Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠
JavaScript ai-agentai-agentsai-toolsbrowser-aibrowser-automationbrowser-extensionchrome-aichrome-devtoolschrome-extensionchrome-extensionsfirefox-addonfirefox-addonsfirefox-extensionfirefox-extensionsgemmagemma4minimaxoffline-aioffline-llmqwen
Call vision mode's default option Auto
Emre Sokullu382fb62514f0
diff --git a/docs/agent-tools.md b/docs/agent-tools.mdindex 01ca717a7..305569a27 100644--- a/docs/agent-tools.md+++ b/docs/agent-tools.md@@ -26,7 +26,7 @@ Tier defaults and resolution rules are documented inlean Act run gets its tier's tools and prompt, and WebBrain skips its qualitychecks; see [lean mode](lean-mode.md).-**Vision mode** (Settings → Advanced → Vision mode, on by default) replaces the+**Vision mode** (Settings → Advanced → Vision mode, Auto by default) replaces thetree, ref and selector tools of an Act run whose model takes images withcoordinate tools (`click_at`, `scroll_at`, `hover_at`, `drag_at`, `zoom`,`take_screenshot`, `wait`) and a vision prompt; the run sees the page as adiff --git a/docs/vision-mode.md b/docs/vision-mode.mdindex 2a3074a74..d24763c27 100644--- a/docs/vision-mode.md+++ b/docs/vision-mode.md@@ -8,7 +8,7 @@ The accessibility-tree path stays available (Settings → Advanced → **VisionSettings → Advanced:-- **Vision mode** (storage key `visionMode`): **On** (default) or **Off**. On applies to Act runs whose model receives screenshots directly (`provider.supportsVision`). A separate describe-only vision model cannot aim clicks, so a text-only model keeps the accessibility tree. Ask and Dev are unchanged.+- **Vision mode** (storage key `visionMode`): **Auto** (default) or **Off**. Auto applies to Act runs whose model receives screenshots directly (`provider.supportsVision`). A separate describe-only vision model cannot aim clicks, so a text-only model keeps the accessibility tree. Ask and Dev are unchanged. The option was called **On** before; a stored `on` (or `true`), and an exported configuration that carries it, reads as Auto.- **Vision screenshot size** (`visionQuality`): **Economy**, **Balanced** (default) or **Sharp**. It caps the model-facing image (Economy: long edge 1024 px / 0.6 MP; Balanced: 1440 px / 1.05 MP; Sharp: the provider's own limit). The model can always `zoom` for detail.A run decides once, when it starts (`_beginVisionRun` snapshots both settings), like lean mode. The resolved state is recorded in the trace's runtime config as `vision_mode_setting` and `vision_mode`. The `Agent` class default is `off`, so embedders and unit tests opt in explicitly; `background.js` applies the stored setting, whose default is `on`.diff --git a/src/chrome/src/agent/agent.js b/src/chrome/src/agent/agent.jsindex ceefc1f87..074828bdc 100644--- a/src/chrome/src/agent/agent.js+++ b/src/chrome/src/agent/agent.js@@ -1066,9 +1066,9 @@ export class Agent extends LoopDetector {// resolves it once at its start (_beginLeanRun) and keeps the answer in// _leanRuns, so its prompt note and guards agree. See lean-mode.js.this.leanMode = 'auto';- // Vision mode (vision-mode.js): 'on' | 'off'. The class default keeps+ // Vision mode (vision-mode.js): 'auto' | 'off'. The class default keeps// the accessibility-tree path for embedders and the unit suite;- // background.js applies the stored setting, whose default is 'on'.+ // background.js applies the stored setting, whose default is 'auto'.this.visionMode = 'off';this.visionQuality = 'balanced';this._visionSessions = new Map();diff --git a/src/chrome/src/agent/vision-mode.js b/src/chrome/src/agent/vision-mode.jsindex 042e9c99f..9ca329c08 100644--- a/src/chrome/src/agent/vision-mode.js+++ b/src/chrome/src/agent/vision-mode.js@@ -2,20 +2,23 @@// Shared verbatim by the Chrome and Firefox builds (test/vision-mode.mjs).//// Settings → Advanced → "Vision mode" (storage key `visionMode`):-// 'on' — Act runs see the page as screenshots and act with coordinates-// whenever the run's model accepts images. This is the default.-// 'off' — the accessibility-tree path.+// 'auto' — Act runs see the page as screenshots and act with coordinates+// whenever the run's model accepts images. This is the default.+// The option was called On before, so a stored 'on' (or true)+// reads as 'auto'.+// 'off' — the accessibility-tree path.// A run decides once, when it starts, and keeps that answer to the end.import { detectVisionProfile, normalizeVisionQuality } from './vision-budget.js';-export const VISION_MODE_SETTINGS = Object.freeze(['on', 'off']);-export const DEFAULT_VISION_MODE_SETTING = 'on';+export const VISION_MODE_SETTINGS = Object.freeze(['auto', 'off']);+export const DEFAULT_VISION_MODE_SETTING = 'auto';export function normalizeVisionModeSetting(value, fallback = DEFAULT_VISION_MODE_SETTING) {- if (value === true) return 'on';+ if (value === true) return 'auto';if (value === false) return 'off';const normalized = String(value ?? '').trim().toLowerCase();+ if (normalized === 'on') return 'auto';if (VISION_MODE_SETTINGS.includes(normalized)) return normalized;return VISION_MODE_SETTINGS.includes(fallback) ? fallback : DEFAULT_VISION_MODE_SETTING;}@@ -39,7 +42,7 @@ export function resolveVisionMode(setting, {} = {}) {const normalized = normalizeVisionModeSetting(setting);const base = { active: false, setting: normalized };- if (normalized !== 'on') return { ...base, reason: 'setting_off' };+ if (normalized !== 'auto') return { ...base, reason: 'setting_off' };if (mode !== 'act') return { ...base, reason: 'not_act_mode' };if (standalone) return { ...base, reason: 'standalone_chat' };if (selectionOnly) return { ...base, reason: 'selection_scope' };diff --git a/src/chrome/src/config-transfer.js b/src/chrome/src/config-transfer.jsindex 9a3a74321..0df5ac638 100644--- a/src/chrome/src/config-transfer.js+++ b/src/chrome/src/config-transfer.js@@ -59,7 +59,7 @@ export const DEFAULT_CONFIG_SETTINGS = Object.freeze({strictSecretMode: false,strictGuards: false,leanMode: 'auto',- visionMode: 'on',+ visionMode: 'auto',visionQuality: 'balanced',agentAllowLocalNetwork: false,scheduledTasksEnabled: true,@@ -253,7 +253,8 @@ function validSettingValue(key, value) {if (key === 'decisionMode') return ['', ...DECISION_MODES].includes(value);if (key === 'decisionVisionMode') return ['auto', 'on', 'off'].includes(value);if (key === 'leanMode') return ['auto', 'on', 'off'].includes(value);- if (key === 'visionMode') return ['on', 'off'].includes(value);+ // 'on' is Auto's name from before the option was renamed (currentSettingValue).+ if (key === 'visionMode') return ['auto', 'on', 'off'].includes(value);if (key === 'visionQuality') return ['economy', 'balanced', 'sharp'].includes(value);if (key === 'decisionBaseUrl') {if (typeof value !== 'string') return false;@@ -269,6 +270,13 @@ function validSettingValue(key, value) {return true;}+// A value an older export names by a setting's former option: vision mode's+// Auto was called On ('on').+function currentSettingValue(key, value) {+ if (key === 'visionMode' && value === 'on') return 'auto';+ return value;+}+function normalizeSettings(source, { strict = false } = {}) {const settings = clone(DEFAULT_CONFIG_SETTINGS);if (!isPlainObject(source)) {@@ -295,7 +303,7 @@ function normalizeSettings(source, { strict = false } = {}) {if (strict) throw new Error(`Invalid value for configuration setting "${key}".`);continue;}- settings[key] = clone(value);+ settings[key] = clone(currentSettingValue(key, value));}settings.providers = sanitizeProviders(settings.providers, { strict });if (!Object.hasOwn(source, 'decisionInputRate')) {diff --git a/src/chrome/src/trace/runtime-config.js b/src/chrome/src/trace/runtime-config.jsindex 07a3e7d93..46864a0a1 100644--- a/src/chrome/src/trace/runtime-config.js+++ b/src/chrome/src/trace/runtime-config.js@@ -8,7 +8,7 @@ const STRING_ENUMS = Object.freeze({image_detail: new Set(['auto', 'low', 'high']),selection_scope_policy: new Set(['selection_only', 'selection_context']),lean_mode_setting: new Set(['auto', 'on', 'off']),- vision_mode_setting: new Set(['on', 'off']),+ vision_mode_setting: new Set(['auto', 'off']),});const BOOLEAN_FIELDS = Object.freeze([diff --git a/src/chrome/src/ui/locales/ar.js b/src/chrome/src/ui/locales/ar.jsindex 45b44cb17..1f9c542b4 100644--- a/src/chrome/src/ui/locales/ar.js+++ b/src/chrome/src/ui/locales/ar.