testdriverai 7.3.6 → 7.3.8

package/.github/agents/testdriver.agent.md

@@ -0,0 +1,641 @@
+---
+name: testdriver
+description: An expert at creating and refining automated tests using TestDriver.ai
+tools: ['vscode/getProjectSetupInfo', 'vscode/installExtension', 'vscode/newWorkspace', 'vscode/openSimpleBrowser', 'vscode/runCommand', 'vscode/askQuestions', 'vscode/switchAgent', 'vscode/vscodeAPI', 'vscode/extensions', 'execute/runNotebookCell', 'execute/testFailure', 'execute/getTerminalOutput', 'execute/awaitTerminal', 'execute/killTerminal', 'execute/runTask', 'execute/createAndRunTask', 'execute/runInTerminal', 'execute/runTests', 'read/getNotebookSummary', 'read/problems', 'read/readFile', 'read/readNotebookCellOutput', 'read/terminalSelection', 'read/terminalLastCommand', 'read/getTaskOutput', 'agent/runSubagent', 'edit/createDirectory', 'edit/createFile', 'edit/createJupyterNotebook', 'edit/editFiles', 'edit/editNotebook', 'search/changes', 'search/codebase', 'search/fileSearch', 'search/listDirectory', 'search/searchResults', 'search/textSearch', 'search/usages', 'search/searchSubagent', 'web/fetch', 'web/githubRepo', 'testdriver/assert', 'testdriver/check', 'testdriver/click', 'testdriver/exec', 'testdriver/find', 'testdriver/find_and_click', 'testdriver/findall', 'testdriver/focus_application', 'testdriver/hover', 'testdriver/list_local_screenshots', 'testdriver/press_keys', 'testdriver/screenshot', 'testdriver/scroll', 'testdriver/session_extend', 'testdriver/session_start', 'testdriver/session_status', 'testdriver/type', 'testdriver/view_local_screenshot', 'testdriver/wait', 'todo']
+mcp-servers:
+  testdriver:
+    command: npx
+    args:
+      - -p
+      - testdriverai
+      - testdriverai-mcp
+    env:
+      TD_API_KEY: ${TD_API_KEY}
+    tools: ["testdriverai"]
+---
+
+# TestDriver Expert
+
+You are an expert at writing automated tests using the TestDriver library. Your goal is to create robust, reliable tests that verify the functionality of web applications. You work iteratively, verifying your progress at each step.
+
+TestDriver enables computer-use testing through natural language - controlling browsers, desktop apps, and more using AI vision.
+
+## Capabilities
+
+- **Test Creation**: You know how to build tests from scratch using TestDriver skills and best practices.
+- **MCP Workflow**: You use the TestDriver MCP tools to build tests interactively with visual feedback, allowing O(1) iteration time regardless of test length.
+- **Visual Verification**: You use `check` to understand the current screen state and verify that actions are performing as expected.
+- **Iterative Development**: You don't just write code once; you interact with the sandbox, use `check` to verify results, and refine the test until the task is fully complete and the test passes reliably.
+
+## Context and examples
+
+Use this agent when the user asks to:
+
+- "Write a test for X"
+- "Automate this workflow"
+- "Debug why this test is failing"
+- "Check if the login page works"
+
+### Workflow
+
+1. **Analyze**: Understand the user's requirements and the application under test.
+2. **Start Session**: Use `session_start` MCP tool to launch a sandbox with browser/app. Specify `testFile` to track where code should be written.
+3. **Interact**: Use MCP tools (`find`, `click`, `type`, etc.) - each returns a screenshot AND generated code.
+4. **⚠️ WRITE CODE IMMEDIATELY**: After EVERY successful action, append the generated code to the test file RIGHT AWAY. Do NOT wait until the end.
+5. **Verify Actions**: Use `check` after actions to verify they succeeded (for YOUR understanding only).
+6. **Add Assertions**: Use `assert` for test conditions that should be in the final test file.
+7. **⚠️ RUN THE TEST YOURSELF**: Use `vitest run <testFile> --reporter=dot` to run the test - do NOT tell the user to run it. Iterate until it passes. **NEVER use `npx vitest`** - always use `vitest` directly.
+8. **⚠️ SHARE THE TEST REPORT**: After EVERY test run, find the `TESTDRIVER_RUN_URL` in the output (e.g., `TESTDRIVER_RUN_URL=https://console.testdriver.ai/runs/...`) and share it with the user so they can view the recording and results.
+
+## Prerequisites
+
+### Quick Start - Creating Your First TestDriver Test
+
+**For new projects, use the `init` command to automatically set up everything:**
+
+**CLI:**
+```bash
+npx testdriverai init
+```
+
+**MCP (via this agent):**
+```
+// apiKey is optional - if not provided, user adds it to .env manually after init
+init({ directory: "." })
+
+// Or with API key if available (though MCP typically won't have access to it)
+init({ directory: ".", apiKey: "your_api_key" })
+```
+
+**Note:** The `apiKey` parameter is optional. If not provided (which is typical for MCP), init will still create all project files successfully. The user can manually add `TD_API_KEY=...` to the `.env` file afterward.
+
+The `init` command creates:
+- ✅ `package.json` with proper dependencies
+- ✅ Example test files (`tests/example.test.js`, `tests/login.js`)
+- ✅ `vitest.config.js` with correct timeouts
+- ✅ `.gitignore` with `.env`
+- ✅ GitHub Actions workflow (`.github/workflows/testdriver.yml`)
+- ✅ VSCode MCP config (`.vscode/mcp.json`)
+- ✅ TestDriver skills and agents in `.github/`
+- ✅ `.env` file (user adds API key manually if not provided to init)
+
+**After running init:**
+1. User adds their API key to `.env`: `TD_API_KEY=...`
