2 Commits

Author SHA1 Message Date
javis-bot
ffc16665e5 fix(controlBrowser): never report moveMouse/search success without a real move
Some checks failed
Release / semantic-release (push) Successful in 19s
tests / Unit tests (Linux, Python 3.11) (push) Failing after 5m15s
Release / build-linux (push) Failing after 7m7s
Release / build-windows (push) Has been cancelled
Release / build-macos (arm64, macos-latest) (push) Has been cancelled
Release / build-macos (x64, macos-15-intel) (push) Has been cancelled
Release / release-main (push) Has been cancelled
Release / release-develop (push) Has been cancelled
moveMouse returned ok:true even when humanHover did nothing (no on-screen box)
or the selector never matched — recreating the "claims it moved but didn't"
bug. Now: humanHover returns a boolean (and brings the element into view first);
moveMouse returns ok:false when the target isn't found or has no on-screen box,
and when site=naver/... whose box isn't on the current page it navigates to the
site home first before hovering. search now reports input=human|api-fallback|api
so a silent fallback to cursor-less DOM input is visible, and the tool surfaces
that note in the reply instead of implying a human-like search happened.
2026-06-24 19:17:46 +09:00
javis-bot
5629da7e9f feat(controlBrowser): add moveMouse (hover) action for the visible cursor
The tool had no cursor-move/hover action, so "move the mouse to the search box"
had nothing to call and a weak model just claimed it had moved it. Add a
moveMouse action wired to human.humanHover (real xdotool cursor), targetable by
CSS selector or site= (that site's search box). Also clarify in the tool
description that 'navigate' types into the address bar (no mouse) while
'search'/'type' move the real cursor to the on-page box and click before
typing, so the model picks the visible-cursor path when the user wants it.
2026-06-24 19:14:04 +09:00
4 changed files with 143 additions and 18 deletions

View File

@@ -17,6 +17,7 @@
// status | listTabs
// navigate {url} | back | forward | refresh
// newTab {url?} | closeTab {index?} | activateTab {index} | closePopups
// moveMouse {selector | site} (hover the real cursor, no click)
// click {selector} | type {text, selector?} | scroll {dir, notches?}
// pressKey {key} | screenshot {path}
import { chromium } from 'playwright';
@@ -40,6 +41,15 @@ if (!action) { out({ ok: false, error: 'no action' }); process.exit(1); }
const norm = (u) => (/^https?:\/\//i.test(u) ? u : `https://${u}`);
// Per-site homepage + search-box selector, shared by `search` and `moveMouse`.
const SITES = {
naver: { home: 'https://www.naver.com', box: '#query, input[name="query"]' },
google: { home: 'https://www.google.com', box: 'textarea[name="q"], input[name="q"]' },
daum: { home: 'https://www.daum.net', box: '#q, input[name="q"]' },
youtube: { home: 'https://www.youtube.com', box: 'input#search, input[name="search_query"]' },
bing: { home: 'https://www.bing.com', box: '#sb_form_q, input[name="q"]' },
};
// The genuinely-active tab is the one whose document is visible. Playwright has
// no "active page" accessor over CDP, so probe visibilityState (fixes treating
// tab 0 as active and breaking sequential ops on a specific tab).
@@ -103,13 +113,6 @@ try {
const q = String(cmd.query || '').trim();
if (!q) throw new Error('search: no query');
const siteKey = String(cmd.site || 'google').toLowerCase();
const SITES = {
naver: { home: 'https://www.naver.com', box: '#query, input[name="query"]' },
google: { home: 'https://www.google.com', box: 'textarea[name="q"], input[name="q"]' },
daum: { home: 'https://www.daum.net', box: '#q, input[name="q"]' },
