Compare commits

...

4 Commits

Author SHA1 Message Date
Oliver Kieselbach 1c3d29f30b refactor(agent): read WiFi info via native WLAN API instead of netsh parsing
netsh wlan show interfaces output is localized: "Radio type"/"Channel"
(and on some languages even "Signal") never matched on non-English
images, silently dropping fields from wifi_signal_info and network
change snapshots. It also spawned a child process per collection.

Replace both netsh call sites with wlanapi.dll P/Invoke
(WlanQueryInterface: current_connection + channel_number):

- New WlanNativeMethods (raw interop) + WifiInfoReader (fail-soft,
  prefers the active NIC's interface GUID, falls back to the first
  connected WLAN interface; returns null on machines without WLAN).
- DeviceInfoCollector.CollectWiFiSignalInfo and
  NetworkChangeDetector.CollectWiFiInfo now use the reader; RadioType
  strings stay netsh-compatible ("802.11ax" ...), event fields
  (wifiSsid/wifiSignalPercent/wifiRadioType/wifiChannel) unchanged.
- SystemPaths.Netsh removed (no remaining references).

V2.Core suite 2085/2085 green incl. new WifiInfoReader tests; struct
marshaling verified against native sizeof (604/68/36/532).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 13:20:12 +02:00
Oliver Kieselbach bb4accfe96 feat: API Latency as optional column in dashboard session list
Off by default; sortable via avgApiLatencyMs. Data comes from the
SessionsIndex mirror the list already reads — no extra query or table.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 13:11:20 +02:00
Oliver Kieselbach 0ec481b479 feat(agent): outcome-calibrated agent_late_start severity and phrasing
Fleet data (2026-07-28, agent 2.0.1380) showed the late-start detector was
outcome-blind: tenant 659c3a90 collected 12 Warnings with the post-mortem/
hung-script note on enrollments that succeeded — the bootstrap merely ran
late in the ESP queue and the agent observed the healthy final minutes live.

New pure helper ObservationCoverage.DescribeLateStart:
- Succeeded -> Info with a tail-only-coverage note (IME-replay hint,
  bootstrap-ordering review if recurring); no alarm framing.
- Failed/TimedOut -> Warning with the existing post-mortem/hung-script note.
- oobeStateAtAgentStart refines the message only: "completed" = pure
  post-mortem, "in_progress" = live tail observed; not_started/unavailable
  add no claim (value flips to not_started after mid-OOBE reboots and
  "completed" is routine on post-desktop restarts).

The coverage gate (10 min boot-to-start / 5 min uptime) is unchanged, and
the OOBE state is deliberately NOT a gate: the canonical hung-script
failure (f148976f) terminates on the still-shown ESP screen, i.e. with
OOBE reading in_progress.

8 new tests (outcome x oobe-state matrix); V2.Core suite 2067 green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 12:53:17 +02:00
Oliver Kieselbach 3ec716a3ec feat: expose API latency to MCP field projection and tool docs
- SearchSessionsFunction fields whitelist += avgApiLatencyMs,
  apiRequestCount so search_sessions lean sweeps (e.g.
  fields=geoCountry,avgApiLatencyMs,apiRequestCount) can aggregate
  latency without full SessionSummary payloads
- search_sessions tool doc lists the new fields incl. the weighting
  hint; get_geographic_metrics doc names avgApiLatencyMs /
  apiLatencyVsGlobalPct as the backend-region distance metric

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 12:28:01 +02:00
13 changed files with 639 additions and 139 deletions
@@ -0,0 +1,97 @@
#nullable enable
using System.Text;
using AutopilotMonitor.Agent.V2.Core.Monitoring.Interop;
using Xunit;
using static AutopilotMonitor.Agent.V2.Core.Monitoring.Interop.WlanNativeMethods;
namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Interop
{
/// <summary>
/// Tests for the native-WLAN-API WiFi reader. The WLAN state of the test machine is
/// unknown (CI runners/VMs have no WLAN service), so the live path only pins the
/// fail-soft contract; the pure helpers (SSID decode, PHY-type mapping) are pinned
/// exactly — their output feeds wifi_signal_info event payloads and must stay
/// consistent with the strings netsh historically reported.
/// </summary>
public sealed class WifiInfoReaderTests
{
[Fact]
public void TryGetCurrentConnection_never_throws_and_returns_sane_values()
{
var result = WifiInfoReader.TryGetCurrentConnection();
if (result != null)
{
Assert.InRange(result.SignalPercent, 0, 100);
if (result.Channel.HasValue)
Assert.True(result.Channel.Value > 0, "channel must be positive when present");
}
}
// ----- DecodeSsid ---------------------------------------------------
[Fact]
public void DecodeSsid_decodes_utf8_bytes()
{
var raw = new byte[32];
var ssid = Encoding.UTF8.GetBytes("Contoso-Büro");
ssid.CopyTo(raw, 0);
Assert.Equal("Contoso-Büro", WifiInfoReader.DecodeSsid(raw, (uint)ssid.Length));
}
[Fact]
public void DecodeSsid_returns_null_for_empty_or_missing()
{
Assert.Null(WifiInfoReader.DecodeSsid(null, 5));
Assert.Null(WifiInfoReader.DecodeSsid(new byte[32], 0));
}
[Fact]
public void DecodeSsid_clamps_length_to_buffer_size()
{
var raw = Encoding.UTF8.GetBytes("abc");
// A corrupt native length beyond the buffer must not throw.
