Pup - the AI's own browser

@@ -1,10 +1,10 @@ {   "manifest_version": 1,   "name": "puppeteer",-  "version": "1.9.140",-  "url": "https://wiki.adom.inc/download/adom/adom-desktop-puppeteer-bridge/1.9.140/adom-bridge-puppeteer-v1.9.140.zip",-  "sha256": "26f224fa850c670c8994cec959b132fd49638833bcf77d79a2e3cf74e33564e1",-  "size": 395547,+  "version": "1.9.141",+  "url": "https://wiki.adom.inc/download/adom/adom-desktop-puppeteer-bridge/1.9.141/adom-bridge-puppeteer-v1.9.141.zip",+  "sha256": "0a3392fafdeb7525b878c14ea203576d2e704e9e1eceed29f3626db80104e791",+  "size": 396222,   "verbPrefixes": [     "browser_",     "desktop_recorder_",

@@ -1 +1 @@-1.9.140+1.9.141

@@ -2,7 +2,7 @@   "manifest_version": 1,   "name": "puppeteer",   "displayName": "Puppeteer (Chrome for Testing + Native)",-  "version": "1.9.140",+  "version": "1.9.141",   "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.",

@@ -1176,7 +1176,7 @@ async function rescanProfile(browser, profileName, { adoptOrphans = false } = {}       sessions.set(sessionId, session);     } else if (session.profileName !== profileName) {       // SessionId collision across profiles — shouldn't happen in practice-      // since profile defaults to sessionId, but guard anyway. Skip rather+      // since profile defaults to the durable shared \'adom-you\' profile (logins/localStorage persist + are shared across all pup windows); isolated:true for a private throwaway, but guard anyway. Skip rather       // than clobber.       console.log(`[rescan] sessionId "${sessionId}" found in profile "${session.profileName}" but page is in profile "${profileName}" — skipping`);       continue;@@ -5947,7 +5947,7 @@ setInterval(async () => { // asked to adopt: a calling AI should never have to guess and never have to // read docs first. { verb: { hint, related[], pitfalls[] } }. const VERB_META = {-  browser_open_window: { hint: 'Opens a generic, fully-controllable pup window (a fresh isolated Chrome/Edge process — never your real signed-in browser) that you then drive by sessionId. To drive the user\'s REAL Chrome/Edge, use the Adom browser extension\'s nbrowser_* verbs instead.', related: ['browser_navigate', 'browser_list_windows', 'browser_close_window'], pitfalls: ['sessionId is required and is your handle for every later call', 'profile defaults to sessionId — omit it for a plain "open in pup"', 'sessionIds are SHARED across all AI threads on this desktop — a generic id ("wiki", "test") may collide with another thread\'s window and navigating it away steals their work. Use a task-prefixed sessionId + pass owner:"<your-task>" so pup can protect it', 'reusing an existing sessionId with a new url NAVIGATES that window — check browser_status (shows owner per window) first if unsure'] },+  browser_open_window: { hint: 'Opens a generic, fully-controllable pup window (a fresh isolated Chrome/Edge process — never your real signed-in browser) that you then drive by sessionId. To drive the user\'s REAL Chrome/Edge, use the Adom browser extension\'s nbrowser_* verbs instead.', related: ['browser_navigate', 'browser_list_windows', 'browser_close_window'], pitfalls: ['sessionId is required and is your handle for every later call', 'profile defaults to the durable shared \'adom-you\' profile (logins/localStorage persist + are shared across all pup windows); isolated:true for a private throwaway — omit it for a plain "open in pup"', 'sessionIds are SHARED across all AI threads on this desktop — a generic id ("wiki", "test") may collide with another thread\'s window and navigating it away steals their work. Use a task-prefixed sessionId + pass owner:"<your-task>" so pup can protect it', 'reusing an existing sessionId with a new url NAVIGATES that window — check browser_status (shows owner per window) first if unsure'] },   browser_open_tab: { hint: 'Adds a tab to an existing session; returns the new tabId.', related: ['browser_switch_tab', 'browser_list_tabs', 'browser_close_tab'], pitfalls: ['the session must already exist (browser_open_window first)'] },   browser_close_tab: { hint: 'Closes one tab; the session stays open.', related: ['browser_close_window', 'browser_list_tabs'], pitfalls: ['omit tabId to close the active tab — closing the last tab may close the window'] },   browser_close_window: { hint: 'Closes the whole session and all its tabs. Destructive.', related: ['browser_list_windows'], pitfalls: ['this ends the session — its sessionId is no longer valid afterward'] },@@ -6521,7 +6521,7 @@ const server = http.createServer(async (req, res) => {                      hint: m.hint || summary, related: m.related || [], pitfalls: m.pitfalls || [] };           };           sendJSON(res, { success: true, bridge: 'puppeteer', verbs: [-            V('browser_open_window', 'Open a generic pup window — a fresh isolated Chrome/Edge process (never your real signed-in browser), fully drivable via CDP. ALWAYS opens in the BACKGROUND (does not steal focus; never disturbs the user\'s main work; still fully screenshottable/drivable) UNLESS you pass foreground:true — do that ONLY when the user explicitly wants to watch. Pass width+height (+ optional x,y, screen px) to place it at a specific size/position for screenshot framing — this NO