software-mansion · filip131311 · Jun 12, 2026 · May 20, 2026 · May 20, 2026 · May 20, 2026
diff --git a/.github/workflows/wayland-e2e.yml b/.github/workflows/wayland-e2e.yml
@@ -232,7 +232,10 @@ jobs:
           curl -sS -m 60 -X POST http://127.0.0.1:3033/tools/screenshot \
             -H 'Content-Type: application/json' \
             -d '{"udid":"emulator-5554"}' > /tmp/shot.json
-          PATH_PNG=$(python3 -c "import json,sys;print(json.load(open('/tmp/shot.json'))['data']['path'])")
+          # The screenshot tool returns an ArtifactHandle ({ image: { hostPath, ... } })
+          # since the remote-artifacts change; the job runs co-located with the
+          # tool-server so hostPath is directly readable.
+          PATH_PNG=$(python3 -c "import json,sys;print(json.load(open('/tmp/shot.json'))['data']['image']['hostPath'])")
           cp "$PATH_PNG" /tmp/wayland-cold-boot.png
           SZ=$(stat -c%s /tmp/wayland-cold-boot.png)
           echo "size=${SZ}B"

diff --git a/packages/argent-mcp/src/auto-screenshot.ts b/packages/argent-mcp/src/auto-screenshot.ts
@@ -11,6 +11,8 @@ import { isFlagEnabled, type FlagsPathOptions } from "@argent/configuration-core
 export const AUTO_SCREENSHOT_TOOLS = new Set([
   "gesture-tap",
   "gesture-swipe",
+  "gesture-scroll",
+  "gesture-drag",
   "gesture-custom",
   "gesture-pinch",
   "gesture-rotate",
@@ -33,6 +35,8 @@ export const AUTO_SCREENSHOT_DELAY_MS_BY_TOOL: Record<string, number> = {
   "restart-app": 3000,
   "open-url": 2000,
   "gesture-swipe": 1500,
+  "gesture-scroll": 1500,
+  "gesture-drag": 1500,
   "gesture-custom": 1500,
   "gesture-tap": 1500,
   "gesture-pinch": 1500,

diff --git a/packages/argent-mcp/src/mcp-server.ts b/packages/argent-mcp/src/mcp-server.ts
@@ -208,7 +208,7 @@ export async function startMcpServer(options: StartMcpServerOptions): Promise<vo
     {
       capabilities: { tools: {} },
       instructions:
-        "Argent — iOS Simulator and Android Emulator control for interacting, testing, profiling and debugging mobile applications. " +
+        "Argent — iOS Simulator, Android Emulator, and Electron app control for interacting, testing, profiling and debugging mobile and Electron applications. " +
         "Always use discovery tools (describe / debugger-component-tree / screenshot) before tapping — never guess coordinates. " +
         "On session end: call stop-all-simulator-servers and perform any necessary cleanup. " +
         "Full guidance is in the argent rule loaded from .claude/rules/argent.md.",

diff --git a/packages/registry/src/types.ts b/packages/registry/src/types.ts
@@ -86,9 +86,9 @@ export interface ToolContext extends InvokeToolOptions {
 
 // ── Device + Capability Types ──
 
-export type Platform = "ios" | "android";
+export type Platform = "ios" | "android" | "electron";
 
-export type DeviceKind = "simulator" | "emulator" | "device" | "unknown";
+export type DeviceKind = "simulator" | "emulator" | "device" | "app" | "unknown";
 
 /**
  * Universal device handle. Platform-aware tools resolve a `udid` parameter into
@@ -119,6 +119,9 @@ export interface ToolCapability {
     device?: boolean;
     unknown?: boolean;
   };
+  electron?: {
+    app?: boolean;
+  };
   /** Optional refiner. Returns true if this device is supported. */
   supports?: (device: DeviceInfo) => boolean;
 }

diff --git a/packages/skills/rules/argent.md b/packages/skills/rules/argent.md
@@ -4,7 +4,7 @@ alwaysApply: true
 ---
 
 <description>
-Argent MCP tools are available in this project for iOS simulator and Android emulator control. Argent MCP tools are the preferred form of interaction with the application.
+Argent MCP tools are available in this project for iOS simulator, Android emulator, and Electron desktop app control. Argent MCP tools are the preferred form of interaction with the application.
 Running MCP server and managing the Argent toolkit utilises `argent` command - if asked use `argent --help` for reference.
 To check current version of MCP server run `argent --version` command.
 
