feat: discover and add connected iOS devices

apps/device-host-agent/host_agent/ios_discovery.py

@@ -0,0 +1,79 @@
+from __future__ import annotations
+
+import json
+import subprocess
+import tempfile
+from pathlib import Path
+from typing import Any
+
+
+class IOSDiscoveryError(RuntimeError):
+    pass
+
+
+def discover_connected_ios_devices(*, timeout_seconds: int = 10) -> list[dict[str, str]]:
+    """Return paired, currently connected physical iOS devices from CoreDevice."""
+    with tempfile.TemporaryDirectory(prefix="ios-device-discovery-") as temp_dir:
+        output_path = Path(temp_dir) / "devices.json"
+        try:
+            completed = subprocess.run(
+                [
+                    "xcrun",
+                    "devicectl",
+                    "list",
+                    "devices",
+                    "--json-output",
+                    str(output_path),
+                    "--timeout",
+                    str(timeout_seconds),
+                    "--quiet",
+                ],
+                capture_output=True,
+                text=True,
+                timeout=timeout_seconds + 2,
+                check=False,
+            )
+        except FileNotFoundError as exc:
+            raise IOSDiscoveryError("xcrun is unavailable; install Xcode command line tools") from exc
+        except subprocess.TimeoutExpired as exc:
+            raise IOSDiscoveryError("iOS device discovery timed out") from exc
+
+        if completed.returncode != 0:
+            detail = completed.stderr.strip() or completed.stdout.strip()
+            raise IOSDiscoveryError(detail or "devicectl failed to discover iOS devices")
+        try:
+            payload = json.loads(output_path.read_text(encoding="utf-8"))
+        except (OSError, ValueError) as exc:
+            raise IOSDiscoveryError("devicectl returned invalid device data") from exc
+
+    raw_devices = payload.get("result", {}).get("devices", [])
+    devices: list[dict[str, str]] = []
+    for item in raw_devices if isinstance(raw_devices, list) else []:
+        if not isinstance(item, dict):
+            continue
+        hardware = item.get("hardwareProperties", {})
+        properties = item.get("deviceProperties", {})
+        connection = item.get("connectionProperties", {})
+        if not all(isinstance(value, dict) for value in (hardware, properties, connection)):
+            continue
+        udid = hardware.get("udid")
+        if (
+            hardware.get("platform") != "iOS"
+            or hardware.get("reality") != "physical"
+            or connection.get("pairingState") != "paired"
+            or connection.get("tunnelState") != "connected"
+            or not isinstance(udid, str)
+            or not udid
+        ):
+            continue
+        devices.append(
+            {
+                "udid": udid,
+                "name": str(properties.get("name") or hardware.get("marketingName") or "iPhone"),
+                "model": str(hardware.get("marketingName") or hardware.get("productType") or "iPhone"),
+                "os_version": str(properties.get("osVersionNumber") or ""),
+                "transport": str(connection.get("transportType") or "unknown"),
+            }
+        )
+    return sorted(devices, key=lambda device: (device["name"], device["udid"]))
+

apps/device-host-agent/host_agent/web/app.py

@@ -13,6 +13,7 @@ from fastapi.responses import HTMLResponse, JSONResponse, RedirectResponse, Resp
 
 from core.errors import DeviceNotFoundError, DeviceOfflineError, DeviceRuntimeError
 from device.manager import DeviceManager
+from driver.registry import build_driver_factory
 from host_agent.assignment import AssignmentExecutor
 from host_agent.client import (
     HostAgentClient,
@@ -26,6 +27,7 @@ from host_agent.conversation_log import ConversationLogStore
 from host_agent.devices import register_local_device, unregister_local_device
 from host_agent.history import ConsoleHistoryStore
 from host_agent.identity import HostIdentityStore
+from host_agent.ios_discovery import IOSDiscoveryError, discover_connected_ios_devices
 from host_agent.local_account import LocalAccountStore
 from host_agent.mcp_lock import McpBusyTracker
 from host_agent.mcp_token import McpTokenStore
@@ -526,6 +528,87 @@ def create_console_app(
             },
         )
 
