Referensi Agent SDK - Python

Referensi API lengkap untuk Python Agent SDK, termasuk semua fungsi, tipe, dan kelas.

Instalasi

pip install claude-agent-sdk

Memilih antara query() dan ClaudeSDKClient

Python SDK menyediakan dua cara untuk berinteraksi dengan Claude Code:

Perbandingan cepat

Kapan menggunakan query() (sesi baru setiap kali)

Terbaik untuk:

• Pertanyaan sekali jalan di mana Anda tidak memerlukan riwayat percakapan
• Tugas independen yang tidak memerlukan konteks dari pertukaran sebelumnya
• Skrip otomasi sederhana
• Ketika Anda menginginkan awal yang segar setiap kali

Kapan menggunakan ClaudeSDKClient (percakapan berkelanjutan)

Terbaik untuk:

• Melanjutkan percakapan - Ketika Anda memerlukan Claude untuk mengingat konteks
• Pertanyaan lanjutan - Membangun berdasarkan respons sebelumnya
• Aplikasi interaktif - Antarmuka obrolan, REPL
• Logika berbasis respons - Ketika tindakan berikutnya bergantung pada respons Claude
• Kontrol sesi - Mengelola siklus hidup percakapan secara eksplisit

Fungsi

query()

Membuat sesi baru untuk setiap interaksi dengan Claude Code. Mengembalikan async iterator yang menghasilkan pesan saat tiba. Setiap panggilan ke query() dimulai segar tanpa memori interaksi sebelumnya.

async def query(
    *,
    prompt: str | AsyncIterable[dict[str, Any]],
    options: ClaudeAgentOptions | None = None,
    transport: Transport | None = None
) -> AsyncIterator[Message]

Parameter

Pengembalian

Mengembalikan AsyncIterator[Message] yang menghasilkan pesan dari percakapan.

Contoh - Dengan opsi

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()

Dekorator untuk mendefinisikan tools MCP dengan keamanan tipe.

def tool(
    name: str,
    description: str,
    input_schema: type | dict[str, Any],
    annotations: ToolAnnotations | None = None
) -> Callable[[Callable[[Any], Awaitable[dict[str, Any]]]], SdkMcpTool[Any]]

Parameter

Opsi skema input

1. Pemetaan tipe sederhana (direkomendasikan):

   {"text": str, "count": int, "enabled": bool}
   

2. Format JSON Schema (untuk validasi kompleks):

   {
       "type": "object",
       "properties": {
           "text": {"type": "string"},
           "count": {"type": "integer", "minimum": 0},
       },
       "required": ["text"],
   }
   

Pengembalian

Fungsi dekorator yang membungkus implementasi tool dan mengembalikan instance SdkMcpTool.

Contoh

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']}!"}]}

ToolAnnotations

Diimpor ulang dari mcp.types (juga tersedia sebagai from claude_agent_sdk import ToolAnnotations). Semua field adalah petunjuk opsional; klien tidak boleh mengandalkannya untuk keputusan keamanan.

from claude_agent_sdk import tool, ToolAnnotations
from typing import Any


@tool(
    "search",
    "Search the web",
    {"query": str},
    annotations=ToolAnnotations(readOnlyHint=True, openWorldHint=True),
)
async def search(args: dict[str, Any]) -> dict[str, Any]:
    return {"content": [{"type": "text", "text": f"Results for: {args['query']}"}]}

create_sdk_mcp_server()

Buat server MCP dalam proses yang berjalan dalam aplikasi Python Anda.

def create_sdk_mcp_server(
    name: str,
    version: str = "1.0.0",
    tools: list[SdkMcpTool[Any]] | None = None
) -> McpSdkServerConfig

Parameter

Pengembalian

Mengembalikan objek McpSdkServerConfig yang dapat diteruskan ke ClaudeAgentOptions.mcp_servers.

Contoh

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"],
)

list_sessions()

Mencantumkan sesi masa lalu dengan metadata. Filter berdasarkan direktori proyek atau cantumkan sesi di semua proyek. Sinkron; mengembalikan segera.

def list_sessions(
    directory: str | None = None,
    limit: int | None = None,
    include_worktrees: bool = True
) -> list[SDKSessionInfo]

Parameter

Tipe pengembalian: SDKSessionInfo

Contoh

Cetak 10 sesi terbaru untuk proyek. Hasil diurutkan berdasarkan last_modified menurun, jadi item pertama adalah yang terbaru. Hilangkan directory untuk mencari di semua proyek.

from claude_agent_sdk import list_sessions

for session in list_sessions(directory="/path/to/project", limit=10):
    print(f"{session.summary} ({session.session_id})")

get_session_messages()

Mengambil pesan dari sesi masa lalu. Sinkron; mengembalikan segera.

def get_session_messages(
    session_id: str,
    directory: str | None = None,
    limit: int | None = None,
    offset: int = 0
) -> list[SessionMessage]

Parameter

Tipe pengembalian: SessionMessage

Contoh

from claude_agent_sdk import list_sessions, get_session_messages

sessions = list_sessions(limit=1)
if sessions:
    messages = get_session_messages(sessions[0].session_id)
    for msg in messages:
        print(f"[{msg.type}] {msg.uuid}")

get_session_info()

Membaca metadata untuk sesi tunggal berdasarkan ID tanpa memindai direktori proyek lengkap. Sinkron; mengembalikan segera.

def get_session_info(
    session_id: str,
    directory: str | None = None,
) -> SDKSessionInfo | None

Parameter

Mengembalikan SDKSessionInfo, atau None jika sesi tidak ditemukan.

Contoh

Cari metadata sesi tunggal tanpa memindai direktori proyek. Berguna ketika Anda sudah memiliki ID sesi dari run sebelumnya.

from claude_agent_sdk import get_session_info

info = get_session_info("550e8400-e29b-41d4-a716-446655440000")
if info:
    print(f"{info.summary} (branch: {info.git_branch}, tag: {info.tag})")

rename_session()

Mengganti nama sesi dengan menambahkan entri judul kustom. Panggilan berulang aman; judul terbaru menang. Sinkron.

def rename_session(
    session_id: str,
    title: str,
    directory: str | None = None,
) -> None

Parameter

Menimbulkan ValueError jika session_id bukan UUID yang valid atau title kosong; FileNotFoundError jika sesi tidak dapat ditemukan.