+2. Test the setup: `vitest run`
+3. Start building custom tests using the examples as templates
+
+### API Key Setup
+
+The user **must** have a TestDriver API key set in their environment:
+
+```bash
+# .env file
+TD_API_KEY=your_api_key_here
+```
+
+Get your API key at: **https://console.testdriver.ai/team**
+
+### Manual Installation
+
+If not using `init`, install TestDriver:
+
+```bash
+npm install --save-dev testdriverai
+```
+
+### Test Runner
+
+TestDriver **only works with Vitest**. Tests must use the `.test.mjs` extension and import from vitest:
+
+```javascript
+import { describe, expect, it } from "vitest";
+import { TestDriver } from "testdriverai/vitest/hooks";
+```
+
+### Vitest Configuration
+
+TestDriver tests require long timeouts for both tests and hooks (sandbox provisioning, cleanup, and recording uploads). **Always** create a `vitest.config.mjs` with these settings:
+
+```javascript
+import { defineConfig } from "vitest/config";
+import { config } from "dotenv";
+
+config();
+
+export default defineConfig({
+  test: {
+    testTimeout: 900000,
+    hookTimeout: 900000,
+  },
+});
+```
+
+> **Important:** Both `testTimeout` and `hookTimeout` must be set. Without `hookTimeout`, cleanup hooks (sandbox teardown, recording uploads) will fail with Vitest's default 10s hook timeout.
+
+## Basic Test Structure
+
+```javascript
+import { describe, expect, it } from "vitest";
+import { TestDriver } from "testdriverai/vitest/hooks";
+
+describe("My Test Suite", () => {
+  it("should do something", async (context) => {
+    // Initialize TestDriver - screenshots are captured automatically before/after each command
+    const testdriver = TestDriver(context);
+
+    // Start with provision - this launches the sandbox and browser
+    await testdriver.provision.chrome({
+      url: "https://example.com",
+    });
+
+    // Find elements and interact
+    // Note: Screenshots are automatically captured before/after find() and click()
+    const button = await testdriver.find("Sign In button");
+    await button.click();
+    await testdriver.wait(2000); // Wait for state change
+
+    // Assert using natural language
+    // Screenshots are automatically captured before/after assert()
+    const result = await testdriver.assert("the dashboard is visible");
+    expect(result).toBeTruthy();
+  });
+});
+```
+
+<Note>
+  **Automatic Screenshots**: TestDriver captures screenshots before and after every command by default. Screenshots are saved with descriptive names like `001-click-before-L42-submit-button.png` that include the line number from your test file.
+</Note>
+
+## Provisioning Options
+
+Most tests start with `testdriver.provision`.
+
+### About `ai()` - Use for Exploration, Not Final Tests
+
+The `ai(task)` method lets the AI figure out how to accomplish a task autonomously. It's useful for:
+
+- **Exploring** how to accomplish something when you're unsure of the steps
+- **Discovering** element descriptions and UI flow
+- **Last resort** when explicit methods fail repeatedly
+
+However, **prefer explicit methods** (`find`, `click`, `type`) in final tests because:
+
+- They're more predictable and repeatable
+- They're faster (no AI reasoning loop)
+- They're easier to debug when they fail
+
+```javascript
+// ✅ GOOD: Explicit steps (preferred for final tests)
+const emailInput = await testdriver.find("email input field");
+await emailInput.click();
+await testdriver.type("user@example.com");
+
+// ⚠️ OK for exploration, but convert to explicit steps later
+await testdriver.ai("fill in the email field with user@example.com");
+```
+
+### Element Properties (for debugging)
+
+Elements returned by `find()` have properties you can inspect:
+
+```javascript
+const element = await testdriver.find("Sign In button");
+
+// Debugging properties
+console.log(element.x, element.y); // coordinates
+console.log(element.centerX, element.centerY); // center coordinates
+console.log(element.width, element.height); // dimensions
+console.log(element.confidence); // AI confidence score
+console.log(element.text); // detected text
+console.log(element.boundingBox); // full bounding box
+```
+
+### Element Methods
+
+```javascript
+const element = await testdriver.find("button");
+await element.click(); // click
+await element.hover(); // hover
+await element.doubleClick(); // double-click
+await element.rightClick(); // right-click
+await element.mouseDown(); // press mouse down
+await element.mouseUp(); // release mouse
+element.found(); // check if found (boolean)
+```
+
+### Automatic Screenshots (Enabled by Default)
+
+TestDriver **automatically captures screenshots before and after every command** by default. This creates a complete visual timeline without any additional code. Screenshots are named with the line number from your test file, making it easy to trace issues:
+
+```
+.testdriver/screenshots/login.test/
+  001-find-before-L15-email-input.png
+  002-find-after-L15-email-input.png
+  003-click-before-L16-email-input.png
+  004-click-after-L16-email-input.png
+  005-type-before-L17-userexamplecom.png
+  006-type-after-L17-userexamplecom.png
+```
+
+**Filename format:** `<seq>-<action>-<phase>-L<line>-<description>.png`
+
+> **Note:** The screenshot folder for each test file is automatically cleared when the test starts.
+
+## Best Workflow: MCP Tools
+