youtube: { home: 'https://www.youtube.com', box: 'input#search, input[name="search_query"]' },
bing: { home: 'https://www.bing.com', box: '#sb_form_q, input[name="q"]' },
};
const s = SITES[siteKey] || SITES.google;
await front(page);
// 1) Go to the homepage.
@@ -122,23 +125,31 @@ try {
// 2) Click the on-page search box, type the query, submit.
const box = page.locator(s.box).first();
await box.waitFor({ state: 'visible', timeout: 15000 }).catch(() => {});
// Report which input path actually ran: 'human' = real xdotool cursor
// move + char typing; 'api-fallback' = the humanClick path threw and we
// fell back to cursor-less DOM click/fill; 'api' = no xdotool at all. This
// makes "did the cursor really move" verifiable from the result.
let searchInput;
if (HAS_XDOTOOL && cmd.human !== false) {
try {
await human.humanClick(page, box);
await human.humanType(q);
await human.pressKey('Return');
searchInput = 'human';
} catch {
searchInput = 'api-fallback';
await box.click().catch(() => {});
await box.fill(q).catch(() => {});
await page.keyboard.press('Enter').catch(() => {});
}
} else {
searchInput = 'api';
await box.click().catch(() => {});
await box.fill(q);
await page.keyboard.press('Enter');
}
await page.waitForLoadState('domcontentloaded').catch(() => {});
out({ ok: true, site: SITES[siteKey] ? siteKey : 'google', query: q, url: page.url(), title: await page.title().catch(() => '') });
out({ ok: true, site: SITES[siteKey] ? siteKey : 'google', query: q, url: page.url(), title: await page.title().catch(() => ''), input: searchInput });
break;
}
@@ -205,6 +216,45 @@ try {
break;
}
case 'moveMouse': {
// Move/hover the REAL cursor onto an element WITHOUT clicking. Target is a
// CSS selector, or site=naver/google/... for that site's search box.
// Only meaningful with xdotool (the visible cursor); with no xdotool there
// is no cursor to move, so report that rather than faking success. Every
// failure to actually move (no xdotool, selector never matches, element
// has no on-screen box) returns ok:false — we must never claim the cursor
// moved when it did not (the exact bug the user reported).
const siteKey = String(cmd.site || '').toLowerCase();
const selector = String(cmd.selector || '').trim() || (SITES[siteKey] ? SITES[siteKey].box : '');
if (!selector) throw new Error('moveMouse: no selector or known site');
if (!(HAS_XDOTOOL && cmd.human !== false)) {
out({ ok: false, error: 'no xdotool: cannot move the visible cursor on this host' });
break;
}
await front(page);
let locator = page.locator(selector).first();
let visible = await locator.waitFor({ state: 'visible', timeout: 8000 }).then(() => true).catch(() => false);
// A named site whose search box isn't on the current page: go to its home
// first (real omnibox), then target the box there.
if (!visible && SITES[siteKey]) {
try { await human.navigateOmnibox(SITES[siteKey].home); await page.waitForLoadState('domcontentloaded').catch(() => {}); }
catch { await page.goto(SITES[siteKey].home, { waitUntil: 'domcontentloaded' }).catch(() => {}); }
locator = page.locator(SITES[siteKey].box).first();
visible = await locator.waitFor({ state: 'visible', timeout: 8000 }).then(() => true).catch(() => false);
}
if (!visible) {
out({ ok: false, error: `moveMouse: target not found (${cmd.selector || siteKey})` });
break;
}
const moved = await human.humanHover(page, locator);
if (!moved) {
out({ ok: false, error: 'moveMouse: element has no on-screen box; cursor not moved' });
break;
}
out({ ok: true, target: cmd.selector || siteKey, input: 'human' });
break;
}
case 'click': {
const selector = String(cmd.selector || '').trim();
if (!selector) throw new Error('click: no selector');

