esp: continue-anyway observation mode — bounded 60-min defang for device-phase failures

Classic UD fleets held at the Device-ESP timeout wall by one slow blocking
app showed ~100% Failed (tenant c9787ba2: 948/1000 esp_terminal_failure)
although the profile allows "Continue anyway" and users demonstrably reach
the desktop — the classic advisory defang requires AccountSetupEnteredUtc
and never applied there.

New operator-set tenant opt-in EnableEspContinueAnywayObservation
(ConfigVersion 36 -> 37, default off):

- DecisionCore: a Device-phase EspTerminalFailure with ContinueAnyway
  allowed + opt-in observed (EspConfigDetected payload fact — kernel stays
  config-free) + Classic/Unknown non-pre-prov scenario defangs into the
  advisory rail with a 60-min AdvisoryCompletion window. Real end via the
  DAD-validated real-user desktop + Hello gate (IME user-session gate is
  structurally unavailable without the AccountSetup anchor): eager
  completion on DesktopArrived, category recovery via the 4910a5a5 hook,
  expiry un-defangs to the original esp_terminal_failure — every observed
  session still gets a terminal verdict.
- Honest outcome: enrollment_complete under an unresolved advisory carries
  espSoftFailure/completionSource (also on the classic post-AccountSetup
  advisory path); backend stamps EspSoftFailure/CompletionSource on the
  Sessions row (+ index mirror, terminal-tuple preservation); web renders
  an amber "with issues" badge plus a session-detail banner. No new
  terminal status — Succeeded + marker.
- Agent: remote-config field merged into AgentConfiguration; stamped into
  both esp_config_detected emitters (orchestrator bootstrap via live
  Func<bool> seam, DeviceInfoCollector via host/factory pass-through).
- Admin UI: GA-only toggle in the tenant management modal (next to
  Bootstrap Token) + stored/runtime rows in the tenant config report;
  GA-gated on both write paths (PUT silently reverts for tenant admins,
  field patch rejects with 400).

Tests: 13 new ContinueAnywayObservationTests; DecisionCore 513, Agent V2
2162, Functions 3948, SummaryDialog 44, vitest 632, tsc clean.
Docs: docs/agent/continue-anyway-observation.md (OKF) + index/log.

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

.github/workflows/ci.yml

@@ -82,7 +82,7 @@ jobs:
       # in eslint.config.mjs + exhaustive-deps) — when you fix warnings, lower
       # the cap to match; never raise it.
       - name: Lint
-        run: npm run lint -- --max-warnings 141
+        run: npm run lint -- --max-warnings 99
 
       - name: Tests
         run: npm test

.github/workflows/codeql.yml

@@ -57,7 +57,7 @@ jobs:
           dotnet-version: '10.0.x'
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v4
+        uses: github/codeql-action/init@v4.37.3
         with:
           languages: ${{ matrix.language }}
           build-mode: ${{ matrix.build-mode }}
@@ -68,6 +68,6 @@ jobs:
         run: dotnet build AutopilotMonitor.sln --configuration Release
 
       - name: Analyze
-        uses: github/codeql-action/analyze@v4
+        uses: github/codeql-action/analyze@v4.37.3
         with:
           category: /language:${{ matrix.language }}

.github/workflows/deploy-web.yml

@@ -39,6 +39,10 @@ jobs:
         uses: Azure/static-web-apps-deploy@v1
         env:
           NEXT_PUBLIC_ENTRA_CLIENT_ID: ${{ vars.NEXT_PUBLIC_ENTRA_CLIENT_ID }}
+          # Dual app-reg window: previous app registration (unset = single-app behaviour)
+          # and the default app for browsers without a stored selection (legacy|primary).
+          NEXT_PUBLIC_ENTRA_LEGACY_CLIENT_ID: ${{ vars.NEXT_PUBLIC_ENTRA_LEGACY_CLIENT_ID }}
+          NEXT_PUBLIC_ENTRA_DEFAULT_APP: ${{ vars.NEXT_PUBLIC_ENTRA_DEFAULT_APP }}
           NEXT_PUBLIC_ENTRA_REDIRECT_URI: ${{ vars.NEXT_PUBLIC_ENTRA_REDIRECT_URI }}
           NEXT_PUBLIC_ENTRA_POST_LOGOUT_REDIRECT_URI: ${{ vars.NEXT_PUBLIC_ENTRA_POST_LOGOUT_REDIRECT_URI }}
           NEXT_PUBLIC_API_BASE_URL: ${{ vars.NEXT_PUBLIC_API_BASE_URL }}

.github/workflows/pester.yml

@@ -0,0 +1,61 @@
+name: Pester (Bootstrap scripts)
+
+# Runs the Pester suite for the Intune bootstrap scripts under Windows PowerShell 5.1
+# (the runtime IME uses to execute platform scripts) so guard/relax logic changes are
+# verified without resetting a device. Like ci.yml it reports rather than blocks.
+
+on:
+  push:
+    branches: [main]
+    paths: ['scripts/Bootstrap/**']
+  pull_request:
+    branches: [main]
+    paths: ['scripts/Bootstrap/**']
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: pester-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  pester:
+    name: Bootstrap guard tests (PS 5.1)
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v7
+
+      - name: Install Pester 5+
+        shell: powershell
+        run: |
+          Install-PackageProvider -Name NuGet -MinimumVersion 2.8.5.201 -Force -Scope CurrentUser | Out-Null
+          Install-Module Pester -Scope CurrentUser -Force -SkipPublisherCheck -MinimumVersion 5.5.0
+
+      - name: Run Pester
+        shell: powershell
+        run: |
+          Import-Module Pester -MinimumVersion 5.5.0
+          $c = New-PesterConfiguration
+          $c.Run.Path = 'scripts/Bootstrap'
+          $c.Run.Exit = $true
+          $c.Output.Verbosity = 'Detailed'
+          Invoke-Pester -Configuration $c
+
+      - name: Guard scripts stay pure ASCII
+        shell: powershell
+        run: |
+          $failed = $false
+          Get-ChildItem 'scripts/Bootstrap' -Filter '*.ps1' | ForEach-Object {
+            $bytes = [System.IO.File]::ReadAllBytes($_.FullName)
+            for ($i = 0; $i -lt $bytes.Length; $i++) {
+              if ($bytes[$i] -gt 127) {
+                Write-Host "::error file=scripts/Bootstrap/$($_.Name)::Non-ASCII byte 0x$('{0:X2}' -f $bytes[$i]) at offset $i. PS 5.1 (IME) reads BOM-less files as ANSI and corrupts multi-byte chars."
+                $failed = $true
+                break
+              }
+            }
+          }
+          if ($failed) { exit 1 }
+          Write-Host 'All bootstrap scripts are pure ASCII.'

README.md

@@ -1,14 +1,14 @@
 # <img src="docs/images/logo.svg" height="28" alt="" /> AutopilotMonitor
 
-[![Status](https://img.shields.io/badge/status-Private%20Preview-orange)](https://www.autopilotmonitor.com)
+[![Status](https://img.shields.io/badge/status-live-brightgreen)](https://www.autopilotmonitor.com)
 [![License](https://img.shields.io/badge/license-MIT%20%2B%20AGPL--3.0-blue)](LICENSE)
 [![Website](https://img.shields.io/badge/website-autopilotmonitor.com-2ea44f)](https://www.autopilotmonitor.com)
 
 Advanced monitoring and troubleshooting solution for Windows Autopilot deployments. Gain full visibility into every enrollment session with a detailed event timeline, fleet health dashboards, and session reporting. Define custom analysis rules to automatically detect issues and gather rules to collect targeted evidence. Retrieve diagnostics packages on demand, configure agent settings like auto-reboot behavior and automatic timezone adjustment — all managed centrally from the web dashboard.
 
-## Private Preview
+## Availability
 
-Autopilot Monitor is currently running as a **Private Preview**. Visit **[autopilotmonitor.com](https://www.autopilotmonitor.com)** to request access and learn more.
+Autopilot Monitor is **publicly available** — the Community plan is free. Sign in with your work account at **[autopilotmonitor.com](https://www.autopilotmonitor.com)**; new organizations complete a short activation step after first sign-in.
 
 <p align="center">
   <img src="docs/images/SessionList.png" width="45%" />

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/cloudpc-device-validation.md

@@ -0,0 +1,142 @@
+---
+type: Concept
+title: W365 Cloud PC Device Validation — Cert-CN-Bound Fallback Validator
+description: Why Windows 365 Cloud PCs can never pass the Autopilot serial lookup, and how the CloudPc validator admits exactly the tenant's service-provisioned Cloud PCs by binding the MDM certificate's Subject CN (= Intune device id) to the Graph virtualEndpoint/cloudPCs inventory.
+resource: src/Backend/AutopilotMonitor.Functions/Security/CloudPcDeviceValidator.cs
+tags:
+  - backend
+  - security
+  - device-validation
+  - windows365
+  - cloudpc
+  - graph
+timestamp: 2026-08-06T00:00:00+02:00
+---
+
+# W365 Cloud PC Device Validation
+
+Windows 365 Cloud PCs are provisioned headless by the Windows 365 service and are
+**structurally never Autopilot-registered** — the serial lookup against
+`windowsAutopilotDeviceIdentities` (and the Corporate Identifier fallback, whose
+serials nobody can pre-import for VMs minted at provisioning time) always misses.
+Before this validator, a Cloud PC agent died in the 403 "Device not registered"
+even though its mTLS cert was perfectly valid, so Cloud PC first-connect
+enrollment (Account Setup, RealmJoin, Hello) could not be monitored.
+
+# Schema — the validator chain
+
+`SecurityValidator.ValidateRequestAsync` stage 4 runs the same chain for every
+device; there is **no device-type routing** and the local W365 markers
+(Windows365 registry key, CloudManagedDesktopExtension service) are never
+consulted for auth — they gain an attacker nothing:
+
+1. **Autopilot serial lookup** (`ValidateAutopilotDevice`) — unchanged primary.
+2. **Corporate Identifier** (`ValidateCorporateIdentifier`) — unchanged fallback.
+3. **CloudPc** (`ValidateCloudPcDevice`, default off) — only reached when 1+2
+   missed. Extracts the Intune device id from the **chain-validated** client
+   certificate's Subject CN (`TryGetIntuneDeviceIdFromCertSubject`: CN present
+   AND canonical GUID, else definitive reject) and requires a `cloudPC` object
+   with `managedDeviceId eq <CN>` in the claimed tenant
+   (`GET /v1.0/deviceManagement/virtualEndpoint/cloudPCs?$filter=…`).
+   `ValidatedBy = ValidatorType.CloudPc (5)`.
+
+Only machines actually provisioned by the Windows 365 service have a `cloudPC`
+object — a regular Intune-enrolled non-Autopilot device still ends in the 403,
+so the "Autopilot devices only" contract of stages 1–2 is not widened. The
+tenant hard gate accepts `ValidateCloudPcDevice` as a third satisfying flag.
+
+## Why the cert CN, not headers or local markers
+
+Field-verified 2026-08-06 on a real W365 Enterprise Cloud PC (gktatooine.net):
+
+- MDM client cert Subject `CN=07623d56-…` == Intune `managedDevice.id` ==
+  `cloudPC.managedDeviceId`. The CN cannot be forged without the Intune MDM
+  Device CA (chain pinned to embedded roots, `CustomRootTrust`).
+- `$filter=managedDeviceId eq '…'` is supported server-side on **v1.0** — no
+  paging fallback needed.
+- `managedDevice.serialNumber` matches local `Win32_BIOS.SerialNumber` exactly;
+  the "Cloud PC Enterprise …" model string exists **only** in Graph, never in
+  local WMI (local WMI reports Manufacturer='Microsoft Corporation',
+  Model='Virtual Machine').
+
+Threat model: a valid Intune cert from a *different* tenant fails (its CN does
+not exist in the claimed tenant's Cloud PC inventory — this is a *tenant
+binding* the serial-based validators do not have); spoofed serial headers and
+faked local W365 markers are irrelevant (never consulted); a rogue enrolled VM
+with doctored SMBIOS cannot mint a `cloudPC` object (service-side state, not
+device-reported inventory — the reason the model-string gate was rejected).
+Retired/deprovisioned Cloud PCs disappear from the inventory and their
+validation dies with them (compensates the absent cert revocation check).
+Residual: a compromised *legitimate* Cloud PC of the tenant — same trust level
+as any tenant device today, rate-limited by cert thumbprint.
+
+## Graph permission plumbing
+
+- Optional add-on permission `CloudPC.Read.All` — NOT part of the default
+  consent set. Feature `W365CloudPcValidation` in `GraphFeatureCatalog` →
+  surfaces automatically in the "Optional Graph capabilities" UI (the feature
+  table and grant command are backend-driven) and in
+  `Grant-AutopilotMonitorAddOn.ps1` (`-Features W365CloudPcValidation`).
+  `GraphFeatureCatalogSyncTests` pins C# catalog ↔ grant script (previously
+  comment-only lock-step).
+- A Graph **403** (permission not granted) is a definitive negative (cached
+  5 min), NOT transient — a 503 Retry-After loop cannot fix a missing grant.
+  The error message names the add-on feature.
+- Same resilience contract as `AutopilotDeviceValidator`: 30/5 min
+  positive/negative cache, 2 attempts, transient → agent-facing 503.
+
+## Bootstrap script interplay (v2.3-dev.3)
+
+The Cloud-PC relax in `Install-AutopilotMonitor-dev.ps1` additionally exempts
+**guard 4** (12 h uptime window): a Cloud PC runs headless for days before the
+user's first connect, and the monitorable phase (Account Setup) only starts at
+that first connect — the single-fresh-profile window (< 15 min) is the time
+anchor there, not boot uptime. The OOBE-restore trigger keeps the uptime guard.
+
+## Agent-side IsCloudPc flag + decision-engine expectation
+
+Same change set, agent side. `CloudPcDetector` (V2.Core) re-uses the bootstrap's
+field-verified marker AND — `HKLM\SOFTWARE\Microsoft\Windows365` key **plus**
+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`.
+
+Three independent transport rails, never an auth input:
+
+- **Session metadata** — `SessionRegistration.IsCloudPc` →
+  Sessions table (sticky-true OR across re-registrations, like
+  `IsSelfDeployingProfile`) → SessionsIndex full mirror → `SessionSummary` →
+  search filter `isCloudPc` (portal, `/api/search/sessions`, `/api/raw/sessions`,
+  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
+  reason `cloud_pc_first_connect:no_device_esp_expected`. That is the
+  engine-recorded expectation "no Device ESP phase will appear": Device-ESP ran
+  headless at provisioning, the session starts at Account Setup. Deliberately
+  reason+observation only — no completion arm depends on DeviceSetup, `Mode`
+  is still classified by AccountSetup/IME signals (Classic), and `EspConfig`
+  keeps the *configured* FirstSync semantics. The positive marker surfaces as
+  `cloud_pc_marker` in the terminal audit-trail signal census.
+
+# Citations
+
+- `src/Backend/AutopilotMonitor.Functions/Security/CloudPcDeviceValidator.cs`
+- `src/Backend/AutopilotMonitor.Functions/Security/SecurityValidator.cs` — stage 4 chain, `TryGetIntuneDeviceIdFromCertSubject`
+- `src/Shared/AutopilotMonitor.Shared/Models/Graph/GraphFeatureCatalog.cs` — `W365CloudPcValidation`
+- `scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1` — customer-side grant
+- `scripts/Bootstrap/Install-AutopilotMonitor-dev.ps1` — Cloud-PC relax + guard-4 exemption
+- `src/Backend/AutopilotMonitor.Functions.Tests/CloudPcDeviceValidatorTests.cs`, `SecurityValidatorTests.cs`, `GraphFeatureCatalogSyncTests.cs`
+- `src/Agent/AutopilotMonitor.Agent.V2.Core/Security/CloudPcDetector.cs` — agent-side marker AND
+- `src/Shared/AutopilotMonitor.DecisionCore/State/EnrollmentScenarioObservations.cs` — `CloudPc` fact; reason annotation in `EnrollmentScenarioProfileUpdater`

docs/backend/tenant-activation-welcome-mail.md

@@ -0,0 +1,75 @@
+---
+type: concept
+title: Tenant Activation & the Once-Only Welcome Mail
+description: How a signup becomes an activated tenant (manual approve or auto-approve queue), and how the welcome mail is sent exactly once even though activation and the user-provided address race each other.
+resource: backend
+tags: [activation, auto-approve, welcome-email, preview-whitelist, race]
+timestamp: 2026-08-02
+---
+
+# Schema
+
+## Activation
+
+A tenant is **activated** when the row `PartitionKey={tenantId}, RowKey="approved"` exists
+in the `PreviewWhitelist` table (legacy name kept on purpose). Everything else in the
+portal gates on that row via `PreviewWhitelistService.IsApprovedAsync` (5 min positive /
+30 s negative cache).
+
+Two activation routes, one shared implementation
+(`TenantApprovalService.ApproveWithSideEffectsAsync`):
+
+* **Manual**: Global Admin approves in the admin panel (`POST /api/preview/whitelist/{tenantId}`).
+* **Auto**: signup unconditionally enqueues a `tenant-auto-approve` envelope; the queue
+  worker (`TenantAutoApproveHandler`) re-checks the `AutoApproveNewTenants` flag
+  (uncached, fail-closed), the suspension gate (fresh config read), then approves.
+  Typical latency: ~1 minute after signup.
+
+The whitelist add is a **conditional INSERT** (`AddEntityAsync`, 409 = lost) — storage
+arbitrates concurrent activations; exactly one caller runs the side effects
+(TenantAdmin auto-promote of the signup UPN, welcome mail, `TenantAutoApproved` ops event).
+
+## The welcome-mail race
+
+The welcome mail goes to the **notification email** (`RowKey="notification-email"` in the
+same table) — the only reliable address: it is typed by the user on the activation-pending
+page (`PUT /api/preview/notification-email`). The signup admin UPN may have no mailbox and
+`ContactEmail` is merely seeded from the notification email.
+
+That makes activation and address entry concurrent writers. With auto-approve, activation
+usually wins (observed in production: approve at T+64 s, address saved at T+69 s → the
+approval path found no address and the mail was silently skipped).
+
+**Arbitration — write-then-read on both sides plus a send-once marker:**
+
+* The approval path writes the `approved` row, then reads the address.
+* The save path (`SavePreviewNotificationEmail`) writes the address row, then checks
+  approval **fresh** (`IsApprovedFreshAsync` — the 30 s negative cache would hide the
+  activation for exactly this window).
+* Since both do write-then-read, at least one sees both halves and calls
+  `TenantApprovalService.TrySendWelcomeEmailAsync`.
+* There, a conditional insert of `RowKey="welcome-email-sent"` decides who actually
+  sends: at most one wins. The marker is consumed strictly **after** the address check —
+  consuming it without an address would permanently suppress the mail.
+
+Marker lifecycle: revoke (`RevokeAsync`) deletes it (re-approve = fresh activation =
+fresh mail); the offboarding cascade wipes the whole `PreviewWhitelist` partition anyway.
+The Global-Admin resend endpoint (`POST /api/preview/send-welcome-email/{tenantId}`)
+always sends (explicit intent) and consumes the marker best-effort so the automatic
+paths never duplicate afterwards.
+
+# Examples
+
+* Auto-approve wins the race: approve at T+64 s finds no address → logs "deferred to the
+  notification-email save path"; user saves address at T+69 s → save path sees approved
+  (fresh read), wins the marker, sends. Response carries `welcomeEmailSent: true`.
+* Address saved before manual approve (classic shape): approval path finds the address,
+  wins the marker, sends; a later re-save of the same address does not re-send.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Services/TenantApprovalService.cs` — shared activation + `TrySendWelcomeEmailAsync`
+* `src/Backend/AutopilotMonitor.Functions/Services/Activation/TenantAutoApproveHandler.cs` — queue-side gates
+* `src/Backend/AutopilotMonitor.Functions/Functions/Rules/PreviewWhitelistFunction.cs` — save-path trigger, GA resend
+* `src/Backend/AutopilotMonitor.Functions/DataAccess/TableStorage/TableConfigRepository.cs` — conditional inserts (approved / welcome-email-sent)
+* `src/Backend/AutopilotMonitor.Functions.Tests/TenantApprovalServiceTests.cs` — ordering + dedup pins

docs/index.md

@@ -23,12 +23,14 @@ 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
 
 * [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).
 
 # Backend
 
@@ -37,11 +39,14 @@ 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.
+* [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.
 
