testdriverai 6.1.10 → 6.2.0

package/docs/overview/comparison.mdx

@@ -10,10 +10,11 @@ icon: boxing-glove
 TestDriver operates a full desktop environment, so it can run any application.
 
 <div className="comparison-table">
-  | Application | TestDriver | Playwright | Selenium |
-  |:-----------------:|:---------:|:-----------:|:--------:| | Web Apps | ✅ |
-  ✅ | ✅ | | Mobile Apps | ✅ | ✅ | ✅ | | VS Code | ✅ | ✅ | ✅ | | Desktop
-  Apps | ✅ | | | | Chrome Extensions | ✅ | | |
+| Application       | TestDriver | Playwright | Selenium |
+|:-----------------:|:---------:|:-----------:|:--------:|
+| Web Apps          | ✅            | ✅       | ✅       |
+| Desktop Apps      | ✅            |          |         |
+| Chrome Extensions | ✅            |          |         |
 </div>
 
 ## Testing features
@@ -21,11 +22,16 @@ TestDriver operates a full desktop environment, so it can run any application.
 TestDriver is AI first.
 
 <div className="comparison-table">
-  | Feature | TestDriver | Playwright | Selenium |
-  |:--------------------:|:---------:|:----------:|:--------:| | Test Generation
-  | ✅ | | | | Adaptive Testing | ✅ | | | | Visual Assertions | ✅ | | | | Self
-  Healing | ✅ | | | | Application Switching | ✅ | | | | GitHub Actions | ✅ |
-  ✅ | | | Team Dashboard | ✅ | | | | Team Collaboration | ✅ | | |
+| Feature               | TestDriver | Playwright | Selenium |
+|:--------------------:|:---------:|:----------:|:--------:|
+| Test Generation       | ✅            |          |        |
+| Adaptive Testing      | ✅            |          |        |
+| Visual Assertions     | ✅            |          |        |
+| Self Healing          | ✅            |          |        |
+| Application Switching | ✅            |          |        |
+| GitHub Actions        | ✅            | ✅       |        |
+| Team Dashboard        | ✅            |          |        |
+| Team Collaboration    | ✅            |          |        |
 </div>
 
 ## Test coverage
@@ -53,11 +59,15 @@ TestDriver has more coverage than selector-based frameworks.
 Debugging features are powered by [Dashcam.io](https://dashcam.io).
 
 <div className="comparison-table">
-  | Feature | TestDriver | Playwright | Selenium |
-  |:------------------:|:----------:|:----------:|:--------:| | AI Summary | ✅
-  | | | | Video Replay | ✅ | ✅ | | | Browser Logs | ✅ | ✅ | | | Desktop Logs
-  | ✅ | | | | Network Requests | ✅ | ✅ | | | Team Dashboard | ✅ | | | | Team
-  Collaboration | ✅ | | |
+| Feature            | TestDriver | Playwright | Selenium |
+|:------------------:|:----------:|:----------:|:--------:|
+| AI Summary         | ✅            |              |        |
+| Video Replay       | ✅            | ✅            |        |
+| Browser Logs       | ✅            | ✅            |        |
+| Desktop Logs       | ✅            |               |        |
+| Network Requests   | ✅            | ✅            |        |
+| Team Dashboard     | ✅            |              |        |
+| Team Collaboration | ✅            |              |        |
 </div>
 
 ## Web browser support
@@ -65,10 +75,15 @@ Debugging features are powered by [Dashcam.io](https://dashcam.io).
 TestDriver is browser agnostic and supports any version of any browser.
 
 <div className="comparison-table">
-  | Feature | TestDriver | Playwright | Selenium |
-  |:--------:|:----------:|:----------:|:--------:| | Chrome | ✅ | ✅ | ✅ | |
-  Firefox | ✅ | ✅ | ✅ | | Webkit | ✅ | ✅ | ✅ | | IE | ✅ | | ✅ | | Edge |
-  ✅ | ✅ | ✅ | | Opera | ✅ | | ✅ | | Safari | ✅ | | ✅ |
+| Feature  | TestDriver | Playwright | Selenium |
+|:--------:|:----------:|:----------:|:--------:|
+| Chrome   | ✅            | ✅         | ✅       |
+| Firefox  | ✅            | ✅         | ✅       |
+| Webkit   | ✅            | ✅         | ✅       |
+| IE       | ✅            |            | ✅       |
+| Edge     | ✅            | ✅         | ✅       |
+| Opera    | ✅            |            | ✅       |
+| Safari   | ✅            |            | ✅       |
 </div>
 
 ## Operating system support
@@ -76,7 +91,9 @@ TestDriver is browser agnostic and supports any version of any browser.
 TestDriver currently supports Mac and Windows!
 
