feat: implement waitFor tool

README.md

@@ -37,7 +37,7 @@ A [Model Context Protocol server](https://modelcontextprotocol.io/quickstart/use
     <details>
     <summary>Set up in Cursor</summary>
 
-    Open Cursor `Settings` (button at the top right corner of the screen), find `MCP` section, click on the `Add new global MCP server` button, edit the config to include Testplane MCP as seen below.
+    Open Cursor `Settings` (button at the top right corner of the screen), find `Tools & Integrations` section, click on the `New MCP Server` button, edit the config to include Testplane MCP as seen below.
 
     ```json
     {
@@ -173,9 +173,12 @@ Close a specific browser tab by its number (1-based), or close the current tab i
 ### `clickOnElement`
 Click an element on the page using semantic queries (`testing-library`-style) or CSS selectors.
 
-- Semantic Queries:
-    - **Parameters:**
-    - `queryType` (string, optional): Semantic query type. One of:
+- **Parameters:**
+  - `locator` (object, required): Element location strategy
+    - `strategy` (string, required): Either `"testing-library"` or `"webdriverio"`
+
+    For **testing-library strategy**:
+    - `queryType` (string, required): Semantic query type. One of:
         - `"role"` - Find by ARIA role (e.g., "button", "link", "heading")
         - `"text"` - Find by visible text content
         - `"labelText"` - Find form inputs by their label text
@@ -184,37 +187,69 @@ Click an element on the page using semantic queries (`testing-library`-style) or
         - `"testId"` - Find by data-testid attribute
         - `"title"` - Find by title attribute
         - `"displayValue"` - Find inputs by their current value
-    - `queryValue` (string, required when using queryType): The value to search for
+    - `queryValue` (string, required): The value to search for
     - `queryOptions` (object, optional): Additional options:
         - `name` (string): Accessible name for role queries
         - `exact` (boolean): Whether to match exact text (default: true)
         - `hidden` (boolean): Include hidden elements (default: false)
         - `level` (number): Heading level for role="heading" (1-6)
-
-- CSS Selectors:
-    - **Parameters:**
-    - `selector` (string, optional): CSS selector or XPath when semantic queries cannot locate the element
+
+    For **webdriverio strategy**:
+    - `selector` (string, required): CSS selector, XPath or WebdriverIO locator
 
 **Examples:**
 ```javascript
-// Semantic queries (preferred)
-{ queryType: "role", queryValue: "button", queryOptions: { name: "Submit" } }
-{ queryType: "text", queryValue: "Click here" }
-{ queryType: "labelText", queryValue: "Email Address" }
-
-// CSS selector fallback
-{ selector: ".submit-btn" }
-{ selector: "#unique-element" }
+// Testing Library strategy
+{
+  locator: {
+    strategy: "testing-library",
+    queryType: "role",
+    queryValue: "button",
+    queryOptions: { name: "Submit" }
+  }
+}
+
+{
+  locator: {
+    strategy: "testing-library",
+    queryType: "text",
+    queryValue: "Click here"
+  }
+}
+
+{
+  locator: {
+    strategy: "testing-library",
+    queryType: "labelText",
+    queryValue: "Email Address"
+  }
+}
+
+// WebdriverIO strategy
+{
+  locator: {
+    strategy: "webdriverio",
+    selector: ".submit-btn"
+  }
+}
+
+{
+  locator: {
+    strategy: "webdriverio",
+    selector: "button*=Submit"
+  }
+}
 ```
 
-**Note:** Provide either semantic query parameters OR selector, not both.
-
 ### `typeIntoElement`
 Type text into an input element on the page using semantic queries (`testing-library`-style) or CSS selectors.
 
-- Semantic Queries:
-    - **Parameters:**
-    - `queryType` (string, optional): Semantic query type. One of:
+- **Parameters:**
+  - `locator` (object, required): Element location strategy
+    - `strategy` (string, required): Either `"testing-library"` or `"webdriverio"`
+
+    For **testing-library strategy**:
+    - `queryType` (string, required): Semantic query type. One of:
         - `"role"` - Find by ARIA role (e.g., "textbox", "searchbox")
         - `"text"` - Find by visible text content
         - `"labelText"` - Find form inputs by their label text
@@ -223,31 +258,55 @@ Type text into an input element on the page using semantic queries (`testing-lib
         - `"testId"` - Find by data-testid attribute
         - `"title"` - Find by title attribute
         - `"displayValue"` - Find inputs by their current value
-    - `queryValue` (string, required when using queryType): The value to search for
-    - `text` (string, required): The text to type into the element
+    - `queryValue` (string, required): The value to search for
     - `queryOptions` (object, optional): Additional options:
         - `name` (string): Accessible name for role queries
         - `exact` (boolean): Whether to match exact text (default: true)
         - `hidden` (boolean): Include hidden elements (default: false)
+
+    For **webdriverio strategy**:
+    - `selector` (string, required): CSS selector or XPath
+
+  - `text` (string, required): The text to type into the element
+
+**Examples:**
 