+    @app.get("/api/devices/discover-ios")
+    async def api_discover_ios_devices(
+        session: SessionState = Depends(require_session),
+    ) -> JSONResponse:
+        try:
+            discovered = await asyncio.to_thread(discover_connected_ios_devices)
+        except IOSDiscoveryError as exc:
+            raise HTTPException(status_code=502, detail=str(exc)) from exc
+
+        configured = await asyncio.to_thread(config_store.list)
+        configured_udids = {
+            str(record["connection_info"].get("udid"))
+            for record in configured
+            if record["driver_type"] == "wda"
+        }
+        used_wda_ports = {
+            record["connection_info"].get("wda_local_port") for record in configured
+        }
+        used_mjpeg_ports = {
+            record["connection_info"].get("mjpegServerPort") for record in configured
+        }
+        next_wda_port = 8100
+        next_mjpeg_port = 9100
+        result = []
+        for device in discovered:
+            while next_wda_port in used_wda_ports:
+                next_wda_port += 1
+            while next_mjpeg_port in used_mjpeg_ports:
+                next_mjpeg_port += 1
+            result.append(
+                {
+                    **device,
+                    "configured": device["udid"] in configured_udids,
+                    "suggested_wda_port": next_wda_port,
+                    "suggested_mjpeg_port": next_mjpeg_port,
+                }
+            )
+            used_wda_ports.add(next_wda_port)
+            used_mjpeg_ports.add(next_mjpeg_port)
+            next_wda_port += 1
+            next_mjpeg_port += 1
+        return JSONResponse({"devices": result})
+
+    @app.post("/api/devices/test-connection")
+    async def api_device_test_connection(
+        request: Request,
+        session: SessionState = Depends(require_csrf),
+    ) -> JSONResponse:
+        payload = await request.json()
+        if not isinstance(payload, dict):
+            raise HTTPException(status_code=400, detail="Request must be an object.")
+        driver_type = str(payload.get("driver_type", "")).strip()
+        connection_info = payload.get("connection_info")
+        if not driver_type or not isinstance(connection_info, dict):
+            raise HTTPException(
+                status_code=400,
+                detail="Driver type and connection info are required.",
+            )
+
+        driver = None
+        connected = False
+        try:
+            driver = build_driver_factory(driver_type, connection_info)()
+            await asyncio.to_thread(driver.connect)
+            connected = True
+            await asyncio.to_thread(driver.health_check)
+        except ValueError as exc:
+            raise HTTPException(status_code=400, detail=str(exc)) from exc
+        except Exception as exc:
+            raise HTTPException(
+                status_code=502,
+                detail=str(exc) or "device connection test failed",
+            ) from exc
+        finally:
+            if connected and driver is not None:
+                try:
+                    await asyncio.to_thread(driver.disconnect)
+                except Exception:
+                    pass
+        return JSONResponse({"ok": True, "driver_type": driver_type})
+
     @app.post("/devices/save")
     async def devices_save(
         request: Request,
@@ -552,6 +635,26 @@ def create_console_app(
                 else:
                     connection_info = parsed
 
+        if error is None:
+            # The console exposes the common Appium settings as regular form
+            # fields. Advanced JSON remains available for uncommon capabilities.
+            field_map = {
+                "server_url": "server_url",
+                "udid": "udid",
+                "device_name": "device_name",
+            }
+            for form_key, config_key in field_map.items():
+                value = str(form.get(form_key, "")).strip()
+                if value:
+                    connection_info[config_key] = value
+            port_key = "wda_local_port" if driver_type == "wda" else "system_port"
+            port_value = str(form.get(port_key, "")).strip()
+            if port_value:
+                try:
+                    connection_info[port_key] = int(port_value)
+                except ValueError:
+                    error = f"{port_key} must be an integer."
+
         if error is None:
             try:
                 await asyncio.to_thread(