 <div className="comparison-table">
-  | Feature | TestDriver | Playwright | Selenium |
-  |:--------:|:----------:|:----------:|:--------:| | Windows | ✅ | ✅ | ✅ | |
-  Mac | ✅ | ✅ | ✅ | | Linux | | ✅ | ✅ |
-</div>
+| Feature  | TestDriver | Playwright | Selenium |
+|:--------:|:----------:|:----------:|:--------:|
+| Windows  | ✅            | ✅       | ✅       |
+| Mac      | ✅            | ✅       | ✅       |
+| Linux    |               | ✅       | ✅       |
+</div>

package/docs/overview/quickstart.mdx

@@ -6,105 +6,53 @@ icon: "gauge-high"
 mode: "wide"
 ---
 
+<Tip>
+  You will need a [TestDriver Pro](https://app.testdriver.ai/team) account
+  ($20/m) to complete setup.
+</Tip>
+
 <Steps>
-  <Step title="Create a TestDriver Account">
-      
-  You will need a [TestDriver Pro](https://app.testdriver.ai/team) account ($20/month) to get an API key. 
-    
+  <Step title="Install TestDriver">
+
+    Click the button below to install the TestDriver extension for your preferred IDE. Then, follow the setup guide and chat with TestDriver to create your first test.
+
     <Card
-      title="Sign Up for TestDriver"
-      icon="user-plus"
-      href="https://app.testdriver.ai/team"
-      arrow
       horizontal
+      title="VS Code"
+      arrow
+      href="vscode:extension/testdriver.testdriver"
+      icon="/images/content/extension/vscode.svg"
     ></Card>
 
-  </Step>
-  <Step title="Set up your environment">
-      
-    Copy your API key from [the TestDriver dashboard](https://app.testdriver.ai/team), and set it as an environment variable.
-    
-    <Tabs>
-      <Tab title="macOS / Linux">
-        ```bash Export an environment variable on macOS or Linux systems
-        export TD_API_KEY="your_api_key_here"
-        ```
-      </Tab>
-      <Tab title="Windows">
-      ```powershell Export an environment variable in PowerShell
-      setx TD_API_KEY "your_api_key_here"
-      ```
-      </Tab>
-    </Tabs>
-
-    <Tip>Using VS Code, Cursor, or Windsurf? [Try our VS Code Extension (beta)](/getting-started/vscode).</Tip>
-
-  </Step>
-  <Step title="Check out an example test">
-      
-    Download the TestDriver GitHub repository and run the example test.
-
-    ```bash
-    git clone --depth 1 https://github.com/testdriverai/cli testdriverai
-    cd testdriverai/testdriver/acceptance
-    ```
+    <Card
+      horizontal
+      title="Cursor"
+      arrow
+    href="cursor:extension/testdriver.testdriver"
+    icon="/images/content/extension/cursor.svg"
 
-    TestDriver tests are written in YAML, a human-readable data format. The `prompt.yaml` file contains an example series of steps for the agent to execute.
+    > </Card>
 
-    ```yaml testdriver/acceptance/prompt.yaml
-    steps:
-      - prompt: log in
-      - prompt: add an item to the cart
-      - prompt: click on the cart icon
-      - prompt: complete checkout
-    ```
+    <Card
+      horizontal
+      title="Windsurf"
+      arrow
+      href="windsurf:extension/testdriver.testdriver"
+      icon="/images/content/extension/windsurf.svg"
+    ></Card>
 
-    Each step has a `prompt` that describes what the agent should do. The agent will use the prompt to generate [commands](/commands/assert) that make the tests faster and more reliable the next time you run the test.
+    The extension will generate most of your tests for you, but you'll probably want to customize them. [Learn more about editing tests](/getting-started/editing).
 
   </Step>
-  <Step title="Generate regression test from prompts">
+  <Step title="Run your tests in CI/CD">
     
-    Run the following command to run the test file. TestDriver will spawn a virtual machine, launch the sandbox test page, and execute the steps defined in the `prompt.yaml` file.
+    Next, use `testdriverai` to run your tests in CI/CD pipelines.
 