View File

@@ -136,14 +136,18 @@ export async function navigateOmnibox(text) {
}
// Move the real cursor over an element (hover, no click) - e.g. to reveal a
// video player's controls or to focus it for a keyboard shortcut.
// video player's controls or to focus it for a keyboard shortcut. Returns true
// only if the element had an on-screen box and the cursor was actually moved;
// returns false when there is nothing to move to (so callers must not report
// success). Brings the element into view with a real wheel scroll first.
export async function humanHover(page, locator) {
const box = await locator.boundingBox().catch(() => null);
if (!box) return;
const box = await bringIntoView(page, locator);
if (!box) return false;
const g = await page.evaluate(() => ({ sx: window.screenX, sy: window.screenY, ow: window.outerWidth, oh: window.outerHeight, iw: window.innerWidth, ih: window.innerHeight }));
const bx = Math.max(0, Math.round((g.ow - g.iw) / 2));
const oy = g.sy + Math.max(0, g.oh - g.ih - bx);
await humanMove(Math.round(g.sx + bx + box.x + box.width * 0.5), Math.round(oy + box.y + box.height * 0.4));
return true;
}
export { sleep, rand };

View File

@@ -45,9 +45,16 @@ class ControlBrowserTool(Tool):
"Use this (NOT webSearch) whenever the user wants something done or shown IN the "
"browser on screen: open a website or URL, search on a specific site (action "
"'search' with site=naver/google/daum/youtube/bing), go back/forward, refresh, "
"manage tabs (list/new/close/switch), close popups, click, type, scroll, or "
"screenshot. webSearch only returns text and shows nothing on screen; this tool "
"actually navigates the visible browser. Only available in screen-share mode. "
"manage tabs (list/new/close/switch), close popups, move the mouse onto an element, "
"click, type, scroll, or screenshot. webSearch only returns text and shows nothing "
"on screen; this tool actually navigates the visible browser. "
"Cursor behaviour matters: 'search' and 'type' (with a selector) move the REAL mouse "
"cursor to the on-page box, click it, then type one character at a time — use these "
"when the user wants to search or type on a page. 'navigate' only types the URL into "
"the address bar (no mouse movement). 'moveMouse' moves/hovers the visible cursor "
"onto an element (selector, or site=naver/... for that site's search box) WITHOUT "
"clicking — use it when the user just asks to move the mouse somewhere. "
"Only available in screen-share mode. "
"Never claim you did any of this unless this tool returns success."
)
@@ -61,16 +68,16 @@ class ControlBrowserTool(Tool):
"enum": [
"status", "listTabs", "navigate", "search", "back",
"forward", "refresh", "newTab", "closeTab", "activateTab",
"closePopups", "click", "type", "scroll", "pressKey",
"closePopups", "moveMouse", "click", "type", "scroll", "pressKey",
"screenshot",
],
"description": "What to do in the browser.",
},
"url": {"type": "string", "description": "Target URL/site for navigate/newTab (e.g. 'naver.com')."},
"query": {"type": "string", "description": "Search text for action 'search'."},
"site": {"type": "string", "description": "Search site for action 'search': naver, google, daum, youtube, bing."},
"site": {"type": "string", "description": "Site for action 'search' or 'moveMouse': naver, google, daum, youtube, bing. For moveMouse it targets that site's search box."},
"index": {"type": "integer", "description": "Tab index for closeTab/activateTab (from listTabs)."},
"selector": {"type": "string", "description": "CSS selector for click/type."},
"selector": {"type": "string", "description": "CSS selector for click/type/moveMouse."},
"text": {"type": "string", "description": "Text to type."},
"key": {"type": "string", "description": "Key to press, e.g. 'Return', 'Escape'."},
"dir": {"type": "string", "description": "Scroll direction: 'down' or 'up'."},
@@ -149,7 +156,12 @@ class ControlBrowserTool(Tool):
if action == "navigate":
return f"브라우저에서 {data.get('url', args.get('url'))} 로 이동했습니다."
if action == "search":
return f"{data.get('site', '')}에서 '{data.get('query', args.get('query'))}'를 검색해 화면에 띄웠습니다."
base = f"{data.get('site', '')}에서 '{data.get('query', args.get('query'))}'를 검색해 화면에 띄웠습니다."
# Flag when the real cursor path didn't run, so a silent fallback to
# cursor-less DOM input is visible rather than reported as "human".
if data.get("input") in ("api", "api-fallback"):
base += " (참고: 실제 마우스 커서 이동 없이 처리됨)"
return base
if action in ("back", "forward", "refresh"):
return f"브라우저: {action} 완료 ({data.get('url', '')})."
if action in ("status", "listTabs"):
@@ -164,6 +176,9 @@ class ControlBrowserTool(Tool):
return f"{data.get('active')}번으로 전환했습니다."
if action == "closePopups":
return f"팝업/빈 탭 {data.get('closed')}개를 닫았습니다."
if action == "moveMouse":
target = data.get("target") or args.get("selector") or args.get("site") or "대상"
return f"마우스 커서를 {target} 위치로 옮겼습니다."
if action == "screenshot":
return f"화면을 캡처했습니다: {data.get('path')}"
return "완료했습니다."

View File

@@ -0,0 +1,56 @@
"""Tests for the controlBrowser tool's action surface.
These are deterministic schema/summary checks — they do not drive a real
browser. The actual cursor movement is exercised live on the browser host
(xdotool + CDP), which these tests cannot reach.
"""
import pytest
from jarvis.tools.builtin.control_browser import ControlBrowserTool
@pytest.fixture
def tool():
return ControlBrowserTool()
def test_movemouse_is_an_exposed_action(tool):
# A weak model confabulated "moved the mouse" because no move/hover action
# existed to call. The cursor-move capability must be a real action so the
# request "move the mouse to the search box" maps to a tool call.
enum = tool.inputSchema["properties"]["action"]["enum"]
assert "moveMouse" in enum
def test_movemouse_summary_reports_the_target(tool):
summary = tool._summarise("moveMouse", {"site": "naver"}, {"ok": True, "target": "naver"})
assert "마우스" in summary and "naver" in summary
def test_description_distinguishes_cursor_paths(tool):
# The model must know navigate is address-bar only (no mouse) while
# search/type/moveMouse move the real cursor — that distinction is the
# whole point of the fix.
desc = tool.description
assert "moveMouse" in desc
assert "address bar" in desc # navigate is described as address-bar typing
def test_search_summary_flags_cursorless_fallback(tool):
# When the real xdotool cursor path didn't run, the summary must say so
# rather than implying a human-like search happened.
human = tool._summarise("search", {"query": "날씨"}, {"ok": True, "site": "naver", "query": "날씨", "input": "human"})
assert "참고: 실제 마우스" not in human
fell_back = tool._summarise("search", {"query": "날씨"}, {"ok": True, "site": "naver", "query": "날씨", "input": "api-fallback"})
assert "실제 마우스 커서 이동 없이" in fell_back
def test_movemouse_summary_only_runs_on_success(tool):
# _summarise is only called on ok:true; an ok:false (target not found / no
# xdotool) is handled by run() as a failure reply, so a failed move can no
# longer be reported as "moved". Sanity-check the success summary names a
# target rather than a placeholder when one is present.
summary = tool._summarise("moveMouse", {"selector": "#query"}, {"ok": True, "target": "#query"})
assert "#query" in summary