LONGER foregrounds it (sizing stays in the background too; default unsized is maximized). profile defaults to sessionId. OWNERSHIP: sessionIds are shared across ALL AI threads — use a task-prefixed sessionId + owner:"<your-task>" so pup can refuse other threads stealing your window (reusing an existing id with a new url navigates it away; declared cross-owner reuse errors with session_owned_by_another_thread unless takeover:true). (For the user\'s REAL Chrome/Edge, use the Adom extension\'s nbrowser_* verbs.)', { sessionId: 'required str — task-prefix it (e.g. "mytask-web"); generic ids collide across threads', url: 'optional str', profile: 'optional str — defaults to sessionId', owner: 'optional str — your thread/task label; lets pup protect this window from other threads', takeover: 'optional bool — claim a window owned by another thread (only when the user explicitly asks)', foreground: 'optional bool — request showing the window on the user\'s screen. GATED (v1.8.70): requires foregroundReason too, else the open succeeds but stays BACKGROUND with foregroundDenied set. Only when the USER explicitly asked to watch.', foregroundReason: 'required WITH foreground:true — quote/paraphrase what the user said that justifies putting a window on their screen (min 10 chars; logged + recorded in lastAgentUpdate, auditable)', width: 'optional int px — sizes for screenshot framing, stays background', height: 'optional int px', x: 'optional int px', y: 'optional int px', wikiView: 'optional "authed"|"public" — for wiki.adom.inc URLs. Default (omit) = PUBLIC/anonymous view (logged out, what the world sees). "authed" routes to pup\'s reserved persistent authed-wiki profile (30-day SSO session; first use needs a one-time login — the response says wikiLoginNeeded). Open the same page BOTH ways to verify publish visibility (e.g. did private source leak to the public?).', appName: 'optional str — the APP this window is driving (e.g. "shotlog"); shown in the hover tooltip', appIconB64: 'optional base64 PNG — override the app icon worn in the taskbar overlay. Usually UNNECESSARY: pup auto-fetches the page\'s own <link rel="icon"> favicon (the adom-ui-design standard artifact every app must serve) and wears it automatically. An app-looking URL with NO favicon gets a reprimand hint.', updateNote: 'optional str — a short "what I did" note, surfaced back in list_tabs/list_windows as lastAgentUpdate so the user knows what changed', autoFlash: 'optional bool (default true) — mutating verbs auto-flash this window\'s taskbar (debounced, never steals focus) so the user notices the agent touched it; pass false to make this window silent by default', silent: 'optional bool — suppress the auto-flash for just this call' }, 60, { sessionId: 'mytask-web', owner: 'mytask', url: 'https://example.com', width: 960, height: 540 }),+            V('browser_open_window', 'Open a generic pup window — a fresh isolated Chrome/Edge process (never your real signed-in browser), fully drivable via CDP. ALWAYS opens in the BACKGROUND (does not steal focus; never disturbs the user\'s main work; still fully screenshottable/drivable) UNLESS you pass foreground:true — do that ONLY when the user explicitly wants to watch. Pass width+height (+ optional x,y, screen px) to place it at a specific size/position for screenshot framing — this NO LONGER foregrounds it (sizing stays in the background too; default unsized is maximized). profile defaults to the durable shared \'adom-you\' profile (logins/localStorage persist + are shared across all pup windows); isolated:true for a private throwaway. OWNERSHIP: sessionIds are shared across ALL AI threads — use a task-prefixed sessionId + owner:"<your-task>" so pup can refuse other threads stealing your window (reusing an existing id with a new url navigates it away; declared cross-owner reuse errors with session_owned_by_another_thread unless takeover:true). (For the user\'s REAL Chrome/Edge, use the Adom extension\'s nbrowser_* verbs.)', { sessionId: 'required str — task-prefix it (e.g. "mytask-web"); generic ids collide across threads', url: 'optional str', profile: 'optional str — a named durable jar; DEFAULT is the shared "adom-you" profile (signed-in state shared across windows). isolated:true overrides to a throwaway', isolated: 'optional bool — private throwaway profile: fresh-login tests, acting as a different user', webSecurity: 'optional false — dev escape hatch for cross-origin eval; FORCES isolation so insecure flags never touch the credentialed profile', owner: 'optional str — your thread/task label; lets pup protect this window from other threads', takeover: 'optional bool — claim a window owned by another thread (only when the user explicitly asks)', foreground: 'optional bool — request showing the window on the user\'s screen. GATED (v1.8.70): requires foregroundReason too, else the open succeeds but stays BACKGROUND with foregroundDenied set. Only when the USER explicitly asked to watch.', foregroundReason: 'required WITH foreground:true — quote/paraphrase what the user said that justifies putting a window on their screen (min 10 chars; logged + recorded in lastAgentUpdate, auditable)', width: 'optional int px — sizes for screenshot framing, stays