hook 事件的輸入資料。
class PostToolUseHookInput(BaseHookInput):
hook_event_name: Literal["PostToolUse"]
tool_name: str
tool_input: dict[str, Any]
tool_response: Any| 欄位 | 型別 | 說明 |
|---|---|---|
hook_event_name | Literal["PostToolUse"] | 始終為 "PostToolUse" |
tool_name | str | 已執行的工具名稱 |
tool_input | dict[str, Any] | 使用的輸入參數 |
tool_response | Any | 工具執行的回應 |
UserPromptSubmitHookInputUserPromptSubmit Hook 事件的輸入資料。
class UserPromptSubmitHookInput(BaseHookInput):
hook_event_name: Literal["UserPromptSubmit"]
prompt: str| 欄位 | 型別 | 說明 |
|---|---|---|
hook_event_name | Literal["UserPromptSubmit"] | 始終為 "UserPromptSubmit" |
prompt | str | 使用者提交的提示 |
StopHookInputStop Hook 事件的輸入資料。
class StopHookInput(BaseHookInput):
hook_event_name: Literal["Stop"]
stop_hook_active: bool| 欄位 | 型別 | 說明 |
|---|---|---|
hook_event_name | Literal["Stop"] | 始終為 "Stop" |
stop_hook_active | bool | 停止 Hook 是否處於活動狀態 |
SubagentStopHookInputSubagentStop Hook 事件的輸入資料。
class SubagentStopHookInput(BaseHookInput):
hook_event_name: Literal["SubagentStop"]
stop_hook_active: bool| 欄位 | 型別 | 說明 |
|---|---|---|
hook_event_name | Literal["SubagentStop"] | 始終為 "SubagentStop" |
stop_hook_active | bool | 停止 Hook 是否處於活動狀態 |
PreCompactHookInputPreCompact Hook 事件的輸入資料。
class PreCompactHookInput(BaseHookInput):
hook_event_name: Literal["PreCompact"]
trigger: Literal["manual", "auto"]
custom_instructions: str | None| 欄位 | 型別 | 說明 |
|---|---|---|
hook_event_name | Literal["PreCompact"] | 始終為 "PreCompact" |
trigger | Literal["manual", "auto"] | 觸發壓縮的原因 |
custom_instructions | str | None | 壓縮的自訂指令 |
HookJSONOutputHook 回呼回傳值的聯合型別。
HookJSONOutput = AsyncHookJSONOutput | SyncHookJSONOutputSyncHookJSONOutput包含控制和決策欄位的同步 Hook 輸出。
class SyncHookJSONOutput(TypedDict):
# Control fields
continue_: NotRequired[bool] # Whether to proceed (default: True)
suppressOutput: NotRequired[bool] # Hide stdout from transcript
stopReason: NotRequired[str] # Message when continue is False
# Decision fields
decision: NotRequired[Literal["block"]]
systemMessage: NotRequired[str] # Warning message for user
reason: NotRequired[str] # Feedback for Claude
# Hook-specific output
hookSpecificOutput: NotRequired[dict[str, Any]]在 Python 程式碼中使用 continue_(帶底線)。傳送至 CLI 時會自動轉換為 continue。
AsyncHookJSONOutput延遲 Hook 執行的非同步 Hook 輸出。
class AsyncHookJSONOutput(TypedDict):
async_: Literal[True] # Set to True to defer execution
asyncTimeout: NotRequired[int] # Timeout in milliseconds在 Python 程式碼中使用 async_(帶底線)。傳送至 CLI 時會自動轉換為 async。
此範例註冊了兩個 Hook:一個阻止危險的 bash 命令(如 rm -rf /),另一個記錄所有工具使用以供稽核。安全 Hook 僅在 Bash 命令上執行(透過 matcher),而記錄 Hook 在所有工具上執行。
from claude_agent_sdk import query, ClaudeAgentOptions, HookMatcher, HookContext
from typing import Any
async def validate_bash_command(
input_data: dict[str, Any],
tool_use_id: str | None,
context: HookContext
) -> dict[str, Any]:
"""Validate and potentially block dangerous bash commands."""
