Ink Claude Dream Agent SDK for Python

Portable downstream distribution of the MIT-licensed Claude Agent SDK Python source pinned to upstream 0.2.143, published as downstream release 0.2.144. It preserves the claude_agent_sdk import namespace and public API while intentionally excluding the proprietary Claude Code executable. See the official Claude Agent SDK documentation for SDK usage.

Installation

pip install ink-claude-dream-agent-sdk

Prerequisites:

• Python 3.10+

This distribution and Anthropic's claude-agent-sdk distribution install the same claude_agent_sdk import namespace. Do not install both in one environment; replace the old distribution before installing this one. This portable package does not bundle Claude Code. The unchanged SDK selection behavior can use a system-wide installation or a specific path:

• Install Claude Code separately: curl -fsSL https://claude.ai/install.sh | bash
• Specify a custom path: ClaudeAgentOptions(cli_path="/path/to/claude")

Quick Start

import anyio
from claude_agent_sdk import query

async def main():
    async for message in query(prompt="What is 2 + 2?"):
        print(message)

anyio.run(main)

Basic Usage: query()

query() is an async function for querying Claude Code. It returns an AsyncIterator of response messages. See src/claude_agent_sdk/query.py.

from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, TextBlock

# Simple query
async for message in query(prompt="Hello Claude"):
    if isinstance(message, AssistantMessage):
        for block in message.content:
            if isinstance(block, TextBlock):
                print(block.text)

# With options
options = ClaudeAgentOptions(
    system_prompt="You are a helpful assistant",
    max_turns=1
)

async for message in query(prompt="Tell me a joke", options=options):
    print(message)

Using Tools

By default, Claude has access to the full Claude Code toolset (Read, Write, Edit, Bash, and others). allowed_tools is a permission allowlist: listed tools are auto-approved, and unlisted tools fall through to permission_mode and can_use_tool for a decision. It does not remove tools from Claude's toolset. To block specific tools, use disallowed_tools. See the permissions guide for the full evaluation order.

options = ClaudeAgentOptions(
    allowed_tools=["Read", "Write", "Bash"],  # auto-approve these tools
    permission_mode='acceptEdits'  # auto-accept file edits
)

async for message in query(
    prompt="Create a hello.py file",
    options=options
):
    # Process tool use and results
    pass

Working Directory

from pathlib import Path

options = ClaudeAgentOptions(
    cwd="/path/to/project"  # or Path("/path/to/project")
)

ClaudeSDKClient

ClaudeSDKClient supports bidirectional, interactive conversations with Claude Code. See src/claude_agent_sdk/client.py.

Unlike query(), ClaudeSDKClient additionally enables custom tools and hooks, both of which can be defined as Python functions.

Custom Tools (as In-Process SDK MCP Servers)

A custom tool is a Python function that you can offer to Claude, for Claude to invoke as needed.

Custom tools are implemented in-process MCP servers that run directly within your Python application, eliminating the need for separate processes that regular MCP servers require.

For an end-to-end example, see MCP Calculator.

Creating a Simple Tool

from claude_agent_sdk import tool, create_sdk_mcp_server, ClaudeAgentOptions, ClaudeSDKClient

# Define a tool using the @tool decorator
@tool("greet", "Greet a user", {"name": str})
async def greet_user(args):
    return {
        "content": [
            {"type": "text", "text": f"Hello, {args['name']}!"}
        ]
    }

# Create an SDK MCP server
server = create_sdk_mcp_server(
    name="my-tools",
    version="1.0.0",
    tools=[greet_user]
)

# Use it with Claude. allowed_tools pre-approves the tool so it runs
# without a permission prompt; it does not control tool availability.
options = ClaudeAgentOptions(
    mcp_servers={"tools": server},
    allowed_tools=["mcp__tools__greet"]
)

async with ClaudeSDKClient(options=options) as client:
    await client.query("Greet Alice")

    # Extract and print response
    async for msg in client.receive_response():
        print(msg)

Benefits Over External MCP Servers

• No subprocess management - Runs in the same process as your application
• Better performance - No IPC overhead for tool calls
• Simpler deployment - Single Python process instead of multiple
• Easier debugging - All code runs in the same process
• Type safety - Direct Python function calls with type hints

Migration from External Servers

# BEFORE: External MCP server (separate process)
options = ClaudeAgentOptions(
    mcp_servers={
        "calculator": {
            "type": "stdio",
            "command": "python",
            "args": ["-m", "calculator_server"]
        }
    }
)

# AFTER: SDK MCP server (in-process)
from my_tools import add, subtract  # Your tool functions

calculator = create_sdk_mcp_server(
    name="calculator",
    tools=[add, subtract]
)

options = ClaudeAgentOptions(
    mcp_servers={"calculator": calculator}
)

Mixed Server Support

You can use both SDK and external MCP servers together:

options = ClaudeAgentOptions(
    mcp_servers={
        "internal": sdk_server,      # In-process SDK server
        "external": {                # External subprocess server
            "type": "stdio",
            "command": "external-server"
        }
    }
)

Hooks

A hook is a Python function that the Claude Code application (not Claude) invokes at specific points of the Claude agent loop. Hooks can provide deterministic processing and automated feedback for Claude. Read more in Intercept and control agent behavior with hooks.

