@loadmill/droid-cua 2.38.0 → 2.40.0

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:
 
@@ -239,7 +244,7 @@ backward compatibility.
 Example headless config:
 ```json
 {
-  "cuaModel": "gpt-5.4",
+  "cuaModel": "gpt-6-sol",
   "promptCustomizations": {
     "basePromptInstructions": "",
     "designModeInstructions": "",
@@ -290,14 +295,18 @@ Supported CLI options include:
 - `--secrets`
 - `--record`
 - `--report`
+- `--report-metadata <path>`
 - `--no-cloud-report`
 - `--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 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.
+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: Droid shows a system notice for three seconds before taking control, brings the selected window to the foreground, then sends physical pointer and keyboard input at the model's coordinates. The three-second delay is fixed; once the test starts, use Stop in Droid to end it. Avoid using the mouse or keyboard during the run. When the run ends, Droid leaves the target window in front and shows another system notice that control has finished, including when the run fails or is stopped. CLI runs also leave the target in front. 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. If Windows returns an all-black window capture, Droid brings the target back to the foreground and crops the visible desktop to the window's visible frame, excluding its invisible resize border. The crop is resized only after extraction to preserve window detail. The fallback logs a warning and requires the target to remain unobstructed on the primary display; off-screen portions appear black. With accessibility input, bring the target to the foreground yourself when requested.
+
+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.
@@ -325,8 +334,11 @@ HTML report (`--report`):
 - With no value it saves `<test>--<date>--<time>.html` (e.g. `login--2026-06-03--16-09-20.html`) in the current directory; pass `--report <file>` to pick a filename or `--report <dir>` to pick a folder.
 - A multi-path selection writes the individual test reports plus one aggregate `Selected tests` report with a child result and timeline for every selected test. When `--report <file.html>` is used, that exact path is used for the aggregate report.
 - In the desktop app the same report is available from a run's **Share → Download HTML report** button.
-- Runs with captured screenshots also expose **Share → Generate video**. The desktop app renders a square mobile replay or 16:9 web and desktop replay locally, then prompts for a save location using `<test>--<date>--<time>--test-replay.mp4` as the suggested filename. While rendering, a compact **Background tasks** card shows progress for **Generating test replay**; it can be minimized to a task-count card or canceled without opening the save dialog.
+- Generated HTML reports opt out of Cloudflare email obfuscation so ordinary email values remain visible in hosted reports. Secret-typing values are omitted from typing logs, but may still appear in screenshots.
+- Loadmill flow entries link **Test started** to the flow's test-suite run results, including in reports generated by CI.
+- Runs with captured screenshots also expose **Share → Generate video**. The desktop app renders portrait mobile runs as square replays and landscape mobile, web, and desktop runs as 16:9 replays. Landscape Android and iOS screenshots keep a device frame sized to the captured screen instead of browser chrome. Rendering happens locally, then the app prompts for a save location using `<test>--<date>--<time>--test-replay.mp4` as the suggested filename. While rendering, a compact **Background tasks** card shows progress for **Generating test replay**; it can be minimized to a task-count card or canceled without opening the save dialog.
 - Authenticated headless runs upload their HTML report and screenshots to Loadmill by default. The Loadmill run record also includes the resolved Droid version, model, provider, Agent Pace, Aim Assist, Context Optimization, and target environment. Use `--no-cloud-report` to disable artifact upload; the Droid run record is still reported.
+- Use `--report-metadata <path>` when automation needs the exact published Loadmill run ID and last uploaded screenshot object name. Droid clears that destination when the invocation starts and writes it only after report publication succeeds, including for published failure reports.
 