@@ -17,6 +17,7 @@ Use cases:
 - Any request to execute manual QA, UI QA, or visual behavior validation for a mobile app
 - Running, debugging, or testing a React Native app (iOS or Android)
 - Profiling performance or diagnosing re-renders in a React Native app (iOS or Android)
+- Running, debugging, or testing an Electron desktop app (boot with `boot-device` + `electronAppPath`; on Electron scroll with `gesture-scroll` and drag with `gesture-drag` — `gesture-swipe` is touch-only)
   </description>
 
 <tapping_rule>
@@ -44,7 +45,7 @@ Before booting, running, or interacting with any app, call `list-devices` first
 Decision order:
 
 1. **Explicit user intent** - choose the user named platform or device. Look for words "simulator" and "emulator".
-2. **Prefer a running device.** iOS simulators - state `Booted` and Android devices - `state: "device"` come first in `list-devices`.
+2. **Prefer a running device.** iOS simulators - state `Booted` and Android devices - `state: "device"` come first in `list-devices`; Electron apps appear as `platform: "electron"`, `state: "Running"`.
 3. **Single-platform project:** (per `argent-environment-inspector` flags `is_native_ios`/`is_native_android`, or RN with only one platform configured) → boot that platform.
    </device_selection_rule>
 

diff --git a/packages/skills/skills/argent-device-interact/SKILL.md b/packages/skills/skills/argent-device-interact/SKILL.md
@@ -1,27 +1,27 @@
 ---
 name: argent-device-interact
-description: Interact with an iOS simulator or Android emulator using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, or checking visible app state after interactions.
+description: Interact with an iOS simulator, Android emulator, or Electron app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, or checking visible app state after interactions.
 ---
 
 ## Unified tool surface
 
-All interaction tools below accept a `udid` parameter and auto-dispatch iOS vs Android based on its shape (UUID → iOS simulator, anything else → Android adb serial). You use the same tool names on both platforms.
+All interaction tools below accept a `udid` parameter and auto-dispatch iOS vs Android based on its shape (UUID → iOS simulator, `electron-cdp-<port>` → Electron app, anything else → Android adb serial). You use the same tool names on both platforms.
 
 For platform-specific caveats (Metro `adb reverse`, locked-screen describe errors, etc.), see § 9 Platform-specific notes at the bottom.
 
 ## 1. Before You Start
 
 If you delegate simulator tasks to sub-agents, make sure they have MCP permissions.
 
-Use `list-devices` to get a target id. Results are tagged with `platform` (`ios` or `android`); booted/ready devices come first. Pick the first entry that matches the platform you need — if none are ready, call `boot-device` with `udid` (iOS) or `avdName` (Android). See `argent-ios-simulator-setup` / `argent-android-emulator-setup` for full setup flow.
+Use `list-devices` to get a target id. Results are tagged with `platform` (`ios`, `android`, or `electron`); booted/ready devices come first. Pick the first entry that matches the platform you need — if none are ready, call `boot-device` with `udid` (iOS), `avdName` (Android), or `electronAppPath` (Electron). See `argent-ios-simulator-setup` / `argent-android-emulator-setup` for full setup flow.
 
 **Load tool schemas before first use.** Gesture tools (`gesture-tap`, `gesture-swipe`, `gesture-pinch`, `gesture-rotate`, `gesture-custom`) may be deferred — their parameter schemas are not loaded until fetched. Always use ToolSearch to load the schemas of all gesture tools you plan to use **before** calling any of them. If you skip this step, parameters may be coerced to strings instead of numbers, causing validation errors.
 
 ## 2. Best Practices
 
 1. **Always refer to tapping_rule** from your argent.md rule before tapping.
 2. Before performing interactions, consider whether they can be **dispatched sequentially** - more on that in `run-sequence`.
-3. **Use `gesture-swipe` for lists/scrolling**, not `gesture-custom`, unless you need non-linear movement. Consider whether you need multiple swipes, if yes - use `run-sequence`.
+3. **Use `gesture-swipe` for lists/scrolling**, not `gesture-custom`, unless you need non-linear movement. On Electron use `gesture-scroll` instead — `gesture-swipe` is touch-only. Consider whether you need multiple swipes, if yes - use `run-sequence`.
 4. **Tap a text field before typing** — on iOS try `paste` first then fall back to `keyboard`; on Android use `keyboard` directly (`paste` is iOS-only).
 5. **Coordinates are normalized** — always 0.0–1.0, not pixels.
 6. **For app navigation, prefer `describe` first.** It works on any screen without app restart. Do not navigate from screenshots on regular in-app screens unless `describe` failed to expose a reliable target. Use `native-describe-screen` only when you need app-scoped UIKit properties.
@@ -48,35 +48,37 @@ Common schemes: `messages://`, `settings://`, `maps://?q=<query>`, `tel://<numbe
 