Contoh

Ganti nama sesi terbaru sehingga lebih mudah ditemukan nanti. Judul baru muncul di SDKSessionInfo.custom_title pada pembacaan berikutnya.

from claude_agent_sdk import list_sessions, rename_session

sessions = list_sessions(directory="/path/to/project", limit=1)
if sessions:
    rename_session(sessions[0].session_id, "Refactor auth module")

tag_session()

Menandai sesi. Teruskan None untuk menghapus tag. Panggilan berulang aman; tag terbaru menang. Sinkron.

def tag_session(
    session_id: str,
    tag: str | None,
    directory: str | None = None,
) -> None

Parameter

Menimbulkan ValueError jika session_id bukan UUID yang valid atau tag kosong setelah sanitasi; FileNotFoundError jika sesi tidak dapat ditemukan.

Contoh

Tandai sesi, kemudian filter berdasarkan tag itu pada pembacaan nanti. Teruskan None untuk menghapus tag yang ada.

from claude_agent_sdk import list_sessions, tag_session

# Tag a session
tag_session("550e8400-e29b-41d4-a716-446655440000", "needs-review")

# Later: find all sessions with that tag
for session in list_sessions(directory="/path/to/project"):
    if session.tag == "needs-review":
        print(session.summary)

Kelas

ClaudeSDKClient

Mempertahankan sesi percakapan di beberapa pertukaran. Ini adalah setara Python dari cara fungsi query() SDK TypeScript bekerja secara internal - ia membuat objek klien yang dapat melanjutkan percakapan.

Fitur Utama

• Kontinuitas sesi: Mempertahankan konteks percakapan di beberapa panggilan query()
• Percakapan yang sama: Sesi mempertahankan pesan sebelumnya
• Dukungan interrupt: Dapat menghentikan eksekusi di tengah-tengah tugas
• Siklus hidup eksplisit: Anda mengontrol kapan sesi dimulai dan berakhir
• Alur berbasis respons: Dapat bereaksi terhadap respons dan mengirim tindak lanjut
• Tools dan hooks kustom: Mendukung tools kustom (dibuat dengan dekorator @tool) dan hooks

class ClaudeSDKClient:
    def __init__(self, options: ClaudeAgentOptions | None = None, transport: Transport | 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 set_permission_mode(self, mode: str) -> None
    async def set_model(self, model: str | None = None) -> None
    async def rewind_files(self, user_message_id: str) -> None
    async def get_mcp_status(self) -> McpStatusResponse
    async def reconnect_mcp_server(self, server_name: str) -> None
    async def toggle_mcp_server(self, server_name: str, enabled: bool) -> None
    async def stop_task(self, task_id: str) -> None
    async def get_server_info(self) -> dict[str, Any] | None
    async def disconnect(self) -> None

Metode

Dukungan Context Manager

Klien dapat digunakan sebagai async context manager untuk manajemen koneksi otomatis:

async with ClaudeSDKClient() as client:
    await client.query("Hello Claude")
    async for message in client.receive_response():
        print(message)

Penting: Saat mengulangi pesan, hindari menggunakan break untuk keluar lebih awal karena ini dapat menyebabkan masalah pembersihan asyncio. Sebaliknya, biarkan iterasi selesai secara alami atau gunakan flag untuk melacak kapan Anda menemukan apa yang Anda butuhkan.

Contoh - Melanjutkan percakapan

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 - the session retains 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())

Contoh - Streaming input dengan ClaudeSDKClient

import asyncio
from claude_agent_sdk import ClaudeSDKClient


async def message_stream():
    """Generate messages dynamically."""
    yield {
        "type": "user",
        "message": {"role": "user", "content": "Analyze the following data:"},
    }
    await asyncio.sleep(0.5)
    yield {
        "type": "user",
        "message": {"role": "user", "content": "Temperature: 25°C, Humidity: 60%"},
    }
    await asyncio.sleep(0.5)
    yield {
        "type": "user",
        "message": {"role": "user", "content": "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())

Contoh - Menggunakan interrupts

import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, ResultMessage


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, using the bash sleep command")

        # Let it run for a bit
        await asyncio.sleep(2)

        # Interrupt the task
        await client.interrupt()
        print("Task interrupted!")

        # Drain the interrupted task's messages (including its ResultMessage)
        async for message in client.receive_response():
            if isinstance(message, ResultMessage):
                print(f"Interrupted task finished with subtype={message.subtype!r}")
                # subtype is "error_during_execution" for interrupted tasks

        # Send a new command
        await client.query("Just say hello instead")

        # Now receive the new response
        async for message in client.receive_response():
            if isinstance(message, ResultMessage) and message.subtype == "success":
                print(f"New result: {message.result}")


asyncio.run(interruptible_task())

Contoh - Kontrol izin lanjutan

from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
from claude_agent_sdk.types import (
    PermissionResultAllow,
    PermissionResultDeny,
    ToolPermissionContext,
)


async def custom_permission_handler(
    tool_name: str, input_data: dict, context: ToolPermissionContext
) -> 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())

Tipe

SdkMcpTool

Definisi untuk tool SDK MCP yang dibuat dengan dekorator @tool.

@dataclass
class SdkMcpTool(Generic[T]):
    name: str
    description: str
    input_schema: type[T] | dict[str, Any]
    handler: Callable[[T], Awaitable[dict[str, Any]]]
    annotations: ToolAnnotations | None = None

Transport

Kelas dasar abstrak untuk implementasi transport kustom. Gunakan ini untuk berkomunikasi dengan proses Claude melalui saluran kustom (misalnya, koneksi jarak jauh alih-alih subprocess lokal).

from abc import ABC, abstractmethod
from collections.abc import AsyncIterator
from typing import Any


class Transport(ABC):
    @abstractmethod
    async def connect(self) -> None: ...

    @abstractmethod
    async def write(self, data: str) -> None: ...