 ```sh
 droid-cua run tests/login.dcua --avd adb:emulator-5554 --report ./reports

package/build/index.js

@@ -22,6 +22,7 @@ import { resolveHeadlessExecutionConfig } from "./src/cli/headless-execution-con
 import { artifactKindsForPool, resolveHeadlessTarget, scopeArtifactKindsToPool, shouldWaitForLoadmillCloudCompletion, } from "./src/cli/headless-target.js";
 import { createHeadlessDebugArtifacts } from "./src/cli/headless-debug.js";
 import { loadHeadlessInstructions } from "./src/cli/headless-instructions.js";
+import { clearLoadmillReportMetadata } from "./src/cli/loadmill-report-metadata.js";
 import { assertRunCommandPosition, getHeadlessInstructionSelectors, resolveHeadlessInstructionSelection, } from "./src/cli/headless-selection.js";
 import { runHeadlessInstructionRuns } from "./src/cli/headless-runner.js";
 import { buildLoadmillCloudDeviceConnectSummaryLines } from "./src/cli/loadmill-cloud-device-connect-summary.js";
@@ -72,6 +73,11 @@ if (args._[0] === "skill") {
         process.exit(1);
     }
 }
+const reportMetadataPath = typeof args["report-metadata"] === "string"
+    && args["report-metadata"].trim().length > 0
+    ? args["report-metadata"].trim()
+    : null;
+await clearLoadmillReportMetadata(reportMetadataPath);
 const targetConfig = resolveHeadlessTarget(args);
 let avdName = targetConfig.avdName;
 let platform = targetConfig.platform || null; // 'ios' or 'android'
@@ -98,6 +104,10 @@ const reportConfig = {
     enabled: args.report === true || (typeof args.report === "string" && args.report.trim().length > 0),
     path: typeof args.report === "string" && args.report.trim().length > 0 ? args.report.trim() : null,
     cloudEnabled: args["no-cloud-report"] !== true,
+    metadataPath: reportMetadataPath,
+    lloydJobId: typeof process.env.LLOYD_JOB_ID === "string" && process.env.LLOYD_JOB_ID.trim().length > 0
+        ? process.env.LLOYD_JOB_ID.trim()
+        : null,
 };
 const screenshotDir = path.join("droid-cua-recording-" + Date.now());
 if (recordScreenshots)
@@ -527,6 +537,7 @@ async function main() {
             app: targetConfig.desktopApp,
             windowId: targetConfig.desktopWindow,
             inputMode: targetConfig.desktopInput,
+            focusOnConnect: true,
             excludePids: [process.pid],
         });
         targetId = desktopController.deviceId;

