wehub-resource-sync
91e75e620b
CI: cua-driver distro-compat matrix / Resolve release version (push) Waiting to run
CI: cua-driver distro-compat matrix / debian:12 (glibc 2.36) (push) Blocked by required conditions
CI: cua-driver distro-compat matrix / fedora:41 (glibc 2.40) (push) Blocked by required conditions
CI: cua-driver distro-compat matrix / rockylinux:9 (glibc 2.34) (push) Blocked by required conditions
CI: cua-driver distro-compat matrix / ubuntu:22.04 (glibc 2.35) (push) Blocked by required conditions
CI: cua-driver distro-compat matrix / ubuntu:24.04 (glibc 2.39) (push) Blocked by required conditions
CI: cua-driver distro-compat matrix / Distro compat summary (push) Blocked by required conditions
CI: Nix Linux Rust source / Nix / compositor build (push) Waiting to run
CI: Nix Linux Rust source / Nix / driver package (push) Waiting to run
CI: Nix Linux Rust source / Nix / Rust unit tests (push) Waiting to run
CI: Rust Linux unit / Rust Linux unit and compile (push) Waiting to run
CI: Rust Windows unit / Rust Windows unit and compile (push) Waiting to run
CI: SPDX Headers / Check SPDX headers (warn-only) (push) Waiting to run
CD: Docs MCP Server / build (linux/amd64) (push) Waiting to run
CD: Docs MCP Server / build (linux/arm64) (push) Waiting to run
CD: Docs MCP Server / merge (push) Blocked by required conditions
84 lines
2.3 KiB
Python
84 lines
2.3 KiB
Python
"""
|
|
Base computer interface protocol for agent interactions.
|
|
"""
|
|
|
|
from typing import (
|
|
Any,
|
|
Dict,
|
|
List,
|
|
Literal,
|
|
Optional,
|
|
Protocol,
|
|
Union,
|
|
runtime_checkable,
|
|
)
|
|
|
|
|
|
@runtime_checkable
|
|
class AsyncComputerHandler(Protocol):
|
|
"""Protocol defining the interface for computer interactions."""
|
|
|
|
# ==== Computer-Use-Preview Action Space ====
|
|
|
|
async def get_environment(self) -> Literal["windows", "mac", "linux", "browser"]:
|
|
"""Get the current environment type."""
|
|
...
|
|
|
|
async def get_dimensions(self) -> tuple[int, int]:
|
|
"""Get screen dimensions as (width, height)."""
|
|
...
|
|
|
|
async def screenshot(self, text: Optional[str] = None) -> str:
|
|
"""Take a screenshot and return as base64 string.
|
|
|
|
Args:
|
|
text: Optional descriptive text (for compatibility with GPT-4o models, ignored)
|
|
"""
|
|
...
|
|
|
|
async def click(self, x: int, y: int, button: str = "left") -> None:
|
|
"""Click at coordinates with specified button."""
|
|
...
|
|
|
|
async def double_click(self, x: int, y: int) -> None:
|
|
"""Double click at coordinates."""
|
|
...
|
|
|
|
async def scroll(self, x: int, y: int, scroll_x: int, scroll_y: int) -> None:
|
|
"""Scroll at coordinates with specified scroll amounts."""
|
|
...
|
|
|
|
async def type(self, text: str) -> None:
|
|
"""Type text."""
|
|
...
|
|
|
|
async def wait(self, ms: int = 1000) -> None:
|
|
"""Wait for specified milliseconds."""
|
|
...
|
|
|
|
async def move(self, x: int, y: int) -> None:
|
|
"""Move cursor to coordinates."""
|
|
...
|
|
|
|
async def keypress(self, keys: Union[List[str], str]) -> None:
|
|
"""Press key combination."""
|
|
...
|
|
|
|
async def drag(self, path: List[Dict[str, int]]) -> None:
|
|
"""Drag along specified path."""
|
|
...
|
|
|
|
async def get_current_url(self) -> str:
|
|
"""Get current URL (for browser environments)."""
|
|
...
|
|
|
|
# ==== Anthropic Action Space ====
|
|
|
|
async def left_mouse_down(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
|
|
"""Left mouse down at coordinates."""
|
|
...
|
|
|
|
async def left_mouse_up(self, x: Optional[int] = None, y: Optional[int] = None) -> None:
|
|
"""Left mouse up at coordinates."""
|
|
...
|