Assert.Equal("abc", WifiInfoReader.DecodeSsid(raw, 200));
}
[Fact]
public void DecodeSsid_uses_only_declared_length()
{
var raw = new byte[32];
Encoding.UTF8.GetBytes("HomeNet-Rest-Ignored").CopyTo(raw, 0);
Assert.Equal("HomeNet", WifiInfoReader.DecodeSsid(raw, 7));
}
// ----- PhyTypeToRadioType -------------------------------------------
// int parameters (cast inside): DOT11_PHY_TYPE is internal and may not appear in a
// public test method signature (CS0051).
[Theory]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_ofdm, "802.11a")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_hrdsss, "802.11b")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_erp, "802.11g")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_ht, "802.11n")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_vht, "802.11ac")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_dmg, "802.11ad")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_he, "802.11ax")]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_eht, "802.11be")]
public void PhyTypeToRadioType_maps_known_generations(int phyType, string expected)
{
Assert.Equal(expected, WifiInfoReader.PhyTypeToRadioType((DOT11_PHY_TYPE)phyType));
}
[Theory]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_unknown)]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_fhss)]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_dsss)]
[InlineData((int)DOT11_PHY_TYPE.dot11_phy_type_irbaseband)]
[InlineData(9999)]
public void PhyTypeToRadioType_returns_null_for_legacy_or_unknown(int phyType)
{
Assert.Null(WifiInfoReader.PhyTypeToRadioType((DOT11_PHY_TYPE)phyType));
}
}
}
@@ -1,5 +1,7 @@
using System;
using AutopilotMonitor.Agent.V2.Core.Orchestration;
using AutopilotMonitor.Agent.V2.Core.Termination;
using AutopilotMonitor.Shared.Models;
using Xunit;
namespace AutopilotMonitor.Agent.V2.Core.Tests.Termination
@@ -70,5 +72,82 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Termination
Assert.Equal(0, bootToStart, 0);
Assert.Equal(10, uptime, 0);
}
// --- DescribeLateStart: outcome-calibrated severity + phrasing (fleet 2026-07-28) ---
private static void Describe(
EnrollmentTerminationOutcome outcome, string oobeState,
out EventSeverity severity, out string message, out string note)
=> ObservationCoverage.DescribeLateStart(
outcome, oobeState, bootToStartSeconds: 34 * 60, uptimeSeconds: 30,
out severity, out message, out note);
[Fact]
public void Failed_outcome_is_a_warning_with_the_hung_script_post_mortem_note()
{
Describe(EnrollmentTerminationOutcome.Failed, "in_progress",
out var severity, out var message, out var note);
Assert.Equal(EventSeverity.Warning, severity);
Assert.Contains("low coverage of the enrollment window", message);
Assert.Contains("post-mortem", note);
Assert.Contains("hung ahead of the bootstrap", note);
}
[Fact]
public void TimedOut_outcome_is_a_warning_like_a_failure()
{
Describe(EnrollmentTerminationOutcome.TimedOut, "in_progress",
out var severity, out _, out var note);
Assert.Equal(EventSeverity.Warning, severity);
Assert.Contains("post-mortem", note);
}
[Fact]
public void Succeeded_outcome_is_an_info_about_tail_only_coverage_without_alarm_framing()
{
// The 659c3a90 shape: healthy enrollment, bootstrap merely ran late in the ESP queue.
Describe(EnrollmentTerminationOutcome.Succeeded, "in_progress",
out var severity, out _, out var note);
Assert.Equal(EventSeverity.Info, severity);
Assert.Contains("succeeded", note);
Assert.Contains("IME log replay", note);
Assert.DoesNotContain("post-mortem", note);
Assert.DoesNotContain("hung", note);
}
[Fact]
public void Oobe_completed_at_start_phrases_a_pure_post_mortem()
{
Describe(EnrollmentTerminationOutcome.Failed, "completed",
out _, out var message, out _);
Assert.Contains("OOBE was already completed when the agent started", message);
}
[Fact]
public void Oobe_in_progress_at_start_phrases_the_live_tail()
{
Describe(EnrollmentTerminationOutcome.Failed, "in_progress",
out _, out var message, out _);
Assert.Contains("OOBE was still in progress at agent start", message);
Assert.Contains("final 30s live", message);
}
[Theory]
[InlineData("not_started")] // flips in after a mid-OOBE reboot — not interpretable
[InlineData("unavailable")] // WinRT contract absent / read failed
[InlineData("unknown_3")] // unexpected enum value
public void Uninterpretable_oobe_states_add_no_claim_to_the_message(string oobeState)
{
Describe(EnrollmentTerminationOutcome.Failed, oobeState,
out _, out var message, out _);
Assert.DoesNotContain("OOBE", message);
Assert.EndsWith("low coverage of the enrollment window.", message);
}
}
}
@@ -0,0 +1,194 @@
using System;
using System.Runtime.InteropServices;
using System.Text;
using static AutopilotMonitor.Agent.V2.Core.Monitoring.Interop.WlanNativeMethods;
namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Interop
{
/// <summary>
/// Current WiFi connection details as read from the native WLAN API.