    @abstractmethod
    def read_messages(self) -> AsyncIterator[dict[str, Any]]: ...

    @abstractmethod
    async def close(self) -> None: ...

    @abstractmethod
    def is_ready(self) -> bool: ...

    @abstractmethod
    async def end_input(self) -> None: ...

Impor: from claude_agent_sdk import Transport

ClaudeAgentOptions

Dataclass konfigurasi untuk query Claude Code.

@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: dict[str, Any] | 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
    sandbox: SandboxSettings | None = None
    plugins: list[SdkPluginConfig] = field(default_factory=list)
    max_thinking_tokens: int | None = None  # Deprecated: use thinking instead
    thinking: ThinkingConfig | None = None
    effort: Literal["low", "medium", "high", "max"] | None = None
    enable_file_checkpointing: bool = False
    session_store: SessionStore | None = None
    session_store_flush: SessionStoreFlushMode = "batched"

OutputFormat

Konfigurasi untuk validasi output terstruktur. Teruskan ini sebagai dict ke field output_format pada ClaudeAgentOptions:

# Expected dict shape for output_format
{
    "type": "json_schema",
    "schema": {...},  # Your JSON Schema definition
}

SystemPromptPreset

Konfigurasi untuk menggunakan preset system prompt Claude Code dengan penambahan opsional.

class SystemPromptPreset(TypedDict):
    type: Literal["preset"]
    preset: Literal["claude_code"]
    append: NotRequired[str]
    exclude_dynamic_sections: NotRequired[bool]

SettingSource

Mengontrol sumber konfigurasi berbasis filesystem mana yang dimuat pengaturan SDK.

SettingSource = Literal["user", "project", "local"]

Perilaku default

Ketika setting_sources dihilangkan atau None, query() memuat pengaturan filesystem yang sama seperti CLI Claude Code: pengguna, proyek, dan lokal. Pengaturan kebijakan terkelola dimuat dalam semua kasus. Lihat What settingSources does not control untuk input yang dibaca terlepas dari opsi ini, dan cara menonaktifkannya.

Mengapa menggunakan setting_sources

Nonaktifkan pengaturan filesystem:

# Do not load user, project, or local settings from disk
from claude_agent_sdk import query, ClaudeAgentOptions

async for message in query(
    prompt="Analyze this code",
    options=ClaudeAgentOptions(
        setting_sources=[]
    ),
):
    print(message)

Muat semua pengaturan filesystem secara eksplisit:

from claude_agent_sdk import query, ClaudeAgentOptions

async for message in query(
    prompt="Analyze this code",
    options=ClaudeAgentOptions(
        setting_sources=["user", "project", "local"]
    ),
):
    print(message)

Muat hanya sumber pengaturan tertentu:

# 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)

Lingkungan testing dan CI:

# 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)

Aplikasi SDK-only:

# Define everything programmatically.
# Pass [] to opt out of filesystem setting sources.
async for message in query(
    prompt="Review this PR",
    options=ClaudeAgentOptions(
        setting_sources=[],
        agents={...},
        mcp_servers={...},
        allowed_tools=["Read", "Grep", "Glob"],
    ),
):
    print(message)

Memuat instruksi proyek CLAUDE.md:

# 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"],  # Loads CLAUDE.md from project
        allowed_tools=["Read", "Write", "Edit"],
    ),
):
    print(message)

Preseden pengaturan

Ketika beberapa sumber dimuat, pengaturan digabungkan dengan preseden ini (tertinggi ke terendah):

1. Pengaturan lokal (.claude/settings.local.json)
2. Pengaturan proyek (.claude/settings.json)
3. Pengaturan pengguna (~/.claude/settings.json)

Opsi programatis seperti agents dan allowed_tools mengganti pengaturan filesystem pengguna, proyek, dan lokal. Pengaturan kebijakan terkelola mengambil prioritas atas opsi programatis.

AgentDefinition

Konfigurasi untuk subagent yang didefinisikan secara programatis.

@dataclass
class AgentDefinition:
    description: str
    prompt: str
    tools: list[str] | None = None
    disallowedTools: list[str] | None = None
    model: str | None = None
    skills: list[str] | None = None
    memory: Literal["user", "project", "local"] | None = None
    mcpServers: list[str | dict[str, Any]] | None = None
    initialPrompt: str | None = None
    maxTurns: int | None = None
    background: bool | None = None
    effort: Literal["low", "medium", "high", "max"] | int | None = None
    permissionMode: PermissionMode | None = None

PermissionMode

Mode izin untuk mengontrol eksekusi tool.

PermissionMode = Literal[
    "default",  # Standard permission behavior
    "acceptEdits",  # Auto-accept file edits
    "plan",  # Planning mode - read-only tools only
    "dontAsk",  # Deny anything not pre-approved instead of prompting
    "bypassPermissions",  # Bypass all permission checks (use with caution)
]

CanUseTool

Type alias untuk fungsi callback izin tool.

CanUseTool = Callable[
    [str, dict[str, Any], ToolPermissionContext], Awaitable[PermissionResult]
]

Callback menerima:

• tool_name: Nama tool yang sedang dipanggil
• input_data: Parameter input tool
• context: ToolPermissionContext dengan informasi tambahan

Mengembalikan PermissionResult (baik PermissionResultAllow atau PermissionResultDeny).

ToolPermissionContext

Informasi konteks yang diteruskan ke callback izin tool.

@dataclass
class ToolPermissionContext:
    signal: Any | None = None  # Future: abort signal support
    suggestions: list[PermissionUpdate] = field(default_factory=list)

PermissionResult

Tipe union untuk hasil callback izin.

PermissionResult = PermissionResultAllow | PermissionResultDeny

PermissionResultAllow

Hasil yang menunjukkan panggilan tool harus diizinkan.

@dataclass
class PermissionResultAllow:
    behavior: Literal["allow"] = "allow"
    updated_input: dict[str, Any] | None = None
    updated_permissions: list[PermissionUpdate] | None = None

PermissionResultDeny

Hasil yang menunjukkan panggilan tool harus ditolak.

