command update

Audit vs decompiled IME 1.97.107: ~55/79 patterns verified verbatim, but
several were broken or dead against the current V3 pipeline.

Fixes:
- IME-ESP-TRACK-STATUS: drop trailing anchor (line grew ' with name: <n>.')
- HS-COMPLIANCE: tolerate both 'remdiation' typo and corrected wording;
  new HS-COMPLIANCE-POST for the reworded post-detection line
- IME-DETECTION-RESULT: capture DetectedDifferentVersion (ordered first)
- IME-ENFORCEMENT-SUCCESS: unpin OldValue (Error/PendingReboot/null paths)
- IME-ERROR-REPORT: allow unquoted null OldValue on first write
- Disable 11 dead patterns (emitters removed with IME's old V1/V2 pipeline;
  IME-DETECTED-OLD additionally collided with IME-SKIP-INSTALL-DETECTED)

New signals (existing actions, tailed files only):
- IME-ESP-APP-REGISTERED + IME-CACHE-MISS as app-name sources (replacing
  dead IME-UPDATE-NAME-1/2/3)
- IME-WINGET-ERROR (WinGet failures were invisible)
- IME-EXITCODE-MAPPED-FAILED (normal mapped-exit-code failure path)
- IME-STOP-SIGNAL (service stop != OS shutdown)
- IME-RESTART-STOP-PROCESSING (reboot-gated processing abort)

Backend seed diff now also compares Enabled + Parameters - enable/disable
flips and parameter changes previously never propagated to the table.

All exact wordings verified against decompiled source; regex smoke-tested
via validate-ime-patterns.py (engine=regex, 75/75 compiled, all new
patterns fire on synthetic lines with the exact IME format strings).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.github/workflows/build-agent.yml

@@ -270,6 +270,12 @@ jobs:
             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"
+            }
           }
 
           # Update AdminConfiguration LatestAgentV2* -- ONLY on stable cutover. The hash-oracle

.github/workflows/ci.yml

@@ -77,12 +77,11 @@ jobs:
       - name: Typecheck
         run: npx tsc --noEmit
 
-      # Errors fail outright. Warnings are ratcheted: the cap is the current
-      # count of accepted warnings (React-Compiler hooks-rule findings demoted
-      # in eslint.config.mjs + exhaustive-deps) — when you fix warnings, lower
-      # the cap to match; never raise it.
+      # Errors fail outright, and so does ANY warning: the codebase is
+      # warning-clean and must stay that way — fix new findings, never
+      # raise the cap.
       - name: Lint
-        run: npm run lint -- --max-warnings 99
+        run: npm run lint -- --max-warnings 0
 
       - name: Tests
         run: npm test
@@ -107,8 +106,22 @@ jobs:
       - name: Typecheck
         run: npx tsc --noEmit
 
+      # The vector-search tests tokenize with the real all-MiniLM-L6-v2 model
+      # (~23 MB tokenizer + ONNX weights). transformers.js caches under
+      # node_modules by default, which npm ci recreates — so every CI run
+      # re-downloaded from huggingface.co and rate-limits (429) failed the job
+      # (run 31252869254). Persist the model across runs instead; HF_CACHE_DIR
+      # is honored by vector-search-provider.ts.
+      - name: Cache embedding model
+        uses: actions/cache@v6
+        with:
+          path: ${{ github.workspace }}/.hf-cache
+          key: hf-model-Xenova-all-MiniLM-L6-v2
+
       - name: Tests
         run: npm test
+        env:
+          HF_CACHE_DIR: ${{ github.workspace }}/.hf-cache
 
   guardrails-in-sync:
     name: Generated guardrails match rules/guardrails.json

.github/workflows/combine-rules.yml

@@ -8,6 +8,7 @@ on:
       - 'rules/ime-log-patterns/**'
       - 'rules/schema/**'
       - 'rules/scripts/**'
+      - 'rules/guardrails.json'
   pull_request:
     paths:
       - 'rules/gather/**'
@@ -15,6 +16,7 @@ on:
       - 'rules/ime-log-patterns/**'
       - 'rules/schema/**'
       - 'rules/scripts/**'
+      - 'rules/guardrails.json'
 
 jobs:
   validate-and-combine:
@@ -55,9 +57,11 @@ jobs:
       - name: Combine rules into dist/
         run: node rules/scripts/combine.js
 
-      - name: Commit dist/ changes
+      - name: Commit generated outputs
         if: github.ref == 'refs/heads/main' && github.event_name == 'push'
         uses: stefanzweifel/git-auto-commit-action@v7
         with:
-          commit_message: "chore: regenerate rules/dist from individual files"
-          file_pattern: "rules/dist/*"
+          commit_message: "chore: regenerate rules/dist + generated TS from individual files"
+          # combine.js writes THREE outputs; committing only dist/ would silently discard
+          # the two generated TS modules and leave the guardrails-in-sync CI check red.
+          file_pattern: "rules/dist/* src/Web/autopilot-monitor-web/utils/guardrails.generated.ts src/McpServer/autopilot-monitor-mcp/src/rule-authoring.generated.ts"

.github/workflows/deploy-web.yml

@@ -16,6 +16,10 @@ on:
       - 'src/Web/autopilot-monitor-web/**'
       - '.github/workflows/deploy-web.yml'
 
+env:
+  PORTAL_VERSION_URL: https://portal.autopilotmonitor.com/version.json
+  VERSIONS_CONTAINER: https://autopilotmonitoreu.blob.core.windows.net/versions
+
 jobs:
   build_and_deploy_job:
     if: github.event_name == 'push' || github.event_name == 'workflow_dispatch' || (github.event_name == 'pull_request' && github.event.action != 'closed')
@@ -48,6 +52,9 @@ jobs:
           NEXT_PUBLIC_API_BASE_URL: ${{ vars.NEXT_PUBLIC_API_BASE_URL }}
           NEXT_PUBLIC_PLATFORM_STATS_MANIFEST_URL: ${{ vars.NEXT_PUBLIC_PLATFORM_STATS_MANIFEST_URL }}
           NEXT_PUBLIC_APPINSIGHTS_CONNECTION_STRING: ${{ secrets.NEXT_PUBLIC_APPINSIGHTS_CONNECTION_STRING }}
+          # Build stamp for public/version.json (scripts/generate-version.js in prebuild);
+          # the verify step below polls the deployed file for exactly this commit.
+          GITHUB_SHA: ${{ github.sha }}
         with:
           azure_static_web_apps_api_token: ${{ secrets.AZURE_SWA_DEPLOY_TOKEN }}
           repo_token: ${{ secrets.GITHUB_TOKEN }} # Used for Github integrations (i.e. PR comments)
@@ -64,6 +71,55 @@ jobs:
           output_location: "out" # Built app content directory - optional
           ###### End of Repository/Build Configurations ######
 
+      # The SWA action reporting success proves the upload, not that the production host
+      # serves the new build — verify against the live /version.json (Cache-Control:
+      # no-store via staticwebapp.config.json) before publishing the version manifest.
+      # PR builds deploy to per-PR preview environments, so only main deploys are verified.
+      - name: Verify deployed portal build is live
+        if: env.DEPLOY_TOKEN != '' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
+        shell: pwsh
+        run: |
+          $expectedCommit = '${{ github.sha }}'.Substring(0, 7)
+          $deadline = [DateTime]::UtcNow.AddMinutes(5)
+          $attempt = 0
+
+          while ([DateTime]::UtcNow -lt $deadline) {
+            $attempt++
+            try {
+              $v = Invoke-RestMethod -Uri '${{ env.PORTAL_VERSION_URL }}' -Method Get -TimeoutSec 30 -Headers @{ 'Cache-Control' = 'no-cache' }
+              if ($v.commit -eq $expectedCommit) {
+                Write-Host "Live after $attempt attempt(s): web @ $($v.commit), built $($v.buildUtc)"
+                exit 0
+              }
+              Write-Host "Attempt ${attempt}: serving $($v.commit) -- waiting for $expectedCommit"
+            } catch {
+              Write-Host "Attempt ${attempt}: /version.json not answering yet -- $($_.Exception.Message)"
+            }
+            Start-Sleep -Seconds 15
+          }
+
+          throw "Portal did not serve commit $expectedCommit within 5 minutes -- deployment not verified, version manifest NOT published"
+
+      # Cross-component deploy record, written last and only on a verified deploy —
+      # same contract as versions/backend.json and versions/mcp.json.
+      - name: Publish version manifest
+        if: env.DEPLOY_TOKEN != '' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
+        shell: pwsh
+        run: |
+          $manifest = [ordered]@{
+            component   = 'web'
+            commit      = '${{ github.sha }}'.Substring(0, 7)
+            deployedUtc = [DateTime]::UtcNow.ToString('o')
+            runId       = '${{ github.run_id }}'
+          } | ConvertTo-Json
+
+          $sas = '${{ secrets.AZURE_BLOB_VERSIONS_SAS_TOKEN }}'.TrimStart('?')
+          $url = "${{ env.VERSIONS_CONTAINER }}/web.json?$sas"
+          # no-cache: rotating pointer, must never be served stale by any fronting cache.
+          Invoke-RestMethod -Uri $url -Method Put -Headers @{ 'x-ms-blob-type' = 'BlockBlob'; 'x-ms-blob-cache-control' = 'no-cache' } -Body $manifest -ContentType 'application/json' | Out-Null
+          Write-Host "Published versions/web.json"
+          Write-Host $manifest
+
   close_pull_request_job:
     if: github.event_name == 'pull_request' && github.event.action == 'closed'
     runs-on: ubuntu-latest

.gitignore

@@ -154,3 +154,7 @@ docs/~$Introduction-AutopilotMonitor.pptx
 
 # Playwright MCP browser artifacts (snapshots, screenshots, console logs)
 .playwright-mcp/
+
+# Web build stamp: generated by scripts/generate-version.js on every build (buildUtc
+# changes each run) and served at /version.json from the static export.
+src/Web/autopilot-monitor-web/public/version.json

Directory.Build.props

@@ -0,0 +1,12 @@
+<Project>
+  <!-- Warning freeze (2026-08-13, backlog cleared to zero): every .NET build in this repo
+       must stay warning-free. Compiler, MSBuild and NuGet restore warnings are all fatal.
+       Exception: NuGet audit advisories (NU1901-NU1904) stay warnings — a CVE published
+       against an already-referenced package must not block an unrelated hotfix deploy;
+       advisories are handled by bumping the package, not by failing the build. -->
+  <PropertyGroup>
+    <TreatWarningsAsErrors>true</TreatWarningsAsErrors>
+    <MSBuildTreatWarningsAsErrors>true</MSBuildTreatWarningsAsErrors>
+    <WarningsNotAsErrors>NU1901;NU1902;NU1903;NU1904</WarningsNotAsErrors>
+  </PropertyGroup>
+</Project>

docs/agent/autopilot-ztd-diagnostics.md

@@ -21,6 +21,14 @@ three of them to turn the `autopilot_profile_missing` warning from a guess into
 evidence-backed verdict, and the backend rule engine uses the error-code map for
 known-issue enrichment.
 
+Windows 365 Cloud PC exception: on Cloud PCs (`CloudPcDetector.DetectIsCloudPc()`)
+`ProfileAvailable=0` is the expected state — Cloud PCs are provisioned by the Windows 365
+service, not by Autopilot. The event is still emitted with the full evidence payload plus
+an `isCloudPc` marker, but as severity Info with a "this is expected" message instead of
+a Warning (`DeviceInfoCollector.ResolveAutopilotProfileMissingPresentation`). The portal's
+Autopilot Profile card mirrors this: a neutral note for Cloud PC sessions
+(`session.isCloudPc` or the event marker), the amber warning otherwise.
+
 Consumers in this repo:
 
 * `ZtdEvidence.cs` (agent) — one-shot event-log query + `Diagnostics\Autopilot` registry

docs/agent/continue-anyway-observation.md

@@ -0,0 +1,114 @@
+---
+type: Concept
+title: Continue-Anyway Observation Mode — Device-Phase ESP Failure Defang
+description: Operator-set tenant opt-in that turns an immediate Device-phase ESP terminal failure on a Continue-Anyway-enabled profile into a bounded 60-minute observation; the DAD-validated real-user desktop plus the Hello gate detect the true end, and the session completes as Succeeded with an esp-soft-failure marker.
+resource: /src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.Edge.cs
+tags:
+  - agent
+  - decision-engine
+  - esp
+  - continue-anyway
+  - soft-failure
+  - tenant-config
+timestamp: 2026-08-08T00:00:00+02:00
+---
+
+# Continue-Anyway Observation Mode
+
+## Problem
+
+A Classic user-driven enrollment whose Device ESP hits the configured terminal timeout
+(`syncFailureTimeoutMinutes`, typically 30) fails **before AccountSetup is ever entered**.
+The classic advisory defang (`HandleEspTerminalFailureV1`) requires
+`AccountSetupEnteredUtc != null`, so these sessions hard-fail immediately — even when the
+ESP profile allows "Continue anyway" and users demonstrably dismiss the failure screen and
+reach a working desktop. A fleet held at the timeout wall by one slow blocking app then
+shows ~100% Failed (tenant c9787ba2: 948/1000 `esp_terminal_failure`, culprit "Encompass
+Hybrid Installer"), which tells the tenant nothing.
+
+## Mechanism
+
+Opt-in flow (default off — absence keeps the immediate hard fail):
+
+1. **Tenant setting** `EnableEspContinueAnywayObservation` (`TenantConfiguration`,
+   operator-set only, NOT exposed in the tenant admin settings UI; the toggle lives in
+   the Global-Admin tenant management modal next to Bootstrap Token / Unrestricted Mode,
+   and the field is GA-gated on both write paths — the generic PUT silently reverts it
+   for tenant admins, the field patch rejects it with 400) → served via `agent/config`
+   (`AgentConfigResponse`, ConfigVersion 37).
+2. **Agent** stamps `espContinueAnywayObservationEnabled=true` into the
+   `EspConfigDetected` signal payload (both emitters: the orchestrator FirstSync
+   bootstrap and `DeviceInfoCollector.PostEspConfigDetectedSignal`) — only when enabled,
+   so the kernel stays config-free and replay/recovery reconstruct the fact from the
+   signal log.
+3. **Engine** (`HandleEspTerminalFailureV1`): a terminal ESP failure is defanged into an
+   `esp_failure_advisory` (`advisoryReason=esp_failure_defanged_continueanyway_observation`)
+   when ALL hold: profile allows Continue-Anyway, observation opt-in observed,
+   `AccountSetupEnteredUtc == null`, and the scenario is Classic/Unknown with
+   `PreProvisioningSide=None` and no registry self-deploying marker (WhiteGlove /
+   SelfDeploying / DevicePreparation have no interactive user to press the button).
+4. **Observation window**: the shared `AdvisoryCompletion` deadline is armed with a
+   **60-minute** window (classic advisory: 30) — long enough for failure screen →
+   Continue anyway → sign-in → desktop, or a full device-phase re-run via "Try again".
+
+## Detecting the real end
+
+The active-advisory-without-AccountSetup shape is unique to this arming site, so
+`IsContinueAnywayObservationActive(state)` (advisory recorded ∧ not resolved ∧
+AccountSetup never entered) needs no separate opt-in re-check. Three outcomes:
+
+* **Continue anyway** — the DAD-validated real-user desktop arrives (defaultuser0/SYSTEM
+  excluded at the detector) and the Hello gate is satisfied (resolved, or policy
+  explicitly disabled without an observed wizard): `HandleDesktopArrivedV1` completes
+  eagerly through Finalizing (trigger `DesktopArrived:ContinueAnywayObservation`) — the
+  session end reflects the real end, not the window edge. The IME user-session gate is
+  deliberately waived: it anchors on `AccountSetupEnteredUtc`, which is structurally
+  absent here. The terminal `enrollment_complete` carries `espSoftFailure=true`,
+  `completionSource=continue_anyway_observation` and the failed category; the backend
+  stamps `EspSoftFailure`/`CompletionSource` on the Sessions row (+ SessionsIndex
+  mirror) and the web renders the amber "with issues" badge plus a detail banner.
+  Sessions completing under the CLASSIC advisory (AccountSetup entered) carry the same
+  marker with `completionSource=continue_anyway_post_accountsetup`.
+* **Try again** — the ESP re-runs the failed category; `DeviceSetupProvisioningComplete`
+  resolves the advisory via the 4910a5a5 recovery hook (`esp_failure_advisory_resolved`)
+  and the session continues on the normal rails, completing clean (no marker).
+* **Nothing** — the window expires: un-defang to `enrollment_failed` with the original
+  `esp_terminal_failure` reason and
+  `advisoryReason=continue_anyway_observation_window_expired_without_completion_evidence`;
+  `LastFailureTrigger=EspTerminalFailure` keeps the likely-stuck app promotion on. Every
+  observed session therefore still gets a terminal verdict ≤ ~60 min after the failure.
+
+Deadline-fire edge cases mirror the classic paths: desktop + unknown Hello promotes to
+`AwaitingHello` with the HelloSafety window (never-observed promote), and enforcement
+progress since arming re-arms the window (30-min re-arm, convergent) instead of failing a
+device mid-"Try again".
+
+## Status semantics
+
+No new terminal status: the session is `Succeeded` + `EspSoftFailure=true` (user
+decision 2026-08-08). Success-rate conventions stay untouched; honesty lives in the
+badge, the detail banner, and ANALYZE-ESP-004 (which continues to fire on the un-defang
+expiry path via `mayHaveContinuedAnyway`).
+
+# Examples
+
+Session `53d1e9f6-4eef-4f3b-a999-c63e96c5148d` (tenant c9787ba2, 2026-08-07) is the
+motivating shape: DeviceSetup/Certificates failed at the 30-min wall while "Encompass
+Hybrid Installer" was still installing, AccountSetup 0/5, Continue-Anyway allowed —
+hard-failed under the default semantics.
+
+Tests: `ContinueAnywayObservationTests` (DecisionCore.Tests) — defang, 60-min arming,
+opt-out/scenario regressions, eager desktop completion with marker, clean-completion
+marker absence, expiry un-defang, hello promotes, category recovery.
+
+# Citations
+
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.Edge.cs` — arming site,
+  observation branches in `HandleAdvisoryCompletionDeadlineFired`,
+  `IsContinueAnywayObservationActive`.
+* `src/Shared/AutopilotMonitor.DecisionCore/Engine/DecisionEngine.Classic.cs` —
+  `HandleDesktopArrivedV1` observation completion, `BuildEnrollmentCompleteEffect`
+  soft-failure marker.
+* `src/Backend/AutopilotMonitor.Functions/Services/EventIngestProcessor.Classification.cs`
+  / `TableStorageService.Sessions.cs` — session stamping + index mirror.
+* `src/Web/autopilot-monitor-web/components/SessionStatusBadge.tsx` — amber badge.

docs/backend/app-version-regression-radar.md

@@ -0,0 +1,98 @@
+---
+type: Concept
+title: App Version Duration Regression Radar
+description: How the radar detects app versions whose median install duration regressed vs. the previous version (median lift ≥2x plus an absolute floor over first-seen-ordered versions), how alert episodes live in the appversionregression tracker keyspace, and which surfaces show them.
+resource: src/Backend/AutopilotMonitor.Functions/Helpers/AppVersionRegressionRadar.cs
+tags:
+  - backend
+  - apps
+  - regression-radar
+  - insights
+timestamp: 2026-08-13T12:00:00+02:00
+---
+
+# App Version Duration Regression Radar
+
+Detects "version X made this app's installs much slower" — the concrete, quotable insight
+("median install duration rose from 11 to 29 min after version X") — from the per-(session,
+app) `AppInstallSummaries` rows. Duration only: failure-rate per version is already visible
+in the apps dashboard's `versionBreakdown`, and rate regressions belong to Wilson-interval
+statistics, not medians.
+
+# Schema
+
+## Signal & detection
+
+Per (tenant, app), the MEASURED install population is: `Status == "Succeeded"`, terminal
+state not Skipped/Postponed, `MetricsMath.HasMeasuredDuration` (1s..6h — 0s means the start
+was unobserved, above 6h means back-stamped batches), no `AppIdCollision`, non-empty
+`AppVersion`. Versions are ordered by FIRST-SEEN install time (min `StartedAt`), never by
+string comparison ("9.1" vs "2024.10" would lie). The comparison pair is always the newest
+version (the one with the most recent measured install) vs. the version with the latest
+first-seen strictly before it.
+
+MEDIANS, not means (nearest-rank, shared with the apps dashboard via
+`AppsAnalyticsHelper.Percentile`) — one back-stamped straggler must not fire a fleet alert.
+A regression fires only when ALL hold over the trailing 35-day horizon:
+
+1. both versions have ≥ 10 measured installs;
+2. current median ≥ 2× the previous version's median;
+3. absolute increase ≥ 300 s (a 20s→45s app is noise, not an incident).
+
+## Suppression & limits
+
+* Parallel ring rollouts can make "previous" a concurrently-deployed version — accepted in
+  v1; the episode key (app, current version) still caps it at one bell per version.
+* Platform kill switch: app setting `AppVersionRegressionRadarDisabled=true` skips the
+  radar (fail-open — it only notifies, never mutates data).
+* One cross-tenant install-summary read per pass (the same query the global apps dashboard
+  runs), grouped by tenant; per-tenant failures are non-fatal.
+
+## Alert episodes (tracker keyspace)
+
+An episode lives as `appversionregression|{app-lower}|{version-lower}` (table-key-sanitized;
+raw AppName/CurrentVersion live in columns, the mapper never parses the RowKey) in the
+notification-tracker table, next to the `ruleregression|` keyspace: the row IS the dedup
+(bell + ops event fire exactly once per episode) and the `versionRegressions[]` payload —
+both medians, both sample counts, lift. Numbers refresh on every radar pass while the
+episode stays active; `FirstNotifiedAt` never moves. The episode closes (dedup re-arms) when
+the alerted version drains under 10 measured installs in the horizon or its recomputed
+median falls back under 1.5× the previous version's median; the tracker's 30-day retention
+sweep also re-arms, so a month-old still-burning regression rings once more by design.
+
+## Notification chain (v1: bell + ops event)
+
+* Tenant bell `app_version_duration_regression` (audience: Admin), href
+  `/apps/detail?name={app}&days=35` (canonical `appDetailUrl` shape). Message carries the
+  full numbers so the admin can verify without a portal round-trip.
+* Ops event `AppVersionDurationRegression` (Tenant category, Warning) — dual-registered in
+  the web `OPS_EVENT_TYPES` catalog so operators can wire Telegram/Teams/Slack alert rules.
+
+## Surfaces
+
+* `apps/{appName}/analytics` (+ global twin with `?tenantId=`) responds with
+  `versionRegressions[]` (empty for the cross-tenant aggregate — episodes are per-tenant
+  rows), and `versionBreakdown[]` rows now carry `measuredInstalls` /
+  `medianDurationSeconds` / `p95DurationSeconds`.
+* Apps detail page: amber "↑ Duration regression" banner above the version cards and a
+  "Median Install Duration by Version" bar chart.
+
+# Examples
+
+A tenant ships Contoso VPN 2.4.0 after 2.3.9. 2.3.9 has 40 measured installs, median 660s;
+2.4.0 accumulates 12 measured installs with median 1740s. Lift 2.6×, absolute +1080s →
+episode `appversionregression|contoso vpn|2.4.0` opens, one bell + one ops event fire.
+Subsequent passes refresh the numbers only. When 2.4.1 replaces 2.4.0 and 2.4.0 drains
+below 10 measured installs in the horizon, the episode deletes and the dedup re-arms.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Helpers/AppVersionRegressionRadar.cs` — pure core
+  (gates, first-seen ordering, re-arm).
+* `src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.AppVersionRegression.cs`
+  — orchestration, kill switch, bell/ops-event emission, wording contract.
+* `src/Backend/AutopilotMonitor.Functions/DataAccess/TableStorage/TableHardwareRejectionNotificationTracker.cs`
+  — episode keyspace, entity round-trip.
+* `src/Shared/AutopilotMonitor.Shared/Models/Metrics/AppVersionRegressionAlert.cs` — persisted
+  alert payload.
+* [Rule Regression Radar](rule-regression-radar.md) — the sibling pattern this radar mirrors.

docs/backend/cloudpc-device-validation.md

@@ -101,7 +101,7 @@ installed `CloudManagedDesktopExtension` service (probed via its
 `HKLM\SYSTEM\CurrentControlSet\Services` key; the agent deliberately has no
 `System.ServiceProcess` dependency). SKIP-safe: any error resolves `false`.
 
-Two independent transport rails, never an auth input:
+Three independent transport rails, never an auth input:
 
 - **Session metadata** — `SessionRegistration.IsCloudPc` →
   Sessions table (sticky-true OR across re-registrations, like
@@ -110,6 +110,15 @@ Two independent transport rails, never an auth input:
   MCP `search_sessions`/`query_raw_sessions`). Agent-reported and unverified —
   can legitimately disagree with the server-derived `ValidatedBy = CloudPc`
   (e.g. Cloud PC admitted via a stage that ran earlier).
+- **Distress channel** — `DistressReport.IsCloudPc` (captured once at
+  `DistressReporter` construction, `BackendClientFactory`) rides every pre-auth
+  distress report → `DistressReportEntry.IsCloudPc` → the "Devices Not
+  Registered" report aggregates it **sticky-true** per serial
+  (`GetDeviceNotRegisteredFunction`) and the portal insight renders a Cloud PC
+  badge plus a hint pointing at the Cloud PC validation toggle + the
+  `W365CloudPcValidation` add-on. Same UNVERIFIED contract as all distress
+  fields; rows from older agents read false. Fits the existing 1536-byte
+  payload cap without a bump.
 - **Decision engine** — the marker rides the `EnrollmentFactsObserved` payload
   (`isCloudPc`), is recorded set-once for BOTH values in
   `EnrollmentScenarioObservations.CloudPc`, and annotates the scenario profile

docs/backend/lifecycle-manifests-and-session-scope.md

@@ -0,0 +1,62 @@
+---
+type: concept
+title: Lifecycle Manifests & Session Scope Resolution
+description: The enforced completeness nets added by the fragility-audit P5/P6 remediation — table lifecycle buckets, the SessionsIndex field manifest, the single session-scope resolver with its SessionTenantLookup point-read, and the server-side dashboard free-text search.
+resource: backend
+tags: [lifecycle, offboarding, sessionsindex, manifest, scope-resolution, search, performance]
+timestamp: 2026-08-13
+---
+
+# Schema
+
+Four mechanisms replace hand-synchronized copies with a declared source plus tests that fail on drift.
+
+## 1. Table lifecycle buckets
+
+Every table in `Constants.TableNames` must belong to at least one deletion lifecycle:
+
+| Bucket | Mechanism | Source of truth |
+|---|---|---|
+| Tenant-offboarding wipe | `TenantOffboardingHandler` bucket arrays (`TenantPartitionTables`, `CompositePartitionTables`, `DiscriminatorTables`, `PropertyOnlyTables`, `RowKeyTables`, `ArchivedRuleTables`) + the one-off `TenantConfiguration` final delete | handler arrays (read via reflection by the test) |
+| Per-session cascade | `DeletionManifestBuilder.BuildAsync` step list (incl. the Final tombstone → Sessions + SessionsIndex) | a real manifest built against an empty-inventory fake |
+| Kept by design | reviewed exception list with per-table reasons | `TableLifecycleBucketTests.KeptByDesign` |
+
+`TableLifecycleBucketTests` (Functions.Tests) asserts: constants set-equal `TableNames.All`, no table unclassified, kept-by-design disjoint from every wipe path, bucket entries are real constants, offboarding buckets disjoint except documented multi-membership (`BootstrapSessions`).
+
+**Not covered mechanically:** whether a bucket's key shape matches the table's writer. That was the UsageMetrics bug (PK=date, RK=tenantId sat in the exact-PK bucket; the wipe matched 0 rows) — SafeWipe **Variant D** (`WipeByRowKeyAsync`, `RowKey eq '{tenantId}'`) now covers RowKey-anchored tables. Read the writer's `new TableEntity(pk, rk)` before classifying a new table.
+
+## 2. SessionsIndex field manifest
+
+`SessionIndexFieldManifest` (Functions/Services) declares the full-mirror column set: `AlwaysProjected` (32, written with defaults on every rebuild), `ConditionallyProjected` (18, written only when present), `PrimaryOnly` (4 — ServerActions + deletion-CAS fields that never touch the index). `SessionIndexFieldManifestTests` pins `BuildSessionIndexEntity` against it bidirectionally (full-row fixture built from a test-local sample table, NOT from the manifest — deriving the fixture from the manifest would make the check circular), pins that every manifest field influences `MapToSessionSummary`, and pins the rebuild's `TableUpdateMode.Replace` (a merge-mode upsert could never clear a conditional column the primary blanked). `MergeSessionIndexAsync` logs a warning for merged keys outside the manifest (fail-soft drift guard).
+
+## 3. Session scope resolution (one implementation)
+
+`RequestContextExtensions.ResolveSessionScopeAsync(ctx, sessionRepo, sessionId, requireGlobalAdmin)` is the single implementation of the former 15-site copy-paste fallback ("which tenant owns this session?"):
+
+- Non-global callers always keep the middleware-validated `TargetTenantId`.
+- Global-scope callers resolve via `ISessionRepository.ResolveSessionTenantIdAsync` — a point-read on **SessionTenantLookup** (PK=sessionId, RK="tenant") with a legacy cross-partition SessionsIndex scan fallback that self-heals the lookup row, so the scan is paid at most once per pre-table session.
+- `requireGlobalAdmin: true` on WRITE paths gates the cross-tenant reach on `IsGlobalAdmin` so a read-only Global Reader can never steer a write into a foreign tenant.
+- Unknown session → `TargetTenantId`, leaving each endpoint's own not-found semantics (404 / empty 200 / 400) in charge.
+- Delegated (MSP) callers deliberately get NO fallback — extending it to `AllowedTenantIds` is a pending user decision.
+
+The lookup row is written at session registration (fail-soft), deleted by the cascade one step before the tombstone, and rebuildable from Sessions (not in the critical-backup set). The former lazy triggers (`events.Count == 0` → scan) are gone: empty-but-owned results no longer pay a table scan, and endpoints resolve upfront.
+
+Related enforcement added with the migration: `RecomputeTriggerGate` — `?reanalyze=true` and `?rescan=true` on the MemberRead session routes are actions (delete + rewrite stored results) and now 403 for Viewer / Global Reader / cross-tenant tenant roles (Global Admin or own-tenant Admin/Operator only).
+
+## 4. Server-side dashboard search
+
+`q=` on `/api/search/sessions` + `/api/global/search/sessions`: case-insensitive substring over exactly the fields the dashboard's client-side filter searches (device name, serial, manufacturer, model, status, sessionId, geo, agent version, OS fields — NOT the client-derived date/duration/blocked tokens; a server-only field would produce ghost results the client filters back out). Azure Tables has no substring operator, so the scan path backfills whole Azure pages until it has `pageSize` matches (max 10 pages per request, continuation at a page boundary — gap-free). `q` is bound into the pagination fingerprint. The web dashboard's `searchAll()` (useDashboardSessions) follows nextLink up to 10 requests / 50 matches and dedupe-merges results into the loaded list (`mergeSessionsById`), replacing the former `loadAll()` walk that downloaded the entire session history to search it client-side. Delegated callers in cross-tenant mode keep the legacy full sweep (the global search route has no delegated tier).
+
+# Examples
+
+Adding a new table: classify it in one lifecycle path before `TableLifecycleBucketTests` lets it ship — offboarding bucket (check the writer's PK/RK shape first), deletion-manifest step, or `KeptByDesign` with a reason.
+
+Adding a mirrored SessionsIndex field: manifest entry + `BuildSessionIndexEntity` write + `MapToSessionSummary` read + a sample value in the test — any missing step is red.
+
+# Citations
+
+- `src/Backend/AutopilotMonitor.Functions.Tests/TableLifecycleBucketTests.cs`
+- `src/Backend/AutopilotMonitor.Functions/Services/SessionIndexFieldManifest.cs`
+- `src/Backend/AutopilotMonitor.Functions/Helpers/RequestContext.cs` (`ResolveSessionScopeAsync`)
+- `src/Backend/AutopilotMonitor.Functions/Services/Offboarding/SafeWipeService.cs` (Variant D)
+- `src/Backend/AutopilotMonitor.Functions/Services/TableStorageService.AgentApi.cs` (`MatchesFreeText`, backfill loop)

docs/backend/session-annotations.md

@@ -0,0 +1,122 @@
+---
+type: Concept
+title: Session Annotations — Role-Separated Human Verdicts
+description: The SessionAnnotations table (PK=tenantId, RK={sessionId}_{lane}) storing per-session human verdicts + notes in three role lanes (operator / tenantadmin / globaladmin), the per-lane write matrix with own-tenant binding, the platform-internal GA lane, the fired-rule-id snapshot that makes annotations rule-quality labels, and the portal/MCP surfaces.
+resource: /src/Backend/AutopilotMonitor.Functions/Functions/Annotations/UpsertSessionAnnotationFunction.cs
+tags:
+  - backend
+  - web
+  - mcp
+  - annotations
+  - authorization
+  - rule-quality
+timestamp: 2026-08-11T00:00:00+02:00
+---
+
+# Schema
+
+**Table.** `SessionAnnotations`: PartitionKey = `tenantId`, RowKey = `{sessionId}_{lane}` with
+lane ∈ `operator | tenantadmin | globaladmin` (a closed set — `AnnotationLanes.All`). One row per
+session + lane, edited in place; per-session reads use the RK range `ge '{sid}_' / lt '{sid}_~'`.
+Serialization lives only in `TableSessionAnnotationRepository.StoreAnnotation`/`MapAnnotation`
+(round-trip-pinned; corrupt `RuleIdsJson` degrades to an empty list on read).
+
+**Row.** `Verdict` (nullable: `root_cause_confirmed | analysis_wrong | different_problem |
+inconclusive`), `Note` (nullable, ≤ 4096 chars), `AuthorUpn`/`AuthorDisplayName` (last editor),
+`CreatedByUpn`/`CreatedAtUtc` (first writer, immutable across edits), `UpdatedAtUtc`, and
+`RuleIdsJson` — a **snapshot of the rule ids that had fired for the session at write time**
+(from `IRuleRepository.GetRuleResultsAsync`, fail-soft to empty). The snapshot is what turns an
+annotation into a rule-quality label without a join: filtering annotations by `ruleId` + `verdict`
+yields confirmed vs false-positive counts per rule even after results are re-analyzed or deleted.
+
+**Verdict + note are independently optional**; a PUT with both null **deletes** the lane row
+(there is no DELETE route). Author identity is always stamped server-side from the JWT
+(`TenantHelper.GetUserDisplayName` + `RequestContext.UserPrincipalName`) — a body-supplied
+author never wins (same anti-spoof contract as the gather-rule PUT-upserts).
+
+# Authorization
+
+Routes (all in `EndpointAccessPolicyCatalog`):
+
+| Route | Policy | Notes |
+| --- | --- | --- |
+| `GET sessions/{sessionId}/annotations` | `MemberRead` + QueryParam | handler filters the GA lane |
+| `PUT sessions/{sessionId}/annotations/{lane}` | `TenantAdminOrOperator` + QueryParam | re-gated per lane in-function |
+| `GET global/session-annotations` | `GlobalReadOrAdmin` + QueryParam | evaluation stream; delegated ("MSP") readers are rescue-admitted on a managed `?tenantId=` only |
+
+**Per-lane write matrix** (`UpsertSessionAnnotationFunction.IsLaneWritableByCaller`, an
+`internal static` pure function like `QueueSessionActionFunction.IsTypeAllowedForCaller`):
+`operator` → tenant Operator or tenant Admin; `tenantadmin` → tenant Admin; `globaladmin` →
+Global Admin only. **Own-tenant binding:** the session's tenant is resolved *before* the gate
+(GA cross-tenant fallback via `FindSessionTenantIdAsync`), and tenant-role inputs are zeroed
+when the resolved tenant differs from the caller's JWT tenant — so a GA who is also an admin of
+their home tenant can never write another tenant's operator/tenantadmin lanes. Cross-tenant, a
+GA writes exactly the `globaladmin` lane (the platform labeling flow).
+
+**GA lane is platform-internal.** `GetSessionAnnotationsFunction.FilterLanesForCaller` drops the
+`globaladmin` lane for every caller without `HasGlobalScope` (tenant members and delegated
+admins). Both list endpoints enforce the same rule server-side via the repository's
+`excludeGlobalAdminLane` OData clause — on the global route this matters exactly for the
+delegated-rescue path, which reaches it without global scope. Tenant lanes are readable by all
+members of that tenant.
+
+**Audit.** Non-GA writes/clears log `LogAuditEntryAsync(..., "SessionAnnotation",
+"{sessionId}/{lane}", ...)`; GA writes are skipped (platform-internal labeling must not surface
+in the tenant-visible audit log — same convention as GA session-report submissions).
+
+# Lifecycle
+
+* **Per-session cascade delete**: three exact-RK steps (one per lane) in `DeletionManifestBuilder`
+  (orders 17–19; inventory 20/21, tombstone 22). `ComputePreflightCounts` sums repeated-table
+  steps so the `sessionAnnotations` count covers all lanes.
+* **Tenant offboarding**: `SessionAnnotations` is in the PK=tenantId wipe list — deliberately
+  wiped, unlike `Feedback` (annotations are customer session data, not product feedback).
+* **Backup**: member of `Constants.CriticalBackupTables.All` — hand-labeled data is the most
+  expensive data on the platform to lose.
+* Being in `Constants.TableNames.All` auto-creates the table at startup and exposes it to the
+  raw `list_tables`/`query_table` tools.
+
+# Surfaces
+
+* **Portal**: `SessionAnnotationsCard` on the session detail page (`#section-annotations`, after
+  Analysis; registered in BOTH the section div and the `sessionSections` sidebar registry). The
+  card mirrors the matrix via the pure module `sessionAnnotationLogic.ts` (vitest-pinned) and
+  uses the explicit-Save pattern; the backend re-gates every save. Collapsed by default with a
+  count + verdict-pill summary header.
+* **Portal overview page** `/annotations` (Monitoring sidebar group — deliberately NO new
+  "Insights" group; Fleet Health & co. are insights too and a second analytics group would
+  dilute both): tenant-scoped list backed by `GET sessions/annotations/list`
+  (`ListTenantSessionAnnotationsFunction`, MemberRead + QueryParam). The path sits under the
+  `/api/sessions` client-cert exclusion prefix (rename-over-exclusion convention; the Azure
+  exclusion list is portal-only config) and uses THREE segments because a two-segment literal
+  would be eaten by the `sessions/{sessionId}` route template. The tenant is always the
+  middleware-validated `TargetTenantId`, and for callers without global scope the repository
+  adds a server-side `Lane ne 'globaladmin'` OData clause — hidden rows never consume page
+  budget, and an explicit lane=globaladmin filter self-contradicts to an empty page. Rows
+  deep-link to `sessions?id=…#section-annotations`. The page carries the standard tenant
+  switcher (`useAggregatedAdminScope` + `TenantScopeSelector`): a GA/Reader defaults to the
+  "All tenants" aggregate (the portal twin of MCP's `list_session_annotations`) with per-tenant
+  drill-down, a delegated ("MSP") admin gets the managed subset; cross-tenant scopes route to
+  `GET global/session-annotations`, a tenant column appears, and deep links carry the row's
+  `tenantId`.
+* **MCP read**: `get_session_summary` carries an `annotations` key (4th parallel leg, fail-soft
+  null); `list_session_annotations` (`ga`-gated) is the evaluation stream with `tenantId / lane /
+  verdict / ruleId / dateFrom / dateTo` filters and nextLink pagination. The `ruleId` filter is
+  applied server-side but client-of-Azure (substring on the JSON column), so the backend
+  back-fills short pages by looping the Azure continuation (bounded rounds) — filtered-out rows
+  never consume page budget.
+* **MCP write**: `annotate_session` (`strictGa`-gated, MUTATING) always PUTs the `globaladmin`
+  lane — no lane argument by design. This is the frictionless labeling path after a session-debug.
+* **Session reports**: `SessionReportService.SubmitReportAsync` snapshots ALL lanes into
+  `annotations.json` inside the report ZIP (`annotationCount` in report-metadata.json; fail-soft).
+  Safe because report blobs are readable only through the GA-only session-reports routes, and
+  valuable because the ZIP outlives the session's retention/delete.
+
+# Citations
+
+* `src/Shared/AutopilotMonitor.Shared/Models/SessionAnnotation.cs` — model, lanes, verdicts.
+* `src/Backend/AutopilotMonitor.Functions/DataAccess/TableStorage/TableSessionAnnotationRepository.cs` — Store/Map + query back-fill.
+* `src/Backend/AutopilotMonitor.Functions/Functions/Annotations/` — the three endpoints.
+* `src/Backend/AutopilotMonitor.Functions/Pagination/SessionAnnotationsPagination.cs` — filter-bound continuation tokens.
+* `src/Web/autopilot-monitor-web/app/sessions/components/sessionAnnotationLogic.ts` — portal matrix mirror.
+* `src/McpServer/autopilot-monitor-mcp/src/tools/admin.ts` — `list_session_annotations`, `annotate_session`.

