@agent-sh/computer-use-linux 0.7.9 → 0.7.11

package/README.md

@@ -26,7 +26,7 @@ The Rust crate is published as [`computer-use-linux`](https://crates.io/crates/c
 
 Most computer-use MCP servers are macOS-only (they lean on AppKit, AXUIElement, CGEvent). The few that target Linux either drive `xdotool` against an X11 root window or shell out to OCR over screenshots. Four things set this one apart:
 
-- **Wayland actually works.** Pointer actions can use the `org.freedesktop.portal.RemoteDesktop` interface on Wayland, with `ydotool` / `ydotoold` (uinput) as the deterministic fallback. Literal text prefers `wtype` on compatible Wayland compositors when portal keyboard input is unavailable, preserving Unicode and the active layout before falling back to ydotool. Screenshots use the GNOME Shell DBus screenshot method when present, `org.freedesktop.portal.Screenshot` otherwise, then on a native X11 session a root-window `GetImage` (device pixels, no toolkit scaling), and finally spawn `gnome-screenshot` for background/systemd contexts where the DBus paths are denied.
+- **Wayland actually works.** Pointer actions can use the `org.freedesktop.portal.RemoteDesktop` interface on Wayland, with `ydotool` / `ydotoold` (uinput) as the deterministic fallback. Literal text prefers KDE clipboard integration on Plasma, `wtype` on compatible Wayland compositors, and portal keysyms on other Wayland sessions, including GNOME with ydotool installed. Portal text startup or conversion errors fail the call without replaying text through ydotool. Raw ydotool text accepts printable ASCII, tab and newline only, and its physical US key positions can produce different text under the active layout. Screenshots use the GNOME Shell DBus screenshot method when present, `org.freedesktop.portal.Screenshot` otherwise, then on a native X11 session a root-window `GetImage` (device pixels, no toolkit scaling), and finally spawn `gnome-screenshot` for background/systemd contexts where the DBus paths are denied.
 - **Window targeting is compositor-aware.** The window registry tries GNOME Shell extension, GNOME Shell Introspect, COSMIC Wayland helper, KWin DBus scripting, Hyprland `hyprctl`, the niri IPC socket, i3 IPC, and generic X11/EWMH in order, then reports exactly which backend won or why each backend failed.
 - **Semantic selectors, not pixel coordinates.** Tools like `click`, `perform_action`, and `set_value` accept `role` / `name` / `text` / `states` selectors backed by AT-SPI. Pixel coordinates remain available as a fallback for rendering-only surfaces (canvas, games, X clients without ATK).
 - **One JSON readiness report.** `computer-use-linux doctor` returns a structured document covering platform, portals, AT-SPI, windowing, input, and a `readiness` summary with explicit blockers and a recommended next step. MCP hosts can render or surface that to the user without parsing prose.
@@ -80,6 +80,8 @@ the origin. A missing window target is rejected.
 
 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. It also reports `tree_scoped` (false when no app target narrowed the AT-SPI tree, with a warning in `message`) and `accessibility_tree_truncated` (true when the node, depth, or read budget stopped traversal with unread elements left).
 
+On GNOME, a read-only keymap preflight rejects the whole string before input if a character is absent or requires a modifier level Mutter cannot synthesize. The background reader cannot establish the active layout group, so every configured group must support the text. This can reject text that works in one of several groups; use `set_value` on an editable field instead. The check requires `libxkbcommon.so.0` at runtime and stops after a two-second keymap read deadline. It does not cover held modifiers or a keymap changed concurrently with typing.
+
 **Semantic actions**
 
 - `perform_action` — invoke any AT-SPI action exposed by an element (`Press`, `Activate`, `Toggle`, …); defaults to the primary action
@@ -384,7 +386,7 @@ Spawn the binary with `["mcp"]` as the argv tail. It speaks JSON-RPC over stdio
    computer-use-linux doctor | jq .readiness
    ```
 
