diff --git a/apps/desktop/src/app/settings/computer-use-panel.tsx b/apps/desktop/src/app/settings/computer-use-panel.tsx new file mode 100644 index 00000000000..ada5c08e3ad --- /dev/null +++ b/apps/desktop/src/app/settings/computer-use-panel.tsx @@ -0,0 +1,239 @@ +import { useCallback, useEffect, useRef, useState } from 'react' + +import { Button } from '@/components/ui/button' +import { getActionStatus, getComputerUseStatus, grantComputerUsePermissions } from '@/hermes' +import { AlertTriangle, Check, ExternalLink, Loader2, RefreshCw, X } from '@/lib/icons' +import { upsertDesktopActionTask } from '@/store/activity' +import { notify, notifyError } from '@/store/notifications' +import type { ComputerUseStatus } from '@/types/hermes' + +import { Pill } from './primitives' + +interface ComputerUsePanelProps { + /** Re-read the parent toolset list after a permission/install change so the + * "Configured / Needs keys" pill stays in sync. */ + onConfiguredChange?: () => void +} + +// Per-OS one-liner shown when there's no TCC grant flow (Windows/Linux). macOS +// drives the permission rows instead, so it has no entry here. +const PLATFORM_NOTE: Record = { + linux: 'Drives your desktop via the X11/XWayland accessibility stack — no permission prompt.', + win32: 'First run may trigger a Windows SmartScreen prompt for the cua-driver UIAccess worker — allow it.' +} + +function tone(granted: boolean | null) { + return granted === true ? 'primary' : 'muted' +} + +function GrantIcon({ granted }: { granted: boolean | null }) { + const Icon = granted === true ? Check : granted === false ? X : AlertTriangle + + return +} + +function PermissionRow({ granted, label, hint }: { granted: boolean | null; label: string; hint: string }) { + return ( +
+
+ {label} +

{hint}

+
+ + + {granted === true ? 'Granted' : granted === false ? 'Not granted' : 'Unknown'} + +
+ ) +} + +/** + * Cross-platform Computer Use preflight card. + * + * cua-driver runs on macOS, Windows, and Linux, but readiness differs: macOS + * needs two TCC grants (Accessibility + Screen Recording) that attach to + * cua-driver's own `com.trycua.driver` identity — not Hermes — and are + * requested via `cua-driver permissions grant` (dialog attributed to + * CuaDriver). Windows/Linux have no TCC toggles, so readiness is driver health + * from `cua-driver doctor`. The backend folds both into one `ready` signal. + * + * Binary install/upgrade stays in the cua-driver provider's post-setup runner + * below this card (the generic ToolsetConfigPanel). + */ +export function ComputerUsePanel({ onConfiguredChange }: ComputerUsePanelProps) { + const [status, setStatus] = useState(null) + const [loading, setLoading] = useState(true) + const [granting, setGranting] = useState(false) + const activeRef = useRef(false) + + const refresh = useCallback(async () => { + try { + setStatus(await getComputerUseStatus()) + } catch (err) { + notifyError(err, 'Could not read Computer Use status') + } finally { + setLoading(false) + } + }, []) + + useEffect(() => { + activeRef.current = true + void refresh() + + return () => void (activeRef.current = false) + }, [refresh]) + + const grant = useCallback(async () => { + setGranting(true) + + try { + const started = await grantComputerUsePermissions() + + if (!started.ok) { + notifyError(new Error('spawn failed'), 'Could not request permissions') + + return + } + + notify({ + kind: 'info', + title: 'Approve in System Settings', + message: 'macOS will show a permission dialog attributed to CuaDriver. Approve it, then return here.' + }) + + // The driver waits for the user to flip the switch — poll until it exits. + for (let attempt = 0; attempt < 150 && activeRef.current; attempt += 1) { + await new Promise(resolve => window.setTimeout(resolve, 1500)) + + if (!activeRef.current) { + break + } + + const polled = await getActionStatus(started.name, 200) + upsertDesktopActionTask(polled) + + if (!polled.running) { + break + } + } + + if (activeRef.current) { + await refresh() + onConfiguredChange?.() + } + } catch (err) { + if (activeRef.current) { + notifyError(err, 'Could not request permissions') + } + } finally { + if (activeRef.current) { + setGranting(false) + } + } + }, [onConfiguredChange, refresh]) + + if (loading) { + return ( +
+ + Checking Computer Use status… +
+ ) + } + + if (!status) { + return null + } + + if (!status.platform_supported) { + return ( +