docs/drift-guards.md

@@ -0,0 +1,106 @@
+---
+type: Concept
+title: Drift Guards — SignalR Names, RowKeys, Config Sections, Scoped Routing
+description: The 2026-08 fragility-audit follow-up contracts that turn formerly hand-synchronized mirrors into enforced ones — SignalR message-name catalog, the inverted-tick RowKey codec, tombstone table tagging, the OkAsync ratchet, per-section config PATCH, and the web's scoped-endpoint builders.
+resource: /src/Backend/AutopilotMonitor.Functions.Tests/OkAsyncBaselineGuardTests.cs
+tags:
+  - contracts
+  - guard-tests
+  - signalr
+  - web
+timestamp: 2026-08-13T00:00:00+02:00
+---
+
+# Drift Guards
+
+Follow-up to the 2026-08 fragility audit (see [Lifecycle Manifests & Session Scope
+Resolution](backend/lifecycle-manifests-and-session-scope.md) for the earlier rounds).
+Each section below replaces a hand-synchronized mirror with an enforced contract: a
+change on one side now fails a build, a type check, or a test on the other side.
+
+# Schema
+
+## SignalR message names — one catalog, typed on both ends
+
+`Constants.SignalRMessages` (Shared) is the complete catalog of SignalR target names.
+Backend senders (output bindings and the imperative `SignalRNotificationService`)
+reference the constants; the hub name is `SignalRGroupHelper.HubName`. The catalog is
+exported into `shared-manifests.json` (`signalRMessages` section) by
+`SharedManifestParityTests`, and the web's `SignalRContext.on/off` type their event
+name against the generated union (`lib/signalrMessages.ts`) — subscribing to a name
+the backend never sends is a tsc error, not a silent no-op. `newevents` is the one
+legacy lowercase name; it is a persisted wire name, do not "fix" the casing.
+
+## Inverted-tick RowKeys — one codec
+
+`RowKeyCodec` (Functions/Helpers) is the single encoder/decoder for
+`rev(t) = MaxTicks - t.Ticks` RowKeys. Every writer routes through it; the persisted
+per-table shapes (D19 standard, AuditLogs `!`-prefix, UserActivity's legacy D20 width,
+ConfigurationBackups' 28-char truncation) are pinned by `RowKeyCodecTests` and must
+never change — a width/prefix change reorders live tables against their existing rows.
+`BusinessTimestamp` keeps the OData clause builders and delegates decode to the codec.
+
+## Tombstone rows carry their table
+
+`DeletionRowDump.Table` names the source table on FINAL (Tombstone) rows — the one
+step that mixes two tables while `DeletionStep.Table` is null.
+`DeletionTombstoneTables.Resolve` is the only consumer-side resolution (delete +
+restore + dry-run); the historical `Contains('_')` RowKey-shape heuristic survives
+solely as the fallback for manifests written before the field existed and must outlive
+one full manifest-retention cycle.
+
+## Anonymous OkAsync responses — frozen, shrink-only
+
+`OkAsyncBaselineGuardTests` freezes the 44 existing `req.OkAsync(new { … })` call
+sites as a per-file baseline. A new anonymous response (new file or count above
+baseline) fails; converting a site to a typed DTO (Shared response models, picked up
+by the manifest parity tests) fails too until its baseline entry is lowered — the debt
+list stays truthful and only ever shrinks.
+
+## Tenant settings — per-section PATCH
+
+The web's Settings sections no longer PUT the full ~92-field configuration. Each
+section's exact write surface lives in `app/settings/sectionFieldMap.ts` (owned fields
+plus documented `alsoWrites` write-throughs); `saveConfiguration` diffs those fields
+against the loaded config and PATCHes only the changes through
+`PATCH config/{tenantId}/fields` — the transactional endpoint (CAS + fail-closed
+backup + exactly-these-fields verify + auto-rollback) that previously served MCP only.
+The policy line is TenantAdminOrGA; a tenant admin runs on the stricter
+`TenantConfigCallerTier.TenantAdmin` whose deny-list turns GA-only fields into
+explicit 400s. Deploy order: backend before web. `sectionFieldMap.test.ts` pins
+field↔section ownership (each field exactly one owner, all fields on the model, none
+server-denied); backups/revert stay GlobalAdminOnly.
+
+## Scoped endpoint routing — one decision object
+
+`lib/scopedApi.ts` owns the tenant/global endpoint-pair choice: pages pass their scope
+hook object (`routeGlobal`, `selectedTenantId`, `effectiveTenantId`) instead of
+hand-rolling `routeGlobal ? global(..., sel || undefined) : tenant(tid, ...)` with the
+tenant parameter at a different position per pair. `useGlobalAdminScope` is now a thin
+projection over `useAggregatedAdminScope` (one hook, aggregated as a mode) via the
+pure `resolveConcreteScopeView`. `lib/scopedFetch.ts` adds the shared JSON+ok-check
+fetch layer. `lib/navVisibility.ts` extracts the sidebar's roles × nav-config × guard
+logic; its matrix test also ratchets the known "sidebar shows it, guard bounces it"
+mismatches (plain Operator and GlobalReader vs. `/settings` — pending a user decision).
+
+# Examples
+
+Renaming a SignalR message end to end: change the constant in
+`Constants.SignalRMessages` → `AM_WRITE_SHARED_MANIFESTS=1 dotnet test --filter
+SharedManifestParityTests` → `node scripts/generate-shared-manifest-types.js` → tsc
+now flags every stale web subscription literal.
+
+Adding a field to a Settings section: add it to the section in `sectionFieldMap.ts`
+(tsc validates the name against the manifest), wire the form state into the
+`updatedConfig` construction in `TenantConfigContext`, and extend the expected-fields
+list in `sectionFieldMap.test.ts`.
+
+# Citations
+
+- `src/Shared/AutopilotMonitor.Shared/Constants.cs` — SignalRMessages catalog
+- `src/Backend/AutopilotMonitor.Functions/Helpers/RowKeyCodec.cs` + `RowKeyCodecTests.cs`
+- `src/Shared/AutopilotMonitor.Shared/Models/Deletion/DeletionManifest.cs` — `DeletionRowDump.Table`, `DeletionTombstoneTables`
+- `src/Backend/AutopilotMonitor.Functions.Tests/OkAsyncBaselineGuardTests.cs`
+- `src/Web/autopilot-monitor-web/app/settings/sectionFieldMap.ts` + `__tests__/sectionFieldMap.test.ts`
+- `src/Web/autopilot-monitor-web/lib/scopedApi.ts`, `lib/navVisibility.ts`, `hooks/concreteAdminScopeView.ts`
+- [Version Contract](versioning.md) — the web `/version.json` stamp + deploy verify added in the same round

docs/index.md

@@ -14,6 +14,7 @@ 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.
 * [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
 
@@ -23,6 +24,7 @@ https://docs.autopilotmonitor.com (separate repository).
 * [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.
 * [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.
 * [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.
 
 # Rules
@@ -30,6 +32,7 @@ https://docs.autopilotmonitor.com (separate repository).
 * [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).
+* [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
 
@@ -38,9 +41,12 @@ https://docs.autopilotmonitor.com (separate repository).
 * [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.
 * [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.
+* [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.
 * [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.
+* [Session Annotations](backend/session-annotations.md) - Role-separated human verdicts on sessions (operator / tenantadmin / globaladmin lanes, one row each): the per-lane write matrix with own-tenant binding, the platform-internal GA lane, the fired-rule-id snapshot that makes annotations rule-quality labels, and the portal card + MCP list/annotate surfaces.
+* [Lifecycle Manifests & Session Scope Resolution](backend/lifecycle-manifests-and-session-scope.md) - The fragility-audit P5/P6 completeness nets: every table classified into a deletion lifecycle (offboarding buckets incl. the RowKey-anchored SafeWipe Variant D, per-session cascade, kept-by-design), the SessionsIndex field manifest with bidirectional builder/reader pinning, the single ResolveSessionScopeAsync helper backed by the SessionTenantLookup point-read, and the server-side dashboard free-text search (q=) with its page-backfill loop.
 
 # MCP Server
 

docs/log.md

@@ -1,5 +1,55 @@
 # Log
 
+## 2026-08-17
+
+* **Update**: `mcp/tool-telemetry.md` — the `tool_call` stderr line now carries `errorMessage` (capped at 300 chars; thrown message or the leading `toolError` text, absent on success), so error drilldowns name the failure class instead of guessing from args. Same change: `get_rule_stats` omits the per-rule daily `trend` rows by default (they drove 50% of calls over the response cap at platform scope); `includeTrends=true` opts back in, the response carries a `trendsNote` marker when stripped.
+
+## 2026-08-14 (later)
+
+* **Update**: `rules/analyze-rule-triggers.md` — status SPEC → IMPLEMENTED. Shipped: `evaluateOn` on the analyze-rule schema (grammar-validated server-side and in validate_rule), `AnalyzeRunContext`-driven engine runs (Terminal/Interim/Reanalyze) with the RuleResult lifecycle columns (FirstDetectedAt/LastEvaluatedAt/IsInterim/ResolvedAt/NotifiedAt), interim rule filtering + KO/stat suppression, resolve/finalize update-semantics, the NotifiedAt one-send-per-(session,rule) notification dedupe (preserved across the manual reanalyze rebuild), the ingest-side `InterimTriggerRegistry` (5-min TTL, fail-soft) gating `interim_trigger` / `whiteglove_sealed` enqueues, the three MCP authoring lints, web preliminary/resolved rendering, and ANALYZE-ID-004 as the first interim-enabled rule.
+
+## 2026-08-14
+
+* **Creation**: Added `rules/analyze-rule-triggers.md` — SPEC for opt-in `evaluateOn` interim evaluation of analyze rules: `enrollment_end` default preserves today's behavior, `whiteglove_sealed` + `on_event:<type>` close the WhiteGlove notification gap and the never-terminal stuck-session gap; RuleResults update-semantics (FirstDetectedAt/IsInterim/ResolvedAt/NotifiedAt) replace the permanent dedupe freeze; interim runs suppress KO + stats, notifications fire on first detection; three new validate_rule lints (terminal-precondition trap, unknown trigger type, KO-on-interim).
+
+## 2026-08-13 (late evening)
+
+* **Creation**: Added `drift-guards.md` — the fragility-audit follow-up contracts (P5.x + P7): SignalR message-name catalog in `Constants.SignalRMessages`, exported through the shared manifest and typed into the web's `SignalRContext.on/off` union; the `RowKeyCodec` single encoder for inverted-tick RowKeys (persisted widths pinned, incl. UserActivity's legacy D20); `DeletionRowDump.Table` on tombstone rows with `DeletionTombstoneTables.Resolve` replacing the duplicated `Contains('_')` heuristic (legacy fallback retained one retention cycle); the shrink-only `OkAsyncBaselineGuardTests` per-file baseline (44 sites frozen); the Settings per-section PATCH (section field map + diff-based `config/{tenantId}/fields` writes on the TenantAdmin caller tier); and the web's `scopedApi` endpoint-pair builders, single admin-scope hook, `navVisibility` matrix and guard-consistency ratchet.
+
+* **Update**: `versioning.md` — the web portal joins the version contract commit-only: `public/version.json` generated at build time from `GITHUB_SHA`, served with `Cache-Control: no-store`, polled by `deploy-web.yml` until the deployed commit matches before `versions/web.json` is published.
+
+## 2026-08-13 (evening)
+
+* **Creation**: Added `backend/lifecycle-manifests-and-session-scope.md` — the fragility-audit P5/P6 completeness nets: (1) `TableLifecycleBucketTests` classifies every `TableNames` constant into offboarding-wipe / per-session-cascade / kept-by-design (fixed en route: UsageMetrics wiped via the new RowKey-anchored SafeWipe Variant D — the exact-PK wipe matched 0 rows; PlatformStats tenant partition + ScriptNameCache added to the tenant-PK bucket); (2) `SessionIndexFieldManifest` as the declared SessionsIndex column set with bidirectional builder/reader test pinning, Replace-mode full rebuilds, and a fail-soft merge-key guard; (3) `ResolveSessionScopeAsync` as the single session-scope fallback (16 former copies), backed by the new `SessionTenantLookup` point-read table (scan fallback + self-heal, cascade step before the tombstone), plus the `RecomputeTriggerGate` 403 for reanalyze/rescan by read-only roles; (4) server-side dashboard free-text search (`q=`) with page-backfill loop and fingerprint binding, replacing the client's full-history loadAll sweep.
+
+* **Creation**: Added `backend/app-version-regression-radar.md` — app-version duration regression radar: per (tenant, app) the newest version's median measured install duration (nearest-rank; population Succeeded + non-skip + `HasMeasuredDuration` + no AppId collision + non-empty AppVersion) is compared against the previous version (first-seen ordering, never string sort); fires at median lift ≥2× AND ≥300s absolute with ≥10 measured installs on both sides. Episodes live as `appversionregression|{app}|{version}` tracker rows (one bell `app_version_duration_regression` + one `AppVersionDurationRegression` ops event per episode, refresh keeps `FirstNotifiedAt`, re-arm on drain/median-recovery/30d retention). Surfaces: `versionRegressions[]` + per-version `measuredInstalls`/`medianDurationSeconds`/`p95DurationSeconds` in the apps analytics responses, amber banner + duration-by-version chart on the apps detail page. Kill switch `AppVersionRegressionRadarDisabled`.
+
+## 2026-08-13
+
+* **Update**: `backend/session-annotations.md` — the `/annotations` portal overview page now carries the standard tenant switcher (GA/Reader: "All tenants" aggregate + per-tenant drill-down via `GET global/session-annotations`; delegated: managed subset), with a tenant column and tenant-qualified session deep links. The global list endpoint now derives `excludeGlobalAdminLane` from `HasGlobalScope`, so delegated-rescue callers on their managed `?tenantId=` path never receive the platform-internal `globaladmin` lane (endpoint-test-pinned).
+
+## 2026-08-12
+
+* **Update**: `agent/autopilot-ztd-diagnostics.md` — Windows 365 Cloud PC exception documented: on Cloud PCs `ProfileAvailable=0` is expected (provisioned by the Windows 365 service, not Autopilot), so `autopilot_profile_missing` is emitted as Info with a Cloud-PC-specific message and an `isCloudPc` payload marker (`ResolveAutopilotProfileMissingPresentation`); the portal's Autopilot Profile card renders a neutral note instead of the amber warning for Cloud PC sessions (`session.isCloudPc` or the event marker).
+
+## 2026-08-11 (later)
+
+* **Creation**: Added `backend/session-annotations.md` — session annotations: the new `SessionAnnotations` table (PK=tenantId, RK=`{sessionId}_{lane}`, lanes operator/tenantadmin/globaladmin) storing structured verdicts (`root_cause_confirmed | analysis_wrong | different_problem | inconclusive`) + notes with server-stamped authorship and a fired-rule-id snapshot for join-free rule-quality evaluation. Per-lane write matrix re-gated in-function with own-tenant binding (a GA writes only the platform-internal `globaladmin` lane cross-tenant; tenant callers never see that lane). Surfaces: portal `SessionAnnotationsCard` (session detail, after Analysis), MCP `list_session_annotations` (ga) + `annotate_session` (strictGa, always the GA lane) + `annotations` key in `get_session_summary`. Lifecycle: per-session cascade steps 17–19, offboarding wipe, critical-backup member.
+
+## 2026-08-11
+
+* **Update**: `rules/gather-rule-guardrails.md` — hard-block mirroring closed across all pre-flight layers: `rules/guardrails.json` now also mirrors `blockedCommandPatterns` + `maxCommandLength` and carries `C:\Windows\System32\config` in `blockedFilePrefixes`; portal (`guardValidation.ts`) and MCP (`rule-validation.ts`) apply them in agent order (before the unrestricted-mode early-return), so a command the agent hard-blocks no longer shows "Allowed" in unrestricted tenants. `GuardrailsParityTests` pins the JSON mirror to the C# constants. MCP `validate_rule` additionally validates `json`/`xml` targets with file semantics (the schema's `collectorType` enum was missing both) and rejects `activePhases`+`activeFromPhase` set together (backend 400 parity). Author stamping extended to PUT-upserts: tenant and global gather-rule updates stamp the caller's JWT display name before the service call, so an upsert of a non-existing ruleId can no longer store a payload-supplied author (true updates still preserve the original author).
+
+## 2026-08-10
+
+* **Update**: `rules/gather-rule-guardrails.md` — WMI matcher generalized from literal prefix matching to shape parsing: `SELECT <* | property-list> FROM <class>` is allowed when the class is derived from the existing `SELECT * FROM <class>` entries (a projection is a strict subset; motivated by `SELECT BatteryStatus FROM Win32_Battery` + `on_change` battery polling that `SELECT *` defeats via fluctuating charge %). Same algorithm mirrored agent/portal/MCP; guardrails.json unchanged. Portal now also gates enabling on the client-side validation (invalid-target custom rules create disabled, cannot be toggled on, force-disable on invalid edit, "Blocked on devices" badge) — UX only, the agent guard stays the boundary. Gather-rule Author is now stamped from the creator's JWT (display name → UPN) at create and immutable on update.
+
+* **New**: `agent/continue-anyway-observation.md` — Continue-Anyway observation mode (`EnableEspContinueAnywayObservation`, ConfigVersion 37, operator-set): Device-phase ESP terminal failures on Continue-Anyway profiles are defanged into a 60-min observation window (Classic/Unknown, non-pre-prov only); real-user desktop + Hello gate complete the session as Succeeded + `EspSoftFailure`/`CompletionSource` (amber "with issues" badge + detail banner), category recovery resolves clean, expiry un-defangs to the original `esp_terminal_failure`. Registered in the Agent index section. Related backend fix (no doc): the auto-analyze enqueue now carries a 30 s `visibilityTimeout` so rule evaluation no longer races the agent's terminal flush (ANALYZE-ESP-004's `{{appName}}` placeholder).
+
+## 2026-08-07 (later)
+
+* **Update**: `backend/cloudpc-device-validation.md` — third `IsCloudPc` transport rail: the pre-auth distress channel. `DistressReport.IsCloudPc` (CloudPcDetector verdict captured at `DistressReporter` construction) → `DistressReportEntry`/table column → "Devices Not Registered" aggregation (sticky-true per serial, same OR semantics as the Sessions merge) → portal Cloud PC badge + actionable hint ("enable Windows 365 Cloud PC Validation + W365CloudPcValidation add-on"). Motivated by the first W365 field run: the rejected Cloud PC showed up as anonymous "Microsoft Corporation / Virtual Machine" with no clue that the fix is the Cloud PC validator, not Autopilot registration. UNVERIFIED like all distress fields; ≤18 bytes, fits the 1536-byte cap.
+
 ## 2026-08-07
 
 * **Update**: `backend/cloudpc-device-validation.md` — the "deliberately out of scope" follow-up landed in the same PR: agent-side `IsCloudPc` flag (`CloudPcDetector`, bootstrap-verified marker AND: Windows365 key + CloudManagedDesktopExtension service key, SKIP-safe) rides two rails — `SessionRegistration` → Sessions/Index (sticky-true) → `SessionSummary` + `isCloudPc` search filter (portal/raw/MCP), and the `EnrollmentFactsObserved` payload → `EnrollmentScenarioObservations.CloudPc` (set-once, both values) with profile reason `cloud_pc_first_connect:no_device_esp_expected` + `cloud_pc_marker` in the audit-trail census. Reason+observation only: no completion arm depends on DeviceSetup, Mode stays AccountSetup/IME-classified, EspConfig keeps configured-FirstSync semantics. Never an auth input.

docs/mcp/tool-telemetry.md

@@ -25,7 +25,10 @@ Three layers answer "are the MCP tools doing their job, and are tools missing?":
    Logs) — the layer that carries what the other two structurally cannot:
    - `tool_call`: duration, `isError` **including soft errors** (handlers never
      throw — `toolError` *returns* `isError: true`, so backend-only telemetry
-     records those calls as successes), `resultChars` + `overCap` (result
+     records those calls as successes), `errorMessage` (capped; the thrown
+     message or the first lines of the `toolError` text, which name the error
+     class — HTTP status / timeout / auth / not found; absent on success),
+     `resultChars` + `overCap` (result
      exceeds the tool's `anthropic/maxResultSizeChars` hint → the host truncates
      it; a frequently-overCap tool needs tighter defaults or projections), a
      size-bounded args summary, and the caller scope (ga/delegated/tenant).

docs/rules/analyze-rule-triggers.md

@@ -0,0 +1,118 @@
+---
+type: Concept
+title: Analyze Rule Evaluation Triggers (evaluateOn)
+description: "Opt-in interim evaluation of analyze rules before a session is terminal — enrollment_end stays the default, whiteglove_sealed and on_event:<type> triggers close the WhiteGlove notification gap and the never-terminal stuck-session gap with one mechanism, backed by update-semantics on RuleResults instead of the permanent dedupe freeze."
+resource: backend/rule-engine
+tags: [rules, analyze, triggers, notifications, whiteglove]
+timestamp: 2026-08-14
+---
+
+# Status
+
+**IMPLEMENTED 2026-08-14** (same day the spec was approved). The open product decisions below were confirmed as "no" for v1. Key implementation anchors: `AnalyzeRuleTriggers` (Shared — grammar + matching helpers, shared by engine, ingest registry and CRUD validation), `AnalyzeRunContext` / `AnalysisOutcome.ResolvedResults` (RuleEngine), `InterimTriggerRegistry` (5-min-TTL per-tenant cache for the ingest hot path, fail-soft), `AnalyzeOnEnrollmentEndHandler` interim branch, `EvaluateOnJson` + five RuleResult lifecycle columns in `TableStorageService.Rules`. ANALYZE-ID-004 ships as the first interim-enabled rule (`on_event:hybrid_login_pending`, repetition-gated at threshold 75).
+
+# Problem
+
+Analyze rules run at exactly three points today, all of them terminal or near-terminal:
+
+1. `enrollment_complete` / `enrollment_failed` observed at ingest (`EventIngestProcessor.cs`, classification → analyze envelope).
+2. The maintenance sweep terminalizing a silent session (Failed / Incomplete + synthetic `session_timeout`, `MaintenanceService.cs`).
+3. The vulnerability-correlation rerun (`vulnerability_correlated` reason — incremental, no stats).
+
+Two incident classes fall through this model:
+
+- **WhiteGlove gap (sits-d, 2026-08-11):** `whiteglove_complete` seals a session to Pending but enqueues no analyze run. A rule that should alert at the end of pre-provisioning (technician still at the bench) never fires, and when Part 2 eventually terminalizes days later, the permanent per-(session, rule) dedupe means a finding that sneaked in earlier (e.g. via the vuln-rerun backdoor) is frozen and never notifies.
+- **Never-terminal stuck sessions (esa-logistics, 2026-08-13/14):** a session looping in Account Setup (user signs in daily, hybrid affinity never establishes) resets the 5h inactivity clock on every logon. It is never terminalized, therefore never analyzed — the exact sessions where a diagnosis would help most (ANALYZE-ID-004, ANALYZE-APP-015) produce no finding while the customer watches the device loop.
+
+Both gaps share one root cause: *evaluation time is hard-wired to session end*. Gather rules already solved the analogous problem on-device with declarative triggers (`startup` / `phase_change` / `phase_exit` / `interval` / `on_event`); analyze rules need the server-side equivalent.
+
+# Design Overview
+
+Add an optional `evaluateOn` array to the analyze-rule schema. Absent field ⇒ `["enrollment_end"]` ⇒ **today's behavior, bit-for-bit, for every existing rule**.
+
+```
+"evaluateOn": ["enrollment_end", "on_event:hybrid_login_pending"]
+```
+
+Trigger grammar (v1):
+
+| Trigger | Fires when | Notes |
+|---|---|---|
+| `enrollment_end` | terminal analyze run (complete / failed / sweep-terminalized) | default; also the **finalization pass** for interim results (below) |
+| `whiteglove_sealed` | ingest classifies the first genuine `whiteglove_complete` (session → Pending, `isPreProvisioned`) | duplicate seals do not re-trigger |
+| `on_event:<eventType>` | an ingest batch contains ≥1 event of `<eventType>` | `<eventType>` validated against the event-types catalog; phase boundaries are covered by `on_event:phase_transition` / `on_event:esp_phase_changed` — no separate phase grammar needed, since every run evaluates the full stream anyway |
+
+Explicitly **not** in v1: interval/timer triggers (no cheap host for them; the sweep remains the only clock), and `on_event` filters on data fields (the rule's own conditions do that — the trigger only decides *when* to look).
+
+# Pipeline Changes
+
+## Ingest (producer side)
+
+- `EventIngestProcessor` already classifies each stored batch. After classification, intersect the batch's event types with the tenant's **trigger registry** (the set of `on_event` types across the tenant's active rules — derivable from `AnalyzeRuleService`'s merged rule load, cached alongside it). Non-empty intersection ⇒ enqueue one envelope `Reason=interim_trigger`, carrying the matched trigger event types. Reuse the existing 30s visibility delay (terminal-flush ordering argument in `AzureQueueAnalyzeOnEnrollmentEndProducer` applies to interim batches too).
+- The `whiteglove_complete` seal path (`EventIngestProcessor.Classification.cs`) enqueues `Reason=whiteglove_sealed` — only on the first seal, only for `isPreProvisioned`.
+- Terminal enqueue (`CompletionEvent` / `FailureEvent`) is unchanged.
+
+## Handler / engine (consumer side)
+
+`AnalyzeOnEnrollmentEndHandler` branches by reason today (primary vs. `vulnerability_correlated`); interim reasons become a third branch. The engine call gets a run context instead of the bare `reanalyze` flag:
+
+| Aspect | Terminal run (`enrollment_end`) | Interim run (`whiteglove_sealed`, `interim_trigger`) |
+|---|---|---|
+| Rule set | ALL active rules (interim-triggered ones get their finalization pass here) | only rules whose `evaluateOn` matches the reason / one of the batch's trigger types |
+| KO (`MarkSessionAsFailed`) | applies (unchanged) | **suppressed** — a Pending/InProgress session must never be flipped Failed by an interim pass (`TryMarkSessionFailedFromRuleAsync` is skipped; the terminal run re-fires the rule and applies KO then) |
+| Platform stat `IssuesDetected` | counted | skipped (like vuln rerun) |
+| Per-rule fire stats | counted | skipped (like vuln rerun) — keeps the terminal-only stats convention and the Rule Regression Radar baselines clean |
+| Channel notifications | new findings notify (unchanged) | new findings notify — **this is the point** of both gaps |
+| SignalR results-available | yes | yes (live update of an open session page) |
+
+## Result lifecycle: update semantics replace the dedupe freeze
+
+Today the engine skips any rule that already has a stored `RuleResult` row for the session (`RuleEngine.AnalyzeSessionAsync`, existing-results lookup) — findings are frozen at first write, which is precisely the WG-gap failure mode ("dedupe permanent").
+
+New model — `RuleResult` gains four fields (`FirstDetectedAt`, `LastEvaluatedAt`, `IsInterim`, `ResolvedAt`, plus `NotifiedAt` for the notification marker):
+
+- **Interim run:** rules in scope are (re-)evaluated even when a row exists. Fired ⇒ upsert (evidence/confidence refreshed, `FirstDetectedAt` preserved, `IsInterim=true`). Not fired + existing interim row ⇒ `ResolvedAt` set (kept for audit; excluded from issue counts and default UI).
+- **Terminal run:** every rule that has an interim row is re-evaluated regardless of dedupe (finalization). Fired ⇒ row finalized (`IsInterim=false`, evidence refreshed — fixes the stale-template-field freeze, e.g. the ESP-004 `{{appName}}` case). Not fired (typically a `not_exists` precondition on `enrollment_complete` now failing because the session healed) ⇒ `ResolvedAt` set. Rules without interim rows keep today's skip-if-exists dedupe.
+- **Notification dedupe** moves off "row exists" onto `NotifiedAt` on the row: notify once per (session, rule) at first fire — interim or terminal, whichever comes first; refreshes and finalization do not re-notify. The manual `reanalyze=true` path must **preserve** `NotifiedAt` across its rebuild (today it deletes rows; delete-and-recreate would silently re-arm notifications) and keeps its designed never-notify behavior.
+- Legacy rows (null new fields) read as final/terminal — no migration.
+
+# Authoring Guardrails (validate_rule lints)
+
+Interim evaluation changes what a rule's conditions mean mid-flight. Three new lints in the MCP `validate_rule` pre-flight (and the baked authoring guide):
+
+1. **Terminal-precondition trap (warning):** `evaluateOn` contains an interim trigger AND a precondition is `not_exists` on `enrollment_complete` / `enrollment_failed` / `session_timeout`. Mid-run these pass trivially — the rule needs conditions that are *monotonic* (once true on the growing event stream, stays true) or repetition-gated. Worked example: ANALYZE-APP-015 must NOT get an interim trigger as-is — even successful sessions transiently show its "completion signal deferred" + `pending>=1` pattern (the terminal precondition is its only gate). ANALYZE-ID-004 is interim-safe by construction (threshold 65 requires repeated `hybrid_login_pending`).
+2. **Unknown trigger event type (error):** `on_event:<type>` not in the event-types catalog.
+3. **KO-on-interim (warning):** `markSessionAsFailedDefault: true` on a rule whose only triggers are interim — the KO would never apply until terminal; say so.
+
+# Cost & Safety
+
+- Interim runs are bounded by trigger frequency, and the chosen v1 triggers are rare by construction (`hybrid_login_pending` ≤1 per boot, `whiteglove_sealed` once per session). High-frequency telemetry event types (performance_snapshot, agent_metrics_snapshot, download_progress, network churn, log_entry, agent_trace, stall_probe_check) are **hard-blocked** as `on_event` triggers, not merely advised against: the CRUD write is rejected (`AnalyzeRuleTriggers.BlockedOnEventTypes`, code-only enforcement), the runtime matcher drops them from any row that slipped in (defense in depth — the trigger registry and the engine both go through `OnEventTypes`), and the MCP lint reports them as an error. The JSON mirror lives in `rules/guardrails.json` (`blockedInterimTriggerEventTypes`) with a parity test pinning it to the C# set — the same pattern the gather hard blocks use. If a legitimate rare-but-bursty type ever hurts, a per-(session, reason) throttle marker is the v2 lever.
+- Each run loads the full event stream once (existing engine behavior, no change); rule filtering makes interim passes strictly cheaper than terminal ones.
+- Queue semantics (retry via visibility timeout, poison after MaxDequeueCount, idempotent partial-success re-runs) are inherited unchanged; upserts keep idempotency.
+
+# Surfaces
+
+- **Web session page:** interim findings render live (existing SignalR results-available notification) with a "preliminary" badge on `IsInterim`; `ResolvedAt` rows hidden by default behind a toggle.
+- **MCP:** `get_session(includeAnalysis)` / `get_session_summary` expose `isInterim` / `resolvedAt`; `list_session_annotations`' fired-rule snapshot semantics unchanged (labels bind to whatever was fired at annotation time).
+- **Success-rate / platform stats:** terminal-only convention untouched (interim runs record no stats).
+
+# 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.
+- 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).
+
+# Product Decisions (settled 2026-08-14)
+
+1. Notify-on-resolve (a "finding healed" message)? **No** (v1) — resolution is visible in UI/MCP.
+2. Re-notify on severity/confidence escalation of an existing finding? **No** (v1) — one notification per finding.
+3. `whiteglove_sealed` runs allowing KO rules to flip Pending → Failed? **No** — the Pending state is the WhiteGlove contract; suppression is unconditional for interim.
+
+# Citations
+
+- `src/Backend/AutopilotMonitor.Functions/Services/EventIngestProcessor.cs` — terminal-only enqueue (classification → analyze envelope).
+- `src/Backend/AutopilotMonitor.Functions/Services/Analyze/AnalyzeOnEnrollmentEndHandler.cs` — reason branching, notify path, stats side-effects.
+- `src/Backend/AutopilotMonitor.Functions/Services/Analyze/AzureQueueAnalyzeOnEnrollmentEndProducer.cs` — 30s visibility delay rationale.
+- `src/Backend/AutopilotMonitor.Functions/Services/RuleEngine.cs` — existing-results dedupe, `TryMarkSessionFailedFromRuleAsync` KO path.
+- `src/Backend/AutopilotMonitor.Functions/Services/MaintenanceService.cs` — sweep terminalization + analyze enqueue; inactivity-clock reset explains the never-terminal gap.
+- `rules/gather-rule-phase-scoping.md` (this bundle) — the on-device trigger precedent this design mirrors.
+- `rules/rule-authoring-surface.md` (this bundle) — where the new lints land (validate_rule + baked guide).

docs/rules/gather-rule-guardrails.md

@@ -7,14 +7,14 @@ description: >-
   guard rather than trusting rule.Target.
 resource: src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/Gather
 tags: [gather-rules, security, guardrails, agent]
-timestamp: 2026-07-22
+timestamp: 2026-08-11
 ---
 
 # Concept
 
-A gather rule is authored by a **tenant administrator** through `POST /api/rules/gather` and executed by the agent as **SYSTEM** on an enrolling device. The backend does not validate `collectorType`, `target`, or `parameters` at all — it only enforces scope/emit-mode fields, a 1 MB body cap, and that the rule lands in the caller's own tenant partition. Everything that decides *what a rule may reach* is therefore enforced **on the agent**, in `GatherRuleGuards`.
+A gather rule is authored by a **tenant administrator** through `POST /api/rules/gather` and executed by the agent as **SYSTEM** on an enrolling device. The backend does not validate `collectorType`, `target`, or `parameters` at all — it only enforces scope/emit-mode fields, a 1 MB body cap, that the rule lands in the caller's own tenant partition, and that `Author` is stamped from the caller's JWT (create and PUT-upsert; true updates preserve the original author). Everything that decides *what a rule may reach* is therefore enforced **on the agent**, in `GatherRuleGuards`.
 
-This is the security boundary. The portal's `ValidationIndicator` is a convenience: it does not block submit, and the API is reachable directly.
+This is the security boundary. The portal's `ValidationIndicator` is a convenience — the API stays reachable directly and the backend stays validation-free — but since 2026-08 the portal additionally **gates enabling** on the same client-side validation: a custom rule whose target fails validation cannot be toggled on, is created `enabled=false`, and an edit that makes the target invalid force-disables the rule (`targetBlocked` in `app/gather-rules/types.ts`). An enabled rule with an invalid target shows a "Blocked on devices" badge. All of this is UX, not security — the agent guard remains the enforcement point.
 
 # Schema
 
@@ -27,7 +27,7 @@ item in `AutopilotMonitor.Agent.V2.Core.csproj`) and regenerated into the portal
 | --- | --- | --- |
 | `IsRegistryPathAllowed` | `registryPrefixes` | prefix, boundary `\` or end |
 | `IsFilePathAllowed` | `filePrefixes` | `Path.GetFullPath` first, then prefix + boundary |
-| `IsWmiQueryAllowed` | `wmiQueryPrefixes` | prefix, boundary whitespace or end |
+| `IsWmiQueryAllowed` | `wmiQueryPrefixes` | `SELECT <* \| property-list> FROM <class>`; class = case-insensitive equality against classes derived from the `SELECT * FROM <class>` entries, boundary whitespace or end (trailing `WHERE` allowed). Non-canonical entries (none today) fall back to literal prefix + boundary |
 | `IsCommandAllowed` | `allowedCommands` | **exact** match, trimmed — never prefix |
 | `IsEventLogChannelAllowed` | `eventLogChannels` | prefix, boundary `/` or end |
 
@@ -44,7 +44,12 @@ but the hard blocks must hold regardless of configuration:
   PowerShell channels (script-block logging routinely contains secrets in clear text).
 