-   Aim for `can_register_mcp_tools`, `can_build_accessibility_tree`, `can_send_development_input`, `can_query_windows`, and `can_capture_screenshots` all `true`. The `blockers` array should be empty. `can_capture_screenshots` means a route was detected, not that a test capture succeeded.
+   Aim for `can_register_mcp_tools`, `can_build_accessibility_tree`, `can_send_development_input`, and `can_query_windows` all `true`, with an empty `blockers` array. Doctor lists detected screenshot routes in `capabilities.screenshot`, but does not take a screenshot or request consent. Detected routes are always `screenshot_capture_status: "unverified"` and `can_capture_screenshots: false` in a doctor report. `get_app_state` records the result of its requested raw capture as `verified` or `failed`; only `verified` sets `can_capture_screenshots: true` in that response. If no route is detected, the status is `unavailable`. An unverified capture is a warning, not an installation blocker.
 
 2. **If `accessibility.at_spi_bus.ok = false`** — run `computer-use-linux setup` (or call the `setup_accessibility` MCP tool). This sets:
    - `org.gnome.desktop.interface toolkit-accessibility true`
@@ -393,7 +395,7 @@ Spawn the binary with `["mcp"]` as the argv tail. It speaks JSON-RPC over stdio
 
 3. **If `windowing.can_list_windows = false`** — inspect `doctor.windowing.backends`. On GNOME Wayland, run `computer-use-linux setup-window-targeting` (or call `setup_window_targeting`) to install the bundled `computer-use-linux@avifenesh.dev` Shell extension, then log out and back in so GNOME Shell loads it. On KDE, Hyprland, niri, i3, COSMIC, or generic X11, install or expose the matching compositor tool/helper shown in the backend details.
 
-4. **Grant the screencast portal on first screenshot.** The first time `get_app_state` or any screenshot subcommand runs, GNOME will pop a portal dialog asking to share the screen. Accept once and tick "remember" to make it sticky for the session.
+4. **Verify screenshot capture.** Call `get_app_state` or run `computer-use-linux screenshot`. The Screenshot portal may request consent for the caller's app ID. On GNOME, that dialog can be rejected when the app ID does not match the focused app. A detected portal interface alone does not prove capture permission. Inspect the full backend error and the desktop portal logs if capture fails; `gnome-screenshot` is an optional fallback when GNOME Shell or portal calls are denied.
 
