clickthrough/server/models.py

from typing import Literal, Optional

from pydantic import BaseModel, Field, model_validator


class PixelTarget(BaseModel):
    mode: Literal["pixel"]
    x: int
    y: int
    dx: int = 0
    dy: int = 0


class GridTarget(BaseModel):
    mode: Literal["grid"]
    region_x: int
    region_y: int
    region_width: int = Field(gt=0)
    region_height: int = Field(gt=0)
    rows: int = Field(gt=0)
    cols: int = Field(gt=0)
    row: int = Field(ge=0)
    col: int = Field(ge=0)
    dx: float = 0.0
    dy: float = 0.0

    @model_validator(mode="after")
    def _validate_indices(self):
        if self.row >= self.rows or self.col >= self.cols:
            raise ValueError("row/col must be inside rows/cols")
        if not -1.0 <= self.dx <= 1.0:
            raise ValueError("dx must be in [-1, 1]")
        if not -1.0 <= self.dy <= 1.0:
            raise ValueError("dy must be in [-1, 1]")
        return self


Target = PixelTarget | GridTarget


class ActionRequest(BaseModel):
    action: Literal[
        "move",
        "click",
        "right_click",
        "double_click",
        "middle_click",
        "scroll",
        "type",
        "hotkey",
        "click_text",
    ]
    target: Optional[Target] = None
    duration_ms: int = Field(default=0, ge=0, le=20000)
    button: Literal["left", "right", "middle"] = "left"
    clicks: int = Field(default=1, ge=1, le=10)
    scroll_amount: int = 0
    text: str = ""
    keys: list[str] = Field(default_factory=list)
    interval_ms: int = Field(default=20, ge=0, le=5000)
    dry_run: bool = False
    click_text: "ClickTextAction | None" = None

    @model_validator(mode="after")
    def _validate_click_text(self):
        if self.action == "click_text" and self.click_text is None:
            raise ValueError("click_text payload is required when action=click_text")
        return self


class ExecRequest(BaseModel):
    command: str = Field(min_length=1, max_length=10000)
    shell: Literal["powershell", "bash", "cmd"] | None = None
    timeout_s: int | None = Field(default=None, ge=1, le=600)
    cwd: str | None = None
    dry_run: bool = False


class WindowQuery(BaseModel):
    title_contains: str | None = Field(default=None, max_length=512)
    title_regex: str | None = Field(default=None, max_length=512)
    process_name: str | None = Field(default=None, max_length=260)
    hwnd: int | None = Field(default=None, ge=1)
    visible_only: bool = True


class WindowActionRequest(WindowQuery):
    action: Literal["focus", "restore", "minimize", "maximize", "close"]
    timeout_ms: int = Field(default=3000, ge=0, le=60000)


class LaunchRequest(BaseModel):
    executable: str = Field(min_length=1, max_length=2048)
    args: list[str] = Field(default_factory=list, max_length=100)
    cwd: str | None = None
    wait_for_window: bool = False
    match: WindowQuery | None = None
    timeout_ms: int = Field(default=5000, ge=0, le=120000)
    dry_run: bool = False


class SeeRequest(BaseModel):
    screen: int = 0
    region_x: int | None = Field(default=None, ge=0)
    region_y: int | None = Field(default=None, ge=0)
    region_width: int | None = Field(default=None, gt=0)
    region_height: int | None = Field(default=None, gt=0)
    with_grid: bool = True
    grid_rows: int = Field(default=12, ge=1, le=300)
    grid_cols: int = Field(default=12, ge=1, le=300)
    include_labels: bool = True
    image_format: Literal["png", "jpeg"] = "png"
    jpeg_quality: int = Field(default=85, ge=1, le=100)
    ocr: bool = False
    ocr_min_confidence: float = Field(default=0.0, ge=0.0, le=100.0)
    ocr_lang: str = Field(default="eng", min_length=1, max_length=64)
    ocr_psm: int | None = Field(default=None, ge=0, le=13)


class SeeZoomRequest(BaseModel):
    screen: int = 0
    center_x: int = Field(ge=0)
    center_y: int = Field(ge=0)
    width: int = Field(default=500, ge=10)
    height: int = Field(default=350, ge=10)
    with_grid: bool = True
    grid_rows: int = Field(default=20, ge=1, le=300)
    grid_cols: int = Field(default=20, ge=1, le=300)
    include_labels: bool = True
    image_format: Literal["png", "jpeg"] = "png"
    jpeg_quality: int = Field(default=90, ge=1, le=100)


class InteractRequest(BaseModel):
    screen: int = 0
    action: ActionRequest


class OCRRegion(BaseModel):
    x: int = Field(ge=0)
    y: int = Field(ge=0)
    width: int = Field(gt=0)
    height: int = Field(gt=0)


class ClickTextAction(BaseModel):
    text: str = Field(min_length=1, max_length=1000)
    match: Literal["contains", "exact", "regex"] = "contains"
    region: OCRRegion | None = None
    screen: int | None = None
    case_sensitive: bool = False
    min_confidence: float = Field(default=0.0, ge=0.0, le=100.0)
    occurrence: Literal["first", "best", "nth"] = "first"
    nth: int | None = Field(default=None, ge=1, le=10000)
    ocr_lang: str = Field(default="eng", min_length=1, max_length=64)
    ocr_psm: int | None = Field(default=None, ge=0, le=13)

    @model_validator(mode="after")
    def _validate_nth(self):
        if self.occurrence == "nth" and self.nth is None:
            raise ValueError("nth is required when occurrence=nth")
        if self.occurrence != "nth" and self.nth is not None:
            raise ValueError("nth is only allowed when occurrence=nth")
        return self


ActionRequest.model_rebuild()