hermes-agent/tools/computer_use/schema.py

"""Schema for the generic `computer_use` tool.

Model-agnostic. Any tool-calling model can drive this. Vision-capable models
should prefer `capture(mode='som')` then `click(element=N)` — much more
reliable than pixel coordinates. Pixel coordinates remain supported for
models that were trained on them (e.g. Claude's computer-use RL).
"""

from __future__ import annotations

from typing import Any, Dict


# One consolidated tool with an `action` discriminator. Keeps the schema
# compact and the per-turn token cost low.
COMPUTER_USE_SCHEMA: Dict[str, Any] = {
    "name": "computer_use",
    "description": (
        "Drive the macOS desktop in the background — screenshots, mouse, "
        "keyboard, scroll, drag — without stealing the user's cursor, "
        "keyboard focus, or Space. Preferred workflow: call with "
        "action='capture' (mode='som' gives numbered element overlays), "
        "then click by `element` index for reliability. Pixel coordinates "
        "are supported for models trained on them. Works on any window — "
        "hidden, minimized, on another Space, or behind another app. "
        "macOS only; requires cua-driver to be installed."
    ),
    "parameters": {
        "type": "object",
        "properties": {
            "action": {
                "type": "string",
                "enum": [
                    "capture",
                    "click",
                    "double_click",
                    "right_click",
                    "middle_click",
                    "drag",
                    "scroll",
                    "type",
                    "key",
                    "wait",
                    "list_apps",
                    "focus_app",
                ],
                "description": (
                    "Which action to perform. `capture` is free (no side "
                    "effects). All other actions require approval unless "
                    "auto-approved."
                ),
            },
            # ── capture ────────────────────────────────────────────
            "mode": {
                "type": "string",
                "enum": ["som", "vision", "ax"],
                "description": (
                    "Capture mode. `som` (default) is a screenshot with "
                    "numbered overlays on every interactable element plus "
                    "the AX tree — best for vision models, lets you click "
                    "by element index. `vision` is a plain screenshot. "
                    "`ax` is the accessibility tree only (no image; useful "
                    "for text-only models)."
                ),
            },
            "app": {
                "type": "string",
                "description": (
                    "Optional. Limit capture/action to a specific app "
                    "(by name, e.g. 'Safari', or bundle ID, "
                    "'com.apple.Safari'). If omitted, operates on the "
                    "frontmost app's window or the whole screen."
                ),
            },
            # ── click / drag / scroll targeting ────────────────────
            "element": {
                "type": "integer",
                "description": (
                    "The 1-based SOM index returned by the last "
                    "`capture(mode='som')` call. Strongly preferred over "
                    "raw coordinates."
                ),
            },
            "coordinate": {
                "type": "array",
                "items": {"type": "integer"},
                "minItems": 2,
                "maxItems": 2,
                "description": (
                    "Pixel coordinates [x, y] in logical screen space (as "
                    "returned by capture width/height). Only use this if "
                    "no element index is available."
                ),
            },
            "button": {
                "type": "string",
                "enum": ["left", "right", "middle"],
                "description": "Mouse button. Defaults to left.",
            },
            "modifiers": {
                "type": "array",
                "items": {
                    "type": "string",
                    "enum": ["cmd", "shift", "option", "alt", "ctrl", "fn"],
                },
                "description": "Modifier keys held during the action.",
            },
            # ── drag ───────────────────────────────────────────────
            "from_element": {"type": "integer",
                              "description": "Source element index (drag)."},
            "to_element": {"type": "integer",
                            "description": "Target element index (drag)."},
            "from_coordinate": {
                "type": "array",
                "items": {"type": "integer"},
                "minItems": 2, "maxItems": 2,
                "description": "Source [x,y] (drag; use when no element available).",
            },
            "to_coordinate": {
                "type": "array",
                "items": {"type": "integer"},
                "minItems": 2, "maxItems": 2,
                "description": "Target [x,y] (drag; use when no element available).",
            },
            # ── scroll ─────────────────────────────────────────────
            "direction": {
                "type": "string",
                "enum": ["up", "down", "left", "right"],
                "description": "Scroll direction.",
            },
            "amount": {
                "type": "integer",
                "description": "Scroll wheel ticks. Default 3.",
            },
            # ── type / key / wait ──────────────────────────────────
            "text": {
                "type": "string",
                "description": "Text to type (respects the current layout).",
            },
            "keys": {
                "type": "string",
                "description": (
                    "Key combo, e.g. 'cmd+s', 'ctrl+alt+t', 'return', "
                    "'escape', 'tab'. Use '+' to combine."
                ),
            },
            "seconds": {
                "type": "number",
                "description": "Seconds to wait. Max 30.",
            },
            # ── focus_app ──────────────────────────────────────────
            "raise_window": {
                "type": "boolean",
                "description": (
                    "Only for action='focus_app'. If true, brings the "
                    "window to front (DISRUPTS the user). Default false "
                    "— input is routed to the app without raising, "
                    "matching the background co-work model."
                ),
            },
            # ── return shape ───────────────────────────────────────
            "capture_after": {
                "type": "boolean",
                "description": (
                    "If true, take a follow-up capture after the action "
                    "and include it in the response. Saves a round-trip "
                    "when you need to verify an action's effect."
                ),
            },
        },
        "required": ["action"],
    },
}


def get_computer_use_schema() -> Dict[str, Any]:
    """Return the generic OpenAI function-calling schema."""
    return COMPUTER_USE_SCHEMA