@loadmill/droid-cua 2.39.0 → 2.41.0

package/README.md

@@ -158,8 +158,13 @@ droid-cua skill install codex
 droid-cua skill install codex --local
 ```
 
-Use `droid-cua skill status <agent>` to inspect an installation and
-`droid-cua skill uninstall <agent>` to remove it. Installed skill
+Use `droid-cua skill status <agent>` to see the installed and bundled skill
+versions and installation path; add `--local` to inspect a project installation.
+The skill version is stored in `SKILL.md` under `metadata.version`, independently
+of the CLI package version. Older copies without version metadata show `unknown`.
+The `modified` status means the files differ from the bundled copy, which can
+indicate an older release or local edits even when version labels match.
+Use `droid-cua skill uninstall <agent>` to remove an installation. Installed skill
 files are never overwritten or removed after local modification unless `--force`
 is supplied. After upgrading the npm package, update an installed skill explicitly:
 
@@ -188,6 +193,9 @@ droid-cua run tests/login.dcua --platform ios --avd "iPhone 16"
 # List running desktop applications and their window IDs (macOS or Windows)
 droid-cua --target desktop --list-desktop-apps
 
+# Control the full primary display across applications
+droid-cua --target desktop --instructions tests/launcher.dcua
+
 # Control one already-running desktop application window
 droid-cua --target desktop --desktop-app com.apple.TextEdit --desktop-window 123 --instructions tests/editor.dcua
 
@@ -239,7 +247,7 @@ backward compatibility.
 Example headless config:
 ```json
 {
-  "cuaModel": "gpt-5.4",
+  "cuaModel": "gpt-6-sol",
   "promptCustomizations": {
     "basePromptInstructions": "",
     "designModeInstructions": "",
@@ -271,8 +279,8 @@ Supported CLI options include:
 - `--list-devices`
 - `--browser`
 - `--target` (`mobile`, `web`, or `desktop`)
-- `--desktop-app` (desktop application ID or exact name)
-- `--desktop-window` (required when the application has multiple visible windows)
+- `--desktop-app` (limit desktop control to an application ID or exact name; omit for full desktop)
+- `--desktop-window` (select a window within `--desktop-app`)
 - `--desktop-input` (`physical` by default; use `accessibility` for cursor-free input)
 - `--list-desktop-apps`
 - `--instructions`
@@ -295,10 +303,21 @@ Supported CLI options include:
 - `--debug`
 
 `--cua-model` accepts `loadmill-smart`, `loadmill-pulse`, `loadmill-beacon`,
-`gpt-5.6-terra`, `gpt-5.6-luna`, and `gpt-5.4`. OpenAI models use direct OpenAI
-mode and require `OPENAI_API_KEY`.
+`gpt-6-sol`, and `gpt-6-luna`. OpenAI models use direct OpenAI mode and require
+`OPENAI_API_KEY`. Saved direct OpenAI selections of GPT-5.6 Terra, GPT-5.6 Luna,
+or GPT-5.4 move to GPT-6 Sol, GPT-6 Luna, or GPT-6 Sol, respectively.
+
+Desktop control supports macOS and Windows. In the desktop app, enable **Experimental desktop control** at the bottom of Settings to show Desktop in the platform picker. Desktop runs use physical pointer and keyboard input by default. Droid shows a system notice for three seconds before taking control and a completion notice when the run finishes, fails, or is stopped. The delay is fixed; use Stop in Droid once the run starts. Avoid using the mouse or keyboard during the run. macOS requires Screen & System Audio Recording and Accessibility permissions for Droid or the terminal running the CLI. On Windows, Droid must run at the same integrity level as the target application. System notices and automatic minimization apply only to runs started in the desktop app.
+
+CLI runs with `--target desktop` control the full primary display by default, with no application flag needed. In the desktop app, choose **Full desktop**, the first option in the Application dropdown. This mode captures and controls the primary display across applications, including apps launched during the test; no target application needs to be running when connecting. Keep all test windows on the primary display. Full desktop requires physical input. Droid minimizes itself after the three-second notice and remains minimized when the run ends; open Droid to review the result or use Stop. Existing saved application selections are preserved.
+
+Use `--desktop-app <id-or-exact-name>` or select an application in Droid to limit control to that application's windows. Application mode brings the selected window forward and leaves it there when the run ends. Add `--desktop-window <id>` to select a particular window, or `--desktop-input accessibility` for cursor-free CLI input; both options require `--desktop-app`. Before each run and screenshot, Droid refreshes window selection within the original application so it can follow a recreated login window. If replacement is ambiguous, select a window again. If a captured window disappears or moves before input, Droid requests a fresh screenshot instead of transferring its coordinates to a replacement. Focus errors report the activation reason; they do not establish an elevation problem.
+
+If Windows returns an all-black window capture, Droid brings the target forward and crops the visible desktop to the window's visible frame, excluding its invisible resize border. The fallback logs a warning, crops before resizing to preserve detail, and requires the target to remain unobstructed on the primary display; off-screen portions appear black. With accessibility input, bring the target forward yourself when requested. Full desktop reports capture failures directly, without this window capture fallback.
+
+Desktop **Test design** uses the same notices once you submit your instructions and exploration starts. Full desktop minimizes Droid at that point. Droid sends the completion notice when the generated test is ready, exploration is stopped, or recovery ends in an error. It does not automatically bring itself forward; open Droid whenever you need to give guidance, use Stop, or review the generated test. Opening Test design alone does not take desktop control. When a controller rejects an action, Droid skips the remaining actions in that batch and asks the model to continue from a fresh screenshot with the failure reason. Rejected actions are not counted as completed.
 