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "إيقاف","st.display.vision_mode.label": "الوضع المرئي","st.display.vision_mode.desc": "في وضع التنفيذ يرى الوكيل الصفحة كلقطات شاشة وينقر ويكتب ويمرّر عند إحداثيات الشاشة بدلًا من قراءة شجرة إمكانية الوصول. يتطلب نموذجًا يقبل الصور؛ وتواصل النماذج الأخرى استخدام شجرة إمكانية الوصول. بعد كل إجراء يُرسَل الجزء المتغيّر من الشاشة فقط. تُعالَج شاشات Retina وتكبير المتصفح تلقائيًا.",- "st.display.vision_mode.on": "تشغيل",+ "st.display.vision_mode.auto": "تلقائي","st.display.vision_mode.off": "إيقاف","st.display.vision_quality.label": "حجم لقطات الوضع المرئي","st.display.vision_quality.desc": "حجم لقطات الشاشة المرسلة في الوضع المرئي. الاقتصادي يستهلك أقل عدد من الرموز ويُرفع أسرع؛ والحاد يحتفظ بأكبر قدر من التفاصيل. يمكن للوكيل دائمًا تكبير النص الصغير.",diff --git a/src/chrome/src/ui/locales/bn.js b/src/chrome/src/ui/locales/bn.jsindex 9ba9a00cd..339bbd17d 100644--- a/src/chrome/src/ui/locales/bn.js+++ b/src/chrome/src/ui/locales/bn.js@@ -771,7 +771,7 @@ export default {"st.display.lean_mode.off": "বন্ধ","st.display.vision_mode.label": "ভিজ্যুয়াল মোড","st.display.vision_mode.desc": "Act মোডে এজেন্ট পেজটিকে স্ক্রিনশট হিসেবে দেখে এবং অ্যাক্সেসিবিলিটি ট্রি পড়ার বদলে স্ক্রিনের স্থানাঙ্কে ক্লিক, টাইপ ও স্ক্রল করে। এর জন্য ছবি গ্রহণ করে এমন মডেল লাগে; অন্য মডেলগুলো অ্যাক্সেসিবিলিটি ট্রি ব্যবহার করে চলে। প্রতিটি কাজের পর স্ক্রিনের শুধু পরিবর্তিত অংশ পাঠানো হয়। রেটিনা ডিসপ্লে ও ব্রাউজার জুম স্বয়ংক্রিয়ভাবে সামলানো হয়।",- "st.display.vision_mode.on": "চালু",+ "st.display.vision_mode.auto": "অটো","st.display.vision_mode.off": "বন্ধ","st.display.vision_quality.label": "ভিজ্যুয়াল মোডের স্ক্রিনশটের আকার","st.display.vision_quality.desc": "ভিজ্যুয়াল মোডে পাঠানো স্ক্রিনশটের আকার। সাশ্রয়ী সবচেয়ে কম টোকেন খরচ করে ও দ্রুত আপলোড হয়; তীক্ষ্ণ সবচেয়ে বেশি বিবরণ রাখে। এজেন্ট ছোট লেখায় সবসময় জুম করতে পারে।",diff --git a/src/chrome/src/ui/locales/de.js b/src/chrome/src/ui/locales/de.jsindex 87fdf4e5f..925da832c 100644--- a/src/chrome/src/ui/locales/de.js+++ b/src/chrome/src/ui/locales/de.js@@ -768,7 +768,7 @@ export default {"st.display.lean_mode.off": "Aus","st.display.vision_mode.label": "Visueller Modus","st.display.vision_mode.desc": "Im Modus „Handeln“ sieht der Agent die Seite als Screenshots und klickt, tippt und scrollt an Bildschirmkoordinaten, statt den Barrierefreiheitsbaum zu lesen. Erfordert ein Modell, das Bilder annimmt; andere Modelle nutzen weiter den Barrierefreiheitsbaum. Nach jeder Aktion wird nur der geänderte Teil des Bildschirms gesendet. Retina-Displays und Browser-Zoom werden automatisch berücksichtigt.",- "st.display.vision_mode.on": "Ein",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Aus","st.display.vision_quality.label": "Screenshot-Größe im visuellen Modus","st.display.vision_quality.desc": "Größe der im visuellen Modus gesendeten Screenshots. Sparsam verbraucht die wenigsten Tokens und lädt am schnellsten; Scharf behält die meisten Details. Der Agent kann kleine Schrift jederzeit vergrößern.",diff --git a/src/chrome/src/ui/locales/en.js b/src/chrome/src/ui/locales/en.jsindex bb3c8c6de..39d885745 100644--- a/src/chrome/src/ui/locales/en.js+++ b/src/chrome/src/ui/locales/en.js@@ -776,7 +776,7 @@ export default {"st.display.lean_mode.off": "Off","st.display.vision_mode.label": "Vision mode","st.display.vision_mode.desc": "In Act mode the agent sees the page as screenshots and clicks, types and scrolls at screen coordinates instead of reading the accessibility tree. Needs a model that accepts images; other models keep the accessibility tree. After each action only the changed part of the screen is sent. Retina displays and browser zoom are handled automatically.",- "st.display.vision_mode.on": "On",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Off","st.display.vision_quality.label": "Vision screenshot size","st.display.vision_quality.desc": "Size of the screenshots sent in vision mode. Economy uses the fewest tokens and uploads fastest; Sharp keeps the most detail. The agent can always zoom into small text.",diff --git a/src/chrome/src/ui/locales/es.js b/src/chrome/src/ui/locales/es.jsindex dfbed7cfd..62db780bb 100644--- a/src/chrome/src/ui/locales/es.js+++ b/src/chrome/src/ui/locales/es.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Desactivado","st.display.vision_mode.label": "Modo visual","st.display.vision_mode.desc": "En el modo Actuar, el agente ve la página como capturas de pantalla y hace clic, escribe y desplaza en coordenadas de pantalla en lugar de leer el árbol de accesibilidad. Requiere un modelo que acepte imágenes; los demás modelos siguen usando el árbol de accesibilidad. Tras cada acción solo se envía la parte de la pantalla que cambió. Las pantallas Retina y el zoom del navegador se gestionan automáticamente.",- "st.display.vision_mode.on": "Activado",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Desactivado","st.display.vision_quality.label": "Tamaño de las capturas en modo visual","st.display.vision_quality.desc": "Tamaño de las capturas enviadas en modo visual. Económico usa menos tokens y se sube más rápido; Nítido conserva más detalle. El agente siempre puede ampliar el texto pequeño.",diff --git a/src/chrome/src/ui/locales/fa.js b/src/chrome/src/ui/locales/fa.jsindex 6a0dba7de..399ecf839 100644--- a/src/chrome/src/ui/locales/fa.js+++ b/src/chrome/src/ui/locales/fa.js@@ -771,7 +771,7 @@ export default {"st.display.lean_mode.off": "خاموش","st.display.vision_mode.label": "حالت تصویری","st.display.vision_mode.desc": "در حالت «انجام» عامل صفحه را بهصورت تصویر صفحه میبیند و بهجای خواندن درخت دسترسپذیری، در مختصات صفحه کلیک میکند، تایپ میکند و پیمایش میکند. به مدلی نیاز دارد که تصویر بپذیرد؛ مدلهای دیگر همچنان از درخت دسترسپذیری استفاده میکنند. پس از هر اقدام فقط بخش تغییرکرده صفحه فرستاده میشود. نمایشگرهای Retina و بزرگنمایی مرورگر خودکار لحاظ میشوند.",- "st.display.vision_mode.on": "روشن",+ "st.display.vision_mode.auto": "خودکار","st.display.vision_mode.off": "خاموش","st.display.vision_quality.label": "اندازه تصویرهای حالت تصویری","st.display.vision_quality.desc": "اندازه تصویرهای صفحه در حالت تصویری. اقتصادی کمترین توکن را مصرف میکند و سریعتر ارسال میشود؛ واضح بیشترین جزئیات را نگه میدارد. عامل همیشه میتواند روی متن ریز بزرگنمایی کند.",diff --git a/src/chrome/src/ui/locales/fr.js b/src/chrome/src/ui/locales/fr.jsindex 197401c61..38de3e4d1 100644--- a/src/chrome/src/ui/locales/fr.js+++ b/src/chrome/src/ui/locales/fr.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Désactivé","st.display.vision_mode.label": "Mode visuel","st.display.vision_mode.desc": "En mode Agir, l’agent voit la page sous forme de captures d’écran et clique, tape et fait défiler à des coordonnées de l’écran au lieu de lire l’arbre d’accessibilité. Nécessite un modèle qui accepte les images ; les autres modèles conservent l’arbre d’accessibilité. Après chaque action, seule la partie de l’écran qui a changé est envoyée. Les écrans Retina et le zoom du navigateur sont gérés automatiquement.",- "st.display.vision_mode.on": "Activé",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Désactivé","st.display.vision_quality.label": "Taille des captures en mode visuel","st.display.vision_quality.desc": "Taille des captures envoyées en mode visuel. Économique utilise le moins de jetons et s’envoie le plus vite ; Net conserve le plus de détails. L’agent peut toujours zoomer sur un petit texte.",diff --git a/src/chrome/src/ui/locales/he.js b/src/chrome/src/ui/locales/he.jsindex b899ed470..57f414e2a 100644--- a/src/chrome/src/ui/locales/he.js+++ b/src/chrome/src/ui/locales/he.js@@ -753,7 +753,7 @@ export default {"st.display.lean_mode.off": "כבוי","st.display.vision_mode.label": "מצב חזותי","st.display.vision_mode.desc": "במצב פעולה הסוכן רואה את הדף כצילומי מסך ולוחץ, מקליד וגולל בקואורדינטות מסך במקום לקרוא את עץ הנגישות. נדרש מודל שמקבל תמונות; מודלים אחרים ממשיכים להשתמש בעץ הנגישות. אחרי כל פעולה נשלח רק החלק שהשתנה במסך. מסכי Retina והגדלת הדפדפן מטופלים אוטומטית.",- "st.display.vision_mode.on": "מופעל",+ "st.display.vision_mode.auto": "אוטומטי","st.display.vision_mode.off": "כבוי","st.display.vision_quality.label": "גודל צילומי המסך במצב חזותי","st.display.vision_quality.desc": "גודל צילומי המסך שנשלחים במצב חזותי. חסכוני משתמש במעט אסימונים ומועלה מהר; חד שומר על מרב הפרטים. הסוכן תמיד יכול להגדיל טקסט קטן.",diff --git a/src/chrome/src/ui/locales/hi.js b/src/chrome/src/ui/locales/hi.jsindex be2e8356f..1ba4480a0 100644--- a/src/chrome/src/ui/locales/hi.js+++ b/src/chrome/src/ui/locales/hi.js@@ -771,7 +771,7 @@ export default {"st.display.lean_mode.off": "बंद","st.display.vision_mode.label": "दृश्य मोड","st.display.vision_mode.desc": "Act मोड में एजेंट पेज को स्क्रीनशॉट के रूप में देखता है और एक्सेसिबिलिटी ट्री पढ़ने के बजाय स्क्रीन निर्देशांकों पर क्लिक, टाइप और स्क्रॉल करता है। इसके लिए ऐसा मॉडल चाहिए जो इमेज स्वीकार करे; बाकी मॉडल एक्सेसिबिलिटी ट्री का उपयोग करते रहते हैं। हर क्रिया के बाद स्क्रीन का केवल बदला हुआ हिस्सा भेजा जाता है। रेटिना डिस्प्ले और ब्राउज़र ज़ूम अपने आप संभाले जाते हैं।",- "st.display.vision_mode.on": "चालू",+ "st.display.vision_mode.auto": "ऑटो","st.display.vision_mode.off": "बंद","st.display.vision_quality.label": "दृश्य मोड स्क्रीनशॉट आकार","st.display.vision_quality.desc": "दृश्य मोड में भेजे गए स्क्रीनशॉट का आकार। किफ़ायती सबसे कम टोकन लेता है और सबसे तेज़ अपलोड होता है; तीक्ष्ण सबसे अधिक विवरण रखता है। एजेंट छोटे पाठ पर हमेशा ज़ूम कर सकता है।",diff --git a/src/chrome/src/ui/locales/id.js b/src/chrome/src/ui/locales/id.jsindex 976b6f39b..9e70412ef 100644--- a/src/chrome/src/ui/locales/id.js+++ b/src/chrome/src/ui/locales/id.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Nonaktif","st.display.vision_mode.label": "Mode visual","st.display.vision_mode.desc": "Dalam mode Bertindak, agen melihat halaman sebagai tangkapan layar dan mengklik, mengetik, serta menggulir pada koordinat layar alih-alih membaca pohon aksesibilitas. Memerlukan model yang menerima gambar; model lain tetap memakai pohon aksesibilitas. Setelah setiap tindakan hanya bagian layar yang berubah yang dikirim. Layar Retina dan zoom browser ditangani otomatis.",- "st.display.vision_mode.on": "Aktif",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Nonaktif","st.display.vision_quality.label": "Ukuran tangkapan layar mode visual","st.display.vision_quality.desc": "Ukuran tangkapan layar yang dikirim dalam mode visual. Hemat memakai token paling sedikit dan paling cepat diunggah; Tajam mempertahankan detail terbanyak. Agen selalu dapat memperbesar teks kecil.",diff --git a/src/chrome/src/ui/locales/ja.js b/src/chrome/src/ui/locales/ja.jsindex 18a567cc9..18f2e6d67 100644--- a/src/chrome/src/ui/locales/ja.js+++ b/src/chrome/src/ui/locales/ja.