+ Computer Use isn't supported on this platform ({status.platform}). +

+ ) + } + + if (!status.installed) { + return ( +

+ Install the cua-driver backend below to drive this machine. + {status.can_grant && ' Then grant Accessibility and Screen Recording here.'} +

+ ) + } + + const failingChecks = status.checks.filter(c => c.status !== 'ok') + + return ( +
+
+
+ {status.can_grant ? ( +

+ Grants attach to CuaDriver's own identity (com.trycua.driver), not Hermes — so the dialog is + attributed to the process that drives your Mac. +

+ ) : ( +

{PLATFORM_NOTE[status.platform] ?? ''}

+ )} + {status.version &&

{status.version}

} +
+ +
+ + {status.can_grant ? ( + <> + + + + ) : ( +
+ Driver health + + + {status.ready === true ? 'Ready' : status.ready === false ? 'Not ready' : 'Unknown'} + +
+ )} + + {failingChecks.map(c => ( +

+ + {c.label}: {c.message} +

+ ))} + + {status.error && ( +

+ + {status.error} +

+ )} + + {status.ready ? ( +
+ + Computer Use is ready. Ask the agent to capture an app and click around. +
+ ) : ( + status.can_grant && ( + + ) + )} +
+ ) +} diff --git a/apps/desktop/src/app/skills/index.tsx b/apps/desktop/src/app/skills/index.tsx index 716f0181f12..90aa4a24357 100644 --- a/apps/desktop/src/app/skills/index.tsx +++ b/apps/desktop/src/app/skills/index.tsx @@ -17,6 +17,7 @@ import { useRefreshHotkey } from '../hooks/use-refresh-hotkey' import { useRouteEnumParam } from '../hooks/use-route-enum-param' import { PAGE_INSET_X } from '../layout-constants' import { PageSearchShell } from '../page-search-shell' +import { ComputerUsePanel } from '../settings/computer-use-panel' import { asText, includesQuery, prettyName, toolNames, toolsetDisplayLabel } from '../settings/helpers' import { ToolsetConfigPanel } from '../settings/toolset-config-panel' import type { SetStatusbarItemGroup } from '../shell/statusbar-controls' @@ -334,6 +335,9 @@ export function SkillsView({ setStatusbarItemGroup: _setStatusbarItemGroup, ...p ))} )} + {expanded && toolset.name === 'computer_use' && ( + + )} {expanded && } ) diff --git a/apps/desktop/src/hermes.ts b/apps/desktop/src/hermes.ts index 197e24611ab..a7b5ae14307 100644 --- a/apps/desktop/src/hermes.ts +++ b/apps/desktop/src/hermes.ts @@ -8,6 +8,7 @@ import type { AudioTranscriptionResponse, AuxiliaryModelsResponse, BackendUpdateCheckResponse, + ComputerUseStatus, ConfigSchemaResponse, CronJob, CronJobCreatePayload, @@ -59,6 +60,9 @@ export type { AudioTranscriptionResponse, AuxiliaryModelsResponse, BackendUpdateCheckResponse, + ComputerUseCheck, + ComputerUsePermissionSource, + ComputerUseStatus, ConfigFieldSchema, ConfigSchemaResponse, CronJob, @@ -516,6 +520,21 @@ export function runToolsetPostSetup(name: string, key: string): Promise { + return window.hermesDesktop.api({ + ...profileScoped(), + path: '/api/tools/computer-use/status' + }) +} + +export function grantComputerUsePermissions(): Promise { + return window.hermesDesktop.api({ + ...profileScoped(), + path: '/api/tools/computer-use/permissions/grant', + method: 'POST' + }) +} + export function getMessagingPlatforms(): Promise { return window.hermesDesktop.api({ path: '/api/messaging/platforms' diff --git a/apps/desktop/src/types/hermes.ts b/apps/desktop/src/types/hermes.ts index b67cc3041a7..338ed2d3544 100644 --- a/apps/desktop/src/types/hermes.ts +++ b/apps/desktop/src/types/hermes.ts @@ -579,6 +579,51 @@ export interface ToolsetConfig { active_provider: string | null } +/** Shape of `GET /api/tools/computer-use/status`. + * + * cua-driver runs on macOS, Windows, and Linux. `ready` is the single OS-aware + * readiness