pi-chrome 0.11.0 → 0.11.2

package/extensions/chrome-profile-bridge/browser-extension/manifest.json

@@ -1,7 +1,7 @@
 {
   "manifest_version": 3,
   "name": "Pi Chrome Connector",
-  "version": "0.11.0",
+  "version": "0.11.2",
   "description": "Lets Pi control tabs in Chrome via a local connector at 127.0.0.1.",
   "permissions": ["tabs", "scripting", "storage", "activeTab", "alarms", "webNavigation", "debugger"],
   "host_permissions": ["<all_urls>", "http://127.0.0.1:17318/*"],

package/extensions/chrome-profile-bridge/browser-extension/service_worker.js

@@ -103,7 +103,7 @@ setInterval(() => {
   }
 }, 5000);
 
-function cdp(tabId, method, params) {
+function cdpRaw(tabId, method, params) {
   return new Promise((resolve, reject) => {
     chrome.debugger.sendCommand({ tabId }, method, params || {}, (result) => {
       if (chrome.runtime.lastError) reject(new Error(`${method}: ${chrome.runtime.lastError.message}`));
@@ -112,6 +112,24 @@ function cdp(tabId, method, params) {
   });
 }
 
+// Wraps cdpRaw with one auto-recover on detached/closed sessions:
+// chrome.debugger.attach can stay cached in attachedTabs even after Chrome killed
+// the session (tab nav, devtools opened/closed, etc). Recover by detaching the
+// stale entry and re-attaching, then retry the command once.
+async function cdp(tabId, method, params) {
+  try {
+    return await cdpRaw(tabId, method, params);
+  } catch (error) {
+    const msg = String(error?.message || error);
+    const isStale = /Debugger is not attached|Detached while|Target closed|No tab with id/i.test(msg);
+    if (!isStale) throw error;
+    attachedTabs.delete(tabId);
+    await chrome.debugger.attach({ tabId }, CDP_VERSION).catch(() => undefined);
+    attachedTabs.set(tabId, { detachAt: Date.now() + TRUSTED_IDLE_DETACH_MS, pointer: { x: 120 + Math.random() * 200, y: 80 + Math.random() * 120 } });
+    return cdpRaw(tabId, method, params);
+  }
+}
+
 // Resolve target -> {x, y, rect} in viewport coords by running tiny script in tab.
 async function resolveTargetInTab(tabId, params) {
   const results = await chrome.scripting.executeScript({
@@ -349,20 +367,49 @@ async function trustedScroll(params) {
   const x = resolved.rect ? resolved.rect.left + Math.min(resolved.rect.width, 800) / 2 : resolved.x;
   const y = resolved.rect ? resolved.rect.top + Math.min(resolved.rect.height, 600) / 2 : resolved.y;
   const totalY = params.deltaY || 0, totalX = params.deltaX || 0;
-  const n = Math.max(3, Math.min(20, params.steps || Math.ceil(Math.abs(totalY) / 120)));
-  // momentum-shaped front-loaded weights
-  const w = []; for (let i = 1; i <= n; i++) w.push(1 / i);
+  // Per-event delta cap so IntersectionObserver / scroll-driven animations get gradient samples.
+  // A real wheel notch is ~50-120px; we aim for the lower end so visibility transitions are visible.
+  const MAX_STEP = 60;
+  const peak = Math.max(Math.abs(totalY), Math.abs(totalX));
+  // We weight events with mild front-loading. The peak weight = 1.5 / n (vs uniform 1/n), so the
+  // first event is ~1.5× average. Choose n so even the peak event stays under MAX_STEP.
+  const minN = Math.ceil(peak * 1.5 / MAX_STEP);
+  const n = Math.max(6, Math.min(80, params.steps || Math.max(minN, 12)));
+  // Front-loaded but smooth weights: w[i] = 1 + 0.5 * (1 - i/(n-1)) so the first event has
+  // weight 1.5, the last has 1.0, average ~1.25; redistribution stays predictable.
+  const w = [];
+  for (let i = 0; i < n; i++) {
+    const t = i / Math.max(1, n - 1);
+    w.push(1 + 0.5 * (1 - t));
+  }
   const sumW = w.reduce((a, b) => a + b, 0);
   for (let i = 0; i < n; i++) {
     const dy = totalY * (w[i] / sumW), dx = totalX * (w[i] / sumW);
     await cdp(tab.id, "Input.dispatchMouseEvent", {
       type: "mouseWheel", x, y, deltaX: dx, deltaY: dy, pointerType: "mouse",
     });
-    await sleep(rng(14, 32));
+    // Sleep one+ frame so IntersectionObserver / rAF samples can run between events.
+    await sleep(rng(22, 48));
   }
   return { trusted: true, deltaX: totalX, deltaY: totalY, steps: n };
 }
 