 5. **Confirm compatible ydotool 1.0.3+ and `ydotoold` are available.**
 
@@ -413,10 +415,12 @@ Most setups need none of these — `doctor` and the installers pick sensible def
 | --- | --- |
 | `COMPUTER_USE_LINUX_NOTIFY_ON_COMPLETE` | Set exactly to `1` to expose the optional `complete_interaction` notification tool. Requires `notify-send` and a desktop notification service; disabled by default. |
 | `COMPUTER_USE_LINUX_COSMIC_HELPER` | Path to the `computer-use-linux-cosmic` helper when it isn't next to the binary or on `PATH`. |
-| `CU_DISABLE_ABS_POINTER` | Disable the uinput absolute pointer and click through `ydotool` instead for setups where the abs-pointer device misbehaves. |
-| `COMPUTER_USE_LINUX_FORCE_PORTAL_POINTER` / `…_KEYBOARD` | Always route pointer / keyboard through the RemoteDesktop portal on Wayland, skipping auto-detection. |
+| `CU_DISABLE_ABS_POINTER` | Disable the uinput absolute pointer. Wayland coordinate actions then need the RemoteDesktop portal; they refuse input rather than use ydotool's relative-motion approximation. Native X11 fallback is unchanged. |
+| `COMPUTER_USE_LINUX_FORCE_PORTAL_POINTER` / `…_KEYBOARD` | Prefer the RemoteDesktop portal on Wayland, skipping auto-detection. Pointer forcing skips the absolute uinput backend. Forced ydotool or XTEST keyboard overrides take precedence; KDE literal text keeps its clipboard route. Portal startup and text conversion failures return errors without replaying through ydotool. |
+| `COMPUTER_USE_LINUX_PORTAL_SCROLL_INVERT` | Set to `1` to reverse vertical scrolling through the RemoteDesktop portal. Defaults to normal direction on both GNOME and KDE Plasma; horizontal direction is unchanged. |
 | `COMPUTER_USE_LINUX_PERSIST_REMOTE_DESKTOP` | Set exactly to `1` to ask the RemoteDesktop portal to remember pointer and keyboard grants across processes. The first dialog still appears (on GNOME the remember box starts checked). Later processes reuse the single-use restore token from `Start`, stored mode `0600` under `$XDG_STATE_HOME/computer-use-linux/` (or `~/.local/state/computer-use-linux/`). Pointer and keyboard tokens are separate. Needs interface version 2. Unset, every new process is prompted. No effect when input is not using the portal. |
-| `COMPUTER_USE_LINUX_FORCE_YDOTOOL_POINTER` / `…_KEYBOARD` | Always route pointer / keyboard through `ydotool`, skipping the portal and KDE clipboard paths; pointer forcing also skips native-X11 `xdotool` coordinate clicks and scrolls. |
+| `COMPUTER_USE_LINUX_FORCE_YDOTOOL_POINTER` / `…_KEYBOARD` | Always route pointer / keyboard through `ydotool`, skipping the portal and KDE clipboard paths; pointer forcing also skips the absolute uinput backend and native-X11 `xdotool` coordinate clicks and scrolls. Coordinate pointer actions on Wayland then refuse input because ydotool cannot position them accurately; scrolling at the current pointer remains available. |
+| `YDOTOOL_SOCKET` | Explicit ydotool socket path. When unset, only an owner-only `.ydotool_socket` in the user's private runtime directory is accepted; the legacy shared `/tmp/.ydotool_socket` is never selected automatically. Setting this variable is an operator trust override for custom layouts. |
 | `COMPUTER_USE_LINUX_FORCE_XDOTOOL_KEYBOARD` | Prefer `xdotool`/XTEST keyboard input when `DISPLAY` is available. `COMPUTER_USE_LINUX_FORCE_YDOTOOL_KEYBOARD=1` takes precedence. |
 | `COMPUTER_USE_LINUX_XDOTOOL_TYPE_DELAY_MS` | Per-character delay for `xdotool type` in milliseconds (default `12`). `0` is faster but can deliver characters out of order on some X servers. |
 | `COMPUTER_USE_LINUX_SCREENSHOT_BACKEND` | Force a single screenshot backend, skipping the fallback chain. Accepts `gnome-shell`, `portal`, `x11`, or `gnome-screenshot`. `x11` works only on a native X11 session. Pin `gnome-screenshot` for background/systemd contexts where the GNOME Shell and portal DBus paths are denied. |
@@ -432,7 +436,7 @@ files.
 
