feat: discover and add connected iOS devices

README.md

@@ -125,6 +125,11 @@ and final replies in a local SQLite database. View them at
 `http://127.0.0.1:8765/conversations`; image bytes are excluded. Set
 `HOST_AGENT_CONVERSATION_LOG_PATH` to change the database path.
 
+The authenticated `Devices` page has an on-demand `Get screenshot` button for
+each connected device. Screenshots are captured only after the operator clicks
+the button; the page does not auto-refresh or capture screenshots as part of
+heartbeat synchronization.
+
 In local mode, Appium supervision is enabled by default. Host Agent probes
 `/status`, adopts a healthy existing Appium instance, starts Appium when no
 listener exists, restarts only processes it started if they crash, and stops

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

@@ -231,12 +231,14 @@ def create_application(
                 "MCP token generated at %s", mcp_token_path
             )
         mcp_busy_tracker = McpBusyTracker(ttl_seconds=20.0)
+        conversation_log = ConversationLogStore(resolved_config.conversation_log_path) if resolved_config.mode == "local" else None
         executor = AssignmentExecutor(
             create_execution_factories(
                 resolved_manager,
                 metadata_store=metadata_store,
                 timeline=timeline,
                 host_agent_config=resolved_config,
+                conversation_log=conversation_log,
             ),
             mcp_busy_tracker=mcp_busy_tracker,
         )
@@ -246,7 +248,6 @@ def create_application(
             status_tracker=status_tracker,
         )
         planner_config = load_planner_config()
-        conversation_log = ConversationLogStore(resolved_config.conversation_log_path) if resolved_config.mode == "local" else None
         conversation_agent = (
             ConversationAgent(
                 config=planner_config,

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

@@ -62,11 +62,13 @@ class CloudProxyToolCallingClient:
         screenshot: bytes | None,
         tools: list[ToolSpec],
         timeout: float,
+        history: list[dict[str, Any]] | None = None,
     ) -> ToolCallDecision:
         payload: dict[str, Any] = {
             "host_id": self.config.host_id,
             "system_prompt": system_prompt,
             "user_prompt": user_prompt,
+            "history": history or [],
             "screenshot_base64": (
                 base64.b64encode(screenshot).decode("ascii")
                 if screenshot is not None

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

@@ -3,6 +3,7 @@ from __future__ import annotations
 import os
 from collections.abc import Callable
 from dataclasses import dataclass, replace
+from typing import Any
 
 from device.manager import DeviceManager
 from host_agent.cloud_planner_client import CloudProxyToolCallingClient
@@ -35,6 +36,7 @@ def create_execution_factories(
     metadata_store: TaskMetadataStore | None = None,
     timeline: Timeline | None = None,
     host_agent_config: HostAgentConfig | None = None,
+    conversation_log: Any | None = None,
 ) -> ExecutionFactories:
     shared_workflow_store = workflow_store or WorkflowStore()
     resolved_host_agent_config = host_agent_config
@@ -48,7 +50,10 @@ def create_execution_factories(
             ),
             metadata_store=metadata_store,
             timeline=timeline,
-            planner=_host_agent_planner(resolved_host_agent_config),
+            planner=_host_agent_planner(
+                resolved_host_agent_config,
+                event_logger=conversation_log.append if conversation_log is not None else None,
+            ),
             planner_config=_host_agent_planner_config(),
             device_platform_provider=lambda device_id: _device_platform(
                 manager, device_id
@@ -86,6 +91,8 @@ def _host_agent_planner_config() -> PlannerConfig:
 
 def _host_agent_planner(
     host_agent_config: HostAgentConfig | None,
+    *,
+    event_logger: Callable[[dict[str, Any]], None] | None = None,
 ) -> Planner | None:
     """Build the `AIPlanner` explicitly when the cloud-proxy transport is
     selected, so its `ToolCallingClient` is a `CloudProxyToolCallingClient`
@@ -100,11 +107,12 @@ def _host_agent_planner(
 
     resolved_config = host_agent_config or load_host_agent_config()
     if resolved_config.ai_planner_transport != "cloud":
-        return None
+        return AIPlanner(config=planner_config, event_logger=event_logger)
 
     return AIPlanner(
         client=CloudProxyToolCallingClient(resolved_config),
         config=planner_config,
+        event_logger=event_logger,
     )
 
 

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

@@ -11,7 +11,9 @@ import jinja2
 from fastapi import Depends, FastAPI, HTTPException, Request
 from fastapi.responses import HTMLResponse, JSONResponse, RedirectResponse, Response
 
+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,
@@ -25,6 +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
@@ -488,6 +491,124 @@ def create_console_app(
             error=None,
         )
 