if input_data['tool_name'] == 'Bash':
command = input_data['tool_input'].get('command', '')
if 'rm -rf /' in command:
return {
'hookSpecificOutput': {
'hookEventName': 'PreToolUse',
'permissionDecision': 'deny',
'permissionDecisionReason': 'Dangerous command blocked'
}
}
return {}
async def log_tool_use(
input_data: dict[str, Any],
tool_use_id: str | None,
context: HookContext
) -> dict[str, Any]:
"""Log all tool usage for auditing."""
print(f"Tool used: {input_data.get('tool_name')}")
return {}
options = ClaudeAgentOptions(
hooks={
'PreToolUse': [
HookMatcher(matcher='Bash', hooks=[validate_bash_command], timeout=120), # 2 min for validation
HookMatcher(hooks=[log_tool_use]) # Applies to all tools (default 60s timeout)
],
'PostToolUse': [
HookMatcher(hooks=[log_tool_use])
]
}
)
async for message in query(
prompt="Analyze this codebase",
options=options
):
print(message)所有內建 Claude Code 工具的輸入/輸出結構描述文件。雖然 Python SDK 不會將這些匯出為型別,但它們代表訊息中工具輸入和輸出的結構。
工具名稱: Task
輸入:
{
"description": str, # A short (3-5 word) description of the task
"prompt": str, # The task for the agent to perform
"subagent_type": str # The type of specialized agent to use
}輸出:
{
"result": str, # Final result from the subagent
"usage": dict | None, # Token usage statistics
"total_cost_usd": float | None, # Total cost in USD
"duration_ms": int | None # Execution duration in milliseconds
}工具名稱: AskUserQuestion
在執行期間向使用者詢問澄清問題。有關使用詳情,請參閱處理核准和使用者輸入。
輸入:
{
"questions": [ # Questions to ask the user (1-4 questions)
{
"question": str, # The complete question to ask the user
"header": str, # Very short label displayed as a chip/tag (max 12 chars)
"options": [ # The available choices (2-4 options)
{
"label": str, # Display text for this option (1-5 words)
"description": str # Explanation of what this option means
}
],
"multiSelect": bool # Set to true to allow multiple selections
}
],
"answers": dict | None # User answers populated by the permission system
}輸出:
{
"questions": [ # The questions that were asked
{
"question": str,
"header": str,
"options": [{"label": str, "description": str}],
"multiSelect": bool
}
],
"answers": dict[str, str] # Maps question text to answer string
# Multi-select answers are comma-separated
}工具名稱: Bash
輸入:
{
"command": str, # The command to execute
"timeout": int | None, # Optional timeout in milliseconds (max 600000)
"description": str | None, # Clear, concise description (5-10 words)
"run_in_background": bool | None # Set to true to run in background
}輸出:
{
"output": str, # Combined stdout and stderr output
"exitCode": int, # Exit code of the command
"killed": bool | None, # Whether command was killed due to timeout
"shellId": str | None # Shell ID for background processes
}工具名稱: Edit
輸入:
{
"file_path": str, # The absolute path to the file to modify
"old_string": str, # The text to replace
"new_string": str, # The text to replace it with
"replace_all": bool | None # Replace all occurrences (default False)
}輸出:
{
"message": str, # Confirmation message
"replacements": int, # Number of replacements made
"file_path": str # File path that was edited
}工具名稱: Read
輸入:
{
"file_path": str, # The absolute path to the file to read
"offset": int | None, # The line number to start reading from
"limit": int | None # The number of lines to read
}輸出(文字檔案):
{
"content": str, # File contents with line numbers
"total_lines": int, # Total number of lines in file
"lines_returned": int # Lines actually returned
}輸出(圖片):
{
"image": str, # Base64 encoded image data
"mime_type": str, # Image MIME type
"file_size": int # File size in bytes
}工具名稱: Write
輸入:
{
"file_path": str, # The absolute path to the file to write
"content": str # The content to write to the file
}輸出:
{
"message": str, # Success message
"bytes_written": int, # Number of bytes written
"file_path": str # File path that was written
}工具名稱: Glob
輸入:
{
"pattern": str, # The glob pattern to match files against
"path": str | None # The directory to search in (defaults to cwd)
}輸出:
{
"matches": list[str], # Array of matching file paths
"count": int, # Number of matches found