-Desktop control supports macOS and Windows. In the desktop app, enable **Experimental desktop control** at the bottom of Settings to show Desktop in the platform picker. Desktop runs use visual input by default: they capture the selected window and send physical pointer and keyboard input at the model's coordinates. Use `--desktop-input accessibility` for cursor-free CLI input instead. macOS requires Screen & System Audio Recording and Accessibility permissions for Droid or the terminal running the CLI. Windows targets must run at the same integrity level as Droid; a non-elevated Droid process cannot inject input into an elevated application.
+The system notices are shown only for desktop control runs started in the desktop app. On macOS, they may not appear in the unsigned Electron dev app; verify them in a signed packaged build.
 
 Config and precedence rules:
 - Use `--config <file>` to supply prompt-affecting settings for headless runs.

package/build/index.js

@@ -534,15 +534,17 @@ async function main() {
     }
     else if (isDesktopTarget) {
         desktopController = await createDesktopController({
+            scope: targetConfig.desktopScope,
             app: targetConfig.desktopApp,
             windowId: targetConfig.desktopWindow,
             inputMode: targetConfig.desktopInput,
+            focusOnConnect: true,
             excludePids: [process.pid],
         });
         targetId = desktopController.deviceId;
         deviceInfo = desktopController.deviceInfo;
-        console.log(`Attached to desktop window: ${deviceInfo.device_name}`);
-        console.log(`Model sees window: ${deviceInfo.scaled_width}x${deviceInfo.scaled_height}`);
+        console.log(`Attached to desktop target: ${deviceInfo.device_name}`);
+        console.log(`Model sees desktop target: ${deviceInfo.scaled_width}x${deviceInfo.scaled_height}`);
         console.log(`Desktop input: ${deviceInfo.desktopInputMode === "physical" ? "physical OS pointer" : "cursor-free accessibility"}`);
         process.once("SIGINT", async () => {
             console.log("\nStopping desktop run...");