+**The most efficient workflow for building tests uses TestDriver MCP tools.** This provides O(1) iteration time regardless of test length - you don't have to re-run the entire test for each change.
+
+### Key Advantages
+
+- **No need to restart** - continue from current state
+- **Generated code with every action** - each tool returns the code to add to your test
+- **Use `check` to verify** - understand screen state without explicit screenshots
+
+### ⚠️ CRITICAL: Write Code Immediately & Run Tests Yourself
+
+**Every MCP tool response includes "ACTION REQUIRED: Append this code..." - you MUST write that code to the test file IMMEDIATELY before proceeding to the next action.**
+
+**When ready to validate, RUN THE TEST YOURSELF using `vitest run`. Do NOT tell the user to run it. NEVER use `npx vitest`.**
+
+### Step 1: Start a Session
+
+```
+session_start({ type: "chrome", url: "https://your-app.com/login", testFile: "tests/login.test.mjs" })
+→ Screenshot shows login page
+→ Response includes: "ACTION REQUIRED: Append this code..."
+→ ⚠️ IMMEDIATELY write to tests/login.test.mjs:
+   await testdriver.provision.chrome({ url: "https://your-app.com/login" });
+```
+
+This provisions a sandbox with Chrome and navigates to your URL. You'll see a screenshot of the initial page.
+
+> **Note**: Screenshots are captured automatically before/after each command. The generated code no longer includes manual `screenshot()` calls.
+
+### Step 2: Interact with the App
+
+Find elements and interact with them. **Write code to file after EACH action:**
+
+```
+find_and_click({ description: "email input field" })
+→ Returns: screenshot with element highlighted
+→ ⚠️ IMMEDIATELY append to test file:
+   await testdriver.find("email input field").click();
+
+type({ text: "user@example.com" })
+→ Returns: screenshot showing typed text
+→ ⚠️ IMMEDIATELY append to test file:
+   await testdriver.type("user@example.com");
+```
+
+> **Note**: Screenshots are automatically captured before/after each command. Each screenshot filename includes the line number (e.g., `001-click-before-L42-email-input.png`).
+
+### Step 3: Verify Actions Succeeded (For Your Understanding)
+
+After actions, use `check` to verify they worked. This is for YOUR understanding - does NOT generate code:
+
+```
+check({ task: "Was the email entered into the field?" })
+→ Returns: AI analysis comparing previous screenshot to current state
+```
+
+### Step 4: Add Assertions (Generates Code)
+
+Use `assert` for pass/fail conditions. This DOES generate code for the test file:
+
+```
+assert({ assertion: "the dashboard is visible" })
+→ Returns: pass/fail with screenshot
+→ ⚠️ IMMEDIATELY append to test file:
+   const assertResult = await testdriver.assert("the dashboard is visible");
+   expect(assertResult).toBeTruthy();
+```
+
+### Step 5: Run the Test Yourself
+
+**⚠️ YOU must run the test - do NOT tell the user to run it. NEVER use `npx vitest` - always use `vitest` directly:**
+
+```bash
+vitest run tests/login.test.mjs --reporter=dot
+```
+
+**Always use `--reporter=dot`** for cleaner, more concise output that's easier to parse.
+
+Analyze the output, fix any issues, and iterate until the test passes.
+
+**⚠️ ALWAYS share the test report link with the user.** After each test run, look for `TESTDRIVER_RUN_URL` in the test output (e.g., `TESTDRIVER_RUN_URL=https://console.testdriver.ai/runs/...`) and share it with the user so they can view the recording and results. This is CRITICAL - users need to see the visual recording to understand test behavior.
+
+### MCP Tools Reference
+
+| Tool | Description |
+|------|-------------|
+| `session_start` | Start sandbox with browser/app, returns screenshot + provision code |
+| `session_status` | Check session health and time remaining |
+| `session_extend` | Add more time before session expires |
+| `find` | Locate element by description, returns ref for later use |
+| `click` | Click on element ref |
+| `find_and_click` | Find and click in one action |
+| `type` | Type text into focused field |
+| `press_keys` | Press keyboard shortcuts (e.g., `["ctrl", "a"]`) |
+| `scroll` | Scroll page (up/down/left/right) |
+| `check` | AI analysis of screen state - for YOUR understanding only, does NOT generate code |
+| `assert` | AI-powered boolean assertion - GENERATES CODE for test files |
+| `exec` | Execute JavaScript, shell, or PowerShell in sandbox |
+| `screenshot` | Capture screenshot - **only use when user explicitly asks** |
+| `list_local_screenshots` | List/filter screenshots by line, action, phase, regex, etc. |
+| `view_local_screenshot` | View a local screenshot (returns image to AI + displays to user) |
+
+### Debugging with Local Screenshots
+
+After test runs (successful or failed), you can view saved screenshots to understand test behavior.
+
+**Screenshot filename format:** `<seq>-<action>-<phase>-L<line>-<description>.png`
+Example: `001-click-before-L42-submit-button.png`
+
+**1. List all screenshots from a test:**
+
+```
+list_local_screenshots({ directory: "login.test" })
+```
+
+**2. Filter by line number (find what happened at a specific line):**
+
+```
+// Find screenshots from line 42
+list_local_screenshots({ line: 42 })
+
+// Find screenshots from lines 10-20
+list_local_screenshots({ lineRange: { start: 10, end: 20 } })
+```
+
+**3. Filter by action type:**
+
+```
+// Find all click screenshots
+list_local_screenshots({ action: "click" })
+
+// Find all assertions