     ```bash
-    npx testdriverai@latest run prompt.yaml --write --heal
+    TD_API_KEY=YOUR_KEY npx testdriverai@latest run testdriver/test.yaml
     ```
 
-    The `--write` flag tells TestDriver to save any generated commands to the test file, and the `--heal` flag allows TestDriver to recover from unexpected issues during the test run.
-
-    <Tip>You can use an interactive CLI to generate test steps with the [explore command](/interactive/explore)</Tip>
-
-  </Step>
-  <Step title="Run the generated regression test">
-
-    After TestDriver has run the exploratory test, you'll see that the `prompt.yaml` file has been updated with commands generated by the agent to make the test faster and more reliable.
-
-    ```yaml
-      version: 6.0.0
-      steps:
-        - prompt: focus chrome
-          commands:
-            - command: focus-application
-              name: Google Chrome
-        - prompt: enter a username
-          commands:
-            - command: hover-text
-              text: Username
-              description: username input field
-              action: click
-            - command: type
-              text: standard_user
-        - prompt: enter a password
-          commands:
-            - command: hover-text
-              text: Password
-              description: password input field
-              action: click
-            - command: type
-              text: secret_password
-      ```
-
-      The `--write` command tells the agent to save the generated commands to the test file, and the `--heal` command gives the agent permission to recover if something goes wrong.
+    Note that you'll want to store your API key within secret storeage. [Learn more about running tests in CI/CD pipelines](/action/setup).
 
   </Step>
 

package/docs/styles.css

@@ -53,13 +53,4 @@
   transform: translateX(-50%);
   justify-content: center;
   display: flex;
-}
-
-img[src$=".svg"] {
-  background: transparent !important;
-}
-
-img[src$="https://tauri.app/favicon.svg"]
-{
-  opacity: 0.3;
-}
+}

package/interfaces/cli/lib/base.js

@@ -42,6 +42,7 @@ class BaseCommand extends Command {
       message = JSON.stringify(message);
     }
     this.agent.sandbox.send({
+      os: "linux",
       type: "output",
       output: Buffer.from(message).toString("base64"),
     });
@@ -55,8 +56,7 @@ class BaseCommand extends Command {
         `testdriverai-cli-${process.pid}.log`,
       );
 
-      console.log(`Log file: ${this.logFilePath}`);
-      console.log("");
+      console.log(`Log file created at: ${this.logFilePath}`);
       fs.writeFileSync(this.logFilePath, ""); // Initialize the log file
     }
 
@@ -69,15 +69,11 @@ class BaseCommand extends Command {
       );
     };
 
-    let isConnected = false;
-
     // Use pattern matching for log events, but skip log:Debug
     this.agent.emitter.on("log:*", (message) => {
       const event = this.agent.emitter.event;
 
       if (event === events.log.debug) return;
-
-      if (event === events.log.narration && isConnected) return;
       console.log(message);
     });
 
@@ -95,7 +91,6 @@ class BaseCommand extends Command {
 
     // Handle sandbox connection with pattern matching for subsequent events
     this.agent.emitter.on("sandbox:connected", () => {
-      isConnected = true;
       // Once sandbox is connected, send all log and error events to sandbox
       this.agent.emitter.on("log:*", (message) => {
         this.sendToSandbox(message);
@@ -130,17 +125,8 @@ class BaseCommand extends Command {
       process.exit(exitCode);
     });
 
-    // Handle unhandled promise rejections to prevent them from interfering with the exit flow
-    // This is particularly important when JavaScript execution in VM contexts leaves dangling promises
-    process.on("unhandledRejection", (reason) => {
-      // Log the rejection but don't let it crash the process
-      console.error("Unhandled Promise Rejection:", reason);
-      // The exit flow should continue normally
-    });
-
     // Handle show window events
     this.agent.emitter.on("show-window", async (url) => {
-      console.log("");
       console.log(`Live test execution: `);
       if (this.agent.config.CI) {
         let u = new URL(url);
@@ -172,27 +158,20 @@ class BaseCommand extends Command {
     return file;
   }
 
-  async setupAgent(firstArg, flags) {
+  async setupAgent(file, flags) {
     // Load .env file into process.env for CLI usage
     require("dotenv").config();
 
     // Create the agent only when actually needed
     const TestDriverAgent = require("../../../agent/index.js");
 
