@swmansion/argent 0.30.2-next.5 → 0.30.2-next.6

package/dist/mcp-server.mjs

@@ -28485,7 +28485,9 @@ var AUTO_SCREENSHOT_TOOLS = /* @__PURE__ */ new Set([
   "restart-app",
   "open-url",
   "describe",
-  "run-sequence"
+  "run-sequence",
+  // A wait is almost always followed by a look at the screen it waited for.
+  "await-ui-element"
 ]);
 var AUTO_SCREENSHOT_DELAY_MS_BY_TOOL = {
   "launch-app": 3e3,
@@ -28506,7 +28508,10 @@ var AUTO_SCREENSHOT_DELAY_MS_BY_TOOL = {
   "fold": 1500,
   "keyboard": 300,
   "paste": 300,
-  "describe": 100
+  "describe": 100,
+  // The wait returns on the first match, often mid-transition; the cap must
+  // leave `await-screen-idle` room to see two identical reads.
+  "await-ui-element": 1500
 };
 var DEFAULT_DELAY_MS = 1400;
 function autoScreenshotEnabled(options) {
@@ -28528,7 +28533,8 @@ var AUTO_DESCRIBE_TOOLS = /* @__PURE__ */ new Set([
   "launch-app",
   "restart-app",
   "open-url",
-  "run-sequence"
+  "run-sequence",
+  "await-ui-element"
 ]);
 function autoDescribeEnabled(options) {
   return !isFlagEnabled("disable-auto-describe", options);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@swmansion/argent",
-  "version": "0.30.2-next.5",
+  "version": "0.30.2-next.6",
   "mcpName": "io.github.software-mansion/argent",
   "description": "MCP server for iOS Simulator and Android Emulator control",
   "license": "Apache-2.0",

package/rules/argent.md

@@ -37,9 +37,9 @@ If argent is ABSENT, treat it as an expected state, not an error to retry. Do no
 
 <tapping_rule>
 <important>**Never** derive tap coordinates from screenshot pixels</important>
-Interaction tools (`gesture-tap`, `gesture-swipe`, `keyboard`, `button`, `launch-app`, `open-url`, `run-sequence`, …) return the screen **after** the action: a screenshot AND the accessibility element tree (`--- Elements after action (describe) ---`, the same format `describe` prints, with normalized 0–1 frames). Take tap coordinates from that tree: the centre of the element's frame (`x + width/2`, `y + height/2`). You do not need a separate discovery call before a tap when the last result already lists the target.
+Interaction tools (`gesture-tap`, `gesture-swipe`, `keyboard`, `button`, `launch-app`, `open-url`, `run-sequence`, `await-ui-element`, …) return the screen **after** the action: a screenshot AND the accessibility element tree (`--- Elements after action (describe) ---`, the same format `describe` prints, with normalized 0–1 frames). Take tap coordinates from that tree: the centre of the element's frame (`x + width/2`, `y + height/2`). You do not need a separate discovery call before a tap when the last result already lists the target.
 
-Call a discovery tool yourself only when you have no fresh tree for the current screen: before the first action on a screen you have not touched yet, after waiting for something to load, or when the last tree did not list your target. Preferred tools are, in order:
+Call a discovery tool yourself only when you have no fresh tree for the current screen: before the first action on a screen you have not touched yet, after waiting for something to load without `await-ui-element`, or when the last tree did not list your target. Preferred tools are, in order:
 
 - `describe` - native app-level components and safely targetable foreground apps (iOS and Android).
 - `native-describe-screen` - accessibility screen description via injected native devtools (iOS only)

package/skills/argent-test-ui-flow/SKILL.md

@@ -98,8 +98,7 @@ Steps:
 ```
 1. gesture-tap { x: 0.5, y: 0.7 } → trigger an action that fetches data
 2. screenshot → loading spinner is showing
-3. await-ui-element { condition: hidden, selector: { text: "Loading" } } → block until the fetch finishes and the spinner disappears
-4. describe / screenshot → verify the fetched content rendered
+3. await-ui-element { condition: hidden, selector: { text: "Loading" } } → block until the fetch finishes and the spinner disappears; its result carries the screenshot and element tree, so verify the fetched content rendered from it
 ```
 
 ---