@agent-sh/computer-use-linux 0.2.9 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -56,12 +56,15 @@ Screenshot payloads are size-bounded by default before they are returned to the
|
|
|
56
56
|
- `press_key` — keys / chords; can focus a window or terminal first
|
|
57
57
|
- `type_text` — literal text input, optionally targeted at a window or terminal
|
|
58
58
|
|
|
59
|
+
Targeted `press_key`/`type_text` results append focused-element feedback from AT-SPI (role, name, editable) and warn when no editable element holds focus. Click/screenshot/input results warn when the target window or coordinate is partially or fully off-screen. `get_app_state` returns a compact readiness block by default; pass `verbose: true` for the full diagnostics report.
|
|
60
|
+
|
|
59
61
|
**Semantic actions**
|
|
60
62
|
- `perform_action` — invoke any AT-SPI action exposed by an element (`Press`, `Activate`, `Toggle`, …); defaults to the primary action
|
|
61
63
|
- `set_value` — write to a settable accessibility element (text fields, sliders, spinners)
|
|
62
64
|
|
|
63
65
|
**Navigation**
|
|
64
66
|
- `activate_window` — focus a window by `window_id`, `pid`, `app_id`, `wm_class`, `title`, or terminal selectors
|
|
67
|
+
- `move_window` / `resize_window` — reposition or resize a window in desktop coordinates (GNOME Shell extension backend); useful to recover windows that are partially off-screen
|
|
65
68
|
|
|
66
69
|
### MCP safety contract
|
|
67
70
|
|
|
@@ -71,7 +74,7 @@ Screenshot payloads are size-bounded by default before they are returned to the
|
|
|
71
74
|
| --- | --- | --- |
|
|
72
75
|
| Read-only observation | `doctor`, `list_apps`, `list_windows`, `focused_window`, `get_app_state` | `readOnlyHint=true`; may reveal app, window, accessibility, and screenshot contents. `get_app_state` may trigger the desktop screenshot portal prompt. |
|
|
73
76
|
| Local setup mutators | `setup_accessibility`, `setup_window_targeting` | `readOnlyHint=false`, `destructiveHint=false`, `idempotentHint=true`; modifies user desktop configuration by enabling accessibility or installing/enabling the GNOME window-targeting extension. |
|
|
74
|
-
| UI state mutators | `activate_window`, `scroll`, `screenshot` | `readOnlyHint=false`, `destructiveHint=false`; changes focus or scroll position in the live desktop, or raises a window to capture it. |
|
|
77
|
+
| UI state mutators | `activate_window`, `move_window`, `resize_window`, `scroll`, `screenshot` | `readOnlyHint=false`, `destructiveHint=false`; changes focus, geometry, or scroll position in the live desktop, or raises a window to capture it. |
|
|
75
78
|
| Desktop action mutators | `click`, `drag`, `press_key`, `type_text`, `perform_action`, `set_value` | `readOnlyHint=false`, `destructiveHint=true`, `openWorldHint=true`; can trigger arbitrary actions in whatever local application is targeted. |
|
|
76
79
|
|
|
77
80
|
Annotations are safety hints, not an authorization system. MCP hosts should still ask the user before calls that could submit, delete, send, purchase, overwrite, or otherwise commit state.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@agent-sh/computer-use-linux",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.3.0",
|
|
4
4
|
"description": "Linux desktop-control MCP server: AT-SPI accessibility trees, Wayland/X11 input, screenshots, and compositor window targeting.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "commonjs",
|