 `rules/guardrails.json` mirrors the blocked lists (`blockedFilePrefixes`,
-`blockedEventLogChannels`) **for display only**. Enforcement is the C# constant.
+`blockedEventLogChannels`, `blockedCommandPatterns`, `maxCommandLength`) **for display
+and pre-flight only**. Enforcement is the C# constant; `GuardrailsParityTests` (agent
+test project) pins the JSON mirror to the constants so neither side can drift. The
+portal (`utils/guardValidation.ts`) and the MCP validator (`rule-validation.ts`) apply
+the mirrored hard blocks in the same order as the agent — before the unrestricted-mode
+early-return — so a rule the agent would refuse is never shown as "Allowed".
 
 # Examples
 
@@ -71,6 +76,15 @@ Two collectors were added to this contract on 2026-07-22 after shipping without
 remote config. The operator using it is already a local admin, so it relaxes the
 allowlist exactly the way unrestricted mode does — hard blocks still apply.
 
+**WMI property projections (2026-08):** `SELECT BatteryStatus FROM Win32_Battery` is
+allowed because `SELECT * FROM Win32_Battery` is — a projection exposes a strict subset
+of the allowed class. The matcher parses the query shape instead of literal-prefix
+matching; the allowed-class set is derived at load time from the existing
+`wmiQueryPrefixes` entries, so `rules/guardrails.json` needs no new key. The same
+algorithm is mirrored in the portal (`utils/guardValidation.ts`) and the MCP server
+(`rule-validation.ts`); agents older than the change still block projections with a
+`security_warning` until they self-update.
+
 # Citations
 
 * `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/Gather/GatherRuleGuards.cs`

docs/versioning.md

@@ -1,7 +1,7 @@
 ---
 type: Concept
-title: Version Contract — Agent, Backend, MCP
-description: One version shape for all three shipping components, the ETag-CAS counter blob that mints build numbers, and the published manifests that make "what is deployed" checkable from outside.
+title: Version Contract — Agent, Backend, MCP, Web
+description: One version shape for all shipping components, the ETag-CAS counter blob that mints build numbers, and the published manifests that make "what is deployed" checkable from outside.
 resource: /.github/scripts/Request-BuildNumber.ps1
 tags:
   - build
@@ -13,9 +13,12 @@ timestamp: 2026-07-22T00:00:00+02:00
 
 # Version Contract
 
-Three components ship from this repository — the agent, the Functions backend and the
-MCP server. They share one version shape, one way of minting build numbers, and one
-manifest format, so that a version string means the same thing whoever emits it.
+Four components ship from this repository — the agent, the Functions backend, the
+MCP server and the web portal. They share one version shape, one way of minting build
+numbers, and one manifest format, so that a version string means the same thing
+whoever emits it. The web portal is the commit-only exception: a static export has no
+runtime that could report a `major.minor.build`, so it carries `commit` + `buildUtc`
+alone (no counter blob).
 
 ```
 version   = <major>.<minor>.<build>    major.minor curated by hand, build minted per build
@@ -28,6 +31,7 @@ buildUtc  = ISO-8601 build moment
 | Agent V2 | `VersionPrefix` in `AutopilotMonitor.Agent.V2.csproj` | `agent/buildcounter-v2.txt` | `agent/version.json` |
 | Backend | `VersionPrefix` in `AutopilotMonitor.Functions.csproj` | `versions/backend.txt` | `GET /api/health` |
 | MCP | `version` in `package.json` | `versions/mcp.txt` | `GET /health`, MCP handshake |
+| Web portal | — (commit-only) | — | `GET /version.json` on the portal host |
 
 # Schema
 
@@ -77,7 +81,12 @@ exception: `build.ps1` produces uploadable artifacts and reserves a real number
 ```
 
 The MCP manifest adds `docsCommit`, because for that component "which build" and "which
-documentation" are separate questions.
+documentation" are separate questions. `versions/web.json` carries `component`, `commit`,
+`deployedUtc` and `runId` (no `version`/`buildUtc` — the served `/version.json` holds the
+build moment). The portal's own stamp is generated into `public/version.json` by
+`scripts/generate-version.js` (prebuild) from `GITHUB_SHA`, served with
+`Cache-Control: no-store`, and `deploy-web.yml` polls it until the deployed commit
+matches the pushed SHA before publishing the manifest.
 
 Each is written **last and only after the deploy workflow has polled the component's
 health endpoint until it reports that exact version and commit**. A green deploy step
@@ -104,5 +113,6 @@ remain, being the customer-facing integrity contract.
 
 - `.github/scripts/Request-BuildNumber.ps1` — the CAS protocol
 - `.github/workflows/deploy-backend.yml`, `deploy-mcp.yml` — reserve, verify, publish
+- `.github/workflows/deploy-web.yml`, `src/Web/autopilot-monitor-web/scripts/generate-version.js` — web stamp, verify, publish
 - `.github/workflows/build-agent.yml`, `scripts/Deployment/build.ps1` — agent line
 - [Build Counter Blob](agent/build-counter-blob.md) — agent-specific consequences

infra/mcp-server.bicep

@@ -25,7 +25,7 @@
 //      az deployment group create \
 //        --resource-group <rg-name> \
 //        --template-file infra/mcp-server.bicep \
-//        --parameters apiUrl=https://autopilotmonitor-api.azurewebsites.net \
+//        --parameters apiUrl=https://autopilotmonitor-api-eu.azurewebsites.net \
 //                     entraClientSecret=<secret-value>
 //      This emits `containerAppUrl` as an output (e.g. https://autopilotmonitor-mcp.<env-suffix>.<region>.azurecontainerapps.io).
 //

rules/analyze/ANALYZE-APP-001.json

@@ -5,8 +5,12 @@
   "description": "Detects when a Win32 app detection script fails or returns unexpected results.",
   "severity": "warning",
   "category": "apps",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 60,
   "conditions": [
     {
@@ -34,5 +38,9 @@
       ]
     }
   ],
-  "tags": ["apps", "detection", "win32"]
+  "tags": [
+    "apps",
+    "detection",
+    "win32"
+  ]
 }

rules/analyze/ANALYZE-APP-002.json

@@ -5,8 +5,13 @@
   "description": "Detects app installation failures with specific exit codes or HRESULT error codes and suggests fixes.",
   "severity": "high",
   "category": "apps",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:app_install_failed"
+  ],
   "baseConfidence": 80,
   "conditions": [
     {
@@ -36,5 +41,9 @@
       ]
     }
   ],
-  "tags": ["apps", "msi", "error-code"]
+  "tags": [
+    "apps",
+    "msi",
+    "error-code"
+  ]
 }

rules/analyze/ANALYZE-APP-003.json

@@ -6,6 +6,10 @@
   "severity": "high",
   "category": "apps",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 70,
   "conditions": [
     {
@@ -29,5 +33,9 @@
       ]
     }
   ],
-  "tags": ["apps", "dependency"]
+  "tags": [
+    "apps",
+    "dependency"
+  ],
+  "version": "1.1.0"
 }

rules/analyze/ANALYZE-APP-004.json

@@ -5,8 +5,13 @@
   "description": "Detects when disk space is critically low during enrollment, which can cause app installation failures. Confidence increases when app installations actually failed while disk space was low.",
   "severity": "critical",
   "category": "apps",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:app_install_failed"
+  ],
   "baseConfidence": 75,
   "conditions": [
     {
@@ -36,8 +41,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "app_failed", "condition": "exists", "weight": 15 },
-    { "signal": "enrollment_failed", "condition": "exists", "weight": 10 }
+    {
+      "signal": "app_failed",
+      "condition": "exists",
+      "weight": 15
+    },
+    {
+      "signal": "enrollment_failed",
+      "condition": "exists",
+      "weight": 10
+    }
   ],
   "explanation": "Performance monitoring shows disk free space dropped below 5 GB during enrollment. This can cause app installation failures, especially for large Win32 apps.\n\nIf app installations failed in the same session while free space was low, treat storage exhaustion as the likely contributing cause — the confidence score of this finding is raised accordingly. Verify the individual app failures for their concrete error codes before concluding storage was the only cause.",
   "remediation": [
@@ -58,5 +71,9 @@
       ]
     }
   ],
-  "tags": ["apps", "disk-space", "critical"]
+  "tags": [
+    "apps",
+    "disk-space",
+    "critical"
+  ]
 }

rules/analyze/ANALYZE-APP-005.json

@@ -6,6 +6,10 @@
   "severity": "high",
   "category": "apps",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 70,
   "conditions": [
     {
@@ -29,5 +33,10 @@
       ]
     }
   ],
-  "tags": ["apps", "download", "timeout"]
+  "tags": [
+    "apps",
+    "download",
+    "timeout"
+  ],
+  "version": "1.1.0"
 }

rules/analyze/ANALYZE-APP-006.json

@@ -5,8 +5,12 @@
   "description": "Detects when the same app installation is attempted 3 or more times during one enrollment — a retry loop caused by unhonored reboot requests, repeated failures, or detection mismatches.",
   "severity": "high",
   "category": "apps",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 70,
   "conditions": [
     {
@@ -31,5 +35,10 @@
       ]
     }
   ],
-  "tags": ["apps", "reboot", "retry", "loop"]
+  "tags": [
+    "apps",
+    "reboot",
+    "retry",
+    "loop"
+  ]
 }

rules/analyze/ANALYZE-APP-007.json

@@ -5,7 +5,13 @@
   "description": "Detects when the app tracking summary reports multiple failed app installations.",
   "severity": "high",
   "category": "apps",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:app_install_failed"
+  ],
   "baseConfidence": 75,
   "conditions": [
     {
@@ -16,10 +22,22 @@
       "operator": "gte",
       "value": "2",
       "required": true
+    },
+    {
+      "signal": "enrollment_failed",
+      "source": "event_type",
+      "eventType": "enrollment_failed",
+      "operator": "exists",
+      "value": "",
+      "required": false
     }
   ],
   "confidenceFactors": [
-    { "signal": "enrollment_failed", "condition": "exists", "weight": 15 }
+    {
+      "signal": "enrollment_failed",
+      "condition": "exists",
+      "weight": 15
+    }
   ],
   "explanation": "The app tracking summary reports 2 or more failed app installations during enrollment. This suggests a systemic issue rather than an isolated app failure.",
   "remediation": [
@@ -32,5 +50,9 @@
       ]
     }
   ],
-  "tags": ["apps", "summary", "multiple-failures"]
+  "tags": [
+    "apps",
+    "summary",
+    "multiple-failures"
+  ]
 }

rules/analyze/ANALYZE-APP-008.json

@@ -6,6 +6,10 @@
   "severity": "warning",
   "category": "apps",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 70,
   "conditions": [
     {
@@ -28,5 +32,11 @@
       ]
     }
   ],
-  "tags": ["apps", "performance", "slow-install", "warning"]
+  "tags": [
+    "apps",
+    "performance",
+    "slow-install",
+    "warning"
+  ],
+  "version": "1.1.0"
 }

rules/analyze/ANALYZE-APP-012.json

@@ -6,6 +6,10 @@
   "severity": "warning",
   "category": "apps",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "correlation",
   "baseConfidence": 80,
   "conditions": [
@@ -34,7 +38,17 @@
     }
   ],
   "relatedDocs": [
-    { "title": "Win32 app return codes in Intune", "url": "https://learn.microsoft.com/en-us/mem/intune/apps/apps-win32-app-management#step-4-return-codes" }
+    {
+      "title": "Win32 app return codes in Intune",
+      "url": "https://learn.microsoft.com/en-us/mem/intune/apps/apps-win32-app-management#step-4-return-codes"
+    }
   ],
-  "tags": ["apps", "enforcement", "exit-code", "unmapped", "resolved"]
+  "tags": [
+    "apps",
+    "enforcement",
+    "exit-code",
+    "unmapped",
+    "resolved"
+  ],
+  "version": "1.1.0"
 }

rules/analyze/ANALYZE-APP-013.json

@@ -5,8 +5,12 @@
   "description": "Detects when the Enrollment Status Page failed because Intune could not verify an app was installed (HRESULT 0x87D1041C). The installer ran but the detection rule did not match afterwards.",
   "severity": "critical",
   "category": "apps",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 90,
   "preconditions": [
     {
@@ -69,8 +73,20 @@
     }
   ],
   "relatedDocs": [
-    { "title": "Microsoft Learn: Troubleshoot Windows Autopilot ESP error codes", "url": "https://learn.microsoft.com/en-us/autopilot/troubleshoot-tsg" },
-    { "title": "Win32 app detection rules in Intune", "url": "https://learn.microsoft.com/en-us/mem/intune/apps/apps-win32-add#step-4-detection-rules" }
+    {
+      "title": "Microsoft Learn: Troubleshoot Windows Autopilot ESP error codes",
+      "url": "https://learn.microsoft.com/en-us/autopilot/troubleshoot-tsg"
+    },
+    {
+      "title": "Win32 app detection rules in Intune",
+      "url": "https://learn.microsoft.com/en-us/mem/intune/apps/apps-win32-add#step-4-detection-rules"
+    }
   ],
-  "tags": ["apps", "detection", "esp", "0x87d1041c", "intune"]
+  "tags": [
+    "apps",
+    "detection",
+    "esp",
+    "0x87d1041c",
+    "intune"
+  ]
 }

rules/analyze/ANALYZE-APP-014.json

@@ -5,8 +5,12 @@
   "description": "Detects when the Enrollment Status Page failed on the Apps subcategory and the agent's AppX deployment log scan identified a suspected MSIX/Store package. Store/MSIX apps install outside the Win32 pipeline, so the regular per-app tracking sees nothing — this correlation names the likely culprit.",
   "severity": "warning",
   "category": "apps",
-  "version": "1.0.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 75,
   "preconditions": [
     {
@@ -35,6 +39,51 @@
       "operator": "regex",
       "value": "^0x80073[cd]",
       "required": false
+    },
+    {
+      "signal": "appx_esp_category",
+      "source": "event_data",
+      "eventType": "esp_appx_failure_analysis",
+      "dataField": "espCategory",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "appx_esp_errorcode",
+      "source": "event_data",
+      "eventType": "esp_appx_failure_analysis",
+      "dataField": "espErrorCode",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "appx_top_candidate_package",
+      "source": "event_data",
+      "eventType": "esp_appx_failure_analysis",
+      "dataField": "topCandidatePackage",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "appx_candidate_count",
+      "source": "event_data",
+      "eventType": "esp_appx_failure_analysis",
+      "dataField": "candidateCount",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "appx_scan_confidence",
+      "source": "event_data",
+      "eventType": "esp_appx_failure_analysis",
+      "dataField": "confidence",
+      "operator": "exists",
+      "value": "",
+      "required": false
     }
   ],
   "explanation": "The ESP **{{espCategory}}/Apps** subcategory failed with HRESULT **{{espErrorCode}}** — an error from the AppX/MSIX deployment stack, i.e. a **Microsoft Store / MSIX app**, not a Win32 app. These apps install via the EnterpriseModernAppManagement CSP and never appear in the IME Win32 sidecar logs, which is why all tracked Win32/WinGet apps in this session can look green while ESP still reports an Apps failure.\n\nThe agent scanned the AppXDeploymentServer event log during the failure settle window and identified **{{topCandidatePackageName}}** (package `{{topCandidatePackage}}`) as the most likely culprit — its deployment error matches the ESP failure code ({{candidateCount}} candidate(s) total, confidence: {{confidence}}).\n\n**This is a correlation-based assessment, not a confirmed root cause** — validate against the AppXDeploymentServer/Operational event log on the device or in the diagnostics archive before acting.",
@@ -65,8 +114,21 @@
     }
   ],
   "relatedDocs": [
-    { "title": "Microsoft Learn: Troubleshoot Windows Autopilot ESP error codes", "url": "https://learn.microsoft.com/en-us/autopilot/troubleshoot-tsg" },
-    { "title": "Add Microsoft Store apps to Intune", "url": "https://learn.microsoft.com/en-us/mem/intune/apps/store-apps-microsoft" }
+    {
+      "title": "Microsoft Learn: Troubleshoot Windows Autopilot ESP error codes",
+      "url": "https://learn.microsoft.com/en-us/autopilot/troubleshoot-tsg"
+    },
+    {
+      "title": "Add Microsoft Store apps to Intune",
+      "url": "https://learn.microsoft.com/en-us/mem/intune/apps/store-apps-microsoft"
+    }
   ],
-  "tags": ["apps", "appx", "msix", "store", "esp", "0x80073cf9"]
+  "tags": [
+    "apps",
+    "appx",
+    "msix",
+    "store",
+    "esp",
+    "0x80073cf9"
+  ]
 }

rules/analyze/ANALYZE-APP-015.json

@@ -0,0 +1,80 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-APP-015",
+  "title": "Required App Never Settled — ESP Completion Deferred",
+  "description": "The IME reported its user-session completion line, but at least one required app stayed pending — without ever failing or even starting to install — so the agent kept deferring the enrollment completion signal. Typically an assignment/requirement problem (requirement rules never met, dependency never satisfied, or the app needs a context that is not available during ESP, e.g. a VPN client waiting for user sign-in to a portal).",
+  "severity": "high",
+  "category": "apps",
+  "version": "1.0.0",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "trigger": "correlation",
+  "baseConfidence": 60,
+  "confidenceThreshold": 55,
+  "preconditions": [
+    {
+      "source": "event_data",
+      "eventType": "enrollment_complete",
+      "operator": "not_exists",
+      "description": "Suppress when the pending app eventually settled and the enrollment completed — a transient deferral is normal."
+    },
+    {
+      "source": "event_data",
+      "eventType": "enrollment_failed",
+      "operator": "not_exists",
+      "description": "Suppress when the session failed explicitly — the app/ESP failure rules already cover that path; this rule targets the never-finishing case."
+    }
+  ],
+  "conditions": [
+    {
+      "signal": "completion_deferred",
+      "source": "event_type",
+      "eventType": "agent_trace",
+      "dataField": "message",
+      "operator": "contains",
+      "value": "completion signal deferred",
+      "required": true
+    },
+    {
+      "signal": "apps_pending",
+      "source": "event_data",
+      "eventType": "app_tracking_summary",
+      "dataField": "pending",
+      "operator": "gte",
+      "value": "1",
+      "required": true
+    },
+    {
+      "signal": "pending_app_names",
+      "source": "event_data",
+      "eventType": "app_tracking_summary",
+      "dataField": "pendingNames",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [
+    { "signal": "pending_app_names", "condition": "exists", "weight": 5 }
+  ],
+  "explanation": "The Intune Management Extension wrote its user-session completion line, but the agent observed `{{pending}}` required app(s) still pending (`{{pendingNames}}`) and therefore **deferred the enrollment completion signal** — repeatedly, if this happened across several logons or reboots.\n\nA pending app that never transitions to downloading/installing and never fails is almost always an **assignment or requirement problem**, not an install error:\n\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 targeted as *required* for the user ESP that needs something unavailable during provisioning (e.g. a VPN client whose portal sign-in only happens after first logon),\n- user-targeted apps on a device where the user identity never fully registered (see the hybrid user-affinity rule if it also fired).",
+  "remediation": [
+    {
+      "title": "Identify and unblock the pending app",
+      "steps": [
+        "Check the app names listed in this finding's evidence (pendingNames) — these are the apps the ESP is waiting for.",
+        "In Intune, review the app's requirement rules and dependencies; test them on the device (IntuneManagementExtension.log logs each requirement evaluation).",
+        "Decide whether the app really must block the ESP: removing it from the ESP's 'blocking apps' list (or making it not-required during enrollment) unblocks completion immediately.",
+        "If the app is user-targeted on a hybrid-joined device, verify the user's Entra affinity first — without a signed-in Entra user, user-targeted policy never applies."
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Microsoft Learn: Enrollment Status Page — blocking apps",
+      "url": "https://learn.microsoft.com/en-us/intune/intune-service/enrollment/windows-enrollment-status"
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": ["apps", "esp", "completion", "assignment", "pending"]
+}

rules/analyze/ANALYZE-CORR-003.json

@@ -5,8 +5,13 @@
   "description": "Correlates an active proxy configuration with app content download failures (Delivery Optimization timeout or download error), suggesting the proxy is blocking or throttling Intune content delivery.",
   "severity": "high",
   "category": "apps",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:app_install_failed"
+  ],
   "trigger": "correlation",
   "baseConfidence": 60,
   "conditions": [
@@ -30,8 +35,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "app_install_failed", "condition": "count >= 2", "weight": 15 },
-    { "signal": "enrollment_failed", "condition": "count >= 1", "weight": 10 }
+    {
+      "signal": "app_install_failed",
+      "condition": "count >= 2",
+      "weight": 15
+    },
+    {
+      "signal": "enrollment_failed",
+      "condition": "count >= 1",
+      "weight": 10
+    }
   ],
   "confidenceThreshold": 50,
   "explanation": "A proxy (explicit or PAC-based) is configured on this device and app content downloads failed (Delivery Optimization timeout or download content error). Proxies can block or throttle downloads from *.delivery.mp.microsoft.com and other Intune CDN endpoints.\n\nThis is a common root cause when app downloads fail consistently on proxy-connected corporate networks. Note this rule only fires when the failure is download-related — generic app install errors behind a proxy do not trigger it.",
@@ -54,5 +67,12 @@
       ]
     }
   ],
-  "tags": ["correlation", "apps", "proxy", "network", "download", "root-cause"]
+  "tags": [
+    "correlation",
+    "apps",
+    "proxy",
+    "network",
+    "download",
+    "root-cause"
+  ]
 }

rules/analyze/ANALYZE-DEV-002.json

@@ -5,8 +5,12 @@
   "description": "Detects when memory usage stays above 90% across at least 3 performance snapshots during enrollment, indicating sustained memory pressure that can cause app installation failures or system instability.",
   "severity": "warning",
   "category": "device",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 55,
   "conditions": [
     {
@@ -38,8 +42,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "app_failed", "condition": "exists", "weight": 20 },
-    { "signal": "enrollment_failed", "condition": "exists", "weight": 15 }
+    {
+      "signal": "app_failed",
+      "condition": "exists",
+      "weight": 20
+    },
+    {
+      "signal": "enrollment_failed",
+      "condition": "exists",
+      "weight": 15
+    }
   ],
   "explanation": "Memory usage exceeded 90% in at least 3 performance snapshots during this enrollment — sustained pressure, not a single transient spike. Persistent high memory usage can cause app installation failures, system slowdowns, and ESP timeouts, especially on devices with 8 GB RAM installing several apps concurrently.",
   "remediation": [
@@ -53,5 +65,9 @@
       ]
     }
   ],
-  "tags": ["device", "memory", "performance"]
+  "tags": [
+    "device",
+    "memory",
+    "performance"
+  ]
 }

rules/analyze/ANALYZE-DEV-003.json

@@ -5,8 +5,12 @@
   "description": "Detects devices enrolling with an OS build that has reached end of support: Windows 11 22H2 (build 22621) or older, which includes every Windows 10 build. Maintenance note: raise the build cutoff to 22631 after Windows 11 23H2 reaches end of support on 2026-11-10.",
   "severity": "warning",
   "category": "device",
-  "version": "2.0.0",
+  "version": "2.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 90,
   "conditions": [
     {
@@ -52,5 +56,11 @@
       "url": "https://learn.microsoft.com/en-us/lifecycle/products/windows-11-home-and-pro"
     }
   ],
-  "tags": ["device", "os-version", "end-of-support", "windows-11", "windows-10"]
+  "tags": [
+    "device",
+    "os-version",
+    "end-of-support",
+    "windows-11",
+    "windows-10"
+  ]
 }

rules/analyze/ANALYZE-DEV-004.json

@@ -5,8 +5,13 @@
   "description": "Detects a Windows quality/cumulative update that FAILED to install during the OOBE / ESP enrollment window (WindowsUpdateClient EventID 20). A cumulative update failing mid-OOBE is a known cause of enrollment errors and is otherwise invisible in the Intune console.",
   "severity": "high",
   "category": "device",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:windows_update_failed"
+  ],
   "trigger": "single",
   "baseConfidence": 70,
   "confidenceThreshold": 60,
@@ -65,8 +70,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "enrollment_failed", "condition": "exists", "weight": 20 },
-    { "signal": "reboot_pending", "condition": "exists", "weight": 10 }
+    {
+      "signal": "enrollment_failed",
+      "condition": "exists",
+      "weight": 20
+    },
+    {
+      "signal": "reboot_pending",
+      "condition": "exists",
+      "weight": 10
+    }
   ],
   "explanation": "A Windows Update failed to install during enrollment: **{{updateTitle}}** (error {{hresult}} {{hresultSymbol}}). Windows can install quality/cumulative updates during OOBE (the \"Getting updates\" screen and the ESP \"Install Windows quality updates during OOBE\" option). When one of these fails mid-enrollment it can leave the device in an inconsistent state, force an unexpected reboot, or block the Enrollment Status Page — a failure mode that is otherwise only discoverable by deep manual digging on the device.",
   "remediation": [
@@ -87,5 +100,10 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["device", "windows-update", "oobe", "servicing"]
+  "tags": [
+    "device",
+    "windows-update",
+    "oobe",
+    "servicing"
+  ]
 }

rules/analyze/ANALYZE-DEV-005.json

@@ -5,8 +5,12 @@
   "description": "Informational: a Windows quality/cumulative update installed during the OOBE / ESP enrollment window (WindowsUpdateClient EventID 19). Surfaces updates applied mid-enrollment — useful context when correlating enrollment duration, reboots, or later issues with a specific KB.",
   "severity": "info",
   "category": "device",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 60,
   "confidenceThreshold": 50,
@@ -39,7 +43,11 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "reboot_pending", "condition": "exists", "weight": 15 }
+    {
+      "signal": "reboot_pending",
+      "condition": "exists",
+      "weight": 15
+    }
   ],
   "explanation": "One or more Windows updates installed during enrollment (e.g. **{{updateTitle}}**). This is normal when Windows Update runs during OOBE, but it extends enrollment time and can trigger a reboot mid-ESP. Track it when correlating enrollment duration or reboot count with a specific cumulative update, or when a device behaves differently after a particular KB landed during provisioning.",
   "remediation": [
@@ -53,5 +61,9 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["device", "windows-update", "oobe"]
+  "tags": [
+    "device",
+    "windows-update",
+    "oobe"
+  ]
 }

rules/analyze/ANALYZE-DEV-006.json

@@ -5,8 +5,12 @@
   "description": "Informational: the OS build (CurrentBuild.UBR) changed across a reboot during enrollment — an update was installed, regardless of which servicing path delivered it. Deterministic corroboration that works even when the Windows Update event channel shows nothing (registry comparison across restart cannot be lost to timing or logging-path differences).",
   "severity": "info",
   "category": "device",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 70,
   "confidenceThreshold": 50,
@@ -47,7 +51,11 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "wu_channel_blind", "condition": "exists", "weight": 10 }
+    {
+      "signal": "wu_channel_blind",
+      "condition": "exists",
+      "weight": 10
+    }
   ],
   "explanation": "The OS build changed from **{{previousBuild}}** to **{{currentBuild}}** across a reboot during enrollment — a Windows update was installed mid-provisioning. This is normal when quality updates run during OOBE, but it adds a reboot and extends enrollment time. If a windows_update_channel_census event is also present, the update installed via a servicing path the Windows Update watcher does not capture yet — its EventID histogram tells which IDs to enable.",
   "remediation": [
@@ -61,5 +69,10 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["device", "windows-update", "oobe", "reboot"]
+  "tags": [
+    "device",
+    "windows-update",
+    "oobe",
+    "reboot"
+  ]
 }

rules/analyze/ANALYZE-DEV-007.json

@@ -5,9 +5,13 @@
   "description": "The device's real-time clock deviates from NTP by more than two minutes. Microsoft documents that a clock off by several minutes causes TPM attestation errors (self-deploying/pre-provisioning) and ESP timeouts. Knowledge source: docs/agent/autopilot-ztd-diagnostics.md.",
   "severity": "warning",
   "category": "device",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 55,
   "confidenceThreshold": 50,
@@ -55,5 +59,12 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["device", "ntp", "clock-skew", "tpm", "esp", "known-issue"]
+  "tags": [
+    "device",
+    "ntp",
+    "clock-skew",
+    "tpm",
+    "esp",
+    "known-issue"
+  ]
 }

rules/analyze/ANALYZE-ENRL-002.json

@@ -5,7 +5,7 @@
   "description": "Detects when the enrollment session was force-failed by the server-side inactivity timeout (no agent telemetry for the configured SessionTimeoutHours window) without ever completing or explicitly failing.",
   "severity": "high",
   "category": "enrollment",
-  "version": "1.0.0",
+  "version": "1.2.0",
   "enabled": true,
   "baseConfidence": 80,
   "preconditions": [
@@ -30,9 +30,35 @@
       "operator": "exists",
       "value": "",
       "required": true
+    },
+    {
+      "signal": "timeoutHours",
+      "source": "event_data",
+      "eventType": "session_timeout",
+      "dataField": "timeoutHours",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "desktop_was_reached",
+      "source": "event_type",
+      "eventType": "desktop_arrived",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    },
+    {
+      "signal": "all_tracked_apps_completed",
+      "source": "event_data",
+      "eventType": "app_tracking_summary",
+      "dataField": "isAllCompleted",
+      "operator": "equals",
+      "value": "true",
+      "required": false
     }
   ],
-  "explanation": "The enrollment session was force-failed by the server-side maintenance sweep after `{{timeoutHours}}` hour(s) of agent inactivity — the device stopped sending telemetry and never reported completion or an explicit failure.\n\nThis usually means the agent process died or the device went offline mid-enrollment (power off, network loss, bluescreen, reimage) rather than a clean enrollment failure. Because there is no terminal `enrollment_failed` event, the more specific app/ESP rules cannot pinpoint a cause — the evidence simply stops at the last event before the gap.",
+  "explanation": "The enrollment session was force-failed by the server-side maintenance sweep after `{{timeoutHours}}` hour(s) of agent inactivity — the device stopped sending telemetry and never reported completion or an explicit failure.\n\nThis usually means the agent process died or the device went offline mid-enrollment (power off, network loss, bluescreen, reimage) rather than a clean enrollment failure. Because there is no terminal `enrollment_failed` event, the more specific app/ESP rules cannot pinpoint a cause — the evidence simply stops at the last event before the gap.\n\n**If the evidence shows the user desktop was reached and all tracked apps completed**, the device most likely got all its content but the ESP never signaled completion — on hybrid-joined devices the usual culprit is the user session never establishing Entra affinity (Account Setup re-running on every logon). Check whether the hybrid user-affinity finding also fired for this session.",
   "remediation": [
     {
       "title": "Investigate the silent session",
@@ -43,6 +69,13 @@
         "If the device is reachable, collect the agent + IME logs and re-run enrollment, correlating with the timeout timestamp",
         "If many sessions time out in the same window, check for a tenant-wide network/connectivity issue or an Intune service incident"
       ]
+    },
+    {
+      "title": "Desktop reached and apps done, but no completion",
+      "steps": [
+        "Sign in as the affected user and run dsregcmd /status — 'SSO State: AzureAdPrt' must be YES; NO means the user never registered with Entra and the Account Setup ESP will loop",
+        "Verify Entra Connect syncs both the computer object (userCertificate) and the signing-in user, and that the user's UPN suffix is a verified Entra domain"
+      ]
     }
   ],
   "tags": ["enrollment", "timeout", "stalled"]

rules/analyze/ANALYZE-ENRL-003.json

@@ -5,9 +5,14 @@
   "description": "A TPM-attestation-related error code documented in the Microsoft Autopilot known-issues list was observed (0x800705B4, 0x801C03EA, 0x81039001, 0x81039023, 0x81039024, 0x80070490). These block self-deploying and pre-provisioning deployments during 'Securing your hardware'. Observability: attestation precedes MDM enrollment, so in the normal deployment model (agent installed via IME after enrollment) these codes are rarely visible — the rule primarily serves bootstrap-token deployments. See docs/agent/autopilot-ztd-diagnostics.md (Observability section).",
   "severity": "high",
   "category": "enrollment",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed",
+    "on_event:modern_deployment_error"
+  ],
   "trigger": "single",
   "baseConfidence": 60,
   "confidenceThreshold": 55,
@@ -75,5 +80,12 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["enrollment", "tpm", "attestation", "self-deploying", "pre-provisioning", "known-issue"]
+  "tags": [
+    "enrollment",
+    "tpm",
+    "attestation",
+    "self-deploying",
+    "pre-provisioning",
+    "known-issue"
+  ]
 }

rules/analyze/ANALYZE-ENRL-004.json

@@ -5,9 +5,13 @@
   "description": "An enrollment-blocking error code documented in the Microsoft Autopilot known-issues/troubleshooting pages was observed (0x80180014, 0x80180018, 0xC1036501, 0x801C03F3, 0x80070774). Each has a specific, documented cause and fix. Observability: a blocked MDM enrollment normally means no agent gets installed at all (IME install happens after enrollment) — this rule can realistically only fire for bootstrap-token deployments (pre-MDM reporting) or mixed retry scenarios. See docs/agent/autopilot-ztd-diagnostics.md (Observability section).",
   "severity": "high",
   "category": "enrollment",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 60,
   "confidenceThreshold": 55,
@@ -74,5 +78,11 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["enrollment", "mdm", "known-issue", "entra-id", "hybrid-join"]
+  "tags": [
+    "enrollment",
+    "mdm",
+    "known-issue",
+    "entra-id",
+    "hybrid-join"
+  ]
 }

rules/analyze/ANALYZE-ENRL-005.json

@@ -5,9 +5,13 @@
   "description": "A Microsoft Entra hybrid join Autopilot deployment hit error 0x80004005 — a documented build-dependent known issue, resolved by KB5065789 (25H2, build >= 26200.6725), KB5065426 (24H2, build >= 26100.6584), and KB5070312 (23H2, build >= 22631.6276). Knowledge source: docs/agent/autopilot-ztd-diagnostics.md (error-code map).",
   "severity": "high",
   "category": "enrollment",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "correlation",
   "baseConfidence": 25,
   "confidenceThreshold": 60,
@@ -59,10 +63,26 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "e_fail_esp_failure", "condition": "exists", "weight": 40 },
-    { "signal": "e_fail_esp_advisory", "condition": "exists", "weight": 35 },
-    { "signal": "e_fail_modern_deployment", "condition": "exists", "weight": 40 },
-    { "signal": "e_fail_error_detected", "condition": "exists", "weight": 35 }
+    {
+      "signal": "e_fail_esp_failure",
+      "condition": "exists",
+      "weight": 40
+    },
+    {
+      "signal": "e_fail_esp_advisory",
+      "condition": "exists",
+      "weight": 35
+    },
+    {
+      "signal": "e_fail_modern_deployment",
+      "condition": "exists",
+      "weight": 40
+    },
+    {
+      "signal": "e_fail_error_detected",
+      "condition": "exists",
+      "weight": 35
+    }
   ],
   "explanation": "This is a **Microsoft Entra hybrid join** deployment that hit error **0x80004005** — a documented, build-dependent Autopilot known issue where hybrid deployments time out.\n\nThe issue is fixed by Windows cumulative updates:\n\n- Windows 11 **25H2**: KB5065789 — fixed from build **26200.6725**\n- Windows 11 **24H2**: KB5065426 — fixed from build **26100.6584**\n- Windows 11 **23H2**: KB5070312 — fixed from build **22631.6276**\n\nCompare this session's OS build (see the Session Info card / os_info event) against the fixed-build threshold for its version. If the device booted with an older build, updating the deployment image (or installing quality updates during OOBE) resolves the timeout. Note that 0x80004005 is a generic failure code (E_FAIL) — if the build is already at or above the fixed threshold, investigate the Intune Connector for Active Directory and domain-controller connectivity instead.",
   "remediation": [
@@ -83,5 +103,11 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["enrollment", "hybrid-join", "known-issue", "windows-update", "esp"]
+  "tags": [
+    "enrollment",
+    "hybrid-join",
+    "known-issue",
+    "windows-update",
+    "esp"
+  ]
 }

rules/analyze/ANALYZE-ESP-001.json

@@ -5,8 +5,12 @@
   "description": "Detects when the DeviceSetup phase of the ESP took longer than 30 minutes, indicating a stuck or very slow blocking app. Confidence increases when the phase exceeds 60 minutes.",
   "severity": "high",
   "category": "esp",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 50,
   "conditions": [
     {
@@ -20,8 +24,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "long_esp", "condition": "phase_duration > 1800", "weight": 40 },
-    { "signal": "very_long_esp", "condition": "phase_duration > 3600", "weight": 15 }
+    {
+      "signal": "long_esp",
+      "condition": "phase_duration > 1800",
+      "weight": 40
+    },
+    {
+      "signal": "very_long_esp",
+      "condition": "phase_duration > 3600",
+      "weight": 15
+    }
   ],
   "confidenceThreshold": 70,
   "explanation": "The ESP DeviceSetup phase took more than 30 minutes. This indicates a blocking app is stuck installing, downloading very slowly, or has entered a retry loop. A duration beyond 60 minutes raises the confidence further — at that point the enrollment is almost certainly held by a single stuck blocking item rather than ordinary slowness.",
@@ -35,5 +47,10 @@
       ]
     }
   ],
-  "tags": ["esp", "blocking", "timeout", "duration"]
+  "tags": [
+    "esp",
+    "blocking",
+    "timeout",
+    "duration"
+  ]
 }

rules/analyze/ANALYZE-ESP-002.json

@@ -5,9 +5,13 @@
   "description": "Detects when the Certificates subcategory of the Enrollment Status Page reported a failure, even if the enrollment later appears to have succeeded. Users can click 'Continue anyway' on an ESP error, which masks the underlying certificate provisioning failure — this rule surfaces the transition so it stays visible.",
   "severity": "high",
   "category": "esp",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 80,
   "conditions": [
@@ -54,5 +58,10 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["esp", "certificates", "subcategory", "silent-failure"]
+  "tags": [
+    "esp",
+    "certificates",
+    "subcategory",
+    "silent-failure"
+  ]
 }