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "オフ","st.display.vision_mode.label": "ビジョンモード","st.display.vision_mode.desc": "実行モードでは、エージェントはアクセシビリティツリーを読む代わりにページをスクリーンショットとして見て、画面座標でクリック・入力・スクロールします。画像を受け付けるモデルが必要で、それ以外のモデルは引き続きアクセシビリティツリーを使います。各操作の後は画面の変化した部分だけが送信されます。Retina ディスプレイとブラウザのズームは自動で処理されます。",- "st.display.vision_mode.on": "オン",+ "st.display.vision_mode.auto": "自動","st.display.vision_mode.off": "オフ","st.display.vision_quality.label": "ビジョンモードのスクリーンショットサイズ","st.display.vision_quality.desc": "ビジョンモードで送るスクリーンショットのサイズ。エコノミーはトークンが最も少なく最速でアップロードでき、シャープは最も多くの詳細を保ちます。エージェントは小さな文字をいつでもズームできます。",diff --git a/src/chrome/src/ui/locales/ko.js b/src/chrome/src/ui/locales/ko.jsindex 334ae12dd..fb7cda149 100644--- a/src/chrome/src/ui/locales/ko.js+++ b/src/chrome/src/ui/locales/ko.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "끔","st.display.vision_mode.label": "비전 모드","st.display.vision_mode.desc": "실행 모드에서 에이전트는 접근성 트리를 읽는 대신 페이지를 스크린샷으로 보고 화면 좌표에서 클릭, 입력, 스크롤합니다. 이미지를 받는 모델이 필요하며, 다른 모델은 계속 접근성 트리를 사용합니다. 각 동작 후에는 화면에서 바뀐 부분만 전송됩니다. 레티나 디스플레이와 브라우저 확대/축소는 자동으로 처리됩니다.",- "st.display.vision_mode.on": "켜짐",+ "st.display.vision_mode.auto": "자동","st.display.vision_mode.off": "꺼짐","st.display.vision_quality.label": "비전 모드 스크린샷 크기","st.display.vision_quality.desc": "비전 모드에서 보내는 스크린샷의 크기입니다. 절약은 토큰을 가장 적게 쓰고 가장 빨리 업로드되며, 선명은 세부 정보를 가장 많이 유지합니다. 에이전트는 작은 글자를 언제든 확대할 수 있습니다.",diff --git a/src/chrome/src/ui/locales/ms.js b/src/chrome/src/ui/locales/ms.jsindex 26312d393..497352787 100644--- a/src/chrome/src/ui/locales/ms.js+++ b/src/chrome/src/ui/locales/ms.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Mati","st.display.vision_mode.label": "Mod visual","st.display.vision_mode.desc": "Dalam mod Bertindak, ejen melihat halaman sebagai tangkapan skrin dan mengklik, menaip serta menatal pada koordinat skrin dan bukannya membaca pepohon kebolehcapaian. Memerlukan model yang menerima imej; model lain terus menggunakan pepohon kebolehcapaian. Selepas setiap tindakan hanya bahagian skrin yang berubah dihantar. Paparan Retina dan zum pelayar dikendalikan secara automatik.",- "st.display.vision_mode.on": "Hidup",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Mati","st.display.vision_quality.label": "Saiz tangkapan skrin mod visual","st.display.vision_quality.desc": "Saiz tangkapan skrin yang dihantar dalam mod visual. Jimat menggunakan token paling sedikit dan dimuat naik paling pantas; Tajam mengekalkan paling banyak butiran. Ejen sentiasa boleh mengezum teks kecil.",diff --git a/src/chrome/src/ui/locales/nl.js b/src/chrome/src/ui/locales/nl.jsindex 465a308fb..76a138324 100644--- a/src/chrome/src/ui/locales/nl.js+++ b/src/chrome/src/ui/locales/nl.js@@ -748,7 +748,7 @@ export default {"st.display.lean_mode.off": "Uit","st.display.vision_mode.label": "Visuele modus","st.display.vision_mode.desc": "In de modus Handelen ziet de agent de pagina als schermafbeeldingen en klikt, typt en scrolt hij op schermcoördinaten in plaats van de toegankelijkheidsboom te lezen. Vereist een model dat afbeeldingen accepteert; andere modellen blijven de toegankelijkheidsboom gebruiken. Na elke actie wordt alleen het gewijzigde deel van het scherm verzonden. Retina-schermen en browserzoom worden automatisch verwerkt.",- "st.display.vision_mode.on": "Aan",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Uit","st.display.vision_quality.label": "Schermafbeeldingsgrootte in visuele modus","st.display.vision_quality.desc": "Grootte van de schermafbeeldingen in de visuele modus. Zuinig gebruikt de minste tokens en uploadt het snelst; Scherp behoudt de meeste details. De agent kan altijd inzoomen op kleine tekst.",diff --git a/src/chrome/src/ui/locales/pl.js b/src/chrome/src/ui/locales/pl.jsindex 9e218a5c3..df038e784 100644--- a/src/chrome/src/ui/locales/pl.js+++ b/src/chrome/src/ui/locales/pl.js@@ -949,7 +949,7 @@ export default {"st.display.lean_mode.off": "Wył.","st.display.vision_mode.label": "Tryb wizualny","st.display.vision_mode.desc": "W trybie Działaj agent widzi stronę jako zrzuty ekranu i klika, pisze oraz przewija we współrzędnych ekranu zamiast czytać drzewo dostępności. Wymaga modelu, który przyjmuje obrazy; inne modele nadal używają drzewa dostępności. Po każdej akcji wysyłana jest tylko zmieniona część ekranu. Ekrany Retina i powiększenie przeglądarki są obsługiwane automatycznie.",- "st.display.vision_mode.on": "Włączony",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Wyłączony","st.display.vision_quality.label": "Rozmiar zrzutów w trybie wizualnym","st.display.vision_quality.desc": "Rozmiar zrzutów wysyłanych w trybie wizualnym. Oszczędny zużywa najmniej tokenów i wysyła się najszybciej; Ostry zachowuje najwięcej szczegółów. Agent zawsze może powiększyć drobny tekst.",diff --git a/src/chrome/src/ui/locales/pt.js b/src/chrome/src/ui/locales/pt.jsindex cc4dc7e14..d47f5f26c 100644--- a/src/chrome/src/ui/locales/pt.js+++ b/src/chrome/src/ui/locales/pt.js@@ -771,7 +771,7 @@ export default {"st.display.lean_mode.off": "Desligado","st.display.vision_mode.label": "Modo visual","st.display.vision_mode.desc": "No modo Agir, o agente vê a página como capturas de tela e clica, digita e rola em coordenadas da tela em vez de ler a árvore de acessibilidade. Requer um modelo que aceite imagens; os outros modelos continuam com a árvore de acessibilidade. Após cada ação, só a parte da tela que mudou é enviada. Telas Retina e o zoom do navegador são tratados automaticamente.",- "st.display.vision_mode.on": "Ativado",+ "st.display.vision_mode.auto": "Automático","st.display.vision_mode.off": "Desativado","st.display.vision_quality.label": "Tamanho das capturas no modo visual","st.display.vision_quality.desc": "Tamanho das capturas enviadas no modo visual. Econômico usa menos tokens e envia mais rápido; Nítido mantém mais detalhes. O agente sempre pode ampliar textos pequenos.",diff --git a/src/chrome/src/ui/locales/ru.js b/src/chrome/src/ui/locales/ru.jsindex 92a2d9fd1..f342a83d2 100644--- a/src/chrome/src/ui/locales/ru.js+++ b/src/chrome/src/ui/locales/ru.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Выкл.","st.display.vision_mode.label": "Визуальный режим","st.display.vision_mode.desc": "В режиме «Действовать» агент видит страницу как снимки экрана и нажимает, печатает и прокручивает по координатам экрана, а не читает дерево доступности. Нужна модель, принимающая изображения; остальные модели продолжают работать с деревом доступности. После каждого действия отправляется только изменившаяся часть экрана. Экраны Retina и масштаб браузера учитываются автоматически.",- "st.display.vision_mode.on": "Вкл.",+ "st.display.vision_mode.auto": "Авто","st.display.vision_mode.off": "Выкл.","st.display.vision_quality.label": "Размер снимков в визуальном режиме","st.display.vision_quality.desc": "Размер снимков, отправляемых в визуальном режиме. «Экономный» тратит меньше всего токенов и загружается быстрее; «Чёткий» сохраняет больше деталей. Агент всегда может увеличить мелкий текст.",diff --git a/src/chrome/src/ui/locales/th.js b/src/chrome/src/ui/locales/th.jsindex 9245976f9..09a60f80e 100644--- a/src/chrome/src/ui/locales/th.js+++ b/src/chrome/src/ui/locales/th.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "ปิด","st.display.vision_mode.label": "โหมดภาพ","st.display.vision_mode.desc": "ในโหมดลงมือ เอเจนต์จะเห็นหน้าเว็บเป็นภาพหน้าจอ และคลิก พิมพ์ และเลื่อนตามพิกัดบนหน้าจอแทนการอ่านแผนผังการเข้าถึง ต้องใช้โมเดลที่รับรูปภาพได้ ส่วนโมเดลอื่นยังใช้แผนผังการเข้าถึงต่อไป หลังแต่ละการกระทำจะส่งเฉพาะส่วนของหน้าจอที่เปลี่ยนไป หน้าจอ Retina และการซูมเบราว์เซอร์ได้รับการจัดการโดยอัตโนมัติ",- "st.display.vision_mode.on": "เปิด",+ "st.display.vision_mode.auto": "อัตโนมัติ","st.display.vision_mode.off": "ปิด","st.display.vision_quality.label": "ขนาดภาพหน้าจอในโหมดภาพ","st.display.vision_quality.desc": "ขนาดของภาพหน้าจอที่ส่งในโหมดภาพ ประหยัดใช้โทเค็นน้อยที่สุดและอัปโหลดเร็วที่สุด คมชัดเก็บรายละเอียดได้มากที่สุด เอเจนต์ซูมดูข้อความเล็กได้เสมอ",diff --git a/src/chrome/src/ui/locales/tl.js b/src/chrome/src/ui/locales/tl.jsindex acf901ed4..9855c98c4 100644--- a/src/chrome/src/ui/locales/tl.js+++ b/src/chrome/src/ui/locales/tl.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Naka-off","st.display.vision_mode.label": "Visual mode","st.display.vision_mode.desc": "Sa Act mode, nakikita ng agent ang page bilang mga screenshot at nagki-click, nagta-type at nag-i-scroll sa mga coordinate ng screen sa halip na basahin ang accessibility tree. Kailangan ng modelong tumatanggap ng larawan; ang ibang modelo ay patuloy na gumagamit ng accessibility tree. Pagkatapos ng bawat aksyon, ang nagbagong bahagi lang ng screen ang ipinapadala. Awtomatikong naaayos ang mga Retina display at browser zoom.",- "st.display.vision_mode.on": "Naka-on",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Naka-off","st.display.vision_quality.label": "Laki ng screenshot sa visual mode","st.display.vision_quality.desc": "Laki ng mga screenshot na ipinapadala sa visual mode. Ang Matipid ay gumagamit ng pinakakaunting token at pinakamabilis i-upload; ang Matalas ay nagpapanatili ng pinakamaraming detalye. Laging makakapag-zoom ang agent sa maliit na teksto.",diff --git a/src/chrome/src/ui/locales/tr.js b/src/chrome/src/ui/locales/tr.jsindex 727bc99ed..16cedeaa4 100644--- a/src/chrome/src/ui/locales/tr.js+++ b/src/chrome/src/ui/locales/tr.js@@ -966,7 +966,7 @@ export default {"st.display.lean_mode.off": "Kapalı","st.display.vision_mode.label": "Görsel mod","st.display.vision_mode.desc": "“Uygula” modunda ajan, erişilebilirlik ağacını okumak yerine sayfayı ekran görüntüleri olarak görür; ekran koordinatlarına tıklar, yazar ve kaydırır. Görüntü kabul eden bir model gerekir; diğer modeller erişilebilirlik ağacıyla devam eder. Her işlemden sonra ekranın yalnızca değişen kısmı gönderilir. Retina ekranlar ve tarayıcı yakınlaştırması otomatik olarak hesaba katılır.",- "st.display.vision_mode.on": "Açık",+ "st.display.vision_mode.auto": "Otomatik","st.display.vision_mode.off": "Kapalı","st.display.vision_quality.label": "Görsel ekran görüntüsü boyutu","st.display.vision_quality.desc": "Görsel modda gönderilen ekran görüntülerinin boyutu. Ekonomik en az token kullanır ve en hızlı yüklenir; Keskin en fazla ayrıntıyı korur. Ajan küçük yazılara her zaman yakınlaştırabilir.",diff --git a/src/chrome/src/ui/locales/uk.js b/src/chrome/src/ui/locales/uk.jsindex a4bb7fb74..743c80cd1 100644--- a/src/chrome/src/ui/locales/uk.js+++ b/src/chrome/src/ui/locales/uk.