@dataclass
class PermissionResultDeny:
    behavior: Literal["deny"] = "deny"
    message: str = ""
    interrupt: bool = False

PermissionUpdate

Konfigurasi untuk memperbarui izin secara programatis.

@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

PermissionRuleValue

Aturan untuk ditambahkan, diganti, atau dihapus dalam pembaruan izin.

@dataclass
class PermissionRuleValue:
    tool_name: str
    rule_content: str | None = None

ToolsPreset

Konfigurasi preset tools untuk menggunakan set tool default Claude Code.

class ToolsPreset(TypedDict):
    type: Literal["preset"]
    preset: Literal["claude_code"]

ThinkingConfig

Mengontrol perilaku extended thinking. Union dari tiga konfigurasi:

class ThinkingConfigAdaptive(TypedDict):
    type: Literal["adaptive"]


class ThinkingConfigEnabled(TypedDict):
    type: Literal["enabled"]
    budget_tokens: int


class ThinkingConfigDisabled(TypedDict):
    type: Literal["disabled"]


ThinkingConfig = ThinkingConfigAdaptive | ThinkingConfigEnabled | ThinkingConfigDisabled

Karena ini adalah kelas TypedDict, mereka adalah dict biasa saat runtime. Baik buatlah sebagai dict literal atau panggil kelas seperti konstruktor; keduanya menghasilkan dict. Akses field dengan config["budget_tokens"], bukan config.budget_tokens:

from claude_agent_sdk import ClaudeAgentOptions, ThinkingConfigEnabled

# Option 1: dict literal (recommended, no import needed)
options = ClaudeAgentOptions(thinking={"type": "enabled", "budget_tokens": 20000})

# Option 2: constructor-style (returns a plain dict)
config = ThinkingConfigEnabled(type="enabled", budget_tokens=20000)
print(config["budget_tokens"])  # 20000
# config.budget_tokens would raise AttributeError

SdkBeta

Tipe literal untuk fitur beta SDK.

SdkBeta = Literal["context-1m-2025-08-07"]

Gunakan dengan field betas dalam ClaudeAgentOptions untuk mengaktifkan fitur beta.

McpSdkServerConfig

Konfigurasi untuk server MCP SDK yang dibuat dengan create_sdk_mcp_server().

class McpSdkServerConfig(TypedDict):
    type: Literal["sdk"]
    name: str
    instance: Any  # MCP Server instance

McpServerConfig

Tipe union untuk konfigurasi server MCP.

McpServerConfig = (
    McpStdioServerConfig | McpSSEServerConfig | McpHttpServerConfig | McpSdkServerConfig
)

McpStdioServerConfig

class McpStdioServerConfig(TypedDict):
    type: NotRequired[Literal["stdio"]]  # Optional for backwards compatibility
    command: str
    args: NotRequired[list[str]]
    env: NotRequired[dict[str, str]]

McpSSEServerConfig

class McpSSEServerConfig(TypedDict):
    type: Literal["sse"]
    url: str
    headers: NotRequired[dict[str, str]]

McpHttpServerConfig

class McpHttpServerConfig(TypedDict):
    type: Literal["http"]
    url: str
    headers: NotRequired[dict[str, str]]

McpServerStatusConfig

Konfigurasi server MCP seperti yang dilaporkan oleh get_mcp_status(). Ini adalah union dari semua varian transport McpServerConfig ditambah varian output-only claudeai-proxy untuk server yang di-proxy melalui claude.ai.

McpServerStatusConfig = (
    McpStdioServerConfig
    | McpSSEServerConfig
    | McpHttpServerConfig
    | McpSdkServerConfigStatus
    | McpClaudeAIProxyServerConfig
)

McpSdkServerConfigStatus adalah bentuk yang dapat diserialisasi dari McpSdkServerConfig dengan hanya field type ("sdk") dan name (str); instance dalam proses dihilangkan. McpClaudeAIProxyServerConfig memiliki field type ("claudeai-proxy"), url (str), dan id (str).

McpStatusResponse

Respons dari ClaudeSDKClient.get_mcp_status(). Membungkus daftar status server di bawah kunci mcpServers.

class McpStatusResponse(TypedDict):
    mcpServers: list[McpServerStatus]

McpServerStatus

Status server MCP yang terhubung, terdapat dalam McpStatusResponse.

class McpServerStatus(TypedDict):
    name: str
    status: McpServerConnectionStatus  # "connected" | "failed" | "needs-auth" | "pending" | "disabled"
    serverInfo: NotRequired[McpServerInfo]
    error: NotRequired[str]
    config: NotRequired[McpServerStatusConfig]
    scope: NotRequired[str]
    tools: NotRequired[list[McpToolInfo]]

SdkPluginConfig

Konfigurasi untuk memuat plugins dalam SDK.

class SdkPluginConfig(TypedDict):
    type: Literal["local"]
    path: str

Contoh:

plugins = [
    {"type": "local", "path": "./my-plugin"},
    {"type": "local", "path": "/absolute/path/to/plugin"},
]

Untuk informasi lengkap tentang membuat dan menggunakan plugins, lihat Plugins.

Tipe Pesan

Message

Tipe union dari semua pesan yang mungkin.

Message = (
    UserMessage
    | AssistantMessage
    | SystemMessage
    | ResultMessage
    | StreamEvent
    | RateLimitEvent
)

UserMessage

Pesan input pengguna.

@dataclass
class UserMessage:
    content: str | list[ContentBlock]
    uuid: str | None = None
    parent_tool_use_id: str | None = None
    tool_use_result: dict[str, Any] | None = None

AssistantMessage

Pesan respons asisten dengan blok konten.

@dataclass
class AssistantMessage:
    content: list[ContentBlock]
    model: str
    parent_tool_use_id: str | None = None
    error: AssistantMessageError | None = None
    usage: dict[str, Any] | None = None
    message_id: str | None = None

AssistantMessageError

Tipe error yang mungkin untuk pesan asisten.

AssistantMessageError = Literal[
    "authentication_failed",
    "billing_error",
    "rate_limit",
    "invalid_request",
    "server_error",
    "max_output_tokens",
    "unknown",
]

SystemMessage

Pesan sistem dengan metadata.