rules/analyze/ANALYZE-ESP-005.json

@@ -5,9 +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": "1.1.0",
+  "version": "1.2.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 70,
   "conditions": [
@@ -47,8 +51,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "multiple_reboot_uris", "condition": "exists", "weight": 10 },
-    { "signal": "omadm_reboot_flag_set", "condition": "exists", "weight": 15 }
+    {
+      "signal": "multiple_reboot_uris",
+      "condition": "exists",
+      "weight": 10
+    },
+    {
+      "signal": "omadm_reboot_flag_set",
+      "condition": "exists",
+      "weight": 15
+    }
   ],
   "confidenceThreshold": 70,
   "explanation": "This session **rebooted during enrollment**, and Windows flagged one or more device-assigned MDM policies as **reboot-required** — the classic cause of the coalesced mid-ESP restart and the unexpected **second sign-in screen** before AccountSetup.\n\nFirst reboot-forcing policy URI: `{{firstRebootUri}}`\n\nThe complete URI list is in the `mdm_policy_reboot_required` timeline event (`rebootUris`). Policies applied DURING ESP DeviceSetup are coalesced into one forced restart at the end of DeviceSetup; the same flags raised later (e.g. user-policy sync in AccountSetup) have no immediate effect — this advisory only fires when a reboot was actually observed.\n\nThis is expected OS behavior, not a failure — but it degrades the enrollment experience, confuses users, and is invisible in the Intune console.",
@@ -81,5 +93,12 @@
     }
   ],
   "markSessionAsFailedDefault": false,
-  "tags": ["esp", "reboot", "coalescing", "second-sign-in", "policy-attribution", "user-experience"]
+  "tags": [
+    "esp",
+    "reboot",
+    "coalescing",
+    "second-sign-in",
+    "policy-attribution",
+    "user-experience"
+  ]
 }

rules/analyze/ANALYZE-ESP-006.json

@@ -5,8 +5,12 @@
   "description": "Detects the recovery story: the ESP reported a terminal failure (typically DeviceSetup/Apps), the user most likely pressed 'Try again' on the failure page, the failed step re-ran and completed successfully. The earlier failure did not stick — the enrollment continued past it.",
   "severity": "info",
   "category": "esp",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 85,
   "conditions": [
     {
@@ -71,8 +75,16 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "retry", "condition": "exists", "weight": 10 },
-    { "signal": "likelyCulpritApps", "condition": "exists", "weight": 5 }
+    {
+      "signal": "retry",
+      "condition": "exists",
+      "weight": 10
+    },
+    {
+      "signal": "likelyCulpritApps",
+      "condition": "exists",
+      "weight": 5
+    }
   ],
   "explanation": "The Enrollment Status Page reported a **failure** in the `{{category}}` phase (`{{failedSubcategory}}` subcategory, most likely app(s): `{{likelyCulpritApps}}`) — and then **recovered**: the failed step left its failed state and completed successfully about `{{minutesSinceFailure}}` min later.\n\nThat pattern is consistent with the user pressing **'Try again'** on the ESP failure page (the profile allows failure-page actions; the agent cannot observe the click itself). The failure the user saw was real, but it did not stick — the ESP re-ran the step, it succeeded, and the enrollment continued.\n\nRead the session timeline as one arc: `esp_failure_advisory` (the failure, with the likely culprit app) → `esp_failure_retry_detected` (the retry) → `esp_failure_recovered` (the recovery). If this pattern repeats across devices for the same app, that app's install is flaky on first attempt — fix the app rather than the devices. Any literal `{{…}}` placeholder means that detail was not recorded for this session.",
   "remediation": [
@@ -86,5 +98,12 @@
       ]
     }
   ],
-  "tags": ["esp", "recovery", "try-again", "retry", "continue-anyway", "enrollment"]
+  "tags": [
+    "esp",
+    "recovery",
+    "try-again",
+    "retry",
+    "continue-anyway",
+    "enrollment"
+  ]
 }

rules/analyze/ANALYZE-ID-001.json

@@ -7,7 +7,11 @@
   "category": "identity",
   "isCommunity": true,
   "enabled": false,
-  "version": "1.2.0",
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
+  "version": "1.3.0",
   "baseConfidence": 75,
   "conditions": [
     {
@@ -50,7 +54,12 @@
       ]
     }
   ],
-  "tags": ["identity", "certificates", "machine-store", "subject-check"],
+  "tags": [
+    "identity",
+    "certificates",
+    "machine-store",
+    "subject-check"
+  ],
   "templateVariables": [
     {
       "name": "cert_subject",

rules/analyze/ANALYZE-ID-002.json

@@ -5,9 +5,13 @@
   "description": "Detects when the LocalAdminAnalyzer flags unexpected local user accounts or profile directories on the device. This is a known Autopilot bypass technique where admin accounts are created before or during enrollment to gain persistent local admin access.",
   "severity": "high",
   "category": "identity",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 60,
   "conditions": [
@@ -81,5 +85,10 @@
     }
   ],
   "relatedDocs": [],
-  "tags": ["identity", "security", "local-admin", "bypass-detection"]
+  "tags": [
+    "identity",
+    "security",
+    "local-admin",
+    "bypass-detection"
+  ]
 }

rules/analyze/ANALYZE-ID-003.json

@@ -5,9 +5,13 @@
   "description": "Fires when the vulnerability correlation finds critical-severity CVEs or CISA KEV entries in installed software. This indicates the device has software with known, actively exploited vulnerabilities.",
   "severity": "critical",
   "category": "security",
-  "version": "1.0.1",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 90,
   "conditions": [
@@ -31,7 +35,11 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "kev_matches", "condition": "exists", "weight": 10 }
+    {
+      "signal": "kev_matches",
+      "condition": "exists",
+      "weight": 10
+    }
   ],
   "confidenceThreshold": 80,
   "explanation": "The device has installed software with critical vulnerabilities. Software with CVEs rated CRITICAL (CVSS >= 9.0) or listed in the CISA Known Exploited Vulnerabilities catalog was detected. These vulnerabilities are actively targeted by attackers and should be remediated immediately.",
@@ -64,5 +72,11 @@
       "url": "https://nvd.nist.gov/"
     }
   ],
-  "tags": ["vulnerability", "cve", "kev", "critical", "security"]
+  "tags": [
+    "vulnerability",
+    "cve",
+    "kev",
+    "critical",
+    "security"
+  ]
 }

rules/analyze/ANALYZE-ID-004.json

@@ -0,0 +1,101 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-ID-004",
+  "title": "Hybrid Sign-In Never Establishes Entra User Affinity",
+  "description": "On a hybrid-joined device the real user reached the desktop, but the Autopilot provisioning placeholder stayed active in JoinInfo and the agent repeatedly reported the hybrid sign-in as overdue. The user session never establishes Entra user affinity (no PRT), so the Account Setup ESP re-runs on every logon and the enrollment never completes.",
+  "severity": "high",
+  "category": "identity",
+  "version": "1.2.0",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "trigger": "correlation",
+  "evaluateOn": ["enrollment_end", "on_event:hybrid_login_pending"],
+  "baseConfidence": 60,
+  "confidenceThreshold": 75,
+  "preconditions": [
+    {
+      "source": "event_data",
+      "eventType": "enrollment_complete",
+      "operator": "not_exists",
+      "description": "Suppress when the session eventually completed — a single overdue-login warning followed by a successful sign-in is normal hybrid latency, not a broken affinity."
+    }
+  ],
+  "conditions": [
+    {
+      "signal": "hybrid_login_overdue",
+      "source": "event_type",
+      "eventType": "hybrid_login_pending",
+      "operator": "exists",
+      "value": "",
+      "required": true
+    },
+    {
+      "signal": "user_desktop_reached",
+      "source": "event_type",
+      "eventType": "desktop_arrived",
+      "operator": "exists",
+      "value": "",
+      "required": true
+    },
+    {
+      "signal": "placeholder_still_active",
+      "source": "event_type",
+      "eventType": "aad_placeholder_user_detected",
+      "operator": "exists",
+      "value": "",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [
+    { "signal": "hybrid_login_pending", "condition": "count >= 2", "weight": 20 },
+    { "signal": "hybrid_login_pending", "condition": "count >= 3", "weight": 10 },
+    { "signal": "aad_placeholder_user_detected", "condition": "count >= 3", "weight": 10 }
+  ],
+  "explanation": "A real user signed in and reached the desktop, but the device kept reporting the **Autopilot provisioning placeholder** as the active identity in JoinInfo and the hybrid sign-in as **overdue** — across multiple reboots. This means the signed-in user never established **Microsoft Entra user affinity** (no Primary Refresh Token), so:\n\n- the Account Setup ESP page re-appears on every logon,\n- user-targeted required apps and policies cannot settle,\n- the enrollment never reaches completion.\n\nAfter this many hours this is not normal Entra Connect sync latency — something is structurally preventing the user (or the computer object) from registering:\n\n- the computer object's `userCertificate` attribute is not syncing to Entra ID (sync scope / OU filtering),\n- the signing-in user is not synced, or their UPN does not match a verified Entra domain,\n- the device has no line of sight to a domain controller **at logon time**, so the hybrid PRT flow cannot finish,\n- time skew or a proxy blocking `login.microsoftonline.com` / `enterpriseregistration.windows.net` from the user context.\n\nA frequent variant: the user's **first sign-in happens without domain-controller reachability** — for example when a pre-logon VPN tunnel (GlobalProtect, Always On VPN, Zscaler ZPA) is not established yet at the logon screen. Windows falls back to cached credentials, the hybrid PRT flow silently never runs, and later reboots do not fix it — sessions in this state typically show repeated reboots and network flapping while the placeholder identity stays active.\n\nA visible side effect: **the Windows Hello for Business wizard never appears**, because Hello provisioning requires an Entra user token (PRT). Hello is a downstream symptom here, not the cause.",
+  "remediation": [
+    {
+      "title": "Verify user affinity on the device",
+      "steps": [
+        "Sign in as the affected user and run: dsregcmd /status — under 'SSO State' the value AzureAdPrt must be YES. NO means the user has no Entra token and this diagnosis is confirmed.",
+        "Also check 'Device State': AzureAdJoined = YES and DomainJoined = YES are expected for hybrid join.",
+        "Check Event Viewer: Applications and Services Logs > Microsoft > Windows > User Device Registration > Admin for PRT / registration errors (e.g. event 304/305/362).",
+        "Enable the gather rules 'Collect dsregcmd join status' so future sessions capture this state automatically."
+      ]
+    },
+    {
+      "title": "Fix the identity pipeline",
+      "steps": [
+        "Entra Connect: confirm BOTH the computer OU and the user OU are in the sync scope, and the computer object's userCertificate attribute is being exported.",
+        "Verify the user's UPN suffix is a verified domain in Entra ID (no .local / mismatched suffix).",
+        "Ensure domain-controller line of sight at logon from the provisioning network/VLAN (hybrid PRT requires a reachable DC).",
+        "Check proxy/firewall rules for login.microsoftonline.com, device.login.microsoftonline.com and enterpriseregistration.windows.net from the user context."
+      ]
+    },
+    {
+      "title": "Address VPN and Windows Hello dependencies",
+      "steps": [
+        "If a VPN is required to reach a domain controller, it must be established before or at the logon screen (machine tunnel / pre-logon tunnel). A user-context tunnel that starts after sign-in is too late for the hybrid PRT flow.",
+        "If you deploy Windows Hello for Business to hybrid-joined devices, use cloud Kerberos trust — it removes the on-premises certificate/key-trust dependencies that commonly stall Hello on hybrid devices.",
+        "If you do not use Windows Hello, disable it explicitly via a device-scoped Intune policy instead of leaving it unconfigured — the enrollment then resolves the Hello step deterministically instead of waiting for a wizard that never comes.",
+        "Avoid feature/quality updates mid-enrollment where possible — an OS update with forced reboots during enrollment aggravates this pattern. Consider a short Windows Update deferral covering the enrollment window.",
+        "For hybrid deployments, pre-provisioning (White Glove) materially shrinks the user-facing phase: the device phase runs on a known-good technician network, and the user phase reduces to sign-in, user ESP, and Hello."
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Autopilot Monitor: Hybrid join — stuck in Account Setup (no user affinity)",
+      "url": "https://docs.autopilotmonitor.com/troubleshooting/hybrid-join-stuck-in-account-setup"
+    },
+    {
+      "title": "Autopilot Monitor: Hybrid join — late device registration",
+      "url": "https://docs.autopilotmonitor.com/troubleshooting/hybrid-join-late-device-registration"
+    },
+    {
+      "title": "Microsoft Learn: Troubleshoot hybrid-joined devices",
+      "url": "https://learn.microsoft.com/en-us/entra/identity/devices/troubleshoot-hybrid-join-windows-current"
+    }
+  ],
+  "markSessionAsFailedDefault": false,
+  "tags": ["identity", "hybrid-join", "entra-id", "user-affinity", "esp"]
+}

rules/analyze/ANALYZE-OFFICE-001.json

@@ -5,8 +5,12 @@
   "description": "Detects when the Microsoft 365 Apps (Office Click-to-Run) background install did not reach completion. The V2 OfficeInstallDetector watches the C2R client directly (registry + process) and emits office_install_failed when the install scenario was abandoned (worker gone and streaming never finished) or a C2R failure code was observed. This catches Office failures that the Intune integrated app type hides, because IME reports the app done within 1-2 minutes while C2R keeps installing in the background.",
   "severity": "warning",
   "category": "apps",
-  "version": "1.0.1",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 75,
   "conditions": [
     {
@@ -28,7 +32,11 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "error_code_present", "condition": "exists", "weight": 15 }
+    {
+      "signal": "error_code_present",
+      "condition": "exists",
+      "weight": 15
+    }
   ],
   "confidenceThreshold": 40,
   "explanation": "The Microsoft 365 Apps (Office Click-to-Run) install did not finish.\n\nThe OfficeInstallDetector watches the C2R client directly and reports the real background install lifecycle. The Intune \"integrated\" Microsoft 365 Apps app type only pushes the configuration XML and starts the C2R bootstrapper, so IME marks the app done within 1-2 minutes while C2R keeps streaming and laying down the product for several more minutes. This event means C2R activity ended (the OfficeC2RClient worker exited and the install scenario cleared) without the StreamingFinished flag being set, or a C2R failure code was observed.\n\nReview the office_install_failed event payload: `products`, `channel`, `phase`, `streamingFinished`, `errorCode` (best-effort — may be empty) and `durationSeconds`.",
@@ -44,5 +52,11 @@
       ]
     }
   ],
-  "tags": ["apps", "office", "microsoft-365-apps", "click-to-run", "install-failure"]
+  "tags": [
+    "apps",
+    "office",
+    "microsoft-365-apps",
+    "click-to-run",
+    "install-failure"
+  ]
 }

rules/analyze/ANALYZE-SEC-001.json

@@ -5,8 +5,12 @@
   "description": "Detects devices where the Windows UEFI CA 2023 certificate has not been deployed to the Secure Boot DB. The 2011 certificates expired in June 2026 — affected devices no longer receive Secure Boot security updates until the 2023 certificate is deployed. Since v3 the agent reads the firmware db/KEK variables directly: when the firmware itself confirms the 2023 certificate, the rule is suppressed even if the Windows servicing status has not caught up yet.",
   "severity": "warning",
   "category": "security",
-  "version": "3.0.0",
+  "version": "3.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 70,
   "preconditions": [
     {
@@ -83,10 +87,26 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "ca2023_notfound", "condition": "exists", "weight": 20 },
-    { "signal": "ca2023_error", "condition": "exists", "weight": 10 },
-    { "signal": "db_ca2023_firmware_missing", "condition": "exists", "weight": 20 },
-    { "signal": "kek_2023_missing", "condition": "exists", "weight": 10 }
+    {
+      "signal": "ca2023_notfound",
+      "condition": "exists",
+      "weight": 20
+    },
+    {
+      "signal": "ca2023_error",
+      "condition": "exists",
+      "weight": 10
+    },
+    {
+      "signal": "db_ca2023_firmware_missing",
+      "condition": "exists",
+      "weight": 20
+    },
+    {
+      "signal": "kek_2023_missing",
+      "condition": "exists",
+      "weight": 10
+    }
   ],
   "explanation": "This device has Secure Boot enabled but the **Windows UEFI CA 2023** certificate has not been deployed to the Secure Boot DB.\n\nThe original Windows UEFI CA 2011 certificates **expired on June 27, 2026 — this deadline has passed**. The automatic pre-expiry rollout window is over: this device no longer receives Secure Boot security updates (DB/DBX) and cannot trust 2023-signed boot managers until the 2023 certificate is deployed. Deploying it now requires active remediation (Windows servicing opt-in and, on some models, an OEM firmware update) rather than waiting for an automatic update.\n\nOn devices running a current agent this finding is verified against the firmware itself: the agent reads the UEFI `db` signature database directly, and this warning is automatically suppressed when the firmware already contains the 2023 certificate — regardless of the Windows servicing status below.\n\nCurrent UEFI CA 2023 servicing status: `{{uefiCA2023Status}}`",
   "remediation": [
@@ -112,5 +132,11 @@
       "url": "https://support.microsoft.com/en-us/topic/kb5036210"
     }
   ],
-  "tags": ["security", "secureboot", "certificate", "ca2023", "compliance"]
+  "tags": [
+    "security",
+    "secureboot",
+    "certificate",
+    "ca2023",
+    "compliance"
+  ]
 }

rules/analyze/ANALYZE-SEC-003.json

@@ -5,8 +5,12 @@
   "description": "Fires when the AutoLogon analyzer reports a DefaultPassword value present in Winlogon. A plaintext AutoLogon password stored in the registry is readable by any local administrator and is a credential exposure — more severe than AutoLogon alone (the Sysinternals Autologon tool deliberately avoids this by storing the secret in the LSA instead).",
   "severity": "high",
   "category": "security",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 90,
   "conditions": [
@@ -45,5 +49,11 @@
       "url": "https://learn.microsoft.com/en-us/sysinternals/downloads/autologon"
     }
   ],
-  "tags": ["security", "autologon", "winlogon", "credentials", "plaintext-password"]
+  "tags": [
+    "security",
+    "autologon",
+    "winlogon",
+    "credentials",
+    "plaintext-password"
+  ]
 }

rules/analyze/ANALYZE-SEC-004.json

@@ -5,8 +5,12 @@
   "description": "Optional kiosk allow-list for AutoLogon. Fires when AutoLogon is enabled for a default user that is NOT on your configured list of approved kiosk / shared-device accounts. Disabled until configured because a normal Autopilot enrollment leaves Windows' own ESP auto-logon for the enrolling user (AutoLogon enabled, a default user, no plaintext password) — so AutoLogon-enabled alone is not graded by default; only a plaintext DefaultPassword on disk (ANALYZE-SEC-003) is. Enable this rule with your expected kiosk account name(s) if you want to surface AutoLogon configured for any other user.",
   "severity": "warning",
   "category": "security",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": false,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 80,
   "conditions": [
@@ -55,7 +59,13 @@
       "url": "https://learn.microsoft.com/en-us/troubleshoot/windows-server/user-profiles-and-logon/turn-on-automatic-logon"
     }
   ],
-  "tags": ["security", "autologon", "winlogon", "kiosk", "allow-list"],
+  "tags": [
+    "security",
+    "autologon",
+    "winlogon",
+    "kiosk",
+    "allow-list"
+  ],
   "templateVariables": [
     {
       "name": "allowed_autologon_users",

rules/analyze/ANALYZE-SEC-005.json

@@ -5,8 +5,12 @@
   "description": "Detects provisioning packages (PPKG) that are not on the built-in allow-list. The agent emits one or more provisioning_package_scan events whose artifacts[] arrays list every PPKG (registry package, .ppkg file, or Recovery\\Customizations residue; a large set is split across several events). This rule iterates that array across all of them and fires for any artifact whose identity does not match the allow-list regex. The default allow-list covers the Windows OS-inbox packages (Cosa, Power.EnergyEstimationEngine, Power.Settings, SecureStart) plus common OEM factory-preload families (Intel PPM power profiles, AMD Power profiles, Lenovo ThinkPad power/battery packages, Microsoft Surface defaults and carrier packages) so clean factory devices stay quiet. OEM imaging leftovers (e.g. USMT.PPKG, InstallOrder.ini) and generically named packages deliberately still alert — on a pure-Autopilot device they are worth a look. To allow your own vendor/recovery packages, enable the template rule ANALYZE-SEC-006, extend its allow-list, then disable this rule.",
   "severity": "warning",
   "category": "security",
-  "version": "2.1.0",
+  "version": "2.2.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 80,
   "conditions": [
     {
@@ -34,5 +38,11 @@
       ]
     }
   ],
-  "tags": ["security", "provisioning-package", "ppkg", "allow-list", "tamper"]
+  "tags": [
+    "security",
+    "provisioning-package",
+    "ppkg",
+    "allow-list",
+    "tamper"
+  ]
 }

rules/analyze/ANALYZE-SEC-006.json

@@ -5,8 +5,12 @@
   "description": "Template version of ANALYZE-SEC-005 with a customizable allow-list. Iterates the provisioning_package_scan artifacts[] array and fires for any PPKG whose identity is not on YOUR allow-list regex. The placeholder ships with the same OS-inbox defaults as ANALYZE-SEC-005 — extend it with your own vendor/recovery packages. This rule is OFF by default: enable it, set your allow-list, then disable ANALYZE-SEC-005 so only packages outside your list alert.",
   "severity": "warning",
   "category": "security",
-  "version": "2.1.0",
+  "version": "2.2.0",
   "enabled": false,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 80,
   "conditions": [
     {
@@ -41,7 +45,13 @@
       ]
     }
   ],
-  "tags": ["security", "provisioning-package", "ppkg", "allow-list", "template"],
+  "tags": [
+    "security",
+    "provisioning-package",
+    "ppkg",
+    "allow-list",
+    "template"
+  ],
   "templateVariables": [
     {
       "name": "allowed_packages",

rules/analyze/ANALYZE-SEC-007.json

@@ -5,8 +5,12 @@
   "description": "Fires when the provisioning-package scan hit a per-source collection cap (too many .ppkg files, registry packages, or Recovery\\Customizations residue files to capture them all). When that happens the allow-list rules (ANALYZE-SEC-005/006) could not evaluate every package, so a non-allow-listed package may have gone unseen. A device with that many provisioning packages is itself unusual and worth a manual look.",
   "severity": "warning",
   "category": "security",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "baseConfidence": 80,
   "conditions": [
     {
@@ -32,5 +36,11 @@
       ]
     }
   ],
-  "tags": ["security", "provisioning-package", "ppkg", "truncated", "coverage"]
+  "tags": [
+    "security",
+    "provisioning-package",
+    "ppkg",
+    "truncated",
+    "coverage"
+  ]
 }

rules/analyze/ANALYZE-SEC-008.json

@@ -5,9 +5,13 @@
   "description": "Detects devices enrolling with Secure Boot turned off. Secure Boot is a firmware-level protection against boot-time malware and is a prerequisite for several Windows security features (VBS/Credential Guard, device health attestation) and common Intune compliance policies. Devices that support Secure Boot but have it disabled should be flagged during enrollment. Legacy BIOS devices (no Secure Boot capability) are excluded — the agent marks those with a note field when the SecureBoot registry state key is absent.",
   "severity": "warning",
   "category": "security",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "author": "Autopilot Monitor",
   "enabled": true,
+  "evaluateOn": [
+    "enrollment_end",
+    "whiteglove_sealed"
+  ],
   "trigger": "single",
   "baseConfidence": 70,
   "preconditions": [
@@ -41,7 +45,11 @@
     }
   ],
   "confidenceFactors": [
-    { "signal": "physical_device", "condition": "exists", "weight": 20 }
+    {
+      "signal": "physical_device",
+      "condition": "exists",
+      "weight": 20
+    }
   ],
   "confidenceThreshold": 60,
   "explanation": "This device enrolled with **Secure Boot disabled**.\n\nThe firmware reports UEFI mode, but Secure Boot is turned off (`HKLM\\SYSTEM\\CurrentControlSet\\Control\\SecureBoot\\State\\UEFISecureBootEnabled = 0`). Without Secure Boot the boot chain is not verified, which:\n\n- Leaves the device exposed to bootkits and unsigned boot-time code\n- Blocks or weakens Virtualization-based Security (VBS), Credential Guard and Device Health Attestation\n- Typically makes the device **non-compliant** if an Intune compliance policy requires Secure Boot — Conditional Access may then block the user right after enrollment\n\nSecure Boot is usually disabled deliberately in firmware setup (e.g. for imaging, dual-boot or legacy CSM mode) and simply never re-enabled before the device was handed to Autopilot.",
@@ -74,5 +82,11 @@
       "url": "https://learn.microsoft.com/en-us/windows-hardware/manufacture/desktop/disabling-secure-boot"
     }
   ],
-  "tags": ["security", "secureboot", "firmware", "uefi", "compliance"]
+  "tags": [
+    "security",
+    "secureboot",
+    "firmware",
+    "uefi",
+    "compliance"
+  ]
 }