+    @app.post("/api/devices/{device_id}/screenshot")
+    async def api_device_screenshot(
+        device_id: str,
+        session: SessionState = Depends(require_csrf),
+    ) -> Response:
+        """Capture one on-demand screenshot for a connected local device."""
+        try:
+            screenshot = await asyncio.to_thread(
+                lambda: manager.active_driver(device_id).screenshot()
+            )
+        except DeviceNotFoundError as exc:
+            raise HTTPException(status_code=404, detail=str(exc)) from exc
+        except DeviceOfflineError as exc:
+            raise HTTPException(status_code=503, detail=str(exc)) from exc
+        except DeviceRuntimeError as exc:
+            raise HTTPException(status_code=502, detail=str(exc)) from exc
+        except Exception as exc:
+            raise HTTPException(
+                status_code=502,
+                detail=str(exc) or "failed to capture device screenshot",
+            ) from exc
+
+        if not isinstance(screenshot, bytes) or not screenshot:
+            raise HTTPException(
+                status_code=502,
+                detail="device returned an empty screenshot",
+            )
+        return Response(
+            content=screenshot,
+            media_type="image/png",
+            headers={
+                "Cache-Control": "no-store",
+                "Pragma": "no-cache",
+                "X-Content-Type-Options": "nosniff",
+            },
+        )
+
+    @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,
@@ -514,6 +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

@@ -5,13 +5,20 @@
     <p class="error">{{ error }}</p>
     {% endif %}
     <table>
-      <thead><tr><th>ID</th><th>Name</th><th>Driver</th><th>Cloud ID</th><th></th></tr></thead>
+      <thead><tr><th>ID</th><th>Name</th><th>Driver</th><th>Cloud ID</th><th>Screenshot</th><th></th></tr></thead>
       <tbody>{% for device in devices %}
         <tr>
           <td>{{ device["device_id"] }}</td>
           <td>{{ device["name"] or "" }}</td>
           <td>{{ device["driver_type"] }}</td>
           <td>{{ device["cloud_device_id"] or "" }}</td>
+          <td>
+            <button type="button" class="screenshot-button" data-device-id="{{ device["device_id"] }}">Get screenshot</button>
+            <div class="screenshot-preview" data-screenshot-preview hidden>
+              <p class="screenshot-status" data-screenshot-status></p>
+              <img alt="Current screen for {{ device["device_id"] }}" data-screenshot-image hidden>
+            </div>
+          </td>
           <td>
             <a href="/devices?edit={{ device["device_id"] }}">Edit</a>
             <form class="inline" method="post" action="/devices/remove">
@@ -24,14 +31,173 @@
         {% 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>Platform and protocol
-      <label>Connection info (JSON)<br>
+        <select name="driver_type" id="driver-type" required>
-        <textarea name="connection_info" rows="3" cols="50">{{ connection_info_json }}</textarea>
+          <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>
+      .screenshot-preview { margin-top: 0.5rem; max-width: 260px; }
+      .screenshot-preview img { display: block; width: 100%; height: auto; border: 1px solid #c8d0d6; }
+      .screenshot-status { margin: 0 0 0.35rem; color: #5e6b73; }
+      .screenshot-status.error { color: #b00020; }
+    </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;
+            const preview = button.parentElement.querySelector("[data-screenshot-preview]");
+            const status = preview.querySelector("[data-screenshot-status]");
+            const image = preview.querySelector("[data-screenshot-image]");
+            const previousUrl = image.dataset.objectUrl;
+            if (previousUrl) URL.revokeObjectURL(previousUrl);
+            button.disabled = true;
+            preview.hidden = false;
+            image.hidden = true;
+            status.classList.remove("error");
+            status.textContent = "Capturing...";
+            try {
+              const response = await fetch(
+                "/api/devices/" + encodeURIComponent(deviceId) + "/screenshot",
+                { method: "POST", headers: { "X-CSRF-Token": csrfToken } }
+              );
+              if (!response.ok) {
+                let detail = "Screenshot failed.";
+                try {
+                  const payload = await response.json();
+                  if (payload.detail) detail = payload.detail;
+                } catch (_) {}
+                throw new Error(detail);
+              }
+              const objectUrl = URL.createObjectURL(await response.blob());
+              image.src = objectUrl;
+              image.dataset.objectUrl = objectUrl;
+              image.hidden = false;
+              status.textContent = "Captured.";
+            } catch (error) {
+              status.classList.add("error");
+              status.textContent = error.message || "Screenshot failed.";
+            } finally {
+              button.disabled = false;
+            }
+          });
+        });
+      })();
+    </script>
 {% endblock %}

apps/device-host-agent/tests/host_agent/web/test_templates.py

@@ -47,6 +47,7 @@ def test_devices_renders(env, sample_session) -> None:
         **make_devices_context(sample_session)
     )
     assert '<form method="post" action="/devices/save">' in html
+    assert 'class="screenshot-button"' in html
 
 
 def test_account_renders(env, sample_session) -> None:

apps/device-host-agent/tests/test_cloud_planner_client.py

@@ -96,6 +96,36 @@ def test_decide_base64_encodes_screenshot() -> None:
     assert body["screenshot_base64"] == "aGVsbG8="
 