/// </summary>
public sealed class WifiConnectionInfo
{
/// <summary>SSID of the connected network; null when the AP broadcasts an empty SSID.</summary>
public string Ssid { get; internal set; }
/// <summary>Signal quality 0–100 (same semantics as the netsh "Signal" percentage).</summary>
public int SignalPercent { get; internal set; }
/// <summary>Human-readable PHY generation ("802.11ax" …); null for exotic/unknown PHYs.</summary>
public string RadioType { get; internal set; }
/// <summary>Current 802.11 channel number; null when the channel query fails.</summary>
public int? Channel { get; internal set; }
}
/// <summary>
/// Fail-soft reader over <see cref="WlanNativeMethods"/>: returns the current WiFi
/// connection or null — never throws, never blocks on a child process. Machines without
/// the WLAN AutoConfig service (VMs, wired-only devices) simply return null.
/// </summary>
public static class WifiInfoReader
{
/// <summary>
/// Reads the current WiFi connection. When <paramref name="preferredInterfaceId"/> is
/// given (the adapter GUID from <c>NetworkInterface.Id</c>), that interface is queried
/// first; otherwise — or when it is not connected — the first connected WLAN interface
/// wins. Returns null when no interface has an active connection.
/// </summary>
public static WifiConnectionInfo TryGetCurrentConnection(Guid? preferredInterfaceId = null)
{
var clientHandle = IntPtr.Zero;
try
{
if (WlanOpenHandle(WLAN_CLIENT_VERSION, IntPtr.Zero, out _, out clientHandle) != ERROR_SUCCESS)
return null;
var interfaceList = IntPtr.Zero;
try
{
if (WlanEnumInterfaces(clientHandle, IntPtr.Zero, out interfaceList) != ERROR_SUCCESS)
return null;
var count = (uint)Marshal.ReadInt32(interfaceList);
var infoSize = Marshal.SizeOf(typeof(WLAN_INTERFACE_INFO));
// List header: DWORD dwNumberOfItems + DWORD dwIndex, then the info array.
var firstEntry = new IntPtr(interfaceList.ToInt64() + 8);
WifiConnectionInfo fallback = null;
for (var i = 0; i < count; i++)
{
var entryPtr = new IntPtr(firstEntry.ToInt64() + i * infoSize);
var info = (WLAN_INTERFACE_INFO)Marshal.PtrToStructure(entryPtr, typeof(WLAN_INTERFACE_INFO));
var connection = QueryCurrentConnection(clientHandle, info.InterfaceGuid);
if (connection == null)
continue;
if (preferredInterfaceId.HasValue && info.InterfaceGuid == preferredInterfaceId.Value)
return connection;
if (fallback == null)
fallback = connection;
}
return fallback;
}
finally
{
if (interfaceList != IntPtr.Zero)
WlanFreeMemory(interfaceList);
}
}
catch
{
return null;
}
finally
{
if (clientHandle != IntPtr.Zero)
WlanCloseHandle(clientHandle, IntPtr.Zero);
}
}
private static WifiConnectionInfo QueryCurrentConnection(IntPtr clientHandle, Guid interfaceGuid)
{
var dataPtr = IntPtr.Zero;
try
{
if (WlanQueryInterface(clientHandle, ref interfaceGuid,
WLAN_INTF_OPCODE.wlan_intf_opcode_current_connection,
IntPtr.Zero, out _, out dataPtr, IntPtr.Zero) != ERROR_SUCCESS)
return null;
var attributes = (WLAN_CONNECTION_ATTRIBUTES)Marshal.PtrToStructure(
dataPtr, typeof(WLAN_CONNECTION_ATTRIBUTES));
if (attributes.isState != WLAN_INTERFACE_STATE.wlan_interface_state_connected)
return null;
var assoc = attributes.wlanAssociationAttributes;
return new WifiConnectionInfo
{
Ssid = DecodeSsid(assoc.dot11Ssid.ucSSID, assoc.dot11Ssid.uSSIDLength),
SignalPercent = (int)Math.Min(assoc.wlanSignalQuality, 100),
RadioType = PhyTypeToRadioType(assoc.dot11PhyType),
Channel = QueryChannel(clientHandle, interfaceGuid),
};
}
finally
{
if (dataPtr != IntPtr.Zero)
WlanFreeMemory(dataPtr);
}
}
private static int? QueryChannel(IntPtr clientHandle, Guid interfaceGuid)
{
var dataPtr = IntPtr.Zero;
try
{
if (WlanQueryInterface(clientHandle, ref interfaceGuid,
WLAN_INTF_OPCODE.wlan_intf_opcode_channel_number,
IntPtr.Zero, out var dataSize, out dataPtr, IntPtr.Zero) != ERROR_SUCCESS)
return null;
if (dataSize < sizeof(uint) || dataPtr == IntPtr.Zero)
return null;
return Marshal.ReadInt32(dataPtr);
}
catch
{
return null;
}
finally
{
if (dataPtr != IntPtr.Zero)
WlanFreeMemory(dataPtr);
}
}
/// <summary>
/// Decodes a raw DOT11_SSID (UTF-8 by convention) into a string; null for empty SSIDs.
/// Internal for direct unit-testing via InternalsVisibleTo.
/// </summary>
internal static string DecodeSsid(byte[] raw, uint length)
{
if (raw == null || length == 0)
return null;
var byteCount = (int)Math.Min(length, (uint)raw.Length);
try
{
var ssid = Encoding.UTF8.GetString(raw, 0, byteCount);
return string.IsNullOrEmpty(ssid) ? null : ssid;
}
catch
{
return null;
}
}
/// <summary>
/// Maps a DOT11 PHY type to the same strings netsh historically reported as
/// "Radio type" — keeps event payloads consistent across the netsh→WLAN-API switch.