package/build/src/cli/headless-execution-config.js

@@ -2,7 +2,7 @@ import path from "path";
 import { readFile } from "fs/promises";
 import { DEFAULT_CONTEXT_OPTIMIZATION_THRESHOLD, MAX_CONTEXT_OPTIMIZATION_THRESHOLD, MIN_CONTEXT_OPTIMIZATION_THRESHOLD, } from "../core/context-optimization.js";
 import { AIM_ASSIST_MODES, DEFAULT_AIM_ASSIST_MODE } from "../core/aim-assist.js";
-import { CUA_MODELS, DEFAULT_OPENAI_CUA_MODEL, isOpenAiCuaModel, isValidCuaModel, resolveCuaModel } from "../core/cua-models.js";
+import { CUA_MODELS, DEFAULT_OPENAI_CUA_MODEL, isOpenAiCuaModel, isValidCuaModel, resolveCuaModel, upgradeLegacyCuaModel } from "../core/cua-models.js";
 import { LLM_PROVIDER_MODES, isValidLlmProviderMode, resolveLlmProviderMode } from "../core/runtime-config.js";
 import { parseSecretsOverrideString } from "../core/secrets.js";
 function createEmptyPromptCustomizations() {
@@ -21,10 +21,11 @@ function assertNonEmptyString(value, label) {
     }
 }
 function validateCuaModel(value, label) {
-    if (typeof value !== "string" || !isValidCuaModel(value)) {
+    const upgraded = typeof value === "string" ? upgradeLegacyCuaModel(value) : value;
+    if (!isValidCuaModel(upgraded)) {
         throw new Error(`${label} must be one of: ${CUA_MODELS.join(", ")}.`);
     }
-    return value;
+    return upgraded;
 }
 function validateAimAssistMode(value, label) {
     if (typeof value !== "string" || !AIM_ASSIST_MODES.includes(value)) {
@@ -44,8 +45,8 @@ function readEnvDefaultCuaModel() {
     // OpenAI model, stay on the OpenAI default rather than crossing over to the
     // global (Loadmill) default.
     if (typeof envValue === "string" && envValue.trim()) {
-        const trimmed = envValue.trim();
-        return isOpenAiCuaModel(trimmed) ? trimmed : DEFAULT_OPENAI_CUA_MODEL;
+        const upgraded = upgradeLegacyCuaModel(envValue.trim());
+        return isOpenAiCuaModel(upgraded) ? upgraded : DEFAULT_OPENAI_CUA_MODEL;
     }
     return resolveCuaModel(envValue);
 }

package/build/src/cli/headless-target.js

@@ -184,6 +184,9 @@ export function shouldWaitForLoadmillCloudCompletion(targetConfig) {
 const MOBILE_ONLY_CLOUD_SOURCES = new Set(["lambdatest", "aws-device-farm"]);
 export function resolveHeadlessTarget(args = {}) {
     const target = normalizeTarget(args.target);
+    if (target !== "desktop" && (args["desktop-app"] != null || args["desktop-window"] != null || args["desktop-input"] != null || args["list-desktop-apps"] != null)) {
+        throw new Error("--desktop-app, --desktop-window, --desktop-input, and --list-desktop-apps can only be used with --target desktop.");
+    }
     const targetGiven = hasNonEmptyString(args.target);
     const avdName = hasNonEmptyString(args.avd) ? args.avd.trim() : null;
     const platform = normalizeMobilePlatform(args.platform, "--platform");
@@ -264,18 +267,25 @@ export function resolveHeadlessTarget(args = {}) {
         }
         const listDesktopApps = args["list-desktop-apps"] != null;
         const desktopApp = hasNonEmptyString(args["desktop-app"]) ? args["desktop-app"].trim() : null;
+        if (args["desktop-app"] != null && !desktopApp) {
+            throw new Error("--desktop-app requires an application ID or exact name.");
+        }
         const rawWindow = readNonEmptyCliValue(args["desktop-window"]);
         const desktopWindow = rawWindow == null ? null : Number(rawWindow);
         const desktopInput = hasNonEmptyString(args["desktop-input"]) ? args["desktop-input"].trim().toLowerCase() : "physical";
-        if (!listDesktopApps && !desktopApp) {
-            throw new Error("--desktop-app is required with --target desktop.");
+        if (args["desktop-window"] != null && !desktopApp) {
+            throw new Error("--desktop-window requires --desktop-app.");
         }
-        if (rawWindow != null && (!Number.isInteger(desktopWindow) || desktopWindow < 0)) {
+        if (args["desktop-window"] != null && (rawWindow == null || !Number.isInteger(desktopWindow) || desktopWindow < 0)) {
             throw new Error("--desktop-window must be a non-negative integer window ID.");
         }
-        if (desktopInput !== "accessibility" && desktopInput !== "physical") {
+        if ((args["desktop-input"] != null && !hasNonEmptyString(args["desktop-input"])) ||
+            (desktopInput !== "accessibility" && desktopInput !== "physical")) {
             throw new Error('--desktop-input must be "accessibility" or "physical".');
         }
+        if (desktopInput === "accessibility" && !desktopApp) {
+            throw new Error("--desktop-input accessibility requires --desktop-app. Full desktop uses physical input only.");
+        }
         return {
             target,
             sessionMode: null,
@@ -290,14 +300,12 @@ export function resolveHeadlessTarget(args = {}) {
             artifacts: null,
             listDevices: false,
             listDesktopApps,
+            desktopScope: desktopApp ? "window" : "desktop",
             desktopApp,
             desktopWindow,
             desktopInput,
         };
     }
-    if (args["desktop-app"] != null || args["desktop-window"] != null || args["desktop-input"] != null || args["list-desktop-apps"] != null) {
-        throw new Error("--desktop-app, --desktop-window, --desktop-input, and --list-desktop-apps can only be used with --target desktop.");
-    }
     if (args["session-mode"] != null) {
         throw new Error("--session-mode can only be used with --target web.");
     }

