@agent-sh/computer-use-linux 0.7.8 → 0.7.10

package/README.md

@@ -9,7 +9,7 @@
   </p>
 </div>
 
-> ⚡ Running this agent 24/7? [**tiyuvta inference**](https://inference.tiyuvta.ai) — hosted LLM inference built for always-on agents, OpenAI/Anthropic-compatible APIs.
+> Running open models for your company? [**Tiyuvta**](https://tiyuvta.ai/services/) helps with model choice, deployment and optimization, and fine-tuning on your hardware or cloud account.
 
 `computer-use-linux` reads accessibility trees, takes screenshots, and drives clicks, scrolls, and keystrokes across GNOME, KDE/KWin, Hyprland, niri, i3, and COSMIC — Wayland-first, X11 best-effort.
 
@@ -417,6 +417,7 @@ Most setups need none of these — `doctor` and the installers pick sensible def
 | `COMPUTER_USE_LINUX_FORCE_PORTAL_POINTER` / `…_KEYBOARD` | Always route pointer / keyboard through the RemoteDesktop portal on Wayland, skipping auto-detection. |
 | `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. |
+| `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 +433,7 @@ 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). |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-sh/computer-use-linux",
-  "version": "0.7.8",
+  "version": "0.7.10",
   "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 = "0.7.8";
-export const GENERATED_TOOL_CATALOG_HASH = "24c86d5a758f000674ea2a44d843779d7af28f75d57ce8c401bb01215a61d9fc";
-export const GENERATED_SHELL_TOOL_CATALOG_HASH = "08ebd9d8ed7177921c880a99ca5ce13ab1fcad6c88bec61dff93019a84fabcd2";
+export const GENERATED_SERVER_VERSION = "0.7.10";
+export const GENERATED_TOOL_CATALOG_HASH = "b65768d5f3112b43fcde1344223f5354557c871969987a0a49b58ebe5605eb70";
+export const GENERATED_SHELL_TOOL_CATALOG_HASH = "984f033a6045848f85209b7e74bf881f7810bcfe1fce820e2c3967fee52a6714";
 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 };
 	}