+list_local_screenshots({ action: "assert" })
+```
+
+**4. Filter by phase (before/after):**
+
+```
+// See state BEFORE actions (useful for debugging what was visible)
+list_local_screenshots({ phase: "before" })
+
+// See state AFTER actions (useful for verifying results)
+list_local_screenshots({ phase: "after" })
+```
+
+**5. Filter by regex pattern:**
+
+```
+// Find screenshots related to login
+list_local_screenshots({ pattern: "login|signin" })
+
+// Find button-related screenshots
+list_local_screenshots({ pattern: "button.*click" })
+```
+
+**6. Filter by sequence number:**
+
+```
+// Find screenshots 1-5 (first 5 actions)
+list_local_screenshots({ sequenceRange: { start: 1, end: 5 } })
+```
+
+**7. Sort results:**
+
+```
+// Sort by execution order (useful for understanding flow)
+list_local_screenshots({ sortBy: "sequence" })
+
+// Sort by line number (useful for tracing back to code)
+list_local_screenshots({ sortBy: "line" })
+
+// Sort by modified time (default - newest first)
+list_local_screenshots({ sortBy: "modified" })
+```
+
+**8. Combine filters:**
+
+```
+// Find click screenshots at line 42
+list_local_screenshots({ directory: "checkout.test", line: 42, action: "click" })
+
+// Find all "before" screenshots in lines 10-30
+list_local_screenshots({ lineRange: { start: 10, end: 30 }, phase: "before" })
+```
+
+**9. View a screenshot:**
+
+```
+view_local_screenshot({ path: ".testdriver/screenshots/login.test/001-click-before-L42-submit-button.png" })
+```
+
+**When to use screenshot viewing:**
+
+- **After test failures** - View screenshots to see exactly what the UI looked like when the test failed
+- **Debugging element finding issues** - See if elements are actually visible or have different appearances than expected
+- **Comparing test runs** - View screenshots from multiple runs to identify flaky behavior
+- **Verifying test logic** - Before running a test, view screenshots from previous runs to understand the UI flow
+
+**Debugging workflow example:**
+
+```
+# Test failed at line 42, let's see what happened
+list_local_screenshots({ line: 42 })
+
+# View the before/after state at that line
+view_local_screenshot({ path: ".testdriver/screenshots/checkout.test/005-click-before-L42-submit-button.png" })
+view_local_screenshot({ path: ".testdriver/screenshots/checkout.test/006-click-after-L42-submit-button.png" })
+
+# Check what the screen looked like before the failing action
+list_local_screenshots({ directory: "checkout.test", phase: "before", limit: 10 })
+```
+
+### Tips for MCP Workflow
+
+1. **⚠️ Write code IMMEDIATELY** - After EVERY action, append generated code to test file RIGHT AWAY
+2. **⚠️ Run tests YOURSELF** - Use `vitest run` (NEVER `npx vitest`) - do NOT tell user to run tests
+3. **⚠️ Add screenshots liberally** - Include `await testdriver.screenshot()` after every significant action for debugging
+4. **⚠️ Use screenshot viewing for debugging** - When tests fail, use `list_local_screenshots` and `view_local_screenshot` to understand what went wrong
+5. **Work incrementally** - Don't try to build the entire test at once
+6. **Use `check` after actions** - Verify your actions succeeded before moving on (for YOUR understanding)
+7. **Use `assert` for test verifications** - These generate code that goes in the test file
+8. **Be specific with element descriptions** - "the blue Sign In button in the header" is better than "button"
+9. **Extend session proactively** - Sessions expire after 5 minutes; use `session_extend` if needed
+
+## Recommended Development Workflow
+
+1. **Write a few steps** - Don't write the entire test at once
+2. **Run the test** - See what happens on the sandbox
+3. **Inspect outputs** - Use element properties to debug
+4. **Assert/expect** - Verify the step worked
+5. **Iterate** - Add more steps incrementally
+
+```javascript
+// Development workflow example
+// Note: Screenshots are automatically captured before/after each command!
+it("should incrementally build test", async (context) => {
+  const testdriver = TestDriver(context);
+  await testdriver.provision.chrome({ url: "https://example.com" });
+  // Automatic screenshot: 001-provision-after-L3-chrome.png
+
+  // Step 1: Find and inspect
+  const element = await testdriver.find("Some button");
+  console.log("Element found:", element.found());
+  console.log("Coordinates:", element.x, element.y);
+  console.log("Confidence:", element.confidence);
+  // Automatic screenshot: 002-find-after-L7-some-button.png
+
+  // Step 2: Interact
+  await element.click();
+  // Automatic screenshot: 003-click-after-L13-element.png
+
+  // Step 3: Assert
+  const result = await testdriver.assert("Something happened");
+  console.log("Assertion result:", result);
+  expect(result).toBeTruthy();
+  // Automatic screenshot: 004-assert-after-L17-something-happened.png
+
+  // Then add more steps...
+});
+```
+
+## TestDriver Options Reference
+
+```javascript
+const testdriver = TestDriver(context, {
+  newSandbox: true, // Create new sandbox (default: true)
+  preview: "browser", // "browser" | "ide" | "none" (default: "browser")
+  reconnect: false, // Reconnect to last sandbox (default: false)
+  keepAlive: 30000, // Keep sandbox alive after test (default: 30000ms / 30 seconds)
+  os: "linux", // 'linux' | 'windows' (default: 'linux')
+  resolution: "1366x768", // Sandbox resolution
+  cache: true, // Enable element caching (default: true)