-- CSS Selectors:
-    - **Parameters:**
-    - `selector` (string, optional): CSS selector or XPath when semantic queries cannot locate the element
-    - `text` (string, required): The text to type into the element
+See above in the `clickOnElement` tool.
+
+### `waitForElement`
+Wait for an element to appear or disappear on the page. Useful for waiting until page loads fully or loading spinners disappear.
+
+- **Parameters:**
+  - `locator` (object, required): Element location strategy
+    - `strategy` (string, required): Either `"testing-library"` or `"webdriverio"`
+
+    For **testing-library strategy**:
+    - `queryType` (string, required): Semantic query type. One of:
+        - `"role"` - Find by ARIA role (e.g., "button", "link", "heading")
+        - `"text"` - Find by visible text content
+        - `"labelText"` - Find form inputs by their label text
+        - `"placeholderText"` - Find inputs by placeholder text
+        - `"altText"` - Find images by alt text
+        - `"testId"` - Find by data-testid attribute
+        - `"title"` - Find by title attribute
+        - `"displayValue"` - Find inputs by their current value
+    - `queryValue` (string, required): The value to search for
+    - `queryOptions` (object, optional): Additional options:
+        - `name` (string): Accessible name for role queries
+        - `exact` (boolean): Whether to match exact text (default: true)
+        - `hidden` (boolean): Include hidden elements (default: false)
+        - `level` (number): Heading level for role="heading" (1-6)
+
+    For **webdriverio strategy**:
+    - `selector` (string, required): CSS selector or XPath
+
+  - `disappear` (boolean, optional): Whether to wait for element to disappear. Default: false (wait for element to appear)
+  - `timeout` (number, optional): Maximum time to wait in milliseconds. Default: 3000
+  - `includeSnapshotInResponse` (boolean, optional): Whether to include page snapshot in response. Default: true
 
 **Examples:**
-```javascript
-// Semantic queries (preferred)
-{ queryType: "labelText", queryValue: "Email Address", text: "[email protected]" }
-{ queryType: "placeholderText", queryValue: "Enter your name", text: "John Smith" }
-{ queryType: "role", queryValue: "textbox", queryOptions: { name: "Username" }, text: "john_doe" }
-
-// CSS selector fallback
-{ selector: "#username", text: "john_doe" }
-{ selector: "input[name='email']", text: "[email protected]" }
-```
 
-**Note:** Provide either semantic query parameters OR selector, not both.
+See above in the `clickOnElement` tool.
 
 </details>
 

src/tools/click-on-element.ts

@@ -11,16 +11,17 @@ const clickOnElementCb: ToolCallback<typeof elementClickSchema> = async args =>
         const context = contextProvider.getContext();
         const browser = await context.browser.get();
 
-        const { element, queryDescription, testplaneCode } = await findElement(browser, args, `await element.click();`);
+        const { element, queryDescription, testplaneCode } = await findElement(browser, args.locator);
 
         await element.click();
 
         console.error(`Successfully clicked element with ${queryDescription}`);
 
         return await createElementStateResponse(element, {
             action: `Successfully clicked element found by ${queryDescription}`,
-            testplaneCode,
-            additionalInfo: `Element selection strategy: ${args.queryType ? `Semantic query (${args.queryType})` : "CSS selector (fallback)"}`,
+            testplaneCode: testplaneCode.startsWith("await")
+                ? `await (${testplaneCode}).click();`
+                : `await ${testplaneCode}.click();`,
         });
     } catch (error) {
         console.error("Error clicking element:", error);
@@ -37,18 +38,7 @@ const clickOnElementCb: ToolCallback<typeof elementClickSchema> = async args =>
 
 export const clickOnElement: ToolDefinition<typeof elementClickSchema> = {
     name: "clickOnElement",
-    description: `Click an element on the page. 
-
-PREFERRED APPROACH (for AI agents): Use semantic queries (queryType + queryValue) which are more robust and accessibility-focused:
-- queryType="role" + queryValue="button" + queryOptions.name="Submit" → finds submit button
-- queryType="text" + queryValue="Click here" → finds element containing that text
-- queryType="labelText" + queryValue="Email" → finds input with Email label
-
-FALLBACK APPROACH: Use selector only when semantic queries cannot locate the element:
-- selector="button.submit-btn" → CSS selector
-- selector="//button[text()='Submit']" → XPath
-
-AI agents should prioritize semantic queries for better accessibility and test maintainability.`,
+    description: "Click an element on the page.",
     schema: elementClickSchema,
     cb: clickOnElementCb,
 };