 # MCP Server
 
 * [MCP Docs Corpus](mcp/docs-corpus.md) - How the published customer documentation becomes the `search_docs` corpus: CRLF-safe heading chunking, build-time embedding as a third precomputed section, and why a docs edit needs an MCP redeploy.
+* [MCP Tool Telemetry](mcp/tool-telemetry.md) - The three telemetry layers for judging tool quality: backend App Insights via X-MCP-Tool-Name, the per-user usage table, and the MCP_TOOL_LOGGING stderr lines (soft errors, result size vs. cap, zero-hit searches, Zod rejections).
 
 # Web Portal
 

docs/log.md

@@ -1,5 +1,38 @@
 # Log
 
+## 2026-08-08
+
+* **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.
+
+## 2026-08-06
+
+* **Creation**: Added `backend/cloudpc-device-validation.md` — the CloudPc fallback validator (`ValidatorType.CloudPc = 5`, tenant flag `ValidateCloudPcDevice`): W365 Cloud PCs are structurally never Autopilot-registered, so stage 4 gains a third stage that binds the chain-validated MDM cert's Subject CN (= Intune device id, field-verified on a real Cloud PC) to the tenant's `virtualEndpoint/cloudPCs` inventory — admits exactly the service-provisioned Cloud PCs, no device-type routing, local W365 markers never consulted for auth. New optional Graph add-on `W365CloudPcValidation` → `CloudPC.Read.All` (catalog + grant script now pinned by `GraphFeatureCatalogSyncTests`; Graph 403 = definitive "grant missing", not transient). Bootstrap dev script v2.3-dev.3 exempts guard 4 (uptime) while the Cloud-PC relax is active — the fresh-profile window is the time anchor at first connect, not boot uptime. Follow-up deliberately out of scope: agent-side `IsCloudPc` classification + decision-engine "no Device ESP" expectation.
+
+## 2026-08-05 (later)
+
+* **Update**: `rules/rule-authoring-surface.md` — new section `POST /api/rules/gather/test-pattern`: the logparser pattern tester (agent-exact .NET matching: no IgnoreCase, first-match-per-line, cmtrace vs text mode, verbatim format=text hint), motivated by a field incident where a PHP-verified regex behaved differently under .NET. `CmTraceLogParser` moved Agent → `AutopilotMonitor.Shared.Logging` so agent and backend share the ONE parsing implementation (timestamp caveat: AssumeLocal = server TZ on backend, endpoint reports no timestamps). MCP: new `test_log_pattern` tool, logparser lint in `validate_rule`, guide gains the case-sensitivity/engine-mismatch pitfalls.
+
+## 2026-08-05
+
+* **Creation**: Added `mcp/tool-telemetry.md` — the three MCP tool-telemetry layers (App Insights `McpToolName`, per-user usage table, `MCP_TOOL_LOGGING` stderr lines) and the new quality signals: soft-error capture (`toolError` returns instead of throwing, so backend telemetry counted those calls as successes), `resultChars`/`overCap` vs. the inline-size hint, bounded args summaries, caller scope, `search_zero_hit` on the three search tools (unmet-demand signal), and `tool_call_rejected` for JSON-RPC-level Zod/unknown-tool rejections sniffed at the `/mcp` route (previously invisible everywhere). Bicep default for `toolLoggingEnabled` flipped to `true` (documented desired state; live flag set via `az containerapp update`).
+* **Creation**: Added `rules/rule-authoring-surface.md` — the AI-assisted rule-authoring stack: three deterministic MCP resources (`rule_authoring_guide` hand-written, `rule_schemas` + `rule_guardrails` generated into `rule-authoring.generated.ts` by a new combine.js emitter, drift-guarded twice), the MCP-local `validate_rule` (ajv 2020-12 against the single-rule $defs, guardrail pre-flight mirroring GatherRuleGuards matching semantics incl. hard blocks, semantic lint for schema-valid-but-dead rules), and the side-effect-free `POST /api/rules/analyze/dryrun` (TenantAdminOrGlobalReader; `RuleEngine.DryRun.cs` trace twin sharing the production evaluators, all-conditions trace with per-condition evidence + matchingEventCount, parity and side-effect-freedom pinned by RuleEngineDryRunTests). MCP `test_analyze_rule` wraps the endpoint with `{{token}}`-interpolated previews; `author-rule` prompt drives the draft → validate → dry-run loop. Deliberately absent: gather-rule remote execution, rule writes via MCP.
+
+## 2026-08-04
+
+* **Update**: `rules/gather-rule-phase-scoping.md` — new section "Which phase feeds the triggers": `GatherRuleExecutorHost` now drives `phase_change`/`phase_exit`/`on_event` gather triggers (and the phase-scope gates) from the post-reduce `TimelineEventStream` (every emitted event's `(eventType, phase)` published by `EventTimelineEmitter`) instead of the pre-reduce `SignalIngress.SignalPosted` payloads. Trigger: session `32312a32` (RealmJoin tenant rsneuffen.de) — a Phase-Start rule on FinalizingSetup fired at the raw ESP-exit `EspPhaseChanged(FinalizingSetup)` signal, 7 minutes before the engine's RealmJoin-gated `phase_transition(FinalizingSetup)`, reading `HKLM\SOFTWARE\RealmJoin\Custom\BIOS` before the RealmJoin package created it. Phase triggers now fire exactly when the timeline shows the phase; `on_event` additionally sees engine-emitted event types (`enrollment_complete`, `realmjoin_resolved`, …) for the first time in V2, restoring V1 semantics and the documented end-of-enrollment pattern. Other raw-signal hosts (DeviceInfo, keep-awake, PPKG) deliberately unchanged.
+
+## 2026-08-02
+
+* **Creation**: Added `backend/tenant-activation-welcome-mail.md` — triggered by the first production auto-approve (activation at signup+64 s, notification address saved at +69 s → welcome mail silently skipped, since the approval path is the only sender and reads the address once). Fix documented in the doc: the notification-email save path now also triggers the send (`PUT /api/preview/notification-email` → fresh approval check `IsApprovedFreshAsync`, bypassing the 30 s negative cache), and a conditional-insert `welcome-email-sent` marker in `PreviewWhitelist` makes the send once-only across both racing paths (marker consumed strictly after the address check; revoke clears it, offboarding wipes the partition, the GA resend endpoint sends unconditionally and consumes it best-effort).
+
 ## 2026-07-29
 
 * **Update**: `agent/gather-rule-debug-log.md` — three trace enrichments: (1) new `phase` stage writing an enrollment-phase transition marker (`phase change: Old -> New`, ruleId `-`) so every rule-level line reads against the current phase; (2) logparser now writes one line per regex match — line number, matched text, capture groups — capped at 10 per file per run (the per-file summary keeps the full count); (3) the invalid-regex `error` line includes the offending pattern string.

docs/mcp/tool-telemetry.md

@@ -0,0 +1,81 @@
+---
+type: concept
+title: MCP Tool Telemetry
+description: The three telemetry layers for judging MCP tool quality — backend App Insights via X-MCP-Tool-Name, the per-user usage table, and the MCP_TOOL_LOGGING stderr lines that carry the signals the backend cannot see (soft errors, result size vs. cap, zero-hit searches, Zod rejections).
+resource: src/McpServer/autopilot-monitor-mcp/src/telemetry.ts
+tags: [mcp, telemetry, observability, tool-quality]
+timestamp: 2026-08-05
+---
+
+# Schema
+
+Three layers answer "are the MCP tools doing their job, and are tools missing?":
+
+1. **Backend App Insights** — every tool handler runs inside `withToolTelemetry`
+   (`src/telemetry.ts`), which propagates the tool name via AsyncLocalStorage so
+   `apiFetch` stamps `X-MCP-Tool-Name` on each backend request.
+   `RequestTelemetryMiddleware` copies it into the request telemetry as
+   `McpToolName`: per-tool call volume, latency percentiles and HTTP failure
+   rates by KQL. Blind spot: tools that never call the backend, and handler-level
+   soft errors (see layer 3).
+2. **Usage table** — `McpQuotaEnforcementMiddleware.TrackUsage` counts per
+   user/day under the key `toolname:endpoint`; surfaced by the `get_api_usage`
+   tool. Counts only, every call counts as success.
+3. **stderr JSON lines** (`MCP_TOOL_LOGGING=true`, queryable via Container App
+   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
+     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).
+     This is the ONLY telemetry for backend-free tools: `search_docs`,
+     `validate_rule`, `get_resource`, the local ranking of `search_knowledge`.
+   - `search_zero_hit`: query text (capped) whenever `search_events` /
+     `search_knowledge` / `search_docs` return zero results — the most direct
+     "missing docs / missing knowledge / missing tool?" demand signal.
+   - `tool_call_rejected`: rejections the SDK answers *before* any handler runs
+     (Zod argument validation, unknown/disabled tool). Two non-obvious facts,
+     both found by live verification: SDK 1.30 wraps these McpErrors as a
+     *successful* JSON-RPC response whose result is `{ isError: true, text:
+     "MCP error <code>: …" }` — a JSON-RPC error envelope never exists for
+     them — and the Hono bridge (`getRequestListener`) may stream the body as
+     `res.write` chunks with a bare `res.end()`. The sniffer in the `/mcp`
+     route therefore wraps both `write` and `end`, reassembles up to 10 KB and
+     matches both shapes (`attachToolCallRejectionSniffer` in `telemetry.ts`).
+     Handler soft errors never carry the `MCP error` prefix, so they are not
+     double-logged. This is the strongest "the schema or description confuses
+     the model" signal and was previously invisible everywhere.
+
+The env flag defaults to `true` in `infra/mcp-server.bicep` (documented desired
+state — the template is not routinely deployed; the live flag is set with
+`az containerapp update --set-env-vars MCP_TOOL_LOGGING=true`).
+
+# Examples
+
+Count zero-hit queries to find unmet demand (Log Analytics):
+
+```kusto
+ContainerAppConsoleLogs_CL
+| where Log_s has '"type":"search_zero_hit"'
+| extend d = parse_json(Log_s)
+| summarize count() by tostring(d.tool), tostring(d.query)
+```
+
+Per-tool soft-error and truncation rates:
+
+```kusto
+ContainerAppConsoleLogs_CL
+| where Log_s has '"type":"tool_call"'
+| extend d = parse_json(Log_s)
+| summarize calls = count(), errors = countif(d.isError == true),
+            overCap = countif(d.overCap == true), p95ms = percentile(tolong(d.durationMs), 95)
+  by tool = tostring(d.tool)
+```
+
+# Citations
+
+- `src/McpServer/autopilot-monitor-mcp/src/telemetry.ts` — wrapper + log emitters
+- `src/McpServer/autopilot-monitor-mcp/src/index.ts` — `/mcp` rejection sniffer
+- `src/Backend/AutopilotMonitor.Functions/Middleware/RequestTelemetryMiddleware.cs` — `McpToolName` stamping
+- `src/Backend/AutopilotMonitor.Functions/Middleware/McpQuotaEnforcementMiddleware.cs` — usage-table counting

docs/rules/gather-rule-phase-scoping.md

@@ -8,7 +8,7 @@ tags:
   - backend
   - gather-rules
   - config
-timestamp: 2026-07-20T00:00:00+02:00
+timestamp: 2026-08-04T00:00:00+02:00
 ---
 
 # Problem
@@ -64,6 +64,35 @@ enter-rule and an exit-rule on the same phase never cannibalise each other's slo
 * Old agents do not know the trigger value and simply never fire the rule (silent no-op) —
   which is why `phase_exit` needs no ConfigVersion bump: no new field is transported.
 
+# Which "phase" feeds the triggers — the emitted timeline, not raw signals
+
+The phase the executor sees is fed by `GatherRuleExecutorHost` from the **post-reduce
+`TimelineEventStream`**: `EventTimelineEmitter` publishes every emitted event's
+`(eventType, phase)` after the decision engine reduced the originating signal. Phase triggers
+therefore fire exactly when the UI timeline shows the phase — by construction.
+
+This replaced the original V2 wiring (`SignalIngress.SignalPosted`), which fires at enqueue
+time with the **raw** collector payload. The raw phase can run minutes ahead of the
+engine-declared one: in session `32312a32` (RealmJoin tenant) the Shell-Core ESP-exit
+synthesized `EspPhaseChanged(FinalizingSetup)` at 12:18, while the engine — holding the
+transition behind the RealmJoin completion gate until the first deployment resolved — declared
+`phase_transition(FinalizingSetup)` at 12:25. A `phase_change` rule on `FinalizingSetup`
+reading `HKLM\SOFTWARE\RealmJoin\Custom\BIOS` fired 7 minutes early and read the key before
+the RealmJoin package wrote it (`exists=false`).
+
+Consequences of the emitted-event feed:
+
+* `phase_change` / `phase_exit` / phase **scope** gates all follow the engine-reduced phase
+  (single feed, consistent with the portal's "collects once when the enrollment reaches …").
+* `on_event` now sees **every emitted event type**, including engine-emitted ones
+  (`enrollment_complete`, `phase_transition`, `realmjoin_resolved`, …) that never existed on
+  the raw signal stream — the documented "On Event with `enrollment_complete`" end-of-enrollment
+  pattern only works because of this. This restores V1 semantics (V1 fired triggers from every
+  emitted `EnrollmentEvent`).
+* Other hosts (`DeviceInfoHost`, `UserEspKeepAwakeHost`, `ProvisioningPackageHost`) still key
+  off the raw signal stream deliberately — their collections are about OS state at the raw
+  boundary (ESP exit, keep-awake), not about timeline agreement.
+
 # Scope semantics (agent, `GatherRuleExecutor`)
 
 * Scope applies to **all trigger types**:
@@ -130,7 +159,9 @@ enter-rule and an exit-rule on the same phase never cannibalise each other's slo
 # Citations
 
 * `src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/Gather/GatherRuleExecutor.cs` — scope gates, latch, canonical hash
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/GatherRuleExecutorHost.cs` — timeline-event trigger feed
+* `src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/TimelineEventStream.cs` — post-reduce observer surface
 * `src/Backend/AutopilotMonitor.Functions/Functions/Rules/GatherRulesFunction.cs` — `ValidateScopeAndEmitMode`
 * `src/Backend/AutopilotMonitor.Functions/Services/GatherRuleService.cs` — partial-PUT merge, `ContentEquivalent`
 * `src/Shared/AutopilotMonitor.Shared/Models/Rules/GatherRule.cs` — field contracts
-* Tests: `GatherRuleExecutorPhaseScopeTests`, `GatherRuleExecutorEmitModeTests` (agent); `GatherRuleUpdatePartialMergeTests`, `GatherRuleScopeFieldsTests` (backend)
+* Tests: `GatherRuleExecutorPhaseScopeTests`, `GatherRuleExecutorEmitModeTests`, `GatherRuleExecutorHostTimelineFeedTests` (agent); `GatherRuleUpdatePartialMergeTests`, `GatherRuleScopeFieldsTests` (backend)

docs/rules/rule-authoring-surface.md

@@ -0,0 +1,152 @@
+---
+type: Concept
+title: Rule Authoring Surface — MCP Resources, validate_rule, and the Analyze Dry-Run
+description: >-
+  How customer AIs author gather/analyze rules against the real contract: the baked
+  authoring resources (guide, schemas, guardrails) generated by combine.js, the
+  MCP-local validate_rule pre-flight, and the side-effect-free backend dry-run that
+  traces a draft analyze rule against one session's events.
+resource: src/McpServer/autopilot-monitor-mcp/src/tools/rules.ts
+tags: [rules, mcp, analyze-rules, gather-rules, dry-run, authoring]
+timestamp: 2026-08-05
+---
+
+# Concept
+
+Customers author rules with an AI connected to the MCP server. Retrieval
+(`search_docs`) is deliberately NOT the knowledge source for authoring: chunked
+top-K retrieval can silently omit an operator, a guardrail prefix, or an enum,
+and the AI then produces a plausible-but-dead rule. The authoring surface is
+therefore **deterministic**: three `get_resource` entries carry the complete
+contract, a local validator rejects what production would reject or silently
+ignore, and a backend dry-run evaluates a draft against real session events with
+a full trace.
+
+The intended loop: draft → `validate_rule` → `test_analyze_rule` against a real
+session (one that should fire, one that should not) → iterate → create in the
+portal. The `author-rule` MCP prompt walks a client through exactly this order.
+
+# Schema
+
+## Resources (deterministic authoring context)
+
+| Resource | Content | Source |
+| --- | --- | --- |
+| `rule_authoring_guide` | Hand-written complete authoring knowledge: collector types, triggers, condition sources, operators, confidence model incl. the exact factor DSL, `{{token}}` interpolation order, guardrail matching semantics, pitfalls | `src/rule-authoring-guide.ts` |
+| `rule_schemas` | Both JSON Schemas (2020-12) verbatim | generated |
+| `rule_guardrails` | `rules/guardrails.json` verbatim | generated |
+
+Generation: `node rules/scripts/combine.js` bakes schemas + guardrails into
+`src/McpServer/autopilot-monitor-mcp/src/rule-authoring.generated.ts` (same
+pattern as the web's `utils/guardrails.generated.ts`; the tsconfig `rootDir` and
+the Docker build's exclusion of `rules/schema` rule out importing the JSON
+directly). Drift is closed twice: CI's `guardrails-in-sync` job re-runs
+combine.js and fails on any diff, and `rule-authoring-drift.test.ts` pins
+generated == repo source plus guide enums == schema enums.
+
+## validate_rule (MCP-local)
+
+`src/rule-validation.ts`, no backend call. Three layers:
+
+1. **Schema** — ajv (draft 2020-12) against the baked schemas, validating the
+   single-rule `$defs` entry directly (the top-level oneOf wrapper would double
+   every error).
+2. **Guardrails** — mirrors the AGENT's matching semantics from
+   `GatherRuleGuards.cs` (see [gather-rule-guardrails.md](gather-rule-guardrails.md)):
+   hive-stripped segment-bounded registry/file prefixes, whitespace-bounded WMI
+   prefixes, EXACT command matching, `/`-bounded event-log channels, and the
+   code-enforced hard blocks (`Security` etc. channels, `C:\Users`,
+   `C:\Windows\System32\config`).
+3. **Semantic lint** — schema-valid-but-dead rules: unreachable
+   confidenceThreshold, factor conditions outside the three parseable shapes
+   (`exists`, `count >= N`, `phase_duration > N`), unknown event types (warning;
+   `gather_*` softened to info), unanchored `not_regex` allow-lists,
+   unresolvable `{{token}}`s, trigger cross-fields, outputEventType
+   convention/collision checks.
+
+The validator is advisory pre-flight only — the agent re-enforces guardrails
+on-device and the backend re-validates structure. It must never be stricter
+than production.
+
+## POST /api/rules/analyze/dryrun (backend)
+
+`DryRunAnalyzeRuleFunction` → `RuleEngine.DryRunRuleAsync`. Body
+`{ sessionId, rule }` (draft `AnalyzeRule`, 1 MB cap). Policy tier
+`TenantAdminOrGlobalReader` — a POST by shape but a pure read in effect, so the
+read-only Global Reader is admitted; platform-scope callers reach any tenant's
+session via `FindSessionTenantIdAsync` (same pattern as `GetRuleResultsFunction`).
+
+`RuleEngine.DryRun.cs` is a partial-class trace twin of `EvaluateRule`: it
+shares the exact evaluators (`EvaluatePrecondition` / `EvaluateCondition` /
+`EvaluateConfidenceFactor`) but evaluates **all** conditions instead of breaking
+on the first failed required one — the full picture is the point of a dry run.
+Verdicts: `fired`, `skipped_by_precondition`, `required_condition_not_met`,
+`no_conditions_matched`, `below_confidence_threshold`, `no_events`. Each
+condition entry carries `matched`, the production evidence dictionary (or the
+evaluator's reason string) and `matchingEventCount` — how many session events
+even have that eventType, the first thing to check on an unexpected miss.
+
+Invariants, pinned by `RuleEngineDryRunTests`:
+
+* **Parity**: verdict `fired` ⇔ `EvaluateRule` produces a result, with identical
+  confidence and evidence keys. Factor evaluation stays sequential against the
+  accumulating `matchedConditions` (a factor can observe earlier `factor_*`
+  entries) — reordering would change results.
+* **Side-effect freedom**: exactly one strict event read; never a RuleResult
+  write, never `TryMarkSessionFailedFromRuleAsync`, never a notification.
+  `wouldMarkSessionAsFailed` is reported, not acted on.
+
+`test_analyze_rule` (MCP) wraps the endpoint and adds the interpolated
+explanation/remediation preview via the existing `interpolate-rule-template.ts`
+against the returned `matchedConditions`.
+
+## POST /api/rules/gather/test-pattern (backend)
+
+The logparser counterpart to the analyze dry-run, added after a field incident:
+a customer verified a logparser regex with a PHP tester and the agent's .NET
+engine matched differently. `TestLogPatternFunction` evaluates a pattern against
+pasted sample lines with the AGENT's exact matching semantics:
+
+* Regex construction identical to `LogParserCollector`: `Compiled`, 1 s timeout,
+  **no IgnoreCase** — logparser matching is case-sensitive (unlike analyze-rule
+  regex conditions, which run IgnoreCase).
+* `format` behaves exactly like the rule parameter: `cmtrace` (default) parses
+  each line via the shared `CmTraceLogParser` and matches against the parsed
+  MESSAGE only; `text` matches the raw line. First match per line
+  (`Regex.Match`), group `"0"` excluded, unsuccessful groups omitted — the
+  returned `groups` are exactly the event-data fields the device would emit.
+* Mirrors the agent's diagnostics: per-line outcomes
+  (`matched | no_match | parse_failed | regex_timeout`), the all-lines-parse-fail
+  hint ("set parameter format=text") verbatim, and a case-sensitivity note on
+  zero matches.
+* Pure compute on the request body — no tenant data touched. Same policy tier
+  as the dry-run (`TenantAdminOrGlobalReader`); caps: 200 lines, 8 KB/line,
+  1 MB body.
+
+Parity is structural, not duplicated: `CmTraceLogParser` moved from the agent
+(`Monitoring/Enrollment/Ime`) to **Shared** (`AutopilotMonitor.Shared.Logging`)
+so agent and backend run the SAME parsing implementation. Timestamp caveat:
+bias-less CMTrace lines parse with `AssumeLocal`, which on the backend is the
+server's timezone — the endpoint therefore reports match/parse results, never
+timestamps. `test_log_pattern` (MCP) wraps the endpoint; `validate_rule`
+additionally lints logparser parameters (missing/non-compiling pattern, unknown
+format value) and its `nextStep` routes logparser drafts to `test_log_pattern`.
+
+## What is deliberately absent
+
+* **No gather-rule remote execution** — gather rules run as SYSTEM on devices;
+  session dry-run is analyze-only. Logparser authors get the pattern tester
+  above; all gather authors get guardrail pre-flight plus the on-device debug
+  log ([gather-rule-debug-log](../agent/gather-rule-debug-log.md)).
+* **No rule write/deploy via MCP** — creating rules stays in the portal.
+
+# Citations
+
+* `src/Backend/AutopilotMonitor.Functions/Functions/Rules/TestLogPatternFunction.cs` — logparser pattern tester
+* `src/Shared/AutopilotMonitor.Shared/Logging/CmTraceLogParser.cs` — shared CMTrace parser (agent + backend)
+* `src/Backend/AutopilotMonitor.Functions/Services/RuleEngine.DryRun.cs` — trace twin + DTOs
+* `src/Backend/AutopilotMonitor.Functions/Functions/Rules/DryRunAnalyzeRuleFunction.cs` — endpoint + draft validation
+* `src/McpServer/autopilot-monitor-mcp/src/rule-validation.ts` — validator
+* `src/McpServer/autopilot-monitor-mcp/src/tools/rules.ts` — validate_rule / test_analyze_rule
+* `src/McpServer/autopilot-monitor-mcp/src/rule-authoring-guide.ts` — guide resource
+* `rules/scripts/combine.js` — MCP module generation