rules/dist/analyze-rules.json

@@ -7,8 +7,12 @@
       "description": "Detects when a Win32 app detection script fails or returns unexpected results.",
       "severity": "warning",
       "category": "apps",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 60,
       "conditions": [
         {
@@ -48,8 +52,13 @@
       "description": "Detects app installation failures with specific exit codes or HRESULT error codes and suggests fixes.",
       "severity": "high",
       "category": "apps",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:app_install_failed"
+      ],
       "baseConfidence": 80,
       "conditions": [
         {
@@ -92,6 +101,10 @@
       "severity": "high",
       "category": "apps",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 70,
       "conditions": [
         {
@@ -118,7 +131,8 @@
       "tags": [
         "apps",
         "dependency"
-      ]
+      ],
+      "version": "1.1.0"
     },
     {
       "ruleId": "ANALYZE-APP-004",
@@ -126,8 +140,13 @@
       "description": "Detects when disk space is critically low during enrollment, which can cause app installation failures. Confidence increases when app installations actually failed while disk space was low.",
       "severity": "critical",
       "category": "apps",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:app_install_failed"
+      ],
       "baseConfidence": 75,
       "conditions": [
         {
@@ -200,6 +219,10 @@
       "severity": "high",
       "category": "apps",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 70,
       "conditions": [
         {
@@ -227,7 +250,8 @@
         "apps",
         "download",
         "timeout"
-      ]
+      ],
+      "version": "1.1.0"
     },
     {
       "ruleId": "ANALYZE-APP-006",
@@ -235,8 +259,12 @@
       "description": "Detects when the same app installation is attempted 3 or more times during one enrollment — a retry loop caused by unhonored reboot requests, repeated failures, or detection mismatches.",
       "severity": "high",
       "category": "apps",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 70,
       "conditions": [
         {
@@ -274,7 +302,13 @@
       "description": "Detects when the app tracking summary reports multiple failed app installations.",
       "severity": "high",
       "category": "apps",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:app_install_failed"
+      ],
       "baseConfidence": 75,
       "conditions": [
         {
@@ -285,6 +319,14 @@
           "operator": "gte",
           "value": "2",
           "required": true
+        },
+        {
+          "signal": "enrollment_failed",
+          "source": "event_type",
+          "eventType": "enrollment_failed",
+          "operator": "exists",
+          "value": "",
+          "required": false
         }
       ],
       "confidenceFactors": [
@@ -318,6 +360,10 @@
       "severity": "warning",
       "category": "apps",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 70,
       "conditions": [
         {
@@ -345,7 +391,8 @@
         "performance",
         "slow-install",
         "warning"
-      ]
+      ],
+      "version": "1.1.0"
     },
     {
       "ruleId": "ANALYZE-APP-010",
@@ -425,6 +472,10 @@
       "severity": "warning",
       "category": "apps",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "correlation",
       "baseConfidence": 80,
       "conditions": [
@@ -464,7 +515,8 @@
         "exit-code",
         "unmapped",
         "resolved"
-      ]
+      ],
+      "version": "1.1.0"
     },
     {
       "ruleId": "ANALYZE-APP-013",
@@ -472,8 +524,12 @@
       "description": "Detects when the Enrollment Status Page failed because Intune could not verify an app was installed (HRESULT 0x87D1041C). The installer ran but the detection rule did not match afterwards.",
       "severity": "critical",
       "category": "apps",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 90,
       "preconditions": [
         {
@@ -559,8 +615,12 @@
       "description": "Detects when the Enrollment Status Page failed on the Apps subcategory and the agent's AppX deployment log scan identified a suspected MSIX/Store package. Store/MSIX apps install outside the Win32 pipeline, so the regular per-app tracking sees nothing — this correlation names the likely culprit.",
       "severity": "warning",
       "category": "apps",
-      "version": "1.0.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 75,
       "preconditions": [
         {
@@ -589,6 +649,51 @@
           "operator": "regex",
           "value": "^0x80073[cd]",
           "required": false
+        },
+        {
+          "signal": "appx_esp_category",
+          "source": "event_data",
+          "eventType": "esp_appx_failure_analysis",
+          "dataField": "espCategory",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "appx_esp_errorcode",
+          "source": "event_data",
+          "eventType": "esp_appx_failure_analysis",
+          "dataField": "espErrorCode",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "appx_top_candidate_package",
+          "source": "event_data",
+          "eventType": "esp_appx_failure_analysis",
+          "dataField": "topCandidatePackage",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "appx_candidate_count",
+          "source": "event_data",
+          "eventType": "esp_appx_failure_analysis",
+          "dataField": "candidateCount",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "appx_scan_confidence",
+          "source": "event_data",
+          "eventType": "esp_appx_failure_analysis",
+          "dataField": "confidence",
+          "operator": "exists",
+          "value": "",
+          "required": false
         }
       ],
       "explanation": "The ESP **{{espCategory}}/Apps** subcategory failed with HRESULT **{{espErrorCode}}** — an error from the AppX/MSIX deployment stack, i.e. a **Microsoft Store / MSIX app**, not a Win32 app. These apps install via the EnterpriseModernAppManagement CSP and never appear in the IME Win32 sidecar logs, which is why all tracked Win32/WinGet apps in this session can look green while ESP still reports an Apps failure.\n\nThe agent scanned the AppXDeploymentServer event log during the failure settle window and identified **{{topCandidatePackageName}}** (package `{{topCandidatePackage}}`) as the most likely culprit — its deployment error matches the ESP failure code ({{candidateCount}} candidate(s) total, confidence: {{confidence}}).\n\n**This is a correlation-based assessment, not a confirmed root cause** — validate against the AppXDeploymentServer/Operational event log on the device or in the diagnostics archive before acting.",
@@ -637,14 +742,108 @@
         "0x80073cf9"
       ]
     },
+    {
+      "ruleId": "ANALYZE-APP-015",
+      "title": "Required App Never Settled — ESP Completion Deferred",
+      "description": "The IME reported its user-session completion line, but at least one required app stayed pending — without ever failing or even starting to install — so the agent kept deferring the enrollment completion signal. Typically an assignment/requirement problem (requirement rules never met, dependency never satisfied, or the app needs a context that is not available during ESP, e.g. a VPN client waiting for user sign-in to a portal).",
+      "severity": "high",
+      "category": "apps",
+      "version": "1.0.0",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "trigger": "correlation",
+      "baseConfidence": 60,
+      "confidenceThreshold": 55,
+      "preconditions": [
+        {
+          "source": "event_data",
+          "eventType": "enrollment_complete",
+          "operator": "not_exists",
+          "description": "Suppress when the pending app eventually settled and the enrollment completed — a transient deferral is normal."
+        },
+        {
+          "source": "event_data",
+          "eventType": "enrollment_failed",
+          "operator": "not_exists",
+          "description": "Suppress when the session failed explicitly — the app/ESP failure rules already cover that path; this rule targets the never-finishing case."
+        }
+      ],
+      "conditions": [
+        {
+          "signal": "completion_deferred",
+          "source": "event_type",
+          "eventType": "agent_trace",
+          "dataField": "message",
+          "operator": "contains",
+          "value": "completion signal deferred",
+          "required": true
+        },
+        {
+          "signal": "apps_pending",
+          "source": "event_data",
+          "eventType": "app_tracking_summary",
+          "dataField": "pending",
+          "operator": "gte",
+          "value": "1",
+          "required": true
+        },
+        {
+          "signal": "pending_app_names",
+          "source": "event_data",
+          "eventType": "app_tracking_summary",
+          "dataField": "pendingNames",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [
+        {
+          "signal": "pending_app_names",
+          "condition": "exists",
+          "weight": 5
+        }
+      ],
+      "explanation": "The Intune Management Extension wrote its user-session completion line, but the agent observed `{{pending}}` required app(s) still pending (`{{pendingNames}}`) and therefore **deferred the enrollment completion signal** — repeatedly, if this happened across several logons or reboots.\n\nA pending app that never transitions to downloading/installing and never fails is almost always an **assignment or requirement problem**, not an install error:\n\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 targeted as *required* for the user ESP that needs something unavailable during provisioning (e.g. a VPN client whose portal sign-in only happens after first logon),\n- user-targeted apps on a device where the user identity never fully registered (see the hybrid user-affinity rule if it also fired).",
+      "remediation": [
+        {
+          "title": "Identify and unblock the pending app",
+          "steps": [
+            "Check the app names listed in this finding's evidence (pendingNames) — these are the apps the ESP is waiting for.",
+            "In Intune, review the app's requirement rules and dependencies; test them on the device (IntuneManagementExtension.log logs each requirement evaluation).",
+            "Decide whether the app really must block the ESP: removing it from the ESP's 'blocking apps' list (or making it not-required during enrollment) unblocks completion immediately.",
+            "If the app is user-targeted on a hybrid-joined device, verify the user's Entra affinity first — without a signed-in Entra user, user-targeted policy never applies."
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Microsoft Learn: Enrollment Status Page — blocking apps",
+          "url": "https://learn.microsoft.com/en-us/intune/intune-service/enrollment/windows-enrollment-status"
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "apps",
+        "esp",
+        "completion",
+        "assignment",
+        "pending"
+      ]
+    },
     {
       "ruleId": "ANALYZE-CORR-003",
       "title": "Proxy Configuration Causing Download Failure",
       "description": "Correlates an active proxy configuration with app content download failures (Delivery Optimization timeout or download error), suggesting the proxy is blocking or throttling Intune content delivery.",
       "severity": "high",
       "category": "apps",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:app_install_failed"
+      ],
       "trigger": "correlation",
       "baseConfidence": 60,
       "conditions": [
@@ -752,8 +951,12 @@
       "description": "Detects when memory usage stays above 90% across at least 3 performance snapshots during enrollment, indicating sustained memory pressure that can cause app installation failures or system instability.",
       "severity": "warning",
       "category": "device",
-      "version": "2.0.0",
+      "version": "2.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 55,
       "conditions": [
         {
@@ -820,8 +1023,12 @@
       "description": "Detects devices enrolling with an OS build that has reached end of support: Windows 11 22H2 (build 22621) or older, which includes every Windows 10 build. Maintenance note: raise the build cutoff to 22631 after Windows 11 23H2 reaches end of support on 2026-11-10.",
       "severity": "warning",
       "category": "device",
-      "version": "2.0.0",
+      "version": "2.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 90,
       "conditions": [
         {
@@ -881,8 +1088,13 @@
       "description": "Detects a Windows quality/cumulative update that FAILED to install during the OOBE / ESP enrollment window (WindowsUpdateClient EventID 20). A cumulative update failing mid-OOBE is a known cause of enrollment errors and is otherwise invisible in the Intune console.",
       "severity": "high",
       "category": "device",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:windows_update_failed"
+      ],
       "trigger": "single",
       "baseConfidence": 70,
       "confidenceThreshold": 60,
@@ -984,8 +1196,12 @@
       "description": "Informational: a Windows quality/cumulative update installed during the OOBE / ESP enrollment window (WindowsUpdateClient EventID 19). Surfaces updates applied mid-enrollment — useful context when correlating enrollment duration, reboots, or later issues with a specific KB.",
       "severity": "info",
       "category": "device",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 60,
       "confidenceThreshold": 50,
@@ -1048,8 +1264,12 @@
       "description": "Informational: the OS build (CurrentBuild.UBR) changed across a reboot during enrollment — an update was installed, regardless of which servicing path delivered it. Deterministic corroboration that works even when the Windows Update event channel shows nothing (registry comparison across restart cannot be lost to timing or logging-path differences).",
       "severity": "info",
       "category": "device",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 70,
       "confidenceThreshold": 50,
@@ -1121,9 +1341,13 @@
       "description": "The device's real-time clock deviates from NTP by more than two minutes. Microsoft documents that a clock off by several minutes causes TPM attestation errors (self-deploying/pre-provisioning) and ESP timeouts. Knowledge source: docs/agent/autopilot-ztd-diagnostics.md.",
       "severity": "warning",
       "category": "device",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 55,
       "confidenceThreshold": 50,
@@ -1268,7 +1492,7 @@
       "description": "Detects when the enrollment session was force-failed by the server-side inactivity timeout (no agent telemetry for the configured SessionTimeoutHours window) without ever completing or explicitly failing.",
       "severity": "high",
       "category": "enrollment",
-      "version": "1.0.0",
+      "version": "1.2.0",
       "enabled": true,
       "baseConfidence": 80,
       "preconditions": [
@@ -1293,9 +1517,35 @@
           "operator": "exists",
           "value": "",
           "required": true
+        },
+        {
+          "signal": "timeoutHours",
+          "source": "event_data",
+          "eventType": "session_timeout",
+          "dataField": "timeoutHours",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "desktop_was_reached",
+          "source": "event_type",
+          "eventType": "desktop_arrived",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        },
+        {
+          "signal": "all_tracked_apps_completed",
+          "source": "event_data",
+          "eventType": "app_tracking_summary",
+          "dataField": "isAllCompleted",
+          "operator": "equals",
+          "value": "true",
+          "required": false
         }
       ],
-      "explanation": "The enrollment session was force-failed by the server-side maintenance sweep after `{{timeoutHours}}` hour(s) of agent inactivity — the device stopped sending telemetry and never reported completion or an explicit failure.\n\nThis usually means the agent process died or the device went offline mid-enrollment (power off, network loss, bluescreen, reimage) rather than a clean enrollment failure. Because there is no terminal `enrollment_failed` event, the more specific app/ESP rules cannot pinpoint a cause — the evidence simply stops at the last event before the gap.",
+      "explanation": "The enrollment session was force-failed by the server-side maintenance sweep after `{{timeoutHours}}` hour(s) of agent inactivity — the device stopped sending telemetry and never reported completion or an explicit failure.\n\nThis usually means the agent process died or the device went offline mid-enrollment (power off, network loss, bluescreen, reimage) rather than a clean enrollment failure. Because there is no terminal `enrollment_failed` event, the more specific app/ESP rules cannot pinpoint a cause — the evidence simply stops at the last event before the gap.\n\n**If the evidence shows the user desktop was reached and all tracked apps completed**, the device most likely got all its content but the ESP never signaled completion — on hybrid-joined devices the usual culprit is the user session never establishing Entra affinity (Account Setup re-running on every logon). Check whether the hybrid user-affinity finding also fired for this session.",
       "remediation": [
         {
           "title": "Investigate the silent session",
@@ -1306,6 +1556,13 @@
             "If the device is reachable, collect the agent + IME logs and re-run enrollment, correlating with the timeout timestamp",
             "If many sessions time out in the same window, check for a tenant-wide network/connectivity issue or an Intune service incident"
           ]
+        },
+        {
+          "title": "Desktop reached and apps done, but no completion",
+          "steps": [
+            "Sign in as the affected user and run dsregcmd /status — 'SSO State: AzureAdPrt' must be YES; NO means the user never registered with Entra and the Account Setup ESP will loop",
+            "Verify Entra Connect syncs both the computer object (userCertificate) and the signing-in user, and that the user's UPN suffix is a verified Entra domain"
+          ]
         }
       ],
       "tags": [
@@ -1320,9 +1577,14 @@
       "description": "A TPM-attestation-related error code documented in the Microsoft Autopilot known-issues list was observed (0x800705B4, 0x801C03EA, 0x81039001, 0x81039023, 0x81039024, 0x80070490). These block self-deploying and pre-provisioning deployments during 'Securing your hardware'. Observability: attestation precedes MDM enrollment, so in the normal deployment model (agent installed via IME after enrollment) these codes are rarely visible — the rule primarily serves bootstrap-token deployments. See docs/agent/autopilot-ztd-diagnostics.md (Observability section).",
       "severity": "high",
       "category": "enrollment",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed",
+        "on_event:modern_deployment_error"
+      ],
       "trigger": "single",
       "baseConfidence": 60,
       "confidenceThreshold": 55,
@@ -1405,9 +1667,13 @@
       "description": "An enrollment-blocking error code documented in the Microsoft Autopilot known-issues/troubleshooting pages was observed (0x80180014, 0x80180018, 0xC1036501, 0x801C03F3, 0x80070774). Each has a specific, documented cause and fix. Observability: a blocked MDM enrollment normally means no agent gets installed at all (IME install happens after enrollment) — this rule can realistically only fire for bootstrap-token deployments (pre-MDM reporting) or mixed retry scenarios. See docs/agent/autopilot-ztd-diagnostics.md (Observability section).",
       "severity": "high",
       "category": "enrollment",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 60,
       "confidenceThreshold": 55,
@@ -1488,9 +1754,13 @@
       "description": "A Microsoft Entra hybrid join Autopilot deployment hit error 0x80004005 — a documented build-dependent known issue, resolved by KB5065789 (25H2, build >= 26200.6725), KB5065426 (24H2, build >= 26100.6584), and KB5070312 (23H2, build >= 22631.6276). Knowledge source: docs/agent/autopilot-ztd-diagnostics.md (error-code map).",
       "severity": "high",
       "category": "enrollment",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "correlation",
       "baseConfidence": 25,
       "confidenceThreshold": 60,
@@ -1596,8 +1866,12 @@
       "description": "Detects when the DeviceSetup phase of the ESP took longer than 30 minutes, indicating a stuck or very slow blocking app. Confidence increases when the phase exceeds 60 minutes.",
       "severity": "high",
       "category": "esp",
-      "version": "1.1.0",
+      "version": "1.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 50,
       "conditions": [
         {
@@ -1647,9 +1921,13 @@
       "description": "Detects when the Certificates subcategory of the Enrollment Status Page reported a failure, even if the enrollment later appears to have succeeded. Users can click 'Continue anyway' on an ESP error, which masks the underlying certificate provisioning failure — this rule surfaces the transition so it stays visible.",
       "severity": "high",
       "category": "esp",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 80,
       "conditions": [
@@ -1791,9 +2069,13 @@
       "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": "1.1.0",
+      "version": "1.2.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 70,
       "conditions": [
@@ -1890,8 +2172,12 @@
       "description": "Detects the recovery story: the ESP reported a terminal failure (typically DeviceSetup/Apps), the user most likely pressed 'Try again' on the failure page, the failed step re-ran and completed successfully. The earlier failure did not stick — the enrollment continued past it.",
       "severity": "info",
       "category": "esp",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 85,
       "conditions": [
         {
@@ -1996,7 +2282,11 @@
       "category": "identity",
       "isCommunity": true,
       "enabled": false,
-      "version": "1.2.0",
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
+      "version": "1.3.0",
       "baseConfidence": 75,
       "conditions": [
         {
@@ -2062,9 +2352,13 @@
       "description": "Detects when the LocalAdminAnalyzer flags unexpected local user accounts or profile directories on the device. This is a known Autopilot bypass technique where admin accounts are created before or during enrollment to gain persistent local admin access.",
       "severity": "high",
       "category": "identity",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 60,
       "conditions": [
@@ -2151,9 +2445,13 @@
       "description": "Fires when the vulnerability correlation finds critical-severity CVEs or CISA KEV entries in installed software. This indicates the device has software with known, actively exploited vulnerabilities.",
       "severity": "critical",
       "category": "security",
-      "version": "1.0.1",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 90,
       "conditions": [
@@ -2222,14 +2520,139 @@
         "security"
       ]
     },
+    {
+      "ruleId": "ANALYZE-ID-004",
+      "title": "Hybrid Sign-In Never Establishes Entra User Affinity",
+      "description": "On a hybrid-joined device the real user reached the desktop, but the Autopilot provisioning placeholder stayed active in JoinInfo and the agent repeatedly reported the hybrid sign-in as overdue. The user session never establishes Entra user affinity (no PRT), so the Account Setup ESP re-runs on every logon and the enrollment never completes.",
+      "severity": "high",
+      "category": "identity",
+      "version": "1.2.0",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "trigger": "correlation",
+      "evaluateOn": [
+        "enrollment_end",
+        "on_event:hybrid_login_pending"
+      ],
+      "baseConfidence": 60,
+      "confidenceThreshold": 75,
+      "preconditions": [
+        {
+          "source": "event_data",
+          "eventType": "enrollment_complete",
+          "operator": "not_exists",
+          "description": "Suppress when the session eventually completed — a single overdue-login warning followed by a successful sign-in is normal hybrid latency, not a broken affinity."
+        }
+      ],
+      "conditions": [
+        {
+          "signal": "hybrid_login_overdue",
+          "source": "event_type",
+          "eventType": "hybrid_login_pending",
+          "operator": "exists",
+          "value": "",
+          "required": true
+        },
+        {
+          "signal": "user_desktop_reached",
+          "source": "event_type",
+          "eventType": "desktop_arrived",
+          "operator": "exists",
+          "value": "",
+          "required": true
+        },
+        {
+          "signal": "placeholder_still_active",
+          "source": "event_type",
+          "eventType": "aad_placeholder_user_detected",
+          "operator": "exists",
+          "value": "",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [
+        {
+          "signal": "hybrid_login_pending",
+          "condition": "count >= 2",
+          "weight": 20
+        },
+        {
+          "signal": "hybrid_login_pending",
+          "condition": "count >= 3",
+          "weight": 10
+        },
+        {
+          "signal": "aad_placeholder_user_detected",
+          "condition": "count >= 3",
+          "weight": 10
+        }
+      ],
+      "explanation": "A real user signed in and reached the desktop, but the device kept reporting the **Autopilot provisioning placeholder** as the active identity in JoinInfo and the hybrid sign-in as **overdue** — across multiple reboots. This means the signed-in user never established **Microsoft Entra user affinity** (no Primary Refresh Token), so:\n\n- the Account Setup ESP page re-appears on every logon,\n- user-targeted required apps and policies cannot settle,\n- the enrollment never reaches completion.\n\nAfter this many hours this is not normal Entra Connect sync latency — something is structurally preventing the user (or the computer object) from registering:\n\n- the computer object's `userCertificate` attribute is not syncing to Entra ID (sync scope / OU filtering),\n- the signing-in user is not synced, or their UPN does not match a verified Entra domain,\n- the device has no line of sight to a domain controller **at logon time**, so the hybrid PRT flow cannot finish,\n- time skew or a proxy blocking `login.microsoftonline.com` / `enterpriseregistration.windows.net` from the user context.\n\nA frequent variant: the user's **first sign-in happens without domain-controller reachability** — for example when a pre-logon VPN tunnel (GlobalProtect, Always On VPN, Zscaler ZPA) is not established yet at the logon screen. Windows falls back to cached credentials, the hybrid PRT flow silently never runs, and later reboots do not fix it — sessions in this state typically show repeated reboots and network flapping while the placeholder identity stays active.\n\nA visible side effect: **the Windows Hello for Business wizard never appears**, because Hello provisioning requires an Entra user token (PRT). Hello is a downstream symptom here, not the cause.",
+      "remediation": [
+        {
+          "title": "Verify user affinity on the device",
+          "steps": [
+            "Sign in as the affected user and run: dsregcmd /status — under 'SSO State' the value AzureAdPrt must be YES. NO means the user has no Entra token and this diagnosis is confirmed.",
+            "Also check 'Device State': AzureAdJoined = YES and DomainJoined = YES are expected for hybrid join.",
+            "Check Event Viewer: Applications and Services Logs > Microsoft > Windows > User Device Registration > Admin for PRT / registration errors (e.g. event 304/305/362).",
+            "Enable the gather rules 'Collect dsregcmd join status' so future sessions capture this state automatically."
+          ]
+        },
+        {
+          "title": "Fix the identity pipeline",
+          "steps": [
+            "Entra Connect: confirm BOTH the computer OU and the user OU are in the sync scope, and the computer object's userCertificate attribute is being exported.",
+            "Verify the user's UPN suffix is a verified domain in Entra ID (no .local / mismatched suffix).",
+            "Ensure domain-controller line of sight at logon from the provisioning network/VLAN (hybrid PRT requires a reachable DC).",
+            "Check proxy/firewall rules for login.microsoftonline.com, device.login.microsoftonline.com and enterpriseregistration.windows.net from the user context."
+          ]
+        },
+        {
+          "title": "Address VPN and Windows Hello dependencies",
+          "steps": [
+            "If a VPN is required to reach a domain controller, it must be established before or at the logon screen (machine tunnel / pre-logon tunnel). A user-context tunnel that starts after sign-in is too late for the hybrid PRT flow.",
+            "If you deploy Windows Hello for Business to hybrid-joined devices, use cloud Kerberos trust — it removes the on-premises certificate/key-trust dependencies that commonly stall Hello on hybrid devices.",
+            "If you do not use Windows Hello, disable it explicitly via a device-scoped Intune policy instead of leaving it unconfigured — the enrollment then resolves the Hello step deterministically instead of waiting for a wizard that never comes.",
+            "Avoid feature/quality updates mid-enrollment where possible — an OS update with forced reboots during enrollment aggravates this pattern. Consider a short Windows Update deferral covering the enrollment window.",
+            "For hybrid deployments, pre-provisioning (White Glove) materially shrinks the user-facing phase: the device phase runs on a known-good technician network, and the user phase reduces to sign-in, user ESP, and Hello."
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Autopilot Monitor: Hybrid join — stuck in Account Setup (no user affinity)",
+          "url": "https://docs.autopilotmonitor.com/troubleshooting/hybrid-join-stuck-in-account-setup"
+        },
+        {
+          "title": "Autopilot Monitor: Hybrid join — late device registration",
+          "url": "https://docs.autopilotmonitor.com/troubleshooting/hybrid-join-late-device-registration"
+        },
+        {
+          "title": "Microsoft Learn: Troubleshoot hybrid-joined devices",
+          "url": "https://learn.microsoft.com/en-us/entra/identity/devices/troubleshoot-hybrid-join-windows-current"
+        }
+      ],
+      "markSessionAsFailedDefault": false,
+      "tags": [
+        "identity",
+        "hybrid-join",
+        "entra-id",
+        "user-affinity",
+        "esp"
+      ]
+    },
     {
       "ruleId": "ANALYZE-OFFICE-001",
       "title": "Microsoft 365 Apps Install Failed",
       "description": "Detects when the Microsoft 365 Apps (Office Click-to-Run) background install did not reach completion. The V2 OfficeInstallDetector watches the C2R client directly (registry + process) and emits office_install_failed when the install scenario was abandoned (worker gone and streaming never finished) or a C2R failure code was observed. This catches Office failures that the Intune integrated app type hides, because IME reports the app done within 1-2 minutes while C2R keeps installing in the background.",
       "severity": "warning",
       "category": "apps",
-      "version": "1.0.1",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 75,
       "conditions": [
         {
@@ -2285,8 +2708,12 @@
       "description": "Detects devices where the Windows UEFI CA 2023 certificate has not been deployed to the Secure Boot DB. The 2011 certificates expired in June 2026 — affected devices no longer receive Secure Boot security updates until the 2023 certificate is deployed. Since v3 the agent reads the firmware db/KEK variables directly: when the firmware itself confirms the 2023 certificate, the rule is suppressed even if the Windows servicing status has not caught up yet.",
       "severity": "warning",
       "category": "security",
-      "version": "3.0.0",
+      "version": "3.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 70,
       "preconditions": [
         {
@@ -2422,8 +2849,12 @@
       "description": "Fires when the AutoLogon analyzer reports a DefaultPassword value present in Winlogon. A plaintext AutoLogon password stored in the registry is readable by any local administrator and is a credential exposure — more severe than AutoLogon alone (the Sysinternals Autologon tool deliberately avoids this by storing the secret in the LSA instead).",
       "severity": "high",
       "category": "security",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 90,
       "conditions": [
@@ -2476,8 +2907,12 @@
       "description": "Optional kiosk allow-list for AutoLogon. Fires when AutoLogon is enabled for a default user that is NOT on your configured list of approved kiosk / shared-device accounts. Disabled until configured because a normal Autopilot enrollment leaves Windows' own ESP auto-logon for the enrolling user (AutoLogon enabled, a default user, no plaintext password) — so AutoLogon-enabled alone is not graded by default; only a plaintext DefaultPassword on disk (ANALYZE-SEC-003) is. Enable this rule with your expected kiosk account name(s) if you want to surface AutoLogon configured for any other user.",
       "severity": "warning",
       "category": "security",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": false,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 80,
       "conditions": [
@@ -2550,8 +2985,12 @@
       "description": "Detects provisioning packages (PPKG) that are not on the built-in allow-list. The agent emits one or more provisioning_package_scan events whose artifacts[] arrays list every PPKG (registry package, .ppkg file, or Recovery\\Customizations residue; a large set is split across several events). This rule iterates that array across all of them and fires for any artifact whose identity does not match the allow-list regex. The default allow-list covers the Windows OS-inbox packages (Cosa, Power.EnergyEstimationEngine, Power.Settings, SecureStart) plus common OEM factory-preload families (Intel PPM power profiles, AMD Power profiles, Lenovo ThinkPad power/battery packages, Microsoft Surface defaults and carrier packages) so clean factory devices stay quiet. OEM imaging leftovers (e.g. USMT.PPKG, InstallOrder.ini) and generically named packages deliberately still alert — on a pure-Autopilot device they are worth a look. To allow your own vendor/recovery packages, enable the template rule ANALYZE-SEC-006, extend its allow-list, then disable this rule.",
       "severity": "warning",
       "category": "security",
-      "version": "2.1.0",
+      "version": "2.2.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 80,
       "conditions": [
         {
@@ -2593,8 +3032,12 @@
       "description": "Template version of ANALYZE-SEC-005 with a customizable allow-list. Iterates the provisioning_package_scan artifacts[] array and fires for any PPKG whose identity is not on YOUR allow-list regex. The placeholder ships with the same OS-inbox defaults as ANALYZE-SEC-005 — extend it with your own vendor/recovery packages. This rule is OFF by default: enable it, set your allow-list, then disable ANALYZE-SEC-005 so only packages outside your list alert.",
       "severity": "warning",
       "category": "security",
-      "version": "2.1.0",
+      "version": "2.2.0",
       "enabled": false,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 80,
       "conditions": [
         {
@@ -2653,8 +3096,12 @@
       "description": "Fires when the provisioning-package scan hit a per-source collection cap (too many .ppkg files, registry packages, or Recovery\\Customizations residue files to capture them all). When that happens the allow-list rules (ANALYZE-SEC-005/006) could not evaluate every package, so a non-allow-listed package may have gone unseen. A device with that many provisioning packages is itself unusual and worth a manual look.",
       "severity": "warning",
       "category": "security",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "baseConfidence": 80,
       "conditions": [
         {
@@ -2694,9 +3141,13 @@
       "description": "Detects devices enrolling with Secure Boot turned off. Secure Boot is a firmware-level protection against boot-time malware and is a prerequisite for several Windows security features (VBS/Credential Guard, device health attestation) and common Intune compliance policies. Devices that support Secure Boot but have it disabled should be flagged during enrollment. Legacy BIOS devices (no Secure Boot capability) are excluded — the agent marks those with a note field when the SecureBoot registry state key is absent.",
       "severity": "warning",
       "category": "security",
-      "version": "1.0.0",
+      "version": "1.1.0",
       "author": "Autopilot Monitor",
       "enabled": true,
+      "evaluateOn": [
+        "enrollment_end",
+        "whiteglove_sealed"
+      ],
       "trigger": "single",
       "baseConfidence": 70,
       "preconditions": [

rules/dist/gather-rules.json

@@ -128,6 +128,27 @@
         "oobe"
       ]
     },
+    {
+      "ruleId": "GATHER-DEVICE-006",
+      "title": "Collect dsregcmd join status on overdue hybrid sign-in",
+      "description": "Runs dsregcmd /status the moment the agent reports a hybrid sign-in as overdue (hybrid_login_pending), capturing the Entra join and registration state at exactly the point where the problem is detected. Complements GATHER-DEVICE-001 (snapshot on entering Account Setup). Note: the agent runs as SYSTEM, so the output shows device join state — the per-user SSO/PRT state still requires running dsregcmd as the signed-in user.",
+      "category": "device",
+      "version": "1.0.0",
+      "author": "Autopilot Monitor",
+      "enabled": false,
+      "collectorType": "command_allowlisted",
+      "target": "dsregcmd /status",
+      "trigger": "on_event",
+      "triggerEventType": "hybrid_login_pending",
+      "outputEventType": "gather_dsregcmd_status",
+      "outputSeverity": "Info",
+      "tags": [
+        "device",
+        "entra",
+        "join",
+        "hybrid"
+      ]
+    },
     {
       "ruleId": "GATHER-ENROLL-001",
       "title": "MDM enrollment diagnostic events",

rules/dist/ime-log-patterns.json

@@ -4,12 +4,23 @@
     {
       "patternId": "HS-COMPLIANCE",
       "category": "always",
-      "pattern": "\\[HS\\] the (?<part>pre|post)-remdiation detection script compliance result for (?<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12}) is (?<compliance>True|False)",
+      "pattern": "\\[HS\\] the (?<part>pre|post)-rem(?:e)?diation detection script compliance result for (?<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12}) is (?<compliance>True|False)",
       "action": "healthScriptDetectionResult",
       "parameters": {
         "scriptType": "remediation"
       },
-      "description": "Early-signal fallback for health-script detection / post-detection results. Microsoft IME emits this line immediately after each detection script runs, ~30-90 seconds before the consolidated [HS] new result = JSON line is logged (which only fires after IME's batch-send to the Microsoft service). Short Autopilot enrollments often end inside that gap, so this pattern guarantees at least the compliance verdict is captured. The full data version arrives later via HS-NEW-RESULT and replaces this sparse entry through the UI dedupe (dataCompleteness scoring).",
+      "description": "Early-signal fallback for health-script detection / post-detection results. Microsoft IME emits this line immediately after each detection script runs, ~30-90 seconds before the consolidated [HS] new result = JSON line is logged (which only fires after IME's batch-send to the Microsoft service). Short Autopilot enrollments often end inside that gap, so this pattern guarantees at least the compliance verdict is captured. The full data version arrives later via HS-NEW-RESULT and replaces this sparse entry through the UI dedupe (dataCompleteness scoring). Tolerates both Microsoft's historical typo 'remdiation' and a future corrected 'remediation'. NOTE: IME 1.97 (Dec 2025) no longer emits the post- variant of this line; the post case is covered by HS-COMPLIANCE-POST.",
+      "enabled": true
+    },
+    {
+      "patternId": "HS-COMPLIANCE-POST",
+      "category": "always",
+      "pattern": "\\[HS\\] the (?<part>post) detection script result for (?<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12}) is (?<compliance>True|False)",
+      "action": "healthScriptDetectionResult",
+      "parameters": {
+        "scriptType": "remediation"
+      },
+      "description": "Post-remediation detection result, current wording. IME 1.97 (Dec 2025) replaced the old '[HS] the post-remdiation detection script compliance result for ...' line (still covered by HS-COMPLIANCE for older logs) with '[HS] the post detection script result for <guid> is <True|False>' (ScriptProcessorV2.cs:721). The literal word 'post' in the line is captured as the part group so the handler classifies it as the post-detection phase.",
       "enabled": true
     },
     {
@@ -139,6 +150,14 @@
       "description": "Captures the install attempt number for the current app. IME logs 'Execute retry 0' for the first attempt and increments on each retry. Reported as attempt+1 so retry 0 becomes AttemptNumber=1 (human-friendly: first attempt).",
       "enabled": true
     },
+    {
+      "patternId": "IME-CACHE-MISS",
+      "category": "always",
+      "pattern": "\\[Win32App\\] Content cache miss for app \\(id = {GUID}, name = (?<name>.*?)\\), start downloading",
+      "action": "updateName",
+      "description": "Captures 'Content cache miss for app (id = <guid>, name = <name>), start downloading...' (ContentManager.cs) as a secondary app-name source. Fires right before a real download begins, so it resolves names for exactly the apps that will produce download/install activity — a redundancy for IME-POLICIES-based naming after IME retired the old name-bearing processing lines.",
+      "enabled": true
+    },
     {
       "patternId": "IME-DECRYPT-FAILED",
       "category": "currentPhase",
@@ -168,15 +187,15 @@
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] Detected app {GUID} ",
       "action": "updateStateInstalled",
-      "description": "Detects when an app is detected as installed (old log format).",
-      "enabled": true
+      "description": "Detects when an app is detected as installed (old log format). DISABLED 2026-08-17: the standalone 'Detected app <guid> ' line no longer exists in IME 1.97.107; this regex instead matched the 'Detected app ... and intent is to install, skip applicability check' line, colliding with IME-SKIP-INSTALL-DETECTED and firing updateStateInstalled and updateStateSkipped on the same physical line (see tasks/ime-v1-code-audit-2026-08-17.md).",
+      "enabled": false
     },
     {
       "patternId": "IME-DETECTION-RESULT",
       "category": "always",
-      "pattern": "\\[Win32App\\]\\[DetectionActionHandler\\] Detection for policy with id: (?<id>{GUID}) resulted in action status: Success and detection state: (?<detection>Detected|NotDetected)",
+      "pattern": "\\[Win32App\\]\\[DetectionActionHandler\\] Detection for policy with id: (?<id>{GUID}) resulted in action status: Success and detection state: (?<detection>DetectedDifferentVersion|NotDetected|Detected)",
       "action": "captureDetectionResult",
-      "description": "Captures the detection rule result after IME runs detection for an app. 'Detected' means the detection rule matched (app is installed), 'NotDetected' means it did not. Excludes [SimulatedDetectionActionHandler] which fires during applicability pre-checks.",
+      "description": "Captures the detection rule result after IME runs detection for an app. 'Detected' means the detection rule matched (app is installed), 'NotDetected' means it did not, 'DetectedDifferentVersion' means a different version was found (supersedence / WinGet version mismatch). DetectedDifferentVersion must come first in the alternation so the unanchored regex does not mis-capture its 'Detected' prefix. Excludes [SimulatedDetectionActionHandler] which fires during applicability pre-checks.",
       "enabled": true
     },
     {
@@ -217,9 +236,9 @@
     {
       "patternId": "IME-ENFORCEMENT-SUCCESS",
       "category": "currentPhase",
-      "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":\"\"InProgressDownloadCompleted\"\",\"\"NewValue\"\":\"\"Success\"\"",
+      "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":(?:\"\"\\w+\"\"|null),\"\"NewValue\"\":\"\"Success\"\"",
       "action": "updateStateInstalled",
-      "description": "Detects when an app's enforcement state transitions from InProgressDownloadCompleted to Success.",
+      "description": "Detects when an app's enforcement state transitions to Success in an Execution state report delta. OldValue is deliberately unpinned: besides InProgressDownloadCompleted it can be Error (retry succeeding in a later check-in), InProgressPendingReboot (post-reboot completion) or null (first write) — the previously pinned InProgressDownloadCompleted missed those legitimate success paths (IME 1.97 audit 2026-08-17).",
       "enabled": true
     },
     {
@@ -266,12 +285,12 @@
     {
       "patternId": "IME-ERROR-REPORT",
       "category": "currentPhase",
-      "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":\"\"(?<from>\\w+)\"\",\"\"NewValue\"\":\"\"(?<to>\\w+)\"\"",
+      "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":(?:\"\"(?<from>\\w+)\"\"|null),\"\"NewValue\"\":\"\"(?<to>\\w+)\"\"",
       "action": "updateStateError",
       "parameters": {
         "checkTo": "true"
       },
-      "description": "Captures enforcement state transitions via ReportingManager. Only triggers error when 'to' value indicates an error state.",
+      "description": "Captures enforcement state transitions via ReportingManager. Only triggers error when 'to' value indicates an error state. OldValue may be the unquoted JSON literal null on the first-ever write of a reporting state — transitions straight from the initial state (e.g. first write directly to an error state) would otherwise be invisible (IME 1.97 audit 2026-08-17).",
       "enabled": true
     },
     {
@@ -293,6 +312,14 @@
       "description": "Detects when an app installer returned an exit code that has no mapping configured in Intune.",
       "enabled": true
     },
+    {
+      "patternId": "IME-ESP-APP-REGISTERED",
+      "category": "always",
+      "pattern": "\\[Win32App\\]\\[EspManager\\] In EspPhase: \\w+\\. App {GUID} has been registered.*?App name: (?<name>.*?)$",
+      "action": "updateName",
+      "description": "Captures the ESP tracked-app registration line ('App <guid> has been registered[ for user <id>]. App name: <name>', EspManager.cs) as an app-name source. Primary replacement for the retired IME-UPDATE-NAME-1/2/3 whose emitters were removed with IME's old V1/V2 processing pipeline; also documents exactly which apps IME registered for ESP tracking. Category 'always' so names resolve even before the first ApplicationPoller EspPhase line is seen.",
+      "enabled": true
+    },
     {
       "patternId": "IME-ESP-PHASE",
       "category": "always",
@@ -304,9 +331,9 @@
     {
       "patternId": "IME-ESP-TRACK-STATUS",
       "category": "currentPhase",
-      "pattern": "\\[Win32App\\]\\[EspManager\\] Updating ESP tracked install status from (?<from>\\w+) to (?<to>\\w+) for application {GUID}\\.",
+      "pattern": "\\[Win32App\\]\\[EspManager\\] Updating ESP tracked install status from (?<from>\\w+) to (?<to>\\w+) for application {GUID}",
       "action": "espTrackStatus",
-      "description": "Captures ESP tracked install status transitions (e.g., InProgress to Installed) for a specific app.",
+      "description": "Captures ESP tracked install status transitions (e.g., InProgress to Installed) for a specific app. No trailing anchor: IME 1.97 (Dec 2025) appends ' with name: <appName>.' after the GUID (EspManager.cs), which broke the previous '\\.' suffix. 'from' can be the literal string 'null' on first tracking.",
       "enabled": true
     },
     {
@@ -320,6 +347,17 @@
       "description": "Captures the installer exit code (lpExitCode) for the current app.",
       "enabled": true
     },
+    {
+      "patternId": "IME-EXITCODE-MAPPED-FAILED",
+      "category": "currentPhase",
+      "pattern": "\\[Win32App\\] lpExitCode is defined as Failed$",
+      "action": "updateStateError",
+      "parameters": {
+        "useCurrentApp": "true"
+      },
+      "description": "Marks the current app as failed when its exit code maps to Failed via the admin-defined return-code table ('[Win32App] lpExitCode is defined as <Failed|Success|SoftReboot|HardReboot|Retry>', Win32AppInstaller.cs). This is the NORMAL mapped-exit-code outcome; the previously matched 'Setting enforcementState as ... Error' line only fires on the rare no-mapping fallback path. The numeric exit code is captured separately by IME-EXITCODE, which precedes this line.",
+      "enabled": true
+    },
     {
       "patternId": "IME-HRESULT",
       "category": "currentPhase",
@@ -422,6 +460,17 @@
       "description": "Captures the JSON policies list discovered by IME, used to build the app inventory.",
       "enabled": true
     },
+    {
+      "patternId": "IME-RESTART-STOP-PROCESSING",
+      "category": "currentPhase",
+      "pattern": "\\[Win32App\\]\\[V3Processor\\] A restart is required to continue processing apps\\. Stop processing\\.",
+      "action": "updateStatePostponed",
+      "parameters": {
+        "useCurrentApp": "true"
+      },
+      "description": "Detects IME aborting app processing because an app requires a restart ('A restart is required to continue processing apps. Stop processing.', SideCarV3AppProcessor.cs). Postpones the current app: remaining apps do nothing until after the reboot, which previously looked like an unexplained stall mid-ESP.",
+      "enabled": true
+    },
     {
       "patternId": "IME-SESSION-CHANGE",
       "category": "always",
@@ -435,24 +484,24 @@
       "category": "always",
       "pattern": "\\[Win32App\\] ProcessAppWithDependencies starts for {GUID} with name",
       "action": "setCurrentApp",
-      "description": "Detects when IME begins processing an app with its dependency chain, setting it as the current app.",
-      "enabled": true
+      "description": "Detects when IME begins processing an app with its dependency chain, setting it as the current app. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-SET-CURRENT-2",
       "category": "always",
       "pattern": "\\[Win32App\\] ExecManager: processing targeted app.*?\\bid\\W+{GUID}",
       "action": "setCurrentApp",
-      "description": "Detects when the IME ExecManager starts processing a targeted app, setting it as current.",
-      "enabled": true
+      "description": "Detects when the IME ExecManager starts processing a targeted app, setting it as current. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-SET-CURRENT-3",
       "category": "always",
       "pattern": "\\[Win32App\\] ===Step=== Start to Present app {GUID}",
       "action": "setCurrentApp",
-      "description": "Detects the start of app presentation step in IME, setting the app as current.",
-      "enabled": true
+      "description": "Detects the start of app presentation step in IME, setting the app as current. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-SET-CURRENT-4",
@@ -478,24 +527,24 @@
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] (?=.*?\\bapplicability\\b)(?=.*?NotMet\\b).*?\\bapp\\W+{GUID}\\b",
       "action": "updateStateSkipped",
-      "description": "Detects when an app's applicability check returns NotMet (old log format with lookaheads).",
-      "enabled": true
+      "description": "Detects when an app's applicability check returns NotMet (old log format with lookaheads). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-SKIP-DEPENDENCY-DETECT",
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] app\\W+{GUID}\\b.*?\\bis a dependency\\b.*?\\bDetect Only mode\\b.*?\\bfinished processing",
       "action": "updateStateSkipped",
-      "description": "Detects when a dependency app in Detect Only mode finishes processing (no install needed).",
-      "enabled": true
+      "description": "Detects when a dependency app in Detect Only mode finishes processing (no install needed). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-SKIP-DETECTED",
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] Detected app {GUID}.*?skip next step",
       "action": "updateStateSkipped",
-      "description": "Detects when an already-detected app is skipped for further processing steps (old log format).",
-      "enabled": true
+      "description": "Detects when an already-detected app is skipped for further processing steps (old log format). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-SKIP-FILTERS",
@@ -529,8 +578,8 @@
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] NOT detected app {GUID}.*?skip un-installation",
       "action": "updateStateSkipped",
-      "description": "Detects when an app is not detected and uninstall is skipped (alternate old log format).",
-      "enabled": true
+      "description": "Detects when an app is not detected and uninstall is skipped (alternate old log format). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-STARTED",
@@ -540,6 +589,17 @@
       "description": "Detects when the Intune Management Extension (IME) agent starts up.",
       "enabled": true
     },
+    {
+      "patternId": "IME-STOP-SIGNAL",
+      "category": "currentPhase",
+      "pattern": "EMS Agent received stop signal",
+      "action": "updateStatePostponed",
+      "parameters": {
+        "useCurrentApp": "true"
+      },
+      "description": "Detects an IME service stop ('EMS Agent received stop signal', EmsAgentService.OnStop) — fired on manual restarts and agent-updater restarts, unlike the OS-shutdown-only 'shutdown signal' line matched by IME-SHUTDOWN. Postpones the current app installation, mirroring IME-SHUTDOWN semantics.",
+      "enabled": true
+    },
     {
       "patternId": "IME-SUBGRAPH",
       "category": "currentPhase",
@@ -564,24 +624,24 @@
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] ExecManager: processing targeted app.*?name\\W+(?<name>.*?)\\W+id\\W+{GUID}",
       "action": "updateName",
-      "description": "Captures the app name from ExecManager processing log (old format: name before id).",
-      "enabled": true
+      "description": "Captures the app name from ExecManager processing log (old format: name before id). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-UPDATE-NAME-2",
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] ProcessAppWithDependencies starts for {GUID} with name (?<name>.*?)$",
       "action": "updateName",
-      "description": "Captures the app name from ProcessAppWithDependencies log entry.",
-      "enabled": true
+      "description": "Captures the app name from ProcessAppWithDependencies log entry. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-UPDATE-NAME-3",
       "category": "currentPhase",
       "pattern": "\\[Win32App\\] Processing app \\(id={GUID}, name = (?<name>.*?)\\)",
       "action": "updateName",
-      "description": "Captures the app name from the Processing app log entry.",
-      "enabled": true
+      "description": "Captures the app name from the Processing app log entry. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+      "enabled": false
     },
     {
       "patternId": "IME-USER-SESSION-COMPLETED",
@@ -607,6 +667,14 @@
       "description": "Captures the Win32 app ESP state (e.g., Installed, InProgress) for a specific app.",
       "enabled": true
     },
+    {
+      "patternId": "IME-WINGET-ERROR",
+      "category": "currentPhase",
+      "pattern": "\\[WinGetMessageProcessor\\] Processing Progress for app = {GUID}.*?- Operation Phase = Error",
+      "action": "updateStateError",
+      "description": "Marks a WinGet (new Store) app as failed when its operation progress reports phase Error (WinGetOperationInstallPhase: Downloading/Installing/Queued/Finished/Error). Before this pattern only the Installing phase was matched, so WinGet failures never surfaced as app errors (IME 1.97 audit 2026-08-17).",
+      "enabled": true
+    },
     {
       "patternId": "IME-WINGET-INSTALLING-1",
       "category": "currentPhase",

rules/gather/GATHER-DEVICE-006.json

@@ -0,0 +1,17 @@
+{
+  "$schema": "../schema/gather-rule.schema.json",
+  "ruleId": "GATHER-DEVICE-006",
+  "title": "Collect dsregcmd join status on overdue hybrid sign-in",
+  "description": "Runs dsregcmd /status the moment the agent reports a hybrid sign-in as overdue (hybrid_login_pending), capturing the Entra join and registration state at exactly the point where the problem is detected. Complements GATHER-DEVICE-001 (snapshot on entering Account Setup). Note: the agent runs as SYSTEM, so the output shows device join state — the per-user SSO/PRT state still requires running dsregcmd as the signed-in user.",
+  "category": "device",
+  "version": "1.0.0",
+  "author": "Autopilot Monitor",
+  "enabled": false,
+  "collectorType": "command_allowlisted",
+  "target": "dsregcmd /status",
+  "trigger": "on_event",
+  "triggerEventType": "hybrid_login_pending",
+  "outputEventType": "gather_dsregcmd_status",
+  "outputSeverity": "Info",
+  "tags": ["device", "entra", "join", "hybrid"]
+}

rules/guardrails.json

@@ -250,6 +250,37 @@
     "C:\\Install\\Log"
   ],
   "blockedFilePrefixes": [
-    "C:\\Users"
+    "C:\\Users",
+    "C:\\Windows\\System32\\config"
+  ],
+  "blockedCommandPatterns": [
+    "Invoke-WebRequest",
+    "Invoke-RestMethod",
+    "Start-BitsTransfer",
+    "wget",
+    "curl",
+    "certutil -urlcache",
+    "New-LocalUser",
+    "Add-LocalGroupMember",
+    "net user",
+    "net localgroup",
+    "bcdedit",
+    "bcdboot",
+    "schtasks /create",
+    "Register-ScheduledTask",
+    "Remove-Item -Recurse",
+    "Format-Volume",
+    "Set-ExecutionPolicy"
+  ],
+  "maxCommandLength": 2000,
+  "blockedInterimTriggerEventTypes": [
+    "performance_snapshot",
+    "agent_metrics_snapshot",
+    "download_progress",
+    "network_state_change",
+    "network_connectivity_check",
+    "log_entry",
+    "agent_trace",
+    "stall_probe_check"
   ]
 }

rules/ime-log-patterns/HS-COMPLIANCE-POST.json

@@ -0,0 +1,10 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "HS-COMPLIANCE-POST",
+  "category": "always",
+  "pattern": "\\[HS\\] the (?<part>post) detection script result for (?<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12}) is (?<compliance>True|False)",
+  "action": "healthScriptDetectionResult",
+  "parameters": { "scriptType": "remediation" },
+  "description": "Post-remediation detection result, current wording. IME 1.97 (Dec 2025) replaced the old '[HS] the post-remdiation detection script compliance result for ...' line (still covered by HS-COMPLIANCE for older logs) with '[HS] the post detection script result for <guid> is <True|False>' (ScriptProcessorV2.cs:721). The literal word 'post' in the line is captured as the part group so the handler classifies it as the post-detection phase.",
+  "enabled": true
+}