@dataclass
class SystemMessage:
    subtype: str
    data: dict[str, Any]

ResultMessage

Pesan hasil akhir dengan informasi biaya dan penggunaan.

@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
    stop_reason: str | None = None
    structured_output: Any = None
    model_usage: dict[str, Any] | None = None

Dict usage berisi kunci berikut ketika ada:

Dict model_usage memetakan nama model ke penggunaan per-model. Kunci dict dalam menggunakan camelCase karena nilai diteruskan tanpa modifikasi dari proses CLI yang mendasar, cocok dengan tipe ModelUsage TypeScript:

StreamEvent

Event stream untuk pembaruan pesan parsial selama streaming. Hanya diterima ketika include_partial_messages=True dalam ClaudeAgentOptions. Impor via from claude_agent_sdk.types import StreamEvent.

@dataclass
class StreamEvent:
    uuid: str
    session_id: str
    event: dict[str, Any]  # The raw Claude API stream event
    parent_tool_use_id: str | None = None

RateLimitEvent

Dipancarkan ketika status rate limit berubah (misalnya, dari "allowed" ke "allowed_warning"). Gunakan ini untuk memperingatkan pengguna sebelum mereka mencapai batas keras, atau untuk mundur ketika status adalah "rejected".

@dataclass
class RateLimitEvent:
    rate_limit_info: RateLimitInfo
    uuid: str
    session_id: str

RateLimitInfo

Status rate limit yang dibawa oleh RateLimitEvent.

RateLimitStatus = Literal["allowed", "allowed_warning", "rejected"]
RateLimitType = Literal[
    "five_hour", "seven_day", "seven_day_opus", "seven_day_sonnet", "overage"
]


@dataclass
class RateLimitInfo:
    status: RateLimitStatus
    resets_at: int | None = None
    rate_limit_type: RateLimitType | None = None
    utilization: float | None = None
    overage_status: RateLimitStatus | None = None
    overage_resets_at: int | None = None
    overage_disabled_reason: str | None = None
    raw: dict[str, Any] = field(default_factory=dict)

TaskStartedMessage

Dipancarkan ketika tugas latar belakang dimulai. Tugas latar belakang adalah apa pun yang dilacak di luar putaran utama: perintah Bash yang di-background, Monitor watch, subagent yang dihasilkan melalui tool Agent, atau agent jarak jauh. Field task_type memberi tahu Anda yang mana. Penamaan ini tidak terkait dengan penggantian nama tool Task-ke-Agent.

@dataclass
class TaskStartedMessage(SystemMessage):
    task_id: str
    description: str
    uuid: str
    session_id: str
    tool_use_id: str | None = None
    task_type: str | None = None

TaskUsage

Data token dan timing untuk tugas latar belakang.

class TaskUsage(TypedDict):
    total_tokens: int
    tool_uses: int
    duration_ms: int

TaskProgressMessage

Dipancarkan secara berkala dengan pembaruan kemajuan untuk tugas latar belakang yang sedang berjalan.

@dataclass
class TaskProgressMessage(SystemMessage):
    task_id: str
    description: str
    usage: TaskUsage
    uuid: str
    session_id: str
    tool_use_id: str | None = None
    last_tool_name: str | None = None

TaskNotificationMessage

Dipancarkan ketika tugas latar belakang selesai, gagal, atau dihentikan. Tugas latar belakang termasuk perintah Bash run_in_background, Monitor watches, dan subagent latar belakang.

@dataclass
class TaskNotificationMessage(SystemMessage):
    task_id: str
    status: TaskNotificationStatus  # "completed" | "failed" | "stopped"
    output_file: str
    summary: str
    uuid: str
    session_id: str
    tool_use_id: str | None = None
    usage: TaskUsage | None = None

Tipe Blok Konten

ContentBlock

Tipe union dari semua blok konten.

ContentBlock = TextBlock | ThinkingBlock | ToolUseBlock | ToolResultBlock

TextBlock

Blok konten teks.

@dataclass
class TextBlock:
    text: str

ThinkingBlock

Blok konten thinking (untuk model dengan kemampuan thinking).

@dataclass
class ThinkingBlock:
    thinking: str
    signature: str

ToolUseBlock

Blok permintaan penggunaan tool.

@dataclass
class ToolUseBlock:
    id: str
    name: str
    input: dict[str, Any]

ToolResultBlock

Blok hasil eksekusi tool.

@dataclass
class ToolResultBlock:
    tool_use_id: str
    content: str | list[dict[str, Any]] | None = None
    is_error: bool | None = None

Tipe Error

ClaudeSDKError

Kelas exception dasar untuk semua error SDK.

class ClaudeSDKError(Exception):
    """Base error for Claude SDK."""

CLINotFoundError

Diangkat ketika Claude Code CLI tidak diinstal atau tidak ditemukan.

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

Diangkat ketika koneksi ke Claude Code gagal.

class CLIConnectionError(ClaudeSDKError):
    """Failed to connect to Claude Code."""

ProcessError

Diangkat ketika proses Claude Code gagal.

class ProcessError(ClaudeSDKError):
    def __init__(
        self, message: str, exit_code: int | None = None, stderr: str | None = None
    ):
        self.exit_code = exit_code
        self.stderr = stderr

CLIJSONDecodeError

Diangkat ketika parsing JSON gagal.

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

Tipe Hook

Untuk panduan komprehensif tentang menggunakan hooks dengan contoh dan pola umum, lihat Hooks guide.

HookEvent

Tipe event hook yang didukung.

HookEvent = Literal[
    "PreToolUse",  # Called before tool execution
    "PostToolUse",  # Called after tool execution
    "PostToolUseFailure",  # Called when a tool execution fails
    "UserPromptSubmit",  # Called when user submits a prompt
    "Stop",  # Called when stopping execution
    "SubagentStop",  # Called when a subagent stops
    "PreCompact",  # Called before message compaction
    "Notification",  # Called for notification events
    "SubagentStart",  # Called when a subagent starts
    "PermissionRequest",  # Called when a permission decision is needed
]

HookCallback

Definisi tipe untuk fungsi callback hook.