infra/mcp-server.bicep

@@ -60,8 +60,8 @@ param apiUrl string = 'https://autopilotmonitor-api-eu.azurewebsites.net'
 @description('Container image tag')
 param imageTag string = 'latest'
 
-@description('Entra ID app registration client_id used for the OAuth proxy. Public value (appears in JWT aud claim); not a secret.')
-param entraClientId string = '1a400946-62c1-4ab4-aa37-f730ac89704d'
+@description('Entra ID app registration client_id used for the OAuth proxy. Public value (appears in JWT aud claim); not a secret. Since the C4A8 app-reg move this is the NEW app (the old 1a400946-… app remains valid at the backend for legacy-homed tenants).')
+param entraClientId string = '886ab5e2-6144-442c-80cc-9b28e0667731'
 
 @secure()
 @description('Entra ID client secret for OAuth token exchange')
@@ -80,8 +80,8 @@ param mcpPublicUrl string = ''
 @description('Base64-encoded HMAC key (>=32 bytes after decode) for signing the OAuth proxy state. Naming and format match the backend\'s PaginationTokenSigningKey for consistency. Empty = generate per-instance random key on startup (acceptable for single-replica deployments since state has 10 min lifetime). Generate with PowerShell: [Convert]::ToBase64String([Security.Cryptography.RandomNumberGenerator]::GetBytes(32))')
 param oAuthStateSigningKey string = ''
 
-@description('Enable structured tool-call logging to stderr (queryable via Container App Logs)')
-param toolLoggingEnabled bool = false
+@description('Enable structured tool-call logging to stderr (queryable via Container App Logs). Volume is one small JSON line per tool call - negligible at current usage.')
+param toolLoggingEnabled bool = true
 
 // --- Azure Container Registry ---
 

rules/analyze/ANALYZE-SEC-008.json

@@ -0,0 +1,78 @@
+{
+  "$schema": "../schema/analyze-rule.schema.json",
+  "ruleId": "ANALYZE-SEC-008",
+  "title": "Secure Boot is disabled",
+  "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",
+  "author": "Autopilot Monitor",
+  "enabled": true,
+  "trigger": "single",
+  "baseConfidence": 70,
+  "preconditions": [
+    {
+      "source": "event_data",
+      "eventType": "secureboot_status",
+      "dataField": "note",
+      "operator": "not_exists",
+      "value": "",
+      "description": "Skip when the agent could not find the SecureBoot state registry key (note field set) — that indicates a legacy BIOS / non-UEFI device where Secure Boot is unsupported rather than disabled, so a warning would not be actionable."
+    }
+  ],
+  "conditions": [
+    {
+      "signal": "secureboot_disabled",
+      "source": "event_data",
+      "eventType": "secureboot_status",
+      "dataField": "uefiSecureBootEnabled",
+      "operator": "equals",
+      "value": "false",
+      "required": true
+    },
+    {
+      "signal": "physical_device",
+      "source": "event_data",
+      "eventType": "hardware_spec",
+      "dataField": "isVirtualMachine",
+      "operator": "equals",
+      "value": "false",
+      "required": false
+    }
+  ],
+  "confidenceFactors": [
+    { "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.",
+  "remediation": [
+    {
+      "title": "Enable Secure Boot in UEFI firmware",
+      "steps": [
+        "Reboot into the UEFI firmware setup (typically F2/F10/F12/Del during boot, or Shift+Restart -> Troubleshoot -> UEFI Firmware Settings)",
+        "Disable Legacy/CSM boot mode if it is active — Secure Boot requires native UEFI boot",
+        "Enable Secure Boot and ensure the Microsoft UEFI CA keys are selected (factory default key set)",
+        "Save, reboot and verify in Windows: msinfo32 -> 'Secure Boot State' = On, or PowerShell Confirm-SecureBootUEFI returns True",
+        "For Hyper-V test VMs: use a Generation 2 VM and enable Secure Boot in the VM's Security settings (template 'Microsoft Windows')"
+      ]
+    },
+    {
+      "title": "Check compliance impact",
+      "steps": [
+        "Review Intune compliance policies assigned to this device for a 'Require Secure Boot' setting",
+        "If the device stays non-compliant, Conditional Access policies may block sign-in — fix firmware settings before user handover"
+      ]
+    }
+  ],
+  "relatedDocs": [
+    {
+      "title": "Microsoft Learn: Secure Boot",
+      "url": "https://learn.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-secure-boot"
+    },
+    {
+      "title": "Microsoft Learn: Re-enable Secure Boot",
+      "url": "https://learn.microsoft.com/en-us/windows-hardware/manufacture/desktop/disabling-secure-boot"
+    }
+  ],
+  "tags": ["security", "secureboot", "firmware", "uefi", "compliance"]
+}

rules/dist/analyze-rules.json

@@ -2687,6 +2687,93 @@
         "truncated",
         "coverage"
       ]
+    },
+    {
+      "ruleId": "ANALYZE-SEC-008",
+      "title": "Secure Boot is disabled",
+      "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",
+      "author": "Autopilot Monitor",
+      "enabled": true,
+      "trigger": "single",
+      "baseConfidence": 70,
+      "preconditions": [
+        {
+          "source": "event_data",
+          "eventType": "secureboot_status",
+          "dataField": "note",
+          "operator": "not_exists",
+          "value": "",
+          "description": "Skip when the agent could not find the SecureBoot state registry key (note field set) — that indicates a legacy BIOS / non-UEFI device where Secure Boot is unsupported rather than disabled, so a warning would not be actionable."
+        }
+      ],
+      "conditions": [
+        {
+          "signal": "secureboot_disabled",
+          "source": "event_data",
+          "eventType": "secureboot_status",
+          "dataField": "uefiSecureBootEnabled",
+          "operator": "equals",
+          "value": "false",
+          "required": true
+        },
+        {
+          "signal": "physical_device",
+          "source": "event_data",
+          "eventType": "hardware_spec",
+          "dataField": "isVirtualMachine",
+          "operator": "equals",
+          "value": "false",
+          "required": false
+        }
+      ],
+      "confidenceFactors": [
+        {
+          "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.",
+      "remediation": [
+        {
+          "title": "Enable Secure Boot in UEFI firmware",
+          "steps": [
+            "Reboot into the UEFI firmware setup (typically F2/F10/F12/Del during boot, or Shift+Restart -> Troubleshoot -> UEFI Firmware Settings)",
+            "Disable Legacy/CSM boot mode if it is active — Secure Boot requires native UEFI boot",
+            "Enable Secure Boot and ensure the Microsoft UEFI CA keys are selected (factory default key set)",
+            "Save, reboot and verify in Windows: msinfo32 -> 'Secure Boot State' = On, or PowerShell Confirm-SecureBootUEFI returns True",
+            "For Hyper-V test VMs: use a Generation 2 VM and enable Secure Boot in the VM's Security settings (template 'Microsoft Windows')"
+          ]
+        },
+        {
+          "title": "Check compliance impact",
+          "steps": [
+            "Review Intune compliance policies assigned to this device for a 'Require Secure Boot' setting",
+            "If the device stays non-compliant, Conditional Access policies may block sign-in — fix firmware settings before user handover"
+          ]
+        }
+      ],
+      "relatedDocs": [
+        {
+          "title": "Microsoft Learn: Secure Boot",
+          "url": "https://learn.microsoft.com/en-us/windows-hardware/design/device-experiences/oem-secure-boot"
+        },
+        {
+          "title": "Microsoft Learn: Re-enable Secure Boot",
+          "url": "https://learn.microsoft.com/en-us/windows-hardware/manufacture/desktop/disabling-secure-boot"
+        }
+      ],
+      "tags": [
+        "security",
+        "secureboot",
+        "firmware",
+        "uefi",
+        "compliance"
+      ]
     }
   ]
 }

rules/scripts/combine.js

@@ -161,3 +161,45 @@ ${flatArray(guardrails.blockedEventLogChannels)}
 } else {
   console.warn('guardrails.json not found — skipping guardrails generation');
 }
+
+// ── MCP rule-authoring module generation ────────────────────────────────────
+// The MCP server exposes the rule schemas + guardrails as get_resource content
+// so a customer's AI can author rules against the real contract instead of
+// retrieval fragments. The server's tsconfig (rootDir: src, no resolveJsonModule)
+// and the Docker build (rules/schema not copied) rule out importing the JSON
+// directly — so we bake it into a TS module, exactly like the web mirror above.
+// CI's guardrails-in-sync job re-runs this script and fails on any diff, which
+// makes drift between rules/* and this generated module impossible to merge.
+
+const mcpAuthoringOutput = path.resolve(
+  rulesRoot, '..', 'src', 'McpServer', 'autopilot-monitor-mcp', 'src', 'rule-authoring.generated.ts'
+);
+
+{
+  const guardrails = JSON.parse(fs.readFileSync(guardrailsPath, 'utf8'));
+  const gatherSchema = JSON.parse(fs.readFileSync(path.join(rulesRoot, 'schema', 'gather-rule.schema.json'), 'utf8'));
+  const analyzeSchema = JSON.parse(fs.readFileSync(path.join(rulesRoot, 'schema', 'analyze-rule.schema.json'), 'utf8'));
+
+  const ts = `/**
+ * AUTO-GENERATED from rules/guardrails.json + rules/schema/*.schema.json — DO NOT EDIT.
+ * Run: node rules/scripts/combine.js
+ *
+ * Consumed by the MCP server's rule-authoring surface (get_resource +
+ * validate_rule): the JSON Schemas are the validation contract, the guardrails
+ * are the agent-side collection allowlists. Single source of truth is rules/;
+ * the CI guardrails-in-sync job guards this file against drift.
+ */
+
+/** JSON Schema (2020-12) for gather rules — rules/schema/gather-rule.schema.json verbatim. */
+export const GATHER_RULE_SCHEMA: Record<string, unknown> = ${JSON.stringify(gatherSchema, null, 2)};
+
+/** JSON Schema (2020-12) for analyze rules — rules/schema/analyze-rule.schema.json verbatim. */
+export const ANALYZE_RULE_SCHEMA: Record<string, unknown> = ${JSON.stringify(analyzeSchema, null, 2)};
+
+/** Gather-rule collection guardrails — rules/guardrails.json verbatim. */
+export const RULE_GUARDRAILS = ${JSON.stringify(guardrails, null, 2)} as const;
+`;
+
+  fs.writeFileSync(mcpAuthoringOutput, ts, 'utf8');
+  console.log('rule-authoring.generated.ts: schemas + guardrails baked for MCP server');
+}

scripts/Bootstrap/Install-AutopilotMonitor.Tests.ps1

@@ -0,0 +1,307 @@
+# Pester tests (Pester 5+) for the bootstrap guard/relax logic in
+# 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,
+# registry, filesystem, WinRT) is mocked; profile directories are real folders
+# under Pester's $TestDrive with a manipulated CreationTimeUtc.
+#
+# Run under Windows PowerShell 5.1 to match the IME runtime:
+#   powershell.exe -NoProfile -Command "& { $c = New-PesterConfiguration; $c.Run.Path = 'scripts\Bootstrap'; $c.Output.Verbosity = 'Detailed'; Invoke-Pester -Configuration $c }"
+#
+# This file MUST remain pure ASCII (PS 5.1 reads BOM-less files as ANSI).
+
+BeforeAll {
+    . (Join-Path $PSScriptRoot 'Install-AutopilotMonitor.ps1')
+
+    function New-FakeProfile {
+        param([string]$Name, [double]$AgeMinutes)
+        $p = Join-Path $TestDrive $Name
+        New-Item -ItemType Directory -Path $p -Force | Out-Null
+        (Get-Item $p).CreationTimeUtc = (Get-Date).ToUniversalTime().AddMinutes(-$AgeMinutes)
+        return $p
+    }
+}
+
+Describe 'Test-IsCloudPc' {
+    # 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' } }
+    }
+
+    It 'detects a Cloud PC when both markers are present' {
+        Mock Test-Path { $true } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\Microsoft\Windows365' }
+        Mock Get-Service { [pscustomobject]@{ Name = 'CloudManagedDesktopExtension'; Status = 'Running' } }
+        Test-IsCloudPc | Should -BeTrue
+    }
+
+    It 'does not detect with the registry key alone (e.g. W365-Boot physical client)' {
+        Mock Test-Path { $true } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\Microsoft\Windows365' }
+        Mock Get-Service { $null }
+        Test-IsCloudPc | Should -BeFalse
+    }
+
+    It 'does not detect with the service alone' {
+        Mock Test-Path { $false } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\Microsoft\Windows365' }
+        Mock Get-Service { [pscustomobject]@{ Name = 'CloudManagedDesktopExtension'; Status = 'Running' } }
+        Test-IsCloudPc | Should -BeFalse
+    }
+
+    It 'does not detect a plain device (no markers)' {
+        Mock Test-Path { $false } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\Microsoft\Windows365' }
+        Mock Get-Service { $null }
+        Test-IsCloudPc | Should -BeFalse
+    }
+
+    It 'still evaluates markers when the WMI identity query fails' {
+        Mock Get-CimInstance { throw 'RPC server unavailable' }
+        Mock Test-Path { $true } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\Microsoft\Windows365' }
+        Mock Get-Service { [pscustomobject]@{ Name = 'CloudManagedDesktopExtension'; Status = 'Running' } }
+        Test-IsCloudPc | Should -BeTrue
+    }
+}
+
+Describe 'Get-OobeState' {
+    It 'returns a non-empty state string and never throws' {
+        Get-OobeState | Should -Not -BeNullOrEmpty
+    }
+}
+
+Describe 'Get-RealUserProfilePaths' {
+    BeforeEach {
+        Mock Write-Log { }
+    }
+
+    It 'merges WMI and filesystem views, drops special/system profiles, dedupes' {
+        Mock Get-CimInstance {
+            @(
+                [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\UserOne' }
+                [pscustomobject]@{ FullName = 'C:\Users\Public' }
+                [pscustomobject]@{ FullName = 'C:\Users\defaultuser0' }
+                [pscustomobject]@{ FullName = 'C:\Users\WDAGUtilityAccount' }
+            )
+        }
+        $result = @(Get-RealUserProfilePaths)
+        $result | Should -Be @('C:\Users\UserOne')
+    }
+
+    It 'falls back to the filesystem view when the WMI query fails' {
+        Mock Get-CimInstance { throw 'WMI broken' }
+        Mock Get-ChildItem {
+            @(
+                [pscustomobject]@{ FullName = 'C:\Users\SomeUser' }
+                [pscustomobject]@{ FullName = 'C:\Users\Default' }
+            )
+        }
+        $result = @(Get-RealUserProfilePaths)
+        $result | Should -Be @('C:\Users\SomeUser')
+    }
+
+    It 'returns an empty result when only special/system profiles exist' {
+        Mock Get-CimInstance { @() }
+        Mock Get-ChildItem {
+            @(
+                [pscustomobject]@{ FullName = 'C:\Users\Public' }
+                [pscustomobject]@{ FullName = 'C:\Users\defaultuser1' }
+            )
+        }
+        @(Get-RealUserProfilePaths).Count | Should -Be 0
+    }
+}
+
+Describe 'Get-RelaxDecision' {
+    BeforeEach {
+        Mock Write-Log { }
+        # Defaults: physical device, OOBE long done. Individual tests override.
+        Mock Get-OobeState { 'Completed' }
+        Mock Test-IsCloudPc { $false }
+    }
+
+    Context 'Windows 365 Cloud PC' {
+        BeforeEach {
+            Mock Test-IsCloudPc { $true }
+        }
+
+        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)' {
+            $p = New-FakeProfile 'CloudPcUser' 30
+            (Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15).Active | Should -BeFalse
+        }
+
+        It 'does not relax for two profiles' {
+            $p1 = New-FakeProfile 'UserA' 2
+            $p2 = New-FakeProfile 'UserB' 400
+            (Get-RelaxDecision -ProfilePaths @($p1, $p2) -OobeProfileMaxAgeMinutes 15).Active | Should -BeFalse
+        }
+
+        It 'relaxes even when the WinRT OOBE API is unavailable (old build)' {
+            Mock Get-OobeState { 'Unavailable' }
+            $p = New-FakeProfile 'CpcUser' 1
+            (Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15).Active | Should -BeTrue
+        }
+
+        It 'does not relax for a profile with a future creation time (clock skew)' {
+            $p = New-FakeProfile 'SkewUser' -10
+            (Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15).Active | Should -BeFalse
+        }
+    }
+
+    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
+            $d = Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15
+            $d.Active | Should -BeTrue
+        }
+    }
+
+    Context 'no trigger' {
+        It 'does not relax on a physical device with a fresh profile and OOBE Completed' {
+            $p = New-FakeProfile 'SomeUser' 2
+            (Get-RelaxDecision -ProfilePaths @($p) -OobeProfileMaxAgeMinutes 15).Active | Should -BeFalse
+        }
+
+        It 'stays inactive with no profiles at all' {
+            (Get-RelaxDecision -ProfilePaths @() -OobeProfileMaxAgeMinutes 15).Active | Should -BeFalse
+        }
+    }
+}
+
+Describe 'Get-BootstrapDecision' {
+    BeforeEach {
+        Mock Write-Log { }
+        # Baseline: clean device during Device ESP -- no marker, no profiles, no
+        # logged-on user, 1h uptime, agent not installed. Tests override selectively.
+        Mock Get-ItemProperty { $null }
+        Mock Get-RealUserProfilePaths { @() }
+        Mock Get-OobeState { 'Completed' }
+        Mock Test-IsCloudPc { $false }
+        Mock Get-CimInstance { [pscustomobject]@{ LastBootUpTime = (Get-Date).AddHours(-1) } } -ParameterFilter { $ClassName -eq 'Win32_OperatingSystem' }
+        $script:cleanAgentBin = Join-Path $TestDrive 'AgentBin'
+    }
+
+    It 'installs on a clean ESP device' {
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeTrue
+        $d.ReasonCode | Should -BeNullOrEmpty
+        $d.RelaxActive | Should -BeFalse
+    }
+
+    It 'skips when the Deployed marker exists (guard 1)' {
+        Mock Get-ItemProperty { [pscustomobject]@{ Deployed = '2026-08-01T10:00:00Z' } } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\AutopilotMonitor' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'AlreadyDeployed'
+    }
+
+    It 'skips a productive device with an old profile (guard 2)' {
+        $script:fakeProfile = New-FakeProfile 'OldUser' 5000
+        Mock Get-RealUserProfilePaths { @($script:fakeProfile) }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'ProfilesFound'
+    }
+
+    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\CloudPcUser' } } -ParameterFilter { $Path -like '*LogonUI*' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeTrue
+        $d.RelaxActive | Should -BeTrue
+    }
+
+    It 'skips when a real user has logged on and no relax applies (guard 3)' {
+        Mock Get-ItemProperty { [pscustomobject]@{ LastLoggedOnUser = 'AzureAD\SomeUser' } } -ParameterFilter { $Path -like '*LogonUI*' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'LastLoggedOnUser'
+    }
+
+    It 'does not skip for the defaultuser0 OOBE account (guard 3)' {
+        Mock Get-ItemProperty { [pscustomobject]@{ LastLoggedOnUser = 'defaultuser0' } } -ParameterFilter { $Path -like '*LogonUI*' }
+        (Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin).Install | Should -BeTrue
+    }
+
+    It 'skips when uptime exceeds the bootstrap window (guard 4)' {
+        Mock Get-CimInstance { [pscustomobject]@{ LastBootUpTime = (Get-Date).AddHours(-20) } } -ParameterFilter { $ClassName -eq 'Win32_OperatingSystem' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'UptimeExceeded'
+    }
+
+    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.
+        $script:fakeProfile = New-FakeProfile 'FirstConnectUser' 0.6
+        Mock Get-RealUserProfilePaths { @($script:fakeProfile) }
+        Mock Test-IsCloudPc { $true }
+        Mock Get-CimInstance { [pscustomobject]@{ LastBootUpTime = (Get-Date).AddHours(-90) } } -ParameterFilter { $ClassName -eq 'Win32_OperatingSystem' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeTrue
+        $d.RelaxActive | Should -BeTrue
+    }
+
+    It 'still skips an over-uptime Cloud PC when the relax is NOT active (no fresh profile)' {
+        Mock Test-IsCloudPc { $true }
+        Mock Get-CimInstance { [pscustomobject]@{ LastBootUpTime = (Get-Date).AddHours(-90) } } -ParameterFilter { $ClassName -eq 'Win32_OperatingSystem' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'UptimeExceeded'
+    }
+
+    It 'keeps guard 4 for the OOBE-restore relax (physical device, uptime is meaningful)' {
+        $script:fakeProfile = New-FakeProfile 'RestoreUser' 3
+        Mock Get-RealUserProfilePaths { @($script:fakeProfile) }
+        Mock Get-OobeState { 'InProgress' }
+        Mock Get-CimInstance { [pscustomobject]@{ LastBootUpTime = (Get-Date).AddHours(-20) } } -ParameterFilter { $ClassName -eq 'Win32_OperatingSystem' }
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $script:cleanAgentBin
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'UptimeExceeded'
+    }
+
+    It 'skips when the agent binary is already present (guard 5)' {
+        $binPath = Join-Path $TestDrive 'AgentBinExisting'
+        New-Item -ItemType Directory -Path $binPath -Force | Out-Null
+        Set-Content -Path (Join-Path $binPath 'AutopilotMonitor.Agent.exe') -Value 'stub'
+        $d = Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath $binPath
+        $d.Install | Should -BeFalse
+        $d.ReasonCode | Should -Be 'AgentPresent'
+    }
+}
+
+Describe 'logging purity' {
+    # Regression guard: Write-Log runs inside functions that RETURN decision
+    # objects. If it ever emits to the output stream again (Write-Output), the
+    # log lines leak into the return values and turn them into arrays. This
+    # test deliberately does NOT mock Write-Log.
+    It 'Get-BootstrapDecision returns exactly one object with real logging' {
+        Mock Get-ItemProperty { [pscustomobject]@{ Deployed = '2026-08-01T10:00:00Z' } } -ParameterFilter { $Path -eq 'HKLM:\SOFTWARE\AutopilotMonitor' }
+        # Plain local assignment: PowerShell's dynamic scoping makes Write-Log
+        # (called from Get-BootstrapDecision) resolve this $LogFile instead of
+        # the ProgramData path defined by the dot-sourced script.
+        $LogFile = Join-Path $TestDrive 'bootstrap_test.log'
+        $d = @(Get-BootstrapDecision -MaxBootstrapWindowHours 12 -OobeProfileMaxAgeMinutes 15 -AgentBinPath (Join-Path $TestDrive 'NoAgent'))
+        $d.Count | Should -Be 1
+        $d[0].ReasonCode | Should -Be 'AlreadyDeployed'
+        Get-Content $LogFile -Raw | Should -Match 'SKIP: Agent was previously deployed'
+    }
+}

