Function create_client

client.py:281–607

Create a Claude Agent SDK client with multi-layered security. Args: project_dir: Directory for the project model: Claude model to use yolo_mode: If True, skip Playwright MCP server for rapid prototyping agent_id: Optional unique identifier for browser isolat

(
    project_dir: Path,
    model: str,
    yolo_mode: bool = False,
    agent_id: str | None = None,
    agent_type: str = "coding",
)

def create_client(
    project_dir: Path,
    model: str,
    yolo_mode: bool = False,
    agent_id: str | None = None,
    agent_type: str = "coding",
):
    """
    Create a Claude Agent SDK client with multi-layered security.

    Args:
        project_dir: Directory for the project
        model: Claude model to use
        yolo_mode: If True, skip Playwright MCP server for rapid prototyping
        agent_id: Optional unique identifier for browser isolation in parallel mode.
                  When provided, each agent gets its own browser profile.
        agent_type: One of "coding", "testing", or "initializer". Controls which
                    MCP tools are exposed and the max_turns limit.

    Returns:
        Configured ClaudeSDKClient (from claude_agent_sdk)

    Security layers (defense in depth):
    1. Sandbox - OS-level bash command isolation prevents filesystem escape
    2. Permissions - File operations restricted to project_dir only
    3. Security hooks - Bash commands validated against an allowlist
       (see security.py for ALLOWED_COMMANDS)

    Note: Authentication is handled by start.bat/start.sh before this runs.
    The Claude SDK auto-detects credentials from the Claude CLI configuration
    """
    # Select the feature MCP tools appropriate for this agent type
    feature_tools_map = {
        "coding": CODING_AGENT_TOOLS,
        "testing": TESTING_AGENT_TOOLS,
        "initializer": INITIALIZER_AGENT_TOOLS,
    }
    feature_tools = feature_tools_map.get(agent_type, CODING_AGENT_TOOLS)

    # Select max_turns based on agent type:
    #   - coding/initializer: 300 turns (complex multi-step implementation)
    #   - testing: 100 turns (focused verification of a single feature)
    max_turns_map = {
        "coding": 300,
        "testing": 100,
        "initializer": 300,
    }
    max_turns = max_turns_map.get(agent_type, 300)

    # Build allowed tools list based on mode and agent type.
    # In YOLO mode, exclude Playwright tools for faster prototyping.
    allowed_tools = [*BUILTIN_TOOLS, *feature_tools]
    if not yolo_mode:
        allowed_tools.extend(PLAYWRIGHT_TOOLS)

    # Build permissions list.
    # We permit ALL feature MCP tools at the security layer (so the MCP server
    # can respond if called), but the LLM only *sees* the agent-type-specific