background', height: 'optional int px', x: 'optional int px', y: 'optional int px', wikiView: 'optional "authed"|"public" — for wiki.adom.inc URLs. Default (omit) = PUBLIC/anonymous view (logged out, what the world sees). "authed" routes to pup\'s reserved persistent authed-wiki profile (30-day SSO session; first use needs a one-time login — the response says wikiLoginNeeded). Open the same page BOTH ways to verify publish visibility (e.g. did private source leak to the public?).', appName: 'optional str — the APP this window is driving (e.g. "shotlog"); shown in the hover tooltip', appIconB64: 'optional base64 PNG — override the app icon worn in the taskbar overlay. Usually UNNECESSARY: pup auto-fetches the page\'s own <link rel="icon"> favicon (the adom-ui-design standard artifact every app must serve) and wears it automatically. An app-looking URL with NO favicon gets a reprimand hint.', updateNote: 'optional str — a short "what I did" note, surfaced back in list_tabs/list_windows as lastAgentUpdate so the user knows what changed', autoFlash: 'optional bool (default true) — mutating verbs auto-flash this window\'s taskbar (debounced, never steals focus) so the user notices the agent touched it; pass false to make this window silent by default', silent: 'optional bool — suppress the auto-flash for just this call' }, 60, { sessionId: 'mytask-web', owner: 'mytask', url: 'https://example.com', width: 960, height: 540 }),             V('browser_open_tab', 'Open a new tab in an EXISTING session/window (returns {tabId, tabCount, activeTabId} — no need to diff list_tabs). This is the right verb for multi-URL work: ONE window with many tabs (one taskbar button), not many windows. The window stays in the background; the tab auto-flashes the taskbar (debounced) so the user notices. The USER can click the window\'s taskbar button at any time to view it — pup never pulls it back down.', { sessionId: 'required str', url: 'optional str', updateNote: 'optional str — short "what I did" note surfaced in list_tabs as lastAgentUpdate', silent: 'optional bool — suppress the auto-flash for this call' }, 30, { sessionId: 'work', url: 'https://example.com' }),             V('browser_close_tab', 'Close a tab.', { sessionId: 'required str', tabId: 'optional str (default active)' }, 15, { sessionId: 'work' }),             V('browser_close_window', 'Close a window/session (its tabs go too).', { sessionId: 'required str' }, 20, { sessionId: 'work' }),@@ -6552,6 +6552,7 @@ const server = http.createServer(async (req, res) => {             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_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>' }),             // Session/tab/window management + probes (were routed but undocumented).@@ -6568,7 +6569,7 @@ const server = http.createServer(async (req, res) => {             V('desktop_record_status', 'Status of the desktop screen recorder + any active clip.', {}, 10, {}),             V('desktop_record_list', 'List completed desktop recordings on disk.', {}, 10, {}),             V('desktop_recorder_close', 'Close the desktop screen-recorder UI.', {}, 15, {}),-            V('browser_configure', 'Get/set user-facing pup preferences (persisted across bridge updates). taskbarGrouping: "split" (default — one taskbar button PER WINDOW, each badged with its own tab count; best for telling AI threads apart) | "grouped" (all pup windows stack under ONE "Adom Pup" button, badge shows window count; tidy taskbar). Applies to live windows immediately. Ask the USER which they prefer before changing it — this is their taskbar. WINDOWS ONLY: macOS has no taskbar, so the setting is stored but INERT there; the reply carries platform + taskbarSupported so branch on those, not on this text.', { taskbarGrouping: 'optional "split"|"grouped"', agentActivity: 'optional "on"|"off" — the taskbar progress bar marking which window a thread is driving', reportIssues: 'optional "on"|"off" — pup\'s bug-report invitation (_reportIssues), on by default' }, 15, { taskbarGrouping: 'grouped' }),+            V('browser_configure', 'Get/set user-facing pup preferences (persisted across bridge updates). taskbarGrouping: "split" (default — one taskbar button PER WINDOW, each badged with its own tab count; best for telling AI threads apart) | "grouped" (all pup windows stack under ONE "Adom Pup" button, badge shows window count; tidy taskbar). Applies to live windows immediately. Ask the USER which they prefer before changing it — this is their taskbar. WINDOWS ONLY: macOS has no taskbar, so the setting is stored but INERT there; the reply carries platform + taskbarSupported so branch on those, not on this text.', { taskbarGrouping: 'optional "split"|"grouped"', agentActivity: 'optional "on"|"off" — the taskbar progress bar marking which window a thread is driving', reportIssues: 'optional "on"|"off" — pup\'s bug-report invitation (_reportIssues), on by default', autoLogin: 'optional "on"|"off" — auto-fill a vault-matched login form on page load (fill only, never submits), on by default' }, 15, { taskbarGrouping: 'grouped' }),             V('browser_describe', 'This list — the bridge\'s verbs + schemas, for AD\'s Verbs tab.', {}, 10, {}),           ] });           return;