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"

scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1

@@ -23,7 +23,11 @@
     One or more high-level feature identifiers. The script translates each to the underlying
     Graph permissions. Use this when you don't want to know permission strings.
     Available features:
-      - ScriptDisplayNames -> DeviceManagementScripts.Read.All
+      - ScriptDisplayNames     -> DeviceManagementScripts.Read.All
+      - W365CloudPcValidation  -> CloudPC.Read.All
+        (validates Windows 365 Cloud PCs against the tenant's Cloud PC inventory --
+         Cloud PCs are never Autopilot-registered, so this enables agent monitoring
+         of Cloud PC first-connect enrollment)
 
 .PARAMETER Permissions
     Microsoft Graph application permission names to grant directly. Use when the admin UI
@@ -76,7 +80,7 @@ param(
     [string]$ClientId,
 
     [Parameter(Mandatory = $true, ParameterSetName = 'ByFeatures')]
-    [ValidateSet('ScriptDisplayNames')]
+    [ValidateSet('ScriptDisplayNames', 'W365CloudPcValidation')]
     [string[]]$Features,
 
     [Parameter(Mandatory = $true, ParameterSetName = 'ByPermissions')]
@@ -97,7 +101,8 @@ $ErrorActionPreference = 'Stop'
 # ---- Feature -> Graph permission catalog -----------------------------------
 # Keep in lock-step with src/Shared/AutopilotMonitor.Shared/Models/Graph/GraphFeatureCatalog.cs
 $FeatureCatalog = @{
-    'ScriptDisplayNames' = @('DeviceManagementScripts.Read.All')
+    'ScriptDisplayNames'    = @('DeviceManagementScripts.Read.All')
+    'W365CloudPcValidation' = @('CloudPC.Read.All')
 }
 
 # Translate Features -> Permissions when caller used the high-level form.

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

@@ -1,5 +1,5 @@
 using System;
-using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using AutopilotMonitor.Shared.Logging;
 using Xunit;
 
 namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
@@ -92,6 +92,27 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Monitoring.Ime
             Assert.InRange(entry.Timestamp, before.AddSeconds(-5), after.AddSeconds(5));
         }
 
+        // ── UTC-bias suffix on the time field → honored, not dropped ──────────
+
+        [Theory]
+        [InlineData("+480", 8 * 60)]   // PST writer (UTC-8): UTC = local + 480min
+        [InlineData("-060", -60)]      // UTC+1 writer: UTC = local - 60min
+        public void TryParseLine_applies_utc_bias_suffix(string bias, int expectedOffsetMinutes)
+        {
+            // Session df1fcf47: a writer whose timezone differs from the agent's stamped its
+            // lines with an explicit bias. Without bias handling the line either failed to
+            // match at all (old regex) or would be misread in agent-local time.
+            var line = CmTraceLine("msg", "11:46:19.0226610" + bias, "7-29-2026");
+
+            var ok = CmTraceLogParser.TryParseLine(line, out var entry);
+
+            Assert.True(ok);
+            Assert.Equal(
+                new DateTime(2026, 7, 29, 11, 46, 19, DateTimeKind.Utc).AddTicks(226610).AddMinutes(expectedOffsetMinutes),
+                entry.Timestamp);
+            Assert.Equal(DateTimeKind.Utc, entry.Timestamp.Kind);
+        }
+
         // ── Oversized line → parses, no throw, no truncation of the message ───
 
         [Fact]

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Orchestration/EnrollmentOrchestratorEventBridgeTests.cs

@@ -54,6 +54,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
             public ISignalIngressSink? CapturedIngress { get; private set; }
             public IClock? CapturedClock { get; private set; }
             public AutopilotMonitor.Agent.V2.Core.Transport.Telemetry.ITelemetrySpool? CapturedTelemetrySpool { get; private set; }
+            public TimelineEventStream? CapturedTimelineEvents { get; private set; }
 
             public CollectorSurfaces CreateCollectorHosts(
                 string sessionId,
@@ -62,12 +63,14 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
                 IReadOnlyCollection<string> whiteGloveSealingPatternIds,
                 ISignalIngressSink ingress,
                 IClock clock,
-                AutopilotMonitor.Agent.V2.Core.Transport.Telemetry.ITelemetrySpool? telemetrySpool)
+                AutopilotMonitor.Agent.V2.Core.Transport.Telemetry.ITelemetrySpool? telemetrySpool,
+                TimelineEventStream? timelineEvents = null)
             {
                 CapturedWhiteGloveSealingPatternIds = whiteGloveSealingPatternIds;
                 CapturedIngress = ingress;
                 CapturedClock = clock;
                 CapturedTelemetrySpool = telemetrySpool;
+                CapturedTimelineEvents = timelineEvents;
                 foreach (var name in HostNames)
                 {
                     Hosts.Add(new FakeCollectorHost(name));

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Orchestration/EnrollmentOrchestratorWhiteGlovePatternTests.cs

@@ -27,7 +27,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
                 IReadOnlyCollection<string> whiteGloveSealingPatternIds,
                 ISignalIngressSink ingress,
                 IClock clock,
-                AutopilotMonitor.Agent.V2.Core.Transport.Telemetry.ITelemetrySpool? telemetrySpool)
+                AutopilotMonitor.Agent.V2.Core.Transport.Telemetry.ITelemetrySpool? telemetrySpool,
+                TimelineEventStream? timelineEvents = null)
             {
                 CapturedPatternIds = whiteGloveSealingPatternIds;
                 return new CollectorSurfaces(Array.Empty<ICollectorHost>());

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Orchestration/GatherRuleExecutorHostTimelineFeedTests.cs

@@ -0,0 +1,189 @@
+#nullable enable
+using System;
+using System.Collections.Generic;
+using System.Diagnostics;
+using System.Threading;
+using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Agent.V2.Core.Orchestration;
+using AutopilotMonitor.Agent.V2.Core.Tests.Harness;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using AutopilotMonitor.Shared.Models;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Orchestration
+{
+    /// <summary>
+    /// GatherRuleExecutorHost feeds its phase_change / phase_exit / on_event triggers from the
+    /// POST-REDUCE <see cref="TimelineEventStream"/> (emitted timeline events), not from raw
+    /// signals. Regression anchor: session 32312a32 (rsneuffen.de) — a phase_change rule on
+    /// FinalizingSetup fired at the raw EspPhaseChanged(FinalizingSetup) signal (ESP exit),
+    /// 7 minutes before the engine's RealmJoin-gated phase_transition(FinalizingSetup), and read
+    /// a registry key before the RealmJoin package wrote it. With the timeline feed the rule
+    /// fires only when the phase declaration is actually emitted.
+    /// Rules use the absent-registry-path pattern so no real system state is touched; execution
+    /// is observed via the InformationalEvent posts the host sends through its ingress sink.
+    /// </summary>
+    [Collection("SerialThreading")] // rules execute on the shared ThreadPool
+    public sealed class GatherRuleExecutorHostTimelineFeedTests : IDisposable
+    {
+        private const string AbsentPath =
+            "HKLM\\SOFTWARE\\AutopilotMonitorTests\\DefinitelyAbsent_5b1f03a2-0000-0000-0000-000000000000";
+
+        private readonly TempDirectory _tmp = new TempDirectory();
+        private readonly CapturingSink _sink = new CapturingSink();
+        private readonly TimelineEventStream _stream = new TimelineEventStream();
+        private GatherRuleExecutorHost? _host;
+
+        public void Dispose()
+        {
+            _host?.Dispose();
+            _tmp.Dispose();
+        }
+
+        private sealed class CapturingSink : ISignalIngressSink
+        {
+            private readonly List<string> _eventTypes = new List<string>();
+            private readonly object _gate = new object();
+
+            public int CountOf(string eventType)
+            {
+                lock (_gate)
+                {
+                    var n = 0;
+                    foreach (var t in _eventTypes)
+                        if (string.Equals(t, eventType, StringComparison.Ordinal)) n++;
+                    return n;
+                }
+            }
+
+            public void Post(
+                DecisionSignalKind kind,
+                DateTime occurredAtUtc,
+                string sourceOrigin,
+                Evidence evidence,
+                IReadOnlyDictionary<string, string>? payload = null,
+                int kindSchemaVersion = 1,
+                object? typedPayload = null)
+            {
+                if (kind != DecisionSignalKind.InformationalEvent || payload == null) return;
+                if (!payload.TryGetValue(SignalPayloadKeys.EventType, out var eventType)) return;
+                lock (_gate) _eventTypes.Add(eventType);
+            }
+        }
+
+        private void BuildHost(params GatherRule[] rules)
+        {
+            var logger = new AgentLogger(_tmp.Path, AgentLogLevel.Info);
+            _host = new GatherRuleExecutorHost(
+                sessionId: "sess",
+                tenantId: "tenant",
+                ingress: _sink,
+                clock: new SystemClock(),
+                logger: logger,
+                rules: new List<GatherRule>(rules),
+                imeLogPathOverride: null,
+                unrestrictedMode: true,
+                gatherDebugLogPath: null,
+                timelineEvents: _stream);
+            _host.Start();
+        }
+
+        private bool WaitForCount(string eventType, int count, int timeoutMs = 10000)
+        {
+            var sw = Stopwatch.StartNew();
+            while (sw.ElapsedMilliseconds < timeoutMs)
+            {
+                if (_sink.CountOf(eventType) >= count) return true;
+                Thread.Sleep(25);
+            }
+            return _sink.CountOf(eventType) >= count;
+        }
+
+        private static GatherRule Rule(string id, string trigger, string? triggerPhase = null, string? triggerEventType = null)
+            => new GatherRule
+            {
+                RuleId = id,
+                Title = id,
+                CollectorType = "registry",
+                Target = AbsentPath,
+                Trigger = trigger,
+                TriggerPhase = triggerPhase ?? string.Empty,
+                TriggerEventType = triggerEventType ?? string.Empty,
+                OutputEventType = "gather_host_test",
+                Enabled = true,
+            };
+
+        [Fact]
+        public void PhaseChangeRule_FiresOnEmittedPhaseDeclaration_NotOnPhaselessEvents()
+        {
+            BuildHost(Rule("GATHER-HOST-001", "phase_change", triggerPhase: "FinalizingSetup"));
+
+            // The raw-world sequence of session 32312a32 as it reaches the emitted timeline:
+            // esp_exiting and hello_wizard_started are emitted WITHOUT a phase declaration
+            // (the engine holds FinalizingSetup back behind the RealmJoin gate) — no fire.
+            _stream.Publish("esp_exiting", EnrollmentPhase.Unknown);
+            _stream.Publish("hello_wizard_started", EnrollmentPhase.Unknown);
+            Thread.Sleep(300);
+            Assert.Equal(0, _sink.CountOf("gather_host_test"));
+
+            // Only the engine's actual phase declaration fires the rule.
+            _stream.Publish("phase_transition", EnrollmentPhase.FinalizingSetup);
+            Assert.True(WaitForCount("gather_host_test", 1));
+        }
+
+        [Fact]
+        public void OnEventRule_FiresForEngineEmittedEventTypes()
+        {
+            // enrollment_complete is an engine-emitted effect event; it never existed on the raw
+            // InformationalEvent signal stream, so the docs-promised "On Event with
+            // enrollment_complete" trigger was dead under the previous SignalPosted feed.
+            BuildHost(Rule("GATHER-HOST-002", "on_event", triggerEventType: "enrollment_complete"));
+
+            _stream.Publish("enrollment_complete", EnrollmentPhase.Unknown);
+            Assert.True(WaitForCount("gather_host_test", 1));
+        }
+
+        [Fact]
+        public void PhaseFeed_DedupsConsecutiveSamePhaseDeclarations()
+        {
+            // "Any phase" phase_change rule fires on every phase TRANSITION — a re-declared
+            // identical phase (e.g. duplicate esp_phase_changed) must not count as one.
+            BuildHost(Rule("GATHER-HOST-003", "phase_change", triggerPhase: ""));
+
+            _stream.Publish("esp_phase_changed", EnrollmentPhase.DeviceSetup);
+            Assert.True(WaitForCount("gather_host_test", 1));
+
+            _stream.Publish("esp_phase_changed", EnrollmentPhase.DeviceSetup);
+            Thread.Sleep(300);
+            Assert.Equal(1, _sink.CountOf("gather_host_test"));
+
+            _stream.Publish("esp_phase_changed", EnrollmentPhase.AccountSetup);
+            Assert.True(WaitForCount("gather_host_test", 2));
+        }
+
+        [Fact]
+        public void PhaseExitRule_FiresWhenEmittedTimelineLeavesThePhase()
+        {
+            BuildHost(Rule("GATHER-HOST-004", "phase_exit", triggerPhase: "AccountSetup"));
+
+            _stream.Publish("esp_phase_changed", EnrollmentPhase.AccountSetup);
+            Thread.Sleep(300);
+            Assert.Equal(0, _sink.CountOf("gather_host_test"));
+
+            _stream.Publish("phase_transition", EnrollmentPhase.FinalizingSetup);
+            Assert.True(WaitForCount("gather_host_test", 1));
+        }
+
+        [Fact]
+        public void StoppedHost_NoLongerReactsToTheStream()
+        {
+            BuildHost(Rule("GATHER-HOST-005", "on_event", triggerEventType: "enrollment_complete"));
+
+            _host!.Stop();
+            _stream.Publish("enrollment_complete", EnrollmentPhase.Unknown);
+            Thread.Sleep(300);
+            Assert.Equal(0, _sink.CountOf("gather_host_test"));
+        }
+    }
+}

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Program/InstallModeMergeTests.cs

@@ -132,10 +132,12 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
         }
 
         [Fact]
-        public void First_install_without_wait_arg_uses_agent_default_of_600()
+        public void First_install_without_wait_arg_persists_null_so_runtime_default_applies()
         {
             // Generic bootstrap path: PS1 calls `--install` without --tenant-id-wait,
-            // and there is no persisted config yet. Agent owns the default (600 s).
+            // and there is no persisted config yet. "Not configured" is persisted as null
+            // so BuildAgentConfiguration applies the agent-side default (600 s) — freezing
+            // a number into the file would decouple deployed devices from default changes.
             var merged = AutopilotMonitor.Agent.V2.Program.MergeBootstrapConfig(
                 existing: null,
                 bootstrapTokenArg: null!, bootstrapTokenGiven: false,
@@ -144,20 +146,42 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
 
             Assert.Null(merged.BootstrapToken);
             Assert.Null(merged.TenantId);
-            Assert.Equal(600, merged.TenantIdWaitSeconds);
+            Assert.Null(merged.TenantIdWaitSeconds);
         }
 
