@swmansion/argent 0.15.1-next.6 → 0.15.1-next.7

package/dist/cli-cmds.mjs

@@ -6324,6 +6324,7 @@ var FAILURE_CODES = {
   CHROMIUM_ELECTRON_EXITED_BEFORE_READY: "CHROMIUM_ELECTRON_EXITED_BEFORE_READY",
   KEYBOARD_KEY_UNSUPPORTED: "KEYBOARD_KEY_UNSUPPORTED",
   KEYBOARD_CHARACTER_UNSUPPORTED: "KEYBOARD_CHARACTER_UNSUPPORTED",
+  SECRET_PLACEHOLDER_UNKNOWN: "SECRET_PLACEHOLDER_UNKNOWN",
   SCREENSHOT_DIFF_INPUT_INVALID: "SCREENSHOT_DIFF_INPUT_INVALID",
   BOOT_DEVICE_TARGET_SELECTION_INVALID: "BOOT_DEVICE_TARGET_SELECTION_INVALID",
   BOOT_IOS_UNSUPPORTED_HOST: "BOOT_IOS_UNSUPPORTED_HOST",

package/dist/installer.mjs

@@ -16231,6 +16231,7 @@ var FAILURE_CODES = {
   CHROMIUM_ELECTRON_EXITED_BEFORE_READY: "CHROMIUM_ELECTRON_EXITED_BEFORE_READY",
   KEYBOARD_KEY_UNSUPPORTED: "KEYBOARD_KEY_UNSUPPORTED",
   KEYBOARD_CHARACTER_UNSUPPORTED: "KEYBOARD_CHARACTER_UNSUPPORTED",
+  SECRET_PLACEHOLDER_UNKNOWN: "SECRET_PLACEHOLDER_UNKNOWN",
   SCREENSHOT_DIFF_INPUT_INVALID: "SCREENSHOT_DIFF_INPUT_INVALID",
   BOOT_DEVICE_TARGET_SELECTION_INVALID: "BOOT_DEVICE_TARGET_SELECTION_INVALID",
   BOOT_IOS_UNSUPPORTED_HOST: "BOOT_IOS_UNSUPPORTED_HOST",

package/dist/mcp-server.mjs

@@ -17750,6 +17750,7 @@ var FAILURE_CODES = {
   CHROMIUM_ELECTRON_EXITED_BEFORE_READY: "CHROMIUM_ELECTRON_EXITED_BEFORE_READY",
   KEYBOARD_KEY_UNSUPPORTED: "KEYBOARD_KEY_UNSUPPORTED",
   KEYBOARD_CHARACTER_UNSUPPORTED: "KEYBOARD_CHARACTER_UNSUPPORTED",
+  SECRET_PLACEHOLDER_UNKNOWN: "SECRET_PLACEHOLDER_UNKNOWN",
   SCREENSHOT_DIFF_INPUT_INVALID: "SCREENSHOT_DIFF_INPUT_INVALID",
   BOOT_DEVICE_TARGET_SELECTION_INVALID: "BOOT_DEVICE_TARGET_SELECTION_INVALID",
   BOOT_IOS_UNSUPPORTED_HOST: "BOOT_IOS_UNSUPPORTED_HOST",
@@ -18981,6 +18982,14 @@ var DEFAULT_DELAY_MS = 1400;
 function autoScreenshotEnabled(options) {
   return !isFlagEnabled("disable-auto-screenshot", options);
 }
+var SECRET_PLACEHOLDER_MARKER = "{{secret:";
+function containsSecretPlaceholder(args) {
+  try {
+    return JSON.stringify(args)?.includes(SECRET_PLACEHOLDER_MARKER) ?? false;
+  } catch {
+    return true;
+  }
+}
 function getUdidFromArgs(args) {
   if (args && typeof args === "object" && "udid" in args && typeof args.udid === "string") {
     return args.udid;
@@ -19209,7 +19218,15 @@ async function startMcpServer(options) {
         content = await toMcpContent(result, outputHint, ctx, params.arguments);
       }
       const udid = getUdidFromArgs(params.arguments);
-      if (autoScreenshotOn && udid && shouldAutoScreenshot(params.name)) {
+      if (autoScreenshotOn && udid && shouldAutoScreenshot(params.name) && containsSecretPlaceholder(params.arguments)) {
+        content = [
+          ...content,
+          {
+            type: "text",
+            text: "Auto-screenshot skipped: the input contains a {{secret:\u2026}} placeholder, and a screenshot of this screen could reveal the typed secret. Submit or navigate away first, then verify the resulting screen as usual."
+          }
+        ];
+      } else if (autoScreenshotOn && udid && shouldAutoScreenshot(params.name)) {
         const maxWaitMs = getAutoScreenshotDelayMs(params.name);
         if (maxWaitMs > 0) {
           try {