 
+def test_decide_forwards_planner_history() -> None:
+    seen_requests: list[httpx.Request] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        seen_requests.append(request)
+        return httpx.Response(200, json={"tool_name": "tap", "arguments": {}})
+
+    client = _client(handler)
+    history = [
+        {
+            "user_prompt": "first screen",
+            "tool_name": "tap",
+            "arguments": {"x": 1, "y": 2},
+            "rationale": "Open it.",
+            "tool_result": {"success": True},
+        }
+    ]
+
+    client.decide(
+        system_prompt="sp",
+        user_prompt="next screen",
+        screenshot=None,
+        tools=_TOOLS,
+        timeout=10.0,
+        history=history,
+    )
+
+    assert json.loads(seen_requests[0].content)["history"] == history
+
+
 def test_decide_clamps_legacy_timeout_and_waits_for_cloud_profile_timeout() -> None:
     seen_requests: list[httpx.Request] = []
 

apps/device-host-agent/tests/test_web_app.py

@@ -242,6 +242,147 @@ def test_add_device_appears_in_devices_page_and_manager(tmp_path) -> None:
     assert [device.id for device in context["manager"].list_devices()] == ["device-a"]
 
 
+def test_devices_page_captures_screenshot_only_when_button_endpoint_is_called(
+    tmp_path,
+) -> None:
+    class ScreenshotDriver:
+        def __init__(self) -> None:
+            self.capture_count = 0
+
+        def connect(self) -> None:
+            pass
+
+        def disconnect(self) -> None:
+            pass
+
+        def screenshot(self) -> bytes:
+            self.capture_count += 1
+            return b"fake-png"
+
+    driver = ScreenshotDriver()
+    client, context = _build_client(tmp_path)
+    context["config_store"].add(
+        device_id="device-a",
+        name="Lab iPhone",
+        driver_type="wda",
+        connection_info={},
+    )
+    context["manager"].register_device("device-a", lambda: driver)
+    context["manager"].connect("device-a")
+    csrf_token = _login(client)
+
+    page = client.get("/devices")
+    assert page.status_code == 200
+    assert 'class="screenshot-button"' in page.text
+    assert 'data-device-id="device-a"' in page.text
+    assert driver.capture_count == 0
+
+    response = client.post(
+        "/api/devices/device-a/screenshot",
+        headers={"X-CSRF-Token": csrf_token},
+    )
+
+    assert response.status_code == 200
+    assert response.content == b"fake-png"
+    assert response.headers["content-type"] == "image/png"
+    assert response.headers["cache-control"] == "no-store"
+    assert driver.capture_count == 1
+
+
+def test_device_screenshot_requires_csrf_and_connected_device(tmp_path) -> None:
+    class ScreenshotDriver:
+        def connect(self) -> None:
+            pass
+
+        def disconnect(self) -> None:
+            pass
+
+        def screenshot(self) -> bytes:
+            return b"fake-png"
+
+    client, context = _build_client(tmp_path)
+    context["manager"].register_device("device-a", ScreenshotDriver)
+    csrf_token = _login(client)
+
+    missing_csrf = client.post("/api/devices/device-a/screenshot")
+    assert missing_csrf.status_code == 403
+
+    offline = client.post(
+        "/api/devices/device-a/screenshot",
+        headers={"X-CSRF-Token": csrf_token},
+    )
+    assert offline.status_code == 503
+
+
+def test_device_connection_test_connects_checks_health_and_disconnects(
+    tmp_path, monkeypatch
+) -> None:
+    events: list[str] = []
+
+    class ProbeDriver:
+        def connect(self) -> None:
+            events.append("connect")
+
+        def health_check(self) -> None:
+            events.append("health")
+
+        def disconnect(self) -> None:
+            events.append("disconnect")
+
+    def factory(driver_type, connection_info):
+        assert driver_type == "wda"
+        assert connection_info["udid"] == "ios-udid"
+        return ProbeDriver
+
+    monkeypatch.setattr("host_agent.web.app.build_driver_factory", factory)
+    client, context = _build_client(tmp_path)
+    csrf_token = _login(client)
+
+    response = client.post(
+        "/api/devices/test-connection",
+        json={"driver_type": "wda", "connection_info": {"udid": "ios-udid"}},
+        headers={"X-CSRF-Token": csrf_token},
+    )
+
+    assert response.status_code == 200
+    assert response.json() == {"ok": True, "driver_type": "wda"}
+    assert events == ["connect", "health", "disconnect"]
+    assert context["config_store"].list() == []
+
+
+def test_ios_discovery_returns_connected_devices_and_unique_ports(
+    tmp_path, monkeypatch
+) -> None:
+    monkeypatch.setattr(
+        "host_agent.web.app.discover_connected_ios_devices",
+        lambda: [
+            {
+                "udid": "ios-new",
+                "name": "New iPhone",
+                "model": "iPhone 15",
+                "os_version": "18.0",
+                "transport": "wired",
+            }
+        ],
+    )
+    client, context = _build_client(tmp_path)
+    context["config_store"].add(
+        device_id="existing",
+        driver_type="wda",
+        connection_info={"udid": "ios-old", "wda_local_port": 8100, "mjpegServerPort": 9100},
+    )
+    _login(client)
+
+    response = client.get("/api/devices/discover-ios")
+
+    assert response.status_code == 200
+    device = response.json()["devices"][0]
+    assert device["udid"] == "ios-new"
+    assert device["configured"] is False
+    assert device["suggested_wda_port"] == 8101
+    assert device["suggested_mjpeg_port"] == 9101
+
+
 def test_remove_device_unregisters_from_manager(tmp_path) -> None:
     client, context = _build_client(tmp_path)
     csrf_token = _login(client)

