Skip to content

feat(browserTool): Implement hover action #2368

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mrubens merged 2 commits into from
Apr 7, 2025
Merged

feat(browserTool): Implement hover action #2368

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
273540a
Implement hover action for the browser action tool
SplittyDev Apr 7, 2025
bee2207
Update snapshots
SplittyDev Apr 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions src/core/prompts/__tests__/__snapshots__/system.test.ts.snap
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2714,6 +2714,9 @@ Parameters:
* launch: Launch a new Puppeteer-controlled browser instance at the specified URL. This **must always be the first action**.
- Use with the \`url\` parameter to provide the URL.
- Ensure the URL is valid and includes the appropriate protocol (e.g. http://localhost:3000/page, file:///path/to/file.html, etc.)
* hover: Move the cursor to a specific x,y coordinate.
- Use with the \`coordinate\` parameter to specify the location.
- Always move to the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
* click: Click at a specific x,y coordinate.
- Use with the \`coordinate\` parameter to specify the location.
- Always click in the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
Expand All @@ -2725,7 +2728,7 @@ Parameters:
- Example: \`<action>close</action>\`
- url: (optional) Use this for providing the URL for the \`launch\` action.
* Example: <url>https://example.com</url>
- coordinate: (optional) The X and Y coordinates for the \`click\` action. Coordinates should be within the **900x600** resolution.
- coordinate: (optional) The X and Y coordinates for the \`click\` and \`hover\` actions. Coordinates should be within the **900x600** resolution.
* Example: <coordinate>450,300</coordinate>
- text: (optional) Use this for providing the text for the \`type\` action.
* Example: <text>Hello, world!</text>
Expand Down Expand Up @@ -3625,6 +3628,9 @@ Parameters:
* launch: Launch a new Puppeteer-controlled browser instance at the specified URL. This **must always be the first action**.
- Use with the \`url\` parameter to provide the URL.
- Ensure the URL is valid and includes the appropriate protocol (e.g. http://localhost:3000/page, file:///path/to/file.html, etc.)
* hover: Move the cursor to a specific x,y coordinate.
- Use with the \`coordinate\` parameter to specify the location.
- Always move to the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
* click: Click at a specific x,y coordinate.
- Use with the \`coordinate\` parameter to specify the location.
- Always click in the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
Expand All @@ -3636,7 +3642,7 @@ Parameters:
- Example: \`<action>close</action>\`
- url: (optional) Use this for providing the URL for the \`launch\` action.
* Example: <url>https://example.com</url>
- coordinate: (optional) The X and Y coordinates for the \`click\` action. Coordinates should be within the **1280x800** resolution.
- coordinate: (optional) The X and Y coordinates for the \`click\` and \`hover\` actions. Coordinates should be within the **1280x800** resolution.
* Example: <coordinate>450,300</coordinate>
- text: (optional) Use this for providing the text for the \`type\` action.
* Example: <text>Hello, world!</text>
Expand Down
5 changes: 4 additions & 1 deletion src/core/prompts/tools/browser-action.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,9 @@ Parameters:
* launch: Launch a new Puppeteer-controlled browser instance at the specified URL. This **must always be the first action**.
- Use with the \`url\` parameter to provide the URL.
- Ensure the URL is valid and includes the appropriate protocol (e.g. http://localhost:3000/page, file:///path/to/file.html, etc.)
* hover: Move the cursor to a specific x,y coordinate.
- Use with the \`coordinate\` parameter to specify the location.
- Always move to the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
* click: Click at a specific x,y coordinate.
- Use with the \`coordinate\` parameter to specify the location.
- Always click in the center of an element (icon, button, link, etc.) based on coordinates derived from a screenshot.
Expand All @@ -26,7 +29,7 @@ Parameters:
- Example: \`<action>close</action>\`
- url: (optional) Use this for providing the URL for the \`launch\` action.
* Example: <url>https://example.com</url>
- coordinate: (optional) The X and Y coordinates for the \`click\` action. Coordinates should be within the **${args.browserViewportSize}** resolution.
- coordinate: (optional) The X and Y coordinates for the \`click\` and \`hover\` actions. Coordinates should be within the **${args.browserViewportSize}** resolution.
* Example: <coordinate>450,300</coordinate>
- text: (optional) Use this for providing the text for the \`type\` action.
* Example: <text>Hello, world!</text>
Expand Down
6 changes: 5 additions & 1 deletion src/core/tools/browserActionTool.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ export async function browserActionTool(
await cline.browserSession.launchBrowser()
browserActionResult = await cline.browserSession.navigateToUrl(url)
} else {
if (action === "click") {
if (action === "click" || action === "hover") {
if (!coordinate) {
cline.consecutiveMistakeCount++
pushToolResult(await cline.sayAndCreateMissingParamError("browser_action", "coordinate"))
Expand Down Expand Up @@ -103,6 +103,9 @@ export async function browserActionTool(
case "click":
browserActionResult = await cline.browserSession.click(coordinate!)
break
case "hover":
browserActionResult = await cline.browserSession.hover(coordinate!)
break
case "type":
browserActionResult = await cline.browserSession.type(text!)
break
Expand All @@ -121,6 +124,7 @@ export async function browserActionTool(
switch (action) {
case "launch":
case "click":
case "hover":
case "type":
case "scroll_down":
case "scroll_up":
Expand Down