package/dist/tool-server.cjs

@@ -404,6 +404,7 @@ var init_failure_codes = __esm({
       CHROMIUM_ELECTRON_EXITED_BEFORE_READY: "CHROMIUM_ELECTRON_EXITED_BEFORE_READY",
       KEYBOARD_KEY_UNSUPPORTED: "KEYBOARD_KEY_UNSUPPORTED",
       KEYBOARD_CHARACTER_UNSUPPORTED: "KEYBOARD_CHARACTER_UNSUPPORTED",
+      SECRET_PLACEHOLDER_UNKNOWN: "SECRET_PLACEHOLDER_UNKNOWN",
       SCREENSHOT_DIFF_INPUT_INVALID: "SCREENSHOT_DIFF_INPUT_INVALID",
       BOOT_DEVICE_TARGET_SELECTION_INVALID: "BOOT_DEVICE_TARGET_SELECTION_INVALID",
       BOOT_IOS_UNSUPPORTED_HOST: "BOOT_IOS_UNSUPPORTED_HOST",
@@ -126687,6 +126688,54 @@ Fails if the device backend is not reachable \u2014 the simulator-server for iOS
 // ../tool-server/src/tools/keyboard/index.ts
 init_zod();
 
+// ../tool-server/src/utils/secrets.ts
+init_src();
+var SECRET_ENV_PREFIX = "ARGENT_SECRET_";
+var SECRET_PLACEHOLDER_MARKER = "{{secret:";
+var PLACEHOLDER_RE = /\{\{secret:([A-Za-z_][A-Za-z0-9_]*)\}\}/g;
+function availableSecretNames(env = process.env) {
+  return Object.keys(env).filter((k) => k.startsWith(SECRET_ENV_PREFIX) && env[k] !== void 0).map((k) => k.slice(SECRET_ENV_PREFIX.length)).sort();
+}
+var REDUNDANT_PREFIX_RE = /^argent_secret_/i;
+function resolveSecretPlaceholders(text, env = process.env) {
+  const secrets = [];
+  const resolved = text.replace(PLACEHOLDER_RE, (placeholder, rawName) => {
+    let name = rawName;
+    let value = env[SECRET_ENV_PREFIX + name];
+    if (value === void 0 && REDUNDANT_PREFIX_RE.test(name)) {
+      name = name.replace(REDUNDANT_PREFIX_RE, "");
+      value = env[SECRET_ENV_PREFIX + name];
+    }
+    if (value === void 0) {
+      const names = availableSecretNames(env);
+      throw new InvalidToolInputError(
+        `Unknown secret "${rawName}" \u2014 no ${SECRET_ENV_PREFIX}${name} environment variable is set on the machine running the tool-server. Available secrets: ${names.length ? names.join(", ") : "(none)"}. To make it available, ask the user to export ${SECRET_ENV_PREFIX}${name} in the tool-server's environment \u2014 never ask the user for the secret value itself.`,
+        {
+          error_code: FAILURE_CODES.SECRET_PLACEHOLDER_UNKNOWN,
+          failure_stage: "secret_placeholder_resolution",
+          error_kind: "validation"
+        }
+      );
+    }
+    if (!secrets.some((s) => s.name === name)) secrets.push({ name, value });
+    return value;
+  });
+  return { text: resolved, secrets };
+}
+function redactSecretsFromError(err, secrets) {
+  const scrub = (s) => secrets.reduce(
+    (acc, { name, value }) => value ? acc.split(value).join(`${SECRET_PLACEHOLDER_MARKER}${name}}}`) : acc,
+    s
+  );
+  if (err instanceof Error) {
+    err.message = scrub(err.message);
+    if (err.stack) err.stack = scrub(err.stack);
+    return err;
+  }
+  if (typeof err === "string") return scrub(err);
+  return err;
+}
+
 // ../tool-server/src/tools/keyboard/simulator-server-keys.ts
 init_src();
 
