somew1nd
a45daf23f8
Report device actions as dispatched and preserve full failure details. Route Flash through McpActionExecutor and use ToolFailure across helper tools and agent loops instead of inferring failure from response text. Require model-provided descriptions for coordinate targets. Keep observed element metadata separate from those descriptions in safety checks, visual summaries, history, and frontend labels. Add Gemini Interactions API video analysis with configurable processing mode, chunk size, and timeouts. Centralize Google provider capabilities and token usage normalization, and update google-genai to 2.22.0. Preserve system instructions on follow-up interactions, replan pending chunks when falling back to static processing, and reject unanswered native video and audio segments instead of caching placeholder results. Keep helper-tool failure status intact through history tools and committee calls. Validation: 1,762 Python unit tests passed (3 skipped), 40 frontend formatter tests passed, and the production UI build completed. Ruff lint, formatting, the quality ratchet, and git diff checks passed.
255 lines
10 KiB
JSON
255 lines
10 KiB
JSON
{
|
|
"CLICK_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "click",
|
|
"description": "[ACTION] Tap/click on the target coordinate on the screen. The screen after click will be returned automatically. For buttons, checkboxes, tabs, icons, items in a list, tap ON the element. For text fields / search bars / input boxes, tap INSIDE the input box to focus it.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"target": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"description": "Normalized coordinates [x, y] in 0-1000 scale."
|
|
},
|
|
"target_description": {
|
|
"type": "string",
|
|
"description": "What the target is, in a few words (e.g. 'play button', 'search input', 'video body'). Required: a coordinate names nothing by itself."
|
|
},
|
|
"times": {
|
|
"type": "integer",
|
|
"description": "Number of taps to perform (default 1). Set to 2 for double click."
|
|
},
|
|
"delay_ms": {
|
|
"type": "integer",
|
|
"description": "Delay between taps in milliseconds (default 100)."
|
|
}
|
|
},
|
|
"required": [
|
|
"target",
|
|
"target_description"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"CLICK_SEQUENCE_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "click_sequence",
|
|
"description": "[ACTION] Executes a sequence of taps one by one in order on the specified targets (e.g. [[500, 280], [885, 362]]). The screen will be returned ONLY after all clicks in the sequence have completed.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"sequence": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"description": "Normalized coordinates [x, y] in 0-1000 scale (e.g., [500, 280])."
|
|
},
|
|
"description": "List of targets to tap in sequence, e.g. [[500, 280], [885, 362]]."
|
|
},
|
|
"target_descriptions": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"description": "What each target is, in a few words, one entry per sequence entry in the same order (e.g. ['video body', 'skip button']). Required: a coordinate names nothing by itself."
|
|
},
|
|
"delay_ms": {
|
|
"type": "integer",
|
|
"description": "Delay between consecutive taps in milliseconds (default 50ms)."
|
|
}
|
|
},
|
|
"required": [
|
|
"sequence",
|
|
"target_descriptions"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"LONG_PRESS_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "long_press",
|
|
"description": "[ACTION] Long press on a target coordinate on the screen. The screen after long pressing will be returned automatically.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"target": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"description": "Normalized coordinates [x, y] in 0-1000 scale."
|
|
},
|
|
"target_description": {
|
|
"type": "string",
|
|
"description": "What the target is, in a few words (e.g. 'play button', 'search input', 'video body'). Required: a coordinate names nothing by itself."
|
|
},
|
|
"duration_ms": {
|
|
"type": "integer",
|
|
"description": "Duration of press in milliseconds (default 1000ms)."
|
|
}
|
|
},
|
|
"required": [
|
|
"target",
|
|
"target_description"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"INPUT_TEXT_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "input_text",
|
|
"description": "[ACTION] Type text into an input field on the screen. The screen after typing will be returned automatically. Automatically taps inside the input box at target [x, y] to focus before typing.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"text": {
|
|
"type": "string",
|
|
"description": "Text to type into the focused input field."
|
|
},
|
|
"target": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"description": "Coordinates [x, y] of the input box in 0-1000 scale."
|
|
},
|
|
"target_description": {
|
|
"type": "string",
|
|
"description": "What the target is, in a few words (e.g. 'play button', 'search input', 'video body'). Required: a coordinate names nothing by itself."
|
|
},
|
|
"clear_exist": {
|
|
"type": "boolean",
|
|
"description": "Whether to clear existing text in the input box before typing (default True)."