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "Вимк.","st.display.vision_mode.label": "Візуальний режим","st.display.vision_mode.desc": "У режимі «Діяти» агент бачить сторінку як знімки екрана й натискає, друкує та прокручує за координатами екрана замість читання дерева доступності. Потрібна модель, що приймає зображення; інші моделі й далі використовують дерево доступності. Після кожної дії надсилається лише змінена частина екрана. Екрани Retina та масштаб браузера враховуються автоматично.",- "st.display.vision_mode.on": "Увімк.",+ "st.display.vision_mode.auto": "Авто","st.display.vision_mode.off": "Вимк.","st.display.vision_quality.label": "Розмір знімків у візуальному режимі","st.display.vision_quality.desc": "Розмір знімків, що надсилаються у візуальному режимі. «Економний» витрачає найменше токенів і завантажується найшвидше; «Чіткий» зберігає найбільше деталей. Агент завжди може збільшити дрібний текст.",diff --git a/src/chrome/src/ui/locales/vi.js b/src/chrome/src/ui/locales/vi.jsindex 8145bbf8c..8e1b92391 100644--- a/src/chrome/src/ui/locales/vi.js+++ b/src/chrome/src/ui/locales/vi.js@@ -771,7 +771,7 @@ export default {"st.display.lean_mode.off": "Tắt","st.display.vision_mode.label": "Chế độ hình ảnh","st.display.vision_mode.desc": "Ở chế độ Hành động, tác tử nhìn trang dưới dạng ảnh chụp màn hình và nhấp, gõ, cuộn theo tọa độ màn hình thay vì đọc cây trợ năng. Cần một mô hình nhận được hình ảnh; các mô hình khác vẫn dùng cây trợ năng. Sau mỗi thao tác, chỉ phần màn hình thay đổi được gửi đi. Màn hình Retina và thu phóng trình duyệt được xử lý tự động.",- "st.display.vision_mode.on": "Bật",+ "st.display.vision_mode.auto": "Tự động","st.display.vision_mode.off": "Tắt","st.display.vision_quality.label": "Kích thước ảnh chụp ở chế độ hình ảnh","st.display.vision_quality.desc": "Kích thước ảnh chụp màn hình gửi đi ở chế độ hình ảnh. Tiết kiệm dùng ít token nhất và tải lên nhanh nhất; Sắc nét giữ nhiều chi tiết nhất. Tác tử luôn có thể phóng to chữ nhỏ.",diff --git a/src/chrome/src/ui/locales/zh.js b/src/chrome/src/ui/locales/zh.jsindex 27509a601..cfa119106 100644--- a/src/chrome/src/ui/locales/zh.js+++ b/src/chrome/src/ui/locales/zh.js@@ -957,7 +957,7 @@ export default {"st.display.lean_mode.off": "关闭","st.display.vision_mode.label": "视觉模式","st.display.vision_mode.desc": "在执行模式下,智能体以屏幕截图的方式查看页面,并在屏幕坐标处点击、输入和滚动,而不是读取无障碍树。需要能接收图像的模型;其他模型继续使用无障碍树。每次操作后只发送屏幕上发生变化的部分。Retina 屏幕和浏览器缩放会自动处理。",- "st.display.vision_mode.on": "开启",+ "st.display.vision_mode.auto": "自动","st.display.vision_mode.off": "关闭","st.display.vision_quality.label": "视觉模式截图尺寸","st.display.vision_quality.desc": "视觉模式下发送的截图尺寸。经济使用最少的令牌、上传最快;清晰保留最多细节。智能体随时可以放大查看小字。",diff --git a/src/chrome/src/ui/settings.html b/src/chrome/src/ui/settings.htmlindex 8fa3d240b..bfb2d302b 100644--- a/src/chrome/src/ui/settings.html+++ b/src/chrome/src/ui/settings.html@@ -894,7 +894,7 @@<div class="setting-desc" data-i18n="st.display.vision_mode.desc"></div></div><select id="select-vision-mode" data-i18n-aria-label="st.display.vision_mode.label">- <option value="on" data-i18n="st.display.vision_mode.on"></option>+ <option value="auto" data-i18n="st.display.vision_mode.auto"></option><option value="off" data-i18n="st.display.vision_mode.off"></option></select></div>diff --git a/src/chrome/src/ui/settings.js b/src/chrome/src/ui/settings.jsindex 4875b2a71..5d4d28443 100644--- a/src/chrome/src/ui/settings.js+++ b/src/chrome/src/ui/settings.js@@ -778,7 +778,7 @@ async function init() {strictGuardsToggle.checked = stored.strictGuards === true; // off by default}if (leanModeSelect) leanModeSelect.value = normalizeLeanModeSetting(stored.leanMode); // auto by default- if (visionModeSelect) visionModeSelect.value = normalizeVisionModeSetting(stored.visionMode); // on by default+ if (visionModeSelect) visionModeSelect.value = normalizeVisionModeSetting(stored.visionMode); // Auto by defaultif (visionQualitySelect) visionQualitySelect.value = normalizeVisionQuality(stored.visionQuality); // balanced by defaultif (allowLocalNetworkToggle) {allowLocalNetworkToggle.checked = stored.agentAllowLocalNetwork === true; // off by defaultdiff --git a/src/firefox/src/agent/agent.js b/src/firefox/src/agent/agent.jsindex ec6a8b9ee..3f8c0b7e3 100644--- a/src/firefox/src/agent/agent.js+++ b/src/firefox/src/agent/agent.js@@ -748,9 +748,9 @@ export class Agent extends LoopDetector {// resolves it once at its start (_beginLeanRun) and keeps the answer in// _leanRuns, so its prompt note and guards agree. See lean-mode.js.this.leanMode = 'auto';- // Vision mode (vision-mode.js): 'on' | 'off'. The class default keeps+ // Vision mode (vision-mode.js): 'auto' | 'off'. The class default keeps// the accessibility-tree path for embedders and the unit suite;- // background.js applies the stored setting, whose default is 'on'.+ // background.js applies the stored setting, whose default is 'auto'.this.visionMode = 'off';this.visionQuality = 'balanced';this._visionSessions = new Map();diff --git a/src/firefox/src/agent/vision-mode.js b/src/firefox/src/agent/vision-mode.jsindex 042e9c99f..9ca329c08 100644--- a/src/firefox/src/agent/vision-mode.js+++ b/src/firefox/src/agent/vision-mode.js@@ -2,20 +2,23 @@// Shared verbatim by the Chrome and Firefox builds (test/vision-mode.mjs).//// Settings → Advanced → "Vision mode" (storage key `visionMode`):-// 'on' — Act runs see the page as screenshots and act with coordinates-// whenever the run's model accepts images. This is the default.-// 'off' — the accessibility-tree path.+// 'auto' — Act runs see the page as screenshots and act with coordinates+// whenever the run's model accepts images. This is the default.+// The option was called On before, so a stored 'on' (or true)+// reads as 'auto'.+// 'off' — the accessibility-tree path.// A run decides once, when it starts, and keeps that answer to the end.import { detectVisionProfile, normalizeVisionQuality } from './vision-budget.js';-export const VISION_MODE_SETTINGS = Object.freeze(['on', 'off']);-export const DEFAULT_VISION_MODE_SETTING = 'on';+export const VISION_MODE_SETTINGS = Object.freeze(['auto', 'off']);+export const DEFAULT_VISION_MODE_SETTING = 'auto';export function normalizeVisionModeSetting(value, fallback = DEFAULT_VISION_MODE_SETTING) {- if (value === true) return 'on';+ if (value === true) return 'auto';if (value === false) return 'off';const normalized = String(value ?? '').trim().toLowerCase();+ if (normalized === 'on') return 'auto';if (VISION_MODE_SETTINGS.includes(normalized)) return normalized;return VISION_MODE_SETTINGS.includes(fallback) ? fallback : DEFAULT_VISION_MODE_SETTING;}@@ -39,7 +42,7 @@ export function resolveVisionMode(setting, {} = {}) {const normalized = normalizeVisionModeSetting(setting);const base = { active: false, setting: normalized };- if (normalized !== 'on') return { ...base, reason: 'setting_off' };+ if (normalized !== 'auto') return { ...base, reason: 'setting_off' };if (mode !== 'act') return { ...base, reason: 'not_act_mode' };if (standalone) return { ...base, reason: 'standalone_chat' };if (selectionOnly) return { ...base, reason: 'selection_scope' };diff --git a/src/firefox/src/config-transfer.js b/src/firefox/src/config-transfer.jsindex e5a66d309..5e77565a4 100644--- a/src/firefox/src/config-transfer.js+++ b/src/firefox/src/config-transfer.js@@ -59,7 +59,7 @@ export const DEFAULT_CONFIG_SETTINGS = Object.freeze({strictSecretMode: false,strictGuards: false,leanMode: 'auto',- visionMode: 'on',+ visionMode: 'auto',visionQuality: 'balanced',agentAllowLocalNetwork: false,scheduledTasksEnabled: true,@@ -253,7 +253,8 @@ function validSettingValue(key, value) {if (key === 'decisionMode') return ['', ...DECISION_MODES].includes(value);if (key === 'decisionVisionMode') return ['auto', 'on', 'off'].includes(value);if (key === 'leanMode') return ['auto', 'on', 'off'].includes(value);- if (key === 'visionMode') return ['on', 'off'].includes(value);+ // 'on' is Auto's name from before the option was renamed (currentSettingValue).+ if (key === 'visionMode') return ['auto', 'on', 'off'].includes(value);if (key === 'visionQuality') return ['economy', 'balanced', 'sharp'].includes(value);if (key === 'decisionBaseUrl') {if (typeof value !== 'string') return false;@@ -291,6 +292,13 @@ function dropChromeOnlyDecisionProvider(settings, { sparse = false } = {}) {if (settings.decisionMode !== 'off') settings.decisionMode = 'auto';}+// A value an older export names by a setting's former option: vision mode's+// Auto was called On ('on').+function currentSettingValue(key, value) {+ if (key === 'visionMode' && value === 'on') return 'auto';+ return value;+}+function normalizeSettings(source, { strict = false } = {}) {const settings = clone(DEFAULT_CONFIG_SETTINGS);if (!isPlainObject(source)) {@@ -317,7 +325,7 @@ function normalizeSettings(source, { strict = false } = {}) {if (strict) throw new Error(`Invalid value for configuration setting "${key}".