@@ -127165,7 +127214,9 @@ var zodSchema24 = external_exports.object({
   udid: external_exports.string().describe(
     "Target device id from `list-devices` (iOS UDID, Android serial, Vega serial, or Chromium id)."
   ),
-  text: external_exports.string().optional().describe("Text to type character by character. Handles uppercase and common punctuation."),
+  text: external_exports.string().optional().describe(
+    'Text to type character by character. Handles uppercase and common punctuation. To type a credential without its plaintext ever entering your context, use a secret placeholder: `{{secret:<NAME>}}` types the value of the `ARGENT_SECRET_<NAME>` environment variable set on the machine running the tool-server \u2014 e.g. text: "{{secret:APP_PASSWORD}}" types the value of `ARGENT_SECRET_APP_PASSWORD`. Only env vars with the `ARGENT_SECRET_` prefix are resolvable. Placeholders can be embedded in longer text and are never echoed back resolved. If the secret you need is not set, ask the user to export it as `ARGENT_SECRET_<NAME>` and restart the session \u2014 NEVER ask the user to paste the secret value into the conversation.'
+  ),
   key: external_exports.string().optional().describe(
     "Named key to press: enter, escape, backspace, tab, space, arrow-up, arrow-down, arrow-left, arrow-right, f1\u2013f12. When combined with `text`, the key is pressed AFTER the text is typed (so text + enter types and submits). Not supported on TV targets \u2014 move focus with `tv-remote` (up/down/left/right) instead."
   ),
@@ -127181,12 +127232,21 @@ var capability16 = {
   vega: { vvd: true }
 };
 function createKeyboardTool(registry2) {
+  const dispatch = dispatchByPlatform({
+    toolId: "keyboard",
+    capability: capability16,
+    ios: makeIosImpl3(registry2),
+    iosRemote: makeIosRemoteImpl(registry2),
+    android: makeAndroidImpl(registry2),
+    chromium: makeChromiumImpl(registry2),
+    vega: vegaImpl4
+  });
   return {
     id: "keyboard",
     description: `Type text or press special keys on the device (iOS simulator, Android emulator or device, Chromium app, Vega Virtual Device, or Apple TV / Android TV) using keyboard events.
 Use when you need to enter text or trigger a named key such as enter, escape, or arrow keys. On Vega and Apple TV / Android TV, prefer the remote tools for D-pad navigation; use keyboard to type into a focused text field (e.g. a search or login box).
 Returns { typed: string, keys: number }. Fails if an unsupported key name is provided or the device's input backend is not reachable.
-- text: types a string (supports uppercase, digits, common punctuation)
+- text: types a string (supports uppercase, digits, common punctuation). To type a credential, use \`{{secret:<NAME>}}\` \u2014 resolved server-side from the \`ARGENT_SECRET_<NAME>\` env var (prefix mandatory; \`{{secret:APP_PASSWORD}}\` \u2194 \`ARGENT_SECRET_APP_PASSWORD\`), so the plaintext never enters agent context; the result echoes the placeholder, not the value, and the after-typing auto-screenshot is skipped.
 - key: presses a single named key (enter, escape, backspace, tab, arrow-up/down/left/right, f1\u2013f12) \u2014 NOT supported on TV targets; move focus with \`tv-remote\` instead.
 On a TV target (runtimeKind 'tv') only \`text\` applies \u2014 focus a text field first (with \`tv-remote\`), then type into it (injected HID keyboard on Apple TV, \`adb input text\` on Android TV).
 Provide text, key, or both \u2014 when both are given, the text is typed first and the key is pressed after it (text + key:"enter" types and submits).`,
@@ -127197,15 +127257,17 @@ Provide text, key, or both \u2014 when both are given, the text is typed first a
     // simulator-server, CDP, or Vega adb), since distinguishing a TV target is
     // async and a tvOS udid must never resolve simulator-server.
     services: () => ({}),
-    execute: dispatchByPlatform({
-      toolId: "keyboard",
-      capability: capability16,
-      ios: makeIosImpl3(registry2),
-      iosRemote: makeIosRemoteImpl(registry2),
-      android: makeAndroidImpl(registry2),
-      chromium: makeChromiumImpl(registry2),
-      vega: vegaImpl4
-    })
+    execute: async (services, params, options) => {
+      if (params.text === void 0) return dispatch(services, params, options);
+      const { text, secrets } = resolveSecretPlaceholders(params.text);
+      if (secrets.length === 0) return dispatch(services, params, options);
+      try {
+        const result = await dispatch(services, { ...params, text }, options);
+        return { ...result, typed: params.text };
+      } catch (err) {
+        throw redactSecretsFromError(err, secrets);
+      }
+    }
   };
 }
 