/// Internal for direct unit-testing via InternalsVisibleTo.
/// </summary>
internal static string PhyTypeToRadioType(DOT11_PHY_TYPE phyType)
{
switch (phyType)
{
case DOT11_PHY_TYPE.dot11_phy_type_ofdm: return "802.11a";
case DOT11_PHY_TYPE.dot11_phy_type_hrdsss: return "802.11b";
case DOT11_PHY_TYPE.dot11_phy_type_erp: return "802.11g";
case DOT11_PHY_TYPE.dot11_phy_type_ht: return "802.11n";
case DOT11_PHY_TYPE.dot11_phy_type_vht: return "802.11ac";
case DOT11_PHY_TYPE.dot11_phy_type_dmg: return "802.11ad";
case DOT11_PHY_TYPE.dot11_phy_type_he: return "802.11ax";
case DOT11_PHY_TYPE.dot11_phy_type_eht: return "802.11be";
default: return null;
}
}
}
}
@@ -0,0 +1,142 @@
using System;
using System.Runtime.InteropServices;
namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Interop
{
/// <summary>
/// Native WLAN API interop (<c>wlanapi.dll</c>) used to read the current WiFi connection
/// (SSID, signal quality, PHY type, channel) without spawning <c>netsh</c>.
/// <para>
/// The WLAN API is language-neutral — unlike parsing <c>netsh wlan show interfaces</c>
/// output, whose labels follow the OS UI language and silently drop fields on
/// non-English images. On machines without the WLAN AutoConfig service (VMs, servers,
/// wired-only devices) <c>WlanOpenHandle</c>/<c>WlanEnumInterfaces</c> fail with a
/// non-zero error code; callers treat that as "no WiFi" (see <see cref="WifiInfoReader"/>).
/// </para>
/// </summary>
internal static class WlanNativeMethods
{
internal const uint ERROR_SUCCESS = 0;
/// <summary>Client version 2 = Vista and later (the only relevant range).</summary>
internal const uint WLAN_CLIENT_VERSION = 2;
internal enum WLAN_INTF_OPCODE : uint
{
wlan_intf_opcode_current_connection = 7,
wlan_intf_opcode_channel_number = 8,
}
internal enum WLAN_INTERFACE_STATE
{
wlan_interface_state_not_ready = 0,
wlan_interface_state_connected = 1,
wlan_interface_state_ad_hoc_network_formed = 2,
wlan_interface_state_disconnecting = 3,
wlan_interface_state_disconnected = 4,
wlan_interface_state_associating = 5,
wlan_interface_state_discovering = 6,
wlan_interface_state_authenticating = 7,
}
internal enum DOT11_PHY_TYPE : uint
{
dot11_phy_type_unknown = 0,
dot11_phy_type_fhss = 1,
dot11_phy_type_dsss = 2,
dot11_phy_type_irbaseband = 3,
dot11_phy_type_ofdm = 4, // 802.11a
dot11_phy_type_hrdsss = 5, // 802.11b
dot11_phy_type_erp = 6, // 802.11g
dot11_phy_type_ht = 7, // 802.11n
dot11_phy_type_vht = 8, // 802.11ac
dot11_phy_type_dmg = 9, // 802.11ad
dot11_phy_type_he = 10, // 802.11ax
dot11_phy_type_eht = 11, // 802.11be
}
[StructLayout(LayoutKind.Sequential, CharSet = CharSet.Unicode)]
internal struct WLAN_INTERFACE_INFO
{
public Guid InterfaceGuid;
[MarshalAs(UnmanagedType.ByValTStr, SizeConst = 256)]
public string strInterfaceDescription;
public WLAN_INTERFACE_STATE isState;
}
[StructLayout(LayoutKind.Sequential)]
internal struct DOT11_SSID
{
public uint uSSIDLength;
[MarshalAs(UnmanagedType.ByValArray, SizeConst = 32)]
public byte[] ucSSID;
}
[StructLayout(LayoutKind.Sequential)]
internal struct WLAN_ASSOCIATION_ATTRIBUTES
{
public DOT11_SSID dot11Ssid;
public int dot11BssType;
[MarshalAs(UnmanagedType.ByValArray, SizeConst = 6)]
public byte[] dot11Bssid;
public DOT11_PHY_TYPE dot11PhyType;
public uint uDot11PhyIndex;
public uint wlanSignalQuality; // 0..100, same semantics as netsh "Signal"
public uint ulRxRate;
public uint ulTxRate;
}
[StructLayout(LayoutKind.Sequential)]
internal struct WLAN_SECURITY_ATTRIBUTES
{
[MarshalAs(UnmanagedType.Bool)]
public bool bSecurityEnabled;
[MarshalAs(UnmanagedType.Bool)]
public bool bOneXEnabled;
public int dot11AuthAlgorithm;
public int dot11CipherAlgorithm;
}
[StructLayout(LayoutKind.Sequential, CharSet = CharSet.Unicode)]
internal struct WLAN_CONNECTION_ATTRIBUTES
{
public WLAN_INTERFACE_STATE isState;
public int wlanConnectionMode;
[MarshalAs(UnmanagedType.ByValTStr, SizeConst = 256)]
public string strProfileName;
public WLAN_ASSOCIATION_ATTRIBUTES wlanAssociationAttributes;
public WLAN_SECURITY_ATTRIBUTES wlanSecurityAttributes;
}
[DllImport("wlanapi.dll")]
internal static extern uint WlanOpenHandle(
uint dwClientVersion,
IntPtr pReserved,
out uint pdwNegotiatedVersion,
out IntPtr phClientHandle);
[DllImport("wlanapi.dll")]
internal static extern uint WlanCloseHandle(
IntPtr hClientHandle,
IntPtr pReserved);
[DllImport("wlanapi.dll")]
internal static extern uint WlanEnumInterfaces(
IntPtr hClientHandle,
IntPtr pReserved,
out IntPtr ppInterfaceList);
[DllImport("wlanapi.dll")]
internal static extern uint WlanQueryInterface(
IntPtr hClientHandle,
[In] ref Guid pInterfaceGuid,
WLAN_INTF_OPCODE OpCode,
IntPtr pReserved,
out uint pdwDataSize,
out IntPtr ppData,
IntPtr pWlanOpcodeValueType);
[DllImport("wlanapi.dll")]
internal static extern void WlanFreeMemory(IntPtr pMemory);
}
}
@@ -815,7 +815,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
/// Collects active network interface details (name, type, link speed, MAC) using
/// System.Net.NetworkInformation — instant, no process spawn.