`);continue;}- settings[key] = clone(value);+ settings[key] = clone(currentSettingValue(key, value));}settings.providers = sanitizeProviders(settings.providers, { strict });dropChromeOnlyDecisionProvider(settings);diff --git a/src/firefox/src/trace/runtime-config.js b/src/firefox/src/trace/runtime-config.jsindex 07a3e7d93..46864a0a1 100644--- a/src/firefox/src/trace/runtime-config.js+++ b/src/firefox/src/trace/runtime-config.js@@ -8,7 +8,7 @@ const STRING_ENUMS = Object.freeze({image_detail: new Set(['auto', 'low', 'high']),selection_scope_policy: new Set(['selection_only', 'selection_context']),lean_mode_setting: new Set(['auto', 'on', 'off']),- vision_mode_setting: new Set(['on', 'off']),+ vision_mode_setting: new Set(['auto', 'off']),});const BOOLEAN_FIELDS = Object.freeze([diff --git a/src/firefox/src/ui/locales/ar.js b/src/firefox/src/ui/locales/ar.jsindex 4bc5a20e0..7ba747643 100644--- a/src/firefox/src/ui/locales/ar.js+++ b/src/firefox/src/ui/locales/ar.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "إيقاف","st.display.vision_mode.label": "الوضع المرئي","st.display.vision_mode.desc": "في وضع التنفيذ يرى الوكيل الصفحة كلقطات شاشة وينقر ويكتب ويمرّر عند إحداثيات الشاشة بدلًا من قراءة شجرة إمكانية الوصول. يتطلب نموذجًا يقبل الصور؛ وتواصل النماذج الأخرى استخدام شجرة إمكانية الوصول. بعد كل إجراء يُرسَل الجزء المتغيّر من الشاشة فقط. تُعالَج شاشات Retina وتكبير المتصفح تلقائيًا.",- "st.display.vision_mode.on": "تشغيل",+ "st.display.vision_mode.auto": "تلقائي","st.display.vision_mode.off": "إيقاف","st.display.vision_quality.label": "حجم لقطات الوضع المرئي","st.display.vision_quality.desc": "حجم لقطات الشاشة المرسلة في الوضع المرئي. الاقتصادي يستهلك أقل عدد من الرموز ويُرفع أسرع؛ والحاد يحتفظ بأكبر قدر من التفاصيل. يمكن للوكيل دائمًا تكبير النص الصغير.",diff --git a/src/firefox/src/ui/locales/bn.js b/src/firefox/src/ui/locales/bn.jsindex 12eedd2ce..6cb61a4f7 100644--- a/src/firefox/src/ui/locales/bn.js+++ b/src/firefox/src/ui/locales/bn.js@@ -767,7 +767,7 @@ export default {"st.display.lean_mode.off": "বন্ধ","st.display.vision_mode.label": "ভিজ্যুয়াল মোড","st.display.vision_mode.desc": "Act মোডে এজেন্ট পেজটিকে স্ক্রিনশট হিসেবে দেখে এবং অ্যাক্সেসিবিলিটি ট্রি পড়ার বদলে স্ক্রিনের স্থানাঙ্কে ক্লিক, টাইপ ও স্ক্রল করে। এর জন্য ছবি গ্রহণ করে এমন মডেল লাগে; অন্য মডেলগুলো অ্যাক্সেসিবিলিটি ট্রি ব্যবহার করে চলে। প্রতিটি কাজের পর স্ক্রিনের শুধু পরিবর্তিত অংশ পাঠানো হয়। রেটিনা ডিসপ্লে ও ব্রাউজার জুম স্বয়ংক্রিয়ভাবে সামলানো হয়।",- "st.display.vision_mode.on": "চালু",+ "st.display.vision_mode.auto": "অটো","st.display.vision_mode.off": "বন্ধ","st.display.vision_quality.label": "ভিজ্যুয়াল মোডের স্ক্রিনশটের আকার","st.display.vision_quality.desc": "ভিজ্যুয়াল মোডে পাঠানো স্ক্রিনশটের আকার। সাশ্রয়ী সবচেয়ে কম টোকেন খরচ করে ও দ্রুত আপলোড হয়; তীক্ষ্ণ সবচেয়ে বেশি বিবরণ রাখে। এজেন্ট ছোট লেখায় সবসময় জুম করতে পারে।",diff --git a/src/firefox/src/ui/locales/de.js b/src/firefox/src/ui/locales/de.jsindex fcb7f9f22..3cf6cf9a3 100644--- a/src/firefox/src/ui/locales/de.js+++ b/src/firefox/src/ui/locales/de.js@@ -764,7 +764,7 @@ export default {"st.display.lean_mode.off": "Aus","st.display.vision_mode.label": "Visueller Modus","st.display.vision_mode.desc": "Im Modus „Handeln“ sieht der Agent die Seite als Screenshots und klickt, tippt und scrollt an Bildschirmkoordinaten, statt den Barrierefreiheitsbaum zu lesen. Erfordert ein Modell, das Bilder annimmt; andere Modelle nutzen weiter den Barrierefreiheitsbaum. Nach jeder Aktion wird nur der geänderte Teil des Bildschirms gesendet. Retina-Displays und Browser-Zoom werden automatisch berücksichtigt.",- "st.display.vision_mode.on": "Ein",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Aus","st.display.vision_quality.label": "Screenshot-Größe im visuellen Modus","st.display.vision_quality.desc": "Größe der im visuellen Modus gesendeten Screenshots. Sparsam verbraucht die wenigsten Tokens und lädt am schnellsten; Scharf behält die meisten Details. Der Agent kann kleine Schrift jederzeit vergrößern.",diff --git a/src/firefox/src/ui/locales/en.js b/src/firefox/src/ui/locales/en.jsindex 011d503ab..3031ec611 100644--- a/src/firefox/src/ui/locales/en.js+++ b/src/firefox/src/ui/locales/en.js@@ -772,7 +772,7 @@ export default {"st.display.lean_mode.off": "Off","st.display.vision_mode.label": "Vision mode","st.display.vision_mode.desc": "In Act mode the agent sees the page as screenshots and clicks, types and scrolls at screen coordinates instead of reading the accessibility tree. Needs a model that accepts images; other models keep the accessibility tree. After each action only the changed part of the screen is sent. Retina displays and browser zoom are handled automatically.",- "st.display.vision_mode.on": "On",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Off","st.display.vision_quality.label": "Vision screenshot size","st.display.vision_quality.desc": "Size of the screenshots sent in vision mode. Economy uses the fewest tokens and uploads fastest; Sharp keeps the most detail. The agent can always zoom into small text.",diff --git a/src/firefox/src/ui/locales/es.js b/src/firefox/src/ui/locales/es.jsindex 2f15e01e2..057cbd3f2 100644--- a/src/firefox/src/ui/locales/es.js+++ b/src/firefox/src/ui/locales/es.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Desactivado","st.display.vision_mode.label": "Modo visual","st.display.vision_mode.desc": "En el modo Actuar, el agente ve la página como capturas de pantalla y hace clic, escribe y desplaza en coordenadas de pantalla en lugar de leer el árbol de accesibilidad. Requiere un modelo que acepte imágenes; los demás modelos siguen usando el árbol de accesibilidad. Tras cada acción solo se envía la parte de la pantalla que cambió. Las pantallas Retina y el zoom del navegador se gestionan automáticamente.",- "st.display.vision_mode.on": "Activado",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Desactivado","st.display.vision_quality.label": "Tamaño de las capturas en modo visual","st.display.vision_quality.desc": "Tamaño de las capturas enviadas en modo visual. Económico usa menos tokens y se sube más rápido; Nítido conserva más detalle. El agente siempre puede ampliar el texto pequeño.",diff --git a/src/firefox/src/ui/locales/fa.js b/src/firefox/src/ui/locales/fa.jsindex f57d53ff9..32f4c5c51 100644--- a/src/firefox/src/ui/locales/fa.js+++ b/src/firefox/src/ui/locales/fa.js@@ -767,7 +767,7 @@ export default {"st.display.lean_mode.off": "خاموش","st.display.vision_mode.label": "حالت تصویری","st.display.vision_mode.desc": "در حالت «انجام» عامل صفحه را بهصورت تصویر صفحه میبیند و بهجای خواندن درخت دسترسپذیری، در مختصات صفحه کلیک میکند، تایپ میکند و پیمایش میکند. به مدلی نیاز دارد که تصویر بپذیرد؛ مدلهای دیگر همچنان از درخت دسترسپذیری استفاده میکنند. پس از هر اقدام فقط بخش تغییرکرده صفحه فرستاده میشود. نمایشگرهای Retina و بزرگنمایی مرورگر خودکار لحاظ میشوند.",- "st.display.vision_mode.on": "روشن",+ "st.display.vision_mode.auto": "خودکار","st.display.vision_mode.off": "خاموش","st.display.vision_quality.label": "اندازه تصویرهای حالت تصویری","st.display.vision_quality.desc": "اندازه تصویرهای صفحه در حالت تصویری. اقتصادی کمترین توکن را مصرف میکند و سریعتر ارسال میشود؛ واضح بیشترین جزئیات را نگه میدارد. عامل همیشه میتواند روی متن ریز بزرگنمایی کند.",diff --git a/src/firefox/src/ui/locales/fr.js b/src/firefox/src/ui/locales/fr.jsindex 0c51b6a6d..202b4de58 100644--- a/src/firefox/src/ui/locales/fr.js+++ b/src/firefox/src/ui/locales/fr.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Désactivé","st.display.vision_mode.label": "Mode visuel","st.display.vision_mode.desc": "En mode Agir, l’agent voit la page sous forme de captures d’écran et clique, tape et fait défiler à des coordonnées de l’écran au lieu de lire l’arbre d’accessibilité. Nécessite un modèle qui accepte les images ; les autres modèles conservent l’arbre d’accessibilité. Après chaque action, seule la partie de l’écran qui a changé est envoyée. Les écrans Retina et le zoom du navigateur sont gérés automatiquement.",- "st.display.vision_mode.on": "Activé",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Désactivé","st.display.vision_quality.label": "Taille des captures en mode visuel","st.display.vision_quality.desc": "Taille des captures envoyées en mode visuel. Économique utilise le moins de jetons et s’envoie le plus vite ; Net conserve le plus de détails. L’agent peut toujours zoomer sur un petit texte.",diff --git a/src/firefox/src/ui/locales/he.js b/src/firefox/src/ui/locales/he.jsindex ef9c00127..3e9ffbcb9 100644--- a/src/firefox/src/ui/locales/he.js+++ b/src/firefox/src/ui/locales/he.js@@ -744,7 +744,7 @@ export default {"st.display.lean_mode.off": "כבוי","st.display.vision_mode.label": "מצב חזותי","st.display.vision_mode.desc": "במצב פעולה הסוכן רואה את הדף כצילומי מסך ולוחץ, מקליד וגולל בקואורדינטות מסך במקום לקרוא את עץ הנגישות. נדרש מודל שמקבל תמונות; מודלים אחרים ממשיכים להשתמש בעץ הנגישות. אחרי כל פעולה נשלח רק החלק שהשתנה במסך. מסכי Retina והגדלת הדפדפן מטופלים אוטומטית.",- "st.display.vision_mode.on": "מופעל",+ "st.display.vision_mode.auto": "אוטומטי","st.display.vision_mode.off": "כבוי","st.display.vision_quality.label": "גודל צילומי המסך במצב חזותי","st.display.vision_quality.desc": "גודל צילומי המסך שנשלחים במצב חזותי. חסכוני משתמש במעט אסימונים ומועלה מהר; חד שומר על מרב הפרטים. הסוכן תמיד יכול להגדיל טקסט קטן.",diff --git a/src/firefox/src/ui/locales/hi.js b/src/firefox/src/ui/locales/hi.jsindex 3fc064649..113f5d08b 100644--- a/src/firefox/src/ui/locales/hi.js+++ b/src/firefox/src/ui/locales/hi.js@@ -767,7 +767,7 @@ export default {"st.display.lean_mode.off": "बंद","st.display.vision_mode.label": "दृश्य मोड","st.display.vision_mode.desc": "Act मोड में एजेंट पेज को स्क्रीनशॉट के रूप में देखता है और एक्सेसिबिलिटी ट्री पढ़ने के बजाय स्क्रीन निर्देशांकों पर क्लिक, टाइप और स्क्रॉल करता है। इसके लिए ऐसा मॉडल चाहिए जो इमेज स्वीकार करे; बाकी मॉडल एक्सेसिबिलिटी ट्री का उपयोग करते रहते हैं। हर क्रिया के बाद स्क्रीन का केवल बदला हुआ हिस्सा भेजा जाता है। रेटिना डिस्प्ले और ब्राउज़र ज़ूम अपने आप संभाले जाते हैं।",- "st.display.vision_mode.on": "चालू",+ "st.display.vision_mode.auto": "ऑटो","st.display.vision_mode.off": "बंद","st.display.vision_quality.label": "दृश्य मोड स्क्रीनशॉट आकार","st.display.vision_quality.desc": "दृश्य मोड में भेजे गए स्क्रीनशॉट का आकार। किफ़ायती सबसे कम टोकन लेता है और सबसे तेज़ अपलोड होता है; तीक्ष्ण सबसे अधिक विवरण रखता है। एजेंट छोटे पाठ पर हमेशा ज़ूम कर सकता है।",diff --git a/src/firefox/src/ui/locales/id.js b/src/firefox/src/ui/locales/id.jsindex 541c4c245..4497cdfbb 100644--- a/src/firefox/src/ui/locales/id.js+++ b/src/firefox/src/ui/locales/id.