"search_path": str # Search directory used
}工具名稱: Grep
輸入:
{
"pattern": str, # The regular expression pattern
"path": str | None, # File or directory to search in
"glob": str | None, # Glob pattern to filter files
"type": str | None, # File type to search
"output_mode": str | None, # "content", "files_with_matches", or "count"
"-i": bool | None, # Case insensitive search
"-n": bool | None, # Show line numbers
"-B": int | None, # Lines to show before each match
"-A": int | None, # Lines to show after each match
"-C": int | None, # Lines to show before and after
"head_limit": int | None, # Limit output to first N lines/entries
"multiline": bool | None # Enable multiline mode
}輸出(content 模式):
{
"matches": [
{
"file": str,
"line_number": int | None,
"line": str,
"before_context": list[str] | None,
"after_context": list[str] | None
}
],
"total_matches": int
}輸出(files_with_matches 模式):
{
"files": list[str], # Files containing matches
"count": int # Number of files with matches
}工具名稱: NotebookEdit
輸入:
{
"notebook_path": str, # Absolute path to the Jupyter notebook
"cell_id": str | None, # The ID of the cell to edit
"new_source": str, # The new source for the cell
"cell_type": "code" | "markdown" | None, # The type of the cell
"edit_mode": "replace" | "insert" | "delete" | None # Edit operation type
}輸出:
{
"message": str, # Success message
"edit_type": "replaced" | "inserted" | "deleted", # Type of edit performed
"cell_id": str | None, # Cell ID that was affected
"total_cells": int # Total cells in notebook after edit
}工具名稱: WebFetch
輸入:
{
"url": str, # The URL to fetch content from
"prompt": str # The prompt to run on the fetched content
}輸出:
{
"response": str, # AI model's response to the prompt
"url": str, # URL that was fetched
"final_url": str | None, # Final URL after redirects
"status_code": int | None # HTTP status code
}工具名稱: WebSearch
輸入:
{
"query": str, # The search query to use
"allowed_domains": list[str] | None, # Only include results from these domains
"blocked_domains": list[str] | None # Never include results from these domains
}輸出:
{
"results": [
{
"title": str,
"url": str,
"snippet": str,
"metadata": dict | None
}
],
"total_results": int,
"query": str
}工具名稱: TodoWrite
輸入:
{
"todos": [
{
"content": str, # The task description
"status": "pending" | "in_progress" | "completed", # Task status
"activeForm": str # Active form of the description
}
]
}輸出:
{
"message": str, # Success message
"stats": {
"total": int,
"pending": int,
"in_progress": int,
"completed": int
}
}工具名稱: BashOutput
輸入:
{
"bash_id": str, # The ID of the background shell
"filter": str | None # Optional regex to filter output lines
}輸出:
{
"output": str, # New output since last check
"status": "running" | "completed" | "failed", # Current shell status
"exitCode": int | None # Exit code when completed
}工具名稱: KillBash
輸入:
{
"shell_id": str # The ID of the background shell to kill
}輸出:
{
"message": str, # Success message
"shell_id": str # ID of the killed shell
}工具名稱: ExitPlanMode
輸入:
{
"plan": str # The plan to run by the user for approval
}輸出:
{
"message": str, # Confirmation message
"approved": bool | None # Whether user approved the plan
}工具名稱: ListMcpResources
輸入:
{
"server": str | None # Optional server name to filter resources by
}輸出:
{
"resources": [
{
"uri": str,
"name": str,
"description": str | None,
"mimeType": str | None,
"server": str
}
],
"total": int
}工具名稱: ReadMcpResource
輸入:
{
"server": str, # The MCP server name
"uri": str # The resource URI to read
}輸出:
{
"contents": [
{
"uri": str,
"mimeType": str | None,
"text": str | None,
"blob": str | None
}
],
"server": str
}from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, AssistantMessage, TextBlock
import asyncio
class ConversationSession:
"""Maintains a single conversation session with Claude."""
def __init__(self, options: ClaudeAgentOptions = None):
self.client = ClaudeSDKClient(options)
self.turn_count = 0
async def start(self):
await self.client.connect()
print("Starting conversation session. Claude will remember context.")