@@ -133622,6 +133684,7 @@ Allowed tools and their args (udid is auto-injected, do NOT include it in args):
   gesture-rotate: { centerX: number, centerY: number, radius: number, startAngle: number, endAngle: number, durationMs?: number }                    [ios only]
   button:         { button: "home"|"back"|"power"|"volumeUp"|"volumeDown"|"appSwitch"|"actionButton" }                  [ios/android]
   keyboard:       { text?: string, key?: string, delayMs?: number }  (key pressed after text; TV: text only)            [ios/android/chromium/vega/tv]
+                  text supports {{secret:<NAME>}} placeholders, resolved server-side from ARGENT_SECRET_<NAME> env vars (prefix mandatory) \u2014 credentials never enter agent context
   rotate:         { orientation: "Portrait"|"LandscapeLeft"|"LandscapeRight"|"PortraitUpsideDown" }                     [ios/android]
   tv-remote:      { button: <remote button | array of them>, repeat?: number }                                          [apple tv/android tv/vega]
                   buttons: up/down/left/right/select/back/home/menu/playPause (+ rewind/fastForward/next/previous/volumeUp/volumeDown/mute \u2014 work on Android TV and Vega; rejected on the Apple TV simulator)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@swmansion/argent",
-  "version": "0.15.1-next.6",
+  "version": "0.15.1-next.7",
   "description": "MCP server for iOS Simulator and Android Emulator control",
   "license": "Apache-2.0",
   "repository": {

package/skills/argent-create-flow/SKILL.md

@@ -60,6 +60,8 @@ For a custom poll interval or bundleId, drop to an explicit `- tool: await-ui-el
 
 `type` presses Enter after typing to commit the value and dismiss the keyboard, so it can't cover later targets. For a chained form whose fields feed one explicit submit — e.g. email then password then a `tap: "Log in"` — set `submit: false` on the intermediate fields so a premature Enter doesn't fire the form early: `type: { into: password, text: "hunter2", submit: false }`.
 
+Never record a real credential into a flow — the YAML is committed to the repo. Use a secret placeholder instead: `type: { into: password, text: "{{secret:APP_PASSWORD}}" }`. The placeholder is stored verbatim (the YAML stays secret-free) and is resolved at run time by the tool-server from the `ARGENT_SECRET_APP_PASSWORD` environment variable — including agent-less `argent flow run` in CI, where the variable comes from the job's secrets.
+
 `scroll-to` takes an optional `direction` (`up` | `down` | `left` | `right`, default `down` — so the common case is just `- scroll-to: <selector>`) and optionally a `within: <selector>` that anchors the scroll inside a specific container — required to drive a **nested** scroller (e.g. a horizontal carousel inside a vertical list), since the device can't be asked which container to scroll. It scrolls in bounded momentum-free increments, re-checks after each, and stops if a scroll reveals nothing new (end of the container). `tap`/`type` do **not** scroll — add a `scroll-to` before any target that may be off-screen. It's a no-op when the target is already visible, so a defensive `scroll-to` costs nothing on replay and keeps the flow working on smaller screens.
 
 ### TV targets (Vega)

package/skills/argent-device-interact/SKILL.md

@@ -171,6 +171,18 @@ Values: `home`, `back`, `power`, `volumeUp`, `volumeDown`, `appSwitch`, `actionB
 
 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 flow `type` steps):
+
+```json
+{ "udid": "<UDID>", "text": "{{secret:APP_PASSWORD}}", "key": "enter" }
+```
+
+The placeholder is resolved on the machine running the tool-server from the `ARGENT_SECRET_<NAME>` environment variable (here `ARGENT_SECRET_APP_PASSWORD`) — the CI-native pattern: expose the secret under that prefix in the environment that starts the tool-server. Rules:
+
+- The result echoes the placeholder, never the value. An unknown name fails with the list of available secret _names_.
+- The auto-screenshot after the call is skipped so the typed value cannot re-enter your context as pixels. Do **not** `describe` or `screenshot` a non-secure field you just filled with a secret — submit or navigate away first, then verify the resulting screen.
+- Only `ARGENT_SECRET_*` variables are resolvable; never ask the user to paste a secret value into the conversation — ask them to export the env var instead.
+
 ### rotate — Change orientation
 
 ```json