         [Fact]
-        public void Existing_config_without_wait_field_treated_as_zero()
+        public void Legacy_config_without_wait_field_stays_null_on_plain_reinstall()
         {
-            // BackCompat: pre-fix bootstrap-config.json has no TenantIdWaitSeconds field;
-            // Newtonsoft deserialises that to 0. New install with --tenant-id-wait 600
-            // overrides cleanly; no extra migration logic required.
+            // BackCompat: pre-feature bootstrap-config.json has no TenantIdWaitSeconds
+            // property → nullable deserialisation yields null. A reinstall that does not
+            // pass --tenant-id-wait must NOT turn that into 0 (which would silently
+            // disable the wait); null carries through and the runtime default applies.
             var existing = new BootstrapConfigFile
             {
                 BootstrapToken = "tok-legacy",
                 TenantId = "tenant-legacy",
-                TenantIdWaitSeconds = 0,
+                TenantIdWaitSeconds = null,
+            };
+
+            var merged = AutopilotMonitor.Agent.V2.Program.MergeBootstrapConfig(
+                existing,
+                bootstrapTokenArg: null!, bootstrapTokenGiven: false,
+                tenantIdArg: null!, tenantIdGiven: false,
+                tenantIdWaitSeconds: 0, tenantIdWaitGiven: false);
+
+            Assert.Equal("tok-legacy", merged.BootstrapToken);
+            Assert.Equal("tenant-legacy", merged.TenantId);
+            Assert.Null(merged.TenantIdWaitSeconds);
+        }
+
+        [Fact]
+        public void Legacy_config_without_wait_field_takes_explicit_wait_arg()
+        {
+            var existing = new BootstrapConfigFile
+            {
+                BootstrapToken = "tok-legacy",
+                TenantId = "tenant-legacy",
+                TenantIdWaitSeconds = null,
             };
 
             var merged = AutopilotMonitor.Agent.V2.Program.MergeBootstrapConfig(
@@ -170,5 +194,26 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
             Assert.Equal("tenant-legacy", merged.TenantId);
             Assert.Equal(600, merged.TenantIdWaitSeconds);
         }
+
+        [Fact]
+        public void Explicit_zero_opt_out_survives_redeploy_without_wait_arg()
+        {
+            // An admin's deliberate `--tenant-id-wait 0` must not be resurrected to a
+            // wait by a later redeploy that omits the flag.
+            var existing = new BootstrapConfigFile
+            {
+                BootstrapToken = "tok-abc",
+                TenantId = "tenant-xyz",
+                TenantIdWaitSeconds = 0,
+            };
+
+            var merged = AutopilotMonitor.Agent.V2.Program.MergeBootstrapConfig(
+                existing,
+                bootstrapTokenArg: null!, bootstrapTokenGiven: false,
+                tenantIdArg: null!, tenantIdGiven: false,
+                tenantIdWaitSeconds: 0, tenantIdWaitGiven: false);
+
+            Assert.Equal(0, merged.TenantIdWaitSeconds);
+        }
     }
 }

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Program/PostEnrollmentFactsObservedSignalTests.cs

@@ -66,6 +66,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
             // same facts signal (safe default "false" off-device).
             var selfDeploying = payload["isSelfDeployingProfile"];
             Assert.True(selfDeploying == "true" || selfDeploying == "false");
+            // W365 — the Cloud PC marker fact rides the same signal (safe default "false"
+            // off-device; a build host is not a Cloud PC).
+            Assert.Contains("isCloudPc", (IDictionary<string, string>)payload);
+            var cloudPc = payload["isCloudPc"];
+            Assert.True(cloudPc == "true" || cloudPc == "false");
         }
 
         [Fact]

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Program/TenantIdWaitResolutionTests.cs

@@ -0,0 +1,90 @@
+using AutopilotMonitor.Agent.V2;
+using AutopilotMonitor.Agent.V2.Core.Configuration;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Program
+{
+    /// <summary>
+    /// Pins the TenantIdWaitSeconds resolution order in
+    /// <see cref="AutopilotMonitor.Agent.V2.Program.BuildAgentConfiguration"/>:
+    /// CLI arg &gt; persisted bootstrap-config.json value &gt; agent default (600 s).
+    /// The regression this guards: a legacy bootstrap-config.json written before the
+    /// TenantIdWaitSeconds property existed deserialises to null — that must fall
+    /// through to the 600 s default, NOT be treated as an explicit 0 opt-out
+    /// (which silently disabled the wait and broke Hybrid-AAD-join devices whose
+    /// registry TenantId lands minutes after first boot).
+    /// </summary>
+    public sealed class TenantIdWaitResolutionTests
+    {
+        private static AgentConfiguration Build(BootstrapConfigFile bootstrapConfig, params string[] args) =>
+            AutopilotMonitor.Agent.V2.Program.BuildAgentConfiguration(
+                args: args,
+                tenantId: "tenant-t",
+                sessionId: "session-s",
+                bootstrapConfig: bootstrapConfig,
+                awaitConfig: null);
+
+        [Fact]
+        public void No_cli_and_no_bootstrap_config_uses_default_600()
+        {
+            var cfg = Build(bootstrapConfig: null);
+
+            Assert.Equal(600, cfg.TenantIdWaitSeconds);
+        }
+
+        [Fact]
+        public void Legacy_bootstrap_config_with_null_wait_uses_default_600()
+        {
+            var legacy = new BootstrapConfigFile
+            {
+                BootstrapToken = "tok-legacy",
+                TenantId = "tenant-legacy",
+                TenantIdWaitSeconds = null,
+            };
+
+            var cfg = Build(legacy);
+
+            Assert.Equal(600, cfg.TenantIdWaitSeconds);
+        }
+
+        [Fact]
+        public void Explicit_zero_in_bootstrap_config_disables_wait()
+        {
+            var optedOut = new BootstrapConfigFile { TenantIdWaitSeconds = 0 };
+
+            var cfg = Build(optedOut);
+
+            Assert.Equal(0, cfg.TenantIdWaitSeconds);
+        }
+
+        [Fact]
+        public void Nonzero_bootstrap_config_value_wins_over_default()
+        {
+            var configured = new BootstrapConfigFile { TenantIdWaitSeconds = 1800 };
+
+            var cfg = Build(configured);
+
+            Assert.Equal(1800, cfg.TenantIdWaitSeconds);
+        }
+
+        [Fact]
+        public void Cli_arg_wins_over_bootstrap_config_value()
+        {
+            var configured = new BootstrapConfigFile { TenantIdWaitSeconds = 1800 };
+
+            var cfg = Build(configured, "--tenant-id-wait", "300");
+
+            Assert.Equal(300, cfg.TenantIdWaitSeconds);
+        }
+
+        [Fact]
+        public void Cli_zero_wins_over_bootstrap_config_value()
+        {
+            var configured = new BootstrapConfigFile { TenantIdWaitSeconds = 1800 };
+
+            var cfg = Build(configured, "--tenant-id-wait", "0");
+
+            Assert.Equal(0, cfg.TenantIdWaitSeconds);
+        }
+    }
+}

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Security/CloudPcDetectorTests.cs

@@ -0,0 +1,74 @@
+using System;
+using System.Collections.Generic;
+using AutopilotMonitor.Agent.V2.Core.Security;
+using Xunit;
+
+namespace AutopilotMonitor.Agent.V2.Core.Tests.Security
+{
+    /// <summary>
+    /// Pins the marker-AND contract of <see cref="CloudPcDetector.ResolveIsCloudPc"/>: BOTH
+    /// the Windows365 registry key and the CloudManagedDesktopExtension service key must be
+    /// present — each alone has plausible look-alikes (W365-Boot physical clients carry
+    /// Windows365 policy state; the MCMD agent family served other managed-desktop
+    /// offerings). Mirrors the bootstrap script's field-verified <c>Test-IsCloudPc</c>.
+    /// </summary>
+    public sealed class CloudPcDetectorTests
+    {
+        private static Func<string, bool> Probe(params string[] existingKeys)
+        {
+            var set = new HashSet<string>(existingKeys, StringComparer.OrdinalIgnoreCase);
+            return path => set.Contains(path);
+        }
+
+        [Fact]
+        public void Both_markers_present_resolves_true()
+        {
+            Assert.True(CloudPcDetector.ResolveIsCloudPc(Probe(
+                CloudPcDetector.Windows365MarkerKey,
+                CloudPcDetector.CmdeServiceKey)));
+        }
+
+        [Fact]
+        public void Windows365_key_alone_resolves_false()
+        {
+            // W365-Boot physical client shape: policy state without the on-device MCMD agent.
+            Assert.False(CloudPcDetector.ResolveIsCloudPc(Probe(CloudPcDetector.Windows365MarkerKey)));
+        }
+
+        [Fact]
+        public void Cmde_service_alone_resolves_false()
+        {
+            // MCMD agent family also served other managed-desktop offerings.
+            Assert.False(CloudPcDetector.ResolveIsCloudPc(Probe(CloudPcDetector.CmdeServiceKey)));
+        }
+
+        [Fact]
+        public void No_markers_resolves_false()
+        {
+            Assert.False(CloudPcDetector.ResolveIsCloudPc(Probe()));
+        }
+
+        [Fact]
+        public void Null_probe_resolves_false()
+        {
+            Assert.False(CloudPcDetector.ResolveIsCloudPc(null));
+        }
+
+        [Fact]
+        public void Throwing_probe_degrades_to_false()
+        {
+            // SKIP-safe contract: a broken registry read must never classify, let alone throw.
+            Assert.False(CloudPcDetector.ResolveIsCloudPc(_ => throw new UnauthorizedAccessException("registry denied")));
+        }
+
+        [Fact]
+        public void DetectIsCloudPc_never_throws_on_build_host()
+        {
+            // Real-registry shell: exercises the exception-swallowing wrapper end to end.
+            // A build host is not a Cloud PC, but the contract under test is "no throw",
+            // not the detected value.
+            var ex = Record.Exception(() => CloudPcDetector.DetectIsCloudPc());
+            Assert.Null(ex);
+        }
+    }
+}

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Security/SessionRegistrationHelperTests.cs

@@ -137,6 +137,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Security
             Assert.Equal(Environment.MachineName, captured.DeviceName);
             Assert.False(string.IsNullOrEmpty(captured.EnrollmentType));
             Assert.True(captured.IsUserDriven);
+            // W365 marker rides the registration body. A build host is not a Cloud PC
+            // (marker-AND: Windows365 key + CloudManagedDesktopExtension service), so the
+            // detector's SKIP-safe default is what must land here.
+            Assert.False(captured.IsCloudPc);
         }
 
         [Fact]

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/SignalAdapters/ImeLogTrackerAdapterHistoricAppReplayTests.cs

@@ -83,13 +83,36 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.SignalAdapters
             using var adapter = new ImeLogTrackerAdapter(f.Tracker, f.Ingress, f.Clock);
             var app = new AppPackageState("app-do", 0);
 
-            f.Tracker.LastMatchedLogTimestamp = ClockNow.AddDays(-7);
-            adapter.TriggerDoTelemetryFromTest(app);
+            // Line-grounded path: the [DO TEL] line's own timestamp travels with the callback.
+            adapter.TriggerDoTelemetryFromTest(app, ClockNow.AddDays(-7));
             Assert.Empty(f.InfoEvents(SharedEventTypes.DoTelemetry));
 
-            f.Tracker.LastMatchedLogTimestamp = ClockNow.AddMinutes(-1);
-            adapter.TriggerDoTelemetryFromTest(app);
-            Assert.Single(f.InfoEvents(SharedEventTypes.DoTelemetry));
+            adapter.TriggerDoTelemetryFromTest(app, ClockNow.AddMinutes(-1));
+            var info = Assert.Single(f.InfoEvents(SharedEventTypes.DoTelemetry));
+            Assert.Equal(ClockNow.AddMinutes(-1), info.OccurredAtUtc);
+        }
+
+        [Fact]
+        public void Poll_driven_do_telemetry_stamps_clock_ignoring_unrelated_last_matched_line()
+        {
+            // Session df1fcf47: the DO collector observed the completion live, but the event
+            // inherited LastMatchedLogTimestamp from an unrelated, tz-skewed log line 8h in
+            // the past — which dragged Sessions.StartedAt back and inflated the duration.
+            // Poll-driven telemetry (null source timestamp) must stamp the clock, never the
+            // last matched line.
+            using var f = new ImeLogTrackerAdapterFixture(ClockNow);
+            using var adapter = new ImeLogTrackerAdapter(f.Tracker, f.Ingress, f.Clock);
+            var app = new AppPackageState("app-do-poll", 0);
+
+            f.Tracker.LastMatchedLogTimestamp = ClockNow.AddHours(-8);
+            adapter.TriggerDoTelemetryFromTest(app, sourceTimestampUtc: null);
+
+            var info = Assert.Single(f.InfoEvents(SharedEventTypes.DoTelemetry));
+            Assert.Equal(ClockNow, info.OccurredAtUtc);
+            Assert.Equal("true", info.Payload!["derivedTimestamp"]);
+            // Not a replay — live observation must never trip the replay suppression,
+            // even with a stale unrelated line on the tracker.
+            Assert.Empty(f.InfoEvents(SharedEventTypes.HistoricImeReplayDetected));
         }
 
         [Fact]

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/SignalAdapters/ImeLogTrackerAdapterTests.cs

@@ -647,13 +647,13 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.SignalAdapters
             int priorDoCalls = 0;
             int priorScriptCalls = 0;
             f.Tracker.OnImeAgentVersion = _ => priorVersionCalls++;
-            f.Tracker.OnDoTelemetryReceived = _ => priorDoCalls++;
+            f.Tracker.OnDoTelemetryReceived = (_, _) => priorDoCalls++;
             f.Tracker.OnScriptCompleted = _ => priorScriptCalls++;
 
             using var adapter = new ImeLogTrackerAdapter(f.Tracker, f.Ingress, f.Clock);
 
             f.Tracker.OnImeAgentVersion("1.0.0.0");
-            f.Tracker.OnDoTelemetryReceived(new AppPackageState("app-1", 0));
+            f.Tracker.OnDoTelemetryReceived(new AppPackageState("app-1", 0), null);
             f.Tracker.OnScriptCompleted(new ScriptExecutionState { PolicyId = "p", ScriptType = "platform" });
 
             Assert.Equal(1, priorVersionCalls);
@@ -667,7 +667,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.SignalAdapters
         {
             using var f = new ImeLogTrackerAdapterFixture();
             Action<string> priorVersion = _ => { };
-            Action<AppPackageState> priorDo = _ => { };
+            Action<AppPackageState, DateTime?> priorDo = (_, _) => { };
             Action<ScriptExecutionState> priorScript = _ => { };
             f.Tracker.OnImeAgentVersion = priorVersion;
             f.Tracker.OnDoTelemetryReceived = priorDo;

src/Agent/AutopilotMonitor.Agent.V2.Core.Tests/Telemetry/Events/EventTimelineEmitterTests.cs

@@ -153,6 +153,58 @@ namespace AutopilotMonitor.Agent.V2.Core.Tests.Telemetry.Events
             Assert.Equal("Device Setup", (string?)parsed["PhaseName"]);
         }
 
+        [Fact]
+        public void Emit_publishes_eventType_and_parsed_phase_to_TimelineEventStream()
+        {
+            // Post-reduce observer surface: gather-rule phase/event triggers subscribe here so
+            // they fire in step with what the timeline shows (session 32312a32 regression).
+            using var r = new Rig();
+            var stream = new AutopilotMonitor.Agent.V2.Core.Orchestration.TimelineEventStream();
+            var published = new List<(string EventType, EnrollmentPhase Phase)>();
+            stream.EventEmitted += (eventType, phase) => published.Add((eventType, phase));
+            var sut = new EventTimelineEmitter(r.Inner, stream);
+
+            sut.Emit(
+                new Dictionary<string, string>
+                {
+                    ["eventType"] = "phase_transition",
+                    ["phase"] = "FinalizingSetup",
+                },
+                State(),
+                At);
+            sut.Emit(
+                new Dictionary<string, string> { ["eventType"] = "enrollment_complete" },
+                State(),
+                At);
+
+            Assert.Equal(2, published.Count);
+            Assert.Equal(("phase_transition", EnrollmentPhase.FinalizingSetup), published[0]);
+            Assert.Equal(("enrollment_complete", EnrollmentPhase.Unknown), published[1]);
+            // Publish happens AFTER the transport enqueue — wire ordering is authoritative.
+            Assert.Equal(2, r.Transport.EnqueueCount);
+        }
+
+        [Fact]
+        public void TimelineEventStream_subscriber_exception_does_not_break_the_emit_path()
+        {
+            using var r = new Rig();
+            var stream = new AutopilotMonitor.Agent.V2.Core.Orchestration.TimelineEventStream();
+            var secondSubscriberCalls = 0;
+            stream.EventEmitted += (_, _) => throw new InvalidOperationException("subscriber bug");
+            stream.EventEmitted += (_, _) => secondSubscriberCalls++;
+            var sut = new EventTimelineEmitter(r.Inner, stream);
+
+            sut.Emit(
+                new Dictionary<string, string> { ["eventType"] = "enrollment_complete" },
+                State(),
+                At);
+
+            // Emit neither threw (would surface as an EffectRunner retry = duplicated event)
+            // nor skipped the remaining subscribers.
+            Assert.Equal(1, r.Transport.EnqueueCount);
+            Assert.Equal(1, secondSubscriberCalls);
+        }
+
         [Fact]
         public void Phase_parameter_with_invalid_value_falls_back_to_Unknown()
         {

src/Agent/AutopilotMonitor.Agent.V2.Core/Configuration/AgentConfiguration.cs

@@ -109,6 +109,14 @@ namespace AutopilotMonitor.Agent.V2.Core.Configuration
         /// </summary>
         public bool EnableTimezoneAutoSet { get; set; } = false;
 
+        /// <summary>
+        /// Continue-Anyway observation mode (operator-set tenant opt-in, delivered via
+        /// remote config): stamped into the esp_config_detected decision-signal payload so
+        /// the DecisionEngine defangs a Device-phase ESP terminal failure into a bounded
+        /// 60-min observation instead of failing immediately. Default: false.
+        /// </summary>
+        public bool EnableEspContinueAnywayObservation { get; set; } = false;
+
         /// <summary>
         /// Optional custom path to IME logs directory for testing.
         /// If set, overrides the default %ProgramData%\Microsoft\IntuneManagementExtension\Logs path.
@@ -272,9 +280,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Configuration
         /// CloudDomainJoin keys and re-probes on every change until either resolution
         /// or this timeout. 0 = no wait, fast-fail on miss (legacy behaviour).
         /// <para>
-        /// Set via the install-time CLI flag <c>--tenant-id-wait &lt;sec&gt;</c>, persisted
-        /// to <c>bootstrap-config.json</c>. The PS1 bootstrap script owns the production
-        /// default; the agent itself never assumes one.
+        /// Set via the CLI flag <c>--tenant-id-wait &lt;sec&gt;</c> or a persisted
+        /// <c>bootstrap-config.json</c> value; when neither supplies a value the agent
+        /// applies its own default of 600 s in BuildAgentConfiguration. The 0 default
+        /// here is only the POCO baseline, not the effective runtime default.
         /// </para>
         /// </summary>
         public int TenantIdWaitSeconds { get; set; } = 0;

src/Agent/AutopilotMonitor.Agent.V2.Core/Configuration/BootstrapConfigFile.cs

@@ -16,8 +16,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Configuration
         /// <summary>
         /// TenantId-wait timeout in seconds, persisted from the <c>--tenant-id-wait</c>
         /// install-time arg. Read by AgentBootstrap when the registry probe finds no
-        /// TenantId on first try. 0 / missing = no wait, legacy fast-fail.
+        /// TenantId on first try. 0 = explicit opt-out (legacy fast-fail).
+        /// Null / missing (files written before this property existed) = not configured —
+        /// the agent-side default (600 s) applies. Nullable so a legacy file without the
+        /// property cannot masquerade as an explicit 0 and silently disable the wait.
         /// </summary>
-        public int TenantIdWaitSeconds { get; set; }
+        public int? TenantIdWaitSeconds { get; set; }
     }
 }

src/Agent/AutopilotMonitor.Agent.V2.Core/Configuration/RemoteConfigMerger.cs

@@ -103,6 +103,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Configuration
 
             agentConfig.SendTraceEvents = remoteConfig.SendTraceEvents;
 