print("Commands: 'exit' to quit, 'interrupt' to stop current task, 'new' for new session")
while True:
user_input = input(f"\n[Turn {self.turn_count + 1}] You: ")
if user_input.lower() == 'exit':
break
elif user_input.lower() == 'interrupt':
await self.client.interrupt()
print("Task interrupted!")
continue
elif user_input.lower() == 'new':
# Disconnect and reconnect for a fresh session
await self.client.disconnect()
await self.client.connect()
self.turn_count = 0
print("Started new conversation session (previous context cleared)")
continue
# Send message - Claude remembers all previous messages in this session
await self.client.query(user_input)
self.turn_count += 1
# Process response
print(f"[Turn {self.turn_count}] Claude: ", end="")
async for message in self.client.receive_response():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(block.text, end="")
print() # New line after response
await self.client.disconnect()
print(f"Conversation ended after {self.turn_count} turns.")
async def main():
options = ClaudeAgentOptions(
allowed_tools=["Read", "Write", "Bash"],
permission_mode="acceptEdits"
)
session = ConversationSession(options)
await session.start()
# Example conversation:
# Turn 1 - You: "Create a file called hello.py"
# Turn 1 - Claude: "I'll create a hello.py file for you..."
# Turn 2 - You: "What's in that file?"
# Turn 2 - Claude: "The hello.py file I just created contains..." (remembers!)
# Turn 3 - You: "Add a main function to it"
# Turn 3 - Claude: "I'll add a main function to hello.py..." (knows which file!)
asyncio.run(main())from claude_agent_sdk import (
ClaudeSDKClient,
ClaudeAgentOptions,
HookMatcher,
HookContext
)
import asyncio
from typing import Any
async def pre_tool_logger(
input_data: dict[str, Any],
tool_use_id: str | None,
context: HookContext
) -> dict[str, Any]:
"""Log all tool usage before execution."""
tool_name = input_data.get('tool_name', 'unknown')
print(f"[PRE-TOOL] About to use: {tool_name}")
# You can modify or block the tool execution here
if tool_name == "Bash" and "rm -rf" in str(input_data.get('tool_input', {})):
return {
'hookSpecificOutput': {
'hookEventName': 'PreToolUse',
'permissionDecision': 'deny',
'permissionDecisionReason': 'Dangerous command blocked'
}
}
return {}
async def post_tool_logger(
input_data: dict[str, Any],
tool_use_id: str | None,
context: HookContext
) -> dict[str, Any]:
"""Log results after tool execution."""
tool_name = input_data.get('tool_name', 'unknown')
print(f"[POST-TOOL] Completed: {tool_name}")
return {}
async def user_prompt_modifier(
input_data: dict[str, Any],
tool_use_id: str | None,
context: HookContext
) -> dict[str, Any]:
"""Add context to user prompts."""
original_prompt = input_data.get('prompt', '')
# Add timestamp to all prompts
from datetime import datetime
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
return {
'hookSpecificOutput': {
'hookEventName': 'UserPromptSubmit',
'updatedPrompt': f"[{timestamp}] {original_prompt}"
}
}
async def main():
options = ClaudeAgentOptions(
hooks={
'PreToolUse': [
HookMatcher(hooks=[pre_tool_logger]),
HookMatcher(matcher='Bash', hooks=[pre_tool_logger])
],
'PostToolUse': [
HookMatcher(hooks=[post_tool_logger])
],
'UserPromptSubmit': [
HookMatcher(hooks=[user_prompt_modifier])
]
},
allowed_tools=["Read", "Write", "Bash"]
)
async with ClaudeSDKClient(options=options) as client:
await client.query("List files in current directory")
async for message in client.receive_response():
# Hooks will automatically log tool usage
pass
asyncio.run(main())from claude_agent_sdk import (
ClaudeSDKClient,
ClaudeAgentOptions,
AssistantMessage,
ToolUseBlock,
ToolResultBlock,
TextBlock
)
import asyncio
async def monitor_progress():
options = ClaudeAgentOptions(
allowed_tools=["Write", "Bash"],
permission_mode="acceptEdits"
)
async with ClaudeSDKClient(options=options) as client:
await client.query(
"Create 5 Python files with different sorting algorithms"
)
# Monitor progress in real-time
files_created = []
async for message in client.receive_messages():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, ToolUseBlock):
if block.name == "Write":
file_path = block.input.get("file_path", "")
print(f"🔨 Creating: {file_path}")
elif isinstance(block, ToolResultBlock):
print(f"✅ Completed tool execution")
elif isinstance(block, TextBlock):
print(f"💭 Claude says: {block.text[:100]}...")