signal: on macOS both TCC grants (Accessibility + Screen + * Recording, which attach to cua-driver's own `com.trycua.driver` identity, + * not Hermes); elsewhere, driver health from `cua-driver doctor`. `null` + * means unknown (binary missing / probe failed). */ +export interface ComputerUsePermissionSource { + attribution?: string + executable?: string + note?: string + pid?: number + responsible_ppid?: number +} + +export interface ComputerUseCheck { + label: string + status: string + message: string +} + +export interface ComputerUseStatus { + /** `sys.platform`: "darwin" | "win32" | "linux" | ... */ + platform: string + /** cua-driver has a runtime backend for this platform. */ + platform_supported: boolean + /** cua-driver binary resolved on PATH. */ + installed: boolean + /** e.g. "cua-driver 0.5.1", or null when unknown. */ + version: string | null + /** Unified readiness — both TCC grants (macOS) or driver health (else). */ + ready: boolean | null + /** Whether a permission grant flow exists (macOS-only TCC). */ + can_grant: boolean + /** Cross-platform `cua-driver doctor` probes. */ + checks: ComputerUseCheck[] + /** macOS TCC detail — `null` off macOS or when unknown. */ + accessibility: boolean | null + screen_recording: boolean | null + screen_recording_capturable: boolean | null + source: ComputerUsePermissionSource | null + /** Populated when the status probe itself failed. */ + error: string | null +} + export interface SessionSearchResult { /** Lineage root of the matched conversation. Stable across compression and * used as the durable pin id; falls back to session_id when absent. */ diff --git a/hermes_cli/main.py b/hermes_cli/main.py index 4b1a3f64db2..9c0d53247f3 100644 --- a/hermes_cli/main.py +++ b/hermes_cli/main.py @@ -12507,6 +12507,33 @@ def main(): action="store_true", help="Emit the raw structured payload as JSON (same shape as `tools/call`).", ) + computer_use_perms = computer_use_sub.add_parser( + "permissions", + help="Check or grant macOS Accessibility + Screen Recording (macOS)", + description=( + "Computer Use drives the Mac through cua-driver, whose TCC grants\n" + "attach to cua-driver's own identity (com.trycua.driver) — not the\n" + "terminal or the Hermes app. `status` reports the driver's grant\n" + "state; `grant` launches CuaDriver via LaunchServices so the macOS\n" + "permission dialog is attributed to the process that does the work." + ), + ) + computer_use_perms_sub = computer_use_perms.add_subparsers( + dest="computer_use_perms_action" + ) + computer_use_perms_status = computer_use_perms_sub.add_parser( + "status", + help="Report Accessibility + Screen Recording grant state (read-only)", + ) + computer_use_perms_status.add_argument( + "--json", + action="store_true", + help="Emit the normalized permission payload as JSON.", + ) + computer_use_perms_sub.add_parser( + "grant", + help="Request the grants (opens the dialog attributed to CuaDriver)", + ) def cmd_computer_use(args): action = getattr(args, "computer_use_action", None) @@ -12564,6 +12591,41 @@ def main(): json_output=bool(getattr(args, "json", False)), ) sys.exit(code) + if action == "permissions": + perms_action = getattr(args, "computer_use_perms_action", None) + if perms_action == "grant": + from tools.computer_use.permissions import request_permissions_grant + sys.exit(request_permissions_grant()) + if perms_action == "status": + import json as _json + from tools.computer_use.permissions import computer_use_status + st = computer_use_status() + if bool(getattr(args, "json", False)): + print(_json.dumps(st, indent=2, sort_keys=True)) + sys.exit(0 