device/manager.py

@@ -130,7 +130,13 @@ class DeviceManager:
             if driver is None:
                 return False
         try:
-            driver.screenshot()
+            health_check = getattr(driver, "health_check", None)
+            if callable(health_check):
+                health_check()
+            else:
+                # Compatibility for drivers implemented before health_check
+                # existed. Built-in drivers use the non-screen health check.
+                driver.screenshot()
         except Exception:
             self.mark_error(device_id, offline=True)
             return False

driver/android_driver.py

@@ -81,6 +81,13 @@ class AndroidDriver(Driver):
         except Exception as exc:
             raise DriverError("screenshot failed") from exc
 
+    def health_check(self) -> None:
+        client = self._require_client()
+        try:
+            client.get_status()
+        except Exception as exc:
+            raise DriverError("health check failed") from exc
+
     def tap(self, x: float, y: float) -> None:
         client = self._require_client()
         try:

driver/base.py

@@ -25,6 +25,15 @@ class Driver(ABC):
     def screenshot(self) -> bytes:
         """Return the current screen as image bytes."""
 
+    def health_check(self) -> None:
+        """Verify the live session without reading the device screen.
+
+        Drivers with a transport-level status endpoint should override this
+        method. The default is a no-op for legacy drivers that do not expose
+        a separate health check.
+        """
+        return None
+
     @abstractmethod
     def tap(self, x: float, y: float) -> None:
         """Tap the screen at the given coordinates."""

driver/wda_driver.py

@@ -71,6 +71,13 @@ class WDADriver(Driver):
         except Exception as exc:
             raise DriverError("screenshot failed") from exc
 
+    def health_check(self) -> None:
+        client = self._require_client()
+        try:
+            client.get_status()
+        except Exception as exc:
+            raise DriverError("health check failed") from exc
+
     def tap(self, x: float, y: float) -> None:
         client = self._require_client()
         try:

packages/cloud-platform/cloud/internal_api/api.py

@@ -6,6 +6,7 @@ import json
 import logging
 from collections.abc import Awaitable, Callable
 from datetime import timedelta
+from inspect import Parameter, signature
 from time import monotonic
 from typing import TYPE_CHECKING
 from uuid import uuid4
@@ -505,13 +506,21 @@ def create_internal_router(
 
         started_at = monotonic()
         try:
-            decision = client.decide(
+            decision_kwargs = {
-                system_prompt=payload.system_prompt,
+                "system_prompt": payload.system_prompt,
-                user_prompt=payload.user_prompt,
+                "user_prompt": payload.user_prompt,
-                screenshot=screenshot,
+                "screenshot": screenshot,
-                tools=tools,
+                "tools": tools,
-                timeout=planner_timeout,
+                "timeout": planner_timeout,
-            )
+            }
+            parameters = signature(client.decide).parameters.values()
+            if any(
+                parameter.name == "history"
+                or parameter.kind == Parameter.VAR_KEYWORD
+                for parameter in parameters
+            ):
+                decision_kwargs["history"] = payload.history
+            decision = client.decide(**decision_kwargs)
         except ToolCallUnavailable as exc:
             logger.info(
                 "planner-decision request failed",

packages/cloud-platform/cloud/internal_api/models.py

@@ -143,6 +143,7 @@ class PlannerDecisionRequest(BaseModel):
     host_id: str = Field(min_length=1)
     system_prompt: str
     user_prompt: str
+    history: list[dict[str, Any]] = Field(default_factory=list)
     screenshot_base64: str | None = None
     tools: list[PlannerToolSpecModel] = Field(default_factory=list)
     timeout_seconds: float = Field(default=30.0, gt=0, le=120)

runtime/ai_planner.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from collections.abc import Callable
+from inspect import Parameter, signature
 from typing import TYPE_CHECKING, Any
 
 from core.errors import TaskFailedError
@@ -23,9 +25,11 @@ class AIPlanner(Planner):
         *,
         client: ToolCallingClient | None = None,
         config: PlannerConfig | None = None,
+        event_logger: Callable[[dict[str, Any]], None] | None = None,
     ) -> None:
         self.config = config or load_config()
         self.client = client or build_client(self.config)
+        self.event_logger = event_logger
 