# Check if we've received the final result
if hasattr(message, 'subtype') and message.subtype in ['success', 'error']:
print(f"\n🎯 Task completed!")
break
asyncio.run(monitor_progress())from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, ToolUseBlock
import asyncio
async def create_project():
options = ClaudeAgentOptions(
allowed_tools=["Read", "Write", "Bash"],
permission_mode='acceptEdits',
cwd="/home/user/project"
)
async for message in query(
prompt="Create a Python project structure with setup.py",
options=options
):
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, ToolUseBlock):
print(f"Using tool: {block.name}")
asyncio.run(create_project())from claude_agent_sdk import (
query,
CLINotFoundError,
ProcessError,
CLIJSONDecodeError
)
try:
async for message in query(prompt="Hello"):
print(message)
except CLINotFoundError:
print("Please install Claude Code: npm install -g @anthropic-ai/claude-code")
except ProcessError as e:
print(f"Process failed with exit code: {e.exit_code}")
except CLIJSONDecodeError as e:
print(f"Failed to parse response: {e}")from claude_agent_sdk import ClaudeSDKClient
import asyncio
async def interactive_session():
async with ClaudeSDKClient() as client:
# Send initial message
await client.query("What's the weather like?")
# Process responses
async for msg in client.receive_response():
print(msg)
# Send follow-up
await client.query("Tell me more about that")
# Process follow-up response
async for msg in client.receive_response():
print(msg)
asyncio.run(interactive_session())from claude_agent_sdk import (
ClaudeSDKClient,
ClaudeAgentOptions,
tool,
create_sdk_mcp_server,
AssistantMessage,
TextBlock
)
import asyncio
from typing import Any
# Define custom tools with @tool decorator
@tool("calculate", "Perform mathematical calculations", {"expression": str})
async def calculate(args: dict[str, Any]) -> dict[str, Any]:
try:
result = eval(args["expression"], {"__builtins__": {}})
return {
"content": [{
"type": "text",
"text": f"Result: {result}"
}]
}
except Exception as e:
return {
"content": [{
"type": "text",
"text": f"Error: {str(e)}"
}],
"is_error": True
}
@tool("get_time", "Get current time", {})
async def get_time(args: dict[str, Any]) -> dict[str, Any]:
from datetime import datetime
current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
return {
"content": [{
"type": "text",
"text": f"Current time: {current_time}"
}]
}
async def main():
# Create SDK MCP server with custom tools
my_server = create_sdk_mcp_server(
name="utilities",
version="1.0.0",
tools=[calculate, get_time]
)
# Configure options with the server
options = ClaudeAgentOptions(
mcp_servers={"utils": my_server},
allowed_tools=[
"mcp__utils__calculate",
"mcp__utils__get_time"
]
)
# Use ClaudeSDKClient for interactive tool usage
async with ClaudeSDKClient(options=options) as client:
await client.query("What's 123 * 456?")
# Process calculation response
async for message in client.receive_response():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(f"Calculation: {block.text}")
# Follow up with time query
await client.query("What time is it now?")