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-runner.js

@@ -1,5 +1,5 @@
 import path from "path";
-import { mkdir } from "fs/promises";
+import { mkdir, writeFile } from "fs/promises";
 import { getCurrentPlatform as getBrowserCurrentPlatform, getScreenshotAsBase64 as getBrowserScreenshotAsBase64, } from "../browser/connection.js";
 import { handleModelAction as handleBrowserModelAction } from "../browser/actions.js";
 import { ExecutionEngine } from "../core/execution-engine.js";
@@ -13,6 +13,7 @@ import { reportDroidCuaCiTestRunCompleted } from "../integrations/segment/droid-
 import { printCliOutput } from "../utils/console-output.js";
 import { emitDesktopDebug } from "../utils/desktop-debug.js";
 import { loadHeadlessInstructions } from "./headless-instructions.js";
+import { clearLoadmillReportMetadata } from "./loadmill-report-metadata.js";
 import { formatHeadlessTestSourceLabel } from "./headless-test-source-label.js";
 import { buildCliRunReportModel, createCapturingAddOutput, createCliAggregateRunReport, createCliRunReport, renderCliCloudReport, writeCliRunReportArtifact, } from "./headless-report.js";
 import { createRefuseReconnectConnectToBrowser } from "../desktop-shared/connection-predicates.js";
@@ -36,6 +37,24 @@ function logPendingScreenshotUploads(uploadManager, uploadSession, subject) {
         console.log(`${subject} finished. Waiting for ${pendingCount} screenshot ${uploads} to finish...`);
     }
 }
+function loadmillReportMetadata(savedRunId, publication) {
+    if (!savedRunId || !publication?.published) {
+        return null;
+    }
+    return {
+        runId: savedRunId,
+        ...(publication.lastScreenshotObjectName
+            ? { lastScreenshotObjectName: publication.lastScreenshotObjectName }
+            : {}),
+    };
+}
+async function writeLoadmillReportMetadata(filePath, metadata) {
+    if (!filePath || !metadata) {
+        return;
+    }
+    await mkdir(path.dirname(path.resolve(filePath)), { recursive: true });
+    await writeFile(filePath, `${JSON.stringify(metadata, null, 2)}\n`, { mode: 0o600 });
+}
 function getRecordScreenshotDirForTest(baseScreenshotDir, testName, isBatchRun) {
     if (!baseScreenshotDir || !isBatchRun) {
         return baseScreenshotDir;
@@ -320,9 +339,10 @@ async function runHeadlessTest({ runId, testPath, testName, instructions, sessio
         const cloudModel = cloudReportEnabled
             ? buildCliRunReportModel({ ...reportInput, events: cloudEvents })
             : null;
+        let reportPublication = null;
         if (cloudModel && reportToLoadmill && reportedRun?.savedRunId) {
             logPendingScreenshotUploads(uploadManager, cloudUploadSession, "Test");
-            await uploadManager.finish(cloudUploadSession, {
+            reportPublication = await uploadManager.finish(cloudUploadSession, {
                 savedRunId: reportedRun.savedRunId,
                 html: renderCliCloudReport(cloudModel, reportedRun.savedRunId),
             });
@@ -339,6 +359,7 @@ async function runHeadlessTest({ runId, testPath, testName, instructions, sessio
             retries: stats.retryCount ?? 0,
             localReportModel: localReport?.model ?? null,
             reportModel: cloudModel,
+            loadmillReport: loadmillReportMetadata(reportedRun?.savedRunId, reportPublication),
         };
     }
     catch (error) {
@@ -418,9 +439,10 @@ async function runHeadlessTest({ runId, testPath, testName, instructions, sessio
         const cloudModel = cloudReportEnabled
             ? buildCliRunReportModel({ ...failedReportInput, events: cloudEvents })
             : null;
+        let reportPublication = null;
         if (cloudModel && reportToLoadmill && reportedRun?.savedRunId) {
             logPendingScreenshotUploads(uploadManager, cloudUploadSession, "Test");
-            await uploadManager.finish(cloudUploadSession, {
+            reportPublication = await uploadManager.finish(cloudUploadSession, {
                 savedRunId: reportedRun.savedRunId,
                 html: renderCliCloudReport(cloudModel, reportedRun.savedRunId),
             });
@@ -439,17 +461,21 @@ async function runHeadlessTest({ runId, testPath, testName, instructions, sessio
                 retries: stats.retryCount ?? 0,
                 localReportModel: localReport?.model ?? null,
                 reportModel: cloudModel,
+                loadmillReport: loadmillReportMetadata(reportedRun?.savedRunId, reportPublication),
             };
         }
+        await writeLoadmillReportMetadata(report?.metadataPath, loadmillReportMetadata(reportedRun?.savedRunId, reportPublication));
         throw error;
     }
 }
 export async function runHeadlessInstructionRuns({ runs, instructionsTarget, session, deviceInfo, headlessConfig, appContext, runtimeContext, headlessDebug, secrets = null, recordScreenshots, screenshotDir, isBrowserTarget, isDesktopTarget = false, desktopController = null, isCloudTarget, runTarget = null, report = null, droidVersion = getDroidVersion(), runHeadlessTestImpl = runHeadlessTest, uploadManager = droidReportUploadManager, }) {
+    await clearLoadmillReportMetadata(report?.metadataPath);
     const resolvedRunTarget = runTarget ?? { isBrowserTarget, isDesktopTarget, isCloudTarget };
     const runConfiguration = buildDroidRunConfiguration({
         droidVersion,
         runtimeConfig: runtimeContext.config,
         aimAssistMode: headlessConfig.aimAssistMode,
+        lloydJobId: report?.lloydJobId,
     });
     const isBatchRun = ["directory", "selection", "scenario"].includes(instructionsTarget?.type);
     const cloudReportEnabled = report?.cloudEnabled !== false &&
@@ -470,6 +496,7 @@ export async function runHeadlessInstructionRuns({ runs, instructionsTarget, ses
         console.log(`\nRunning ${runs.length} tests from: ${instructionsTarget.path}\n`);
     }
     let failures = 0;
+    let reportMetadata = null;
     const batchStartedAt = Date.now();
     const aggregateStats = {
         durationMs: 0,
@@ -530,6 +557,7 @@ export async function runHeadlessInstructionRuns({ runs, instructionsTarget, ses
             if (result.reportModel) {
                 aggregateReportModels.push(result.reportModel);
             }
+            reportMetadata = result.loadmillReport ?? reportMetadata;
             if (result.localReportModel) {
                 aggregateLocalReportModels.push(result.localReportModel);
             }
@@ -642,12 +670,14 @@ export async function runHeadlessInstructionRuns({ runs, instructionsTarget, ses
                 childModels: aggregateReportModels,
             });
             logPendingScreenshotUploads(uploadManager, cloudUploadSession, "Run");
-            await uploadManager.finish(cloudUploadSession, {
+            const publication = await uploadManager.finish(cloudUploadSession, {
                 savedRunId: reportedRun.savedRunId,
                 html: renderCliCloudReport(aggregateReport.model, reportedRun.savedRunId),
             });
+            reportMetadata = loadmillReportMetadata(reportedRun.savedRunId, publication);
         }
     }
+    await writeLoadmillReportMetadata(report?.metadataPath, reportMetadata);
     return {
         exitCode: failures === 0 ? 0 : 1,
         failures

package/build/src/cli/loadmill-report-metadata.js

@@ -0,0 +1,7 @@
+import { rm } from "fs/promises";
+export async function clearLoadmillReportMetadata(filePath) {
+    if (!filePath) {
+        return;
+    }
+    await rm(filePath, { force: true });
+}

