feat(ops): ops events for Collect Logs usage and diagnostics-upload enablement

CollectLogsQuickConfigEnabled fires when a tenant admin switches on Hosted diagnostics upload through the session Collect Logs quick-config dialog (PUT ?intent=collect-logs -> write source portal-collect-logs); every other enable/disable path emits DiagnosticsUploadEnabled/Disabled (PUT, PATCH, revert, MCP). SessionActionQueued records portal-queued server actions. DiagnosticsUploadConfigChange is the single definition behind the diagnosticsUploadConfigured feature flag and the flip detection. Event types dual-registered in the OpsAlertRules catalog. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
fix(agent): rotate_config applies the fetched config; diagnostics skip gates report their reason
2026-10-25 13:10:13 +00:00 · 2026-08-29 19:30:20 +02:00 · 2026-08-29 19:30:00 +02:00 · 2026-08-29 19:21:47 +02:00 · 2026-08-29 18:35:47 +02:00 · 2026-08-29 17:55:50 +02:00
634 changed files with 50238 additions and 4553 deletions
@@ -0,0 +1,367 @@
+<#
+.SYNOPSIS
+    Publishes the customer-facing PowerShell scripts behind download.autopilotmonitor.com/agent/.
+
+.DESCRIPTION
+    Single owner of the script-publishing chain. Called from two places:
+
+      * publish-scripts.yml  -- on every push to main that touches the sources,
+                                so a script fix reaches customers without waiting
+                                for an agent release.
+      * build-agent.yml      -- on a publish_as_stable run, so a release always
+                                lands a consistent set (ZIP + manifest + scripts).
+
+    Both callers run the same code. The scripts on the download alias are the live
+    copy the WDP bootstrap MSI (Invoke-BootstrapDownload.ps1) downloads on every
+    enrolling device, so "current" is a correctness property, not cosmetics.
+
+    Steps, in order:
+      1. Parse $ScriptVersion from the bootstrap source.
+      2. Render the -Dev variant by literal substitution of the two URL/manifest
+         defaults. A missing anchor is a hard failure -- a silently un-substituted
+         dev script would point the dev fleet at the stable agent.
+      3. Version-bump guard: if the published bootstrap differs from the source
+         but carries the same $ScriptVersion, abort. Otherwise the docs badge,
+         version.json.bootstrapVersion and the portal's "your script is outdated"
+         hint would all keep asserting a version that is no longer what ships.
+      4. Upload every script blob with Cache-Control: no-cache (they rotate in
+         place), mirrored fail-soft to the legacy account.
+      5. Reconcile the two version oracles: version.json.bootstrapVersion
+         (read-modify-write under If-Match, so a concurrent agent release cannot
+         lose its agent fields) and AdminConfiguration.LatestBootstrapV2ScriptVersion.
+      6. Verify through the alias -- re-download each blob and compare SHA-256.
+
+.PARAMETER SasToken
+    Container SAS for the eu storage account with write permission. Leading '?' tolerated.
+
+.PARAMETER LegacySasToken
+    Container SAS for the legacy account. Optional -- a mirror failure warns, never fails.
+
+.PARAMETER TableSasToken
+    Table SAS for AdminConfiguration. Optional -- omitted or 'XXX' skips the oracle update.
+
+.PARAMETER RepoRoot
+    Repository root. Defaults to the parent of .github/scripts.
+
+.PARAMETER DryRun
+    Run every check and render, upload nothing.
+
+.EXAMPLE
+    ./Publish-BootstrapScripts.ps1 -DryRun
+
+.EXAMPLE
+    ./Publish-BootstrapScripts.ps1 -SasToken $env:SAS -TableSasToken $env:TABLE_SAS
+#>
+[CmdletBinding()]
+param(
+    [string]$SasToken,
+    [string]$LegacySasToken,
+    [string]$TableSasToken,
+    [string]$RepoRoot,
+    [switch]$DryRun
+)
+
+$ErrorActionPreference = 'Stop'
+
+if (-not $RepoRoot) {
+    $RepoRoot = (Resolve-Path (Join-Path $PSScriptRoot '../..')).Path
+}
+if (-not $DryRun -and [string]::IsNullOrWhiteSpace($SasToken)) {
+    throw 'SasToken is required unless -DryRun is used.'
+}
+
+$ContainerUrl       = 'https://autopilotmonitoreu.blob.core.windows.net/agent'
+$LegacyContainerUrl = 'https://autopilotmonitor.blob.core.windows.net/agent'
+$AliasUrl           = 'https://download.autopilotmonitor.com/agent'
+$TableUrl           = "https://autopilotmonitoreu.table.core.windows.net/AdminConfiguration(PartitionKey='GlobalConfig',RowKey='config')"
+
+$BootstrapSource   = Join-Path $RepoRoot 'scripts/Bootstrap/Install-AutopilotMonitor.ps1'
+$BootstrapBlob     = 'Install-AutopilotMonitor.ps1'
+$DevBlob           = 'Install-AutopilotMonitor-Dev.ps1'
+$ScriptContentType = 'text/plain; charset=utf-8'
+
+function Get-HttpStatus {
+    param($ErrorRecord)
+    if ($ErrorRecord.Exception.PSObject.Properties['Response'] -and $ErrorRecord.Exception.Response) {
+        return [int]$ErrorRecord.Exception.Response.StatusCode
+    }
+    return 0
+}
+
+function Get-Sha256 {
+    param([byte[]]$Bytes)
+    $sha = [System.Security.Cryptography.SHA256]::Create()
+    try { return [BitConverter]::ToString($sha.ComputeHash($Bytes)).Replace('-', '').ToLowerInvariant() }
+    finally { $sha.Dispose() }
+}
+
+# Raw bytes of a published blob, or $null when it does not exist yet.
+function Get-PublishedBytes {
+    param([string]$Url)
+    try {
+        $resp = Invoke-WebRequest -Uri $Url -Method Get -UseBasicParsing
+    } catch {
+        if ((Get-HttpStatus $_) -eq 404) { return $null }
+        throw
+    }
+    # Comma operator: PowerShell unrolls an array returned from a function into the output
+    # stream and reassembles it as Object[], which would silently defeat every [byte[]] use
+    # downstream. ',' wraps it so the byte[] survives the return.
+    if ($resp.Content -is [byte[]]) { return ,$resp.Content }
+    return ,[System.Text.Encoding]::UTF8.GetBytes([string]$resp.Content)
+}
+
+# Deterministic publish form: CRLF, UTF-8 without BOM. Git normalises line endings on
+# checkout (a Windows runner yields CRLF, a core.autocrlf=false clone yields LF), so
+# publishing the raw working-copy bytes would emit different blobs for identical source
+# and make every byte comparison -- guard and verify alike -- environment-dependent.
+# CRLF is also what PS 5.1 on the device expects and what is published today.
+function Get-PublishBytes {
+    param([string]$Text)
+    $normalised = $Text.Replace("`r`n", "`n").Replace("`n", "`r`n")
+    # ',' keeps this a byte[]: without it PowerShell unrolls the array into the output stream
+    # and the caller receives Object[]. Invoke-RestMethod then serialises an Object[] body as
+    # space-separated decimals instead of raw bytes -- a silent corruption of the upload.
+    return ,(New-Object System.Text.UTF8Encoding $false).GetBytes($normalised)
+}
+
+function Get-BootstrapScriptVersion {
+    param([string]$Content, [string]$Origin, [switch]$Optional)
+    if ($Content -match '\$ScriptVersion\s*=\s*"([\d\.\-a-zA-Z]+)"') { return $Matches[1] }
+    # Unreadable SOURCE is fatal. An unreadable PUBLISHED copy must not be: that is exactly
+    # the state a republish is meant to repair, and a guard that blocks the repair is worse
+    # than no guard.
+    if ($Optional) { return $null }
+    throw "Could not parse ScriptVersion from $Origin"
+}
+
+# What the script actually DOES, with comments and layout removed: the PowerShell token
+# stream minus comments, newlines and line continuations. Lets the version-bump guard tell
+# a behaviour change (must be versioned -- consumers act on the version) apart from a
+# comment fix or reflow (nobody needs to know). Tokenising rather than regex-stripping
+# keeps '#' inside strings from being mistaken for a comment.
+function Get-CodeFingerprint {
+    param([string]$Text, [string]$Origin)
+    $tokens = $null
+    $errors = $null
+    [System.Management.Automation.Language.Parser]::ParseInput($Text, [ref]$tokens, [ref]$errors) | Out-Null
+    if ($errors -and $errors.Count -gt 0) {
+        throw "Parse error in ${Origin}: $($errors[0])"
+    }
+    $ignored = @('Comment', 'NewLine', 'LineContinuation', 'EndOfInput')
+    return (($tokens | Where-Object { $ignored -notcontains $_.Kind.ToString() } | ForEach-Object { $_.Text }) -join "`n")
+}
+
+# ------------------------------------------------------------------ 1. source
+$sourceContent = Get-Content $BootstrapSource -Raw
+$sourceBytes   = Get-PublishBytes $sourceContent
+$scriptVersion = Get-BootstrapScriptVersion -Content $sourceContent -Origin $BootstrapSource
+Write-Host "Bootstrap script version: $scriptVersion"
+
+# ------------------------------------------------------------------ 2. dev render
+$stableUrlLiteral = '$AgentDownloadUrl = "https://download.autopilotmonitor.com/agent/AutopilotMonitor-Agent.zip"'
+$devUrlLiteral    = '$AgentDownloadUrl = "https://download.autopilotmonitor.com/agent/AutopilotMonitor-Agent-dev.zip"'
+$stableManLiteral = '$VersionJsonName = "version.json"'
+$devManLiteral    = '$VersionJsonName = "version-dev.json"'
+
+if ($sourceContent.IndexOf($stableUrlLiteral) -lt 0 -or $sourceContent.IndexOf($stableManLiteral) -lt 0) {
+    throw "Bootstrap dev-render: anchor literal missing in $BootstrapSource"
+}
+$devContent = $sourceContent.Replace($stableUrlLiteral, $devUrlLiteral).Replace($stableManLiteral, $devManLiteral)
+Write-Host "Rendered $DevBlob (dev agent URL + version-dev.json)"
+
+# ------------------------------------------------------------------ 3. bump guard
+$publishedBytes = Get-PublishedBytes "$AliasUrl/$BootstrapBlob"
+if ($null -eq $publishedBytes) {
+    Write-Host 'No published bootstrap yet -- version-bump guard skipped (first publish)'
+} elseif ((Get-Sha256 $publishedBytes) -eq (Get-Sha256 $sourceBytes)) {
+    Write-Host 'Published bootstrap is already byte-identical to the source'
+} else {
+    $publishedText    = [System.Text.Encoding]::UTF8.GetString($publishedBytes)
+    $publishedVersion = Get-BootstrapScriptVersion -Content $publishedText -Origin "$AliasUrl/$BootstrapBlob" -Optional
+
+    if ($null -eq $publishedVersion) {
+        Write-Host "::warning::The published $BootstrapBlob is not a readable bootstrap script (no ScriptVersion found). Republishing over it."
+    } elseif ($publishedVersion -ne $scriptVersion) {
+        Write-Host "Version bump: $publishedVersion -> $scriptVersion"
+    } elseif ((Get-CodeFingerprint -Text $publishedText -Origin "$AliasUrl/$BootstrapBlob") -eq
+              (Get-CodeFingerprint -Text $sourceContent -Origin $BootstrapSource)) {
+        # Comments, typos in comments, reflow -- nothing a consumer of the version can act on.
+        Write-Host "::warning::$BootstrapBlob changed in comments or formatting only; publishing under the unchanged version $scriptVersion."
+    } else {
+        throw ("Version-bump guard: $BootstrapBlob changed behaviour but ScriptVersion is still $scriptVersion. " +
+               "Bump it in $BootstrapSource -- the docs badge, version.json.bootstrapVersion and the " +
+               'portal outdated-script hint all read that value, and customers decide from it whether ' +
+               'to re-upload their Intune copy. Comment-only and formatting changes do not need a bump.')
+    }
+}
+
+# ------------------------------------------------------------------ 4. upload
+# Sources beyond the bootstrap pair, read straight from the repo.
+$extraSources = @(
+    @{ Path = 'scripts/Bootstrap/Test-ShouldBootstrapAgent.ps1';       BlobName = 'Test-ShouldBootstrapAgent.ps1' }
+    # Customer-side Graph add-on grant script -- docs and admin UI link it directly.
+    @{ Path = 'scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1'; BlobName = 'Grant-AutopilotMonitorAddOn.ps1' }
+)
+# Uninstall-AutopilotMonitor.ps1 is deliberately NOT published: nothing links it, and
+# an unauthenticated uninstall script on the public download host is not a feature.
+
+$publishSet = [System.Collections.Generic.List[object]]::new()
+$publishSet.Add([pscustomobject]@{ BlobName = $BootstrapBlob; Bytes = $sourceBytes })
+$publishSet.Add([pscustomobject]@{ BlobName = $DevBlob;       Bytes = (Get-PublishBytes $devContent) })
+foreach ($extra in $extraSources) {
+    $extraPath = Join-Path $RepoRoot $extra.Path
+    if (-not (Test-Path $extraPath)) {
+        throw "Publish source missing: $extraPath"
+    }
+    $publishSet.Add([pscustomobject]@{ BlobName = $extra.BlobName; Bytes = (Get-PublishBytes (Get-Content $extraPath -Raw)) })
+}
+
+$legacySas = if ($LegacySasToken) { $LegacySasToken.TrimStart('?') } else { '' }
+$writeSas  = if ($SasToken) { $SasToken.TrimStart('?') } else { '' }
+
+foreach ($item in $publishSet) {
+    # Explicit type, not a convenience: an Object[] body is uploaded as space-separated
+    # decimals rather than raw bytes, and every hash check still passes because [byte[]]
+    # parameter coercion repairs it everywhere EXCEPT the wire.
+    [byte[]]$bytes = $item.Bytes
+    $item | Add-Member -NotePropertyName Sha256 -NotePropertyValue (Get-Sha256 $bytes) -Force
+
+    if ($DryRun) {
+        # Doubles as a drift check: says per blob whether the alias already serves this source.
+        $served = Get-PublishedBytes "$AliasUrl/$($item.BlobName)"
+        $state = if ($null -eq $served) { 'MISSING on the alias' }
+                 elseif ((Get-Sha256 $served) -eq $item.Sha256) { 'already current' }
+                 else { 'STALE on the alias' }
+        Write-Host "  [dry-run] $($item.BlobName) ($($bytes.Length) bytes, sha256 $($item.Sha256)) -- $state"
+        continue
+    }
+
+    # no-cache on every blob: they all rotate in place and the download alias fronts them
+    # with Front Door. Route caching is disabled there, but a stale script paired with a
+    # fresh manifest would fail the bootstrap SHA check -- this keeps that class of bug
+    # impossible even if caching is ever re-enabled.
+    $headers = @{ 'x-ms-blob-type' = 'BlockBlob'; 'Content-Type' = $ScriptContentType; 'x-ms-blob-cache-control' = 'no-cache' }
+    Invoke-RestMethod -Uri "$ContainerUrl/$($item.BlobName)?$writeSas" -Method Put -Headers $headers -Body $bytes | Out-Null
+
+    # Read straight back from the blob (authoritative, no CDN in the way) before touching the
+    # mirror or the next file. The alias verification at the end would catch a bad body too,
+    # but only after every blob was already overwritten -- these are live customer downloads.
+    $written = Get-PublishedBytes "$ContainerUrl/$($item.BlobName)"
+    if ($null -eq $written -or (Get-Sha256 $written) -ne $item.Sha256) {
+        $writtenLength = if ($null -eq $written) { 'missing' } else { "$($written.Length) bytes" }
+        throw ("Upload of $($item.BlobName) did not round-trip: sent $($bytes.Length) bytes, " +
+               "blob now holds $writtenLength. Publishing stopped before the mirror and the " +
+               'remaining files, so no further blob was touched.')
+    }
+    Write-Host "  uploaded $($item.BlobName) ($($bytes.Length) bytes, round-trip verified)"
+
+    if ($legacySas) {
+        try {
+            Invoke-RestMethod -Uri "$LegacyContainerUrl/$($item.BlobName)?$legacySas" -Method Put -Headers $headers -Body $bytes | Out-Null
+            Write-Host "  mirrored $($item.BlobName) to legacy storage"
+        } catch {
+            Write-Host "::warning::legacy mirror failed for $($item.BlobName) -- $($_.Exception.Message)"
+        }
+    }
+}
+
+# ------------------------------------------------------------------ 5. version oracles
+# version.json is the agent manifest; only bootstrapVersion belongs to us. Read from the
+# blob (not the alias) for an authoritative ETag, write back under If-Match so a concurrent
+# agent release cannot lose its version/sha256 fields.
+if (-not $DryRun) {
+    try {
+        $manifestResp = Invoke-WebRequest -Uri "$ContainerUrl/version.json" -Method Get -UseBasicParsing
+        $manifestRaw = if ($manifestResp.Content -is [byte[]]) {
+            [System.Text.Encoding]::UTF8.GetString($manifestResp.Content)
+        } else { [string]$manifestResp.Content }
+        $manifest = $manifestRaw | ConvertFrom-Json
+
+        if ($manifest.bootstrapVersion -eq $scriptVersion) {
+            Write-Host "version.json already reports bootstrapVersion $scriptVersion"
+        } else {
+            $etag = '"' + ([string]($manifestResp.Headers['ETag'] | Select-Object -First 1)).Trim('"') + '"'
+            $manifest | Add-Member -NotePropertyName 'bootstrapVersion' -NotePropertyValue $scriptVersion -Force
+            $body = [System.Text.Encoding]::UTF8.GetBytes(($manifest | ConvertTo-Json -Compress))
+            $manifestHeaders = @{
+                'x-ms-blob-type'          = 'BlockBlob'
+                'Content-Type'            = 'application/json'
+                'x-ms-blob-cache-control' = 'no-cache'
+                'If-Match'                = $etag
+            }
+            Invoke-RestMethod -Uri "$ContainerUrl/version.json?$writeSas" -Method Put -Headers $manifestHeaders -Body $body | Out-Null
+            Write-Host "version.json bootstrapVersion -> $scriptVersion (agent fields untouched)"
+
+            if ($legacySas) {
+                try {
+                    $legacyHeaders = @{ 'x-ms-blob-type' = 'BlockBlob'; 'Content-Type' = 'application/json'; 'x-ms-blob-cache-control' = 'no-cache' }
+                    Invoke-RestMethod -Uri "$LegacyContainerUrl/version.json?$legacySas" -Method Put -Headers $legacyHeaders -Body $body | Out-Null
+                } catch {
+                    Write-Host "::warning::legacy mirror failed for version.json -- $($_.Exception.Message)"
+                }
+            }
+        }
+    } catch {
+        if ((Get-HttpStatus $_) -eq 412) {
+            throw 'version.json changed while publishing (concurrent agent release). Re-run this workflow.'
+        }
+        throw
+    }
+}
+
+$tableSas = if ($TableSasToken) { $TableSasToken.TrimStart('?') } else { '' }
+if ($DryRun) {
+    Write-Host "  [dry-run] would set AdminConfiguration.LatestBootstrapV2ScriptVersion = $scriptVersion"
+} elseif ([string]::IsNullOrEmpty($tableSas) -or $tableSas -eq 'XXX') {
+    Write-Host 'SKIPPED: AdminConfiguration update -- set AZURE_TABLE_ADMIN_SAS_TOKEN to enable the portal version oracle'
+} else {
+    $tableHeaders = @{
+        'Content-Type' = 'application/json'
+        'Accept'       = 'application/json;odata=nometadata'
+        'If-Match'     = '*'
+    }
+    $tableBody = @{ LatestBootstrapV2ScriptVersion = $scriptVersion } | ConvertTo-Json
+    Invoke-RestMethod -Uri "$TableUrl`?$tableSas" -Method Merge -Headers $tableHeaders -Body $tableBody | Out-Null
+    Write-Host "AdminConfiguration.LatestBootstrapV2ScriptVersion = $scriptVersion"
+}
+
+# ------------------------------------------------------------------ 6. verify via alias
+if (-not $DryRun) {
+    $pending = [System.Collections.ArrayList]::new()
+    $publishSet | ForEach-Object { [void]$pending.Add($_) }
+
+    for ($attempt = 1; $attempt -le 6 -and $pending.Count -gt 0; $attempt++) {
+        if ($attempt -gt 1) { Start-Sleep -Seconds 20 }
+        foreach ($item in @($pending)) {
+            $servedBytes = Get-PublishedBytes "$AliasUrl/$($item.BlobName)"
+            if ($null -ne $servedBytes -and (Get-Sha256 $servedBytes) -eq $item.Sha256) {
+                Write-Host "  verified $($item.BlobName) via $AliasUrl"
+                $pending.Remove($item)
+            }
+        }
+        if ($pending.Count -gt 0) {
+            Write-Host "  attempt $attempt : $($pending.Count) blob(s) not current on the alias yet"
+        }
+    }
+
+    if ($pending.Count -gt 0) {
+        $names = ($pending | ForEach-Object { $_.BlobName }) -join ', '
+        throw ("Alias still serves stale content for: $names. The blobs were written, so this is a Front Door " +
+               'cache issue -- purge with: az afd endpoint purge --resource-group rg-autopilotmonitor-prd-gwc ' +
+               "--profile-name autopilotmonitor-fd --endpoint-name apm-download --content-paths '/agent/*'")
+    }
+}
+
+if ($env:GITHUB_STEP_SUMMARY) {
+    $mode = if ($DryRun) { 'DRY RUN -- nothing uploaded' } else { 'published + verified via the download alias' }
+    $summary = @(
+        "### Bootstrap scripts: $mode",
+        '',
+        "Bootstrap script version: **$scriptVersion**",
+        ''
+    ) + ($publishSet | ForEach-Object { "- $($_.BlobName) -- sha256 $($_.Sha256)" })
+    ($summary -join [Environment]::NewLine) | Out-File -FilePath $env:GITHUB_STEP_SUMMARY -Append -Encoding utf8
+}
+
+Write-Host 'Done.'
@@ -0,0 +1,63 @@
+name: Bootstrap script gates
+
+# Quality gate for the customer-facing PowerShell scripts, factored out so it exists
+# once and both callers run the identical checks:
+#   * pester.yml           -- pull requests (reports, does not block the merge button)
+#   * publish-scripts.yml  -- pushes to main, where it BLOCKS the upload to the
+#                             download alias. Devices execute these scripts as SYSTEM
+#                             during enrollment, so a red suite must never ship.
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  gates:
+    name: Bootstrap guard tests (PS 5.1)
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Install Pester 5+
+        shell: powershell
+        run: |
+          Install-PackageProvider -Name NuGet -MinimumVersion 2.8.5.201 -Force -Scope CurrentUser | Out-Null
+          Install-Module Pester -Scope CurrentUser -Force -SkipPublisherCheck -MinimumVersion 5.5.0
+
+      # Windows PowerShell 5.1 on purpose: that is the runtime IME uses to execute
+      # platform scripts, so guard/relax logic is verified without resetting a device.
+      - name: Run Pester
+        shell: powershell
+        run: |
+          Import-Module Pester -MinimumVersion 5.5.0
+          $c = New-PesterConfiguration
+          $c.Run.Path = 'scripts/Bootstrap'
+          $c.Run.Exit = $true
+          $c.Output.Verbosity = 'Detailed'
+          Invoke-Pester -Configuration $c
+
+      - name: Guard scripts stay pure ASCII
+        shell: powershell
+        run: |
+          $failed = $false
+          Get-ChildItem 'scripts/Bootstrap' -Filter '*.ps1' | ForEach-Object {
+            $bytes = [System.IO.File]::ReadAllBytes($_.FullName)
+            for ($i = 0; $i -lt $bytes.Length; $i++) {
+              if ($bytes[$i] -gt 127) {
+                Write-Host "::error file=scripts/Bootstrap/$($_.Name)::Non-ASCII byte 0x$('{0:X2}' -f $bytes[$i]) at offset $i. PS 5.1 (IME) reads BOM-less files as ANSI and corrupts multi-byte chars."
+                $failed = $true
+                break
+              }
+            }
+          }
+          if ($failed) { exit 1 }
+          Write-Host 'All bootstrap scripts are pure ASCII.'
+
+      # The publish chain renders the -Dev variant by literal substitution and refuses to
+      # ship when an anchor moved. Running it dry here surfaces that (and any drift against
+      # the alias) on the PR instead of on the push that would have published.
+      - name: Publish dry run (dev-render anchors + version-bump guard + drift)
+        shell: pwsh
+        run: ./.github/scripts/Publish-BootstrapScripts.ps1 -DryRun
@@ -33,6 +33,13 @@ permissions:
  id-token: write      # keyless Sigstore signing (artifact attestation)
  attestations: write  # store the provenance attestation

+# Shared with publish-scripts.yml: both write version.json (this workflow the agent fields,
+# the script publisher bootstrapVersion under If-Match). Serialising them keeps a script push
+# from colliding with a release. Never cancel -- a half-published set is worse than a queue.
+concurrency:
+  group: agent-blob-publish
+  cancel-in-progress: false
+
 env:
  LINE_MAJOR: 2
  AGENT_PROJECT: src/Agent/AutopilotMonitor.Agent.V2/AutopilotMonitor.Agent.V2.csproj
@@ -46,8 +53,6 @@ env:
  VERSIONED_ZIP: AutopilotMonitor-Agent-v2.zip
  STABLE_ZIP: AutopilotMonitor-Agent.zip
  STABLE_MANIFEST: version.json
-  STABLE_BOOTSTRAP: Install-AutopilotMonitor.ps1
-  STABLE_BOOTSTRAP_DEV: Install-AutopilotMonitor-Dev.ps1

 jobs:
  build:
@@ -181,6 +186,8 @@ jobs:
          # commit/buildUtc are the same two fields the backend and MCP manifests carry —
          # additive, and the bootstrap reads this file by field name, so older installers
          # ignore them. sha256/bootstrapVersion stay: those are the customer contract.
+          # bootstrapVersion is seeded here so the published manifest is never briefly
+          # missing it; Publish-BootstrapScripts.ps1 owns and re-asserts the field afterwards.
          $manifest | Add-Member -NotePropertyName "sha256" -NotePropertyValue $sha256Hash -Force
          $manifest | Add-Member -NotePropertyName "commit" -NotePropertyValue '${{ github.sha }}'.Substring(0, 7) -Force
          $manifest | Add-Member -NotePropertyName "buildUtc" -NotePropertyValue ([DateTime]::UtcNow.ToString('o')) -Force
@@ -190,29 +197,12 @@ jobs:
          $manifest | ConvertTo-Json -Compress | Set-Content $env:MANIFEST_NAME -Encoding UTF8
          Write-Host "$env:MANIFEST_NAME content: $(Get-Content $env:MANIFEST_NAME)"

-          # Bootstrap = single generic source. Stable variant = source 1:1.
-          # Dev variant = literal-string substitution of the two URL/manifest defaults.
-          # Both are uploaded only on -PublishAsStable runs (versioned namespace doesn't carry bootstrap).
-          if ('${{ inputs.publish_as_stable }}' -eq 'true') {
-            $stableUrl = '$AgentDownloadUrl = "https://download.autopilotmonitor.com/agent/AutopilotMonitor-Agent.zip"'
-            $devUrl    = '$AgentDownloadUrl = "https://download.autopilotmonitor.com/agent/AutopilotMonitor-Agent-dev.zip"'
-            $stableMan = '$VersionJsonName = "version.json"'
-            $devMan    = '$VersionJsonName = "version-dev.json"'
-
-            Copy-Item $env:BOOTSTRAP_SOURCE $env:STABLE_BOOTSTRAP -Force
-            $content = Get-Content $env:BOOTSTRAP_SOURCE -Raw
-            if ($content.IndexOf($stableUrl) -lt 0 -or $content.IndexOf($stableMan) -lt 0) {
-              Write-Error "Bootstrap dev-render: anchor literal missing in $env:BOOTSTRAP_SOURCE"
-              exit 1
-            }
-            $devContent = $content.Replace($stableUrl, $devUrl).Replace($stableMan, $devMan)
-            [System.IO.File]::WriteAllText("$env:STABLE_BOOTSTRAP_DEV", $devContent, (New-Object System.Text.UTF8Encoding $false))
-          }
+          # The customer-facing scripts (stable + dev render, test script, grant script) are
+          # published by .github/scripts/Publish-BootstrapScripts.ps1 -- see the upload step.

          "versioned_zip_release=$versionedZip" >> $env:GITHUB_OUTPUT
          "sha256=$sha256Hash" >> $env:GITHUB_OUTPUT
          "exe_sha256=$exeSha256Hash" >> $env:GITHUB_OUTPUT
-          "bootstrap_version=$bootstrapVersion" >> $env:GITHUB_OUTPUT

      - name: Upload to Azure Blob Storage
        if: inputs.upload_blob
@@ -264,22 +254,21 @@ jobs:
            Write-Host "PUBLISH AS STABLE -- writing V2 into stable namespace (customer-facing)" -ForegroundColor Magenta
            Send-Blob -Local $env:VERSIONED_ZIP -BlobName $env:STABLE_ZIP -ContentType "application/zip"
            Send-Blob -Local $env:MANIFEST_NAME -BlobName $env:STABLE_MANIFEST -ContentType "application/json"
-            Send-Blob -Local $env:STABLE_BOOTSTRAP -BlobName $env:STABLE_BOOTSTRAP -ContentType "text/plain; charset=utf-8"
-            Send-Blob -Local $env:STABLE_BOOTSTRAP_DEV -BlobName $env:STABLE_BOOTSTRAP_DEV -ContentType "text/plain; charset=utf-8"

-            if (Test-Path "scripts/Bootstrap/Test-ShouldBootstrapAgent.ps1") {
-              Send-Blob -Local "scripts/Bootstrap/Test-ShouldBootstrapAgent.ps1" -BlobName "Test-ShouldBootstrapAgent.ps1" -ContentType "text/plain; charset=utf-8"
-            }
-
-            # Customer-side Graph add-on grant script -- docs and admin UI link
-            # https://download.autopilotmonitor.com/agent/Grant-AutopilotMonitorAddOn.ps1
-            if (Test-Path "scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1") {
-              Send-Blob -Local "scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1" -BlobName "Grant-AutopilotMonitorAddOn.ps1" -ContentType "text/plain; charset=utf-8"
-            }
+            # Customer-facing scripts: same publisher publish-scripts.yml runs on every push
+            # to main, so a release lands a set that is consistent with what is already live
+            # (dev render, version-bump guard, bootstrapVersion oracles, alias verification).
+            # Runs AFTER version.json so its bootstrapVersion read sees this build's manifest.
+            ./.github/scripts/Publish-BootstrapScripts.ps1 `
+              -SasToken '${{ secrets.AZURE_BLOB_AGENT_SAS_TOKEN }}' `
+              -LegacySasToken '${{ secrets.AZURE_BLOB_AGENT_LEGACY_SAS_TOKEN }}' `
+              -TableSasToken '${{ secrets.AZURE_TABLE_ADMIN_SAS_TOKEN }}'
          }

          # Update AdminConfiguration LatestAgentV2* -- ONLY on stable cutover. The hash-oracle
          # must never point at a build that is not actually in the stable namespace.
+          # LatestBootstrapV2ScriptVersion is NOT set here: it belongs to the script publisher
+          # above, which also owns it on script-only pushes. One writer per field.
          $tableSasToken = "${{ secrets.AZURE_TABLE_ADMIN_SAS_TOKEN }}".TrimStart('?')
          if ('${{ inputs.publish_as_stable }}' -ne 'true') {
            Write-Host "SKIPPED: AdminConfiguration update (versioned-only run -- stable namespace unchanged)"
@@ -289,22 +278,18 @@ jobs:
            $sha256 = "${{ steps.artifact.outputs.sha256 }}"
            $exeSha256 = "${{ steps.artifact.outputs.exe_sha256 }}"
            $agentVersion = "${{ steps.version.outputs.version }}"
-            $bootstrapVersion = "${{ steps.artifact.outputs.bootstrap_version }}"
            $tableUrl = "https://autopilotmonitoreu.table.core.windows.net/AdminConfiguration(PartitionKey='GlobalConfig',RowKey='config')?$tableSasToken"
            $tableBody = @{
              LatestAgentV2Version    = $agentVersion
              LatestAgentV2Sha256     = $sha256
              LatestAgentV2ExeSha256  = $exeSha256
            }
-            if ($bootstrapVersion) {
-              $tableBody["LatestBootstrapV2ScriptVersion"] = $bootstrapVersion
-            }
            Invoke-RestMethod -Uri $tableUrl -Method Merge -Headers @{
              "Content-Type" = "application/json"
              "Accept"       = "application/json;odata=nometadata"
              "If-Match"     = "*"
            } -Body ($tableBody | ConvertTo-Json)
-            Write-Host "AdminConfiguration updated: V2 version=$agentVersion, sha256=$sha256, exeSha256=$exeSha256, bootstrapVersion=$bootstrapVersion"
+            Write-Host "AdminConfiguration updated: V2 version=$agentVersion, sha256=$sha256, exeSha256=$exeSha256"
          }

      # Sigstore keyless provenance: binds the ZIP digest to this workflow run (repo, ref,
@@ -0,0 +1,139 @@
+name: Build & Publish Bootstrap MSI
+
+# Thin MDM LOB delivery vehicle for WDP (Autopilot v2) — see
+# src/Agent/AutopilotMonitor.BootstrapMsi/Package.wxs. The MSI carries no bootstrap
+# logic (only the runner script that downloads the CURRENT server-hosted
+# Install-AutopilotMonitor.ps1), so it is rebuilt rarely: only when the runner script
+# or the WiX package changes. Version lives in Package.wxs — bump it there before
+# dispatching so Intune LOB update detection sees a new ProductVersion.
+
+on:
+  workflow_dispatch:
+    inputs:
+      upload_blob:
+        description: 'Upload to blob (customer-facing via download.autopilotmonitor.com/agent/)'
+        required: true
+        type: boolean
+        default: true
+
+permissions:
+  contents: read
+  id-token: write      # keyless Sigstore signing (artifact attestation)
+  attestations: write  # store the provenance attestation
+
+env:
+  MSI_PROJECT_DIR: src/Agent/AutopilotMonitor.BootstrapMsi
+  RUNNER_SCRIPT: src/Agent/AutopilotMonitor.BootstrapMsi/Invoke-BootstrapDownload.ps1
+  STABLE_MSI: AutopilotMonitor-Bootstrap.msi
+
+jobs:
+  build:
+    runs-on: windows-latest
+    name: Build Bootstrap MSI
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v7
+
+      # The runner executes as SYSTEM on every enrolling device — a parse error or
+      # non-ASCII mojibake (PS 5.1 codepage roulette) must fail the build, not the fleet.
+      - name: Validate runner script (parse + ASCII-only)
+        shell: pwsh
+        run: |
+          $errs = $null
+          [System.Management.Automation.Language.Parser]::ParseFile((Resolve-Path $env:RUNNER_SCRIPT), [ref]$null, [ref]$errs) | Out-Null
+          if ($errs) { $errs | ForEach-Object { Write-Error $_.ToString() }; exit 1 }
+          if ((Get-Content $env:RUNNER_SCRIPT -Raw) -match '[^\x00-\x7F]') {
+            Write-Error "Runner script contains non-ASCII characters"
+            exit 1
+          }
+          Write-Host "Runner script parse + ASCII check passed"
+
+      - name: Read MSI version from Package.wxs
+        id: version
+        shell: pwsh
+        run: |
+          $wxs = Get-Content "$env:MSI_PROJECT_DIR/Package.wxs" -Raw
+          if ($wxs -notmatch 'Version="(\d+\.\d+\.\d+)"') {
+            Write-Error "Could not parse Version from Package.wxs"
+            exit 1
+          }
+          $version = $Matches[1]
+          Write-Host "MSI version (from Package.wxs): $version"
+          "version=$version" >> $env:GITHUB_OUTPUT
+
+      - name: Install WiX toolset
+        run: dotnet tool install --global wix --version "5.*"
+
+      - name: Build MSI
+        shell: pwsh
+        run: |
+          # wix resolves File/@Source relative to the working directory, not the wxs —
+          # build from inside the project dir (same as the local build documented in the wxs).
+          $out = Join-Path (Get-Location) $env:STABLE_MSI
+          Push-Location $env:MSI_PROJECT_DIR
+          wix build Package.wxs -arch x64 -o $out
+          Pop-Location
+          if (-not (Test-Path $env:STABLE_MSI)) { Write-Error "wix build produced no MSI"; exit 1 }
+          $sha256 = (Get-FileHash $env:STABLE_MSI -Algorithm SHA256).Hash.ToLowerInvariant()
+          Write-Host "Built $env:STABLE_MSI ($([math]::Round((Get-Item $env:STABLE_MSI).Length / 1KB)) KB)"
+          Write-Host "SHA-256: $sha256"
+
+      - name: Upload to Azure Blob Storage
+        if: inputs.upload_blob
+        shell: pwsh
+        run: |
+          $containerUrl = "https://autopilotmonitoreu.blob.core.windows.net/agent"
+          $sasToken = "${{ secrets.AZURE_BLOB_AGENT_SAS_TOKEN }}".TrimStart('?')
+          $version = "${{ steps.version.outputs.version }}"
+
+          # Same Send-Blob contract as build-agent.yml: no-cache on every blob because the
+          # stable name rotates in place behind the download alias. No legacy mirror — the
+          # MSI channel never existed on the legacy account.
+          function Send-Blob {
+            param([string]$Local, [string]$BlobName)
+            $bytes = [System.IO.File]::ReadAllBytes($Local)
+            $headers = @{
+              "x-ms-blob-type" = "BlockBlob"
+              "Content-Type" = "application/octet-stream"
+              "x-ms-blob-cache-control" = "no-cache"
+            }
+            $md5 = [System.Security.Cryptography.MD5]::Create()
+            $headers["Content-MD5"] = [Convert]::ToBase64String($md5.ComputeHash($bytes))
+            $md5.Dispose()
+            Write-Host "Uploading $BlobName ($([math]::Round($bytes.Length / 1KB)) KB)..."
+            Invoke-RestMethod -Uri "$containerUrl/$BlobName`?$sasToken" -Method Put -Headers $headers -Body $bytes
+            Write-Host "  uploaded $BlobName"
+          }
+
+          # Versioned copy for provenance/rollback + stable customer-facing name.
+          Send-Blob -Local $env:STABLE_MSI -BlobName "AutopilotMonitor-Bootstrap-v$version.msi"
+          Send-Blob -Local $env:STABLE_MSI -BlobName $env:STABLE_MSI
+
+      # E2E: the Front Door route /agent/* must serve the fresh bytes on the public alias.
+      - name: Verify download alias serves the MSI
+        if: inputs.upload_blob
+        shell: pwsh
+        run: |
+          $localSize = (Get-Item $env:STABLE_MSI).Length
+          $resp = Invoke-WebRequest -Uri "https://download.autopilotmonitor.com/agent/$env:STABLE_MSI" -Method Head -UseBasicParsing
+          if ($resp.StatusCode -ne 200) { Write-Error "Alias HEAD returned $($resp.StatusCode)"; exit 1 }
+          $remoteSize = [long]$resp.Headers['Content-Length'][0]
+          if ($remoteSize -ne $localSize) {
+            Write-Error "Size mismatch: alias serves $remoteSize bytes, local MSI is $localSize bytes"
+            exit 1
+          }
+          Write-Host "Alias verified: https://download.autopilotmonitor.com/agent/$env:STABLE_MSI ($remoteSize bytes)"
+
+      # Sigstore keyless provenance, same as the agent ZIP. Verify:
+      # gh attestation verify AutopilotMonitor-Bootstrap.msi --repo okieselbach/AutopilotMonitor
+      - name: Attest build provenance (MSI)
+        uses: actions/attest-build-provenance@v4
+        with:
+          subject-path: ${{ env.STABLE_MSI }}
+
+      - name: Upload build artifact
+        uses: actions/upload-artifact@v7
+        with:
+          name: AutopilotMonitor-Bootstrap-v${{ steps.version.outputs.version }}
+          path: ${{ env.STABLE_MSI }}
@@ -11,7 +11,11 @@ env:
  ACR_NAME: autopilotmonitoreuacr
  CONTAINER_APP_NAME: autopilotmonitor-mcp
  RESOURCE_GROUP: ${{ secrets.AZURE_MCP_RESOURCE_GROUP }}
-  IMAGE_TAG: ${{ github.sha }}
+  # Unique per RUN, not per commit: the docs corpus is baked into the image, so a
+  # docs-only redeploy at an unchanged code sha must still produce a new image
+  # reference — with a sha-only tag `az containerapp update` saw the same image
+  # and silently created no revision (2026-08-28).
+  IMAGE_TAG: ${{ github.sha }}-${{ github.run_number }}
  HEALTH_URL: https://mcp.autopilotmonitor.com/health
  VERSIONS_CONTAINER: https://autopilotmonitoreu.blob.core.windows.net/versions
  PACKAGE_JSON: src/McpServer/autopilot-monitor-mcp/package.json
@@ -28,8 +32,9 @@ jobs:
      # baked into the image as the search_docs corpus (see the Dockerfile). No
      # token is needed. Checking it out here rather than vendoring it keeps the
      # docs single-sourced — but it also means EDITING THE DOCS DOES NOT UPDATE A
-      # RUNNING SERVER; this workflow must be re-run. /health reports the SHA
-      # captured below so that staleness is checkable.
+      # RUNNING SERVER; this workflow must be re-run (IMAGE_TAG is per run so the
+      # re-run actually rolls a new revision). /health reports the SHA captured
+      # below so that staleness is checkable.
      - name: Check out documentation bundle
        uses: actions/checkout@v7
        with:
@@ -1,16 +1,20 @@
 name: Pester (Bootstrap scripts)

-# Runs the Pester suite for the Intune bootstrap scripts under Windows PowerShell 5.1
-# (the runtime IME uses to execute platform scripts) so guard/relax logic changes are
-# verified without resetting a device. Like ci.yml it reports rather than blocks.
+# Pull-request view of the bootstrap script gates. Like ci.yml it reports rather than
+# blocks the merge button.
+#
+# There is deliberately no push trigger: publish-scripts.yml runs the very same
+# reusable gate workflow on every push to main and blocks the upload to the download
+# alias on it. A push trigger here would only duplicate that run, with no consequence.

 on:
-  push:
-    branches: [main]
-    paths: ['scripts/Bootstrap/**']
  pull_request:
    branches: [main]
-    paths: ['scripts/Bootstrap/**']
+    paths:
+      - 'scripts/Bootstrap/**'
+      - 'scripts/CustomerSetup/**'
+      - '.github/scripts/Publish-BootstrapScripts.ps1'
+      - '.github/workflows/bootstrap-script-gates.yml'
  workflow_dispatch:

 permissions:
@@ -21,41 +25,5 @@ concurrency:
  cancel-in-progress: true

 jobs:
-  pester:
-    name: Bootstrap guard tests (PS 5.1)
-    runs-on: windows-latest
-    steps:
-      - uses: actions/checkout@v7
-
-      - name: Install Pester 5+
-        shell: powershell
-        run: |
-          Install-PackageProvider -Name NuGet -MinimumVersion 2.8.5.201 -Force -Scope CurrentUser | Out-Null
-          Install-Module Pester -Scope CurrentUser -Force -SkipPublisherCheck -MinimumVersion 5.5.0
-
-      - name: Run Pester
-        shell: powershell
-        run: |
-          Import-Module Pester -MinimumVersion 5.5.0
-          $c = New-PesterConfiguration
-          $c.Run.Path = 'scripts/Bootstrap'
-          $c.Run.Exit = $true
-          $c.Output.Verbosity = 'Detailed'
-          Invoke-Pester -Configuration $c
-
-      - name: Guard scripts stay pure ASCII
-        shell: powershell
-        run: |
-          $failed = $false
-          Get-ChildItem 'scripts/Bootstrap' -Filter '*.ps1' | ForEach-Object {
-            $bytes = [System.IO.File]::ReadAllBytes($_.FullName)
-            for ($i = 0; $i -lt $bytes.Length; $i++) {
-              if ($bytes[$i] -gt 127) {
-                Write-Host "::error file=scripts/Bootstrap/$($_.Name)::Non-ASCII byte 0x$('{0:X2}' -f $bytes[$i]) at offset $i. PS 5.1 (IME) reads BOM-less files as ANSI and corrupts multi-byte chars."
-                $failed = $true
-                break
-              }
-            }
-          }
-          if ($failed) { exit 1 }
-          Write-Host 'All bootstrap scripts are pure ASCII.'
+  gates:
+    uses: ./.github/workflows/bootstrap-script-gates.yml
@@ -0,0 +1,56 @@
+name: Publish customer scripts
+
+# Keeps the scripts behind download.autopilotmonitor.com/agent/ current WITHOUT waiting
+# for an agent release. Before this workflow existed, the script blobs rotated only on a
+# publish_as_stable run of build-agent.yml, so a bootstrap fix sat unpublished until the
+# next agent cutover -- while the WDP bootstrap MSI downloads the published copy on every
+# enrolling device.
+#
+# Same publish code as the release path (.github/scripts/Publish-BootstrapScripts.ps1);
+# this workflow only supplies a second trigger for it.
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'scripts/Bootstrap/**'
+      - 'scripts/CustomerSetup/**'
+      - '.github/scripts/Publish-BootstrapScripts.ps1'
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: 'Run every check and report drift, upload nothing'
+        required: true
+        type: boolean
+        default: false
+
+permissions:
+  contents: read
+
+# Shared with build-agent.yml: a script publish and an agent release both touch
+# version.json, and the bootstrapVersion read-modify-write must not interleave with the
+# release writing its agent fields. Never cancel -- a half-published set is worse than a queue.
+concurrency:
+  group: agent-blob-publish
+  cancel-in-progress: false
+
+jobs:
+  gates:
+    uses: ./.github/workflows/bootstrap-script-gates.yml
+
+  publish:
+    name: Publish to the download alias
+    needs: gates
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Publish bootstrap + customer scripts
+        shell: pwsh
+        run: |
+          $dryRun = '${{ inputs.dry_run }}' -eq 'true'
+          ./.github/scripts/Publish-BootstrapScripts.ps1 `
+            -SasToken '${{ secrets.AZURE_BLOB_AGENT_SAS_TOKEN }}' `
+            -LegacySasToken '${{ secrets.AZURE_BLOB_AGENT_LEGACY_SAS_TOKEN }}' `
+            -TableSasToken '${{ secrets.AZURE_TABLE_ADMIN_SAS_TOKEN }}' `
+            -DryRun:$dryRun
@@ -159,3 +159,8 @@ docs/~$Introduction-AutopilotMonitor.pptx
 # changes each run) and served at /version.json from the static export.
 src/Web/autopilot-monitor-web/public/version.json

+
+# Local IME binaries scratch used by the /ime-decompile skill (MSI + msiexec-
+# extracted payload per version, for grepping in binaries). Decompilates live in
+# the private ime-decompiles repo, MSIs in the ime-archive blob - this stays local.
+ime-files/
@@ -0,0 +1,131 @@
+---
+type: concept
+title: CMTrace Time Resolution — Per-Line Self-Anchoring
+description: How the agent converts bias-less CMTrace local times to UTC without trusting any process's timezone belief — each provably fresh line anchors its own offset against the agent clock on the 15-minute grid; everything not provably fresh falls back uniformly and says so.
+resource: src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime
+tags: [agent, ime, cmtrace, timestamps, timezone, calibration, provenance]
+timestamp: 2026-08-20
+---
+
+# Problem
+
+A CMTrace line carries local time and no offset — IME 1.104 writes `DateTime.Now.TimeOfDay`
+in both of its trace listeners. Converting such a line with the reader's own
+`TimeZoneInfo.Local` silently assumes the writing and reading processes agree on the zone.
+They do not: each caches its zone at process start and follows neither a later `tzutil` nor
+a Windows auto-timezone change. The error is `Offset_writer − Offset_reader` — zero only
+when both believe the same thing, right or wrong. Field measurement over 11,068 sessions
+found 26 sessions with a real error, from +1 h to −17 h.
+
+Two designs failed before this one:
+
+* **Fix the reader's belief** (`TimeZoneInfo.ClearCachedData`, live OS offset): makes the
+  agent isolated-correct and thereby breaks the majority of sessions, where two equally
+  stale beliefs cancel.
+* **One measured offset per file** (agent 2.0.1410, reverted in `04b1a7c6`): a single log
+  file holds lines from multiple writer *eras*. `AgentExecutor.log` is written by
+  short-lived child processes whose zone belief flips per process — interleaved in one
+  file, and flipping *back* (fixture:
+  `tests/fixtures/cmtrace-logs/agentexecutor-two-writer-eras-v1.cmtrace`). Any cross-line
+  anchor — per file, or nearest-in-write-order — applies one era's offset to the other
+  era's lines. In the field this shifted `script_started` events by −9 h against their
+  correct completions.
+
+# Schema
+
+The resolution rule, in order:
+
+1. **Writer-declared bias** (`+480` suffix): authoritative, used as-is. Never a calibration
+   anchor — it needs no measurement and must not overwrite one.
+2. **Per-line self-anchoring** — only for lines read in a *provably fresh* pass:
+
+   ```
+   offset_line = round((local − agentUtcNow) / 15 min) · 15 min
+   lineUtc     = local − offset_line
+   ```
+
+   Every real UTC offset is a whole multiple of 15 minutes, so the rounding absorbs poll
+   and flush latency. No cross-line state exists, so interleaved eras resolve line by
+   line — the property the fixture test pins. The line's own timestamp still contributes
+   sub-poll precision and ordering (two lines 6 ms apart stay 6 ms apart; a plain
+   `occurredAt = now` could not do that). Guards: grid residual ≤ 2 min, offset within
+   UTC−12 … UTC+14.
+3. **Uniform reader-zone fallback** for everything else: wrong in absolute terms whenever
+   the writer held a different belief, but *self-consistent* — both ends of a duration are
+   wrong by the same amount, so derived durations stay right. The revert's core lesson:
+   partially corrected is strictly worse than uniformly wrong.
+
+**Freshness** is what makes rule 2 sound, and it is strict:
+
+* Every poll look at a file stamps `LastCheckedUtc` (`LogFilePositionTracker.MarkChecked`),
+  including "no new data" and an empty first sight — so a file first seen empty
+  (`AgentExecutor.log` appearing mid-enrollment) anchors from its very first content.
+* A pass's lines are fresh only if the file was previously observed *in this process* and
+  the gap since the last look is ≤ `FreshLineMaxAge` (30 s — far above the 100 ms poll,
+  far below the 13-minute zone where a line's *age* could round onto the offset grid).
+* A restart-restored position bookmark deliberately carries **no** freshness: the first
+  pass after a restart reads downtime backlog and must never anchor.
+
+**Provenance** (`sourceOffsetOrigin` in event DataJson): `bias` | `line-anchored` |
+`reader-zone-fallback` (plus retired `calibrated` from 2.0.1410 events). The applied
+offset is always recorded (`sourceOffsetMinutes`), the raw local time too
+(`sourceLocalTs`), so any event can be re-derived later. The per-*file* measurement still
+runs, purely observationally (`measuredWriterOffsetMinutes`, Info log when it disagrees
+with the process zone).
+
+# Constraints
+
+* An anchored line resolves to `now ± 2 min` *by construction*. The accepted edge: a
+  freshly written line carrying a **replayed** old timestamp whose age is exactly
+  N×15 min ± 2 min anchors to ≈now instead of its replayed past — bounded error, and
+  sub-24 h replays are treated as current by the historic-replay guard anyway.
+* Snapshot readers (`StallProbeCollector`, `LogParserCollector`) cannot tail and therefore
+  cannot prove freshness — they stay on the marked fallback. This is a documented limit,
+  not an omission; sharing the per-file measurement with them would re-apply exactly what
+  the revert removed.
+* Mixed pairs remain possible across a restart (start resolved from backlog fallback,
+  completion line-anchored) and are recognizable via provenance.
+
+# Backend regression tripwire
+
+The backend watches for the failure mode this design eliminates. On every terminal ingest
+batch, the counter reconcile's existing event-partition scan additionally collects
+`Δ = ReceivedAt − OccurredUtc` per event, split by `Source == "ImeLogTracker"` versus the
+rest (`CmTraceSkewTripwire`, hooked in `EventIngestProcessor`). If
+`median(Δ_IME) − median(Δ_other)` is a clean 15-minute multiple (residual < 2 min — the
+same constants as the anchoring grid guard above) with ≥ 20 samples over ≥ 3 distinct
+upload batches per side, and ≥ 80 % of the individual IME deltas (relative to the other
+side's median) themselves sit within 2 min of some grid multiple — added after the 2026-08-28
+soak, when relaunched agents re-tailing the IME log produced one burst holding most of a
+session's IME samples with a continuum of ages whose median hit the grid by chance (7 false
+fires in a week, 0 true) — a `CmTraceTimeSkewRegression` ops event fires (category Agent,
+warning), carrying all numbers plus the session's `sourceOffsetOrigin` histogram.
+Bias-dominated sessions are suppressed (writer-declared offsets cannot be an anchoring
+regression); `measuredWriterOffsetMinutes` is never consulted (sticky after era
+flip-backs). Kill switch: app setting `CmTraceSkewTripwireDisabled`. Goal state: the event
+never fires — any hit is an anchoring case the per-line design misses, or a detector bug.
+
+Device-clock problems (the customer-actionable cousin) are covered separately by the
+`clock_skew` analyze condition behind `ANALYZE-DEV-008`, which excludes IME-derived events
+precisely so an anchoring regression can never surface as a customer finding.
+
+# Citations
+
+* `CmTraceOffsetCalibrator.TryMeasureOffset` — the pure grid measurement, shared by
+  anchoring and the observational per-file path.
+* `CmTraceSkewTripwire` + `CmTraceSkewTripwireTests` — the backend tripwire above.
+* `RuleEngine.ConditionEvaluators.EvaluateClockSkewCondition` + `RuleEngineClockSkewTests`
+  — the customer-facing device-clock metrics (batch-median frames, spool-spread filter,
+  plateau step detection, end-state persistence).
+* `ImeLogTracker.LogProcessing.cs` `ResolveEntryUtc` — the resolution order above.
+* `ImeLogTrackerLineAnchoringTests` — resolves-to-T across writer beliefs, interleaved
+  eras in one chunk, freshness boundaries (first sight, empty first sight, poll gap,
+  restart restore), the grid-replay edge, and the field fixture replayed at production
+  poll cadence.
+* `CmTraceCalibratorFileIsolationTests` — pins per-file isolation of the observational
+  measurement (session e9753578 logged a cross-file pairing the committed code could not
+  be shown to produce; the mechanism remains open, the resolution path is immune by
+  design, and `CalibrateFrom` logs the anchor timestamp as a tripwire).
+* `tasks/todo.md` (2026-08-20) — full evidence trail: field measurements, the revert,
+  the two-writer-era fixture, and the disproven foreign-binary hypothesis (the SHA
+  mismatch was the known release race against the 5-minute AdminConfiguration cache).
@@ -128,6 +128,15 @@ user-ESP Install-intent apps are still pending (IME logs "Completed user session
 *pass*, not once per session — sessions 14690fc2/6cb01530). The reducer stays free of
 app-pending guards; adapters sanitize evidence before it becomes a signal.

+**Zero user-targeted apps** (sessions 81daa77f/75d6ae8e): IME never writes its
+"Completed user session" line at all when the user has no assigned apps — its zero-app
+branch returns first — so fact 3 was unreachable by construction and every such device
+fell through to the backstop. `IME-USER-SESSION-ZERO-APPS` reads the line IME *does*
+write there and posts the same signal, guarded to the AccountSetup phase. The event
+carries an `evidence` field (`zero_user_apps_enumerated` vs `user_session_completed`)
+naming which observation carried the completion. See
+[zero-user-apps-completion-gate.md](zero-user-apps-completion-gate.md).
+
 ## Completion attempt sites and sequence

 Completion can be attempted from whichever fact arrives last: `HelloResolved`,
@@ -143,11 +152,34 @@ advisory backstop. All routes converge on `CompleteThroughFinalizingOrDefer`:
   first-deployment window 100/101 for 200/210 without 110 — the RJ ESP was aborted,
   typically by an interactive logon reclassifying the run as secondary-user; emits
   the `realmjoin_first_deployment_incomplete` Warning, session 224b2087), and
-   `Timeout` (hard 60-min deadline). The abort rule reads the *persisted*
+   `Timeout` (60-min deadline from detection). The abort rule reads the *persisted*
   `RealmJoinFacts.LastDeploymentPhase` (updated by the typed `RealmJoinPhaseChanged`
   signal), so it survives agent restarts — the `RealmJoinDetected` replay path
   evaluates it too. A first observation of 210 does **not** release (RJ may have
   completed before agent boot and deploy afterwards).
+
+   **Activity-based timeout extension** (report 55e6afd61c9d — a large RJ package
+   catalog outlived the 60-min window mid-install): when the timeout deadline fires
+   while the first deployment is demonstrably active — `LastDeploymentPhase` 100/101
+   *and* deployment activity (`RealmJoinPhaseChanged` or a package observation, tracked
+   in `RealmJoinFacts.LastActivityUtc`; the phase captured at detection deliberately
+   does not count) within the last 60 min — the handler re-arms the deadline to
+   `lastActivity + 60 min` instead of timing out, emitting an Info
+   `realmjoin_timeout_extended` event. Re-arms clamp to an absolute cap of
+   **detection + 4 h**. Package activity is only observable at package *completion*
+   (RJ writes the registry subkey when the install finishes), so a single install
+   that is registry-silent for over 60 min still times out — the eventual
+   `realmjoin_timeout` carries a `reason` payload (`hard_timeout` / `inactivity` /
+   `absolute_cap`) telling the three shapes apart. A stale fire of an older deadline
+   incarnation (armed due later than the fire time; `OccurredAtUtc = DueAtUtc` per
+   scheduler contract) dead-ends as `realmjoin_timeout_stale_superseded_by_rearm`.
+   The idle case (detected, no deployment activity ever) times out at 60 min
+   unchanged, and phase 200/210 activity never extends.
+   A closed gate also outranks the 30-minute `AdvisoryCompletion` backstop: that
+   handler re-arms (trigger suffix `:CompletionGateHolding`) instead of failing while
+   the RealmJoin gate is closed *and* its own deadline is still armed, because the gate
+   carries a bounded resolution of its own. Before this, the shorter timer always won —
+   session 75d6ae8e was failed 2 min after its 25th successful RealmJoin package.
 2. `Finalizing` stage + ~5 s `FinalizingGrace` deadline.
 3. Grace fires → `Completed`, `EnrollmentComplete` outcome, `enrollment_complete`
   timeline event with full audit payload.
@@ -0,0 +1,147 @@
+---
+type: concept
+title: Diagnostics Package
+description: What the agent's diagnostics ZIP contains and why — the built-in section catalog shared with the portal, the RealmJoin and Device Preparation collection gates, the configured-path guards, caps, and the package manifest.
+resource: agent
+tags: [diagnostics, realmjoin, device-preparation, guardrails, portal]
+timestamp: 2026-08-23
+---
+
+# Schema
+
+The diagnostics package is the agent's last-resort support artifact: a ZIP built in memory
+by `DiagnosticsPackageService.BuildArchiveBytes` and uploaded through a short-lived SAS
+URL at the end of a session, at the WhiteGlove seal (`Always` mode) or on a server-requested
+on-demand collection ([server actions](../backend/server-actions-on-demand-diagnostics.md)).
+
+## Archive layout
+
+```
+sessioninfo.txt                 session/tenant/device/outcome, hardware via WMI
+<built-in sections>             catalog order, see below
+AdditionalLogs/<last folder>/   admin-configured paths (global ∪ tenant)
+package-manifest.txt            every packaging decision (always written)
+_TRUNCATED.txt                  only when a cap skipped something
+```
+
+## The built-in catalog is the single source of truth
+
+Everything the package collects **before** any configured path is data, not code paths:
+`DiagnosticsBuiltInSections.All` in Shared (`Models/Diagnostics/DiagnosticsBuiltInSections.cs`).
+The agent iterates it in order; the backend serves the same list to the portal
+(`GET /api/diagnostics/paths`, MemberRead) so what administrators see is exactly what the
+agent does. There is no second copy to drift.
+
+| Id | ZIP folder | Source (unexpanded) | Patterns | Recursive | Condition |
+| --- | --- | --- | --- | --- | --- |
+| AgentLogs | `AgentLogs` | `%ProgramData%\AutopilotMonitor\Logs` | log patterns | no | Always |
+| ImeLogs | `ImeLogs` | `%ProgramData%\Microsoft\IntuneManagementExtension\Logs` | log patterns | no | Always |
+| ImeBootstrapperEventLog | `ImeLogs` | `C:\Windows\System32\winevt\Logs` | `BootstrapperAgentServiceLogProvider.evtx` | no | DevicePreparation |
+| AgentState | `AgentState` | `%ProgramData%\AutopilotMonitor\State` | log patterns + `*.complete`, `*.marker` | yes | Always |
+| AgentSpool | `AgentSpool` | `%ProgramData%\AutopilotMonitor\Spool` | `*.jsonl`, `*.json` | no | Always |
+| AgentMarkers | `AgentMarkers` | `%ProgramData%\AutopilotMonitor` | `*.complete`, `*.marker` | no | Always |
+| RealmJoinWindows | `RealmJoinLogs/Windows` | `C:\Windows\Logs` | `realmjoin*.log` | no | RealmJoinWatcher |
+| RealmJoinPackages | `RealmJoinLogs/Windows/RealmJoin` | `C:\Windows\Logs\RealmJoin` | `*.log` | yes | RealmJoinWatcher |
+| RealmJoinChoco | `RealmJoinLogs/Choco` | `%ProgramData%\RealmJoin\choco\logs` | `*.log` | yes | RealmJoinWatcher |
+| RealmJoinUserTray | `RealmJoinLogs/User` | `%LOGGED_ON_USER_PROFILE%\AppData\Local\RealmJoin` | `tray*.log` | no | RealmJoinWatcher |
+| RealmJoinUserLogs | `RealmJoinLogs/User/Logs` | `%LOGGED_ON_USER_PROFILE%\AppData\Local\RealmJoin\Logs` | `*.log` | yes | RealmJoinWatcher |
+
+"Log patterns" = `*.log *.txt *.json *.jsonl *.etl *.evtx *.xml *.csv *.cab`. The five
+`Always` sections are the historical layout (PR1-B forensics) and are lock-tested in order;
+the RealmJoin ZIP layout mirrors the disk (`C:\Windows\Logs\{realmjoin*.log, RealmJoin\…}` →
+`RealmJoinLogs/Windows/…`, `%LOCALAPPDATA%\RealmJoin\{tray*.log, Logs\…}` →
+`RealmJoinLogs/User/…`), so a flat section and a tree section never produce the same entry
+name. Two sections may share a ZIP folder only when they read different source folders
+(`ImeLogs` + the bootstrapper evtx) — `(ZipFolder, SourceFolder)` pairs are unique.
+
+### Conditions
+
+`DiagnosticsSectionCondition` is evaluated by the agent (`IsSectionActive`, pure) against its
+effective configuration and the enrollment scenario; unknown values fail closed.
+
+* **RealmJoinWatcher** — the tenant's RealmJoin Watcher toggle
+  (`AnalyzerConfiguration.EnableRealmJoinWatcher`). The package service only sees
+  `AgentConfiguration`, so `RemoteConfigMerger` mirrors that one Analyzers knob onto
+  `AgentConfiguration.EnableRealmJoinWatcher` (the RealmJoin host keeps reading the remote
+  block). Deliberately NOT additionally gated on the compile-time `RealmJoinTrackingEnabled`
+  kill switch: if the live watcher is ever disabled, the logs become more useful, not less.
+  No ConfigVersion bump — no new wire field.
+* **DevicePreparation** — `EnrollmentRegistryDetector.IsDeterministicDevicePreparation()`,
+  the same deterministic `DevicePreparation\BootstrapperAgent\ExecutionContext` marker every
+  other WDP gate keys on ([WDP scenario gates](wdp-scenario-gates.md)); CloudAssigned*
+  fallback rules count as Classic. The probe is a registry read, evaluated once per build
+  (`SCENARIO: devicePreparation=… realmJoinWatcher=…` in the manifest); a probe failure is
+  treated as Classic and logged — the evtx export is skipped, never the package. The channel
+  is exclusively locked while active, so the existing `wevtutil epl` export path
+  (`ResolveChannelForEvtxFile`, field case 2026-08-17) handles it.
+
+Inactive sections are never silent: `BUILT-IN SKIPPED (RealmJoin Watcher disabled): <Id>`,
+`BUILT-IN SKIPPED (not a Device Preparation enrollment): <Id>`,
+`BUILT-IN SKIPPED (no user session for token): <Id> '<source>'` (the
+`%LOGGED_ON_USER_PROFILE%` token resolves via `UserProfileResolver` only once an
+interactive user exists — identical to configured paths). Active ones log
+`BUILT-IN: <Id> -> folder='…' zip='…' recursive=…` followed by the per-pattern
+`ADDED / NO MATCH / FOLDER MISSING` lines.
+
+## Built-ins bypass the configured-path guards — on purpose
+
+`DiagnosticsPathGuards` ([gather-rule guardrails](../rules/gather-rule-guardrails.md))
+validates **admin-typed** paths: allowlisted prefixes, wildcard only in the last segment,
+`C:\Users` blocked except the token's `AppData\Local|Roaming`. The catalog is reviewed code,
+exactly like the five sections that never went through the guard before — and
+`%ProgramData%\RealmJoin` is not on the allowlist at all. What does apply to every section:
+the reparse-point skip (files and directories), the `.evtx` channel export, and the caps
+(100 MB per file, 500 MB total, 5000 files) tracked globally across sections by
+`BudgetTracker`, with every skip recorded in the manifest and `_TRUNCATED.txt`.
+
+## Configured paths: global ∪ tenant
+
+`GetAgentConfigFunction.MergeDiagnosticsLogPaths` sends global paths (Global Admin,
+`AdminConfiguration.DiagnosticsGlobalLogPathsJson`) first, then tenant paths
+(`TenantConfiguration.DiagnosticsLogPathsJson`), dropping blank entries and collapsing
+duplicates (trimmed, case-insensitive) onto the first occurrence — a path present in both
+lists used to produce duplicate ZIP entry names. The agent keys each entry's ZIP folder on
+the last directory name (`AdditionalLogs/<folder>`), so two configured paths ending in a
+same-named folder share one ZIP folder.
+
+## Portal surfaces
+
+* Global Admin → Settings → Diagnostics Log Paths: the built-in catalog (collapsed, read-only,
+  neutral condition pills) above the editable global list; add-row first.
+* Tenant → Settings → Agent → Diagnostics Package: built-in catalog (header carries the
+  tenant's persisted RealmJoin Watcher state, RealmJoin rows show on/off), the global paths
+  read-only, then the tenant's own entries; every role with a tenant membership can read the
+  catalog (the route is MemberRead, JWT-scoped). One line per entry (`DiagnosticsPathRow`),
+  full values in tooltips.
+
+## Test seams
+
+* `DiagnosticsPackageService` internal ctor: the five historical folder overrides map onto
+  catalog ids; `sectionFolderOverrides` covers any other section; `devicePreparationProbe`
+  replaces the registry read (seam callers default to "not WDP", so existing rigs never touch
+  the registry). `UserProfileResolver.SetForTesting(path|null)` / `Reset()` drive the token.
+* Catalog invariants live in the backend test project (`DiagnosticsBuiltInSectionsTests`),
+  because Shared has no test project.
+
+# Examples
+
+A RealmJoin tenant (watcher on) with a signed-in user: `RealmJoinLogs/Windows/realmjoin.log`,
+`RealmJoinLogs/Windows/RealmJoin/Packages/<pkg>/<timestamp>_install.log`,
+`RealmJoinLogs/Choco/<pkg>/<timestamp>_install.log`, `RealmJoinLogs/User/tray.log`,
+`RealmJoinLogs/User/Logs/RjImeHost.log`. The same tenant's package collected before the
+desktop: the two `User` sections appear as `BUILT-IN SKIPPED (no user session for token)`.
+A Classic enrollment: `BUILT-IN SKIPPED (not a Device Preparation enrollment):
+ImeBootstrapperEventLog`. A tenant that had added
+`%LOGGED_ON_USER_PROFILE%\AppData\Local\RealmJoin\Logs\*.log` manually keeps working — the
+files simply appear twice (`AdditionalLogs/Logs/…` and `RealmJoinLogs/User/Logs/…`) until the
+entry is removed.
+
+# Citations
+
+* `src/Shared/AutopilotMonitor.Shared/Models/Diagnostics/DiagnosticsBuiltInSections.cs` — the catalog
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Runtime/DiagnosticsPackageService.cs` — `BuildArchiveBytes`, `AddBuiltInSection`, `IsSectionActive`, caps, evtx export
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Configuration/RemoteConfigMerger.cs` — `EnableRealmJoinWatcher` mirror
+* `src/Backend/AutopilotMonitor.Functions/Functions/Diagnostics/GetDiagnosticsPathsFunction.cs` — `GET diagnostics/paths`
+* `src/Backend/AutopilotMonitor.Functions/Functions/Config/GetAgentConfigFunction.cs` — `MergeDiagnosticsLogPaths`
+* `src/Web/autopilot-monitor-web/components/diagnostics/` — `DiagnosticsPathRow`, `BuiltInSectionsList`, `builtInSectionDisplay`
+* Tests: `DiagnosticsPackageServiceTests` (RealmJoin on/off, no user session, bootstrapper evtx, probe failure), `DiagnosticsBuiltInSectionsTests`, `GetDiagnosticsPathsPayloadTests`, `GetAgentConfigFunctionTests.MergeDiagnosticsLogPaths_*`
@@ -0,0 +1,113 @@
+---
+type: Concept
+title: DO GroupId Auto-Set — Delivery Optimization peering group from a network fingerprint
+description: EnableDoGroupIdAutoSet (ConfigVersion 40) makes the agent set the DOGroupId policy value to a deterministic GUID derived from the default gateway's IPv4 address and MAC (RealmJoin-compatible byte layout), so devices on the same local network form one DO peering group during enrollment; foreign DOGroupId/DOGroupIdSource policies always win.
+resource: /src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Transport/DoGroupIdService.cs
+tags:
+  - agent
+  - delivery-optimization
+  - network
+  - tenant-configuration
+timestamp: 2026-08-21T00:00:00+02:00
+---
+
+# DO GroupId Auto-Set
+
+## Schema
+
+### The problem
+
+With Delivery Optimization download mode Group (2), peering is scoped by GroupId. When no
+GroupId is configured, Windows derives it from AD site → authenticated domain SID → Entra
+tenant ID — for a cloud-native tenant that means **one tenant-wide group**, so "peers on
+the same network" degrades to "peers anywhere in the tenant" and DO's cloud service has to
+match them by public IP. A GroupId derived from the local network makes the group exactly
+"devices behind the same gateway" — including branch offices behind NAT. RealmJoin ships
+this as its network-fingerprint GroupId; our agent is on the device even earlier (during
+ESP, when the big app downloads actually happen), so it can seed the same value for
+Autopilot enrollments.
+
+### The setting
+
+`TenantConfiguration.EnableDoGroupIdAutoSet` (`bool?`, default null→false), served as
+`AgentConfigResponse.EnableDoGroupIdAutoSet` — **ConfigVersion 40**. Portal: Settings →
+Agent → Settings, toggle "Set Delivery Optimization Group ID", stored via the usual
+tenant-config roundtrip (`TableConfigRepository` Store+Map). Also shown in the admin
+tenant-config report. `RemoteConfigMerger` maps the bool 1:1; it survives the offline
+config cache like every plain feature flag.
+
+The agent does NOT configure `DODownloadMode` — the fingerprint GroupId only has an
+effect when the tenant already deploys download mode Group (2) via Intune/GPO.
+
+### The fingerprint
+
+`DoGroupIdService.ComputeGroupId(ipv4Bytes, macBytes)` builds a 16-byte GUID:
+
+```
+{101,48,6} + {0,0,0} + {ip[1], 0, ip[2], ip[3]} + mac[0..5]   →  new Guid(byte[16])
+```
+
+Gateway discovery reuses the shared `NetworkInterfaceLocator` heuristic (Up, not
+Loopback/Tunnel, non-0.0.0.0 gateway; IPv4 gateway required), the gateway MAC comes from
+`ArpNativeMethods` (`iphlpapi!SendARP`). The byte layout — including the IP shuffle and
+the zero padding — is **RealmJoin-compatible and must never change**: devices managed by
+RealmJoin on the same network compute the identical GUID and peer with ours. The registry
+value is written as `Guid.ToString()` (braceless lowercase), identical to RealmJoin's
+`SetValue(name, Guid)` string form. Deliberate divergence from RealmJoin: **no
+random-GUID fallback** — a random per-device ID would isolate the device in a one-member
+group, which is worse than the OS default grouping, so no gateway/no MAC means skip.
+
+### Ownership + conflict rules (never fight a foreign policy)
+
+Target: `HKLM\SOFTWARE\Policies\Microsoft\Windows\DeliveryOptimization\DOGroupId`
+(64-bit registry view — the Policies store is WOW64-redirected; key paths reused from
+`DoThrottlePolicyReader`). Only this GPO-store value is written; the legacy pre-1607
+`GroupId` value name is intentionally not.
+
+Skip conditions (Info event with `skipReason`, nothing written):
+
+| skipReason | Meaning |
+|---|---|
+| `no_ipv4_gateway` | No active interface with an IPv4 default gateway |
+| `arp_failed` | Gateway MAC could not be resolved via SendARP |
+| `group_id_source_policy` | `DOGroupIdSource` configured in GPO or MDM store (dynamic group source wins) |
+| `mdm_policy_present` | `DOGroupId` managed via the Policy CSP store (Intune owns it) |
+| `foreign_value_present` | Existing GPO value neither matches the computed GUID nor the one we last wrote |
+
+Ownership is tracked through the `StartupEventGate` fingerprint for the
+`do_group_id_auto_set` key: `written:<guid>` records the GUID we last wrote, so after a
+gateway change the agent recognizes its own stale value and updates it — while a value
+written by anyone else is never overwritten (`DecideAction`: empty→write, equal→no-op,
+ours→update, else→skip; unparseable existing values count as foreign). Every write is
+verified by readback.
+
+### The event
+
+One `do_group_id_auto_set` event per outcome change (Source `StartupEnvironmentProbes`,
+gated on the fingerprint — unchanged reruns across reboots stay silent; errors never
+latch, so each failing start keeps its retry trail). Severity: Info for
+success/skip, Warning for errors. Data: `groupId`, `previousValue`, `gatewayIp`,
+`gatewayMac`, `written`, `skipped`, `skipReason`, `success`, `error`.
+
+## Examples
+
+First boot on a network with gateway `192.168.178.1` / MAC `00-11-22-33-44-55`:
+
+```
+do_group_id_auto_set (Info): Delivery Optimization GroupId set to
+00063065-0000-00a8-b201-001122334455 (gateway 192.168.178.1)
+```
+
+Tenant already deploys a DO GroupId via Intune:
+
+```
+do_group_id_auto_set (Info): Delivery Optimization GroupId not set: mdm_policy_present
+```
+
+## Citations
+
+* Service (fingerprint, ownership, write+readback): `../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Transport/DoGroupIdService.cs`
+* ARP interop: `../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/ArpNativeMethods.cs`
+* Probe wiring + event + fingerprint dedup: `../../src/Agent/AutopilotMonitor.Agent.V2.Core/Runtime/StartupEnvironmentProbes.cs`
+* Backend serve + ConfigVersion: `../../src/Backend/AutopilotMonitor.Functions/Functions/Config/GetAgentConfigFunction.cs`
+* DO policy stores (key paths, Registry64 rationale): `../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/Periodic/DoThrottlePolicyReader.cs`
@@ -44,7 +44,7 @@ tenant-config report.