+async function trustedTap(params) {
+  const tab = await getTabByParams(params);
+  if (params.foreground) await bringToFront(tab);
+  await attachDebugger(tab.id);
+  const resolved = (params.selector || params.uid || (typeof params.x === "number" && typeof params.y === "number"))
+    ? await resolveTargetInTab(tab.id, params)
+    : null;
+  if (!resolved || !resolved.found) throw new Error("trusted.tap: target not found");
+  const point = resolved.rect ? pickInsideRect(resolved.rect) : { x: resolved.x, y: resolved.y };
+  const tp = { x: point.x, y: point.y, radiusX: 8, radiusY: 8, rotationAngle: 0, force: 0.5, id: 1 };
+  await cdp(tab.id, "Input.dispatchTouchEvent", { type: "touchStart", touchPoints: [tp] });
+  await sleep(rng(40, 110));
+  await cdp(tab.id, "Input.dispatchTouchEvent", { type: "touchEnd", touchPoints: [] });
+  return { trusted: true, x: point.x, y: point.y, tag: resolved.tag };
+}
+
 async function trustedDrag(params) {
   const tab = await getTabByParams(params);
   if (params.foreground) await bringToFront(tab);
@@ -537,6 +584,8 @@ async function dispatch(action, params) {
     case "page.scroll":
       if (await wantsTrusted(params)) return trustedScroll(params);
       return executeActionInTab(params, scrollPage, [params.selector ?? null, params.uid ?? null, params.deltaY ?? 0, params.deltaX ?? 0, params.steps ?? null]);
+    case "page.tap":
+      return trustedTap(params);
     case "trusted.mode":
       return setTrustedMode(params.mode);
     case "trusted.status":

package/extensions/chrome-profile-bridge/index.ts

@@ -1165,6 +1165,29 @@ Usage rules:
 		},
 	});
 
+	pi.registerTool({
+		name: "chrome_tap",
+		label: "Chrome Tap (Touch)",
+		description:
+			"Dispatch a real browser-trusted touchstart/touchend tap via chrome.debugger (CDP Input.dispatchTouchEvent). Use for sites that gate on TouchEvent rather than MouseEvent (mobile-first PWAs, swipe carousels). Always uses the trusted CDP path — the yellow debugger banner appears.",
+		promptSnippet: "Tap (real touch) a Chrome element by snapshot uid, selector, or coordinate.",
+		parameters: Type.Object({
+			uid: Type.Optional(Type.String()),
+			selector: Type.Optional(Type.String()),
+			x: Type.Optional(Type.Number()),
+			y: Type.Optional(Type.Number()),
+			targetId: Type.Optional(Type.String()),
+			urlIncludes: Type.Optional(Type.String()),
+			titleIncludes: Type.Optional(Type.String()),
+			background: Type.Optional(Type.Boolean()),
+		}),
+		async execute(_id, params): Promise<ToolTextResult> {
+			const result = await bridge.send("page.tap", withBackground(params), DEFAULT_TIMEOUT_MS);
+			const target = params.uid ?? params.selector ?? `${params.x},${params.y}`;
+			return { content: [{ type: "text", text: `Tapped ${target} (touch)` }], details: { result: result as Json } };
+		},
+	});
+
 	pi.registerTool({
 		name: "chrome_scroll",
 		label: "Chrome Scroll",

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "pi-chrome",
-	"version": "0.11.0",
+	"version": "0.11.2",
 	"description": "Drive your existing logged-in Chrome from Pi — no re-login, no throwaway profile, watch the agent work in real time (or toggle quiet background mode).",
 	"keywords": [
 		"pi-package",