Pup - the AI's own browser

@@ -1,10 +1,10 @@ {   "manifest_version": 1,   "name": "puppeteer",-  "version": "1.9.167",-  "url": "https://wiki.adom.inc/download/adom/adom-desktop-puppeteer-bridge/1.9.167/adom-bridge-puppeteer-v1.9.167.zip",-  "sha256": "9d6d6ef74af97f73c70c1f0feedca7f12e4b4ecdbb77ffeccdac1437ab8a4ae4",-  "size": 406697,+  "version": "1.9.169",+  "url": "https://wiki.adom.inc/download/adom/adom-desktop-puppeteer-bridge/1.9.169/adom-bridge-puppeteer-v1.9.169.zip",+  "sha256": "1457cac0b41d6082aa82534ff855e7b5663038d11d92170c835efe364297c009",+  "size": 407400,   "verbPrefixes": [     "browser_",     "desktop_recorder_",

@@ -1 +1 @@-1.9.167+1.9.169

@@ -2,7 +2,7 @@   "manifest_version": 1,   "name": "puppeteer",   "displayName": "Puppeteer (Chrome for Testing + Native)",-  "version": "1.9.167",+  "version": "1.9.169",   "description": "Drives a browser ALREADY on the machine \u2014 installed Chrome, else Microsoft Edge (every Windows PC ships with Edge) \u2014 launched with a FRESH isolated profile, so the common case has NO ~150 MB Chrome-for-Testing download and it never touches the user's real tabs/logins. Binds its local server to LOOPBACK (127.0.0.1) only, so no Windows Firewall 'allow Node through the firewall' prompt ever pops. Chrome for Testing is fetched only as a LAST RESORT if the machine has no Chromium browser at all. SPAWN-VERIFIED fallback: pup tries each detected browser (Chrome \u2192 Edge \u2192 CfT) and actually launches it, falling through to the next if one won't start (and handling browsers like Edge that relaunch onto another PID), so a corrupt/partial install never hard-fails an open. The browser that launches is cached as the default (persisted across restarts) so it isn't re-probed each time. On spawn the bridge SELF-WARMS: detects browsers + disk, and only if the box has no Chrome/Edge and no cached CfT does it background-fetch CfT so the first open is instant. browser_use pins a specific browser (chrome | edge | cft | auto); {browser:'chrome',install:true} downloads & installs REAL Google Chrome (user-scoped, no admin) on an Edge-only box. browser_readiness (READ-ONLY) reports which browser will be used + the full candidate list + the default + free disk. Every failure returns a specific errorCode + _hint (chrome_install_no_disk, chrome_download_network, chrome_install_permission, chrome_stable_not_detected, \u2026). Launches with FULL browser permissions by default for full debug (strictPermissions:true opts out). Headful automation: open/close windows+tabs, navigate, screenshot, eval JS, record. pup is a GENERIC, non-profile browser only \u2014 every session is a fresh isolated Chrome/Edge process, never the user's real signed-in browser; profile defaults to sessionId. To drive the user's REAL Chrome/Edge (their profile, cookies, SSO), use the Adom browser EXTENSION's nbrowser_* verbs \u2014 a separate bridge, not pup's job. macOS (v1.9.74+): full parity with mac-native mechanics \u2014 background-by-default is the app-level hide (windows stay drivable/screenshottable while hidden), raise/lower map to unhide+activate/hide, browser_alert_window posts a native toast whose click focuses the window, browser_use {browser:'chrome',install:true} installs Chrome from the official dmg, and taskbar identity/badging remains Windows-only.",   "homepage": "https://wiki.adom.inc/adom/adom-desktop",   "author": "Adom Inc.",