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

@@ -54,6 +54,7 @@ export async function handleHelp(args, session, context) {
     addOutput({ type: 'info', text: '  --explain              Explain non-obvious decisions and completion evidence' });
     addOutput({ type: 'info', text: '  --report [path]        Save a self-contained HTML report locally' });
     addOutput({ type: 'info', text: '  --no-cloud-report      Skip uploading the HTML report and screenshots to Loadmill' });
+    addOutput({ type: 'info', text: '  --report-metadata <path> Write uploaded Loadmill report metadata as JSON' });
     addOutput({ type: 'info', text: '  --debug                Enable structured JSONL debug artifacts' });
     addOutput({ type: 'info', text: '' });
     addOutput({ type: 'info', text: 'Interactive commands:' });

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/report/render-html-report.js

@@ -255,12 +255,36 @@ function renderCloudCard(events) {
 }
 function renderLoadmillCard(events) {
     const lines = events.map((event) => event.text.replace(/^\[Loadmill\]\s*/, "").trim());
+    const runId = events.map((event) => event.payload?.loadmillSuiteRunId)
+        .find((value) => typeof value === "string" && value.trim()) ??
+        lines.map((line) => line.match(/Test started \(ID:\s*([^)]+)\)/i)?.[1]?.trim() ||
+            line.match(/Run ID:\s*(.+)$/i)?.[1]?.trim()).find(Boolean);
+    const baseUrl = events.map((event) => event.payload?.loadmillBaseUrl)
+        .find((value) => typeof value === "string" && value.trim()) ?? "https://app.loadmill.com";
+    let runUrl = null;
+    if (runId) {
+        try {
+            const url = new URL(`${baseUrl.trim().replace(/\/$/, "")}/app/api-tests/test-suite-runs/${encodeURIComponent(runId.trim())}`);
+            if (url.protocol === "https:" || url.protocol === "http:")
+                runUrl = url.href;
+        }
+        catch {
+            // Keep the original log text when the recorded base URL is invalid.
+        }
+    }
+    const renderedLines = lines.map((line) => {
+        const started = line.match(/^Test started \(ID:\s*([^)]+)\)\.(.*)$/i);
+        const text = started && runUrl
+            ? `<a href="${escapeHtml(runUrl)}" target="_blank" rel="noreferrer">Test started</a>${renderLinkedText(started[2])}`
+            : renderLinkedText(line);
+        return `<div>${text}</div>`;
+    });
     const failed = events.some((event) => /\[Loadmill\]\s*FAILED|^Error:/i.test(event.text));
     const passed = !failed && events.some((event) => /\bpassed\b/i.test(event.text));
     const status = failed ? "failed" : passed ? "passed" : "running";
     return `<details class="dc-special dc-loadmill"${passed ? "" : " open"}>
   <summary><span class="dc-special-title">${ICONS.loadmill}Loadmill Flow</span><span class="dc-pill dc-pill-${status}">${status}</span></summary>
-  <div class="dc-special-body">${lines.map((line) => `<div>${renderLinkedText(line)}</div>`).join("")}</div>
+  <div class="dc-special-body">${renderedLines.join("")}</div>
 </details>`;
 }
 function renderTimeline(events, shots, warnings = []) {
@@ -464,10 +488,12 @@ ${STYLES}
 </style>
 </head>
 <body>
+<!--email_off-->
 <div class="dc-wrap" id="dc-top">
 <div class="dc-header"><div class="dc-title">Run Details: ${escapeHtml(heading)}</div><span class="dc-pill dc-pill-${escapeHtml(model.status)}">${escapeHtml(runStatusLabel(model.status))}</span></div>
 ${body}
 </div>${lightboxes ? `\n${lightboxes}` : ""}${script ? `\n${script}` : ""}
+<!--/email_off-->
 </body>
 </html>`;
 }