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Nonaktif","st.display.vision_mode.label": "Mode visual","st.display.vision_mode.desc": "Dalam mode Bertindak, agen melihat halaman sebagai tangkapan layar dan mengklik, mengetik, serta menggulir pada koordinat layar alih-alih membaca pohon aksesibilitas. Memerlukan model yang menerima gambar; model lain tetap memakai pohon aksesibilitas. Setelah setiap tindakan hanya bagian layar yang berubah yang dikirim. Layar Retina dan zoom browser ditangani otomatis.",- "st.display.vision_mode.on": "Aktif",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Nonaktif","st.display.vision_quality.label": "Ukuran tangkapan layar mode visual","st.display.vision_quality.desc": "Ukuran tangkapan layar yang dikirim dalam mode visual. Hemat memakai token paling sedikit dan paling cepat diunggah; Tajam mempertahankan detail terbanyak. Agen selalu dapat memperbesar teks kecil.",diff --git a/src/firefox/src/ui/locales/ja.js b/src/firefox/src/ui/locales/ja.jsindex 3fe0ad14d..409d5553e 100644--- a/src/firefox/src/ui/locales/ja.js+++ b/src/firefox/src/ui/locales/ja.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "オフ","st.display.vision_mode.label": "ビジョンモード","st.display.vision_mode.desc": "実行モードでは、エージェントはアクセシビリティツリーを読む代わりにページをスクリーンショットとして見て、画面座標でクリック・入力・スクロールします。画像を受け付けるモデルが必要で、それ以外のモデルは引き続きアクセシビリティツリーを使います。各操作の後は画面の変化した部分だけが送信されます。Retina ディスプレイとブラウザのズームは自動で処理されます。",- "st.display.vision_mode.on": "オン",+ "st.display.vision_mode.auto": "自動","st.display.vision_mode.off": "オフ","st.display.vision_quality.label": "ビジョンモードのスクリーンショットサイズ","st.display.vision_quality.desc": "ビジョンモードで送るスクリーンショットのサイズ。エコノミーはトークンが最も少なく最速でアップロードでき、シャープは最も多くの詳細を保ちます。エージェントは小さな文字をいつでもズームできます。",diff --git a/src/firefox/src/ui/locales/ko.js b/src/firefox/src/ui/locales/ko.jsindex 91c5e9a9e..935e72070 100644--- a/src/firefox/src/ui/locales/ko.js+++ b/src/firefox/src/ui/locales/ko.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "끔","st.display.vision_mode.label": "비전 모드","st.display.vision_mode.desc": "실행 모드에서 에이전트는 접근성 트리를 읽는 대신 페이지를 스크린샷으로 보고 화면 좌표에서 클릭, 입력, 스크롤합니다. 이미지를 받는 모델이 필요하며, 다른 모델은 계속 접근성 트리를 사용합니다. 각 동작 후에는 화면에서 바뀐 부분만 전송됩니다. 레티나 디스플레이와 브라우저 확대/축소는 자동으로 처리됩니다.",- "st.display.vision_mode.on": "켜짐",+ "st.display.vision_mode.auto": "자동","st.display.vision_mode.off": "꺼짐","st.display.vision_quality.label": "비전 모드 스크린샷 크기","st.display.vision_quality.desc": "비전 모드에서 보내는 스크린샷의 크기입니다. 절약은 토큰을 가장 적게 쓰고 가장 빨리 업로드되며, 선명은 세부 정보를 가장 많이 유지합니다. 에이전트는 작은 글자를 언제든 확대할 수 있습니다.",diff --git a/src/firefox/src/ui/locales/ms.js b/src/firefox/src/ui/locales/ms.jsindex c9705e79f..9c9da29fb 100644--- a/src/firefox/src/ui/locales/ms.js+++ b/src/firefox/src/ui/locales/ms.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Mati","st.display.vision_mode.label": "Mod visual","st.display.vision_mode.desc": "Dalam mod Bertindak, ejen melihat halaman sebagai tangkapan skrin dan mengklik, menaip serta menatal pada koordinat skrin dan bukannya membaca pepohon kebolehcapaian. Memerlukan model yang menerima imej; model lain terus menggunakan pepohon kebolehcapaian. Selepas setiap tindakan hanya bahagian skrin yang berubah dihantar. Paparan Retina dan zum pelayar dikendalikan secara automatik.",- "st.display.vision_mode.on": "Hidup",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Mati","st.display.vision_quality.label": "Saiz tangkapan skrin mod visual","st.display.vision_quality.desc": "Saiz tangkapan skrin yang dihantar dalam mod visual. Jimat menggunakan token paling sedikit dan dimuat naik paling pantas; Tajam mengekalkan paling banyak butiran. Ejen sentiasa boleh mengezum teks kecil.",diff --git a/src/firefox/src/ui/locales/nl.js b/src/firefox/src/ui/locales/nl.jsindex 3eb260f58..3c99fc0ed 100644--- a/src/firefox/src/ui/locales/nl.js+++ b/src/firefox/src/ui/locales/nl.js@@ -744,7 +744,7 @@ export default {"st.display.lean_mode.off": "Uit","st.display.vision_mode.label": "Visuele modus","st.display.vision_mode.desc": "In de modus Handelen ziet de agent de pagina als schermafbeeldingen en klikt, typt en scrolt hij op schermcoördinaten in plaats van de toegankelijkheidsboom te lezen. Vereist een model dat afbeeldingen accepteert; andere modellen blijven de toegankelijkheidsboom gebruiken. Na elke actie wordt alleen het gewijzigde deel van het scherm verzonden. Retina-schermen en browserzoom worden automatisch verwerkt.",- "st.display.vision_mode.on": "Aan",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Uit","st.display.vision_quality.label": "Schermafbeeldingsgrootte in visuele modus","st.display.vision_quality.desc": "Grootte van de schermafbeeldingen in de visuele modus. Zuinig gebruikt de minste tokens en uploadt het snelst; Scherp behoudt de meeste details. De agent kan altijd inzoomen op kleine tekst.",diff --git a/src/firefox/src/ui/locales/pl.js b/src/firefox/src/ui/locales/pl.jsindex 15e631784..609cc12e4 100644--- a/src/firefox/src/ui/locales/pl.js+++ b/src/firefox/src/ui/locales/pl.js@@ -924,7 +924,7 @@ export default {"st.display.lean_mode.off": "Wył.","st.display.vision_mode.label": "Tryb wizualny","st.display.vision_mode.desc": "W trybie Działaj agent widzi stronę jako zrzuty ekranu i klika, pisze oraz przewija we współrzędnych ekranu zamiast czytać drzewo dostępności. Wymaga modelu, który przyjmuje obrazy; inne modele nadal używają drzewa dostępności. Po każdej akcji wysyłana jest tylko zmieniona część ekranu. Ekrany Retina i powiększenie przeglądarki są obsługiwane automatycznie.",- "st.display.vision_mode.on": "Włączony",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Wyłączony","st.display.vision_quality.label": "Rozmiar zrzutów w trybie wizualnym","st.display.vision_quality.desc": "Rozmiar zrzutów wysyłanych w trybie wizualnym. Oszczędny zużywa najmniej tokenów i wysyła się najszybciej; Ostry zachowuje najwięcej szczegółów. Agent zawsze może powiększyć drobny tekst.",diff --git a/src/firefox/src/ui/locales/pt.js b/src/firefox/src/ui/locales/pt.jsindex 0a6d40837..5d8d96480 100644--- a/src/firefox/src/ui/locales/pt.js+++ b/src/firefox/src/ui/locales/pt.js@@ -767,7 +767,7 @@ export default {"st.display.lean_mode.off": "Desligado","st.display.vision_mode.label": "Modo visual","st.display.vision_mode.desc": "No modo Agir, o agente vê a página como capturas de tela e clica, digita e rola em coordenadas da tela em vez de ler a árvore de acessibilidade. Requer um modelo que aceite imagens; os outros modelos continuam com a árvore de acessibilidade. Após cada ação, só a parte da tela que mudou é enviada. Telas Retina e o zoom do navegador são tratados automaticamente.",- "st.display.vision_mode.on": "Ativado",+ "st.display.vision_mode.auto": "Automático","st.display.vision_mode.off": "Desativado","st.display.vision_quality.label": "Tamanho das capturas no modo visual","st.display.vision_quality.desc": "Tamanho das capturas enviadas no modo visual. Econômico usa menos tokens e envia mais rápido; Nítido mantém mais detalhes. O agente sempre pode ampliar textos pequenos.",diff --git a/src/firefox/src/ui/locales/ru.js b/src/firefox/src/ui/locales/ru.jsindex 75ef4ab12..774610ff3 100644--- a/src/firefox/src/ui/locales/ru.js+++ b/src/firefox/src/ui/locales/ru.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Выкл.","st.display.vision_mode.label": "Визуальный режим","st.display.vision_mode.desc": "В режиме «Действовать» агент видит страницу как снимки экрана и нажимает, печатает и прокручивает по координатам экрана, а не читает дерево доступности. Нужна модель, принимающая изображения; остальные модели продолжают работать с деревом доступности. После каждого действия отправляется только изменившаяся часть экрана. Экраны Retina и масштаб браузера учитываются автоматически.",- "st.display.vision_mode.on": "Вкл.",+ "st.display.vision_mode.auto": "Авто","st.display.vision_mode.off": "Выкл.","st.display.vision_quality.label": "Размер снимков в визуальном режиме","st.display.vision_quality.desc": "Размер снимков, отправляемых в визуальном режиме. «Экономный» тратит меньше всего токенов и загружается быстрее; «Чёткий» сохраняет больше деталей. Агент всегда может увеличить мелкий текст.",diff --git a/src/firefox/src/ui/locales/th.js b/src/firefox/src/ui/locales/th.jsindex 2463f7e89..730ccd122 100644--- a/src/firefox/src/ui/locales/th.js+++ b/src/firefox/src/ui/locales/th.