src/tools/index.ts

@@ -8,6 +8,7 @@ import { listTabs } from "./list-tabs.js";
 import { switchToTab } from "./switch-to-tab.js";
 import { openNewTab } from "./open-new-tab.js";
 import { closeTab } from "./close-tab.js";
+import { waitForElement } from "./wait-for-element.js";
 
 export const tools = [
     navigate,
@@ -19,4 +20,5 @@ export const tools = [
     switchToTab,
     openNewTab,
     closeTab,
+    waitForElement,
 ] as const satisfies ToolDefinition<any>[]; // eslint-disable-line @typescript-eslint/no-explicit-any

src/tools/navigate.ts

@@ -16,11 +16,11 @@ const navigateCb: ToolCallback<typeof navigateSchema> = async args => {
         const browser = await context.browser.get();
 
         console.error(`Navigating to: ${url}`);
-        await browser.url(url);
+        await browser.openAndWait(url);
 
         return await createBrowserStateResponse(browser, {
             action: `Successfully navigated to ${url}`,
-            testplaneCode: `await browser.url("${url}");`,
+            testplaneCode: `await browser.openAndWait("${url}");`,
         });
     } catch (error) {
         console.error("Error navigating to URL:", error);

src/tools/take-page-snapshot.ts

@@ -46,7 +46,7 @@ const takePageSnapshotCb: ToolCallback<typeof takePageSnapshotSchema> = async ar
 export const takePageSnapshot: ToolDefinition<typeof takePageSnapshotSchema> = {
     name: "takePageSnapshot",
     description:
-        "Capture a DOM snapshot of the current page. Note: by default, only useful tags and attributes are included. Prefer to use defaults. Response contains info as to what was omitted. If you need more info, request a snapshot with more tags and attributes.",
+        "Capture a DOM snapshot of the current page. Note: by default, not useful tags and attributes are excluded (e.g. script, style, etc.). Prefer to use defaults. Response contains info as to what was omitted. If you need more info, request a snapshot with more tags and attributes.",
     schema: takePageSnapshotSchema,
     cb: takePageSnapshotCb,
 };

src/tools/type-into-element.ts

@@ -12,25 +12,22 @@ export const typeIntoElementSchema = {
 
 const typeIntoElementCb: ToolCallback<typeof typeIntoElementSchema> = async args => {
     try {
-        const { text, ...selectorArgs } = args;
+        const { text } = args;
 
         const context = contextProvider.getContext();
         const browser = await context.browser.get();
 
-        const { element, queryDescription, testplaneCode } = await findElement(
-            browser,
-            selectorArgs,
-            `await element.setValue("${text}");`,
-        );
+        const { element, queryDescription, testplaneCode } = await findElement(browser, args.locator);
 
         await element.setValue(text);
 
         console.error(`Successfully typed "${text}" into element with ${queryDescription}`);
 
         return await createElementStateResponse(element, {
             action: `Successfully typed "${text}" into element found by ${queryDescription}`,
-            testplaneCode,
-            additionalInfo: `Element selection strategy: ${selectorArgs.queryType ? `Semantic query (${selectorArgs.queryType})` : "CSS selector (fallback)"}`,
+            testplaneCode: testplaneCode.startsWith("await")
+                ? `await (${testplaneCode}).setValue("${text}");`
+                : `await ${testplaneCode}.setValue("${text}");`,
         });
     } catch (error) {
         console.error("Error typing into element:", error);
@@ -47,18 +44,7 @@ const typeIntoElementCb: ToolCallback<typeof typeIntoElementSchema> = async args
 
 export const typeIntoElement: ToolDefinition<typeof typeIntoElementSchema> = {
     name: "typeIntoElement",
-    description: `Type text into an element on the page. The API is very similar to clickOnElement for consistency.
-
-PREFERRED APPROACH (for AI agents): Use semantic queries (queryType + queryValue) which are more robust and accessibility-focused:
-- queryType="role" + queryValue="textbox" + queryOptions.name="Email" → finds email input
-- queryType="labelText" + queryValue="Password" → finds input with Password label
-- queryType="placeholderText" + queryValue="Enter your name" → finds input with specific placeholder
-
-FALLBACK APPROACH: Use selector only when semantic queries cannot locate the element:
-- selector="input[name='email']" → CSS selector
-- selector="//input[@placeholder='Search...']" → XPath
-
-AI agents should prioritize semantic queries for better accessibility and test maintainability.`,
+    description: "Type text into an element on the page.",
     schema: typeIntoElementSchema,
     cb: typeIntoElementCb,
 };