/// If the active interface is WiFi, fires off a separate async task to collect
/// WiFi signal info via netsh (fire-and-forget, never blocks).
/// WiFi signal info via the native WLAN API (fire-and-forget, never blocks).
/// </summary>
private void CollectActiveNetworkInterfaceInfo()
{
@@ -858,7 +858,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
// Fire-and-forget WiFi signal collection — separate event, never blocks
if (isWifi)
{
Task.Run(() => CollectWiFiSignalInfo());
Guid? nicGuid = Guid.TryParse(activeNic.Id, out var parsedGuid) ? parsedGuid : (Guid?)null;
Task.Run(() => CollectWiFiSignalInfo(nicGuid));
}
}
catch (Exception ex)
@@ -899,78 +900,37 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
}
/// <summary>
/// Collects WiFi signal info via netsh wlan show interfaces and emits a separate
/// wifi_signal_info event. Designed to run as fire-and-forget via Task.Run —
/// never blocks other collection. VMs without WiFi service simply get no event.
/// Collects WiFi signal info via the native WLAN API (<see cref="WifiInfoReader"/>,
/// language-neutral, no process spawn) and emits a separate wifi_signal_info event.
/// Designed to run as fire-and-forget via Task.Run — never blocks other collection.
/// VMs without WiFi service simply get no event.
/// </summary>
private void CollectWiFiSignalInfo()
private void CollectWiFiSignalInfo(Guid? interfaceGuid)
{
try
{
var psi = new ProcessStartInfo
{
FileName = SystemPaths.Netsh,
Arguments = "wlan show interfaces",
UseShellExecute = false,
RedirectStandardOutput = true,
RedirectStandardError = true,
CreateNoWindow = true
};
string output;
using (var process = Process.Start(psi))
{
output = process.StandardOutput.ReadToEnd();
process.WaitForExit(5000);
}
if (string.IsNullOrEmpty(output))
var wifi = WifiInfoReader.TryGetCurrentConnection(interfaceGuid);
if (wifi == null)
return;
var data = new Dictionary<string, object>();
foreach (var line in output.Split(new[] { '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries))
var data = new Dictionary<string, object>
{
var trimmed = line.Trim();
var colonIndex = trimmed.IndexOf(':');
if (colonIndex < 0) continue;
["wifiSignalPercent"] = wifi.SignalPercent
};
if (wifi.Ssid != null)
data["wifiSsid"] = wifi.Ssid;
if (wifi.RadioType != null)
data["wifiRadioType"] = wifi.RadioType;
if (wifi.Channel.HasValue)
data["wifiChannel"] = wifi.Channel.Value;
var key = trimmed.Substring(0, colonIndex).Trim();
var value = trimmed.Substring(colonIndex + 1).Trim();
var message = wifi.Ssid != null
? $"WiFi: {wifi.Ssid}, Signal: {wifi.SignalPercent}%"
: $"WiFi signal info, Signal: {wifi.SignalPercent}%";
if (wifi.RadioType != null)
message += $" ({wifi.RadioType})";
if (key.Equals("SSID", StringComparison.OrdinalIgnoreCase) &&
!key.Equals("BSSID", StringComparison.OrdinalIgnoreCase))
{
data["wifiSsid"] = value;
}
else if (key.Equals("Signal", StringComparison.OrdinalIgnoreCase))
{
if (int.TryParse(value.TrimEnd('%'), out var signal))
data["wifiSignalPercent"] = signal;
}
else if (key.Equals("Radio type", StringComparison.OrdinalIgnoreCase))
{
data["wifiRadioType"] = value;
}
else if (key.Equals("Channel", StringComparison.OrdinalIgnoreCase))
{
if (int.TryParse(value, out var channel))
data["wifiChannel"] = channel;
}
}
if (data.Count > 0)
{
var message = data.ContainsKey("wifiSsid")
? $"WiFi: {data["wifiSsid"]}"
: "WiFi signal info";
if (data.ContainsKey("wifiSignalPercent"))
message += $", Signal: {data["wifiSignalPercent"]}%";
if (data.ContainsKey("wifiRadioType"))
message += $" ({data["wifiRadioType"]})";
EmitDeviceInfoEvent(Constants.EventTypes.WifiSignalInfo, message, data);
}
EmitDeviceInfoEvent(Constants.EventTypes.WifiSignalInfo, message, data);
}
catch (Exception ex)
{
@@ -8,8 +8,8 @@ using System.Net.Sockets;
using System.Threading;
using System.Threading.Tasks;
using AutopilotMonitor.Agent.V2.Core.Logging;
using AutopilotMonitor.Agent.V2.Core.Monitoring.Interop;
using AutopilotMonitor.Agent.V2.Core.Orchestration;
using AutopilotMonitor.Agent.V2.Core.Security;
using AutopilotMonitor.Shared;
using AutopilotMonitor.Shared.Models;
@@ -37,7 +37,6 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.Periodic
