testdriverai 7.9.9-test → 7.9.11-test

package/docs/v7/scroll.mdx

@@ -27,21 +27,21 @@ Scroll the page or active element in any direction using mouse wheel or keyboard
 ## Syntax
 
 ```javascript
-await testdriver.scroll(direction, amount, method)
+await testdriver.scroll(direction, options)
 ```
 
 ## Parameters
 
 <ParamField path="direction" type="string" default="down">
-  Direction to scroll: `'up'`, `'down'`, `'left'`, `'right'`
+  Direction to scroll: `'up'`, `'down'`
 </ParamField>
 
-<ParamField path="amount" type="number" default="300">
-  Amount to scroll in pixels
-</ParamField>
-
-<ParamField path="method" type="string" default="mouse">
-  Scroll method: `'mouse'` or `'keyboard'`
+<ParamField path="options" type="object">
+  <Expandable title="properties">
+    <ParamField path="amount" type="number" default="300">
+      Amount to scroll in pixels
+    </ParamField>
+  </Expandable>
 </ParamField>
 
 ## Returns
@@ -56,95 +56,34 @@ await testdriver.scroll(direction, amount, method)
 // Scroll down (default)
 await testdriver.scroll();
 
-// Scroll down 500 pixels
-await testdriver.scroll('down', 500);
+// Scroll down 5 clicks
+await testdriver.scroll('down', { amount: 5 });
 
 // Scroll up
 await testdriver.scroll('up');
 
-// Scroll up 200 pixels
-await testdriver.scroll('up', 200);
+// Scroll up 2 clicks
+await testdriver.scroll('up', { amount: 2 });
 ```
 
 ### Horizontal Scrolling
 
 ```javascript
 // Scroll right
-await testdriver.scroll('right', 300);
+await testdriver.scroll('right', { amount: 3 });
 
 // Scroll left
-await testdriver.scroll('left', 300);
+await testdriver.scroll('left', { amount: 3 });
 ```
 
 ### Scroll Methods
 
 ```javascript
-// Mouse wheel scroll (smooth, pixel-precise)
-await testdriver.scroll('down', 300, 'mouse');
-
-// Keyboard scroll (uses Page Down/Up, more compatible)
-await testdriver.scroll('down', 300, 'keyboard');
-```
-
-## Scroll Until Found
-
-### scrollUntilText()
-
-Scroll until specific text appears on screen.
-
-```javascript
-await testdriver.scrollUntilText(text, direction, maxDistance, textMatchMethod, method, invert)
-```
-
-**Parameters:**
-- `text` (string) - Text to find
-- `direction` (string) - Scroll direction (default: `'down'`)
-- `maxDistance` (number) - Max pixels to scroll (default: 10000)
-- `textMatchMethod` (string) - `'turbo'` or `'ai'` (default: `'turbo'`)
-- `method` (string) - `'keyboard'` or `'mouse'` (default: `'keyboard'`)
-- `invert` (boolean) - Scroll until text disappears (default: false)
-
-**Examples:**
-```javascript
-// Scroll down until "Contact Us" appears
-await testdriver.scrollUntilText('Contact Us');
-
-// Scroll up to find text
-await testdriver.scrollUntilText('Header', 'up');
-
-// Scroll until text disappears
-await testdriver.scrollUntilText('Loading...', 'down', 5000, 'turbo', 'keyboard', true);
+// Mouse wheel scroll (default)
+await testdriver.scroll('down', { amount: 3 });
 
-// Use AI matching for fuzzy text
-await testdriver.scrollUntilText('footer content', 'down', 10000, 'ai');
-```
-
-### scrollUntilImage()
-
-Scroll until a visual element appears.
-
-```javascript
-await testdriver.scrollUntilImage(description, direction, maxDistance, method, path, invert)
-```
-
-**Parameters:**
-- `description` (string) - Description of the image/element
-- `direction` (string) - Scroll direction (default: `'down'`)
-- `maxDistance` (number) - Max pixels to scroll (default: 10000)
-- `method` (string) - `'keyboard'` or `'mouse'` (default: `'keyboard'`)
-- `path` (string | null) - Path to image template (optional)
-- `invert` (boolean) - Scroll until image disappears (default: false)
-
-**Examples:**
-```javascript
-// Scroll until visual element appears
-await testdriver.scrollUntilImage('red subscribe button');
-
-// Scroll using image template
-await testdriver.scrollUntilImage('', 'down', 10000, 'keyboard', './footer-logo.png');
-
-// Scroll until image disappears
-await testdriver.scrollUntilImage('loading spinner', 'down', 5000, 'keyboard', null, true);
+// For keyboard-based scrolling, use pressKeys instead
+await testdriver.pressKeys(['pagedown']);
 ```
 
 ## Best Practices
@@ -163,7 +102,7 @@ await testdriver.scrollUntilImage('loading spinner', 'down', 5000, 'keyboard', n
   // await testdriver.find('page background').click();
   
   // Now scroll will work properly
-  await testdriver.scroll('down', 300);
+  await testdriver.scroll('down');
   
   // If scroll still doesn't work, use Page Down directly
   // await testdriver.pressKeys(['pagedown']);
@@ -171,84 +110,31 @@ await testdriver.scrollUntilImage('loading spinner', 'down', 5000, 'keyboard', n
 </Check>
 
 <Check>
-  **Choose the right scroll method**
-  
-  ```javascript
-  // For web pages, mouse scroll is usually smoother
-  await testdriver.scroll('down', 300, 'mouse');
-  
-  // For desktop apps or when mouse doesn't work
-  await testdriver.scroll('down', 300, 'keyboard');
-  ```
-</Check>
-
-<Check>
-  **Use scrollUntil for dynamic content**
+  **Control scroll distance with the options object**
   
   ```javascript
-  // Instead of guessing scroll amount
-  await testdriver.scrollUntilText('Load More button');
+  // For web pages, mouse scroll works well
+  await testdriver.scroll('down', { amount: 3 });
   