     def plan(
         self,
@@ -36,11 +40,11 @@ class AIPlanner(Planner):
         world: "WorldState | None" = None,
         screenshot: bytes | None = None,
     ) -> list[PlannedStep]:
+        _sync_tool_results(context)
         scene_json = _without_ocr(scene.to_dict()) if self.config.multimodal else scene.to_dict()
         user_prompt = planner_user_prompt(
             goal=goal,
             scene_json=scene_json,
-            history_summary=_history_summary(world),
             device_platform=context.device_platform,
         )
         if context.step_results and not context.step_results[-1].success:
@@ -49,19 +53,45 @@ class AIPlanner(Planner):
                 "corrected action or finish the task if it cannot proceed.\n"
                 f"Previous failure: {context.step_results[-1].error or 'unknown error'}"
             )
-        decision = self.client.decide(
+        self._log({"type": "llm_request", "task_id": context.task_id, "goal": goal,
-            system_prompt=PLANNER_SYSTEM_PROMPT,
+                   "system_prompt": PLANNER_SYSTEM_PROMPT, "user_prompt": user_prompt,
-            user_prompt=user_prompt,
+                   "has_screenshot": screenshot is not None})
-            screenshot=screenshot,
+        try:
-            tools=ALL_TOOL_SPECS,
+            kwargs = {
-            timeout=self.config.timeout,
+                "system_prompt": PLANNER_SYSTEM_PROMPT,
-        )
+                "user_prompt": user_prompt,
+                "screenshot": screenshot,
+                "tools": ALL_TOOL_SPECS,
+                "timeout": self.config.timeout,
+            }
+            if _accepts_history(self.client.decide):
+                kwargs["history"] = context.planner_history[
+                    -self.config.history_max_turns :
+                ]
+            decision = self.client.decide(**kwargs)
+        except Exception as exc:
+            self._log({"type": "agent_error", "task_id": context.task_id, "error": str(exc)})
+            raise
+        self._log({"type": "llm_response", "task_id": context.task_id,
+                   "content": decision.text_output, "thinking": decision.thinking,
+                   "tool_name": decision.tool_name, "arguments": decision.arguments,
+                   "purpose": decision.purpose, "expected_outcome": decision.expected_outcome})
 
         if decision.tool_name == FINISH_TASK_TOOL:
             if decision.arguments.get("success"):
                 return []
             raise TaskFailedError(decision.arguments.get("reason") or "task failed")
 
+        context.planner_history.append(
+            {
+                "user_prompt": user_prompt,
+                "tool_name": decision.tool_name,
+                "arguments": _conversation_arguments(decision),
+                "rationale": decision.text_output,
+                "tool_result": None,
+            }
+        )
+
         return [
             PlannedStep(
                 action=decision.tool_name,
@@ -85,22 +115,12 @@ class AIPlanner(Planner):
         # (mapped to an empty plan above), never via this hook.
         return False
 
-
+    def _log(self, event: dict[str, Any]) -> None:
-def _history_summary(world: "WorldState | None") -> list[dict[str, Any]]:
+        if self.event_logger is not None:
-    if world is None:
+            try:
-        return []
+                self.event_logger(event)
-    return [
+            except Exception:
-        {
+                pass
-            "page": event.page,
-            "action": event.action,
-            "arguments": dict(event.arguments),
-            "rationale": event.rationale,
-            "purpose": event.purpose,
-            "expected_outcome": event.expected_outcome,
-            "success": event.success,
-        }
-        for event in world.history
-    ]
 
 
 def _without_ocr(scene_json: dict[str, Any]) -> dict[str, Any]:
@@ -114,3 +134,26 @@ def _without_ocr(scene_json: dict[str, Any]) -> dict[str, Any]:
         ]
     cleaned.pop("ocr_elements", None)
     return cleaned
+
+
+def _sync_tool_results(context: TaskContext) -> None:
+    for turn, result in zip(context.planner_history, context.step_results, strict=False):
+        if turn.get("tool_result") is None:
+            turn["tool_result"] = result.to_dict()
+
+
+def _conversation_arguments(decision: Any) -> dict[str, Any]:
+    arguments = dict(decision.arguments)
+    if decision.purpose is not None:
+        arguments["purpose"] = decision.purpose
+    if decision.expected_outcome is not None:
+        arguments["expected_outcome"] = decision.expected_outcome
+    return arguments
+
+
+def _accepts_history(method: Any) -> bool:
+    parameters = signature(method).parameters.values()
+    return any(
+        parameter.name == "history" or parameter.kind == Parameter.VAR_KEYWORD
+        for parameter in parameters
+    )

runtime/context.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any
 
 from core.models import Scene
 
@@ -18,6 +18,7 @@ class TaskContext:
     scenes: list[Scene] = field(default_factory=list)
     step_results: list["StepResult"] = field(default_factory=list)
     world: "WorldState | None" = None
+    planner_history: list[dict[str, Any]] = field(default_factory=list)
 
     def add_scene(self, scene: Scene) -> None:
         self.scenes.append(scene)

runtime/planner_config.py

@@ -11,6 +11,7 @@ DEFAULT_MODEL_BY_PROVIDER = {
     "openai_compatible": "local-model",
 }
 DEFAULT_TIMEOUT_SECONDS = 30.0
+DEFAULT_HISTORY_MAX_TURNS = 20
 