rules/ime-log-patterns/HS-COMPLIANCE.json

@@ -2,9 +2,9 @@
   "$schema": "../schema/ime-log-pattern.schema.json",
   "patternId": "HS-COMPLIANCE",
   "category": "always",
-  "pattern": "\\[HS\\] the (?<part>pre|post)-remdiation detection script compliance result for (?<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12}) is (?<compliance>True|False)",
+  "pattern": "\\[HS\\] the (?<part>pre|post)-rem(?:e)?diation detection script compliance result for (?<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12}) is (?<compliance>True|False)",
   "action": "healthScriptDetectionResult",
   "parameters": { "scriptType": "remediation" },
-  "description": "Early-signal fallback for health-script detection / post-detection results. Microsoft IME emits this line immediately after each detection script runs, ~30-90 seconds before the consolidated [HS] new result = JSON line is logged (which only fires after IME's batch-send to the Microsoft service). Short Autopilot enrollments often end inside that gap, so this pattern guarantees at least the compliance verdict is captured. The full data version arrives later via HS-NEW-RESULT and replaces this sparse entry through the UI dedupe (dataCompleteness scoring).",
+  "description": "Early-signal fallback for health-script detection / post-detection results. Microsoft IME emits this line immediately after each detection script runs, ~30-90 seconds before the consolidated [HS] new result = JSON line is logged (which only fires after IME's batch-send to the Microsoft service). Short Autopilot enrollments often end inside that gap, so this pattern guarantees at least the compliance verdict is captured. The full data version arrives later via HS-NEW-RESULT and replaces this sparse entry through the UI dedupe (dataCompleteness scoring). Tolerates both Microsoft's historical typo 'remdiation' and a future corrected 'remediation'. NOTE: IME 1.97 (Dec 2025) no longer emits the post- variant of this line; the post case is covered by HS-COMPLIANCE-POST.",
   "enabled": true
 }

rules/ime-log-patterns/IME-CACHE-MISS.json

@@ -0,0 +1,9 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-CACHE-MISS",
+  "category": "always",
+  "pattern": "\\[Win32App\\] Content cache miss for app \\(id = {GUID}, name = (?<name>.*?)\\), start downloading",
+  "action": "updateName",
+  "description": "Captures 'Content cache miss for app (id = <guid>, name = <name>), start downloading...' (ContentManager.cs) as a secondary app-name source. Fires right before a real download begins, so it resolves names for exactly the apps that will produce download/install activity — a redundancy for IME-POLICIES-based naming after IME retired the old name-bearing processing lines.",
+  "enabled": true
+}

rules/ime-log-patterns/IME-DETECTED-OLD.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] Detected app {GUID} ",
   "action": "updateStateInstalled",
-  "description": "Detects when an app is detected as installed (old log format).",
-  "enabled": true
+  "description": "Detects when an app is detected as installed (old log format). DISABLED 2026-08-17: the standalone 'Detected app <guid> ' line no longer exists in IME 1.97.107; this regex instead matched the 'Detected app ... and intent is to install, skip applicability check' line, colliding with IME-SKIP-INSTALL-DETECTED and firing updateStateInstalled and updateStateSkipped on the same physical line (see tasks/ime-v1-code-audit-2026-08-17.md).",
+  "enabled": false
 }

rules/ime-log-patterns/IME-DETECTION-RESULT.json

@@ -2,8 +2,8 @@
   "$schema": "../schema/ime-log-pattern.schema.json",
   "patternId": "IME-DETECTION-RESULT",
   "category": "always",
-  "pattern": "\\[Win32App\\]\\[DetectionActionHandler\\] Detection for policy with id: (?<id>{GUID}) resulted in action status: Success and detection state: (?<detection>Detected|NotDetected)",
+  "pattern": "\\[Win32App\\]\\[DetectionActionHandler\\] Detection for policy with id: (?<id>{GUID}) resulted in action status: Success and detection state: (?<detection>DetectedDifferentVersion|NotDetected|Detected)",
   "action": "captureDetectionResult",
-  "description": "Captures the detection rule result after IME runs detection for an app. 'Detected' means the detection rule matched (app is installed), 'NotDetected' means it did not. Excludes [SimulatedDetectionActionHandler] which fires during applicability pre-checks.",
+  "description": "Captures the detection rule result after IME runs detection for an app. 'Detected' means the detection rule matched (app is installed), 'NotDetected' means it did not, 'DetectedDifferentVersion' means a different version was found (supersedence / WinGet version mismatch). DetectedDifferentVersion must come first in the alternation so the unanchored regex does not mis-capture its 'Detected' prefix. Excludes [SimulatedDetectionActionHandler] which fires during applicability pre-checks.",
   "enabled": true
 }

rules/ime-log-patterns/IME-ENFORCEMENT-SUCCESS.json

@@ -2,8 +2,8 @@
   "$schema": "../schema/ime-log-pattern.schema.json",
   "patternId": "IME-ENFORCEMENT-SUCCESS",
   "category": "currentPhase",
-  "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":\"\"InProgressDownloadCompleted\"\",\"\"NewValue\"\":\"\"Success\"\"",
+  "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":(?:\"\"\\w+\"\"|null),\"\"NewValue\"\":\"\"Success\"\"",
   "action": "updateStateInstalled",
-  "description": "Detects when an app's enforcement state transitions from InProgressDownloadCompleted to Success.",
+  "description": "Detects when an app's enforcement state transitions to Success in an Execution state report delta. OldValue is deliberately unpinned: besides InProgressDownloadCompleted it can be Error (retry succeeding in a later check-in), InProgressPendingReboot (post-reboot completion) or null (first write) — the previously pinned InProgressDownloadCompleted missed those legitimate success paths (IME 1.97 audit 2026-08-17).",
   "enabled": true
 }

rules/ime-log-patterns/IME-ERROR-REPORT.json

@@ -2,9 +2,9 @@
   "$schema": "../schema/ime-log-pattern.schema.json",
   "patternId": "IME-ERROR-REPORT",
   "category": "currentPhase",
-  "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":\"\"(?<from>\\w+)\"\",\"\"NewValue\"\":\"\"(?<to>\\w+)\"\"",
+  "pattern": "\\[Win32App\\]\\[ReportingManager\\] Execution state for app with id: {GUID} has been updated\\. Report delta: \\{\"\"EnforcementState\"\":\\{\"\"OldValue\"\":(?:\"\"(?<from>\\w+)\"\"|null),\"\"NewValue\"\":\"\"(?<to>\\w+)\"\"",
   "action": "updateStateError",
   "parameters": { "checkTo": "true" },
-  "description": "Captures enforcement state transitions via ReportingManager. Only triggers error when 'to' value indicates an error state.",
+  "description": "Captures enforcement state transitions via ReportingManager. Only triggers error when 'to' value indicates an error state. OldValue may be the unquoted JSON literal null on the first-ever write of a reporting state — transitions straight from the initial state (e.g. first write directly to an error state) would otherwise be invisible (IME 1.97 audit 2026-08-17).",
   "enabled": true
 }

rules/ime-log-patterns/IME-ESP-APP-REGISTERED.json

@@ -0,0 +1,9 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-ESP-APP-REGISTERED",
+  "category": "always",
+  "pattern": "\\[Win32App\\]\\[EspManager\\] In EspPhase: \\w+\\. App {GUID} has been registered.*?App name: (?<name>.*?)$",
+  "action": "updateName",
+  "description": "Captures the ESP tracked-app registration line ('App <guid> has been registered[ for user <id>]. App name: <name>', EspManager.cs) as an app-name source. Primary replacement for the retired IME-UPDATE-NAME-1/2/3 whose emitters were removed with IME's old V1/V2 processing pipeline; also documents exactly which apps IME registered for ESP tracking. Category 'always' so names resolve even before the first ApplicationPoller EspPhase line is seen.",
+  "enabled": true
+}

rules/ime-log-patterns/IME-ESP-TRACK-STATUS.json

@@ -2,8 +2,8 @@
   "$schema": "../schema/ime-log-pattern.schema.json",
   "patternId": "IME-ESP-TRACK-STATUS",
   "category": "currentPhase",
-  "pattern": "\\[Win32App\\]\\[EspManager\\] Updating ESP tracked install status from (?<from>\\w+) to (?<to>\\w+) for application {GUID}\\.",
+  "pattern": "\\[Win32App\\]\\[EspManager\\] Updating ESP tracked install status from (?<from>\\w+) to (?<to>\\w+) for application {GUID}",
   "action": "espTrackStatus",
-  "description": "Captures ESP tracked install status transitions (e.g., InProgress to Installed) for a specific app.",
+  "description": "Captures ESP tracked install status transitions (e.g., InProgress to Installed) for a specific app. No trailing anchor: IME 1.97 (Dec 2025) appends ' with name: <appName>.' after the GUID (EspManager.cs), which broke the previous '\\.' suffix. 'from' can be the literal string 'null' on first tracking.",
   "enabled": true
 }

rules/ime-log-patterns/IME-EXITCODE-MAPPED-FAILED.json

@@ -0,0 +1,10 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-EXITCODE-MAPPED-FAILED",
+  "category": "currentPhase",
+  "pattern": "\\[Win32App\\] lpExitCode is defined as Failed$",
+  "action": "updateStateError",
+  "parameters": { "useCurrentApp": "true" },
+  "description": "Marks the current app as failed when its exit code maps to Failed via the admin-defined return-code table ('[Win32App] lpExitCode is defined as <Failed|Success|SoftReboot|HardReboot|Retry>', Win32AppInstaller.cs). This is the NORMAL mapped-exit-code outcome; the previously matched 'Setting enforcementState as ... Error' line only fires on the rare no-mapping fallback path. The numeric exit code is captured separately by IME-EXITCODE, which precedes this line.",
+  "enabled": true
+}

rules/ime-log-patterns/IME-RESTART-STOP-PROCESSING.json

@@ -0,0 +1,10 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-RESTART-STOP-PROCESSING",
+  "category": "currentPhase",
+  "pattern": "\\[Win32App\\]\\[V3Processor\\] A restart is required to continue processing apps\\. Stop processing\\.",
+  "action": "updateStatePostponed",
+  "parameters": { "useCurrentApp": "true" },
+  "description": "Detects IME aborting app processing because an app requires a restart ('A restart is required to continue processing apps. Stop processing.', SideCarV3AppProcessor.cs). Postpones the current app: remaining apps do nothing until after the reboot, which previously looked like an unexplained stall mid-ESP.",
+  "enabled": true
+}

rules/ime-log-patterns/IME-SET-CURRENT-1.json

@@ -4,6 +4,6 @@
   "category": "always",
   "pattern": "\\[Win32App\\] ProcessAppWithDependencies starts for {GUID} with name",
   "action": "setCurrentApp",
-  "description": "Detects when IME begins processing an app with its dependency chain, setting it as the current app.",
-  "enabled": true
+  "description": "Detects when IME begins processing an app with its dependency chain, setting it as the current app. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-SET-CURRENT-2.json

@@ -4,6 +4,6 @@
   "category": "always",
   "pattern": "\\[Win32App\\] ExecManager: processing targeted app.*?\\bid\\W+{GUID}",
   "action": "setCurrentApp",
-  "description": "Detects when the IME ExecManager starts processing a targeted app, setting it as current.",
-  "enabled": true
+  "description": "Detects when the IME ExecManager starts processing a targeted app, setting it as current. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-SET-CURRENT-3.json

@@ -4,6 +4,6 @@
   "category": "always",
   "pattern": "\\[Win32App\\] ===Step=== Start to Present app {GUID}",
   "action": "setCurrentApp",
-  "description": "Detects the start of app presentation step in IME, setting the app as current.",
-  "enabled": true
+  "description": "Detects the start of app presentation step in IME, setting the app as current. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-SKIP-APPLICABILITY-NOTMET.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] (?=.*?\\bapplicability\\b)(?=.*?NotMet\\b).*?\\bapp\\W+{GUID}\\b",
   "action": "updateStateSkipped",
-  "description": "Detects when an app's applicability check returns NotMet (old log format with lookaheads).",
-  "enabled": true
+  "description": "Detects when an app's applicability check returns NotMet (old log format with lookaheads). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-SKIP-DEPENDENCY-DETECT.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] app\\W+{GUID}\\b.*?\\bis a dependency\\b.*?\\bDetect Only mode\\b.*?\\bfinished processing",
   "action": "updateStateSkipped",
-  "description": "Detects when a dependency app in Detect Only mode finishes processing (no install needed).",
-  "enabled": true
+  "description": "Detects when a dependency app in Detect Only mode finishes processing (no install needed). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-SKIP-DETECTED.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] Detected app {GUID}.*?skip next step",
   "action": "updateStateSkipped",
-  "description": "Detects when an already-detected app is skipped for further processing steps (old log format).",
-  "enabled": true
+  "description": "Detects when an already-detected app is skipped for further processing steps (old log format). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-SKIP-UNINSTALL-NOTDETECTED-2.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] NOT detected app {GUID}.*?skip un-installation",
   "action": "updateStateSkipped",
-  "description": "Detects when an app is not detected and uninstall is skipped (alternate old log format).",
-  "enabled": true
+  "description": "Detects when an app is not detected and uninstall is skipped (alternate old log format). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-STOP-SIGNAL.json

@@ -0,0 +1,10 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-STOP-SIGNAL",
+  "category": "currentPhase",
+  "pattern": "EMS Agent received stop signal",
+  "action": "updateStatePostponed",
+  "parameters": { "useCurrentApp": "true" },
+  "description": "Detects an IME service stop ('EMS Agent received stop signal', EmsAgentService.OnStop) — fired on manual restarts and agent-updater restarts, unlike the OS-shutdown-only 'shutdown signal' line matched by IME-SHUTDOWN. Postpones the current app installation, mirroring IME-SHUTDOWN semantics.",
+  "enabled": true
+}

rules/ime-log-patterns/IME-UPDATE-NAME-1.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] ExecManager: processing targeted app.*?name\\W+(?<name>.*?)\\W+id\\W+{GUID}",
   "action": "updateName",
-  "description": "Captures the app name from ExecManager processing log (old format: name before id).",
-  "enabled": true
+  "description": "Captures the app name from ExecManager processing log (old format: name before id). DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-UPDATE-NAME-2.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] ProcessAppWithDependencies starts for {GUID} with name (?<name>.*?)$",
   "action": "updateName",
-  "description": "Captures the app name from ProcessAppWithDependencies log entry.",
-  "enabled": true
+  "description": "Captures the app name from ProcessAppWithDependencies log entry. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-UPDATE-NAME-3.json

@@ -4,6 +4,6 @@
   "category": "currentPhase",
   "pattern": "\\[Win32App\\] Processing app \\(id={GUID}, name = (?<name>.*?)\\)",
   "action": "updateName",
-  "description": "Captures the app name from the Processing app log entry.",
-  "enabled": true
+  "description": "Captures the app name from the Processing app log entry. DISABLED 2026-08-17: emitter no longer exists in current IME (1.97.107, Dec 2025) - the old V1/V2 app processing pipeline was removed and this line is not logged anymore (verified against decompiled source, see tasks/ime-v1-code-audit-2026-08-17.md). Kept for history.",
+  "enabled": false
 }

rules/ime-log-patterns/IME-WINGET-ERROR.json

@@ -0,0 +1,9 @@
+{
+  "$schema": "../schema/ime-log-pattern.schema.json",
+  "patternId": "IME-WINGET-ERROR",
+  "category": "currentPhase",
+  "pattern": "\\[WinGetMessageProcessor\\] Processing Progress for app = {GUID}.*?- Operation Phase = Error",
+  "action": "updateStateError",
+  "description": "Marks a WinGet (new Store) app as failed when its operation progress reports phase Error (WinGetOperationInstallPhase: Downloading/Installing/Queued/Finished/Error). Before this pattern only the Installing phase was matched, so WinGet failures never surfaced as app errors (IME 1.97 audit 2026-08-17).",
+  "enabled": true
+}

rules/schema/analyze-rule.schema.json

@@ -75,6 +75,16 @@
           "enum": ["single", "correlation"],
           "default": "single"
         },
+        "evaluateOn": {
+          "type": "array",
+          "description": "When this rule is evaluated. Absent = [\"enrollment_end\"] (terminal-only, the historical behavior). Interim triggers let the rule fire before the session is terminal: \"whiteglove_sealed\" (first genuine WhiteGlove seal) and \"on_event:<eventType>\" (an ingest batch contained that event type). High-frequency telemetry event types are HARD-BLOCKED as on_event triggers (guardrails blockedInterimTriggerEventTypes): the backend rejects them on save and the runtime ignores them. Interim runs suppress markSessionAsFailed and record no stats; findings notify once per (session, rule). Interim-enabled rules need monotonic conditions — a not_exists precondition on enrollment_complete/enrollment_failed/session_timeout passes trivially mid-run.",
+          "items": {
+            "type": "string",
+            "pattern": "^(enrollment_end|whiteglove_sealed|on_event:[a-z0-9_]{1,128})$"
+          },
+          "minItems": 1,
+          "uniqueItems": true
+        },
         "conditions": {
           "type": "array",
           "description": "Conditions evaluated against the event stream. All required conditions must match for the rule to fire.",

rules/schema/gather-rule.schema.json

@@ -67,7 +67,7 @@
         "collectorType": {
           "type": "string",
           "description": "Type of data collection.",
-          "enum": ["registry", "eventlog", "wmi", "file", "command_allowlisted", "logparser"]
+          "enum": ["registry", "eventlog", "wmi", "file", "json", "xml", "command_allowlisted", "logparser"]
         },
         "target": {
           "type": "string",

rules/scripts/combine.js

@@ -154,6 +154,18 @@ ${flatArray(flatEventLogChannels)}
 export const BLOCKED_EVENT_LOG_CHANNELS: readonly string[] = [
 ${flatArray(guardrails.blockedEventLogChannels)}
 ];
+
+export const BLOCKED_COMMAND_PATTERNS: readonly string[] = [
+${flatArray(guardrails.blockedCommandPatterns)}
+];
+
+// High-frequency telemetry event types hard-blocked as analyze-rule evaluateOn
+// on_event triggers (backend rejects on save, runtime ignores them).
+export const BLOCKED_INTERIM_TRIGGER_EVENT_TYPES: readonly string[] = [
+${flatArray(guardrails.blockedInterimTriggerEventTypes ?? [])}
+];
+
+export const MAX_COMMAND_LENGTH = ${guardrails.maxCommandLength};
 `;
 
   fs.writeFileSync(guardrailsOutput, ts, 'utf8');

scripts/Bootstrap/Install-AutopilotMonitor-dev.ps1

@@ -1,523 +0,0 @@
-<#
-.SYNOPSIS
-    DEV bootstrap script (v2.3-dev) to deploy and start the Autopilot Monitor agent.
-
-.DESCRIPTION
-    DEV VARIANT of Install-AutopilotMonitor.ps1 for validating the v2.3 Cloud-PC-relax
-    on Windows 365 before promoting it to the production script. Differences to v2.2:
-      - Cloud-PC-relax (see below) as a second trigger for the guard 2+3 exemption
-      - Raw OutOfBoxExperienceState value is logged (diagnosis)
-      - Logs to bootstrap_agent_dev.log so runs never interleave with the prod script
-      - Testable structure: guard/relax logic lives in functions; the script only
-        executes when run directly. Dot-sourcing it (as the Pester suite in
-        Install-AutopilotMonitor-dev.Tests.ps1 does) loads the functions without
-        side effects.
-
-    Designed to be deployed via Intune as a PowerShell Script during Autopilot.
-    Runs very early in the enrollment process (first Intune action) and:
-      1. Runs pre-flight guards to skip productive devices and ghost re-installs.
-         A relax exemption allows install when a single freshly-created profile
-         appears DURING OOBE (Windows Backup for Organizations restore) or on a
-         freshly provisioned Windows 365 Cloud PC.
-      2. Downloads the monitoring agent ZIP from Azure Blob Storage
-      3. Verifies integrity via SHA-256 hash from the version manifest (mandatory)
-      4. Extracts the agent into %ProgramData%\AutopilotMonitor\Agent
-      5. Runs the agent in --install mode (registers Scheduled Task, spawns the runtime)
-      6. Verifies the runtime process actually launched
-    Agent self-destructs when enrollment completes.
-
-    Relax flow (guards 2+3): a real user profile (or a real LastLoggedOnUser)
-    normally means "productive -> skip". Two legitimate flows break that assumption:
-
-    (1) Windows Backup for Organizations: one user signs in + restores DURING OOBE.
-        Trigger: the OS positively reports OOBE InProgress (Test via WinRT
-        SystemSetupInfo.OutOfBoxExperienceState).
-
-    (2) Windows 365 Cloud PC: W365 provisions headless -- OOBE and Intune enrollment
-        complete before any user ever connects, so OutOfBoxExperienceState is NEVER
-        InProgress when this script runs. The assigned user's profile is created at
-        first connect, typically seconds before IME pulls this script. Trigger: the
-        device positively identifies as a Cloud PC via TWO local markers (both
-        required; captured from a real Cloud PC -- local WMI reports only the
-        generic 'Virtual Machine' model): HKLM\SOFTWARE\Microsoft\Windows365
-        registry key AND the CloudManagedDesktopExtension service.
-
-    Either trigger relaxes guards 2+3 ONLY when additionally:
-      (a) there is exactly ONE real user profile, AND
-      (b) that profile was created within $OobeProfileMaxAgeMinutes minutes.
-    The Cloud PC trigger additionally exempts guard 4 (uptime window) -- see
-    .PARAMETER MaxBootstrapWindowHours for why boot uptime is meaningless there.
-    Any miss keeps the original skip (SKIP-safe: we never install on uncertainty).
-    On productive devices the profile is old, so (b) keeps skipping correctly.
-    Known accepted edge: a W365 Frontline shared-mode device can legitimately show a
-    single fresh profile while productive; a mis-install there is one-time (agent
-    finds enrollment complete and self-destructs; Deployed marker prevents repeats).
-
-.PARAMETER AgentDownloadUrl
-    URL to download the agent ZIP from. Defaults to the production download endpoint;
-    override only for parallel lab/dev assignments that point at a separate pre-release ZIP.
-
-.PARAMETER VersionJsonName
-    Filename of the integrity manifest in the same blob container as the agent ZIP.
-    Defaults to "version.json"; override only for parallel lab/dev manifests.
-
-.PARAMETER MaxBootstrapWindowHours
-    Maximum device uptime (hours) within which the bootstrap is still considered
-    valid. Devices booted more than this many hours ago are skipped because we no
-    longer trust their OOBE state. Default: 12.
-    Cloud PC note: NOT applied when the Cloud-PC relax is active. A Cloud PC runs
-    headless for days between provisioning and the user's first connect, and the
-    phase worth monitoring (Account Setup) only starts at that first connect --
-    there the fresh-profile window (OobeProfileMaxAgeMinutes) is the time anchor,
-    not boot uptime.
-
-.PARAMETER OobeProfileMaxAgeMinutes
-    Maximum age (minutes) of the single profile that may appear for the relax
-    exemption to apply. The restore/first-connect -> bootstrap gap is always
-    minutes; an older profile is treated as a productive device. Default: 15.
-
-.NOTES
-    - Agent is temporary and auto-removes after enrollment.
-    - All files live under C:\ProgramData\AutopilotMonitor (easy cleanup).
-    - One registry key remains after removal: HKLM\SOFTWARE\AutopilotMonitor\Deployed
-      (prevents ghost re-installs on re-Autopilot of the same device).
-    - Scheduled Task survives reboots during enrollment.
-    - OOBE detection uses Windows.System.Profile.SystemSetupInfo.OutOfBoxExperienceState.
-      Requires Windows 10, version 1809 (introduced in 10.0.17763.0). Older builds lack
-      the class -> state reads as 'Unavailable' -> original (skip) behaviour. Docs:
-      https://learn.microsoft.com/en-us/uwp/api/windows.system.profile.systemsetupinfo
-    - This script MUST remain pure ASCII (no Unicode/UTF-8 special chars).
-      PowerShell 5.1 (IME) reads scripts without BOM as ANSI, corrupting multi-byte chars.
-
-.CHANGELOG
-    2026-08-06  v2.3-dev.3  Guard 4 (uptime window) exempted while the Cloud-PC relax is
-                      active: Cloud PCs run headless for days before the user's first
-                      connect, so boot uptime says nothing about enrollment freshness --
-                      the single-fresh-profile window (< OobeProfileMaxAgeMinutes) already
-                      anchors the relax in time. OOBE-restore keeps the uptime guard.
-    2026-08-06  v2.3-dev.2  Cloud PC detection rebuilt on captured evidence: first field
-                      test proved local WMI reports only Manufacturer='Microsoft
-                      Corporation' + Model='Virtual Machine' (the 'Cloud PC ...' model
-                      string exists only in Intune/Graph). Detection now requires the
-                      HKLM\SOFTWARE\Microsoft\Windows365 registry key AND the
-                      CloudManagedDesktopExtension service (both verified present on a
-                      real Cloud PC); raw identity + marker states are always logged.
-    2026-08-05  v2.3-dev  DEV variant (-dev.ps1, own log file bootstrap_agent_dev.log)
-                      to validate on Windows 365 before promotion to v2.3:
-                      Cloud-PC-relax -- a positively identified Cloud PC
-                      (Win32_ComputerSystem Manufacturer 'Microsoft Corporation' +
-                      Model 'Cloud PC*') now triggers the guard 2+3 relax alongside
-                      OOBE InProgress; the single-fresh-profile conditions are
-                      unchanged. Raw OutOfBoxExperienceState is now logged.
-                      Refactored into functions with a dot-source entry guard so the
-                      Pester suite (*.Tests.ps1) can load the logic without executing
-                      the bootstrap; behaviour when run directly is unchanged.
-    2026-07-20  v2.2  Switched default download endpoint from the legacy blob
-                      (autopilotmonitor.blob.core.windows.net) to the Front Door alias
-                      https://download.autopilotmonitor.com/agent/ (route /agent/*).
-                      version.json is still derived from the same container.
-    2026-06-25  v2.1  OOBE-relax: detect genuine OOBE via WinRT
-                      SystemSetupInfo.OutOfBoxExperienceState and exempt guards 2+3 when a
-                      single freshly-created profile appears in OOBE (Windows Backup for
-                      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).
-    2026-05-09  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.
-    (older entries: see Install-AutopilotMonitor.ps1)
-#>
-
-[CmdletBinding()]
-param(
-    [Parameter(Mandatory = $false)]
-    [string]$AgentDownloadUrl = "https://download.autopilotmonitor.com/agent/AutopilotMonitor-Agent.zip",
-
-    [Parameter(Mandatory = $false)]
-    [string]$VersionJsonName = "version.json",
-
-    [Parameter(Mandatory = $false)]
-    [int]$MaxBootstrapWindowHours = 12,
-
-    [Parameter(Mandatory = $false)]
-    [int]$OobeProfileMaxAgeMinutes = 15
-)
-
-# Script version (bump on meaningful changes; see .CHANGELOG above)
-$ScriptVersion = "2.3-dev.3"
-
-# Configuration - Everything in ProgramData for easy cleanup
-$AgentBasePath = "$env:ProgramData\AutopilotMonitor"
-$AgentBinPath = "$AgentBasePath\Agent"
-$AgentLogPath = "$AgentBasePath\Logs"
-$LogFile = "$AgentLogPath\bootstrap_agent_dev.log"
-
-# Write-Host (NOT Write-Output): log calls happen inside functions that return
-# decision objects; Write-Output would leak every log line into those return
-# values and turn them into arrays. Write-Host goes to the console host only.
-function Write-Log {
-    param([string]$Message)
-    $timestamp = Get-Date -Format "yyyy-MM-dd HH:mm:ss"
-    $logMessage = "[$timestamp] $Message"
-    Write-Host $logMessage
-    Add-Content -Path $LogFile -Value $logMessage -ErrorAction SilentlyContinue
-}
-
-# Raw OOBE state via the documented WinRT API
-# Windows.System.Profile.SystemSetupInfo.OutOfBoxExperienceState.
-# Returns the state string (InProgress/Completed/NotStarted). An older OS without the
-# class (< Win10 1809 / 10.0.17763.0) or any error returns 'Unavailable'
-# -> SKIP-safe (we never relax a guard on uncertainty).
-# Docs: https://learn.microsoft.com/en-us/uwp/api/windows.system.profile.systemsetupinfo
-function Get-OobeState {
-    try {
-        $null = [Windows.System.Profile.SystemSetupInfo, Windows.System.Profile, ContentType = WindowsRuntime]
-        return ([Windows.System.Profile.SystemSetupInfo]::OutOfBoxExperienceState).ToString()
-    }
-    catch {
-        return 'Unavailable'
-    }
-}
-
-# Positive Windows 365 Cloud PC detection.
-# Evidence captured 2026-08-06 on a real, freshly provisioned W365 Enterprise Cloud PC:
-#   - Win32_ComputerSystem is GENERIC there: Manufacturer='Microsoft Corporation',
-#     Model='Virtual Machine'. The 'Cloud PC Enterprise ...' model string exists only
-#     in the Intune/Graph inventory, NOT in local WMI/SMBIOS -- it cannot be used here.
-#   - HKLM:\SOFTWARE\Microsoft\Windows365 exists.
-#   - Service 'CloudManagedDesktopExtension' (Microsoft Cloud Managed Desktop
-#     Extension, the W365 management agent that runs ON Cloud PCs) is installed.
-# BOTH markers are required (AND): each alone has plausible look-alikes (W365-Boot
-# physical clients may carry Windows365 policy state; the MCMD agent family also
-# served other managed-desktop offerings). Raw identity and both marker states are
-# always logged for field diagnosis; any error returns $false (SKIP-safe).
-function Test-IsCloudPc {
-    try {
-        $cs = Get-CimInstance Win32_ComputerSystem -ErrorAction Stop
-        Write-Log "Computer identity: Manufacturer='$($cs.Manufacturer)' Model='$($cs.Model)'."
-    }
-    catch { Write-Log "INFO: computer identity query failed: $($_.Exception.Message)" }
-
-    try {
-        $regMarker = Test-Path 'HKLM:\SOFTWARE\Microsoft\Windows365'
-        $svcMarker = $null -ne (Get-Service -Name 'CloudManagedDesktopExtension' -ErrorAction SilentlyContinue)
-        Write-Log "Cloud PC markers: Windows365 registry key=$regMarker; CloudManagedDesktopExtension service=$svcMarker."
-        return ($regMarker -and $svcMarker)
-    }
-    catch {
-        Write-Log "INFO: Cloud PC marker check failed: $($_.Exception.Message)"
-        return $false
-    }
-}
-
-# Collects real (non-special) user profiles as full paths (WMI Special flag + filesystem).
-# NOTE: callers MUST wrap the result in @(...). PowerShell unrolls function output, so an
-# empty result returns $null and a single path returns a scalar string, whose [0] indexer
-# would yield its first char ('C') instead of the full path.
-function Get-RealUserProfilePaths {
-    $excludePattern = '^(defaultuser\d*|Public|Default( User)?|All Users|WDAGUtilityAccount)$'
-    @(
-        try {
-            Get-CimInstance Win32_UserProfile -ErrorAction Stop |
-                Where-Object { -not $_.Special -and $_.LocalPath -like 'C:\Users\*' } |
-                ForEach-Object { $_.LocalPath }
-        } catch { Write-Log "INFO: WMI profile query failed, continuing with filesystem check." }
-
-        (Get-ChildItem 'C:\Users' -Directory -ErrorAction SilentlyContinue).FullName
-    ) | Where-Object { $_ -and (Split-Path $_ -Leaf) -notmatch $excludePattern } |
-        Select-Object -Unique
-}
-
-# Relax: the ONLY exemption to guards 2+3. Two triggers (see .DESCRIPTION):
-#   (1) OOBE InProgress          -> Windows Backup for Organizations restore
-#   (2) Cloud PC identity        -> Windows 365 (headless OOBE, profile at first connect)
-# Either trigger additionally requires: exactly one real profile AND that profile
-# created < $OobeProfileMaxAgeMinutes minutes ago. Any miss keeps the original skip.
-# Returns an object with: Active (bool), OobeState (string), IsCloudPc (bool).
-function Get-RelaxDecision {
-    param(
-        [string[]]$ProfilePaths,
-        [int]$OobeProfileMaxAgeMinutes
-    )
-    if ($null -eq $ProfilePaths) { $ProfilePaths = @() }
-
-    $relaxActive = $false
-    $oobeState = Get-OobeState
-    $oobeInProgress = ($oobeState -eq 'InProgress')
-    $isCloudPc = Test-IsCloudPc
-    if ($isCloudPc) {
-        Write-Log "Cloud PC detected (OOBE state: $oobeState)."
-    }
-
-    $relaxTrigger = $null
-    if ($oobeInProgress) {
-        $relaxTrigger = "OOBE InProgress (Windows Backup restore case)"
-    } elseif ($isCloudPc) {
-        $relaxTrigger = "Cloud PC (headless provisioning, OOBE state: $oobeState)"
-    }
-
-    if ($ProfilePaths.Count -eq 1 -and $relaxTrigger) {
-        try {
-            $created = (Get-Item -LiteralPath $ProfilePaths[0] -Force -ErrorAction Stop).CreationTimeUtc
-            $ageMin = ((Get-Date).ToUniversalTime() - $created).TotalMinutes
-            if ($ageMin -ge 0 -and $ageMin -lt $OobeProfileMaxAgeMinutes) {
-                $relaxActive = $true
-                Write-Log ("Relax active: {0} + single profile created {1:N1}min ago (< {2}min). Guards 2+3 relaxed." -f $relaxTrigger, $ageMin, $OobeProfileMaxAgeMinutes)
-            } else {
-                Write-Log ("Relax NOT applied: {0} + single profile '{1}', but profile created {2:N1}min ago (created {3:u}) is outside the [0, {4})min window." -f $relaxTrigger, (Split-Path $ProfilePaths[0] -Leaf), $ageMin, $created, $OobeProfileMaxAgeMinutes)
-            }
-        } catch { Write-Log "INFO: profile age check failed; relax not applied. $($_.Exception.Message)" }
-    } elseif ($ProfilePaths.Count -eq 1) {
-        Write-Log "Relax NOT applied: single profile present but neither OOBE InProgress nor Cloud PC (OOBE state: $oobeState)."
-    } elseif ($ProfilePaths.Count -gt 1) {
-        Write-Log ("Relax NOT applied: {0} real profiles present (relax requires exactly one). OOBE state: {1}; CloudPC: {2}." -f $ProfilePaths.Count, $oobeState, $isCloudPc)
-    }
-
-    return [pscustomobject]@{
-        Active    = $relaxActive
-        OobeState = $oobeState
-        IsCloudPc = $isCloudPc
-    }
-}
-
-# Runs pre-flight guards 1-5 and returns the install decision WITHOUT side effects
-# beyond logging. Returns an object with:
-#   Install (bool), ReasonCode (null | AlreadyDeployed | ProfilesFound |
-#   LastLoggedOnUser | UptimeExceeded | AgentPresent), RelaxActive (bool).
-function Get-BootstrapDecision {
-    param(
-        [int]$MaxBootstrapWindowHours,
-        [int]$OobeProfileMaxAgeMinutes,
-        [string]$AgentBinPath
-    )
-
-    # Guard 1: Agent was already deployed on this device (registry marker survives self-destruct)
-    $deployed = (Get-ItemProperty -Path 'HKLM:\SOFTWARE\AutopilotMonitor' -Name 'Deployed' -ErrorAction SilentlyContinue).Deployed
-    if ($deployed) {
-        Write-Log "SKIP: Agent was previously deployed at $deployed."
-        return [pscustomobject]@{ Install = $false; ReasonCode = 'AlreadyDeployed'; RelaxActive = $false }
-    }
-
-    # The @() wrap is required, see NOTE on Get-RealUserProfilePaths.
-    $profilePaths = @(Get-RealUserProfilePaths)
-    $relax = Get-RelaxDecision -ProfilePaths $profilePaths -OobeProfileMaxAgeMinutes $OobeProfileMaxAgeMinutes
-
-    # Guard 2: No real user profile should exist yet (primary productive-device guard),
-    # unless the relax signature holds.
-    if ($profilePaths.Count -gt 0 -and -not $relax.Active) {
-        $details = (($profilePaths | ForEach-Object {
-            $leaf = Split-Path $_ -Leaf
-            try {
-                $c = (Get-Item -LiteralPath $_ -Force -ErrorAction Stop).CreationTimeUtc
-                "{0} (created {1:u}, {2:N1}min ago)" -f $leaf, $c, ((Get-Date).ToUniversalTime() - $c).TotalMinutes
-            } catch { "$leaf (age unknown)" }
-        }) | Select-Object -First 3) -join '; '
-        Write-Log "SKIP: Real user profile(s) found ($details). OOBE state: $($relax.OobeState). CloudPC: $($relax.IsCloudPc). Device appears productive."
-        return [pscustomobject]@{ Install = $false; ReasonCode = 'ProfilesFound'; RelaxActive = $false }
-    }
-
-    # Guard 3: LastLoggedOnUser - during Device ESP no real user has logged on yet
-    # (same relax exemption: the restoring/first-connect user signs in legitimately).
-    $lastLoggedOnUser = (Get-ItemProperty -Path 'HKLM:\SOFTWARE\Microsoft\Windows\CurrentVersion\Authentication\LogonUI' -Name 'LastLoggedOnUser' -EA SilentlyContinue).LastLoggedOnUser
-    if ($lastLoggedOnUser -and $lastLoggedOnUser -notmatch 'defaultuser\d*' -and -not $relax.Active) {
-        Write-Log "SKIP: LastLoggedOnUser found ($lastLoggedOnUser). Device appears productive."
-        return [pscustomobject]@{ Install = $false; ReasonCode = 'LastLoggedOnUser'; RelaxActive = $false }
-    }
-
-    # Guard 4: Bootstrap window check - device uptime must be within accepted OOBE window.
-    # Sleep/standby does not reset uptime, only real boot/restart does.
-    # Cloud PC exemption (v2.3-dev.3): a Cloud PC runs headless from provisioning until the
-    # user's first connect -- often days -- and the phase worth monitoring (Account Setup)
-    # only STARTS at that first connect. Boot uptime is therefore meaningless there; the
-    # single-fresh-profile window of the relax (< $OobeProfileMaxAgeMinutes min) is the time
-    # anchor instead. The OOBE-restore trigger keeps the original uptime guard (physical
-    # device, uptime is meaningful).
-    $lastBoot = (Get-CimInstance Win32_OperatingSystem).LastBootUpTime
-    $uptimeHours = ((Get-Date) - $lastBoot).TotalHours
-    Write-Log "Device uptime: $([int]$uptimeHours)h (last boot: $lastBoot)"
-    if ($uptimeHours -gt $MaxBootstrapWindowHours) {
-        if ($relax.Active -and $relax.IsCloudPc) {
-            Write-Log "Uptime $([int]$uptimeHours)h exceeds the ${MaxBootstrapWindowHours}h window, but the Cloud PC relax is active (fresh first-connect profile is the time anchor). Continuing."
-        } else {
-            Write-Log "SKIP: Device uptime is $([int]$uptimeHours)h. OOBE state is older than accepted bootstrap window of ${MaxBootstrapWindowHours}h."
-            return [pscustomobject]@{ Install = $false; ReasonCode = 'UptimeExceeded'; RelaxActive = $relax.Active }
-        }
-    }
-
-    # Guard 5: Is the agent already installed? (leftover from previous run)
-    if (Test-Path $AgentBinPath) {
-        $existingAgent = Get-ChildItem -Path $AgentBinPath -Filter "AutopilotMonitor.Agent.exe" -ErrorAction SilentlyContinue
-        if ($existingAgent) {
-            Write-Log "SKIP: Agent already installed at $($existingAgent.FullName)."
-            return [pscustomobject]@{ Install = $false; ReasonCode = 'AgentPresent'; RelaxActive = $relax.Active }
-        }
-    }
-
-    return [pscustomobject]@{ Install = $true; ReasonCode = $null; RelaxActive = $relax.Active }
-}
-
-# Main bootstrap flow. Only invoked when the script is run directly (see entry guard
-# at the bottom); never on dot-source.
-function Invoke-Bootstrap {
-    try {
-        New-Item -Path $AgentBasePath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
-        New-Item -Path $AgentBinPath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
-        New-Item -Path $AgentLogPath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
-
-        Write-Log "===== Autopilot Monitor Bootstrap Started ====="
-        Write-Log "Bootstrap script version: v$ScriptVersion"
-
-        $decision = Get-BootstrapDecision -MaxBootstrapWindowHours $MaxBootstrapWindowHours -OobeProfileMaxAgeMinutes $OobeProfileMaxAgeMinutes -AgentBinPath $AgentBinPath
-        if (-not $decision.Install) {
-            exit 0
-        }
-
-        Write-Log "Pre-flight checks passed -- no prior deployment, no productive-device signals, within bootstrap window (relaxActive=$($decision.RelaxActive))"
-
-        # Download and extract agent binaries
-        $agentExePath = Join-Path $AgentBinPath "AutopilotMonitor.Agent.exe"
-
-        if (Test-Path $agentExePath) {
-            Write-Log "Agent already installed at $agentExePath"
-        }
-        else {
-            Write-Log "Downloading agent from $AgentDownloadUrl..."
-
-            try {
-                # Derive manifest URL from the agent download URL (same blob container)
-                $versionJsonUrl = $AgentDownloadUrl -replace '[^/]+$', $VersionJsonName
-                $expectedSha256 = $null
-                $manifestAttempts = 3
-                $manifestDelays = @(1, 2)   # short backoff between attempts; do not block enrollment
-
-                for ($attempt = 1; $attempt -le $manifestAttempts; $attempt++) {
-                    try {
-                        Write-Log "Fetching $VersionJsonName (attempt ${attempt}/${manifestAttempts}) from $versionJsonUrl for integrity verification..."
-                        $versionJsonResponse = Invoke-RestMethod -Uri $versionJsonUrl -UseBasicParsing -TimeoutSec 5 -ErrorAction Stop
-                        if ($versionJsonResponse.sha256) {
-                            $expectedSha256 = $versionJsonResponse.sha256.ToLowerInvariant()
-                            Write-Log "SHA-256 hash from manifest: $expectedSha256 (version: $($versionJsonResponse.version))"
-                        } else {
-                            Write-Log "WARNING: Manifest has no sha256 field - integrity cannot be verified."
-                        }
-                        break   # manifest reached (with or without hash); retrying would not help
-                    }
-                    catch {
-                        Write-Log "WARNING: Could not fetch integrity manifest (attempt $attempt): $($_.Exception.Message)"
-                        if ($attempt -lt $manifestAttempts) {
-                            Start-Sleep -Seconds $manifestDelays[$attempt - 1]
-                        }
-                    }
-                }
-
-                $zipPath = Join-Path $env:TEMP "AutopilotMonitor-Agent.zip"
-                $maxDownloadAttempts = 3
-                $downloadAttempt = 0
-
-                do {
-                    $downloadAttempt++
-                    try {
-                        Write-Log "Download attempt ${downloadAttempt}/${maxDownloadAttempts}"
-                        $downloadStopwatch = [System.Diagnostics.Stopwatch]::StartNew()
-                        Invoke-WebRequest `
-                            -Uri $AgentDownloadUrl `
-                            -OutFile $zipPath `
-                            -UseBasicParsing `
-                            -TimeoutSec 30 `
-                            -ErrorAction Stop
-                        $downloadStopwatch.Stop()
-                        $downloadSeconds = [math]::Round($downloadStopwatch.Elapsed.TotalSeconds, 1)
-                        Write-Log "Downloaded agent to $zipPath (took ${downloadSeconds}s)"
-                        break
-                    }
-                    catch {
-                        if ($downloadAttempt -ge $maxDownloadAttempts) {
-                            throw
-                        }
-
-                        $retryDelaysInSeconds = @(2, 4, 8)
-                        $retryDelaySeconds = $retryDelaysInSeconds[$downloadAttempt - 1]
-                        Write-Log "Download failed (attempt $downloadAttempt): $($_.Exception.Message). Retrying in ${retryDelaySeconds}s..."
-                        Start-Sleep -Seconds $retryDelaySeconds
-                    }
-                } while ($downloadAttempt -lt $maxDownloadAttempts)
-
-                # SHA-256 from the version manifest is the only accepted integrity proof.
-                # No hash -> refuse to install an unverified ZIP (SKIP-safe security posture).
-                if (-not $expectedSha256) {
-                    throw "No SHA-256 hash available from manifest - refusing to install unverified agent ZIP."
-                }
-                $actualSha256 = (Get-FileHash $zipPath -Algorithm SHA256).Hash.ToLowerInvariant()
-                Write-Log "Validating SHA-256 hash against manifest"
-                if ($actualSha256 -ne $expectedSha256) {
-                    throw "SHA-256 integrity check FAILED. Expected='$expectedSha256', Actual='$actualSha256'. Download may be tampered or corrupted."
-                }
-                Write-Log "SHA-256 integrity check passed"
-
-                Expand-Archive -Path $zipPath -DestinationPath $AgentBinPath -Force
-                Write-Log "Extracted agent to $AgentBinPath"
-
-                Remove-Item $zipPath -Force -ErrorAction SilentlyContinue
-                Write-Log "Cleaned up temporary files"
-
-                if (-not (Test-Path $agentExePath)) {
-                    throw "Agent executable not found after extraction at $agentExePath"
-                }
-
-                Write-Log "Agent installation completed successfully"
-            }
-            catch {
-                Write-Log "ERROR downloading/extracting agent: $($_.Exception.Message)"
-                throw
-            }
-        }
-
-        Write-Log "Calling agent install mode (--install)..."
-        & $agentExePath --install
-        $installExitCode = $LASTEXITCODE
-        if ($installExitCode -ne 0) {
-            throw "Agent install failed with exit code $installExitCode"
-        }
-        Write-Log "Agent install mode completed successfully"
-
-        $runtimeProcessName = 'AutopilotMonitor.Agent'
-        $verifyTimeoutSec = 10
-        $verifyDeadline = (Get-Date).AddSeconds($verifyTimeoutSec)
-        $runtimeProc = $null
-        while ((Get-Date) -lt $verifyDeadline) {
-            $runtimeProc = Get-Process -Name $runtimeProcessName -ErrorAction SilentlyContinue | Select-Object -First 1
-            if ($null -ne $runtimeProc) { break }
-            Start-Sleep -Milliseconds 500
-        }
-        if ($null -ne $runtimeProc) {
-            $startedUtc = 'unavailable'
-            try { $startedUtc = $runtimeProc.StartTime.ToUniversalTime().ToString('o') } catch { }
-            Write-Log ("Runtime process verified: name={0}.exe pid={1} startedUtc={2}" -f $runtimeProcessName, $runtimeProc.Id, $startedUtc)
-        } else {
-            Write-Log ("WARNING: Runtime process verification FAILED. Agent --install reported success but no '{0}.exe' process appeared within {1}s. Likely silent block (AV/EDR, AppLocker/WDAC) of the runtime launch. Agent should still come up at next boot via the BootTrigger task. Check Event Viewer > Microsoft > Windows > TaskScheduler/Operational and AV/EDR logs for '{0}.exe'." -f $runtimeProcessName, $verifyTimeoutSec)
-        }
-
-        Write-Log "===== Bootstrap Completed Successfully ====="
-
-        exit 0
-    }
-    catch {
-        Write-Log "===== Bootstrap FAILED ====="
-        Write-Log "ERROR: $($_.Exception.Message)"
-        Write-Log "Stack trace: $($_.ScriptStackTrace)"
-        Write-Log "Please check log file: $LogFile"
-
-        $errMsg = "AutopilotMonitor bootstrap failed: $($_.Exception.Message)"
-        if ($errMsg.Length -gt 2048) { $errMsg = $errMsg.Substring(0, 1045) + '...' }
-        [Console]::Error.WriteLine($errMsg)
-
-        exit 1
-    }
-}
-
-# Entry guard: execute only when run as a script (IME, console). Dot-sourcing
-# (". .\Install-AutopilotMonitor-dev.ps1", as the Pester suite does) only loads
-# the functions above and MUST stay side-effect free.
-if ($MyInvocation.InvocationName -ne '.') {
-    Invoke-Bootstrap
-}