HookCallback = Callable[[HookInput, str | None, HookContext], Awaitable[HookJSONOutput]]

Parameter:

• input: Input hook yang kuat dengan union yang dibedakan berdasarkan hook_event_name (lihat HookInput)
• tool_use_id: Pengenal penggunaan tool opsional (untuk hook terkait tool)
• context: Konteks hook dengan informasi tambahan

Mengembalikan HookJSONOutput yang mungkin berisi:

• decision: "block" untuk memblokir tindakan
• systemMessage: Pesan sistem untuk ditambahkan ke transkrip
• hookSpecificOutput: Data output spesifik hook

HookContext

Informasi konteks yang diteruskan ke callback hook.

class HookContext(TypedDict):
    signal: Any | None  # Future: abort signal support

HookMatcher

Konfigurasi untuk mencocokkan hooks ke event atau tools tertentu.

@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

Tipe union dari semua tipe input hook. Tipe aktual bergantung pada field hook_event_name.

HookInput = (
    PreToolUseHookInput
    | PostToolUseHookInput
    | PostToolUseFailureHookInput
    | UserPromptSubmitHookInput
    | StopHookInput
    | SubagentStopHookInput
    | PreCompactHookInput
    | NotificationHookInput
    | SubagentStartHookInput
    | PermissionRequestHookInput
)

BaseHookInput

Field dasar yang ada di semua tipe input hook.

class BaseHookInput(TypedDict):
    session_id: str
    transcript_path: str
    cwd: str
    permission_mode: NotRequired[str]

PreToolUseHookInput

Data input untuk event hook PreToolUse.

class PreToolUseHookInput(BaseHookInput):
    hook_event_name: Literal["PreToolUse"]
    tool_name: str
    tool_input: dict[str, Any]
    tool_use_id: str
    agent_id: NotRequired[str]
    agent_type: NotRequired[str]

PostToolUseHookInput

Data input untuk event hook PostToolUse.

class PostToolUseHookInput(BaseHookInput):
    hook_event_name: Literal["PostToolUse"]
    tool_name: str
    tool_input: dict[str, Any]
    tool_response: Any
    tool_use_id: str
    agent_id: NotRequired[str]
    agent_type: NotRequired[str]

PostToolUseFailureHookInput

Data input untuk event hook PostToolUseFailure. Dipanggil ketika eksekusi tool gagal.

class PostToolUseFailureHookInput(BaseHookInput):
    hook_event_name: Literal["PostToolUseFailure"]
    tool_name: str
    tool_input: dict[str, Any]
    tool_use_id: str
    error: str
    is_interrupt: NotRequired[bool]
    agent_id: NotRequired[str]
    agent_type: NotRequired[str]

UserPromptSubmitHookInput

Data input untuk event hook UserPromptSubmit.

class UserPromptSubmitHookInput(BaseHookInput):
    hook_event_name: Literal["UserPromptSubmit"]
    prompt: str

StopHookInput

Data input untuk event hook Stop.

class StopHookInput(BaseHookInput):
    hook_event_name: Literal["Stop"]
    stop_hook_active: bool

SubagentStopHookInput

Data input untuk event hook SubagentStop.

class SubagentStopHookInput(BaseHookInput):
    hook_event_name: Literal["SubagentStop"]
    stop_hook_active: bool
    agent_id: str
    agent_transcript_path: str
    agent_type: str

PreCompactHookInput

Data input untuk event hook PreCompact.

class PreCompactHookInput(BaseHookInput):
    hook_event_name: Literal["PreCompact"]
    trigger: Literal["manual", "auto"]
    custom_instructions: str | None

NotificationHookInput

Data input untuk event hook Notification.

class NotificationHookInput(BaseHookInput):
    hook_event_name: Literal["Notification"]
    message: str
    title: NotRequired[str]
    notification_type: str

SubagentStartHookInput

Data input untuk event hook SubagentStart.

class SubagentStartHookInput(BaseHookInput):
    hook_event_name: Literal["SubagentStart"]
    agent_id: str
    agent_type: str

PermissionRequestHookInput

Data input untuk event hook PermissionRequest. Memungkinkan hooks untuk menangani keputusan izin secara programatis.

class PermissionRequestHookInput(BaseHookInput):
    hook_event_name: Literal["PermissionRequest"]
    tool_name: str
    tool_input: dict[str, Any]
    permission_suggestions: NotRequired[list[Any]]

HookJSONOutput

Tipe union untuk nilai pengembalian callback hook.

HookJSONOutput = AsyncHookJSONOutput | SyncHookJSONOutput

SyncHookJSONOutput

Output hook sinkron dengan field kontrol dan keputusan.

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[HookSpecificOutput]

HookSpecificOutput

TypedDict yang berisi nama event hook dan field spesifik event. Bentuknya bergantung pada nilai hookEventName. Untuk detail lengkap tentang field yang tersedia per event hook, lihat Control execution with hooks.

Union yang dibedakan dari tipe output spesifik event. Field hookEventName menentukan field mana yang valid.

class PreToolUseHookSpecificOutput(TypedDict):
    hookEventName: Literal["PreToolUse"]
    permissionDecision: NotRequired[Literal["allow", "deny", "ask"]]
    permissionDecisionReason: NotRequired[str]
    updatedInput: NotRequired[dict[str, Any]]
    additionalContext: NotRequired[str]


class PostToolUseHookSpecificOutput(TypedDict):
    hookEventName: Literal["PostToolUse"]
    additionalContext: NotRequired[str]
    updatedMCPToolOutput: NotRequired[Any]


class PostToolUseFailureHookSpecificOutput(TypedDict):
    hookEventName: Literal["PostToolUseFailure"]
    additionalContext: NotRequired[str]


class UserPromptSubmitHookSpecificOutput(TypedDict):
    hookEventName: Literal["UserPromptSubmit"]
    additionalContext: NotRequired[str]


class NotificationHookSpecificOutput(TypedDict):
    hookEventName: Literal["Notification"]
    additionalContext: NotRequired[str]


class SubagentStartHookSpecificOutput(TypedDict):
    hookEventName: Literal["SubagentStart"]
    additionalContext: NotRequired[str]


class PermissionRequestHookSpecificOutput(TypedDict):
    hookEventName: Literal["PermissionRequest"]
    decision: dict[str, Any]