+            // ---------------- Continue-Anyway observation — remote wins (operator-set tenant
+            //                  opt-in; false must clear a stale cached true).
+            agentConfig.EnableEspContinueAnywayObservation = remoteConfig.EnableEspContinueAnywayObservation;
+
             // ---------------- UnrestrictedMode audit — track old/new for the caller so the
             //                  agent_unrestricted_mode_changed event can fire AFTER the
             //                  orchestrator emitter is alive (V1 parity with

src/Agent/AutopilotMonitor.Agent.V2.Core/Configuration/RemoteConfigService.cs

@@ -328,6 +328,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Configuration
                 EnableGeoLocation = true,
                 EnableImeMatchLog = false,
                 EnableGatherRuleDebugLog = false,
+                EnableEspContinueAnywayObservation = false,
                 Collectors = CollectorConfiguration.CreateDefault(),
                 GatherRules = new System.Collections.Generic.List<GatherRule>(),
                 ImeLogPatterns = new System.Collections.Generic.List<ImeLogPattern>()

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime/ImeLogTracker.Handlers.cs

@@ -112,7 +112,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime
                     $"size={fileSize}, peers={bytesFromPeers} ({peerCachingPct}%), " +
                     $"http={bytesFromHttp}, cache={bytesFromCacheServer}, mode={downloadMode}, duration={downloadDuration}");
 
-                OnDoTelemetryReceived?.Invoke(pkg);
+                OnDoTelemetryReceived?.Invoke(pkg, LastMatchedLogTimestamp);
                 _stateDirty = true;
             }
             catch (Exception ex)

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime/ImeLogTracker.LogProcessing.cs

@@ -7,6 +7,7 @@ using System.Text.RegularExpressions;
 using System.Threading;
 using System.Threading.Tasks;
 using AutopilotMonitor.Agent.V2.Core.Logging;
+using AutopilotMonitor.Shared.Logging;
 using AutopilotMonitor.Shared.Models;
 
 namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/Ime/ImeLogTracker.cs

@@ -194,7 +194,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime
         public Action OnAllAppsCompleted { get; set; }
         public Action OnUserSessionCompleted { get; set; }
         public Action<string> OnImeSessionChange { get; set; }
-        public Action<AppPackageState> OnDoTelemetryReceived { get; set; }
+        // Second arg: the [DO TEL] source log line's timestamp when the DO data came from a
+        // log line, null when the DO collector observed the completion live via polling. The
+        // consumer must stamp poll-driven telemetry with the clock — inheriting an unrelated
+        // line's LastMatchedLogTimestamp put a tz-skewed time on the event (session df1fcf47).
+        public Action<AppPackageState, DateTime?> OnDoTelemetryReceived { get; set; }
         public Action<ScriptExecutionState> OnScriptCompleted { get; set; }
 
         /// <summary>

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Enrollment/SystemSignals/StallProbeCollector.cs

@@ -10,6 +10,7 @@ using AutopilotMonitor.Agent.V2.Core.Logging;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
 using AutopilotMonitor.Agent.V2.Core.Orchestration;
 using AutopilotMonitor.Shared;
+using AutopilotMonitor.Shared.Logging;
 using AutopilotMonitor.Shared.Models;
 using Microsoft.Win32;
 

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/DeviceInfo/DeviceInfoCollector.NetworkAndSecurity.cs

@@ -1021,6 +1021,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
                     .ToString(System.Globalization.CultureInfo.InvariantCulture);
             if (snapshot.AllowContinueAnyway.HasValue)
                 payload[SignalPayloadKeys.EspAllowContinueAnyway] = snapshot.AllowContinueAnyway.Value ? "true" : "false";
+            // Tenant opt-in (remote config, not a registry fact) — only stamped when
+            // enabled; absent = default hard-fail semantics in the engine.
+            if (_espContinueAnywayObservationEnabled?.Invoke() == true)
+                payload[SignalPayloadKeys.EspContinueAnywayObservationEnabled] = "true";
 
             var derivationInputs = new Dictionary<string, string>(payload, StringComparer.Ordinal)
             {

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/DeviceInfo/DeviceInfoCollector.cs

@@ -35,6 +35,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
         private readonly IClock _clock;
         private readonly Persistence.StartupEventGate _startupGate;
 
+        // Live accessor for AgentConfiguration.EnableEspContinueAnywayObservation — read at
+        // esp_config_detected stamping time so a late remote-config merge takes effect on
+        // the phase-triggered re-emissions. Null (tests / legacy callers) means disabled.
+        private readonly Func<bool> _espContinueAnywayObservationEnabled;
+
         private const string RegKeyWindowsCurrentVersion = @"HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Windows NT\CurrentVersion";
 
         // Restart dedup (StartupEventGate) — exemptions. boot_time is genuinely new per boot
@@ -65,7 +70,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
             AgentLogger logger,
             ISignalIngressSink signalIngress = null,
             IClock clock = null,
-            Persistence.StartupEventGate startupGate = null)
+            Persistence.StartupEventGate startupGate = null,
+            Func<bool> espContinueAnywayObservationEnabled = null)
         {
             _sessionId = sessionId ?? throw new ArgumentNullException(nameof(sessionId));
             _tenantId  = tenantId  ?? throw new ArgumentNullException(nameof(tenantId));
@@ -74,6 +80,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.DeviceInfo
             _signalIngress = signalIngress;
             _clock = clock;
             _startupGate = startupGate;
+            _espContinueAnywayObservationEnabled = espContinueAnywayObservationEnabled;
         }
 
         /// <summary>

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Telemetry/Gather/Collectors/LogParserCollector.cs

@@ -10,6 +10,7 @@ using AutopilotMonitor.Agent.V2.Core.Monitoring.Runtime;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.SystemSignals;
+using AutopilotMonitor.Shared.Logging;
 
 namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Telemetry.Gather.Collectors
 {

src/Agent/AutopilotMonitor.Agent.V2.Core/Monitoring/Transport/DistressReporter.cs

@@ -56,6 +56,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Transport
         private DateTime? _lastReportTime;
         private int _reportCount;
 
+        // Local W365 marker verdict, captured once at construction (same UNVERIFIED contract
+        // as the hardware fields). Optional ctor arg so test fakes stay source-compatible.
+        private readonly bool _isCloudPc;
+
         public DistressReporter(
             string baseUrl,
             string tenantId,
@@ -64,7 +68,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Transport
             string serialNumber,
             string agentVersion,
             AgentLogger logger,
-            X509Certificate2 clientCertificate = null)
+            X509Certificate2 clientCertificate = null,
+            bool isCloudPc = false)
         {
             _tenantId = tenantId;
             _manufacturer = manufacturer;
@@ -72,6 +77,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Transport
             _serialNumber = serialNumber;
             _agentVersion = agentVersion;
             _logger = logger;
+            _isCloudPc = isCloudPc;
 
             // Capture cert context. Each field is independently nullable so the backend can tell
             // "agent had no cert at all" (NoCertInStore + all-null fields) from "agent had a cert
@@ -169,6 +175,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Monitoring.Transport
                 HttpStatusCode = httpStatusCode,
                 Message = Truncate(message, 256),
                 Timestamp = DateTime.UtcNow,
+                IsCloudPc = _isCloudPc,
                 CertSourceState = _capturedCertState,
                 CertThumbprint = _capturedCertThumbprint,
                 CertSubject = Truncate(_capturedCertSubject, 96),

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/DefaultComponentFactory.cs

@@ -97,7 +97,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             IReadOnlyCollection<string> whiteGloveSealingPatternIds,
             ISignalIngressSink ingress,
             IClock clock,
-            Transport.Telemetry.ITelemetrySpool? telemetrySpool)
+            Transport.Telemetry.ITelemetrySpool? telemetrySpool,
+            TimelineEventStream? timelineEvents = null)
         {
             if (string.IsNullOrEmpty(sessionId)) throw new ArgumentException("SessionId required.", nameof(sessionId));
             if (string.IsNullOrEmpty(tenantId)) throw new ArgumentException("TenantId required.", nameof(tenantId));
@@ -126,7 +127,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
                 ingress: ingress,
                 clock: clock,
                 logger: logger,
-                startupGate: _startupEventGate));
+                startupGate: _startupEventGate,
+                // Live accessor (not the current value): a remote-config merge landing after
+                // factory construction must still reach the phase-triggered re-emissions.
+                espContinueAnywayObservationEnabled: () => _agentConfig.EnableEspContinueAnywayObservation));
 
             // Session caa6cf50 gate-starvation fix: the EspAndHelloTracker's user-ESP-apps-settled
             // probe reads the IME log host, which is constructed further down. Same closure-over-
@@ -471,8 +475,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             if (officeHost != null) hosts.Add(officeHost);
 
             // M4.6.δ — Gather-rules runtime executor. Runs "startup" rules once the agent is up
-            // and "interval" rules on their timers; "phase_change" / "on_event" rules are driven
-            // by the host's SignalIngress.SignalPosted subscription (MON-A1).
+            // and "interval" rules on their timers; "phase_change" / "phase_exit" / "on_event"
+            // rules are driven by the post-reduce TimelineEventStream (emitted timeline events),
+            // NOT the raw SignalPosted stream — the raw phase can run minutes ahead of the
+            // engine-declared one (RealmJoin gate, session 32312a32). See TimelineEventStream doc.
             if (_remoteConfig.GatherRules != null && _remoteConfig.GatherRules.Count > 0)
             {
                 hosts.Add(new GatherRuleExecutorHost(
@@ -484,7 +490,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
                     rules: _remoteConfig.GatherRules,
                     imeLogPathOverride: _agentConfig.ImeLogPathOverride,
                     unrestrictedMode: _agentConfig.UnrestrictedMode,
-                    gatherDebugLogPath: _agentConfig.GatherRuleDebugLogPath));
+                    gatherDebugLogPath: _agentConfig.GatherRuleDebugLogPath,
+                    timelineEvents: timelineEvents));
             }
             else if (!string.IsNullOrEmpty(_agentConfig.GatherRuleDebugLogPath))
             {

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/EnrollmentOrchestrator.cs

@@ -91,6 +91,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
         // (tests / legacy callers) means trace events always flow.
         private readonly Func<bool>? _traceEventsEnabled;
 
+        // Live accessor for AgentConfiguration.EnableEspContinueAnywayObservation — read at
+        // esp_config_detected stamping time so a remote-config merge that lands after
+        // construction still takes effect. Null (tests / legacy callers) means disabled.
+        private readonly Func<bool>? _espContinueAnywayObservationEnabled;
+
         // Max-lifetime watchdog (M4.6.α). Timer is armed in Start() when _agentMaxLifetime != null.
         private System.Threading.Timer? _maxLifetimeTimer;
         private int _terminatedFired;
@@ -107,6 +112,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
         private TelemetrySignalEmitter? _signalEmitter;
         private TelemetryTransitionEmitter? _transitionEmitter;
         private EventTimelineEmitter? _timelineEmitter;
+        private TimelineEventStream? _timelineEvents;
         private BackPressureEventObserver? _backPressureObserver;
         private IDeadlineScheduler? _scheduler;
         private ClassifierRegistry? _classifierRegistry;
@@ -172,7 +178,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             TimeSpan? agentMaxLifetime = null,
             int uploadBatchSize = 100,
             IDeadlineScheduler? schedulerOverride = null,
-            Func<bool>? traceEventsEnabled = null)
+            Func<bool>? traceEventsEnabled = null,
+            Func<bool>? espContinueAnywayObservationEnabled = null)
         {
             if (string.IsNullOrEmpty(sessionId)) throw new ArgumentException("SessionId is mandatory.", nameof(sessionId));
             if (string.IsNullOrEmpty(tenantId)) throw new ArgumentException("TenantId is mandatory.", nameof(tenantId));
@@ -213,6 +220,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
 
             _schedulerOverride = schedulerOverride;
             _traceEventsEnabled = traceEventsEnabled;
+            _espContinueAnywayObservationEnabled = espContinueAnywayObservationEnabled;
         }
 
         /// <summary>
@@ -413,7 +421,12 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
                 _transport, _eventSequenceCounter, _sessionId, _tenantId, _traceEventsEnabled);
             _signalEmitter = new TelemetrySignalEmitter(_transport, _sessionId, _tenantId);
             _transitionEmitter = new TelemetryTransitionEmitter(_transport, _sessionId, _tenantId);
-            _timelineEmitter = new EventTimelineEmitter(eventEmitter);
+            // Post-reduce timeline observer: EventTimelineEmitter publishes every emitted event's
+            // (eventType, phase) here. Fed to the collector-host factory at step 14 so gather-rule
+            // phase_change/on_event triggers key off the ENGINE-REDUCED timeline (RealmJoin gate
+            // et al. respected) instead of raw pre-reduce signals — see TimelineEventStream doc.
+            _timelineEvents = new TimelineEventStream();
+            _timelineEmitter = new EventTimelineEmitter(eventEmitter, _timelineEvents);
             _backPressureObserver = new BackPressureEventObserver(eventEmitter, _clock);
 
             // 5) Deadlines + Classifiers.
@@ -653,7 +666,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             {
                 var surfaces = _componentFactory.CreateCollectorHosts(
                     _sessionId, _tenantId, _logger, _whiteGloveSealingPatternIds,
-                    ingress: _ingress, clock: _clock, telemetrySpool: _spool);
+                    ingress: _ingress, clock: _clock, telemetrySpool: _spool,
+                    timelineEvents: _timelineEvents);
                 CollectorSurfaces = surfaces;
                 _collectorHosts = surfaces.Hosts;
                 foreach (var host in _collectorHosts)
@@ -766,6 +780,10 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
                         .ToString(System.Globalization.CultureInfo.InvariantCulture);
                 if (snapshot.AllowContinueAnyway.HasValue)
                     payload[SignalPayloadKeys.EspAllowContinueAnyway] = snapshot.AllowContinueAnyway.Value ? "true" : "false";
+                // Tenant opt-in (remote config, not a registry fact) — only stamped when
+                // enabled; absent = default hard-fail semantics in the engine.
+                if (_espContinueAnywayObservationEnabled?.Invoke() == true)
+                    payload[SignalPayloadKeys.EspContinueAnywayObservationEnabled] = "true";
 
                 _ingress!.Post(
                     kind: DecisionSignalKind.EspConfigDetected,

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/DeliveryOptimizationHost.cs

@@ -51,7 +51,9 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
                 getPackageStates: () => imeHost.PackageStates,
                 onDoTelemetryReceived: pkg =>
                 {
-                    try { imeHost.Tracker.OnDoTelemetryReceived?.Invoke(pkg); }
+                    // null source timestamp: poll-driven completion, no log line backs it —
+                    // the adapter stamps the clock instead of LastMatchedLogTimestamp.
+                    try { imeHost.Tracker.OnDoTelemetryReceived?.Invoke(pkg, null); }
                     catch (Exception ex) { logger.Warning($"DeliveryOptimizationHost: OnDoTelemetryReceived invocation threw: {ex.Message}"); }
                 },
                 logDirectory: Environment.ExpandEnvironmentVariables(Constants.LogDirectory),

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/DeviceInfoHost.cs

@@ -82,7 +82,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             ISignalIngressSink ingress,
             IClock clock,
             AgentLogger logger,
-            Persistence.StartupEventGate? startupGate = null)
+            Persistence.StartupEventGate? startupGate = null,
+            Func<bool>? espContinueAnywayObservationEnabled = null)
         {
             if (ingress == null) throw new ArgumentNullException(nameof(ingress));
             if (clock == null) throw new ArgumentNullException(nameof(clock));
@@ -92,7 +93,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             // when it reads the FirstSync SkipUser/SkipDevice registry values, so that Fix 8's
             // reducer guards have the SkipUserEsp/SkipDeviceEsp state facts to read.
             _collector = new Monitoring.Telemetry.DeviceInfo.DeviceInfoCollector(
-                sessionId, tenantId, post, logger, ingress, clock, startupGate);
+                sessionId, tenantId, post, logger, ingress, clock, startupGate,
+                espContinueAnywayObservationEnabled);
             _observableIngress = ingress as SignalIngress;
         }
 

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/Hosts/GatherRuleExecutorHost.cs

@@ -4,7 +4,6 @@ using System.Collections.Generic;
 using System.Threading;
 using AutopilotMonitor.Agent.V2.Core.Logging;
 using AutopilotMonitor.DecisionCore.Engine;
-using AutopilotMonitor.DecisionCore.Signals;
 using AutopilotMonitor.Shared.Models;
 
 namespace AutopilotMonitor.Agent.V2.Core.Orchestration
@@ -19,17 +18,24 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
         private readonly bool _unrestrictedMode;
         private int _disposed;
 
-        // MON-A1: drive phase_change / on_event gather triggers from the central signal stream.
-        // V1 fired these from MonitoringService on every EnrollmentEvent (OnPhaseChanged(evt.Phase)
-        // on phase change + OnEvent(evt.EventType) per event); the V2 host previously only called
-        // UpdateRules, so 5 of 10 shipped rules (incl. the only enabled one, dsregcmd at
-        // FinalizingSetup) silently never fired. In V2 every event is an InformationalEvent signal
-        // carrying eventType + (optional) phase in its payload. Null on test fakes / non-SignalIngress
-        // sinks — then signal-triggers degrade off (startup + interval rules still run).
-        private readonly SignalIngress? _observableIngress;
-        private Action<DecisionSignalKind, IReadOnlyDictionary<string, string>?>? _signalPostedHandler;
+        // MON-A1 (revised): drive phase_change / phase_exit / on_event gather triggers from the
+        // POST-REDUCE emitted timeline (TimelineEventStream), not from the raw signal stream.
+        // V1 fired these from MonitoringService on every emitted EnrollmentEvent; the first V2
+        // wiring subscribed to SignalIngress.SignalPosted instead, which fires at enqueue time
+        // with the RAW collector payload — before the reducer has applied gates like the
+        // RealmJoin completion gate. Consequence (session 32312a32, rsneuffen.de): a phase_change
+        // rule on FinalizingSetup fired at the raw EspPhaseChanged(FinalizingSetup) signal (ESP
+        // exit / Hello wizard), 7 minutes before the engine declared phase_transition(FinalizingSetup)
+        // on the timeline — and before the RealmJoin package wrote the registry key the rule was
+        // built to read. The raw feed also never carried engine-emitted event types at all, so
+        // on_event rules on enrollment_complete (documented) could never fire. The emitted-event
+        // feed restores V1 semantics and matches what the UI timeline shows ("collect once when
+        // the enrollment reaches this phase"). Null on test fakes / standalone configurations —
+        // then phase/event triggers degrade off (startup + interval rules still run).
+        private readonly TimelineEventStream? _timelineEvents;
+        private Action<string, EnrollmentPhase>? _timelineHandler;
         private readonly object _sync = new object();
-        private string? _lastPhaseName;
+        private EnrollmentPhase _lastPhase = EnrollmentPhase.Unknown;
 
         public GatherRuleExecutorHost(
             string sessionId,
@@ -40,7 +46,8 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             List<GatherRule> rules,
             string? imeLogPathOverride,
             bool unrestrictedMode = false,
-            string? gatherDebugLogPath = null)
+            string? gatherDebugLogPath = null,
+            TimelineEventStream? timelineEvents = null)
         {
             if (ingress == null) throw new ArgumentNullException(nameof(ingress));
             if (clock == null) throw new ArgumentNullException(nameof(clock));
@@ -60,7 +67,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             _executor = new Monitoring.Telemetry.Gather.GatherRuleExecutor(
                 sessionId, tenantId, evt => post.Emit(evt), logger, imeLogPathOverride,
                 debugLogPath: gatherDebugLogPath);
-            _observableIngress = ingress as SignalIngress;
+            _timelineEvents = timelineEvents;
         }
 
         public void Start()
@@ -71,46 +78,43 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             _executor.UnrestrictedMode = _unrestrictedMode;
             _executor.UpdateRules(_rules);
 
-            // MON-A1: observe the central signal stream so phase_change / on_event rules fire.
-            if (_observableIngress != null && _signalPostedHandler == null)
+            // MON-A1 (revised): observe the emitted timeline so phase/event triggers fire in
+            // step with what the timeline actually shows.
+            if (_timelineEvents != null && _timelineHandler == null)
             {
-                _signalPostedHandler = OnSignalPosted;
-                _observableIngress.SignalPosted += _signalPostedHandler;
+                _timelineHandler = OnTimelineEventEmitted;
+                _timelineEvents.EventEmitted += _timelineHandler;
             }
 
             _logger.Info(
-                $"GatherRuleExecutorHost: started with {_rules.Count} rule(s), unrestrictedMode={_unrestrictedMode}, signalTriggers={(_observableIngress != null)}.");
+                $"GatherRuleExecutorHost: started with {_rules.Count} rule(s), unrestrictedMode={_unrestrictedMode}, timelineTriggers={(_timelineEvents != null)}.");
         }
 