package/build/src/cli/skill-command.js

@@ -12,7 +12,7 @@ const SUBCOMMANDS = new Set(["install", "status", "uninstall"]);
 const ALLOWED_OPTIONS = new Set(["_", "local", "force", "h", "help"]);
 const COMMAND_DESCRIPTIONS = Object.freeze({
     install: "Install Droid CUA skill for a coding agent",
-    status: "Show Droid CUA skill status for a coding agent",
+    status: "Show installation status and installed/bundled skill versions",
     uninstall: "Uninstall Droid CUA skill for a coding agent",
 });
 function skillCommandHelp(subcommand) {
@@ -53,7 +53,7 @@ function skillRootHelp() {
         "",
         "Commands:",
         "  install    Install the skill",
-        "  status     Show installation status",
+        "  status     Show installation status and skill versions",
         "  uninstall  Uninstall the skill",
     ].join("\n");
 }
@@ -103,6 +103,18 @@ async function directoryMatches(sourcePath, destinationPath) {
     ]);
     return JSON.stringify(sourceSnapshot) === JSON.stringify(destinationSnapshot);
 }
+// Read the bundled skill's block-style metadata.version scalar without a YAML dependency.
+async function readSkillVersion(skillPath) {
+    if (await pathType(skillPath) !== "directory")
+        return null;
+    if (await pathType(path.join(skillPath, "SKILL.md")) !== "file")
+        return null;
+    const markdown = await readFile(path.join(skillPath, "SKILL.md"), "utf8");
+    const frontmatter = markdown.replace(/\r\n/g, "\n").match(/^---\n([\s\S]*?)\n---(?:\n|$)/)?.[1];
+    const metadata = frontmatter?.match(/^metadata:[ \t]*\n((?:[ \t]+[^\n]*(?:\n|$))*)/m)?.[1];
+    const value = metadata?.match(/^  version:[ \t]*(?:"([^"\n]+)"|'([^'\n]+)'|([^\s#]+))[ \t]*(?:#.*)?$/m);
+    return value ? (value[1] ?? value[2] ?? value[3]) : null;
+}
 async function getInstallationState(sourcePath, destinationPath) {
     if (await pathType(destinationPath) === "missing")
         return "not-installed";
@@ -214,7 +226,12 @@ export async function runSkillCommand({ args, cwd = process.cwd(), home = os.hom
     }
     for (const destination of states) {
         if (command.subcommand === "status") {
-            output.log(`${destination.displayName}: ${stateLabel(destination.state)} at ${destination.path}`);
+            const [installedVersion, bundledVersion] = await Promise.all([
+                readSkillVersion(destination.path),
+                readSkillVersion(bundledSkillPath),
+            ]);
+            const installedLabel = destination.state === "not-installed" ? "not installed" : installedVersion ?? "unknown";
+            output.log(`${destination.displayName}: ${stateLabel(destination.state)} at ${destination.path}\nInstalled skill version: ${installedLabel}\nBundled skill version: ${bundledVersion ?? "unknown"}`);
         }
         else if (command.subcommand === "install") {
             if (destination.state === "installed") {