-  const loadMoreBtn = await testdriver.find('Load More button');
-  await loadMoreBtn.click();
-  ```
-</Check>
-
-<Check>
-  **Set reasonable max distance**
-  
-  ```javascript
-  // Avoid infinite scrolling
-  await testdriver.scrollUntilText('Footer', 'down', 5000); // Max 5000px
+  // For desktop apps or when mouse doesn't work, use keyboard
+  await testdriver.pressKeys(['pagedown']);
   ```
 </Check>
 
 <Warning>
   **Keyboard scroll uses Page Down/Up**
   
-  Keyboard scrolling typically moves by one "page" at a time, which may be more than the specified pixel amount. It's more compatible but less precise than mouse scrolling.
+  Keyboard scrolling typically moves by one "page" at a time, which may be more than the specified click amount. It's more compatible but less precise than mouse scrolling.
 </Warning>
 
 ## Use Cases
 
 <AccordionGroup>
-  <Accordion title="Navigate to Footer">
-    ```javascript
-    // Scroll to bottom of page
-    await testdriver.scrollUntilText('Contact Us');
-    
-    const contactLink = await testdriver.find('Contact Us link');
-    await contactLink.click();
-    ```
-  </Accordion>
-  
-  <Accordion title="Load More Results">
-    ```javascript
-    // Scroll to load more button
-    await testdriver.scrollUntilText('Load More');
-    
-    const loadBtn = await testdriver.find('Load More button');
-    await loadBtn.click();
-    
-    await new Promise(r => setTimeout(r, 2000));
-    ```
-  </Accordion>
-  
-  <Accordion title="Find Element in Long List">
-    ```javascript
-    // Scroll through list to find item
-    await testdriver.scrollUntilText('Product #42');
-    
-    const product = await testdriver.find('Product #42');
-    await product.click();
-    ```
-  </Accordion>
-  
   <Accordion title="Infinite Scroll">
     ```javascript
     // Scroll multiple times for infinite scroll
     for (let i = 0; i < 5; i++) {
-      await testdriver.scroll('down', 500);
+      await testdriver.scroll('down', { amount: 5 });
       await new Promise(r => setTimeout(r, 1000)); // Wait for load
     }
     ```
@@ -257,7 +143,7 @@ await testdriver.scrollUntilImage('loading spinner', 'down', 5000, 'keyboard', n
   <Accordion title="Horizontal Gallery">
     ```javascript
     // Navigate horizontal carousel
-    await testdriver.scroll('right', 300);
+    await testdriver.scroll('right', { amount: 3 });
     await new Promise(r => setTimeout(r, 500));
     
     const nextImage = await testdriver.find('next image in carousel');
@@ -288,8 +174,8 @@ describe('Scrolling', () => {
   it('should scroll to find elements', async () => {
     await testdriver.focusApplication('Google Chrome');
     
-    // Scroll to footer
-    await testdriver.scrollUntilText('Contact Information');
+    // Scroll down the page
+    await testdriver.scroll('down', { amount: 5 });
     
     // Click footer link
     const privacyLink = await testdriver.find('Privacy Policy link');
@@ -303,29 +189,13 @@ describe('Scrolling', () => {
     
     // Scroll multiple times to load content
     for (let i = 0; i < 3; i++) {
-      await testdriver.scroll('down', 500);
+      await testdriver.scroll('down', { amount: 5 });
       await new Promise(r => setTimeout(r, 1500)); // Wait for load
     }
     
     // Verify content loaded
     await testdriver.assert('more than 10 items are visible');
   });
-
-  it('should scroll until loading completes', async () => {
-    // Scroll until loading spinner disappears
-    await testdriver.scrollUntilImage(
-      'loading spinner', 
-      'down', 
-      5000, 
-      'keyboard', 
-      null, 
-      true // invert - wait for it to disappear
-    );
-    
-    // Now interact with loaded content
-    const firstResult = await testdriver.find('first search result');
-    await firstResult.click();
-  });
 });
 ```
 

package/lib/github-comment.mjs

@@ -8,7 +8,13 @@
  * - Links to test runs
  */
 
-import { Octokit } from '@octokit/rest';
+/**
+ * Lazily load Octokit to avoid hard failure when @octokit/rest is not installed
+ */
+async function getOctokit(token) {
+  const { Octokit } = await import('@octokit/rest');
+  return new Octokit({ auth: token });
+}
 