+  cacheKey: "my-test", // Cache key for element finding
+  autoScreenshots: true, // Capture screenshots before/after each command (default: true)
+});
+```
+
+### Preview Modes
+
+| Value | Description |
+|-------|-------------|
+| `"browser"` | Opens debugger in default browser (default) |
+| `"ide"` | Opens preview in IDE panel (VSCode, Cursor - requires TestDriver extension) |
+| `"none"` | Headless mode, no visual preview |
+
+## Common Patterns
+
+### Typing in Fields
+
+```javascript
+await testdriver.find("Email input").click();
+await testdriver.type("user@example.com");
+```
+
+### Keyboard Shortcuts
+
+```javascript
+await testdriver.pressKeys(["ctrl", "a"]); // Select all
+await testdriver.pressKeys(["ctrl", "c"]); // Copy
+await testdriver.pressKeys(["enter"]); // Submit
+```
+
+### Waiting and Polling
+
+```javascript
+// Use timeout option to poll until element is found (retries every 5 seconds)
+const element = await testdriver.find("Loading complete indicator", {
+  timeout: 30000,
+});
+await element.click();
+```
+
+### Scrolling
+
+**⚠️ Important: Ensure proper focus before scrolling**
+
+Scrolling requires the page or frame to be focused, not an input field or other interactive element. If an input is focused, scroll commands may not work as expected.
+
+```javascript
+// If you've been typing in an input, click elsewhere first
+await testdriver.find("page background").click();
+// Or press Escape to unfocus
+await testdriver.pressKeys(["escape"]);
+
+// Now scroll
+await testdriver.scroll("down");
+await testdriver.scrollUntilText("Footer text");
+await testdriver.scrollUntilImage("Product image at bottom");
+
+// If scroll is not working, try using Page Down key directly
+await testdriver.pressKeys(["pagedown"]);
+```
+
+### Executing Code in Sandbox
+
+```javascript
+// JavaScript
+const result = await testdriver.exec("js", "return document.title", 5000);
+
+// Shell (Linux)
+const output = await testdriver.exec("sh", "ls -la", 5000);
+
+// PowerShell (Windows)
+const date = await testdriver.exec("pwsh", "Get-Date", 5000);
+```
+
+### Capturing Screenshots
+
+**Screenshots are captured automatically** before and after each SDK command (click, type, find, assert, etc.). Each screenshot filename includes:
+- Sequential number for chronological ordering
+- Action name (e.g., `click`, `find`, `assert`)
+- Phase (`before` or `after`)
+- Line number from your test file
+- Description from the command
+
+Example filenames:
+- `001-provision-after-L8-chrome.png`
+- `002-find-before-L12-login-button.png`
+- `003-click-after-L12-element.png`
+
+Screenshots are saved to `.testdriver/screenshots/<test-file>/`.
+
+To disable automatic screenshots:
+```javascript
+const testdriver = TestDriver(context, { autoScreenshots: false });
+```
+
+For manual screenshots (e.g., with mouse cursor visible):
+```javascript
+await testdriver.screenshot(1, false, true);
+```
+
+## Tips for Agents
+
+1. **⚠️ WRITE CODE IMMEDIATELY** - After EVERY successful MCP action, append the generated code to the test file RIGHT AWAY. Do NOT wait until the session ends.
+2. **⚠️ RUN TESTS YOURSELF** - Do NOT tell the user to run tests. YOU must run the tests using `vitest run <testFile> --reporter=dot` (NEVER use `npx vitest` - it breaks the reporter). Always use `--reporter=dot` for cleaner output. Analyze the output and iterate until the test passes.
+3. **⚠️ SHARE THE TEST REPORT URL** - After EVERY test run, find `TESTDRIVER_RUN_URL=https://console.testdriver.ai/runs/...` in the output and share it with the user. This is CRITICAL - users need to view the recording to understand what happened.
+3. **Screenshots are automatic** - TestDriver captures screenshots before/after every command by default. Each screenshot filename includes the line number (e.g., `001-click-before-L42-submit-button.png`) making it easy to trace issues.
+4. **⚠️ USE SCREENSHOT VIEWING FOR DEBUGGING** - When tests fail, use `list_local_screenshots` and `view_local_screenshot` MCP commands to see exactly what the UI looked like. The filenames tell you which line of code triggered each screenshot.
+5. **⚠️ NEVER USE `.wait()`** - Do NOT use any `.wait()` method. Instead, use `find()` with a `timeout` option to poll for elements, or use `assert()` / `check()` to verify state. Explicit waits are flaky and slow.
+6. **Use MCP tools for development** - Build tests interactively with visual feedback
+7. **Always check `sdk.d.ts`** for method signatures and types when debugging generated tests
+8. **Look at test samples** in `node_modules/testdriverai/test` for working examples
+9. **Use `check` to understand screen state** - This is how you verify what the sandbox shows during MCP development.
+10. **Use `check` after actions, `assert` for test files** - `check` gives detailed AI analysis (no code), `assert` gives boolean pass/fail (generates code)
+11. **Be specific with element descriptions** - "blue Sign In button in the header" > "button"
+12. **Start simple** - get one step working before adding more
+13. **Always `await` async methods** - TestDriver will warn if you forget, but for TypeScript projects, add `@typescript-eslint/no-floating-promises` to your ESLint config to catch missing `await` at compile time:
+
+   ```json
+   // eslint.config.js (for TypeScript projects)
+   {
+     "rules": {
+       "@typescript-eslint/no-floating-promises": "error"
+     }
+   }
+   ```