@@ -6745,6 +6745,7 @@ const server = http.createServer(async (req, res) => {             V('browser_forward', 'History forward.', { sessionId: 'required str' }, 20, { sessionId: 'work' }),             V('browser_reload', 'Reload the active tab.', { sessionId: 'required str' }, 30, { sessionId: 'work' }),             V('browser_click', 'Click an element (by selector or coords).', { sessionId: 'required str', selector: 'optional str', x: 'optional int', y: 'optional int' }, 20, { sessionId: 'work', selector: 'button#go' }),+            V('browser_assisted_click', 'RESPECTFUL real-cursor click for a surface pup CDP cannot drive (a NATIVE OS dialog, or a cross-origin FedCM "Sign in with Google" account chooser that rejects every in-page click). Do NOT hand-roll raise+desktop_click for these — use THIS. It: captions the reason + toasts BEFORE touching the screen; foregrounds; then WAITS, detecting if the user alt-tabbed away and holding (captioning "Adom is waiting — click back when ready") until the user is actually on the window; then runs the TIGHT real-cursor hover->click that FedCM accepts (interleaving any screenshot/eval between raise and click makes the click silently no-op); captions each step. Times out as user_not_ready clicking NOTHING if they never return. First take a desktop_screenshot_window of the session to read the target\'s WINDOW-pixel x,y.', { sessionId: 'required str', x: 'required int — WINDOW-image pixel of the target (from desktop_screenshot_window)', y: 'required int', reason: 'required str — WHY you must click (shown to the user as a caption)', label: 'required str — WHAT you are clicking (e.g. "your Google account")', maxWaitMs: 'optional int — how long to wait for the user (default 120000)' }, 130, { sessionId: 'adsk', x: 900, y: 379, reason: 'clicking your Google account to finish signing into Autodesk', label: 'your Google account' }),             V('browser_type', 'Type text into the focused/selected field.', { sessionId: 'required str', text: 'required str', selector: 'optional str' }, 20, { sessionId: 'work', text: 'hello' }),             V('browser_press_key', 'Press a key / chord (e.g. Enter, Ctrl+A).', { sessionId: 'required str', key: 'required str' }, 15, { sessionId: 'work', key: 'Enter' }),             V('browser_screenshot', 'Screenshot the page (PNG; fullPage optional). NOTE: fullPage only covers DOCUMENT-level scroll — on SPAs that scroll inside a nested container it returns just the viewport + a nestedScroll hint; use browser_screenshot_element or browser_scroll for those.', { sessionId: 'required str', fullPage: 'optional bool' }, 30, { sessionId: 'work' }),@@ -6765,7 +6766,7 @@ const server = http.createServer(async (req, res) => {             V('browser_prewarm', 'Install Chrome for Testing WITHOUT opening a window, and pin it as the default. Use when you specifically want CfT rather than the machine\'s installed Chrome/Edge.', { wait: 'optional bool — block until installed', setDefault: 'optional bool (default true) — pin CfT as the default' }, 240, {}),             V('browser_use', 'Pin (or clear) the browser pup drives by default: chrome | edge | cft | auto (or an explicit executablePath). "cft" fetches Chrome for Testing then pins it. With {browser:"chrome", install:true} it DOWNLOADS & INSTALLS real Google Chrome on an Edge-only box, then pins it — SILENT on a normal PC; on a locked-down box (VM/managed device) it needs a Windows approval, so the bridge pops a native "click YES on the UAC" notification and, if it expires, re-notifies with a one-tap "Approve now" (all autonomous — no AI turn). Poll browser_readiness.chromeStablePhase: installing → awaiting_uac → ready. Persists across restarts; launch still spawn-verifies + falls back.', { browser: '"chrome" | "edge" | "cft" | "auto"', install: 'optional bool — with browser:"chrome", install real Chrome if missing', elevate: 'optional "auto"(default)|true|false — auto: quiet install, prompt only if it needs admin; false: never prompt; true: go straight to the prompt', executablePath: 'optional — pin an exact browser binary' }, 240, {}),             V('browser_lower_os_window', 'Send a pup window to the BACKGROUND (behind the user\'s windows) without stealing focus — still fully drivable. The default for open; use this to re-hide a window you foregrounded.', { sessionId: 'optional str' }, 15, {}),-            V('browser_raise_os_window', 'Bring a pup window to the FOREGROUND (user\'s screen). GATED (v1.8.70): REFUSED with foreground_reason_required unless you pass foregroundReason — a quote/paraphrase of what