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "ปิด","st.display.vision_mode.label": "โหมดภาพ","st.display.vision_mode.desc": "ในโหมดลงมือ เอเจนต์จะเห็นหน้าเว็บเป็นภาพหน้าจอ และคลิก พิมพ์ และเลื่อนตามพิกัดบนหน้าจอแทนการอ่านแผนผังการเข้าถึง ต้องใช้โมเดลที่รับรูปภาพได้ ส่วนโมเดลอื่นยังใช้แผนผังการเข้าถึงต่อไป หลังแต่ละการกระทำจะส่งเฉพาะส่วนของหน้าจอที่เปลี่ยนไป หน้าจอ Retina และการซูมเบราว์เซอร์ได้รับการจัดการโดยอัตโนมัติ",- "st.display.vision_mode.on": "เปิด",+ "st.display.vision_mode.auto": "อัตโนมัติ","st.display.vision_mode.off": "ปิด","st.display.vision_quality.label": "ขนาดภาพหน้าจอในโหมดภาพ","st.display.vision_quality.desc": "ขนาดของภาพหน้าจอที่ส่งในโหมดภาพ ประหยัดใช้โทเค็นน้อยที่สุดและอัปโหลดเร็วที่สุด คมชัดเก็บรายละเอียดได้มากที่สุด เอเจนต์ซูมดูข้อความเล็กได้เสมอ",diff --git a/src/firefox/src/ui/locales/tl.js b/src/firefox/src/ui/locales/tl.jsindex 7ee92bfb6..ddeec62ae 100644--- a/src/firefox/src/ui/locales/tl.js+++ b/src/firefox/src/ui/locales/tl.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Naka-off","st.display.vision_mode.label": "Visual mode","st.display.vision_mode.desc": "Sa Act mode, nakikita ng agent ang page bilang mga screenshot at nagki-click, nagta-type at nag-i-scroll sa mga coordinate ng screen sa halip na basahin ang accessibility tree. Kailangan ng modelong tumatanggap ng larawan; ang ibang modelo ay patuloy na gumagamit ng accessibility tree. Pagkatapos ng bawat aksyon, ang nagbagong bahagi lang ng screen ang ipinapadala. Awtomatikong naaayos ang mga Retina display at browser zoom.",- "st.display.vision_mode.on": "Naka-on",+ "st.display.vision_mode.auto": "Auto","st.display.vision_mode.off": "Naka-off","st.display.vision_quality.label": "Laki ng screenshot sa visual mode","st.display.vision_quality.desc": "Laki ng mga screenshot na ipinapadala sa visual mode. Ang Matipid ay gumagamit ng pinakakaunting token at pinakamabilis i-upload; ang Matalas ay nagpapanatili ng pinakamaraming detalye. Laging makakapag-zoom ang agent sa maliit na teksto.",diff --git a/src/firefox/src/ui/locales/tr.js b/src/firefox/src/ui/locales/tr.jsindex 5bcfa9310..a3beaab5b 100644--- a/src/firefox/src/ui/locales/tr.js+++ b/src/firefox/src/ui/locales/tr.js@@ -941,7 +941,7 @@ export default {"st.display.lean_mode.off": "Kapalı","st.display.vision_mode.label": "Görsel mod","st.display.vision_mode.desc": "“Uygula” modunda ajan, erişilebilirlik ağacını okumak yerine sayfayı ekran görüntüleri olarak görür; ekran koordinatlarına tıklar, yazar ve kaydırır. Görüntü kabul eden bir model gerekir; diğer modeller erişilebilirlik ağacıyla devam eder. Her işlemden sonra ekranın yalnızca değişen kısmı gönderilir. Retina ekranlar ve tarayıcı yakınlaştırması otomatik olarak hesaba katılır.",- "st.display.vision_mode.on": "Açık",+ "st.display.vision_mode.auto": "Otomatik","st.display.vision_mode.off": "Kapalı","st.display.vision_quality.label": "Görsel ekran görüntüsü boyutu","st.display.vision_quality.desc": "Görsel modda gönderilen ekran görüntülerinin boyutu. Ekonomik en az token kullanır ve en hızlı yüklenir; Keskin en fazla ayrıntıyı korur. Ajan küçük yazılara her zaman yakınlaştırabilir.",diff --git a/src/firefox/src/ui/locales/uk.js b/src/firefox/src/ui/locales/uk.jsindex 3ecfb231b..9c4b3b0f9 100644--- a/src/firefox/src/ui/locales/uk.js+++ b/src/firefox/src/ui/locales/uk.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "Вимк.","st.display.vision_mode.label": "Візуальний режим","st.display.vision_mode.desc": "У режимі «Діяти» агент бачить сторінку як знімки екрана й натискає, друкує та прокручує за координатами екрана замість читання дерева доступності. Потрібна модель, що приймає зображення; інші моделі й далі використовують дерево доступності. Після кожної дії надсилається лише змінена частина екрана. Екрани Retina та масштаб браузера враховуються автоматично.",- "st.display.vision_mode.on": "Увімк.",+ "st.display.vision_mode.auto": "Авто","st.display.vision_mode.off": "Вимк.","st.display.vision_quality.label": "Розмір знімків у візуальному режимі","st.display.vision_quality.desc": "Розмір знімків, що надсилаються у візуальному режимі. «Економний» витрачає найменше токенів і завантажується найшвидше; «Чіткий» зберігає найбільше деталей. Агент завжди може збільшити дрібний текст.",diff --git a/src/firefox/src/ui/locales/vi.js b/src/firefox/src/ui/locales/vi.jsindex a2bdf2fc8..b5a8f959c 100644--- a/src/firefox/src/ui/locales/vi.js+++ b/src/firefox/src/ui/locales/vi.js@@ -767,7 +767,7 @@ export default {"st.display.lean_mode.off": "Tắt","st.display.vision_mode.label": "Chế độ hình ảnh","st.display.vision_mode.desc": "Ở chế độ Hành động, tác tử nhìn trang dưới dạng ảnh chụp màn hình và nhấp, gõ, cuộn theo tọa độ màn hình thay vì đọc cây trợ năng. Cần một mô hình nhận được hình ảnh; các mô hình khác vẫn dùng cây trợ năng. Sau mỗi thao tác, chỉ phần màn hình thay đổi được gửi đi. Màn hình Retina và thu phóng trình duyệt được xử lý tự động.",- "st.display.vision_mode.on": "Bật",+ "st.display.vision_mode.auto": "Tự động","st.display.vision_mode.off": "Tắt","st.display.vision_quality.label": "Kích thước ảnh chụp ở chế độ hình ảnh","st.display.vision_quality.desc": "Kích thước ảnh chụp màn hình gửi đi ở chế độ hình ảnh. Tiết kiệm dùng ít token nhất và tải lên nhanh nhất; Sắc nét giữ nhiều chi tiết nhất. Tác tử luôn có thể phóng to chữ nhỏ.",diff --git a/src/firefox/src/ui/locales/zh.js b/src/firefox/src/ui/locales/zh.jsindex 1aa1444b6..e06767ffa 100644--- a/src/firefox/src/ui/locales/zh.js+++ b/src/firefox/src/ui/locales/zh.js@@ -932,7 +932,7 @@ export default {"st.display.lean_mode.off": "关闭","st.display.vision_mode.label": "视觉模式","st.display.vision_mode.desc": "在执行模式下,智能体以屏幕截图的方式查看页面,并在屏幕坐标处点击、输入和滚动,而不是读取无障碍树。需要能接收图像的模型;其他模型继续使用无障碍树。每次操作后只发送屏幕上发生变化的部分。Retina 屏幕和浏览器缩放会自动处理。",- "st.display.vision_mode.on": "开启",+ "st.display.vision_mode.auto": "自动","st.display.vision_mode.off": "关闭","st.display.vision_quality.label": "视觉模式截图尺寸","st.display.vision_quality.desc": "视觉模式下发送的截图尺寸。经济使用最少的令牌、上传最快;清晰保留最多细节。智能体随时可以放大查看小字。",diff --git a/src/firefox/src/ui/settings.html b/src/firefox/src/ui/settings.htmlindex 739a30bc1..c6682978f 100644--- a/src/firefox/src/ui/settings.html+++ b/src/firefox/src/ui/settings.html@@ -862,7 +862,7 @@<div class="setting-desc" data-i18n="st.display.vision_mode.desc"></div></div><select id="select-vision-mode" data-i18n-aria-label="st.display.vision_mode.label">- <option value="on" data-i18n="st.display.vision_mode.on"></option>+ <option value="auto" data-i18n="st.display.vision_mode.auto"></option><option value="off" data-i18n="st.display.vision_mode.off"></option></select></div>diff --git a/src/firefox/src/ui/settings.js b/src/firefox/src/ui/settings.jsindex e96c19890..2a6a28c22 100644--- a/src/firefox/src/ui/settings.js+++ b/src/firefox/src/ui/settings.js@@ -698,7 +698,7 @@ async function init() {if (strictSecretToggle) strictSecretToggle.checked = stored.strictSecretMode === true; // off by defaultif (strictGuardsToggle) strictGuardsToggle.checked = stored.strictGuards === true; // off by defaultif (leanModeSelect) leanModeSelect.value = normalizeLeanModeSetting(stored.leanMode); // auto by default- if (visionModeSelect) visionModeSelect.value = normalizeVisionModeSetting(stored.visionMode); // on by default+ if (visionModeSelect) visionModeSelect.value = normalizeVisionModeSetting(stored.visionMode); // Auto by defaultif (visionQualitySelect) visionQualitySelect.value = normalizeVisionQuality(stored.visionQuality); // balanced by defaultif (allowLocalNetworkToggle) allowLocalNetworkToggle.checked = stored.agentAllowLocalNetwork === true;if (scheduledTasksToggle) scheduledTasksToggle.checked = stored.scheduledTasksEnabled !== false;diff --git a/test/vision-mode-agent.mjs b/test/vision-mode-agent.mjsindex 35def1ea3..bebef1c67 100644--- a/test/vision-mode-agent.mjs+++ b/test/vision-mode-agent.mjs@@ -65,7 +65,7 @@ function createScene({ cssWidth = 1440, cssHeight = 900, devicePixelRatio = 2 }for (const build of (process.env.VISION_BUILDS || 'chrome,firefox').split(',')) {const { Agent } = await import(`../src/${build}/src/agent/agent.js`);- function runAgent(next, { visionMode = 'on', provider = VISION, scene = createScene(), maxSteps = 8, onDispatch = null } = {}) {+ function runAgent(next, { visionMode = 'auto', provider = VISION, scene = createScene(), maxSteps = 8, onDispatch = null } = {}) {const requests = [];const scripted = {contextWindow: 200000, supportsTools: true, supportsVision: true, promptTier: 'full', ...provider,diff --git a/test/vision-mode-guards.mjs b/test/vision-mode-guards.mjsindex 89e298586..64e0da24b 100644--- a/test/vision-mode-guards.mjs+++ b/test/vision-mode-guards.mjs@@ -330,10 +330,10 @@ for (const build of ['chrome', 'firefox']) {};test(`${build}: a whole-thread read and WhatsApp Web or Telegram keep the tree path; other pages stay in vision`, () => {- assert.equal(resolveVisionMode('on', { mode: 'act', provider: seeing, completeThreadRead: true }).reason, 'complete_thread_read');- assert.equal(resolveVisionMode('on', { mode: 'act', provider: seeing, nativeChatPage: true }).reason, 'native_chat_needs_element_inventory');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: seeing, completeThreadRead: true }).reason, 'complete_thread_read');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: seeing, nativeChatPage: true }).reason, 'native_chat_needs_element_inventory');const agent = agentFor();- agent.visionMode = 'on';+ agent.visionMode = 'auto';const tab = 31;assert.equal(agent._visionRunState(tab, 'act').active, true);agent.readCompletenessStates.set(tab, { required: true, complete: false });diff --git a/test/vision-mode.mjs b/test/vision-mode.mjsindex 95fa429ac..ad4392538 100644--- a/test/vision-mode.mjs+++ b/test/vision-mode.mjs@@ -317,28 +317,38 @@ test('click_at translates into a canonical CSS coordinate click', () => {assert.equal(bad.result.visionCoordinateError, 'out_of_bounds');});-test('settings: on by default, off disables, only Act with an image-capable model qualifies', () => {+test('settings: Auto by default, off disables, only Act with an image-capable model qualifies', () => {const { normalizeVisionModeSetting, resolveVisionMode } = visionMode;- assert.equal(normalizeVisionModeSetting(undefined), 'on');+ assert.equal(normalizeVisionModeSetting(undefined), 'auto');assert.equal(normalizeVisionModeSetting('OFF'), 'off');assert.equal(normalizeVisionModeSetting(false), 'off');- assert.equal(normalizeVisionModeSetting('maybe'), 'on');+ assert.equal(normalizeVisionModeSetting('maybe'), 'auto');+ // Auto was called On: a stored 'on' or true reads as Auto, and still applies.