package/build/src/commands/help.js

@@ -11,19 +11,21 @@ import { CUA_MODELS } from '../core/cua-models.js';
  */
 export async function handleHelp(args, session, context) {
     const addOutput = context?.addOutput || ((item) => console.log(item.text || item));
-    addOutput({ type: 'system', text: 'droid-cua - AI-powered mobile and web testing CLI' });
+    addOutput({ type: 'system', text: 'droid-cua - AI-powered mobile, web, and desktop testing CLI' });
     addOutput({ type: 'info', text: '' });
     addOutput({ type: 'info', text: 'Usage:' });
     addOutput({ type: 'info', text: '  droid-cua --avd <device-name> [options]' });
     addOutput({ type: 'info', text: '  droid-cua run <file-or-directory...> [options]' });
     addOutput({ type: 'info', text: '  droid-cua --target web --instructions <file> [options]' });
+    addOutput({ type: 'info', text: '  droid-cua --target desktop --instructions <file> [options]' });
     addOutput({ type: 'info', text: '  droid-cua --device-source lambdatest --instructions <file> [options]' });
     addOutput({ type: 'info', text: '' });
     addOutput({ type: 'info', text: 'Options:' });
     addOutput({ type: 'info', text: '  --target <kind>        Target kind: mobile (default), web, or desktop' });
-    addOutput({ type: 'info', text: '  --desktop-app <id>     Running desktop app ID or exact name' });
-    addOutput({ type: 'info', text: '  --desktop-window <id>  Window ID when the app has multiple windows' });
-    addOutput({ type: 'info', text: '  --desktop-input <mode> Physical pointer (default) or cursor-free accessibility' });
+    addOutput({ type: 'info', text: '                        Desktop controls the primary display by default' });
+    addOutput({ type: 'info', text: '  --desktop-app <id>     Limit desktop control to a running app ID or exact name' });
+    addOutput({ type: 'info', text: '  --desktop-window <id>  Select a window within --desktop-app' });
+    addOutput({ type: 'info', text: '  --desktop-input <mode> Physical pointer (default); accessibility requires --desktop-app' });
     addOutput({ type: 'info', text: '  --list-desktop-apps    List running desktop apps and windows' });
     addOutput({ type: 'info', text: '  --avd <name>           Device name (Android device ID/serial or iOS Simulator)' });
     addOutput({ type: 'info', text: '  --platform <platform>  Force platform: android or ios' });
@@ -76,6 +78,7 @@ export async function handleHelp(args, session, context) {
     addOutput({ type: 'info', text: '  iOS:     Uses Appium + XCUITest for iOS Simulator automation' });
     addOutput({ type: 'info', text: '  LambdaTest: Uses real cloud devices for headless mobile runs' });
     addOutput({ type: 'info', text: '  Web:     Uses Playwright with installed Google Chrome or Microsoft Edge for browser execution' });
+    addOutput({ type: 'info', text: '  Desktop: Controls the primary display or a selected application on macOS and Windows' });
     addOutput({ type: 'info', text: '' });
     addOutput({ type: 'info', text: 'Platform Detection:' });
     addOutput({ type: 'info', text: '  - Use --platform flag to force a specific platform' });
@@ -98,6 +101,7 @@ export async function handleHelp(args, session, context) {
     addOutput({ type: 'info', text: '  droid-cua --instructions tests/login.dcua --context app/context.md' });
     addOutput({ type: 'info', text: '  droid-cua --instructions tests --test-data tests/test-data.md --scenario "Run every checkout test with each buyer account"' });
     addOutput({ type: 'info', text: '  droid-cua --target web --instructions tests/search.dcua' });
+    addOutput({ type: 'info', text: '  droid-cua --target desktop --instructions tests/launcher.dcua' });
     addOutput({ type: 'info', text: '  droid-cua --device-source lambdatest --platform android --device-name "Galaxy S24" --os-version 14 --app app.apk --instructions tests/login.dcua' });
     addOutput({ type: 'info', text: '  /create login-test                      (design a new test)' });
     addOutput({ type: 'info', text: '  /list                                   (see all tests)' });