 ## 4. Choosing the Right Tool
 
-| Action           | Tool             | Notes                                                                  |
-| ---------------- | ---------------- | ---------------------------------------------------------------------- |
-| Multiple actions | `run-sequence`   | Batch steps in one call (no intermediate screenshots)                  |
-| Open an app      | `launch-app`     | **Always — never tap home-screen icons**                               |
-| Restart an app   | `restart-app`    | Terminate and relaunch by bundle ID                                    |
-| Open URL/scheme  | `open-url`       | Web pages, deep links, URL schemes                                     |
-| Single tap       | `gesture-tap`    | Buttons, links, checkboxes                                             |
-| Scroll/swipe     | `gesture-swipe`  | Straight-line scroll or swipe                                          |
-| Long press       | `gesture-custom` | Context menus, drag start                                              |
-| Drag & drop      | `gesture-custom` | Complex drag interactions                                              |
-| Pinch/zoom       | `gesture-pinch`  | Two-finger pinch with auto-interpolation                               |
-| Rotation         | `gesture-rotate` | Two-finger rotation with auto-interpolation                            |
-| Custom gesture   | `gesture-custom` | Arbitrary touch sequences, optional interpolation                      |
-| Hardware key     | `button`         | Home, back, power, volume, appSwitch, actionButton                     |
-| Type text (fast) | `paste`          | iOS only. Form fields — uses clipboard                                 |
-| Type text        | `keyboard`       | iOS+Android. Fallback when paste fails; supports Enter, Escape, arrows |
-| Rotate device    | `rotate`         | Orientation changes                                                    |
+| Action            | Tool             | Notes                                                                  |
+| ----------------- | ---------------- | ---------------------------------------------------------------------- |
+| Multiple actions  | `run-sequence`   | Batch steps in one call (no intermediate screenshots)                  |
+| Open an app       | `launch-app`     | **Always — never tap home-screen icons**                               |
+| Restart an app    | `restart-app`    | Terminate and relaunch by bundle ID                                    |
+| Open URL/scheme   | `open-url`       | Web pages, deep links, URL schemes                                     |
+| Single tap        | `gesture-tap`    | Buttons, links, checkboxes                                             |
+| Scroll/swipe      | `gesture-swipe`  | Straight-line scroll or swipe                                          |
+| Scroll (Electron) | `gesture-scroll` | Wheel-based; deltas are window fractions, positive deltaY = down       |
+| Drag (Electron)   | `gesture-drag`   | Sliders, drag-and-drop, text selection                                 |
+| Long press        | `gesture-custom` | Context menus, drag start                                              |
+| Drag & drop       | `gesture-custom` | Complex drag interactions                                              |
+| Pinch/zoom        | `gesture-pinch`  | Two-finger pinch with auto-interpolation                               |
+| Rotation          | `gesture-rotate` | Two-finger rotation with auto-interpolation                            |
+| Custom gesture    | `gesture-custom` | Arbitrary touch sequences, optional interpolation                      |
+| Hardware key      | `button`         | Home, back, power, volume, appSwitch, actionButton                     |
+| Type text (fast)  | `paste`          | iOS only. Form fields — uses clipboard                                 |
+| Type text         | `keyboard`       | iOS+Android. Fallback when paste fails; supports Enter, Escape, arrows |
+| Rotate device     | `rotate`         | Orientation changes                                                    |
 
 ## 5. Finding Tap Targets
 
 IMPORTANT. When moved to a different screen after an action or do not know the coordinates of component, **always** perform proper discovery first.
 
-| App type                          | Discovery tool            | What it returns                                                                                                                                                                                                               |
-| --------------------------------- | ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Target app discovery              | `describe`                | Accessibility element tree for the current device screen (iOS AX-service or Android uiautomator) with normalized frame coordinates. Works on any app, system dialogs, and Home screen — no app restart or `bundleId` required |
-| React Native                      | `debugger-component-tree` | React component tree with names, text, testID, and (tap: x,y)                                                                                                                                                                 |
-| App-scoped native                 | `native-describe-screen`  | Low-level app-scoped accessibility elements with normalized and raw coordinates; requires `bundleId`                                                                                                                          |
-| Permission / system modal overlay | `describe`                | `describe` detects system dialogs automatically and returns dialog buttons with tap coordinates. Fall back to `screenshot` only if `describe` does not expose the controls                                                    |
-| Final visual fallback             | `screenshot`              | Use only when discovery tools cannot inspect the current UI reliably. Do not derive routine in-app navigation targets from screenshots                                                                                        |
+| App type                          | Discovery tool            | What it returns                                                                                                                                                                                                                                     |
+| --------------------------------- | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Target app discovery              | `describe`                | Accessibility element tree for the current device screen (iOS AX-service, Android uiautomator, or Electron DOM walker) with normalized frame coordinates. Works on any app, system dialogs, and Home screen — no app restart or `bundleId` required |
+| React Native                      | `debugger-component-tree` | React component tree with names, text, testID, and (tap: x,y)                                                                                                                                                                                       |
+| App-scoped native                 | `native-describe-screen`  | Low-level app-scoped accessibility elements with normalized and raw coordinates; requires `bundleId`                                                                                                                                                |
+| Permission / system modal overlay | `describe`                | `describe` detects system dialogs automatically and returns dialog buttons with tap coordinates. Fall back to `screenshot` only if `describe` does not expose the controls                                                                          |
+| Final visual fallback             | `screenshot`              | Use only when discovery tools cannot inspect the current UI reliably. Do not derive routine in-app navigation targets from screenshots                                                                                                              |
 
 Point follow-up native diagnostics after you already have a candidate point: