q792602257/agentic-mobile-control
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(planner): persist reusable action semantics
Tests / Test passed: 879
Details

Browse Source
This commit is contained in:
q792602257
2026-07-15 18:14:28 +08:00
parent 361dada276
commit d69be48f96
41 changed files with 733 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files
runtime/tool_specs.py
+59 -32
View File
@@ -11,18 +11,51 @@ class ToolSpec:
parameters: dict[str, Any]
ACTION_METADATA_PROPERTIES: dict[str, dict[str, Any]] = {
"purpose": {
"type": "string",
"minLength": 1,
"maxLength": 240,
"description": "Concise intent for this action, used by later reuse.",
},
"expected_outcome": {
"type": "string",
"minLength": 1,
"maxLength": 240,
"description": "Observable screen state expected after this action.",
},
}
def _action_parameters(
*,
required: list[str],
properties: dict[str, dict[str, Any]],
) -> dict[str, Any]:
return {
"type": "object",
"additionalProperties": False,
"required": [*required, "purpose", "expected_outcome"],
"properties": {**properties, **ACTION_METADATA_PROPERTIES},
}
TAP_SPEC = ToolSpec(
name="tap",
description="Tap a point on the screen, given in Scene pixel coordinates.",
parameters={
"type": "object",
"additionalProperties": False,
"required": ["x", "y"],
"properties": {
"x": {"type": "number", "description": "X coordinate in Scene pixel space."},
"y": {"type": "number", "description": "Y coordinate in Scene pixel space."},
parameters=_action_parameters(
required=["x", "y"],
properties={
"x": {
"type": "number",
"description": "X coordinate in Scene pixel space.",
},
"y": {
"type": "number",
"description": "Y coordinate in Scene pixel space.",
},
},
},
),
)
SWIPE_SPEC = ToolSpec(
@@ -31,11 +64,9 @@ SWIPE_SPEC = ToolSpec(
"Swipe from a start point to an end point on the screen, given in "
"Scene pixel coordinates."
),
parameters={
"type": "object",
"additionalProperties": False,
"required": ["start_x", "start_y", "end_x", "end_y"],
"properties": {
parameters=_action_parameters(
required=["start_x", "start_y", "end_x", "end_y"],
properties={
"start_x": {"type": "number", "description": "Start X coordinate."},
"start_y": {"type": "number", "description": "Start Y coordinate."},
"end_x": {"type": "number", "description": "End X coordinate."},
@@ -46,52 +77,46 @@ SWIPE_SPEC = ToolSpec(
"default": 500,
},
},
},
),
)
INPUT_TEXT_SPEC = ToolSpec(
name="input_text",
description="Type text into the currently focused input field.",
parameters={
"type": "object",
"additionalProperties": False,
"required": ["text"],
"properties": {
parameters=_action_parameters(
required=["text"],
properties={
"text": {"type": "string", "description": "Text to type."},
},
},
),
)
LAUNCH_APP_SPEC = ToolSpec(
name="launch_app",
description="Launch (foreground) an app by its bundle/package identifier.",
parameters={
"type": "object",
"additionalProperties": False,
"required": ["app_id"],
"properties": {
parameters=_action_parameters(
required=["app_id"],
properties={
"app_id": {
"type": "string",
"description": "App bundle/package identifier.",
},
},
},
),
)
TERMINATE_APP_SPEC = ToolSpec(
name="terminate_app",
description="Terminate a running app by its bundle/package identifier.",
parameters={
"type": "object",
"additionalProperties": False,
"required": ["app_id"],
"properties": {
parameters=_action_parameters(
required=["app_id"],
properties={
"app_id": {
"type": "string",
"description": "App bundle/package identifier.",
},
},
},
),
)
FINISH_TASK_SPEC = ToolSpec(
@@ -126,4 +151,6 @@ ACTION_TOOL_SPECS: list[ToolSpec] = [
TERMINATE_APP_SPEC,
]
ACTION_TOOL_NAMES = frozenset(spec.name for spec in ACTION_TOOL_SPECS)
ALL_TOOL_SPECS: list[ToolSpec] = [*ACTION_TOOL_SPECS, FINISH_TASK_SPEC]