 `RemoteConfigMerger` projects the bool onto a runtime path (same pattern as
 `EnableImeMatchLog`): `true` → `Constants.GatherRuleDebugLogPath` =
-`%ProgramData%\AutopilotMonitor\Logs\gather_rules_debug.log`; `false` → null, unless a
+`%ProgramData%\AutopilotMonitor\Logs\gather-rules-debug.log`; `false` → null, unless a
 `--gather-debug-log <path>` CLI override supplied a non-default path. The field is not
 security-sensitive and deliberately **survives the offline config cache**.

@@ -5,8 +5,13 @@ How the on-device agent works:
 * [Runtime Overview](overview.md) - lifecycle (install → boot guards → runtime → termination), collector hosts, the single-rail event pipeline to the backend, config & kill switch, on-disk layout.
 * [Decision Engine](decision-engine.md) - the pure-reducer state machine (DecisionCore): signals, state, effects, the A/B/C completion arms, invariants, threading.
 * [Logs, Persistence & Crash Recovery](logs-and-persistence.md) - every persisted file and why it exists; signal log vs spool; snapshot/journal; the replay-based recovery flow and quarantine.
+* [Diagnostics Package](diagnostics-package.md) - what the diagnostics ZIP contains: the built-in section catalog shared with the portal (Shared `DiagnosticsBuiltInSections`, served by GET diagnostics/paths), the RealmJoin Watcher and Device Preparation collection gates, why built-ins bypass the configured-path guards, global ∪ tenant path dedup, caps and the package manifest.
 * [Hello Wizard Un-Skip](hello-wizard-unskip.md) - why a single "WHfB disabled" policy read never decides completion: the HelloWizardStarted signal (prevention + cure) and the HelloTracker confirmation second read.
+* [Zero User-Targeted Apps](zero-user-apps-completion-gate.md) - why a user with no targeted Intune apps starved every user-phase completion path (IME never writes its "Completed user session" line in the zero-app branch), and why a completion gate that is still holding the session must outrank the 30-minute backstop.
 * [Autopilot ZTD Diagnostics](autopilot-ztd-diagnostics.md) - Windows' own diagnostic surfaces for the profile-download flow: ModernDeployment event IDs (807/815/164/...), the Diagnostics\Autopilot registry key, deployment-service endpoints, and the known-issue error-code map.
 * [MDM Reboot Coalescing](mdm-reboot-coalescing.md) - attributing the mid-ESP coalesced reboot ("second sign-in") to the device-assigned policy URIs that forced it: aggregated 2800 observations (neutral, flush-time watermark) + ANALYZE-ESP-005 gated on an actually-observed reboot.
+* [Power-State Watcher](power-state-watcher.md) - live AC↔battery transitions and 50/30/15% downward threshold crossings via a WMI push subscription (no polling): power_state_change semantics (latch/debounce/cap, never armed without a battery) and the single-condition analyze rules ANALYZE-DEV-009/-010 on top.
+* [DO GroupId Auto-Set](do-group-id-auto-set.md) - the optional Delivery Optimization peering-group seed: deterministic GUID from default gateway IPv4 + MAC (RealmJoin-compatible), written to the DOGroupId policy value with readback, ownership-tracked so foreign Intune/GPO values are never overwritten; skip reasons and the do_group_id_auto_set event.
+* [System Timeline Watcher](system-timeline-watcher.md) - clock steps (system_clock_changed: oldTime/newTime/timeDeltaMs/process, micro-slew floor) and completed sleep episodes (system_sleep_episode: sleep/hibernate/Modern Standby with authoritative enteredAt/exitedAt) from one System-channel EventLogWatcher with pre-agent backfill; feeds the web clock-set jump cause, the standby duration note, time-attribution SleepSpans and ANALYZE-DEV-012.

 Reading order for newcomers: overview → decision engine → persistence.
@@ -53,7 +53,7 @@ every line; the spool fsyncs only items flagged `RequiresImmediateFlush`.
 | Event sequence | `State\event-sequence.json` | `{ LastAssignedSequence }` | atomic | none; survives WhiteGlove Part-2 resume |
 | Spool | `Spool\spool.jsonl` | JSONL (`TelemetryItem`/line) | only `RequiresImmediateFlush` items | none — never truncated, cursor skips uploaded items |
 | Upload cursor | `Spool\upload-cursor.json` | `{ LastUploadedItemId }` | atomic | idempotent, never regresses |
-| Agent trace log | `Logs\agent_YYYYMMDD[_NNN].log` | text `[utc] [LEVEL] msg` | no | 50 MB → suffix rotation; consumed by `/diag-agent-log` |
+| Agent trace log | `Logs\agent.log` (segments `agent-NNN.log`) | text `[utc] [LEVEL] msg` | no | 50 MB → suffix rotation; consumed by `/diag-agent-log` |
 | Crash dump + record | `Crashes\<stem>.dmp` + `.json` | MiniDump + JSON | n/a (process dying) | 5 files / 7 days |
 | Startup-event gate | `State\startup-event-state.json` | JSON dict | no (atomic) | cross-reboot dedup of one-shot probes |
 | Bandwidth state | `State\bandwidth-state.json` | JSON samples/counters | no (atomic) | reboot-survivor for the DO bandwidth estimate |
@@ -146,7 +146,7 @@ snapshots) are executed by the `EffectRunner` — the reducer itself is pure. De
 | `\Agent\` | deployed binaries |
 | `\State\` | decision persistence (SignalLog, Journal, Snapshot), `enrollment-complete.marker`, `final-status.json`, self-update state, `.quarantine/`, `.part1-<ts>/` |
 | `\Spool\` | telemetry spool (offline queue) |
-| `\Logs\` | agent trace log, `crash_*.log`, `ime_pattern_matches.log` |
+| `\Logs\` | agent trace log (`agent.log`), `crash-*.log`, `ime-pattern-matches.log` |
 | `\Config\` | `remote-config.json` cache |
 | `\Agent-Update\`, `\Updates\` | self-update staging/download |

@@ -0,0 +1,200 @@
+---
+type: Concept
+title: ESP Completion Starvation — the sits-d Cloud-PC complex
+description: Why five Windows 365 Cloud PCs finished enrolling but never completed in the product — a SkipUser=true flow produces none of the signals every completion-gate evaluation site hangs off — plus the two adjacent defects fixed alongside (edge-only user-apps-settled synthesis, orphaned Hello-wizard restart replay) and what a Shell-Core replay deliberately does not do.
+resource: /src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals
+tags:
+  - agent
+  - esp
+  - completion
+  - skip-user
+  - reboot
+  - recovery
+timestamp: 2026-08-20T00:00:00+02:00
+---
+
+# ESP Completion Starvation — the sits-d Cloud-PC complex
+
+Seven Windows 365 Cloud PCs, same tenant, first sign-in the same morning. Two sessions
+succeeded within minutes; five sat at `Completion is waiting on: hello_resolution` from
+second five onward and ran into the six-hour max-lifetime watchdog — verdict `Incomplete`
+on devices whose users were working normally the whole time.
+
+The first diagnosis blamed the mid-ESP reboot (DeviceGuard/DmaGuard, see
+[MDM Reboot Coalescing](mdm-reboot-coalescing.md)): the agent is killed in
+`Stage=EspAccountSetup` and, so the theory went, loses the Shell-Core ESP exit to the
+downtime. The evidence disproved it. `8110e262` ran **six hours uninterrupted** after its
+last reboot with the Shell-Core watcher armed — and Windows never wrote a 62407 in all
+that time, because on these machines **the user ESP page never existed**.
+
+# Schema
+
+## The actual defect — a satisfied gate nobody evaluates
+
+The five stuck machines carried `SkipUserStatusPage=True` in the enrollment `FirstSync`
+key (read 10+ times across three agent processes, `True` on every read — not a stale
+single read). Windows honours it: no user ESP page, hence
+
+* no Shell-Core 62407 (`esp_exiting`) — the page that would exit does not exist,
+* no `AccountSetupCategory` provisioning registry — nothing writes categories for a page
+  that never renders,
+* desktop within seconds of sign-in.
+
+The reducer is *built* for this flow: **arm B** of `ShouldTransitionToAwaitingHello`
+(`SkipUserEsp == true`) declares the gate open, and the missing-prerequisites bookkeeping
+already exempts the AccountSetup gate — which is why the sessions reported only
+`hello_resolution` as missing. But the gate is a predicate, not a process. Something has
+to evaluate it, and every evaluation site hangs off a signal a skip-user flow structurally
+cannot produce:
+
+| Evaluation site | Carrier signal | On SkipUser=true |
+|---|---|---|
+| `HandleEspExitingV1` | Shell-Core 62407 | never fires |
+| `HandleEspPhaseChangedV1(FinalizingSetup)` | Shell-Core 62407 via coordinator | never fires |
+| `HandleDesktopArrivedV1` fast-path | requires Hello policy **disabled** | Hello was enabled |
+| `HandleImeUserSessionCompletedV1` arm-C attempt | requires the recorded final exit | unsatisfiable |
+
+No knock, no promotion, no `HelloSafety` — and the `AdvisoryCompletion` backstop is armed
+exclusively from an `EspExiting` signal, so it never armed either. The session idles to
+the watchdog with an open gate.
+
+## The fix — the observed skip is the exit evidence
+
+`HandleImeUserSessionCompletedV1`'s completion attempt now accepts the observed skip in
+place of the final exit (`skipUserExitEquivalent`): on a flow where no page exists, no
+exit can ever say more than the `FirstSync` read already did. Everything else stays
+mandatory — AccountSetup anchor, genuine (at-or-after-anchor) IME user-session completion,
+DAD-validated real-user desktop — which makes this knock **stricter** than the existing
+Shell-Core-carried arm-B promotion (pinned in `ClassicAwaitingHelloGuardTests`, which
+requires no IME or desktop evidence at all). Hello semantics ride the existing rails:
+enabled-or-unknown promotes to `AwaitingHello` with `HelloSafety` armed (on Cloud PCs
+reached via RDP the Hello wizard never appears, so the synthetic timeout resolves the
+wait), disabled completes directly with the synthetic `Skipped` outcome.
+
+The knock deliberately lives on the IME user-session edge, not on desktop arrival:
+
+* **Ordering-robust against Fix 10.** An `EspPhaseChanged(AccountSetup)` arriving on
+  `AwaitingHello` bounces the stage back and cancels `HelloSafety` (the premature-promotion
+  guard). The IME AccountSetup phase line lands *after* the desktop on this flow, so a
+  desktop-side knock would be undone two signals later. The IME phase line always precedes
+  the user-session-complete line in log order, so a bounced promotion is re-knocked by the
+  very next re-emission — including the restart re-parse.
+* **Right semantics.** The IME user session completes when the required-app processing is
+  done; a desktop-side knock would mark the session `Succeeded` mid-installation.
+* Device Preparation is excluded — WDP keeps its Hello+Desktop conjunction and the
+  `DevicePrepCompletion` backstop.
+
+`ClassicSkipUserEspUserSessionCompletionTests` replays the real `8110e262` signal ordering
+end to end (bootstrap `EspConfigDetected` → Hello enabled → desktop → AccountSetup anchor →
+IME completion → HelloSafety → `enrollment_complete`), including the Fix-10
+bounce-then-re-knock cycle, and pins the negative space (no skip observed / no desktop /
+ghost pre-anchor IME completion / WDP).
+
+Why five of seven identically administered Cloud PCs carried `SkipUserStatusPage=True` is
+a tenant-side question (ESP profile assignment state at each machine's provisioning
+moment); the value did not change during any observed session, and machine age does not
+cleanly explain the split. The agent's job is to complete the flow Windows actually ran —
+which it now does.
+
+## Adjacent defect — the synthesis was edge-triggered
+
+This one is real but belongs to the `SkipUser=false` flow (the two sessions that
+succeeded). The user-apps-settled synthesis
+(`MaybeSynthesizeAccountSetupCompleteFromSettledUserApps`, session `caa6cf50`) ran **only**
+from `OnEspExited`. On a tenant with ~138 required apps the ESP page exits while apps are
+still in flight: the single attempt misses and nothing ever re-checks, even when every
+tracked app reaches a terminal state minutes later.
+
+The ESP exit is an **edge** (happens once); settled user-ESP apps are a **level** (reached
+later). `EspAndHelloTracker` records the edge in `_espExitObserved` and exposes
+`ReevaluateUserAppsSettledSynthesis()`, chained into `ImeLogTracker.OnAppStateChanged` and
+into the post-restore `onStateRestored` callback (a live exit observed before the IME
+state restore completes would otherwise never get a second look). Gate conditions are
+unchanged — no new completion path, only a second opportunity for the existing one. Only a
+**live, confirmed post-AccountSetup** exit may be remembered
+(`IsConfirmedPostAccountSetupExit`, stricter than the `IsIntermediateDeviceEspExit`
+forward guard: unknown counts as not confirmed).
+
+## Adjacent defect — the restart replay was never wired up
+
+`ShellCoreTracker`'s backfill had existed since session `772fe502` with **no caller**; the
+Shell-Core `EventLogWatcher` only delivers records written after `Start()`.
+`EspAndHelloHost.Start()` now calls it as `BackfillRecentHelloWizardStart` — which is
+exactly what it does and all it does:
+
+| Record | Replayed | Why |
+|---|---|---|
+| 62404 Hello-wizard start | **yes** | Conservative: vetoes a premature "Hello is disabled" skip, can never complete a session by itself. The observation `772fe502` was about. |
+| 62407 ESP exit | **no** | Cannot be placed in time — see below. |
+| 62407 ESP failure | **no** | Re-injecting a historic failure as fresh can fail a session that recovered on retry (`ANALYZE-ESP-006`). |
+
+A replayed exit is unusable, and every candidate ordering mechanism fails independently:
+
+1. Windows writes the **identical** description `CommercialOOBE_ESPProgress_Page_Exiting`
+   for the intermediate DeviceSetup→AccountSetup transition and the final exit.
+2. Every post-hoc ordering probe (AccountSetup registry, settled-apps) reads state as it
+   is **now**, not as it was at the event's time.
+3. The reducer orders exits by **ingest ordinal**, not timestamp
+   (`IsPostAccountSetupFinalExit`) — a historic exit replayed today gets a fresher ordinal
+   than reality and reads as post-AccountSetup by construction.
+4. `HandleEspExitingV1` passes `espFinalExitInFlight: true` for every arriving exit; with
+   restored state, arm C would open on a historic intermediate exit.
+
+`ClassicEspExitingOnRestoredStateTests` pins that the reducer *does* open on any arriving
+exit; `ShellCoreTrackerReplayScopeTests` pins that the replay never produces one. Skipped
+62407 records are counted and reported once as an `agent_trace`
+(`reason: replayed_62407_not_orderable`) — silently dropping evidence is how this class of
+bug survives.
+
+**Residual gap, named honestly:** a `SkipUser=false` session whose final exit falls
+exactly into an agent downtime *and* whose AccountSetup category never resolves
+(`1ec8f4c6` shape) still has no completion carrier after the restart. The normal case is
+covered — `ProvisioningStatusTracker` reads the current registry at startup, so a
+category that resolved during the downtime fires arm A. The residual shape is rare,
+surfaced by `ANALYZE-ESP-005` via the `session_stalled` interim trigger, and deliberately
+not patched with a replay that cannot be ordered.
+
+### Sizing the replay window
+
+A constant is provably wrong: the scheduled task has a `BootTrigger` only
+(`Program.InstallMode.BuildScheduledTaskXml`) — after an `exception_crash` the agent does
+not return until the next boot. `ResolveEspExitBackfillLookbackMinutes` reaches back to
+the last moment the previous run is known to have been alive (max of `snapshot.json`
+mtime and `LastBootUtc` for kill-type exits), floored at 5 minutes, capped at 360, off on
+`first_run`, and immune to cross-reboot clock skew (a future timestamp is ignored).
+
+# Examples
+
+Tenant `sits-d.cloud`, 2026-08-19, seven Windows 365 Cloud PCs, first sign-ins the same
+morning. The discriminator is a single registry value:
+
+| Session | SkipUser | `esp_exiting` | AccountSetup registry | Reboots | Outcome |
+|---|---|---|---|---|---|
+| `08fc6bda` | False | yes | yes | 0 | Succeeded (10 min) |
+| `3b9291aa` | False | yes | yes | 0 | Succeeded (2.1 h) |
+| `8110e262` | True | — | — | 2 | Incomplete (6 h watchdog) |
+| `a89aac2d` | True | — | — | 1 | Incomplete |
+| `e7ba63c9` | True | — | — | 1 | Incomplete |
+| `cb4a485a` | True | — | — | 2 | Incomplete |
+| `3d6278fb` | True | — | — | 1 | Incomplete |
+
+The reboot correlation was a red herring: `8110e262` ran six hours live after its final
+reboot and would have seen every signal. `8110e262` and `a89aac2d` both reached
+`138/138 completed, 0 failed` and a genuine IME user-session completion — with the fix,
+all five complete a few minutes after their IME user session settles.
+
+`08fc6bda` exercises the edge-level fix on the same day: ESP page exited normally while
+`categorySucceeded` never confirmed — completed via the user-apps-settled synthesis.
+`3b9291aa` shows the independent starvation visibility gap: 99 `app_install_starved`
+events on a session recorded as `Succeeded` — surfaced from now on by `ANALYZE-APP-016`.
+
+# Citations
+
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.Classic.cs` — `HandleImeUserSessionCompletedV1`, `skipUserExitEquivalent`
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.Shared.cs` — `ShouldTransitionToAwaitingHello` (arm B)
+* `src/Agent/AutopilotMonitor.DecisionCore.Tests/ClassicSkipUserEspUserSessionCompletionTests.cs` — end-to-end replay of the 8110e262 ordering
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/ShellCoreTracker.cs` — `BackfillRecentHelloWizardStart`, `ReplayBackfillRecords`
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/EspAndHelloTracker.cs` — `_espExitObserved`, `ReevaluateUserAppsSettledSynthesis`
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/DefaultComponentFactory.cs` — lookback sizing, `OnAppStateChanged` chaining
+* [MDM Reboot Coalescing](mdm-reboot-coalescing.md) — the policy attribution for the reboots themselves
+* [Decision Engine](decision-engine.md) — the AccountSetup gate and completion arms
@@ -0,0 +1,106 @@
+---
+type: Concept
+title: Power-State Watcher — live AC/battery transitions and threshold events during enrollment
+description: How the agent observes AC↔battery switches and downward battery-threshold crossings mid-enrollment via a WMI push subscription (no polling), the power_state_change event semantics (transition field, 50/30/15 ladder, latch/debounce/cap), and the two analyze rules on top (ANALYZE-DEV-009/-010).
+resource: /src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/PowerStateWatcherHost.cs
+tags:
+  - agent
+  - power
+  - battery
+  - collector
+  - wmi
+  - analyze-rules
+timestamp: 2026-08-21T00:00:00+02:00
+---
+
+# Power-State Watcher
+
+The startup probe (`power_state_check`, one-shot from `StartupEnvironmentProbes` via
+`PowerStateProbe`/`GetSystemPowerStatus`) only captures the power state at agent start. A
+device unplugged mid-enrollment — or draining its battery across a multi-hour ESP — was
+invisible. The watcher closes that gap **event-driven, with zero polling**.
+
+# Mechanism
+
+- `PowerStateWatcherHost` (`Orchestration/Hosts`) arms a WMI event subscription with a
+  two-step chain:
+  1. `SELECT * FROM Win32_PowerManagementEvent WHERE EventCode = 10` (PBT_APMPOWERSTATUSCHANGE:
+     true kernel push, fires on AC↔DC switches and battery-percentage steps).
+  2. **Fallback** `SELECT * FROM __InstanceModificationEvent WITHIN 30 WHERE TargetInstance
+     ISA 'Win32_Battery'` — required because on Windows 11 24H2/25H2 (observed on builds
+     26200 and 26220, session 161b838c) the `MS_Power_Management_Event_Provider` is still
+     registered in the repository but its activation fails with `WBEM_E_NOT_FOUND`: the
+     legacy push provider no longer loads on exactly the OS builds new devices enroll with.
+     The WITHIN sampling runs inside WinMgmt (one Win32_Battery snapshot every 30 s), not in
+     the agent; worst-case detection latency ≈ 35 s incl. debounce. `collector_degraded`
+     (`watcher_arm_failed`) is emitted only when BOTH attempts fail; the agent log's arm
+     line names the active mode.
+
+  Either way the arriving event's payload is ignored — each arrival re-probes via the
+  existing `PowerStateProbe.Probe()` (cheap P/Invoke).
+- Snapshots are diffed by the pure `PowerStateTransitionTracker`
+  (`Monitoring/Enrollment/SystemSignals`), which decides what to emit. The host only owns
+  WMI, a 5 s trailing-edge debounce timer (dock-flap AC→battery→AC inside the window
+  collapses to a no-diff) and the emit path (`InformationalEventPost`, single rail).
+- **No battery / probe error ⇒ WMI is never armed** — desktops and VMs pay nothing. WMI
+  arming runs on a background thread (WinMgmt can hang in OOBE; `ConsoleBypassWatcher`
+  precedent); an arm failure emits one `collector_degraded` (`watcher_arm_failed`).
+- Registered as a plain always-on peripheral host after `NetworkChangeHost`, deliberately
+  NOT under `PeriodicCollectorLifecycleHost`: it is push-based (zero idle cost) and must be
+  alive precisely when the device idles on battery. Kill-switch:
+  `Collectors.EnablePowerStateWatcher` (default true, compile-time default like the other
+  collector toggles; ConfigVersion 38).
+
+# Event: power_state_change
+
+`data.transition` discriminates three shapes (payload always carries `onAcPower`,
+`batteryPercent`, `isCharging`, `batteryLifeMinutes`; unknowns as `"unknown"`):
+
+| transition | Severity | Immediate | Notes |
+|---|---|---|---|
+| `ac_to_battery` | Warning | yes | one per accepted edge |
+| `battery_to_ac` | Info | no | recovery |
+| `threshold_crossed` | Info (50) / Warning (30) / Error (15) | 30+15 only | extra field `thresholdPercent` |
+
+Threshold semantics (tracker):
+
+- Ladder 50/30/15, evaluated only while ON battery; **each level latches once per agent
+  lifetime** (charge-up + re-drain does not re-emit — no plug-cycle alarm spam).
+- A multi-level jump emits only the LOWEST newly-crossed level (60%→10% ⇒ one `15` event).
+- Entering battery power already below a level counts as crossing it; the arm-time baseline
+  does too — an enrollment STARTING at 12% battery emits its `thresholdPercent: 15` event
+  immediately (the analyze rule would otherwise never see sessions that began low).
+- Lifetime emission cap 20 (storm backstop against a flapping dock / dying battery
+  controller); the host logs one warning when it engages.
+
+Backend/agent hygiene: `power_state_change` is classified as non-activity on both sides —
+`SignalActivityClassifier.NonActivityEventTypes` (agent: must not reset the
+PeriodicCollectorLifecycleHost/StallProbeHost idle clocks) and
+`EventIngestProcessor.IsPeriodicOrStallEvent` (backend: must not heal a Stalled session —
+battery drain is not enrollment progress).
+
+# Analyze Rules
+
+- **ANALYZE-DEV-009** (high): battery crossed 15% while on battery — matches the
+  agent-stamped `thresholdPercent equals 15`.
+- **ANALYZE-DEV-010** (warning): AC→battery switch — matches `transition equals
+  ac_to_battery`.
+- Both: `evaluateOn: ["enrollment_end", "whiteglove_sealed", "on_event:power_state_change"]`
+  (live interim finding + terminal finalization), `markSessionAsFailedDefault: false`.
+- Both are deliberately **single-required-condition**: `event_data` conditions scan events
+  independently (no same-instance join), so a two-condition rule (e.g. `transition ==
+  threshold_crossed AND batteryPercent < 15`) could false-positive across two different
+  power events. `thresholdPercent` exists only on threshold events and its value pins the
+  ladder level, so one condition fully identifies the instance.
+- `{{token}}` caveat: `AddDataFieldsToEvidence` whitelists only generic identifiers
+  (appId/errorCode/…), so `{{batteryPercent}}` would render literally. DEV-009 interpolates
+  `{{thresholdPercent}}` (the matched condition's own dataField); the exact percentage lives
+  on the linked event in the timeline.
+
+# Citations
+
+- `src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/PowerStateWatcherHost.cs`
+- `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/PowerStateTransitionTracker.cs`
+- `src/Agent/AutopilotMonitor.Agent.V2.Core/Runtime/PowerStateProbe.cs` (probe, unchanged)
+- `rules/analyze/ANALYZE-DEV-009.json`, `rules/analyze/ANALYZE-DEV-010.json`
+- [analyze-rule-triggers](../rules/analyze-rule-triggers.md) (interim-trigger design; the WG battery rule was its motivating case)
@@ -0,0 +1,110 @@
+---
+type: Concept
+title: System Timeline Watcher — clock steps and sleep episodes from the System event log
+description: How the agent turns two enrollment blind spots into timeline ground truth via one EventLogWatcher on the System channel — system_clock_changed (Kernel-General 1, oldTime/newTime/timeDeltaMs/process) and system_sleep_episode (Power-Troubleshooter 1 classic sleep/hibernate, Kernel-Power 507 Modern Standby) — including backfill of pre-agent records, the payload-times-are-authoritative rule, SleepSpans in time attribution, the web clock-set jump cause, and ANALYZE-DEV-012.
+resource: /src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/SystemTimelineTracker.cs
+tags:
+  - agent
+  - eventlog
+  - time
+  - clock-skew
+  - standby
+  - collector
+  - time-attribution
+  - analyze-rules
+timestamp: 2026-08-21T00:00:00+02:00
+---
+
+# System Timeline Watcher
+
+Two things silently distort every session timeline and its wall-clock duration:
+
+1. **The OS clock gets stepped** — classically w32time correcting a wrong BIOS clock early
+   in OOBE, but also tzutil/MDM actions. Before this watcher the jump was only *inferred*
+   (TimeJumpBadge, `clock_skew`/DEV-008); Windows records the ground truth.
+2. **The device sleeps mid-enrollment** — the timeline shows an unexplained gap, the
+   duration looks inflated, and nothing says "the device was simply asleep for 56 minutes".
+
+`SystemTimelineTracker` (hosted by `SystemTimelineWatcherHost`, config flag
+`Collectors.EnableSystemTimelineWatcher`, ConfigVersion 39) subscribes to the **System**
+channel with one provider-qualified XPath and forwards both facts as events.
+
+# Sources and events
+
+| Source (System channel) | Emitted event | Key payload |
+|---|---|---|
+| `Microsoft-Windows-Kernel-General` EventID 1 | `system_clock_changed` | `oldTime`, `newTime` (ISO-8601), signed `timeDeltaMs`, `reason`/`reasonText` (1=`application_set`, 2=`hardware_clock_sync`), `processName`/`processId` |
+| `Microsoft-Windows-Power-Troubleshooter` EventID 1 | `system_sleep_episode` | `kind`=`sleep`/`hibernate` (EffectiveState 5 ⇒ hibernate), `enteredAt`=SleepTime, `exitedAt`=WakeTime, `durationSeconds`, `wakeSourceType`/`wakeSourceText` |
+| `Microsoft-Windows-Kernel-Power` EventID 507 | `system_sleep_episode` | `kind`=`modern_standby`, `exitedAt`=TimeCreated, `enteredAt`=exit − DurationInUs, `durationSeconds` (scenario), `sleepDurationSeconds` (real sleep), `reason`, `onAcPower`, `batteryRemainingCapacityOnExit` |
+
+**506 is deliberately not consumed.** 507 carries the full episode; pairing 506/507 would
+need an orphan-tolerant state machine across agent restarts for zero information gain — an
+episode without a 507 never completed and would not be emitted under any design.
+
+# Thresholds (constants, not knobs)
+
+- `MinClockDeltaMs = 2000` — w32time logs Kernel-General 1 for routine **1 ms micro-slews**
+  (verified live, several per hour); only genuine steps are emitted. Suppressed records are
+  still claimed by the dedup watermark.
+- `ClockDeltaWarningMs = 5 min` — larger steps are Warning + immediate upload (can break
+  token/cert validation windows; matches the web TimeJumpBadge threshold).
+- `MinSleepDurationSeconds = 60` — **Modern Standby only**: every screen-off scenario logs a
+  506/507 pair, including seconds-long ones with `SleepDurationInUs 0` (`SleepEntered=false`);
+  the single duration gate suppresses both. Classic Power-Troubleshooter episodes have no
+  floor — they only exist for genuinely completed S3/S4 transitions.
+
+# Payload times are authoritative
+
+The decisive clock correction happens exactly when the device clock is untrustworthy, and
+the backend clamps implausible event timestamps (±168 h/24 h) to server time. Every semantic
+instant therefore travels as an explicit ISO-8601 payload field (`oldTime`/`newTime`,
+`enteredAt`/`exitedAt`); consumers must never read the event's own `Timestamp` for these.
+The event `Timestamp` is set to the record's TimeCreated (WindowsUpdateTracker backfill
+convention) so rows land where the wake/step happened.
+
+# Backfill and dedup
+
+Template: `WindowsUpdateTracker`. `LoadWatermark → arm watcher → backfill` with lookback
+`SystemEventBackfillLookbackMinutes` (default 1440 = 24 h; 0 disables). The System .evtx
+persists across OOBE reboots, so the pre-agent w32time correction and pre-agent standby
+episodes are recovered with `backfilled=true`. Cross-restart dedup via RecordId watermark
+(`system-timeline-watermark.json` in the state directory) plus an intra-run `HashSet` —
+deliberately **not** a high-water mark, which would drop exactly the older, never-emitted
+pre-agent records (the live watcher arms before the backfill scan).
+
+# Non-activity classification (both sides)
+
+Both event types are environment observation, not enrollment progress:
+`SignalActivityClassifier.NonActivityEventTypes` (agent — must not reset idle/stall clocks)
+and `EventIngestProcessor.IsPeriodicOrStallEvent` (backend — a device that slept through its
+stall must stay Stalled).
+
+# Consumers
+
+- **Web timeline** (`EventTimeline.tsx`): badge blocks for both events; the TimeJumpBadge
+  gains the ground-truth cause `clock-set` — `classifyTimeJump` receives the session's
+  `system_clock_changed` deltas and matches a backward display step against a backward clock
+  set within max(60 s, 20 %) (`lib/timeProvenance.ts`).
+- **Duration story** (`SessionInfoCard` via `useSessionDerivedData.standbySeconds`): the
+  wall-clock duration deliberately keeps the pause (the enrollment really took that long);
+  a `· 🌙 56m standby` note explains it. Episodes are dedup'd on `enteredAt`.
+- **Time attribution** (`TimeAttributionCalculator.BuildSleepSpans`, AttributionVersion 3):
+  `SleepSpan`s mirror `RebootSpan`s — cross-cutting annotations clipped to the observation
+  windows (a WhiteGlove-pause episode contributes only its in-window flanks), never a slice
+  of the wall-clock partition. Persisted as `SleepSeconds`/`SleepSpansJson`; rendered as the
+  standby chip in `TimeAttributionLane`.
+- **ANALYZE-DEV-012** (info, `trigger: single`, `on_event:system_sleep_episode`): fires once
+  per session for episodes ≥ 5 min. Deliberately the ONLY new rule: clock issues already
+  have DEV-008 (`clock_skew`) — a second clock rule would double-report the same action item
+  (user decision 2026-08-21); clock steps stay timeline ground truth with badges instead.
+
+# Citations
+
+- `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/SystemTimelineTracker.cs`
+- `src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/SystemTimelineWatcherHost.cs`
+- `src/Backend/AutopilotMonitor.Functions/Helpers/TimeAttributionCalculator.cs` (`BuildSleepSpans`)
+- `src/Web/autopilot-monitor-web/lib/timeProvenance.ts` (`clock-set`, `findExplainingClockChange`)
+- `rules/analyze/ANALYZE-DEV-012.json`
+- Live payload evidence (2026-08-21, Win11 26220): Kernel-General 1 with `TimeDeltaInMs=1`
+  micro-slews; Kernel-Power 507 with `SleepDurationInUs=2324095807`; Power-Troubleshooter 1
+  with `SleepTime`/`WakeTime` across a hibernate.
@@ -0,0 +1,108 @@
+---
+type: concept
+title: WDP Scenario Gates & Completion Backstop
+description: How the agent gates Autopilot/ESP-only machinery off on Windows Device Preparation (WDP) sessions and how a WDP session resolves without any ESP signal.
+resource: agent
+tags: [wdp, device-preparation, decision-engine, collectors, completion]
+timestamp: 2026-08-18
+---
+
+# Schema
+
+Windows Device Preparation (Autopilot v2, "WDP") has **no deployment profile and no ESP**.
+Before the afee7ae0 audit (2026-08-18) the agent ran the full Classic apparatus anyway:
+misleading `autopilot_profile_missing` warnings, a ZTD event-log query + HTTP probe,
+`esp_config_detected` "unknown/unknown" noise, an Autopilot-channel noise flood
+(EventIDs 100/417/418/1005, 900+ occurrences per session), a subtree registry watcher
+woken by every WDP progress write, and — worst — no completion path when Hello never
+resolved (park until the 360-min watchdog).
+
+## Detection: deterministic vs. fallback
+
+`EnrollmentRegistryDetector` classifies v2 through three rules. Only the first is
+**deterministic WDP**:
+
+1. `AutopilotSettings\DevicePreparation\BootstrapperAgent` subkey with non-empty
+   `ExecutionContext` → the WDP policy orchestration tree, present before the agent
+   starts. Exposed as `EnrollmentRegistryDetector.IsDeterministicDevicePreparation()`
+   and the `DevicePreparationExecutionContextRule` constant.
+2./3. `CloudAssignedDeviceRegistration == 2` / `CloudAssignedEspEnabled == 0` —
+   profile-derived legacy signals. They imply a REAL Autopilot profile (just ESP-less),
+   so every gate below deliberately ignores them: **gates require the deterministic
+   marker and fail toward Classic behavior.**
+
+## Agent-side gates (all keyed to the deterministic marker)
+
+* `DeviceInfoCollector.CollectAutopilotProfile`: no `autopilot_profile` event, no
+  `autopilot_profile_missing` warning, no ZTD event-log query, no ZTD HTTP probe.
+  `enrollment_type_detected` still fires. (WDP devices DO carry an
+  `AutopilotPolicyCache` with `ProfileAvailable=0` / error 807 `ZtdDeviceIsNotRegistered`
+  — Windows runs the ZTD download regardless — so the probe fired for real before.)
+* `CollectEspConfigurationLocked`: `esp_config_detected` is emitted only when at least
+  one FirstSync value or ESP tracking list exists (generic null-gate, mirrors the
+  orchestrator bootstrap's signal gate) — fixes "unknown/unknown" for WDP AND plain
+  Entra joins.
+* `DefaultComponentFactory`: `EspPolicyProviderStallHost` (60-s poll of the ESP-only
+  `EnrollmentStatusTracking` key) is not created on WDP.
+* `EspAndHelloTracker.Start`: `ProvisioningStatusTracker` is not started on WDP — its
+  subtree watcher sits on `AutopilotSettings`, exactly where WDP's BootstrapperAgent
+  writes progress, so it woke on every write only to read three ESP category values
+  that never exist there.
+* `ModernDeploymentTracker`: `DevicePreparationNoiseEventIds` {100, 417, 418, 1005}
+  are suppressed entirely on WDP (before `FormatDescription()`); Critical (level 1)
+  always passes; genuine WDP diagnostics (e.g. 408) keep flowing. The Autopilot error
+  backfill (807/809/815/908 replay) is skipped — 807 is the EXPECTED state on WDP.
+  The watcher itself stays on: WDP's provisioning stack logs into the same channels.
+* `StallProbeCollector`: skips the ESP category registry scan on WDP and unions the
+  noise IDs into its harmless set; the channel scans remain (they carry genuine WDP
+  diagnostics during a stall).
+* `EnrollmentTerminationHandler`: the `app_install_starved` terminal sweep is skipped
+  on WDP — post-desktop installs are the DESIGNED order there (only DPP-policy apps
+  run during provisioning); per-app data still travels via `app_tracking_summary` and
+  final-status.json.
+
+## DecisionCore: WDP completion without ESP facts
+
+* **Seeding**: `EnrollmentFactsObserved` carries `enrollmentTypeDeterministic`;
+  the deterministic marker seeds `DevicePreparation` at **High** confidence (same
+  registry-determinism standard as the self-deploying OobeConfig bits), the fallback
+  rules stay Medium. The three explicit downgrade guards from d0ab3eee remain as
+  defence in depth.
+* **Arm D** (`ShouldTransitionToAwaitingHello`): on WDP the DAD-validated real-user
+  desktop is a legitimate promotion basis — arms A–C are unsatisfiable by construction
+  (no provisioning categories, no Shell-Core 62407 final exit). With a disabled Hello
+  policy the fast-path now completes at desktop arrival.
+* **Prerequisites**: `completion_waiting` never lists
+  `account_setup_provisioning_complete` on WDP (unsatisfiable; mirrors the
+  `skipUserEsp` exemption).
+* **Backstop**: `DeadlineNames.DevicePrepCompletion` (30 min, replay-safe base) is
+  armed by `HandleDesktopArrivedV1` when a WDP session parks desktop-first with Hello
+  pending. On fire it mirrors the HelloSafety timeout: synthetic
+  `HelloOutcome=Timeout` + completion through Finalizing. This closes the
+  "no Hello → park until watchdog" hole; a timer surviving into a terminal stage is
+  swallowed by the post-terminal dispatch guard.
+* **Tripwire**: `DecisionStepProcessor.IsParkedWithoutDeadline` has a WDP branch
+  (dead-end zone = desktop arrived) so a regression in the backstop becomes visible
+  as `session_parked_without_deadline`.
+
+# Examples
+
+Session afee7ae0 (the audit trigger): Succeeded in 9:32 min, but its timeline carried
+`autopilot_profile` (807), an `autopilot_profile_missing` WARN, `esp_config_detected`
+unknown/unknown, 30 `modern_deployment_log` rollup events and 10 `app_install_starved`
+entries — all structurally meaningless on WDP. After the gates, the same session shape
+emits none of these; completion rode Hello-skipped + desktop as before.
+
+Deliberately NOT changed (open follow-ups, see the WDP audit topic memory): the ESP
+phase vocabulary (`esp_phase_changed`/stage names ride the Classic rails on WDP),
+subscription to the `BootstrapperAgentServiceLogProvider` event channel, and
+`registry_app_state` as the primary WDP app source.
+
+# Citations
+
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Security/EnrollmentRegistryDetector.cs` — deterministic rule + helper
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/DeviceInfo/DeviceInfoCollector.NetworkAndSecurity.cs` — profile/ESP emission gates
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/ModernDeploymentTracker.cs` — `DevicePreparationNoiseEventIds`
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.DevicePreparation.cs` — backstop deadline
+* `src/Shared/AutopilotMonitor.DecisionCore/State/EnrollmentScenarioProfileUpdater.cs` — High/Medium seeding
+* Tests: `DevicePreparationEngineTests`, `ModernDeploymentTrackerDevicePrepTests`, `EnrollmentTerminationHandlerTests.StarvedApps_skipped_on_device_preparation`, `DeviceInfoCollectorEspRefreshTests.NoEspEvidenceAtAll_SuppressesTheEvent`
@@ -0,0 +1,185 @@
+---
+type: Concept
+title: WiFi SSID and the Windows 24H2 Location Gate
+description: Why wifi_signal_info silently disappeared on Windows 11 24H2+ devices, why the netsh fallback could never fix it, and the tiered reader that restores the SSID from the SYSTEM context.
+resource: src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/WifiInfoProvider.cs
+tags:
+  - agent
+  - interop
+  - wifi
+  - telemetry
+timestamp: 2026-08-26T14:05:00+02:00
+---
+
+# Summary
+
+The agent reports the enrollment WiFi as a `wifi_signal_info` event (SSID, signal, PHY, channel).
+On Windows 11 24H2 and later the event went missing on a large share of devices — no error, no
+partial payload, simply no event. The cause is a Windows privacy change, not a bug in the reader:
+**`WlanQueryInterface` with `wlan_intf_opcode_current_connection` is gated behind precise-location
+consent**, and the agent runs as SYSTEM in session 0 where that consent usually does not exist.
+
+The fix is a tiered reader ([WifiInfoProvider](../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/WifiInfoProvider.cs))
+whose middle tier uses the one SSID API Microsoft left ungated.
+
+# The Gate
+
+Microsoft restricted the Win32 WLAN APIs that expose BSSIDs, because nearby-BSSID lists are a
+precise-location oracle. Without consent these return `ERROR_ACCESS_DENIED` (5):
+
+* `WlanGetAvailableNetworkList`
+* `WlanGetNetworkBssList`
+* `WlanScan`
+* **`WlanQueryInterface` when `OpCode` is `wlan_intf_opcode_current_connection`** — the only opcode
+  the agent needs, and the one that carries SSID, signal quality, PHY type.
+
+Two properties of the gate decide the agent's fate:
+
+1. **The consent prompt only appears for a process running in the user's context and outside
+   `C:\Windows\System32`.** The agent is neither during ESP: it is SYSTEM, in session 0, before any
+   user has seen the OOBE privacy page. It is therefore denied *silently* — no prompt, no event
+   log, nothing that surfaces without asking the API for its return code.
+2. **Consent resolves per user hive, with the device-level setting as the floor.** An interactive
+   user typically has
+   `HKCU\...\CapabilityAccessManager\ConsentStore\location\NonPackaged\Value = Allow`
+   ("Let desktop apps access your location"). The SYSTEM account (`HKU\S-1-5-18`) normally has
+   **nothing** set there and falls back to
+   `HKLM\...\ConsentStore\location\Value`. Where that device-level value is `Deny`, SYSTEM is
+   denied even though the logged-on user on the very same machine reads the SSID fine.
+
+That asymmetry is why the failure looks random from the outside: it tracks the **image's
+device-level location setting**, which varies per fleet, not per hardware, driver, or language.
+
+# Why netsh Was Never the Answer
+
+`NetshWifiFallback` was added in 2026-07 on the theory that inbox `netsh` still reported the
+connection where the WLAN API did not, and it was later extended with localized label variants for
+every enrollment-geography language. Field data says otherwise: **`netsh wlan` hangs off the same
+location gate** ("Network shell commands need location permission to access WLAN information"), so
+it fails in lockstep with tier 1 rather than covering for it. In the reported session the agent
+build already contained the netsh fallback and still produced no event.
+
+Consequence for future work: **adding more netsh language labels cannot fix a missing SSID.** Every
+`wifi_signal_info` event that does exist carries a fully populated SSID — the failure is binary at
+the reader level, never a half-parsed or mis-decoded payload. A missing SSID is an access problem,
+not a parsing problem.
+
+# The Tiered Reader
+
+`WifiInfoProvider.TryRead` owns the order so the two collectors (`DeviceInfoCollector`,
+`NetworkChangeDetector`) cannot drift apart. First non-null wins:
+
+| # | Reader | Yields | Location-gated |
+|---|---|---|---|
+| 1 | `WifiInfoReader` (native `wlanapi.dll`) | SSID, signal %, PHY, channel | yes |
+| 2 | `WinRtWifiSsidReader` (WinRT `GetConnectedSsid`) | SSID only | **no** |
+| 3 | `NetshWifiFallback` (process spawn, localized parse) | SSID, signal %, radio type, channel | yes |
+
+Tier 2 is Microsoft's own documented replacement for this exact scenario:
+`Windows.Networking.Connectivity.WlanConnectionProfileDetails.GetConnectedSsid()`. It is not part of
+the BSSID-bearing surface, so it needs no consent, and it has existed since Windows 10 1507.
+
+It is bound through the CLR's built-in WinRT projection with
+`Type.GetType("…, ContentType=WindowsRuntime")` — no NuGet package, no winmd reference, no csproj
+change — the same mechanism [OobeStateReader](../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/OobeStateReader.cs)
+already uses from the SYSTEM service context. Every step degrades to null rather than throwing,
+because the caller runs fire-and-forget inside `Task.Run`.
+
+# Telling the Operator
+
+A missing signal reading is indistinguishable from a bug unless the payload says why, and the
+device-level location setting is not something an admin would think to check. When tier 2 wins
+*and* the native tier reported `rc=5`, the `wifi_signal_info` payload therefore carries
+
+```
+wifiDataLimitedReason = "location_services_off"
+```
+
+and the event message gains `- signal unavailable, Location services off`, so the reason is visible
+in the timeline itself. The portal's WiFi card (`DeviceDetailsCard`) matches that literal and
+renders the explanation plus the Intune setting that fixes it. The value is a published contract —
+agent, portal and the MCP device-property catalog all match the same string.
+
+The claim is only made on observed evidence: any other native failure (no WLAN service, no
+connected interface) leaves the field null rather than blaming a privacy setting we did not
+measure. `WifiInfoProvider.IsLocationGateDenied` is the single predicate, pinned by tests at its
+boundaries (`rc=5` yes; `rc=50`, `rc=5023`, `rc=1062` no).
+
+The network timeline reads the same field. It needs no payload of its own: `buildSegments`
+already merges every `wifi_signal_info` into the WiFi segment covering its timestamp, so the
+reason rides in with the sample. A segment that never got a sample (a mid-session reconnect emits
+no `wifi_signal_info`) inherits it — the gate is a device-level setting and cannot flip during an
+enrollment — while a segment that *did* get a real reading is never overwritten. The segment
+tooltip then reads `Signal: unavailable - Location services off on this device` where the
+percentage would be, and the "Avg WiFi signal" stat says `n/a (Location services off)` instead of
+disappearing.
+
+`network_state_change` deliberately does NOT carry the reason: that event has never carried
+`signalPercent` or `radioType` at all (`NetworkChangeDetector` collects them into its snapshot for
+change detection but only `before_/after_wifiSsid` reaches the payload), so there is no absent
+field there for a reason to explain. Adding it would ship a field nothing reads. The SSID it does
+carry is unaffected by the gate.
+
+Fleet-wide the same field is queryable through
+`search_sessions(deviceProperties: { "wifi_signal_info.wifiDataLimitedReason": "location_services_off" })`,
+which sizes how much of a fleet is affected before anyone changes a policy.
+
+Tier 2 returns the SSID alone. Signal quality, PHY type and channel have no ungated source; they
+stay null when the native tier is denied. That is deliberate — deriving a percentage from
+`ConnectionProfile.GetSignalBars()` (0–5) would fabricate precision the API does not have.
+
+# Diagnostics
+
+The step-level native return codes were already collected, but they were logged with
+`_logger.Debug` — and the agent's default log level is `Info`, so the diagnostic built to explain
+this failure never reached a single field log. Both collectors now log at **Warning** when all tiers
+fail, which they only reach when the active NIC really is WiFi. A native `rc=5` is spelled out as
+`ERROR_ACCESS_DENIED` with the location-gate explanation, so the log line diagnoses itself:
+
+```
+EnrollmentTracker: no wifi_signal_info — no WiFi info from any reader — native: [<guid>]
+query(current_connection) rc=5; ; WinRT: no SSID; netsh: no parsable output. rc=5 is
+ERROR_ACCESS_DENIED — Windows 11 24H2+ gates the current-connection opcode (and netsh wlan)
+behind precise-location consent, which is off in this image; enable Location services to
+restore signal/PHY/channel.
+```
+
+# Evidence
+
+Session `7305e0ad` (HP EliteBook X Flip G1i, build 26200.9168, agent 2.0.1407, reported as
+`WIFI SSID fehlt`): `network_interface_info` shows the active NIC as `Intel(R) Wi-Fi 7 BE201`,
+`Wireless80211`, `connectionType=WiFi`, so the `isWifi` gate passed and collection ran — yet zero
+`wifi_signal_info` events across 214 events and 22 minutes, with the netsh fallback already shipped
+in that build.
+
+Fleet correlation over WiFi sessions from 2026-08-01 (n=276), share with a `wifi_signal_info` event:
+
+| OS build | WiFi sessions | with SSID |
+|---|---|---|
+| 22631 (23H2, pre-gate) | 3 | 100% |
+| 26100 (24H2) | 178 | 21% |
+| 26200 (25H2) | 95 | 45% |
+
+Within a single model the outcome splits by fleet, not by hardware — ThinkPad T14 Gen 6: 7/91;
+ThinkPad E14 Gen 7: 9/9 — which is what a per-image privacy setting looks like.
+
+Local verification (build 26220.9022): `HKLM\…\ConsentStore\location = Deny` while
+`HKCU\…\ConsentStore\location\NonPackaged = Allow`; the interactive user reads the SSID through
+both the native API and netsh, `HKU\S-1-5-18` has no consent value at all, and the WinRT chain
+resolves and returns the SSID under net48.
+
+# Operator Guidance
+
+A device that reports no SSID is not misconfigured for enrollment — only the telemetry field is
+missing. To get the full payload (signal, PHY, channel) back, the **device-level** location setting
+must be on: *Settings → Privacy & security → Location → Location services*, or via Intune
+(`Privacy/LetAppsAccessLocation`). Without it the SSID still arrives via tier 2.
+
+# Citations
+
+* [Changes to API behavior for Wi-Fi access and location](https://learn.microsoft.com/en-us/windows/win32/nativewifi/wi-fi-access-location-changes)
+* [WlanConnectionProfileDetails.GetConnectedSsid](https://learn.microsoft.com/en-us/uwp/api/windows.networking.connectivity.wlanconnectionprofiledetails.getconnectedssid)
+* [WifiInfoProvider.cs](../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/WifiInfoProvider.cs)
+* [WinRtWifiSsidReader.cs](../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/WinRtWifiSsidReader.cs)
+* [WifiInfoReader.cs](../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/WifiInfoReader.cs)
+* [NetshWifiFallback.cs](../../src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Interop/NetshWifiFallback.cs)
@@ -0,0 +1,136 @@
+---
+type: Concept
+title: Zero User-Targeted Apps — the starved user-phase completion gate
+description: Why a device with no user-targeted Intune apps could never satisfy the IME user-session gate, how that turned into a 30-minute esp_exit_without_completion_evidence false positive on a third of one tenant's enrollments, and the two fixes — reading the line IME actually writes in its zero-app branch, and refusing to fail a session while a completion gate is deliberately holding it.
+resource: /src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime
+tags:
+  - agent
+  - ime
+  - esp
+  - completion
+  - realmjoin
+  - false-positive
+timestamp: 2026-08-25
+---
+
+# Summary
+
+A Classic user-driven enrollment whose user has **zero targeted Intune Win32 apps** could not
+produce the evidence every user-phase completion path required. The session parked, and the
+30-minute `advisory_completion` backstop resolved it as
+`enrollment_failed: esp_exit_without_completion_evidence` — while the user was at a working
+desktop, Windows Hello was provisioned, and RealmJoin was still installing packages.
+
+One tenant hit this on **10 of 30 enrollments in a week**. Every one of them was a false
+positive; the devices were healthy in Intune and RealmJoin.
+
+# The starvation chain
+
+The IME writes `Completed user session N, userId: …` at the end of a user-session processing
+pass. `IME-USER-SESSION-COMPLETED` matches it and the adapter posts
+`ImeUserSessionCompleted`, which sets `DecisionState.ImeUserSessionCompletedUtc`.
+
+But the IME never reaches that statement when the user has no assigned apps. Decompiled IME
+`1.104.102.0`, `Win32AppPlugIn/ApplicationPoller.cs`:
+
+```csharp
+if (!appPolicies.Any())
+{
+    AppWorkloadLog.TraceInformation($"[Win32App] Get 0 apps for user session {user.RDSSessionId}, user id = {user.IntuneId}");
+    RegisterApplicationsInIfInESP(sender, user, delegate {
+        espLockInProcessor.AttemptToLockInApplications(user, new List<ProcessorSubgraph>());
+    });
+    continue;                       // skips the "Completed user session" statement below
+}
+```
+
+Identical shape in `1.97.107.0`, `1.83.107.0`, `1.80.132.0`. With that fact missing, every door
+out of the user phase is shut at once:
+
+| Path | Requirement | Why it is dead |
+|---|---|---|
+| `ShouldTransitionToAwaitingHello` arm A | `AccountSetupProvisioningSucceededUtc` | ESP registry froze at `AccountSetup: 1 of 5`; neither `categorySucceeded` nor the all-subcategories fallback can ever hold |
+| arm B | `SkipUserEsp` | Full ESP, not a skip-user flow |
+| arm C | `IsImeUserSessionGenuine` | needs the missing IME fact |
+| arm D | `EnrollmentMode.DevicePreparation` | Autopilot v1, not WDP |
+| `MaybeSynthesizeAccountSetupCompleteFromSettledUserApps` | `AreUserEspAppsSettled` | returned `false` on an empty app list |
+| `HandleAdvisoryCompletionDeadlineFired` conjunction | `imeUserSessionGenuine \|\| isObservationAdvisory` | both false |
+
+The last row is the one that produced the verdict: the backstop that exists to resolve a
+dead-end resolved it as a failure.
+
+`AreUserEspAppsSettled` deserves its own note. Its "at least one required app" rule is
+deliberately conservative — an empty list normally means *the phase just cleared* or *apps have
+not surfaced yet*. But it made **zero apps**, the most settled state possible, indistinguishable
+from *unknown*, and there was no evidence available to tell them apart.
+
+# Fix 1 — read the line IME does write
+
+`IME-USER-SESSION-ZERO-APPS` matches the zero-app line and routes it through the **same**
+`OnUserSessionCompleted` callback. Downstream this genuinely *is* a completed user session, so
+the adapter's pending-apps deferral and its fire-once flag apply unchanged.
+
+This is not a weakened gate — it is IME's own verdict. The zero-app branch locks the ESP in with
+an *empty* application list, and the sibling emit site in `AppWorkloadAbstraction.ExecuteUserCheckIn`
+returns `ProviderResult.ProvisioningComplete` straight after logging it. All three emit sites are
+user-session-scoped (`user.RDSSessionId`, `user.IntuneId`); none is device-scoped.
+
+Guards that stay in force:
+
+* **Phase guard** — the observation only fires while the tracker is in `AccountSetup`. Firing
+  earlier would burn the adapter's fire-once flag on a pre-sign-in (defaultuser0) timestamp that
+  `IsImeUserSessionGenuine` (`>= AccountSetupEnteredUtc`) can never accept. An observation made
+  before the phase was known is remembered and replayed on the transition into it, because IME
+  writes its check-in lines independently of when the agent first parses the phase marker.
+* **Engine guards unchanged** — arm C still requires a post-AccountSetup final ESP exit *and* a
+  DAD-validated real-user desktop.
+* `AreUserEspAppsSettled` returns `true` for an empty list **only** with this explicit
+  observation — never for a merely empty list.
+
+# Fix 2 — do not fail while a completion gate is holding
+
+An independent defect, and the decisive one for the affected tenant. `advisory_completion` runs
+for 30 minutes. The RealmJoin completion gate blocks completion until phase 110 and carries its
+*own* bounded resolution: 60 minutes from detection, re-armed on deployment activity, hard-capped
+at 4 hours. The shorter timer always won.
+
+Session `75d6ae8e` installed **25 RealmJoin packages successfully inside the window**, the last
+one 2 minutes before the failure, while the engine's own `completion_waiting` still read
+`waiting on: realmjoin_resolution`.
+
+`HandleAdvisoryCompletionDeadlineFired` now re-arms instead of failing when the RealmJoin gate is
+closed *and* its deadline is still armed, emitting `completion_waiting` with trigger
+`DeadlineFired:advisory_completion:CompletionGateHolding`.
+
+Convergence comes from the gate itself: `Resolved`, `FirstDeploymentIncomplete` and `Timeout` all
+set `RealmJoinFacts.Outcome`, which opens `RealmJoinGateOpen` and stops the guard applying.
+Requiring the gate's deadline to still be armed keeps a gate that can no longer resolve itself
+from parking the session; `AgentMaxLifetimeMinutes` bounds it regardless.
+
+# Timeline evidence
+
+`ime_user_session_completed` carries an `evidence` field so the basis of the verdict is legible
+without the diagnostics archive:
+
+* `user_session_completed` — IME wrote its completion line and no required app was pending.
+* `zero_user_apps_enumerated` — IME reported zero targeted apps; the user phase had nothing to
+  enforce.
+
+No new event type: the fact is the same, only the observation behind it differs.
+
+# Deployment
+
+The pattern ships through the config API and reaches existing agents without a rebuild; an agent
+that does not know the `userSessionZeroApps` action logs one Debug line and ignores it. The
+*behaviour* needs an agent release. Sessions already stamped `Failed` are not reclassified — the
+backend mirrors the agent verdict (`VerdictPaths.AgentFailed`) and has no independent judgement
+here by design.
+
+# Citations
+
+* `rules/ime-log-patterns/IME-USER-SESSION-ZERO-APPS.json`
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime/ImeLogTracker.Handlers.cs` — `HandleUserSessionZeroApps`, the phase replay in `HandleEspPhaseDetected`
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime/ImeLogTracker.cs` — `AreUserEspAppsSettled`
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/SignalAdapters/ImeLogTrackerAdapter.cs` — `EmitUserSessionCompleted`, evidence labels
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.Edge.cs` — `HandleAdvisoryCompletionDeadlineFired`
+* [decision-engine.md](decision-engine.md), [post-reboot-completion-recovery.md](post-reboot-completion-recovery.md)
@@ -0,0 +1,165 @@
+---
+type: Concept
+title: Admin Identity Binding — tid + oid behind every cross-tenant-role UPN
+description: Why a GlobalAdmins or DelegatedAdmins row keyed on a UPN string must never confer access by itself in an API that accepts tokens from every Entra tenant, the AdminIdentityBindings table that pins each such UPN to its immutable home tenant id and object id, the fail-closed resolution order in both role services, the first-sign-in object-id pin, and the explicit rebind surface.
+resource: src/Backend/AutopilotMonitor.Functions/Services/AdminIdentityBindingService.cs
+tags:
+  - backend
+  - security
+  - authorization
+  - multi-tenant
+  - global-admin
+  - delegated-admin
+timestamp: 2026-08-29T00:00:00+02:00
+---
+
+# Problem
+
+The API is a multi-tenant Entra application on purpose: `AuthenticationMiddleware` accepts a token from
+any tenant (issuer prefix `login.microsoftonline.com/` or `sts.windows.net/`), and signature, audience,
+lifetime and algorithm are validated strictly. Tenant-member roles (`TenantAdmins`) are keyed on
+`(tid, upn)` and therefore bound to the verified tenant.
+
+The two cross-tenant tiers were not. `GlobalAdmins` (GlobalAdmin / GlobalReader) and the delegated MSP
+tier (`DelegatedAdmins` + `TenantGroupAssignments`) resolved their role from the **UPN string alone**
+(`upn`, falling back to `preferred_username`). Both claims are mutable and reusable across tenants:
+
+* **Domain re-registration**: if the domain behind a platform admin's UPN lapses or moves, whoever
+  verifies it in a fresh tenant can mint the identical UPN; the token is genuine, only `tid` differs.
+* **UPN recycling**: a User Administrator in the home tenant can re-assign the UPN to another account;
+  same `tid`, different `oid`.
+* **MSP variant**: the delegated tier was gated only on the caller's home tenant being Pro — which any
+  tenant can self-provision via the trial endpoint.
+
+Any of these yielded full platform scope: raw table dumps including `TenantConfiguration` secrets,
+tenant offboarding, GA management. Microsoft's own guidance (post-nOAuth) is explicit: authorization
+data must be keyed on the immutable `tid` + `oid` pair, never on `upn` / `preferred_username`.
+
+# Mechanism
+
+## One binding per UPN
+
+`AdminIdentityBindings` (PK `Bindings`, RK = lowercase UPN) holds, for every UPN that carries a
+cross-tenant role, the identity that may use it:
+
+| Column | Meaning |
+| --- | --- |
+| `TenantId` | The admin's **home** Entra tenant — must equal the JWT `tid`. Mandatory at grant time. |
+| `ObjectId` | The admin's Entra object id — must equal the JWT `oid`. Empty until pinned. |
+| `BoundBy`, `BoundDate` | Operator provenance. |
+| `ObjectIdPinnedDate` | When the object id was fixed (grant time, or the first matching sign-in). |
+
+A single table rather than columns on three role tables: a UPN string belongs to exactly one identity
+at a time, a person may hold a GlobalAdmins row *and* delegated assignments, and the role rows stay
+what they are — grants. The binding says whose grants they are.
+
+## Resolution order (both role services)
+
+`AdminIdentity` is the record `(Upn, TenantId, ObjectId)` built from a validated principal; it is
+`null` when any of the three claims is missing (app-only tokens, foreign IdP shapes). Both
+`GlobalAdminService.GetGlobalRoleAsync(AdminIdentity?)` and
+`DelegatedAdminService.GetScopeAsync(AdminIdentity?)` follow the same order:
+
+1. `null` identity → no role, no storage read.
+2. Resolve the **row** by UPN (cached 30 s, unchanged from before).
+3. No row / empty scope → return; the binding is not even read. Ordinary tenant users cost one cached
+   read and never produce a binding log line.
+4. `AdminIdentityBindingService.IsBoundAsync(identity)` → false ⇒ no role / empty scope.
+5. Delegated only: the Pro home-tenant entitlement gate, **after** the binding check — an unbound caller
+   never triggers an edition lookup.
+
+`IsBoundAsync` is the single choke-point: no binding ⇒ false; `TenantId` mismatch ⇒ false (checked
+before anything else, so a foreign-tenant token can never claim the pin below); pinned `ObjectId`
+mismatch ⇒ false; unpinned binding + matching tenant ⇒ **pin** the caller's `oid` and verify against
+what was actually stored afterwards. Every false outcome is logged at Warning with its reason
+(`[IdentityBinding] TENANT MISMATCH …` / `OBJECT-ID MISMATCH …` / `holds no identity binding`), the
+one level the worker forwards to Application Insights; matches are silent. Pins are logged at Warning
+once — they are one-off, operator-relevant events.
+
+The pin is a conditional update in the repository (`TryPinIdentityObjectIdAsync`: only onto an unpinned
+row homed in the caller's tenant, ETag-guarded; a 412 re-reads and the caller compares against the
+winner). Two accounts racing the first sign-in inside the home tenant therefore leave exactly one bound.
+
+Row lookups stay cached by UPN; the binding has its own 30 s cache keyed by UPN and is invalidated on
+pin, rebind and removal. A rebind on one scaled-out instance converges on the others within seconds.
+
+## Grants bind first — and resolve the identity themselves
+
+Granting is "type the UPN". The three grant endpoints (`POST auth/global-admins`,
+`POST global/delegated-admins`, `POST global/tenant-groups/{id}/assignees`) accept `homeTenantId` /
+`objectId` only as optional overrides; normally `AdminIdentityResolver` supplies them:
+
+1. **Sign-in history** (`UserActivity`, filtered on the UPN): the person has signed in before ⇒ tid + oid
+   are known, both from validated tokens. The most recent sign-in wins for the oid. A UPN seen under
+   **more than one tenant** is never auto-resolved — that is the attack shape the binding exists for.
+2. **UPN domain → onboarded tenant** (`TenantConfiguration.DomainName`, exactly one match): tid only; the
+   oid is pinned on the first sign-in.
+3. Neither ⇒ **422 `HomeTenantUnresolved`**; the portal then shows a home-tenant picker (onboarded
+   tenants) and retries with `homeTenantId`. This is the only manual step, and only for a UPN whose
+   domain the platform has never seen.
+
+`AddGlobalAdminAsync`, `DelegatedAdminService.UpsertAsync` and `AssignGroupAsync` then take the resolved
+`homeTenantId` / `objectId` and call `EnsureBoundAsync` **before** writing the role row. `EnsureBoundAsync` creates the binding, keeps a compatible one (same tenant; the
+supplied object id equals the pin or upgrades an unpinned one), and throws
+`IdentityBindingConflictException` for a different tenant or a different pinned object id — the
+functions map that to **409**. A grant can therefore never silently re-home a UPN.
+
+Why the object id may be unknown: a person who has never signed in has no history to resolve from, and
+the operator granting an external MSP admin has no directory access to the partner tenant. The first
+sign-in from the bound tenant pins it; from then on a recycled UPN in the same tenant is refused.
+
+## Explicit rebind surface
+
+| Route | Policy | Purpose |
+| --- | --- | --- |
+| `GET global/identity-bindings` | GlobalReadOrAdmin | Audit which tenant / object id each grant is usable from. |
+| `PUT global/identity-bindings/{upn}` | GlobalAdminOnly | Replace the binding: move a UPN to another tenant, or re-pin after a legitimate account re-creation (omit `objectId` to clear the pin). |
+| `DELETE global/identity-bindings/{upn}` | GlobalAdminOnly | Make every role row of the UPN inert without touching the rows. Self-removal is refused. |
+
+Both mutations are audited under the binding's home tenant (`AdminIdentityBinding` entity, previous
+values in the details) and logged at Warning. The portal surfaces this in **Tenant Management → Edit
+Tenant Configuration → Identity bindings** (collapsed): the bindings homed in that tenant, with inline
+edit (re-home / re-pin; empty object id ⇒ re-pinned on the next sign-in) and remove. The grant forms
+themselves carry no identity fields — the binding is a background property of the grant.
+
+## Lifecycle and secondary effects
+
+* `AdminIdentityBindings` is in `TableNames.All`, in `CriticalBackupTables.All` and in
+  `AuthTablesFullRestoreForbidden` (single-row restore only, like the other auth tables).
+* Tenant offboarding wipes bindings whose `TenantId` is the offboarded tenant (property-only bucket):
+  once a home tenant is gone, its admins' grants become inert.
+* `RequestContext.ObjectId` carries the JWT `oid`; `AdminIdentity.FromRequestContext` serves the
+  handlers that resolve roles outside the middleware (SignalR group join/leave, health checks).
+* The throttle identity (`GetCallerId`) now prefers `oid` over the UPN, so two accounts in different
+  tenants that share a UPN string no longer share a rate-limit bucket. Audit and presence rows keep the
+  UPN as their display key; they already carry the tenant id.
+* Legacy role rows without a binding are **inert, not grandfathered**. Rolling this out therefore means
+  seeding the binding rows for the existing admin UPNs (their `tid` and `oid` are recorded per login in
+  `UserActivity`) *before* the backend deploy — an unseeded platform admin locks themselves out of every
+  GlobalAdminOnly route, including the rebind surface.
+
+# Examples
+
+A GlobalAdmin row for `admin@vendor.example` bound to tenant `1111…` with object id `aaaa…`:
+
+| Token | Result |
+| --- | --- |
+| `tid=1111… oid=aaaa… upn=admin@vendor.example` | GlobalAdmin |
+| `tid=2222… oid=aaaa… upn=admin@vendor.example` | no role — `TENANT MISMATCH` warning |
+| `tid=1111… oid=bbbb… upn=admin@vendor.example` | no role — `OBJECT-ID MISMATCH` warning |
+| `tid=1111… upn=admin@vendor.example` (no `oid`) | no role — identity incomplete |
+
+Same row, binding without an object id: the first `tid=1111…` sign-in pins its `oid` and is admitted; a
+`tid=2222…` sign-in before that is refused **and does not pin**.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Security/AdminIdentity.cs` — the identity record and its factories.
+* `src/Backend/AutopilotMonitor.Functions/Services/AdminIdentityBindingService.cs` — verdict, pin, grant-time binding, rebind; the table entity.
+* `src/Backend/AutopilotMonitor.Functions/Services/AdminIdentityResolver.cs` — sign-in-history / UPN-domain resolution at grant time (`AdminIdentityResolverTests`).
+* `src/Web/autopilot-monitor-web/app/admin/components/IdentityBindingsSection.tsx` — the per-tenant inspect/correct panel.
+* `src/Backend/AutopilotMonitor.Functions/Services/GlobalAdminService.cs`, `DelegatedAdminService.cs` — resolution order.
+* `src/Backend/AutopilotMonitor.Functions/DataAccess/TableStorage/TableAdminRepository.cs` — `TryPinIdentityObjectIdAsync` and the binding CRUD.
+* `src/Backend/AutopilotMonitor.Functions/Functions/Admin/IdentityBindingManagementFunction.cs` — the rebind surface and the shared `IdentityBindingRequest.Validate`.
+* `src/Backend/AutopilotMonitor.Functions.Tests/AdminIdentityBindingServiceTests.cs`, `AdminIdentityBindingAuthorizationTests.cs` — verdict matrix, race semantics, and the middleware-level denials for foreign-tenant and recycled-UPN tokens.
+* [Client-Certificate Tenant Binding](client-cert-tenant-binding.md) — the same "chain-valid is not tenant-bound" argument on the device side.
@@ -0,0 +1,82 @@
+---
+type: concept
+title: Attempt-Scoped App Install Durations
+description: AppInstallSummary.DurationSeconds measures the status-defining (last) install attempt via a LastAttemptStartedAt max-fold anchor — replacing the first-observation-to-last-terminal span that billed multi-pass IME processing gaps to trivial apps; time attribution counts the union of active attempt segments.
+resource: src/Backend/AutopilotMonitor.Functions/Services/EventIngestProcessor.AppInstall.cs
+tags: [backend, agent, ingest, app-installs, metrics, time-attribution, durations]
+timestamp: 2026-08-21
+---
+
+# Problem
+
+The IME processes the ESP app list in multiple passes: a device-ESP evaluation pass can
+touch an app (often ending `Skipped`) long before the real install runs in a later pass.
+`AppInstallSummary` is keyed by `{SessionId}_{AppName}` and folded from ALL of the app's
+events, so `DurationSeconds = last terminal − first observation` spanned those passes.
+Field case (session `44862cd3`, "Set TimeZone"): evaluation pass 09:16, real install
+10:22:58 → 10:23:21 — reported 4002 s for a 23-second install. Fleet averages, the
+Slowest-Apps ranking, p95s, and the version-regression radar all inherited the inflation;
+the rule engine's `app_install_duration` (already attempt-scoped) contradicted the
+dashboard for the same install.
+
+# Schema
+
+Three durable anchors on the row — each with a distinct, non-interchangeable job:
+
+| Column | Fold | Role |
+|---|---|---|
+| `StartedAt` | min (earliest wins) | First observation. Server-side window/bucket filter of every AppInstallSummaries scan and the radar's version-ordering key. Never re-anchored. |
+| `LastAttemptStartedAt` | **max** (in-batch and in `ReconcileAppInstallSummaryWithExisting`) | Anchor of `DurationSeconds`. Null = sentinel (row predates 2026-08, or no start observed) → duration falls back to the historical `StartedAt` span. Replay of an older batch can never regress it. |
+| `InstallPassCount` | additive, guarded by `LastAttemptStartedAt` monotonicity (a batch whose newest start is not newer than the stored anchor adds 0) | Explains "finished long after first seen" (web ×N chip); 2+ is normal. |
+
+`DurationSeconds = CompletedAt − LastAttemptStartedAt`, computed at the terminal event and
+re-derived in one central reconcile site covering in-order and Q4 out-of-order batches.
+A `LastAttemptStartedAt` newer than `CompletedAt` means a fresh pass is in flight — the
+completed attempt's stored duration stands (the 0 value omits the column; Merge preserves).
+`DownloadDurationSeconds` pairs the latest `app_download_started` with the NEXT
+`app_install_started` (attempt-scoped, in-batch). The full span stays derivable as
+`CompletedAt − StartedAt` — deliberately not a column.
+
+Weaker-terminal guard (both in-batch and cross-batch): `app_install_completed` with
+state `Skipped`/`Postponed` never overrides an `Installed`/`Error` terminal, nor its
+`CompletedAt`/`DurationSeconds` — mirroring the long-pinned `app_install_skipped` rule.
+
+# Consumers
+
+* **Fleet metrics / apps dashboard / PDF** (`MetricsMath`, `AppsAnalyticsHelper`): values
+  drop to attempt scale; labels say "install time (final attempt)". The 6 h
+  `MaxPlausibleInstallDurationSeconds` gate remains (an attempt longer than the agent's
+  lifetime is still unobservable).
+* **AppVersionRegressionRadar**: cutover gate in `MeasuredAppGroups` — only rows with
+  `LastAttemptStartedAt` enter the duration population, on BOTH comparison sides. A mixed
+  population would mask real regressions and falsely re-arm active episodes for up to the
+  35-day horizon. `MinMeasuredInstalls` keeps it silent until enough post-cutover rows
+  exist. Thresholds (2.0× / 300 s) were tuned on span data — re-evaluate ~4 weeks after
+  rollout.
+* **Time attribution** (`TimeAttributionCalculator.BuildBlockingAppIntervals`):
+  sequence-ordered start→terminal pairing yields one segment per pass/attempt. Per-app
+  seconds = SUM of clamped segments (failed attempts and evaluation passes count — they
+  occupied the path); occupancy merges the segments, never the per-app hulls; hull
+  endpoints remain first-start→last-terminal for display and what-if. Deliberately
+  BROADER than the metrics duration: active time across all passes vs. final attempt.
+* **Agent payloads** (`AppInstallTiming` / `ImeLogTrackerAdapter.UpdateAppTiming`): a
+  terminal→active transition re-arms BOTH endpoints, so event `durationSeconds` also
+  describes the attempt (needs the agent release carrying this change).
+* **Rule engine** `app_install_duration`: was already attempt-scoped — now consistent.
+
+# Rollout
+
+No backfill (user decision, analog to the CMTrace legacy): pre-cutover rows keep span
+values, so time-series charts step down visibly at the changeover (documented in the
+public platform changelog). Sentinel-gated columns follow the standard chain:
+`BuildAppInstallSummaryEntity` + `MapToAppInstallSummary` + `AppsDashboardProjection`
+(the only projection whose consumers read the new columns).
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/EventIngestProcessor.AppInstall.cs` — fold + weaker-terminal guard + attempt pairing
+* `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.Metrics.cs` — reconcile max-fold, pass-count guard, central duration recompute
+* `src/Backend/AutopilotMonitor.Functions/Helpers/AppVersionRegressionRadar.cs` — cutover gate
+* `src/Backend/AutopilotMonitor.Functions/Helpers/TimeAttributionCalculator.cs` — per-pass segments + occupancy
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/SignalAdapters/ImeLogTrackerAdapter.cs` — payload timing re-arm
+* Tests: `AppInstallTerminalStateAndReconcileTests`, `EventTimestampValidationTests`, `AppVersionRegressionRadarTests`, `TimeAttributionCalculatorTests`
@@ -0,0 +1,235 @@
+---
+type: Concept
+title: Client-Certificate Tenant Binding — Closing the Cross-Tenant Gap
+description: Why a chain-valid Intune MDM certificate does not prove the caller belongs to the tenant it claims, which certificate extension carries the Entra tenant id (and which two look like it but do not), and the shadow-then-enforce rollout that measures field coverage before it can lock devices out.
+resource: src/Backend/AutopilotMonitor.Functions/Security/CertTenantBinding.cs
+tags:
+  - backend
+  - security
+  - authentication
+  - certificates
+  - intune
+  - multi-tenant
+timestamp: 2026-08-24T00:00:00+02:00
+---
+
+# Problem
+
+Agent requests authenticate with mTLS. `CertificateValidator` pins the chain to the embedded
+Intune roots (`X509ChainTrustMode.CustomRootTrust`), checks the validity window and requires the
+Client-Authentication EKU. All of that together proves exactly one thing: **the certificate was
+issued by the Microsoft Intune MDM Device CA to some tenant**.
+
+Those roots are shared by every Intune tenant on the planet. Nothing in the certificate stage ties
+the caller to the tenant in the request. The tenant scoping came entirely from the downstream
+device validators — the serial number must appear in that tenant's Autopilot / imported-device /
+Cloud PC inventory. Device serial numbers are not secrets; they are printed on the chassis.
+
+So the pre-existing attack was: enroll a device in your own Intune tenant, obtain a legitimate
+device certificate, learn one serial number of the victim tenant, and submit telemetry as that
+tenant. Certificate validation passes, device validation passes.
+
+# Mechanism
+
+The Intune MDM Device CA stamps the customer's identifiers into the leaf certificate. Since the
+agent presents this certificate in the TLS handshake, its contents are proof of possession and the
+backend can compare them against the requested tenant — no Graph call, no additional consent, and
+nothing the agent has to send.
+
+## Which extension carries what
+
+Verified by decoding a real field certificate (issued 2026-05-08, `Functions.Tests/device-cert-sample.pem`):
+
+| OID | Encoding | Content |
+| --- | --- | --- |
+| `1.2.840.113556.5.14` | nested OCTET STRING (`04 10` + 16 bytes) | **Entra tenant id** — the one to compare |
+| `1.2.840.113556.5.6` | nested OCTET STRING (`04 10` + 16 bytes) | Intune **Account** id — a *different* GUID, never equal to the tenant id |
+| `1.2.840.113556.5.4` | **16 raw bytes, no wrapper** | Intune device id, identical to the certificate's Subject CN |
+
+Two traps are worth stating explicitly, because both cost real debugging time:
+
+1. `…5.6` is widely described as "the tenant id (AccountID)". It is not the Entra tenant id.
+   Comparing it against the requested tenant would reject every request in production.
+2. The encodings are not uniform. `…5.4` holds the GUID bare while the other two nest it in a
+   second OCTET STRING, so a decoder written against one shape silently fails on the other.
+   `MsDeviceCertificateOids.TryParseGuid` accepts both, and all GUIDs are Microsoft
+   little-endian (what `new Guid(byte[])` expects).
+
+A 16-byte input is inherently ambiguous — it is indistinguishable from a truncated wrapper and is
+always read as a bare GUID. That is harmless here: the value is only ever compared for equality
+against a known tenant id, never trusted as a standalone claim.
+
+## Where it is NOT
+
+`EntraDeviceCertHelper` reads tenant and device ids from the **MS-Organization-Access** certificate
+(`1.2.840.113556.1.5.284.*`). That certificate is not part of the authentication path at all — the
+agent selects the Intune MDM certificate by exact issuer match (`CN=Microsoft Intune MDM Device CA`,
+see `CertificateHelper.SelectMdmCertificate`) and the backend pins only the MDM chain. The Entra
+certificate is used purely as a local fallback for `TenantIdResolver`; it never leaves the device.
+
+Sending it in a header instead would prove nothing: only the certificate used in the TLS handshake
+demonstrates possession of a private key. A certificate copied into a custom header can be replayed
+by anyone who has seen it once.
+
+# Rollout
+
+Enforcing immediately would be reckless: any device population whose certificates predate the
+extension, or whose CA behaves differently (sovereign clouds), would be locked out at once. The
+rollout therefore has staged consequences.
+
+**Stage 1 — shadow (completed, kept as the measurement that justified stage 2).** `SecurityValidator.ObserveCertTenantBinding` evaluates the binding
+after certificate validation and logs the outcome. It returns `void`, changes no state, and swallows
+its own exceptions, so it cannot fail a request that would otherwise be accepted. The pure comparison
+lives in `CertTenantBinding.Evaluate`; the outcome codes (`Match`, `Mismatch`, `ExtensionMissing`,
+`Unparseable`, `RequestTenantNotAGuid`) are stable and queried by exact match in KQL.
+`WouldRejectUnderEnforcement` records what stage 2 *would* have done, so the telemetry can be read
+without re-deriving the rule at query time.
+
+The telemetry uses two carriers, because the numerator and the denominator have very different
+costs and answer different questions:
+
+* **Every** outcome, `Match` included, is stamped onto the request row as the `CertTenantBinding`
+  dimension — `SecurityValidator` writes it into `FunctionContext.Items`
+  (`CertTenantBinding.RequestItemKey`) and `RequestTelemetryMiddleware` copies it onto the
+  `RequestTelemetry` it already emits. That row exists per request and is unsampled, so the
+  denominator costs no additional telemetry at all.
+* Outcomes that need an enforcement decision (mismatch, missing, undecodable) are **additionally**
+  logged at Warning with the full context — thumbprint, certificate tenant, session.
+
+`Match` is deliberately not a trace line. Worker-side `LogInformation` never reaches App Insights
+(the ApplicationInsightsLoggerProvider default rule is Warning+ and host-forwarding of worker logs
+is disabled), so a `Match` trace is dead code that silently costs the denominator. The first
+deployment of this feature made exactly that mistake: it emitted zero rows across 32k requests,
+which is indistinguishable from the code never running.
+
+**Stage 2 — enforced since 2026-08-25.** `Mismatch` returns 403 and is recorded through the shared
+`LogRequestRejection` path (`stage=certtenant`) so it lands in the same KQL raster as every other
+rejection reason. The switch was made against measured data: 35,684 requests across 32 tenants,
+every one a `Match`, with the Warning channel independently verified to be carrying other traffic so
+the zero could not be a telemetry artefact.
+
+The rule lives in one place, `CertTenantBinding.Rejects`, and only `Mismatch` blocks. Everything
+else means "cannot tell" and is deliberately tolerated:
+
+* `ExtensionMissing` — the sample only covers devices active in the measurement window, so older
+  certificates or a sovereign-cloud CA could still lack the extension. Rejecting on absence would
+  lock those devices out for something they cannot control. **This is the one to tighten later**,
+  once the `ExtensionMissing` rate is provably zero across a wider window; a test pins the current
+  tolerance so removing it has to be a deliberate decision rather than a drive-by edit.
+* `Unparseable` — a decoder or encoding surprise is our problem, not the device's.
+* `RequestTenantNotAGuid` — nothing to compare against, and such a request fails the tenant lookup
+  in §0 long before reaching this point.
+
+The evaluation fails open on its own exception: this gate exists to stop a cross-tenant certificate,
+and a defect on our side is not evidence of one. The 403 body deliberately does not echo which
+tenant the certificate belongs to — that pair is in the rejection log, not in the response.
+
+Grep marker for every site involved: `CERT-TENANT-BINDING`.
+
+The bootstrap-token path (`X-Bootstrap-Token`) bypasses certificate validation by design and is
+unaffected by either stage.
+
+**Stage 3 — device binding (Global-Admin-only preview).** Tenant binding proves the certificate was
+issued to this tenant; it does not prove the certificate belongs to a device the tenant still has.
+`IntuneDeviceBindingValidator` closes that by resolving the Intune managedDevice id from the
+certificate's Subject CN against the tenant's own `deviceManagement/managedDevices` inventory
+(point-GET on `managedDevices/{id}` — no OData filter to inject into, and a 404 is unambiguous).
+
+It is modelled on `CloudPcDeviceValidator` and shares its cache/retry/transient contract, with one
+important difference in how it is wired: the lookup is fire-and-forget, like the DevPrep
+association shadow, because a cold Graph round-trip can take seconds and must never sit in the
+agent's request path. That rules out the request-row dimension stage 1 uses — the row is written
+the moment the function returns, before the detached task finishes — so the outcome is logged at
+Warning instead. Volume stays bounded because only Global Admins can see the toggle
+(`user?.isGlobalAdmin === true`, the same gate as the DevPrep preview). Widening it beyond preview
+should move to an inline call plus a request dimension.
+
+Outcomes: `Match`, `NotFound`, `NoDeviceIdInCert`, `PermissionMissing`, `Transient`. Only
+`Transient` is retried and left uncached — a missing grant or a foreign device is a state, not an
+outage.
+
+Graph cost is not a concern, and that is measured rather than assumed: the first live enrollment
+produced **136 requests and exactly one Graph call**, because the 30-minute positive cache absorbs
+the rest. For comparison, the per-request Autopilot serial validator made 25 calls in the same
+window. Lengthening the positive TTL would buy nothing and would delay noticing a device that has
+been wiped or removed; shortening the 5-minute negative TTL matters more, since that is how quickly
+a device object appearing late is picked up.
+
+What the 136 requests *did* cost was log lines saying the same thing 136 times, so the shadow log is
+gated on `IntuneDeviceBindingResult.ServedFromCache`: one line per real Graph lookup. Cached repeats
+add nothing — the reported age just counts up mechanically from the same `enrolledDateTime`.
+Outcomes that are never cached (`Transient`, `NoDeviceIdInCert`) still log every time, which is the
+right behaviour for an anomaly.
+
+The open question this preview exists to answer is a race, not an attack: a device object can in
+principle appear in Intune *after* the agent's first call, and enforcing before that is understood
+would reject legitimate enrollments. Every result therefore carries `enrolledDateTime`, and the log
+line records `enrolledAgeSeconds` — a device whose object was created seconds before the request
+looks completely different from a certificate that never belonged to the tenant. Grep marker:
+`CERT-DEVICE-BINDING-SHADOW`.
+
+Enabling it needs the optional Graph permission `DeviceManagementManagedDevices.Read.All`, granted
+per tenant with the customer script — it is not in the default-consent set:
+
+```powershell
+.\Grant-AutopilotMonitorAddOn.ps1 -ClientId "<client-id>" -Features IntuneDeviceBinding
+```
+
+`GraphFeatureCatalog` (feature `IntuneDeviceBinding`) and the script's catalog, `ValidateSet` and
+help block are pinned to each other by `GraphFeatureCatalogSyncTests`.
+
+# Examples
+
+Coverage — the question stage 2 depends on ("would enforcing lock anyone out?"):
+
+```kusto
+requests
+| where isnotempty(customDimensions.CertTenantBinding)
+| summarize Requests = sum(itemCount)
+    by Outcome = tostring(customDimensions.CertTenantBinding),
+       Tenant  = tostring(customDimensions.TenantId)
+| order by Requests desc
+```
+
+Detail on the individually actionable ones:
+
+```kusto
+traces
+| where message has "AgentCertTenantBinding"
+| extend Outcome = tostring(customDimensions.Outcome),
+         Tenant  = tostring(customDimensions.TenantId)
+| summarize count() by Outcome, Tenant
+```
+
+Anything in `Mismatch` is a cross-tenant certificate; anything in `ExtensionMissing` is a device
+that stage-2 enforcement would have to make a policy decision about. Note that the trace query
+alone can never show `Match`, so it cannot tell "everything matched" apart from "nothing ran" —
+use the request-row query for that.
+
+Stage 3, including the enrollment-race measurement:
+
+```kusto
+traces
+| where message has "AgentCertDeviceBinding"
+| extend Outcome  = tostring(customDimensions.Outcome),
+         AgeSecs  = toint(customDimensions.EnrolledAgeSeconds)
+| summarize Requests = count(),
+            MinAgeSecs = min(AgeSecs),
+            P05AgeSecs = percentile(AgeSecs, 5)
+    by Outcome
+```
+
+`NotFound` is the row that decides whether this can ever become a gate. A small `MinAgeSecs` on
+`Match` means device objects are appearing only just in time — the race is real and enforcement
+would need a grace path.
+
+# Citations
+
+* `src/Shared/AutopilotMonitor.Shared/Security/MsDeviceCertificateOids.cs` — OID catalog and the
+  shared ASN.1 GUID decoder (one implementation for agent and backend).
+* `src/Backend/AutopilotMonitor.Functions/Security/CertificateValidator.cs` — extension extraction
+  alongside chain validation, cached per thumbprint.
+* `src/Backend/AutopilotMonitor.Functions/Security/CertTenantBinding.cs` — the pure comparison.
+* `src/Backend/AutopilotMonitor.Functions/Security/SecurityValidator.cs` — shadow observation.
+* [W365 Cloud PC Device Validation](cloudpc-device-validation.md) — the other consumer of this
+  certificate's identity fields (Subject CN = Intune device id).
@@ -78,7 +78,8 @@ Durations shown for attempts are the sessions' authoritative `DurationSeconds` v
  completed journeys, first-time-right count, attempt histogram, junk-serial exclusion
  count, `JourneyVersion`. A journey buckets on the StartedAt date of its completing
  success session (the platform's StartedAt-date convention; late terminals converge via
-  the sweep). All counts are **additive**, so a window rate is the ratio of summed daily
+  the sweep, which slices the tick's shared projected window scan — see
+  `time-attribution.md`). All counts are **additive**, so a window rate is the ratio of summed daily
  rows — there is no rolling-window row (unlike the median-based time-attribution
  aggregates, which cannot merge). 180-day retention. Rows exist below the ≥20 UI gate
  on purpose (the UI needs the n for "insufficient data (n=…)").
@@ -0,0 +1,114 @@
+---
+type: Concept
+title: IME Installer Archive (version-verified, multi-host)
+description: How every fleet-observed Intune Management Extension build is archived as its MSI - the ime_agent_version sighting that queues the job, the candidate hosts, the ProductVersion check that keeps a wrong ring's build out of the version folder, the re-queue on later sightings, and the manual skill-side backfill.
+resource: src/Backend/AutopilotMonitor.Functions/Services/Ime/ImeMsiArchiver.cs
+tags:
+  - backend
+  - ime
+  - archive
+  - blob
+  - queue
+timestamp: 2026-08-29T17:30:00+02:00
+---
+
+# IME Installer Archive
+
+The platform keeps every Intune Management Extension build it has ever seen in the fleet
+as the original installer, so any IME version can be decompiled and diffed later
+(`ime-decompiles` repository, `/ime-decompile` skill) even after Microsoft's CDN has moved
+on. Two stores:
+
+| Store | Content | Written by |
+| --- | --- | --- |
+| Blob container `ime-archive` (private, kept by design, not tenant-scoped) | `{version}/IntuneWindowsAgent.msi` (write-once) + `{version}/provenance.json` (derived, overwritable) | `ImeMsiArchiver` via the `ime-msi-archive` queue; `/ime-decompile` skill as manual backfill |
+| Table `ImeVersionHistory` (partition `Global`, RowKey = version) | first/last seen, session count, `MsiArchiveStatus`, `MsiArchiveUpdatedAt`, `MsiArchiveBlobPath`, `MsiSha256`, `MsiBytes`, `MsiSourceUrl` | `RecordImeVersionAsync` (sighting), `UpdateImeVersionArchiveInfoAsync` (archive outcome / queued stamp) |
+
+# Schema
+
+## Sighting → job
+
+`EventIngestProcessor` looks at the batch's `ime_agent_version` event (`agentVersion`, plus
+the agent's CSP-registry enrichment `msiDownloadUrl` / `msiMatchedBy` when present).
+`RecordImeVersionAsync` returns an `ImeVersionSighting`:
+
+* `IsNew` — the insert succeeded: first fleet-wide sighting → ops event + enqueue.
+* otherwise the row's `MsiArchiveStatus` / `MsiArchiveUpdatedAt`, read in the same point
+  read that bumps `SessionCount` (no second table read).
+
+A known version is **re-queued** (`ImeMsiArchiver.ShouldRequeueOnSighting`) only when all
+of these hold: the event URL passes the allowlist **and** `msiMatchedBy == productVersion`
+(the CSP row's ProductVersion equals the observed version, so the URL is authoritative),
+the status is neither `Archived` nor `Failed:BadVersion`, and the last archive activity is
+older than 24 h (`RequeueBackoff`) or never happened. The ingest path then merges
+`MsiArchiveStatus = Queued` (stamping `MsiArchiveUpdatedAt`) before enqueueing, so the other
+sessions of that version see "in flight" and do not pile on. Worst case for a version no
+host serves any more: one walk over the hosts per day, not one per enrollment.
+
+## Candidate hosts and the version check
+
+Microsoft distributes IME from several versionless URLs that carry **different rollout
+rings at the same time**. Observed 2026-08-29: `imeswdb-afd-secondary` served 1.104.102.0,
+`imeswda-afd-primary` 1.105.101.0, `imeswda-afd-hotfix` 1.105.103.0. "A new version is by
+definition what the canonical URL serves right now" is therefore false, and the first
+version of the archiver filed a 1.104.102.0 package under `1.105.103.0/` (fixed by hand:
+blob overwritten, row merged).
+
+The archiver walks `BuildCandidateUrls(eventUrl)`: the allowlisted event URL first (HTTPS,
+host `*.manage.microsoft.com`, filename exactly `IntuneWindowsAgent.msi`), then
+`FallbackMsiUrls` = primary, secondary, hotfix — de-duplicated. For each candidate:
+
+1. Download with the admin size cap (Content-Length preflight + mid-stream cap) into a
+   delete-on-close temp file while SHA-256 hashing.
+2. Read the package's `ProductVersion` with `MsiProductVersionReader` — a pure managed OLE
+   compound-file reader (v3 512-byte and v4 4096-byte sectors, DIFAT/FAT/mini-FAT, MSI
+   stream-name decoding, `_StringPool`/`_StringData` incl. long strings and holes, the
+   column-major `Property` table with 2- or 3-byte string refs). It never throws; anything
+   unreadable is `null`. Needed because the Function host is Linux — no `msiexec`.
+3. `VersionsMatch(observed, productVersion)` (component-count tolerant: `1.105.103` ==
+   `1.105.103.0`). Mismatch or unreadable → log, record the attempt, next candidate.
+4. Match → write-once upload (If-None-Match:*), then `provenance.json` with
+   `productVersion`, the chosen `url`, `urlFromEvent`, hash/size and the full `candidates`
+   walk (`url`, `outcome` ∈ match / version-mismatch / too-large / download-failed /
+   timeout, `productVersion`).
+
+Outcome precedence when no candidate archived: any transient failure (download/timeout)
+→ `Failed:Download` / `Failed:Timeout`, retryable via the queue's visibility ladder (the
+down host might have had it); every candidate over the cap → `Failed:TooLarge`; otherwise
+`Failed:VersionMismatch` — **not** retryable by the queue (retrying in minutes changes
+nothing), left to the sighting re-queue above. Storage/unexpected errors stay
+`Failed:Error`, retryable. A 409 on the write-once upload means an earlier attempt
+archived the version: the provenance sidecar is healed from the archived bytes (hash,
+size, ProductVersion) if missing — this is also how a manual skill backfill turns a null
+row into `Archived` on the next authoritative sighting.
+
+## Manual path (skill)
+
+`/ime-decompile` downloads from the blob (`ime-blob.sh download`), and
+`fetch-ime-decompile.py` names the decompile folder after the **actual** FileVersion of
+the extracted binaries — so the decompile repo can never be poisoned, only the blob folder.
+When the blob's version mismatches, look for `msiDownloadUrl` in *other* sessions of the
+version (the first-seen session often lacks the enrichment) and fetch from that host.
+`ime-blob.sh upload … --overwrite` replaces a blob known to hold the wrong build; merge the
+row's `MsiSha256` / `MsiBytes` / `MsiSourceUrl` afterwards.
+
+# Examples
+
+* First sighting of 1.105.103.0 with no URL: primary → 1.105.101.0 (mismatch), secondary →
+  1.104.102.0 (mismatch), hotfix → 1.105.103.0 (match) → archived from hotfix, provenance
+  lists all three.
+* Hotfix host down during the walk, others mismatching → `Failed:Download`, queue retries.
+* Version 1.101.111.0 (predates the archiver, row status null): a session whose CSP row
+  matches by ProductVersion arrives → status `Queued`, job runs; if no host serves it any
+  more → `Failed:VersionMismatch`, next try no sooner than 24 h later.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/Ime/ImeMsiArchiver.cs`
+* `src/Backend/AutopilotMonitor.Functions/Services/Ime/MsiProductVersionReader.cs`
+* `src/Backend/AutopilotMonitor.Functions/Services/Ime/ImeMsiArchiveQueueWorker.cs`
+* `src/Backend/AutopilotMonitor.Functions/Services/EventIngestProcessor.cs` (ime_agent_version block)
+* `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.Sessions.cs` (`RecordImeVersionAsync`, `UpdateImeVersionArchiveInfoAsync`)
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/ImeMsiInstallSourceProbe.cs` (event enrichment)
+* `.claude/commands/scripts/ime-blob.sh`, `.claude/commands/scripts/fetch-ime-decompile.py`
+* Tests: `ImeMsiArchiverTests`, `MsiProductVersionReaderTests` (synthetic packages + local sweep over `ime-files/`)
@@ -0,0 +1,93 @@
+---
+type: concept
+title: Plan Downgrade Policy & the Retention Grace Period
+description: What happens when a tenant loses Pro (explicit downgrade or trial expiry) — every entitlement gates read-time and reversibly, except retention, which gets a 30-day grace before the Community cap starts hard-deleting; the anchor model, the ops events, and the deliberate non-grace of everything else.
+resource: backend
+tags: [plan, edition, downgrade, retention, grace-period, trial, entitlements]
+timestamp: 2026-08-22
+---
+
+# Schema
+
+## The downgrade model: gate, don't destroy
+
+Edition is resolved at READ time (`FeatureEntitlementCatalog.ResolveEdition`): Pro ⇔
+permanent tier `pro`/legacy `enterprise` OR an active trial. A plan mutation is a single
+field write (`PATCH config/{tenantId}/plan`, GA-only) — there is no downgrade event
+handler, no cascade. On Pro → Community every entitlement simply gates on the next read
+(≤ ~5 min config cache):
+
+* **Unrestricted Mode** — effective value flips false; the GA on-request flag and the
+  tenant toggle survive untouched (inert). Re-upgrade restores it verbatim.
+* **Delegated (MSP) admin** — scope suppressed at the home-tenant gate
+  (`DelegatedAdminService.ApplyHomeTenantGateAsync`); grant rows / tenant groups /
+  assignments are never touched. Resurrects on re-upgrade.
+* **OOBE bootstrap** — endpoints 403/404 unless the additive GA per-tenant flag
+  (`BootstrapTokenEnabled`) is set; `BootstrapSessions` rows are kept.
+* **Rate limits / MCP quota** — pure computed-at-read floors/plan names.
+
+**Retention is the one exception**: the retention sweep (12-hourly
+`SessionDeletionMaintenance` → `SessionRetentionFanoutService`) hard-deletes sessions
+older than `GetEffectiveRetentionDays` = `min(stored DataRetentionDays, edition cap)`.
+Without protection, a downgrade (or trial expiry) with stored retention 365 would start
+irreversibly cascade-deleting the 90–365-day band on the next tick.
+
+## The retention grace period (30 days)
+
+`FeatureEntitlementCatalog.RetentionDowngradeGraceDays = 30`. For 30 days after losing
+Pro, `GetEffectiveRetentionDays` keeps clamping to the **Pro** cap (365); only after the
+grace does the Community cap (90) bite. The stored `DataRetentionDays` is never rewritten.
+`days <= 0` (GA-only "infinite") short-circuits before any cap — those tenants are never
+swept, grace or not.
+
+**Anchor** — "when was Pro lost" (`TenantEntitlementService.GetRetentionGraceEndUtc`,
+returns null while effectively Pro; grace end = latest anchor + 30d):
+
+* **Explicit downgrade**: `TenantConfiguration.ProDowngradedUtc` (backend-only field, no
+  agent ConfigVersion impact), maintained exclusively by the plan endpoint's pure mutation
+  core `PlanManagementFunction.ApplyPlanChanges`. Stamped when the EFFECTIVE edition
+  (before vs. after, same `nowUtc`) transitions Pro → Community — this covers both a
+  planTier downgrade and a GA explicitly ending a trial (`trialExpiresUtc: null`, where
+  the trial timestamp disappears and could not anchor). Cleared on any transition back to
+  effectively Pro (PATCH pro, trial grant, self-service trial start), so a re-upgrade also
+  resets the grace clock.
+* **Trial expiry**: no write happens — the stored `TrialExpiresUtc` itself is the anchor
+  (read-time, like edition resolution). A planTier downgrade under a still-active trial
+  deliberately does NOT stamp: the edition is still Pro, and the later trial expiry
+  anchors the grace then.
+
+The field is on the patch-endpoint `BaseDeniedFields` and `RevertProtectedFields` lists
+(a config revert must not time-travel the anchor) and roundtrips the table-serialization
+contract (Store+Map + roundtrip tests). Legacy rows read null → no anchor → no grace,
+which is correct: no tenant had been downgraded before the feature existed.
+
+## Ops visibility (dual-registered event types)
+
+* `TenantPlanDowngraded` (Warning) — emitted by the PATCH handler on an effective
+  Pro→Community transition; carries `retentionGraceEndsUtc` + stored retention days. The
+  response body also returns `retentionGraceEndsUtc`.
+* `TenantRetentionGraceExpiring` / `TenantRetentionGraceEnded` (Warning) — emitted by the
+  daily `TrialExpirySweepFunction` (03:30 UTC) with the same stateless window mechanics as
+  the trial events (≤3-day heads-up re-fired daily; ended once via the 24h look-back), and
+  ONLY when data is actually at risk: stored `DataRetentionDays` above the Community cap
+  (0 = infinite ⇒ never). Re-upgraded tenants go silent automatically (grace resolves null).
+
+All three are registered in the web `OPS_EVENT_TYPES` catalog (OpsAlertRulesSection.tsx)
+so Telegram alert rules can route them.
+
+## Deliberate non-goals
+
+* No grace for Unrestricted/MSP/bootstrap/limits — reversible gates need none.
+* The retention WRITE cap (`TenantConfigValidation`) does not honor the grace: during the
+  grace a tenant admin cannot SET a value above the Community cap. The grace protects
+  existing data; new writes follow the new plan.
+* The feature-flags endpoint keeps publishing the plain edition cap
+  (`retentionCapDays`) — it feeds the settings input maximum, which is the write cap.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/TenantEntitlementService.cs` — grace + effective retention
+* `src/Backend/AutopilotMonitor.Functions/Functions/Config/PlanManagementFunction.cs` — `ApplyPlanChanges` anchor lifecycle
+* `src/Backend/AutopilotMonitor.Functions/Functions/Maintenance/TrialExpirySweepFunction.cs` — grace event windows
+* `src/Backend/AutopilotMonitor.Functions/Services/Deletion/SessionRetentionFanoutService.cs` — enforcement point
+* Tests: `TenantEntitlementServiceTests`, `PlanManagementTransitionTests`, `TrialExpirySweepFunctionTests`, `SessionRetentionFanoutServiceTests`, `TenantConfigTableSerializationTests`
@@ -0,0 +1,84 @@
+---
+type: concept
+title: Send-Time Frame Separation (X-Send-Time-Utc)
+description: One device-clock send timestamp per upload batch splits ReceivedAt − OccurredUtc into pure spool delay and pure device-vs-server clock offset — turning clock diagnostics from median statistics into direct per-request measurement.
+resource: src/Backend/AutopilotMonitor.Functions/Functions/Ingest/IngestTelemetryFunction.cs
+tags: [backend, agent, ingest, timestamps, clock-skew, telemetry, provenance]
+timestamp: 2026-08-21
+---
+
+# Problem
+
+Events carry two time anchors: `OccurredUtc` (device clock at emission) and `ReceivedAt`
+(server clock at ingest). Their difference conflates two physically distinct phenomena:
+
+* **Spool delay** — the event waited offline or in retry backoff before upload. Expected,
+  harmless, minutes to hours.
+* **Device-vs-server clock offset** — the actual diagnostic signal.
+
+A uniform spool backlog (events emitted close together, uploaded after an outage) is
+indistinguishable from a clock offset in that delta; a draining backlog fakes a clock jump
+ramp. Every consumer had to filter this statistically (spread caps, plateau guards,
+persistence tests) — and the first field clock-jump measurement failed exactly on this
+ambiguity.
+
+# Schema
+
+The agent stamps one header per upload attempt (`BackendTelemetryUploader`):
+
+```
+X-Send-Time-Utc: <DateTime.UtcNow, ISO-8601 round-trip>
+```
+
+Per **attempt**, not per batch content: a retry after backoff is a new send moment. The
+ingest function parses it (`ParseSendTimeHeader`: round-trip parse, UTC-normalized, values
+before year 2000 rejected as garbage — deliberately **no upper clamp**, a future-dated
+send time IS the clock-error measurement), and `StampServerFields` writes it as `SentAt`
+onto every event of the request — server-stamped, request-level, never trusted per-event
+from the wire. Stored as the nullable `SentAt` column on Events (absent for pre-header
+agents), mapped back everywhere events are read, exposed as `sentAt` in the `fields=`
+projection and verbatim on the raw endpoints.
+
+The separation is then exact:
+
+```
+SentAt − OccurredUtc   = pure spool delay            (both device frame; offset cancels)
+ReceivedAt − SentAt    = network latency + clock offset   (the only frame crossing)
+```
+
+Network latency is seconds; anything beyond is device clock error, per request, no
+statistics required.
+
+# Consumers
+
+* **`clock_skew` analyze condition** (ANALYZE-DEV-008): batches whose events carry
+  `SentAt` measure the batch offset directly as `SentAt − ReceivedAt` — spool-immune by
+  construction, so the spread cap and the IME/clamped exclusions are unnecessary there
+  (no event timestamps are read at all; IME-only sessions become measurable). Batches
+  without `SentAt` keep the legacy per-event median + spread-cap path. Downstream logic
+  (stability check, plateau step detection, end-state persistence) is shared; evidence
+  carries `sentAtBatchCount`.
+* **`CmTraceSkewTripwire` deliberately unchanged**: `median(Δ_IME) − median(Δ_other)`
+  cancels the device clock offset as common mode — send time adds nothing to that
+  differential measurement.
+
+# Constraints
+
+* `SentAt` comes from the same device wall clock as the event timestamps — a clock jump
+  between emission and send lands in the spool-delay term. That is the intended place for
+  it to become visible, not a defect.
+* Signals and DecisionTransitions do not carry `SentAt` (no consumer); the header is
+  request-level, so extending them later is a storage-only change.
+* Fleet coverage grows with agent rollout; all analyses must treat `SentAt == null`
+  (legacy rows, old agents) as "legacy path", never as zero.
+
+# Citations
+
+* `BackendTelemetryUploader.UploadBatchAsync` — header stamping per attempt.
+* `IngestTelemetryFunction.ParseSendTimeHeader` + `IngestTelemetryFunctionTests` — parse
+  contract incl. the no-upper-clamp decision.
+* `EventIngestProcessor.StampServerFields` + `IngestCriticalPathTests` — server-side
+  stamping, forged per-event values overridden.
+* `RuleEngine.ConditionEvaluators.EvaluateClockSkewCondition` + `RuleEngineClockSkewTests`
+  — the two measurement paths (the backlog-alias test pair pins why SentAt exists).
+* `tasks/todo.md` P14 (2026-08-21) — decision trail incl. why the tripwire stays as is.
@@ -0,0 +1,140 @@
+---
+type: Concept
+title: Silent-Session Classification (Sweep, Max-Lifetime, Retro-Reconcile)
+description: How a session whose agent went silent gets its honest status — the two-stage maintenance sweep (2h Stalled marker, 5h timeout classification), the EnrollmentTimeoutClassifier rule order incl. the WhiteGlove Part-2 and self-deploying gates, which ingest paths share the classifier, and the admin retro-reconcile modes.
+resource: src/Backend/AutopilotMonitor.Functions/Services/EnrollmentTimeoutClassifier.cs
+tags:
+  - backend
+  - maintenance
+  - session-status
+  - classification
+  - whiteglove
+  - self-deploying
+timestamp: 2026-08-27T20:00:00+02:00
+---
+
+# Silent-Session Classification
+
+A session only ever becomes terminal through evidence. When the agent stops reporting
+(power-off, reboot without relaunch, Wi-Fi never re-associating, max-lifetime watchdog),
+the backend must decide the status from what it last saw — it never hard-fails a session
+for being silent. One pure function holds that decision,
+`EnrollmentTimeoutClassifier.ClassifyTimedOutSession`, and every silent-session path calls it
+so a session gets the same verdict regardless of which path noticed the silence first.
+
+# Schema
+
+## Inputs (`EspProvisioningRollup` + session flags)
+
+`ExtractRollup(events)` distills the event stream into facts: Device/Account Setup
+subcategory counts (incl. the 30s fallback-confirmed messages), `HasExplicitFailure`,
+`HasEnrollmentComplete` vs. `HasTerminalComplete` (the Part-1 `whiteglove_complete`),
+`HasAgentEmergencyBreak`, `DesktopArrived`, `HelloResolved`, `HelloPolicyDisabled`,
+`SkipUserEsp`, RealmJoin detection/resolution, `HasAppInstallFailure` (any
+`app_install_failed`), and `HasAgentMaxLifetimeTimeout` (either max-lifetime shape:
+`enrollment_failed`/`agent_timeout` or `agent_shutting_down`/`max_lifetime` — the agent is
+provably gone). Session-row flags are passed alongside:
+`IsPreProvisioned` + `ResumedAt` (WhiteGlove Part 2) and `IsSelfDeployingProfile`
+(registry-confirmed `CloudAssignedOobeConfig 0x20|0x40`, set at registration).
+
+## Rule order (first match wins)
+
+| # | Condition | Verdict |
+| --- | --- | --- |
+| 1 | `HasExplicitFailure` | Failed |
+| 1b | `IsWhiteGloveAwaitingUser`: pre-provisioned + resumed + Device Setup done + **no** user evidence since resume + no explicit failure/enrollment_complete | AwaitingUser within grace; Succeeded (honest WG reason) past grace |
+| 1c | `IsSelfDeployingProvisioned`: self-deploying profile + Device Setup done + no explicit failure | **Succeeded** (reconcile) — no grace, no AwaitingUser: the profile has no user phase |
+| 2 | Account Setup all-succeeded, or `enrollment_complete`, or `whiteglove_complete` on a **non-resumed** session | Succeeded |
+| 3 | `HasAgentEmergencyBreak` | Incomplete immediately (agent self-destructed, nothing can arrive) |
+| 4 | `DesktopArrived` + (Hello terminal, or Hello disabled + SkipUserEsp) | Succeeded (user provably finished) |
+| 5 | Device Setup done + within grace + **no** max-lifetime watchdog observed | AwaitingUser |
+| 5a | Device Setup done + past grace (or watchdog observed) + `DesktopArrived` + no `app_install_failed` | **Succeeded** — completed (assumed), `r5_assumed` |
+| 5b | Device Setup done, otherwise past grace (or watchdog observed) | Incomplete |
+| 6 | otherwise | Incomplete |
+
+Grace = `ResolveGraceHours(SessionGraceHours, AbsoluteMaxSessionHours)` (~51h default),
+measured from `ResumedAt ?? StartedAt`. Every Succeeded-reconcile reason carries the
+silence-transparency clause (`AppendReconcileTiming`: last agent contact, silence, verdict time).
+
+## Why rule 1c exists (kiosk tenant audit 2026-08-23)
+
+On a self-deploying profile Device ESP all-succeeded IS the enrollment's end; the agent's
+own SelfDeploying terminal only adds a 5-min confirmation window
+(`DecisionEngine.SelfDeploying.s_deviceOnlyEspDetectionWindow`). Tenant `aebdce78` (school,
+Wi-Fi ThinkBooks, a language-change app forcing a reboot right after Device ESP) lost that
+window on 836 of ~970 sessions in one week: the agent died 0–4 min after
+`DeviceSetup fallback_confirmed`, the reboot relaunch never registered (30s registration
+budget on a Wi-Fi link still associating), and rule 5 labeled finished kiosks
+"awaiting user / Account Setup 0/5" → Incomplete 51h later. Nobody signs in on these devices
+(prepared during the holidays, boxed, in service) — AwaitingUser was factually wrong and
+Incomplete turned a working rollout into a red wall. Other self-deploying tenants completed
+normally in the same window, so this is a classification gap, not a profile-wide agent bug.
+Agent-side companion fix: `SessionRegistrationHelper` now waits up to 15s for a network link
+and retries 6× (~62s backoff) instead of 5× (~30s). Measured 2026-08-27 (builds
+2.0.1428/1429, both carrying the fix): the reconcile share did not move, and the backend saw
+no registration attempt from any relaunch — no success, no 4xx, zero `register:superseded`
+in the tenant — so the relaunch never reaches the network at all (device powered off after
+ESP, or the relaunch never runs). The sweep reconcile is the permanent completion path for
+this profile, not a stopgap.
+
+## Callers (all pass both gate inputs)
+
+| Path | File | Notes |
+| --- | --- | --- |
+| Sweep stage 1 (2h agent-silent marker) | `MaintenanceService.MarkStalledSessionsAsTimedOutAsync` | Default: InProgress → Stalled. Gates run BEFORE the Stalled write: `TryMarkWhiteGloveAwaitingUserAsync` (AwaitingUser) and `TryReconcileSelfDeployingAsync` (Succeeded). Only flagged sessions pay the event read. |
+| Sweep stage 2 (SessionTimeoutHours, 5h default) | same | InProgress/Stalled/AwaitingUser past the window and past the 2h silence cutoff → full classification; AwaitingUser within grace is skipped without an event read. |
+| Agent max-lifetime (`enrollment_failed`/max_lifetime, `agent_shutting_down`/max_lifetime) | `EventIngestProcessor.ApplyMaxLifetimeVerdictAsync` | Watchdog = "agent stopped waiting", not a verdict; classified from evidence. Pending sessions exempt. |
+| Late-telemetry reconcile | `EventIngestProcessor.TryLateTelemetryReconcileAsync` | Heal-only: applies a Succeeded verdict to Incomplete/AwaitingUser rows when straggler events arrive. |
+| Agent stall probe (`session_stalled`) | `EventIngestProcessor.TryMapStallToWhiteGloveAwaitingUserAsync` | Only the WG gate (1b); a stall probe on a self-deploying device with Device Setup done means the agent is alive and something else blocks — stays Stalled. |
+| Admin retro-reconcile | `LegacyReclassificationService` | Modes `legacy_timeouts`, `pending_orphans`, `self_deploying_silent` (Incomplete/AwaitingUser/Stalled rows with the profile flag, heal-only to Succeeded, admin-marked rows skipped). `POST /api/maintenance/reclassify-legacy?mode=…&dryRun=false&tenantId=…&maxSessions=…`, dry-run by default. |
+
+## Why rule 5a exists (calibration read 2026-08-27)
+
+The verdict-calibration matrix showed r5-Incomplete devices re-enrolling at 2.6 % within
+7 days — the succeeded background (`agent:complete_soft` sits at 2.8 %), not the ~29 %
+failure level — consistently across tenants, and half the sampled sessions were healthy
+desktops with a clean app record whose agent died before the Hello terminal (some with the
+agent's own "AccountSetup treated as complete" synthesis as the literally last event). Past
+the full grace, "the user phase is still running" is no longer a possible explanation, so
+desktop + zero `app_install_failed` + no explicit failure now reconciles to Succeeded
+("completed (assumed)") instead of a red Incomplete. Sessions without a desktop (user never
+began sign-in: battery-drained, powered off, max-lifetime) and sessions with any failed app
+stay Incomplete — "completed" must not overclaim. Rule 4 remains the IMMEDIATE reconcile
+(desktop + Hello proof); 5a only fires where waiting is over. Desktop arrival alone is still
+rejected as a live completion signal.
+
+## Closed gap: max-lifetime AwaitingUser (2026-08-27)
+
+After max-lifetime the agent writes `enrollment-complete.marker` and self-destructs, so an
+AwaitingUser verdict from that path could never heal — the calibration correction stream
+confirmed it: all five observed `maxlife:r5_awaiting` episodes expired to Incomplete
+unhealed, while live-agent `sweep:r5_awaiting` parks upgraded 7 of 26 to Succeeded. Rule 5
+therefore skips the grace once `HasAgentMaxLifetimeTimeout` is in the stream and decides the
+terminal fork (5a/5b) immediately; the max-lifetime ingest appends its trigger event to the
+read stream so the fact is never missed, and late straggler telemetry still heals a terminal
+verdict via `TryLateTelemetryReconcileAsync`. WhiteGlove rule 1b deliberately keeps its
+park — sealed/boxed devices do heal (the observed `maxlife:r1b_awaiting` episode resolved to
+Succeeded).
+
+# Examples
+
+* Session `195593e2` (tenant aebdce78): `DeviceSetup 4/4` + `fallback_confirmed`, `AccountSetup 0/5`
+  (IME false positive), Hello disabled, SkipUser=True, silent after 13:01 → rule 1c →
+  Succeeded "self-deploying profile — Device Setup fully provisioned … agent went silent
+  before confirming completion. Agent last reported 2026-08-21 13:01 UTC …".
+* Same event shape on a user-driven profile → rule 5 → AwaitingUser (within grace) /
+  Incomplete (past grace). Guarded by
+  `Classify_same_stream_without_self_deploying_flag_keeps_user_phase_verdicts`.
+* fairstone WG Part 2 reseal-reboot, technician powers off at logon screen → rule 1b →
+  AwaitingUser; user unboxes days later → ingest completion heals to Succeeded.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/EnrollmentTimeoutClassifier.cs` — rollup + rule order, `IsWhiteGloveAwaitingUser`, `IsSelfDeployingProvisioned`, reason helpers.
+* `src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.cs` — `MarkStalledSessionsAsTimedOutAsync`, `TryMarkWhiteGloveAwaitingUserAsync`, `TryReconcileSelfDeployingAsync`.
+* `src/Backend/AutopilotMonitor.Functions/Services/EventIngestProcessor.Classification.cs` — max-lifetime verdict, late-telemetry reconcile, stall mapping.
+* `src/Backend/AutopilotMonitor.Functions/Services/LegacyReclassificationService.cs`, `Functions/Admin/ReclassifyLegacySessionsFunction.cs` — retro modes.
+* `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.Maintenance.cs` — `GetAgentSilentSessionsAsync`, `GetStalledSessionsAsync`, `GetSelfDeployingSilentSessionsAsync`.
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Security/SessionRegistrationHelper.cs` — link wait + 6-attempt registration budget.
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.SelfDeploying.cs` — the agent-side 5-min SelfDeploying terminal window.
+* `src/Backend/AutopilotMonitor.Functions.Tests/EnrollmentTimeoutClassifierTests.cs` — rule coverage incl. the 2026-08-23 self-deploying block.
@@ -0,0 +1,67 @@
+---
+type: Concept
+title: Table Schema Sentinel (startup table initialization)
+description: Why a cold start no longer issues one CreateTableIfNotExists per registered table - a hash over TableNames.All stored in AdminConfiguration gates the full pass, the SessionsIndex backfill only runs after a full pass and behind a conditional-insert claim, and daily maintenance repairs out-of-band deletions.
+resource: /src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.cs
+tags:
+  - backend
+  - table-storage
+  - startup
+  - maintenance
+timestamp: 2026-08-23
+---
+
+# Schema
+
+## Problem
+
+`TableInitializerService` (hosted service) called `InitializeTablesAsync` on every process start, which issued `CreateTableIfNotExistsAsync` for every entry of `Constants.TableNames.All` (66 at the time of writing, DoP 8). Each call is a Create POST whose 409 is swallowed - on Flex Consumption with frequent cold starts that was ~9 serial round-trip waves before the first request. It was followed by a SessionsIndex emptiness query whose *error* path returned "empty", so a transient storage error triggered a full Sessions scan with serial upserts - on every scaled-out instance at once.
+
+## Sentinel
+
+* Row `AdminConfiguration` / PK `SchemaSentinel` / RK `tables`, property `TableSchemaHash` (+ `TableCount`, `UpdatedUtc`).
+* Value = `ComputeTableSchemaHash(TableNames.All)`: SHA-256 over the ordinal-sorted, newline-joined table names. Derived, never hand-maintained: adding a table to `TableNames.All` changes the hash by construction (`TableLifecycleBucketTests` already forces every constant into `All`).
+* `InitializeTablesAsync` (returns `bool fullPassRan`):
+  1. Point-read the sentinel. Match -> mark initialized, **zero** table calls, return `false`.
+  2. Missing / stale / unreadable (fresh storage has no AdminConfiguration table yet) -> `EnsureAllTablesAsync` (the old full pass), then upsert the sentinel **only if no table failed**, return `true`. A failed pass leaves `_tablesInitialized = false`, so the next call retries.
+* Scale-out: two instances that both see a stale sentinel both run the idempotent pass - harmless.
+
+## SessionsIndex backfill
+
+* Only evaluated when the full pass ran (`fullPassRan == true`): an empty index can only exist on fresh storage, which is exactly the case without a sentinel.
+* `IsSessionIndexEmptyAsync` now returns `false` on error (skip), not `true`.
+* `TryClaimSessionIndexBackfillAsync`: conditional `AddEntityAsync` on `SchemaSentinel` / `sessionIndexBackfill` - only the winner scans; 409 or any error -> skip. The manual maintenance backfill (`RunManualAsync`) remains the safety net.
+
+## Known gap and repair
+
+A table deleted out-of-band (cleanup skill, portal, tests) is not noticed at startup anymore. `IStorageInitializer.EnsureAllAsync` runs as the first step of the daily timer maintenance (`MaintenanceService.RunAllAsync`), recreating it within 24h. Storage helpers are fail-soft in the meantime.
+
+## Measuring it
+
+`StartupTelemetryService` (hosted service) emits two App Insights metrics on `IHostApplicationLifetime.ApplicationStarted` - i.e. after every hosted service finished `StartAsync`:
+
+* `BackendStartupMs` - process start (`Process.StartTime`) to host ready; includes runtime, DI and all hosted services.
+* `BackendTableInitMs` - the `InitializeTablesAsync` slice alone (`TableStorageService.LastInitialization`).
+
+Dimensions: `version`, `commit`, `tableInitFullPass`, `instance`. Metrics bypass adaptive sampling and the worker log level, so they arrive even though Information traces do not. The MCP server logs the same idea as one `{"type":"boot","readyMs":…}` stderr line per start (ContainerAppConsoleLogs_CL, see `.claude/commands/mcp-telemetry.md`).
+
+```kusto
+customMetrics
+| where name in ("BackendStartupMs", "BackendTableInitMs")
+| summarize p50 = percentile(value, 50), p95 = percentile(value, 95), n = count()
+  by name, version = tostring(customDimensions.version), fullPass = tostring(customDimensions.tableInitFullPass)
+```
+
+# Examples
+
+* Deploy that adds a table: first cold start after the deploy runs the full pass once (log: "Table schema sentinel missing or stale"), every later start logs "Table schema sentinel matches (...)".
+* Fresh storage account: sentinel read throws TableNotFound -> full pass -> index empty -> one instance claims and backfills.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.cs` - sentinel, `InitializeTablesAsync`, `EnsureAllTablesAsync`, `TryClaimSessionIndexBackfillAsync`
+* `src/Backend/AutopilotMonitor.Functions/Services/TableInitializerService.cs` - startup gating
+* `src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.cs` - daily `EnsureAllTablesAsync`
+* `src/Backend/AutopilotMonitor.Functions/Services/StartupTelemetryService.cs` - `BackendStartupMs` / `BackendTableInitMs`
+* `src/McpServer/autopilot-monitor-mcp/src/index.ts` - `{"type":"boot"}` line
+* `src/Backend/AutopilotMonitor.Functions.Tests/TableSchemaSentinelTests.cs`, `StartupTelemetryServiceTests.cs`
@@ -0,0 +1,89 @@
+---
+type: Concept
+title: Telemetry Ingest Shaping (App Insights / Log Analytics)
+description: What the backend deliberately keeps out of Application Insights and why - one canonical request record (worker copy, per-item sampling bypass; host HTTP duplicate dropped by a workspace transformation), expected storage outcomes (404/412/409) and successful SignalR REST calls filtered in the worker, and the query rules that follow.
+resource: /src/Backend/AutopilotMonitor.Functions/Telemetry/StorageDependencyFilterProcessor.cs
+tags:
+  - backend
+  - telemetry
+  - application-insights
+  - cost
+timestamp: 2026-08-23
+---
+
+# Telemetry Ingest Shaping
+
+The backend is storage-I/O heavy and runs on the Functions isolated worker, which emits telemetry from TWO processes (host and worker). Left alone, Log Analytics ingestion is dominated by rows nobody reads. This document records what is removed, where, and what that means for queries.
+
+# Schema
+
+## Request telemetry — one canonical record
+
+| Source | Emitted by | Content | Fate |
+|---|---|---|---|
+| Host HTTP request (`Properties.Source` empty, `Url` set) | Functions host process | Name, duration, status — no tenant/user/correlation | **Dropped at ingestion** by the workspace transformation on `AppRequests` (`infra/appinsights-workspace-transforms.bicep`) |
+| Host non-HTTP invocation (`Url` empty) | Functions host process | Timer / queue executions | Kept (the worker middleware never sees them) |
+| Worker request (`Properties.Source == 'WorkerMiddleware'`) | `RequestTelemetryMiddleware` | TenantId, UserId, UserRole, CorrelationId, ClientSource, McpToolName, HttpPath | **Kept, unsampled** — the canonical record |
+
+Why two mechanisms:
+
+* The host request item cannot be suppressed from worker code or from `host.json` (`Host.Results` controls log traces, not the request item; verified 2026-06-09). The only lever is a Log Analytics workspace transformation: `source | where tostring(Properties.Source) == 'WorkerMiddleware' or isempty(Url)`.
+* `host.json` `samplingSettings.excludedTypes: "Request;Event"` only applies to the host process. The worker's `AddApplicationInsightsTelemetryWorkerService` runs its own adaptive sampling; before 2026-08-23 worker request rows carried `ItemCount` 2–5 on weekdays (≈30 % of individual requests missing, `count()` undercounting by the same share — `sum(ItemCount)` matched the host copy to 1.00 per day). Re-configuring the worker sampling chain did not take effect in the isolated worker (see the L4 note in `Program.cs`). The per-item opt-out does: the middleware sets `SamplingPercentage = 100` on its own `RequestTelemetry`, and the SDK sampling processor passes through every item whose sampling percentage is already set.
+
+## Dependency telemetry — keep only signal
+
+`StorageDependencyFilterProcessor` (worker pipeline) drops:
+
+* successful Azure Storage calls (Table/Queue/Blob) in both shapes — the HTTP shape (`Azure table`, target `*.table.core.windows.net`) and the Azure SDK ActivitySource shape (`InProc | Microsoft.Tables`, `InProc | Microsoft.Storage`);
+* storage calls with an **expected outcome**: `404` (point-read miss — EventTypeIndex, BlockedDevices lookups), `412` (ETag precondition), `409` (idempotent insert conflict). HTTP-shape rows carry the code in `ResultCode`; InProc rows only in `Properties["Error"]` (`Status: 404 (`). Before this filter these were 100 % of the remaining "failed" storage rows (~540 MB/week, two rows per call);
+* successful Azure SignalR Service REST calls the worker makes itself (`*.service.signalr.net`).
+
+The bulk of SignalR REST traffic (group add/remove per connection, ~470 MB/week) is emitted by the **host** process for the SignalR output binding (`SDKVersion rdddsc:*`) and never passes the worker pipeline — live-verified after the 2026-08-23 deploy (worker rows: 0, host rows: ~560/h). Those are removed by the second data flow of the same workspace transformation: `AppDependencies | where not(Success == true and Target endswith '.service.signalr.net')`.
+
+Everything else passes: storage 429/5xx/auth/timeouts, failed SignalR calls, all HTTP/Graph/NVD/MSRC dependencies, the worker's own `InProc Invoke` span, and every non-dependency item.
+
+## Measured baseline (7 days before the change, `_BilledSize`, `autopilotmonitor-api-eu`)
+
+| Table | Rows | MB | After |
+|---|---|---|---|
+| AppDependencies | 976k | 1248 | ≈ 240 (SignalR + expected-outcome rows gone) |
+| AppRequests host copy | 274k | 323 | ≈ 0 (only timer/queue rows) |
+| AppRequests worker copy | 189k | 208 | ≈ 300 (now 100 % of requests) |
+| AppTraces | 142k | 137 | unchanged |
+| AppEvents | 6k | 4 | unchanged — not worth touching |
+
+Net ≈ −1.3 GB/week with MORE usable data (every request now has tenant context).
+
+# Examples
+
+Counting requests (exact since 2026-08-23; for older data replace `count()` with `sum(itemCount)`):
+
+```kql
+requests
+| where customDimensions.Source == 'WorkerMiddleware'
+| summarize total=count(), failed=countif(success == false) by name
+```
+
+Real storage trouble only:
+
+```kql
+dependencies
+| where type startswith 'InProc | Microsoft.Tables' or target endswith '.table.core.windows.net'
+| summarize count() by resultCode, tostring(customDimensions.Error)
+```
+
+Post-deploy verification of the per-item sampling bypass (must be `ItemCount == 1` only):
+
+```kql
+AppRequests
+| where TimeGenerated > ago(1h) and tostring(Properties.Source) == 'WorkerMiddleware'
+| summarize rows=count() by ItemCount
+```
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Middleware/RequestTelemetryMiddleware.cs` — `SamplingPercentage = 100` before `TrackRequest`.
+* `src/Backend/AutopilotMonitor.Functions/Telemetry/StorageDependencyFilterProcessor.cs` + `StorageDependencyFilterProcessorTests.cs` — the filter contract.
+* `src/Backend/AutopilotMonitor.Functions/Program.cs` — the failed L4 worker-sampling attempt and why it must not be retried.
+* `infra/appinsights-workspace-transforms.bicep` — the AppRequests transformation DCR, apply/verify/rollback commands.
+* `.claude/commands/backend-logs.md`, `session-debug.md` — query conventions.
@@ -4,7 +4,7 @@ title: Tenant Activation & the Once-Only Welcome Mail
 description: How a signup becomes an activated tenant (manual approve or auto-approve queue), and how the welcome mail is sent exactly once even though activation and the user-provided address race each other.
 resource: backend
 tags: [activation, auto-approve, welcome-email, preview-whitelist, race]
-timestamp: 2026-08-02
+timestamp: 2026-08-23
 ---

