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.
352 lines
13 KiB
JSON
352 lines
13 KiB
JSON
{
|
|
"click": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "click",
|
|
"description": "[ACTION] Click on the target location on the screen (supports element index or absolute normalized coordinates).",
|
|
"parameters": {
|
|
"properties": {
|
|
"target": {
|
|
"anyOf": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
}
|
|
],
|
|
"description": "Click target. Can be an element index number (int, e.g. 3) OR normalized coordinates (list of 2 integers, e.g. [500, 600])."
|
|
},
|
|
"target_description": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "What the target is, in a few words (e.g. 'play button', 'search input', 'video body'). REQUIRED when target is a coordinate pair; ignored for an element index."
|
|
},
|
|
"times": {
|
|
"default": 1,
|
|
"description": "Number of consecutive clicks on this target. Use this for double-clicks or multi-clicks (e.g. 7 to enter developer mode). Default is 1.",
|
|
"type": "integer"
|
|
},
|
|
"delay_ms": {
|
|
"default": 100,
|
|
"description": "Delay in milliseconds between consecutive clicks. Default is 100.",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"target"
|
|
],
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"input_text": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "input_text",
|
|
"description": "[ACTION] Type text into the target input field (supports replacing whole text or appending to the end, and multi-line strings with '\\n').",
|
|
"parameters": {
|
|
"properties": {
|
|
"text": {
|
|
"description": "The text content to input. Supports multi-line content with '\\n'.",
|
|
"type": "string"
|
|
},
|
|
"target": {
|
|
"anyOf": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
}
|
|
],
|
|
"description": "Input target field. Can be an input box element index number (int, e.g. 3) OR normalized coordinates (list of 2 integers, e.g. [500, 600])."
|
|
},
|
|
"target_description": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "What the target is, in a few words (e.g. 'play button', 'search input', 'video body'). REQUIRED when target is a coordinate pair; ignored for an element index."
|
|
},
|
|
"clear_exist": {
|
|
"default": true,
|
|
"description": "Whether to clear existing text before typing. True (default): clear/replace entire text. False: append at the end of existing content.",
|
|
"type": "boolean"
|
|
}
|
|
},
|
|
"required": [
|
|
"text",
|
|
"target"
|
|
],
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"swipe": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "swipe",
|
|
"description": "[ACTION] Perform a swipe, drag, or slider-adjustment gesture on the screen.\n\n• Directional Scrolling ('direction'): 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'): 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.\n\nArgs:\n direction: Smart directional scrolling ('up', 'down', 'left', 'right'). Automatically computes safe swipe vectors, retaining 40% visual overlap: 'up' (reveal content below), 'down' (reveal content above), 'left', 'right'.\n start: Start normalized coordinates [start_x, start_y] in 0-1000 scale.\n end: End normalized coordinates [end_x, end_y] in 0-1000 scale.\n target: Optional target element index (e.g. 2) or container bounds [left, top, right, bottom] to scope the directional swipe within.\n gesture: Backward-compatible parameter: direction string OR custom coordinates list [start_x, start_y, end_x, end_y] in 0-1000 scale.\n target_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.\n duration: Optional gesture duration in milliseconds (default 800).",
|
|
"parameters": {
|
|
"properties": {
|
|
"direction": {
|
|
"anyOf": [
|
|
{
|
|
"enum": [
|
|
"up",
|
|
"down",
|
|
"left",
|
|
"right"
|
|
],
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"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": {
|
|
"anyOf": [
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "Start normalized coordinates [start_x, start_y] in 0-1000 scale for precise, local interactions (e.g. adjusting sliders, SeekBars, fine range selection, or drag-and-drop)."
|
|
},
|
|
"end": {
|
|
"anyOf": [
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "End normalized coordinates [end_x, end_y] in 0-1000 scale for precise, local interactions (e.g. adjusting sliders, SeekBars, fine range selection, or drag-and-drop)."
|
|
},
|
|
"target": {
|
|
"anyOf": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
},
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "Optional target element index (e.g. 2) or container bounds [left, top, right, bottom] to scope the directional swipe within."
|
|
},
|
|
"gesture": {
|
|
"anyOf": [
|
|
{
|
|
"enum": [
|
|
"up",
|
|
"down",
|
|
"left",
|
|
"right"
|
|
],
|
|
"type": "string"
|
|
},
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"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": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"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": {
|
|
"anyOf": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "Optional swipe/drag duration in milliseconds (default 800; computed automatically for directional swipes)."
|
|
}
|
|
},
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"press_key": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "press_key",
|
|
"description": "[ACTION] Press a physical or virtual system button (e.g. ENTER, BACK, HOME, APP_SWITCH).",
|
|
"parameters": {
|
|
"properties": {
|
|
"key": {
|
|
"description": "Standard Android system button name (ENTER, BACK, HOME, APP_SWITCH).",
|
|
"enum": [
|
|
"ENTER",
|
|
"BACK",
|
|
"HOME",
|
|
"APP_SWITCH"
|
|
],
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"key"
|
|
],
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"manage_app": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "manage_app",
|
|
"description": "[ACTION] Launch or force stop a specified application.",
|
|
"parameters": {
|
|
"properties": {
|
|
"action": {
|
|
"description": "The action type.",
|
|
"enum": [
|
|
"launch",
|
|
"stop"
|
|
],
|
|
"type": "string"
|
|
},
|
|
"app_name": {
|
|
"description": "Display name or package name of the application.",
|
|
"type": "string"
|
|
}
|
|
},
|
|
"required": [
|
|
"action",
|
|
"app_name"
|
|
],
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"wait_for_delay": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "wait_for_delay",
|
|
"description": "[ACTION] Pause execution and wait for a specified duration in milliseconds.\n\nUse this whenever you need time to elapse—whether for UI loading, animations,\nscreen transitions, or longer scheduled delays and intervals specified in the task.",
|
|
"parameters": {
|
|
"properties": {
|
|
"time_in_ms": {
|
|
"description": "The exact duration to wait in milliseconds. Accurately convert the required time duration into milliseconds based on your objective or plan (e.g., 2000 for 2s, 5000 for 5s, 60000 for 1 minute, 180000 for 3 minutes, 300000 for 5 minutes).",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"time_in_ms"
|
|
],
|
|
"type": "object"
|
|
}
|
|
}
|
|
},
|
|
"long_press": {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "long_press",
|
|
"description": "[ACTION] Long press on the target location on the screen (supports element index or absolute normalized coordinates).",
|
|
"parameters": {
|
|
"properties": {
|
|
"target": {
|
|
"anyOf": [
|
|
{
|
|
"type": "integer"
|
|
},
|
|
{
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array"
|
|
}
|
|
],
|
|
"description": "Long press target. Can be an element index number (int, e.g. 3) OR normalized coordinates (list of 2 integers, e.g. [500, 600])."
|
|
},
|
|
"target_description": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"default": null,
|
|
"description": "What the target is, in a few words (e.g. 'play button', 'search input', 'video body'). REQUIRED when target is a coordinate pair; ignored for an element index."
|
|
},
|
|
"duration": {
|
|
"default": 1000,
|
|
"description": "Long press duration in milliseconds (default 1000).",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"target"
|
|
],
|
|
"type": "object"
|
|
}
|
|
}
|
|
}
|
|
}
|