apps/device-host-agent/host_agent/web/templates/devices.html

@@ -31,14 +31,30 @@
         {% endfor %}</tbody>
     </table>
     <h2>{{ "Edit device" if edit_record else "Add device" }}</h2>
+    <button type="button" id="discover-ios">Scan connected iPhones</button>
+    <p id="discovery-status" class="screenshot-status"></p>
+    <div id="discovered-devices"></div>
     <form method="post" action="/devices/save">
       <input type="hidden" name="csrf_token" value="{{ csrf_token }}">
       <label>Device ID <input type="text" name="device_id" value="{{ edit_record["device_id"] if edit_record else "" }}" required></label><br>
       <label>Name <input type="text" name="name" value="{{ edit_record["name"] if edit_record else "" }}"></label><br>
-      <label>Driver type <input type="text" name="driver_type" value="{{ edit_record["driver_type"] if edit_record else "wda" }}" required></label><br>
-      <label>Connection info (JSON)<br>
-        <textarea name="connection_info" rows="3" cols="50">{{ connection_info_json }}</textarea>
+      <label>Platform and protocol
+        <select name="driver_type" id="driver-type" required>
+          <option value="wda"{% if not edit_record or edit_record["driver_type"] == "wda" %} selected{% endif %}>iOS - Appium / XCUITest (WDA)</option>
+          <option value="uiautomator2"{% if edit_record and edit_record["driver_type"] == "uiautomator2" %} selected{% endif %}>Android - Appium / UiAutomator2</option>
+        </select>
       </label><br>
+      <label>Appium server URL <input type="url" name="server_url" value="{{ edit_record["connection_info"].get("server_url", "http://127.0.0.1:4723") if edit_record else "http://127.0.0.1:4723" }}" required></label><br>
+      <label>Device UDID <input type="text" name="udid" value="{{ edit_record["connection_info"].get("udid", "") if edit_record else "" }}" required></label><br>
+      <label>Device name <input type="text" name="device_name" value="{{ edit_record["connection_info"].get("device_name", "") if edit_record else "" }}" placeholder="iPhone"></label><br>
+      <label class="ios-setting">WDA local port <input type="number" min="1" max="65535" name="wda_local_port" value="{{ edit_record["connection_info"].get("wda_local_port", "") if edit_record else "" }}" placeholder="8100"></label>
+      <label class="android-setting">UiAutomator2 system port <input type="number" min="1" max="65535" name="system_port" value="{{ edit_record["connection_info"].get("system_port", "") if edit_record else "" }}" placeholder="8200"></label><br>
+      <details>
+        <summary>Advanced connection capabilities (JSON)</summary>
+        <textarea name="connection_info" rows="4" cols="60">{{ connection_info_json }}</textarea>
+      </details>
+      <p id="connection-test-status" class="screenshot-status"></p>
+      <button type="button" id="test-connection">Test connection</button>
       <button type="submit">Save</button>
     </form>
     <style>
@@ -49,8 +65,100 @@
     </style>
     <script>
       (() => {
+        const driverType = document.getElementById("driver-type");
+        const syncPlatformFields = () => {
+          const ios = driverType.value === "wda";
+          document.querySelectorAll(".ios-setting").forEach((el) => { el.hidden = !ios; });
+          document.querySelectorAll(".android-setting").forEach((el) => { el.hidden = ios; });
+        };
+        driverType.addEventListener("change", syncPlatformFields);
+        syncPlatformFields();
         const csrfInput = document.querySelector('input[name="csrf_token"]');
         const csrfToken = csrfInput ? csrfInput.value : "";
+        const form = document.querySelector('form[action="/devices/save"]');
+        const discoverButton = document.getElementById("discover-ios");
+        const discoveryStatus = document.getElementById("discovery-status");
+        const discoveredDevices = document.getElementById("discovered-devices");
+        discoverButton.addEventListener("click", async () => {
+          discoverButton.disabled = true;
+          discoveryStatus.classList.remove("error");
+          discoveryStatus.textContent = "Scanning...";
+          discoveredDevices.replaceChildren();
+          try {
