revert: computer-use cua-driver (PR #16919) (#16927)

Reverts PR #16919 (commits dad10a78d, 413ee1a28, b4a8031b2, afb958829)
which was merged prematurely. Restoring the pre-merge state so #14817
and #15328 can be revisited as standing PRs.

Reverted commits:
- afb958829 fix(computer-use): harden image-rejection fallback + AUTHOR_MAP
- b4a8031b2 fix(computer-use): unwrap _multimodal tool results
- 413ee1a28 feat(computer-use): background focus-safe backend
- dad10a78d feat(computer-use): cua-driver backend, universal any-model schema

Co-authored-by: teknium1 <teknium@users.noreply.github.com>

tools/computer_use/backend.py

@@ -1,150 +0,0 @@
-"""Abstract backend interface for computer use.
-
-Any implementation (cua-driver over MCP, pyautogui, noop, future Linux/Windows)
-must return the shape described below. All methods synchronous; async is
-handled inside the backend implementation if needed.
-"""
-
-from __future__ import annotations
-
-from abc import ABC, abstractmethod
-from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional, Tuple
-
-
-@dataclass
-class UIElement:
-    """One interactable element on the current screen."""
-
-    index: int                       # 1-based SOM index
-    role: str                        # AX role (AXButton, AXTextField, ...)
-    label: str = ""                  # AXTitle / AXDescription / AXValue snippet
-    bounds: Tuple[int, int, int, int] = (0, 0, 0, 0)  # x, y, w, h (logical px)
-    app: str = ""                    # owning bundle ID or app name
-    pid: int = 0                     # owning process PID
-    window_id: int = 0               # SkyLight / CG window ID
-    attributes: Dict[str, Any] = field(default_factory=dict)
-
-    def center(self) -> Tuple[int, int]:
-        x, y, w, h = self.bounds
-        return x + w // 2, y + h // 2
-
-
-@dataclass
-class CaptureResult:
-    """Result of a screen capture call.
-
-    At least one of png_b64 / elements is populated depending on capture mode:
-      * mode="vision" → png_b64 only
-      * mode="ax"     → elements only
-      * mode="som"    → both (default): PNG already has numbered overlays
-                         drawn by the backend, and `elements` holds the
-                         matching index → element mapping.
-    """
-
-    mode: str
-    width: int                      # screenshot width (logical px, pre-Anthropic-scale)
-    height: int
-    png_b64: Optional[str] = None
-    elements: List[UIElement] = field(default_factory=list)
-    # Optional: the target app/window the elements were captured for.
-    app: str = ""
-    window_title: str = ""
-    # Raw bytes we sent to Anthropic, for token estimation.
-    png_bytes_len: int = 0
-
-
-@dataclass
-class ActionResult:
-    """Result of any action (click / type / scroll / drag / key / wait)."""
-
-    ok: bool
-    action: str
-    message: str = ""                # human-readable summary
-    # Optional trailing screenshot — set when the caller asked for a
-    # post-action capture or the backend always returns one.
-    capture: Optional[CaptureResult] = None
-    # Arbitrary extra fields for debugging / telemetry.
-    meta: Dict[str, Any] = field(default_factory=dict)
-
-
-class ComputerUseBackend(ABC):
-    """Lifecycle: `start()` before first use, `stop()` at shutdown."""
-
-    @abstractmethod
-    def start(self) -> None: ...
-
-    @abstractmethod
-    def stop(self) -> None: ...
-
-    @abstractmethod
-    def is_available(self) -> bool:
-        """Return True if the backend can be used on this host right now.
-
-        Used by check_fn gating and by the post-setup wizard.
-        """
-
-    # ── Capture ─────────────────────────────────────────────────────
-    @abstractmethod
-    def capture(self, mode: str = "som", app: Optional[str] = None) -> CaptureResult: ...
-
-    # ── Pointer actions ─────────────────────────────────────────────
-    @abstractmethod
-    def click(
-        self,
-        *,
-        element: Optional[int] = None,
-        x: Optional[int] = None,
-        y: Optional[int] = None,
-        button: str = "left",           # left | right | middle
-        click_count: int = 1,
-        modifiers: Optional[List[str]] = None,
-    ) -> ActionResult: ...
-
-    @abstractmethod
-    def drag(
-        self,
-        *,
-        from_element: Optional[int] = None,
-        to_element: Optional[int] = None,
-        from_xy: Optional[Tuple[int, int]] = None,
-        to_xy: Optional[Tuple[int, int]] = None,
-        button: str = "left",
-        modifiers: Optional[List[str]] = None,
-    ) -> ActionResult: ...
-
-    @abstractmethod
-    def scroll(
-        self,
-        *,
-        direction: str,                 # up | down | left | right
-        amount: int = 3,                # wheel ticks
-        element: Optional[int] = None,
-        x: Optional[int] = None,
-        y: Optional[int] = None,
-        modifiers: Optional[List[str]] = None,
-    ) -> ActionResult: ...
-
-    # ── Keyboard ────────────────────────────────────────────────────
-    @abstractmethod
-    def type_text(self, text: str) -> ActionResult: ...
-
-    @abstractmethod
-    def key(self, keys: str) -> ActionResult:
-        """Send a key combo, e.g. 'cmd+s', 'ctrl+alt+t', 'return'."""
-
-    # ── Introspection ───────────────────────────────────────────────
-    @abstractmethod
-    def list_apps(self) -> List[Dict[str, Any]]:
-        """Return running apps with bundle IDs, PIDs, window counts."""
-
-    @abstractmethod
-    def focus_app(self, app: str, raise_window: bool = False) -> ActionResult:
-        """Route input to `app` (by name or bundle ID). Default: focus without raise."""
-
-    # ── Timing ──────────────────────────────────────────────────────
-    def wait(self, seconds: float) -> ActionResult:
-        """Default implementation: time.sleep."""
-        import time
-        time.sleep(max(0.0, min(seconds, 30.0)))
-        return ActionResult(ok=True, action="wait", message=f"waited {seconds:.2f}s")