if st["ready"] else 1) + if not st["platform_supported"]: + print(f"Computer Use is not supported on {st['platform']}.") + sys.exit(1) + if not st["installed"]: + print("cua-driver: not installed. Run: hermes computer-use install") + sys.exit(1) + glyph = lambda v: "✅" if v is True else ("❌" if v is False else "•") # noqa: E731 + print(f"cua-driver: {st['version'] or 'installed'} ({st['platform']})") + if st["can_grant"]: # macOS TCC permissions + print(f" {glyph(st['accessibility'])} Accessibility") + print(f" {glyph(st['screen_recording'])} Screen Recording") + if not st["ready"]: + print(" Grant: hermes computer-use permissions grant") + else: # no TCC model — readiness is driver health + print(f" {glyph(st['ready'])} driver health (no permission toggles on {st['platform']})") + for c in st["checks"]: + if c["status"] != "ok": + print(f" ⚠ {c['label']}: {c['message']}") + if st["error"]: + print(f" ⚠ {st['error']}") + sys.exit(0 if st["ready"] else 1) + computer_use_perms.print_help() + return # No subcommand → show help computer_use_parser.print_help() diff --git a/hermes_cli/web_server.py b/hermes_cli/web_server.py index 997803b8f0a..c6a6b065589 100644 --- a/hermes_cli/web_server.py +++ b/hermes_cli/web_server.py @@ -8349,6 +8349,7 @@ async def install_mcp_catalog_entry(body: MCPCatalogInstall, profile: Optional[s # Register the mcp-install action log so /api/actions/mcp-install/status works. _ACTION_LOG_FILES.setdefault("mcp-install", "action-mcp-install.log") +_ACTION_LOG_FILES.setdefault("computer-use-grant", "action-computer-use-grant.log") # --------------------------------------------------------------------------- @@ -10671,6 +10672,63 @@ async def run_toolset_post_setup( return {"ok": True, "pid": proc.pid, "name": "tools-post-setup", "key": body.key} +# --------------------------------------------------------------------------- +# Computer Use (cua-driver) — cross-platform readiness + macOS permission grant +# +# cua-driver runs on macOS, Windows, and Linux. The desktop card reflects +# per-OS readiness: on macOS the Accessibility + Screen Recording TCC grants +# (which attach to cua-driver's OWN identity, com.trycua.driver — not Hermes, +# so no app entitlement is involved); elsewhere, driver health from +# `cua-driver doctor`. The grant flow is macOS-only (no TCC toggles to request +# on Windows/Linux). +# --------------------------------------------------------------------------- + + +@app.get("/api/tools/computer-use/status") +async def get_computer_use_status(profile: Optional[str] = None): + """Cross-platform Computer Use readiness for the desktop card. + + See ``tools.computer_use.permissions.computer_use_status`` for the payload + shape. Read-only and fast (shells ``cua-driver doctor`` + macOS + ``permissions status``). + """ + from tools.computer_use.permissions import computer_use_status + + with _profile_scope(profile): + return computer_use_status() + + +@app.post("/api/tools/computer-use/permissions/grant") +async def grant_computer_use_permissions(profile: Optional[str] = None): + """Spawn ``hermes computer-use permissions grant`` as a background action. + + macOS-only: ``cua-driver permissions grant`` launches CuaDriver via + LaunchServices so the TCC dialog is attributed to com.trycua.driver, then + waits for approval. The frontend polls ``GET /api/actions/computer-use- + grant/status`` and re-reads ``/status`` once it exits. Windows/Linux have + no TCC toggles to grant, so this returns 400 there. + """ + if sys.platform != "darwin": + raise HTTPException( + status_code=400, + detail="Computer