private const int DebounceDelayMs = 3000;
private const int ConnectivityCheckDelayMs = 5000;
private const int ConnectivityCheckTimeoutMs = 8000;
private const int WifiCollectTimeoutMs = 3000;
private const string Source = "NetworkChangeDetector";
/// <summary>
@@ -374,7 +373,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.Periodic
// Collect WiFi SSID synchronously (needed for before/after comparison)
if (isWifi)
{
var wifiInfo = CollectWiFiInfo();
Guid? nicGuid = Guid.TryParse(activeNic.Id, out var parsedGuid) ? parsedGuid : (Guid?)null;
var wifiInfo = CollectWiFiInfo(nicGuid);
snapshot.WifiSsid = wifiInfo.ssid;
snapshot.WifiSignalPercent = wifiInfo.signal;
snapshot.WifiRadioType = wifiInfo.radioType;
@@ -390,73 +390,24 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.Periodic
}
/// <summary>
/// Collects WiFi SSID, signal, and radio type via netsh wlan show interfaces.
/// Synchronous with timeout — needed before emitting the event.
/// Collects WiFi SSID, signal, and radio type via the native WLAN API
/// (<see cref="WifiInfoReader"/> — language-neutral, no process spawn).
/// Synchronous — needed before emitting the event.
/// </summary>
private (string ssid, int? signal, string radioType) CollectWiFiInfo()
private (string ssid, int? signal, string radioType) CollectWiFiInfo(Guid? interfaceGuid)
{
string ssid = null;
int? signal = null;
string radioType = null;
try
{
var psi = new ProcessStartInfo
{
FileName = SystemPaths.Netsh,
Arguments = "wlan show interfaces",
UseShellExecute = false,
RedirectStandardOutput = true,
RedirectStandardError = true,
CreateNoWindow = true
};
string output;
using (var process = Process.Start(psi))
{
output = process.StandardOutput.ReadToEnd();
if (!process.WaitForExit(WifiCollectTimeoutMs))
{
try { process.Kill(); } catch { }
_logger.Debug("NetworkChangeDetector: netsh timed out");
return (null, null, null);
}
}
if (string.IsNullOrEmpty(output))
return (null, null, null);
foreach (var line in output.Split(new[] { '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries))
{
var trimmed = line.Trim();
var colonIndex = trimmed.IndexOf(':');
if (colonIndex < 0) continue;
var key = trimmed.Substring(0, colonIndex).Trim();
var value = trimmed.Substring(colonIndex + 1).Trim();
if (key.Equals("SSID", StringComparison.OrdinalIgnoreCase) &&
!key.Equals("BSSID", StringComparison.OrdinalIgnoreCase))
{
ssid = value;
}
else if (key.Equals("Signal", StringComparison.OrdinalIgnoreCase))
{
if (int.TryParse(value.TrimEnd('%'), out var sig))
signal = sig;
}
else if (key.Equals("Radio type", StringComparison.OrdinalIgnoreCase))
{
radioType = value;
}
}
var wifi = WifiInfoReader.TryGetCurrentConnection(interfaceGuid);
if (wifi != null)
return (wifi.Ssid, wifi.SignalPercent, wifi.RadioType);
}
catch (Exception ex)
{
_logger.Debug($"NetworkChangeDetector: WiFi info collection failed: {ex.Message}");
}
return (ssid, signal, radioType);
return (null, null, null);
}
// -------------------------------------------------------------------
@@ -35,9 +35,6 @@ namespace AutopilotMonitor.Agent.V2.Core.Security
/// <summary>C:\Windows\System32\tzutil.exe</summary>
public static readonly string TzUtil = Path.Combine(System32, "tzutil.exe");
/// <summary>C:\Windows\System32\netsh.exe</summary>
public static readonly string Netsh = Path.Combine(System32, "netsh.exe");
/// <summary>C:\Windows\System32\schtasks.exe</summary>
public static readonly string Schtasks = Path.Combine(System32, "schtasks.exe");
@@ -623,12 +623,15 @@ namespace AutopilotMonitor.Agent.V2.Core.Termination
}
/// <summary>
/// Emits a one-shot <c>agent_late_start</c> Warning when the agent had low observation
/// Emits a one-shot <c>agent_late_start</c> event when the agent had low observation
/// coverage: it started a long time after device boot AND lived only briefly before this
/// terminal outcome (gate in <see cref="ObservationCoverage"/>). Such a session looks like a
/// normal multi-minute failure in the list (StartedAt is back-dated to the earliest replayed
/// IME-log event) but the agent actually observed only the end-state — so the operator should
/// read the diagnosis as a post-mortem reconstruction, not live evidence. No state mutation.
