@swmansion/argent 0.30.2-next.5 → 0.30.2-next.7

package/dist/cli-cmds.mjs

@@ -35577,7 +35577,7 @@ var _CI_VENDOR_COUNT_FOR_TEST = vendors_default.length;
 var SESSION_ID2 = randomUUID5();
 function readCliVersion() {
   if (true) {
-    return "0.30.2-next.5";
+    return "0.30.2-next.7";
   }
   return "0.0.0";
 }

package/dist/installer.mjs

@@ -16899,7 +16899,7 @@ var _CI_VENDOR_COUNT_FOR_TEST = vendors_default.length;
 var SESSION_ID = randomUUID4();
 function readCliVersion() {
   if (true) {
-    return "0.30.2-next.5";
+    return "0.30.2-next.7";
   }
   return "0.0.0";
 }

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/dist/tool-server.cjs

@@ -100944,7 +100944,7 @@ var _CI_VENDOR_COUNT_FOR_TEST = vendors_default.length;
 var SESSION_ID = (0, import_node_crypto3.randomUUID)();
 function readCliVersion() {
   if (true) {
-    return "0.30.2-next.5";
+    return "0.30.2-next.7";
   }
   return "0.0.0";
 }
@@ -139501,7 +139501,7 @@ Returns { launched, bundleId, note? }. Fails if the app is not installed on the
 For Chromium, the app is already running behind a CDP port; this call simply refreshes the cached viewport and acknowledges the bundleId tag. To change the visible route, use \`open-url\`.
 On Vega (Fire TV), pass the interactive component app id from manifest.toml (e.g. com.example.app.main) as bundleId.
 
-Common iOS bundle ids: com.apple.MobileSMS, com.apple.mobilesafari, com.apple.Preferences, com.apple.Maps, com.apple.camera, com.apple.Photos, com.apple.mobilemail, com.apple.mobilenotes, com.apple.MobileAddressBook
+Common iOS bundle ids: com.apple.MobileSMS, com.apple.mobilesafari, com.apple.Preferences, com.apple.Maps, com.apple.mobileslideshow (Photos), com.apple.MobileAddressBook
 Common Android packages: com.android.settings, com.android.chrome, com.google.android.apps.maps, com.google.android.gm, com.android.vending, com.google.android.dialer, com.google.android.apps.messaging`,
     alwaysLoad: true,
     searchHint: "open start app bundle id package simulator emulator chromium vega launch tvos apple tv fire tv",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@swmansion/argent",
-  "version": "0.30.2-next.5",
+  "version": "0.30.2-next.7",
   "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-device-interact/SKILL.md

@@ -36,7 +36,7 @@ Use `list-devices` to get a target id. Results are tagged with `platform` (`ios`
 { "udid": "<UDID>", "bundleId": "com.apple.MobileSMS" }
 ```
 
-Common IDs: `com.apple.MobileSMS` (Messages), `com.apple.mobilesafari` (Safari), `com.apple.Preferences` (Settings), `com.apple.Maps`, `com.apple.Photos`, `com.apple.mobilemail`, `com.apple.mobilenotes`, `com.apple.MobileAddressBook` (Contacts)
+Common IDs: `com.apple.MobileSMS` (Messages), `com.apple.mobilesafari` (Safari), `com.apple.Preferences` (Settings), `com.apple.Maps`, `com.apple.mobileslideshow` (Photos), `com.apple.MobileAddressBook` (Contacts)
 
 ### open-url: by URL scheme
 
@@ -169,6 +169,8 @@ Values: `home`, `back`, `power`, `volumeUp`, `volumeDown`, `appSwitch`, `actionB
 
 One call does one action. `text` and `key` are mutually exclusive, and a call that carries both is rejected with nothing typed. To type and then submit, send two `keyboard` steps in one `run-sequence` (§ 8): `{ "text": "search query" }`, then `{ "key": "enter" }`. Two separate calls do the same work, but cost an extra round-trip.
 
+**React Native: the first tap after typing may only close the keyboard.** Inside a scroll view with the default `keyboardShouldPersistTaps="never"`, React Native uses a tap outside the focused field to dismiss the keyboard and does not pass it on (with `"handled"` or `"always"` the tap reaches the button), so a button tapped right after typing may need a second tap; check the returned tree. When the field submits on return, `{ "key": "enter" }` avoids the extra tap.
+
 Special keys: `enter`, `escape`, `backspace`, `tab`, `space`, `arrow-up`, `arrow-down`, `arrow-left`, `arrow-right`, `f1`–`f12`. Optional: `"delayMs": 100` between keystrokes (default 50ms); applies to the iOS simulator and Chromium; it is ignored on Android phones/tablets (typed via `adb input text`, no per-key cadence), on Vega, and on TV targets.
 
 **Typing secrets.** To enter a credential without its plaintext ever entering your context, transcript, or logs, use a secret placeholder in `text` (works in `keyboard`, `paste`, `run-sequence` keyboard steps, and e2e `type` steps):

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
 ```
 
 ---