@testdriverai/mcp 7.10.0-canary.0 → 7.10.1-test

package/ai/skills/testdriver-screenshot/SKILL.md

@@ -9,7 +9,7 @@ description: Capture and save screenshots during test execution
 Capture a screenshot of the current screen and automatically save it to a local file. Screenshots are organized by test file for easy debugging and review.
 
 <Note>
-  **Automatic Screenshots (Default: Enabled)**: TestDriver automatically captures screenshots before and after every command (click, type, find, etc.). These are saved with descriptive filenames like `001-click-before-L42-submit-button.png` that include the line number from your test file. You can disable this with `autoScreenshots: false` in your TestDriver options.
+  **Automatic Screenshots**: TestDriver can automatically capture screenshots before and after every command (click, type, find, etc.). These are saved with descriptive filenames like `001-click-before-L42-submit-button.png` that include the line number from your test file. Enable this with `autoScreenshots: true` in your TestDriver options.
 </Note>
 
 ## Syntax
@@ -50,7 +50,7 @@ Screenshots are automatically saved to `.testdriver/screenshots/<test-file-name>
 
 ### Automatic Screenshot Naming
 
-When `autoScreenshots` is enabled (default), filenames follow this format:
+When `autoScreenshots` is enabled, filenames follow this format:
 
 `<seq>-<action>-<phase>-L<line>-<description>.png`
 
@@ -91,7 +91,7 @@ await testdriver.screenshot("after-click");
 
 ```javascript
 import { describe, expect, it } from "vitest";
-import { TestDriver } from "testdriverai/lib/vitest/hooks.mjs";
+import { TestDriver } from "testdriverai/vitest/hooks";
 
 describe("Login Flow", () => {
   it("should log in successfully", async (context) => {
@@ -153,7 +153,7 @@ Automatic screenshots are taken around these commands:
 - `find()` / `findAll()`
 - `click()` / `hover()` / `doubleClick()` / `rightClick()`
 - `type()` / `pressKeys()`
-- `scroll()` / `scrollUntilText()` / `scrollUntilImage()`
+- `scroll()`
 - `waitForText()` / `waitForImage()`
 - `focusApplication()`
 - `assert()` / `extract()` / `exec()`
@@ -188,7 +188,7 @@ If an error occurs, the phase will be `error` instead of `after`.
 
 <AccordionGroup>
   <Accordion title="Let automatic screenshots do the work">
-    With `autoScreenshots: true` (default), you get comprehensive coverage without adding manual `screenshot()` calls. Only add manual screenshots for specific named checkpoints.
+    With `autoScreenshots: true`, you get comprehensive coverage without adding manual `screenshot()` calls. Only add manual screenshots for specific named checkpoints.
   </Accordion>
   
   <Accordion title="Use screenshots for debugging flaky tests">

package/ai/skills/testdriver-scroll/SKILL.md

@@ -26,21 +26,21 @@ 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
@@ -55,95 +55,34 @@ 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
@@ -162,7 +101,7 @@ 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']);
@@ -170,84 +109,31 @@ 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
     }
     ```
@@ -256,7 +142,7 @@ 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');
@@ -287,8 +173,8 @@ 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');
@@ -302,29 +188,13 @@ 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/ai/skills/testdriver-test-writer/SKILL.md

@@ -50,12 +50,12 @@ Get your API key at: **https://console.testdriver.ai/team**
 
 ### Installation
 
-Always use the **beta** tag when installing TestDriver:
+Always use the **canary** tag when installing TestDriver:
 
 ```bash
-npm install --save-dev testdriverai@beta
+npm install --save-dev testdriverai@canary
 # or
-npx testdriverai@beta init
+npx testdriverai@canary init
 ```
 
 ### Test Runner
@@ -392,8 +392,6 @@ await element.click();
 
 ```javascript
 await testdriver.scroll("down");
-await testdriver.scrollUntilText("Footer text");
-await testdriver.scrollUntilImage("Product image at bottom");
 ```
 
 ### Executing Code in Sandbox

package/ai/skills/testdriver-testdriver/SKILL.md

@@ -34,7 +34,7 @@ Use this agent when the user asks to:
 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.
+7. **⚠️ RUN THE TEST YOURSELF**: Use `vitest run <testFile>` 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
@@ -305,11 +305,9 @@ assert({ assertion: "the dashboard is visible" })
 **⚠️ 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
+vitest run tests/login.test.mjs
 ```
 
-**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.
@@ -558,8 +556,6 @@ 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"]);
@@ -604,7 +600,7 @@ 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.
+2. **⚠️ RUN TESTS YOURSELF** - Do NOT tell the user to run tests. YOU must run the tests using `vitest run <testFile>` (NEVER use `npx vitest`). 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.

package/ai/skills/testdriver-wait/SKILL.md

@@ -47,4 +47,4 @@ await testdriver.wait();
   const element = await testdriver.find('success message');
   ```
 - Avoid excessively long timeouts to keep tests efficient.
-- Use sparingly — TestDriver's [redraw detection](/v7/waiting-for-elements) automatically waits for screen and network stability after each action.
+- Use sparingly — TestDriver's [redraw detection](/v7/performing-actions#waiting-for-dynamic-content) automatically waits for screen and network stability after each action.

package/{docs/v7/ai.mdx → ai/skills/testdriver:ai/SKILL.md}

@@ -1,9 +1,8 @@
 ---
-title: "ai()"
-sidebarTitle: "ai"
-description: "Execute natural language tasks using AI"
-icon: "wand-magic-sparkles"
+name: testdriver:ai
+description: Execute natural language tasks using AI
 ---
+<!-- Generated from ai.mdx. DO NOT EDIT. -->
 
 ## Overview