|
|
}
|
|
},
|
|
"required": [
|
|
"text",
|
|
"target",
|
|
"target_description"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"SWIPE_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "swipe",
|
|
"description": "[ACTION] Perform a swipe, drag, or slider-adjustment gesture on the screen. The screen and UI hierarchy after swipe will be returned automatically.\n\n• Directional Scrolling ('direction' or 'action'): Recommended for general browsing and standard page scrolling in most scenarios. Automatically computes safe swipe vectors and adaptive duration, retains a ~40% visual overlap anchor for zero-omission traversal, and prevents inertial flings. Supports scoping to a sub-container via 'target'. If it fails on certain custom layouts, fall back to specifying exact coordinates ('start' and 'end') directly.\n• Precise Coordinate Gestures ('start', 'end' or coordinates list): Best for local, fine-grained interactions such as adjusting sliders/SeekBars (e.g., volume, brightness, progress bars), drag-and-drop / list reordering, or as a reliable fallback when directional scrolling fails on specific containers. Always drag slightly PAST the target position to overcome touch slop and reliably trigger the update. When setting a slider to Maximum (100%) or Minimum (0%), swipe fully to the extreme boundary.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"direction": {
|
|
"type": "string",
|
|
"enum": [
|
|
"up",
|
|
"down",
|
|
"left",
|
|
"right"
|
|
],
|
|
"description": "Direction for scrolling and swiping: 'up' (drags bottom-to-top, scrolling down to reveal content below), 'down' (drags top-to-bottom, scrolling up to reveal content above), 'left' (drags right-to-left, scrolling right), 'right' (drags left-to-right, scrolling left)."
|
|
},
|
|
"start": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"description": "Start normalized coordinates [start_x, start_y] in 0-1000 scale."
|
|
},
|
|
"end": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"description": "End normalized coordinates [end_x, end_y] in 0-1000 scale."
|
|
},
|
|
"target": {
|
|
"description": "Optional target element index (e.g. 2) or container bounds [left, top, right, bottom] to scope the directional swipe within."
|
|
},
|
|
"action": {
|
|
"description": "Backward-compatible swipe gesture: smart direction string ('up', 'down', 'left', 'right') OR precise custom coordinates [start_x, start_y, end_x, end_y] in 0-1000 scale."
|
|
},
|
|
"target_description": {
|
|
"type": "string",
|
|
"description": "What is being dragged, in a few words (e.g. 'brightness slider knob'). Required for coordinate gestures ('start'/'end' or a coordinates list); ignored for directional scrolling."
|
|
},
|
|
"duration": {
|
|
"type": "integer",
|
|
"description": "Optional swipe/drag duration in milliseconds (default 800). For drag-and-drop, list reordering, or sliding/adjusting sliders (e.g., volume, brightness, SeekBars), set duration >= 1000 (e.g. 1500). If omitted for directional swipe, duration is computed automatically."
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"PRESS_KEY_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "press_key",
|
|
"description": "[ACTION] Press a physical or virtual system button. The screen after pressing will be returned automatically.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"key": {
|
|
"type": "string",
|
|
"description": "Standard Android system button name (ENTER, BACK, HOME, APP_SWITCH)."
|
|
}
|
|
},
|
|
"required": [
|
|
"key"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"MANAGE_APP_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "manage_app",
|
|
"description": "[ACTION] Launch or force stop a specified application. The screen after launch/stop will be returned automatically.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"action": {
|
|
"type": "string",
|
|
"description": "The action type ('launch' or 'stop')."
|
|
},
|
|
"app_name": {
|
|
"type": "string",
|
|
"description": "Display name or package name of the application."
|
|
}
|
|
},
|
|
"required": [
|
|
"action",
|
|
"app_name"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"WAIT_FOR_DELAY_TOOL": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "wait_for_delay",
|
|
"description": "[ACTION] Pause execution and wait for a specified duration in milliseconds. The screen after pause will be returned automatically.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"time_in_ms": {
|
|
"type": "integer",
|
|
"description": "The exact duration to pause in milliseconds (e.g., 2000 for 2s, 60000 for 1 min, 180000 for 3 mins, 300000 for 5 mins). Convert any required waiting duration into milliseconds."
|
|
}
|
|
},
|
|
"required": [
|
|
"time_in_ms"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|