package/build/src/core/cua-models.js

@@ -1,4 +1,4 @@
-export const DEFAULT_OPENAI_CUA_MODEL = "gpt-5.4";
+export const DEFAULT_OPENAI_CUA_MODEL = "gpt-6-sol";
 export const DEFAULT_LOADMILL_CUA_MODEL = "loadmill-smart";
 export const DEFAULT_CUA_MODEL = DEFAULT_LOADMILL_CUA_MODEL;
 export const CUA_CONVERSATION_POLICIES = Object.freeze({
@@ -28,27 +28,28 @@ export const CUA_MODEL_OPTIONS = Object.freeze([
         label: "Loadmill - Beacon",
     }),
     Object.freeze({
-        id: "gpt-5.6-terra",
+        id: "gpt-6-sol",
         providerMode: "openai",
         providerLabel: "OpenAI",
-        name: "GPT-5.6 Terra",
-        label: "OpenAI GPT-5.6 Terra",
+        name: "GPT-6 Sol",
+        label: "OpenAI GPT-6 Sol",
     }),
     Object.freeze({
-        id: "gpt-5.6-luna",
+        id: "gpt-6-luna",
         providerMode: "openai",
         providerLabel: "OpenAI",
-        name: "GPT-5.6 Luna",
-        label: "OpenAI GPT-5.6 Luna",
-    }),
-    Object.freeze({
-        id: "gpt-5.4",
-        providerMode: "openai",
-        providerLabel: "OpenAI",
-        name: "GPT-5.4",
-        label: "OpenAI GPT-5.4",
+        name: "GPT-6 Luna",
+        label: "OpenAI GPT-6 Luna",
     }),
 ]);
+const LEGACY_OPENAI_CUA_MODELS = Object.freeze({
+    "gpt-5.6-terra": "gpt-6-sol",
+    "gpt-5.6-luna": "gpt-6-luna",
+    "gpt-5.4": "gpt-6-sol",
+});
+export function upgradeLegacyCuaModel(value) {
+    return LEGACY_OPENAI_CUA_MODELS[value] ?? value;
+}
 export const CUA_MODELS = Object.freeze(CUA_MODEL_OPTIONS.map((option) => option.id));
 export const OPENAI_CUA_MODELS = Object.freeze(CUA_MODEL_OPTIONS
     .filter((option) => option.providerMode === "openai")
@@ -70,7 +71,8 @@ export function isLoadmillCuaModel(value) {
     return LOADMILL_CUA_MODEL_SET.has(value);
 }
 export function resolveCuaModel(value) {
-    return isValidCuaModel(value) ? value : DEFAULT_CUA_MODEL;
+    const upgraded = upgradeLegacyCuaModel(value);
+    return isValidCuaModel(upgraded) ? upgraded : DEFAULT_CUA_MODEL;
 }
 export function resolveCuaModelProviderMode(value) {
     const normalized = resolveCuaModel(value);