/// IME-log event) but the agent actually observed only the end-state. Severity and phrasing
/// are outcome-calibrated via <see cref="ObservationCoverage.DescribeLateStart"/>: a failure
/// stays a Warning with the post-mortem/hung-script note, a success is an Info about
/// tail-only coverage (fleet 2026-07-28: tenant 659c3a90 collected 12 Warnings on healthy
/// enrollments whose bootstrap merely ran late). No state mutation.
/// </summary>
private void MaybeEmitAgentLateStart(EnrollmentTerminatedEventArgs args)
{
@@ -642,21 +645,24 @@ namespace AutopilotMonitor.Agent.V2.Core.Termination
out var bootToStartSeconds, out var uptimeSeconds))
return;
ObservationCoverage.DescribeLateStart(
args.Outcome, _oobeStateAtAgentStart, bootToStartSeconds, uptimeSeconds,
out var severity, out var message, out var note);
_logger.Info(
$"EnrollmentTerminationHandler: low observation coverage — agent started " +
$"{bootToStartSeconds / 60.0:F1} min after boot and lived {uptimeSeconds:F0}s; " +
$"emitting agent_late_start.");
$"emitting agent_late_start ({severity}, outcome {args.Outcome}).");
_post.Emit(new EnrollmentEvent
{
SessionId = _configuration.SessionId,
TenantId = _configuration.TenantId,
EventType = Constants.EventTypes.AgentLateStart,
Severity = EventSeverity.Warning,
Severity = severity,
Source = "EnrollmentTerminationHandler",
Phase = EnrollmentPhase.Unknown,
Message = $"Agent started {bootToStartSeconds / 60.0:F0} min after boot and observed only " +
$"{uptimeSeconds:F0}s before terminating ({args.Outcome}) — low coverage of the enrollment window.",
Message = message,
Data = new Dictionary<string, object>
{
{ "bootToAgentStartSeconds", Math.Round(bootToStartSeconds, 1) },
@@ -665,7 +671,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Termination
{ "agentStartUtc", _agentStartTimeUtc.ToString("o") },
{ "oobeStateAtAgentStart", _oobeStateAtAgentStart },
{ "outcome", args.Outcome.ToString() },
{ "note", "The agent's bootstrap (an Intune platform script) ran only near the end of the enrollment, so the agent observed the already-decided end-state rather than the failure window. Treat the diagnosis as a post-mortem; check for a platform/remediation script that hung ahead of the bootstrap (see script_timeout_suspected)." },
{ "note", note },
},
ImmediateUpload = true,
});
@@ -1,6 +1,8 @@
#nullable enable
using System;
using System.Runtime.InteropServices;
using AutopilotMonitor.Agent.V2.Core.Orchestration;
using AutopilotMonitor.Shared.Models;
namespace AutopilotMonitor.Agent.V2.Core.Termination
{
@@ -76,5 +78,57 @@ namespace AutopilotMonitor.Agent.V2.Core.Termination
uptimeSeconds = Math.Max(0, uptime.TotalSeconds);
return bootToStart >= LateStartBootThreshold && uptime <= LowCoverageUptime;
}
/// <summary>
/// Severity + operator-facing phrasing for the <c>agent_late_start</c> event, calibrated
/// by fleet data (2026-07-28): the gate alone is outcome-blind and attached a
/// "post-mortem / check for a hung script" Warning to sessions that in fact succeeded —
/// there the late bootstrap is deployment hygiene, not an alarm. The OOBE state refines
/// the phrasing but must never gate: the canonical hung-script failure terminates on the
/// still-shown ESP screen, i.e. with OOBE reading <c>in_progress</c>.
/// </summary>
/// <param name="outcome">Terminal outcome the enrollment reached.</param>
/// <param name="oobeStateAtAgentStart"><see cref="Monitoring.Interop.OobeStateReader"/>
/// sample taken at THIS process's start. Only <c>completed</c> / <c>in_progress</c> are
/// interpreted; <c>not_started</c> flips in after mid-OOBE reboots and <c>completed</c> is
/// routine for post-desktop restarts, so no claim is phrased from the other values.</param>
/// <param name="bootToStartSeconds">From <see cref="IsLowObservationCoverage"/>.</param>
/// <param name="uptimeSeconds">From <see cref="IsLowObservationCoverage"/>.</param>
internal static void DescribeLateStart(
EnrollmentTerminationOutcome outcome,
string oobeStateAtAgentStart,
double bootToStartSeconds,
double uptimeSeconds,
out EventSeverity severity,
out string message,
out string note)
{
var succeeded = outcome == EnrollmentTerminationOutcome.Succeeded;
severity = succeeded ? EventSeverity.Info : EventSeverity.Warning;
message = $"Agent started {bootToStartSeconds / 60.0:F0} min after boot and observed only " +
$"{uptimeSeconds:F0}s before terminating ({outcome}) — low coverage of the enrollment window.";
switch (oobeStateAtAgentStart)
{
case "completed":
message += " OOBE was already completed when the agent started — the diagnosis is a " +
"post-mortem reconstruction, not live observation.";
break;
case "in_progress":
message += $" OOBE was still in progress at agent start — the agent did observe the " +
$"final {uptimeSeconds:F0}s live.";
break;
}
note = succeeded
? "The agent's bootstrap (an Intune platform script) ran late in the enrollment, so only the " +
"final stretch was observed live; earlier timeline entries are reconstructed from IME log " +
"replay. The enrollment itself succeeded. If this recurs across sessions, review which " +
"platform/remediation scripts run ahead of the bootstrap (see script_timeout_suspected)."