HookSpecificOutput = (
    PreToolUseHookSpecificOutput
    | PostToolUseHookSpecificOutput
    | PostToolUseFailureHookSpecificOutput
    | UserPromptSubmitHookSpecificOutput
    | NotificationHookSpecificOutput
    | SubagentStartHookSpecificOutput
    | PermissionRequestHookSpecificOutput
)

AsyncHookJSONOutput

Output hook async yang menunda eksekusi hook.

class AsyncHookJSONOutput(TypedDict):
    async_: Literal[True]  # Set to True to defer execution
    asyncTimeout: NotRequired[int]  # Timeout in milliseconds

Contoh Penggunaan Hook

Contoh ini mendaftarkan dua hooks: satu yang memblokir perintah bash berbahaya seperti rm -rf /, dan satu lagi yang mencatat semua penggunaan tool untuk audit. Hook keamanan hanya berjalan pada perintah Bash (melalui matcher), sementara hook logging berjalan pada semua tools.

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)

Tipe Input/Output Tool

Dokumentasi skema input/output untuk semua tools Claude Code bawaan. Meskipun Python SDK tidak mengekspor ini sebagai tipe, mereka mewakili struktur input dan output tool dalam pesan.

Agent

Nama tool: Agent (sebelumnya Task, yang masih diterima sebagai alias)

Input:

{
    "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
}

Output:

{
    "result": str,  # Final result from the subagent
    "usage": dict | None,  # Token usage statistics
    "total_cost_usd": float | None,  # Estimated total cost in USD
    "duration_ms": int | None,  # Execution duration in milliseconds
}

AskUserQuestion

Nama tool: AskUserQuestion

Mengajukan pertanyaan klarifikasi kepada pengguna selama eksekusi. Lihat Handle approvals and user input untuk detail penggunaan.

Input:

{
    "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
}

Output:

{
    "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
}

Bash

Nama tool: Bash

Input:

{
    "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
}

Output:

{
    "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
}

Monitor

Nama tool: Monitor

Menjalankan skrip latar belakang dan mengirimkan setiap baris stdout ke Claude sebagai event sehingga dapat bereaksi tanpa polling. Monitor mengikuti aturan izin yang sama seperti Bash. Lihat Monitor tool reference untuk perilaku dan ketersediaan penyedia.

Input:

{
    "command": str,  # Shell script; each stdout line is an event, exit ends the watch
    "description": str,  # Short description shown in notifications
    "timeout_ms": int | None,  # Kill after this deadline (default 300000, max 3600000)
    "persistent": bool | None,  # Run for the lifetime of the session; stop with TaskStop
}

Output:

{
    "taskId": str,  # ID of the background monitor task
    "timeoutMs": int,  # Timeout deadline in milliseconds
    "persistent": bool | None,  # True when running until TaskStop or session end
}

Edit

Nama tool: Edit

Input:

{
    "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)
}

Output:

{
    "message": str,  # Confirmation message
    "replacements": int,  # Number of replacements made
    "file_path": str,  # File path that was edited
}

Read

Nama tool: Read

Input:

{
    "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
}

Output (File teks):

{
    "content": str,  # File contents with line numbers
    "total_lines": int,  # Total number of lines in file
    "lines_returned": int,  # Lines actually returned
}

Output (Gambar):

{
    "image": str,  # Base64 encoded image data
    "mime_type": str,  # Image MIME type
    "file_size": int,  # File size in bytes
}

Write

Nama tool: Write

Input:

{
    "file_path": str,  # The absolute path to the file to write
    "content": str,  # The content to write to the file
}

Output:

{
    "message": str,  # Success message
    "bytes_written": int,  # Number of bytes written
    "file_path": str,  # File path that was written
}

Glob

Nama tool: Glob

Input:

{
    "pattern": str,  # The glob pattern to match files against
    "path": str | None,  # The directory to search in (defaults to cwd)
}

Output:

{
    "matches": list[str],  # Array of matching file paths
    "count": int,  # Number of matches found
    "search_path": str,  # Search directory used
}

Grep

Nama tool: Grep

Input:

{
    "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
}

Output (content mode):

{
    "matches": [
        {
            "file": str,
            "line_number": int | None,
            "line": str,
            "before_context": list[str] | None,
            "after_context": list[str] | None,
        }
    ],
    "total_matches": int,
}

Output (files_with_matches mode):

{
    "files": list[str],  # Files containing matches
    "count": int,  # Number of files with matches
}

NotebookEdit

Nama tool: NotebookEdit

Input:

{
    "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
}

Output:

{
    "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
}

WebFetch

Nama tool: WebFetch

Input:

{
    "url": str,  # The URL to fetch content from
    "prompt": str,  # The prompt to run on the fetched content
}

Output:

{
    "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
}

WebSearch

Nama tool: WebSearch

Input:

{
    "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
}

Output:

{
    "results": [{"title": str, "url": str, "snippet": str, "metadata": dict | None}],
    "total_results": int,
    "query": str,
}

TodoWrite

Nama tool: TodoWrite

Input:

{
    "todos": [
        {
            "content": str,  # The task description
            "status": "pending" | "in_progress" | "completed",  # Task status
            "activeForm": str,  # Active form of the description
        }
    ]
}

Output:

{
    "message": str,  # Success message
    "stats": {"total": int, "pending": int, "in_progress": int, "completed": int},
}

BashOutput

Nama tool: BashOutput

Input:

{
    "bash_id": str,  # The ID of the background shell
    "filter": str | None,  # Optional regex to filter output lines
}

Output:

{
    "output": str,  # New output since last check
    "status": "running" | "completed" | "failed",  # Current shell status
    "exitCode": int | None,  # Exit code when completed
}

KillBash

Nama tool: KillBash

Input:

