haijun-agent-sdk 0.1.0

Haijun Agent SDK for Python — Python SDK for Haijun Agent. See the [Haijun Agent SDK documentation](https://raw.haijun.my.id/docs/en/agent-sdk/python) for more information.

Installation

pip install haijun-agent-sdk

Prerequisites:

• Python 3.10+

Note: The Haijun Code CLI is automatically bundled with the package - no separate installation required! The SDK will use the bundled CLI by default. If you prefer to use a system-wide installation or a specific version, you can:

• Install Haijun Code separately: curl -fsSL https://downloads.haijun.my.id/cli/install.sh | bash
• Specify a custom path: HaijunAgentOptions(cli_path="/path/to/haijun")

Quick Start

import anyio
from haijun_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 Haijun Code. It returns an AsyncIterator of response messages. See src/haijun_agent_sdk/query.py.

from haijun_agent_sdk import query, HaijunAgentOptions, AssistantMessage, TextBlock

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

# With options
options = HaijunAgentOptions(
    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, Haijun has access to the full Haijun 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 Haijun's toolset. To block specific tools, use disallowed_tools. See the permissions guide for the full evaluation order.

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

HaijunSDKClient

HaijunSDKClient supports bidirectional, interactive conversations with Haijun Code. See src/haijun_agent_sdk/client.py.

Unlike query(), HaijunSDKClient 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 Haijun, for Haijun 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 haijun_agent_sdk import tool, create_sdk_mcp_server, HaijunAgentOptions, HaijunSDKClient

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

async with HaijunSDKClient(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 = HaijunAgentOptions(
    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 = HaijunAgentOptions(
    mcp_servers={"calculator": calculator}
)

Mixed Server Support

You can use both SDK and external MCP servers together:

options = HaijunAgentOptions(
    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 Haijun Code application (not Haijun) invokes at specific points of the Haijun agent loop. Hooks can provide deterministic processing and automated feedback for Haijun. Read more in Intercept and control agent behavior with hooks.

For more examples, see examples/hooks.py.

Example

from haijun_agent_sdk import HaijunAgentOptions, HaijunSDKClient, 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 = HaijunAgentOptions(
    allowed_tools=["Bash"],
    hooks={
        "PreToolUse": [
            HookMatcher(matcher="Bash", hooks=[check_bash_command]),
        ],
    }
)

async with HaijunSDKClient(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/haijun_agent_sdk/types.py for complete type definitions:

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

Error Handling

from haijun_agent_sdk import (
    HaijunSDKError,      # Base error
    CLINotFoundError,    # Haijun 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 Haijun 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/haijun_agent_sdk/_errors.py for all error types.

Available Tools

See the Haijun 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 HaijunSDKClient. You can even run interactive examples in IPython from examples/streaming_mode_ipython.py.

Migrating from Haijun Code SDK

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

• HaijunCodeOptions → HaijunAgentOptions 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 Wheels Locally

To build wheels with the bundled Haijun Code CLI:

# Install build dependencies
pip install build twine

# Build wheel with bundled CLI
python scripts/build_wheel.py

# Build with specific version
python scripts/build_wheel.py --version 0.1.4

# Build with specific CLI version
python scripts/build_wheel.py --cli-version 2.0.0

# Clean bundled CLI after building
python scripts/build_wheel.py --clean

# Skip CLI download (use existing)
python scripts/build_wheel.py --skip-download

The build script:

1. Downloads Haijun Code CLI for your platform
2. Bundles it in the wheel
3. Builds both wheel and source distribution
4. Checks the package with twine

See python scripts/build_wheel.py --help for all options.

Release Workflow

The package is published to PyPI via the GitHub Actions workflow in .github/workflows/publish.yml. To create a new release:

1. Trigger the workflow manually from the Actions tab with two inputs:

   • version: The package version to publish (e.g., 0.1.5)
   • haijun_code_version: The Haijun Code CLI version to bundle (e.g., 2.0.0 or latest)

2. The workflow will:

   • Build platform-specific wheels for macOS, Linux, and Windows
   • Bundle the specified Haijun Code CLI version in each wheel
   • Build a source distribution
   • Publish all artifacts to PyPI
   • Create a release branch with version updates
   • Open a PR to main with:
     • Updated pyproject.toml version
     • Updated src/haijun_agent_sdk/_version.py
     • Updated src/haijun_agent_sdk/_cli_version.py with bundled CLI version
     • Auto-generated CHANGELOG.md entry

3. Review and merge the release PR to update main with the new version information

The workflow tracks both the package version and the bundled CLI version separately, allowing you to release a new package version with an updated CLI without code changes.

License and terms

Use of this SDK is governed by JuGloW'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.