| [ |
| { |
| "type": "function", |
| "function": { |
| "name": "click", |
| "description": "Left-click.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "x": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| } |
| }, |
| "required": [ |
| "x", |
| "y" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "double_click", |
| "description": "Double-click.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "x": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| } |
| }, |
| "required": [ |
| "x", |
| "y" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "right_click", |
| "description": "Right-click.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "x": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| } |
| }, |
| "required": [ |
| "x", |
| "y" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "type", |
| "description": "Type literal text into the input that currently has focus. It takes no coordinates: click (or focus) the target input first, then type. To replace existing text, use click → clear → type.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "text": { |
| "type": "string" |
| } |
| }, |
| "required": [ |
| "text" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "hotkey", |
| "description": "Press one key, or a key combination held down together, on the currently focused page/element. Pass the keys in order as a list: modifiers first, then the main key (e.g. [\"Control\", \"a\"]). Key names are case-sensitive and use these exact spellings (modifiers Control, Shift, Alt, Meta; named keys such as Enter, Escape, Tab, Backspace, Space, ArrowUp, ArrowDown, ArrowLeft, ArrowRight, Home, End, PageUp, PageDown, F1-F12; letters and digits in lowercase, e.g. a, 0, -). Keys and when to use them: Enter - submit a focused search box or form, or confirm a selection (use after type). Control+a - select all text in the focused input (e.g. before Backspace or before typing replacement text). Control+c - copy the current selection. Control+v - paste the clipboard into the focused input. Backspace - delete the character before the cursor, or the selected text. Tab / Shift+Tab - move focus to the next / previous element. Escape - close a popup, dialog, dropdown or autocomplete list. ArrowDown / ArrowUp - move through dropdown or autocomplete options, or scroll a little. ArrowLeft / ArrowRight - move the cursor in a text input, or switch slides/carousel items. Home / End - jump to the top / bottom of the page (or start / end of the input line). Control+Home / Control+End - jump to the very top / bottom of the page or document. PageDown / PageUp - scroll down / up by one screen. Space - toggle a focused checkbox/button, or scroll down. Control+f - open find-in-page. F3 - find the next match in find-in-page. Control+l / Alt+d / F6 - focus the address bar (prefer goto(url) to open a URL). Control+r / F5 - reload the current page. Control+Shift+r - hard reload the current page, ignoring the cache. Alt+ArrowLeft - go back in browser history (same as go_back). Alt+Home - open the browser home page. Control+t - open a new tab (prefer new_tab). Control+w - close the current tab (prefer close_tab). Control+n - open a new browser window. Control+Tab - switch to the next tab (prefer switch_tab). Control+1 ... Control+8 - switch to the tab at that position (prefer switch_tab). Control+- / Control+0 - zoom the page out / reset the zoom. F11 - toggle full-screen view. Control+h - open the browser history page. Control+j - open the browser downloads page. Control+d - bookmark the current page. Control+p - open the print dialog. Control+u - view the page source. F12 / Control+Shift+i / Control+Shift+j / Control+Shift+c - open the browser developer tools (console / element picker). Alt / Meta / Meta+r / Control+Escape / Alt+Tab / Control+Alt+t - operating-system or browser-menu keys (open the menu bar or start menu, run dialog, switch windows, open a terminal); they usually do not help with a web task. j / k / w - single-letter shortcuts that some websites define (for example next / previous item). Do not use hotkey to type text; use type for that. Clicking an input first gives it focus.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "keys": { |
| "type": "array", |
| "items": { |
| "type": "string" |
| }, |
| "minItems": 1, |
| "description": "Keys pressed together, modifiers first. Examples: [\"Enter\"], [\"Control\", \"a\"], [\"Escape\"], [\"ArrowDown\"], [\"Control\", \"r\"]." |
| } |
| }, |
| "required": [ |
| "keys" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "scroll", |
| "description": "Scroll by signed pixel deltas.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "scroll_dy": { |
| "type": "number", |
| "description": "Signed pixel delta, not a normalized coordinate." |
| }, |
| "scroll_dx": { |
| "type": "number", |
| "description": "Signed pixel delta, not a normalized coordinate." |
| } |
| }, |
| "required": [ |
| "scroll_dy" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "wait", |
| "description": "Wait for the specified duration.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "seconds": { |
| "type": "number", |
| "minimum": 0 |
| } |
| }, |
| "required": [ |
| "seconds" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "finished", |
| "description": "Finish the task, optionally returning an answer.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "answer": { |
| "type": "string" |
| } |
| }, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "fail", |
| "description": "Terminate because the task cannot be completed.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "unknown", |
| "description": "Signal that a reliable action cannot be determined.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "go_back", |
| "description": "Go back in browser history.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "go_forward", |
| "description": "Go forward in browser history.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "goto", |
| "description": "Navigate to a URL.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "url": { |
| "type": "string" |
| } |
| }, |
| "required": [ |
| "url" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "hover", |
| "description": "Move the pointer without clicking.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "x": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| } |
| }, |
| "required": [ |
| "x", |
| "y" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "drag", |
| "description": "Drag from (x,y) to (x2,y2).", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "x": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "x2": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y2": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| } |
| }, |
| "required": [ |
| "x", |
| "y", |
| "x2", |
| "y2" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "upload", |
| "description": "Upload a local file to the web page. Use it right after the page has opened a file picker (e.g. after clicking a button such as 'Upload', 'Choose file', or '컴퓨터에서 선택'); the file is attached to that picker. Use only a file name or path that the user gave in the request — never invent one. If no file picker is open yet, click the page's upload button first.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "path": { |
| "type": "string", |
| "description": "File name or path exactly as given by the user, e.g. \"puppy.jpg\"." |
| } |
| }, |
| "required": [ |
| "path" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "focus", |
| "description": "Focus the element at the coordinates.", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "x": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| }, |
| "y": { |
| "type": "number", |
| "minimum": 0, |
| "maximum": 1000, |
| "description": "Normalized 0-1000 screenshot coordinate." |
| } |
| }, |
| "required": [ |
| "x", |
| "y" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "clear", |
| "description": "Clear all text in the currently focused input. Give the input focus first (click or focus on it), then clear, then type.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "EXIT", |
| "description": "Explicit final termination.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "new_tab", |
| "description": "Open a new blank browser tab.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "switch_tab", |
| "description": "Switch to the browser tab at the given 0-based index (see Available tabs in the observation).", |
| "parameters": { |
| "type": "object", |
| "properties": { |
| "index": { |
| "type": "integer", |
| "minimum": 0, |
| "description": "0-based tab index." |
| } |
| }, |
| "required": [ |
| "index" |
| ], |
| "additionalProperties": false |
| } |
| } |
| }, |
| { |
| "type": "function", |
| "function": { |
| "name": "close_tab", |
| "description": "Close the current browser tab.", |
| "parameters": { |
| "type": "object", |
| "properties": {}, |
| "required": [], |
| "additionalProperties": false |
| } |
| } |
| } |
| ] |