scripts/Bootstrap/Install-AutopilotMonitor.Tests.ps1

@@ -1,5 +1,5 @@
 # Pester tests (Pester 5+) for the bootstrap guard/relax logic in
-# Install-AutopilotMonitor-dev.ps1 (v2.3-dev).
+# Install-AutopilotMonitor.ps1.
 #
 # The script under test is dot-sourced; its entry guard prevents the bootstrap
 # from executing, so loading it here is side-effect free. External state (WMI,
@@ -12,7 +12,7 @@
 # This file MUST remain pure ASCII (PS 5.1 reads BOM-less files as ANSI).
 
 BeforeAll {
-    . (Join-Path $PSScriptRoot 'Install-AutopilotMonitor-dev.ps1')
+    . (Join-Path $PSScriptRoot 'Install-AutopilotMonitor.ps1')
 
     function New-FakeProfile {
         param([string]$Name, [double]$AgeMinutes)
@@ -24,9 +24,9 @@ BeforeAll {
 }
 
 Describe 'Test-IsCloudPc' {
-    # Marker set captured 2026-08-06 from a real W365 Enterprise Cloud PC: local WMI
-    # is generic ('Virtual Machine'), so detection rests on the Windows365 registry
-    # key AND the CloudManagedDesktopExtension service (both required).
+    # Local WMI on a Cloud PC is generic ('Virtual Machine'), so detection rests on
+    # the Windows365 registry key AND the CloudManagedDesktopExtension service
+    # (both required).
     BeforeEach {
         Mock Write-Log { }
         Mock Get-CimInstance { [pscustomobject]@{ Manufacturer = 'Microsoft Corporation'; Model = 'Virtual Machine' } }
@@ -78,21 +78,21 @@ Describe 'Get-RealUserProfilePaths' {
     It 'merges WMI and filesystem views, drops special/system profiles, dedupes' {
         Mock Get-CimInstance {
             @(
-                [pscustomobject]@{ Special = $false; LocalPath = 'C:\Users\LeonGottschalk' }
+                [pscustomobject]@{ Special = $false; LocalPath = 'C:\Users\UserOne' }
                 [pscustomobject]@{ Special = $true; LocalPath = 'C:\Users\systemprofile' }
                 [pscustomobject]@{ Special = $false; LocalPath = 'D:\Profiles\Elsewhere' }
             )
         }
         Mock Get-ChildItem {
             @(
-                [pscustomobject]@{ FullName = 'C:\Users\LeonGottschalk' }
+                [pscustomobject]@{ FullName = 'C:\Users\UserOne' }
                 [pscustomobject]@{ FullName = 'C:\Users\Public' }
                 [pscustomobject]@{ FullName = 'C:\Users\defaultuser0' }
                 [pscustomobject]@{ FullName = 'C:\Users\WDAGUtilityAccount' }
             )
         }
         $result = @(Get-RealUserProfilePaths)
-        $result | Should -Be @('C:\Users\LeonGottschalk')
+        $result | Should -Be @('C:\Users\UserOne')
     }
 
     It 'falls back to the filesystem view when the WMI query fails' {
@@ -132,15 +132,15 @@ Describe 'Get-RelaxDecision' {
             Mock Test-IsCloudPc { $true }
         }
 
-        It 'relaxes for a single fresh profile although OOBE is Completed (W365 field case)' {
-            $p = New-FakeProfile 'LeonGottschalk' 0.6
+        It 'relaxes for a single fresh profile although OOBE is Completed (first connect)' {
+            $p = New-FakeProfile 'CloudPcUser' 0.6
             $d = Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15
             $d.Active | Should -BeTrue
             $d.IsCloudPc | Should -BeTrue
         }
 
         It 'does not relax for an old profile (productive Cloud PC)' {
-            $p = New-FakeProfile 'LeonGottschalk' 30
+            $p = New-FakeProfile 'CloudPcUser' 30
             (Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15).Active | Should -BeFalse
         }
 
@@ -162,7 +162,7 @@ Describe 'Get-RelaxDecision' {
         }
     }
 
-    Context 'OOBE InProgress (Windows Backup for Organizations, v2.2 behaviour)' {
+    Context 'OOBE InProgress (Windows Backup for Organizations)' {
         It 'relaxes for a single fresh profile during OOBE' {
             Mock Get-OobeState { 'InProgress' }
             $p = New-FakeProfile 'RestoreUser' 3
@@ -218,12 +218,12 @@ Describe 'Get-BootstrapDecision' {
         $d.ReasonCode | Should -Be 'ProfilesFound'
     }
 
-    It 'installs on a freshly provisioned Cloud PC with one fresh profile (W365 field case)' {
-        $script:fakeProfile = New-FakeProfile 'LeonGottschalk' 0.6
+    It 'installs on a freshly provisioned Cloud PC with one fresh profile' {
+        $script:fakeProfile = New-FakeProfile 'CloudPcUser' 0.6
         Mock Get-RealUserProfilePaths { @($script:fakeProfile) }
         Mock Test-IsCloudPc { $true }
         # First-connect user is already visible in LogonUI on W365 -- must not block either.
-        Mock Get-ItemProperty { [pscustomobject]@{ LastLoggedOnUser = 'AzureAD\LeonGottschalk' } } -ParameterFilter { $Path -like '*LogonUI*' }
+        Mock Get-ItemProperty { [pscustomobject]@{ LastLoggedOnUser = 'AzureAD\CloudPcUser' } } -ParameterFilter { $Path -like '*LogonUI*' }
         $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
         $d.Install | Should -BeTrue
         $d.RelaxActive | Should -BeTrue
@@ -248,7 +248,7 @@ Describe 'Get-BootstrapDecision' {
         $d.ReasonCode | Should -Be 'UptimeExceeded'
     }
 
-    It 'installs on a Cloud PC despite uptime over the window when the relax is active (guard 4 exemption, v2.3-dev.3)' {
+    It 'installs on a Cloud PC despite uptime over the window when the relax is active (guard 4 exemption)' {
         # W365 reality: provisioned days ago, running headless ever since; the user's
         # first connect just created the profile. Uptime is meaningless here.
         $script:fakeProfile = New-FakeProfile 'FirstConnectUser' 0.6

scripts/Bootstrap/Install-AutopilotMonitor.ps1

@@ -6,8 +6,9 @@
     Designed to be deployed via Intune as a PowerShell Script during Autopilot.
     Runs very early in the enrollment process (first Intune action) and:
       1. Runs pre-flight guards to skip productive devices and ghost re-installs.
-         An OOBE-relax exemption allows install when a single freshly-created profile
-         appears DURING OOBE (the "Windows Backup for Organizations" restore case).
+         A relax exemption allows install when a single freshly-created profile
+         appears DURING OOBE (Windows Backup for Organizations restore) or on a
+         freshly provisioned Windows 365 Cloud PC.
       2. Downloads the monitoring agent ZIP from Azure Blob Storage
       3. Verifies integrity via SHA-256 hash from the version manifest (mandatory)
       4. Extracts the agent into %ProgramData%\AutopilotMonitor\Agent
@@ -15,14 +16,27 @@
       6. Verifies the runtime process actually launched
     Agent self-destructs when enrollment completes.
 
-    OOBE-relax flow (guards 2+3): a real user profile (or a real LastLoggedOnUser)
-    normally means "productive -> skip". Windows Backup for Organizations breaks that
-    by restoring settings and creating ONE profile while still in OOBE. We relax guards
-    2+3 ONLY when all three positives hold, and nothing else:
-      (a) the OS positively reports OOBE InProgress (Test-OobeInProgress), AND
-      (b) there is exactly ONE real user profile, AND
-      (c) that profile was created within $OobeProfileMaxAgeMinutes minutes.
-    Any miss keeps the original skip (SKIP-safe: we never install on uncertainty).
+    Relax flow (guards 2+3): a real user profile (or a real LastLoggedOnUser)
+    normally means "productive -> skip". Two legitimate flows break that assumption:
+
+    (1) Windows Backup for Organizations: one user signs in + restores DURING OOBE.
+        Trigger: the OS positively reports OOBE InProgress.
+
+    (2) Windows 365 Cloud PC: W365 provisions headless -- OOBE and Intune enrollment
+        complete before any user ever connects, so OOBE is never InProgress when
+        this script runs. The assigned user's profile is created at first connect,
+        typically seconds before Intune pulls this script. Trigger: the device
+        positively identifies as a Cloud PC via TWO local markers (both required):
+        the HKLM\SOFTWARE\Microsoft\Windows365 registry key AND the
+        CloudManagedDesktopExtension service.
+
+    Either trigger relaxes guards 2+3 ONLY when additionally:
+      (a) there is exactly ONE real user profile, AND
+      (b) that profile was created within $OobeProfileMaxAgeMinutes minutes.
+    The Cloud PC trigger additionally exempts guard 4 (uptime window) -- see
+    .PARAMETER MaxBootstrapWindowHours. Any miss keeps the original skip
+    (SKIP-safe: we never install on uncertainty). On productive devices the
+    profile is old, so (b) keeps skipping correctly.
 
 .PARAMETER AgentDownloadUrl
     URL to download the agent ZIP from. Defaults to the production download endpoint;
@@ -36,11 +50,14 @@
     Maximum device uptime (hours) within which the bootstrap is still considered
     valid. Devices booted more than this many hours ago are skipped because we no
     longer trust their OOBE state. Default: 12.
+    Not applied while the Cloud PC relax is active: a Cloud PC runs headless for
+    days between provisioning and the user's first connect, so the fresh-profile
+    window (OobeProfileMaxAgeMinutes) is the time anchor there, not boot uptime.
 
 .PARAMETER OobeProfileMaxAgeMinutes
-    Maximum age (minutes) of the single profile that may appear during OOBE for the
-    OOBE-relax exemption to apply. The restore->bootstrap gap is always minutes; an
-    older profile is treated as a productive device. Default: 15.
+    Maximum age (minutes) of the single profile that may appear for the relax
+    exemption to apply. The restore/first-connect -> bootstrap gap is always
+    minutes; an older profile is treated as a productive device. Default: 15.
 
 .NOTES
     - Agent is temporary and auto-removes after enrollment.
@@ -50,12 +67,24 @@
     - Scheduled Task survives reboots during enrollment.
     - OOBE detection uses Windows.System.Profile.SystemSetupInfo.OutOfBoxExperienceState.
       Requires Windows 10, version 1809 (introduced in 10.0.17763.0). Older builds lack
-      the class -> Test-OobeInProgress returns $false -> original (skip) behaviour. Docs:
+      the class -> state reads as 'Unavailable' -> original (skip) behaviour. Docs:
       https://learn.microsoft.com/en-us/uwp/api/windows.system.profile.systemsetupinfo
+    - Guard/relax logic lives in functions; the script only executes when run
+      directly. Dot-sourcing it (as the Pester suite in
+      Install-AutopilotMonitor.Tests.ps1 does) loads the functions without side effects.
     - This script MUST remain pure ASCII (no Unicode/UTF-8 special chars).
       PowerShell 5.1 (IME) reads scripts without BOM as ANSI, corrupting multi-byte chars.
 
 .CHANGELOG
+    2026-08-08  v2.3  Windows 365 Cloud PC support: a positively identified Cloud PC
+                      (Windows365 registry key AND CloudManagedDesktopExtension
+                      service) now triggers the guard 2+3 relax alongside OOBE
+                      InProgress; the single-fresh-profile conditions are unchanged
+                      and guard 4 (uptime window) is exempted for Cloud PCs.
+                      Raw OOBE state and Cloud PC marker states are now logged.
+                      Guard/relax logic refactored into functions with a dot-source
+                      entry guard so the Pester suite can test it without executing
+                      the bootstrap; behaviour when run directly is unchanged.
     2026-07-20  v2.2  Switched default download endpoint from the legacy blob
                       (autopilotmonitor.blob.core.windows.net) to the Front Door alias
                       https://download.autopilotmonitor.com/agent/ (route /agent/*).
@@ -97,7 +126,7 @@ param(
 )
 
 # Script version (bump on meaningful changes; see .CHANGELOG above)
-$ScriptVersion = "2.2"
+$ScriptVersion = "2.3"
 
 # Configuration - Everything in ProgramData for easy cleanup
 $AgentBasePath = "$env:ProgramData\AutopilotMonitor"
@@ -105,89 +134,151 @@ $AgentBinPath = "$AgentBasePath\Agent"
 $AgentLogPath = "$AgentBasePath\Logs"
 $LogFile = "$AgentLogPath\bootstrap_agent.log"
 
-New-Item -Path $AgentBasePath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
-New-Item -Path $AgentBinPath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
-New-Item -Path $AgentLogPath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
-
+# Write-Host (NOT Write-Output): log calls happen inside functions that return
+# decision objects; Write-Output would leak every log line into those return values.
 function Write-Log {
     param([string]$Message)
     $timestamp = Get-Date -Format "yyyy-MM-dd HH:mm:ss"
     $logMessage = "[$timestamp] $Message"
-    Write-Output $logMessage
+    Write-Host $logMessage
     Add-Content -Path $LogFile -Value $logMessage -ErrorAction SilentlyContinue
 }
 
-# Positive OOBE check via the documented WinRT API
+# Raw OOBE state via the documented WinRT API
 # Windows.System.Profile.SystemSetupInfo.OutOfBoxExperienceState.
-# Returns $true ONLY when the OS reports InProgress. Any other state (Completed/NotStarted),
-# an older OS without the class (< Win10 1809 / 10.0.17763.0), or any error returns $false
+# Returns the state string (InProgress/Completed/NotStarted). An older OS without the
+# class (< Win10 1809 / 10.0.17763.0) or any error returns 'Unavailable'
 # -> SKIP-safe (we never relax a guard on uncertainty).
-# Docs: https://learn.microsoft.com/en-us/uwp/api/windows.system.profile.systemsetupinfo
-function Test-OobeInProgress {
+function Get-OobeState {
     try {
         $null = [Windows.System.Profile.SystemSetupInfo, Windows.System.Profile, ContentType = WindowsRuntime]
-        return ([Windows.System.Profile.SystemSetupInfo]::OutOfBoxExperienceState).ToString() -eq 'InProgress'
+        return ([Windows.System.Profile.SystemSetupInfo]::OutOfBoxExperienceState).ToString()
     }
     catch {
+        return 'Unavailable'
+    }
+}
+
+# Positive Windows 365 Cloud PC detection. Local WMI/SMBIOS on a Cloud PC only
+# reports the generic Manufacturer='Microsoft Corporation' / Model='Virtual Machine',
+# so identification uses two W365-specific markers instead. BOTH are required (AND):
+# each alone has look-alikes (e.g. W365 Boot physical clients, other managed-desktop
+# agents). Identity and marker states are logged for diagnosis; any error returns
+# $false (SKIP-safe).
+function Test-IsCloudPc {
+    try {
+        $cs = Get-CimInstance Win32_ComputerSystem -ErrorAction Stop
+        Write-Log "Computer identity: Manufacturer='$($cs.Manufacturer)' Model='$($cs.Model)'."
+    }
+    catch { Write-Log "INFO: computer identity query failed: $($_.Exception.Message)" }
+
+    try {
+        $regMarker = Test-Path 'HKLM:\SOFTWARE\Microsoft\Windows365'
+        $svcMarker = $null -ne (Get-Service -Name 'CloudManagedDesktopExtension' -ErrorAction SilentlyContinue)
+        Write-Log "Cloud PC markers: Windows365 registry key=$regMarker; CloudManagedDesktopExtension service=$svcMarker."
+        return ($regMarker -and $svcMarker)
+    }
+    catch {
+        Write-Log "INFO: Cloud PC marker check failed: $($_.Exception.Message)"
         return $false
     }
 }
 
-try {
-    Write-Log "===== Autopilot Monitor Bootstrap Started ====="
-    Write-Log "Bootstrap script version: v$ScriptVersion"
+# Collects real (non-special) user profiles as full paths (WMI Special flag + filesystem).
+# NOTE: callers MUST wrap the result in @(...). PowerShell unrolls function output, so an
+# empty result returns $null and a single path returns a scalar string, whose [0] indexer
+# would yield its first char ('C') instead of the full path.
+function Get-RealUserProfilePaths {
+    $excludePattern = '^(defaultuser\d*|Public|Default( User)?|All Users|WDAGUtilityAccount)$'
+    @(
+        try {
+            Get-CimInstance Win32_UserProfile -ErrorAction Stop |
+                Where-Object { -not $_.Special -and $_.LocalPath -like 'C:\Users\*' } |
+                ForEach-Object { $_.LocalPath }
+        } catch { Write-Log "INFO: WMI profile query failed, continuing with filesystem check." }
+
+        (Get-ChildItem 'C:\Users' -Directory -ErrorAction SilentlyContinue).FullName
+    ) | Where-Object { $_ -and (Split-Path $_ -Leaf) -notmatch $excludePattern } |
+        Select-Object -Unique
+}
+
+# Relax: the ONLY exemption to guards 2+3. Two triggers (see .DESCRIPTION):
+#   (1) OOBE InProgress          -> Windows Backup for Organizations restore
+#   (2) Cloud PC identity        -> Windows 365 (headless OOBE, profile at first connect)
+# Either trigger additionally requires: exactly one real profile AND that profile
+# created < $OobeProfileMaxAgeMinutes minutes ago. Any miss keeps the original skip.
+# Returns an object with: Active (bool), OobeState (string), IsCloudPc (bool).
+function Get-RelaxDecision {
+    param(
+        [string[]]$ProfilePaths,
+        [int]$OobeProfileMaxAgeMinutes
+    )
+    if ($null -eq $ProfilePaths) { $ProfilePaths = @() }
+
+    $relaxActive = $false
+    $oobeState = Get-OobeState
+    $oobeInProgress = ($oobeState -eq 'InProgress')
+    $isCloudPc = Test-IsCloudPc
+    if ($isCloudPc) {
+        Write-Log "Cloud PC detected (OOBE state: $oobeState)."
+    }
+
+    $relaxTrigger = $null
+    if ($oobeInProgress) {
+        $relaxTrigger = "OOBE InProgress (Windows Backup restore case)"
+    } elseif ($isCloudPc) {
+        $relaxTrigger = "Cloud PC (headless provisioning, OOBE state: $oobeState)"
+    }
+
+    if ($ProfilePaths.Count -eq 1 -and $relaxTrigger) {
+        try {
+            $created = (Get-Item -LiteralPath $ProfilePaths[0] -Force -ErrorAction Stop).CreationTimeUtc
+            $ageMin = ((Get-Date).ToUniversalTime() - $created).TotalMinutes
+            if ($ageMin -ge 0 -and $ageMin -lt $OobeProfileMaxAgeMinutes) {
+                $relaxActive = $true
+                Write-Log ("Relax active: {0} + single profile created {1:N1}min ago (< {2}min). Guards 2+3 relaxed." -f $relaxTrigger, $ageMin, $OobeProfileMaxAgeMinutes)
+            } else {
+                Write-Log ("Relax NOT applied: {0} + single profile '{1}', but profile created {2:N1}min ago (created {3:u}) is outside the [0, {4})min window." -f $relaxTrigger, (Split-Path $ProfilePaths[0] -Leaf), $ageMin, $created, $OobeProfileMaxAgeMinutes)
+            }
+        } catch { Write-Log "INFO: profile age check failed; relax not applied. $($_.Exception.Message)" }
+    } elseif ($ProfilePaths.Count -eq 1) {
+        Write-Log "Relax NOT applied: single profile present but neither OOBE InProgress nor Cloud PC (OOBE state: $oobeState)."
+    } elseif ($ProfilePaths.Count -gt 1) {
+        Write-Log ("Relax NOT applied: {0} real profiles present (relax requires exactly one). OOBE state: {1}; CloudPC: {2}." -f $ProfilePaths.Count, $oobeState, $isCloudPc)
+    }
+
+    return [pscustomobject]@{
+        Active    = $relaxActive
+        OobeState = $oobeState
+        IsCloudPc = $isCloudPc
+    }
+}
+
+# Runs pre-flight guards 1-5 and returns the install decision WITHOUT side effects
+# beyond logging. Returns an object with:
+#   Install (bool), ReasonCode (null | AlreadyDeployed | ProfilesFound |
+#   LastLoggedOnUser | UptimeExceeded | AgentPresent), RelaxActive (bool).
+function Get-BootstrapDecision {
+    param(
+        [int]$MaxBootstrapWindowHours,
+        [int]$OobeProfileMaxAgeMinutes,
+        [string]$AgentBinPath
+    )
 
     # Guard 1: Agent was already deployed on this device (registry marker survives self-destruct)
     $deployed = (Get-ItemProperty -Path 'HKLM:\SOFTWARE\AutopilotMonitor' -Name 'Deployed' -ErrorAction SilentlyContinue).Deployed
     if ($deployed) {
         Write-Log "SKIP: Agent was previously deployed at $deployed."
-        exit 0
+        return [pscustomobject]@{ Install = $false; ReasonCode = 'AlreadyDeployed'; RelaxActive = $false }
     }
 
-    # Collect real (non-special) user profiles as full paths (WMI Special flag + filesystem).
-    $excludePattern = '^(defaultuser\d*|Public|Default( User)?|All Users|WDAGUtilityAccount)$'
-
-    # NOTE: the outer @() is required. Without it the trailing Where/Select pipeline
-    # unwraps a single result back to a scalar string, so $profilePaths[0] would index
-    # into the string and return its first char ('C') instead of the full path.
-    $profilePaths = @(
-        @(
-            try {
-                Get-CimInstance Win32_UserProfile -ErrorAction Stop |
-                    Where-Object { -not $_.Special -and $_.LocalPath -like 'C:\Users\*' } |
-                    ForEach-Object { $_.LocalPath }
-            } catch { Write-Log "INFO: WMI profile query failed, continuing with filesystem check." }
-
-            (Get-ChildItem 'C:\Users' -Directory -ErrorAction SilentlyContinue).FullName
-        ) | Where-Object { $_ -and (Split-Path $_ -Leaf) -notmatch $excludePattern } |
-            Select-Object -Unique
-    )
-
-    # OOBE-relax: the ONLY exemption to guards 2+3. Matches exactly the Windows Backup for
-    # Organizations restore (one user signs in + restores DURING OOBE). All three must hold:
-    #   OOBE InProgress  AND  exactly one profile  AND  that profile created < N minutes ago.
-    $oobeRelax = $false
-    $oobeInProgress = Test-OobeInProgress
-    if ($profilePaths.Count -eq 1 -and $oobeInProgress) {
-        try {
-            $created = (Get-Item -LiteralPath $profilePaths[0] -Force -ErrorAction Stop).CreationTimeUtc
-            $ageMin = ((Get-Date).ToUniversalTime() - $created).TotalMinutes
-            if ($ageMin -ge 0 -and $ageMin -lt $OobeProfileMaxAgeMinutes) {
-                $oobeRelax = $true
-                Write-Log ("OOBE-relax active: OOBE InProgress + single profile created {0:N1}min ago (< {1}min). Guards 2+3 relaxed (Windows Backup restore case)." -f $ageMin, $OobeProfileMaxAgeMinutes)
-            } else {
-                Write-Log ("OOBE-relax NOT applied: OOBE InProgress + single profile '{0}', but profile created {1:N1}min ago (created {2:u}) is outside the [0, {3})min window." -f (Split-Path $profilePaths[0] -Leaf), $ageMin, $created, $OobeProfileMaxAgeMinutes)
-            }
-        } catch { Write-Log "INFO: profile age check failed; OOBE-relax not applied. $($_.Exception.Message)" }
-    } elseif ($profilePaths.Count -eq 1 -and -not $oobeInProgress) {
-        Write-Log "OOBE-relax NOT applied: single profile present but OutOfBoxExperienceState != InProgress (OOBE already finished / not detectable)."
-    } elseif ($profilePaths.Count -gt 1) {
-        Write-Log ("OOBE-relax NOT applied: {0} real profiles present (relax requires exactly one)." -f $profilePaths.Count)
-    }
+    # The @() wrap is required, see NOTE on Get-RealUserProfilePaths.
+    $profilePaths = @(Get-RealUserProfilePaths)
+    $relax = Get-RelaxDecision -ProfilePaths $profilePaths -OobeProfileMaxAgeMinutes $OobeProfileMaxAgeMinutes
 
     # Guard 2: No real user profile should exist yet (primary productive-device guard),
-    # unless the OOBE-relax signature holds.
-    if ($profilePaths.Count -gt 0 -and -not $oobeRelax) {
+    # unless the relax signature holds.
+    if ($profilePaths.Count -gt 0 -and -not $relax.Active) {
         $details = (($profilePaths | ForEach-Object {
             $leaf = Split-Path $_ -Leaf
             try {
@@ -195,26 +286,33 @@ try {
                 "{0} (created {1:u}, {2:N1}min ago)" -f $leaf, $c, ((Get-Date).ToUniversalTime() - $c).TotalMinutes
             } catch { "$leaf (age unknown)" }
         }) | Select-Object -First 3) -join '; '
-        Write-Log "SKIP: Real user profile(s) found ($details). OOBE InProgress=$oobeInProgress. Device appears productive."
-        exit 0
+        Write-Log "SKIP: Real user profile(s) found ($details). OOBE state: $($relax.OobeState). CloudPC: $($relax.IsCloudPc). Device appears productive."
+        return [pscustomobject]@{ Install = $false; ReasonCode = 'ProfilesFound'; RelaxActive = $false }
     }
 
     # Guard 3: LastLoggedOnUser - during Device ESP no real user has logged on yet
-    # (same OOBE-relax exemption: the restoring user signs in during OOBE).
+    # (same relax exemption: the restoring/first-connect user signs in legitimately).
     $lastLoggedOnUser = (Get-ItemProperty -Path 'HKLM:\SOFTWARE\Microsoft\Windows\CurrentVersion\Authentication\LogonUI' -Name 'LastLoggedOnUser' -EA SilentlyContinue).LastLoggedOnUser
-    if ($lastLoggedOnUser -and $lastLoggedOnUser -notmatch 'defaultuser\d*' -and -not $oobeRelax) {
+    if ($lastLoggedOnUser -and $lastLoggedOnUser -notmatch 'defaultuser\d*' -and -not $relax.Active) {
         Write-Log "SKIP: LastLoggedOnUser found ($lastLoggedOnUser). Device appears productive."
-        exit 0
+        return [pscustomobject]@{ Install = $false; ReasonCode = 'LastLoggedOnUser'; RelaxActive = $false }
     }
 
     # Guard 4: Bootstrap window check - device uptime must be within accepted OOBE window.
     # Sleep/standby does not reset uptime, only real boot/restart does.
+    # Exempted while the Cloud PC relax is active: a Cloud PC runs headless from
+    # provisioning until the user's first connect (often days), so boot uptime says
+    # nothing there -- the fresh-profile window of the relax is the time anchor.
     $lastBoot = (Get-CimInstance Win32_OperatingSystem).LastBootUpTime
     $uptimeHours = ((Get-Date) - $lastBoot).TotalHours
     Write-Log "Device uptime: $([int]$uptimeHours)h (last boot: $lastBoot)"
     if ($uptimeHours -gt $MaxBootstrapWindowHours) {
-        Write-Log "SKIP: Device uptime is $([int]$uptimeHours)h. OOBE state is older than accepted bootstrap window of ${MaxBootstrapWindowHours}h."
-        exit 0
+        if ($relax.Active -and $relax.IsCloudPc) {
+            Write-Log "Uptime $([int]$uptimeHours)h exceeds the ${MaxBootstrapWindowHours}h window, but the Cloud PC relax is active (fresh first-connect profile is the time anchor). Continuing."
+        } else {
+            Write-Log "SKIP: Device uptime is $([int]$uptimeHours)h. OOBE state is older than accepted bootstrap window of ${MaxBootstrapWindowHours}h."
+            return [pscustomobject]@{ Install = $false; ReasonCode = 'UptimeExceeded'; RelaxActive = $relax.Active }
+        }
     }
 