 | Variable | Effect |
 | --- | --- |
-| `COMPUTER_USE_LINUX_BIN` | Run this binary instead of the one bundled by the npm package. |
+| `COMPUTER_USE_LINUX_BIN` | Run this absolute binary path instead of the one bundled by the npm package. Relative paths are ignored. |
 | `COMPUTER_USE_LINUX_DOWNLOAD_BASE` | Override the GitHub release base URL the installer downloads from (mirrors, air-gapped hosts). |
 | `COMPUTER_USE_LINUX_SKIP_DOWNLOAD=1` | Skip the post-install binary download entirely. |
 | `COMPUTER_USE_LINUX_LOCAL_BINARY` / `…_LOCAL_COSMIC_HELPER` | Install from a local build instead of downloading (used by CI and local testing). |
@@ -443,8 +447,9 @@ files.
 - **DBus where desktops expose it** — [`zbus`](https://crates.io/crates/zbus) for portal calls (`org.freedesktop.portal.Screenshot`, `…RemoteDesktop`, `…ScreenCast`), GNOME Shell screenshots (`org.gnome.Shell.Screenshot`), the bundled GNOME extension's `dev.avifenesh.ComputerUseLinux.WindowControl` service, and temporary KWin scripting.
 - **MCP transport** — [`rmcp`](https://crates.io/crates/rmcp) with the `transport-io` feature; stdio framing, no network.
 - **Input fallback** — on X11, keyboard input prefers `xdotool`/XTEST and falls back only when xdotool cannot launch. On Wayland, literal text uses `wtype` when installed and the remote-desktop portal is unavailable; `wtype` supports Unicode through the virtual-keyboard protocol on compatible compositors such as Hyprland/wlroots. If wtype is unavailable, the binary falls back to a compatible ydotool 1.0.3+ CLI and `ydotoold` socket. A launched wtype failure is returned without replaying the text. `install.sh` can configure `ydotoold`; the `setup` command only enables the GNOME AT-SPI bridge.
+- **Wayland coordinate input** — coordinate clicks, drags, and targeted scrolls require the absolute uinput pointer or an approved RemoteDesktop portal session. Targeted scroll positions through uinput before sending only wheel events through ydotool. If accurate positioning is unavailable, the call returns `ok: false` before sending coordinate input. The absolute pointer still requires a successful full-desktop capture when first created; an existing device does not need another capture. Scrolling without a point or window/element target keeps using the current pointer position.
 - **Native X11 coordinate clicks** — eligible native X11 sessions use one supervised `xdotool mousemove -- X Y click --repeat N BUTTON` command for left, middle, and right clicks; ydotool is used only when xdotool cannot launch, while a launched nonzero xdotool command is reported as an error without replay. `COMPUTER_USE_LINUX_FORCE_YDOTOOL_POINTER=1` skips this xdotool path.
-- **Native X11 scroll.** The same sessions send one `xdotool` command, `mousemove -- X Y click --delay 12 --repeat N BUTTON` when a point is set, or `click` alone when it is not. Buttons are 4 up, 5 down, 6 left, and 7 right, and `N` is the same notch count ydotool would pass to `mousemove --wheel` (five per page). ydotool's absolute move warps through (0, 0); GTK 3 then drops the single following wheel event because re-entry resets its XI2 scroll valuators. XTEST has no scroll valuators, so GTK takes the button path. A missing xdotool falls back to ydotool; a launched nonzero xdotool command does not. `COMPUTER_USE_LINUX_FORCE_YDOTOOL_POINTER=1` skips this path. Wayland portal scroll is unchanged.
+- **Native X11 scroll.** The same sessions send one `xdotool` command, `mousemove -- X Y click --delay 12 --repeat N BUTTON` when a point is set, or `click` alone when it is not. Buttons are 4 up, 5 down, 6 left, and 7 right, and `N` is the same notch count ydotool would pass to `mousemove --wheel` (five per page). ydotool's absolute move warps through (0, 0); GTK 3 then drops the single following wheel event because re-entry resets its XI2 scroll valuators. XTEST has no scroll valuators, so GTK takes the button path. A missing xdotool falls back to ydotool; a launched nonzero xdotool command does not. `COMPUTER_USE_LINUX_FORCE_YDOTOOL_POINTER=1` skips this path.
 - **Native X11 transport.** Native X11 queries (window origins, root screenshots, `doctor`) connect and read replies under one shared 2-second deadline enforced in the transport itself, including the handshake and every reply. A stalled X server closes the query connection instead of leaving a blocked worker behind. Unix sockets, literal IP addresses, and `localhost` need no resolver. A remote hostname in `DISPLAY` needs `getent ahosts` for bounded name resolution; if it is missing or fails, the X11 route is reported as unavailable.
 - **Window registry** — `list_windows`, `focused_window`, `activate_window`, `press_key`, and `type_text` share a backend registry. It tries GNOME extension, GNOME Introspect, COSMIC helper, KWin scripting, Hyprland `hyprctl`, the niri IPC socket, i3 IPC, and generic X11/EWMH in that order, skipping empty or failed backends so another compositor backend can answer.
 - **niri backend** — prefers `niri msg`, falling back to direct JSON IPC over the same session socket. `is_minimized` maps to `hidden`. Bounds use `layout.window_size` (or `tile_size`) and, when available, the tile position plus the window's offset and the output's logical origin. Uniform output scaling converts these to device pixels; unknown or mixed scaling omits bounds. Missing window positions stay `null`, so listing and focusing still work without enabling coordinate targeting. An accepted focus action is verified by querying the focused window again.
@@ -457,7 +462,7 @@ files.
 Computer-use tooling is, by definition, a privilege-escalation surface. The threat model:
 