-    let args;
-    if (this.id === "generate") {
-      // For generate command, the first parameter is a prompt, not a file
-      args = firstArg ? [firstArg] : [];
-    } else {
-      // For run and other commands, handle file path
-      const filePath = this.id === "run" && flags.path ? flags.path : firstArg;
-      args = filePath ? [filePath] : [];
-    }
+    // Use --path flag if provided, otherwise use the file argument
+    const filePath = this.id === "run" && flags.path ? flags.path : file;
 
     // Prepare CLI args for the agent with all derived options
     const cliArgs = {
       command: this.id,
-      args,
+      args: [filePath], // Pass the resolved file path as the first argument
       options: {
         ...flags,
         resultFile:

package/interfaces/cli/utils/factory.js

@@ -28,18 +28,9 @@ function createOclifCommand(commandName) {
           this.agent.readlineInterface = readlineInterface;
           await readlineInterface.start();
         } else {
-          // For run and generate commands, use the unified command system
-          let commandArgs;
-          if (commandName === "generate") {
-            // Generate command: pass prompt as first argument
-            await this.setupAgent(args.prompt, flags);
-            commandArgs = [args.prompt];
-          } else {
-            // Run and other commands use file argument
-            const fileArg = args.file || args.action || null;
-            await this.setupAgent(fileArg, flags);
-            commandArgs = [fileArg];
-          }
+          // For run and sandbox commands, use the unified command system
+          const fileArg = args.file || args.action || null;
+          await this.setupAgent(fileArg, flags);
 
           if (commandName === "run") {
             // Set error limit higher for run command
@@ -47,11 +38,7 @@ function createOclifCommand(commandName) {
           }
 
           // Execute through unified command system
-          await this.agent.executeUnifiedCommand(
-            commandName,
-            commandArgs,
-            flags,
-          );
+          await this.agent.executeUnifiedCommand(commandName, [fileArg], flags);
         }
       } catch (error) {
         console.error(`Error executing ${commandName} command:`, error);

package/interfaces/logger.js

@@ -29,6 +29,7 @@ class CustomTransport extends Transport {
         }
 
         this.sandbox.send({
+          os: "linux",
           type: "output",
           output: Buffer.from(message).toString("base64"),
         });
@@ -44,7 +45,7 @@ class CustomTransport extends Transport {
 // responsible for rendering ai markdown output
 const { marked } = require("marked");
 const { markedTerminal } = require("marked-terminal");
-const { censorSensitiveDataDeep } = require("../agent/lib/censorship");
+const { censorSensitiveData } = require("../agent/lib/censorship");
 
 const { printf } = winston.format;
 
@@ -56,7 +57,7 @@ const logger = winston.createLogger({
   format: winston.format.combine(
     winston.format.splat(),
     winston.format((info) => {
-      info.message = censorSensitiveDataDeep(info.message);
+      info.message = censorSensitiveData(info.message);
       return info;
     })(),
     logFormat,
@@ -340,7 +341,7 @@ const createMarkdownLogger = (emitter) => {
 
     let diff = consoleOutput.replace(previousConsoleOutput, "");
     if (diff) {
-      diff = censorSensitiveDataDeep(diff);
+      diff = censorSensitiveData(diff);
       process.stdout.write(diff);
     }
   });
@@ -357,7 +358,7 @@ const createMarkdownLogger = (emitter) => {
     let diff = consoleOutput.replace(previousConsoleOutput, "");
 
     if (diff) {
-      diff = censorSensitiveDataDeep(diff);
+      diff = censorSensitiveData(diff);
       process.stdout.write(diff);
     }
     process.stdout.write("\n\n");