: "The agent's bootstrap (an Intune platform script) ran only near the end of the enrollment, " +
"so the agent observed the already-decided end-state rather than the failure window. Treat " +
"the diagnosis as a post-mortem; check for a platform/remediation script that hung ahead of " +
"the bootstrap (see script_timeout_suspected).";
}
}
}
@@ -210,6 +210,8 @@ public class SearchSessionsFunction
if (fields.Contains("imeAgentVersion")) dict["imeAgentVersion"] = s.ImeAgentVersion;
if (fields.Contains("geoCountry")) dict["geoCountry"] = s.GeoCountry;
if (fields.Contains("rebootCount")) dict["rebootCount"] = s.RebootCount;
if (fields.Contains("avgApiLatencyMs")) dict["avgApiLatencyMs"] = s.AvgApiLatencyMs;
if (fields.Contains("apiRequestCount")) dict["apiRequestCount"] = s.ApiRequestCount;
if (dict.Count == 0)
{
@@ -295,7 +295,9 @@ export function registerAdminTools(server: McpServer, ga: boolean, strictGa: boo
title: 'Geographic Metrics',
description:
'Get geographic distribution of enrollments — where devices are enrolling from, with performance comparisons. ' +
'Shows per-location: session counts, success rates, avg/median/p95 duration, throughput, and outlier detection. ' +
'Shows per-location: session counts, success rates, avg/median/p95 duration, throughput, outlier detection, and ' +
'avgApiLatencyMs (agent→backend HTTP round-trip, request-weighted — the metric for judging backend-region distance, ' +
'e.g. when evaluating a new backend region; apiLatencyVsGlobalPct compares against the global weighted average). ' +
(ga ? 'Omit tenantId for cross-tenant view (Global Admin). ' : '') +
'Use get_geographic_sessions to drill into a specific location. ' +
'days accepts any value 1-365 (e.g. 5, 7, 12, 30, 90).',
@@ -144,7 +144,9 @@ export function registerSessionTools(server: McpServer, ga: boolean, delegated:
'Use for counting / aggregation to avoid the response cap. Available: sessionId, tenantId, status, ' +
'serialNumber, manufacturer, model, deviceName, osBuild, osName, startedAt, completedAt, ' +
'durationSeconds, currentPhase, failureReason, eventCount, enrollmentType, isPreProvisioned, ' +
'isUserDriven, isHybridJoin, isSelfDeployingProfile, agentVersion, imeAgentVersion, geoCountry, rebootCount.'),
'isUserDriven, isHybridJoin, isSelfDeployingProfile, agentVersion, imeAgentVersion, geoCountry, rebootCount, ' +
'avgApiLatencyMs, apiRequestCount (agent→backend HTTP round-trip; weight latency by apiRequestCount when aggregating, ' +
'e.g. fields=geoCountry,avgApiLatencyMs,apiRequestCount for a per-country latency sweep; null on sessions from agents predating the field).'),
deviceProperties: z.record(z.string(), z.string()).optional().describe(
'Dynamic device property filters. Keys use "eventType.propertyName" dot notation. ' +
'See the device_properties catalog (call get_resource(name="device_properties")) for all available keys and types. ' +
@@ -30,6 +30,7 @@ const ALL_COLUMNS: ColumnDef[] = [
{ key: "duration", label: "Duration", defaultVisible: true, sortKey: "durationSeconds" },
{ key: "started", label: "Started", defaultVisible: true, sortKey: "startedAt" },
{ key: "country", label: "Country", defaultVisible: false, sortKey: "geoCountry", filterKey: "geoCountry" },
{ key: "apiLatency", label: "API Latency", defaultVisible: false, sortKey: "avgApiLatencyMs" },
{ key: "agentVersion", label: "Agent Version", defaultVisible: false, sortKey: "agentVersion", filterKey: "agentVersion" },
{ key: "osName", label: "OS Name", defaultVisible: false, sortKey: "osName", filterKey: "osName" },
{ key: "osBuild", label: "OS Build", defaultVisible: false, sortKey: "osBuild", filterKey: "osBuild" },
@@ -640,7 +641,7 @@ export function SessionTable({
currentSort={sortColumn}
direction={sortDirection}
onSort={onSort}
className={["eventCount", "duration", "started", "country", "agentVersion", "osName", "osBuild", "osDisplayVersion", "osEdition", "osLanguage"].includes(col.key) ? "px-3" : undefined}
className={["eventCount", "duration", "started", "country", "apiLatency", "agentVersion", "osName", "osBuild", "osDisplayVersion", "osEdition", "osLanguage"].includes(col.key) ? "px-3" : undefined}
filterKey={col.filterKey}
filterValues={col.filterKey ? uniqueValuesByField[col.filterKey] : undefined}
activeFilter={col.filterKey ? columnFilters[col.filterKey] : undefined}
@@ -904,6 +905,19 @@ function SessionCell({
</td>
);
case "apiLatency":
return (
<td className="px-3 py-4 whitespace-nowrap text-sm text-gray-500">
{(session.avgApiLatencyMs ?? 0) > 0 ? (
<span title={`Agent→backend HTTP round-trip${session.apiRequestCount ? ` across ${session.apiRequestCount} requests` : ""}`}>
{Math.round(session.avgApiLatencyMs!)} ms
</span>
) : (
<span className="text-gray-300">—</span>
)}
</td>
);
case "agentVersion": {
const fullVersion = session.agentVersion || "";
const shortVersion = fullVersion.split("+")[0];