mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-21 16:18:55 +00:00
9d6d772837
Hermes' computer_use wrapper dropped cua-driver's structured action verdicts, exposed no delivery_mode, and injected background-only guidance — so the agent reported unverified no-ops as success and concluded cua-driver 'cannot drive' Electron/Chromium surfaces (observed live on tldraw offline). Fixes #67052. Phase A — preserve the result contract: - ActionResult carries verified/effect/escalation/path/degraded/code/delivery_mode - CuaDriverBackend._action() reads structuredContent (was data-only); a helper normalizes it, additive and None-safe on old drivers - _text_response surfaces the fields additively (ok stays transport-only) Phase B — bounded, model-reachable foreground: - delivery_mode (background|foreground) + bring_to_front on the schema, dispatcher, ABC, and all input methods - foreground is capability-gated (input.delivery_mode); old drivers get a structured foreground_unsupported refusal, never a silent background downgrade - no automatic/hidden foreground retry — the model selects it from the signal Phase C — guidance + isolation: - system prompt (prompt_builder) and bundled skills/computer-use/SKILL.md go from background-ONLY to background-FIRST, teaching the AX→PX→foreground ladder driven by returned effect/escalation, not predicted from the app being Electron - foreground approval scoped by (action, delivery_mode): a background approval never silently authorizes foreground - approval state keyed per session_id so concurrent gateway runs don't leak unlocks Tests: tests/tools/test_computer_use_delivery_ladder.py (15) cover confirmed/ unverifiable/suspected_noop/degraded/old-driver verdicts, delivery_mode gating + foreground_unsupported, and session-scoped foreground approval. Existing 265 computer_use tests still green. Live E2E (real cua-driver 0.8.3 + tldraw offline on Linux/X11): a background click returned effect='unverifiable'/path='ax' (no fabricated success), and a foreground request returned code='foreground_unsupported' — correct on a driver that predates the input.delivery_mode capability.
267 lines
12 KiB
Python
267 lines
12 KiB
Python
"""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 desktop in the background via cua-driver — screenshots, "
|
|
"mouse, keyboard, scroll, drag — without stealing the user's cursor "
|
|
"or keyboard focus. Supported on macOS, Windows, and Linux. "
|
|
"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, or behind another app. 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",
|
|
"set_value",
|
|
"wait",
|
|
"list_apps",
|
|
"list_windows",
|
|
"focus_app",
|
|
],
|
|
"description": (
|
|
"Which action to perform. `capture` is free (no side "
|
|
"effects). All other actions require approval unless "
|
|
"auto-approved. Use `set_value` for select/popup elements "
|
|
"and sliders — it selects the matching option directly "
|
|
"without opening the native menu (no focus steal)."
|
|
),
|
|
},
|
|
# ── 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. Pass app='screen' (or "
|
|
"'desktop') to capture the OS desktop/shell surface — "
|
|
"e.g. to see the wallpaper or click the taskbar. Note: "
|
|
"capture is per-window; a single image cannot span "
|
|
"multiple monitors, so on a multi-screen setup capture "
|
|
"one window or display at a time."
|
|
),
|
|
},
|
|
"pid": {
|
|
"type": "integer",
|
|
"description": (
|
|
"Optional exact process target for action='capture'. Pair "
|
|
"with window_id when discovery cannot resolve an X11 app."
|
|
),
|
|
},
|
|
"window_id": {
|
|
"type": "integer",
|
|
"description": (
|
|
"Optional exact native window target for action='capture'. "
|
|
"Pair with pid when an external cua-driver list_windows "
|
|
"lookup has already identified the window."
|
|
),
|
|
},
|
|
"max_elements": {
|
|
"type": "integer",
|
|
"description": (
|
|
"Optional cap on the AX `elements` array returned by "
|
|
"`action='capture'`. Default 100, hard maximum 1000. "
|
|
"Dense UIs (Electron apps such as Obsidian or VS Code, "
|
|
"JetBrains IDEs) can publish 500+ AX nodes — capping "
|
|
"prevents a single capture from blowing session "
|
|
"context. When the cap trims the response, "
|
|
"`total_elements` and `truncated_elements` are "
|
|
"surfaced in the result so you can re-call with "
|
|
"`app=` to narrow scope or raise `max_elements` when "
|
|
"the full tree is required. Has no effect on "
|
|
"`mode='som'` / `mode='vision'` when a screenshot is "
|
|
"included in the response; only the rare image-"
|
|
"missing fallback returns an `elements` array and is "
|
|
"subject to the cap."
|
|
),
|
|
"default": 100,
|
|
"minimum": 1,
|
|
"maximum": 1000,
|
|
},
|
|
# ── 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] relative to the captured window "
|
|
"screenshot (top-left origin). 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",
|
|
"win", "windows", "super", "meta",
|
|
],
|
|
},
|
|
"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.",
|
|
},
|
|
# ── set_value ──────────────────────────────────────────
|
|
"value": {
|
|
"type": "string",
|
|
"description": (
|
|
"For action='set_value': the value to set on the element. "
|
|
"For AXPopUpButton / select dropdowns, pass the option's "
|
|
"display label (e.g. 'Blue'). For sliders and other "
|
|
"AXValue-settable elements, pass the numeric or string value."
|
|
),
|
|
},
|
|
# ── 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."
|
|
),
|
|
},
|
|
# ── delivery (verify → escalate ladder) ────────────────
|
|
"delivery_mode": {
|
|
"type": "string",
|
|
"enum": ["background", "foreground"],
|
|
"description": (
|
|
"How input is delivered, for the input actions (click, "
|
|
"double_click, right_click, drag, scroll, type, key). "
|
|
"`background` (DEFAULT) routes input to the target without "
|
|
"raising it or stealing focus — the co-work model. "
|
|
"`foreground` briefly fronts the window, acts, then "
|
|
"restores the prior frontmost app. Only escalate to "
|
|
"`foreground` when a background attempt did NOT land — i.e. "
|
|
"a prior result had `effect: 'suspected_noop'`, "
|
|
"`code: 'background_unavailable'`, or "
|
|
"`escalation.recommended: 'foreground'`. Do not predict it "
|
|
"from the app being Electron/Chromium; react to the "
|
|
"returned signal. Foreground is a visible focus change and "
|
|
"needs its own approval."
|
|
),
|
|
},
|
|
"bring_to_front": {
|
|
"type": "boolean",
|
|
"description": (
|
|
"Optional, pairs with delivery_mode='foreground'. Keep the "
|
|
"target fronted after the action instead of restoring the "
|
|
"previous app, to avoid a per-call flash across a short "
|
|
"sequence of foreground actions. Default false."
|
|
),
|
|
},
|
|
# ── 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
|