{
    "shell_id": str  # The ID of the background shell to kill
}

Output:

{
    "message": str,  # Success message
    "shell_id": str,  # ID of the killed shell
}

ExitPlanMode

Nama tool: ExitPlanMode

Input:

{
    "plan": str  # The plan to run by the user for approval
}

Output:

{
    "message": str,  # Confirmation message
    "approved": bool | None,  # Whether user approved the plan
}

ListMcpResources

Nama tool: ListMcpResources

Input:

{
    "server": str | None  # Optional server name to filter resources by
}

Output:

{
    "resources": [
        {
            "uri": str,
            "name": str,
            "description": str | None,
            "mimeType": str | None,
            "server": str,
        }
    ],
    "total": int,
}

ReadMcpResource

Nama tool: ReadMcpResource

Input:

{
    "server": str,  # The MCP server name
    "uri": str,  # The resource URI to read
}

Output:

{
    "contents": [
        {"uri": str, "mimeType": str | None, "text": str | None, "blob": str | None}
    ],
    "server": str,
}

Fitur Lanjutan dengan ClaudeSDKClient

Membangun Antarmuka Percakapan Berkelanjutan

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 = 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 - the session retains all previous messages
            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())

Menggunakan Hooks untuk Modifikasi Perilaku

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 a timestamp as additional context for Claude to see
    from datetime import datetime

    timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")

    return {
        "hookSpecificOutput": {
            "hookEventName": "UserPromptSubmit",
            "additionalContext": f"[Submitted at {timestamp}] Original prompt: {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())

Pemantauan Kemajuan Real-time

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
        async for message in client.receive_response():
            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("Completed tool execution")
                    elif isinstance(block, TextBlock):
                        print(f"Claude says: {block.text[:100]}...")

        print("Task completed!")


asyncio.run(monitor_progress())

Contoh Penggunaan

Operasi file dasar (menggunakan query)

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())

Penanganan error

from claude_agent_sdk import query, CLINotFoundError, ProcessError, CLIJSONDecodeError

try:
    async for message in query(prompt="Hello"):
        print(message)
except CLINotFoundError:
    print(
        "Claude Code CLI not found. Try reinstalling: pip install --force-reinstall claude-agent-sdk"
    )
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}")

Mode streaming dengan klien

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())

Menggunakan tools kustom dengan ClaudeSDKClient

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())

Konfigurasi Sandbox

SandboxSettings

Konfigurasi untuk perilaku sandbox. Gunakan ini untuk mengaktifkan sandboxing perintah dan mengonfigurasi pembatasan jaringan secara programatis.

class SandboxSettings(TypedDict, total=False):
    enabled: bool
    autoAllowBashIfSandboxed: bool
    excludedCommands: list[str]
    allowUnsandboxedCommands: bool
    network: SandboxNetworkConfig
    ignoreViolations: SandboxIgnoreViolations
    enableWeakerNestedSandbox: bool

Contoh penggunaan

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)

SandboxNetworkConfig

Konfigurasi spesifik jaringan untuk mode sandbox.

class SandboxNetworkConfig(TypedDict, total=False):
    allowedDomains: list[str]
    deniedDomains: list[str]
    allowManagedDomainsOnly: bool
    allowUnixSockets: list[str]
    allowAllUnixSockets: bool
    allowLocalBinding: bool
    allowMachLookup: list[str]
    httpProxyPort: int
    socksProxyPort: int

SandboxIgnoreViolations

Konfigurasi untuk mengabaikan pelanggaran sandbox tertentu.

class SandboxIgnoreViolations(TypedDict, total=False):
    file: list[str]
    network: list[str]

Fallback Izin untuk Perintah Tanpa Sandbox

Ketika allowUnsandboxedCommands diaktifkan, model dapat meminta untuk menjalankan perintah di luar sandbox dengan mengatur dangerouslyDisableSandbox: True dalam input tool. Permintaan ini jatuh kembali ke sistem izin yang ada, berarti handler can_use_tool Anda akan dipanggil, memungkinkan Anda menerapkan logika otorisasi kustom.

from claude_agent_sdk import (
    query,
    ClaudeAgentOptions,
    HookMatcher,
    PermissionResultAllow,
    PermissionResultDeny,
    ToolPermissionContext,
)


async def can_use_tool(
    tool: str, input: dict, context: ToolPermissionContext
) -> PermissionResultAllow | PermissionResultDeny:
    # Check if the model is requesting to bypass the sandbox
    if tool == "Bash" and input.get("dangerouslyDisableSandbox"):
        # The model is requesting to run this command outside the sandbox
        print(f"Unsandboxed command requested: {input.get('command')}")

        if is_command_authorized(input.get("command")):
            return PermissionResultAllow()
        return PermissionResultDeny(
            message="Command not authorized for unsandboxed execution"
        )
    return PermissionResultAllow()


# Required: dummy hook keeps the stream open for can_use_tool
async def dummy_hook(input_data, tool_use_id, context):
    return {"continue_": True}


async def prompt_stream():
    yield {
        "type": "user",
        "message": {"role": "user", "content": "Deploy my application"},
    }


async def main():
    async for message in query(
        prompt=prompt_stream(),
        options=ClaudeAgentOptions(
            sandbox={
                "enabled": True,
                "allowUnsandboxedCommands": True,  # Model can request unsandboxed execution
            },
            permission_mode="default",
            can_use_tool=can_use_tool,
            hooks={"PreToolUse": [HookMatcher(matcher=None, hooks=[dummy_hook])]},
        ),
    ):
        print(message)

Pola ini memungkinkan Anda untuk:

• Audit permintaan model: Catat ketika model meminta eksekusi tanpa sandbox
• Implementasikan allowlist: Hanya izinkan perintah tertentu untuk berjalan tanpa sandbox
• Tambahkan alur persetujuan: Memerlukan otorisasi eksplisit untuk operasi istimewa

Lihat juga

• SDK overview - Konsep SDK umum
• TypeScript SDK reference - Dokumentasi SDK TypeScript
• CLI reference - Antarmuka baris perintah
• Common workflows - Panduan langkah demi langkah