 # Schema
@@ -58,6 +58,64 @@ The Global-Admin resend endpoint (`POST /api/preview/send-welcome-email/{tenantI
 always sends (explicit intent) and consumes the marker best-effort so the automatic
 paths never duplicate afterwards.

+## Finding the tenant behind an address
+
+The provider's delivery log names only the recipient — never the tenant it belonged to. The
+reverse lookup is therefore part of the tenant console: its search matches `tenantId`,
+`domainName`, `ContactEmail` **and** the notification address. No other address is searchable
+(an admin UPN never receives platform mail and would only widen the PII surface of the list).
+
+The addresses live in a different table than the tenant configs the list is built from, so the
+console loads them as a map from `GET /api/preview/notification-emails` (GA + read-only Global
+Reader, `excludeDelegated`) — one cross-partition scan of `RowKey eq 'notification-email'`
+instead of a point read per tenant. Keys are lowercased on both sides of the join: the address
+rows are written from the JWT `tid` (lowercase) while a config PartitionKey's casing is not
+guaranteed. Stored addresses keep the casing the user typed, so matching is case-insensitive.
+
+The map is **best-effort** in the portal: it powers only the search-by-address, so a failed read
+degrades that one capability instead of taking the tenant list down. The addresses are not
+rendered in the list — they are a search key, and stay visible in the tenant editor.
+
+## Mail transport
+
+Both transactional mails (welcome, post-offboarding farewell) go through the
+provider-neutral `EmailService` (`IEmailService` for the welcome path,
+`IOffboardFarewellEmailSender` for the farewell path). The provider is an implementation
+detail confined to one private transport method plus the `Email:*` configuration
+section — a provider swap must not rename classes, DI registrations or callers.
+
+* Current provider: **Mailchimp Transactional (Mandrill)**, `POST {Email:Endpoint}`
+  (`messages/send`), API key in the JSON body, typed `HttpClient` with the shared
+  `ResiliencePolicies.Notification` retry policy (15 s timeout).
+* Settings (App Settings use `Email__Key`): `Email:ApiKey` (required — empty means every
+  send is a logged no-op, never an error), `Email:Endpoint`, `Email:FromAddress`
+  (default `noreply@autopilotmonitor.com`), `Email:FromName` (default `Autopilot Monitor`).
+* Result handling: per-recipient status `sent`/`queued`/`scheduled` = success;
+  `rejected`/`invalid` (with `reject_reason`), non-2xx or malformed bodies = warning.
+  Never throws — both callers rely on that fail-soft contract.
+* `track_opens`/`track_clicks` are explicitly `false` and `auto_text` is `true`: the provider
+  receives only the recipient address and the tenant domain, which is exactly the claim on
+  the privacy page and the trust data-flows page. Changing tracking = changing those pages.
+
+## Template overrides (operator-editable)
+
+Global Admins can replace either HTML body without a deployment (portal: Settings →
+Email Templates). `EmailTemplateService` resolves the body for every send: the stored
+override wins, otherwise the built-in `EmailTemplates.*`. Overrides live in the
+`PreviewConfig` table (partition `EmailTemplates`, row key `welcome` | `farewell`,
+properties `Html`, `UpdatedBy`, `UpdatedUtc`), cached 5 minutes, invalidated on save/reset.
+
+* The only placeholder is `{{domainName}}`; an empty domain renders as "your organization",
+  matching the built-ins. Subjects are not editable (pinned constants).
+* Limit 30 000 characters (Table string property cap is 32K UTF-16 chars).
+* The send path is fail-soft: a storage error falls back to the built-in body. The admin
+  read path is not — a broken store surfaces as an error instead of silently showing the
+  built-in.
+* Endpoints (all GlobalAdminOnly): `GET|PUT|DELETE /api/global/email-templates/{kind}` and
+  `POST /api/global/email-templates/{kind}/test`. The test send goes to the caller's tenant
+  contact address (activation notification email → `ContactEmail` → caller UPN) with the
+  caller's tenant domain, optionally with an unsaved draft body; provider tag `test`.
+
 # Examples

 * Auto-approve wins the race: approve at T+64 s finds no address → logs "deferred to the
@@ -73,3 +131,9 @@ paths never duplicate afterwards.
 * `src/Backend/AutopilotMonitor.Functions/Functions/Rules/PreviewWhitelistFunction.cs` — save-path trigger, GA resend
 * `src/Backend/AutopilotMonitor.Functions/DataAccess/TableStorage/TableConfigRepository.cs` — conditional inserts (approved / welcome-email-sent)
 * `src/Backend/AutopilotMonitor.Functions.Tests/TenantApprovalServiceTests.cs` — ordering + dedup pins
+* `src/Backend/AutopilotMonitor.Functions/Services/EmailService.cs` — provider-neutral transport (Mandrill wire format, result handling, tracking off)
+* `src/Backend/AutopilotMonitor.Functions.Tests/EmailServiceTests.cs` — wire-format, fail-soft and gate-ordering pins
+* `src/Backend/AutopilotMonitor.Functions/Services/EmailTemplateService.cs` — override resolution, placeholder rendering, cache
+* `src/Backend/AutopilotMonitor.Functions/Functions/Admin/EmailTemplatesFunction.cs` — GA endpoints (read / override / reset / test send)
+* `src/Web/autopilot-monitor-web/app/admin/settings/sections/SectionEmailTemplates.tsx` — portal editor, preview frame, test send
+* `src/Web/autopilot-monitor-web/app/admin/components/tenantSearch.ts` — the console's match rules (searchable fields, quoted exact mode, lowercased join)
@@ -58,6 +58,21 @@ timestamp runs backward are dropped (`ClockSkewDropped`).
 | Complete, `desktop_arrived` event | `desktop_handoff` |
 | Failed | attribution ends — tail stays unattributed |

+## Quality flags (AttributionVersion 2)
+
+Duration-critical flags (`ClockSkewDropped`, `PartialObservation`,
+`WhiteGloveAnchorsIncomplete`, `PriorEnrollmentResidue`) exclude a breakdown from fleet
+segment statistics with a disclosed count; the blocking-set flags (`BlockingSetUnknown`,
+`BlockingSetTruncated`) only limit per-app evidence and never gate fleet stats.
+
+`PriorEnrollmentResidue` (v2) fires on `historic_ime_replay_detected`: the IME log on disk
+predates the enrollment, so the device was re-enrolled without a wipe — pre-installed apps
+complete as instant detections and pull the phase anchors ahead of the real ESP page
+(session f475e697: AccountSetup anchor 6.5 min early, 457 s misattributed to
+`identity_hello`). `registry_app_baseline` successes are deliberately NOT a trigger — they
+are by-design normal for Windows Device Preparation (DPP Batch-1 apps install before the
+agent exists) and would starve that class's aggregates.
+
 ## ESP-blocking apps (positive evidence only)

 Per-app intervals use EVENT timestamps (first started/download event → LAST terminal
@@ -90,6 +105,11 @@ the partition).
 * Self-healing 30-day maintenance sweep (2h tick): backfills missing breakdowns, folds
  late-terminating sessions into their StartedAt-date aggregates, and enforces version
  purity — a stale-version row whose events aged out counts as missing, never mixed.
+  Reads the tick's **shared window scan** (`MaintenanceService.LoadSweepWindowSessionsAsync`,
+  one projected 35-day cross-tenant drain via `MaintenanceSweepSessionProjection` that
+  also feeds the device-journey and verdict-calibration sweeps) — the StartedAt-only
+  filter is a full-table read in Table Storage, so it is done once per tick, not once per
+  sweep; `MaintenanceSweepProjectionEquivalenceTests` pins the column set.
 * `TimeAttributionAggregates` (PK = TenantId or `global`, RK = `{yyyy-MM-dd}|{class}` and
  `rolling30|{class}`): per enrollment class (`user_driven`, `whiteglove`, `self_deploying`,
  `device_preparation` — never mixed) median/p75/p90 per segment over the fixed six-segment
@@ -117,7 +137,7 @@ gap before the first part-2 phase declaration is unattributed, not guessed.