the user said that justifies it (min 10 chars; logged, recorded in lastAgentUpdate, auditable). Allowed ONLY when the user EXPLICITLY must SEE it (a demo, recording, "show me"). It STEALS focus — to just signal "I updated this window", use browser_alert_window (or the auto-flash), NOT raise. After the show-me: browser_lower_os_window to return it to the background. Alias: browser_focus_window.', { sessionId: 'optional str', foregroundReason: 'REQUIRED — why the user asked to see this window' }, 15, { foregroundReason: 'user said "show me the wiki page"' }),+            V('browser_raise_os_window', 'Bring a pup window to the FOREGROUND (user\'s screen). GATED (v1.8.70): REFUSED with foreground_reason_required unless you pass foregroundReason — a quote/paraphrase of what the user said that justifies it (min 10 chars; logged, recorded in lastAgentUpdate, auditable). Allowed ONLY when the user EXPLICITLY must SEE it (a demo, recording, "show me"). It STEALS focus — to just signal "I updated this window", use browser_alert_window (or the auto-flash), NOT raise. After the show-me: browser_lower_os_window to return it to the background. Alias: browser_focus_window. IMPORTANT: if you are foregrounding in order to CLICK a native dialog or a cross-origin FedCM/Google account chooser, do NOT raise-then-click yourself — use browser_assisted_click, which waits for the user to actually be on the window (alt-tab aware) and narrates via captions, so you never act while they are not ready.', { sessionId: 'optional str', foregroundReason: 'REQUIRED — why the user asked to see this window' }, 15, { foregroundReason: 'user said "show me the wiki page"' }),             V('browser_login', 'Fill (and optionally submit) an HTML login form in the CURRENT tab, in the BACKGROUND — no Chrome autofill dropdown, no foregrounding, React/Vue-safe. Creds from the vault (matched on the tab URL; store via credential_set or save:true) or passed explicitly. Passwords are NEVER echoed back. Vault-matched login pages also AUTO-FILL on load (_autoLogin on the response; browser_configure {autoLogin:"off"} disables). Pairs with the durable shared profile: sign in once, every window stays signed in.', { sessionId: 'required str', username: 'optional str', password: 'optional str — with username, fills these instead of the vault', submit: 'optional bool — click the submit button after filling (default false)', save: 'optional bool — with explicit creds, store them (OS keychain) so next time is automatic', host: 'optional str — override the vault host key when saving' }, 20, { sessionId: 'work', submit: true }),             V('browser_alert_window', 'Nudge the user about a pup window WITHOUT stealing focus — on Windows it flashes the taskbar button; on macOS (no taskbar, and no API to bounce another app\'s Dock tile) it unhides the window at its z-position and posts an AD toast whose click focuses it. Same contract on both, so call it identically; just never tell a Mac user to look for a flashing icon. NOTE (v1.8.23): mutating verbs already AUTO-FLASH (debounced, one per ~5s burst per window) so the user always knows the agent touched a window — use this for an explicit end-of-task "it\'s ready" nudge on top of that. STRONGLY prefer this (or the auto-flash) over browser_raise_os_window, which steals focus and can leak a mid-typed keystroke into the page.', { sessionId: 'optional str', stop: 'optional bool — CLEAR the highlight instead of flashing' }, 15, {}),             V('browser_render_html', 'Render a local HTML string in the tab via page.setContent — UTF-8-correct (a data: URL mojibakes accented chars without an explicit charset). Great for previewing generated markup without a temp file. Auto-flashes the window.', { sessionId: 'required str', html: 'required HTML string', waitUntil: 'optional (domcontentloaded default)', updateNote: 'optional note for lastAgentUpdate', silent: 'optional bool — suppress the auto-flash' }, 30, { sessionId: 'work', html: '<h1>Café</h1>' }),