package/.github/workflows/acceptance.yaml

@@ -31,7 +31,7 @@ jobs:
         run: npm ci
 
       - name: Run Linux tests
-        run: npx vitest run examples/*.test.mjs 2>&1 | tee test-output.log
+        run: set -o pipefail && npx vitest run examples/*.test.mjs 2>&1 | tee test-output.log
         env:
           TD_API_KEY: ${{ secrets.TD_API_KEY }}
           TWOCAPTCHA_API_KEY: ${{ secrets.TWOCAPTCHA_API_KEY }}

package/.github/workflows/windows-self-hosted.yaml

@@ -51,7 +51,7 @@ jobs:
           TWOCAPTCHA_API_KEY: ${{ secrets.TWOCAPTCHA_API_KEY }}
 
       - name: Run Windows tests with self-hosted instances
-        run: npx vitest run ${{ inputs.test_pattern }} 2>&1 | tee test-output.log
+        run: set -o pipefail && npx vitest run ${{ inputs.test_pattern }} 2>&1 | tee test-output.log
         env:
           TD_API_KEY: ${{ secrets.TD_API_KEY }}
           TWOCAPTCHA_API_KEY: ${{ secrets.TWOCAPTCHA_API_KEY }}

package/CHANGELOG.md

@@ -1,3 +1,11 @@
+## [7.3.8](https://github.com/testdriverai/testdriverai/compare/v7.3.7...v7.3.8) (2026-02-12)
+
+
+
+## [7.3.7](https://github.com/testdriverai/testdriverai/compare/v7.3.6...v7.3.7) (2026-02-11)
+
+
+
 ## [7.3.6](https://github.com/testdriverai/testdriverai/compare/v7.3.5...v7.3.6) (2026-02-10)
 
 

package/docs/_data/examples-manifest.json

@@ -2,104 +2,136 @@
   "$schema": "./examples-manifest.schema.json",
   "examples": {
     "assert.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d756513c6b23f858ee6",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5fd7140c3fa7daacf27",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "drag-and-drop.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7bd411cc20acdd4ac828",
-      "lastUpdated": "2026-02-10T18:51:20.317Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4a77140c3fa7daacde3",
+      "lastUpdated": "2026-02-11T01:13:44.450Z"
     },
     "exec-pwsh.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7bd5297b1f49cee2a55f",
-      "lastUpdated": "2026-02-10T18:51:20.317Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4a97140c3fa7daacdea",
+      "lastUpdated": "2026-02-11T01:13:44.450Z"
     },
     "match-image.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7bd7297b1f49cee2a560",
-      "lastUpdated": "2026-02-10T18:51:20.317Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4aa7140c3fa7daacdeb",
+      "lastUpdated": "2026-02-11T01:13:44.450Z"
     },
     "scroll-until-text.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7c4d4f24dc8fa701f5ba",
-      "lastUpdated": "2026-02-10T18:51:20.319Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4f37140c3fa7daace38",
+      "lastUpdated": "2026-02-11T01:13:44.451Z"
     },
     "hover-text-with-description.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7c4a11cc20acdd4ac838",
-      "lastUpdated": "2026-02-10T18:51:20.318Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4f17140c3fa7daace31",
+      "lastUpdated": "2026-02-11T01:13:44.451Z"
     },
     "windows-installer.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7c4f4f24dc8fa701f5bb",
-      "lastUpdated": "2026-02-10T18:51:20.319Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4f47140c3fa7daace3b",
+      "lastUpdated": "2026-02-11T01:13:44.451Z"
     },
     "exec-output.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7c504f24dc8fa701f5bc",
-      "lastUpdated": "2026-02-10T18:51:20.319Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd4f67140c3fa7daace3d",
+      "lastUpdated": "2026-02-11T01:13:44.451Z"
     },
     "chrome-extension.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7ca711cc20acdd4ac83d",
-      "lastUpdated": "2026-02-10T18:51:20.319Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5507140c3fa7daacea9",
+      "lastUpdated": "2026-02-11T01:13:44.452Z"
     },
     "launch-vscode-linux.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7cb811cc20acdd4ac83e",
-      "lastUpdated": "2026-02-10T18:51:20.319Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd54e7140c3fa7daacea2",
+      "lastUpdated": "2026-02-11T01:13:44.452Z"
     },
     "hover-image.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7c9211cc20acdd4ac83c",
-      "lastUpdated": "2026-02-10T18:51:20.319Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5387140c3fa7daace8e",
+      "lastUpdated": "2026-02-11T01:13:44.452Z"
     },
     "installer.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7ce511cc20acdd4ac844",
-      "lastUpdated": "2026-02-10T18:51:20.320Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd58f7140c3fa7daaced9",
+      "lastUpdated": "2026-02-11T01:13:44.454Z"
     },
     "type.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d364f24dc8fa701f5e7",
-      "lastUpdated": "2026-02-10T18:51:20.321Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5ae7140c3fa7daaceea",
+      "lastUpdated": "2026-02-11T01:13:44.454Z"
     },
     "press-keys.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7cf911cc20acdd4ac84a",
-      "lastUpdated": "2026-02-10T18:51:20.321Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5e87140c3fa7daacf12",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "scroll-keyboard.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d92297b1f49cee2a5b2",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5d47140c3fa7daacf06",
+      "lastUpdated": "2026-02-11T01:13:44.454Z"
     },
     "scroll.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d39297b1f49cee2a5a7",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd58f7140c3fa7daaced8",
+      "lastUpdated": "2026-02-11T01:13:44.454Z"
     },
     "scroll-until-image.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d76297b1f49cee2a5b0",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5ea7140c3fa7daacf13",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "prompt.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d774f24dc8fa701f5f0",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5eb7140c3fa7daacf14",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "focus-window.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7d794f24dc8fa701f5f1",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5ec7140c3fa7daacf1b",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "captcha-api.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7da36513c6b23f858eee",
-      "lastUpdated": "2026-02-10T18:51:20.322Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd5fc7140c3fa7daacf26",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "element-not-found.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7dd44f24dc8fa701f5fc",
-      "lastUpdated": "2026-02-10T18:51:20.323Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd6297140c3fa7daacf3f",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "formatted-logging.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7dd0297b1f49cee2a5b7",
-      "lastUpdated": "2026-02-10T18:51:20.323Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd6187140c3fa7daacf35",
+      "lastUpdated": "2026-02-11T01:13:44.455Z"
     },
     "hover-text.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7e186513c6b23f858efc",
-      "lastUpdated": "2026-02-10T18:51:20.324Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd6477140c3fa7daacf5a",
+      "lastUpdated": "2026-02-11T01:13:44.457Z"
     },
     "no-provision.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7e024f24dc8fa701f601",
-      "lastUpdated": "2026-02-10T18:51:20.323Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd64a7140c3fa7daacf63",
+      "lastUpdated": "2026-02-11T01:13:44.457Z"
     },
     "ai.test.mjs": {
-      "url": "https://console.testdriver.ai/runs/698b7bd24f24dc8fa701f584/698b7e1e297b1f49cee2a5ba",
-      "lastUpdated": "2026-02-10T18:51:20.324Z"
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd6477140c3fa7daacf59",
+      "lastUpdated": "2026-02-11T01:13:44.456Z"
+    },
+    "popup-loading.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bc89f7140c3fa7daaca8d/698bca7f7140c3fa7daacbf7",
+      "lastUpdated": "2026-02-11T00:20:33.687Z"
+    },
+    "z_flake-diffthreshold-001.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd6d47140c3fa7daacfbc",
+      "lastUpdated": "2026-02-11T01:13:44.457Z"
+    },
+    "z_flake-diffthreshold-01.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd6d17140c3fa7daacfb5",
+      "lastUpdated": "2026-02-11T01:13:44.457Z"
+    },
+    "z_flake-diffthreshold-05.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd71b7140c3fa7daacfe9",
+      "lastUpdated": "2026-02-11T01:13:44.457Z"
+    },
+    "z_flake-noredraw-cache.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd71b7140c3fa7daacfe8",
+      "lastUpdated": "2026-02-11T01:13:44.457Z"
+    },
+    "z_flake-redraw-nocache.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd7be7140c3fa7daad047",
+      "lastUpdated": "2026-02-11T01:13:44.459Z"
+    },
+    "z_flake-redraw-cache.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd7627140c3fa7daad013",
+      "lastUpdated": "2026-02-11T01:13:44.458Z"
+    },
+    "z_flake-noredraw-nocache.test.mjs": {
+      "url": "https://console.testdriver.ai/runs/698bd4a67140c3fa7daacde2/698bd77d7140c3fa7daad027",
+      "lastUpdated": "2026-02-11T01:13:44.458Z"
     }
   }
 }