         /// <summary>
-        /// Translates posted signals into the executor's phase_change / on_event triggers (MON-A1).
-        /// Phase: fire <see cref="Monitoring.Telemetry.Gather.GatherRuleExecutor.OnPhaseChanged"/> when
-        /// the observed phase changes and parses to an <see cref="EnrollmentPhase"/> (raw collector
-        /// phase strings that aren't enum names are ignored — they carry no gather-rule meaning).
-        /// Event: fire <see cref="Monitoring.Telemetry.Gather.GatherRuleExecutor.OnEvent"/> for every
-        /// InformationalEvent's eventType. The executor dispatches rule execution on the ThreadPool,
-        /// so this stays off the signal-posting hot path; it also dedups phase rules per (rule, phase).
+        /// Translates emitted timeline events into the executor's triggers. Phase: fire
+        /// <see cref="Monitoring.Telemetry.Gather.GatherRuleExecutor.OnPhaseChanged"/> when a
+        /// phase-declaration event (Phase != Unknown) moves the timeline to a new phase — this
+        /// is by construction the engine-reduced phase, so deferred transitions (RealmJoin gate)
+        /// fire the rules exactly when the timeline shows them. Event: fire
+        /// <see cref="Monitoring.Telemetry.Gather.GatherRuleExecutor.OnEvent"/> for every emitted
+        /// event's type — including engine-emitted types (enrollment_complete, phase_transition,
+        /// realmjoin_resolved, …) that never existed on the raw signal stream. The executor
+        /// dispatches rule execution on the ThreadPool, so this stays off the ingress worker's
+        /// effect path; it also dedups phase rules per (rule, phase).
         /// </summary>
-        private void OnSignalPosted(DecisionSignalKind kind, IReadOnlyDictionary<string, string>? payload)
+        private void OnTimelineEventEmitted(string eventType, EnrollmentPhase phase)
         {
-            if (payload == null) return;
-
             try
             {
                 lock (_sync)
                 {
-                    if (payload.TryGetValue(SignalPayloadKeys.EspPhase, out var phaseName)
-                        && !string.IsNullOrEmpty(phaseName)
-                        && !string.Equals(phaseName, _lastPhaseName, StringComparison.OrdinalIgnoreCase)
-                        && Enum.TryParse<EnrollmentPhase>(phaseName, ignoreCase: true, out var phase))
+                    if (phase != EnrollmentPhase.Unknown && phase != _lastPhase)
                     {
-                        _lastPhaseName = phaseName;
+                        _lastPhase = phase;
                         _executor.OnPhaseChanged(phase);
                     }
 
-                    if (kind == DecisionSignalKind.InformationalEvent
-                        && payload.TryGetValue(SignalPayloadKeys.EventType, out var eventType)
-                        && !string.IsNullOrEmpty(eventType))
+                    if (!string.IsNullOrEmpty(eventType))
                     {
                         _executor.OnEvent(eventType);
                     }
@@ -118,17 +122,17 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             }
             catch (Exception ex)
             {
-                _logger.Verbose($"GatherRuleExecutorHost: signal-trigger dispatch failed: {ex.Message}");
+                _logger.Verbose($"GatherRuleExecutorHost: timeline-trigger dispatch failed: {ex.Message}");
             }
         }
 
         public void Stop()
         {
-            if (_observableIngress != null && _signalPostedHandler != null)
+            if (_timelineEvents != null && _timelineHandler != null)
             {
-                try { _observableIngress.SignalPosted -= _signalPostedHandler; }
+                try { _timelineEvents.EventEmitted -= _timelineHandler; }
                 catch { /* best-effort unsubscribe during shutdown */ }
-                _signalPostedHandler = null;
+                _timelineHandler = null;
             }
             // GatherRuleExecutor is IDisposable; no explicit Stop beyond unsubscribe. Rely on Dispose.
         }

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/IComponentFactory.cs

@@ -39,6 +39,13 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
         /// <c>spool.pendingItemCount</c> / <c>spool.fileSizeBytes</c>. Nullable — fakes and
         /// spool-less configurations pass null and the metrics fields are simply absent.
         /// </para>
+        /// <para>
+        /// <paramref name="timelineEvents"/> flows into the <c>GatherRuleExecutorHost</c> so
+        /// <c>phase_change</c> / <c>phase_exit</c> / <c>on_event</c> gather triggers key off the
+        /// ENGINE-REDUCED emitted timeline (post-reduce, RealmJoin gate respected) instead of raw
+        /// pre-reduce signals — see <see cref="TimelineEventStream"/>. Nullable — fakes pass null
+        /// and the host's phase/event triggers degrade off (startup + interval rules still run).
+        /// </para>
         /// </summary>
         CollectorSurfaces CreateCollectorHosts(
             string sessionId,
@@ -47,6 +54,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Orchestration
             IReadOnlyCollection<string> whiteGloveSealingPatternIds,
             ISignalIngressSink ingress,
             IClock clock,
-            Transport.Telemetry.ITelemetrySpool? telemetrySpool);
+            Transport.Telemetry.ITelemetrySpool? telemetrySpool,
+            TimelineEventStream? timelineEvents = null);
     }
 }

src/Agent/AutopilotMonitor.Agent.V2.Core/Orchestration/TimelineEventStream.cs

@@ -0,0 +1,55 @@
+#nullable enable
+using System;
+using AutopilotMonitor.Shared.Models;
+
+namespace AutopilotMonitor.Agent.V2.Core.Orchestration
+{
+    /// <summary>
+    /// Post-reduce observer surface for emitted timeline events: <see cref="Telemetry.Events.EventTimelineEmitter"/>
+    /// publishes every <see cref="EnrollmentEvent"/> it emits as an <c>(eventType, phase)</c> pair,
+    /// AFTER the decision engine has reduced the originating signal and its effects have been
+    /// executed.
+    /// <para>
+    /// This is deliberately different from <see cref="SignalIngress.SignalPosted"/>, which fires
+    /// at enqueue time on the producer thread and therefore only ever carries the RAW collector
+    /// payload — before the reducer has applied gates like the RealmJoin completion gate that can
+    /// defer or suppress a phase transition. Consumers that must agree with what the timeline
+    /// actually shows (the gather-rule phase/event triggers) subscribe here, not to the raw
+    /// signal stream. See session 32312a32: a <c>phase_change</c> gather rule on FinalizingSetup
+    /// fired at the raw <c>EspPhaseChanged(FinalizingSetup)</c> signal (ESP exit), 7 minutes
+    /// before the engine — deferred behind the RealmJoin gate — actually declared
+    /// <c>phase_transition(FinalizingSetup)</c> on the timeline.
+    /// </para>
+    /// <para>
+    /// <b>Threading</b>: <see cref="Publish"/> runs on the ingress worker thread (the effect
+    /// execution path). Subscribers must stay fast and must not block; subscriber exceptions are
+    /// swallowed per handler so the emit path can never throw (an exception here would surface
+    /// as an EffectRunner transient retry and duplicate the emitted event).
+    /// </para>
+    /// </summary>
+    public sealed class TimelineEventStream
+    {
+        /// <summary>
+        /// Raised once per emitted timeline event with its <see cref="EnrollmentEvent.EventType"/>
+        /// and parsed <see cref="EnrollmentEvent.Phase"/> (<see cref="EnrollmentPhase.Unknown"/>
+        /// for the vast majority of events — only phase-declaration events carry a real phase,
+        /// which is exactly the set the UI timeline groups on).
+        /// </summary>
+        public event Action<string, EnrollmentPhase>? EventEmitted;
+
+        internal void Publish(string eventType, EnrollmentPhase phase)
+        {
+            var handler = EventEmitted;
+            if (handler == null) return;
+
+            foreach (Action<string, EnrollmentPhase> subscriber in handler.GetInvocationList())
+            {
+                try { subscriber(eventType, phase); }
+                catch
+                {
+                    // Subscriber isolation — see class doc: the emit path must never throw.
+                }
+            }
+        }
+    }
+}

src/Agent/AutopilotMonitor.Agent.V2.Core/Security/CloudPcDetector.cs

@@ -0,0 +1,77 @@
+using System;
+using Microsoft.Win32;
+
+namespace AutopilotMonitor.Agent.V2.Core.Security
+{
+    /// <summary>
+    /// Detects whether the agent runs on a Windows 365 Cloud PC, using the same marker
+    /// evidence the bootstrap script's <c>Test-IsCloudPc</c> settled on after the first
+    /// W365 field test (2026-08-06) disproved WMI-model matching (a Cloud PC reports only
+    /// Manufacturer='Microsoft Corporation' + Model='Virtual Machine' locally — identical
+    /// to any Hyper-V VM):
+    /// <list type="bullet">
+    ///   <item><c>HKLM\SOFTWARE\Microsoft\Windows365</c> exists, AND</item>
+    ///   <item>the <c>CloudManagedDesktopExtension</c> service (Microsoft Cloud Managed
+    ///         Desktop Extension, the W365 management agent that runs ON Cloud PCs) is
+    ///         installed — probed via its <c>HKLM\SYSTEM\CurrentControlSet\Services</c> key,
+    ///         so the agent needs no System.ServiceProcess dependency.</item>
+    /// </list>
+    /// 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).
+    /// <para>
+    /// Display/context metadata only — the flag rides on <c>SessionRegistration</c> and the
+    /// <c>EnrollmentFactsObserved</c> signal. It is NEVER an auth input: backend device
+    /// validation trusts exclusively the cert-CN-bound Graph lookup
+    /// (<c>CloudPcDeviceValidator</c>), not this locally-derived value.
+    /// Exception-swallowing, false on any error — mirrors the SKIP-safe bootstrap contract
+    /// and the <see cref="EnrollmentRegistryDetector"/> degradation rules.
+    /// </para>
+    /// </summary>
+    public static class CloudPcDetector
+    {
+        internal const string Windows365MarkerKey = @"SOFTWARE\Microsoft\Windows365";
+        internal const string CmdeServiceKey = @"SYSTEM\CurrentControlSet\Services\CloudManagedDesktopExtension";
+
+        public static bool DetectIsCloudPc()
+        {
+            try
+            {
+                return ResolveIsCloudPc(SubKeyExists);
+            }
+            catch
+            {
+                return false;
+            }
+        }
+
+        /// <summary>
+        /// Pure decision logic for <see cref="DetectIsCloudPc"/>. Exposed internally so the
+        /// marker-AND semantics can be exercised without a real registry (same seam contract
+        /// as <see cref="EnrollmentRegistryDetector.ResolveHybridJoinFromValues"/>).
+        /// <paramref name="subKeyExists"/> receives an HKLM-relative subkey path and reports
+        /// whether it exists; a throwing probe degrades to <c>false</c>.
+        /// </summary>
+        internal static bool ResolveIsCloudPc(Func<string, bool> subKeyExists)
+        {
+            if (subKeyExists == null) return false;
+
+            try
+            {
+                return subKeyExists(Windows365MarkerKey) && subKeyExists(CmdeServiceKey);
+            }
+            catch
+            {
+                return false;
+            }
+        }
+
+        private static bool SubKeyExists(string subKeyPath)
+        {
+            using (var key = Registry.LocalMachine.OpenSubKey(subKeyPath))
+            {
+                return key != null;
+            }
+        }
+    }
+}

src/Agent/AutopilotMonitor.Agent.V2.Core/Security/SessionRegistrationHelper.cs

@@ -176,6 +176,7 @@ namespace AutopilotMonitor.Agent.V2.Core.Security
                 EnrollmentType = EnrollmentRegistryDetector.DetectEnrollmentType(),
                 IsHybridJoin = EnrollmentRegistryDetector.DetectHybridJoin(),
                 IsSelfDeployingProfile = EnrollmentRegistryDetector.DetectSelfDeployingProfile(),
+                IsCloudPc = CloudPcDetector.DetectIsCloudPc(),
                 // Deliberately stays true even for self-deploying profiles: the WhiteGlove
                 // Part1/Part2 merge paths and existing dashboards key on IsUserDriven;
                 // IsSelfDeployingProfile is the additive classification signal.

src/Agent/AutopilotMonitor.Agent.V2.Core/SignalAdapters/ImeLogTrackerAdapter.cs

@@ -72,7 +72,7 @@ namespace AutopilotMonitor.Agent.V2.Core.SignalAdapters
         private readonly Action<AppPackageState, AppInstallationState, AppInstallationState>? _prevOnAppStateChanged;
         private readonly Action<string>? _prevOnPatternMatched;
         private readonly Action<string>? _prevOnImeAgentVersion;
-        private readonly Action<AppPackageState>? _prevOnDoTelemetryReceived;
+        private readonly Action<AppPackageState, DateTime?>? _prevOnDoTelemetryReceived;
         private readonly Action<ScriptExecutionState>? _prevOnScriptCompleted;
         private readonly Action<ScriptStartedInfo>? _prevOnScriptStarted;
 
@@ -82,7 +82,7 @@ namespace AutopilotMonitor.Agent.V2.Core.SignalAdapters
         private readonly Action<AppPackageState, AppInstallationState, AppInstallationState> _ourOnAppStateChanged;
         private readonly Action<string> _ourOnPatternMatched;
         private readonly Action<string> _ourOnImeAgentVersion;
-        private readonly Action<AppPackageState> _ourOnDoTelemetryReceived;
+        private readonly Action<AppPackageState, DateTime?> _ourOnDoTelemetryReceived;
         private readonly Action<ScriptExecutionState> _ourOnScriptCompleted;
         private readonly Action<ScriptStartedInfo> _ourOnScriptStarted;
 
@@ -242,10 +242,10 @@ namespace AutopilotMonitor.Agent.V2.Core.SignalAdapters
             EmitImeAgentVersion(version);
         }
 
-        private void OnDoTelemetryReceived(AppPackageState app)
+        private void OnDoTelemetryReceived(AppPackageState app, DateTime? sourceTimestampUtc)
         {
-            _prevOnDoTelemetryReceived?.Invoke(app);
-            EmitDoTelemetry(app);
+            _prevOnDoTelemetryReceived?.Invoke(app, sourceTimestampUtc);
+            EmitDoTelemetry(app, sourceTimestampUtc);
         }
 
         private void OnScriptCompleted(ScriptExecutionState script)
@@ -266,7 +266,8 @@ namespace AutopilotMonitor.Agent.V2.Core.SignalAdapters
             EmitAppState(app, oldState, newState);
         internal void TriggerPatternMatchedFromTest(string patternId) => MaybeEmitWhiteGloveSealingPattern(patternId);
         internal void TriggerImeAgentVersionFromTest(string version) => EmitImeAgentVersion(version);
-        internal void TriggerDoTelemetryFromTest(AppPackageState app) => EmitDoTelemetry(app);
+        internal void TriggerDoTelemetryFromTest(AppPackageState app, DateTime? sourceTimestampUtc = null) =>
+            EmitDoTelemetry(app, sourceTimestampUtc);
         internal void TriggerScriptCompletedFromTest(ScriptExecutionState script) => EmitScriptCompleted(script);
         internal void TriggerScriptStartedFromTest(ScriptStartedInfo info) => EmitScriptStarted(info);
 
@@ -876,7 +877,7 @@ namespace AutopilotMonitor.Agent.V2.Core.SignalAdapters
             _logger?.Info($"ImeAdapter: IME agent version detected: {version}");
         }
 
-        private void EmitDoTelemetry(AppPackageState app)
+        private void EmitDoTelemetry(AppPackageState app, DateTime? sourceTimestampUtc)
         {
             if (app == null || string.IsNullOrEmpty(app.Id)) return;
 
@@ -912,11 +913,31 @@ namespace AutopilotMonitor.Agent.V2.Core.SignalAdapters
             var patternId = _tracker.LastMatchedPatternId;
             if (!string.IsNullOrEmpty(patternId)) data["patternId"] = patternId!;
 
-            var now = ResolveOccurredAt(out var derivedFromClock, out var rawSourceTs);
+            // Two trigger paths with different time grounding (session df1fcf47: a single
+            // tz-skewed unrelated log line inherited via LastMatchedLogTimestamp dragged the
+            // session StartedAt back 7h and inflated the reported duration):
+            //  - [DO TEL] log line (sourceTimestampUtc set): the line's own timestamp is the
+            //    event time — resolve/clamp it and apply historic-replay suppression.
+            //  - DO collector poll (sourceTimestampUtc null): the completion was observed live
+            //    via Get-DeliveryOptimizationStatus; no log line is involved, so the clock is
+            //    the only honest source. LastMatchedLogTimestamp must NOT be consulted here.
+            DateTime now;
+            bool derivedFromClock;
+            DateTime? rawSourceTs;
+            if (sourceTimestampUtc.HasValue)
+            {
+                now = ResolveOccurredAt(sourceTimestampUtc, out derivedFromClock, out rawSourceTs);
 
-            // Historic replay — a week-old DO summary is not this enrollment's download.
-            if (SuppressIfHistoricReplay(derivedFromClock, rawSourceTs, SharedEventTypes.DoTelemetry, app.Id))
-                return;
+                // Historic replay — a week-old DO summary is not this enrollment's download.
+                if (SuppressIfHistoricReplay(derivedFromClock, rawSourceTs, SharedEventTypes.DoTelemetry, app.Id))
+                    return;
+            }
+            else
+            {
+                now = _clock.UtcNow;
+                derivedFromClock = true;
+                rawSourceTs = null;
+            }
 
             TagDerivedTimestamp(data, derivedFromClock, rawSourceTs);
 

src/Agent/AutopilotMonitor.Agent.V2.Core/Telemetry/Events/EventTimelineEmitter.cs

@@ -81,10 +81,12 @@ namespace AutopilotMonitor.Agent.V2.Core.Telemetry.Events
         internal const string ReasonParamKey = "reason";
 
         private readonly TelemetryEventEmitter _emitter;
+        private readonly TimelineEventStream? _timelineEvents;
 
-        public EventTimelineEmitter(TelemetryEventEmitter emitter)
+        public EventTimelineEmitter(TelemetryEventEmitter emitter, TimelineEventStream? timelineEvents = null)
         {
             _emitter = emitter ?? throw new ArgumentNullException(nameof(emitter));
+            _timelineEvents = timelineEvents;
         }
 
         public void Emit(
@@ -142,6 +144,11 @@ namespace AutopilotMonitor.Agent.V2.Core.Telemetry.Events
             };
 
             _emitter.Emit(evt);
+
+            // Post-reduce observer surface: published AFTER the transport enqueue so subscribers
+            // (gather-rule phase/event triggers) see exactly the ordering that reaches the wire.
+            // Publish never throws (subscriber isolation inside the stream).
+            _timelineEvents?.Publish(evt.EventType, evt.Phase);
         }
 