 # Citations

-* `src/Backend/AutopilotMonitor.Functions/Helpers/TimeAttributionCalculator.cs` — calculator + semantics (AttributionVersion 1).
+* `src/Backend/AutopilotMonitor.Functions/Helpers/TimeAttributionCalculator.cs` — calculator + semantics (AttributionVersion 2).
 * `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.TimeAttribution.cs` — persistence.
 * `src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.Aggregation.cs` — sweep + aggregation.
 * `src/Backend/AutopilotMonitor.Functions.Tests/TimeAttributionCalculatorTests.cs` — golden fixtures pinning the invariant.
@@ -0,0 +1,176 @@
+---
+type: Concept
+title: Verdict Calibration (classifier thermometer)
+description: How every session status write declares its VerdictPath, how overriding a verdict preserves it as PriorStatus/PriorVerdictPath, how the daily calibration aggregate counts paths with the re-enrollment proxy and the correction stream, and how the drift radar (share / silence / evidence-gap) turns that into operator-only ops events.
+resource: src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.VerdictCalibration.cs
+tags:
+  - backend
+  - sessions
+  - classifier
+  - calibration
+  - regression-radar
+timestamp: 2026-08-27T20:00:00+02:00
+---
+
+# Verdict Calibration (classifier thermometer)
+
+A session's terminal status is written by ~20 code paths: the agent's own terminal events,
+the silence classifier (`EnrollmentTimeoutClassifier`, rules 1–6) reached via the
+maintenance sweep / the agent's max-lifetime shutdown / late-telemetry heal / retro
+reclassification, the analyze-rule engine, admin marks and session superseding. Verdict
+calibration makes every one of those paths **countable**, tracks how often a path's verdict
+was later **overridden**, attaches the delayed **re-enrollment proxy**, and raises an
+operator-only alarm when a path's share **drifts**. It is deterministic, fact-based tuning
+input for the rules — explicitly not a learned model, and never a customer-facing feature.
+
+# Schema
+
+## VerdictPath on the session row
+
+`SessionSummary.VerdictPath` (`VerdictPaths` vocabulary, `origin:detail`, append-only) is
+stamped by **every** status write — `UpdateSessionStatusAsync` takes it as a required
+parameter, `StoreSessionAsync` stamps `register:new` / `register:whiteglove_resume` and
+preserves an existing path through the re-registration Replace, `SetSessionPreProvisionedAsync`
+requires it whenever it writes a status. Unlike `FailureSource` (persisted only on `Failed`),
+the path survives for Incomplete, AwaitingUser, Stalled and Pending.
+
+| Origin | Paths |
+| --- | --- |
+| `agent` | `complete`, `complete_soft` (Continue-Anyway), `failed`, `esp_failure_fallback`, `gather_complete`, `whiteglove_pending`, `whiteglove_resumed`, `stall_probe`, `stall_heal` |
+| `ingest` | `wg_awaiting` (stall probe mapped to WhiteGlove AwaitingUser) |
+| `sweep` | `stalled`, `wg_awaiting`, `sd_reconcile`, `r{rule}` (stage-2 classifier) |
+| `maxlife` / `late` / `retro` | `r{rule}` (classifier via max-lifetime shutdown / late-telemetry heal / retro reclassification); `retro:sd_reconcile`, `retro:superseded` |
+| `register` | `new`, `whiteglove_resume`, `superseded` |
+| `rule` | `rule:{ruleId}` (analyze rule with MarkSessionAsFailed) |
+| `manual` | `failed`, `succeeded` |
+| `legacy` | read-side derivation only (`legacy:{rule}` when the rule is recoverable from the reason literal, `legacy:unknown` otherwise) — never written |
+
+Classifier rule ids (`ClassifierRules`): `r1`, `r1b_awaiting`, `r1b_succeeded`, `r1c`, `r2`,
+`r3`, `r4`, `r5_awaiting`, `r5_incomplete`, `r6`. `ClassifyTimedOutSession` returns
+`(Status, Reason, Rule)` so each `return` names its rule.
+
+## PriorStatus / PriorVerdictPath — the correction stream
+
+When a write replaces a prior **verdict** (existing status ∈ Succeeded/Failed/Incomplete/
+AwaitingUser with a stamped path, incoming status different), the storage seam preserves the
+pair (`TableStorageService.ComputePriorVerdict`, both the ETag path and the force path). A
+stall marker healing to InProgress, a same-status refresh, or an unstamped legacy row never
+sets it. Admin marks, late agent completions and retro reclassifications all flow through it.
+
+## Read-side derivation for pre-instrumentation rows
+
+`VerdictPathDerivation.Derive(session)` returns the stamped path verbatim, otherwise derives
+from `AdminMarkedAction`, `FailureSource`, `ReconcileReason` and `FailureReason` using the
+writers' fixed literals (classifier rule prefixes, the `max-lifetime watchdog` / `Retro-
+reclassified` suffixes, `Rule: `, `Superseded by session`, `Late completion report received`).
+Unambiguous rows get the real path (`agent:complete`, `manual:failed`, `rule:…`,
+`maxlife:r6`), ambiguous-but-rule-known rows `legacy:{rule}`, the rest `legacy:unknown`. No
+mass backfill: the aggregate counts derived rows with `DerivedCount` so the matrix shows
+history while flagging its weaker evidence. Tests pin the literals against the classifier
+output so a wording change fails loudly.
+
+## Daily aggregate — `VerdictCalibrationAggregates`
+
+PK = `TenantId` | `"global"`, RK = `yyyy-MM-dd` (session **StartedAt** date, like every daily
+aggregate). `VerdictCalibrationDailyAggregate { Version, SessionCount, TerminalSessionCount,
+Buckets[], ComputedAt }` with one bucket per (VerdictPath, Status):
+
+| Field | Meaning |
+| --- | --- |
+| `Count` / `DerivedCount` | sessions currently on the path; of those, derived read-side |
+| `Eligible7d` | terminal sessions whose end (`CompletedAt ?? LastEventAt ?? StartedAt`) lies ≥ 7 d before compute time |
+| `ReEnrolled7d` | of the eligible: the device's `DeviceHistories` chain shows the next terminal session starting < 7 d after this one's end |
+| `OverriddenByAdmin` / `OverriddenByLateCompletion` / `OverriddenOther` | sessions whose **PriorVerdictPath** is this bucket — attributed to the path that was overridden, so a bucket can carry overrides with `Count = 0` |
+
+`MaintenanceService.SweepVerdictCalibrationAsync` (2-hourly, after the device-journey sweep
+so the chains are fresh; manual maintenance parity; kill switch
+`VerdictCalibrationSweepDisabled`) slices the tick's shared projected window scan
+(`LoadSweepWindowSessionsAsync` — one 35-day cross-tenant drain feeds the time-attribution,
+device-journey and calibration sweeps plus the radar's tenant discovery; the StartedAt-only
+filter is a full-table read, so never per sweep), recomputes the rolling 30-day window whole (Replace),
+deletes stale date rows it did not regenerate, and the unbounded-tables cleanup applies the
+180-day retention. Sessions inside a deletion cascade are skipped; the table is regenerable
+and is wiped with the tenant on offboarding.
+
+## Read surfaces
+
+* `GET global/metrics/verdict-calibration?days=&tenantId=` (GlobalReadOrAdmin,
+  TenantScoping.QueryParam; `VerdictCalibrationResponse.Build`): per path — count, share of
+  all window sessions, derived count, eligible/re-enrolled with `reEnrollRatePct` **null below
+  20 eligible**, the three override counters, a today-anchored 7d-vs-28d share trend
+  (`window7`, `baseline28`, `lift` null without baseline) — plus totals, the trend basis and
+  the active `alerts[]`. Empty but well-formed before the first sweep.
+* MCP `get_verdict_calibration` (platform scope: GA + Global Reader). Same endpoint, LLM-shaped in
+  `verdict-calibration-shape.ts`: per-row `window7.sessions` / `baseline28.sessions` are dropped (the
+  denominators live once in `trend`), `reEnrollRatePct` / `lift` are always present (`null` = withheld),
+  and `minSharePct` / `top` trim the one-session tail — rows carrying overrides are never trimmed and
+  everything dropped is reported in `omitted`. The wire shape the admin page consumes is untouched.
+* Portal: Global Admin → Metrics → Verdict Calibration (`/admin/metrics/verdict-calibration`):
+  matrix grouped by origin, status pill, `derived n` gray pill, trend glyph (arrow only from
+  5 window hits and lift ≥ 2 / ≤ 0.5), re-enrollment rate or `— (n=…)`, overrides
+  `admin / late / other`, `↑ Drift` pill on rows with an active episode, and the active
+  episodes list.
+
+## Drift radar — `VerdictCalibrationRadar`
+
+Same statistics as the [rule regression radar](rule-regression-radar.md) (7-day window vs the
+prior 28 days, ≥ 20 window sessions, lift ≥ 2, `MetricsMath.RateIncreaseSeparated`), with
+stricter floors since the first-month tuning (2026-08-27): **≥ 10 window hits** (verdict
+shares on single-digit counts are noise — a 3-hit episode survived as such), and a per-path
+share regression additionally needs **≥ 5 baseline hits** — a path with no established
+baseline is new (or renamed) vocabulary, not a regression. Anchored on yesterday, over every
+partition with rows (each tenant and `global`):
+
+| Kind | Signal | Re-arm |
+| --- | --- | --- |
+| `share_regression` | one **backend-decided** path's share of all sessions doubled (`sweep`/`maxlife`/`late`/`retro`/`rule`/`manual`/`ingest`; `agent:*` and `register:*` mirror customer workflow mix — first prod pass fired on `agent:whiteglove_pending` rollout weeks — and `legacy:*` is derived, all excluded per-path) | share < 1.5× baseline, the path stops occurring, the path is no longer eligible, or the current numbers fall below the fire floors |
+| `silence_share_regression` | the `sweep:*` + `maxlife:*` share doubled — the backend had to decide more often because the agent went silent (a liveness signal, not a classifier one). Rule-shaped `legacy:*` paths count into BOTH sums (window and baseline): they were the same backend decisions before the 2026-08-23 instrumentation, and without that continuity the group had a near-zero baseline by construction and fired a lift-124 rollout artifact | share < 1.5× baseline or hits stop |
+| `evidence_gap` | absolute: `r6` (pure fallthrough) decides ≥ 20 % of the window's classifier verdicts (stamped rule paths plus rule-shaped `legacy:*`, same continuity), ≥ 20 verdicts | < 15 % or < 20 verdicts |
+
+Episodes are tracker rows `verdictcalibration|{kind}|{path}|{status}` (register = `AddEntity`,
+409 = already burning, fail-closed; refresh carries `FirstNotifiedAt`; 30-day tracker
+retention re-arms long burners). A new episode fires **one** `VerdictCalibrationDrift` ops
+event (category Maintenance, Warning; dual-registered in the web `OPS_EVENT_TYPES`) — there
+is deliberately **no tenant bell**. Per-path findings on a tenant partition get the on-fire
+dimension correlation (`RuleRegressionRadar.ComputeDimensionConcentration` over the window's
+sessions whose derived path matches), reported with the shared wording contract "correlated,
+not necessarily causal"; group kinds and the global partition carry no dimension claim.
+Kill switch `VerdictCalibrationRadarDisabled`.
+
+# Examples
+
+* **Reading the thermometer (prod, 2026-08-23 hand analysis that motivated this):**
+  re-enrollment within 7 days after Succeeded 8.9 % (lab background), after Failed 24.3 %,
+  after Incomplete 10.6 % — Incomplete behaves like Succeeded, so rules 5/6 are probably too
+  cautious; the matrix now shows this per rule instead of per status.
+* **First real calibration read (2026-08-27, four days instrumented):** the per-rule and
+  per-tenant split resolved that hand analysis — `legacy:r5_incomplete` re-enrolled at 2.6 %
+  (the `agent:complete_soft` background), spread across tenants, while `legacy:r6`'s 29 %
+  was concentrated in one tenant that disciplinedly redoes failed enrollments (48.5 % there,
+  6.7 % elsewhere — so r6 stays untouched, it correctly flags that tenant). Consequences
+  shipped the same day: rule 5a "completed (assumed)" (see
+  [Silent-Session Classification](silent-session-classification.md)), the max-lifetime grace
+  skip, and the radar floors + legacy group continuity above — the first production month
+  had produced nine standing alerts, every one an instrumentation-rollout artifact.
+* **Correction stream:** a session swept to `sweep:r5_incomplete`, later completed by the
+  agent → row `agent:complete` with `PriorVerdictPath = sweep:r5_incomplete`; the aggregate
+  increments `OverriddenByLateCompletion` on the `sweep:r5_incomplete / Incomplete` bucket.
+  Four admin marks since launch were invisible before — now each one counts against the path
+  it corrected.
+* **Evidence gap:** a tenant whose agent build stopped emitting the Device Setup rollup line
+  drives its sweep verdicts into `r6`; the absolute gate fires at 20 % and names the
+  tenant — the fix is agent-side, the classifier is only the messenger.
+
+# Citations
+
+* `src/Shared/AutopilotMonitor.Shared/Models/VerdictPaths.cs` — vocabulary + `ClassifierRules`
+* `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.Sessions.cs` — `ComputePriorVerdict`, `ApplyVerdictPath`, re-registration preserve
+* `src/Backend/AutopilotMonitor.Functions/Helpers/VerdictPathDerivation.cs`
+* `src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.VerdictCalibration.cs` — sweep + `BuildVerdictCalibrationAggregates`
+* `src/Backend/AutopilotMonitor.Functions/Functions/Metrics/GetVerdictCalibrationFunction.cs`
+* `src/Backend/AutopilotMonitor.Functions/Helpers/VerdictCalibrationRadar.cs`, `Services/MaintenanceService.VerdictCalibrationRadar.cs`
+* `src/McpServer/autopilot-monitor-mcp/src/tools/admin.ts` — `get_verdict_calibration`
+* `src/McpServer/autopilot-monitor-mcp/src/verdict-calibration-shape.ts` — LLM-facing response shaping (`minSharePct` / `top`, explicit nulls)
+* `src/Web/autopilot-monitor-web/app/admin/metrics/sections/SectionVerdictCalibration.tsx`
+* Tests: `VerdictPathTests`, `VerdictCalibrationTests`, `VerdictCalibrationRadarTests`
+* Related: [Silent-Session Classification](silent-session-classification.md), [Device Journeys](device-journeys.md), [Rule Regression Radar](rule-regression-radar.md)
@@ -0,0 +1,160 @@
+---
+type: Concept
+title: Vulnerability Correlation Sources (NVD, KEV, MSRC, EPSS)
+description: How the software inventory is turned into CVE findings - CPE mapping, the per-CPE NVD cache with its budget and TTLs, KEV/MSRC/EPSS enrichment, the throttle contract that keeps a refused NVD answer out of the cache, and the act/attend/track priority.
+resource: src/Backend/AutopilotMonitor.Functions/Services/Vulnerability/VulnerabilityCorrelationService.cs
+tags:
+  - backend
+  - vulnerability
+  - nvd
+  - epss
+  - kev
+  - msrc
+  - cache
+timestamp: 2026-08-29T18:00:00+02:00
+---
+
+# Vulnerability Correlation Sources
+
+The Software Inventory & Vulnerability Analyzer (tenant opt-in) ships the installed-software
+list with the session; the backend turns it into CVE findings entirely from cached public
+reference data. Four sources, all trustworthy primaries, no aggregators:
+
+| Source | What it contributes | Fetch shape | Cache |
+| --- | --- | --- | --- |
+| NVD 2.0 (NIST) | CVE records per product: CVSS v3.1 (v3.0 fallback) score, severity, **vector**, description, affected version ranges; CPE dictionary for auto-mapping | `cves/2.0?virtualMatchString={cpe}` per product, `cpes/2.0?keywordSearch=` for unmapped titles; optional API key (`AdminConfiguration.NvdApiKey`) | Azure Table `VulnerabilityCache`, one row per CPE (`cve_{cpe}` / `cache_result`), `CveDataJson` chunked; soft TTL 7 d (serve + background refresh), hard 14 d |
+| CISA KEV | "Exploited in the wild" flag, due date, required action, ransomware use | Whole catalog JSON | In-memory dictionary, 24 h, blob mirror `kev-catalog.json` |
+| MSRC | Microsoft-side confirmation: document id/title, release date, Microsoft severity / score / vector | CVRF v3.0 index of the last six Patch Tuesdays | In-memory index, blob mirror `msrc-index.json` |
+| FIRST EPSS | Probability (0..1) that the CVE is exploited within 30 days + percentile + scoring date | `api.first.org/data/v1/epss?cve=a,b,c` - 100 ids per request, unauthenticated | Stored **on the cached CVE** (no separate table): filled when a CPE row is (re)fetched, re-scored for every row by the nightly sync |
+
+Nothing about a tenant leaves the backend. The one outbound query that carries content is the
+EPSS lookup, and its payload is the list of public CVE ids held in the shared, tenant-agnostic
+CPE cache. Customer-facing wording: `autopilotmonitor-docs/trust/data-flows.md` and the
+terms page attribution block.
+
+# Schema
+
+## Cached CVE (`CachedCve`, serialised into `CveDataJson`)
+
+```
+CveId, CvssScore, CvssSeverity, CvssVector?, Description (<=500), PublishedDate,
+EpssScore?, EpssPercentile?, EpssDate?, AffectedVersions[] {Criteria, VersionStart/End Incl/Excl}
+```
+
+`JsonOptions` is `WhenWritingNull` + case-insensitive, so rows written before the vector / EPSS
+properties existed deserialise with those as `null`, and a row is never rewritten just to add
+nulls. `CveCacheBudget` bounds the row (24 months, or CVSS >= 7 within 60 months; max 100 CVEs
+per CPE, 50 ranges per CVE) - which is also why one CPE fill is exactly one EPSS request.
+
+`ProjectNvdResponse` is the single NVD -> `CachedCve` projection; the live fill and the nightly
+refresh both call it, so both write the same shape. `BuildCveCacheRow(cpe, cves, cachedAt)` is the
+single row builder; `cachedAt` is the **NVD** freshness stamp, an EPSS-only rewrite passes the
+existing value through so it does not look like a fresh NVD fetch to the 7-day TTL.
+
+## Per-finding output (report `findings[].vulnerabilities[]`)
+
+```
+cveId, cvssScore, cvssSeverity, cvssVector?, description, publishedDate, source ("NVD" | "NVD+MSRC"),
+isKev, kevDueDate, kevRequiredAction, knownRansomware,
+epssScore?, epssPercentile?, epssDate?,
+priority ("act" | "attend" | "track"),
+msrc* (when MSRC confirmed), versionMatchConfidence ("low" on wildcard CPE matches)
+```
+
+Finding level: `riskLevel` (unchanged CVSS+KEV bands), `priority` (highest band), `maxEpssScore?`.
+`scan_summary` additionally carries `act_cves` / `attend_cves`. `MergeReports` (Part 1 + Part 2)
+recomputes all of these. The `CveIndex` row (one per tenant/CVE/session) carries `EpssScore`
+(max over occurrences, absent when unscored) and `Priority` (highest), which the fleet summary
+(`TopCve.epssScore` / `priority`) reads.
+
+## Priority (`CvePriority.Compute`)
+
+* `act` - in CISA KEV.
+* `attend` - EPSS >= 0.1 **or** CVSS >= 9.0.
+* `track` - everything else.
+
+Three visible rules instead of a weighted composite: severity (`riskLevel`) keeps saying how bad,
+priority says how soon. A CVE without an EPSS score is "unknown likelihood" - it can still reach
+`attend` via CVSS, never via a defaulted 0. The thresholds are constants; changing them is a
+product decision, not a tuning knob.
+
+# Throttle contract (NVD)
+
+The typed `HttpClient` runs under the `ExternalDataApi` Polly policy: 429/5xx/timeouts are retried
+three times (1/2/4 s + jitter) with a circuit breaker. A 429 that reaches `NvdApiClient` therefore
+means NVD is refusing us for real. Two things then happen, and one deliberately does not:
+
+1. `NvdFetchResult<T>` reports `Succeeded = false`, `Throttled = true`. `Data` is an empty object
+   so enumerating callers keep working, but **nothing that persists may treat it as an answer**:
+   the CPE cache fill returns null and writes no row; the negative auto-resolve cache is not
+   touched; the admin auto-resolve reports `nvd_throttled`. Before this contract an empty response
+   was cached as "0 CVEs" for seven days - a product NVD happened to throttle disappeared from
+   every report for a week.
+2. A process-wide cooldown opens: `Retry-After` when present (delta or date, capped at 120 s),
+   otherwise 30 s. During the cooldown every NVD call fails fast with `Throttled` - no wait, no
+   retry chain. Worst case added latency per cooldown window is one Polly chain (~7.5 s), never
+   a per-item stall; the nightly refresh breaks out of its loop on the first throttled answer and
+   reports the remainder as `cveSkippedThrottled`.
+3. Not done on purpose: no in-process retry beyond Polly, no VulnCheck-style mirror, no separate
+   "throttled" cache state. Hard-expired cache rows keep serving while NVD is unavailable
+   (better than nothing, logged); a product with no row at all is reported without CVE data for
+   that run and gets a real attempt on the next correlation.
+
+# Nightly sync (`VulnerabilityDataSync`, 03:00 UTC) and the manual buttons
+
+1. KEV catalog refresh (blob mirror updated).
+2. MSRC index refresh (last six Patch Tuesdays).
+3. NVD refresh of cache rows older than 7 days (sequential, breaks on throttle).
+4. **EPSS re-score of every `cve_*` row** - all ids batched through FIRST, only rows whose score /
+   percentile / date changed are rewritten (with their original `CachedAt`). A missing id in the
+   response keeps yesterday's score: a failed batch never erases data.
+
+Steps 3 and 4 live in `VulnerabilityCacheRefreshService` (singleton, one in-flight slot per walk),
+which the timer and the Global-Admin buttons share, so a manual run writes exactly what the nightly
+run writes. Four endpoints, one per source, each with its own "Last … Sync" line on the admin page
+(`GET vulnerability/sync-status`):
+
+| Button | Endpoint | Shape | Timestamp |
+| --- | --- | --- | --- |
+| Sync KEV | `POST vulnerability/sync` | synchronous | `VulnerabilityDataLastSyncUtc` |
+| Sync MSRC | `POST vulnerability/sync-msrc` | synchronous | `MsrcLastSyncUtc` |
+| Refresh NVD Cache | `POST vulnerability/sync-nvd` | **202 + background** (minutes, NVD-rate-limited); 409 while running; the page polls `nvdRefreshRunning` / `nvdLastRun` every 10 s | `NvdCacheLastRefreshUtc` - stamped only for a walk that reached every stale row (no throttle cut-off) |
+| Sync EPSS | `POST vulnerability/sync-epss` | synchronous (seconds); 409 while running | `EpssLastSyncUtc` |
+
+The timer skips a walk whose slot a manual run currently holds (`cveSkippedBusy` in telemetry)
+rather than queueing a duplicate. `nvdLastRun` / `epssLastRun` are in-memory on the answering
+instance (null after a cold start); the persisted timestamps are the durable signal.
+
+Telemetry event `VulnerabilityDataSyncCompleted` carries `epssRows / epssCves / epssScored /
+epssRowsRewritten / epssError` next to the KEV / MSRC / CVE counters; the manual EPSS run emits
+`ManualEpssSyncCompleted`.
+
+# Examples
+
+* Chrome 126 finding: `CVE-2024-4947` CVSS 8.8 HIGH, `AV:N/AC:L/PR:N/UI:R`, KEV yes -> `priority =
+  act`, riskLevel `critical` (KEV) - unchanged severity semantics, priority now explicit.
+* A 5.5 MEDIUM local-privilege CVE with EPSS 0.31 -> `attend`; the same CVE with EPSS 0.004 ->
+  `track`. Same severity band, different order of work.
+* Nightly sync while NVD throttles: `[VulnSync] NVD throttled - leaving 37 stale entries for the
+  next run`, then `[VulnSync] EPSS refresh: 1412/1450 CVEs scored across 212 rows, 180 rows
+  rewritten` - EPSS is independent of NVD's mood.
+
+# Not done (recorded)
+
+* **ExploitDB CSV** as a "public exploit exists" flag (static file, daily, same shape as the KEV
+  mirror) - useful, cheap, deliberately not added: four primary sources are enough for now and
+  each additional outbound dependency is a trust-page line. Revisit if customers ask "is there a
+  public exploit?".
+* GitHub / Nuclei PoC search, composite 0-100 risk scores, CWE -> ATT&CK mapping - noise for an
+  Intune admin, not adopted.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/Vulnerability/NvdApiClient.cs` - `NvdFetchResult`, cooldown, `ComputeCooldown`
+* `src/Backend/AutopilotMonitor.Functions/Services/Vulnerability/EpssApiClient.cs` - batching, `ParseResponse`
+* `src/Backend/AutopilotMonitor.Functions/Services/Vulnerability/CvePriority.cs`
+* `src/Backend/AutopilotMonitor.Functions/Services/Vulnerability/VulnerabilityCorrelationService.cs` - `ProjectNvdResponse`, `ApplyEpssScores`, `BuildCveCacheRow`, `StampFindingPriority`, `FetchAndCacheCvesFromNvdAsync`
+* `src/Backend/AutopilotMonitor.Functions/Functions/Vulnerability/VulnerabilityDataSyncFunction.cs` - `RefreshStaleCveCacheAsync`, `RefreshEpssScoresAsync`
+* `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.AgentApi.cs` - `BuildCveIndexEntities`, `ScanCveIndexAsync`
+* `src/Backend/AutopilotMonitor.Functions.Tests/EpssAndNvdThrottleTests.cs`
+* FIRST EPSS API: https://api.first.org/epss/ - CISA KEV: https://www.cisa.gov/known-exploited-vulnerabilities-catalog
@@ -13,36 +13,53 @@ https://docs.autopilotmonitor.com (separate repository).

 * [Architecture Guide](architecture.md) - High-level architecture overview and solution layout for contributors.
 * [Version Contract](versioning.md) - One version shape for agent, backend and MCP: the ETag-CAS counter blob that mints build numbers, and the manifests published only after a deploy is verified live.
+* [Customer Script Publishing](script-publishing.md) - How the customer-facing PowerShell scripts reach download.autopilotmonitor.com/agent/, why publishing is decoupled from agent releases, and the guards keeping the published copy, the version badge and the portal's version oracle in agreement.
 * [URL Registry](url-registry.md) - Every well-known host lives in one registry file per component (Constants.cs / utils/config.ts / src/config.ts), enforced by guard tests; includes the agent-download migration to the download alias and its deploy-order constraint.
 * [Drift Guards](drift-guards.md) - The 2026-08 fragility-audit follow-up contracts: SignalR message-name catalog (typed on both ends), the inverted-tick RowKey codec, tombstone table tagging, the shrink-only OkAsync baseline, per-section config PATCH with the section field map, and the web's scoped-endpoint builders + sidebar visibility matrix.

 # Agent

-* [V2 Agent](agent/index.md) - How the on-device agent works: [runtime overview](agent/overview.md), [decision engine](agent/decision-engine.md) (reducer, signals, completion arms), [logs & persistence](agent/logs-and-persistence.md) (signal log, snapshot, crash recovery), [Hello wizard un-skip](agent/hello-wizard-unskip.md) (why a single "WHfB disabled" read never decides completion), [Autopilot ZTD diagnostics](agent/autopilot-ztd-diagnostics.md) (event IDs, diagnostic registry, endpoints, error-code map).
+* [V2 Agent](agent/index.md) - How the on-device agent works: [runtime overview](agent/overview.md), [decision engine](agent/decision-engine.md) (reducer, signals, completion arms), [logs & persistence](agent/logs-and-persistence.md) (signal log, snapshot, crash recovery), [diagnostics package](agent/diagnostics-package.md) (built-in section catalog shared with the portal, RealmJoin/Device Preparation collection gates, caps, manifest), [Hello wizard un-skip](agent/hello-wizard-unskip.md) (why a single "WHfB disabled" read never decides completion), [Autopilot ZTD diagnostics](agent/autopilot-ztd-diagnostics.md) (event IDs, diagnostic registry, endpoints, error-code map).
 * [Build Counter Blob](agent/build-counter-blob.md) - How agent build numbers are minted: shared counter blob with ETag-CAS so local and CI builds never collide; CI additionally attests build provenance (Sigstore).
 * [Agent Endpoint Migration](agent/endpoint-migration.md) - How the backend re-homes agents to a new API base URL via the config channel (backend move or per-tenant region move): live-fetch-only, allowlist-validated on both sides, one hop, kill wins.
 * [Gather Rule Debug Log](agent/gather-rule-debug-log.md) - EnableGatherRuleDebugLog (ConfigVersion 36): the per-tenant local trace file that explains every gather-rule evaluation decision — scope skips, on_change suppression, empty collector results, logparser position/parse-mode outcomes — for rules that produce no timeline events.
 * [MDM Reboot Coalescing](agent/mdm-reboot-coalescing.md) - Attributing the mid-ESP coalesced reboot ("second sign-in") to the device-assigned policy URIs that forced it: aggregated DM-Enterprise 2800 observations (neutral, flush-time watermark) + the ANALYZE-ESP-005 advisory gated on an actually-observed reboot.
+* [ESP Completion Starvation — the sits-d Cloud-PC complex](agent/post-reboot-completion-recovery.md) - Why a SkipUser=true flow (no user ESP page → no Shell-Core 62407, no AccountSetup registry) left the completion gate satisfied but never evaluated — five Cloud PCs idled six hours at "waiting on: hello_resolution" — and the fix: the observed skip stands in for the final-exit evidence in the IME user-session completion attempt. Plus the two adjacent defects fixed alongside: the edge-only user-apps-settled synthesis (now level-triggered) and the never-wired Shell-Core restart replay (now Hello-wizard-only, with the reasoning why a replayed 62407 must never reach the reducer).
+* [Zero User-Targeted Apps — the starved user-phase completion gate](agent/zero-user-apps-completion-gate.md) - Why a device with no user-targeted Intune apps could never satisfy the IME user-session gate — IME skips its "Completed user session" line entirely in the zero-app branch — turning the 30-minute completion backstop into `esp_exit_without_completion_evidence` on a third of one tenant's enrollments, with the user at the desktop and RealmJoin still installing. The two fixes: read the line IME does write (IME-USER-SESSION-ZERO-APPS), and never fail a session while a completion gate with its own armed deadline is deliberately holding it.
 * [Secure Boot CA-2023 Detection](agent/secureboot-ca2023-detection.md) - Why ANALYZE-SEC-001 v3 reads the UEFI db/KEK variables directly instead of trusting the SecureBoot\Servicing registry, and how the one-sided uefiCa2023FirmwareConfirmed marker plus a not_exists precondition give absence-tolerant suppression across old and new agents.
 * [Continue-Anyway Observation Mode](agent/continue-anyway-observation.md) - EnableEspContinueAnywayObservation (ConfigVersion 37, operator-set): Device-phase ESP terminal failures on Continue-Anyway profiles get a bounded 60-min observation instead of an immediate hard fail; the DAD-validated real-user desktop + Hello gate detect the true end, the session completes Succeeded + EspSoftFailure (amber "with issues" badge), expiry un-defangs to the original esp_terminal_failure.
+* [CMTrace Time Resolution](agent/cmtrace-time-resolution.md) - Converting bias-less CMTrace local times to UTC without trusting any process's timezone belief: per-line self-anchoring on the 15-minute offset grid for provably fresh lines, uniform marked reader-zone fallback for backlog, and the provenance vocabulary (bias / line-anchored / reader-zone-fallback) that keeps every event re-derivable.
 * [Registry App-State Second Pillar](agent/registry-app-state-pillar.md) - IME's authoritative per-app state read straight from the registry (Win32Apps EnforcementStateMessage, EspTrackingWin32Apps, StatusServiceReports) via a snapshot-and-diff watcher; registry/log reconciliation doubles as the built-in IME log-pattern drift alarm.
+* [WDP Scenario Gates & Completion Backstop](agent/wdp-scenario-gates.md) - How the agent gates Autopilot/ESP-only machinery off on Windows Device Preparation sessions (deterministic ExecutionContext marker, fail-toward-Classic), which noise it suppresses (ZTD probe, esp_config unknown, ModernDeployment 100/417/418/1005, starved sweep), and the WDP completion model: High-confidence seed, desktop-based arm D, and the 30-min device_prep_completion backstop.
+* [Power-State Watcher](agent/power-state-watcher.md) - Live AC↔battery transitions and 50/30/15% downward battery-threshold crossings during enrollment via a WMI Win32_PowerManagementEvent push subscription (zero polling, never armed on battery-less devices): the power_state_change event (transition field, per-level lifetime latch, 5s debounce, emission cap) and the analyze rules ANALYZE-DEV-009 (battery <15%, high) / ANALYZE-DEV-010 (AC→battery, warning) with on_event interim triggers.
+* [System Timeline Watcher](agent/system-timeline-watcher.md) - Ground truth for two timeline blind spots from one System-channel EventLogWatcher with pre-agent backfill: system_clock_changed (Kernel-General 1 — oldTime/newTime/signed timeDeltaMs/reason/setting process; 2 s micro-slew floor, ≥5 min Warning+immediate) and system_sleep_episode (Power-Troubleshooter 1 sleep/hibernate + Kernel-Power 507 Modern Standby; authoritative enteredAt/exitedAt payload instants, 60 s Modern-Standby floor). Consumed by the TimeJumpBadge clock-set cause, the SessionInfoCard standby note, time-attribution SleepSpans (AttributionVersion 3) and ANALYZE-DEV-012.
+* [DO GroupId Auto-Set](agent/do-group-id-auto-set.md) - EnableDoGroupIdAutoSet (ConfigVersion 40): the agent seeds the Delivery Optimization DOGroupId policy with a deterministic network-fingerprint GUID (default gateway IPv4 + SendARP MAC, RealmJoin-compatible byte layout) so same-network devices form one DO peering group during ESP; ownership-tracked via the StartupEventGate fingerprint, foreign DOGroupId/DOGroupIdSource policies always win, no random-GUID fallback.
 * [ESP Policy-Provider Stall Detection](agent/esp-policy-provider-stall.md) - The EnrollmentStatusTracking CSP's no-timeout Setup/Apps wait is keyed to the Intune-registered "Sidecar" provider by NAME: co-management's "ConfigMgr" parks the user ESP at "Apps (Identifying)" for days even with TrackingPoliciesCreated=1 (issue #106); the always-on two-arm esp_policy_provider_stalled tripwire (provider_incomplete | sidecar_provider_missing) and the SOFTWARE\Microsoft\Windows\Autopilot gather-rule allowlist entry that surface it.
+* [WiFi SSID and the Windows 24H2 Location Gate](agent/wifi-ssid-location-gate.md) - Why wifi_signal_info vanished on Windows 11 24H2+: WlanQueryInterface(wlan_intf_opcode_current_connection) is gated behind precise-location consent, the prompt only fires in a user context outside System32, and SYSTEM in session 0 falls back to the device-level ConsentStore value - so netsh (same gate) could never cover for it. The tiered WifiInfoProvider (native, then ungated WinRT GetConnectedSsid, then netsh), SSID-only semantics on tier 2, and the Warning-level rc=5 diagnostic that names the gate.

 # Rules

 * [Gather Rule Phase Scoping, One-Shot Triggers & Emit-on-Change](rules/gather-rule-phase-scoping.md) - Restricting gather rules to enrollment phases (activePhases / activeFromPhase sticky latch), one-shot collection at a phase's start/end (phase_change / phase_exit), and emitMode "on_change" result-dedup.
 * [Gather Rule Guardrails](rules/gather-rule-guardrails.md) - Why the allowlists in rules/guardrails.json are enforced on the agent and nowhere else, which hard blocks survive unrestricted mode, and the rule that every collector must call a guard and emit security_warning on refusal.
 * [Rule Authoring Surface](rules/rule-authoring-surface.md) - How customer AIs author rules against the real contract: the baked MCP resources (guide/schemas/guardrails via combine.js), the MCP-local validate_rule pre-flight, and the side-effect-free POST rules/analyze/dryrun whose trace twin shares the production evaluators (parity + side-effect-freedom pinned by tests).
+* [Rule ID Namespace & Collision Guards](rules/rule-id-namespace.md) - Why rule identity is the human-readable ruleId (no GUIDs) with tenant isolation via Table Storage partitioning, the reserved built-in namespace (RuleIdPolicy), which collisions are possible (custom-vs-custom across tenants: allowed and harmless), and the guards keeping the global RuleStats aggregate catalog-only and the global partition inside the reserved namespace (combine.js, reseed, cross-tenant RuleState GC).
 * [Analyze Rule Evaluation Triggers](rules/analyze-rule-triggers.md) - Opt-in `evaluateOn` interim triggers (`whiteglove_sealed`, `on_event:<type>`) so rules can fire before a session is terminal, with RuleResults update-semantics (interim → finalize/resolve, NotifiedAt notification dedupe) replacing the permanent dedupe freeze, KO/stat suppression on interim runs, the ingest-side cached trigger registry, and the authoring lints that keep interim rules monotonic.

 # Backend

+* [Telemetry Ingest Shaping](backend/telemetry-ingest-shaping.md) - One canonical App Insights request record (worker copy with tenant context, per-item sampling bypass; host HTTP duplicate dropped by a workspace transformation DCR), expected storage outcomes 404/412/409 and successful SignalR REST calls filtered in the worker, and the count()/sum(itemCount) query rules that follow.
+* [Table Schema Sentinel](backend/table-schema-sentinel.md) - Startup no longer issues one CreateTableIfNotExists per table: a SHA-256 over TableNames.All in AdminConfiguration gates the full pass (derived, never hand-maintained), the SessionsIndex backfill runs only after a full pass behind a conditional-insert claim, and daily maintenance repairs out-of-band deletions.
 * [Business Timestamps](backend/business-timestamps.md) - Why the Azure Tables system Timestamp is never authoritative (migrations reset it), and the OccurredUtc + RowKey-decode compensation for AuditLogs/OpsEvents/Events after the 2026-07-18 migration.
+* [Send-Time Frame Separation](backend/send-time-frame-separation.md) - One device-clock send timestamp per upload batch (X-Send-Time-Utc → SentAt on Events) splits ReceivedAt − OccurredUtc into pure spool delay and pure device-vs-server clock offset; the clock_skew condition measures SentAt batches directly (spool-immune), the CMTrace tripwire deliberately stays on its differential math.
 * [OOBE Bootstrap go-Code Flow](backend/oobe-bootstrap-go-flow.md) - The bootstrap short-code lifecycle (portal-created session → `irm go.autopilotmonitor.com/CODE | iex` at Shift+F10 → GetBootstrapScriptFunction), the always-HTTP-200 text/plain contract, the two-line injection defense (GUID/URL/expiry validator + single-quoted PS literals, golden-pinned against the legacy TS template), and the per-IP rate-limit story behind Front Door.
+* [Silent-Session Classification](backend/silent-session-classification.md) - How a session whose agent went silent gets its honest status: the two-stage maintenance sweep (2h Stalled marker with the WhiteGlove Part-2 AwaitingUser gate and the self-deploying Succeeded gate, 5h timeout classification), the EnrollmentTimeoutClassifier rule order (explicit failure → WG Part 2 → self-deploying → completion evidence → emergency break → desktop+Hello → Device Setup/grace), the ingest paths sharing it (max-lifetime, late-telemetry heal, stall probe) and the admin retro-reconcile modes incl. self_deploying_silent.
 * [Device Journeys & First-Time-Right](backend/device-journeys.md) - How a device's terminal enrollment attempts are grouped into journeys (trim+casefold device key with junk-serial exclusion, first-success end, 30-day gap, WhiteGlove = one attempt), the DeviceHistories chain with its tombstone-driven deleted-session pruning, the additive daily FTR aggregates, and the banner/fleet/MCP surfaces.
 * [Enrollment Time Attribution](backend/time-attribution.md) - How a terminal session's authoritative wall clock (DurationSeconds, WhiteGlove pause excluded) is partitioned into named segments with an explicit unattributed remainder, ESP-blocking apps as positive evidence with "up to" what-if bounds, reboot spans from event gaps, and the breakdown/aggregate tables the sweep maintains.
+* [Attempt-Scoped App Install Durations](backend/app-install-duration-attempt.md) - AppInstallSummary.DurationSeconds = status-defining (last) install attempt via the LastAttemptStartedAt max-fold anchor instead of the first-observation→last-terminal span that billed multi-pass IME gaps to trivial apps; InstallPassCount, the weaker-terminal guard, the radar's cutover gate, and time attribution's union-of-attempt-segments occupancy.
 * [Rule Regression Radar](backend/rule-regression-radar.md) - How analyze-rule hit-rate regressions are detected (7-day window ≥2× the 28-day baseline with disjoint Wilson intervals), which suppressions keep the radar quiet (grace period, edit-in-window, kill switch), how alert episodes live in the ruleregression tracker keyspace with re-arm semantics, and the on-fire dimension correlation with its "correlated, not necessarily causal" wording contract.
+* [Verdict Calibration](backend/verdict-calibration.md) - How every session status write declares its VerdictPath (origin:detail vocabulary incl. classifier rule ids), how overriding a verdict preserves PriorStatus/PriorVerdictPath as the correction stream, the daily per-path calibration aggregate with the 7-day re-enrollment proxy and read-side legacy derivation, the GA endpoint / MCP tool / admin matrix, and the drift radar (share, silence-share, r6 evidence gap) with its operator-only ops events.
 * [App Version Duration Regression Radar](backend/app-version-regression-radar.md) - How app versions whose median install duration regressed vs. the previous version are detected (first-seen-ordered versions, median lift ≥2× plus a 5-minute absolute floor over measured installs only), how alert episodes live in the appversionregression tracker keyspace with drain/median re-arm semantics, and the bell/ops-event/analytics surfaces.
+* [Plan Downgrade Policy & the Retention Grace Period](backend/plan-downgrade-retention-grace.md) - What happens when a tenant loses Pro: every entitlement gates read-time and reversibly ("gate, don't destroy"), except retention — a 30-day grace keeps the Pro cap before the Community cap starts hard-deleting; the ProDowngradedUtc/trial-expiry anchor model, the TenantPlanDowngraded/RetentionGrace* ops events, and the deliberate non-grace of everything else.
 * [Tenant Activation & the Once-Only Welcome Mail](backend/tenant-activation-welcome-mail.md) - How a signup becomes an activated tenant (manual approve or the auto-approve queue), and the write-then-read + conditional-marker arbitration that sends the welcome mail exactly once even though activation and the user-typed notification address race each other.
 * [W365 Cloud PC Device Validation](backend/cloudpc-device-validation.md) - Why Cloud PCs can never pass the Autopilot serial lookup, and the cert-CN-bound CloudPc fallback validator: Subject CN (= Intune device id) matched against the tenant's Graph virtualEndpoint/cloudPCs inventory — admits exactly the service-provisioned Cloud PCs, nothing else.
 * [ServerActions & On-Demand Diagnostics](backend/server-actions-on-demand-diagnostics.md) - The queue-on-session, deliver-on-ingest action channel, the TenantAdminOrOperator tier with in-function per-type re-gating, the portal's Collect Logs flow (quick-config orders rotate_config before request_diagnostics), and the hosted-prefix sweep in the offboarding cascade.
@@ -51,6 +68,7 @@ https://docs.autopilotmonitor.com (separate repository).

 # MCP Server

+* [MCP Protocol Eras & Client ID Metadata Documents](mcp/protocol-eras-and-cimd.md) - One per-request factory serving the 2026-07-28 stateless revision (server/discover, ttlMs/cacheScope, Mcp-Method routing) and 2025-era initialize clients side by side, why the legacy leg stays a hand-wired JSON+gzip transport, the never-public cache-hint contract, and the CIMD client-registration path (SSRF-gated document fetch, same redirect allowlist) next to the deprecated dynamic registration.
 * [MCP Docs Corpus](mcp/docs-corpus.md) - How the published customer documentation becomes the `search_docs` corpus: CRLF-safe heading chunking, build-time embedding as a third precomputed section, and why a docs edit needs an MCP redeploy.
 * [MCP Tool Telemetry](mcp/tool-telemetry.md) - The three telemetry layers for judging tool quality: backend App Insights via X-MCP-Tool-Name, the per-user usage table, and the MCP_TOOL_LOGGING stderr lines (soft errors, result size vs. cap, zero-hit searches, Zod rejections).

@@ -61,6 +79,10 @@ https://docs.autopilotmonitor.com (separate repository).
 # Security & Identity

 * [MCP OAuth Flow](mcp-oauth-flow.md) - Who authenticates where when connecting an AI client to the MCP server; two identities, three parties plus Entra ID.
+* [Vulnerability Correlation Sources](backend/vulnerability-correlation-sources.md) - How the software inventory becomes CVE findings from four cached primaries (NVD per-CPE cache with budget and TTLs, CISA KEV, MSRC, FIRST EPSS stored on the cached CVE and re-scored nightly), the NVD throttle contract (a refused answer is never cached as "0 CVEs"; bounded process-wide cooldown honouring Retry-After), the persisted CVSS vector, and the act/attend/track priority that keeps severity and likelihood as two visible signals instead of one composite score.
+* [Client-Certificate Tenant Binding](backend/client-cert-tenant-binding.md) - Why a chain-valid Intune MDM certificate only proves "issued to some tenant", which extension actually carries the Entra tenant id (`…5.14`) versus the two that look like it (`…5.6` Intune Account id, `…5.4` device id, different encodings), why the Entra join certificate is not part of the auth path, and the shadow-then-enforce rollout with its volume-controlled telemetry.
+* [Admin Identity Binding](backend/admin-identity-binding.md) - Why a GlobalAdmins / DelegatedAdmins row keyed on a UPN string must never confer access by itself in an API that accepts tokens from every Entra tenant (domain re-registration, UPN recycling), the AdminIdentityBindings table pinning each cross-tenant-role UPN to its immutable home tid + oid, the fail-closed resolution order in both role services (row → binding → entitlement), the first-sign-in object-id pin with its race semantics, the 409 on grant-time conflicts, and the explicit GET/PUT/DELETE rebind surface.
+* [IME Installer Archive](backend/ime-msi-archive.md) - How every fleet-observed IME build is archived as its MSI: the ime_agent_version sighting that queues the job (first sighting, or a later sighting with a version-authoritative CSP URL after a 24 h backoff), the primary/secondary/hotfix candidate walk, the managed MSI ProductVersion check that keeps another ring's build out of the version folder (Failed:VersionMismatch), provenance with the full candidate walk, and the skill-side overwrite path for corrections.

 # Conventions for this bundle

@@ -1,7 +1,138 @@
 # Log

+## 2026-08-29 (6)
+
+* **Update**: `backend/admin-identity-binding.md` — grants are self-maintaining: `AdminIdentityResolver` derives the home tenant + object id from sign-in history (`UserActivity`), falls back to the UPN domain of an onboarded tenant, refuses to guess when a UPN was seen under two tenants; 422 `HomeTenantUnresolved` + portal tenant picker only for a never-seen domain. Identity fields and pills removed from the delegated / tenant-group forms; inspect/correct lives in Tenant Management → Edit Tenant Configuration → Identity bindings (collapsed).
+
+## 2026-08-29 (5)
+
+* **Creation**: Added `backend/admin-identity-binding.md` — cross-tenant roles (GlobalAdmin / GlobalReader, delegated MSP) were resolved from the UPN string alone while the API accepts tokens from every Entra tenant. New `AdminIdentityBindings` table (RK = UPN → home `TenantId` + `ObjectId`), `AdminIdentity` (upn + tid + oid) as the key both role services resolve on, binding checked after the row and before the Pro gate, object id pinned on the first sign-in from the bound tenant (ETag-guarded), grants require `homeTenantId` and refuse to re-home (409), `global/identity-bindings` GET/PUT/DELETE as the audited rebind path, `RequestContext.ObjectId`, throttle bucket keyed on oid. Legacy rows are inert until bound — seed bindings before the backend deploy.
+
+## 2026-08-29 (4)
+
+* **Creation**: Added `backend/ime-msi-archive.md` — the version-verified, multi-host IME installer archive: MsiProductVersionReader (managed CFB/MSI Property reader), candidate host walk, Failed:VersionMismatch, sighting re-queue with 24 h backoff, and the 2026-08-29 1.105.103.0 poisoning that motivated it.
+
+## 2026-08-29 (3)
+
+* **Update**: `backend/vulnerability-correlation-sources.md` - the admin page's Data Sync Status is complete: next to Sync KEV / Sync MSRC there are now Refresh NVD Cache and Sync EPSS, each with its own last-sync line (`NvdCacheLastRefreshUtc`, `EpssLastSyncUtc` on AdminConfiguration; shared manifest regenerated). The NVD and EPSS walks moved out of the timer into `VulnerabilityCacheRefreshService` (singleton, one in-flight slot per walk) so the button and the nightly run are literally the same code; the NVD walk is minutes long and rate-limited, so `POST vulnerability/sync-nvd` answers 202 and the page polls `sync-status` (`nvdRefreshRunning`, `nvdLastRun`) while it runs, `sync-epss` runs synchronously. 409 while a walk is in flight; the timer skips a slot a manual run holds. Operator-only surface - no customer docs.
+
+## 2026-08-29 (2)
+
+* **New**: `backend/vulnerability-correlation-sources.md` - FIRST EPSS joins NVD / CISA KEV / MSRC as the fourth vulnerability source: the probability + percentile + date live on the cached CVE (one batch of <= 100 ids per CPE fill, every `cve_*` row re-scored by the nightly sync, only changed rows rewritten and with their original `CachedAt`), the CVSS vector is persisted instead of dropped, and each CVE carries an act / attend / track priority (KEV; EPSS >= 0.1 or CVSS >= 9.0; rest) next to the unchanged severity bands - two visible signals, no composite score. The comparison with an open-source CVE MCP server surfaced the real 429 defect: Polly already retried, but a refused NVD answer came back as an empty response and was cached as "0 CVEs" for seven days. `NvdFetchResult` now separates "answered" from "refused" (nothing persists a refusal - CPE cache, negative auto-resolve cache, admin auto-resolve), and a 429 opens a process-wide cooldown (`Retry-After` capped at 120 s, else 30 s) so the run fails fast instead of paying a retry chain per software item; hard-expired rows keep serving meanwhile. NVD -> cache projection and the row builder are now single functions shared by the live fill and the sync. CveIndex / fleet summary carry `epssScore` + `priority`; portal shows EPSS pill, priority pill, vector; MCP tool descriptions and the CVE-audit prompt name the fields. ExploitDB recorded as a deliberate not-now. Backend before web; trust pages (terms attribution, privacy, data-flows), settings and portal-guide docs updated in the same change.
+
+## 2026-08-29
+
+* **New**: `mcp/protocol-eras-and-cimd.md` - the MCP server moved to the 2026-07-28 protocol revision (TypeScript SDK v2: `@modelcontextprotocol/server` + `/node`, zod 4; the monolithic `@modelcontextprotocol/sdk` is gone). One per-request factory (`mcp-server-factory.ts`) feeds both eras through `mcp-http.ts`: 2026 clients are served by the SDK entry (`createMcpHandler`, `legacy: 'reject'`, JSON response mode), 2025 clients keep the existing stateless transport with `enableJsonResponse` - routed on the SDK's own `isLegacyRequest` predicate, because the built-in stateless fallback would answer today's Claude/VS Code clients with SSE and lose the gzip win. Capabilities now declare `listChanged: false` (the SDK default advertised a notification a per-request server cannot send); `cacheHints` stamp `ttlMs`/`cacheScope: 'private'` on discover/list results (5 min) and resource reads (60 min) - never public, the catalog is role-dependent. Client registration: `client_id_metadata_document_supported: true`; an https `client_id` is a Client ID Metadata Document resolved by `cimd.ts` (SSRF gate on the resolved addresses before any request, no redirects, 5 s / 16 KB, exact `client_id` match, bounded `redirect_uris`, 10-60 min cache), the requested redirect_uri still has to pass the dynamic-registration allowlist; HMAC-signed DCR client_ids stay as the fallback. `mcp-oauth-flow.md` updated. Package version 1.5 -> 1.6. Pinned by `mcp-http.test.ts` (real v2 client over loopback HTTP, both eras, role parity), `cimd.test.ts`, `oauth-cimd.test.ts`.
+
+## 2026-08-28
+
+* **Update**: `CmTraceSkewTripwire` - the backend regression tripwire additionally requires >= 80 % of the individual IME deltas (relative to the other side's median) to sit within 2 min of some 15-minute grid multiple before `CmTraceTimeSkewRegression` fires; the ops event and its details now carry that fraction. Motivation: the first soak week produced 7 fires, all backlog replays - a relaunched agent re-tailing the IME log uploads one burst holding most of the session's IME samples with a continuum of ages whose median hit the grid by chance (session d832560a: 508 of 627 samples, 46...733 min, median 91). Era-mixing regressions (every line on the grid) still fire. Doc: `docs/agent/cmtrace-time-resolution.md`.
+
+## 2026-08-27 (2)
+
+* **Update**: `SecurityValidator` / `DeviceAssociationValidator` - Microsoft released Windows Autopilot device association on 2026-08-25 (learn.microsoft.com/autopilot/device-preparation/device-association/overview: TPM-backed UEFI marker, device-targeted device preparation policies, associated devices are marked corporate-owned by Intune with no corporate identifier upload). The DevPrep association lookup therefore leaves shadow mode and becomes the third accepting method of the device-validation gate, evaluated inline after the Autopilot and Corporate Identifier lookups and before the Cloud PC fallback; a match sets `ValidatedBy = DeviceAssociation`, a miss joins the combined 403 detail, a transient failure the 503 Retry-After - the same contract as its siblings, so enabling it can only widen acceptance, never reject a device the other methods would have taken. `ValidateDeviceAssociation` counts toward "at least one validation enabled" and is no longer GA-only anywhere (`UpdateTenantConfigurationFunction` revert, `TenantConfigPatchService.GaOnlyFields`, the Global-Admin gate on the settings toggle); the toggle sits under Device Preparation next to Corporate Identifier and follows the shared consent rule (first serial-based validation carries the consent, any further one is a plain persisted toggle). Known gap carried over from the shadow phase: the `/beta/deviceManagement/tenantAssociatedDevices` endpoint is still undocumented in Graph reference and every production lookup so far answered `matched=False` for Autopilot v1 devices, i.e. the positive match path is unproven in the field - first associated enrollment must be checked for `ValidatedBy = DeviceAssociation` on the session row. Landing hero carries a release pill linking to the customer docs; dashboard tip added. Backend before web; customer docs updated in `autopilotmonitor-docs`.
+
+## 2026-08-27
+
+* **Update**: `backend/silent-session-classification.md`, `backend/verdict-calibration.md` - the first real calibration read tuned what it measures. Rule 5 grew a past-grace fork 5a: Device Setup done + real-user desktop + zero `app_install_failed` reconciles to Succeeded "completed (assumed)" (`r5_assumed`) - r5-Incomplete devices re-enrolled at 2.6 %, the succeeded background, and the sampled desktop half had clean app records; no desktop or any failed app stays Incomplete. The max-lifetime watchdog (either event shape) now skips the AwaitingUser grace entirely - all five observed maxlife parks expired unhealed, and late telemetry heals a terminal verdict anyway - while WhiteGlove rule 1b keeps its park (its one episode healed). The drift radar got floors (≥ 10 window hits; per-path share regression needs ≥ 5 baseline hits, so new/renamed vocabulary cannot "regress") and legacy continuity: rule-shaped `legacy:*` paths count into the silence and classifier-verdict group sums on both sides of the 2026-08-23 cutover, which dissolves the lift-124 silence artifact and lets sub-floor episodes clear themselves. Backend only; the new path shows up in the matrix on its own.
+
+* **Update**: `backend/tenant-activation-welcome-mail.md` - the reverse lookup. A delivery log names only the recipient, so an address had to lead back to its tenant: the tenant console's search now matches the notification and contact address as well as domain and tenant id, with the quoted exact mode unchanged. The addresses sit in `PreviewWhitelist`, not on the tenant config, so a new GA/Reader-only `GET /api/preview/notification-emails` returns them as one map (single cross-partition scan of `RowKey eq 'notification-email'`) instead of a point read per tenant; both sides join on the lowercased tenant id because the address rows carry the JWT `tid` while a config PartitionKey's casing is not guaranteed, and matching is case-insensitive because stored addresses keep the casing the user typed. The map is best-effort in the portal - a failed read costs only the search-by-address, never the tenant list - and the addresses stay out of the list rows (search key, not a column). Match rules moved into `tenantSearch.ts` with unit pins. Backend before web.
+
+
+## 2026-08-26
+
+* **Update**: `agent/wifi-ssid-location-gate.md` - the network timeline now explains its blank signal too, with no agent change: `buildSegments` already merges `wifi_signal_info` into the covering WiFi segment, so `wifiDataLimitedReason` rides in with the sample. Segments that never got a sample (a mid-session reconnect emits none) inherit it - the gate is a device-level setting and cannot flip mid-enrollment - while a segment with a real reading is never overwritten. Tooltip shows `Signal: unavailable - Location services off on this device`; the "Avg WiFi signal" stat reads `n/a (Location services off)` instead of vanishing. `network_state_change` is deliberately left alone: it has never carried `signalPercent` or `radioType` (only `before_/after_wifiSsid` reaches its payload), so there is no absent field there for a reason to explain, and the SSID it does carry is unaffected by the gate. Web-only change.
+
+
+## 2026-08-26
+
+* **Update**: `agent/wifi-ssid-location-gate.md` - the gate is now surfaced instead of only logged. When the WinRT tier wins and the native tier reported `rc=5`, `wifi_signal_info` carries `wifiDataLimitedReason = "location_services_off"` and the message gains `- signal unavailable, Location services off`, so the reason is readable straight from the timeline; the portal WiFi card (`DeviceDetailsCard`) matches that literal and names the Intune setting that restores the full payload. The claim is evidence-only - any other native failure leaves the field null rather than blaming a privacy setting, with `IsLocationGateDenied` pinned at its boundaries. New `wifi_signal_info` group in the MCP `DEVICE_PROPERTIES_CATALOG` so a fleet can be sized via `search_sessions` before any policy changes. Agent release + web deploy + MCP redeploy; backend untouched (the payload is opaque DataJson).
+
+
+## 2026-08-26
+
+* **New**: `agent/wifi-ssid-location-gate.md` - `wifi_signal_info` was missing on most Windows 11 24H2+ WiFi enrollments (build 22631 3/3, 26100 37/178, 26200 43/95 over n=276 sessions from 08-01). Not a parser or language problem: every event that exists carries a full SSID, so the failure is binary at the reader. Cause is the 24H2 location gate on `WlanQueryInterface` with `wlan_intf_opcode_current_connection` - the only opcode the agent uses - which returns `ERROR_ACCESS_DENIED`; the consent prompt only fires for a process in the user context outside `System32`, so the agent (SYSTEM, session 0, pre-privacy-page) is denied silently, and it resolves consent from the HKLM ConsentStore because the `S-1-5-18` hive has none - while the interactive user on the same box reads the SSID fine via the per-user NonPackaged value. `netsh wlan` hangs off the same gate, so the 2026-07 netsh fallback (and its multi-language labels) never covered the case it was built for; more labels cannot fix it. New `WinRtWifiSsidReader` uses the documented replacement `WlanConnectionProfileDetails.GetConnectedSsid` (ungated, SSID only), bound via the CLR WinRT projection with no winmd/NuGet like `OobeStateReader`; new `WifiInfoProvider` owns the tier order (native, WinRT, netsh) that both collectors had duplicated. The step diagnostics added in 2026-07 were logged at `Debug` while the default level is `Info`, so they never reached a field log - the all-tiers-failed case is now a Warning that decodes `rc=5` into the location-gate explanation. Agent-only change; needs an agent release.
+
+
+## 2026-08-25
+
+* **Update**: `backend/client-cert-tenant-binding.md` — stage 2 enforced: `Mismatch` now returns 403 via `LogRequestRejection(stage=certtenant)`. Switched on against 35,684 requests / 32 tenants at 100 % `Match`, with the Warning channel verified to be carrying other traffic so the zero was not an artefact. The rule is one function (`CertTenantBinding.Rejects`) and only `Mismatch` blocks; `ExtensionMissing` / `Unparseable` / `RequestTenantNotAGuid` are tolerated on purpose (the first is the candidate for later tightening and has a test pinning the tolerance). Evaluation fails open on its own exception, and the 403 body does not echo the certificate's tenant. Device binding (stage 3) stays shadow + Global-Admin-only and is unaffected.
+
+## 2026-08-25
+
+* **New**: `agent/zero-user-apps-completion-gate.md` — a Classic enrollment whose user has zero targeted Intune Win32 apps could not produce the evidence any user-phase completion path required: IME's zero-app branch (`ApplicationPoller`, verified against decompiled 1.104.102.0 and three older builds) `continue`s before its `Completed user session` statement, so `ImeUserSessionCompletedUtc` stayed null, all four arms of `ShouldTransitionToAwaitingHello` were dead, and the 30-min `advisory_completion` backstop resolved the session as `esp_exit_without_completion_evidence` — with a DAD-validated desktop, Hello provisioned and RealmJoin still installing. One tenant: 10 of 30 enrollments in a week, all false positives. Two fixes. (1) New pattern `IME-USER-SESSION-ZERO-APPS` reads the line IME *does* write and routes it through the same `OnUserSessionCompleted` callback, guarded to the AccountSetup phase and replayed if the observation predates the phase marker; `AreUserEspAppsSettled` now accepts an empty app list only with that explicit observation. (2) `HandleAdvisoryCompletionDeadlineFired` re-arms instead of failing while the RealmJoin gate is closed and its own deadline is still armed — session 75d6ae8e installed 25 RealmJoin packages inside the window, the last 2 min before the failure. `ime_user_session_completed` gains an `evidence` field (`zero_user_apps_enumerated` / `user_session_completed`); no new event type. The pattern reaches existing agents via the config API (an unknown action is a Debug line), the behaviour needs an agent release.
+
+## 2026-08-24
+
+* **Change**: `DeviceAssociationValidator` / `SecurityValidator` — the DevPrep association shadow now logs one line per real Graph lookup instead of one per request (`DeviceAssociationResult.ServedFromCache`, `AsCacheHit()` copies rather than marking the shared cached instance), the same gate the cert-device-binding shadow uses. Measured: one enrollment produced 263 identical lines off a handful of calls. Status of that preview, for the record: the `/beta/deviceManagement/tenantAssociatedDevices` endpoint answers (6 calls, all HTTP 200, `transient=False`), but every result so far is `matched=False` from a single Autopilot **v1** device — which is the correct answer for a device that was never part of a Device Preparation policy. The matching itself is therefore still unproven, and the endpoint remains undocumented in both v1.0 and beta Graph reference, so it is not a basis for enforcement.
+
+* **Update**: `backend/client-cert-tenant-binding.md` — stage 3 verified live (`ea6a375`, gktatooine): 136 requests, all `Match`, device object ~72 s older than the session start, so no enrollment race in that run. Measured Graph cost: **1 call for 136 requests** (30 min positive cache), versus 25 for the per-request Autopilot validator — the positive TTL needs no change. The shadow log is now gated on `ServedFromCache` (one line per real lookup instead of per request); never-cached outcomes still log every time.
+
+* **Update**: `backend/client-cert-tenant-binding.md` — stage 3, the cert-to-device binding: new `IntuneDeviceBindingValidator` resolves the Subject-CN managedDevice id against the tenant's own `deviceManagement/managedDevices` (point-GET, no filter literal), modelled on `CloudPcDeviceValidator` and wired fire-and-forget like the DevPrep shadow so a cold Graph round-trip never enters the agent request path. New GA-only tenant toggle `ValidateIntuneDeviceBinding` (shadow — never touches `deviceValidated`), new optional Graph feature `IntuneDeviceBinding` → `DeviceManagementManagedDevices.Read.All` in `GraphFeatureCatalog` + the customer grant script, and `enrolledAgeSeconds` on every log line so the enrollment race can be measured before this could ever become a gate. Grep marker: `CERT-DEVICE-BINDING-SHADOW`.
+
+* **Update**: `backend/client-cert-tenant-binding.md` — shadow telemetry moved off the dead `LogInformation` path: the `Match` outcome now rides on the request row as the `CertTenantBinding` dimension (`SecurityValidator` → `FunctionContext.Items` → `RequestTelemetryMiddleware`), which is unsampled and already exists per request, so the denominator costs nothing. Non-Match outcomes keep their Warning trace. Post-deploy verification of 249e39bc found zero rows across 32k requests — worker `LogInformation` never reaches App Insights (provider default rule Warning+), making "everything matched" indistinguishable from "never ran". `CertificateValidationResult.FromCache` removed with the sampling path it existed for.
+* **New**: `backend/client-cert-tenant-binding.md` — the agent's mTLS certificate chains to Microsoft's shared Intune roots, so certificate validation alone never proved tenant membership; tenant scoping rested entirely on the (non-secret) device serial in the downstream validators. The Intune MDM leaf carries the Entra tenant id in OID `1.2.840.113556.5.14` (nested OCTET STRING), which is NOT `…5.6` (Intune Account id, a different GUID) and NOT `…5.4` (device id, stored as 16 bare bytes) — all decoded by one shared `MsDeviceCertificateOids.TryParseGuid` now used by agent and backend. Stage 1 ships as shadow only: `CertTenantBinding.Evaluate` (pure) plus `SecurityValidator.ObserveCertTenantBinding` (returns void, swallows its own exceptions, cannot change an authorization outcome), with `Match` sampled via `CertificateValidationResult.FromCache` so the denominator survives without per-request volume. Grep marker for the stage-2 enforcement change: `CERT-TENANT-BINDING-SHADOW`.
+
+## 2026-08-23
+
+* **New**: `backend/telemetry-ingest-shaping.md` — `RequestTelemetryMiddleware` sets `SamplingPercentage=100` on its own item (worker request rows were adaptively sampled, ItemCount 2–5 on weekdays, despite host.json `excludedTypes`), the redundant host HTTP request copy is dropped by a workspace transformation DCR (`infra/appinsights-workspace-transforms.bicep`, timer/queue rows kept), and `StorageDependencyFilterProcessor` now also drops expected storage outcomes (404/412/409, both InProc and HTTP shapes) and successful SignalR REST calls; the host-emitted SignalR binding calls (bulk of the volume, SDK `rdddsc`) are dropped by a second `AppDependencies` flow in the same DCR. Measured ≈ −1.3 GB/week.
+* **Update**: `backend/table-schema-sentinel.md` — "Measuring it": `StartupTelemetryService` emits `BackendStartupMs` (process start → ApplicationStarted) and `BackendTableInitMs` as App Insights custom metrics with version/commit/fullPass dimensions; the MCP server writes one `{"type":"boot","readyMs"}` stderr line per start (query in `.claude/commands/mcp-telemetry.md` §A2).
+* **New**: `backend/table-schema-sentinel.md` — startup table initialization gated by a schema sentinel (SHA-256 over `TableNames.All` in `AdminConfiguration`/`SchemaSentinel`/`tables`): matching sentinel ⇒ zero `CreateTableIfNotExists` calls on a cold start, missing/stale ⇒ one full pass + sentinel rewrite. SessionsIndex startup backfill only after a full pass, `IsSessionIndexEmptyAsync` no longer treats errors as "empty", conditional-insert claim so one scaled-out instance backfills. Daily maintenance runs `IStorageInitializer.EnsureAllAsync` to repair out-of-band table deletions.
+* **Update**: `backend/verdict-calibration.md` — MCP `get_verdict_calibration` response shaping: per-row trend denominators dropped, explicit nulls, `minSharePct` / `top` with an `omitted` report.
+* **Update**: `backend/verdict-calibration.md` — share-regression radar restricted to backend-decided paths; agent-declared/registration paths (customer workflow mix) and derived legacy paths no longer alert, stale episodes re-arm themselves.
+* **Update**: `backend/time-attribution.md`, `backend/device-journeys.md`, `backend/verdict-calibration.md` — the rolling maintenance sweeps (time attribution, device journeys, verdict calibration, calibration-radar discovery) now share ONE projected 35-day cross-tenant Sessions scan per tick (`LoadSweepWindowSessionsAsync` + `MaintenanceSweepSessionProjection`, pinned by `MaintenanceSweepProjectionEquivalenceTests`) instead of four full-table drains; each sweep slices its own window by StartedAt.
+* **New**: `backend/verdict-calibration.md` — the classifier thermometer: every status write now stamps `VerdictPath` (required parameter on `UpdateSessionStatusAsync`; `EnrollmentTimeoutClassifier` returns its rule id), overriding a verdict preserves `PriorStatus`/`PriorVerdictPath`, `VerdictPathDerivation` attributes pre-instrumentation rows read-side (`legacy:*` when ambiguous). New daily aggregate `VerdictCalibrationAggregates` (per-path count/derived/eligible7d/reEnrolled7d/overridden-by-admin|late|other, sweep after the device-journey pass, 180d retention), `GET global/metrics/verdict-calibration`, MCP `get_verdict_calibration`, admin metrics section, and the `VerdictCalibrationRadar` (share / silence-share / r6 evidence-gap episodes in the tracker keyspace `verdictcalibration|`, `VerdictCalibrationDrift` ops event, no tenant bell).
+* **New**: `backend/silent-session-classification.md` — one place for the silent-session verdict: `EnrollmentTimeoutClassifier` rule order incl. the new rule 1c `IsSelfDeployingProvisioned` (self-deploying profile + Device Setup all-succeeded + no explicit failure ⇒ Succeeded reconcile, no grace/AwaitingUser — kiosk tenant aebdce78 audit: 836 finished devices parked AwaitingUser/Incomplete), the sweep stage-1 gates (`TryMarkWhiteGloveAwaitingUserAsync`, new `TryReconcileSelfDeployingAsync`), the ingest callers (max-lifetime, late-telemetry heal, stall probe) and the new admin retro mode `self_deploying_silent` (`GetSelfDeployingSilentSessionsAsync`). Agent companion: `SessionRegistrationHelper` waits up to 15s for a network link and retries 6× (~62s) instead of 5× (~30s) so the reboot relaunch on Wi-Fi no longer exits 7 before the link is back.
+* **New**: `agent/diagnostics-package.md` — the diagnostics ZIP's built-in collection is now ONE catalog in Shared (`DiagnosticsBuiltInSections.All`): the agent iterates it in order and the backend serves the same list to the portal (`GET diagnostics/paths`, MemberRead), so what administrators see is exactly what the agent collects. New conditional sections: RealmJoin client/package/Chocolatey/per-user logs behind the tenant's RealmJoin Watcher toggle (mirrored onto `AgentConfiguration.EnableRealmJoinWatcher` by the merger) and the Device Preparation bootstrapper event log behind the deterministic WDP marker (probe once per build, fail toward Classic); every skip is a manifest line. Built-ins bypass `DiagnosticsPathGuards` by design (reviewed code, `%ProgramData%\RealmJoin` is not allowlisted); caps/reparse/evtx export still apply. `MergeDiagnosticsLogPaths` dedups global ∪ tenant paths. Portal: collapsed read-only catalog + one-line rows in both cards, tenant context dropped the GA-only global fetch.
+* **Update**: `rules/gather-rule-guardrails.md` — `DiagnosticsPathGuards` scope clarified: configured diagnostics paths only, never the built-in catalog.
+* **Update**: `backend/tenant-activation-welcome-mail.md` — new "Template overrides" section: Global Admins can replace the welcome/farewell HTML in the portal (Settings → Email Templates); `EmailTemplateService` resolves override-or-built-in per send (PreviewConfig table, partition `EmailTemplates`, 5-min cache, `{{domainName}}` placeholder, 30k limit, fail-soft send path), GA endpoints `global/email-templates/{kind}` (+`/test` to the caller's tenant contact address). Also: the mail header is image-free (CSS-drawn brand mark, gradient stripes and clip-path edge as progressive enhancement).
+
+## 2026-08-22
+
+* **Update**: `backend/tenant-activation-welcome-mail.md` — new "Mail transport" section: transactional mail now goes through the provider-neutral `EmailService` (`IEmailService` + `IOffboardFarewellEmailSender`) with the provider confined to one private transport method and the `Email:*` settings (`ApiKey`, `Endpoint`, `FromAddress`, `FromName`); current provider Mailchimp Transactional (Mandrill) replacing Resend (NuGet dropped, typed `HttpClient` + `ResiliencePolicies.Notification`). Result-array semantics (`sent`/`queued`/`scheduled` ok, `rejected`/`invalid` warn), open/click tracking explicitly off because the privacy/trust claim depends on it.
+
+* **New**: `backend/plan-downgrade-retention-grace.md` — plan downgrade policy: every Pro entitlement gates read-time and reversibly on downgrade ("gate, don't destroy"), except retention, which now gets a 30-day grace (`FeatureEntitlementCatalog.RetentionDowngradeGraceDays`) before the Community cap starts hard-deleting the 90–365-day band. Anchor model: `ProDowngradedUtc` stamped/cleared by the plan endpoint's pure `ApplyPlanChanges` core on EFFECTIVE-edition transitions (covers explicitly ended trials; planTier downgrade under an active trial deliberately doesn't stamp), trial expiry anchors read-time via `TrialExpiresUtc`. New Warning ops events `TenantPlanDowngraded` (PATCH handler) and `TenantRetentionGraceExpiring`/`TenantRetentionGraceEnded` (TrialExpirySweep window mechanics, only when stored retention exceeds the Community cap). Field is patch-denied + revert-protected; retention WRITE cap deliberately ignores the grace.
+
+## 2026-08-21
+
+* **New**: `agent/do-group-id-auto-set.md` — optional DO peering-group seed (`EnableDoGroupIdAutoSet`, default off, ConfigVersion 40): `DoGroupIdService` derives a deterministic GUID from the default gateway's IPv4 + SendARP MAC in RealmJoin's exact byte layout (cross-product peering) and writes `DOGroupId` in the 64-bit GPO Policies store with readback verification. Conservative by design: no random-GUID fallback (skip on missing gateway/MAC), `DOGroupIdSource`/MDM-managed values/foreign GPO values always win (skip reasons in the `do_group_id_auto_set` event), own stale values are recognized via the `written:<guid>` StartupEventGate fingerprint and updated after a gateway change. Gateway heuristic extracted into the shared `NetworkInterfaceLocator` (dedup of NetworkChangeDetector + DeviceInfoCollector copies).
+
+* **New**: `agent/system-timeline-watcher.md` — clock-step and sleep-episode ground truth from the System event log: one `EventLogWatcher` (Kernel-General 1, Power-Troubleshooter 1, Kernel-Power 507; 506 deliberately unconsumed) emits `system_clock_changed` (oldTime/newTime/signed timeDeltaMs/reason/process; 2 s micro-slew floor, ≥5 min = Warning+immediate) and `system_sleep_episode` (kind sleep/hibernate/modern_standby, authoritative `enteredAt`/`exitedAt` payload instants, 60 s Modern-Standby floor). WindowsUpdateTracker-style backfill (24 h default, `system-timeline-watermark.json`) recovers pre-agent records; ConfigVersion 39 (`Collectors.EnableSystemTimelineWatcher`). Consumers: TimeJumpBadge cause `clock-set` (ground truth beats inference), SessionInfoCard standby note next to the unchanged wall-clock duration, `SleepSpan`s in time attribution (AttributionVersion 3, RebootSpan clone), and ANALYZE-DEV-012 (info, single, ≥5 min episode; deliberately the only new rule — clock issues stay with DEV-008).
+
+* **New**: `agent/power-state-watcher.md` — live AC/battery observation during enrollment: `PowerStateWatcherHost` subscribes to the WMI push `Win32_PowerManagementEvent EventCode 10` (no polling; re-probes `GetSystemPowerStatus` per push, 5 s trailing-edge debounce, never armed on battery-less devices, `Collectors.EnablePowerStateWatcher` kill-switch, ConfigVersion 38). The pure `PowerStateTransitionTracker` emits `power_state_change` with `transition` = ac_to_battery (Warning, immediate) / battery_to_ac (Info) / threshold_crossed at 50/30/15% (each level latched once per lifetime, lowest-crossed-only on jumps, baseline-below-level covered, emission cap 20). Classified non-activity on both sides (SignalActivityClassifier + IsPeriodicOrStallEvent). New analyze rules ANALYZE-DEV-009 (thresholdPercent=15, high) and ANALYZE-DEV-010 (transition=ac_to_battery, warning), both with `on_event:power_state_change` interim triggers and deliberately single-required-condition (event_data conditions have no same-instance join).
+
+* **Update**: `rules/rule-id-namespace.md` — the export→paste round-trip is no longer lossy: the JSON editors now map rule-shaped exports into the form (`gatherRuleToForm` unflattens the nested gather `parameters` object, analyze `jsonToForm` maps `evaluateOn` onto the eval checkboxes; `tags` and the effective `markSessionAsFailed` carry into the created rule). Both editors still accept the serialized-form shape; edit-mode pastes merge, with an explicit `parameters`/`evaluateOn` winning over stale flat fields.
+
+* **New**: `rules/rule-id-namespace.md` — rule identity model: human-readable `ruleId` strings (no GUIDs), tenant isolation via Table Storage partitioning (`global` = built-in/community, tenantId = custom), the reserved built-in namespace from `RuleIdPolicy`, and the four collision guards: catalog-only global `RuleStats` aggregate (same-ID custom rules of unrelated tenants no longer sum into one `global_{ruleId}` row), combine.js duplicate/namespace fail, GitHub-reseed rejection of non-reserved IDs into the global partition, and the namespace gate on the cross-tenant RuleState GC.
+
+* **New**: `backend/app-install-duration-attempt.md` — attempt-scoped app install durations: `DurationSeconds` = status-defining (last) attempt anchored on the new max-folded `LastAttemptStartedAt` (StartedAt stays the earliest-wins window/version-ordering key; legacy rows without the anchor keep the span fallback); `InstallPassCount` with replay-guarded additive fold; weaker-terminal guard (completed-with-Skipped never overrides Installed/Error, in-batch and cross-batch); attempt-scoped `DownloadDurationSeconds` pairing; the version-regression radar's both-sides cutover gate; time attribution counts the union of per-pass active segments (occupancy merges segments, hulls stay for display/what-if); agent payload timing re-arms both endpoints on terminal→active. No backfill — pre-cutover rows keep span semantics.
+
+* **Update**: `agent/decision-engine.md` — activity-based RealmJoin timeout extension (report 55e6afd61c9d: a large RJ package catalog outlived the 60-min window mid-install — the timer arms at RJ-agent-MSI detection, so the first deployment had effectively ~44 min). When the `RealmJoinTimeout` deadline fires with `LastDeploymentPhase` 100/101 and deployment activity (phase change or package observation, persisted in `RealmJoinFacts.LastActivityUtc`; the detection-time phase capture deliberately excluded) inside the last 60 min, the deadline re-arms to `lastActivity + 60 min` (Info event `realmjoin_timeout_extended`), clamped at detection + 4 h. `realmjoin_timeout` now carries `reason` = `hard_timeout` / `inactivity` / `absolute_cap`; a fire of a superseded deadline incarnation dead-ends. Idle detection and phase-200/210 sessions keep the original 60-min behavior.
+
+* **New**: `backend/send-time-frame-separation.md` — P14: the agent stamps one device-clock send timestamp per upload attempt (`X-Send-Time-Utc`), the ingest function server-stamps it as `SentAt` on every event of the request. `SentAt − OccurredUtc` is pure spool delay, `ReceivedAt − SentAt` is network + device-vs-server clock offset — the two were indistinguishable before and had to be separated statistically. The `clock_skew` condition measures SentAt-carrying batches directly (spool-immune, no spread cap, IME-only sessions become measurable; evidence carries `sentAtBatchCount`), legacy batches keep the median path; the CMTrace tripwire deliberately stays on its differential math (common-mode clock offset cancels there).
+
+## 2026-08-20
+
+* **Update**: `agent/cmtrace-time-resolution.md` — new "Backend regression tripwire" section: the P6 split. Operator side: `CmTraceSkewTripwire` piggybacks on the terminal counter reconcile's partition scan (`Δ = ReceivedAt − OccurredUtc` per source, 15-min grid + 2-min residual, ≥20 samples / ≥3 distinct batches per side, bias-dominated sessions suppressed, `measuredWriterOffsetMinutes` never consulted) and emits the `CmTraceTimeSkewRegression` ops event — goal state: never fires; kill switch `CmTraceSkewTripwireDisabled`. Customer side: new `clock_skew` analyze condition source (`skewMetric: clock_jump | sustained_offset`, threshold in seconds, batch-median frames with spool-spread filter, plateau step detection, end-state persistence, IME-derived events excluded) behind the new built-in `ANALYZE-DEV-008` (300 s = the Kerberos/Entra 5-minute skew boundary) — the during-enrollment complement of ANALYZE-DEV-007's one-shot NTP check. P5 (agent-side observability event) is subsumed by the tripwire.
+
+* **New**: `agent/cmtrace-time-resolution.md` — the era-aware answer to the CMTrace timezone skew: a bias-less line read in a provably fresh pass anchors its own UTC offset against the agent clock (15-minute grid, 2-minute residual), so interleaved writer eras in one file resolve line by line; everything not provably fresh keeps the uniform reader-zone fallback and says so via `sourceOffsetOrigin`. Freshness is a per-file `LastCheckedUtc` stamped on every poll look (empty first sights included) with a 30-second window, never restored across restarts. Replaces the reverted per-file offset application (04b1a7c6); the per-file measurement stays observational, now with the anchor timestamp logged as a tripwire for the still-unexplained e9753578 label/anchor crossing.
+
+* **Update**: `agent/post-reboot-completion-recovery.md` — retitled to "ESP Completion Starvation — the sits-d Cloud-PC complex" and reframed on the evidence: the reboot was a red herring. The five stuck Cloud PCs carried `SkipUserStatusPage=True` (read 10+ times across three agent processes, `True` every time) and Windows honoured it — no user ESP page, hence no Shell-Core 62407 and no AccountSetup provisioning registry, verified over a six-hour uninterrupted post-reboot run with the watcher armed. Arm B of `ShouldTransitionToAwaitingHello` was open from the bootstrap onward, but every evaluation site hangs off a signal a skip-user flow cannot produce, and the `AdvisoryCompletion` backstop arms exclusively from an `EspExiting` signal — an open gate nobody knocks on. Fix: `HandleImeUserSessionCompletedV1` accepts the observed skip in place of the final-exit evidence (`skipUserExitEquivalent`; anchor + genuine IME completion + real-user desktop stay mandatory, WDP excluded). The knock deliberately lives on the IME edge, not desktop arrival — ordering-robust against Fix 10's AccountSetup bounce-back and semantically "user-phase work finished" rather than mid-install. `ClassicSkipUserEspUserSessionCompletionTests` replays the real 8110e262 ordering end to end. Docs and comments no longer claim an ESP-exit recovery that does not exist (stray duplicate summary in `ShellCoreTracker`, `ImeLogHost` restore-callback comment); the residual `SkipUser=false` exit-in-downtime gap is named honestly and surfaced by `ANALYZE-ESP-005` via `session_stalled` instead of being patched with an unorderable replay.
+
+## 2026-08-19
+
+* **New**: `agent/post-reboot-completion-recovery.md` — a forced mid-ESP reboot (DeviceGuard/DmaGuard) used to cost the session its AccountSetup completion permanently. Two defects: `ShellCoreTracker.BackfillRecentEspExitEvents()` existed but had no caller, so every agent restart dropped an ESP exit (62407) written while it was down; and the user-apps-settled synthesis was edge-triggered on `EspExited` only, so apps settling afterwards never re-opened the gate. `EspAndHelloHost.Start()` now backfills with a lookback sized to the downtime (`previousExit=reboot_kill` → since `LastBootUtc`, clamped to 360 min), and `ReevaluateUserAppsSettledSynthesis()` is chained into `ImeLogTracker.OnAppStateChanged`. No new completion path — the gate conditions are unchanged. Evidence: sits-d Cloud PCs, five `Incomplete` sessions on healthy devices, two of them at `138/138 apps, 0 failed`. Hardened over two review rounds: the remembered edge must be a **live** exit that is **confirmed** post-AccountSetup (a replay carries no evidence of its own position — Shell-Core writes the same `CommercialOOBE_ESPProgress_Page_Exiting` for the intermediate and the final exit, and the registry check reads *now*, not the event's time); the replay hands over the **newest** exit rather than the oldest; the replay is narrowed to the Hello-wizard start (62404) alone — a conservative fact that can only make the agent wait longer. A replayed ESP exit is never re-raised at all: Windows writes the identical description for the intermediate and the final exit, the reducer orders exits by ingest ordinal (fresher than reality for a replay) and `HandleEspExitingV1` passes `espFinalExitInFlight: true` for every arriving exit, so arm C of `ShouldTransitionToAwaitingHello` would open on a historic handoff once the restored state carries AccountSetupEntered + IME user session + desktop. A replayed ESP failure is likewise dropped (it could fail a session that recovered). Skipped records are reported as an `agent_trace`. The window is **measured** from the previous run's last known liveness (snapshot mtime, widened by `LastBootUtc`) instead of a constant — the scheduled task has a BootTrigger only and no restart-on-failure, so a crashed agent returns hours later and five minutes would lose the exit every time. On `first_run` the replay stays off, leaving the happy path untouched.
+
+* **Update**: `rules/analyze-rule-triggers.md` — `on_event:session_stalled` documented as an established interim trigger for the never-terminal stuck session (one emission per session, no throttle needed). `ANALYZE-ESP-005` carries it: both its conditions are monotonic and it has no terminal precondition, and it fires at confidence 95 on the sits-d stalled stream. `ANALYZE-APP-015` deliberately does NOT — it is the worked example of the terminal-precondition trap (lint 1) — and `ANALYZE-ESP-001` does not either, because its `phase_duration` gate on a still-open phase is unverified mid-run. New `ANALYZE-APP-016` ("Required Apps Never Started — ESP Apps Gate Starved") turns the existing `app_install_starved` events into a customer-facing finding and, unlike `ANALYZE-APP-015`, fires even when the session succeeded — session `3b9291aa` was recorded `Succeeded` with 99 required apps that never started installing.
+
+* **New**: `script-publishing.md` — the customer script publishing chain. `.github/scripts/Publish-BootstrapScripts.ps1` becomes the single owner (dev render, version-bump guard, uploads, version oracles, alias verification), called both by the new `publish-scripts.yml` (push to `main` on `scripts/Bootstrap/**` and `scripts/CustomerSetup/**`) and by the `publish_as_stable` branch of `build-agent.yml`. Script publishing no longer waits for an agent release. Blobs are published in a deterministic CRLF/UTF-8-no-BOM form so byte comparisons do not depend on the checkout; the Pester + ASCII gates move into the reusable `bootstrap-script-gates.yml` and block the upload; `AdminConfiguration.LatestBootstrapV2ScriptVersion` now has exactly one writer. The version-bump guard compares a code fingerprint (PowerShell token stream without comments, newlines and line continuations), so only behaviour changes require a `$ScriptVersion` bump — comment and formatting changes publish with a warning.
+
 ## 2026-08-18

+* **New**: `agent/wdp-scenario-gates.md` — WDP scenario gates (afee7ae0 audit): deterministic ExecutionContext marker as the only gate key (fail-toward-Classic), suppressed Autopilot/ESP-only emissions and hosts (autopilot_profile*/ZTD probe, esp_config unknown null-gate, EspPolicyProviderStallHost, ProvisioningStatusTracker, ModernDeployment noise IDs 100/417/418/1005 + error-backfill skip, starved sweep), and the WDP completion model (High-confidence v2 seed via `enrollmentTypeDeterministic`, desktop-based arm D, 30-min `device_prep_completion` backstop, parked-tripwire WDP branch).
+
+* **Update**: `backend/time-attribution.md` — AttributionVersion 1 → 2: new duration-critical quality flag `PriorEnrollmentResidue` (fires on `historic_ime_replay_detected`; a re-enrollment without wipe pulls the phase anchors ahead of the real ESP page, so the segments are excluded from fleet stats; `registry_app_baseline` successes deliberately not a trigger — by-design normal for WDP). Added the quality-flags section.
+* **Update**: `agent/logs-and-persistence.md`, `agent/overview.md`, `agent/gather-rule-debug-log.md` — log files renamed to unified kebab-case: `agent.log` (date rotation dropped; size segments `agent-NNN.log`), `bootstrap-script.log` (was `bootstrap_agent.log`), `bootstrap-msi.log` (was `msi-bootstrap.log`), `crash-*.log`, `gather-rules-debug.log`, `ime-pattern-matches.log`. Old names still appear in archives from pre-rename agents.
 * **New**: `agent/registry-app-state-pillar.md` — the registry second pillar for IME app state (audit follow-up): snapshot-and-diff watcher on `HKLM\...\IntuneManagementExtension` (Win32Apps / EspTrackingWin32Apps / StatusServiceReports), `registry_app_state` + `app_state_reconciliation` events, silent startup baseline, WDP reuse notes.