package/build/src/core/droid-cua-run-usage.js

@@ -3,29 +3,26 @@ const OPENAI_GPT_5_4_PRICING = Object.freeze({
     inputPerMillionUsd: 2.5,
 });
 const OPENAI_GPT_5_6_TERRA_PRICING = Object.freeze({
-    inputPerMillionUsd: 2.5,
+    inputPerMillionUsd: 2,
 });
 const OPENAI_GPT_5_6_LUNA_PRICING = Object.freeze({
-    inputPerMillionUsd: 1,
+    inputPerMillionUsd: 0.2,
+});
+const OPENAI_GPT_6_SOL_PRICING = Object.freeze({
+    inputPerMillionUsd: 2,
+});
+const OPENAI_GPT_6_LUNA_PRICING = Object.freeze({
+    inputPerMillionUsd: 0.1,
 });
 const MODEL_PRICING = Object.freeze({
-    "gpt-5.6-terra": Object.freeze({
-        ...OPENAI_GPT_5_6_TERRA_PRICING,
-    }),
-    "gpt-5.6-luna": Object.freeze({
-        ...OPENAI_GPT_5_6_LUNA_PRICING,
-    }),
-    "gpt-5.4": Object.freeze({
-        ...OPENAI_GPT_5_4_PRICING,
-    }),
-    // Loadmill Smart currently routes to GPT-5.6 Terra behind the Loadmill LLM gateway.
-    // Keep this explicit so pricing can be updated here if the backing model changes.
-    "loadmill-smart": Object.freeze({
-        ...OPENAI_GPT_5_6_TERRA_PRICING,
-    }),
-    "loadmill-pulse": Object.freeze({
-        ...OPENAI_GPT_5_6_LUNA_PRICING,
-    }),
+    "gpt-6-sol": OPENAI_GPT_6_SOL_PRICING,
+    "gpt-6-luna": OPENAI_GPT_6_LUNA_PRICING,
+    "gpt-5.6-terra": OPENAI_GPT_5_6_TERRA_PRICING,
+    "gpt-5.6-luna": OPENAI_GPT_5_6_LUNA_PRICING,
+    "gpt-5.4": OPENAI_GPT_5_4_PRICING,
+    // Loadmill Smart and Pulse route to GPT-6 Sol and Luna, respectively.
+    "loadmill-smart": OPENAI_GPT_6_SOL_PRICING,
+    "loadmill-pulse": OPENAI_GPT_6_LUNA_PRICING,
 });
 function finiteNumber(value) {
     return typeof value === "number" && Number.isFinite(value) && value > 0 ? value : 0;
@@ -41,6 +38,12 @@ export function normalizeDroidCuaCostModel(model) {
     if (typeof model !== "string") {
         return null;
     }
+    if (model === "gpt-6-sol" || model.startsWith("gpt-6-sol-")) {
+        return "gpt-6-sol";
+    }
+    if (model === "gpt-6-luna" || model.startsWith("gpt-6-luna-")) {
+        return "gpt-6-luna";
+    }
     if (model === "gpt-5.6-terra" || model.startsWith("gpt-5.6-terra-")) {
         return "gpt-5.6-terra";
     }

package/build/src/core/execution-engine.js

@@ -408,7 +408,7 @@ export class ExecutionEngine {
             // The Desktop recorder returns one from disk; for runs without a recorder (e.g. a
             // plain CLI `--report`) render the same marker in-memory from the raw screenshot.
             const annotatedDataUrl = await this.resolveAnnotatedDataUrl(annotatedScreenshot, currentScreenshot, action, context);
-            await this.handleModelAction(this.session.deviceId, action, this.session.deviceInfo.scale, {
+            const actionResult = await this.handleModelAction(this.session.deviceId, action, this.session.deviceInfo.scale, {
                 ...context,
                 shouldStop,
                 stepId: stepContext?.stepId,
@@ -430,6 +430,13 @@ export class ExecutionEngine {
                 ...(annotatedScreenshot?.screenshotPath ? { screenshotPath: annotatedScreenshot.screenshotPath } : {}),
                 ...(context?.includeScreenshotDataUrl && annotatedDataUrl ? { screenshotDataUrl: annotatedDataUrl } : {})
             });
+            if (actionResult?.success === false) {
+                if (shouldStop())
+                    return { stopped: true, sawExplicitScreenshotAction };
+                const actionError = `${action.type} failed: ${actionResult.error || "The action could not be completed."}`;
+                this.session.addToTranscript?.(`[Action Error] ${actionError}`);
+                return { refreshModelState: true, actionError, sawExplicitScreenshotAction };
+            }
             if (trackAction) {
                 trackAction(action);
             }
@@ -823,6 +830,9 @@ export class ExecutionEngine {
             }
             if (actionBatchResult.refreshModelState) {
                 const followUp = await this.buildActionFollowUp(call_id, pendingSafetyChecks, true, addOutput, eventMeta, context, stepContext);
+                if (actionBatchResult.actionError) {
+                    followUp.input.push({ role: "user", content: `${actionBatchResult.actionError} The remaining actions were skipped. Use the fresh screenshot to decide what to do next.` });
+                }
                 currentScreenshot = followUp.currentScreenshot ?? currentScreenshot;
                 response = await this.requestNextTurn(followUp.input, newResponseId, context, stepContext);
                 newResponseId = response.id;