async for message in client.receive_response():
if isinstance(message, AssistantMessage):
for block in message.content:
if isinstance(block, TextBlock):
print(f"Time: {block.text}")
asyncio.run(main())SandboxSettings沙箱行為的配置。使用此設定以程式化方式啟用命令沙箱並配置網路限制。
class SandboxSettings(TypedDict, total=False):
enabled: bool
autoAllowBashIfSandboxed: bool
excludedCommands: list[str]
allowUnsandboxedCommands: bool
network: SandboxNetworkConfig
ignoreViolations: SandboxIgnoreViolations
enableWeakerNestedSandbox: bool| 屬性 | 類型 | 預設值 | 說明 |
|---|---|---|---|
enabled | bool | False | 啟用命令執行的沙箱模式 |
autoAllowBashIfSandboxed | bool | False | 當沙箱啟用時自動批准 bash 命令 |
excludedCommands | list[str] | [] | 始終繞過沙箱限制的命令(例如 ["docker"])。這些命令會自動在沙箱外執行,無需模型參與 |
allowUnsandboxedCommands |
檔案系統和網路存取限制不是透過沙箱設定來配置的。相反,它們是從權限規則衍生而來:
使用沙箱設定進行命令執行沙箱化,使用權限規則進行檔案系統和網路存取控制。
from claude_agent_sdk import query, ClaudeAgentOptions, SandboxSettings
sandbox_settings: SandboxSettings = {
"enabled": True,
"autoAllowBashIfSandboxed": True,
"network": {
"allowLocalBinding": True
}
}
async for message in query(
prompt="Build and test my project",
options=ClaudeAgentOptions(sandbox=sandbox_settings)
):
print(message)Unix socket 安全性:allowUnixSockets 選項可以授予對強大系統服務的存取權限。例如,允許 /var/run/docker.sock 實際上會透過 Docker API 授予完整的主機系統存取權限,繞過沙箱隔離。僅允許嚴格必要的 Unix socket,並了解每個 socket 的安全影響。
SandboxNetworkConfig沙箱模式的網路特定配置。
class SandboxNetworkConfig(TypedDict, total=False):
allowLocalBinding: bool
allowUnixSockets: list[str]
allowAllUnixSockets: bool
httpProxyPort: int
socksProxyPort: int| 屬性 | 類型 | 預設值 | 說明 |
|---|---|---|---|
allowLocalBinding | bool | False | 允許程序綁定到本地連接埠(例如用於開發伺服器) |
allowUnixSockets | list[str] | [] | 程序可以存取的 Unix socket 路徑(例如 Docker socket) |
allowAllUnixSockets | bool | False | 允許存取所有 Unix socket |
httpProxyPort |
SandboxIgnoreViolations忽略特定沙箱違規的配置。
class SandboxIgnoreViolations(TypedDict, total=False):
file: list[str]
network: list[str]| 屬性 | 類型 | 預設值 | 說明 |
|---|---|---|---|
file | list[str] | [] | 要忽略違規的檔案路徑模式 |
network | list[str] | [] | 要忽略違規的網路模式 |
當啟用 allowUnsandboxedCommands 時,模型可以透過在工具輸入中設定 dangerouslyDisableSandbox: True 來請求在沙箱外執行命令。這些請求會回退到現有的權限系統,這意味著您的 can_use_tool 處理器將被呼叫,允許您實作自訂授權邏輯。
excludedCommands 與 allowUnsandboxedCommands 的區別:
excludedCommands:一個靜態命令列表,始終自動繞過沙箱(例如 ["docker"])。模型無法控制此設定。allowUnsandboxedCommands:讓模型在執行時透過在工具輸入中設定 dangerouslyDisableSandbox: True 來決定是否請求非沙箱執行。from claude_agent_sdk import query, ClaudeAgentOptions
async def can_use_tool(tool: str, input: dict) -> bool:
# Check if the model is requesting to bypass the sandbox
if tool == "Bash" and input.get("dangerouslyDisableSandbox"):
# The model wants to run this command outside the sandbox
print(f"Unsandboxed command requested: {input.get('command')}")
# Return True to allow, False to deny
return is_command_authorized(input.get("command"))
return True
async def main():
async for message in query(