+ assert.equal(normalizeVisionModeSetting('on'), 'auto');+ assert.equal(normalizeVisionModeSetting(' ON '), 'auto');+ assert.equal(normalizeVisionModeSetting(true), 'auto');+ assert.equal(normalizeVisionModeSetting('auto'), 'auto');+ assert.equal(normalizeVisionModeSetting('maybe', 'off'), 'off');const seeing = { name: 'anthropic', supportsVision: true, config: { model: 'claude-sonnet-5' } };+ assert.deepEqual(+ { ...resolveVisionMode('auto', { mode: 'act', provider: seeing }) },+ { active: true, setting: 'auto', reason: 'vision_capable_model', profileId: 'anthropic', coordinates: 'pixel', quality: 'balanced' },+ );assert.deepEqual({ ...resolveVisionMode('on', { mode: 'act', provider: seeing }) },- { active: true, setting: 'on', reason: 'vision_capable_model', profileId: 'anthropic', coordinates: 'pixel', quality: 'balanced' },+ { active: true, setting: 'auto', reason: 'vision_capable_model', profileId: 'anthropic', coordinates: 'pixel', quality: 'balanced' },);assert.equal(resolveVisionMode('off', { mode: 'act', provider: seeing }).reason, 'setting_off');- assert.equal(resolveVisionMode('on', { mode: 'ask', provider: seeing }).reason, 'not_act_mode');- assert.equal(resolveVisionMode('on', { mode: 'dev', provider: seeing }).reason, 'not_act_mode');- assert.equal(resolveVisionMode('on', { mode: 'act', provider: { ...seeing, supportsVision: false } }).reason, 'model_without_images');+ assert.equal(resolveVisionMode('auto', { mode: 'ask', provider: seeing }).reason, 'not_act_mode');+ assert.equal(resolveVisionMode('auto', { mode: 'dev', provider: seeing }).reason, 'not_act_mode');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: { ...seeing, supportsVision: false } }).reason, 'model_without_images');// A describe-only vision sub-model cannot aim clicks.- assert.equal(resolveVisionMode('on', { mode: 'act', provider: seeing, rawImage: false }).reason, 'model_without_images');- assert.equal(resolveVisionMode('on', { mode: 'act', provider: seeing, standalone: true }).reason, 'standalone_chat');- assert.equal(resolveVisionMode('on', { mode: 'act', provider: { name: 'openrouter', supportsVision: true, config: { model: 'google/gemini-2.5-flash' } } }).coordinates, 'normalized');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: seeing, rawImage: false }).reason, 'model_without_images');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: seeing, standalone: true }).reason, 'standalone_chat');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: { name: 'openrouter', supportsVision: true, config: { model: 'google/gemini-2.5-flash' } } }).coordinates, 'normalized');// A site workflow proved against the element inventory keeps the tree path.- assert.equal(resolveVisionMode('on', { mode: 'act', provider: seeing, ledgerWorkflow: true }).reason, 'workflow_needs_element_inventory');- assert.equal(resolveVisionMode('on', { mode: 'act', provider: seeing, ledgerWorkflow: false }).active, true);+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: seeing, ledgerWorkflow: true }).reason, 'workflow_needs_element_inventory');+ assert.equal(resolveVisionMode('auto', { mode: 'act', provider: seeing, ledgerWorkflow: false }).active, true);});for (const build of ['chrome', 'firefox']) {@@ -424,24 +434,28 @@ for (const build of ['chrome', 'firefox']) {const settings = read(`src/${build}/src/ui/settings.js`);const background = read(`src/${build}/src/background.js`);const runtime = build === 'chrome' ? 'chrome' : 'browser';- assert.match(html, /<select id="select-vision-mode" data-i18n-aria-label="st\.display\.vision_mode\.label">\s*<option value="on" data-i18n="st\.display\.vision_mode\.on"><\/option>\s*<option value="off" data-i18n="st\.display\.vision_mode\.off"><\/option>/);+ assert.match(html, /<select id="select-vision-mode" data-i18n-aria-label="st\.display\.vision_mode\.label">\s*<option value="auto" data-i18n="st\.display\.vision_mode\.auto"><\/option>\s*<option value="off" data-i18n="st\.display\.vision_mode\.off"><\/option>/);assert.match(html, /<select id="select-vision-quality"[\s\S]*?value="economy"[\s\S]*?value="balanced"[\s\S]*?value="sharp"/);assert.ok(html.indexOf('select-vision-mode') > html.indexOf('select-lean-mode'), 'next to Lean mode in Advanced');assert.match(settings, /visionModeSelect\.value = normalizeVisionModeSetting\(stored\.visionMode\)/);assert.match(settings, new RegExp(`await ${runtime}\\.storage\\.local\\.set\\(\\{ visionMode: normalizeVisionModeSetting\\(visionModeSelect\\.value\\) \\}\\)`));assert.match(settings, new RegExp(`await ${runtime}\\.storage\\.local\\.set\\(\\{ visionQuality: normalizeVisionQuality\\(visionQualitySelect\\.value\\) \\}\\)`));- // Background applies the stored setting (default on) before the first chat.+ // Background applies the stored setting (default Auto) before the first chat.assert.match(background, /agent\.visionMode = normalizeVisionModeSetting\(stored\?\.visionMode\);/);assert.match(background, /if \(changes\.visionMode\) \{\s*agent\.visionMode = normalizeVisionModeSetting\(changes\.visionMode\.newValue\);/);assert.equal((background.match(/await strictSecretModeReady;/g) || []).length, (background.match(/await visionModeReady;/g) || []).length,'every hydration wait also waits for the vision setting');const config = await import(`../src/${build}/src/config-transfer.js`);- assert.equal(config.DEFAULT_CONFIG_SETTINGS.visionMode, 'on');+ assert.equal(config.DEFAULT_CONFIG_SETTINGS.visionMode, 'auto');assert.equal(config.DEFAULT_CONFIG_SETTINGS.visionQuality, 'balanced');assert.ok(config.CONFIG_STORAGE_KEYS.includes('visionMode'));assert.ok(config.CONFIG_STORAGE_KEYS.includes('visionQuality'));const exported = config.createConfigExport({});assert.equal(config.parseConfigImport(JSON.stringify({ ...exported, settings: { ...exported.settings, visionMode: 'off', visionQuality: 'sharp' } })).settings.visionMode, 'off');+ assert.equal(config.parseConfigImport(JSON.stringify({ ...exported, settings: { ...exported.settings, visionMode: 'auto' } })).settings.visionMode, 'auto');+ // An export made while Auto was called On imports as Auto, and a stored 'on' exports as Auto.+ assert.equal(config.parseConfigImport(JSON.stringify({ ...exported, settings: { ...exported.settings, visionMode: 'on' } })).settings.visionMode, 'auto');+ assert.equal(config.createConfigExport({ visionMode: 'on' }).settings.visionMode, 'auto');assert.throws(() => config.parseConfigImport(JSON.stringify({ ...exported, settings: { ...exported.settings, visionMode: 'maybe' } })), /visionMode/);assert.throws(() => config.parseConfigImport(JSON.stringify({ ...exported, settings: { ...exported.settings, visionQuality: 'huge' } })), /visionQuality/);// Every locale has real, translated copy.@@ -449,17 +463,20 @@ for (const build of ['chrome', 'firefox']) {const english = (await import(`../src/${build}/src/ui/locales/en.js`)).default;const locales = fs.readdirSync(dir).filter(name => /^[a-z]{2}\.js$/.test(name));assert.equal(locales.length, 23);- const keys = ['vision_mode.label', 'vision_mode.desc', 'vision_mode.on', 'vision_mode.off', 'vision_quality.label', 'vision_quality.desc',+ const keys = ['vision_mode.label', 'vision_mode.desc', 'vision_mode.auto', 'vision_mode.off', 'vision_quality.label', 'vision_quality.desc','vision_quality.economy', 'vision_quality.balanced', 'vision_quality.sharp'];for (const file of locales) {const dict = (await import(`../src/${build}/src/ui/locales/${file}`)).default;for (const key of keys) assert.ok(String(dict[`st.display.${key}`] || '').trim(), `${file}: ${key}`);if (file !== 'en.js') assert.notEqual(dict['st.display.vision_mode.desc'], english['st.display.vision_mode.desc'], `${file}: translated description`);+ // Auto reads as Lean mode's Auto beside it, and On is gone.+ assert.equal(dict['st.display.vision_mode.auto'], dict['st.display.lean_mode.auto'], `${file}: Auto label`);+ assert.equal(Object.hasOwn(dict, 'st.display.vision_mode.on'), false, `${file}: no On label`);}// Traces record the setting and the run's resolved state, nothing else.const runtimeConfig = await import(`../src/${build}/src/trace/runtime-config.js`);- assert.deepEqual(runtimeConfig.normalizeRuntimeTraceConfig({ vision_mode: true, vision_mode_setting: 'on', token: 'x' }),- { schema_version: 1, vision_mode: true, vision_mode_setting: 'on' });+ assert.deepEqual(runtimeConfig.normalizeRuntimeTraceConfig({ vision_mode: true, vision_mode_setting: 'auto', token: 'x' }),+ { schema_version: 1, vision_mode: true, vision_mode_setting: 'auto' });});}