+            const response = await fetch("/api/devices/discover-ios");
+            const payload = await response.json();
+            if (!response.ok) throw new Error(payload.detail || "Discovery failed.");
+            discoveryStatus.textContent = payload.devices.length
+              ? `Found ${payload.devices.length} connected iPhone(s).`
+              : "No connected, paired iPhones found.";
+            payload.devices.forEach((device, index) => {
+              const row = document.createElement("p");
+              const description = document.createElement("span");
+              description.textContent = `${device.name} - ${device.model} - iOS ${device.os_version} (${device.transport}) `;
+              const select = document.createElement("button");
+              select.type = "button";
+              select.textContent = device.configured ? "Already added" : "Use this iPhone";
+              select.disabled = device.configured;
+              select.addEventListener("click", () => {
+                form.elements.driver_type.value = "wda";
+                form.elements.udid.value = device.udid;
+                form.elements.device_name.value = device.name;
+                form.elements.wda_local_port.value = device.suggested_wda_port;
+                form.elements.device_id.value ||= `ios-phone-${index + 1}`;
+                form.elements.name.value ||= device.name;
+                const advanced = JSON.parse(form.elements.connection_info.value || "{}");
+                advanced.mjpegServerPort = device.suggested_mjpeg_port;
+                advanced.derivedDataPath = `/tmp/wda-${device.udid}`;
+                form.elements.connection_info.value = JSON.stringify(advanced, null, 2);
+                syncPlatformFields();
+                form.scrollIntoView({ behavior: "smooth", block: "start" });
+              });
+              row.append(description, select);
+              discoveredDevices.append(row);
+            });
+          } catch (error) {
+            discoveryStatus.classList.add("error");
+            discoveryStatus.textContent = error.message || "Discovery failed.";
+          } finally {
+            discoverButton.disabled = false;
+          }
+        });
+        const testButton = document.getElementById("test-connection");
+        const testStatus = document.getElementById("connection-test-status");
+        const connectionInfo = () => {
+          const data = new FormData(form);
+          let info = {};
+          const advanced = String(data.get("connection_info") || "{}");
+          info = JSON.parse(advanced);
+          ["server_url", "udid", "device_name"].forEach((key) => {
+            const value = String(data.get(key) || "").trim();
+            if (value) info[key] = value;
+          });
+          const portKey = data.get("driver_type") === "wda" ? "wda_local_port" : "system_port";
+          const port = String(data.get(portKey) || "").trim();
+          if (port) info[portKey] = Number(port);
+          return { driver_type: data.get("driver_type"), connection_info: info };
+        };
+        testButton.addEventListener("click", async () => {
+          testButton.disabled = true;
+          testStatus.classList.remove("error");
+          testStatus.textContent = "Testing connection...";
+          try {
+            const response = await fetch("/api/devices/test-connection", {
+              method: "POST",
+              headers: { "Content-Type": "application/json", "X-CSRF-Token": csrfToken },
+              body: JSON.stringify(connectionInfo()),
+            });
+            const payload = await response.json();
+            if (!response.ok) throw new Error(payload.detail || "Connection test failed.");
+            testStatus.textContent = "Connection successful.";
+          } catch (error) {
+            testStatus.classList.add("error");
+            testStatus.textContent = error.message || "Connection test failed.";
+          } finally {
+            testButton.disabled = false;
+          }
+        });
         document.querySelectorAll(".screenshot-button").forEach((button) => {
           button.addEventListener("click", async () => {
             const deviceId = button.dataset.deviceId;