 ## 2026-08-17
@@ -8,7 +8,7 @@ tags:
  - oauth
  - entra-id
  - security
-timestamp: 2026-07-11T10:59:31+02:00
+timestamp: 2026-08-29T08:45:00+02:00
 ---

 # MCP OAuth Flow — Who Authenticates Where
@@ -41,9 +41,12 @@ The two identities never mix:
   in the vendor's backend, not on the user's machine.
 2. **MCP server** (Container App) — acts as a stateless **OAuth proxy /
   authorization-server façade** in front of Entra ID. It is *not* an IdP:
-   it registers clients dynamically (RFC 7591, HMAC-signed stateless
-   `client_id`), enforces the redirect-URI allowlist and PKCE, and exchanges
-   codes at Entra using its confidential client secret.
+   it establishes the client's identity statelessly — a Client ID Metadata
+   Document (MCP spec 2026-07-28: the `client_id` is an HTTPS URL the server
+   fetches and validates) or, for older clients, dynamic registration
+   (RFC 7591, HMAC-signed stateless `client_id`) — enforces the redirect-URI
+   allowlist and PKCE, and exchanges codes at Entra using its confidential
+   client secret. See [Protocol Eras & CIMD](mcp/protocol-eras-and-cimd.md).
 3. **Entra ID** — the real identity provider. This is where `adm.luke` lives.

 ## Full sequence
@@ -54,9 +57,10 @@ Claude Desktop        Browser (user's           MCP server              Entra ID
     │                      │                        │                      │
 1.  │─ POST /mcp ──────────┼───────────────────────▶│ 401 + WWW-Auth       │
 2.  │─ Discovery ──────────┼───────────────────────▶│ RFC 9728/8414 docs   │
- 3.  │─ POST /oauth/register┼───────────────────────▶│ client_id (HMAC-     │
-     │                      │                        │ signed, embeds the   │
-     │                      │                        │ registered callback) │
+ 3.  │─ client identity ────┼───────────────────────▶│ CIMD: client_id is a │
+     │   (CIMD, or legacy   │                        │ URL, doc fetched at  │
+     │    POST /oauth/      │                        │ /authorize; DCR:     │
+     │    register)         │                        │ HMAC-signed client_id│
     │                      │                        │                      │
 4.  │─ opens browser ─────▶│─ GET /oauth/authorize ▶│─ 302 to Entra ──────▶│
     │                      │  (PKCE challenge)      │  app-reg client_id,  │
@@ -0,0 +1,129 @@
+---
+type: Concept
+title: MCP Protocol Eras & Client ID Metadata Documents
+description: How the MCP server serves the 2026-07-28 stateless revision and 2025-era clients from one per-request factory, why the legacy leg is hand-wired (JSON + gzip), the cache-hint and capability contract, and the CIMD client-registration path next to the deprecated dynamic registration.
+resource: /src/McpServer/autopilot-monitor-mcp/src/mcp-http.ts
+tags:
+  - mcp
+  - protocol
+  - oauth
+  - cimd
+  - security
+timestamp: 2026-08-29T08:40:00+02:00
+---
+
+# MCP Protocol Eras & Client ID Metadata Documents
+
+**Status:** Concept · **Owner:** MCP Server · **Code:** [`mcp-http.ts`](../../src/McpServer/autopilot-monitor-mcp/src/mcp-http.ts), [`mcp-server-factory.ts`](../../src/McpServer/autopilot-monitor-mcp/src/mcp-server-factory.ts), [`cimd.ts`](../../src/McpServer/autopilot-monitor-mcp/src/cimd.ts), [`oauth.ts`](../../src/McpServer/autopilot-monitor-mcp/src/oauth.ts)
+
+# Schema
+
+## The two eras
+
+MCP revision **2026-07-28** turned the protocol into a stateless request/response
+protocol: no `initialize` handshake, no `Mcp-Session-Id`, every request carries its
+protocol version, client identity and capabilities in `_meta`, capabilities and
+instructions are fetched with `server/discover`, list results carry `ttlMs` /
+`cacheScope`, and `Mcp-Method` / `Mcp-Name` HTTP headers let gateways route without
+parsing bodies. Roots, Sampling, Logging and the HTTP+SSE transport are deprecated
+(twelve-month window); Dynamic Client Registration is deprecated in favour of Client
+ID Metadata Documents.
+
+The server was already stateless by design (scale-to-zero Container App, no
+server→client traffic), so the revision cost no architecture — only wiring:
+
+| Concern | 2026-07-28 ("modern") | 2025-era ("legacy") |
+| --- | --- | --- |
+| Routing decision | `isLegacyRequest()` from the SDK — the exact classifier `createMcpHandler` uses internally | same predicate, inverse |
+| Serving | `createMcpHandler(factory, { legacy: 'reject', responseMode: 'json' })` via `toNodeHandler` | fresh `NodeStreamableHTTPServerTransport({ sessionIdGenerator: undefined, enableJsonResponse: true })` per POST |
+| Response shape | single `application/json` body | single `application/json` body |
+| Instructions | `server/discover` result | `initialize` result |
+| Cache fields | `ttlMs` + `cacheScope` stamped by the SDK from `cacheHints` | none (2025 codec has no cache path) |
+
+Both legs are fed by **one** factory (`createServerForCaller`), so the tool catalog,
+resource set, prompts and instructions can never drift between eras — the
+`mcp-http.test.ts` suite pins that a Global Admin and a plain tenant user see the
+same catalog on either path.
+
+## Why the legacy leg is hand-wired
+
+`createMcpHandler`'s built-in `legacy: 'stateless'` fallback constructs its transport
+with only `sessionIdGenerator: undefined`, i.e. it answers every 2025 client with an
+SSE frame. Every production client today (Claude Code, Claude.ai, VS Code) is a 2025
+client, and their large tool results are gzipped by the compression middleware only
+because the response is a plain JSON body (measured 5–30×). Routing on the SDK's own
+predicate in user land keeps that behaviour while still running the 2026 path through
+the SDK entry unchanged — no re-implementation of the classification, no second
+catalog.
+
+## Capability and cache contract
+
+* `capabilities` are declared explicitly with `listChanged: false` for tools,
+  resources and prompts. The SDK's default (`?? true`) would advertise a
+  notification a per-request server can never emit.
+* `cacheHints`: `server/discover`, `tools/list`, `prompts/list`, `resources/list`,
+  `resources/templates/list` → `{ ttlMs: 300_000, cacheScope: 'private' }`;
+  `resources/read` → `{ ttlMs: 3_600_000, cacheScope: 'private' }`. **Never
+  `public`**: the catalog and the instructions are role-dependent (Global Admin /
+  Global Reader / delegated MSP / tenant user), so a shared cache would leak one
+  caller's surface to another. Five minutes is the bound on how long a role change
+  can go unnoticed by a caching client; resources are static per deployment.
+* No Roots / Sampling / Logging / elicitation / subscriptions are used anywhere, so
+  nothing on the deprecation list has to be migrated.
+
+## Client registration: CIMD first, DCR as fallback
+
+The authorization-server metadata now advertises
+`client_id_metadata_document_supported: true` next to the (deprecated)
+`registration_endpoint`. Clients following the spec's priority order use a
+**Client ID Metadata Document**: their `client_id` *is* an HTTPS URL that serves a
+JSON document (`client_id`, `client_name`, `redirect_uris`, …). `oauth.ts` resolves
+every `client_id` through one helper: an HTTPS URL goes to `cimd.ts`, anything else
+must be one of our HMAC-signed dynamic-registration tokens. Both yield the same shape
+(`redirectUris`), and the rest of the authorize/callback logic is unchanged.
+
+What the document decides — and what it does not:
+
+* It only asserts **which** redirect URIs the client claims. The requested
+  `redirect_uri` must still pass the host/path allowlist that gates dynamic
+  registration (`isAllowedRedirectUri`), checked *before* the document is fetched. A
+  self-hosted document cannot widen the destinations an authorization code may be
+  sent to. Loopback remains allowed for every client (RFC 8252 §7.3);
+  `application_type: "native"` is informational.
+* Fetching a caller-chosen URL is an SSRF surface, so the fetch is: HTTPS only, path
+  component required, no fragment/userinfo, no loopback or IP-literal host, every
+  resolved address must be public (RFC 1918/4193/3927/6598, CGNAT, multicast,
+  IPv4-mapped all refused — checked before any request leaves), `redirect: 'error'`,
+  5 s budget, 16 KB body cap (declared *and* streamed), JSON media type required.
+  Nothing from the response reaches the caller beyond an OAuth error code.
+* The document's `client_id` must equal the URL by simple string comparison — no
+  normalization, per the draft. `redirect_uris` is bounded exactly like a dynamic
+  registration (`oauth-limits.ts`). A missing `client_name` falls back to the host:
+  it only ever reaches a log line, and failing a login over a label would be wrong.
+* Cache: positive entries live for the document's `Cache-Control: max-age`, clamped
+  to 10–60 min so the `/oauth/callback` re-check within the 10-min signed-state
+  window is a cache hit on the same replica; rejections are cached for 60 s; the map
+  is bounded to 256 entries.
+
+RFC 9207 `iss` (already emitted since 2026-07-29) completes the authorization side
+of the 2026-07-28 revision.
+
+# Examples
+
+* A 2026 client: `POST /mcp` with `_meta["io.modelcontextprotocol/protocolVersion"] = "2026-07-28"`
+  and `Mcp-Method: tools/list` → `{ tools: [...], ttlMs: 300000, cacheScope: "private", _meta: { "io.modelcontextprotocol/serverInfo": { name: "Autopilot-Monitor", version: "1.6.<build>" } } }`.
+* A 2025 client: `POST /mcp` `initialize` → `application/json` body with
+  `protocolVersion: "2025-11-25"` and the role-tailored `instructions`; no
+  `Mcp-Session-Id` header.
+* `GET /oauth/authorize?client_id=https://app.example.test/oauth/client.json&redirect_uri=http://127.0.0.1:49152/callback&code_challenge=…` →
+  document fetched (or served from cache) → 302 to Entra. `client_id=https://10.0.0.8/x` → `400 invalid_client`
+  without any outbound request.
+
+# Citations
+
+* MCP spec 2026-07-28 — https://blog.modelcontextprotocol.io/posts/2026-07-28/ ; authorization / client registration:
+  https://modelcontextprotocol.io/specification/2026-07-28/basic/authorization/client-registration
+* TypeScript SDK v2 (`@modelcontextprotocol/server` 2.0.0) — `createMcpHandler`, `isLegacyRequest`, `cacheHints`.
+* draft-ietf-oauth-client-id-metadata-document-00 §6 (security considerations, SSRF).
+* Tests: `src/__tests__/mcp-http.test.ts`, `src/__tests__/cimd.test.ts`, `src/__tests__/oauth-cimd.test.ts`.
+* Related: [MCP OAuth Flow](../mcp-oauth-flow.md), [MCP Docs Corpus](docs-corpus.md).
@@ -98,9 +98,13 @@ Interim evaluation changes what a rule's conditions mean mid-flight. Three new l

 # Application to the Motivating Cases

- WG battery rule (sits-d): `evaluateOn: ["enrollment_end", "whiteglove_sealed"]` — technician gets the channel alert at the bench; Part-2 terminal pass finalizes or resolves the finding.
+- WG battery rule (sits-d): shipped 2026-08-21 as ANALYZE-DEV-009 (battery below 15% while on battery) and ANALYZE-DEV-010 (AC→battery switch), both `evaluateOn: ["enrollment_end", "whiteglove_sealed", "on_event:power_state_change"]` on the live power watcher's `power_state_change` events (see `../agent/power-state-watcher.md`) — technician gets the channel alert at the bench; the terminal pass finalizes the finding. Both are deliberately single-required-condition rules: `event_data` conditions scan events independently (no same-instance join), so DEV-009 matches the agent-stamped `thresholdPercent` and DEV-010 matches `transition`.
 - Hybrid-affinity stuck (esa): ANALYZE-ID-004 gets `evaluateOn: ["enrollment_end", "on_event:hybrid_login_pending"]` — the second overdue-login event (threshold 65) produces a live finding on the still-InProgress session. ANALYZE-APP-015 stays `enrollment_end`-only until its conditions are hardened (lint 1).

+- Stuck after a forced mid-ESP reboot (sits-d Cloud PCs, 2026-08-19): `on_event:session_stalled` is the established trigger for the never-terminal stuck session. The agent emits `session_stalled` exactly once per session (60-minute stall probe), so the trigger is rare by construction and needs no throttle. Five Cloud PCs sat at `InProgress` with **zero findings** for hours — a mid-ESP reboot had killed the agent in `Stage=EspAccountSetup` — before the max-lifetime watchdog eventually terminalised them as `Incomplete`. ANALYZE-ESP-005 carries the trigger and fires on that stream at confidence 95 (verified against session `8110e262`): both its conditions (`mdm_policy_reboot_required.firstRebootUri` exists, `system_reboot_detected` count ≥ 1) are **monotonic** and it has no terminal preconditions, so lint 1 does not apply. ANALYZE-APP-016 is interim-safe for the same reason (`app_install_starved` count ≥ 1 only ever grows).
+
+  Two rules were considered and deliberately **not** given the trigger: ANALYZE-APP-015 is the worked example of lint 1 above and stays `enrollment_end`-only; ANALYZE-ESP-001 gates on `phase_duration` of a phase that is still open mid-run, and that evaluation is not pinned by a test — an unverified trigger is not worth a possible false positive on every slow DeviceSetup.
+
 # Product Decisions (settled 2026-08-14)

 1. Notify-on-resolve (a "finding healed" message)? **No** (v1) — resolution is visible in UI/MCP.
@@ -31,6 +31,12 @@ item in `AutopilotMonitor.Agent.V2.Core.csproj`) and regenerated into the portal
 | `IsCommandAllowed` | `allowedCommands` | **exact** match, trimmed — never prefix |
 | `IsEventLogChannelAllowed` | `eventLogChannels` | prefix, boundary `/` or end |

+`DiagnosticsPathGuards.IsDiagnosticsPathAllowed` (allowlist `diagnosticsPathPrefixes`, a C#
+literal mirrored in the JSON) applies the same hard blocks and the same user-profile
+exception to **admin-configured diagnostics paths** only. The diagnostics package's built-in
+sections are reviewed code and never pass through it — see
+[Diagnostics Package](../agent/diagnostics-package.md).
+
 **Hard blocks live in code, not in the JSON**, so a parse error cannot lift them — on a
 parse failure the allowlists fall back to empty and everything is blocked (fail-closed),
 but the hard blocks must hold regardless of configuration:
@@ -0,0 +1,47 @@
+---
+type: concept
+title: Rule ID Namespace & Collision Guards
+description: How gather/analyze rule identity is scoped (tenant partition vs global partition), why there are no GUIDs, which collisions are possible, and the guards that keep the reserved built-in namespace and the global RuleStats aggregate clean.
+resource: backend, rules
+tags: [rules, ruleid, namespace, collision, rulestats, tenant-isolation]
+timestamp: 2026-08-21
+---
+
+# Schema
+
+Rule identity is the human-readable `ruleId` string — there are no GUIDs, deliberately: the ID appears in logs, mails, notifications, RuleResults, the agent config payload, and docs, and tenant isolation is provided by Table Storage partitioning instead.
+
+| Store | PartitionKey | RowKey | Content |
+|---|---|---|---|
+| `GatherRules` / `AnalyzeRules` | `"global"` | ruleId | Built-in + community rules (shared, all tenants) |
+| `GatherRules` / `AnalyzeRules` | tenantId | ruleId | Custom rules (visible only to that tenant) |
+| `RuleStates` | tenantId | ruleId | Per-tenant enable/notify overrides — built-in/community rules ONLY (custom rules fold state into their own row) |
+| `RuleStats` | date | `{tenantId}_{ruleId}` and `global_{ruleId}` | Daily fire/eval telemetry; the global row is catalog-only (see guards) |
+
+Namespace split (`RuleIdPolicy.cs`, shared model):
+
+- **Reserved built-in namespace**: `(ANALYZE|GATHER)-<CATEGORY>-<NUMBER>` with `CATEGORY != CUSTOM`, case-insensitive, including currently unused numbers (gaps = retired rules that may return).
+- **Tenant namespace**: everything else — `ANALYZE-CUSTOM-NNN` (portal suggestion), `-CUSTOM` suffixes, org prefixes (`CONTOSO-WIFI-001`), freeform.
+
+# Collision model
+
+- **Custom vs built-in**: impossible via API — `CreateRuleAsync`/`UpdateRuleAsync` reject reserved IDs (409) and check existence against `global` ∪ own tenant partition. Legacy debris is neutralized at merge time: global wins, tenant copy dropped with a warning (pinned by `RuleMergeCollisionGuardTests`, motivated by the 5ca2b350 duplicate-key incident).
+- **Custom vs custom across tenants**: allowed and harmless — separate partitions, separate evaluation, separate RuleResults/tenant stats. Two tenants both using `ANALYZE-CUSTOM-101` never interact.
+- **JSON copy between tenants** (export → paste into create editor): goes through the same create path, so an ID already taken in the receiving tenant surfaces as 409 — the user renames. There is no bulk import endpoint. The JSON editors accept both shapes — a rule export and the serialized form — via `gatherRuleToForm` / `jsonToForm` (web `types.ts` of each rules page): nested gather `parameters` are unflattened, analyze `evaluateOn` maps onto the eval checkboxes, and `tags` plus the effective `markSessionAsFailed` survive the import.
+
+# Guards (all enforced, 2026-08-21)
+
+1. **Global RuleStats aggregate is catalog-only.** The `global_{ruleId}` row would otherwise sum same-ID custom rules of unrelated tenants (title/severity last-writer-wins). Analyze gates on `rule.IsBuiltIn || rule.IsCommunity` (`AnalyzeOnEnrollmentEndHandler`), gather gates on `RuleIdPolicy.IsReservedBuiltInId` (`EventIngestProcessor.RuleStats`) because agent events carry no flag — valid because custom rules can never occupy the reserved pattern.
+2. **Catalog build fails on namespace violations.** `rules/scripts/combine.js` rejects duplicate IDs (case-insensitive) and any gather/analyze built-in outside the reserved pattern; `BuiltInRuleCatalogPolicyTests` pins the same invariants on the embedded resource actually deployed.
+3. **GitHub reseed rejects non-reserved IDs** before writing to the `global` partition (`ReseedFromGitHubFunction`) — a seeded `*-CUSTOM-*` rule would silently shadow every tenant's same-ID custom rule at merge time.
+4. **Cross-tenant RuleState GC is namespace-gated.** `DeleteRuleStatesForRuleIdAcrossTenantsAsync` deletes by bare RowKey across all partitions; it now refuses non-reserved IDs with `failed=-1` (callers then skip the global catalog delete, same contract as enumeration failure).
+
+Invariant chain: schema pattern + combine.js + reseed guard ⇒ the `global` partition only ever contains reserved-pattern IDs ⇒ the pattern is a safe built-in/custom discriminator everywhere no `IsBuiltIn` flag is available.
+
+# Citations
+
+- `src/Shared/AutopilotMonitor.Shared/Models/Rules/RuleIdPolicy.cs` — reserved pattern + rationale
+- `src/Backend/AutopilotMonitor.Functions/Services/AnalyzeRuleService.cs`, `GatherRuleService.cs` — create/update guards, merge collision guard
+- `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.Rules.cs` — key schemes, cross-tenant GC guard
+- `src/Backend/AutopilotMonitor.Functions.Tests/BuiltInRuleCatalogPolicyTests.cs`, `RuleIdReservationTests.cs`, `RuleMergeCollisionGuardTests.cs`
+- `rules/scripts/combine.js` — build-time namespace/duplicate guard
@@ -0,0 +1,137 @@
+---
+type: Concept
+title: Customer Script Publishing — download.autopilotmonitor.com/agent/
+description: How the customer-facing PowerShell scripts reach the download alias, why publishing is decoupled from agent releases, and the guards that keep the published copy, the version badge and the portal's version oracle in agreement.
+resource: /.github/scripts/Publish-BootstrapScripts.ps1
+tags:
+  - build
+  - ci
+  - release
+  - bootstrap
+  - download-alias
+timestamp: 2026-08-19T00:00:00+02:00
+---
+
+# Overview
+
+Four PowerShell scripts are served to customers from `https://download.autopilotmonitor.com/agent/`:
+
+| Blob | Source | Consumed by |
+| --- | --- | --- |
+| `Install-AutopilotMonitor.ps1` | `scripts/Bootstrap/Install-AutopilotMonitor.ps1` | Intune platform script (customer uploads a copy); downloaded live on every device by the WDP bootstrap MSI |
+| `Install-AutopilotMonitor-Dev.ps1` | rendered from the same source | dev fleet |
+| `Test-ShouldBootstrapAgent.ps1` | `scripts/Bootstrap/Test-ShouldBootstrapAgent.ps1` | customer dry run via `irm ... \| iex` |
+| `Grant-AutopilotMonitorAddOn.ps1` | `scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1` | optional Graph permission grant |
+
+`Uninstall-AutopilotMonitor.ps1` is deliberately not published — nothing links it, and an
+unauthenticated uninstall script on the public download host is not a feature.
+
+The alias is a Front Door route in front of the `agent` container; see
+[url-registry.md](url-registry.md) for the host registry and the migration to the alias.
+
+# Publishing chain
+
+`.github/scripts/Publish-BootstrapScripts.ps1` is the single owner. Two workflows call it
+with identical arguments:
+
+* **`publish-scripts.yml`** — on every push to `main` touching `scripts/Bootstrap/**`,
+  `scripts/CustomerSetup/**` or the publisher itself, plus `workflow_dispatch` with a
+  `dry_run` input.
+* **`build-agent.yml`** — inside the `publish_as_stable` branch, after `version.json` is
+  uploaded, so a release lands a set consistent with what is already live.
+
+Before this split, the script blobs rotated **only** on a stable agent release. A bootstrap
+fix therefore sat unpublished until the next agent cutover — while the WDP MSI downloads the
+published copy on every enrolling device. Script publishing is now decoupled from the agent
+release cadence; the release path still publishes, so it can never fall behind either.
+
+Both workflows share the concurrency group `agent-blob-publish` (`cancel-in-progress: false`).
+Both write `version.json`, and the publisher's `bootstrapVersion` read-modify-write must not
+interleave with a release writing the agent fields.
+
+# Publisher steps
+
+1. **Parse** `$ScriptVersion` from the bootstrap source.
+2. **Dev render** — literal substitution of the two `$AgentDownloadUrl` / `$VersionJsonName`
+   defaults. A missing anchor literal is a hard failure: a silently un-substituted dev script
+   would point the dev fleet at the stable agent.
+3. **Version-bump guard** — if the published bootstrap changed *behaviour* under an unchanged
+   `$ScriptVersion`, the run aborts. Comment and formatting changes publish with a warning.
+   See [Version oracles](#version-oracles).
+4. **Upload** every blob with `Cache-Control: no-cache` (they all rotate in place), mirrored
+   fail-soft to the legacy storage account.
+5. **Reconcile the version oracles.**
+6. **Verify through the alias** — re-download each blob and compare SHA-256, six attempts
+   20 s apart. A persistent mismatch means blobs were written but Front Door serves stale
+   content, and the error names the `az afd endpoint purge` command.
+
+## Deterministic publish form
+
+Every blob is published as **CRLF, UTF-8 without BOM**, normalized by the publisher rather
+than taken from the working copy. Git normalizes line endings on checkout — a Windows runner
+yields CRLF, a `core.autocrlf=false` clone yields LF — so publishing raw working-copy bytes
+would emit different blobs for identical source and make every byte comparison, guard and
+verification alike, depend on where the workflow ran. CRLF is also what PS 5.1 expects on the
+device and what has always been published.
+
+The ASCII-only rule for `scripts/Bootstrap/*.ps1` (enforced by the gates below) is unrelated
+but adjacent: PS 5.1 reads BOM-less files as ANSI and corrupts multi-byte characters.
+
+## Version oracles
+
+Three places state the bootstrap script version, and all three are derived from
+`$ScriptVersion` in the source:
+
+* `version.json.bootstrapVersion` — read by the docs badge. Written by the publisher as a
+  read-modify-write under `If-Match`, so a concurrent agent release keeps its own fields.
+  `build-agent.yml` seeds the field when it builds the manifest so the published manifest is
+  never briefly missing it; the publisher owns and re-asserts it afterwards.
+* `AdminConfiguration.LatestBootstrapV2ScriptVersion` — read by the portal to tell a customer
+  their uploaded copy is outdated. **Only** the publisher writes it; `build-agent.yml` writes
+  the `LatestAgentV2*` fields and nothing else. One writer per field.
+* The `Bootstrap script version: v<x>` marker the script logs, parsed out of captured platform
+  script stdout by `utils/bootstrapVersion.ts`.
+
+The version-bump guard exists because those three would otherwise keep asserting a version
+that no longer matches what customers download: a behaviour change under an unchanged version
+is invisible to every consumer, and customers decide from that version whether to re-upload
+their Intune copy.
+
+"Changed" means changed **behaviour**, matching what the source file's own comment on
+`$ScriptVersion` already asks for ("bump on meaningful changes"). The guard compares a code
+fingerprint — the PowerShell token stream with comments, newlines and line continuations
+removed — so comment fixes, typo corrections in comments and reflow publish with a
+`::warning::` instead of failing. Tokenising rather than regex-stripping keeps a `#` inside a
+string literal from being mistaken for a comment.
+
+# Gates
+
+`.github/workflows/bootstrap-script-gates.yml` is a `workflow_call` workflow holding the
+checks once:
+
+* Pester suite under **Windows PowerShell 5.1** — the runtime IME uses for platform scripts.
+* ASCII-only scan over `scripts/Bootstrap/*.ps1`.
+* `Publish-BootstrapScripts.ps1 -DryRun` — exercises the dev-render anchors and the
+  version-bump guard, and reports per blob whether the alias is current, stale or missing.
+
+Two callers: `pester.yml` on pull requests (reports, does not block the merge button), and
+`publish-scripts.yml` on pushes to `main`, where the gates job is a `needs:` dependency of the
+publish job and therefore **blocks** the upload. `pester.yml` deliberately has no push trigger
+— it would duplicate the gate run with no consequence.
+
+# Operating it
+
+* Dry run and drift check, no credentials needed for the read paths:
+  `pwsh .github/scripts/Publish-BootstrapScripts.ps1 -DryRun`
+* Republish without a code change: `workflow_dispatch` on **Publish customer scripts** with
+  `dry_run=false`.
+* Front Door serving stale content after a successful upload:
+  `az afd endpoint purge --resource-group rg-autopilotmonitor-prd-gwc --profile-name autopilotmonitor-fd --endpoint-name apm-download --content-paths '/agent/*'`
+
+# Citations
+
+* `.github/scripts/Publish-BootstrapScripts.ps1`
+* `.github/workflows/publish-scripts.yml`, `.github/workflows/bootstrap-script-gates.yml`, `.github/workflows/pester.yml`
+* `.github/workflows/build-agent.yml` (the `publish_as_stable` branch of the upload step)
+* `src/Agent/AutopilotMonitor.BootstrapMsi/Invoke-BootstrapDownload.ps1`
+* `src/Web/autopilot-monitor-web/utils/bootstrapVersion.ts`
@@ -0,0 +1,78 @@
+// Autopilot-Monitor — Log Analytics workspace transformation (ingestion-time filter)
+//
+// Two ingestion-time filters. (2) Successful Azure SignalR REST dependencies emitted by the
+// HOST process for the SignalR output binding (SDKVersion rdddsc:*) — the worker-side
+// StorageDependencyFilterProcessor never sees those. Failed SignalR calls are kept.
+// (1) Drops the redundant HOST-side HTTP request record from AppRequests so that exactly one
+// canonical request row remains: the worker-side copy emitted by RequestTelemetryMiddleware
+// (Properties.Source == 'WorkerMiddleware', carries TenantId/UserId/CorrelationId and is
+// sampling-exempt per item). Non-HTTP host invocations (timer/queue triggers) have an empty
+// Url and are kept — the worker middleware never sees them.
+//
+// Why ingestion-time: the host request item is emitted by the Functions host process and
+// cannot be suppressed from worker code or host.json (verified 2026-06-09, see Program.cs).
+// Live numbers 2026-08-23 (7d): host copy 274k rows / 323 MB, worker copy 189k rows / 208 MB.
+//
+// Cost note: transformation filtering is free up to 50% of the table's incoming volume; the
+// portion beyond that (here ~11% of AppRequests) is billed at the (cheap) data-processing rate.
+//
+// Apply (two steps; the link is a CLI update = GET+PUT, which keeps retention/SKU intact):
+//   az deployment group create -g rg-autopilotmonitor-prd-gwc \
+//     --template-file infra/appinsights-workspace-transforms.bicep \
+//     --query properties.outputs.dcrId.value -o tsv
+//   az monitor log-analytics workspace update -g rg-autopilotmonitor-prd-gwc -n AutopilotMonitor \
+//     --data-collection-rule <dcrId-from-above>
+//
+// Verify after ~20 min (ingestion latency):
+//   AppRequests | where TimeGenerated > ago(15m) | where AppRoleName == 'autopilotmonitor-api-eu'
+//   | summarize rows=count() by source=tostring(Properties.Source), hasUrl=isnotempty(Url)
+//   → only (WorkerMiddleware, true) and ('', false) buckets remain.
+//
+// Rollback: az monitor log-analytics workspace update -g <rg> -n AutopilotMonitor
+//   --set properties.defaultDataCollectionRuleResourceId=null   (then delete the DCR)
+
+@description('Log Analytics workspace that backs the workspace-based Application Insights resources.')
+param workspaceName string = 'AutopilotMonitor'
+
+param location string = resourceGroup().location
+
+resource workspace 'Microsoft.OperationalInsights/workspaces@2023-09-01' existing = {
+  name: workspaceName
+}
+
+resource transforms 'Microsoft.Insights/dataCollectionRules@2023-03-11' = {
+  name: 'dcr-autopilotmonitor-ws-transforms'
+  location: location
+  kind: 'WorkspaceTransforms'
+  properties: {
+    description: 'AppRequests: keep the enriched worker request record (Properties.Source == WorkerMiddleware) and non-HTTP host invocations (empty Url); drop the host HTTP duplicate.'
+    destinations: {
+      logAnalytics: [
+        {
+          workspaceResourceId: workspace.id
+          name: 'ws'
+        }
+      ]
+    }
+    dataFlows: [
+      {
+        streams: [ 'Microsoft-Table-AppRequests' ]
+        destinations: [ 'ws' ]
+        transformKql: 'source | where tostring(Properties.Source) == \'WorkerMiddleware\' or isempty(Url)'
+      }
+      {
+        // Successful Azure SignalR REST calls (group add/remove per connection) are emitted by
+        // the HOST process for the SignalR output binding (SDKVersion rdddsc:*), so the worker's
+        // StorageDependencyFilterProcessor never sees them. Failed SignalR calls are kept.
+        streams: [ 'Microsoft-Table-AppDependencies' ]
+        destinations: [ 'ws' ]
+        transformKql: 'source | where not(Success == true and Target endswith \'.service.signalr.net\')'
+      }
+    ]
+  }
+}
+
+// A workspace has exactly one transformation DCR, activated by linking it as the workspace's
+// defaultDataCollectionRuleResourceId — deliberately NOT modelled here (see Apply above).
+
+output dcrId string = transforms.id
@@ -0,0 +1,113 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-APP-016",
+  "title": "Required Apps Never Started — ESP Apps Gate Starved",
+  "description": "One or more required user-ESP apps never started installing while the ESP AccountSetup apps gate waited on them — the agent observed the ESP page exit with those apps still in a non-terminal, never-started state. Unlike ANALYZE-APP-015 (which reports that completion was DEFERRED because of a pending app, and stays silent once the session reaches a terminal verdict) this rule reports the delivery gap itself and fires regardless of the final outcome: an enrollment that Windows called done while required apps never ran is a successful enrollment with missing software, and the operator must see it.",
+  "severity": "warning",
+  "category": "apps",
+  "version": "1.0.0",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:session_stalled"
+  ],
+  "trigger": "single",
+  "baseConfidence": 75,
+  "confidenceThreshold": 70,
+  "conditions": [
+    {
+      "signal": "starved_apps_present",
+      "source": "event_count",
+      "eventType": "app_install_starved",
+      "operator": "count_gte",
+      "value": "1",
+      "required": true
+    },
+    {
+      "signal": "many_starved_apps",
+      "source": "event_count",
+      "eventType": "app_install_starved",
+      "operator": "count_gte",
+      "value": "5",
+      "required": false
+    },
+    {
+      "signal": "appName",
+      "source": "event_type",
+      "eventType": "app_install_starved",
+      "dataField": "appName",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "state",
+      "source": "event_type",
+      "eventType": "app_install_starved",
+      "dataField": "state",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [
+    {
+      "signal": "many_starved_apps",
+      "condition": "exists",
+      "weight": 15
+    },
+    {
+      "signal": "appName",
+      "condition": "exists",
+      "weight": 10
+    }
+  ],
+  "explanation": "At least one **required** app assigned to the user ESP never started installing. The Intune Management Extension never moved it out of its initial state (`{{state}}`) — it did not download, did not install, and did not fail — while the ESP AccountSetup apps gate was waiting on it. First app observed: `{{appName}}`.\n\nEvery starved app has its own `app_install_starved` timeline event carrying `appId`, `appName` and `state` — open the timeline and filter on that event type for the complete list.\n\nThis is a **delivery** problem, not an install error, and it is invisible in the Intune console: the app simply never appears. Typical causes:\n\n- far more required apps targeted at the ESP than the gate can service in the available window,\n- requirement rules that are never met on this device (OS / architecture / registry / script checks),\n- an unsatisfied dependency or supersedence chain,\n- an app that needs a context unavailable during provisioning (e.g. a VPN client waiting on a portal sign-in),\n- a mid-ESP reboot that cut the gate short — check whether the mid-ESP reboot advisory also fired for this session.\n\nNote that this finding is independent of the session verdict. A session can be marked **Succeeded** and still be missing every app listed here.",
+  "remediation": [
+    {
+      "title": "Shrink the ESP blocking set",
+      "steps": [
+        "Open the Enrollment Status Page profile and review the blocking app list — every required app there must finish before the user reaches the desktop.",
+        "Move apps that do not have to be present at first logon from *required* to *available*, or remove them from the ESP's blocking apps selection.",
+        "Prefer a small, deliberately chosen blocking set (security agent, VPN, management tooling) over the full application catalogue."
+      ]
+    },
+    {
+      "title": "Unblock the individual apps",
+      "steps": [
+        "Collect the app names from the `app_install_starved` timeline events in this session.",
+        "For each app, review its requirement rules and dependencies in Intune — IntuneManagementExtension.log records every requirement evaluation.",
+        "Verify the assignment actually targets the signed-in user (user-targeted apps need an established Entra user affinity; check the hybrid user-affinity finding if it also fired).",
+        "Re-run an enrollment and confirm the apps now reach a terminal state before the ESP exits."
+      ]
+    },
+    {
+      "title": "Rule out a truncated gate",
+      "steps": [
+        "Check whether a mid-ESP reboot was observed for this session — a forced restart during AccountSetup cuts the apps gate short and can starve everything still queued.",
+        "If so, reassign the reboot-forcing device policies to user groups so the restart lands after AccountSetup."
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Microsoft Learn: Enrollment Status Page — blocking apps",
+      "url": "https://learn.microsoft.com/en-us/intune/intune-service/enrollment/windows-enrollment-status"
+    },
+    {
+      "title": "Microsoft Learn: Win32 app requirement rules",
+      "url": "https://learn.microsoft.com/en-us/intune/intune-service/apps/apps-win32-add"
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": [
+    "apps",
+    "esp",
+    "starvation",
+    "assignment",
+    "blocking",
+    "delivery-gap"
+  ]
+}
@@ -0,0 +1,92 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-APP-017",
+  "title": "App Install Blocked by Another Installer (0x80070652)",
+  "description": "Detects Win32 app installs that failed because the Windows Installer was busy with another installation (HRESULT 0x80070652 / MSI exit code 1618, ERROR_INSTALL_ALREADY_RUNNING). The IME retries on a fixed budget (~15-17 minutes across several attempts) and then reports the app as failed; when the app is ESP-blocking, the Device Setup Apps subcategory terminates with it.",
+  "severity": "high",
+  "category": "apps",
+  "version": "1.0.0",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "baseConfidence": 70,
+  "conditions": [
+    {
+      "signal": "mutex_blocked_install",
+      "source": "event_type",
+      "eventType": "app_install_failed",
+      "dataField": "hresultFromWin32",
+      "operator": "equals",
+      "value": "-2147023278",
+      "required": true
+    },
+    {
+      "signal": "installer_exit_1618",
+      "source": "event_data",
+      "eventType": "app_install_failed",
+      "dataField": "exitCode",
+      "operator": "equals",
+      "value": "1618",
+      "required": false
+    },
+    {
+      "signal": "esp_failed_with_mutex_code",
+      "source": "event_data",
+      "eventType": "esp_failure_settle_started",
+      "dataField": "errorCode",
+      "operator": "equals",
+      "value": "0x80070652",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [
+    {
+      "signal": "installer_exit_1618",
+      "condition": "exists",
+      "weight": 10
+    },
+    {
+      "signal": "esp_failed_with_mutex_code",
+      "condition": "exists",
+      "weight": 20
+    }
+  ],
+  "confidenceThreshold": 65,
+  "explanation": "App **{{appName}}** failed to install because the Windows Installer service was already busy with another installation — HRESULT **0x80070652** / MSI exit code **1618** (`ERROR_INSTALL_ALREADY_RUNNING`). Only one Windows Installer transaction can run at a time; the Intune Management Extension retried on its fixed budget (typically ~15-17 minutes across several attempts) and then reported the app as failed. If this app is required in the Enrollment Status Page, the Device Setup Apps subcategory fails with it and the enrollment terminates.\n\nThis failure is **deterministic per attempt**: as long as the competing installer keeps winning the race, a plain re-enrollment fails again at roughly the same minute mark — retrying without fixing the collision only churns devices.\n\nCommon sources of the competing installation:\n\n- The **preceding Win32 app in the install order**: its installer exits 0 (so IME moves on) but leaves a child `msiexec` transaction or post-install MSI work running. Security agents and proxy clients that chain multiple MSIs are frequent offenders.\n- **OEM factory software** installing on first boot (factory-image provisioning packages, vendor updaters) — typical on brand-new hardware batches.\n- **Microsoft 365 Apps (C2R), driver updaters or Windows servicing** running installations in parallel outside IME's control.",
+  "remediation": [
+    {
+      "title": "Identify the competing installer",
+      "steps": [
+        "In this session's timeline, note which app finished installing immediately before {{appName}} started — its installer is the prime suspect for holding the Windows Installer mutex",
+        "On a reproduction device, when the failure window is active, check for running installers: Get-Process msiexec | Select-Object Id,StartTime and the in-progress marker key HKLM\\SOFTWARE\\Microsoft\\Windows\\Installer\\InProgress",
+        "Check the Application event log for MsiInstaller events around the failure timestamp to see which product held the transaction",
+        "On factory-fresh hardware, also look for OEM first-boot installers (vendor updater services, factory provisioning packages) that run outside Intune"
+      ]
+    },
+    {
+      "title": "Serialize the install chain",
+      "steps": [
+        "Add an Intune Win32 dependency so {{appName}} depends on the app whose installer causes the collision — IME then orders them explicitly instead of racing",
+        "Alternatively, wrap the offending predecessor so its install script waits until msiexec has fully finished (poll the InProgress registry key or the _MSIExecute mutex with a bounded timeout) before exiting",
+        "If the app does not have to gate the ESP, remove it from the blocking-app list so a transient 1618 no longer terminates the enrollment; Intune retries it after the desktop"
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Microsoft Learn: MsiExec.exe error messages (1618 = another installation is in progress)",
+      "url": "https://learn.microsoft.com/en-us/windows/win32/msi/error-codes"
+    },
+    {
+      "title": "Microsoft Learn: Troubleshoot Win32 app installations in Intune",
+      "url": "https://learn.microsoft.com/en-us/troubleshoot/mem/intune/app-management/troubleshoot-win32-app-install"
+    }
+  ],
+  "tags": [
+    "apps",
+    "msiexec",
+    "mutex",
+    "0x80070652",
+    "1618",
+    "esp"
+  ]
+}
@@ -0,0 +1,69 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-DEV-008",
+  "title": "Device Clock Wrong During Enrollment — Jump or Sustained Offset",
+  "description": "The device's clock changed by five or more minutes mid-session (clock jump) or ran five or more minutes off server time for the whole session (sustained offset), measured against the server receive frame of every uploaded event. Complements ANALYZE-DEV-007, which is a one-shot NTP check at agent startup and misses devices where NTP was unreachable or the clock changed later. IME-log-derived events are excluded from the measurement.",
+  "severity": "warning",
+  "category": "device",
+  "version": "1.0.0",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
+  "trigger": "single",
+  "baseConfidence": 60,
+  "confidenceThreshold": 50,
+  "conditions": [
+    {
+      "signal": "clock_jump",
+      "source": "clock_skew",
+      "skewMetric": "clock_jump",
+      "operator": "gte",
+      "value": "300",
+      "required": false
+    },
+    {
+      "signal": "sustained_offset",
+      "source": "clock_skew",
+      "skewMetric": "sustained_offset",
+      "operator": "gte",
+      "value": "300",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [],
+  "explanation": "This device's {{skewSummary}} (five-minute threshold). A clock that is off by five or more minutes breaks time-sensitive enrollment mechanisms: Kerberos tolerates at most 5 minutes of skew (Hybrid Join), Entra ID token validation allows about 5 minutes on token lifetimes, and freshly issued SCEP/PKCS certificates can be rejected as \"not yet valid\" when the clock is more than ~10 minutes behind the CA.\n\nUnlike ANALYZE-DEV-007 (a one-shot NTP comparison at agent startup), this finding is measured across the whole session against the server's receive time — it also catches devices where the NTP check could not run (UDP 123 blocked) or where the clock changed after startup (time sync correcting a wrong RTC, Windows auto-timezone, manual change).",
+  "remediation": [
+    {
+      "title": "Fix the device clock and time source",
+      "steps": [
+        "Check the BIOS/RTC clock and the CMOS battery if the wrong time recurs on the same hardware.",
+        "At OOBE, run 'w32tm /resync /force' (Shift+F10 command prompt) to sync with time.windows.com.",
+        "Ensure UDP port 123 to time.windows.com is open in the deployment network.",
+        "Review 'Set time automatically' and 'Set time zone automatically' behavior on the deployment image — automatic timezone changes mid-enrollment show up as clock jumps."
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Microsoft Learn: Windows Autopilot known issues — device provisioning can fail (clock skew)",
+      "url": "https://learn.microsoft.com/en-us/autopilot/known-issues"
+    },
+    {
+      "title": "Microsoft Learn: Windows Autopilot requirements — Networking (NTP)",
+      "url": "https://learn.microsoft.com/en-us/autopilot/requirements?tabs=networking"
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": [
+    "device",
+    "clock-skew",
+    "clock-jump",
+    "time-sync",
+    "kerberos",
+    "certificates",
+    "known-issue"
+  ]
+}
@@ -0,0 +1,48 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-DEV-009",
+  "title": "Battery Critically Low During Enrollment",
+  "description": "Detects that the device's battery dropped to 15% or less while enrolling on battery power (power_state_change threshold event from the agent's live power watcher). A device dying mid-enrollment leaves a half-provisioned state that typically needs a full reset; this rule surfaces the risk while there is still time to plug the device in. Uses a single required condition on the agent-stamped thresholdPercent field (the data field 'transition' on the event is unrelated to this rule's 'trigger' property).",
+  "severity": "high",
+  "category": "device",
+  "version": "1.0.0",
+  "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:power_state_change"
+  ],
+  "trigger": "single",
+  "baseConfidence": 90,
+  "confidenceThreshold": 60,
+  "conditions": [
+    {
+      "signal": "battery_threshold_15",
+      "source": "event_data",
+      "eventType": "power_state_change",
+      "dataField": "thresholdPercent",
+      "operator": "equals",
+      "value": "15",
+      "required": true
+    }
+  ],
+  "explanation": "The device's battery fell below **{{thresholdPercent}}%** while the enrollment was running on battery power. If the battery drains completely mid-enrollment, the device is left in a half-provisioned state — apps, policies, or the user profile may be incomplete, and in most cases the device has to be reset and re-enrolled. The agent detected the threshold crossing live via a Windows power-status notification; the exact percentage at that moment is recorded on the matched power_state_change event in the session timeline.",
+  "remediation": [
+    {
+      "title": "Secure power for the running enrollment",
+      "steps": [
+        "Connect the device to AC power immediately — the enrollment continues normally once power is stable.",
+        "If the device shut down before completing, check whether the session reached the desktop; if not, reset the device (Autopilot reset or reimage) and re-enroll it plugged in.",
+        "For technician/White Glove flows, make AC power part of the bench checklist — pre-provisioning on battery is the most common source of this alert.",
+        "If this fires across many devices of one model, review that model's battery health (the hardware_spec event carries design vs. full-charge capacity)."
+      ]
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": [
+    "device",
+    "power",
+    "battery",
+    "environment"
+  ]
+}
@@ -0,0 +1,48 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-DEV-010",
+  "title": "Enrollment Switched From AC to Battery Power",
+  "description": "Detects that the device lost AC power and switched to battery while the enrollment was running (power_state_change event with transition ac_to_battery from the agent's live power watcher). Uses a single required condition so the match is pinned to one event instance; the event payload carries the battery percentage at the moment of the switch. The agent debounces power flapping (5s) so a brief unplug/replug does not produce this event.",
+  "severity": "warning",
+  "category": "device",
+  "version": "1.0.0",
+  "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:power_state_change"
+  ],
+  "trigger": "single",
+  "baseConfidence": 85,
+  "confidenceThreshold": 60,
+  "conditions": [
+    {
+      "signal": "switched_to_battery",
+      "source": "event_data",
+      "eventType": "power_state_change",
+      "dataField": "transition",
+      "operator": "equals",
+      "value": "ac_to_battery",
+      "required": true
+    }
+  ],
+  "explanation": "The device switched from AC to battery power mid-enrollment. Enrollments are power-hungry — app downloads, Windows Update and disk encryption drain a battery quickly, and Windows may also throttle CPU and network on battery, slowing the enrollment down. The battery percentage at the moment of the switch is recorded on the matched power_state_change event in the session timeline; if the device stayed on battery, look there for subsequent threshold events (50/30/15%) — a later battery_to_ac event means power was restored.",
+  "remediation": [
+    {
+      "title": "Restore AC power",
+      "steps": [
+        "Reconnect the device to AC power; the enrollment continues normally.",
+        "Check the session timeline for a subsequent battery_to_ac event (power restored) or threshold_crossed events (battery draining) to judge urgency.",
+        "If this alert is frequent in a deployment area, check docking stations/USB-C hubs for loose power delivery — a flapping dock is a common cause.",
+        "Make 'plugged in during setup' part of the end-user/technician enrollment instructions."
+      ]
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": [
+    "device",
+    "power",
+    "battery",
+    "environment"
+  ]
+}
@@ -0,0 +1,49 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-DEV-012",
+  "title": "Device Entered Standby During Enrollment",
+  "description": "Detects that the device completed a sleep, hibernate or Modern Standby episode of at least 5 minutes while the enrollment was running (system_sleep_episode event from the agent's system timeline watcher, recorded retroactively at wake from the Windows event log — pre-agent episodes are backfilled). Uses a single required condition on the episode's durationSeconds so the match is pinned to one event instance and the interpolated duration is the matched value. Short Modern Standby screen-off scenarios (under 60 s of real sleep) never emit the event, and this rule adds a 5-minute floor so brief lid-close moments do not fire it.",
+  "severity": "info",
+  "category": "device",
+  "version": "1.0.0",
+  "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:system_sleep_episode"
+  ],
+  "trigger": "single",
+  "baseConfidence": 90,
+  "confidenceThreshold": 60,
+  "conditions": [
+    {
+      "signal": "slept_during_enrollment",
+      "source": "event_data",
+      "eventType": "system_sleep_episode",
+      "dataField": "durationSeconds",
+      "operator": "gte",
+      "value": "300",
+      "required": true
+    }
+  ],
+  "explanation": "The device was asleep for {{durationSeconds}} seconds during the enrollment window. Nothing progresses while the device sleeps — downloads pause, the IME stops processing and the ESP simply waits — so the wall-clock enrollment duration includes this pause and can look much slower than the enrollment actually was. The matched system_sleep_episode event in the session timeline carries the exact enter/exit times, the episode kind (sleep, hibernate or Modern Standby) and, for Modern Standby, whether the device was on AC power. A long unexplained gap in the timeline right before that event is this pause, not missing telemetry.",
+  "remediation": [
+    {
+      "title": "Keep the device awake during enrollment",
+      "steps": [
+        "Check the matched system_sleep_episode event in the timeline for the episode bounds and kind — the enrollment duration minus the episode duration is the real active time.",
+        "If the device slept on battery, connect AC power during setup; Windows sleeps far more aggressively on battery.",
+        "Instruct users/technicians to keep the lid open and the device powered until the enrollment finishes.",
+        "For recurring cases, review the power plan applied during OOBE/ESP (e.g. via provisioning or Intune policy) — consider disabling sleep on AC for the enrollment window."
+      ]
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": [
+    "device",
+    "power",
+    "standby",
+    "sleep",
+    "environment"
+  ]
+}
@@ -5,12 +5,13 @@
  "description": "Attributes an observed enrollment reboot to device-assigned MDM policies that Windows flagged as reboot-required. Fires ONLY when both facts are present in the session: at least one actually-observed reboot (system_reboot_detected) AND reboot-required policy flags (mdm_policy_reboot_required). Policy flags alone — e.g. from a user-policy sync during AccountSetup — force no reboot and stay advisory-silent.",
  "severity": "warning",
  "category": "esp",
-  "version": "1.2.0",
+  "version": "1.3.0",
  "author": "Autopilot Monitor",
  "enabled": true,
  "evaluateOn": [
    "enrollment_end",
-    "whiteglove_sealed"
+    "whiteglove_sealed",
+    "on_event:session_stalled"
  ],
  "trigger": "single",
  "baseConfidence": 70,
@@ -0,0 +1,81 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-NET-001",
+  "title": "Diagnostics Upload Blocked by Web Security Gateway",
+  "description": "Detects diagnostics package uploads that were answered by a security appliance's HTML block page instead of the Autopilot Monitor backend. A forward proxy / secure web gateway (SWG) with SSL inspection is intercepting the upload endpoint, so exactly the sessions where diagnostics matter most (OnFailure uploads) are the ones losing them.",
+  "severity": "warning",
+  "category": "network",
+  "version": "1.0.0",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "baseConfidence": 75,
+  "conditions": [
+    {
+      "signal": "foreign_html_response",
+      "source": "event_data",
+      "eventType": "diagnostics_upload_failed",
+      "dataField": "errorCode",
+      "operator": "contains",
+      "value": "HTML platform error page",
+      "required": true
+    },
+    {
+      "signal": "security_gateway_marker",
+      "source": "event_data",
+      "eventType": "diagnostics_upload_failed",
+      "dataField": "errorCode",
+      "operator": "regex",
+      "value": "mcafee|skyhigh|zscaler|netskope|blue ?coat|proxysg|forcepoint|websense|palo ?alto|fortigate|fortiguard|sophos|watchguard|barracuda|iboss|umbrella|lightspeed|smoothwall|contentkeeper|web ?gateway|web ?filter|content ?filter|secure ?gateway",
+      "required": true
+    },
+    {
+      "signal": "http_403_block",
+      "source": "event_data",
+      "eventType": "diagnostics_upload_failed",
+      "dataField": "errorCode",
+      "operator": "contains",
+      "value": "403",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [
+    {
+      "signal": "http_403_block",
+      "condition": "exists",
+      "weight": 15
+    }
+  ],
+  "confidenceThreshold": 70,
+  "explanation": "The agent collected a diagnostics package but the upload was answered with an **HTML block page from a web security gateway** instead of a response from the Autopilot Monitor backend — the event message names the product that served the page. A forward proxy / SWG with SSL inspection is intercepting HTTPS traffic from the enrollment network and blocking the upload endpoint.\n\nThe consequence is quietly painful: diagnostics upload is typically configured **OnFailure**, so the sessions that fail — the ones where the IME logs and diagnostics ZIP would explain the root cause — are exactly the sessions whose evidence never arrives. Enrollment telemetry itself may still flow (the agent often starts before the gateway's client enforcement does, or other endpoints are treated differently), which makes the gap easy to miss until a failure needs investigating.\n\nNote this rule only fires when the blocking page carries a recognizable security-product marker. A plain HTML error page without one usually means a stale or stopped endpoint instead — that is a different problem.",
+  "remediation": [
+    {
+      "title": "Exempt the upload endpoint in the web gateway",
+      "steps": [
+        "Identify the product from the block-page title quoted in this event's message (e.g. a Skyhigh/McAfee Web Gateway notification page)",
+        "In that gateway, add the Autopilot Monitor API host shown in the event message to the SSL-inspection bypass AND the URL allowlist for the enrollment network segment",
+        "Enrollment traffic often originates from a dedicated provisioning VLAN or from devices without the proxy client yet — make sure the exemption applies to that segment, not only to managed clients",
+        "If the gateway enforces per-user policy, remember ESP-phase traffic runs as SYSTEM/device before any user signs in — the exemption must cover unauthenticated device traffic"
+      ]
+    },
+    {
+      "title": "Verify the fix",
+      "steps": [
+        "Re-run an enrollment (or wait for the next failed one) and confirm a diagnostics package appears on the session in the portal",
+        "Optionally set diagnostics upload to Always temporarily to validate the path without needing a failure"
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Microsoft Learn: Windows Autopilot networking requirements",
+      "url": "https://learn.microsoft.com/en-us/autopilot/networking-requirements"
+    }
+  ],
+  "tags": [
+    "network",
+    "proxy",
+    "ssl-inspection",
+    "swg",
+    "diagnostics"
+  ]
+}
@@ -831,6 +831,209 @@
        "pending"
      ]
    },
+    {
+      "ruleId": "ANALYZE-APP-016",
+      "title": "Required Apps Never Started — ESP Apps Gate Starved",
+      "description": "One or more required user-ESP apps never started installing while the ESP AccountSetup apps gate waited on them — the agent observed the ESP page exit with those apps still in a non-terminal, never-started state. Unlike ANALYZE-APP-015 (which reports that completion was DEFERRED because of a pending app, and stays silent once the session reaches a terminal verdict) this rule reports the delivery gap itself and fires regardless of the final outcome: an enrollment that Windows called done while required apps never ran is a successful enrollment with missing software, and the operator must see it.",
+      "severity": "warning",
+      "category": "apps",
+      "version": "1.0.0",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:session_stalled"
+      ],
+      "trigger": "single",
+      "baseConfidence": 75,
+      "confidenceThreshold": 70,
+      "conditions": [
+        {
+          "signal": "starved_apps_present",
+          "source": "event_count",
+          "eventType": "app_install_starved",
+          "operator": "count_gte",
+          "value": "1",
+          "required": true
+        },
+        {
+          "signal": "many_starved_apps",
+          "source": "event_count",
+          "eventType": "app_install_starved",
+          "operator": "count_gte",
+          "value": "5",
+          "required": false
+        },
+        {
+          "signal": "appName",
+          "source": "event_type",
+          "eventType": "app_install_starved",
+          "dataField": "appName",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "state",
+          "source": "event_type",
+          "eventType": "app_install_starved",
+          "dataField": "state",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [
+        {
+          "signal": "many_starved_apps",
+          "condition": "exists",
+          "weight": 15
+        },
+        {
+          "signal": "appName",
+          "condition": "exists",
+          "weight": 10
+        }
+      ],
+      "explanation": "At least one **required** app assigned to the user ESP never started installing. The Intune Management Extension never moved it out of its initial state (`{{state}}`) — it did not download, did not install, and did not fail — while the ESP AccountSetup apps gate was waiting on it. First app observed: `{{appName}}`.\n\nEvery starved app has its own `app_install_starved` timeline event carrying `appId`, `appName` and `state` — open the timeline and filter on that event type for the complete list.\n\nThis is a **delivery** problem, not an install error, and it is invisible in the Intune console: the app simply never appears. Typical causes:\n\n- far more required apps targeted at the ESP than the gate can service in the available window,\n- requirement rules that are never met on this device (OS / architecture / registry / script checks),\n- an unsatisfied dependency or supersedence chain,\n- an app that needs a context unavailable during provisioning (e.g. a VPN client waiting on a portal sign-in),\n- a mid-ESP reboot that cut the gate short — check whether the mid-ESP reboot advisory also fired for this session.\n\nNote that this finding is independent of the session verdict. A session can be marked **Succeeded** and still be missing every app listed here.",
+      "remediation": [
+        {
+          "title": "Shrink the ESP blocking set",
+          "steps": [
+            "Open the Enrollment Status Page profile and review the blocking app list — every required app there must finish before the user reaches the desktop.",
+            "Move apps that do not have to be present at first logon from *required* to *available*, or remove them from the ESP's blocking apps selection.",
+            "Prefer a small, deliberately chosen blocking set (security agent, VPN, management tooling) over the full application catalogue."
+          ]
+        },
+        {
+          "title": "Unblock the individual apps",
+          "steps": [
+            "Collect the app names from the `app_install_starved` timeline events in this session.",
+            "For each app, review its requirement rules and dependencies in Intune — IntuneManagementExtension.log records every requirement evaluation.",
+            "Verify the assignment actually targets the signed-in user (user-targeted apps need an established Entra user affinity; check the hybrid user-affinity finding if it also fired).",
+            "Re-run an enrollment and confirm the apps now reach a terminal state before the ESP exits."
+          ]
+        },
+        {
+          "title": "Rule out a truncated gate",
+          "steps": [
+            "Check whether a mid-ESP reboot was observed for this session — a forced restart during AccountSetup cuts the apps gate short and can starve everything still queued.",
+            "If so, reassign the reboot-forcing device policies to user groups so the restart lands after AccountSetup."
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Microsoft Learn: Enrollment Status Page — blocking apps",
+          "url": "https://learn.microsoft.com/en-us/intune/intune-service/enrollment/windows-enrollment-status"
+        },
+        {
+          "title": "Microsoft Learn: Win32 app requirement rules",
+          "url": "https://learn.microsoft.com/en-us/intune/intune-service/apps/apps-win32-add"
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "apps",
+        "esp",
+        "starvation",
+        "assignment",
+        "blocking",
+        "delivery-gap"
+      ]
+    },
+    {
+      "ruleId": "ANALYZE-APP-017",
+      "title": "App Install Blocked by Another Installer (0x80070652)",
+      "description": "Detects Win32 app installs that failed because the Windows Installer was busy with another installation (HRESULT 0x80070652 / MSI exit code 1618, ERROR_INSTALL_ALREADY_RUNNING). The IME retries on a fixed budget (~15-17 minutes across several attempts) and then reports the app as failed; when the app is ESP-blocking, the Device Setup Apps subcategory terminates with it.",
+      "severity": "high",
+      "category": "apps",
+      "version": "1.0.0",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "baseConfidence": 70,
+      "conditions": [
+        {
+          "signal": "mutex_blocked_install",
+          "source": "event_type",
+          "eventType": "app_install_failed",
+          "dataField": "hresultFromWin32",
+          "operator": "equals",
+          "value": "-2147023278",
+          "required": true
+        },
+        {
+          "signal": "installer_exit_1618",
+          "source": "event_data",
+          "eventType": "app_install_failed",
+          "dataField": "exitCode",
+          "operator": "equals",
+          "value": "1618",
+          "required": false
+        },
+        {
+          "signal": "esp_failed_with_mutex_code",
+          "source": "event_data",
+          "eventType": "esp_failure_settle_started",
+          "dataField": "errorCode",
+          "operator": "equals",
+          "value": "0x80070652",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [
+        {
+          "signal": "installer_exit_1618",
+          "condition": "exists",
+          "weight": 10
+        },
+        {
+          "signal": "esp_failed_with_mutex_code",
+          "condition": "exists",
+          "weight": 20
+        }
+      ],
+      "confidenceThreshold": 65,
+      "explanation": "App **{{appName}}** failed to install because the Windows Installer service was already busy with another installation — HRESULT **0x80070652** / MSI exit code **1618** (`ERROR_INSTALL_ALREADY_RUNNING`). Only one Windows Installer transaction can run at a time; the Intune Management Extension retried on its fixed budget (typically ~15-17 minutes across several attempts) and then reported the app as failed. If this app is required in the Enrollment Status Page, the Device Setup Apps subcategory fails with it and the enrollment terminates.\n\nThis failure is **deterministic per attempt**: as long as the competing installer keeps winning the race, a plain re-enrollment fails again at roughly the same minute mark — retrying without fixing the collision only churns devices.\n\nCommon sources of the competing installation:\n\n- The **preceding Win32 app in the install order**: its installer exits 0 (so IME moves on) but leaves a child `msiexec` transaction or post-install MSI work running. Security agents and proxy clients that chain multiple MSIs are frequent offenders.\n- **OEM factory software** installing on first boot (factory-image provisioning packages, vendor updaters) — typical on brand-new hardware batches.\n- **Microsoft 365 Apps (C2R), driver updaters or Windows servicing** running installations in parallel outside IME's control.",
+      "remediation": [
+        {
+          "title": "Identify the competing installer",
+          "steps": [
+            "In this session's timeline, note which app finished installing immediately before {{appName}} started — its installer is the prime suspect for holding the Windows Installer mutex",
+            "On a reproduction device, when the failure window is active, check for running installers: Get-Process msiexec | Select-Object Id,StartTime and the in-progress marker key HKLM\\SOFTWARE\\Microsoft\\Windows\\Installer\\InProgress",
+            "Check the Application event log for MsiInstaller events around the failure timestamp to see which product held the transaction",
+            "On factory-fresh hardware, also look for OEM first-boot installers (vendor updater services, factory provisioning packages) that run outside Intune"
+          ]
+        },
+        {
+          "title": "Serialize the install chain",
+          "steps": [
+            "Add an Intune Win32 dependency so {{appName}} depends on the app whose installer causes the collision — IME then orders them explicitly instead of racing",
+            "Alternatively, wrap the offending predecessor so its install script waits until msiexec has fully finished (poll the InProgress registry key or the _MSIExecute mutex with a bounded timeout) before exiting",
+            "If the app does not have to gate the ESP, remove it from the blocking-app list so a transient 1618 no longer terminates the enrollment; Intune retries it after the desktop"
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Microsoft Learn: MsiExec.exe error messages (1618 = another installation is in progress)",
+          "url": "https://learn.microsoft.com/en-us/windows/win32/msi/error-codes"
+        },
+        {
+          "title": "Microsoft Learn: Troubleshoot Win32 app installations in Intune",
+          "url": "https://learn.microsoft.com/en-us/troubleshoot/mem/intune/app-management/troubleshoot-win32-app-install"
+        }
+      ],
+      "tags": [
+        "apps",
+        "msiexec",
+        "mutex",
+        "0x80070652",
+        "1618",
+        "esp"
+      ]
+    },
    {
      "ruleId": "ANALYZE-CORR-003",
      "title": "Proxy Configuration Causing Download Failure",
@@ -1404,6 +1607,216 @@
        "known-issue"
      ]
    },
+    {
+      "ruleId": "ANALYZE-DEV-008",
+      "title": "Device Clock Wrong During Enrollment — Jump or Sustained Offset",
+      "description": "The device's clock changed by five or more minutes mid-session (clock jump) or ran five or more minutes off server time for the whole session (sustained offset), measured against the server receive frame of every uploaded event. Complements ANALYZE-DEV-007, which is a one-shot NTP check at agent startup and misses devices where NTP was unreachable or the clock changed later. IME-log-derived events are excluded from the measurement.",
+      "severity": "warning",
+      "category": "device",
+      "version": "1.0.0",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
+      "trigger": "single",
+      "baseConfidence": 60,
+      "confidenceThreshold": 50,
+      "conditions": [
+        {
+          "signal": "clock_jump",
+          "source": "clock_skew",
+          "skewMetric": "clock_jump",
+          "operator": "gte",
+          "value": "300",
+          "required": false
+        },
+        {
+          "signal": "sustained_offset",
+          "source": "clock_skew",
+          "skewMetric": "sustained_offset",
+          "operator": "gte",
+          "value": "300",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [],
+      "explanation": "This device's {{skewSummary}} (five-minute threshold). A clock that is off by five or more minutes breaks time-sensitive enrollment mechanisms: Kerberos tolerates at most 5 minutes of skew (Hybrid Join), Entra ID token validation allows about 5 minutes on token lifetimes, and freshly issued SCEP/PKCS certificates can be rejected as \"not yet valid\" when the clock is more than ~10 minutes behind the CA.\n\nUnlike ANALYZE-DEV-007 (a one-shot NTP comparison at agent startup), this finding is measured across the whole session against the server's receive time — it also catches devices where the NTP check could not run (UDP 123 blocked) or where the clock changed after startup (time sync correcting a wrong RTC, Windows auto-timezone, manual change).",
+      "remediation": [
+        {
+          "title": "Fix the device clock and time source",
+          "steps": [
+            "Check the BIOS/RTC clock and the CMOS battery if the wrong time recurs on the same hardware.",
+            "At OOBE, run 'w32tm /resync /force' (Shift+F10 command prompt) to sync with time.windows.com.",
+            "Ensure UDP port 123 to time.windows.com is open in the deployment network.",
+            "Review 'Set time automatically' and 'Set time zone automatically' behavior on the deployment image — automatic timezone changes mid-enrollment show up as clock jumps."
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Microsoft Learn: Windows Autopilot known issues — device provisioning can fail (clock skew)",
+          "url": "https://learn.microsoft.com/en-us/autopilot/known-issues"
+        },
+        {
+          "title": "Microsoft Learn: Windows Autopilot requirements — Networking (NTP)",
+          "url": "https://learn.microsoft.com/en-us/autopilot/requirements?tabs=networking"
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "device",
+        "clock-skew",
+        "clock-jump",
+        "time-sync",
+        "kerberos",
+        "certificates",
+        "known-issue"
+      ]
+    },
+    {
+      "ruleId": "ANALYZE-DEV-009",
+      "title": "Battery Critically Low During Enrollment",
+      "description": "Detects that the device's battery dropped to 15% or less while enrolling on battery power (power_state_change threshold event from the agent's live power watcher). A device dying mid-enrollment leaves a half-provisioned state that typically needs a full reset; this rule surfaces the risk while there is still time to plug the device in. Uses a single required condition on the agent-stamped thresholdPercent field (the data field 'transition' on the event is unrelated to this rule's 'trigger' property).",
+      "severity": "high",
+      "category": "device",
+      "version": "1.0.0",
+      "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:power_state_change"
+      ],
+      "trigger": "single",
+      "baseConfidence": 90,
+      "confidenceThreshold": 60,
+      "conditions": [
+        {
+          "signal": "battery_threshold_15",
+          "source": "event_data",
+          "eventType": "power_state_change",
+          "dataField": "thresholdPercent",
+          "operator": "equals",
+          "value": "15",
+          "required": true
+        }
+      ],
+      "explanation": "The device's battery fell below **{{thresholdPercent}}%** while the enrollment was running on battery power. If the battery drains completely mid-enrollment, the device is left in a half-provisioned state — apps, policies, or the user profile may be incomplete, and in most cases the device has to be reset and re-enrolled. The agent detected the threshold crossing live via a Windows power-status notification; the exact percentage at that moment is recorded on the matched power_state_change event in the session timeline.",
+      "remediation": [
+        {
+          "title": "Secure power for the running enrollment",
+          "steps": [
+            "Connect the device to AC power immediately — the enrollment continues normally once power is stable.",
+            "If the device shut down before completing, check whether the session reached the desktop; if not, reset the device (Autopilot reset or reimage) and re-enroll it plugged in.",
+            "For technician/White Glove flows, make AC power part of the bench checklist — pre-provisioning on battery is the most common source of this alert.",
+            "If this fires across many devices of one model, review that model's battery health (the hardware_spec event carries design vs. full-charge capacity)."
+          ]
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "device",
+        "power",
+        "battery",
+        "environment"
+      ]
+    },
+    {
+      "ruleId": "ANALYZE-DEV-010",
+      "title": "Enrollment Switched From AC to Battery Power",
+      "description": "Detects that the device lost AC power and switched to battery while the enrollment was running (power_state_change event with transition ac_to_battery from the agent's live power watcher). Uses a single required condition so the match is pinned to one event instance; the event payload carries the battery percentage at the moment of the switch. The agent debounces power flapping (5s) so a brief unplug/replug does not produce this event.",
+      "severity": "warning",
+      "category": "device",
+      "version": "1.0.0",
+      "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:power_state_change"
+      ],
+      "trigger": "single",
+      "baseConfidence": 85,
+      "confidenceThreshold": 60,
+      "conditions": [
+        {
+          "signal": "switched_to_battery",
+          "source": "event_data",
+          "eventType": "power_state_change",
+          "dataField": "transition",
+          "operator": "equals",
+          "value": "ac_to_battery",
+          "required": true
+        }
+      ],
+      "explanation": "The device switched from AC to battery power mid-enrollment. Enrollments are power-hungry — app downloads, Windows Update and disk encryption drain a battery quickly, and Windows may also throttle CPU and network on battery, slowing the enrollment down. The battery percentage at the moment of the switch is recorded on the matched power_state_change event in the session timeline; if the device stayed on battery, look there for subsequent threshold events (50/30/15%) — a later battery_to_ac event means power was restored.",
+      "remediation": [
+        {
+          "title": "Restore AC power",
+          "steps": [
+            "Reconnect the device to AC power; the enrollment continues normally.",
+            "Check the session timeline for a subsequent battery_to_ac event (power restored) or threshold_crossed events (battery draining) to judge urgency.",
+            "If this alert is frequent in a deployment area, check docking stations/USB-C hubs for loose power delivery — a flapping dock is a common cause.",
+            "Make 'plugged in during setup' part of the end-user/technician enrollment instructions."
+          ]
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "device",
+        "power",
+        "battery",
+        "environment"
+      ]
+    },
+    {
+      "ruleId": "ANALYZE-DEV-012",
+      "title": "Device Entered Standby During Enrollment",
+      "description": "Detects that the device completed a sleep, hibernate or Modern Standby episode of at least 5 minutes while the enrollment was running (system_sleep_episode event from the agent's system timeline watcher, recorded retroactively at wake from the Windows event log — pre-agent episodes are backfilled). Uses a single required condition on the episode's durationSeconds so the match is pinned to one event instance and the interpolated duration is the matched value. Short Modern Standby screen-off scenarios (under 60 s of real sleep) never emit the event, and this rule adds a 5-minute floor so brief lid-close moments do not fire it.",
+      "severity": "info",
+      "category": "device",
+      "version": "1.0.0",
+      "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:system_sleep_episode"
+      ],
+      "trigger": "single",
+      "baseConfidence": 90,
+      "confidenceThreshold": 60,
+      "conditions": [
+        {
+          "signal": "slept_during_enrollment",
+          "source": "event_data",
+          "eventType": "system_sleep_episode",
+          "dataField": "durationSeconds",
+          "operator": "gte",
+          "value": "300",
+          "required": true
+        }
+      ],
+      "explanation": "The device was asleep for {{durationSeconds}} seconds during the enrollment window. Nothing progresses while the device sleeps — downloads pause, the IME stops processing and the ESP simply waits — so the wall-clock enrollment duration includes this pause and can look much slower than the enrollment actually was. The matched system_sleep_episode event in the session timeline carries the exact enter/exit times, the episode kind (sleep, hibernate or Modern Standby) and, for Modern Standby, whether the device was on AC power. A long unexplained gap in the timeline right before that event is this pause, not missing telemetry.",
+      "remediation": [
+        {
+          "title": "Keep the device awake during enrollment",
+          "steps": [
+            "Check the matched system_sleep_episode event in the timeline for the episode bounds and kind — the enrollment duration minus the episode duration is the real active time.",
+            "If the device slept on battery, connect AC power during setup; Windows sleeps far more aggressively on battery.",
+            "Instruct users/technicians to keep the lid open and the device powered until the enrollment finishes.",
+            "For recurring cases, review the power plan applied during OOBE/ESP (e.g. via provisioning or Intune policy) — consider disabling sleep on AC for the enrollment window."
+          ]
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "device",
+        "power",
+        "standby",
+        "sleep",
+        "environment"
+      ]
+    },
    {
      "ruleId": "ANALYZE-ENRL-001",
      "title": "Enrollment Failed",
@@ -2069,12 +2482,13 @@
      "description": "Attributes an observed enrollment reboot to device-assigned MDM policies that Windows flagged as reboot-required. Fires ONLY when both facts are present in the session: at least one actually-observed reboot (system_reboot_detected) AND reboot-required policy flags (mdm_policy_reboot_required). Policy flags alone — e.g. from a user-policy sync during AccountSetup — force no reboot and stay advisory-silent.",
      "severity": "warning",
      "category": "esp",
-      "version": "1.2.0",
+      "version": "1.3.0",
      "author": "Autopilot Monitor",
      "enabled": true,
      "evaluateOn": [
        "enrollment_end",
-        "whiteglove_sealed"
+        "whiteglove_sealed",
+        "on_event:session_stalled"
      ],
      "trigger": "single",
      "baseConfidence": 70,
@@ -2641,6 +3055,86 @@
        "esp"
      ]
    },
+    {
+      "ruleId": "ANALYZE-NET-001",
+      "title": "Diagnostics Upload Blocked by Web Security Gateway",
+      "description": "Detects diagnostics package uploads that were answered by a security appliance's HTML block page instead of the Autopilot Monitor backend. A forward proxy / secure web gateway (SWG) with SSL inspection is intercepting the upload endpoint, so exactly the sessions where diagnostics matter most (OnFailure uploads) are the ones losing them.",
+      "severity": "warning",
+      "category": "network",
+      "version": "1.0.0",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "baseConfidence": 75,
+      "conditions": [
+        {
+          "signal": "foreign_html_response",
+          "source": "event_data",
+          "eventType": "diagnostics_upload_failed",
+          "dataField": "errorCode",
+          "operator": "contains",
+          "value": "HTML platform error page",
+          "required": true
+        },
+        {
+          "signal": "security_gateway_marker",
+          "source": "event_data",
+          "eventType": "diagnostics_upload_failed",
+          "dataField": "errorCode",
+          "operator": "regex",
+          "value": "mcafee|skyhigh|zscaler|netskope|blue ?coat|proxysg|forcepoint|websense|palo ?alto|fortigate|fortiguard|sophos|watchguard|barracuda|iboss|umbrella|lightspeed|smoothwall|contentkeeper|web ?gateway|web ?filter|content ?filter|secure ?gateway",
+          "required": true
+        },
+        {
+          "signal": "http_403_block",
+          "source": "event_data",
+          "eventType": "diagnostics_upload_failed",
+          "dataField": "errorCode",
+          "operator": "contains",
+          "value": "403",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [
+        {
+          "signal": "http_403_block",
+          "condition": "exists",
+          "weight": 15
+        }
+      ],
+      "confidenceThreshold": 70,
+      "explanation": "The agent collected a diagnostics package but the upload was answered with an **HTML block page from a web security gateway** instead of a response from the Autopilot Monitor backend — the event message names the product that served the page. A forward proxy / SWG with SSL inspection is intercepting HTTPS traffic from the enrollment network and blocking the upload endpoint.\n\nThe consequence is quietly painful: diagnostics upload is typically configured **OnFailure**, so the sessions that fail — the ones where the IME logs and diagnostics ZIP would explain the root cause — are exactly the sessions whose evidence never arrives. Enrollment telemetry itself may still flow (the agent often starts before the gateway's client enforcement does, or other endpoints are treated differently), which makes the gap easy to miss until a failure needs investigating.\n\nNote this rule only fires when the blocking page carries a recognizable security-product marker. A plain HTML error page without one usually means a stale or stopped endpoint instead — that is a different problem.",
+      "remediation": [
+        {
+          "title": "Exempt the upload endpoint in the web gateway",
+          "steps": [
+            "Identify the product from the block-page title quoted in this event's message (e.g. a Skyhigh/McAfee Web Gateway notification page)",
+            "In that gateway, add the Autopilot Monitor API host shown in the event message to the SSL-inspection bypass AND the URL allowlist for the enrollment network segment",
+            "Enrollment traffic often originates from a dedicated provisioning VLAN or from devices without the proxy client yet — make sure the exemption applies to that segment, not only to managed clients",
+            "If the gateway enforces per-user policy, remember ESP-phase traffic runs as SYSTEM/device before any user signs in — the exemption must cover unauthenticated device traffic"
+          ]
+        },
+        {
+          "title": "Verify the fix",
+          "steps": [
+            "Re-run an enrollment (or wait for the next failed one) and confirm a diagnostics package appears on the session in the portal",
+            "Optionally set diagnostics upload to Always temporarily to validate the path without needing a failure"
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Microsoft Learn: Windows Autopilot networking requirements",
+          "url": "https://learn.microsoft.com/en-us/autopilot/networking-requirements"
+        }
+      ],
+      "tags": [
+        "network",
+        "proxy",
+        "ssl-inspection",
+        "swg",
+        "diagnostics"
+      ]
+    },
    {
      "ruleId": "ANALYZE-OFFICE-001",
      "title": "Microsoft 365 Apps Install Failed",
@@ -629,7 +629,7 @@
      "category": "always",
      "pattern": "Failed to get AAD token\\..*?errorCode = (?<errorCode>.*?)$",
      "action": "imeTokenFailure",
-      "description": "IME token acquisition failure ('Failed to get AAD token. len = N using client id ... and resource id ..., errorCode = N', IntuneTokenManager, IntuneManagementExtension.log). Complements IME-TOKEN-SUCCESS: an auth outage (WAM broken, conditional access, network) previously left every check-in silently doing nothing with no timeline evidence. errorCode can be empty when IME logged none; the agent dedups to one Warning per distinct code. Verified against IME 1.97 and 1.104 decompiled sources.",
+      "description": "IME token acquisition failure ('Failed to get AAD token. len = N using client id ... and resource id ..., errorCode = N', IntuneTokenManager, IntuneManagementExtension.log). This line appears ROUTINELY during the device phase (no user token exists yet), so the agent holds the failure pending: any IME-TOKEN-SUCCESS match clears it, and the ime_token_failure Warning fires only when no success follows for the whole 30-min grace window (then deduped to one Warning per distinct errorCode). A genuine auth outage (WAM broken, conditional access, network) runs long enough to hit the window. Verified against IME 1.97 and 1.104 decompiled sources.",
      "enabled": true
    },
    {
@@ -675,6 +675,14 @@
      "description": "Detects when IME completes a user session, indicating enrollment has finished for that user.",
      "enabled": true
    },
+    {
+      "patternId": "IME-USER-SESSION-ZERO-APPS",
+      "category": "always",
+      "pattern": "\\[Win32App\\] Get 0 apps for user session (?<sessionId>\\d+), user id = (?<userId>[a-f0-9\\-]+)",
+      "action": "userSessionZeroApps",
+      "description": "Detects when IME enumerated a user session and found zero targeted Win32 apps. IME then skips its 'Completed user session' line entirely (the zero-app branch in ApplicationPoller continues before that log statement), so this line is the only evidence that user-phase enforcement finished on a device with no user-targeted apps. Treated as equivalent to a completed user session.",
+      "enabled": true
+    },
    {
      "patternId": "IME-WIN32-STATE-1",
      "category": "currentPhase",
@@ -4,6 +4,6 @@
  "category": "always",
  "pattern": "Failed to get AAD token\\..*?errorCode = (?<errorCode>.*?)$",
  "action": "imeTokenFailure",
-  "description": "IME token acquisition failure ('Failed to get AAD token. len = N using client id ... and resource id ..., errorCode = N', IntuneTokenManager, IntuneManagementExtension.log). Complements IME-TOKEN-SUCCESS: an auth outage (WAM broken, conditional access, network) previously left every check-in silently doing nothing with no timeline evidence. errorCode can be empty when IME logged none; the agent dedups to one Warning per distinct code. Verified against IME 1.97 and 1.104 decompiled sources.",
+  "description": "IME token acquisition failure ('Failed to get AAD token. len = N using client id ... and resource id ..., errorCode = N', IntuneTokenManager, IntuneManagementExtension.log). This line appears ROUTINELY during the device phase (no user token exists yet), so the agent holds the failure pending: any IME-TOKEN-SUCCESS match clears it, and the ime_token_failure Warning fires only when no success follows for the whole 30-min grace window (then deduped to one Warning per distinct errorCode). A genuine auth outage (WAM broken, conditional access, network) runs long enough to hit the window. Verified against IME 1.97 and 1.104 decompiled sources.",
  "enabled": true
 }
@@ -0,0 +1,9 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-USER-SESSION-ZERO-APPS",
+  "category": "always",
+  "pattern": "\\[Win32App\\] Get 0 apps for user session (?<sessionId>\\d+), user id = (?<userId>[a-f0-9\\-]+)",
+  "action": "userSessionZeroApps",
+  "description": "Detects when IME enumerated a user session and found zero targeted Win32 apps. IME then skips its 'Completed user session' line entirely (the zero-app branch in ApplicationPoller continues before that log statement), so this line is the only evidence that user-phase enforcement finished on a device with no user-targeted apps. Treated as equivalent to a completed user session.",
+  "enabled": true
+}
@@ -169,7 +169,12 @@
        "source": {
          "type": "string",
          "description": "Source of the signal.",
-          "enum": ["event_type", "event_data", "event_data_array", "phase_duration", "event_count", "app_install_duration", "event_correlation"]
+          "enum": ["event_type", "event_data", "event_data_array", "phase_duration", "event_count", "app_install_duration", "event_correlation", "clock_skew"]
+        },
+        "skewMetric": {
+          "type": "string",
+          "description": "For clock_skew only: which device-clock metric to evaluate. clock_jump = persistent step in the device's clock frame mid-session; sustained_offset = whole session ran on a clock off by at least the threshold. value is the threshold in seconds; operator is limited to gt/gte on the magnitude. IME-log-derived events are excluded from the measurement.",
+          "enum": ["clock_jump", "sustained_offset"]
        },
        "eventType": {
          "type": "string",
@@ -63,6 +63,7 @@
            "imeImpersonation",
            "imeTokenFailure",
            "enrollmentCompleted",
+            "userSessionZeroApps",
            "updateDoTelemetry",
            "scriptStarted",
            "scriptContext",
@@ -13,18 +13,26 @@ const rulesRoot = path.resolve(__dirname, '..');