 ENABLED_ENV = "AI_PLANNER_ENABLED"
 PROVIDER_ENV = "AI_PLANNER_PROVIDER"
@@ -20,6 +21,7 @@ THINKING_BUDGET_ENV = "AI_PLANNER_THINKING_BUDGET_TOKENS"
 API_KEY_ENV = "AI_PLANNER_API_KEY"
 BASE_URL_ENV = "AI_PLANNER_BASE_URL"
 MULTIMODAL_ENV = "AI_PLANNER_MULTIMODAL"
+HISTORY_MAX_TURNS_ENV = "AI_PLANNER_HISTORY_MAX_TURNS"
 
 SUPPORTED_PROVIDERS = frozenset(DEFAULT_MODEL_BY_PROVIDER)
 
@@ -34,6 +36,7 @@ class PlannerConfig:
     api_key: str | None = None
     base_url: str | None = None
     multimodal: bool = False
+    history_max_turns: int = DEFAULT_HISTORY_MAX_TURNS
 
     def resolved_model(self) -> str:
         return self.model or DEFAULT_MODEL_BY_PROVIDER[self.provider]
@@ -50,6 +53,10 @@ def load_config(env: Mapping[str, str] | None = None) -> PlannerConfig:
         api_key=values.get(API_KEY_ENV) or _provider_key(values),
         base_url=values.get(BASE_URL_ENV) or None,
         multimodal=_parse_bool(values.get(MULTIMODAL_ENV), default=False),
+        history_max_turns=_parse_positive_int(
+            values.get(HISTORY_MAX_TURNS_ENV),
+            default=DEFAULT_HISTORY_MAX_TURNS,
+        ),
     )
 
 
@@ -88,6 +95,16 @@ def _parse_thinking_budget(value: str | None) -> int | None:
     return budget if budget > 0 else None
 
 
+def _parse_positive_int(value: str | None, *, default: int) -> int:
+    if value is None:
+        return default
+    try:
+        parsed = int(value)
+    except ValueError:
+        return default
+    return parsed if parsed > 0 else default
+
+
 def _provider_key(values: Mapping[str, str]) -> str | None:
     provider = (values.get(PROVIDER_ENV) or DEFAULT_PROVIDER).strip().lower()
     if provider == "openai":

runtime/planner_prompts.py

@@ -66,7 +66,6 @@ def planner_user_prompt(
     *,
     goal: str,
     scene_json: dict[str, Any],
-    history_summary: list[dict[str, Any]],
     device_platform: str | None = None,
     now: datetime | None = None,
 ) -> str:
@@ -83,8 +82,6 @@ def planner_user_prompt(
         f"{goal}\n\n"
         "Current Scene (JSON):\n"
         f"{json.dumps(scene_json, ensure_ascii=False, sort_keys=True)}\n\n"
-        "Recent history, oldest first (JSON):\n"
-        f"{json.dumps(history_summary, ensure_ascii=False, sort_keys=True)}\n\n"
         "Call exactly one tool for this turn."
     )
 

runtime/tool_calling_client.py

@@ -51,6 +51,7 @@ class ToolCallingClient(Protocol):
         screenshot: bytes | None,
         tools: list[ToolSpec],
         timeout: float,
+        history: list[dict[str, Any]] | None = None,
     ) -> ToolCallDecision: ...
 
 
@@ -80,6 +81,7 @@ class AnthropicToolCallingClient:
         screenshot: bytes | None,
         tools: list[ToolSpec],
         timeout: float,
+        history: list[dict[str, Any]] | None = None,
     ) -> ToolCallDecision:
         try:
             response = self._create_message(
@@ -87,6 +89,7 @@ class AnthropicToolCallingClient:
                 user_prompt,
                 screenshot,
                 tools,
+                history=history,
                 timeout=timeout,
                 forced=False,
             )
@@ -103,6 +106,7 @@ class AnthropicToolCallingClient:
                     user_prompt,
                     screenshot,
                     tools,
+                    history=history,
                     timeout=timeout,
                     forced=True,
                 )
@@ -123,6 +127,7 @@ class AnthropicToolCallingClient:
         screenshot: bytes | None,
         tools: list[ToolSpec],
         *,
+        history: list[dict[str, Any]] | None,
         timeout: float,
         forced: bool,
     ) -> Any:
@@ -146,10 +151,8 @@ class AnthropicToolCallingClient:
                 }
             ],
             "messages": [
-                {
+                *_anthropic_history(history or []),
-                    "role": "user",
+                {"role": "user", "content": _anthropic_content(user_prompt, screenshot)},
-                    "content": _anthropic_content(user_prompt, screenshot),
-                }
             ],
             "tools": [_anthropic_tool(spec) for spec in tools],
             "tool_choice": {
@@ -207,6 +210,7 @@ class OpenAIToolCallingClient:
         screenshot: bytes | None,
         tools: list[ToolSpec],
         timeout: float,
+        history: list[dict[str, Any]] | None = None,
     ) -> ToolCallDecision:
         try:
             response = self._create_completion(
@@ -214,6 +218,7 @@ class OpenAIToolCallingClient:
                 user_prompt,
                 screenshot,
                 tools,
+                history=history,
                 timeout=timeout,
                 forced=False,
             )
@@ -227,6 +232,7 @@ class OpenAIToolCallingClient:
                     user_prompt,
                     screenshot,
                     tools,
+                    history=history,
                     timeout=timeout,
                     forced=True,
                 )
@@ -247,6 +253,7 @@ class OpenAIToolCallingClient:
         screenshot: bytes | None,
         tools: list[ToolSpec],
         *,
+        history: list[dict[str, Any]] | None,
         timeout: float,
         forced: bool,
     ) -> Any:
@@ -257,6 +264,7 @@ class OpenAIToolCallingClient:
             "timeout": timeout,
             "messages": [
                 {"role": "system", "content": system_prompt},
+                *_openai_history(history or []),
                 {"role": "user", "content": _openai_content(user_prompt, screenshot)},
             ],
             "tools": [_openai_tool(spec) for spec in tools],
@@ -320,6 +328,44 @@ def _anthropic_content(
     return content
 