Use permission grants are a macOS concept.", + ) + try: + proc = _spawn_hermes_action( + _profile_cli_args(profile) + + ["computer-use", "permissions", "grant"], + "computer-use-grant", + ) + except HTTPException: + raise + except Exception as exc: + _log.exception("Failed to spawn computer-use permissions grant") + raise HTTPException( + status_code=500, detail=f"Failed to request permissions: {exc}" + ) + return {"ok": True, "pid": proc.pid, "name": "computer-use-grant"} + + # --------------------------------------------------------------------------- # Raw YAML config endpoint # --------------------------------------------------------------------------- diff --git a/tools/computer_use/permissions.py b/tools/computer_use/permissions.py new file mode 100644 index 00000000000..ab97b60ee66 --- /dev/null +++ b/tools/computer_use/permissions.py @@ -0,0 +1,189 @@ +""" +Cross-platform Computer Use readiness + macOS permission helpers. + +cua-driver runs on macOS, Windows, and Linux, but "ready to drive" means +something different on each: + + * macOS — explicit TCC grants (Accessibility + Screen Recording). cua-driver + reports/requests them via ``permissions status`` / ``permissions grant``. + The grants attach to cua-driver's OWN identity (``com.trycua.driver`` / + the installed ``CuaDriver.app``), NOT Hermes — so no Hermes entitlement is + involved, and ``grant`` launches CuaDriver via LaunchServices so the macOS + dialog is attributed correctly. + * Windows — no TCC toggles; the UIAccess worker (``cua-driver-uia.exe``) may + trip a SmartScreen prompt on first run. Readiness == driver health. + * Linux — assistive control via the X11/XWayland stack. Readiness == driver + health. + +The universal signal on every platform is ``cua-driver doctor --json`` (binary +integrity + platform support). ``computer_use_status`` folds that together with +the macOS permission detail into one payload for the desktop card, the +``hermes computer-use permissions`` CLI, and ``/api/tools/computer-use/status``. +""" + +from __future__ import annotations + +import json +import os +import shutil +import subprocess +import sys +from typing import Any, Dict, List, Optional + +# Platforms with a cua-driver runtime backend (mirrors the toolset platform_gate). +_RUNTIME_PLATFORMS = frozenset({"darwin", "win32", "linux"}) +_BOOLS = ("accessibility", "screen_recording", "screen_recording_capturable") + + +def _driver_cmd(override: Optional[str]) -> str: + if override: + return override + try: + from hermes_cli.tools_config import _cua_driver_cmd + + return _cua_driver_cmd() + except Exception: + return os.environ.get("HERMES_CUA_DRIVER_CMD", "").strip() or "cua-driver" + + +def _child_env() -> Dict[str, str]: + """cua-driver child env honoring the Hermes telemetry opt-in policy.""" + try: + from tools.computer_use.cua_backend import cua_driver_child_env + + return cua_driver_child_env() + except Exception: + return dict(os.environ) + + +def _run(binary: str, *args: str, timeout: float) -> subprocess.CompletedProcess: + return subprocess.run( + [binary, *args], + capture_output=True, + text=True, + timeout=timeout, + env=_child_env(), + stdin=subprocess.DEVNULL, + ) + + +def _json_out(binary: str, *args: str, timeout: float) -> Any: + """Run ``binary args`` and parse stdout as JSON, or ``None`` on any failure.""" + raw = (_run(binary, *args, timeout=timeout).stdout or "").strip() + return json.loads(raw) if raw else None + + +def _doctor(binary: str) -> Optional[Dict[str, Any]]: + """``cua-driver doctor --json`` → ``{ok, checks:[{label,status,message}]}``.""" + try: + data = _json_out(binary, "doctor", "--json", timeout=12) + except Exception: + return None + if not isinstance(data, dict): + return None + checks: List[Dict[str, str]] = [ + { + "label": str(p.get("label", "")), + "status": str(p.get("status", "")), + "message": str(p.get("message", "")), + } + for p in data.get("probes", []) + if isinstance(p, dict) + ] + return {"ok": bool(data.get("ok")), "checks": checks} + + +def _mac_permissions(binary: str, out: Dict[str, Any]) -> None: + """Fold ``cua-driver permissions status --json`` booleans into ``out``.""" + try: + data = _json_out(binary, "permissions", "status", "--json", timeout=10) + except subprocess.TimeoutExpired: + out["error"] = "cua-driver permissions status timed out" + return + except Exception as exc: # spawn failure or malformed JSON + out["error"] = f"cua-driver permissions status failed: {exc}" + return + if isinstance(data, dict): + out.update({k: data[k] for k in _BOOLS if isinstance(data.get(k), bool)}) + if isinstance(data.get("source"), dict): + out["source"] = data["source"] + + +def computer_use_status(driver_cmd: Optional[str] = None) -> Dict[str, Any]: + """Unified, OS-aware Computer Use readiness for the desktop card. + + ``ready`` is the single signal the UI keys off: on macOS it's both TCC + grants; elsewhere it's driver health (no TCC model). ``None`` means + unknown (binary missing / probe failed). ``can_grant`` is macOS-only. + """ + plat = sys.platform + binary = shutil.which(_driver_cmd(driver_cmd)) + out: Dict[str, Any] = { + "platform": plat, + "platform_supported": plat in _RUNTIME_PLATFORMS, + "installed": bool(binary), + "version": None, + "ready": None, + "can_grant": plat == "darwin", + "checks": [], + "source": None, + "error": None, + **{k: None for k in _BOOLS}, + } + if not binary: + return out + + try: + out["version"] = (_run(binary, "--version", timeout=5).stdout or "").strip() or None + except Exception: + pass + + doctor = _doctor(binary) + if doctor is not None: + out["checks"] = doctor["checks"] + + if plat == "darwin": + _mac_permissions(binary, out) + if out["error"] is None: + out["ready"] = out["accessibility"] is True and out["screen_recording"] is True + elif doctor is not None: + # No TCC model off macOS — readiness is driver health. + out["ready"] = doctor["ok"] + return out + + +def request_permissions_grant(driver_cmd: Optional[str] = None) -> int: + """Run ``cua-driver permissions grant`` (macOS); stream its output. + + Launches CuaDriver via LaunchServices so the TCC dialog is attributed to + ``com.trycua.driver``, then waits for the grant. Returns the driver's exit + code (0 ok), 2 if the binary is missing, 64 on a non-macOS platform (which + has no TCC permission model to grant). + """ + if sys.platform != "darwin": + print("Computer Use permissions are a macOS concept; nothing to grant here.") + return 64 + + binary = shutil.which(_driver_cmd(driver_cmd)) + if not binary: + print("cua-driver: not installed. Run: hermes computer-use install") + return 2 + + print( + "Requesting Accessibility + Screen Recording for CuaDriver.\n" + "macOS will show a dialog attributed to CuaDriver (com.trycua.driver) — " + "approve it, then return here." + ) + try: + return int( + subprocess.run( + [binary, "permissions", "grant"], + env=_child_env(), + stdin=subprocess.DEVNULL, + ).returncode + ) + except KeyboardInterrupt: # pragma: no cover - interactive + return 130 + except Exception as exc: # pragma: no cover - defensive + print(f"cua-driver permissions grant failed: {exc}", file=sys.stderr) + return 2