 - **`ydotoold` runs as a per-user service** with read/write access to `/dev/uinput`. `install.sh` automates this for systemd user sessions and prints manual supervisor guidance elsewhere. Any process that can connect to its socket (`/run/user/$UID/.ydotool_socket`, mode `0600` by default) can synthesize arbitrary input — keypresses, clicks, anything. Keep the socket in the user runtime dir (the default), not in `/tmp` or any world-readable location. Do not run `ydotoold` as root or as a system service.
-- **The screencast portal asks for permission once per session.** Granting it lets the calling MCP host capture the screen for the rest of the session. If you don't want that, decline the portal dialog and use `get_app_state` with `include_screenshot: false`.
+- **Screenshot consent depends on the portal and caller's app ID.** A saved permission can apply to multiple processes with that identity. Doctor only detects the available routes and does not request consent. Use `get_app_state` with `include_screenshot: false` to skip capture.
 - **Persisted remote control is opt-in.** `COMPUTER_USE_LINUX_PERSIST_REMOTE_DESKTOP=1` stores the portal's single-use restore token in the user state directory, mode `0600`. A same-user process that can read that file can restore remote control without a new prompt until the desktop revokes the grant. Leave the variable unset to keep a prompt on every new process.
 - **AT-SPI exposes window contents to any client on your session bus.** Enabling the AT-SPI bridge (`setup_accessibility`) is a prerequisite for this binary; it's also what screen readers use, and it shares the same trust boundary.
 - **The GNOME Shell extension** is loaded only into your user's GNOME Shell, runs in the Shell's JS sandbox, and exposes a single DBus interface on the user session bus. It does not request any extra permissions.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-sh/computer-use-linux",
-  "version": "0.7.9",
+  "version": "0.7.11",
   "description": "Linux desktop-control MCP server: AT-SPI accessibility trees, Wayland/X11 input, screenshots, and compositor window targeting.",
   "license": "MIT",
   "type": "commonjs",

package/pi/extension/generated-tools.ts

@@ -7,9 +7,9 @@ export interface GeneratedMcpToolDefinition {
 	annotations: Record<string, unknown>;
 }
 
-export const GENERATED_SERVER_VERSION = "0.7.9";
-export const GENERATED_TOOL_CATALOG_HASH = "24c86d5a758f000674ea2a44d843779d7af28f75d57ce8c401bb01215a61d9fc";
-export const GENERATED_SHELL_TOOL_CATALOG_HASH = "08ebd9d8ed7177921c880a99ca5ce13ab1fcad6c88bec61dff93019a84fabcd2";
+export const GENERATED_SERVER_VERSION = "0.7.11";
+export const GENERATED_TOOL_CATALOG_HASH = "666f4649084b7c1a240e6a0eacc01a55379b64a579355f50071211437e91229c";
+export const GENERATED_SHELL_TOOL_CATALOG_HASH = "554322e70886f5c1e1a3ad06869c5be91c140103f71350ad635160e128c1563d";
 export const GENERATED_MCP_TOOLS =
 [
   {
@@ -1030,6 +1030,8 @@ export const GENERATED_MCP_TOOLS =
         "pages": {
           "default": null,
           "format": "double",
+          "maximum": 100,
+          "minimum": -100,
           "type": [
             "number",
             "null"

package/pi/extension/index.ts

@@ -22,7 +22,7 @@ import {
 } from "node:fs";
 import { createRequire } from "node:module";
 import { homedir } from "node:os";
-import { delimiter, join } from "node:path";
+import { delimiter, isAbsolute, join } from "node:path";
 import { Type, type TSchema } from "typebox";
 import {
 	GENERATED_MCP_TOOLS,
@@ -47,6 +47,7 @@ const DEFAULT_TOOLS = [
 const MAX_RESULT_TEXT_CHARS = 200_000;
 const MAX_RESULT_IMAGE_BYTES = 2 * 1024 * 1024;
 const MAX_RESULT_IMAGES = 4;
+const SAFE_CHILD_PATH = ["/usr/local/bin", "/usr/bin", "/bin"].join(delimiter);
 const TRUNCATION_NOTICE =
 	"[Result truncated by the Pi extension. Request a smaller/bounded result.]";
 const SHELL_ENABLED = process.env.COMPUTER_USE_LINUX_ENABLE_SHELL === "1";
@@ -164,16 +165,23 @@ function executable(path: string): boolean {
 	}
 }
 