 // ── Rule combination ────────────────────────────────────────────────────────

+// Shipped gather/analyze rules must stay inside the reserved built-in namespace:
+// (ANALYZE|GATHER)-<CATEGORY>-<NNN> with CATEGORY !== CUSTOM. The CUSTOM category is
+// the sanctioned tenant namespace (RuleIdPolicy.cs) — a built-in shipped there would
+// silently shadow every tenant's same-ID custom rule at merge time (global wins).
+const RESERVED_BUILTIN_ID = /^(ANALYZE|GATHER)-(?!CUSTOM-)[A-Z]+-\d{3}$/;
+
 const configs = [
  {
    dir: path.join(rulesRoot, 'gather'),
    output: path.join(rulesRoot, 'dist', 'gather-rules.json'),
    schema: '../schema/gather-rule.schema.json',
-    idField: 'ruleId'
+    idField: 'ruleId',
+    reservedNamespace: RESERVED_BUILTIN_ID
  },
  {
    dir: path.join(rulesRoot, 'analyze'),
    output: path.join(rulesRoot, 'dist', 'analyze-rules.json'),
    schema: '../schema/analyze-rule.schema.json',
-    idField: 'ruleId'
+    idField: 'ruleId',
+    reservedNamespace: RESERVED_BUILTIN_ID
  },
  {
    dir: path.join(rulesRoot, 'ime-log-patterns'),
@@ -37,12 +45,27 @@ const configs = [
 for (const config of configs) {
  const files = fs.readdirSync(config.dir).filter(f => f.endsWith('.json')).sort();
  const rules = [];
+  const seenIds = new Map(); // lowercased id -> filename (case variants collide for humans and RuleIdPolicy)

  for (const file of files) {
    const content = fs.readFileSync(path.join(config.dir, file), 'utf8');
    const rule = JSON.parse(content);
    // Remove $schema from individual entries (it's on the wrapper)
    delete rule['$schema'];
+
+    const id = rule[config.idField] || '';
+    const idKey = id.toLowerCase();
+    if (seenIds.has(idKey)) {
+      console.error(`ERROR: duplicate ${config.idField} "${id}" in ${file} (already defined in ${seenIds.get(idKey)})`);
+      process.exit(1);
+    }
+    seenIds.set(idKey, file);
+
+    if (config.reservedNamespace && !config.reservedNamespace.test(id)) {
+      console.error(`ERROR: ${file}: ${config.idField} "${id}" is outside the reserved built-in namespace ${config.reservedNamespace} — built-ins must never use the tenant CUSTOM namespace`);
+      process.exit(1);
+    }
+
    rules.push(rule);
  }

@@ -95,6 +95,8 @@
                      Organizations). SKIP-safe when the API is absent (< 1809).
                      Removed legacy Content-MD5 fallback; SHA-256 manifest verification is
                      now mandatory (no hash -> bootstrap aborts, no unverified install).
+    2026-08-18  v2.4  Renamed log file bootstrap_agent.log -> bootstrap-script.log
+                      (unified kebab-case log naming across the agent log directory).
    2026-05-09  v2.0  Generic bootstrap: agent owns its own defaults (e.g. 600 s
                      TenantId-wait), so the script only calls `--install` plain.
                      Hardened post-install with a 10 s runtime-process verify.
@@ -126,13 +128,13 @@ param(
 )

 # Script version (bump on meaningful changes; see .CHANGELOG above)
-$ScriptVersion = "2.3"
+$ScriptVersion = "2.4"

 # Configuration - Everything in ProgramData for easy cleanup
 $AgentBasePath = "$env:ProgramData\AutopilotMonitor"
 $AgentBinPath = "$AgentBasePath\Agent"
 $AgentLogPath = "$AgentBasePath\Logs"
-$LogFile = "$AgentLogPath\bootstrap_agent.log"
+$LogFile = "$AgentLogPath\bootstrap-script.log"

 # Write-Host (NOT Write-Output): log calls happen inside functions that return
 # decision objects; Write-Output would leak every log line into those return values.
@@ -1,4 +1,4 @@
-#Requires -Version 5.1
+#Requires -Version 5.1
 <#
 .SYNOPSIS
    Grants additional Microsoft Graph application permissions to the Autopilot Monitor
@@ -28,10 +28,18 @@
        (validates Windows 365 Cloud PCs against the tenant's Cloud PC inventory --
         Cloud PCs are never Autopilot-registered, so this enables agent monitoring
         of Cloud PC first-connect enrollment)
+      - IntuneDeviceBinding     -> DeviceManagementManagedDevices.Read.All
+        (cert-to-device binding: verifies that the Intune device id carried in the
+         agent's client certificate is a device THIS tenant actually enrolled --
+         currently a Global-Admin-only preview that records telemetry and does not
+         block enrollment)
+      - All                    -> every optional permission above, in one run
+        (also works with -Revoke to remove all optional grants at once)

 .PARAMETER Permissions
-    Microsoft Graph application permission names to grant directly. Use when the admin UI
-    rendered a copy-paste command for you, or when you have a specific list in mind.
+    Microsoft Graph application permission names to grant directly. Use when you copied the
+    permission list from the admin UI ("Copy permissions"), or when you have a specific list
+    in mind.

 .PARAMETER TenantId
    Tenant ID (GUID) or verified domain. Optional -- defaults to the signed-in context.
@@ -47,12 +55,16 @@
    .\Grant-AutopilotMonitorAddOn.ps1 -ClientId "<your-client-id>" -Features ScriptDisplayNames

 .EXAMPLE
-    # Same effect, using the explicit-permission form (what the admin UI generates):
+    # Same effect, using the explicit-permission form:
    .\Grant-AutopilotMonitorAddOn.ps1 `
        -ClientId "<your-client-id>" `
        -Permissions "DeviceManagementScripts.Read.All" `
        -TenantId "contoso.onmicrosoft.com"

+.EXAMPLE
+    # Grant every optional capability in one run:
+    .\Grant-AutopilotMonitorAddOn.ps1 -ClientId "<your-client-id>" -Features All
+
 .EXAMPLE
    # Verify current state only, no changes:
    .\Grant-AutopilotMonitorAddOn.ps1 -ClientId "<your-client-id>" -Features ScriptDisplayNames -VerifyOnly
@@ -65,6 +77,12 @@
    Requires:
      - Microsoft.Graph.Authentication PowerShell module (auto-installs if missing).
      - Sign-in as Global Administrator OR Privileged Role Administrator OR Cloud Application Administrator.
+
+    Sign-in behaviour:
+      In Azure Cloud Shell the script signs in via the ambient identity endpoint (a delegated
+      token for the already-signed-in user) - no device-code prompt, which Conditional Access
+      policies commonly block. Outside Cloud Shell it falls back to a normal interactive
+      Microsoft Graph sign-in. -TenantId only applies to the interactive fallback.
      - The Autopilot Monitor app must be admin-consented in your tenant first
        (its service principal must exist before grants can be added).

@@ -80,7 +98,7 @@ param(
    [string]$ClientId,

    [Parameter(Mandatory = $true, ParameterSetName = 'ByFeatures')]
-    [ValidateSet('ScriptDisplayNames', 'W365CloudPcValidation')]
+    [ValidateSet('All', 'ScriptDisplayNames', 'W365CloudPcValidation', 'IntuneDeviceBinding')]
    [string[]]$Features,

    [Parameter(Mandatory = $true, ParameterSetName = 'ByPermissions')]
@@ -103,10 +121,15 @@ $ErrorActionPreference = 'Stop'
 $FeatureCatalog = @{
    'ScriptDisplayNames'    = @('DeviceManagementScripts.Read.All')
    'W365CloudPcValidation' = @('CloudPC.Read.All')
+    'IntuneDeviceBinding'   = @('DeviceManagementManagedDevices.Read.All')
 }

 # Translate Features -> Permissions when caller used the high-level form.
+# 'All' is a script-side meta-value: it expands to every catalog feature.
 if ($PSCmdlet.ParameterSetName -eq 'ByFeatures') {
+    if ($Features -contains 'All') {
+        $Features = @($FeatureCatalog.Keys)
+    }
    $Permissions = @()
    foreach ($f in $Features) {
        $Permissions += $FeatureCatalog[$f]
@@ -133,7 +156,25 @@ if ($TenantId) { $connectParams['TenantId'] = $TenantId }

 Write-Host ""
 Write-Host "[Auth] Connecting to Microsoft Graph..." -ForegroundColor Cyan
-Connect-MgGraph @connectParams | Out-Null
+
+# Preferred path: ambient identity. In Azure Cloud Shell the local identity endpoint issues a
+# delegated Graph token for the signed-in user, which avoids the device-code flow that
+# Conditional Access policies commonly block. Outside Azure this throws and we fall back to
+# an interactive sign-in with explicit scopes.
+$identityConnected = $false
+try {
+    Connect-MgGraph -Identity -NoWelcome -ErrorAction Stop | Out-Null
+    # An ambient identity can exist yet hold no Graph permissions (e.g. a plain VM managed
+    # identity) - probe with a read before committing to this session.
+    Invoke-MgGraphRequest -Method GET -Uri "https://graph.microsoft.com/v1.0/servicePrincipals?`$select=id&`$top=1" -ErrorAction Stop | Out-Null
+    $identityConnected = $true
+    Write-Host "[Auth] Connected via ambient identity (Azure Cloud Shell / managed identity)." -ForegroundColor Green
+}
+catch {
+    if (Get-MgContext) { Disconnect-MgGraph -ErrorAction SilentlyContinue | Out-Null }
+    Write-Host "[Auth] No usable ambient identity - falling back to interactive sign-in..." -ForegroundColor Yellow
+    Connect-MgGraph @connectParams | Out-Null
+}

 $ctx = Get-MgContext
 if (-not $ctx) {
@@ -144,7 +185,10 @@ Write-Host "[Auth] Signed in as : $($ctx.Account)"
 Write-Host "[Auth] Tenant       : $($ctx.TenantId)"
 Write-Host "[Auth] Granted scopes: $($ctx.Scopes -join ', ')"

-if (-not ($ctx.Scopes -contains 'AppRoleAssignment.ReadWrite.All')) {
+# Scope check only applies to the interactive path: an ambient-identity (Cloud Shell) token
+# carries a fixed scope set (incl. Directory.AccessAsUser.All) instead of the requested scopes,
+# and its effective rights follow the signed-in user's directory role.
+if (-not $identityConnected -and -not ($ctx.Scopes -contains 'AppRoleAssignment.ReadWrite.All')) {
    Write-Warning "Scope 'AppRoleAssignment.ReadWrite.All' was NOT granted. The signed-in user likely lacks the required role (Global Admin / Privileged Role Admin / Cloud App Admin)."
    if (-not $VerifyOnly) { return }
 }
@@ -0,0 +1,62 @@
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Configuration;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
+{
+    /// <summary>
+    /// Pins the compiled-in fallback rule catalogs (<see cref="BuiltInConfigCatalog"/>):
+    /// the agent embeds the SAME CI-combined rules/dist artifacts the backend serves, so a
+    /// no-config/no-cache session still runs full IME tracking. These tests guard the
+    /// embedding + deserialization end-to-end — a broken LogicalName, a moved resource or a
+    /// shape change in the combined JSON must fail HERE, not silently strip the fallback
+    /// back down to zero patterns in the field.
+    /// </summary>
+    public class BuiltInConfigCatalogTests
+    {
+        [Fact]
+        public void ImeLogPatterns_LoadFromEmbeddedCatalog_EnabledOnly()
+        {
+            var patterns = BuiltInConfigCatalog.GetEnabledImeLogPatterns(logger: null);
+
+            Assert.NotEmpty(patterns);
+            Assert.All(patterns, p =>
+            {
+                Assert.True(p.Enabled);
+                Assert.False(string.IsNullOrWhiteSpace(p.PatternId));
+                Assert.False(string.IsNullOrWhiteSpace(p.Pattern));
+                Assert.False(string.IsNullOrWhiteSpace(p.Action));
+                Assert.False(string.IsNullOrWhiteSpace(p.Category));
+            });
+            Assert.Equal(patterns.Count, patterns.Select(p => p.PatternId).Distinct().Count());
+        }
+
+        [Fact]
+        public void ImeLogPatterns_CarryCoreTrackingActions()
+        {
+            // The app-tracking backbone: without these two actions the ImeLogTracker cannot
+            // attribute installs to apps or follow ESP phases. Their presence proves the
+            // deserialization actually populated the action field (a shape drift in the
+            // combined JSON would otherwise still pass the structural checks above).
+            var actions = BuiltInConfigCatalog.GetEnabledImeLogPatterns(logger: null)
+                .Select(p => p.Action).ToHashSet();
+
+            Assert.Contains("setCurrentApp", actions);
+            Assert.Contains("espPhaseDetected", actions);
+        }
+
+        [Fact]
+        public void GatherRules_LoadFromEmbeddedCatalog_EnabledOnly()
+        {
+            // The built-in gather-rule catalog ships mostly disabled rules — only the
+            // default-enabled ones may reach the fallback config.
+            var rules = BuiltInConfigCatalog.GetEnabledGatherRules(logger: null);
+
+            Assert.All(rules, r =>
+            {
+                Assert.True(r.Enabled);
+                Assert.False(string.IsNullOrWhiteSpace(r.RuleId));
+            });
+        }
+    }
+}
@@ -37,6 +37,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            nameof(AgentConfigResponse.EnrollmentSummaryLaunchRetrySeconds),
            nameof(AgentConfigResponse.NtpServer),
            nameof(AgentConfigResponse.EnableTimezoneAutoSet),
+            nameof(AgentConfigResponse.EnableDoGroupIdAutoSet),
            nameof(AgentConfigResponse.DiagnosticsUploadEnabled),
            nameof(AgentConfigResponse.DiagnosticsUploadMode),
            nameof(AgentConfigResponse.DiagnosticsLogPaths),
@@ -52,6 +53,9 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            // Merge reads two Collectors knobs (AgentMaxLifetimeMinutes, HelloWaitTimeoutSeconds);
            // the remaining CollectorConfiguration flags flow untouched to DefaultComponentFactory.
            nameof(AgentConfigResponse.Collectors),
+            // Merge reads one Analyzers knob (EnableRealmJoinWatcher → diagnostics RealmJoin sections);
+            // the remaining flags flow untouched to DefaultComponentFactory + AgentAnalyzerManager.
+            nameof(AgentConfigResponse.Analyzers),
        };

        /// <summary>
@@ -69,8 +73,6 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            nameof(AgentConfigResponse.ImeLogPatterns),
            // Passed by AgentRuntimeHost into IComponentFactory.CreateCollectorHosts → ImeLogHost sealing re-emit.
            nameof(AgentConfigResponse.WhiteGloveSealingPatternIds),
-            // Consumed by DefaultComponentFactory (RealmJoin/KeepAwake/ConsoleBypass host gates) + AgentAnalyzerManager.
-            nameof(AgentConfigResponse.Analyzers),
            // Self-update ZIP integrity second trust channel — BinaryIntegrityVerifier / Program update path.
            nameof(AgentConfigResponse.LatestAgentSha256),
            // Running-EXE integrity verification — BinaryIntegrityVerifier post-config check.
@@ -43,6 +43,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            EnrollmentSummaryLaunchRetrySeconds = 300,
            NtpServer = "pool.ntp.org",
            EnableTimezoneAutoSet = true,
+            EnableDoGroupIdAutoSet = true,
            DiagnosticsUploadEnabled = true,
            DiagnosticsUploadMode = "OnFailure",
            DiagnosticsLogPaths = new List<DiagnosticsLogPath>
@@ -83,6 +84,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            Assert.Equal(300, agent.EnrollmentSummaryLaunchRetrySeconds);
            Assert.Equal("pool.ntp.org", agent.NtpServer);
            Assert.True(agent.EnableTimezoneAutoSet);
+            Assert.True(agent.EnableDoGroupIdAutoSet);
            Assert.True(agent.DiagnosticsUploadEnabled);
            Assert.Equal("OnFailure", agent.DiagnosticsUploadMode);
            Assert.Single(agent.DiagnosticsLogPaths);
@@ -366,6 +368,33 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            Assert.Equal(30, agent.HelloWaitTimeoutSeconds);
        }

+        [Fact]
+        public void Merge_mirrors_analyzers_realmjoin_watcher_onto_agent_config()
+        {
+            // The diagnostics package gates its RealmJoin sections on this flag but never
+            // sees the remote response — the merger carries the one Analyzers knob over.
+            var agent = NewAgentConfig();
+            var remote = FullRemote();
+            remote.Analyzers = new AnalyzerConfiguration { EnableRealmJoinWatcher = true };
+
+            RemoteConfigMerger.Merge(agent, remote);
+
+            Assert.True(agent.EnableRealmJoinWatcher);
+        }
+
+        [Fact]
+        public void Merge_clears_realmjoin_watcher_when_remote_analyzers_missing()
+        {
+            var agent = NewAgentConfig();
+            agent.EnableRealmJoinWatcher = true;   // stale cached true must not survive
+            var remote = FullRemote();
+            remote.Analyzers = null!;
+
+            RemoteConfigMerger.Merge(agent, remote);
+
+            Assert.False(agent.EnableRealmJoinWatcher);
+        }
+
        [Fact]
        public void Merge_replaces_diagnostics_log_paths_with_empty_list_when_remote_null()
        {
@@ -114,6 +114,22 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            Assert.Equal(1, svc.LastFetchAttempts);
        }

+        [Fact]
+        public async Task FetchConfig_DefaultsFallback_CarriesBuiltInCatalogs()
+        {
+            // A no-config/no-cache session must still get the compiled-in rule catalogs —
+            // an empty ImeLogPatterns list kills the entire IME tracking pipeline (the
+            // pre-catalog behaviour this pins against regressing to).
+            var svc = NewService(BackendBehaviour.AlwaysTransientFailure);
+
+            var result = await svc.FetchConfigAsync(retryOnTransientErrors: true);
+
+            Assert.Equal(0, result.ConfigVersion);
+            Assert.NotEmpty(result.ImeLogPatterns);
+            Assert.All(result.ImeLogPatterns, p => Assert.True(p.Enabled));
+            Assert.All(result.GatherRules, r => Assert.True(r.Enabled));
+        }
+
        [Fact]
        public async Task FetchConfig_EmptyResponse_TreatedAsTransient()
        {
@@ -128,6 +144,94 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            Assert.Equal(4, svc.LastFetchAttempts);
        }

+        // ── Network-link gate (tenant aebdce78 audit 2026-08-24) ────────────
+
+        [Fact]
+        public async Task FetchConfig_InitialFetch_WaitsForNetworkLink()
+        {
+            // The initial startup fetch must gate on the link-level signal so the retry
+            // budget isn't burned into a NIC that is provably still down (agent relaunched
+            // at boot, Wi-Fi still associating).
+            var svc = NewService(BackendBehaviour.SuccessImmediately);
+
+            await svc.FetchConfigAsync(retryOnTransientErrors: true);
+
+            Assert.Equal(1, svc.NetworkLinkWaits);
+        }
+
+        [Fact]
+        public async Task FetchConfig_RotatePath_SkipsNetworkLinkGate()
+        {
+            // rotate_config runs mid-session on a proven link and must stay latency-bounded.
+            var svc = NewService(BackendBehaviour.SuccessImmediately);
+
+            await svc.FetchConfigAsync(retryOnTransientErrors: false);
+
+            Assert.Equal(0, svc.NetworkLinkWaits);
+        }
+
+        // ── Post-registration recovery ──────────────────────────────────────
+
+        [Fact]
+        public async Task TryRecover_AfterFailedFetch_AppliesLiveConfig_KeepsFailureRecord()
+        {
+            // The core self-heal contract: registration proved the backend reachable, the
+            // recovery swaps in the live config — but the LastFetch* observability keeps
+            // describing the failed startup fetch so the wire event can report both.
+            var svc = NewService(BackendBehaviour.FailAllThenSucceed);
+            await svc.FetchConfigAsync(retryOnTransientErrors: true);
+            Assert.Equal(RemoteConfigFetchOutcome.UsedDefaults, svc.LastFetchOutcome);
+
+            var recovered = await svc.TryRecoverConfigAsync();
+
+            Assert.NotNull(recovered);
+            Assert.Equal(42, recovered.ConfigVersion);
+            Assert.Equal(42, svc.CurrentConfig.ConfigVersion);
+            Assert.True(svc.RecoveredAfterFetchFailure);
+            // Startup-failure record intact:
+            Assert.Equal(RemoteConfigFetchOutcome.UsedDefaults, svc.LastFetchOutcome);
+            Assert.Equal(1 + RemoteConfigService.InitialFetchRetryBackoff.Length, svc.LastFetchAttempts);
+            Assert.Equal(nameof(HttpRequestException), svc.LastFetchFailureType);
+        }
+
+        [Fact]
+        public async Task TryRecover_AfterSuccessfulFetch_IsNoOp()
+        {
+            var svc = NewService(BackendBehaviour.SuccessImmediately);
+            await svc.FetchConfigAsync(retryOnTransientErrors: true);
+
+            var recovered = await svc.TryRecoverConfigAsync();
+
+            Assert.Null(recovered);
+            Assert.False(svc.RecoveredAfterFetchFailure);
+        }
+
+        [Fact]
+        public async Task TryRecover_BeforeAnyFetch_IsNoOp()
+        {
+            var svc = NewService(BackendBehaviour.SuccessImmediately);
+
+            var recovered = await svc.TryRecoverConfigAsync();
+
+            Assert.Null(recovered);
+            Assert.False(svc.RecoveredAfterFetchFailure);
+        }
+
+        [Fact]
+        public async Task TryRecover_WhenBackendStillFailing_KeepsFallback_NeverThrows()
+        {
+            var svc = NewService(BackendBehaviour.AlwaysTransientFailure);
+            var fallback = await svc.FetchConfigAsync(retryOnTransientErrors: true);
+            Assert.Equal(0, fallback.ConfigVersion);
+
+            var recovered = await svc.TryRecoverConfigAsync();
+
+            Assert.Null(recovered);
+            Assert.False(svc.RecoveredAfterFetchFailure);
+            Assert.Equal(0, svc.CurrentConfig.ConfigVersion); // fallback config untouched
+            Assert.Equal(RemoteConfigFetchOutcome.UsedDefaults, svc.LastFetchOutcome);
+        }
+
        // ── Outcome state defaults ──────────────────────────────────────────

        [Fact]
@@ -145,6 +249,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            SuccessImmediately,
            AlwaysTransientFailure,
            FailTwiceThenSucceed,
+            /// <summary>All 4 initial attempts fail; the NEXT call (the recovery fetch) succeeds.</summary>
+            FailAllThenSucceed,
            AlwaysAuthFailure401,
            AlwaysReturnNull,
        }
@@ -177,6 +283,9 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
                _behaviour = behaviour;
            }

+            /// <summary>Number of times the network-link gate seam was awaited.</summary>
+            public int NetworkLinkWaits { get; private set; }
+
            protected override Task<AgentConfigResponse> CallBackendAsync()
            {
                _calls++;
@@ -188,6 +297,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
                        if (_calls < 3)
                            throw new HttpRequestException("simulated cold-start timeout");
                        return Task.FromResult(new AgentConfigResponse { ConfigVersion = 42 });
+                    case BackendBehaviour.FailAllThenSucceed:
+                        if (_calls <= 1 + RemoteConfigService.InitialFetchRetryBackoff.Length)
+                            throw new HttpRequestException("simulated dead network link");
+                        return Task.FromResult(new AgentConfigResponse { ConfigVersion = 42 });
                    case BackendBehaviour.AlwaysTransientFailure:
                        throw new HttpRequestException("simulated network failure");
                    case BackendBehaviour.AlwaysAuthFailure401:
@@ -202,6 +315,13 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
            // Zero-delay so the suite finishes in ms instead of the live 10/30/60 s schedule.
            protected override Task DelayBetweenAttemptsAsync(TimeSpan delay) => Task.CompletedTask;

+            // Record + skip the real link poll so the suite is deterministic on offline CI.
+            protected override Task WaitForNetworkLinkAsync()
+            {
+                NetworkLinkWaits++;
+                return Task.CompletedTask;
+            }
+
            // In-memory + per-instance cache so a prior test's successful fetch can't
            // bleed into a later test that expects UsedDefaults.
            private AgentConfigResponse? _cached;
@@ -61,6 +61,41 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.DeviceInfo
            return Assert.IsAssignableFrom<IReadOnlyList<string>>(data[key]);
        }

+        [Fact]
+        public void NoEspEvidenceAtAll_SuppressesTheEvent()
+        {
+            // afee7ae0 (WDP / plain Entra join): FirstSync has no values and the ESP tracking
+            // key does not exist — an event saying only "SkipUser=unknown, SkipDevice=unknown"
+            // is noise and must not be emitted (mirrors the orchestrator bootstrap's null-gate).
+            using var tmp = new TempDirectory();
+            var logger = new AgentLogger(tmp.Path, AgentLogLevel.Info);
+            var ingress = new FakeSignalIngressSink();
+            var clock = new VirtualClock(T0);
+            var collector = new DeviceInfoCollector(
+                "session-nullgate", "tenant-1",
+                new InformationalEventPost(ingress, clock), logger,
+                signalIngress: null, clock: clock,
+                startupGate: new StartupEventGate(tmp.Path, logger));
+
+            using var skip = new EspSkipConfigurationProbe.ScopedFullOverride(
+                _ => new EspFirstSyncSnapshot(
+                    skipUser: null, skipDevice: null,
+                    blockInStatusPage: null, syncFailureTimeoutMinutes: null));
+            using (new EspTrackingInfoProbe.ScopedOverride(_ => default))
+            {
+                collector.CollectEspConfiguration();
+            }
+
+            Assert.Empty(EspConfigEvents(ingress));
+
+            // A later refresh where real evidence appeared must still emit normally.
+            using (new EspTrackingInfoProbe.ScopedOverride(_ => Snapshot(new[] { DeviceApp1 }, Array.Empty<string>())))
+            {
+                collector.RefreshEspConfiguration(DeviceInfoHost.EspConfigTriggerAppsDevice);
+            }
+            Assert.Single(EspConfigEvents(ingress));
+        }
+
        [Fact]
        public void Refresh_reemits_when_lists_grew_and_stays_silent_when_unchanged()
        {
@@ -17,14 +17,22 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Integration
 {
    /// <summary>
    /// Plan §EspExiting Adapter — wire-through verification of the production EspExiting path:
-    /// <c>ShellCoreTracker.HandleBackfillRecord</c> → <c>EspExited</c> event → inner re-raise on
-    /// <c>EspAndHelloTracker.EspExited</c> → <c>EspAndHelloTrackerAdapter</c> → ingress → engine
-    /// reducer. This is the path the live V2-Host uses; without the coordinator forward the
-    /// EspExiting signal would never reach the engine in production.
+    /// <c>ShellCoreTracker.ProcessEvent</c> (live Shell-Core 62407) → <c>EspExited</c> event →
+    /// inner re-raise on <c>EspAndHelloTracker.EspExited</c> → <c>EspAndHelloTrackerAdapter</c> →
+    /// ingress → engine reducer. Without the coordinator forward the EspExiting signal would
+    /// never reach the engine in production.
    /// <para>
    /// The first test isolates the tracker's <c>EspExited</c> contract (source-event timestamp
-    /// preserved through backfill); the coordinator tests drive the full production chain through
-    /// to the <c>HelloSafety</c> deadline when AccountSetup is already entered.
+    /// preserved rather than collapsed to wall-clock-now); the coordinator tests drive the full
+    /// production chain through to the <c>HelloSafety</c> deadline when AccountSetup is already
+    /// entered.
+    /// </para>
+    /// <para>
+    /// It used to drive that first test through <c>HandleBackfillRecord</c> because the replay is
+    /// easier to call than the event-log watcher — but the replay no longer raises
+    /// <c>EspExited</c> at all (a replayed 62407 cannot be placed in time; see
+    /// <c>ShellCoreTrackerReplayScopeTests</c>), and it never was the production path: the replay
+    /// had no caller when this test was written.
    /// </para>
    /// </summary>
    public sealed class ShellCoreToEngineEspExitingTests
@@ -34,12 +42,12 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Integration
            "CommercialOOBE_ESPProgress_Page_Exiting"; // matches EspExitingPattern in ShellCoreTracker

        [Fact]
-        public void Tracker_backfill_record_raises_EspExited_with_source_timestamp()
+        public void Tracker_live_record_raises_EspExited_with_source_timestamp()
        {
-            // Tracker-level contract: HandleBackfillRecord raises EspExited carrying the source
-            // event time (not Clock.UtcNow). The EspExited→EspExiting signal mapping and SourceOrigin
-            // are covered by the coordinator tests below; here we isolate the backfill→event link
-            // that the production coordinator depends on.
+            // Tracker-level contract: the live 62407 path raises EspExited carrying the source
+            // event time (record.TimeCreated, not Clock.UtcNow). The EspExited→EspExiting signal
+            // mapping and SourceOrigin are covered by the coordinator tests below; here we isolate
+            // the event-log→event link that the production coordinator depends on.
            using var tmp = new TempDirectory();
            var logger = new AgentLogger(tmp.Path, AgentLogLevel.Info);
            var clock = new VirtualClock(ClockNow);
@@ -57,7 +65,12 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Integration
            // Source time IS in the past relative to the clock — verify the tracker carries the
            // historical timestamp on the event rather than collapsing to Clock.UtcNow.
            var sourceTime = ClockNow.AddMinutes(-2);
-            tracker.HandleBackfillRecord(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspExitingDescription, sourceTime);
+            tracker.ProcessEvent(
+                eventId: ShellCoreTracker.EventId_ShellCore_WebAppEvent,
+                description: EspExitingDescription,
+                timestamp: sourceTime,
+                providerName: "Microsoft-Windows-Shell-Core",
+                isBackfill: false);

            Assert.NotNull(captured);
            Assert.Equal(sourceTime, captured!.OccurredAtUtc);
@@ -15,7 +15,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging
    /// </summary>
    public sealed class AgentLoggerTests
    {
-        private static string TodayBaseName => $"agent_{DateTime.Now:yyyyMMdd}";
+        private const string BaseName = "agent";

        [Fact]
        public void Log_writes_to_unsuffixed_base_file_when_dir_is_empty()
@@ -25,7 +25,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging

            logger.Info("hello");

-            var basePath = Path.Combine(tmp.Path, TodayBaseName + ".log");
+            var basePath = Path.Combine(tmp.Path, BaseName + ".log");
            Assert.True(File.Exists(basePath), $"expected base file at {basePath}");
            Assert.Contains("hello", File.ReadAllText(basePath));
        }
@@ -39,17 +39,17 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging

            // Each line ~80 bytes after timestamp/severity envelope; 30 lines clears 1 KB
            // even at the smallest payload. The first lines fill the base file; once the
-            // FileInfo.Length read sees >= 1024 the next call rotates to _002.
+            // FileInfo.Length read sees >= 1024 the next call rotates to -002.
            for (int i = 0; i < 60; i++)
            {
                logger.Info($"line-{i:D4}-padded-with-some-extra-context-to-cross-1KB-quickly");
            }

-            var files = Directory.GetFiles(tmp.Path, TodayBaseName + "*.log").OrderBy(s => s).ToArray();
+            var files = Directory.GetFiles(tmp.Path, BaseName + "*.log").OrderBy(s => s).ToArray();
            Assert.True(files.Length >= 2, $"expected at least 2 segments, got: {string.Join(",", files.Select(Path.GetFileName))}");

-            // The unsuffixed file is the first segment; rotated segments use _002 onward.
-            var rotated = files.FirstOrDefault(p => Path.GetFileNameWithoutExtension(p).EndsWith("_002"));
+            // The unsuffixed file is the first segment; rotated segments use -002 onward.
+            var rotated = files.FirstOrDefault(p => Path.GetFileNameWithoutExtension(p).EndsWith("-002"));
            Assert.NotNull(rotated);
        }

@@ -64,8 +64,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging
                logger.Info($"pad-{i:D4}-content-content-content-content-content-content");
            }

-            var rotatedPath = Path.Combine(tmp.Path, TodayBaseName + "_002.log");
-            Assert.True(File.Exists(rotatedPath), "expected agent_YYYYMMDD_002.log to exist");
+            var rotatedPath = Path.Combine(tmp.Path, BaseName + "-002.log");
+            Assert.True(File.Exists(rotatedPath), "expected agent-002.log to exist");
            var first = File.ReadAllLines(rotatedPath).FirstOrDefault();
            Assert.NotNull(first);
            Assert.Contains("AgentLogger: rotated", first);
@@ -75,23 +75,23 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging
        public void Log_continues_existing_rotation_on_restart_without_overwriting()
        {
            using var tmp = new TempDirectory();
-            // Pre-seed: looks like an earlier process already rotated up to _003.
-            File.WriteAllText(Path.Combine(tmp.Path, TodayBaseName + ".log"), "older-base\n");
-            File.WriteAllText(Path.Combine(tmp.Path, TodayBaseName + "_002.log"), "older-002\n");
-            File.WriteAllText(Path.Combine(tmp.Path, TodayBaseName + "_003.log"), "older-003\n");
+            // Pre-seed: looks like an earlier process already rotated up to -003.
+            File.WriteAllText(Path.Combine(tmp.Path, BaseName + ".log"), "older-base\n");
+            File.WriteAllText(Path.Combine(tmp.Path, BaseName + "-002.log"), "older-002\n");
+            File.WriteAllText(Path.Combine(tmp.Path, BaseName + "-003.log"), "older-003\n");

            var logger = new AgentLogger(tmp.Path, AgentLogLevel.Info, maxFileSizeBytes: 1024L * 1024);
            logger.Info("after-restart");

-            // New entries must land in the highest existing segment (_003), not in a fresh
+            // New entries must land in the highest existing segment (-003), not in a fresh
            // base file. Older content in _003 must be preserved.
-            var resumed = File.ReadAllText(Path.Combine(tmp.Path, TodayBaseName + "_003.log"));
+            var resumed = File.ReadAllText(Path.Combine(tmp.Path, BaseName + "-003.log"));
            Assert.Contains("older-003", resumed);
            Assert.Contains("after-restart", resumed);

            // Older segments are left alone.
-            Assert.Equal("older-base\n", File.ReadAllText(Path.Combine(tmp.Path, TodayBaseName + ".log")));
-            Assert.Equal("older-002\n", File.ReadAllText(Path.Combine(tmp.Path, TodayBaseName + "_002.log")));
+            Assert.Equal("older-base\n", File.ReadAllText(Path.Combine(tmp.Path, BaseName + ".log")));
+            Assert.Equal("older-002\n", File.ReadAllText(Path.Combine(tmp.Path, BaseName + "-002.log")));
        }

        [Fact]
@@ -105,7 +105,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging
            // as plain ASCII, while genuine non-ASCII payload stays untouched.
            logger.Info("check failed \u2014 range 1\u20132 \u2192 done\u2026 \u2018a\u2019 \u201Cb\u201D nb\u00A0sp f\u00FCr M\u00FCller");

-            var text = File.ReadAllText(Path.Combine(tmp.Path, TodayBaseName + ".log"));
+            var text = File.ReadAllText(Path.Combine(tmp.Path, BaseName + ".log"));
            Assert.Contains("check failed - range 1-2 -> done... 'a' \"b\" nb sp f\u00FCr M\u00FCller", text);
        }

@@ -115,8 +115,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging
            using var tmp = new TempDirectory();
            var logger = new AgentLogger(tmp.Path, AgentLogLevel.Info, maxFileSizeBytes: 1024L * 1024);

-            // Hold an exclusive lock on today's file to force AppendAllText to throw.
-            var lockedPath = Path.Combine(tmp.Path, TodayBaseName + ".log");
+            // Hold an exclusive lock on the log file to force AppendAllText to throw.
+            var lockedPath = Path.Combine(tmp.Path, BaseName + ".log");
            File.WriteAllText(lockedPath, ""); // ensure exists
            using var holder = new FileStream(lockedPath, FileMode.Open, FileAccess.ReadWrite, FileShare.None);

@@ -170,5 +170,53 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring
            Assert.Empty(f.StarvedPosts());
            Assert.Empty(coordinator.StarvedAppsReported);
        }
+
+        [Fact]
+        public void Reevaluate_does_not_re_emit_starved_warnings()
+        {
+            // sits-d Cloud-PC fix (2026-08-19): the synthesis re-check now runs on EVERY IME
+            // app-state transition. It must not turn the one-shot starvation warning into a
+            // per-transition stream — the re-check path suppresses the emission entirely
+            // (the per-appId dedupe would swallow the duplicates, but walking the probe
+            // hundreds of times on the IME hot path is waste, not safety).
+            using var f = new Fixture();
+            using var coordinator = f.BuildCoordinator(
+                () => false,
+                () => new[] { StarvedApp("app-1", "Contoso Backgrounds") });
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            var afterExit = f.StarvedPosts().Count;
+            Assert.Equal(1, afterExit);
+
+            for (var i = 0; i < 10; i++) coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Equal(afterExit, f.StarvedPosts().Count);
+            Assert.Single(coordinator.StarvedAppsReported);
+        }
+
+        [Fact]
+        public void Starved_apps_that_settle_later_still_complete_the_enrollment()
+        {
+            // The real sits-d shape: the ESP exits with apps still starved (warning emitted),
+            // the apps then all settle, and the re-check must open the gate — the warning
+            // already on the timeline is history, not a permanent veto.
+            using var f = new Fixture();
+            var settled = false;
+            using var coordinator = f.BuildCoordinator(
+                () => settled,
+                () => new[] { StarvedApp("app-1", "Contoso Backgrounds") });
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            Assert.Single(f.StarvedPosts());
+            Assert.DoesNotContain(f.Ingress.Posted, p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete);
+
+            settled = true;
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Equal(1, f.Ingress.Posted.Count(p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete));
+            Assert.Single(f.StarvedPosts());
+        }
    }
 }
@@ -35,14 +35,25 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring
            public Fixture() { Logger = new AgentLogger(Tmp.Path, AgentLogLevel.Debug); }

            public EspAndHelloTracker BuildCoordinator(Func<bool> settledProbe)
+                => BuildCoordinator(settledProbe, accountSetupActivityProbe: () => true, skipUserEsp: false);
+
+            /// <summary>
+            /// Codex review P1 (2026-08-19): the remembered exit edge is gated on positive evidence
+            /// that the exit is post-AccountSetup, so these two probes decide whether the deferred
+            /// re-check may fire at all.
+            /// </summary>
+            public EspAndHelloTracker BuildCoordinator(
+                Func<bool> settledProbe,
+                Func<bool> accountSetupActivityProbe,
+                bool? skipUserEsp)
            {
                return new EspAndHelloTracker(
                    sessionId: "S1",
                    tenantId: "T1",
                    post: new InformationalEventPost(TrackerPostSink, Clock),
                    logger: Logger,
-                    skipConfigProbe: () => ((bool?)false, (bool?)false),
-                    accountSetupActivityProbe: () => true,
+                    skipConfigProbe: () => (skipUserEsp, (bool?)false),
+                    accountSetupActivityProbe: accountSetupActivityProbe,
                    userEspAppsSettledProbe: settledProbe);
            }

@@ -159,5 +170,174 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring
            var posted = Assert.Single(f.Ingress.Posted);
            Assert.Equal(DecisionSignalKind.EspExiting, posted.Kind);
        }
+
+        // ------------------------------------------------------------------------------
+        // sits-d Cloud-PC fix (2026-08-19) — the synthesis is no longer edge-only.
+        // Sessions 8110e262 / a89aac2d: the ESP page exited while 138 required user-ESP apps
+        // were still in flight, they all reached a terminal state (0 failed) minutes later,
+        // and because nothing re-checked, the enrollment never completed.
+        // ------------------------------------------------------------------------------
+
+        [Fact]
+        public void Reevaluate_after_apps_settle_synthesizes_without_a_second_exit()
+        {
+            using var f = new Fixture();
+            var settled = false;
+            using var coordinator = f.BuildCoordinator(() => settled);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            Assert.DoesNotContain(f.Ingress.Posted, p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete);
+
+            // The apps settle later; only the IME app-state callback fires — there is NO second
+            // ESP exit on a real device, which is exactly why the edge-only version starved.
+            settled = true;
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Equal(1, f.Ingress.Posted.Count(p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete));
+            Assert.True(coordinator.UserAppsSettledSynthesisFiredForTest);
+
+            var info = Assert.Single(f.TrackerPostSink.Posted);
+            var data = Assert.IsAssignableFrom<System.Collections.Generic.IReadOnlyDictionary<string, object>>(info.TypedPayload);
+            Assert.Equal("esp_exited_user_apps_settled_category_unresolved", data["fallbackReason"]);
+        }
+
+        [Fact]
+        public void Reevaluate_without_an_observed_esp_exit_never_synthesizes()
+        {
+            // The gate needs BOTH facts. Settled apps alone must never open it — otherwise every
+            // quiet moment during AccountSetup would look like completion.
+            using var f = new Fixture();
+            using var coordinator = f.BuildCoordinator(() => true);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Empty(f.Ingress.Posted);
+            Assert.Empty(f.TrackerPostSink.Posted);
+            Assert.False(coordinator.UserAppsSettledSynthesisFiredForTest);
+        }
+
+        [Fact]
+        public void Reevaluate_is_idempotent_after_the_synthesis_fired()
+        {
+            // The IME callback fires per app-state transition — on these tenants that is 138+
+            // times. The synthesis must stay fire-once.
+            using var f = new Fixture();
+            using var coordinator = f.BuildCoordinator(() => true);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            for (var i = 0; i < 20; i++) coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Equal(1, f.Ingress.Posted.Count(p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete));
+            Assert.Single(f.TrackerPostSink.Posted);
+        }
+
+        // ------------------------------------------------------------------------------
+        // Codex review P1 (2026-08-19): Shell-Core raises 62407 at EVERY ESP phase transition.
+        // Remembering the intermediate DeviceSetup→AccountSetup exit would let the deferred
+        // re-check open the strong AccountSetup gate as soon as the last user app settles —
+        // while the AccountSetup page is still up and its other subcategories still running.
+        // ------------------------------------------------------------------------------
+
+        [Fact]
+        public void Intermediate_device_exit_is_not_remembered_as_the_edge()
+        {
+            using var f = new Fixture();
+            var settled = false;
+            // Classic user-driven enrollment (SkipUser=false) that has NOT reached AccountSetup:
+            // this 62407 is the DeviceSetup→AccountSetup transition, not the final exit.
+            using var coordinator = f.BuildCoordinator(
+                () => settled, accountSetupActivityProbe: () => false, skipUserEsp: false);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+
+            // Apps settle afterwards — the level is reached, but the edge was never a valid one.
+            settled = true;
+            for (var i = 0; i < 10; i++) coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.DoesNotContain(f.Ingress.Posted, p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete);
+            Assert.False(coordinator.UserAppsSettledSynthesisFiredForTest);
+            Assert.Empty(f.TrackerPostSink.Posted);
+        }
+
+        [Fact]
+        public void Unknown_skip_user_is_treated_as_unconfirmed()
+        {
+            // Erring strict costs at worst today's stall; erring loose costs a premature Succeeded.
+            using var f = new Fixture();
+            var settled = false;
+            using var coordinator = f.BuildCoordinator(
+                () => settled, accountSetupActivityProbe: () => false, skipUserEsp: null);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            settled = true;
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.False(coordinator.UserAppsSettledSynthesisFiredForTest);
+        }
+
+        [Fact]
+        public void Skip_user_profile_confirms_the_device_exit_as_final()
+        {
+            // SkipUser=true means there is no user ESP at all — the Device-ESP exit IS the final
+            // one and no second exit is coming, so the edge is legitimately remembered.
+            using var f = new Fixture();
+            var settled = false;
+            using var coordinator = f.BuildCoordinator(
+                () => settled, accountSetupActivityProbe: () => false, skipUserEsp: true);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            settled = true;
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Equal(1, f.Ingress.Posted.Count(p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete));
+        }
+
+        [Fact]
+        public void Account_setup_activity_confirms_the_edge_for_the_deferred_recheck()
+        {
+            // The real reboot shape: AccountSetup activity is visible in the registry, the final
+            // exit lands, the apps settle a moment later.
+            using var f = new Fixture();
+            var settled = false;
+            using var coordinator = f.BuildCoordinator(
+                () => settled, accountSetupActivityProbe: () => true, skipUserEsp: false);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            Assert.DoesNotContain(f.Ingress.Posted, p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete);
+
+            settled = true;
+            coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            Assert.Equal(1, f.Ingress.Posted.Count(p => p.Kind == DecisionSignalKind.AccountSetupProvisioningComplete));
+        }
+
+        // NOTE: the "replayed exit" cases that used to live here are gone by construction —
+        // ShellCoreTracker never re-raises a 62407 from the replay any more, so no backfilled exit
+        // can reach this handler at all. That contract is pinned one layer up, in
+        // ShellCoreTrackerReplayScopeTests, together with the reducer-side proof of why it matters
+        // (ClassicEspExitingOnRestoredStateTests).
+
+        [Fact]
+        public void Reevaluate_stays_silent_while_apps_are_still_unsettled()
+        {
+            using var f = new Fixture();
+            using var coordinator = f.BuildCoordinator(() => false);
+            using var adapter = new EspAndHelloTrackerAdapter(coordinator, f.Ingress, f.Clock);
+
+            coordinator.TriggerEspExitedForTest(Fixed);
+            for (var i = 0; i < 5; i++) coordinator.ReevaluateUserAppsSettledSynthesis();
+
+            var posted = Assert.Single(f.Ingress.Posted);
+            Assert.Equal(DecisionSignalKind.EspExiting, posted.Kind);
+            Assert.False(coordinator.UserAppsSettledSynthesisFiredForTest);
+        }
    }
 }
@@ -25,7 +25,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Gather

        public void Dispose() => _tmp.Dispose();

-        private string LogPath => Path.Combine(_tmp.Path, "sub", "gather_rules_debug.log");
+        private string LogPath => Path.Combine(_tmp.Path, "sub", "gather-rules-debug.log");

        [Fact]
        public void Write_produces_pipe_delimited_line_and_creates_directory_lazily()
@@ -73,7 +73,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Gather
            for (int i = 0; i < 20; i++)
                log.Write("RULE-1", GatherRuleDebugLog.StageExec, new string('x', 100));

-            var oldPath = Path.Combine(Path.GetDirectoryName(LogPath), "gather_rules_debug.old.log");
+            var oldPath = Path.Combine(Path.GetDirectoryName(LogPath), "gather-rules-debug.old.log");
            Assert.True(File.Exists(oldPath), "expected one .old rotation generation");
            Assert.True(File.Exists(LogPath));
            Assert.Contains("-- rotated", File.ReadAllText(LogPath) + File.ReadAllText(oldPath));
@@ -28,7 +28,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Gather
        public GatherRuleExecutorDebugLogTests()
        {
            var logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
-            _debugLogPath = Path.Combine(_tmp.Path, "gather_rules_debug.log");
+            _debugLogPath = Path.Combine(_tmp.Path, "gather-rules-debug.log");
            _executor = new GatherRuleExecutor(
                "sess", "tenant", _ => { }, logger,
                debugLogPath: _debugLogPath)
@@ -32,7 +32,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Gather
        {
            Directory.CreateDirectory(_outsideUsers);
            var logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
-            _debugLogPath = Path.Combine(_tmp.Path, "gather_rules_debug.log");
+            _debugLogPath = Path.Combine(_tmp.Path, "gather-rules-debug.log");
            _context = new GatherRuleContext(
                logger, "sess", "tenant",
                evt => _events.Add(evt),
@@ -0,0 +1,109 @@
+using System;
+using System.Collections.Generic;
+using System.IO;
+using System.Threading;
+using System.Threading.Tasks;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
+{
+    /// <summary>
+    /// Pins the per-FILE isolation of the offset measurement across a full read cycle.
+    ///
+    /// <para>
+    /// Background (2026-08-20, session e9753578): the field showed "+02:00 measured for
+    /// IntuneManagementExtension.log" although that file held no +2-era line — the anchor had
+    /// crossed file boundaries. The committed code was proven innocent (this very scenario is
+    /// green here); the leak lived in a binary built from an uncommitted tree. This test keeps
+    /// the property pinned so a real regression of the file scoping can never ship silently
+    /// again — it replays the exact field pass structure: a NEW file appearing mid-run with a
+    /// different writer era than the file already being tailed.
+    /// </para>
+    /// </summary>
+    public sealed class CmTraceCalibratorFileIsolationTests
+    {
+        private static readonly DateTime T0 = new DateTime(2026, 8, 20, 12, 13, 0, DateTimeKind.Utc);
+
+        private static List<ImeLogPattern> Patterns() => new List<ImeLogPattern>
+        {
+            new ImeLogPattern
+            {
+                PatternId = "T-MARK", Category = "always", Enabled = true,
+                Pattern = @"marker (?<n>\d+)",
+                Action = "noop",
+                Parameters = new Dictionary<string, string>(),
+            },
+        };
+
+        private static string Line(string message, DateTime utcInstant, TimeSpan writerOffset)
+        {
+            var local = utcInstant + writerOffset;
+            return $"<![LOG[{message}]LOG]!><time=\"{local:HH:mm:ss.fffffff}\" date=\"{local:M-d-yyyy}\" " +
+                   "component=\"X\" context=\"\" type=\"1\" thread=\"1\" file=\"\">";
+        }
+
+        [Fact]
+        public async Task NewFileWithOtherEra_MustNotRecalibrateTheOldFile()
+        {
+            var pdt = TimeSpan.FromHours(-7);   // IME service era
+            var cest = TimeSpan.FromHours(2);   // fresh child-process era
+
+            using var tmp = new TempDirectory();
+            var now = T0;
+            var tracker = new ImeLogTracker(
+                logFolder: tmp.Path,
+                patterns: Patterns(),
+                logger: new AgentLogger(tmp.Path, AgentLogLevel.Info));
+            try
+            {
+                tracker.UtcNowProvider = () => now;
+                var imeLog = Path.Combine(tmp.Path, "IntuneManagementExtension.log");
+                var execLog = Path.Combine(tmp.Path, "AgentExecutor.log");
+
+                // Pass 1: IME.log first sight (no calibration).
+                File.AppendAllText(imeLog, Line("marker 1", now, pdt) + Environment.NewLine);
+                await tracker.CheckLogFilesAsync(CancellationToken.None);
+
+                // Pass 2: IME.log grew -> measures -7.
+                now = T0.AddSeconds(10);
+                File.AppendAllText(imeLog, Line("marker 2", now, pdt) + Environment.NewLine);
+                await tracker.CheckLogFilesAsync(CancellationToken.None);
+
+                TimeSpan imeMeasured;
+                Assert.True(tracker.OffsetCalibrator.TryGetOffset("IntuneManagementExtension.log", out imeMeasured));
+                Assert.Equal(pdt, imeMeasured);
+
+                // Pass 3: AgentExecutor.log appears for the FIRST time with fresh +2-era lines
+                // while IME.log grows too — the exact field pass structure. The +2 anchor must
+                // never land under IME.log's key.
+                now = T0.AddSeconds(20);
+                File.AppendAllText(execLog, Line("marker 3", now, cest) + Environment.NewLine);
+                File.AppendAllText(imeLog, Line("marker 4", now, pdt) + Environment.NewLine);
+                await tracker.CheckLogFilesAsync(CancellationToken.None);
+
+                Assert.True(tracker.OffsetCalibrator.TryGetOffset("IntuneManagementExtension.log", out imeMeasured));
+                Assert.Equal(pdt, imeMeasured);
+
+                // Pass 4: both grow — each file measures its own writer's era.
+                now = T0.AddSeconds(30);
+                File.AppendAllText(execLog, Line("marker 5", now, cest) + Environment.NewLine);
+                File.AppendAllText(imeLog, Line("marker 6", now, pdt) + Environment.NewLine);
+                await tracker.CheckLogFilesAsync(CancellationToken.None);
+
+                TimeSpan execMeasured;
+                Assert.True(tracker.OffsetCalibrator.TryGetOffset("AgentExecutor.log", out execMeasured));
+                Assert.Equal(cest, execMeasured);
+                Assert.True(tracker.OffsetCalibrator.TryGetOffset("IntuneManagementExtension.log", out imeMeasured));
+                Assert.Equal(pdt, imeMeasured);
+            }
+            finally
+            {
+                tracker.Dispose();
+            }
+        }
+    }
+}
@@ -67,29 +67,34 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
            Assert.Equal("EnforcementState: Installing app X", entry.Message);
            Assert.Equal("AppEnforce", entry.Component);
            Assert.Equal(1, entry.Type);
-            Assert.NotEqual(default, entry.Timestamp);
+            Assert.True(entry.HasTimestamp);
+            Assert.NotEqual(default, entry.LocalTimestamp);
+            // Bias-less line: the parser refuses to guess the writer's zone, so no UTC value.
+            Assert.Null(entry.BiasMinutes);
+            Assert.Null(entry.TimestampUtc);
+            Assert.Equal(DateTimeKind.Unspecified, entry.LocalTimestamp.Kind);
        }

-        // ── Structurally valid but unparseable timestamp → UtcNow fallback ────
+        // ── Structurally valid but unparseable timestamp → flagged, not invented ──

        [Fact]
-        public void TryParseLine_falls_back_to_utcnow_for_unparseable_timestamp()
+        public void TryParseLine_flags_unparseable_timestamp_instead_of_inventing_one()
        {
            // time/date satisfy the regex character classes ([\d:.]+ / [\d-]+) so the line MATCHES,
-            // but "13-45-2026" / "25:99:99" fail every DateTime format → the parser falls back to
-            // DateTime.UtcNow (CmTraceLogParser.cs:57) instead of throwing.
-            var before = DateTime.UtcNow;
+            // but "13-45-2026" / "25:99:99" fail every DateTime format. The parser used to stamp
+            // DateTime.UtcNow here, which made a fabricated value indistinguishable from a real
+            // one downstream. It now reports HasTimestamp=false and leaves the choice of fallback
+            // to the caller, which is the only party that knows what a safe default is in context.
            var line = CmTraceLine("some message", "25:99:99.0000000", "13-45-2026");

            var ok = CmTraceLogParser.TryParseLine(line, out var entry);
-            var after = DateTime.UtcNow;

            Assert.True(ok);
            Assert.NotNull(entry);
            Assert.Equal("some message", entry.Message);
-            // Don't assert an exact instant — only that the fallback stamped a fresh "now"
-            // (a successfully-parsed date would land in 2026, far outside this window).
-            Assert.InRange(entry.Timestamp, before.AddSeconds(-5), after.AddSeconds(5));
+            Assert.False(entry.HasTimestamp);
+            Assert.Equal(default, entry.LocalTimestamp);
+            Assert.Null(entry.TimestampUtc);
        }

        // ── UTC-bias suffix on the time field → honored, not dropped ──────────
@@ -108,10 +113,14 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime

            Assert.True(ok);
            Assert.NotNull(entry);
+            // A writer-declared bias IS the fact we otherwise have to measure, so it is honored
+            // and resolved to UTC right here — unlike the bias-less form.
+            Assert.Equal(expectedOffsetMinutes, entry.BiasMinutes);
+            Assert.NotNull(entry.TimestampUtc);
            Assert.Equal(
                new DateTime(2026, 7, 29, 11, 46, 19, DateTimeKind.Utc).AddTicks(226610).AddMinutes(expectedOffsetMinutes),
-                entry.Timestamp);
-            Assert.Equal(DateTimeKind.Utc, entry.Timestamp.Kind);
+                entry.TimestampUtc!.Value);
+            Assert.Equal(DateTimeKind.Utc, entry.TimestampUtc!.Value.Kind);
        }

