[Doc] Wrong example on can_use_tool for custom permission handler

[FesonX]

the Claude SDK docs example is misleading for can_use_tool with custom permission handler, the correct case lays on github repo.

WRONG

from claude_agent_sdk import query, ClaudeAgentOptions

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

        # Return True to allow, False to deny
        return is_command_authorized(input.get("command"))
    return True

async def main():
    async for message in query(
        prompt="Deploy my application",
        options=ClaudeAgentOptions(
            sandbox={
                "enabled": True,
                "allowUnsandboxedCommands": True  # Model can request unsandboxed execution
            },
            permission_mode="default",
            can_use_tool=can_use_tool
        )
    ):
        print(message)

will result:

Error: Tool permission request failed: Error: Tool permission callback must return PermissionResult (PermissionResultAllow or PermissionResultDeny), got <class 'dict'>

The correct example is https://github.com/anthropics/claude-agent-sdk-python/blob/3cbb9e56be1f5b947d640f0b05710d7d032781be/examples/tool_permission_callback.py

[FesonX]

By the way, the SDK docs website has not way to send feedback, really sucks