package/interfaces/readline.js

@@ -110,7 +110,7 @@ class ReadlineInterface {
 
     try {
       // Parse interactive commands (starting with /)
-      if (input.startsWith("/") && !input.startsWith("/explore")) {
+      if (input.startsWith("/")) {
         const parts = input.slice(1).split(" ");
         const commandName = parts[0];
         const args = parts.slice(1);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "testdriverai",
-  "version": "6.1.10",
+  "version": "6.2.0",
   "description": "Next generation autonomous AI agent for end-to-end testing of web & desktop",
   "main": "index.js",
   "bin": {
@@ -10,9 +10,9 @@
     "start": "node bin/testdriverai.js",
     "dev": "DEV=true node bin/testdriverai.js",
     "debug": "DEV=true VERBOSE=true node bin/testdriverai.js",
-    "docs": "node docs/_scripts/link-replacer.js && cd docs && npx mint@latest dev",
+    "docs": "node docs/_scripts/link-replacer.js && cd docs && npx mint dev",
     "docs:dev": "cd docs && npx mint dev",
-    "docs:build": "node docs/_scripts/link-replacer.js && cd docs && npx mint@latest build",
+    "docs:build": "node docs/_scripts/link-replacer.js && cd docs && npx mint build",
     "docs:links": "node docs/_scripts/link-replacer.js",
     "bundle": "node build.mjs",
     "test": "mocha test/*",

package/schema.json

@@ -415,9 +415,6 @@
               "ai",
               "turbo"
             ]
-          },
-          "timeout": {
-            "type": "integer"
           }
         }
       },
@@ -474,9 +471,6 @@
               "drag-start",
               "drag-end"
             ]
-          },
-          "invert": {
-            "type": "boolean"
           }
         }
       },
@@ -496,9 +490,6 @@
           },
           "timeout": {
             "type": "integer"
-          },
-          "invert": {
-            "type": "boolean"
           }
         }
       },
@@ -525,9 +516,6 @@
               "ai",
               "turbo"
             ]
-          },
-          "invert": {
-            "type": "boolean"
           }
         }
       },
@@ -564,9 +552,6 @@
               "keyboard",
               "mouse"
             ]
-          },
-          "invert": {
-            "type": "boolean"
           }
         }
       },
@@ -605,9 +590,6 @@
               "keyboard",
               "mouse"
             ]
-          },
-          "invert": {
-            "type": "boolean"
           }
         },
         "anyOf": [
@@ -675,9 +657,6 @@
           },
           "async": {
             "type": "boolean"
-          },
-          "invert": {
-            "type": "boolean"
           }
         }
       },
@@ -697,7 +676,8 @@
             "type": "string",
             "enum": [
               "js",
-              "pwsh"
+              "pwsh",
+              "sh"
             ]
           },
           "code": {

package/testdriver/acceptance/hover-text.yaml

@@ -1,4 +1,4 @@
-version: 6.0.0
+version: 5.7.7
 session: 682f5aab811bd5a322c0e5a1
 steps:
   - prompt: click on sign in
@@ -9,6 +9,5 @@ steps:
         text: Sign In
         description: black button below the password field
         action: click
-        timeout: 5000
       - command: assert
         expect: an error shows that fields are required

package/testdriver/acceptance/prompt.yaml

@@ -1,10 +1,7 @@
 version: 6.0.0
 session: 6869c3e61445b2acbbdc0018
 steps:
-  - prompt: log in
-  - prompt: add an item to the cart
-  - prompt: click on the cart icon
-  - prompt: complete checkout
+  - prompt: enter a valid username, password, and sign in
   - prompt: assert
     commands:
       - command: assert

package/testdriver/acceptance/scroll-until-image.yaml

@@ -19,8 +19,3 @@ steps:
       - command: scroll-until-image
         description: a brown colored house
         direction: down
-
-  - prompt: assert image of brown colored house appears on screen
-    commands:
-      - command: assert
-        expect: image of brown colored house appears on screen

package/testdriver/{lifecycle/prerun.yaml → examples/web/lifecycle/provision.yaml}

@@ -2,12 +2,6 @@ version: 6.0.0
 steps:
   - prompt: launch chrome
     commands:
-      - command: exec
-        lang: pwsh
-        code: dashcam track --name=TestDriver --type=application --pattern="C:\Users\testdriver\Documents\testdriver.log"
-      - command: exec
-        lang: pwsh
-        code: dashcam start
       - command: exec
         lang: pwsh
         code: |

package/testdriver/lifecycle/provision.yaml

@@ -0,0 +1,20 @@
+version: 5.1.1
+session: 67f00511acbd9ccac373edf7
+steps:
+  - prompt: launch chrome
+    commands:
+      - command: exec
+        lang: sh
+        code: |
+          google-chrome \
+            --start-maximized \
+            --disable-infobars \
+            --disable-fre \
+            --no-default-browser-check \
+            --no-first-run \
+            --guest \
+            "${TD_WEBSITE}" \
+            >/dev/null 2>&1 &
+      - command: wait-for-text
+        text: ${TD_WEBSITE}
+        timeout: 60000