prompt="Deploy my application",
options=ClaudeAgentOptions(
sandbox={
"enabled": True,
"allowUnsandboxedCommands": True # Model can request unsandboxed execution
},
permission_mode="default",
can_use_tool=can_use_tool
)
):
print(message)此模式使您能夠:
使用 dangerouslyDisableSandbox: True 執行的命令具有完整的系統存取權限。請確保您的 can_use_tool 處理器仔細驗證這些請求。
如果 permission_mode 設定為 bypassPermissions 且 allow_unsandboxed_commands 已啟用,模型可以在沒有任何審批提示的情況下自主在沙箱外執行命令。這種組合實際上允許模型靜默地逃脫沙箱隔離。
disconnect() | 與 Claude 斷開連線 |
"append"mcp_servers | dict[str, McpServerConfig] | str | Path | {} | MCP 伺服器配置或配置檔案路徑 |
permission_mode | PermissionMode | None | None | 工具使用的權限模式 |
continue_conversation | bool | False | 繼續最近的對話 |
resume | str | None | None | 要恢復的工作階段 ID |
max_turns | int | None | None | 最大對話回合數 |
max_budget_usd | float | None | None | 工作階段的最大預算(美元) |
disallowed_tools | list[str] | [] | 不允許的工具名稱列表 |
enable_file_checkpointing | bool | False | 啟用檔案變更追蹤以進行回溯。請參閱檔案檢查點 |
model | str | None | None | 要使用的 Claude 模型 |
fallback_model | str | None | None | 當主要模型失敗時使用的備用模型 |
betas | list[SdkBeta] | [] | 要啟用的 Beta 功能。請參閱 SdkBeta 了解可用選項 |
output_format | OutputFormat | None | None | 定義代理結果的輸出格式。請參閱結構化輸出了解詳情 |
permission_prompt_tool_name | str | None | None | 用於權限提示的 MCP 工具名稱 |
cwd | str | Path | None | None | 目前工作目錄 |
cli_path | str | Path | None | None | Claude Code CLI 可執行檔的自訂路徑 |
settings | str | None | None | 設定檔案路徑 |
add_dirs | list[str | Path] | [] | Claude 可以存取的額外目錄 |
env | dict[str, str] | {} | 環境變數 |
extra_args | dict[str, str | None] | {} | 直接傳遞給 CLI 的額外 CLI 引數 |
max_buffer_size | int | None | None | 緩衝 CLI stdout 時的最大位元組數 |
debug_stderr | Any | sys.stderr | 已棄用 - 用於除錯輸出的類檔案物件。請改用 stderr 回呼函式 |
stderr | Callable[[str], None] | None | None | 用於 CLI stderr 輸出的回呼函式 |
can_use_tool | CanUseTool | None | None | 工具權限回呼函式。請參閱權限型別了解詳情 |
hooks | dict[HookEvent, list[HookMatcher]] | None | None | 用於攔截事件的 Hook 配置 |
user | str | None | None | 使用者識別碼 |
include_partial_messages | bool | False | 包含部分訊息串流事件。啟用時,會產生 StreamEvent 訊息 |
fork_session | bool | False | 使用 resume 恢復時,分叉到新的工作階段 ID 而不是繼續原始工作階段 |
agents | dict[str, AgentDefinition] | None | None | 以程式方式定義的子代理 |
plugins | list[SdkPluginConfig] | [] | 從本地路徑載入自訂外掛程式。請參閱外掛程式了解詳情 |
sandbox | SandboxSettings | None | None | 以程式方式配置沙箱行為。請參閱沙箱設定了解詳情 |
setting_sources | list[SettingSource] | None | None(不載入設定) | 控制要載入哪些檔案系統設定。省略時不載入任何設定。注意: 必須包含 "project" 才能載入 CLAUDE.md 檔案 |
max_thinking_tokens | int | None | None | 思考區塊的最大 token 數 |
| 用於新增/移除目錄操作的目錄 |
destination | Literal[...] | None | 權限更新套用的位置 |
bool |
False |
允許模型請求在沙箱外執行命令。當設為 True 時,模型可以在工具輸入中設定 dangerouslyDisableSandbox,這會回退到權限系統 |
network | SandboxNetworkConfig | None | 網路特定的沙箱配置 |
ignoreViolations | SandboxIgnoreViolations | None | 配置要忽略哪些沙箱違規 |
enableWeakerNestedSandbox | bool | False | 啟用較弱的巢狀沙箱以提高相容性 |
int |
None |
| 用於網路請求的 HTTP 代理連接埠 |
socksProxyPort | int | None | 用於網路請求的 SOCKS 代理連接埠 |