diff options
| author | amankumarsingh77 <amankumarsingh7702@gmal.com> | 2026-05-02 16:12:36 +0530 |
|---|---|---|
| committer | amankumarsingh77 <amankumarsingh7702@gmal.com> | 2026-05-02 16:12:36 +0530 |
| commit | 307f9e746c5288e12c62f16efdd6a0868f84bc59 (patch) | |
| tree | aa7e27989b3e6458951bbf9429090708ffe9fd33 /src | |
| parent | 41e3b69b257442551bb581947f850161ae58aaec (diff) | |
feat(domains): migrate scroll with W3C deltaY semantics and dialog guard
Diffstat (limited to 'src')
| -rw-r--r-- | src/domains/scroll.ts | 53 | ||||
| -rw-r--r-- | src/registry.ts | 2 | ||||
| -rw-r--r-- | src/tools.ts | 70 |
3 files changed, 55 insertions, 70 deletions
diff --git a/src/domains/scroll.ts b/src/domains/scroll.ts new file mode 100644 index 0000000..db80af7 --- /dev/null +++ b/src/domains/scroll.ts @@ -0,0 +1,53 @@ +import { Type } from "typebox"; +import { type Result, err, ok } from "../util/result"; +import { defineBrowserTool, type ToolErr, type ToolOk } from "../util/tool"; + +const ScrollArgs = Type.Object({ + x: Type.Optional(Type.Number({ description: "X coordinate where to scroll. Default: viewport center" })), + y: Type.Optional(Type.Number({ description: "Y coordinate where to scroll. Default: viewport center" })), + deltaX: Type.Optional(Type.Number({ default: 0, description: "Horizontal scroll delta (CSS pixels). Positive = right." })), + deltaY: Type.Optional(Type.Number({ + default: -300, + description: "Vertical scroll delta (CSS pixels). Positive = up (matches W3C wheel events). Default: -300 (scroll down).", + })), +}); + +export const scrollTool = defineBrowserTool({ + name: "browser_scroll", + label: "Browser Scroll", + description: + "Scroll the page at given coordinates. deltaY follows W3C wheel-event convention: positive = scroll up, negative = scroll down. Default scrolls down (deltaY = -300).", + promptSnippet: "Scroll the page (deltaY positive=up, negative=down)", + promptGuidelines: [ + "Default behavior scrolls down 300px (deltaY=-300). Pass a positive deltaY to scroll up.", + "Pass x/y to target a specific scrollable region (e.g., a div with overflow); otherwise scrolls the page at viewport center.", + ], + parameters: ScrollArgs, + async handler(args, { client }): Promise<Result<ToolOk, ToolErr>> { + const info = await client.pageInfo(); + if (!info.success) return err({ kind: "cdp_error", message: info.error.message }); + if ("dialog" in info.data) { + return err({ + kind: "invalid_state", + message: `Dialog open: ${info.data.dialog.type} — ${info.data.dialog.message}`, + }); + } + const cx = args.x ?? Math.round(info.data.width / 2); + const cy = args.y ?? Math.round(info.data.height / 2); + const dx = args.deltaX ?? 0; + const dy = args.deltaY ?? -300; + // Establish compositor mouse position before mouseWheel; without this, + // CDP sometimes drops the wheel event with a timeout. Fix preserved + // from v0.2.0. + const moved = await client.session().call("Input.dispatchMouseEvent", { type: "mouseMoved", x: cx, y: cy }); + if (!moved.success) return err({ kind: "cdp_error", message: moved.error.message }); + const wheel = await client.session().call("Input.dispatchMouseEvent", { + type: "mouseWheel", x: cx, y: cy, deltaX: dx, deltaY: dy, + }); + if (!wheel.success) return err({ kind: "cdp_error", message: wheel.error.message }); + return ok({ + text: `Scrolled at (${cx}, ${cy}) by (${dx}, ${dy})`, + details: { x: cx, y: cy, deltaX: dx, deltaY: dy }, + }); + }, +}); diff --git a/src/registry.ts b/src/registry.ts index e2b13b4..a635042 100644 --- a/src/registry.ts +++ b/src/registry.ts @@ -3,12 +3,14 @@ import type { BrowserClient } from "./client"; import { type AnyBrowserToolDefinition, registerBrowserTool } from "./util/tool"; import { clickTool } from "./domains/click"; import { typeTool, pressKeyTool, dispatchKeyTool } from "./domains/keyboard"; +import { scrollTool } from "./domains/scroll"; const TOOLS: ReadonlyArray<AnyBrowserToolDefinition> = [ clickTool, typeTool, pressKeyTool, dispatchKeyTool, + scrollTool, ]; export const registerAllTools = (pi: ExtensionAPI, client: BrowserClient): void => { diff --git a/src/tools.ts b/src/tools.ts index 834d9c3..b1ef044 100644 --- a/src/tools.ts +++ b/src/tools.ts @@ -319,76 +319,6 @@ export function registerTools(pi: ExtensionAPI, daemon: BrowserDaemon): void { }); // ═══════════════════════════════════════════════════════════════════════════ - // browser_scroll - // ═══════════════════════════════════════════════════════════════════════════ - pi.registerTool({ - name: "browser_scroll", - label: "Browser Scroll", - description: - "Scroll the page at given coordinates (or center of viewport if not specified). Default scrolls down 300px.", - promptSnippet: "Scroll the page by deltaY/deltaX pixels at coordinates", - promptGuidelines: [ - "Use browser_scroll to scroll pages. Default deltaY=-300 scrolls down.", - "Positive deltaY scrolls up, negative scrolls down.", - "Capture browser_screenshot after scrolling to see the new viewport content.", - "If mouseWheel scroll doesn't work on a specific element, try browser_execute_js to scroll a container directly: e.scrollTop += 300 or e.scrollIntoView().", - ], - parameters: Type.Object({ - deltaY: Type.Optional(Type.Number({ description: "Vertical scroll delta in pixels. Negative = down, positive = up. Default: -300" })), - deltaX: Type.Optional(Type.Number({ description: "Horizontal scroll delta in pixels. Default: 0" })), - x: Type.Optional(Type.Number({ description: "X position to scroll from. Default: viewport center" })), - y: Type.Optional(Type.Number({ description: "Y position to scroll from. Default: viewport center" })), - }), - async execute(_id, params) { - try { - await daemon.ensureAlive(); - const dy = params.deltaY ?? -300; - const dx = params.deltaX ?? 0; - - // Default to center of viewport if not specified - let cx = params.x; - let cy = params.y; - if (cx === undefined || cy === undefined) { - try { - const info = await daemon.getPageInfo(); - if (!("dialog" in info)) { - if (cx === undefined) cx = Math.round(info.width / 2); - if (cy === undefined) cy = Math.round(info.height / 2); - } - } catch { - cx = cx ?? 500; - cy = cy ?? 400; - } - } - - // Establish mouse position before wheel — Chrome requires a prior - // mouseMoved for mouseWheel to hit the correct element. - await daemon.cdp("Input.dispatchMouseEvent", { - type: "mouseMoved", - x: cx, - y: cy, - }); - - await daemon.cdp("Input.dispatchMouseEvent", { - type: "mouseWheel", - x: cx, - y: cy, - deltaX: dx, - deltaY: dy, - }); - - return { content: [{ type: "text" as const, text: `Scrolled by (${dx}, ${dy}) at (${cx}, ${cy})` }], details: undefined }; - } catch (err) { - return { - isError: true, - content: [{ type: "text" as const, text: `Scroll failed: ${err instanceof Error ? err.message : String(err)}` }], - details: undefined, - }; - } - }, - }); - - // ═══════════════════════════════════════════════════════════════════════════ // browser_upload_file // ═══════════════════════════════════════════════════════════════════════════ pi.registerTool({ |