For more examples, see examples/hooks.py.

Example

from claude_agent_sdk import ClaudeAgentOptions, ClaudeSDKClient, HookMatcher

async def check_bash_command(input_data, tool_use_id, context):
    tool_name = input_data["tool_name"]
    tool_input = input_data["tool_input"]
    if tool_name != "Bash":
        return {}
    command = tool_input.get("command", "")
    block_patterns = ["foo.sh"]
    for pattern in block_patterns:
        if pattern in command:
            return {
                "hookSpecificOutput": {
                    "hookEventName": "PreToolUse",
                    "permissionDecision": "deny",
                    "permissionDecisionReason": f"Command contains invalid pattern: {pattern}",
                }
            }
    return {}

options = ClaudeAgentOptions(
    allowed_tools=["Bash"],
    hooks={
        "PreToolUse": [
            HookMatcher(matcher="Bash", hooks=[check_bash_command]),
        ],
    }
)

async with ClaudeSDKClient(options=options) as client:
    # Test 1: Command with forbidden pattern (will be blocked)
    await client.query("Run the bash command: ./foo.sh --help")
    async for msg in client.receive_response():
        print(msg)

    print("\n" + "=" * 50 + "\n")

    # Test 2: Safe command that should work
    await client.query("Run the bash command: echo 'Hello from hooks example!'")
    async for msg in client.receive_response():
        print(msg)

Types

See src/claude_agent_sdk/types.py for complete type definitions:

• ClaudeAgentOptions - Configuration options
• AssistantMessage, UserMessage, SystemMessage, ResultMessage - Message types
• TextBlock, ToolUseBlock, ToolResultBlock - Content blocks

Error Handling

from claude_agent_sdk import (
    ClaudeSDKError,      # Base error
    CLINotFoundError,    # Claude Code not installed
    CLIConnectionError,  # Connection issues
    ProcessError,        # Process failed
    ResultError,         # Run ended with an error result (subclass of ProcessError)
    CLIJSONDecodeError,  # JSON parsing issues
)

try:
    async for message in query(prompt="Hello"):
        pass
except CLINotFoundError:
    print("Please install Claude Code")
except ResultError as e:
    # The CLI reported a terminal error result (also yielded as the final
    # ResultMessage) and exited. Structured fields are on the exception.
    print(f"Run failed: {e.subtype=} {e.terminal_reason=} {e.api_error_status=}")
    print(e.result or e.errors)
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}")

See src/claude_agent_sdk/_errors.py for all error types.

Available Tools

See the Claude Code documentation for a complete list of available tools.

Examples

See examples/quick_start.py for a complete working example.

See examples/streaming_mode.py for comprehensive examples involving ClaudeSDKClient. You can even run interactive examples in IPython from examples/streaming_mode_ipython.py.

Migrating from Claude Code SDK

If you're upgrading from the Claude Code SDK (versions < 0.1.0), please see the CHANGELOG.md for details on breaking changes and new features, including:

• ClaudeCodeOptions → ClaudeAgentOptions rename
• Merged system prompt configuration
• Settings isolation and explicit control
• New programmatic subagents and session forking features

Development

If you're contributing to this project, run the initial setup script to install git hooks:

./scripts/initial-setup.sh

This installs a pre-push hook that runs lint checks before pushing, matching the CI workflow. To skip the hook temporarily, use git push --no-verify.

Building portable packages locally

Use the pinned, reproducible source-only build documented in docs/packaging/runtime-integration.md. The resulting artifact names are:

ink_claude_dream_agent_sdk-0.2.144-py3-none-any.whl
ink_claude_dream_agent_sdk-0.2.144.tar.gz

Default Hatch wheel and sdist targets explicitly exclude src/claude_agent_sdk/_bundled/claude{,.exe}. The inherited upstream scripts/build_wheel.py vendor builder also refuses to run under this renamed distribution, before downloading anything.

Reproducible downstream packages

For pinned upstream provenance, read-only sync inspection, a portable SDK-only wheel/sdist, repeat-build verification, and isolated official/custom CLI path smoke tests, see docs/packaging/runtime-integration.md. The downstream procedure does not authorize redistribution of the proprietary Claude Code binary. Local artifacts remain ignored and untracked; reviewed SDK archives leave CI only through the protected promotion workflow below.

Release policy

The downstream portable-SDK promotion workflow is configured to publish one reviewed wheel/sdist byte set to TestPyPI, verify the published bytes, and only then enter the protected PyPI approval environment. Repository administrators must still configure both Trusted Publishers and required reviewers before the workflow is usable. The inherited vendor-wheel and official PyPI workflows stay repository-identity gated to anthropics/claude-agent-sdk-python; they skip in this mirror. See RELEASING.md for the Chinese authoritative release procedure. Neither release path permits a Claude CLI or *.map file in the downstream Python archives.

License and terms

Use of this SDK is governed by Anthropic's Commercial Terms of Service, including when you use it to power products and services that you make available to your own customers and end users, except to the extent a specific component or dependency is covered by a different license as indicated in that component's LICENSE file.