+export function sanitizeExecutablePath(pathValue: string | undefined): string {
+	return (pathValue ?? "")
+		.split(delimiter)
+		.filter((dir) => dir.length > 0 && isAbsolute(dir))
+		.join(delimiter);
+}
+
 /**
- * First executable `name` in a PATH-style list, or `null`. Empty segments are
- * skipped rather than read as the current directory.
+ * First executable `name` in a PATH-style list, or `null`. Empty and relative
+ * segments are skipped rather than read relative to the current directory.
  */
 export function findExecutableOnPath(
 	pathValue: string | undefined,
 	name: string,
 	isExecutable: (path: string) => boolean = executable,
 ): string | null {
-	for (const dir of (pathValue ?? "").split(delimiter)) {
+	for (const dir of sanitizeExecutablePath(pathValue).split(delimiter)) {
 		if (!dir) continue;
 		const candidate = join(dir, name);
 		if (isExecutable(candidate)) return candidate;
@@ -228,19 +236,24 @@ function runtimeEnvironment(): Record<string, string> {
 		"COMPUTER_USE_LINUX_SCREENSHOT_BACKEND",
 		"CU_DISABLE_ABS_POINTER",
 	]);
-	return Object.fromEntries(
+	const env = Object.fromEntries(
 		Object.entries(process.env).filter(
 			(entry): entry is [string, string] =>
 				typeof entry[1] === "string" &&
 				(allowed.has(entry[0]) || entry[0].startsWith("LC_")),
 		),
 	);
+	const sanitizedPath = sanitizeExecutablePath(env.PATH);
+	env.PATH = sanitizedPath || SAFE_CHILD_PATH;
+	return env;
 }
 
 function defaultFindBinary(): BinaryLaunch | null {
 	const env = runtimeEnvironment();
 	const override = process.env.COMPUTER_USE_LINUX_BIN?.trim();
-	if (override && executable(override)) {
+	// Relative overrides would be resolved from Pi's potentially untrusted
+	// project directory. Ignore them and continue with bundled/global discovery.
+	if (override && isAbsolute(override) && executable(override)) {
 		return { binaryPath: override, env };
 	}
 

package/skills/computer-use-linux/SKILL.md

@@ -194,7 +194,10 @@ Ready output should have:
 - `can_build_accessibility_tree: true`
 - `can_query_windows: true`
 - `can_send_development_input: true`
-- `can_capture_screenshots: true`
+- `screenshot_capture_status: "unverified"`
+- `can_capture_screenshots: false`
 - `blockers: []`
 
+Doctor detects screenshot routes without capturing or requesting consent. Treat unverified capture as a warning. Call `get_app_state` with `include_screenshot: true` to verify it: a successful raw capture reports `screenshot_capture_status: "verified"` and `can_capture_screenshots: true`; a failure reports `failed` and keeps the boolean false. Inspect `screenshot_error` for the full backend cause.
+
 Then test with your agent by calling the `doctor` tool or asking the agent to list desktop windows.

package/skills/computer-use-linux/references/pi-setup.md

@@ -137,5 +137,8 @@ Ready output has:
 - `can_build_accessibility_tree: true`
 - `can_query_windows: true`
 - `can_send_development_input: true`
-- `can_capture_screenshots: true`
+- `screenshot_capture_status: "unverified"`
+- `can_capture_screenshots: false`
 - `blockers: []`
+
+Doctor detects screenshot routes without capturing or requesting consent. Treat unverified capture as a warning. Call `get_app_state` with `include_screenshot: true` to verify it: a successful raw capture reports `screenshot_capture_status: "verified"` and `can_capture_screenshots: true`; a failure reports `failed` and keeps the boolean false. Inspect `screenshot_error` for the full backend cause.