 
+def _anthropic_history(history: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    messages: list[dict[str, Any]] = []
+    for index, turn in enumerate(history):
+        result = turn.get("tool_result")
+        if result is None:
+            continue
+        tool_use_id = f"planner-turn-{index}"
+        assistant_content: list[dict[str, Any]] = []
+        rationale = turn.get("rationale")
+        if isinstance(rationale, str) and rationale:
+            assistant_content.append({"type": "text", "text": rationale})
+        assistant_content.append(
+            {
+                "type": "tool_use",
+                "id": tool_use_id,
+                "name": turn["tool_name"],
+                "input": dict(turn.get("arguments") or {}),
+            }
+        )
+        messages.extend(
+            [
+                {"role": "user", "content": turn["user_prompt"]},
+                {"role": "assistant", "content": assistant_content},
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "tool_result",
+                            "tool_use_id": tool_use_id,
+                            "content": json.dumps(result, ensure_ascii=False, default=str),
+                        }
+                    ],
+                },
+            ]
+        )
+    return messages
+
+
 def _anthropic_tool(spec: ToolSpec) -> dict[str, Any]:
     return {
         "name": spec.name,
@@ -393,6 +439,43 @@ def _openai_content(
     ]
 
 
+def _openai_history(history: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    messages: list[dict[str, Any]] = []
+    for index, turn in enumerate(history):
+        result = turn.get("tool_result")
+        if result is None:
+            continue
+        tool_call_id = f"planner-turn-{index}"
+        messages.extend(
+            [
+                {"role": "user", "content": turn["user_prompt"]},
+                {
+                    "role": "assistant",
+                    "content": turn.get("rationale"),
+                    "tool_calls": [
+                        {
+                            "id": tool_call_id,
+                            "type": "function",
+                            "function": {
+                                "name": turn["tool_name"],
+                                "arguments": json.dumps(
+                                    turn.get("arguments") or {},
+                                    ensure_ascii=False,
+                                ),
+                            },
+                        }
+                    ],
+                },
+                {
+                    "role": "tool",
+                    "tool_call_id": tool_call_id,
+                    "content": json.dumps(result, ensure_ascii=False, default=str),
+                },
+            ]
+        )
+    return messages
+
+
 def _openai_tool(spec: ToolSpec) -> dict[str, Any]:
     return {
         "type": "function",

tests/test_ai_planner.py

@@ -8,6 +8,7 @@ from core.errors import TaskFailedError
 from core.models import Bounds, Scene, SceneElement
 from runtime.ai_planner import AIPlanner
 from runtime.context import TaskContext
+from runtime.executor import StepResult
 from runtime.planner_config import PlannerConfig
 from runtime.tool_calling_client import ToolCallDecision
 from runtime.tool_specs import ALL_TOOL_SPECS
@@ -26,6 +27,7 @@ class FakeToolCallingClient:
         screenshot: bytes | None,
         tools: list[Any],
         timeout: float,
+        history: list[dict[str, Any]] | None = None,
     ) -> ToolCallDecision:
         self.calls.append(
             {
@@ -34,6 +36,7 @@ class FakeToolCallingClient:
                 "screenshot": screenshot,
                 "tools": tools,
                 "timeout": timeout,
+                "history": list(history) if history is not None else None,
             }
         )
         return self.decision
@@ -242,63 +245,64 @@ def test_ai_planner_propagates_rationale_and_thinking_to_planned_step() -> None:
     assert steps[0].expected_outcome == "The account settings page is visible."
 