        // ── Oversized line → parses, no throw, no truncation of the message ───
@@ -0,0 +1,190 @@
+using System;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
+{
+    /// <summary>
+    /// Pins the measurement contract of <see cref="CmTraceOffsetCalibrator"/>.
+    ///
+    /// <para>
+    /// The cases are taken from real sessions: +1 h (GMT to W. Europe, session bfff9b1c) and
+    /// -17 h (a writer left on the Pacific OOBE default while the agent had moved to
+    /// E. Australia). The backlog case is the one the residual guard cannot catch on its own and
+    /// is the reason the freshness rule exists.
+    /// </para>
+    /// </summary>
+    public class CmTraceOffsetCalibratorTests
+    {
+        private const string Source = "IntuneManagementExtension.log";
+        private static readonly DateTime UtcNow = new DateTime(2026, 08, 20, 07, 31, 46, DateTimeKind.Utc);
+
+        /// <summary>A line written "now" by a writer that believes it is at <paramref name="offset"/>.</summary>
+        private static DateTime LineWrittenNow(TimeSpan offset, DateTime utcNow)
+            => DateTime.SpecifyKind(utcNow + offset, DateTimeKind.Unspecified);
+
+        [Theory]
+        [InlineData(2)]     // CEST — the bfff9b1c writer
+        [InlineData(1)]     // BST — what the agent wrongly assumed there
+        [InlineData(-7)]    // PDT — the OOBE default seen in the -17 h sessions
+        [InlineData(10)]    // E. Australia
+        [InlineData(14)]    // Line Islands, the upper bound
+        [InlineData(-12)]   // Dateline, the lower bound
+        public void MeasuresWholeHourOffsets(int hours)
+        {
+            var sut = new CmTraceOffsetCalibrator();
+            var offset = TimeSpan.FromHours(hours);
+
+            Assert.True(sut.TryCalibrate(Source, LineWrittenNow(offset, UtcNow), UtcNow));
+
+            TimeSpan measured;
+            Assert.True(sut.TryGetOffset(Source, out measured));
+            Assert.Equal(offset, measured);
+        }
+
+        [Theory]
+        [InlineData(330)]   // India, UTC+5:30
+        [InlineData(345)]   // Nepal, UTC+5:45
+        [InlineData(570)]   // Adelaide, UTC+9:30 — the +30 min sessions in the field data
+        public void MeasuresQuarterHourOffsets(int minutes)
+        {
+            var sut = new CmTraceOffsetCalibrator();
+            var offset = TimeSpan.FromMinutes(minutes);
+
+            Assert.True(sut.TryCalibrate(Source, LineWrittenNow(offset, UtcNow), UtcNow));
+
+            TimeSpan measured;
+            Assert.True(sut.TryGetOffset(Source, out measured));
+            Assert.Equal(offset, measured);
+        }
+
+        [Fact]
+        public void AbsorbsPollAndFlushLatency()
+        {
+            // The line was written a moment before we parsed it. That lag must vanish into the
+            // grid rather than shift the measured offset.
+            var sut = new CmTraceOffsetCalibrator();
+            var lineLocal = LineWrittenNow(TimeSpan.FromHours(2), UtcNow.AddMilliseconds(-450));
+
+            Assert.True(sut.TryCalibrate(Source, lineLocal, UtcNow));
+
+            TimeSpan measured;
+            Assert.True(sut.TryGetOffset(Source, out measured));
+            Assert.Equal(TimeSpan.FromHours(2), measured);
+        }
+
+        [Fact]
+        public void RejectsBacklogLine_EvenWhenItRoundsCleanly()
+        {
+            // THE case the residual guard cannot catch alone: a line exactly 30 minutes old is a
+            // clean multiple of the grid, so it rounds with zero residual — and would calibrate
+            // the offset half an hour wrong. Only the caller's freshness rule prevents this from
+            // ever being offered; this test pins that a 30-minute-old line does not silently
+            // produce the true offset.
+            var sut = new CmTraceOffsetCalibrator();
+            var thirtyMinutesOld = LineWrittenNow(TimeSpan.FromHours(2), UtcNow.AddMinutes(-30));
+
+            Assert.True(sut.TryCalibrate(Source, thirtyMinutesOld, UtcNow));
+
+            TimeSpan measured;
+            Assert.True(sut.TryGetOffset(Source, out measured));
+            Assert.Equal(TimeSpan.FromMinutes(90), measured);
+            Assert.NotEqual(TimeSpan.FromHours(2), measured);
+        }
+
+        [Fact]
+        public void RejectsOffGridCandidate()
+        {
+            // 7 minutes off the grid: not fresh, and not a timezone either.
+            var sut = new CmTraceOffsetCalibrator();
+            var offGrid = LineWrittenNow(TimeSpan.FromHours(2), UtcNow.AddMinutes(-7));
+
+            Assert.False(sut.TryCalibrate(Source, offGrid, UtcNow));
+
+            TimeSpan ignored;
+            Assert.False(sut.TryGetOffset(Source, out ignored));
+        }
+
+        [Fact]
+        public void RejectsOffsetOutsideAnyRealTimezone()
+        {
+            var sut = new CmTraceOffsetCalibrator();
+            var absurd = LineWrittenNow(TimeSpan.FromHours(20), UtcNow);
+
+            Assert.False(sut.TryCalibrate(Source, absurd, UtcNow));
+        }
+
+        [Fact]
+        public void SelfHeals_WhenTheWritingProcessPicksUpANewZone()
+        {
+            // The writer restarts mid-session and now believes CEST instead of the stale BST.
+            var sut = new CmTraceOffsetCalibrator();
+            Assert.True(sut.TryCalibrate(Source, LineWrittenNow(TimeSpan.FromHours(1), UtcNow), UtcNow));
+
+            var later = UtcNow.AddMinutes(5);
+            Assert.True(sut.TryCalibrate(Source, LineWrittenNow(TimeSpan.FromHours(2), later), later));
+
+            TimeSpan measured;
+            Assert.True(sut.TryGetOffset(Source, out measured));
+            Assert.Equal(TimeSpan.FromHours(2), measured);
+        }
+
+        [Fact]
+        public void IgnoresAnchorOlderThanTheCurrentOne()
+        {
+            var sut = new CmTraceOffsetCalibrator();
+            Assert.True(sut.TryCalibrate(Source, LineWrittenNow(TimeSpan.FromHours(2), UtcNow), UtcNow));
+
+            // An out-of-order line from before the current anchor must not move the offset back.
+            var earlier = UtcNow.AddMinutes(-10);
+            Assert.False(sut.TryCalibrate(Source, LineWrittenNow(TimeSpan.FromHours(1), earlier), earlier));
+
+            TimeSpan measured;
+            Assert.True(sut.TryGetOffset(Source, out measured));
+            Assert.Equal(TimeSpan.FromHours(2), measured);
+        }
+
+        [Fact]
+        public void KeepsSourcesIndependent()
+        {
+            // IntuneManagementExtension.log and AppWorkload.log are written by different
+            // processes and may hold different beliefs.
+            var sut = new CmTraceOffsetCalibrator();
+            Assert.True(sut.TryCalibrate("IntuneManagementExtension.log", LineWrittenNow(TimeSpan.FromHours(2), UtcNow), UtcNow));
+            Assert.True(sut.TryCalibrate("AppWorkload.log", LineWrittenNow(TimeSpan.FromHours(-7), UtcNow), UtcNow));
+
+            TimeSpan ime, appWorkload;
+            Assert.True(sut.TryGetOffset("IntuneManagementExtension.log", out ime));
+            Assert.True(sut.TryGetOffset("AppWorkload.log", out appWorkload));
+            Assert.Equal(TimeSpan.FromHours(2), ime);
+            Assert.Equal(TimeSpan.FromHours(-7), appWorkload);
+        }
+
+        [Fact]
+        public void ResolvesTheRealFieldLine_FromSessionBfff9b1c()
+        {
+            // Raw line: <![LOG[Agent version is: 1.104.102.0]LOG]!><time="09:31:46.5192284" ...>
+            // Server-side ReceivedAt puts the true UTC at 07:31:46.4. The old code produced
+            // 08:31:46.5192284 — local minus the agent's stale +1 h belief.
+            var sut = new CmTraceOffsetCalibrator();
+            var trueUtc = new DateTime(2026, 08, 20, 07, 31, 46, 400, DateTimeKind.Utc);
+            var lineLocal = new DateTime(2026, 08, 20, 09, 31, 46, 519, DateTimeKind.Unspecified);
+
+            Assert.True(sut.TryCalibrate(Source, lineLocal, trueUtc));
+
+            DateTime resolved;
+            Assert.True(sut.TryResolveUtc(Source, lineLocal, out resolved));
+            Assert.Equal(DateTimeKind.Utc, resolved.Kind);
+            Assert.Equal(new DateTime(2026, 08, 20, 07, 31, 46, 519, DateTimeKind.Utc), resolved);
+        }
+
+        [Fact]
+        public void ReportsUncalibratedSource_SoTheCallerCanFlagIt()
+        {
+            var sut = new CmTraceOffsetCalibrator();
+
+            DateTime resolved;
+            Assert.False(sut.TryResolveUtc(Source, UtcNow, out resolved));
+        }
+    }
+}
@@ -0,0 +1,441 @@
+using System;
+using System.Collections.Generic;
+using System.IO;
+using System.Threading;
+using System.Threading.Tasks;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Shared.Logging;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
+{
+    /// <summary>
+    /// Per-line self-anchoring — the era-aware successor to the reverted per-file offset
+    /// application (04b1a7c6).
+    ///
+    /// <para>
+    /// The property under test: a line read in a provably FRESH pass resolves to the instant it
+    /// was written, whatever timezone its writer believed — and neighbouring lines from writers
+    /// with DIFFERENT beliefs each resolve to their own era, because no cross-line state is
+    /// involved. That interleaving (fixture: AgentExecutor.log with PDT and CEST children in one
+    /// file, flipping both ways) is exactly what broke every cross-line anchor design.
+    /// </para>
+    ///
+    /// <para>
+    /// The freshness boundary is equally load-bearing: backlog (first sight, restart catch-up,
+    /// stalled polls) must NEVER anchor, because an old line's age can round onto the 15-minute
+    /// offset grid. Those paths keep the uniform reader-zone fallback.
+    /// </para>
+    /// </summary>
+    public sealed class ImeLogTrackerLineAnchoringTests
+    {
+        private static readonly DateTime T0 = new DateTime(2026, 8, 20, 12, 13, 0, DateTimeKind.Utc);
+
+        private static List<ImeLogPattern> Patterns() => new List<ImeLogPattern>
+        {
+            new ImeLogPattern
+            {
+                PatternId = "T-ALL", Category = "always", Enabled = true,
+                Pattern = @"marker (?<n>\d+)",
+                Action = "noop",
+                Parameters = new Dictionary<string, string>(),
+            },
+        };
+
+        /// <summary>A CMTrace line as a writer holding <paramref name="writerOffset"/> renders instant <paramref name="utcInstant"/>.</summary>
+        private static string Line(string message, DateTime utcInstant, TimeSpan writerOffset)
+        {
+            var local = utcInstant + writerOffset;
+            return $"<![LOG[{message}]LOG]!><time=\"{local:HH:mm:ss.fffffff}\" date=\"{local:M-d-yyyy}\" " +
+                   "component=\"X\" context=\"\" type=\"1\" thread=\"1\" file=\"\">";
+        }
+
+        private sealed class Harness : IDisposable
+        {
+            private readonly TempDirectory _tmp = new TempDirectory();
+            public ImeLogTracker Tracker { get; }
+            public DateTime Now { get; set; } = T0;
+
+            public Harness(string? stateDirectory = null)
+            {
+                Tracker = new ImeLogTracker(
+                    logFolder: _tmp.Path,
+                    patterns: Patterns(),
+                    logger: new AgentLogger(_tmp.Path, AgentLogLevel.Info),
+                    stateDirectory: stateDirectory);
+                Tracker.UtcNowProvider = () => Now;
+            }
+
+            public string PathOf(string fileName) => Path.Combine(_tmp.Path, fileName);
+
+            public void Append(string fileName, string line)
+                => File.AppendAllText(PathOf(fileName), line + Environment.NewLine);
+
+            public Task Pass() => Tracker.CheckLogFilesAsync(CancellationToken.None);
+
+            public void Dispose()
+            {
+                Tracker.Dispose();
+                _tmp.Dispose();
+            }
+        }
+
+        [Theory]
+        // The writer's belief. A fresh line must resolve to the instant it was written,
+        // WHATEVER that belief is — including agreement with this process (the majority case,
+        // which a fix to the agent's own zone cache would have broken).
+        [InlineData(2)]     // CEST
+        [InlineData(1)]     // BST
+        [InlineData(0)]     // UTC
+        [InlineData(-7)]    // PDT — the OOBE default behind the -9 h and -17 h field cases
+        [InlineData(10)]    // E. Australia
+        public async Task FreshLine_ResolvesToItsTrueInstant_ForAnyWriterBelief(int writerOffsetHours)
+        {
+            var writerOffset = TimeSpan.FromHours(writerOffsetHours);
+            using var h = new Harness();
+
+            // First sight: backlog, must not anchor.
+            h.Append("IntuneManagementExtension.log", Line("marker 1", h.Now, writerOffset));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            var writtenAt = h.Now.AddMilliseconds(-80);   // written just before the poll sees it
+            h.Append("IntuneManagementExtension.log", Line("marker 2", writtenAt, writerOffset));
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h.Tracker.LastMatchedSourceOffsetOrigin);
+            Assert.Equal(writtenAt, h.Tracker.LastMatchedLogTimestamp);
+            Assert.Equal(writerOffsetHours * 60, h.Tracker.LastMatchedSourceOffsetMinutes);
+        }
+
+        [Fact]
+        public async Task InterleavedEras_InOneGrowingPass_EachLineResolvesToItsOwnEra()
+        {
+            // The e9753578 file shape: two writer processes with different zone beliefs
+            // interleaved in ONE file. Any per-file offset gets one of them wrong by 9 h;
+            // per-line anchoring must get both right within the same chunk.
+            var pdt = TimeSpan.FromHours(-7);
+            var cest = TimeSpan.FromHours(2);
+            using var h = new Harness();
+
+            h.Append("AgentExecutor.log", Line("marker 1", h.Now, pdt));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            var wrotePdt = h.Now.AddMilliseconds(-90);
+            var wroteCest = h.Now.AddMilliseconds(-50);
+            h.Append("AgentExecutor.log", Line("marker 2", wrotePdt, pdt));
+            h.Append("AgentExecutor.log", Line("marker 3", wroteCest, cest));
+
+            var resolved = new List<(DateTime? Ts, CmTraceOffsetOrigin Origin, int? Offset)>();
+            Action<string> capture = _ => resolved.Add((
+                h.Tracker.LastMatchedLogTimestamp,
+                h.Tracker.LastMatchedSourceOffsetOrigin,
+                h.Tracker.LastMatchedSourceOffsetMinutes));
+            h.Tracker.OnPatternMatched += capture;
+            try
+            {
+                await h.Pass();
+            }
+            finally
+            {
+                h.Tracker.OnPatternMatched -= capture;
+            }
+
+            Assert.Equal(2, resolved.Count);
+            Assert.Equal(wrotePdt, resolved[0].Ts);
+            Assert.Equal(-420, resolved[0].Offset);
+            Assert.Equal(wroteCest, resolved[1].Ts);
+            Assert.Equal(120, resolved[1].Offset);
+            Assert.All(resolved, r => Assert.Equal(CmTraceOffsetOrigin.LineAnchored, r.Origin));
+        }
+
+        [Fact]
+        public async Task FirstSightBacklog_FallsBackToReaderZone()
+        {
+            using var h = new Harness();
+
+            h.Append("IntuneManagementExtension.log", Line("marker 1", h.Now.AddHours(-3), TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.None, h.Tracker.LastMatchedSourceOffsetOrigin);
+        }
+
+        [Fact]
+        public async Task FileFirstSeenEmpty_ItsFirstContentIsFresh()
+        {
+            // AgentExecutor.log in the field: the file APPEARS mid-enrollment. Seeing it empty
+            // (or not existing content-wise) counts as an observation, so its very first lines
+            // are provably written between passes and may anchor. This closes the warm-up gap
+            // for exactly the file whose eras flip the most.
+            using var h = new Harness();
+
+            File.WriteAllText(h.PathOf("AgentExecutor.log"), string.Empty);
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(5);
+            var writtenAt = h.Now.AddMilliseconds(-60);
+            h.Append("AgentExecutor.log", Line("marker 1", writtenAt, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h.Tracker.LastMatchedSourceOffsetOrigin);
+            Assert.Equal(writtenAt, h.Tracker.LastMatchedLogTimestamp);
+        }
+
+        [Fact]
+        public async Task PollGapBeyondFreshWindow_FallsBack()
+        {
+            // A stalled agent (GC, CPU starvation) re-polls after a long gap: the new bytes span
+            // the whole gap and their age is unbounded, so the pass must not anchor — even
+            // though most of its lines may in fact be recent. Conservative by design.
+            using var h = new Harness();
+
+            h.Append("IntuneManagementExtension.log", Line("marker 1", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+            h.Now = T0.AddSeconds(10);
+            h.Append("IntuneManagementExtension.log", Line("marker 2", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h.Tracker.LastMatchedSourceOffsetOrigin);
+
+            // Gap far beyond FreshLineMaxAge.
+            h.Now = h.Now + ImeLogTracker.FreshLineMaxAge + TimeSpan.FromSeconds(10);
+            h.Append("IntuneManagementExtension.log", Line("marker 3", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.None, h.Tracker.LastMatchedSourceOffsetOrigin);
+
+            // And the very next tight poll is fresh again.
+            h.Now = h.Now.AddSeconds(1);
+            h.Append("IntuneManagementExtension.log", Line("marker 4", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h.Tracker.LastMatchedSourceOffsetOrigin);
+        }
+
+        [Fact]
+        public async Task RestartWithRestoredBookmark_FirstPassIsBacklog_SecondPassAnchors()
+        {
+            // The persisted position bookmark survives a restart; the freshness guarantee must
+            // not — the first pass after a restart reads the downtime backlog, whose lines can
+            // be arbitrarily old.
+            using var stateDir = new TempDirectory();
+            using var h = new Harness(stateDirectory: stateDir.Path);
+
+            h.Append("IntuneManagementExtension.log", Line("marker 1", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+            h.Tracker.SaveStateForTest();
+
+            // "Restart": a second tracker over the same folder restores the bookmark.
+            using var h2 = new HarnessOver(h, stateDir.Path);
+            h2.Tracker.LoadStateForTest();
+
+            // Backlog written during the downtime — 30 min old, exactly on the offset grid,
+            // the nastiest possible backlog shape. Must NOT anchor.
+            h2.Now = T0.AddMinutes(30);
+            h2.Append(Line("marker 2", T0.AddSeconds(20), TimeSpan.FromHours(2)));
+            await h2.Pass();
+            Assert.Equal(CmTraceOffsetOrigin.None, h2.Tracker.LastMatchedSourceOffsetOrigin);
+
+            // The next tight poll is fresh again.
+            h2.Now = h2.Now.AddSeconds(1);
+            var writtenAt = h2.Now.AddMilliseconds(-70);
+            h2.Append(Line("marker 3", writtenAt, TimeSpan.FromHours(2)));
+            await h2.Pass();
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h2.Tracker.LastMatchedSourceOffsetOrigin);
+            Assert.Equal(writtenAt, h2.Tracker.LastMatchedLogTimestamp);
+        }
+
+        /// <summary>Second tracker over the FIRST harness's log folder — the "restarted agent".</summary>
+        private sealed class HarnessOver : IDisposable
+        {
+            private readonly string _logFolder;
+            public ImeLogTracker Tracker { get; }
+            public DateTime Now { get; set; }
+
+            public HarnessOver(Harness original, string stateDirectory)
+            {
+                _logFolder = Path.GetDirectoryName(original.PathOf("x"));
+                Tracker = new ImeLogTracker(
+                    logFolder: _logFolder,
+                    patterns: Patterns(),
+                    logger: new AgentLogger(_logFolder, AgentLogLevel.Info),
+                    stateDirectory: stateDirectory);
+                Tracker.UtcNowProvider = () => Now;
+            }
+
+            public void Append(string line)
+                => File.AppendAllText(Path.Combine(_logFolder, "IntuneManagementExtension.log"), line + Environment.NewLine);
+
+            public Task Pass() => Tracker.CheckLogFilesAsync(CancellationToken.None);
+
+            public void Dispose() => Tracker.Dispose();
+        }
+
+        [Fact]
+        public async Task FreshlyWrittenReplayLine_OnExactGridAge_ResolvesToRoughlyNow()
+        {
+            // Characterization of the one accepted edge: a line freshly WRITTEN but carrying a
+            // REPLAYED timestamp whose age is exactly a grid multiple (here 30 min) measures
+            // that age as an "offset" and resolves to ~now instead of its replayed past. The
+            // error is bounded by construction (an anchored line always lands at now ± 2 min),
+            // and sub-24h replays are treated as current by the historic-replay guard anyway.
+            using var h = new Harness();
+
+            h.Append("IntuneManagementExtension.log", Line("marker 1", h.Now, TimeSpan.Zero));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            var replayedInstant = h.Now.AddMinutes(-30);
+            h.Append("IntuneManagementExtension.log", Line("marker 2", replayedInstant, TimeSpan.Zero));
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h.Tracker.LastMatchedSourceOffsetOrigin);
+            Assert.NotNull(h.Tracker.LastMatchedLogTimestamp);
+            var error = (h.Tracker.LastMatchedLogTimestamp!.Value - h.Now).Duration();
+            Assert.True(error <= CmTraceOffsetCalibrator.MaxGridResidual,
+                $"anchored line must resolve to now ± residual, was off by {error}");
+        }
+
+        // =====================================================================
+        // The committed field fixture — session e9753578, ImeLogs/AgentExecutor.log.
+        // One file, two writer eras (PDT hour-05 / CEST hour-14), interleaved, flipping
+        // BOTH ways. Replayed here as the live tail the field agent saw: entry by entry,
+        // with the clock following the true write time.
+        // =====================================================================
+
+        private static string FixturePath()
+        {
+            var dir = AppContext.BaseDirectory;
+            for (int i = 0; i < 12; i++)
+            {
+                if (File.Exists(Path.Combine(dir, "AutopilotMonitor.sln")))
+                    return Path.Combine(dir, "tests", "fixtures", "cmtrace-logs",
+                        "agentexecutor-two-writer-eras-v1.cmtrace");
+                var parent = Directory.GetParent(dir)?.FullName;
+                if (parent == null || parent == dir) break;
+                dir = parent;
+            }
+            throw new DirectoryNotFoundException(
+                "Could not locate repo root (AutopilotMonitor.sln) walking up from " + AppContext.BaseDirectory);
+        }
+
+        /// <summary>Group the fixture's physical lines into complete CMTrace entries (multiline-safe).</summary>
+        private static List<string> FixtureEntries()
+        {
+            var entries = new List<string>();
+            string? pending = null;
+            foreach (var rawWithBom in File.ReadAllLines(FixturePath()))
+            {
+                // The fixture keeps the original file's BOM verbatim — it sat at the START of
+                // the real AgentExecutor.log, which is mid-file in this excerpt.
+                var raw = rawWithBom.TrimStart('');
+                if (pending == null)
+                {
+                    if (raw.Length == 0 || raw[0] == '#') continue;
+                    if (!raw.StartsWith("<![LOG[", StringComparison.Ordinal)) continue;
+                    if (raw.Contains("]LOG]!>")) { entries.Add(raw); continue; }
+                    pending = raw;
+                }
+                else
+                {
+                    pending += "\n" + raw;
+                    if (raw.Contains("]LOG]!>")) { entries.Add(pending!); pending = null; }
+                }
+            }
+            return entries;
+        }
+
+        [Fact]
+        public async Task TwoWriterEraFixture_EveryLineOfBothErasResolvesToItsTrueInstant()
+        {
+            // The committed fixture is a curated, verbatim excerpt of the transition window
+            // (commit policy: anonymized, versioned) — 20 entries covering both eras and the flip.
+            var entries = FixtureEntries();
+            Assert.True(entries.Count >= 15, $"fixture unexpectedly small: {entries.Count} entries");
+
+            using var h = new Harness();
+
+            // Match every fixture entry.
+            h.Tracker.CompilePatterns(new List<ImeLogPattern>
+            {
+                new ImeLogPattern
+                {
+                    PatternId = "T-ANY", Category = "always", Enabled = true,
+                    Pattern = ".+", Action = "noop",
+                    Parameters = new Dictionary<string, string>(),
+                },
+            });
+
+            // The file exists (empty) before its first content — first sight is the observation
+            // baseline, everything after is a fresh tail, exactly like the field.
+            File.WriteAllText(h.PathOf("AgentExecutor.log"), string.Empty);
+            h.Now = new DateTime(2026, 8, 20, 12, 13, 30, DateTimeKind.Utc);
+            await h.Pass();
+
+            var anchored = 0;
+            var resolvedList = new List<(DateTime Resolved, DateTime Expected)>();
+            Action<string> capture = _ =>
+            {
+                if (h.Tracker.LastMatchedSourceOffsetOrigin == CmTraceOffsetOrigin.LineAnchored)
+                    anchored++;
+                if (h.Tracker.LastMatchedLogTimestamp.HasValue && _expectedForCurrentEntry.HasValue)
+                    resolvedList.Add((h.Tracker.LastMatchedLogTimestamp.Value, _expectedForCurrentEntry.Value));
+            };
+            h.Tracker.OnPatternMatched += capture;
+            try
+            {
+                foreach (var entry in entries)
+                {
+                    CmTraceLogEntry? parsed;
+                    Assert.True(CmTraceLogParser.TryParseLine(entry, out parsed), "fixture entry did not parse");
+
+                    // Era by local hour: the fixture holds exactly two eras — PDT (UTC-7) lines
+                    // render at local hour 05, CEST (UTC+2) lines at hour 14 (fixture header).
+                    var eraOffset = parsed.LocalTimestamp.Hour == 14
+                        ? TimeSpan.FromHours(2)
+                        : TimeSpan.FromHours(-7);
+                    var trueUtc = DateTime.SpecifyKind(parsed.LocalTimestamp - eraOffset, DateTimeKind.Utc);
+
+                    // The clock follows the write; never move backwards (interleaved eras are
+                    // written in true-UTC order, but guard against sub-ms jitter).
+                    var readAt = trueUtc.AddMilliseconds(120);
+                    if (readAt > h.Now) h.Now = readAt;
+
+                    // In production the 100 ms poll keeps running through write silences — every
+                    // empty look refreshes the freshness window. The fixture's transition window
+                    // spans multi-minute write gaps, so replay that cadence with one empty poll
+                    // just before each append; without it the NEXT pass would (correctly!)
+                    // classify the gap as a stall and refuse to anchor.
+                    h.Now = h.Now.AddMilliseconds(-100);
+                    await h.Pass();
+                    h.Now = readAt;
+
+                    _expectedForCurrentEntry = trueUtc;
+                    File.AppendAllText(h.PathOf("AgentExecutor.log"), entry + Environment.NewLine);
+                    await h.Pass();
+                    _expectedForCurrentEntry = null;
+                }
+            }
+            finally
+            {
+                h.Tracker.OnPatternMatched -= capture;
+            }
+
+            // Every matched entry resolved to the instant its writer rendered — across BOTH
+            // eras, including the flips. This is the exact property whose absence produced the
+            // -9 h script durations.
+            Assert.Equal(entries.Count, resolvedList.Count);
+            Assert.All(resolvedList, r => Assert.Equal(r.Expected, r.Resolved));
+            Assert.True(anchored == resolvedList.Count,
+                $"expected every entry line-anchored, got {anchored}/{resolvedList.Count}");
+
+            // Both eras genuinely exercised: PDT entries render at local hour 05, CEST at 14.
+            Assert.Contains(resolvedList, r => (r.Expected + TimeSpan.FromHours(-7)).Hour == 5);
+            Assert.Contains(resolvedList, r => (r.Expected + TimeSpan.FromHours(2)).Hour == 14);
+        }
+
+        private DateTime? _expectedForCurrentEntry;
+    }
+}
@@ -0,0 +1,275 @@
+using System;
+using System.Collections.Generic;
+using System.IO;
+using System.Threading;
+using System.Threading.Tasks;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
+{
+    /// <summary>
+    /// End-to-end offset calibration through a real read cycle.
+    ///
+    /// <para>
+    /// A CMTrace line states local time and nothing else, so its UTC value depends on which zone
+    /// the WRITING process believed it was in. The tracker used to substitute its own belief,
+    /// which is right only when the two happen to agree.
+    /// </para>
+    ///
+    /// <para>
+    /// These tests are deliberately independent of the machine they run on: the assertion is
+    /// always "a line written at instant T resolves to T", for every writer belief. That single
+    /// property covers both field cases at once — the writer disagreeing with us (the bug) and
+    /// the writer agreeing with us (the majority, which a naive fix would have broken).
+    /// </para>
+    /// </summary>
+    public sealed class ImeLogTrackerOffsetCalibrationTests
+    {
+        private const string LogFileName = "IntuneManagementExtension.log";
+        private static readonly DateTime T0 = new DateTime(2026, 8, 20, 7, 30, 0, DateTimeKind.Utc);
+
+        private static List<ImeLogPattern> Patterns() => new List<ImeLogPattern>
+        {
+            new ImeLogPattern
+            {
+                PatternId = "T-MARK", Category = "always", Enabled = true,
+                Pattern = @"marker (?<n>\d+)",
+                Action = "noop",
+                Parameters = new Dictionary<string, string>(),
+            },
+        };
+
+        /// <summary>A CMTrace line as a writer holding <paramref name="writerOffset"/> renders instant <paramref name="utcInstant"/>.</summary>
+        private static string Line(string message, DateTime utcInstant, TimeSpan writerOffset)
+        {
+            var local = utcInstant + writerOffset;
+            return $"<![LOG[{message}]LOG]!><time=\"{local:HH:mm:ss.fffffff}\" date=\"{local:M-d-yyyy}\" " +
+                   "component=\"IntuneManagementExtension\" context=\"\" type=\"1\" thread=\"1\" file=\"\">";
+        }
+
+        private sealed class Harness : IDisposable
+        {
+            private readonly TempDirectory _tmp = new TempDirectory();
+            public ImeLogTracker Tracker { get; }
+            public DateTime Now { get; set; } = T0;
+
+            public Harness()
+            {
+                Tracker = new ImeLogTracker(
+                    logFolder: _tmp.Path,
+                    patterns: Patterns(),
+                    logger: new AgentLogger(_tmp.Path, AgentLogLevel.Info));
+                Tracker.UtcNowProvider = () => Now;
+            }
+
+            public string LogPath => Path.Combine(_tmp.Path, LogFileName);
+
+            public void Append(string line) => File.AppendAllText(LogPath, line + Environment.NewLine);
+
+            public Task Pass() => Tracker.CheckLogFilesAsync(CancellationToken.None);
+
+            public void Dispose()
+            {
+                Tracker.Dispose();
+                _tmp.Dispose();
+            }
+        }
+
+        [Theory]
+        // The writer's belief. The MEASUREMENT must recover it exactly, whatever it is.
+        [InlineData(2)]     // CEST
+        [InlineData(1)]     // BST
+        [InlineData(-7)]    // PDT — the OOBE default behind the -17 h and -9 h field cases
+        [InlineData(10)]    // E. Australia
+        [InlineData(0)]     // UTC
+        public async Task MeasuresTheWritersOffsetExactly_ForAnyBelief(int writerOffsetHours)
+        {
+            // NOTE: the per-FILE measurement asserted here is OBSERVATIONAL — its application was
+            // reverted on 2026-08-20 (04b1a7c6) because one offset per file is wrong when a file
+            // holds interleaved writer eras. Resolution now anchors per LINE instead (see
+            // ImeLogTrackerLineAnchoringTests, which restores the "a line written at T resolves
+            // to T" property era-safely). The per-file measurement stays for the Info log and
+            // measuredWriterOffsetMinutes provenance.
+            var writerOffset = TimeSpan.FromHours(writerOffsetHours);
+            using var h = new Harness();
+
+            h.Append(Line("marker 1", h.Now, writerOffset));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            h.Append(Line("marker 2", h.Now, writerOffset));
+            await h.Pass();
+
+            TimeSpan measured;
+            Assert.True(h.Tracker.OffsetCalibrator.TryGetOffset(LogFileName, out measured));
+            Assert.Equal(writerOffset, measured);
+        }
+
+        [Fact]
+        public async Task MeasuresTheWritersOffset_NotItsOwn()
+        {
+            using var h = new Harness();
+            var writerOffset = TimeSpan.FromHours(2);
+
+            h.Append(Line("marker 1", h.Now, writerOffset));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            h.Append(Line("marker 2", h.Now, writerOffset));
+            await h.Pass();
+
+            TimeSpan measured;
+            Assert.True(h.Tracker.OffsetCalibrator.TryGetOffset(LogFileName, out measured));
+            Assert.Equal(writerOffset, measured);
+        }
+
+        [Fact]
+        public async Task DoesNotCalibrateOnFirstSightOfAFile()
+        {
+            // The first pass reads from position 0, so the newest line in the file may be hours
+            // old. Anchoring on it would measure the line's age instead of the writer's offset.
+            using var h = new Harness();
+
+            h.Append(Line("marker 1", T0.AddHours(-3), TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            TimeSpan ignored;
+            Assert.False(h.Tracker.OffsetCalibrator.TryGetOffset(LogFileName, out ignored));
+        }
+
+        [Fact]
+        public async Task FollowsTheWriterAcrossARestartIntoANewZone()
+        {
+            // IME restarts mid-enrollment and picks up the timezone the OS moved to. The
+            // measurement has to follow, otherwise every later line is off by the difference.
+            using var h = new Harness();
+
+            h.Append(Line("marker 1", h.Now, TimeSpan.FromHours(1)));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            h.Append(Line("marker 2", h.Now, TimeSpan.FromHours(1)));
+            await h.Pass();
+
+            TimeSpan before;
+            Assert.True(h.Tracker.OffsetCalibrator.TryGetOffset(LogFileName, out before));
+            Assert.Equal(TimeSpan.FromHours(1), before);
+
+            // Writer restarts, now on +2.
+            h.Now = T0.AddSeconds(20);
+            h.Append(Line("marker 3", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(30);
+            var writtenAt = h.Now;
+            h.Append(Line("marker 4", writtenAt, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            TimeSpan after;
+            Assert.True(h.Tracker.OffsetCalibrator.TryGetOffset(LogFileName, out after));
+            Assert.Equal(TimeSpan.FromHours(2), after);
+            // The measurement follows the restart. Applying it is what the 2026-08-20 revert
+            // removed — that is exactly the case a file with two writer eras breaks.
+            Assert.Equal(120, h.Tracker.LastMatchedMeasuredWriterOffsetMinutes);
+        }
+
+        [Fact]
+        public async Task HonorsAWriterDeclaredBiasWithoutMeasuring()
+        {
+            // A line carrying its own bias states the offset outright; it must be used as-is and
+            // must never become a calibration anchor.
+            using var h = new Harness();
+
+            h.Append(Line("marker 1", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            var writtenAt = h.Now;
+            var local = writtenAt + TimeSpan.FromHours(-8);        // a PST writer
+            h.Append($"<![LOG[marker 2]LOG]!><time=\"{local:HH:mm:ss.fffffff}+480\" date=\"{local:M-d-yyyy}\" " +
+                     "component=\"IntuneManagementExtension\" context=\"\" type=\"1\" thread=\"1\" file=\"\">");
+            await h.Pass();
+
+            Assert.True(h.Tracker.LastMatchedLogTimestamp.HasValue);
+            Assert.Equal(writtenAt, h.Tracker.LastMatchedLogTimestamp.Value);
+
+            TimeSpan ignored;
+            Assert.False(h.Tracker.OffsetCalibrator.TryGetOffset(LogFileName, out ignored));
+        }
+
+        [Fact]
+        public async Task RecordsMeasuredOffsetSeparatelyFromTheAppliedOne()
+        {
+            // The regression that forced the revert shipped an event tagged "calibrated" while
+            // carrying an offset that did not hold for that line. Measured and applied are now
+            // separate fields so a future reader cannot mistake one for the other.
+            using var h = new Harness();
+            var writerOffset = TimeSpan.FromHours(-7);   // PDT, the OOBE default
+
+            h.Append(Line("marker 1", h.Now, writerOffset));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            h.Append(Line("marker 2", h.Now, writerOffset));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(20);
+            h.Append(Line("marker 3", h.Now, writerOffset));
+            await h.Pass();
+
+            // Measured: the writer's actual belief, per file.
+            Assert.Equal(-420, h.Tracker.LastMatchedMeasuredWriterOffsetMinutes);
+
+            // Applied: the line's OWN anchor (fresh pass), never the per-file "calibrated" value —
+            // the two must stay distinguishable even when they agree numerically.
+            Assert.Equal(CmTraceOffsetOrigin.LineAnchored, h.Tracker.LastMatchedSourceOffsetOrigin);
+            Assert.NotEqual(CmTraceOffsetOrigin.Calibrated, h.Tracker.LastMatchedSourceOffsetOrigin);
+        }
+
+        [Fact]
+        public async Task RecordsProvenance_AsFallback_BeforeAnyCalibration()
+        {
+            // The warm-up pass: the offset is not measured yet, so the reader zone is assumed and
+            // the event has to say so rather than look source-grounded.
+            using var h = new Harness();
+
+            h.Append(Line("marker 1", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.None, h.Tracker.LastMatchedSourceOffsetOrigin);
+            Assert.True(h.Tracker.LastMatchedSourceLocalTimestamp.HasValue);
+
+            // The APPLIED offset is reported even on the fallback path — an event that states no
+            // offset at all cannot be recomputed later, which defeats the purpose of recording
+            // provenance. Asserted against the running machine's zone so this stays portable.
+            var readerZone = (int)TimeZoneInfo.Local
+                .GetUtcOffset(h.Tracker.LastMatchedSourceLocalTimestamp!.Value).TotalMinutes;
+            Assert.Equal(readerZone, h.Tracker.LastMatchedSourceOffsetMinutes);
+        }
+
+        [Fact]
+        public async Task RecordsProvenance_ForADeclaredBias()
+        {
+            using var h = new Harness();
+
+            h.Append(Line("marker 1", h.Now, TimeSpan.FromHours(2)));
+            await h.Pass();
+
+            h.Now = T0.AddSeconds(10);
+            var local = h.Now + TimeSpan.FromHours(-8);
+            h.Append($"<![LOG[marker 2]LOG]!><time=\"{local:HH:mm:ss.fffffff}+480\" date=\"{local:M-d-yyyy}\" " +
+                     "component=\"IntuneManagementExtension\" context=\"\" type=\"1\" thread=\"1\" file=\"\">");
+            await h.Pass();
+
+            Assert.Equal(CmTraceOffsetOrigin.Bias, h.Tracker.LastMatchedSourceOffsetOrigin);
+            // Reported in the same sense as a measured offset (local = UTC + offset), so the two
+            // origins are directly comparable; the wire bias uses the opposite convention.
+            Assert.Equal(-480, h.Tracker.LastMatchedSourceOffsetMinutes);
+        }
+
+    }
+}
@@ -0,0 +1,199 @@
+using System.Collections.Generic;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
+{
+    /// <summary>
+    /// Sessions 81daa77f / 75d6ae8e (2026-08-25) — zero user-targeted apps starved every
+    /// user-phase completion probe. The IME zero-app branch returns before it writes the
+    /// "Completed user session" line, so a device whose user has no targeted Win32 apps never
+    /// produced the evidence <c>IsImeUserSessionGenuine</c> requires, and the AdvisoryCompletion
+    /// window failed the enrollment 30 minutes later — with the user at the desktop, Hello
+    /// provisioned and RealmJoin still installing.
+    /// <para>
+    /// IME-USER-SESSION-ZERO-APPS reads the line IME does write in that branch and routes it
+    /// through the same <see cref="ImeLogTracker.OnUserSessionCompleted"/> callback.
+    /// </para>
+    /// </summary>
+    public sealed class ImeLogTrackerZeroUserAppsTests
+    {
+        // Mirrors rules/ime-log-patterns/IME-USER-SESSION-ZERO-APPS.json. The JSON itself is
+        // pinned against a real IME line by BuiltInRulesTests in the backend suite.
+        private const string ZeroAppsPattern =
+            @"\[Win32App\] Get 0 apps for user session (?<sessionId>\d+), user id = (?<userId>[a-f0-9\-]+)";
+
+        private const string EspPhasePattern =
+            @"\[Win32App\] (?:In|The) EspPhase: (?<espPhase>\w+)";
+
+        private const string ZeroAppsLine =
+            "[Win32App] Get 0 apps for user session 1, user id = 4a1ba5db-44ed-4e69-8477-47ed88e76020";
+
+        private static ImeLogTracker BuildTracker(TempDirectory tmp) =>
+            new ImeLogTracker(
+                logFolder: tmp.Path,
+                patterns: new List<ImeLogPattern>
+                {
+                    new ImeLogPattern
+                    {
+                        PatternId = "IME-USER-SESSION-ZERO-APPS",
+                        Category = "always",
+                        Pattern = ZeroAppsPattern,
+                        Action = "userSessionZeroApps",
+                    },
+                    new ImeLogPattern
+                    {
+                        PatternId = "IME-ESP-PHASE",
+                        Category = "always",
+                        Pattern = EspPhasePattern,
+                        Action = "espPhaseDetected",
+                    },
+                },
+                logger: new AgentLogger(tmp.Path, AgentLogLevel.Info));
+
+        [Fact]
+        public void ZeroApps_line_during_user_phase_fires_user_session_completed()
+        {
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+            var fired = 0;
+            tracker.OnUserSessionCompleted = () => fired++;
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+
+            Assert.Equal(1, fired);
+            Assert.True(tracker.UserSessionZeroAppsObserved);
+        }
+
+        [Fact]
+        public void ZeroApps_line_before_user_phase_does_not_fire()
+        {
+            // Firing here would burn the adapter fire-once flag on a pre-sign-in timestamp that
+            // IsImeUserSessionGenuine (>= AccountSetupEnteredUtc) can never accept.
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+            var fired = 0;
+            tracker.OnUserSessionCompleted = () => fired++;
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: DeviceSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+
+            Assert.Equal(0, fired);
+            Assert.True(tracker.UserSessionZeroAppsObserved);
+        }
+
+        [Fact]
+        public void ZeroApps_observed_early_is_replayed_on_the_user_phase_transition()
+        {
+            // IME writes its check-in lines independently of when the agent first parses the ESP
+            // phase marker, so the evidence can legitimately arrive first. Dropping it would
+            // leave a zero-app device with no completion evidence at all.
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+            var fired = 0;
+            tracker.OnUserSessionCompleted = () => fired++;
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: DeviceSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+            Assert.Equal(0, fired);
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+
+            Assert.Equal(1, fired);
+        }
+
+        [Fact]
+        public void Repeated_user_phase_matches_do_not_replay_again()
+        {
+            // IME re-emits the phase string as it re-evaluates app sets. Only a real transition
+            // replays; the adapter fire-once flag is the outer guard, but the tracker must not
+            // spam the callback either.
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+            var fired = 0;
+            tracker.OnUserSessionCompleted = () => fired++;
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: DeviceSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+
+            Assert.Equal(1, fired);
+        }
+
+        [Fact]
+        public void Nonzero_app_count_lines_do_not_match_the_pattern()
+        {
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+            var fired = 0;
+            tracker.OnUserSessionCompleted = () => fired++;
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+
+            tracker.ProcessLogMessageForTest(
+                "[Win32App] Get 3 apps for user session 1, user id = 4a1ba5db-44ed-4e69-8477-47ed88e76020");
+            tracker.ProcessLogMessageForTest(
+                "[Win32App] Get 10 apps for user session 1, user id = 4a1ba5db-44ed-4e69-8477-47ed88e76020");
+
+            Assert.Equal(0, fired);
+            Assert.False(tracker.UserSessionZeroAppsObserved);
+        }
+
+        [Fact]
+        public void AreUserEspAppsSettled_true_after_zero_apps_observation()
+        {
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+
+            Assert.True(tracker.AreUserEspAppsSettled());
+        }
+
+        [Fact]
+        public void AreUserEspAppsSettled_stays_false_on_an_empty_list_without_the_observation()
+        {
+            // Mutation proof for the branch above: an empty live list on its own still means
+            // "phase just cleared / apps not surfaced yet", never vacuously settled.
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+
+            Assert.False(tracker.AreUserEspAppsSettled());
+        }
+
+        [Fact]
+        public void AreUserEspAppsSettled_false_outside_the_user_phase_even_after_the_observation()
+        {
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: DeviceSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+
+            Assert.True(tracker.UserSessionZeroAppsObserved);
+            Assert.False(tracker.AreUserEspAppsSettled());
+        }
+
+        [Fact]
+        public void GetPendingRequiredUserEspInstallApps_is_empty_for_a_zero_app_user_session()
+        {
+            // The adapter deferral probe must not park the signal when there is nothing to wait
+            // for — otherwise the zero-app path would starve exactly like the old one.
+            using var tmp = new TempDirectory();
+            var tracker = BuildTracker(tmp);
+
+            tracker.ProcessLogMessageForTest("[Win32App] In EspPhase: AccountSetup");
+            tracker.ProcessLogMessageForTest(ZeroAppsLine);
+
+            Assert.Empty(tracker.GetPendingRequiredUserEspInstallApps());
+        }
+    }
+}
@@ -0,0 +1,140 @@
+#nullable enable
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Interop;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Interop
+{
+    /// <summary>
+    /// Tests for the tiered WiFi reader. The WLAN state of the test machine is unknown (CI
+    /// runners have no WLAN service, dev boxes may be on WiFi with or without location consent),
+    /// so the live path only pins the fail-soft contract. The diagnostics composer is pinned
+    /// exactly — it is the only field evidence for a missing wifi_signal_info event, and the
+    /// ERROR_ACCESS_DENIED hint is what tells an operator that Windows 11 24H2's location gate,
+    /// not the hardware, swallowed the SSID.
+    /// </summary>
+    public sealed class WifiInfoProviderTests
+    {
+        [Fact]
+        public void TryRead_never_throws_and_reports_a_reason_when_it_yields_nothing()
+        {
+            var result = WifiInfoProvider.TryRead(null, out var diagnostics);
+
+            if (result == null)
+            {
+                Assert.False(string.IsNullOrWhiteSpace(diagnostics),
+                    "a null result must always explain itself — that string is the only field evidence");
+                Assert.Contains("native:", diagnostics);
+                Assert.Contains("WinRT:", diagnostics);
+                Assert.Contains("netsh:", diagnostics);
+            }
+            else
+            {
+                Assert.Null(diagnostics);
+                // Every tier either carries an SSID or was not supposed to return at all.
+                Assert.False(result.Ssid == null && result.SignalPercent == null
+                             && result.RadioType == null && result.Channel == null,
+                    "an all-null payload must surface as null, not as an empty connection");
+            }
+        }
+
+        // ----- BuildDiagnostics ---------------------------------------------
+
+        [Fact]
+        public void BuildDiagnostics_names_every_tier()
+        {
+            var text = WifiInfoProvider.BuildDiagnostics(null, null);
+
+            Assert.Contains("no WiFi info from any reader", text);
+            Assert.Contains("native: no connected WLAN interface", text);
+            Assert.Contains("WinRT: no SSID", text);
+            Assert.Contains("netsh: no parsable output", text);
+        }
+
+        [Fact]
+        public void BuildDiagnostics_passes_through_tier_reasons()
+        {
+            var text = WifiInfoProvider.BuildDiagnostics("WlanOpenHandle rc=1062", "WinRT NetworkInformation unavailable");
+
+            Assert.Contains("native: WlanOpenHandle rc=1062", text);
+            Assert.Contains("WinRT: WinRT NetworkInformation unavailable", text);
+        }
+
+        [Fact]
+        public void BuildDiagnostics_explains_access_denied_as_the_location_gate()
+        {
+            var text = WifiInfoProvider.BuildDiagnostics(
+                "[1cbc79c3-2e31-468a-b949-17fafa6e23ed] query(current_connection) rc=5; ", null);
+
+            Assert.Contains("ERROR_ACCESS_DENIED", text);
+            Assert.Contains("24H2", text);
+            Assert.Contains("Location services", text);
+        }
+
+        [Fact]
+        public void BuildDiagnostics_explains_access_denied_without_a_trailing_separator()
+        {
+            var text = WifiInfoProvider.BuildDiagnostics("WlanOpenHandle rc=5", null);
+
+            Assert.Contains("ERROR_ACCESS_DENIED", text);
+        }
+
+        // ----- IsLocationGateDenied -----------------------------------------
+        //
+        // This predicate decides whether the wifi_signal_info payload claims
+        // "location_services_off" to the operator. A false positive blames a privacy setting
+        // that is actually fine, so the boundaries are pinned exactly.
+
+        [Theory]
+        [InlineData("[guid] query(current_connection) rc=5; ")]
+        [InlineData("WlanOpenHandle rc=5")]
+        public void IsLocationGateDenied_true_only_for_error_access_denied(string nativeDiag)
+        {
+            Assert.True(WifiInfoProvider.IsLocationGateDenied(nativeDiag));
+        }
+
+        [Theory]
+        [InlineData(null)]
+        [InlineData("")]
+        [InlineData("query(current_connection) rc=50; ")]
+        [InlineData("query(current_connection) rc=5023; ")]
+        [InlineData("WlanEnumInterfaces rc=1062")]
+        [InlineData("no WLAN interfaces")]
+        [InlineData("[guid] state=wlan_interface_state_disconnected; ")]
+        public void IsLocationGateDenied_false_for_every_other_reason(string? nativeDiag)
+        {
+            Assert.False(WifiInfoProvider.IsLocationGateDenied(nativeDiag));
+        }
+
+        [Fact]
+        public void LocationServicesOff_literal_is_the_published_payload_contract()
+        {
+            // Matched verbatim by the portal's WiFi card (wifiDataLimitedReason) — renaming it
+            // silently drops the hint instead of breaking a build.
+            Assert.Equal("location_services_off", WifiInfoProvider.LocationServicesOff);
+        }
+
+        [Fact]
+        public void TryRead_never_claims_the_location_gate_on_the_native_tier()
+        {
+            // The native tier only returns when it succeeded, so a full payload must never carry
+            // a "data limited" reason.
+            var result = WifiInfoProvider.TryRead(null, out _);
+
+            if (result?.SignalPercent != null)
+                Assert.Null(result.DataLimitedReason);
+        }
+
+        [Theory]
+        [InlineData("query(current_connection) rc=50; ")]
+        [InlineData("query(current_connection) rc=5023; ")]
+        [InlineData("WlanEnumInterfaces rc=1062")]
+        [InlineData("[guid] state=wlan_interface_state_disconnected; ")]
+        public void BuildDiagnostics_does_not_blame_the_location_gate_for_other_codes(string nativeDiag)
+        {
+            var text = WifiInfoProvider.BuildDiagnostics(nativeDiag, null);
+
+            Assert.DoesNotContain("ERROR_ACCESS_DENIED", text);
+            Assert.Contains($"native: {nativeDiag}", text);
+        }
+    }
+}
@@ -0,0 +1,48 @@
+#nullable enable
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Interop;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Interop
+{
+    /// <summary>
+    /// Tests for the WinRT SSID reader. Its whole value is that it keeps working where the
+    /// native WLAN API is denied, so the contract that matters here is fail-soft resolution:
+    /// the type is bound by name at runtime (no winmd), and every step must degrade to null
+    /// with a reason instead of throwing — a throw would take the Task.Run collector down
+    /// silently, which is precisely the failure mode this tier exists to end.
+    /// </summary>
+    public sealed class WinRtWifiSsidReaderTests
+    {
+        [Fact]
+        public void TryGetConnectedSsid_never_throws()
+        {
+            var ssid = WinRtWifiSsidReader.TryGetConnectedSsid(out var diagnostics);
+
+            if (ssid == null)
+                Assert.False(string.IsNullOrWhiteSpace(diagnostics), "a null SSID must carry a reason");
+            else
+                Assert.Null(diagnostics);
+        }
+
+        [Fact]
+        public void TryGetConnectedSsid_never_returns_an_empty_ssid()
+        {
+            // An AP broadcasting an empty SSID must surface as null, never as "" — the caller
+            // maps a non-null SSID straight into the wifi_signal_info payload.
+            var ssid = WinRtWifiSsidReader.TryGetConnectedSsid(out _);
+
+            Assert.True(ssid == null || ssid.Length > 0);
+        }
+
+        [Fact]
+        public void TryGetConnectedSsid_is_stable_across_calls()
+        {
+            // Reflection members are resolved once and cached; a second call must take the
+            // cached path and behave identically.
+            var first = WinRtWifiSsidReader.TryGetConnectedSsid(out _);
+            var second = WinRtWifiSsidReader.TryGetConnectedSsid(out _);
+
+            Assert.Equal(first, second);
+        }
+    }
+}
@@ -56,6 +56,42 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Office
            Assert.Equal(1, loaded.PeakDo.DownloadMode);
        }

+        [Fact]
+        public void Save_then_load_roundtrips_terminal_metadata()
+        {
+            // Session bc803955 — CompletedAtUtc/VersionReached feed the summary dialog's
+            // synthetic Office row (duration + version).
+            using var tmp = new TempDirectory();
+            var sut = new OfficeInstallStatePersistence(tmp.Path, NewLogger(tmp.Path));
+            var completedAt = new DateTime(2026, 6, 8, 12, 3, 22, DateTimeKind.Utc);
+
+            sut.Save(new OfficeInstallStateData
+            {
+                State = OfficeInstallStateData.StateCompleted,
+                CompletedAtUtc = completedAt,
+                VersionReached = "16.0.20228.20190",
+            });
+
+            var loaded = sut.Load();
+            Assert.Equal(completedAt, loaded!.CompletedAtUtc);
+            Assert.Equal("16.0.20228.20190", loaded.VersionReached);
+        }
+
+        [Fact]
+        public void Load_tolerates_state_files_from_older_agents_without_terminal_metadata()
+        {
+            using var tmp = new TempDirectory();
+            var sut = new OfficeInstallStatePersistence(tmp.Path, NewLogger(tmp.Path));
+            // Pre-terminal-metadata wire format (verbatim shape from a live 2.0.1404 session).
+            File.WriteAllText(sut.StateFilePath,
+                "{\"State\":\"Completed\",\"StartedAtUtc\":\"2026-08-18T07:56:16.8208141Z\",\"StartedTrigger\":\"registry\"}");
+
+            var loaded = sut.Load();
+            Assert.Equal(OfficeInstallStateData.StateCompleted, loaded!.State);
+            Assert.Null(loaded.CompletedAtUtc);
+            Assert.Null(loaded.VersionReached);
+        }
+
        [Fact]
        public void Save_overwrites_a_previous_state()
        {
@@ -1,9 +1,11 @@
 #nullable enable
+using System.Collections.Generic;
 using System.IO;
 using System.IO.Compression;
 using System.Linq;
 using System.Text;
 using AutopilotMonitor.Agent.V2.Core.Configuration;
+using AutopilotMonitor.Shared.Models;
 using AutopilotMonitor.Agent.V2.Core.Logging;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Runtime;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Transport;
@@ -46,7 +48,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
                Directory.CreateDirectory(SpoolFolder);
            }

-            public DiagnosticsPackageService Build(System.Action<AgentConfiguration>? mutateConfig = null)
+            public DiagnosticsPackageService Build(
+                System.Action<AgentConfiguration>? mutateConfig = null,
+                IReadOnlyDictionary<string, string>? sectionFolderOverrides = null,
+                System.Func<bool>? devicePreparationProbe = null)
            {
                // BackendApiClient is required by the public ctor but BuildArchiveBytes
                // never touches it — construct with a throwaway HttpClient. Tests only
@@ -71,7 +76,9 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
                    imeLogFolderOverride: ImeTmp.Path,
                    agentStateFolderOverride: StateFolder,
                    agentSpoolFolderOverride: SpoolFolder,
-                    agentDataFolderOverride: DataFolder);
+                    agentDataFolderOverride: DataFolder,
+                    sectionFolderOverrides: sectionFolderOverrides,
+                    devicePreparationProbe: devicePreparationProbe);
            }

            public void Dispose()
@@ -287,6 +294,185 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
            Assert.DoesNotContain(entries, e => e.StartsWith("AgentSpool/"));
        }

+        // ===================================================== built-in catalog gates ====
+        // The RealmJoin sections ride behind the tenant's RealmJoin Watcher toggle, the
+        // Device Preparation bootstrapper event log behind the deterministic WDP marker.
+        // Every conditional section is skipped WITH a manifest line, never silently.
+
+        /// <summary>RealmJoin system-side folders redirected to temp (user-side goes via UserProfileResolver).</summary>
+        private sealed class RealmJoinRig : System.IDisposable
+        {
+            public TempDirectory WindowsLogs { get; } = new TempDirectory();
+            public TempDirectory Choco { get; } = new TempDirectory();
+            public TempDirectory UserProfile { get; } = new TempDirectory();
+            public string PackagesFolder => Path.Combine(WindowsLogs.Path, "RealmJoin");
+
+            public RealmJoinRig()
+            {
+                File.WriteAllText(Path.Combine(WindowsLogs.Path, "realmjoin.log"), "rj");
+                File.WriteAllText(Path.Combine(WindowsLogs.Path, "realmjoin2.log"), "rj2");
+                var pkg = Path.Combine(PackagesFolder, "Packages", "generic-7zip");
+                Directory.CreateDirectory(pkg);
+                File.WriteAllText(Path.Combine(pkg, "install.log"), "pkg");
+                var choco = Path.Combine(Choco.Path, "generic-7zip");
+                Directory.CreateDirectory(choco);
+                File.WriteAllText(Path.Combine(choco, "2026-06-30_install.log"), "choco");
+                var userRj = Path.Combine(UserProfile.Path, "AppData", "Local", "RealmJoin");
+                Directory.CreateDirectory(Path.Combine(userRj, "Logs", "generic-office"));
+                File.WriteAllText(Path.Combine(userRj, "tray.log"), "tray");
+                File.WriteAllText(Path.Combine(userRj, "config.pjson"), "not a log");
+                File.WriteAllText(Path.Combine(userRj, "Logs", "RjImeHost.log"), "host");
+                File.WriteAllText(Path.Combine(userRj, "Logs", "generic-office", "usersettings.log"), "pkg-user");
+            }
+
+            public IReadOnlyDictionary<string, string> Overrides => new Dictionary<string, string>
+            {
+                ["RealmJoinWindows"] = WindowsLogs.Path,
+                ["RealmJoinPackages"] = PackagesFolder,
+                ["RealmJoinChoco"] = Choco.Path,
+            };
+
+            public void Dispose()
+            {
+                WindowsLogs.Dispose();
+                Choco.Dispose();
+                UserProfile.Dispose();
+            }
+        }
+
+        [Fact]
+        public void BuildArchiveBytes_skips_realmjoin_sections_when_watcher_disabled()
+        {
+            using var rig = new Rig();
+            using var rj = new RealmJoinRig();
+            UserProfileResolver.SetForTesting(rj.UserProfile.Path);
+            try
+            {
+                var bytes = rig.Build(sectionFolderOverrides: rj.Overrides).BuildArchiveBytes(enrollmentSucceeded: true);
+
+                var entries = ZipEntryNames(bytes);
+                Assert.DoesNotContain(entries, e => e.StartsWith("RealmJoinLogs/"));
+                var manifest = ReadZipEntryText(bytes, "package-manifest.txt")!;
+                Assert.Contains("SCENARIO: devicePreparation=False realmJoinWatcher=False", manifest);
+                Assert.Contains("BUILT-IN SKIPPED (RealmJoin Watcher disabled): RealmJoinWindows", manifest);
+                Assert.Contains("BUILT-IN SKIPPED (RealmJoin Watcher disabled): RealmJoinUserLogs", manifest);
+            }
+            finally
+            {
+                UserProfileResolver.Reset();
+            }
+        }
+
+        [Fact]
+        public void BuildArchiveBytes_includes_realmjoin_sections_when_watcher_enabled()
+        {
+            using var rig = new Rig();
+            using var rj = new RealmJoinRig();
+            UserProfileResolver.SetForTesting(rj.UserProfile.Path);
+            try
+            {
+                var bytes = rig.Build(cfg => cfg.EnableRealmJoinWatcher = true, rj.Overrides)
+                    .BuildArchiveBytes(enrollmentSucceeded: false);
+
+                var entries = ZipEntryNames(bytes);
+                // ZIP layout mirrors the disk layout: flat client logs + package tree under
+                // Windows/, tray logs + per-user Logs tree under User/.
+                Assert.Contains("RealmJoinLogs/Windows/realmjoin.log", entries);
+                Assert.Contains("RealmJoinLogs/Windows/realmjoin2.log", entries);
+                Assert.Contains("RealmJoinLogs/Windows/RealmJoin/Packages/generic-7zip/install.log", entries);
+                Assert.Contains("RealmJoinLogs/Choco/generic-7zip/2026-06-30_install.log", entries);
+                Assert.Contains("RealmJoinLogs/User/tray.log", entries);
+                Assert.Contains("RealmJoinLogs/User/Logs/RjImeHost.log", entries);
+                Assert.Contains("RealmJoinLogs/User/Logs/generic-office/usersettings.log", entries);
+                // Only tray*.log is collected from the user RealmJoin root — config stays out.
+                Assert.DoesNotContain(entries, e => e.EndsWith("config.pjson"));
+                var manifest = ReadZipEntryText(bytes, "package-manifest.txt")!;
+                Assert.Contains("BUILT-IN: RealmJoinUserLogs -> folder=", manifest);
+                Assert.DoesNotContain("BUILT-IN SKIPPED (RealmJoin Watcher disabled)", manifest);
+            }
+            finally
+            {
+                UserProfileResolver.Reset();
+            }
+        }
+
+        [Fact]
+        public void BuildArchiveBytes_skips_realmjoin_user_sections_without_user_session()
+        {
+            using var rig = new Rig();
+            using var rj = new RealmJoinRig();
+            // Token present, no interactive user detected → user-profile sections skip with a
+            // manifest line; the system-side sections are unaffected.
+            UserProfileResolver.SetForTesting(null!);
+            try
+            {
+                var bytes = rig.Build(cfg => cfg.EnableRealmJoinWatcher = true, rj.Overrides)
+                    .BuildArchiveBytes(enrollmentSucceeded: true);
+
+                var entries = ZipEntryNames(bytes);
+                Assert.Contains("RealmJoinLogs/Windows/realmjoin.log", entries);
+                Assert.DoesNotContain(entries, e => e.StartsWith("RealmJoinLogs/User"));
+                var manifest = ReadZipEntryText(bytes, "package-manifest.txt")!;
+                Assert.Contains("BUILT-IN SKIPPED (no user session for token): RealmJoinUserTray", manifest);
+                Assert.Contains("BUILT-IN SKIPPED (no user session for token): RealmJoinUserLogs", manifest);
+            }
+            finally
+            {
+                UserProfileResolver.Reset();
+            }
+        }
+
+        [Fact]
+        public void BuildArchiveBytes_collects_bootstrapper_event_log_only_on_device_preparation()
+        {
+            using var rig = new Rig();
+            using var winevt = new TempDirectory();
+            // Synthetic evtx: no registered channel claims the file, so the export falls
+            // back to a raw copy — the point here is the scenario gate, not wevtutil.
+            File.WriteAllBytes(Path.Combine(winevt.Path, "BootstrapperAgentServiceLogProvider.evtx"), new byte[] { 1, 2, 3 });
+            var overrides = new Dictionary<string, string> { ["ImeBootstrapperEventLog"] = winevt.Path };
+
+            var classic = rig.Build(sectionFolderOverrides: overrides, devicePreparationProbe: () => false)
+                .BuildArchiveBytes(enrollmentSucceeded: true);
+            Assert.DoesNotContain("ImeLogs/BootstrapperAgentServiceLogProvider.evtx", ZipEntryNames(classic));
+            Assert.Contains("BUILT-IN SKIPPED (not a Device Preparation enrollment): ImeBootstrapperEventLog",
+                ReadZipEntryText(classic, "package-manifest.txt"));
+
+            var wdp = rig.Build(sectionFolderOverrides: overrides, devicePreparationProbe: () => true)
+                .BuildArchiveBytes(enrollmentSucceeded: true);
+            Assert.Contains("ImeLogs/BootstrapperAgentServiceLogProvider.evtx", ZipEntryNames(wdp));
+            Assert.Contains("SCENARIO: devicePreparation=True", ReadZipEntryText(wdp, "package-manifest.txt"));
+        }
+
+        [Fact]
+        public void BuildArchiveBytes_treats_failing_device_preparation_probe_as_classic()
+        {
+            using var rig = new Rig();
+            var bytes = rig.Build(devicePreparationProbe: () => throw new System.InvalidOperationException("registry boom"))
+                .BuildArchiveBytes(enrollmentSucceeded: true);
+
+            var manifest = ReadZipEntryText(bytes, "package-manifest.txt")!;
+            Assert.Contains("SCENARIO PROBE FAILED (treated as Classic): registry boom", manifest);
+            Assert.Contains("BUILT-IN SKIPPED (not a Device Preparation enrollment): ImeBootstrapperEventLog", manifest);
+            Assert.Contains("sessioninfo.txt", ZipEntryNames(bytes)); // archive still built
+        }
+
+        [Theory]
+        [InlineData(DiagnosticsSectionCondition.Always, false, false, true)]
+        [InlineData(DiagnosticsSectionCondition.RealmJoinWatcher, false, true, false)]
+        [InlineData(DiagnosticsSectionCondition.RealmJoinWatcher, true, false, true)]
+        [InlineData(DiagnosticsSectionCondition.DevicePreparation, true, false, false)]
+        [InlineData(DiagnosticsSectionCondition.DevicePreparation, false, true, true)]
+        [InlineData((DiagnosticsSectionCondition)999, true, true, false)]
+        public void IsSectionActive_gates_on_condition(DiagnosticsSectionCondition condition, bool watcher, bool wdp, bool expected)
+        {
+            var section = new DiagnosticsBuiltInSection("X", "X", @"C:\X", new[] { "*.log" }, false, "x", condition);
+            var cfg = Cfg();
+            cfg.EnableRealmJoinWatcher = watcher;
+
+            Assert.Equal(expected, DiagnosticsPackageService.IsSectionActive(section, cfg, wdp));
+        }
+
        private static string[] ZipEntryNames(byte[] zipBytes)
        {
            using var ms = new MemoryStream(zipBytes);
@@ -341,7 +527,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
        {
            // On-demand mid-session (no outcome yet): the OnFailure gate must NOT skip —
            // there is no known success to skip on. Reaching the archive build (sentinel
-            // throw → error result) proves the gate was passed; a skip would return null.
+            // throw → error result) proves the gate was passed; a skip would return Skipped.
            using var rig = new Rig();
            var result = await BuildGateProbe(rig.Logger, "OnFailure")
                .CreateAndUploadAsync(enrollmentSucceeded: null, fileNameSuffix: "server-requested");
@@ -357,7 +543,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
            var result = await BuildGateProbe(rig.Logger, "OnFailure")
                .CreateAndUploadAsync(enrollmentSucceeded: true);

-            Assert.Null(result);
+            Assert.NotNull(result);
+            Assert.True(result!.Skipped);
+            Assert.False(result.Success);
+            Assert.Equal(DiagnosticsUploadResult.SkipOnFailureSucceeded, result.ErrorCode);
        }

        [Fact]
@@ -367,7 +556,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
            var result = await BuildGateProbe(rig.Logger, "Off")
                .CreateAndUploadAsync(enrollmentSucceeded: null);

-            Assert.Null(result);
+            // The gate name travels in ErrorCode so the dispatcher's server_action_failed
+            // event says "mode_off" instead of a generic "diagnostics_upload_failed".
+            Assert.NotNull(result);
+            Assert.True(result!.Skipped);
+            Assert.Equal(DiagnosticsUploadResult.SkipModeOff, result.ErrorCode);
        }

        [Theory]
@@ -122,6 +122,28 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Runtime
            Assert.Equal("config_fetch_failed", (string)typed["failureReason"]);
        }

+        [Fact]
+        public async Task Dispatch_request_diagnostics_skipped_by_gate_surfaces_gate_name_as_failure_reason()
+        {
+            // Session 2550bcea (2026-08-29): the on-demand collection was refused by the
+            // mode=Off gate and the portal only saw a generic "diagnostics_upload_failed".
+            // The gate name must travel through to the event so the operator can tell a
+            // config gate from a real upload error.
+            using var rig = new Rig();
+            rig.DiagnosticsResult = DiagnosticsUploadResult.SkippedBy(DiagnosticsUploadResult.SkipModeOff);
+
+            await rig.Build().DispatchAsync(new List<ServerAction>
+            {
+                new ServerAction { Type = ServerActionTypes.RequestDiagnostics, QueuedAt = DateTime.UtcNow },
+            });
+
+            Assert.Equal(1, rig.DiagnosticsCalls);
+            Assert.Empty(rig.EventsOfType("server_action_executed"));
+            var failed = rig.EventsOfType("server_action_failed").Single();
+            var typed = Assert.IsAssignableFrom<IReadOnlyDictionary<string, object>>(failed.TypedPayload!);
+            Assert.Equal(DiagnosticsUploadResult.SkipModeOff, (string)typed["failureReason"]);
+        }
+
        [Fact]
        public async Task Dispatch_unknown_action_type_emits_failed_with_unknown_action_type_reason()
        {
@@ -0,0 +1,322 @@
+#nullable enable
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.SystemSignals;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Agent.V2.Core.Tests.Orchestration;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring
+{
+    /// <summary>
+    /// Scope of the Shell-Core replay: it recovers the Hello-wizard start and NOTHING else.
+    /// <para>
+    /// The replay had existed since session 772fe502 with no caller. Wiring it up (2026-08-19)
+    /// activated three rails at once, and only one of them is safe to replay:
+    /// </para>
+    /// <list type="bullet">
+    ///   <item><b>62404 Hello-wizard start — replayed.</b> A conservative fact: it vetoes a
+    ///     premature "Hello is disabled" skip and can never by itself complete a session, so
+    ///     replaying it can only make the agent wait longer, never finish early.</item>
+    ///   <item><b>62407 ESP exit — never replayed.</b> Windows writes the identical description
+    ///     for the intermediate DeviceSetup-to-AccountSetup transition and the final exit, so the
+    ///     record carries no evidence of its own position; the reducer orders exits by ingest
+    ///     ordinal, which for a replay is fresher than reality; and arm C of
+    ///     ShouldTransitionToAwaitingHello opens on any arriving exit once the restored state
+    ///     carries AccountSetupEntered + a genuine IME user session + desktop arrival. See
+    ///     ClassicEspExitingOnRestoredStateTests for the reducer half of that proof.</item>
+    ///   <item><b>62407 ESP failure — never replayed.</b> Re-injecting a historic failure as
+    ///     fresh can fail a session that recovered (ANALYZE-ESP-006).</item>
+    /// </list>
+    /// </summary>
+    public sealed class ShellCoreTrackerReplayScopeTests
+    {
+        private static readonly DateTime ClockNow = new DateTime(2026, 8, 19, 8, 43, 16, DateTimeKind.Utc);
+
+        // The REAL Shell-Core wording. Byte-identical for the intermediate DeviceSetup-to-
+        // AccountSetup transition and for the final post-AccountSetup exit — that identity is the
+        // whole reason a replayed exit cannot be classified.
+        private const string EspExitDescription = "CommercialOOBE_ESPProgress_Page_Exiting";
+        private const string EspFailureDescription = "CommercialOOBE_ESPProgress_Failure";
+        private const string AadHelloDescription = "CloudExperienceHost web app activity: AADHello";
+        private const string OtherWebAppDescription = "CloudExperienceHost web app activity: SomethingElse";
+
+        private sealed class Fixture : IDisposable
+        {
+            public TempDirectory Tmp { get; } = new TempDirectory();
+            public FakeSignalIngressSink PostSink { get; } = new FakeSignalIngressSink();
+            public VirtualClock Clock { get; } = new VirtualClock(ClockNow);
+
+            public ShellCoreTracker Build() => new ShellCoreTracker(
+                sessionId: "S1",
+                tenantId: "T1",
+                post: new InformationalEventPost(PostSink, Clock),
+                logger: new AgentLogger(Tmp.Path, AgentLogLevel.Info),
+                helloTracker: null);
+
+            public List<FakeSignalIngressSink.PostedSignal> AgentTraces() =>
+                PostSink.Posted.Where(p =>
+                    p.Payload != null
+                    && p.Payload.TryGetValue(SignalPayloadKeys.EventType, out var et)
+                    && et == "agent_trace").ToList();
+
+            public void Dispose() => Tmp.Dispose();
+        }
+
+        private static (int, string, DateTime) Record(int id, string description, DateTime at)
+            => (id, description, at);
+
+        // ------------------------------------------------------------------ the wizard rail
+
+        [Fact]
+        public void The_hello_wizard_start_is_replayed_with_its_original_source_time()
+        {
+            // Session 772fe502: an agent restarted while the user sits inside the Hello wizard
+            // would otherwise never learn the wizard ran. This is the observation the replay
+            // exists for.
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var order = new List<string>();
+            HelloWizardStartedEventArgs? captured = null;
+            tracker.HelloWizardStarted += (_, args) => { order.Add("wizard"); captured = args; };
+            tracker.FinalizingSetupPhaseTriggered += (_, reason) => order.Add($"finalizing:{reason}");
+
+            var duringDowntime = ClockNow.AddMinutes(-37);
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppStarted, AadHelloDescription, duringDowntime),
+            });
+
+            Assert.Equal(new[] { "wizard", "finalizing:hello_wizard_started" }, order);
+            Assert.NotNull(captured);
+            // The historical time must survive the replay — collapsing to now would date the
+            // wizard after the restart and skew every duration derived from it.
+            Assert.Equal(duringDowntime, captured!.OccurredAtUtc);
+        }
+
+        [Fact]
+        public void The_wizard_replay_is_single_shot_across_repeated_records()
+        {
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var starts = 0;
+            tracker.HelloWizardStarted += (_, __) => starts++;
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppStarted, AadHelloDescription, ClockNow.AddMinutes(-30)),
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppStarted, AadHelloDescription, ClockNow.AddMinutes(-20)),
+            });
+
+            Assert.Equal(1, starts);
+        }
+
+        [Fact]
+        public void A_non_hello_web_app_start_is_ignored()
+        {
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var starts = 0;
+            tracker.HelloWizardStarted += (_, __) => starts++;
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppStarted, OtherWebAppDescription, ClockNow.AddMinutes(-5)),
+            });
+
+            Assert.Equal(0, starts);
+            Assert.Empty(f.AgentTraces());
+        }
+
+        // ------------------------------------------------------------------ the exit rail
+
+        [Fact]
+        public void An_intermediate_only_window_raises_nothing_that_can_reach_the_reducer()
+        {
+            // THE regression this whole review chain is about: restart, and the only 62407 in the
+            // window is the historic DeviceSetup-to-AccountSetup handoff. Nothing may leave the
+            // tracker on a rail the decision engine listens to.
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var espExits = 0;
+            var finalizing = new List<string>();
+            var failures = 0;
+            tracker.EspExited += (_, __) => espExits++;
+            tracker.FinalizingSetupPhaseTriggered += (_, reason) => finalizing.Add(reason);
+            tracker.EspFailureDetected += (_, __) => failures++;
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspExitDescription, ClockNow.AddMinutes(-52)),
+            });
+
+            Assert.Equal(0, espExits);
+            Assert.Empty(finalizing);
+            Assert.Equal(0, failures);
+        }
+
+        [Fact]
+        public void Even_several_exits_in_the_window_stay_out_of_the_decision_stream()
+        {
+            // "Newest exit wins" was an earlier attempt at this problem. It does not help: if the
+            // final exit has not happened yet, the newest record in the window is still the
+            // intermediate one. Picking a record is the wrong lever — none of them is usable.
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var espExits = 0;
+            tracker.EspExited += (_, __) => espExits++;
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspExitDescription, ClockNow.AddMinutes(-52)),
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspExitDescription, ClockNow.AddMinutes(-9)),
+            });
+
+            Assert.Equal(0, espExits);
+        }
+
+        [Fact]
+        public void A_historic_esp_failure_is_never_re_injected()
+        {
+            // A session that failed and then recovered on retry (ANALYZE-ESP-006) must not be
+            // failed again by its own history.
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var failures = new List<string>();
+            tracker.EspFailureDetected += (_, failureType) => failures.Add(failureType);
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspFailureDescription, ClockNow.AddMinutes(-40)),
+            });
+
+            Assert.Empty(failures);
+        }
+
+        // ------------------------------------------------------------------ visibility
+
+        [Fact]
+        public void Skipped_records_are_reported_once_as_an_agent_trace()
+        {
+            // Dropping evidence silently is how this class of bug survives. The gap has to stay
+            // visible to whoever debugs the session later — as an informational event, which is
+            // decision-neutral by construction.
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspExitDescription, ClockNow.AddMinutes(-52)),
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspFailureDescription, ClockNow.AddMinutes(-40)),
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppEvent, EspExitDescription, ClockNow.AddMinutes(-9)),
+            });
+
+            var trace = Assert.Single(f.AgentTraces());
+            var data = Assert.IsAssignableFrom<IReadOnlyDictionary<string, object>>(trace.TypedPayload);
+            Assert.Equal(2, data["skippedEspExits"]);
+            Assert.Equal(1, data["skippedEspFailures"]);
+            Assert.Equal("replayed_62407_not_orderable", data["reason"]);
+            Assert.Equal(ClockNow.AddMinutes(-52).ToString("o"), data["oldestSkippedUtc"]);
+            Assert.Equal(ClockNow.AddMinutes(-9).ToString("o"), data["newestSkippedUtc"]);
+        }
+
+        [Fact]
+        public void A_wizard_only_window_reports_nothing_as_skipped()
+        {
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>
+            {
+                Record(ShellCoreTracker.EventId_ShellCore_WebAppStarted, AadHelloDescription, ClockNow.AddMinutes(-30)),
+            });
+
+            Assert.Empty(f.AgentTraces());
+        }
+
+        [Fact]
+        public void An_empty_batch_is_a_no_op()
+        {
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var raised = 0;
+            tracker.EspExited += (_, __) => raised++;
+            tracker.HelloWizardStarted += (_, __) => raised++;
+
+            tracker.ReplayBackfillRecords(new List<(int, string, DateTime)>());
+
+            Assert.Equal(0, raised);
+            Assert.Empty(f.AgentTraces());
+        }
+
+        // ------------------------------------------------------------------ live path untouched
+
+        [Fact]
+        public void The_live_path_still_raises_the_exit_normally()
+        {
+            // Narrowing the REPLAY must not narrow live observation — that is the agent's primary
+            // signal source and the one the completion recovery actually runs on.
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var exits = new List<DateTime>();
+            tracker.EspExited += (_, args) => exits.Add(args.OccurredAtUtc);
+
+            tracker.ProcessEvent(
+                eventId: ShellCoreTracker.EventId_ShellCore_WebAppEvent,
+                description: EspExitDescription,
+                timestamp: ClockNow,
+                providerName: "Microsoft-Windows-Shell-Core",
+                isBackfill: false);
+
+            Assert.Equal(ClockNow, Assert.Single(exits));
+        }
+
+        [Fact]
+        public void The_live_path_still_raises_esp_failures()
+        {
+            using var f = new Fixture();
+            using var tracker = f.Build();
+
+            var failures = new List<string>();
+            tracker.EspFailureDetected += (_, failureType) => failures.Add(failureType);
+
+            tracker.ProcessEvent(
+                eventId: ShellCoreTracker.EventId_ShellCore_WebAppEvent,
+                description: EspFailureDescription,
+                timestamp: ClockNow,
+                providerName: "Microsoft-Windows-Shell-Core",
+                isBackfill: false);
+
+            Assert.Single(failures);
+        }
+
+        // ------------------------------------------------------------------ window clamp
+
+        [Theory]
+        [InlineData(0, 1)]
+        [InlineData(-42, 1)]
+        [InlineData(5, 5)]
+        [InlineData(ShellCoreTracker.BackfillLookbackMaxMinutes, ShellCoreTracker.BackfillLookbackMaxMinutes)]
+        [InlineData(ShellCoreTracker.BackfillLookbackMaxMinutes + 1, ShellCoreTracker.BackfillLookbackMaxMinutes)]
+        [InlineData(int.MaxValue, ShellCoreTracker.BackfillLookbackMaxMinutes)]
+        public void Lookback_is_clamped_to_a_sane_window(int requested, int expected)
+        {
+            // int.MaxValue matters: the query multiplies minutes by 60_000, so an unclamped value
+            // would overflow into a negative timediff and silently match nothing.
+            Assert.Equal(expected, ShellCoreTracker.ClampLookbackMinutes(requested));
+        }
+    }
+}
@@ -59,6 +59,71 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.SystemSignals
        public void ClassifyEnforcementState_bands(int state, string expected)
            => Assert.Equal(expected, ImeRegistryAppStateObserver.ClassifyEnforcementState(state));

