mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-07-10 01:29:17 +00:00
9605bcc25f
* feat(cua-driver): sync vendored cua-driver from 0.6.8 to 0.7.0 Upstream 0.7.0 brings action-time modality (get_window_state always returns AX tree + screenshot, capture_mode retired), honest verification (every action returns verified/path/effect/escalation), browser page (CDP) tools, desktop-scope (capture_scope=window|desktop, get_desktop_state, screen-absolute click/scroll), and Rust-only consolidation (Swift backend retired). Cherry-pick patch changes: - #2025 (X11 synthetic click): retired — superseded by 0.7.0 honest-verification - #2035 (session revive): retired — superseded by 0.7.0 revive_session/loud-reject/is_session_lifecycle_tool - #2036 (EAGAIN socket write retry): re-injected — merged upstream post-0.7.0 tag, EAGAIN os error 35 is not acceptable - #2021 (null/empty-title windows + resolve_uwp_host_window): retained, adapted to 0.7.0's new is_listable_top_level and window_title helpers Shim extensions: - coord_norm: desktop-scope support — denormalize_args falls back to screen basis when no window cache (desktop-scope click), normalize_result handles get_desktop_state, ingest_screen_size reads get_desktop_state's screen_width/height - serve.rs: rewrite_coord_desc re-injected at both tools/list sites Install scripts simplified to Rust-only (Swift backend retired upstream). Fix platform-linux cross-compilation: cfg-gate wayland::PORTAL_LIBEI_ENABLED reference in health_report.rs for non-linux hosts. * fix(cua-driver): distinguish desktop-scope from window cache miss in denormalize_args When screenshot_w == 0 (no cached window size), check whether the call has a pid/window_id target before falling back to screen-size basis. Window-scoped clicks with a cache miss now correctly leave coordinates as-is instead of mapping them against the screen dimensions. * fix(cua-driver): use screenshot pixels not logical points for desktop-scope coord basis ingest_screen_size was reading screen_width/height (logical display points from CGDisplayBounds) for get_desktop_state, but the model operates on the screenshot PNG whose dimensions are physical pixels. On Retina displays (2x) this caused every desktop-scope click to land at half the intended position. Read screenshot_width/height instead — the same basis normalize_result rewrites to 1000. Updated test to use realistic Retina values (screen 1920, screenshot 3840) to catch 1:1 masking. * fix(cua-driver): split screen cache into logical (move_cursor) and physical (desktop-scope) The single screen_cache was being written by both get_screen_size (logical points, e.g. 1920x1080) and get_desktop_state (physical pixels, e.g. 3840x2160). Since move_cursor operates in CGEvent screen points (logical) while desktop-scope clicks operate in screenshot pixels (physical), whichever tool ran last would corrupt the other's denormalization basis — causing 2x overshoot or 1/2 offset on Retina. Split into: - SCREEN_SIZE: logical points, written by get_screen_size, consumed by move_cursor (screen_basis=true) - DESKTOP_SCREENSHOT_SIZE: physical pixels, written by get_desktop_state, consumed by desktop-scope click fallback (screenshot_w==0, no pid) Added cross-contamination isolation tests. --------- Co-authored-by: Shaojin Wen <shaojin.wensj@alibaba-inc.com> |
||
|---|---|---|
| .. | ||
| src/cua_driver | ||
| tests | ||
| .gitignore | ||
| build_wheel.py | ||
| MANIFEST.in | ||
| pyproject.toml | ||
| README.md | ||
cua-driver
Python wrapper for cua-driver - a cross-platform MCP (Model Context Protocol) server for computer-use automation.
Installation
Install and usage docs live at https://cua.ai/docs/how-to-guides/driver/install and https://cua.ai/docs/reference/cua-driver/mcp-tools.
Usage
The package provides a cua-driver command that wraps the native Rust binary.
See the canonical tool reference at https://cua.ai/docs/reference/cua-driver/mcp-tools.
Python API
You can also use the Python API directly:
from cua_driver import run_cua_driver, get_binary_path
# Run with custom args
exit_code = run_cua_driver(["mcp"])
# Get path to bundled binary
binary_path = get_binary_path()
Features
- Cross-platform: Works on macOS (universal), Linux (x86_64), and Windows (x86_64/ARM64)
- Zero dependencies: Pure Python wrapper with no external dependencies
- Stdio passthrough: Transparent piping for MCP protocol communication
- Bundled binary: No separate installation required - the Rust binary is included in the wheel
Platform Support
| Platform | Architecture | Status |
|---|---|---|
| macOS | Universal (ARM64 + x86_64) | ✅ Supported |
| Linux | x86_64 | ✅ Supported |
| Windows | x86_64 | ✅ Supported |
| Windows | ARM64 | ✅ Supported |
License
MIT License - see LICENSE