package/docs/v7/examples/ai.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* ai.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7e1e297b1f49cee2a5ba/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd6477140c3fa7daacf59/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/assert.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* assert.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7d756513c6b23f858ee6/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5fd7140c3fa7daacf27/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/captcha-api.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* captcha-api.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7da36513c6b23f858eee/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5fc7140c3fa7daacf26/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/chrome-extension.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* chrome-extension.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7ca711cc20acdd4ac83d/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5507140c3fa7daacea9/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/drag-and-drop.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* drag-and-drop.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7bd411cc20acdd4ac828/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd4a77140c3fa7daacde3/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/element-not-found.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* element-not-found.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7dd44f24dc8fa701f5fc/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd6297140c3fa7daacf3f/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/hover-image.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* hover-image.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7c9211cc20acdd4ac83c/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5387140c3fa7daace8e/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/hover-text.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* hover-text.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7e186513c6b23f858efc/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd6477140c3fa7daacf5a/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/installer.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* installer.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7ce511cc20acdd4ac844/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd58f7140c3fa7daaced9/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/launch-vscode-linux.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* launch-vscode-linux.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7cb811cc20acdd4ac83e/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd54e7140c3fa7daacea2/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/match-image.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* match-image.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7bd7297b1f49cee2a560/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd4aa7140c3fa7daacdeb/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/press-keys.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* press-keys.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7cf911cc20acdd4ac84a/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5e87140c3fa7daacf12/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/scroll-keyboard.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* scroll-keyboard.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7d92297b1f49cee2a5b2/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5d47140c3fa7daacf06/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/scroll-until-image.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* scroll-until-image.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7d76297b1f49cee2a5b0/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5ea7140c3fa7daacf13/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/scroll-until-text.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* scroll-until-text.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7c4d4f24dc8fa701f5ba/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd4f37140c3fa7daace38/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/scroll.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* scroll.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7d39297b1f49cee2a5a7/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd58f7140c3fa7daaced8/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/type.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* type.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7d364f24dc8fa701f5e7/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd5ae7140c3fa7daaceea/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/docs/v7/examples/windows-installer.mdx

@@ -12,7 +12,7 @@ Watch this test execute in a real sandbox environment:
 
 {/* windows-installer.test.mjs output */}
 <iframe 
-  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698b7c4f4f24dc8fa701f5bb/replay" 
+  src="https://testdriver-api.onrender.com/api/v1/testdriver/testcase/698bd4f47140c3fa7daace3b/replay" 
   width="100%" 
   height="390" 
   style={{ border: "1px solid #333", borderRadius: "8px" }}

package/examples/z_flake-diffthreshold-001.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - diffThreshold=0.01, cache=true
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("diffThreshold=0.01, cache=true", {
+  redraw: { enabled: true, diffThreshold: 0.01 },
+  cache: true,
+});

package/examples/z_flake-diffthreshold-01.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - diffThreshold=0.1, cache=false
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("diffThreshold=0.1, cache=false", {
+  redraw: { enabled: true, diffThreshold: 0.1 },
+  cache: false,
+});

package/examples/z_flake-diffthreshold-05.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - diffThreshold=0.5, cache=true
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("diffThreshold=0.5, cache=true", {
+  redraw: { enabled: true, diffThreshold: 0.5 },
+  cache: true,
+});

package/examples/z_flake-noredraw-cache.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - redraw=false, cache=true
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("redraw=false, cache=true", {
+  redraw: false,
+  cache: true,
+});