     # Guard 5: Is the agent already installed? (leftover from previous run)
@@ -222,148 +320,175 @@ try {
         $existingAgent = Get-ChildItem -Path $AgentBinPath -Filter "AutopilotMonitor.Agent.exe" -ErrorAction SilentlyContinue
         if ($existingAgent) {
             Write-Log "SKIP: Agent already installed at $($existingAgent.FullName)."
+            return [pscustomobject]@{ Install = $false; ReasonCode = 'AgentPresent'; RelaxActive = $relax.Active }
+        }
+    }
+
+    return [pscustomobject]@{ Install = $true; ReasonCode = $null; RelaxActive = $relax.Active }
+}
+
+# Main bootstrap flow. Only invoked when the script is run directly (see entry guard
+# at the bottom); never on dot-source.
+function Invoke-Bootstrap {
+    try {
+        New-Item -Path $AgentBasePath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
+        New-Item -Path $AgentBinPath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
+        New-Item -Path $AgentLogPath -ItemType Directory -Force -ErrorAction SilentlyContinue | Out-Null
+
+        Write-Log "===== Autopilot Monitor Bootstrap Started ====="
+        Write-Log "Bootstrap script version: v$ScriptVersion"
+
+        $decision = Get-BootstrapDecision -MaxBootstrapWindowHours $MaxBootstrapWindowHours -OobeProfileMaxAgeMinutes $OobeProfileMaxAgeMinutes -AgentBinPath $AgentBinPath
+        if (-not $decision.Install) {
             exit 0
         }
-    }
 
-    Write-Log "Pre-flight checks passed -- no prior deployment, no productive-device signals, within bootstrap window (oobeRelax=$oobeRelax)"
+        Write-Log "Pre-flight checks passed -- no prior deployment, no productive-device signals, within bootstrap window (relaxActive=$($decision.RelaxActive))"
 
-    # Download and extract agent binaries
-    $agentExePath = Join-Path $AgentBinPath "AutopilotMonitor.Agent.exe"
+        # Download and extract agent binaries
+        $agentExePath = Join-Path $AgentBinPath "AutopilotMonitor.Agent.exe"
 
-    if (Test-Path $agentExePath) {
-        Write-Log "Agent already installed at $agentExePath"
-    }
-    else {
-        Write-Log "Downloading agent from $AgentDownloadUrl..."
-
-        try {
-            # Derive manifest URL from the agent download URL (same blob container)
-            $versionJsonUrl = $AgentDownloadUrl -replace '[^/]+$', $VersionJsonName
-            $expectedSha256 = $null
-            $manifestAttempts = 3
-            $manifestDelays = @(1, 2)   # short backoff between attempts; do not block enrollment
-
-            for ($attempt = 1; $attempt -le $manifestAttempts; $attempt++) {
-                try {
-                    Write-Log "Fetching $VersionJsonName (attempt ${attempt}/${manifestAttempts}) from $versionJsonUrl for integrity verification..."
-                    $versionJsonResponse = Invoke-RestMethod -Uri $versionJsonUrl -UseBasicParsing -TimeoutSec 5 -ErrorAction Stop
-                    if ($versionJsonResponse.sha256) {
-                        $expectedSha256 = $versionJsonResponse.sha256.ToLowerInvariant()
-                        Write-Log "SHA-256 hash from manifest: $expectedSha256 (version: $($versionJsonResponse.version))"
-                    } else {
-                        Write-Log "WARNING: Manifest has no sha256 field - integrity cannot be verified."
-                    }
-                    break   # manifest reached (with or without hash); retrying would not help
-                }
-                catch {
-                    Write-Log "WARNING: Could not fetch integrity manifest (attempt $attempt): $($_.Exception.Message)"
-                    if ($attempt -lt $manifestAttempts) {
-                        Start-Sleep -Seconds $manifestDelays[$attempt - 1]
-                    }
-                }
-            }
-
-            $zipPath = Join-Path $env:TEMP "AutopilotMonitor-Agent.zip"
-            $maxDownloadAttempts = 3
-            $downloadAttempt = 0
-
-            do {
-                $downloadAttempt++
-                try {
-                    Write-Log "Download attempt ${downloadAttempt}/${maxDownloadAttempts}"
-                    $downloadStopwatch = [System.Diagnostics.Stopwatch]::StartNew()
-                    Invoke-WebRequest `
-                        -Uri $AgentDownloadUrl `
-                        -OutFile $zipPath `
-                        -UseBasicParsing `
-                        -TimeoutSec 30 `
-                        -ErrorAction Stop
-                    $downloadStopwatch.Stop()
-                    $downloadSeconds = [math]::Round($downloadStopwatch.Elapsed.TotalSeconds, 1)
-                    Write-Log "Downloaded agent to $zipPath (took ${downloadSeconds}s)"
-                    break
-                }
-                catch {
-                    if ($downloadAttempt -ge $maxDownloadAttempts) {
-                        throw
-                    }
-
-                    $retryDelaysInSeconds = @(2, 4, 8)
-                    $retryDelaySeconds = $retryDelaysInSeconds[$downloadAttempt - 1]
-                    Write-Log "Download failed (attempt $downloadAttempt): $($_.Exception.Message). Retrying in ${retryDelaySeconds}s..."
-                    Start-Sleep -Seconds $retryDelaySeconds
-                }
-            } while ($downloadAttempt -lt $maxDownloadAttempts)
-
-            # SHA-256 from the version manifest is the only accepted integrity proof.
-            # No hash -> refuse to install an unverified ZIP (SKIP-safe security posture).
-            if (-not $expectedSha256) {
-                throw "No SHA-256 hash available from manifest - refusing to install unverified agent ZIP."
-            }
-            $actualSha256 = (Get-FileHash $zipPath -Algorithm SHA256).Hash.ToLowerInvariant()
-            Write-Log "Validating SHA-256 hash against manifest"
-            if ($actualSha256 -ne $expectedSha256) {
-                throw "SHA-256 integrity check FAILED. Expected='$expectedSha256', Actual='$actualSha256'. Download may be tampered or corrupted."
-            }
-            Write-Log "SHA-256 integrity check passed"
-
-            Expand-Archive -Path $zipPath -DestinationPath $AgentBinPath -Force
-            Write-Log "Extracted agent to $AgentBinPath"
-
-            Remove-Item $zipPath -Force -ErrorAction SilentlyContinue
-            Write-Log "Cleaned up temporary files"
-
-            if (-not (Test-Path $agentExePath)) {
-                throw "Agent executable not found after extraction at $agentExePath"
-            }
-
-            Write-Log "Agent installation completed successfully"
+        if (Test-Path $agentExePath) {
+            Write-Log "Agent already installed at $agentExePath"
         }
-        catch {
-            Write-Log "ERROR downloading/extracting agent: $($_.Exception.Message)"
-            throw
+        else {
+            Write-Log "Downloading agent from $AgentDownloadUrl..."
+
+            try {
+                # Derive manifest URL from the agent download URL (same blob container)
+                $versionJsonUrl = $AgentDownloadUrl -replace '[^/]+$', $VersionJsonName
+                $expectedSha256 = $null
+                $manifestAttempts = 3
+                $manifestDelays = @(1, 2)   # short backoff between attempts; do not block enrollment
+
+                for ($attempt = 1; $attempt -le $manifestAttempts; $attempt++) {
+                    try {
+                        Write-Log "Fetching $VersionJsonName (attempt ${attempt}/${manifestAttempts}) from $versionJsonUrl for integrity verification..."
+                        $versionJsonResponse = Invoke-RestMethod -Uri $versionJsonUrl -UseBasicParsing -TimeoutSec 5 -ErrorAction Stop
+                        if ($versionJsonResponse.sha256) {
+                            $expectedSha256 = $versionJsonResponse.sha256.ToLowerInvariant()
+                            Write-Log "SHA-256 hash from manifest: $expectedSha256 (version: $($versionJsonResponse.version))"
+                        } else {
+                            Write-Log "WARNING: Manifest has no sha256 field - integrity cannot be verified."
+                        }
+                        break   # manifest reached (with or without hash); retrying would not help
+                    }
+                    catch {
+                        Write-Log "WARNING: Could not fetch integrity manifest (attempt $attempt): $($_.Exception.Message)"
+                        if ($attempt -lt $manifestAttempts) {
+                            Start-Sleep -Seconds $manifestDelays[$attempt - 1]
+                        }
+                    }
+                }
+
+                $zipPath = Join-Path $env:TEMP "AutopilotMonitor-Agent.zip"
+                $maxDownloadAttempts = 3
+                $downloadAttempt = 0
+
+                do {
+                    $downloadAttempt++
+                    try {
+                        Write-Log "Download attempt ${downloadAttempt}/${maxDownloadAttempts}"
+                        $downloadStopwatch = [System.Diagnostics.Stopwatch]::StartNew()
+                        Invoke-WebRequest `
+                            -Uri $AgentDownloadUrl `
+                            -OutFile $zipPath `
+                            -UseBasicParsing `
+                            -TimeoutSec 30 `
+                            -ErrorAction Stop
+                        $downloadStopwatch.Stop()
+                        $downloadSeconds = [math]::Round($downloadStopwatch.Elapsed.TotalSeconds, 1)
+                        Write-Log "Downloaded agent to $zipPath (took ${downloadSeconds}s)"
+                        break
+                    }
+                    catch {
+                        if ($downloadAttempt -ge $maxDownloadAttempts) {
+                            throw
+                        }
+
+                        $retryDelaysInSeconds = @(2, 4, 8)
+                        $retryDelaySeconds = $retryDelaysInSeconds[$downloadAttempt - 1]
+                        Write-Log "Download failed (attempt $downloadAttempt): $($_.Exception.Message). Retrying in ${retryDelaySeconds}s..."
+                        Start-Sleep -Seconds $retryDelaySeconds
+                    }
+                } while ($downloadAttempt -lt $maxDownloadAttempts)
+
+                # SHA-256 from the version manifest is the only accepted integrity proof.
+                # No hash -> refuse to install an unverified ZIP (SKIP-safe security posture).
+                if (-not $expectedSha256) {
+                    throw "No SHA-256 hash available from manifest - refusing to install unverified agent ZIP."
+                }
+                $actualSha256 = (Get-FileHash $zipPath -Algorithm SHA256).Hash.ToLowerInvariant()
+                Write-Log "Validating SHA-256 hash against manifest"
+                if ($actualSha256 -ne $expectedSha256) {
+                    throw "SHA-256 integrity check FAILED. Expected='$expectedSha256', Actual='$actualSha256'. Download may be tampered or corrupted."
+                }
+                Write-Log "SHA-256 integrity check passed"
+
+                Expand-Archive -Path $zipPath -DestinationPath $AgentBinPath -Force
+                Write-Log "Extracted agent to $AgentBinPath"
+
+                Remove-Item $zipPath -Force -ErrorAction SilentlyContinue
+                Write-Log "Cleaned up temporary files"
+
+                if (-not (Test-Path $agentExePath)) {
+                    throw "Agent executable not found after extraction at $agentExePath"
+                }
+
+                Write-Log "Agent installation completed successfully"
+            }
+            catch {
+                Write-Log "ERROR downloading/extracting agent: $($_.Exception.Message)"
+                throw
+            }
         }
-    }
 
-    Write-Log "Calling agent install mode (--install)..."
-    & $agentExePath --install
-    $installExitCode = $LASTEXITCODE
-    if ($installExitCode -ne 0) {
-        throw "Agent install failed with exit code $installExitCode"
-    }
-    Write-Log "Agent install mode completed successfully"
+        Write-Log "Calling agent install mode (--install)..."
+        & $agentExePath --install
+        $installExitCode = $LASTEXITCODE
+        if ($installExitCode -ne 0) {
+            throw "Agent install failed with exit code $installExitCode"
+        }
+        Write-Log "Agent install mode completed successfully"
 
-    $runtimeProcessName = 'AutopilotMonitor.Agent'
-    $verifyTimeoutSec = 10
-    $verifyDeadline = (Get-Date).AddSeconds($verifyTimeoutSec)
-    $runtimeProc = $null
-    while ((Get-Date) -lt $verifyDeadline) {
-        $runtimeProc = Get-Process -Name $runtimeProcessName -ErrorAction SilentlyContinue | Select-Object -First 1
-        if ($null -ne $runtimeProc) { break }
-        Start-Sleep -Milliseconds 500
-    }
-    if ($null -ne $runtimeProc) {
-        $startedUtc = 'unavailable'
-        try { $startedUtc = $runtimeProc.StartTime.ToUniversalTime().ToString('o') } catch { }
-        Write-Log ("Runtime process verified: name={0}.exe pid={1} startedUtc={2}" -f $runtimeProcessName, $runtimeProc.Id, $startedUtc)
-    } else {
-        Write-Log ("WARNING: Runtime process verification FAILED. Agent --install reported success but no '{0}.exe' process appeared within {1}s. Likely silent block (AV/EDR, AppLocker/WDAC) of the runtime launch. Agent should still come up at next boot via the BootTrigger task. Check Event Viewer > Microsoft > Windows > TaskScheduler/Operational and AV/EDR logs for '{0}.exe'." -f $runtimeProcessName, $verifyTimeoutSec)
-    }
+        $runtimeProcessName = 'AutopilotMonitor.Agent'
+        $verifyTimeoutSec = 10
+        $verifyDeadline = (Get-Date).AddSeconds($verifyTimeoutSec)
+        $runtimeProc = $null
+        while ((Get-Date) -lt $verifyDeadline) {
+            $runtimeProc = Get-Process -Name $runtimeProcessName -ErrorAction SilentlyContinue | Select-Object -First 1
+            if ($null -ne $runtimeProc) { break }
+            Start-Sleep -Milliseconds 500
+        }
+        if ($null -ne $runtimeProc) {
+            $startedUtc = 'unavailable'
+            try { $startedUtc = $runtimeProc.StartTime.ToUniversalTime().ToString('o') } catch { }
+            Write-Log ("Runtime process verified: name={0}.exe pid={1} startedUtc={2}" -f $runtimeProcessName, $runtimeProc.Id, $startedUtc)
+        } else {
+            Write-Log ("WARNING: Runtime process verification FAILED. Agent --install reported success but no '{0}.exe' process appeared within {1}s. Likely silent block (AV/EDR, AppLocker/WDAC) of the runtime launch. Agent should still come up at next boot via the BootTrigger task. Check Event Viewer > Microsoft > Windows > TaskScheduler/Operational and AV/EDR logs for '{0}.exe'." -f $runtimeProcessName, $verifyTimeoutSec)
+        }
 
-    Write-Log "===== Bootstrap Completed Successfully ====="
+        Write-Log "===== Bootstrap Completed Successfully ====="
 
-    exit 0
+        exit 0
+    }
+    catch {
+        Write-Log "===== Bootstrap FAILED ====="
+        Write-Log "ERROR: $($_.Exception.Message)"
+        Write-Log "Stack trace: $($_.ScriptStackTrace)"
+        Write-Log "Please check log file: $LogFile"
+
+        $errMsg = "AutopilotMonitor bootstrap failed: $($_.Exception.Message)"
+        if ($errMsg.Length -gt 2048) { $errMsg = $errMsg.Substring(0, 1045) + '...' }
+        [Console]::Error.WriteLine($errMsg)
+
+        exit 1
+    }
 }
-catch {
-    Write-Log "===== Bootstrap FAILED ====="
-    Write-Log "ERROR: $($_.Exception.Message)"
-    Write-Log "Stack trace: $($_.ScriptStackTrace)"
-    Write-Log "Please check log file: $LogFile"
 
-    $errMsg = "AutopilotMonitor bootstrap failed: $($_.Exception.Message)"
-    if ($errMsg.Length -gt 2048) { $errMsg = $errMsg.Substring(0, 1045) + '...' }
-    [Console]::Error.WriteLine($errMsg)
-
-    exit 1
+# Entry guard: execute only when run as a script (IME, console). Dot-sourcing
+# (". .\Install-AutopilotMonitor.ps1", as the Pester suite does) only loads
+# the functions above and MUST stay side-effect free.
+if ($MyInvocation.InvocationName -ne '.') {
+    Invoke-Bootstrap
 }

scripts/Bootstrap/Test-ShouldBootstrapAgent.ps1

@@ -1,7 +1,9 @@
 # Autopilot Monitor Bootstrap Guard Test
 # Dry-run only: does not exit, does not install, only reports what WOULD happen.
-# Mirrors Install-AutopilotMonitor.ps1 incl. the OOBE-relax exemption for the
-# "Windows Backup for Organizations" restore case (guards 2+3).
+# Mirrors Install-AutopilotMonitor.ps1 (v2.3) incl. the relax exemption for
+# guards 2+3, triggered by "Windows Backup for Organizations" (OOBE InProgress)
+# or a positively identified Windows 365 Cloud PC, and the guard 4 (uptime)
+# exemption while the Cloud PC relax is active.
 
 param(
     [string]$AgentBinPath = 'C:\ProgramData\AutopilotMonitor\Agent',
@@ -54,6 +56,12 @@ function Test-OobeInProgress {
     }
 }
 
+# Positive Windows 365 Cloud PC detection: two local markers, BOTH required (AND),
+# because each alone has look-alikes. Mirrors Test-IsCloudPc in the bootstrapper.
+$cloudPcRegMarker = Test-Path 'HKLM:\SOFTWARE\Microsoft\Windows365'
+$cloudPcSvcMarker = $null -ne (Get-Service -Name 'CloudManagedDesktopExtension' -ErrorAction SilentlyContinue)
+$isCloudPc = ($cloudPcRegMarker -and $cloudPcSvcMarker)
+
 $AgentExePath = Join-Path $AgentBinPath 'AutopilotMonitor.Agent.exe'
 $MaxBootstrapWindowHours = 12
 
@@ -104,8 +112,9 @@ if ($wmiProfileQueryFailed) {
 
 $profileNames = $profilePaths | ForEach-Object { Split-Path $_ -Leaf }
 
-# OOBE-relax: the ONLY exemption to guards 2+3. Matches exactly the Windows Backup for
-# Organizations restore: OOBE InProgress AND exactly one profile AND that profile fresh.
+# Relax: the ONLY exemption to guards 2+3. Two triggers -- OOBE InProgress (Windows
+# Backup for Organizations restore) or Cloud PC identity (headless provisioning,
+# profile at first connect). Either additionally requires exactly one fresh profile.
 $oobeInProgress = Test-OobeInProgress
 $profileAgeMin = $null
 $oobeRelax = $false
@@ -114,12 +123,13 @@ if ($profilePaths.Count -eq 1) {
         $created = (Get-Item -LiteralPath $profilePaths[0] -Force -ErrorAction Stop).CreationTimeUtc
         $profileAgeMin = [math]::Round(((Get-Date).ToUniversalTime() - $created).TotalMinutes, 1)
     } catch { }
-    if ($oobeInProgress -and $null -ne $profileAgeMin -and $profileAgeMin -ge 0 -and $profileAgeMin -lt $OobeProfileMaxAgeMinutes) {
+    if (($oobeInProgress -or $isCloudPc) -and $null -ne $profileAgeMin -and $profileAgeMin -ge 0 -and $profileAgeMin -lt $OobeProfileMaxAgeMinutes) {
         $oobeRelax = $true
     }
 }
 
-Write-Step -Status 'INFO' -Message "OOBE: OutOfBoxExperienceState InProgress = $oobeInProgress ; profileCount = $($profilePaths.Count) ; singleProfileAgeMin = $profileAgeMin ; OOBE-relax = $oobeRelax"
+Write-Step -Status 'INFO' -Message "Cloud PC markers: Windows365 registry key = $cloudPcRegMarker ; CloudManagedDesktopExtension service = $cloudPcSvcMarker ; IsCloudPc = $isCloudPc"
+Write-Step -Status 'INFO' -Message "OOBE: OutOfBoxExperienceState InProgress = $oobeInProgress ; profileCount = $($profilePaths.Count) ; singleProfileAgeMin = $profileAgeMin ; relax = $oobeRelax"
 
 # Guard 2: No real user profile should exist yet (unless OOBE-relax holds)
 if ($profilePaths.Count -gt 0 -and -not $oobeRelax) {
@@ -129,7 +139,8 @@ if ($profilePaths.Count -gt 0 -and -not $oobeRelax) {
     $reasons.Add("Real user profile(s) found: $names")
 } elseif ($profilePaths.Count -gt 0 -and $oobeRelax) {
     $names = ($profileNames | Select-Object -First 3) -join ', '
-    Write-Step -Status 'PASS' -Message "Guard 2: Profile ($names) present but OOBE-relax active (single fresh profile in OOBE) -- not blocking."
+    $trigger = if ($oobeInProgress) { 'OOBE InProgress' } else { 'Cloud PC' }
+    Write-Step -Status 'PASS' -Message "Guard 2: Profile ($names) present but relax active ($trigger + single fresh profile) -- not blocking."
 } else {
     Write-Step -Status 'PASS' -Message 'Guard 2: No real user profiles found (combined WMI/filesystem view).'
 }
@@ -141,7 +152,7 @@ if ($lastLoggedOnUser -and $lastLoggedOnUser -notmatch 'defaultuser\d*' -and -no
     $wouldInstall = $false
     $reasons.Add("LastLoggedOnUser found: $lastLoggedOnUser")
 } elseif ($lastLoggedOnUser -and $lastLoggedOnUser -notmatch 'defaultuser\d*' -and $oobeRelax) {
-    Write-Step -Status 'PASS' -Message "Guard 3: LastLoggedOnUser ($lastLoggedOnUser) present but OOBE-relax active -- not blocking."
+    Write-Step -Status 'PASS' -Message "Guard 3: LastLoggedOnUser ($lastLoggedOnUser) present but relax active -- not blocking."
 } else {
     Write-Step -Status 'PASS' -Message "Guard 3: No real LastLoggedOnUser (value: '$lastLoggedOnUser')."
 }
@@ -155,9 +166,15 @@ try {
     $uptimeHours = ((Get-Date) - $lastBoot).TotalHours
 
     if ($uptimeHours -gt $MaxBootstrapWindowHours) {
-        Write-Step -Status 'SKIP' -Message "Guard 4: Device uptime is $([int]$uptimeHours)h. Older than accepted bootstrap window of ${MaxBootstrapWindowHours}h."
-        $wouldInstall = $false
-        $reasons.Add("Uptime exceeds bootstrap window: $([int]$uptimeHours)h > ${MaxBootstrapWindowHours}h")
+        if ($oobeRelax -and $isCloudPc) {
+            # Cloud PCs run headless for days before the user's first connect; the
+            # fresh-profile window is the time anchor there, not boot uptime.
+            Write-Step -Status 'PASS' -Message "Guard 4: Device uptime is $([int]$uptimeHours)h (over ${MaxBootstrapWindowHours}h), but the Cloud PC relax is active -- not blocking."
+        } else {
+            Write-Step -Status 'SKIP' -Message "Guard 4: Device uptime is $([int]$uptimeHours)h. Older than accepted bootstrap window of ${MaxBootstrapWindowHours}h."
+            $wouldInstall = $false
+            $reasons.Add("Uptime exceeds bootstrap window: $([int]$uptimeHours)h > ${MaxBootstrapWindowHours}h")
+        }
     } else {
         Write-Step -Status 'PASS' -Message "Guard 4: Device uptime is $([int]$uptimeHours)h and within bootstrap window of ${MaxBootstrapWindowHours}h."
     }
@@ -202,9 +219,12 @@ Write-Host "Deployed marker           : $deployed"
 Write-Host "DetectedProfileNames      : $($profileNames -join ', ')"
 Write-Host "ProfileCount              : $($profilePaths.Count)"
 Write-Host "OobeInProgress (WinRT)    : $oobeInProgress"
+Write-Host "CloudPcRegistryMarker     : $cloudPcRegMarker"
+Write-Host "CloudPcServiceMarker      : $cloudPcSvcMarker"
+Write-Host "IsCloudPc                 : $isCloudPc"
 Write-Host "SingleProfileAgeMinutes   : $profileAgeMin"
 Write-Host "OobeProfileMaxAgeMinutes  : $OobeProfileMaxAgeMinutes"
-Write-Host "OobeRelaxActive           : $oobeRelax"
+Write-Host "RelaxActive               : $oobeRelax"
 Write-Host "LastLoggedOnUser          : $lastLoggedOnUser"
 Write-Host "MaxBootstrapWindowHours   : $MaxBootstrapWindowHours"
 Write-Host "LastBootUpTime            : $lastBoot"

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Configuration/RemoteConfigMergerCompletenessTests.cs

@@ -0,0 +1,125 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Reflection;
+using AutopilotMonitor.Agent.V2.Core.Configuration;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Configuration
+{
+    /// <summary>
+    /// Completeness tripwire for <see cref="RemoteConfigMerger"/>: the merger hand-maps
+    /// <see cref="AgentConfigResponse"/> fields onto <c>AgentConfiguration</c>, and
+    /// historically new tenant knobs were forgotten there and silently ignored. Every public
+    /// property of <see cref="AgentConfigResponse"/> must be classified in exactly one of the
+    /// two lists below. A new property fails this test until a human either wires it through
+    /// <see cref="RemoteConfigMerger.Merge"/> or documents where else it is consumed.
+    /// </summary>
+    public sealed class RemoteConfigMergerCompletenessTests
+    {
+        /// <summary>
+        /// Fields <see cref="RemoteConfigMerger.Merge"/> maps onto <c>AgentConfiguration</c>.
+        /// Keep in sync with the Merge body — the test only proves classification coverage,
+        /// the value-level mapping itself is covered by <see cref="RemoteConfigMergerTests"/>.
+        /// </summary>
+        private static readonly string[] MergedByMerger =
+        {
+            nameof(AgentConfigResponse.SelfDestructOnComplete),
+            nameof(AgentConfigResponse.KeepLogFile),
+            nameof(AgentConfigResponse.RebootOnComplete),
+            nameof(AgentConfigResponse.EnableGeoLocation),
+            nameof(AgentConfigResponse.LogLevel),
+            nameof(AgentConfigResponse.RebootDelaySeconds),
+            nameof(AgentConfigResponse.ShowEnrollmentSummary),
+            nameof(AgentConfigResponse.EnrollmentSummaryTimeoutSeconds),
+            nameof(AgentConfigResponse.EnrollmentSummaryBrandingImageUrl),
+            nameof(AgentConfigResponse.EnrollmentSummaryLaunchRetrySeconds),
+            nameof(AgentConfigResponse.NtpServer),
+            nameof(AgentConfigResponse.EnableTimezoneAutoSet),
+            nameof(AgentConfigResponse.DiagnosticsUploadEnabled),
+            nameof(AgentConfigResponse.DiagnosticsUploadMode),
+            nameof(AgentConfigResponse.DiagnosticsLogPaths),
+            nameof(AgentConfigResponse.SendTraceEvents),
+            nameof(AgentConfigResponse.EnableEspContinueAnywayObservation),
+            nameof(AgentConfigResponse.UnrestrictedMode),
+            nameof(AgentConfigResponse.EnableImeMatchLog),
+            nameof(AgentConfigResponse.EnableGatherRuleDebugLog),
+            nameof(AgentConfigResponse.UploadIntervalSeconds),
+            nameof(AgentConfigResponse.MaxBatchSize),
+            nameof(AgentConfigResponse.MaxAuthFailures),
+            nameof(AgentConfigResponse.AuthFailureTimeoutMinutes),
+            // Merge reads two Collectors knobs (AgentMaxLifetimeMinutes, HelloWaitTimeoutSeconds);
+            // the remaining CollectorConfiguration flags flow untouched to DefaultComponentFactory.
+            nameof(AgentConfigResponse.Collectors),
+        };
+
+        /// <summary>
+        /// Fields deliberately NOT mapped by the merger because another component consumes them
+        /// directly from the remote config. One-line justification per entry — verify the
+        /// consumer before classifying a new field here.
+        /// </summary>
+        private static readonly string[] IntentionallyNotMerged =
+        {
+            // Schema/version metadata — logged and cached by RemoteConfigService, not a runtime knob.
+            nameof(AgentConfigResponse.ConfigVersion),
+            // Consumed by DefaultComponentFactory → GatherRuleExecutorHost (rules run against the raw remote list).
+            nameof(AgentConfigResponse.GatherRules),
+            // Consumed by DefaultComponentFactory → ImeLogHost (pattern list handed to ImeLogTracker).
+            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.
+            nameof(AgentConfigResponse.LatestAgentExeSha256),
+            // Self-updater force-update downgrade gate — BinaryIntegrityVerifier / Program update path.
+            nameof(AgentConfigResponse.AllowAgentDowngrade),
+            // Control-channel block signal — RemoteConfigService/ServerControlPlane; stripped from the disk cache.
+            nameof(AgentConfigResponse.DeviceBlocked),
+            // Control-channel kill signal — ServerControlPlane / Program.Guards; live fetch only.
+            nameof(AgentConfigResponse.DeviceKillSignal),
+            // Temporary-block expiry accompanying DeviceBlocked — ServerControlPlane.
+            nameof(AgentConfigResponse.UnblockAt),
+            // Endpoint migration — EndpointMigration/RemoteConfigService re-run the fetch, live fetch only.
+            nameof(AgentConfigResponse.MigrateToApiBaseUrl),
+        };
+
+        [Fact]
+        public void Every_AgentConfigResponse_property_is_classified_exactly_once()
+        {
+            var properties = typeof(AgentConfigResponse)
+                .GetProperties(BindingFlags.Public | BindingFlags.Instance)
+                .Select(p => p.Name)
+                .OrderBy(n => n, StringComparer.Ordinal)
+                .ToArray();
+
+            var merged = new HashSet<string>(MergedByMerger, StringComparer.Ordinal);
+            var notMerged = new HashSet<string>(IntentionallyNotMerged, StringComparer.Ordinal);
+
+            var inBoth = merged.Intersect(notMerged, StringComparer.Ordinal).ToArray();
+            Assert.True(
+                inBoth.Length == 0,
+                $"Fields listed in BOTH classification lists: [{string.Join(", ", inBoth)}].");
+
+            var unclassified = properties
+                .Where(p => !merged.Contains(p) && !notMerged.Contains(p))
+                .ToArray();
+            Assert.True(
+                unclassified.Length == 0,
+                "New AgentConfigResponse field(s) without a classification: " +
+                $"[{string.Join(", ", unclassified)}]. Either map them in RemoteConfigMerger.Merge " +
+                "(+ MergedByMerger here) or verify the consuming component and add them to " +
+                "IntentionallyNotMerged with a justification comment.");
+
+            // Stale entries (renamed/removed properties) must be cleaned up too.
+            var known = new HashSet<string>(properties, StringComparer.Ordinal);
+            var stale = merged.Concat(notMerged).Where(n => !known.Contains(n)).ToArray();
+            Assert.True(
+                stale.Length == 0,
+                $"Classification lists reference non-existent AgentConfigResponse properties: [{string.Join(", ", stale)}].");
+        }
+    }
+}

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Logging/AgentLoggerTests.cs

@@ -94,6 +94,21 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Logging
             Assert.Equal("older-002\n", File.ReadAllText(Path.Combine(tmp.Path, TodayBaseName + "_002.log")));
         }
 
+        [Fact]
+        public void Log_transliterates_typographic_punctuation_to_ascii()
+        {
+            using var tmp = new TempDirectory();
+            var logger = new AgentLogger(tmp.Path, AgentLogLevel.Info, maxFileSizeBytes: 1024L * 1024);
+
+            // The log file is UTF-8 without BOM; cp1252-guessing viewers (Outlook web
+            // preview) render em dashes as mojibake. Our own punctuation must come out
+            // 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"));
+            Assert.Contains("check failed - range 1-2 -> done... 'a' \"b\" nb sp f\u00FCr M\u00FCller", text);
+        }
+
         [Fact]
         public void Log_swallows_io_errors_silently()
         {

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Monitoring/Gather/GatherRuleCollectorGuardTests.cs

@@ -308,9 +308,52 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Gather
         [InlineData("SELECT * FROM Win32_UserAccount")]
         [InlineData("SELECT * FROM Win32_ShadowCopy")]
         [InlineData("SELECT * FROM Win32_OperatingSystemExtra")]          // prefix spoofing
+        [InlineData("SELECT Name FROM Win32_Process")]                    // projection of a disallowed class
+        [InlineData("SELECT BatteryStatus FROM Win32_BatteryX")]          // class spoofing via projection
         public void WmiCollector_OffAllowlistQuery_IsBlockedBeforeTheQueryRuns(string query)
             => AssertBlocked(new WmiCollector().Execute(Rule("wmi", query), Context()), query);
 
+        // -------------------------------------------------------------------
+        // WMI query matcher: "SELECT <* | property-list> FROM <allowed class>"
+        //
+        // Guard-level (no WMI touched): a property projection of an allowed class
+        // exposes a strict subset of the already-allowed SELECT *, so it is admitted.
+        // -------------------------------------------------------------------
+
+        [Theory]
+        [InlineData("SELECT * FROM Win32_Battery")]                                       // legacy form unchanged
+        [InlineData("SELECT * FROM Win32_BIOS WHERE PrimaryBIOS = TRUE")]                 // legacy + WHERE
+        [InlineData("SELECT BatteryStatus FROM Win32_Battery")]
+        [InlineData("SELECT BatteryStatus, EstimatedChargeRemaining FROM Win32_Battery")]
+        [InlineData("select batterystatus from win32_battery")]                           // case-insensitive
+        [InlineData("SELECT\tBatteryStatus\tFROM\tWin32_Battery")]                        // tabs as separators
+        [InlineData("  SELECT BatteryStatus FROM Win32_Battery  ")]                       // surrounding whitespace
+        [InlineData("SELECT BatteryStatus,EstimatedChargeRemaining FROM Win32_Battery")]  // no space after comma
+        [InlineData("SELECT Status FROM Win32_Battery WHERE BatteryStatus = 1")]          // projection + WHERE
+        public void WmiGuard_ProjectionOfAllowedClass_IsAllowed(string query)
+            => Assert.True(GatherRuleGuards.IsWmiQueryAllowed(query));
+
+        [Theory]
+        [InlineData("SELECT Name FROM Win32_Process")]                    // class not on the allowlist
+        [InlineData("SELECT BatteryStatus FROM Win32_BatteryX")]          // class spoofing
+        [InlineData("SELECT * FROM Win32_BatteryX")]
+        [InlineData("SELECT *, Name FROM Win32_BIOS")]                    // star mixed into a property list
+        [InlineData("SELECT FROM Win32_BIOS")]                            // empty property list
+        [InlineData("SELECT BatteryStatus FROM")]                         // missing class
+        [InlineData("SELECT BatteryStatus FROM Win32_Battery;DROP")]      // non-whitespace boundary after class
+        [InlineData("SELECT BatteryStatus, FROM Win32_Battery")]          // trailing comma
+        [InlineData("")]
+        public void WmiGuard_MalformedOrDisallowedQuery_IsBlocked(string query)
+            => Assert.False(GatherRuleGuards.IsWmiQueryAllowed(query));
+
+        [Fact]
+        public void WmiGuard_NullQuery_IsBlocked()
+            => Assert.False(GatherRuleGuards.IsWmiQueryAllowed(null));
+
+        [Fact]
+        public void WmiGuard_UnrestrictedMode_AllowsAnyQuery()
+            => Assert.True(GatherRuleGuards.IsWmiQueryAllowed("SELECT Name FROM Win32_Process", unrestrictedMode: true));
+
         [Fact]
         public void JsonCollector_UserProfilePath_IsBlockedBeforeTheFileIsOpened()
         {

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Monitoring/Ime/CmTraceLogParserTests.cs

@@ -107,6 +107,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
             var ok = CmTraceLogParser.TryParseLine(line, out var entry);
 
             Assert.True(ok);
+            Assert.NotNull(entry);
             Assert.Equal(
                 new DateTime(2026, 7, 29, 11, 46, 19, DateTimeKind.Utc).AddTicks(226610).AddMinutes(expectedOffsetMinutes),
                 entry.Timestamp);

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Monitoring/Telemetry/Gather/GuardrailsParityTests.cs

@@ -0,0 +1,69 @@
+using System.IO;
+using System.Linq;
+using AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.Gather;
+using Newtonsoft.Json.Linq;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Telemetry.Gather
+{
+    /// <summary>
+    /// Pins the display mirror in rules/guardrails.json (embedded into this assembly)
+    /// to the agent's hard-block CONSTANTS in <see cref="GatherRuleGuards"/>.
+    /// Enforcement is code-only by design (a JSON parse error must never lift a hard
+    /// block); the JSON mirror exists so the portal and the MCP validator can
+    /// pre-flight the same blocks. This test keeps the two from drifting: an addition
+    /// on either side fails here until the other side follows.
+    /// </summary>
+    public sealed class GuardrailsParityTests
+    {
+        private static JObject LoadEmbeddedGuardrails()
+        {
+            var assembly = typeof(GatherRuleGuards).Assembly;
+            using var stream = assembly.GetManifestResourceStream(
+                "AutopilotMonitor.Agent.V2.Core.Resources.guardrails.json");
+            Assert.NotNull(stream);
+            using var reader = new StreamReader(stream!);
+            return JObject.Parse(reader.ReadToEnd());
+        }
+
+        [Fact]
+        public void Blocked_file_prefixes_match_code_constants()
+        {
+            var json = LoadEmbeddedGuardrails()["blockedFilePrefixes"]!.ToObject<string[]>()!;
+            var code = new[] { GatherRuleGuards.BlockedUsersPrefix }
+                .Concat(GatherRuleGuards.AdditionalHardBlockedPathPrefixes);
+
+            Assert.Equal(
+                code.Select(p => p.ToLowerInvariant()).OrderBy(p => p),
+                json.Select(p => Path.GetFullPath(p).ToLowerInvariant()).OrderBy(p => p));
+        }
+
+        [Fact]
+        public void Blocked_command_patterns_match_code_constants()
+        {
+            var json = LoadEmbeddedGuardrails()["blockedCommandPatterns"]!.ToObject<string[]>()!;
+
+            Assert.Equal(
+                GatherRuleGuards.HardBlockedCommandPatterns.OrderBy(p => p),
+                json.OrderBy(p => p));
+        }
+
+        [Fact]
+        public void Max_command_length_matches_code_constant()
+        {
+            Assert.Equal(
+                GatherRuleGuards.MaxCommandLength,
+                LoadEmbeddedGuardrails()["maxCommandLength"]!.Value<int>());
+        }
+
+        [Fact]
+        public void Blocked_event_log_channels_match_code_constants()
+        {
+            var json = LoadEmbeddedGuardrails()["blockedEventLogChannels"]!.ToObject<string[]>()!;
+
+            Assert.Equal(
+                GatherRuleGuards.HardBlockedEventLogChannels.OrderBy(c => c),
+                json.OrderBy(c => c));
+        }
+    }
+}