 /**
  * Format test duration in human-readable format
@@ -334,7 +340,7 @@ export async function postGitHubComment(options) {
     throw new Error('Either prNumber or commitSha must be provided');
   }
 
-  const octokit = new Octokit({ auth: token });
+  const octokit = await getOctokit(token);
 
   if (prNumber) {
     // Comment on PR
@@ -374,7 +380,7 @@ export async function updateGitHubComment(options) {
     throw new Error('Token, owner, repo, and commentId are required');
   }
 
-  const octokit = new Octokit({ auth: token });
+  const octokit = await getOctokit(token);
 
   const response = await octokit.rest.issues.updateComment({
     owner,
@@ -402,7 +408,7 @@ export async function findExistingComment(options) {
     return null;
   }
 
-  const octokit = new Octokit({ auth: token });
+  const octokit = await getOctokit(token);
 
   const comments = await octokit.rest.issues.listComments({
     owner,
@@ -435,7 +441,7 @@ export async function postOrUpdateTestResults(testRunData, testCases, githubOpti
 
     if (existingComment) {
       // Delete the old comment
-      const octokit = new Octokit({ auth: githubOptions.token });
+      const octokit = await getOctokit(githubOptions.token);
       await octokit.rest.issues.deleteComment({
         owner: githubOptions.owner,
         repo: githubOptions.repo,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "testdriverai",
-  "version": "7.9.9-test",
+  "version": "7.9.11-test",
   "description": "Next generation autonomous AI agent for end-to-end testing of web & desktop",
   "main": "sdk.js",
   "types": "sdk.d.ts",

package/sdk.d.ts

@@ -282,7 +282,7 @@ export interface TestDriverOptions {
   /** Enable/disable Dashcam video recording (default: true) */
   dashcam?: boolean;
   /**
-   * Enable automatic screenshots before and after each command (default: true)
+   * Enable automatic screenshots before and after each command (default: false)
    * Screenshots are saved to .testdriver/screenshots/<test>/ with descriptive filenames
    * Format: <seq>-<action>-<phase>-L<line>-<description>.png
    * Example: 001-click-before-L42-submit-button.png
@@ -1086,7 +1086,7 @@ export default class TestDriverSDK {
   find(description: string, cacheThreshold?: number): ChainableElementPromise;
   find(
     description: string,
-    options?: { cacheThreshold?: number; cacheKey?: string; timeout?: number; confidence?: number; type?: "text" | "image" | "ui" | "any"; ai?: AIConfig; cache?: { thresholds?: { screen?: number; element?: number } } },
+    options?: { cacheThreshold?: number; cacheKey?: string; timeout?: number; confidence?: number; type?: "text" | "image" | "ui" | "any"; zoom?: boolean | number; verify?: boolean; ai?: AIConfig; cache?: { thresholds?: { screen?: number; element?: number } } },
   ): ChainableElementPromise;
 
   /**

package/sdk.js

@@ -481,7 +481,8 @@ class Element {
       let cacheKey = null;
       let cacheThreshold = null;
       let perCommandThresholds = null; // Per-command { screen, element } override
-      let zoom = true; // Default to enabled
+      let zoom = false; // Default to disabled
+      let verify = false; // Default to disabled (skip AI verification)
       let perCommandAi = null; // Per-command AI config override
 
       let minConfidence = null; // Minimum confidence threshold
@@ -494,8 +495,10 @@ class Element {
         // New: options is an object with cacheKey and/or cacheThreshold
         cacheKey = options.cacheKey || null;
         cacheThreshold = options.cacheThreshold ?? null;
-        // zoom defaults to true unless explicitly set to false
-        zoom = options.zoom !== false;
+        // zoom defaults to false unless explicitly set to true
+        zoom = options.zoom === true;
+        // verify defaults to false unless explicitly set to true
+        verify = options.verify === true;
         // Minimum confidence threshold: fail find if AI confidence is below this value
         minConfidence = options.confidence ?? null;
         // Element type hint for prompt wrapping
@@ -569,6 +572,7 @@ class Element {
         os: this.sdk.os,
         resolution: this.sdk.resolution,
         zoom: zoom === true ? 1 : zoom === false ? 0 : zoom,
+        skipVerify: !verify,
         confidence: minConfidence,
         type: elementType,
         ai: {