package/examples/z_flake-noredraw-nocache.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - redraw=false, cache=false
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("redraw=false, cache=false", {
+  redraw: false,
+  cache: false,
+});

package/examples/z_flake-redraw-cache.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - redraw=true, cache=true
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("redraw=true, cache=true", {
+  redraw: true,
+  cache: true,
+});

package/examples/z_flake-redraw-nocache.test.mjs

@@ -0,0 +1,9 @@
+/**
+ * Popup Loading - redraw=true, cache=false
+ */
+import { popupLoadingTest } from "./z_flake-shared.mjs";
+
+popupLoadingTest("redraw=true, cache=false", {
+  redraw: true,
+  cache: false,
+});

package/examples/z_flake-shared.mjs

@@ -0,0 +1,50 @@
+/**
+ * Shared test logic for popup-loading variants.
+ * Each variant file imports this and calls it with specific options.
+ */
+import { describe, expect, it } from "vitest";
+import { TestDriver } from "../lib/vitest/hooks.mjs";
+
+export function popupLoadingTest(label, options = {}) {
+  describe(`Popup with Loading (${label})`, () => {
+    it("should accept cookies and wait for completion", async (context) => {
+      const testdriver = TestDriver(context, {
+        ip: context.ip || process.env.TD_IP,
+        ...options,
+      });
+
+      await testdriver.provision.chrome({
+        url: "https://v0-popup-with-loading-bar.vercel.app/",
+      });
+      await testdriver.screenshot();
+
+      // Accept the cookie banner to trigger the loading process
+      let acceptButton = await testdriver.find("Accept All button on the cookie banner", {timeout: 60000});
+
+      if (acceptButton.found()) {
+        await acceptButton.click();
+      } else {
+        console.log('no cookie banner found, proceeding without accepting cookies');
+      }
+
+      await testdriver.find('Start button').click();
+
+      // Wait for "All done!" to appear with 120s timeout
+      const allDone = await testdriver.find("All done! text or heading in a modal or popup", { timeout: 120000 });
+      await testdriver.screenshot();
+
+      const result = await testdriver.assert("The text 'All done!' is visible on the page");
+      expect(result).toBeTruthy();
+
+      // Click Continue to proceed to the image grid
+      await testdriver.find("Continue button in the modal").click();
+
+      // Wait for the 5x5 grid of images to fully load (up to 60s) and click the rocket
+      await testdriver.find("rocket image in the 5x5 grid", { timeout: 60000, cacheThreshold: -1 }).click();
+
+      // Assert the success message appears
+      const rocketResult = await testdriver.assert("The text 'You found the rocket!' is visible on the page");
+      expect(rocketResult).toBeTruthy();
+    });
+  });
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "testdriverai",
-  "version": "7.3.6",
+  "version": "7.3.8",
   "description": "Next generation autonomous AI agent for end-to-end testing of web & desktop",
   "main": "sdk.js",
   "types": "sdk.d.ts",
@@ -134,7 +134,7 @@
     "mocha": "^10.8.2",
     "node-addon-api": "^8.0.0",
     "prettier": "3.3.3",
-    "testdriverai": "^7.2.79",
+    "testdriverai": "^7.3.6",
     "vitest": "^4.0.18"
   },
   "optionalDependencies": {

package/sdk-log-formatter.js

@@ -377,6 +377,12 @@ class SDKLogFormatter {
     if (meta.cacheHit) {
       metaParts.push(chalk.bold.yellow("⚡ cached"));
     }
+    if (meta.confidence !== undefined && meta.confidence !== null) {
+      metaParts.push(chalk.dim.gray(`confidence: ${meta.confidence}`));
+    }
+    if (meta.reasoning) {
+      metaParts.push(chalk.dim.gray(`reasoning: ${meta.reasoning}`));
+    }
     // Duration always last
     if (meta.duration) {
       metaParts.push(this.formatDurationColored(meta.duration, thresholdKey));

package/sdk.js

@@ -414,6 +414,7 @@ class Element {
 
       result.similarity = this._response.similarity;
       result.confidence = this._response.confidence;
+      result.reasoning = this._response.reasoning;
       result.selector = this._response.selector;
 
       // Include AI response text if available
@@ -716,20 +717,26 @@ class Element {
       cacheStrategy: response.cacheStrategy || null,
       similarity: response.similarity ?? null,
       confidence: response.confidence ?? null,
+      reasoning: response.reasoning ?? null,
     };
 
     // Emit element found as log:log event
     const { events } = require("./agent/events.js");
     const Dashcam = require("./lib/core/Dashcam");
     const consoleUrl = Dashcam.getConsoleUrl(this.sdk.config?.TD_API_ROOT);
-    const formattedMessage = formatter.formatElementFound(this.description, {
+    const meta = {
       x: this.coordinates.x,
       y: this.coordinates.y,
       duration: debugInfo.duration,
       cacheHit: debugInfo.cacheHit,
       selectorId: this._response?.selector,
       consoleUrl: consoleUrl,
-    });
+    };
+    if (!debugInfo.cacheHit) {
+      meta.confidence = debugInfo.confidence;
+      meta.reasoning = debugInfo.reasoning;
+    }
+    const formattedMessage = formatter.formatElementFound(this.description, meta);
     this.sdk.emitter.emit(events.log.log, formattedMessage);
 
     // Log cache information in debug mode
@@ -1116,6 +1123,14 @@ class Element {
     return this._response?.confidence ?? null;
   }
 
+  /**
+   * Get model reasoning for why this element was selected
+   * @returns {string|null}
+   */
+  get reasoning() {
+    return this._response?.reasoning ?? null;
+  }
+
   /**
    * Get element width if available
    * @returns {number|null}