+        [Theory]
+        [InlineData(1000, "installed")]
+        [InlineData(1999, "installed")]
+        [InlineData(3000, "failed")]
+        [InlineData(2000, "notApplicable")]
+        [InlineData(2999, "notApplicable")]
+        [InlineData(0, null)]
+        [InlineData(999, null)]
+        [InlineData(3001, null)]
+        [InlineData(4000, null)]
+        public void ClassifyStatusServiceStatus_bands(int status, string? expected)
+            => Assert.Equal(expected, ImeRegistryAppStateObserver.ClassifyStatusServiceStatus(status));
+
+        [Fact]
+        public void TerminalOutcome_prefers_enforcement_state_then_status_service()
+        {
+            // Enforcement state alone decides when terminal.
+            Assert.Equal("success", ImeRegistryAppStateObserver.TerminalOutcome(Entry(enforcementState: 1000)));
+            Assert.Equal("error", ImeRegistryAppStateObserver.TerminalOutcome(Entry(enforcementState: 5003)));
+            // Non-terminal enforcement bands defer to the StatusService pillar.
+            Assert.Null(ImeRegistryAppStateObserver.TerminalOutcome(Entry(enforcementState: 2009)));
+            Assert.Equal("error", ImeRegistryAppStateObserver.TerminalOutcome(
+                Entry(enforcementState: 2009, statusServiceStatus: 3000)));
+            Assert.Equal("success", ImeRegistryAppStateObserver.TerminalOutcome(Entry(statusServiceStatus: 1000)));
+            Assert.Equal("error", ImeRegistryAppStateObserver.TerminalOutcome(Entry(statusServiceStatus: 3000)));
+            // requirementsNotMet / notApplicable / empty entries are not judgeable.
+            Assert.Null(ImeRegistryAppStateObserver.TerminalOutcome(Entry(enforcementState: 3000)));
+            Assert.Null(ImeRegistryAppStateObserver.TerminalOutcome(Entry(statusServiceStatus: 2500)));
+            Assert.Null(ImeRegistryAppStateObserver.TerminalOutcome(Entry()));
+        }
+
+        [Fact]
+        public void ChangedFields_reports_each_field_and_ignores_espPhase_casing()
+        {
+            var prev = Entry(enforcementState: 2009, errorCode: null, exitCode: null,
+                statusServiceStatus: null, espTracked: false, espPhase: "DevicePreparation");
+            var next = Entry(enforcementState: 1000, errorCode: 0, exitCode: 0,
+                statusServiceStatus: 1000, espTracked: true, espPhase: "devicepreparation");
+
+            var changed = ImeRegistryAppStateObserver.ChangedFields(prev, next);
+
+            Assert.Equal(
+                new[] { "enforcementState", "errorCode", "exitCode", "statusServiceStatus", "espTracked" },
+                changed);
+            // Case-only espPhase difference is not a change; identity diffs to empty.
+            Assert.DoesNotContain("espPhase", changed);
+            Assert.Empty(ImeRegistryAppStateObserver.ChangedFields(next, next));
+        }
+
+        [Fact]
+        public void ChangedFields_null_previous_reports_populated_fields_of_new_entry()
+        {
+            var fresh = Entry(enforcementState: 2000, espTracked: true, espPhase: "AccountSetup");
+
+            var changed = ImeRegistryAppStateObserver.ChangedFields(null, fresh);
+
+            Assert.Contains("enforcementState", changed);
+            Assert.Contains("espTracked", changed);
+            Assert.Contains("espPhase", changed);
+            // Fields that are null on both sides are not "changes" for a brand-new entry.
+            Assert.DoesNotContain("errorCode", changed);
+            Assert.DoesNotContain("exitCode", changed);
+            Assert.DoesNotContain("statusServiceStatus", changed);
+        }
+
        [Fact]
        public void DiffSnapshots_reports_only_changed_fields()
        {
@@ -119,6 +184,40 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.SystemSignals
            Assert.Equal("success", evt.Payload["enforcementClass"]);
        }

+        [Fact]
+        public void NonEmpty_baseline_emits_one_summary_with_counts()
+        {
+            var (sink, clock, observer) = CreateObserver(trackerApps: null);
+            var current = Snapshot((App1, 1000, 0), (App2, 5003, 101));
+
+            using (new ImeRegistryAppStateObserver.ScopedSnapshotOverride(() => current))
+            {
+                observer.Tick("baseline");
+                observer.Tick("periodic"); // summary is one-shot, not per tick
+            }
+
+            var summary = Assert.Single(Events(sink, SharedEventTypes.RegistryAppBaseline));
+            Assert.Equal("2", summary.Payload!["totalApps"]);
+            Assert.Equal("1", summary.Payload["successCount"]);
+            Assert.Equal("1", summary.Payload["errorCount"]);
+            // The baseline stays silent on the diff rail.
+            Assert.Empty(Events(sink, SharedEventTypes.RegistryAppState));
+        }
+
+        [Fact]
+        public void Empty_baseline_emits_no_summary()
+        {
+            var (sink, clock, observer) = CreateObserver(trackerApps: null);
+            var current = new ImeRegistrySnapshot();
+
+            using (new ImeRegistryAppStateObserver.ScopedSnapshotOverride(() => current))
+            {
+                observer.Tick("baseline");
+            }
+
+            Assert.Empty(Events(sink, SharedEventTypes.RegistryAppBaseline));
+        }
+
        [Fact]
        public void Unchanged_snapshot_emits_nothing()
        {
@@ -230,6 +329,20 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.SystemSignals
            return (sink, clock, observer);
        }

+        private static AppRegistryEntry Entry(
+            int? enforcementState = null, long? errorCode = null, int? exitCode = null,
+            int? statusServiceStatus = null, bool espTracked = false, string? espPhase = null)
+        {
+            var entry = new AppRegistryEntry($"{ImeRegistrySnapshot.DeviceContext}|{App1}", ImeRegistrySnapshot.DeviceContext, App1);
+            entry.EnforcementState = enforcementState;
+            entry.ErrorCode = errorCode;
+            entry.ExitCode = exitCode;
+            entry.StatusServiceStatus = statusServiceStatus;
+            entry.EspTracked = espTracked;
+            entry.EspPhase = espPhase;
+            return entry;
+        }
+
        private static ImeRegistrySnapshot Snapshot(params (string appId, int enforcementState, long? errorCode)[] apps)
        {
            var snapshot = new ImeRegistrySnapshot();
@@ -0,0 +1,130 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.SystemSignals;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Agent.V2.Core.Tests.Orchestration;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.SystemSignals
+{
+    /// <summary>
+    /// Session afee7ae0 (2026-08-18) — Device Preparation structural-noise suppression.
+    /// A nine-minute WDP session shipped 900+ occurrences of WIL error 1005 plus 400+
+    /// duplicate-workload 417/418 records and "Autopilot policy not found" 100s — all
+    /// structural on WDP (no deployment profile exists; the BootstrapperAgent's SLDM
+    /// progress poll produces the 417/418 chatter). On WDP those IDs are suppressed
+    /// entirely (<see cref="ModernDeploymentTracker.DevicePreparationNoiseEventIds"/>);
+    /// genuine diagnostics (e.g. 408 provisioning warnings) and Critical records keep
+    /// flowing, and Classic sessions keep the harmless-downgrade + rollup path.
+    /// </summary>
+    public sealed class ModernDeploymentTrackerDevicePrepTests : IDisposable
+    {
+        private static readonly DateTime At = new DateTime(2026, 8, 18, 9, 10, 0, DateTimeKind.Utc);
+
+        private readonly TempDirectory _tmp = new TempDirectory();
+        private readonly FakeSignalIngressSink _sink;
+        private readonly AgentLogger _logger;
+
+        public ModernDeploymentTrackerDevicePrepTests()
+        {
+            _sink = new FakeSignalIngressSink();
+            _logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
+        }
+
+        public void Dispose() => _tmp.Dispose();
+
+        private ModernDeploymentTracker BuildTracker(bool isDevicePreparation) =>
+            new ModernDeploymentTracker(
+                sessionId: "sess-wdp-noise",
+                tenantId: "tenant-wdp-noise",
+                post: new InformationalEventPost(_sink, new VirtualClock(At)),
+                logger: _logger,
+                backfillEnabled: false,
+                isDevicePreparation: isDevicePreparation);
+
+        private void Process(ModernDeploymentTracker tracker, int eventId, int level, string shortName, string channel)
+        {
+            tracker.ProcessEvent(
+                eventId: eventId,
+                level: level,
+                levelDisplayName: level == 1 ? "Critical" : level == 2 ? "Error" : "Warning",
+                providerName: "ModernDeployment-Diagnostics-Provider",
+                timeCreatedUtc: At,
+                formattedDescription: $"EventID {eventId} record.",
+                shortName: shortName,
+                channelName: channel,
+                isBackfill: false);
+        }
+
+        private List<FakeSignalIngressSink.PostedSignal> PostedModernDeployment() =>
+            _sink.Posted.Where(p =>
+                p.Kind == DecisionSignalKind.InformationalEvent
+                && p.Payload != null
+                && p.Payload.TryGetValue(SignalPayloadKeys.EventType, out var et)
+                && et.StartsWith("modern_deployment", StringComparison.Ordinal)).ToList();
+
+        [Theory]
+        [InlineData(100, 3, "Autopilot")]           // policy not found — no profile exists on WDP
+        [InlineData(417, 3, "Autopilot")]           // duplicate workload — SLDM poll chatter
+        [InlineData(418, 3, "Autopilot")]           // duplicate batch — SLDM poll chatter
+        [InlineData(1005, 2, "ManagementService")]  // WIL error storm
+        public void WdpNoiseIds_AreFullySuppressed_OnDevicePreparation(int eventId, int level, string shortName)
+        {
+            var tracker = BuildTracker(isDevicePreparation: true);
+            var channel = shortName == "Autopilot"
+                ? ModernDeploymentTracker.AutopilotChannel
+                : ModernDeploymentTracker.ManagementChannel;
+
+            for (var i = 0; i < 10; i++)
+            {
+                Process(tracker, eventId, level, shortName, channel);
+            }
+
+            Assert.Empty(PostedModernDeployment());
+        }
+
+        [Fact]
+        public void GenuineWdpWarning_408_KeepsFlowing_OnDevicePreparation()
+        {
+            // 408 "Autopilot Provisioning reported a warning" carries the real WDP session
+            // context — it is NOT in the noise set and must keep flowing.
+            var tracker = BuildTracker(isDevicePreparation: true);
+
+            Process(tracker, 408, level: 3, shortName: "Autopilot", channel: ModernDeploymentTracker.AutopilotChannel);
+
+            var posted = Assert.Single(PostedModernDeployment());
+            Assert.Equal("modern_deployment_warning", posted.Payload![SignalPayloadKeys.EventType]);
+        }
+
+        [Fact]
+        public void CriticalRecords_AreNeverSuppressed_EvenForNoiseIds()
+        {
+            var tracker = BuildTracker(isDevicePreparation: true);
+
+            Process(tracker, 1005, level: 1, shortName: "ManagementService", channel: ModernDeploymentTracker.ManagementChannel);
+
+            var posted = Assert.Single(PostedModernDeployment());
+            Assert.Equal("modern_deployment_error", posted.Payload![SignalPayloadKeys.EventType]);
+        }
+
+        [Fact]
+        public void ClassicSessions_KeepTheHarmlessDowngradePath_ForTheSameIds()
+        {
+            // Classic regression guard: without the WDP flag EventID 100 still flows through
+            // the harmless-downgrade path (individual Debug emissions up to the rollup limit).
+            var tracker = BuildTracker(isDevicePreparation: false);
+
+            for (var i = 0; i < 2; i++)
+            {
+                Process(tracker, 100, level: 3, shortName: "Autopilot", channel: ModernDeploymentTracker.AutopilotChannel);
+            }
+
+            Assert.Equal(2, PostedModernDeployment().Count);
+        }
+    }
+}
@@ -0,0 +1,258 @@
+#nullable enable
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.SystemSignals;
+using AutopilotMonitor.Agent.V2.Core.Runtime;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.SystemSignals
+{
+    /// <summary>
+    /// Pure state machine behind the power watcher: AC↔battery edges, the 50/30/15 threshold
+    /// ladder (latch once per lifetime, lowest-crossed-only on multi-level jumps, baseline
+    /// coverage for sessions starting low), null-percent tolerance and the storm cap.
+    /// </summary>
+    public sealed class PowerStateTransitionTrackerTests
+    {
+        private static PowerStateResult Ac(int? percent = 80, bool charging = true) => new PowerStateResult
+        {
+            OnAcPower = true,
+            HasBattery = true,
+            BatteryPercent = percent,
+            IsCharging = charging,
+            BatteryLifeMinutes = null,
+        };
+
+        private static PowerStateResult Battery(int? percent, int? lifeMinutes = 90) => new PowerStateResult
+        {
+            OnAcPower = false,
+            HasBattery = true,
+            BatteryPercent = percent,
+            IsCharging = false,
+            BatteryLifeMinutes = lifeMinutes,
+        };
+
+        [Fact]
+        public void Baseline_on_ac_is_silent()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            Assert.Empty(tracker.Baseline(Ac()));
+        }
+
+        [Fact]
+        public void Baseline_without_battery_or_with_probe_error_is_silent()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            Assert.Empty(tracker.Baseline(new PowerStateResult { OnAcPower = true, HasBattery = false }));
+            Assert.Empty(tracker.Baseline(new PowerStateResult { ProbeError = "boom" }));
+        }
+
+        [Fact]
+        public void Baseline_on_battery_above_ladder_is_silent()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            Assert.Empty(tracker.Baseline(Battery(80)));
+        }
+
+        [Fact]
+        public void Baseline_at_12_percent_emits_exactly_the_15_threshold()
+        {
+            var tracker = new PowerStateTransitionTracker();
+
+            var emissions = tracker.Baseline(Battery(12));
+
+            var e = Assert.Single(emissions);
+            Assert.Equal(PowerStateTransitionTracker.TransitionThresholdCrossed, e.Transition);
+            Assert.Equal(15, e.ThresholdPercent);
+            Assert.Equal(12, e.BatteryPercent);
+            Assert.Equal(EventSeverity.Error, e.Severity);
+            Assert.True(e.ImmediateUpload);
+        }
+
+        [Fact]
+        public void Baseline_at_25_percent_emits_30_and_latches_50()
+        {
+            var tracker = new PowerStateTransitionTracker();
+
+            var baseline = tracker.Baseline(Battery(25));
+            var e = Assert.Single(baseline);
+            Assert.Equal(30, e.ThresholdPercent);
+            Assert.Equal(EventSeverity.Warning, e.Severity);
+            Assert.True(e.ImmediateUpload);
+
+            // 50 and 30 are latched by the baseline; draining to 40% stays silent, 14% emits 15.
+            Assert.Empty(tracker.Evaluate(Battery(40)));
+            var next = Assert.Single(tracker.Evaluate(Battery(14)));
+            Assert.Equal(15, next.ThresholdPercent);
+        }
+
+        [Fact]
+        public void Ac_to_battery_emits_warning_with_immediate_upload()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Ac(63));
+
+            var e = Assert.Single(tracker.Evaluate(Battery(63)));
+
+            Assert.Equal(PowerStateTransitionTracker.TransitionAcToBattery, e.Transition);
+            Assert.Null(e.ThresholdPercent);
+            Assert.Equal(EventSeverity.Warning, e.Severity);
+            Assert.True(e.ImmediateUpload);
+            Assert.False(e.OnAcPower);
+            Assert.Equal(63, e.BatteryPercent);
+        }
+
+        [Fact]
+        public void Battery_to_ac_emits_info_without_immediate_upload()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Battery(70));
+
+            var e = Assert.Single(tracker.Evaluate(Ac(70)));
+
+            Assert.Equal(PowerStateTransitionTracker.TransitionBatteryToAc, e.Transition);
+            Assert.Equal(EventSeverity.Info, e.Severity);
+            Assert.False(e.ImmediateUpload);
+        }
+
+        [Fact]
+        public void No_diff_stays_silent()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Ac());
+
+            Assert.Empty(tracker.Evaluate(Ac()));
+            Assert.Empty(tracker.Evaluate(Ac(79)));
+        }
+
+        [Fact]
+        public void Unplug_below_threshold_emits_transition_and_threshold_together()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Ac(10));
+
+            var emissions = tracker.Evaluate(Battery(10));
+
+            Assert.Equal(2, emissions.Count);
+            Assert.Equal(PowerStateTransitionTracker.TransitionAcToBattery, emissions[0].Transition);
+            Assert.Equal(PowerStateTransitionTracker.TransitionThresholdCrossed, emissions[1].Transition);
+            Assert.Equal(15, emissions[1].ThresholdPercent);
+        }
+
+        [Fact]
+        public void Multi_level_drop_emits_lowest_crossed_level_only()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Battery(60));
+
+            var e = Assert.Single(tracker.Evaluate(Battery(10)));
+
+            Assert.Equal(15, e.ThresholdPercent);
+            // All levels are latched — recovering and re-draining emits nothing more.
+            tracker.Evaluate(Ac(90));
+            Assert.Single(tracker.Evaluate(Battery(45)), x => x.Transition == PowerStateTransitionTracker.TransitionAcToBattery);
+            Assert.Empty(tracker.Evaluate(Battery(13)));
+        }
+
+        [Fact]
+        public void Each_level_latches_once_per_lifetime()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Battery(70));
+
+            Assert.Single(tracker.Evaluate(Battery(48))); // 50
+            Assert.Empty(tracker.Evaluate(Battery(47)));  // still inside 50, no re-emit
+            Assert.Single(tracker.Evaluate(Battery(29))); // 30
+            Assert.Single(tracker.Evaluate(Battery(15))); // 15 (boundary: <= level)
+            Assert.Empty(tracker.Evaluate(Battery(5)));   // ladder exhausted
+        }
+
+        [Fact]
+        public void Threshold_severity_ladder_is_info_warning_error()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Battery(70));
+
+            var fifty = Assert.Single(tracker.Evaluate(Battery(50)));
+            Assert.Equal(EventSeverity.Info, fifty.Severity);
+            Assert.False(fifty.ImmediateUpload);
+
+            var thirty = Assert.Single(tracker.Evaluate(Battery(30)));
+            Assert.Equal(EventSeverity.Warning, thirty.Severity);
+            Assert.True(thirty.ImmediateUpload);
+
+            var fifteen = Assert.Single(tracker.Evaluate(Battery(15)));
+            Assert.Equal(EventSeverity.Error, fifteen.Severity);
+            Assert.True(fifteen.ImmediateUpload);
+        }
+
+        [Fact]
+        public void Null_battery_percent_skips_thresholds_but_ac_diff_still_works()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Ac(null));
+
+            var e = Assert.Single(tracker.Evaluate(Battery(null, lifeMinutes: null)));
+
+            Assert.Equal(PowerStateTransitionTracker.TransitionAcToBattery, e.Transition);
+            Assert.Null(e.BatteryPercent);
+            Assert.Contains("battery level unknown", e.Message);
+            Assert.Empty(tracker.Evaluate(Battery(null, lifeMinutes: null)));
+        }
+
+        [Fact]
+        public void Probe_error_mid_run_preserves_state()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Ac());
+
+            Assert.Empty(tracker.Evaluate(new PowerStateResult { ProbeError = "transient" }));
+            // State was not corrupted by the error — the real transition still diffs cleanly.
+            Assert.Single(tracker.Evaluate(Battery(60)));
+        }
+
+        [Fact]
+        public void Evaluate_without_baseline_latches_like_a_baseline()
+        {
+            var tracker = new PowerStateTransitionTracker();
+
+            var e = Assert.Single(tracker.Evaluate(Battery(12)));
+
+            // No phantom ac_to_battery from the implicit default state — only the threshold.
+            Assert.Equal(PowerStateTransitionTracker.TransitionThresholdCrossed, e.Transition);
+        }
+
+        [Fact]
+        public void Emission_cap_suppresses_and_flips_flag_once()
+        {
+            var tracker = new PowerStateTransitionTracker(maxEmissions: 4);
+            tracker.Baseline(Ac());
+
+            // Flapping power source: each edge is one emission.
+            for (var i = 0; i < 2; i++)
+            {
+                Assert.Single(tracker.Evaluate(Battery(80)));
+                Assert.Single(tracker.Evaluate(Ac(80)));
+            }
+            Assert.False(tracker.EmissionCapReached);
+
+            Assert.Empty(tracker.Evaluate(Battery(80)));
+            Assert.True(tracker.EmissionCapReached);
+            Assert.Empty(tracker.Evaluate(Ac(80)));
+        }
+
+        [Fact]
+        public void Message_carries_percent_and_transition_context()
+        {
+            var tracker = new PowerStateTransitionTracker();
+            tracker.Baseline(Ac(62));
+
+            var toBattery = Assert.Single(tracker.Evaluate(Battery(62)));
+            Assert.Contains("AC to battery", toBattery.Message);
+            Assert.Contains("battery 62%", toBattery.Message);
+
+            var backToAc = Assert.Single(tracker.Evaluate(Ac(63)));
+            Assert.Contains("back to AC", backToAc.Message);
+            Assert.Contains("charging", backToAc.Message);
+        }
+    }
+}
@@ -0,0 +1,429 @@
+#nullable enable
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.SystemSignals;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.Agent.V2.Core.Tests.Orchestration;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using AutopilotMonitor.Shared;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.SystemSignals
+{
+    /// <summary>
+    /// SystemTimelineTracker — clock steps (Kernel-General 1) and completed sleep episodes
+    /// (Power-Troubleshooter 1 / Kernel-Power 507) from the System channel. Drives the primitive
+    /// <see cref="SystemTimelineTracker.ProcessEvent"/> test seam (no real EventRecord, which is
+    /// abstract + Windows-only), mirroring the WindowsUpdateTracker test pattern.
+    /// </summary>
+    public sealed class SystemTimelineTrackerTests : IDisposable
+    {
+        private static readonly DateTime At = new DateTime(2026, 8, 21, 10, 0, 0, DateTimeKind.Utc);
+
+        private readonly TempDirectory _tmp = new TempDirectory();
+        private readonly FakeSignalIngressSink _sink;
+        private readonly SystemTimelineTracker _tracker;
+        private long _nextRecordId = 1;
+
+        public SystemTimelineTrackerTests()
+        {
+            _sink = new FakeSignalIngressSink();
+            var post = new InformationalEventPost(_sink, new VirtualClock(At));
+            var logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
+            _tracker = new SystemTimelineTracker(
+                sessionId: "sess-stl",
+                tenantId: "tenant-stl",
+                post: post,
+                logger: logger,
+                backfillEnabled: false,
+                stateDirectory: null); // in-memory dedup for most tests
+        }
+
+        public void Dispose() => _tmp.Dispose();
+
+        // -------------------------------------------------------------------
+        // Emission helpers
+        // -------------------------------------------------------------------
+
+        private void EmitClockChange(
+            DateTime? oldTime, DateTime? newTime, string? rawDeltaMs = null,
+            int reason = 1, long? recordId = null, bool isBackfill = false, DateTime? timeCreatedUtc = null)
+        {
+            var data = new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase);
+            if (oldTime.HasValue) data["OldTime"] = oldTime.Value.ToString("o");
+            if (newTime.HasValue) data["NewTime"] = newTime.Value.ToString("o");
+            if (rawDeltaMs != null) data["TimeDeltaInMs"] = rawDeltaMs;
+            data["Reason"] = reason.ToString();
+            data["ProcessName"] = @"\Device\HarddiskVolume3\Windows\System32\svchost.exe";
+            data["ProcessID"] = "6892";
+
+            _tracker.ProcessEvent(
+                providerName: SystemTimelineTracker.ProviderKernelGeneral,
+                eventId: SystemTimelineTracker.EventId_ClockChange,
+                recordId: recordId ?? _nextRecordId++,
+                timeCreatedUtc: timeCreatedUtc ?? At,
+                eventData: data,
+                isBackfill: isBackfill);
+        }
+
+        private void EmitClassicResume(
+            DateTime sleepTime, DateTime wakeTime, string? effectiveState = "1",
+            string? wakeSourceText = null, long? recordId = null, bool isBackfill = false, DateTime? timeCreatedUtc = null)
+        {
+            var data = new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase)
+            {
+                ["SleepTime"] = sleepTime.ToString("o"),
+                ["WakeTime"] = wakeTime.ToString("o"),
+                ["WakeSourceType"] = "0",
+            };
+            if (effectiveState != null) data["EffectiveState"] = effectiveState;
+            if (wakeSourceText != null) data["WakeSourceText"] = wakeSourceText;
+
+            _tracker.ProcessEvent(
+                providerName: SystemTimelineTracker.ProviderPowerTroubleshooter,
+                eventId: SystemTimelineTracker.EventId_ClassicResume,
+                recordId: recordId ?? _nextRecordId++,
+                timeCreatedUtc: timeCreatedUtc ?? wakeTime,
+                eventData: data,
+                isBackfill: isBackfill);
+        }
+
+        private void EmitModernStandbyExit(
+            long sleepDurationUs, long durationUs, string powerStateAc = "true",
+            long? recordId = null, bool isBackfill = false, DateTime? timeCreatedUtc = null)
+        {
+            var data = new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase)
+            {
+                ["SleepDurationInUs"] = sleepDurationUs.ToString(),
+                ["DurationInUs"] = durationUs.ToString(),
+                ["Reason"] = "32",
+                ["PowerStateAc"] = powerStateAc,
+                ["BatteryRemainingCapacityOnExit"] = "34180",
+            };
+
+            _tracker.ProcessEvent(
+                providerName: SystemTimelineTracker.ProviderKernelPower,
+                eventId: SystemTimelineTracker.EventId_ModernStandbyExit,
+                recordId: recordId ?? _nextRecordId++,
+                timeCreatedUtc: timeCreatedUtc ?? At,
+                eventData: data,
+                isBackfill: isBackfill);
+        }
+
+        private IReadOnlyList<FakeSignalIngressSink.PostedSignal> ByType(string eventType) =>
+            _sink.Posted.Where(p =>
+                p.Kind == DecisionSignalKind.InformationalEvent
+                && p.Payload != null
+                && p.Payload.TryGetValue(SignalPayloadKeys.EventType, out var et)
+                && et == eventType).ToList();
+
+        private static IReadOnlyDictionary<string, object> Data(FakeSignalIngressSink.PostedSignal s) =>
+            (IReadOnlyDictionary<string, object>)s.TypedPayload!;
+
+        // -------------------------------------------------------------------
+        // system_clock_changed
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void ClockStep_AboveThreshold_EmitsInfo_WithSignedDeltaAndNormalizedTimes()
+        {
+            var oldTime = At;
+            var newTime = At.AddSeconds(10);
+            EmitClockChange(oldTime, newTime, reason: 1);
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemClockChanged));
+            Assert.Equal("Info", s.Payload![SignalPayloadKeys.Severity]);
+            Assert.Equal("false", s.Payload![SignalPayloadKeys.ImmediateUpload]);
+
+            var data = Data(s);
+            Assert.Equal(10_000L, data["timeDeltaMs"]);
+            Assert.Equal("application_set", data["reasonText"]);
+            Assert.Equal(1, data["reason"]);
+            Assert.Equal(oldTime.ToString("o"), data["oldTime"]);
+            Assert.Equal(newTime.ToString("o"), data["newTime"]);
+            Assert.Equal(6892, data["processId"]);
+            Assert.Contains("forward", (string)s.Payload![SignalPayloadKeys.Message]);
+            Assert.Contains("svchost.exe", (string)s.Payload![SignalPayloadKeys.Message]);
+        }
+
+        [Theory]
+        [InlineData(1)]
+        [InlineData(1999)]
+        public void ClockMicroStep_BelowThreshold_Suppressed(int deltaMs)
+        {
+            EmitClockChange(At, At.AddMilliseconds(deltaMs));
+            Assert.Empty(ByType(Constants.EventTypes.SystemClockChanged));
+        }
+
+        [Fact]
+        public void ClockStep_Backward_EmitsNegativeDelta()
+        {
+            EmitClockChange(oldTime: At, newTime: At.AddSeconds(-3));
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemClockChanged));
+            Assert.Equal(-3000L, Data(s)["timeDeltaMs"]);
+            Assert.Contains("backward", (string)s.Payload![SignalPayloadKeys.Message]);
+        }
+
+        [Fact]
+        public void ClockStep_AtLeastFiveMinutes_WarningAndImmediateUpload()
+        {
+            EmitClockChange(At, At.AddMinutes(5), reason: 2);
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemClockChanged));
+            Assert.Equal("Warning", s.Payload![SignalPayloadKeys.Severity]);
+            Assert.Equal("true", s.Payload![SignalPayloadKeys.ImmediateUpload]);
+            Assert.Equal("hardware_clock_sync", Data(s)["reasonText"]);
+        }
+
+        [Fact]
+        public void ClockStep_NoUsableTimesOrDelta_Skipped()
+        {
+            EmitClockChange(oldTime: null, newTime: null, rawDeltaMs: "not-a-number");
+            Assert.Empty(ByType(Constants.EventTypes.SystemClockChanged));
+        }
+
+        [Fact]
+        public void ClockStep_FallsBackToTimeDeltaInMs_WhenTimesUnparseable()
+        {
+            // Only the raw delta parses — the direction information of NewTime/OldTime is gone,
+            // but the magnitude still gates and emits.
+            EmitClockChange(oldTime: null, newTime: null, rawDeltaMs: "7200000");
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemClockChanged));
+            Assert.Equal(7_200_000L, Data(s)["timeDeltaMs"]);
+        }
+
+        // -------------------------------------------------------------------
+        // system_sleep_episode — classic (Power-Troubleshooter 1)
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void ClassicResume_EffectiveState5_EmitsHibernateEpisode()
+        {
+            var sleepAt = At.AddHours(-2);
+            EmitClassicResume(sleepAt, At, effectiveState: "5", wakeSourceText: "Power Button");
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemSleepEpisode));
+            Assert.Equal("Info", s.Payload![SignalPayloadKeys.Severity]);
+
+            var data = Data(s);
+            Assert.Equal("hibernate", data["kind"]);
+            Assert.Equal(7200L, data["durationSeconds"]);
+            Assert.Equal(sleepAt.ToString("o"), data["enteredAt"]);
+            Assert.Equal(At.ToString("o"), data["exitedAt"]);
+            Assert.Equal("Power Button", data["wakeSourceText"]);
+            Assert.Contains("hibernate", (string)s.Payload![SignalPayloadKeys.Message]);
+        }
+
+        [Fact]
+        public void ClassicResume_NonHibernateState_EmitsSleepKind()
+        {
+            EmitClassicResume(At.AddMinutes(-30), At, effectiveState: "4");
+            Assert.Equal("sleep", Data(Assert.Single(ByType(Constants.EventTypes.SystemSleepEpisode)))["kind"]);
+        }
+
+        [Fact]
+        public void ClassicResume_ShortEpisode_StillEmits()
+        {
+            // No duration floor for classic sleep: the event only exists for genuinely completed
+            // S3/S4 transitions, so a 30 s real sleep is still signal.
+            EmitClassicResume(At.AddSeconds(-30), At);
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemSleepEpisode));
+            Assert.Equal(30L, Data(s)["durationSeconds"]);
+        }
+
+        // -------------------------------------------------------------------
+        // system_sleep_episode — Modern Standby (Kernel-Power 507)
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void ModernStandbyExit_EmitsEpisode_WithDerivedEnterTime()
+        {
+            // Values from a live 507 on this dev machine: 38 min scenario, ~38 min actual sleep.
+            EmitModernStandbyExit(sleepDurationUs: 2_324_095_807, durationUs: 2_330_201_652);
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemSleepEpisode));
+            var data = Data(s);
+            Assert.Equal("modern_standby", data["kind"]);
+            Assert.Equal(2330L, data["durationSeconds"]);
+            Assert.Equal(2324L, data["sleepDurationSeconds"]);
+            Assert.Equal(true, data["onAcPower"]);
+            Assert.Equal(34180L, data["batteryRemainingCapacityOnExit"]);
+            Assert.Equal(At.ToString("o"), data["exitedAt"]);
+            Assert.Equal(At.AddMilliseconds(-2_330_201.652).ToString("o"), data["enteredAt"]);
+            Assert.Contains("Modern Standby", (string)s.Payload![SignalPayloadKeys.Message]);
+        }
+
+        [Fact]
+        public void ModernStandbyExit_SleepBelowFloor_Suppressed()
+        {
+            EmitModernStandbyExit(sleepDurationUs: 30_000_000, durationUs: 90_000_000); // 30 s sleep
+            Assert.Empty(ByType(Constants.EventTypes.SystemSleepEpisode));
+        }
+
+        [Fact]
+        public void ModernStandbyExit_ScreenOffWithoutSleep_Suppressed()
+        {
+            // SleepEntered=false scenarios carry SleepDurationInUs 0 — the single duration gate
+            // suppresses them without a separate branch.
+            EmitModernStandbyExit(sleepDurationUs: 0, durationUs: 6_106_696);
+            Assert.Empty(ByType(Constants.EventTypes.SystemSleepEpisode));
+        }
+
+        [Fact]
+        public void ModernStandbyExit_ScenarioShorterThanSleep_ClampsToSleepDuration()
+        {
+            EmitModernStandbyExit(sleepDurationUs: 120_000_000, durationUs: 0);
+
+            var data = Data(Assert.Single(ByType(Constants.EventTypes.SystemSleepEpisode)));
+            Assert.Equal(120L, data["durationSeconds"]);
+            Assert.Equal(120L, data["sleepDurationSeconds"]);
+        }
+
+        // -------------------------------------------------------------------
+        // Backfill semantics
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void BackfilledEvent_UsesEventTimeForTimelineTimestamp_AndFlagsData()
+        {
+            // A pre-agent standby episode (record created before the agent started) must land on
+            // the timeline where the device actually woke, not at agent start.
+            var wakeTime = At.AddHours(-3);
+            EmitClassicResume(wakeTime.AddHours(-1), wakeTime, isBackfill: true, timeCreatedUtc: wakeTime);
+
+            var s = Assert.Single(ByType(Constants.EventTypes.SystemSleepEpisode));
+            Assert.Equal(wakeTime, s.OccurredAtUtc);
+            Assert.Equal(true, Data(s)["backfilled"]);
+        }
+
+        // -------------------------------------------------------------------
+        // Dedup / watermark
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void SameRecordId_ProcessedTwice_EmitsOnce()
+        {
+            EmitClockChange(At, At.AddMinutes(1), recordId: 42);
+            EmitClockChange(At, At.AddMinutes(1), recordId: 42);
+
+            Assert.Single(ByType(Constants.EventTypes.SystemClockChanged));
+        }
+
+        [Fact]
+        public void BackfillEventWithLowerRecordId_AfterLiveEvent_IsStillEmitted()
+        {
+            // The live watcher is armed BEFORE backfill runs, so a live record with a higher
+            // RecordId can be processed first. An older, never-emitted backfill record must NOT be
+            // suppressed — pre-agent episodes are the whole point (high-water-mark trap).
+            EmitClockChange(At, At.AddMinutes(1), recordId: 100);                       // live, high
+            EmitClockChange(At, At.AddMinutes(2), recordId: 50, isBackfill: true);      // backfill, older
+
+            Assert.Equal(2, ByType(Constants.EventTypes.SystemClockChanged).Count);
+        }
+
+        [Fact]
+        public void Watermark_PersistsAcrossTrackerInstances()
+        {
+            var post = new InformationalEventPost(_sink, new VirtualClock(At));
+            var logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
+            var clockData = new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase)
+            {
+                ["OldTime"] = At.ToString("o"),
+                ["NewTime"] = At.AddMinutes(10).ToString("o"),
+                ["Reason"] = "1",
+            };
+
+            var first = new SystemTimelineTracker("s", "t", post, logger, backfillEnabled: false, stateDirectory: _tmp.Path);
+            first.ProcessEvent(SystemTimelineTracker.ProviderKernelGeneral, SystemTimelineTracker.EventId_ClockChange,
+                recordId: 500, timeCreatedUtc: At, eventData: clockData, isBackfill: false);
+
+            // A fresh tracker (agent restart) must load the watermark and skip the already-emitted
+            // record when the backfill re-reads it.
+            var second = new SystemTimelineTracker("s", "t", post, logger, backfillEnabled: false, stateDirectory: _tmp.Path);
+            second.LoadWatermark();
+            second.ProcessEvent(SystemTimelineTracker.ProviderKernelGeneral, SystemTimelineTracker.EventId_ClockChange,
+                recordId: 500, timeCreatedUtc: At, eventData: clockData, isBackfill: true);
+
+            Assert.Single(ByType(Constants.EventTypes.SystemClockChanged));
+        }
+
+        [Fact]
+        public void UnknownProviderOrEventId_Ignored()
+        {
+            _tracker.ProcessEvent("Microsoft-Windows-Kernel-Power", eventId: 566, recordId: _nextRecordId++,
+                timeCreatedUtc: At, eventData: new Dictionary<string, string>(), isBackfill: false);
+            _tracker.ProcessEvent("Some-Other-Provider", eventId: 1, recordId: _nextRecordId++,
+                timeCreatedUtc: At, eventData: new Dictionary<string, string>(), isBackfill: false);
+
+            Assert.Empty(_sink.Posted);
+        }
+
+        // -------------------------------------------------------------------
+        // XPath + parsing
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void BuildXPath_ContainsAllThreeProviderIdPairs_AndNo506()
+        {
+            var xpath = SystemTimelineTracker.BuildXPath();
+            Assert.Contains("Provider[@Name='Microsoft-Windows-Kernel-General'] and EventID=1", xpath);
+            Assert.Contains("Provider[@Name='Microsoft-Windows-Power-Troubleshooter'] and EventID=1", xpath);
+            Assert.Contains("Provider[@Name='Microsoft-Windows-Kernel-Power'] and EventID=507", xpath);
+            Assert.DoesNotContain("506", xpath);
+        }
+
+        [Fact]
+        public void BuildBackfillXPath_AppendsTimediffClause()
+        {
+            var xpath = SystemTimelineTracker.BuildBackfillXPath(86_400_000);
+            Assert.Contains("TimeCreated[timediff(@SystemTime) <= 86400000]", xpath);
+            Assert.Contains("EventID=507", xpath);
+        }
+
+        [Fact]
+        public void ParseEventData_RealKernelGeneralPayload_YieldsAuthoritativeFields()
+        {
+            // Verbatim (values shortened) from a live Kernel-General 1 record on a 26220 dev machine.
+            const string xml =
+                "<Event xmlns='http://schemas.microsoft.com/win/2004/08/events/event'>" +
+                "<System><Provider Name='Microsoft-Windows-Kernel-General'/><EventID>1</EventID></System>" +
+                "<EventData>" +
+                "<Data Name='NewTime'>2026-08-21T09:40:02.1987028Z</Data>" +
+                "<Data Name='OldTime'>2026-08-21T09:40:02.1973028Z</Data>" +
+                "<Data Name='TimeDeltaInMs'>1</Data>" +
+                "<Data Name='Reason'>1</Data>" +
+                "<Data Name='ProcessName'>\\Device\\HarddiskVolume3\\Windows\\System32\\svchost.exe</Data>" +
+                "<Data Name='ProcessID'>6892</Data>" +
+                "</EventData></Event>";
+
+            var data = SystemTimelineTracker.ParseEventData(xml);
+            Assert.Equal("1", data["TimeDeltaInMs"]);
+            Assert.Equal("2026-08-21T09:40:02.1987028Z", data["newtime"]); // case-insensitive keys
+            Assert.NotNull(SystemTimelineTracker.TryParseUtc(data["OldTime"]));
+        }
+
+        [Fact]
+        public void FormatDuration_CompactForms()
+        {
+            Assert.Equal("2h 05m", SystemTimelineTracker.FormatDuration(TimeSpan.FromMinutes(125)));
+            Assert.Equal("56m 12s", SystemTimelineTracker.FormatDuration(TimeSpan.FromSeconds(56 * 60 + 12)));
+            Assert.Equal("45s", SystemTimelineTracker.FormatDuration(TimeSpan.FromSeconds(45)));
+        }
+
+        [Fact]
+        public void ProcessLeafName_StripsDevicePath()
+        {
+            Assert.Equal("svchost.exe",
+                SystemTimelineTracker.ProcessLeafName(@"\Device\HarddiskVolume3\Windows\System32\svchost.exe"));
+            Assert.Null(SystemTimelineTracker.ProcessLeafName(null));
+            Assert.Null(SystemTimelineTracker.ProcessLeafName(@"\Device\HarddiskVolume3\"));
+        }
+    }
+}
@@ -0,0 +1,126 @@
+using System;
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Transport;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Transport
+{
+    public class DoGroupIdServiceTests
+    {
+        // -------------------------------------------------------------------
+        // ComputeGroupId — RealmJoin byte-layout compatibility
+        // -------------------------------------------------------------------
+
+        [Fact]
+        public void ComputeGroupId_MatchesHandComputedVector()
+        {
+            // Layout: {101,48,6} + {0,0,0} + {ip[1],0,ip[2],ip[3]} + mac — through new Guid(byte[])
+            // the first three groups print little-endian, the last eight bytes verbatim.
+            var guid = DoGroupIdService.ComputeGroupId(
+                new byte[] { 192, 168, 178, 1 },
+                new byte[] { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55 });
+
+            Assert.Equal("00063065-0000-00a8-b201-001122334455", guid.ToString());
+        }
+
+        [Theory]
+        [InlineData(new byte[] { 10, 0, 0, 1 }, new byte[] { 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF })]
+        [InlineData(new byte[] { 192, 168, 1, 254 }, new byte[] { 0x00, 0x50, 0x56, 0x01, 0x02, 0x03 })]
+        [InlineData(new byte[] { 172, 16, 254, 3 }, new byte[] { 0xF0, 0x9F, 0xC2, 0x00, 0x00, 0x01 })]
+        public void ComputeGroupId_MatchesRealmJoinReferenceImplementation(byte[] ip, byte[] mac)
+        {
+            Assert.Equal(RealmJoinReferenceGuid(ip, mac), DoGroupIdService.ComputeGroupId(ip, mac));
+        }
+
+        /// <summary>Verbatim port of RealmJoin's ConvertToGuid — the compatibility contract.</summary>
+        private static Guid RealmJoinReferenceGuid(byte[] ipBytes, byte[] address)
+        {
+            byte[] prefix = { 101, 48, 6 };
+            var stuff = new byte[4];
+            stuff[0] = ipBytes[1];
+            stuff[2] = ipBytes[2];
+            stuff[3] = ipBytes[3];
+
+            return new Guid(prefix
+                .Concat(new byte[16 - prefix.Length - stuff.Length - address.Length])
+                .Concat(stuff)
+                .Concat(address)
+                .ToArray());
+        }
+
+        [Fact]
+        public void ComputeGroupId_RejectsNonIpv4AndBadMacLengths()
+        {
+            var ip4 = new byte[] { 10, 0, 0, 1 };
+            var mac = new byte[] { 1, 2, 3, 4, 5, 6 };
+
+            Assert.Throws<ArgumentException>(() => DoGroupIdService.ComputeGroupId(new byte[16], mac));
+            Assert.Throws<ArgumentException>(() => DoGroupIdService.ComputeGroupId(null!, mac));
+            Assert.Throws<ArgumentException>(() => DoGroupIdService.ComputeGroupId(ip4, new byte[8]));
+            Assert.Throws<ArgumentException>(() => DoGroupIdService.ComputeGroupId(ip4, null!));
+        }
+
+        [Fact]
+        public void ComputeGroupId_RegistryFormat_IsBracelessLowercase()
+        {
+            // RealmJoin writes SetValue(name, Guid) which stringifies via Guid.ToString() ("d"
+            // format) — our written value must be the identical string form.
+            var text = DoGroupIdService.ComputeGroupId(
+                new byte[] { 10, 1, 2, 3 }, new byte[] { 0xAB, 0xCD, 0xEF, 0x01, 0x02, 0x03 }).ToString();
+
+            Assert.DoesNotContain("{", text);
+            Assert.Equal(text.ToLowerInvariant(), text);
+            Assert.Equal(36, text.Length);
+        }
+
+        // -------------------------------------------------------------------
+        // DecideAction — ownership matrix
+        // -------------------------------------------------------------------
+
+        private const string Computed = "00063065-0000-00a8-b201-001122334455";
+        private const string Other = "11111111-2222-3333-4444-555555555555";
+
+        [Theory]
+        [InlineData(null)]
+        [InlineData("")]
+        public void DecideAction_NoExistingValue_Writes(string? existing)
+        {
+            Assert.Equal(DoGroupIdAction.Write, DoGroupIdService.DecideAction(existing, Computed, null));
+        }
+
+        [Fact]
+        public void DecideAction_ExistingEqualsComputed_IsNoOp()
+        {
+            Assert.Equal(DoGroupIdAction.NoOp, DoGroupIdService.DecideAction(Computed, Computed, null));
+        }
+
+        [Fact]
+        public void DecideAction_ExistingEqualsComputed_ToleratesBracesAndCase()
+        {
+            // A value written by another tool in "{...}"/uppercase form is still semantically ours.
+            var braced = "{" + Computed.ToUpperInvariant() + "}";
+            Assert.Equal(DoGroupIdAction.NoOp, DoGroupIdService.DecideAction(braced, Computed, null));
+        }
+
+        [Fact]
+        public void DecideAction_ExistingIsOurStaleValue_WritesUpdate()
+        {
+            // Gateway changed: the registry still holds the GUID we wrote for the old network.
+            Assert.Equal(DoGroupIdAction.Write, DoGroupIdService.DecideAction(Other, Computed, Other));
+        }
+
+        [Fact]
+        public void DecideAction_ForeignValue_Skips()
+        {
+            Assert.Equal(DoGroupIdAction.SkipForeign, DoGroupIdService.DecideAction(Other, Computed, null));
+            Assert.Equal(DoGroupIdAction.SkipForeign, DoGroupIdService.DecideAction(Other, Computed, Computed));
+        }
+
+        [Fact]
+        public void DecideAction_NonGuidGarbageExisting_SkipsAsForeign()
+        {
+            // Never overwrite a value we can't even parse — conservative by design.
+            Assert.Equal(DoGroupIdAction.SkipForeign, DoGroupIdService.DecideAction("not-a-guid", Computed, null));
+        }
+    }
+}
@@ -3,6 +3,7 @@ using System.Collections.Generic;
 using System.Linq;
 using AutopilotMonitor.Agent.V2.Core.Configuration;
 using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
 using AutopilotMonitor.Agent.V2.Core.Orchestration;
 using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
 using AutopilotMonitor.Shared.Models;
@@ -117,6 +118,16 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
                    hosts,
                    "AadJoinHost wires its onRealUserJoined callback to the already-constructed DesktopArrivalHost.");

+                // Codex review P2 (2026-08-19): EspAndHelloHost.Start() replays the Shell-Core
+                // ESP exit, but ImeLogTracker only restores its persisted app states in its own
+                // Start() — which happens later. Pin the order that makes ImeLogHost's
+                // onStateRestored nudge necessary, so a future reshuffle either keeps the nudge
+                // meaningful or fails here loudly.
+                AssertBefore<EspAndHelloHost, ImeLogHost>(
+                    hosts,
+                    "the ESP-exit replay runs before the IME app-state restore, which is why " +
+                    "ImeLogHost re-triggers the user-apps-settled synthesis after LoadState.");
+
                // Closure-latch sanity (factory lines ~139/297): the EspAndHelloHost probes close
                // over the ImeLogHost reference, which is assigned during the same factory call —
                // the host must therefore exist in the returned list.
@@ -130,5 +141,40 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
                }
            }
        }
+
+        [Fact]
+        public void Ime_app_state_callback_is_chained_into_the_user_apps_settled_recheck()
+        {
+            // sits-d Cloud-PC fix (2026-08-19): the AccountSetup synthesis is re-evaluated on every
+            // terminal IME app transition, which only works while the factory keeps this chain
+            // wired. It is five lines that a refactor can drop silently and whose absence costs a
+            // whole class of sessions their completion — so pin it here.
+            var surfaces = CreateSurfaces();
+            var hosts = surfaces.Hosts;
+            try
+            {
+                var imeHost = hosts.OfType<ImeLogHost>().Single();
+                var handler = imeHost.Tracker.OnAppStateChanged;
+
+                Assert.NotNull(handler);
+
+                // Invoking it must reach the re-check without throwing. The re-check is a no-op
+                // here (no ESP exit observed), which is the point — it must stay cheap and silent
+                // on the IME hot path until both facts are in.
+                var pkg = new AppPackageState("app-1", listPos: 0);
+                var ex = Record.Exception(() => handler!(
+                    pkg,
+                    AppInstallationState.Installing,
+                    AppInstallationState.Installed));
+                Assert.Null(ex);
+            }
+            finally
+            {
+                foreach (var host in hosts)
+                {
+                    try { host.Dispose(); } catch { /* construction-only test — best-effort cleanup */ }
+                }
+            }
+        }
    }
 }
@@ -0,0 +1,147 @@
+#nullable enable
+using System;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.SystemSignals;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
+{
+    /// <summary>
+    /// The Shell-Core ESP-exit replay is RESTART RECOVERY: it re-reads observations the agent could
+    /// not make because no agent process was running. The window is therefore measured against the
+    /// previous run's last known liveness, not guessed from a constant.
+    /// <para>
+    /// Why a constant is not enough (Codex review P2): the scheduled task carries a BootTrigger
+    /// only, with no restart-on-failure. A crashed agent does not come back until the NEXT BOOT —
+    /// possibly hours later, long after Windows wrote the final ESP exit. Five minutes would lose
+    /// it every time.
+    /// </para>
+    /// </summary>
+    public sealed class EspExitBackfillLookbackPolicyTests
+    {
+        private static readonly DateTime Now = new DateTime(2026, 8, 19, 8, 43, 16, DateTimeKind.Utc);
+        private const int Default = ShellCoreTracker.BackfillLookbackMinutes;
+
+        private static int Resolve(string? exitType, DateTime? lastAlive = null, DateTime? bootUtc = null)
+            => DefaultComponentFactory.ResolveEspExitBackfillLookbackMinutes(exitType, bootUtc, lastAlive, Now);
+
+        // ---- no previous run => nothing to recover ---------------------------------------
+
+        [Theory]
+        [InlineData("first_run")]
+        [InlineData("FIRST_RUN")]
+        [InlineData("")]
+        [InlineData(null)]
+        public void No_previous_run_means_no_replay(string? exitType)
+        {
+            Assert.Equal(0, Resolve(exitType));
+        }
+
+        [Fact]
+        public void First_run_stays_off_even_with_timestamps_available()
+        {
+            // The exit type decides, not the presence of a timestamp.
+            Assert.Equal(0, Resolve("first_run", lastAlive: Now.AddHours(-3), bootUtc: Now.AddHours(-3)));
+        }
+
+        // ---- the default is a floor, never a ceiling --------------------------------------
+
+        [Theory]
+        [InlineData("clean")]
+        [InlineData("hard_kill")]
+        [InlineData("exception_crash")]
+        [InlineData("reboot_kill")]
+        public void Without_any_timestamp_the_default_applies(string exitType)
+        {
+            Assert.Equal(Default, Resolve(exitType));
+        }
+
+        [Fact]
+        public void A_restart_that_returned_within_seconds_keeps_the_default()
+        {
+            Assert.Equal(Default, Resolve("clean", lastAlive: Now.AddSeconds(-20)));
+        }
+
+        // ---- the crash case P2 is about ---------------------------------------------------
+
+        [Fact]
+        public void A_crash_recovered_only_at_the_next_boot_gets_the_whole_gap()
+        {
+            // BootTrigger-only task: the agent was gone for three hours while the ESP finished.
+            Assert.Equal(181, Resolve("exception_crash", lastAlive: Now.AddHours(-3)));
+        }
+
+        [Fact]
+        public void Snapshot_mtime_carries_the_window_when_no_boot_time_exists()
+        {
+            // LastBootUtc is only populated for hard_kill / reboot_kill — exception_crash and
+            // clean have nothing else to go on.
+            Assert.Equal(46, Resolve("clean", lastAlive: Now.AddMinutes(-45)));
+        }
+
+        // ---- reboot: both inputs available, wider wins ------------------------------------
+
+        [Fact]
+        public void The_wider_of_the_two_inputs_wins()
+        {
+            // Snapshot last written 40 min ago, boot 12 min ago — the gap started at the snapshot.
+            Assert.Equal(41, Resolve("reboot_kill", lastAlive: Now.AddMinutes(-40), bootUtc: Now.AddMinutes(-12)));
+        }
+
+        [Fact]
+        public void Boot_time_alone_still_covers_a_reboot_without_a_snapshot()
+        {
+            Assert.Equal(41, Resolve("reboot_kill", bootUtc: Now.AddMinutes(-40)));
+        }
+
+        // ---- robustness -------------------------------------------------------------------
+
+        [Fact]
+        public void A_timestamp_in_the_future_is_ignored()
+        {
+            // Clock skew across a reboot must never produce a negative window.
+            Assert.Equal(Default, Resolve("reboot_kill", lastAlive: Now.AddMinutes(5), bootUtc: Now.AddMinutes(9)));
+        }
+
+        [Fact]
+        public void A_future_timestamp_does_not_suppress_a_valid_one()
+        {
+            Assert.Equal(31, Resolve("reboot_kill", lastAlive: Now.AddMinutes(9), bootUtc: Now.AddMinutes(-30)));
+        }
+
+        [Fact]
+        public void A_very_long_gap_is_clamped_by_the_tracker()
+        {
+            // The policy may propose more than the cap; ClampLookbackMinutes is the backstop, so
+            // the two together can never produce an unbounded event-log query.
+            var proposed = Resolve("exception_crash", lastAlive: Now.AddHours(-20));
+            Assert.True(proposed > ShellCoreTracker.BackfillLookbackMaxMinutes);
+            Assert.Equal(ShellCoreTracker.BackfillLookbackMaxMinutes,
+                ShellCoreTracker.ClampLookbackMinutes(proposed));
+        }
+
+        // ---- the snapshot probe itself ----------------------------------------------------
+
+        [Fact]
+        public void Missing_snapshot_reads_as_null_not_as_an_exception()
+        {
+            using var tmp = new Harness.TempDirectory();
+            Assert.Null(DefaultComponentFactory.ReadPreviousRunLastAliveUtc(tmp.Path));
+            Assert.Null(DefaultComponentFactory.ReadPreviousRunLastAliveUtc(string.Empty));
+        }
+
+        [Fact]
+        public void An_existing_snapshot_reports_its_write_time()
+        {
+            using var tmp = new Harness.TempDirectory();
+            var path = System.IO.Path.Combine(tmp.Path, "snapshot.json");
+            System.IO.File.WriteAllText(path, "{}");
+
+            var read = DefaultComponentFactory.ReadPreviousRunLastAliveUtc(tmp.Path);
+
+            Assert.NotNull(read);
+            Assert.Equal(DateTimeKind.Utc, read!.Value.Kind);
+            Assert.True((DateTime.UtcNow - read.Value).Duration() < TimeSpan.FromMinutes(5));
+        }
+    }
+}
@@ -1,5 +1,6 @@
 using System;
 using System.Collections.Generic;
+using System.Linq;
 using AutopilotMonitor.Agent.V2.Core.Orchestration;
 using AutopilotMonitor.DecisionCore.Signals;

@@ -11,8 +12,18 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
    internal sealed class FakeSignalIngressSink : ISignalIngressSink
    {
        private readonly List<PostedSignal> _posted = new List<PostedSignal>();
+        private readonly object _gate = new object();

-        public IReadOnlyList<PostedSignal> Posted => _posted;
+        /// <summary>
+        /// Snapshot, not the live list: producers post from timer / worker threads (e.g. the
+        /// parked-dwell tripwire) while tests poll this in a SpinWait loop. Enumerating the live
+        /// list across an Add throws "Collection was modified" — a rare CI-only failure
+        /// (run 32644425162) with no assertion text.
+        /// </summary>
+        public IReadOnlyList<PostedSignal> Posted
+        {
+            get { lock (_gate) return _posted.ToArray(); }
+        }

        /// <summary>When non-null, <see cref="Post"/> throws instead of capturing.</summary>
        public Exception? ThrowOnPost { get; set; }
@@ -27,7 +38,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
            object? typedPayload = null)
        {
            if (ThrowOnPost != null) throw ThrowOnPost;
-            _posted.Add(new PostedSignal(kind, occurredAtUtc, sourceOrigin, evidence, payload, kindSchemaVersion, typedPayload));
+            lock (_gate)
+                _posted.Add(new PostedSignal(kind, occurredAtUtc, sourceOrigin, evidence, payload, kindSchemaVersion, typedPayload));
        }

        internal sealed class PostedSignal
@@ -0,0 +1,72 @@
+#nullable enable
+using System;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
+{
+    /// <summary>
+    /// Codex review P2 (2026-08-19) — <see cref="ImeLogHost"/> starts AFTER <c>EspAndHelloHost</c>,
+    /// and <c>ImeLogTracker.Start()</c> restores the persisted package states silently (LoadState
+    /// raises no <c>OnAppStateChanged</c>). On an agent restart the Shell-Core ESP-exit replay
+    /// therefore runs against an empty app list. Without the post-restore nudge the exact reboot
+    /// case the completion recovery exists for — apps already terminal BEFORE the reboot, only the
+    /// final exit lost to the downtime — would still never complete.
+    /// </summary>
+    public sealed class ImeLogHostStateRestoredCallbackTests : IDisposable
+    {
+        private readonly TempDirectory _tmp = new TempDirectory();
+
+        public void Dispose() => _tmp.Dispose();
+
+        private ImeLogHost CreateHost(Action? onStateRestored)
+            => new ImeLogHost(
+                sessionId: "s",
+                tenantId: "t",
+                logger: new AgentLogger(_tmp.Path, AgentLogLevel.Info),
+                ingress: new FakeSignalIngressSink(),
+                clock: new VirtualClock(new DateTime(2026, 8, 19, 8, 43, 16, DateTimeKind.Utc)),
+                imeLogPathOverride: _tmp.Path,
+                imeMatchLogPath: null,
+                imePatterns: null,
+                stateDirectory: _tmp.Path,
+                whiteGloveSealingPatternIds: null,
+                onStateRestored: onStateRestored);
+
+        [Fact]
+        public void Start_invokes_the_state_restored_callback_exactly_once()
+        {
+            var calls = 0;
+            using var host = CreateHost(() => calls++);
+
+            host.Start();
+            try { Assert.Equal(1, calls); }
+            finally { host.Stop(); }
+        }
+
+        [Fact]
+        public void A_throwing_callback_does_not_break_host_start()
+        {
+            // Fail-soft like every other co-wired callback in the orchestration layer: a broken
+            // re-check must never take the IME log host — the session's primary signal source —
+            // down with it.
+            using var host = CreateHost(() => throw new InvalidOperationException("recheck boom"));
+
+            var ex = Record.Exception(() => host.Start());
+            try { Assert.Null(ex); }
+            finally { host.Stop(); }
+        }
+
+        [Fact]
+        public void No_callback_is_a_valid_configuration()
+        {
+            using var host = CreateHost(null);
+
+            var ex = Record.Exception(() => host.Start());
+            try { Assert.Null(ex); }
+            finally { host.Stop(); }
+        }
+    }
+}
@@ -0,0 +1,162 @@
+#nullable enable
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Runtime;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using AutopilotMonitor.Shared;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
+{
+    /// <summary>
+    /// PowerStateWatcherHost — no-battery/probe-error devices never arm, a low-battery baseline
+    /// emits its threshold event onto the single rail, and debounced ticks translate tracker
+    /// emissions into <c>power_state_change</c> events. WMI arming itself stays untested
+    /// (ConsoleBypassWatcher precedent); <c>StartCore(armWmi: false)</c> exercises everything else.
+    /// </summary>
+    public sealed class PowerStateWatcherHostTests : IDisposable
+    {
+        private static readonly DateTime At = new DateTime(2026, 8, 21, 9, 0, 0, DateTimeKind.Utc);
+
+        private readonly TempDirectory _tmp = new TempDirectory();
+        private readonly FakeSignalIngressSink _sink = new FakeSignalIngressSink();
+        private readonly AgentLogger _logger;
+        private PowerStateResult _probeResult = new PowerStateResult { OnAcPower = true, HasBattery = true, BatteryPercent = 80 };
+
+        public PowerStateWatcherHostTests()
+        {
+            _logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
+        }
+
+        public void Dispose() => _tmp.Dispose();
+
+        private PowerStateWatcherHost Build() => new PowerStateWatcherHost(
+            sessionId: "sess-power",
+            tenantId: "tenant-power",
+            ingress: _sink,
+            clock: new VirtualClock(At),
+            logger: _logger,
+            probe: () => _probeResult);
+
+        private IReadOnlyList<FakeSignalIngressSink.PostedSignal> PowerEvents() =>
+            _sink.Posted.Where(p =>
+                p.Kind == DecisionSignalKind.InformationalEvent
+                && p.Payload != null
+                && p.Payload.TryGetValue(SignalPayloadKeys.EventType, out var et)
+                && et == Constants.EventTypes.PowerStateChange).ToList();
+
+        [Fact]
+        public void No_battery_emits_nothing()
+        {
+            _probeResult = new PowerStateResult { OnAcPower = true, HasBattery = false };
+
+            Build().StartCore(armWmi: false);
+
+            Assert.Empty(_sink.Posted);
+        }
+
+        [Fact]
+        public void Probe_error_emits_nothing()
+        {
+            _probeResult = new PowerStateResult { ProbeError = "GetSystemPowerStatus returned false" };
+
+            Build().StartCore(armWmi: false);
+
+            Assert.Empty(_sink.Posted);
+        }
+
+        [Fact]
+        public void Baseline_below_threshold_emits_threshold_event_with_immediate_upload()
+        {
+            _probeResult = new PowerStateResult { OnAcPower = false, HasBattery = true, BatteryPercent = 12, BatteryLifeMinutes = 34 };
+
+            Build().StartCore(armWmi: false);
+
+            var s = Assert.Single(PowerEvents());
+            Assert.Equal("Error", s.Payload![SignalPayloadKeys.Severity]);
+            Assert.Equal("true", s.Payload![SignalPayloadKeys.ImmediateUpload]);
+            Assert.Contains("15%", s.Payload![SignalPayloadKeys.Message]);
+
+            var data = (IReadOnlyDictionary<string, object>)s.TypedPayload!;
+            Assert.Equal("threshold_crossed", data["transition"]);
+            Assert.Equal(15, data["thresholdPercent"]);
+            Assert.Equal(12, data["batteryPercent"]);
+            Assert.Equal(false, data["onAcPower"]);
+            Assert.Equal(34, data["batteryLifeMinutes"]);
+        }
+
+        [Fact]
+        public void Tick_after_unplug_emits_ac_to_battery_warning()
+        {
+            var host = Build();
+            host.StartCore(armWmi: false);
+            Assert.Empty(PowerEvents());
+
+            _probeResult = new PowerStateResult { OnAcPower = false, HasBattery = true, BatteryPercent = 79 };
+            host.TickForTest();
+
+            var s = Assert.Single(PowerEvents());
+            Assert.Equal("Warning", s.Payload![SignalPayloadKeys.Severity]);
+            Assert.Equal("true", s.Payload![SignalPayloadKeys.ImmediateUpload]);
+
+            var data = (IReadOnlyDictionary<string, object>)s.TypedPayload!;
+            Assert.Equal("ac_to_battery", data["transition"]);
+            Assert.Equal(79, data["batteryPercent"]);
+            Assert.False(data.ContainsKey("thresholdPercent"));
+
+            // Replug: Info recovery event without immediate upload.
+            _probeResult = new PowerStateResult { OnAcPower = true, HasBattery = true, BatteryPercent = 79, IsCharging = true };
+            host.TickForTest();
+
+            Assert.Equal(2, PowerEvents().Count);
+            var back = PowerEvents()[1];
+            Assert.Equal("Info", back.Payload![SignalPayloadKeys.Severity]);
+            Assert.Equal("false", back.Payload![SignalPayloadKeys.ImmediateUpload]);
+            Assert.Equal("battery_to_ac", ((IReadOnlyDictionary<string, object>)back.TypedPayload!)["transition"]);
+        }
+
+        [Fact]
+        public void Tick_with_unchanged_state_emits_nothing()
+        {
+            var host = Build();
+            host.StartCore(armWmi: false);
+
+            host.TickForTest();
+            host.TickForTest();
+
+            Assert.Empty(PowerEvents());
+        }
+
+        [Fact]
+        public void Stopped_host_ignores_ticks()
+        {
+            var host = Build();
+            host.StartCore(armWmi: false);
+            host.Stop();
+
+            _probeResult = new PowerStateResult { OnAcPower = false, HasBattery = true, BatteryPercent = 50 };
+            host.TickForTest();
+
+            Assert.Empty(PowerEvents());
+        }
+
+        [Fact]
+        public void Unknown_battery_percent_serializes_as_unknown()
+        {
+            var host = Build();
+            host.StartCore(armWmi: false);
+
+            _probeResult = new PowerStateResult { OnAcPower = false, HasBattery = true, BatteryPercent = null, BatteryLifeMinutes = null };
+            host.TickForTest();
+
+            var data = (IReadOnlyDictionary<string, object>)Assert.Single(PowerEvents()).TypedPayload!;
+            Assert.Equal("unknown", data["batteryPercent"]);
+            Assert.Equal("unknown", data["batteryLifeMinutes"]);
+        }
+    }
+}
@@ -35,6 +35,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
        // OS-eventlog forwarding — observability, not enrollment progress (session 8bc1180f:
        // an EventID-100 burst must not keep the periodic collectors alive).
        [InlineData("modern_deployment_log")]
+        // Environment observation — battery drain on an idle device must not reset idle clocks.
+        [InlineData("power_state_change")]
        // Agent health / control / transport — not device/enrollment progress (P2).
        [InlineData("collector_degraded")]
        [InlineData("telemetry_upload_poisoned")]
@@ -0,0 +1,57 @@
+#nullable enable
+using System;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.DecisionCore.Engine;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
+{
+    /// <summary>
+    /// SystemTimelineWatcherHost — thin ICollectorHost wrapper over SystemTimelineTracker.
+    /// Real event-log arming stays untested by convention (ConsoleBypassWatcher precedent);
+    /// these tests pin the lifecycle contract only.
+    /// </summary>
+    public sealed class SystemTimelineWatcherHostTests : IDisposable
+    {
+        private readonly TempDirectory _tmp = new TempDirectory();
+
+        public void Dispose() => _tmp.Dispose();
+
+        private SystemTimelineWatcherHost CreateHost() => new SystemTimelineWatcherHost(
+            sessionId: "sess-stl",
+            tenantId: "tenant-stl",
+            logger: new AgentLogger(_tmp.Path, AgentLogLevel.Info),
+            ingress: new FakeSignalIngressSink(),
+            clock: new VirtualClock(new DateTime(2026, 8, 21, 10, 0, 0, DateTimeKind.Utc)),
+            backfillLookbackMinutes: 0,
+            stateDirectory: _tmp.Path);
+
+        [Fact]
+        public void Stop_BeforeStart_DoesNotThrow()
+        {
+            using (var host = CreateHost())
+            {
+                host.Stop();
+            }
+        }
+
+        [Fact]
+        public void Dispose_Twice_DoesNotThrow()
+        {
+            var host = CreateHost();
+            host.Dispose();
+            host.Dispose();
+        }
+
+        [Fact]
+        public void Name_IsStable()
+        {
+            using (var host = CreateHost())
+            {
+                Assert.Equal("SystemTimelineTracker", host.Name);
+            }
+        }
+    }
+}
@@ -182,6 +182,73 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
            Assert.Equal("FromCache", data["outcome"]);
        }

+        // ── Post-registration recovery (Phase 6.5, tenant aebdce78 audit 2026-08-24) ─
+
+        [Fact]
+        public void EmitFetchFailedIfAny_AfterRecovery_MarksRecoveredAndDemotesToInfo()
+        {
+            using var rig = new EmitterRig();
+            // Startup fetch failed (network link not up yet), then the post-registration
+            // recovery fetched ConfigVersion 39. The event must keep the original failure
+            // details AND mark the heal.
+            rig.RemoteConfig.SetFakeOutcome(
+                RemoteConfigFetchOutcome.UsedDefaults,
+                configVersion: 39, // CurrentConfig now holds the recovered config
+                attempts: 4,
+                failureType: "HttpRequestException",
+                failureMessage: "simulated dead network link",
+                recovered: true);
+
+            LifecycleEmitters.EmitRemoteConfigFetchFailedIfAny(
+                rig.Post, rig.AgentConfig, rig.RemoteConfig, rig.Logger);
+
+            var data = AssertSingleEmit(rig.Sink, expectedEventType: "remote_config_fetch_failed");
+            Assert.Equal("UsedDefaults", data["outcome"]); // startup failure record intact
+            Assert.Equal(4, data["attempts"]);
+            Assert.Equal(true, data["recovered"]);
+            Assert.Equal(39, data["recoveredConfigVersion"]);
+            Assert.Equal(nameof(EventSeverity.Info), rig.Sink.Posted[0].Payload!["severity"]);
+        }
+
+        [Fact]
+        public void EmitFetchFailedIfAny_WithoutRecovery_StaysWarning()
+        {
+            using var rig = new EmitterRig();
+            rig.RemoteConfig.SetFakeOutcome(
+                RemoteConfigFetchOutcome.UsedDefaults,
+                configVersion: 0,
+                attempts: 4,
+                failureType: "HttpRequestException",
+                failureMessage: "still down");
+
+            LifecycleEmitters.EmitRemoteConfigFetchFailedIfAny(
+                rig.Post, rig.AgentConfig, rig.RemoteConfig, rig.Logger);
+
+            var data = AssertSingleEmit(rig.Sink, expectedEventType: "remote_config_fetch_failed");
+            Assert.False(data.ContainsKey("recovered"));
+            Assert.False(data.ContainsKey("recoveredConfigVersion"));
+            Assert.Equal(nameof(EventSeverity.Warning), rig.Sink.Posted[0].Payload!["severity"]);
+        }
+
+        [Fact]
+        public void EmitAgentStarted_AfterRecovery_FlagsLiveConfig()
+        {
+            using var rig = new EmitterRig();
+            rig.RemoteConfig.SetFakeOutcome(
+                RemoteConfigFetchOutcome.UsedDefaults,
+                configVersion: 39,
+                recovered: true);
+
+            LifecycleEmitters.EmitAgentStarted(
+                rig.Post, rig.AgentConfig, rig.PreviousExit, "2.0.806", rig.RemoteConfig, rig.Logger);
+
+            var data = AssertSingleEmit(rig.Sink, expectedEventType: "agent_started");
+            Assert.Equal(39, data["configVersion"]);
+            Assert.Equal(true, data["remoteConfigFetched"]); // running on a live-fetched config
+            Assert.Equal("UsedDefaults", data["remoteConfigOutcome"]); // startup outcome stays honest
+            Assert.Equal(true, data["remoteConfigRecovered"]);
+        }
+
        // ── Helpers ─────────────────────────────────────────────────────────

        private static Dictionary<string, object> AssertSingleEmit(
@@ -258,8 +325,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
                int attempts = 1,
                string? failureType = null,
                string? failureMessage = null,
-                int? authStatusCode = null)
+                int? authStatusCode = null,
+                bool recovered = false)
            {
+                typeof(RemoteConfigService).GetProperty(nameof(RecoveredAfterFetchFailure))?.SetValue(this, recovered);
                // CurrentConfig is set via the protected SetConfig path — easiest:
                // a real FetchConfigAsync replacement that just stashes a canned config.
                typeof(RemoteConfigService).GetMethod("SetConfig",
--- a/Show More
+++ b/Show More