 
-def test_history_summary_returns_compact_format() -> None:
+def test_ai_planner_carries_completed_turn_into_the_next_llm_call() -> None:
-    from collections import deque
+    client = FakeToolCallingClient(
-    from runtime.ai_planner import _history_summary
+        ToolCallDecision(
-    from world.models import WorldEvent, WorldState
+            tool_name="tap",
-
+            arguments={"x": 1, "y": 2},
-    state = WorldState(
+            text_output="Opening the send control.",
-        history=deque(
+            purpose="Open the send control.",
-            [
+            expected_outcome="The composer is focused.",
-                WorldEvent(
-                    action="tap",
-                    success=True,
-                    rationale="Opened settings.",
-                    arguments={"x": 1, "y": 2},
-                    purpose="Open settings.",
-                    expected_outcome="Settings is visible.",
-                    page="Home",
-                ),
-                WorldEvent(
-                    action="swipe",
-                    success=False,
-                    rationale=None,
-                    arguments={"start_y": 700, "end_y": 200},
-                    page="Settings",
-                ),
-            ]
         )
     )
+    planner = AIPlanner(client=client)
+    context = _context()
 
-    summary = _history_summary(state)
+    first_step = planner.plan(goal=context.goal, scene=_scene(), context=context)[0]
+    context.add_step_result(
+        StepResult(
+            step=first_step,
+            success=True,
+            attempts=1,
+            result={"ok": True},
+        )
+    )
+    planner.plan(goal=context.goal, scene=_scene(), context=context)
 
-    assert summary == [
+    assert client.calls[0]["history"] == []
+    history = client.calls[1]["history"]
+    assert history is not None
+    assert history[0]["tool_name"] == "tap"
+    assert history[0]["arguments"] == {
+        "x": 1,
+        "y": 2,
+        "purpose": "Open the send control.",
+        "expected_outcome": "The composer is focused.",
+    }
+    assert history[0]["tool_result"]["success"] is True
+    assert history[0]["tool_result"]["result"] == {"ok": True}
+
+
+def test_ai_planner_limits_history_sent_to_the_llm() -> None:
+    client = FakeToolCallingClient(
+        ToolCallDecision(tool_name="tap", arguments={"x": 1, "y": 2})
+    )
+    planner = AIPlanner(client=client, config=PlannerConfig(history_max_turns=2))
+    context = _context()
+    context.planner_history.extend(
         {
-            "page": "Home",
+            "user_prompt": f"turn-{index}",
-            "action": "tap",
+            "tool_name": "tap",
-            "arguments": {"x": 1, "y": 2},
+            "arguments": {},
-            "rationale": "Opened settings.",
-            "purpose": "Open settings.",
-            "expected_outcome": "Settings is visible.",
-            "success": True,
-        },
-        {
-            "page": "Settings",
-            "action": "swipe",
-            "arguments": {"start_y": 700, "end_y": 200},
             "rationale": None,
-            "purpose": None,
+            "tool_result": {"success": True},
-            "expected_outcome": None,
+        }
-            "success": False,
+        for index in range(3)
-        },
+    )
+
+    planner.plan(goal=context.goal, scene=_scene(), context=context)
+
+    assert [turn["user_prompt"] for turn in client.calls[0]["history"]] == [
+        "turn-1",
+        "turn-2",
     ]
-    # Must not contain scene element data
-    for entry in summary:
-        assert "scene_summary" not in entry
-        assert "elements" not in entry
-
-
-def test_history_summary_returns_empty_for_none_world() -> None:
-    from runtime.ai_planner import _history_summary
-
-    assert _history_summary(None) == []

tests/test_device_manager.py

@@ -46,3 +46,29 @@ def test_probe_marks_connected_device_offline_when_driver_is_unreachable() -> No
 
     assert manager.probe("iphone-1") is False
     assert manager.status("iphone-1") == "offline"
+
+
+def test_probe_uses_health_check_without_capturing_screen() -> None:
+    class HealthCheckedDriver:
+        def __init__(self) -> None:
+            self.health_checks = 0
+            self.screenshots = 0
+
+        def connect(self) -> None:
+            return None
+
+        def screenshot(self) -> bytes:
+            self.screenshots += 1
+            return b"screen"
+
+        def health_check(self) -> None:
+            self.health_checks += 1
+
+    driver = HealthCheckedDriver()
+    manager = DeviceManager()
+    manager.register_device("iphone-1", lambda: driver)  # type: ignore[arg-type]
+    manager.connect("iphone-1")
+
+    assert manager.probe("iphone-1") is True
+    assert driver.health_checks == 1
+    assert driver.screenshots == 0

tests/test_planner_prompts.py

@@ -9,7 +9,6 @@ def test_planner_user_prompt_includes_time_zone_and_configured_device_type() ->
     prompt = planner_user_prompt(
         goal="open settings",
         scene_json={"screen": {"width": 1, "height": 1}, "elements": []},
-        history_summary=[],
         device_platform="ios",
         now=datetime(
             2026,
@@ -35,8 +34,16 @@ def test_planner_user_prompt_uses_scene_platform_when_context_is_unavailable() -
             "elements": [],
             "app": {"platform": "android"},
         },
-        history_summary=[],
         now=datetime(2026, 7, 16, tzinfo=timezone.utc),
     )
 
     assert "Device type: android" in prompt
+
+
+def test_planner_user_prompt_does_not_duplicate_conversation_history() -> None:
+    prompt = planner_user_prompt(
+        goal="open settings",
+        scene_json={"screen": {"width": 1, "height": 1}, "elements": []},
+    )
+
+    assert "Recent history" not in prompt