         /// <summary>

src/Agent/AutopilotMonitor.Agent.V2/Program.ImeMatchingMode.cs

@@ -6,6 +6,7 @@ using System.Net.Http;
 using System.Text;
 using System.Text.RegularExpressions;
 using AutopilotMonitor.Agent.V2.Core.Monitoring.Enrollment.Ime;
+using AutopilotMonitor.Shared.Logging;
 using AutopilotMonitor.Shared.Models;
 using Newtonsoft.Json;
 

src/Agent/AutopilotMonitor.Agent.V2/Program.InstallMode.cs

@@ -135,7 +135,7 @@ namespace AutopilotMonitor.Agent.V2
                         $"{(bootstrapTokenGiven ? "*" : "")}, " +
                         $"tenantId={(string.IsNullOrEmpty(merged.TenantId) ? "no" : "yes")}" +
                         $"{(tenantIdGiven ? "*" : "")}, " +
-                        $"tenantIdWait={merged.TenantIdWaitSeconds}s" +
+                        $"tenantIdWait={(merged.TenantIdWaitSeconds is int w ? $"{w}s" : "default")}" +
                         $"{(tenantIdWaitGiven ? "*" : "")})." +
                         " Star = explicitly set on this --install invocation, others were preserved from prior config.");
                 }
@@ -361,9 +361,12 @@ namespace AutopilotMonitor.Agent.V2
             {
                 BootstrapToken = bootstrapTokenGiven ? bootstrapTokenArg : existing?.BootstrapToken,
                 TenantId = tenantIdGiven ? tenantIdArg : existing?.TenantId,
+                // Not given → carry the prior value through, INCLUDING null. Persisting a
+                // number here would freeze the agent-side default into the file; persisting
+                // null keeps "not configured" distinguishable from an explicit opt-out (0).
                 TenantIdWaitSeconds = tenantIdWaitGiven
                     ? tenantIdWaitSeconds
-                    : (existing?.TenantIdWaitSeconds ?? 600),
+                    : existing?.TenantIdWaitSeconds,
             };
         }
 

src/Agent/AutopilotMonitor.Agent.V2/Program.cs

@@ -339,13 +339,15 @@ namespace AutopilotMonitor.Agent.V2
             // over the agent-side default (600 s). Hybrid-AAD-joined devices typically
             // need ~5 min for the AAD device cert to land in the registry; 600 s leaves
             // headroom. Pass `--tenant-id-wait 0` to opt out (legacy fast-fail).
+            // A bootstrap-config.json whose TenantIdWaitSeconds is null (file predates the
+            // property) is "not configured", NOT an opt-out — the default must still apply.
             var tenantIdWaitRaw = GetArgValue(args, "--tenant-id-wait");
             const int tenantIdWaitDefaultSeconds = 600;
             int tenantIdWaitSeconds = tenantIdWaitDefaultSeconds;
             if (!string.IsNullOrEmpty(tenantIdWaitRaw) && int.TryParse(tenantIdWaitRaw, out var parsedTenantIdWait))
                 tenantIdWaitSeconds = parsedTenantIdWait;
-            else if (bootstrapConfig != null)
-                tenantIdWaitSeconds = bootstrapConfig.TenantIdWaitSeconds;
+            else if (bootstrapConfig?.TenantIdWaitSeconds != null)
+                tenantIdWaitSeconds = bootstrapConfig.TenantIdWaitSeconds.Value;
 
             var useBootstrapTokenAuth = !string.IsNullOrEmpty(bootstrapToken);
 

src/Agent/AutopilotMonitor.Agent.V2/Runtime/AgentRuntimeHost.cs

@@ -135,7 +135,8 @@ namespace AutopilotMonitor.Agent.V2.Runtime
                 uploadBatchSize: uploadBatchSize,
                 // Live read: remote config is merged into agentConfig mid-session, so the
                 // trace-event gate must follow it rather than snapshot at construction.
-                traceEventsEnabled: () => agentConfig.SendTraceEvents))
+                traceEventsEnabled: () => agentConfig.SendTraceEvents,
+                espContinueAnywayObservationEnabled: () => agentConfig.EnableEspContinueAnywayObservation))
             {
                 using (var shutdown = new ManualResetEventSlim(false))
                 using (var shutdownComplete = new ManualResetEventSlim(false))

src/Agent/AutopilotMonitor.Agent.V2/Runtime/BackendClientFactory.cs

@@ -102,7 +102,8 @@ namespace AutopilotMonitor.Agent.V2.Runtime
                 serialNumber: hardware.SerialNumber,
                 agentVersion: agentVersion,
                 logger: logger,
-                clientCertificate: clientCertificate);
+                clientCertificate: clientCertificate,
+                isCloudPc: CloudPcDetector.DetectIsCloudPc());
 
             var emergencyReporter = new EmergencyReporter(
                 apiClient: backendApiClient,

src/Agent/AutopilotMonitor.Agent.V2/Runtime/LifecycleEmitters.cs

@@ -309,12 +309,14 @@ namespace AutopilotMonitor.Agent.V2.Runtime
                 var enrollmentType = EnrollmentRegistryDetector.DetectEnrollmentType();
                 var isHybridJoin = EnrollmentRegistryDetector.DetectHybridJoin();
                 var isSelfDeploying = EnrollmentRegistryDetector.DetectSelfDeployingProfile();
+                var isCloudPc = CloudPcDetector.DetectIsCloudPc();
 
                 var payload = new Dictionary<string, string>(StringComparer.Ordinal)
                 {
                     ["enrollmentType"] = enrollmentType,
                     ["isHybridJoin"] = isHybridJoin ? "true" : "false",
                     ["isSelfDeployingProfile"] = isSelfDeploying ? "true" : "false",
+                    ["isCloudPc"] = isCloudPc ? "true" : "false",
                 };
 
                 var evidence = new Evidence(
@@ -329,7 +331,7 @@ namespace AutopilotMonitor.Agent.V2.Runtime
                     evidence: evidence,
                     payload: payload);
 
-                logger.Debug($"EnrollmentFactsObserved signal posted (enrollmentType={enrollmentType}, isHybridJoin={isHybridJoin}, isSelfDeployingProfile={isSelfDeploying}).");
+                logger.Debug($"EnrollmentFactsObserved signal posted (enrollmentType={enrollmentType}, isHybridJoin={isHybridJoin}, isSelfDeployingProfile={isSelfDeploying}, isCloudPc={isCloudPc}).");
             }
             catch (Exception ex)
             {

src/Agent/AutopilotMonitor.DecisionCore.Tests/CloudPcObservationTests.cs

@@ -0,0 +1,103 @@
+using System;
+using System.Collections.Generic;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using AutopilotMonitor.DecisionCore.State;
+using Xunit;
+
+namespace AutopilotMonitor.DecisionCore.Tests
+{
+    /// <summary>
+    /// W365 — reducer-level coverage for the Cloud PC marker fact riding
+    /// <see cref="DecisionSignalKind.EnrollmentFactsObserved"/>: the observation records BOTH
+    /// values set-once (mirror of the registry self-deploying fact), the profile reason
+    /// carries the "no Device-ESP phase expected" expectation, and the signal census folds the
+    /// positive marker into terminal audit trails. The engine deliberately has no DeviceSetup
+    /// arrival requirement, so no behavioural gate is added — the observation is the
+    /// engine-side context that a session starting at Account Setup is the expected shape.
+    /// </summary>
+    public sealed class CloudPcObservationTests
+    {
+        private static readonly DateTime T0 = new DateTime(2026, 8, 7, 10, 0, 0, DateTimeKind.Utc);
+
+        private static DecisionSignal MakeSignal(
+            long ordinal,
+            DecisionSignalKind kind,
+            DateTime occurredAtUtc,
+            IReadOnlyDictionary<string, string>? payload = null) =>
+            new DecisionSignal(
+                sessionSignalOrdinal: ordinal,
+                sessionTraceOrdinal: ordinal,
+                kind: kind,
+                kindSchemaVersion: 1,
+                occurredAtUtc: occurredAtUtc,
+                sourceOrigin: "test",
+                evidence: new Evidence(EvidenceKind.Synthetic, $"t-{kind}-{ordinal}", $"synthetic {kind}"),
+                payload: payload);
+
+        private static DecisionState ReduceFacts(DecisionEngine engine, DecisionState state, long ordinal, string isCloudPc)
+            => engine.Reduce(state, MakeSignal(ordinal, DecisionSignalKind.EnrollmentFactsObserved, T0.AddSeconds(ordinal),
+                new Dictionary<string, string>
+                {
+                    [SignalPayloadKeys.EnrollmentType] = "v1",
+                    [SignalPayloadKeys.IsCloudPc] = isCloudPc,
+                })).NewState;
+
+        [Fact]
+        public void EnrollmentFactsObserved_true_recordsObservation_andExpectationReason()
+        {
+            var engine = new DecisionEngine();
+            var state = engine.Reduce(
+                DecisionState.CreateInitial("cpc-1", "t", T0),
+                MakeSignal(0, DecisionSignalKind.SessionStarted, T0)).NewState;
+
+            state = ReduceFacts(engine, state, 1, "true");
+
+            Assert.NotNull(state.ScenarioObservations.CloudPc);
+            Assert.True(state.ScenarioObservations.CloudPc!.Value);
+            Assert.Equal(1, state.ScenarioObservations.CloudPc!.SourceSignalOrdinal);
+            Assert.Equal(
+                EnrollmentScenarioProfileUpdater.CloudPcNoDeviceEspExpectedReason,
+                state.ScenarioProfile.Reason);
+            // Stage-agnostic fact signal — the reducer must not move the session anywhere.
+            Assert.Equal(SessionStage.SessionStarted, state.Stage);
+        }
+
+        [Fact]
+        public void EnrollmentFactsObserved_false_recordsObservation_setOnce()
+        {
+            var engine = new DecisionEngine();
+            var state = engine.Reduce(
+                DecisionState.CreateInitial("cpc-2", "t", T0),
+                MakeSignal(0, DecisionSignalKind.SessionStarted, T0)).NewState;
+
+            state = ReduceFacts(engine, state, 1, "false");
+            Assert.NotNull(state.ScenarioObservations.CloudPc);
+            Assert.False(state.ScenarioObservations.CloudPc!.Value);
+
+            // Set-once: a later contradicting re-read must not overwrite the first sighting
+            // (same contract as RegistrySelfDeployingProfile — replay-deterministic evidence).
+            state = ReduceFacts(engine, state, 2, "true");
+            Assert.False(state.ScenarioObservations.CloudPc!.Value);
+            Assert.Equal(1, state.ScenarioObservations.CloudPc!.SourceSignalOrdinal);
+        }
+
+        [Fact]
+        public void Census_foldsPositiveMarker_only()
+        {
+            var engine = new DecisionEngine();
+            var initial = engine.Reduce(
+                DecisionState.CreateInitial("cpc-3", "t", T0),
+                MakeSignal(0, DecisionSignalKind.SessionStarted, T0)).NewState;
+
+            var cloudPcState = ReduceFacts(engine, initial, 1, "true");
+            var census = DecisionStateSignalCensus.Build(cloudPcState);
+            Assert.Contains("cloud_pc_marker", census.SignalsSeen);
+            Assert.True(census.SignalEvidence.ContainsKey("cloudPcMarker"));
+
+            var physicalState = ReduceFacts(engine, initial, 1, "false");
+            var physicalCensus = DecisionStateSignalCensus.Build(physicalState);
+            Assert.DoesNotContain("cloud_pc_marker", physicalCensus.SignalsSeen);
+        }
+    }
+}

src/Agent/AutopilotMonitor.DecisionCore.Tests/ContinueAnywayObservationTests.cs

@@ -0,0 +1,383 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using AutopilotMonitor.DecisionCore.Engine;
+using AutopilotMonitor.DecisionCore.Signals;
+using AutopilotMonitor.DecisionCore.State;
+using Xunit;
+
+namespace AutopilotMonitor.DecisionCore.Tests
+{
+    /// <summary>
+    /// Continue-Anyway observation mode (tenant c9787ba2, session 53d1e9f6, 2026-08-08).
+    /// A Device-phase ESP terminal failure (AccountSetup never entered) on a
+    /// Continue-Anyway-enabled profile is a hard fail by default; with the tenant opt-in
+    /// (<c>EspContinueAnywayObservationEnabled</c> observation) it is defanged into a 60-min
+    /// observation advisory instead. Coverage:
+    /// <list type="bullet">
+    ///   <item>Defang + 60-min AdvisoryCompletion arming (vs the classic 30-min window).</item>
+    ///   <item>Opt-out / ContinueAnyway-off / self-deploying-scenario regressions still hard-fail.</item>
+    ///   <item>Real-user desktop + Hello-disabled completes eagerly through Finalizing; the
+    ///         terminal enrollment_complete carries the espSoftFailure marker.</item>
+    ///   <item>Window expiry without desktop un-defangs to esp_terminal_failure.</item>
+    ///   <item>Deadline fire with desktop but unknown Hello promotes to AwaitingHello.</item>
+    ///   <item>Category recovery ("Try again") resolves the advisory (classic 4910a5a5 hook).</item>
+    /// </list>
+    /// </summary>
+    public sealed class ContinueAnywayObservationTests
+    {
+        private static readonly DateTime T0 = new DateTime(2026, 8, 7, 15, 16, 0, DateTimeKind.Utc);
+
+        private static DecisionSignal MakeSignal(
+            long ordinal,
+            DecisionSignalKind kind,
+            DateTime occurredAtUtc,
+            IReadOnlyDictionary<string, string>? payload = null,
+            string sourceOrigin = "test")
+        {
+            return new DecisionSignal(
+                sessionSignalOrdinal: ordinal,
+                sessionTraceOrdinal: ordinal,
+                kind: kind,
+                kindSchemaVersion: 1,
+                occurredAtUtc: occurredAtUtc,
+                sourceOrigin: sourceOrigin,
+                evidence: new Evidence(EvidenceKind.Synthetic, $"{kind}-{ordinal}", "test"),
+                payload: payload);
+        }
+
+        private static DecisionSignal DeadlineFired(long ordinal, DateTime occurredAtUtc, string deadlineName) =>
+            MakeSignal(ordinal, DecisionSignalKind.DeadlineFired, occurredAtUtc,
+                new Dictionary<string, string> { [SignalPayloadKeys.Deadline] = deadlineName });
+
+        private static DecisionEffect SingleTimelineEffect(DecisionStep step, string eventType) =>
+            step.Effects.Single(e =>
+                e.Kind == DecisionEffectKind.EmitEventTimelineEntry
+                && e.Parameters != null
+                && e.Parameters.TryGetValue("eventType", out var et)
+                && et == eventType);
+
+        private static ActiveDeadline? FindDeadline(DecisionState state, string name) =>
+            state.Deadlines.FirstOrDefault(d => d.Name == name);
+
+        /// <summary>
+        /// Replays the session-53d1e9f6 shape up to (but excluding) the ESP terminal failure:
+        /// Continue-Anyway profile with the tenant observation opt-in stamped into the
+        /// EspConfigDetected payload, Hello policy disabled, DeviceSetup entered —
+        /// AccountSetup never reached (the 30-min Device-ESP wall kills it first).
+        /// </summary>
+        private static DecisionState SetupObservationEligibleSession(
+            DecisionEngine engine,
+            bool observationOptIn = true,
+            bool continueAnyway = true,
+            bool helloPolicyDisabled = true)
+        {
+            var state = DecisionState.CreateInitial("sess-53d1e9f6", "tenant-c9787ba2", T0);
+            state = engine.Reduce(state, MakeSignal(0, DecisionSignalKind.SessionStarted, T0)).NewState;
+            var espConfig = new Dictionary<string, string>
+            {
+                [SignalPayloadKeys.SkipUserEsp] = "false",
+                [SignalPayloadKeys.SkipDeviceEsp] = "false",
+                [SignalPayloadKeys.EspSyncFailureTimeoutMinutes] = "30",
+                [SignalPayloadKeys.EspAllowContinueAnyway] = continueAnyway ? "true" : "false",
+            };
+            if (observationOptIn)
+            {
+                espConfig[SignalPayloadKeys.EspContinueAnywayObservationEnabled] = "true";
+            }
+            state = engine.Reduce(state, MakeSignal(
+                5, DecisionSignalKind.EspConfigDetected, T0.AddMinutes(1), espConfig)).NewState;
+            if (helloPolicyDisabled)
+            {
+                state = engine.Reduce(state, MakeSignal(
+                    8, DecisionSignalKind.HelloPolicyDetected, T0.AddMinutes(1),
+                    new Dictionary<string, string> { [SignalPayloadKeys.HelloEnabled] = "false" })).NewState;
+            }
+            state = engine.Reduce(state, MakeSignal(
+                10, DecisionSignalKind.EspPhaseChanged, T0.AddMinutes(2),
+                new Dictionary<string, string> { [SignalPayloadKeys.EspPhase] = "DeviceSetup" })).NewState;
+            return state;
+        }
+
+        private static DecisionStep ApplyDeviceSetupTerminalFailure(DecisionEngine engine, DecisionState state, long ordinal = 50) =>
+            engine.Reduce(state, MakeSignal(
+                ordinal, DecisionSignalKind.EspTerminalFailure, T0.AddMinutes(38),
+                new Dictionary<string, string>
+                {
+                    ["failureType"] = "Provisioning_DeviceSetup_Certificates_Failed",
+                    ["failedSubcategory"] = "Certificates",
+                    ["category"] = "DeviceSetup",
+                }));
+
+        // ============================================================ defang path ====
+
+        [Fact]
+        public void DeviceSetupFailure_WithOptIn_DefangsToObservationAdvisory()
+        {
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            Assert.Null(state.AccountSetupEnteredUtc);
+
+            var preStage = state.Stage;
+            var step = ApplyDeviceSetupTerminalFailure(engine, state);
+
+            // No terminal — stage unchanged, advisory anchored, no LastFailureTrigger.
+            Assert.Equal(preStage, step.NewState.Stage);
+            Assert.Null(step.NewState.Outcome);
+            Assert.NotNull(step.NewState.EspAdvisoryFailureRecordedUtc);
+            Assert.Equal("DeviceSetup", step.NewState.EspAdvisoryFailureCategory!.Value);
+            Assert.Null(step.NewState.LastFailureTrigger);
+
+            var advisory = SingleTimelineEffect(step, "esp_failure_advisory");
+            Assert.Equal("esp_failure_defanged_continueanyway_observation", advisory.Parameters!["advisoryReason"]);
+            Assert.Equal("Warning", advisory.Parameters!["severity"]);
+            Assert.Equal("true", advisory.Parameters!["mayHaveContinuedAnyway"]);
+
+            Assert.DoesNotContain(step.Effects, e =>
+                e.Parameters != null
+                && e.Parameters.TryGetValue("eventType", out var et)
+                && et == "enrollment_failed");
+        }
+
+        [Fact]
+        public void DeviceSetupFailure_WithOptIn_Arms60MinObservationWindow()
+        {
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+
+            var step = ApplyDeviceSetupTerminalFailure(engine, state);
+
+            var deadline = FindDeadline(step.NewState, DeadlineNames.AdvisoryCompletion);
+            Assert.NotNull(deadline);
+            // 60-min observation window (user decision 2026-08-08) — NOT the classic 30-min
+            // advisory-completion window.
+            Assert.Equal(T0.AddMinutes(38).AddMinutes(60), deadline!.DueAtUtc);
+        }
+
+        // ==================================================== negative / regression ====
+
+        [Fact]
+        public void DeviceSetupFailure_WithoutOptIn_StillHardFails()
+        {
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine, observationOptIn: false);
+
+            var step = ApplyDeviceSetupTerminalFailure(engine, state);
+
+            Assert.Equal(SessionStage.Failed, step.NewState.Stage);
+            Assert.Equal(SessionOutcome.EnrollmentFailed, step.NewState.Outcome);
+            Assert.Null(step.NewState.EspAdvisoryFailureRecordedUtc);
+            SingleTimelineEffect(step, "enrollment_failed");
+        }
+
+        [Fact]
+        public void DeviceSetupFailure_WithOptIn_ButContinueAnywayDisabled_StillHardFails()
+        {
+            // The observation only makes sense when the ESP profile actually offers the
+            // "Continue anyway" button — without it the user cannot reach the desktop.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine, continueAnyway: false);
+
+            var step = ApplyDeviceSetupTerminalFailure(engine, state);
+
+            Assert.Equal(SessionStage.Failed, step.NewState.Stage);
+            Assert.Null(step.NewState.EspAdvisoryFailureRecordedUtc);
+            SingleTimelineEffect(step, "enrollment_failed");
+        }
+
+        [Fact]
+        public void DeviceSetupFailure_WithOptIn_OnSelfDeployingProfile_StillHardFails()
+        {
+            // Scope gate: self-deploying/kiosk flows have no interactive user who could press
+            // "Continue anyway" — observation would only ever expire. Immediate fail is truthful.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = engine.Reduce(state, MakeSignal(
+                20, DecisionSignalKind.EnrollmentFactsObserved, T0.AddMinutes(3),
+                new Dictionary<string, string> { [SignalPayloadKeys.IsSelfDeployingProfile] = "true" })).NewState;
+
+            var step = ApplyDeviceSetupTerminalFailure(engine, state);
+
+            Assert.Equal(SessionStage.Failed, step.NewState.Stage);
+            Assert.Null(step.NewState.EspAdvisoryFailureRecordedUtc);
+        }
+
+        [Fact]
+        public void ClassicAdvisory_WithAccountSetupEntered_KeepsClassicReasonAndWindow()
+        {
+            // Regression: the opt-in must not change the classic post-AccountSetup advisory —
+            // same advisoryReason literal, same 30-min window.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = engine.Reduce(state, MakeSignal(
+                20, DecisionSignalKind.EspPhaseChanged, T0.AddMinutes(17),
+                new Dictionary<string, string> { [SignalPayloadKeys.EspPhase] = "AccountSetup" })).NewState;
+            Assert.NotNull(state.AccountSetupEnteredUtc);
+
+            var step = ApplyDeviceSetupTerminalFailure(engine, state);
+
+            var advisory = SingleTimelineEffect(step, "esp_failure_advisory");
+            Assert.Equal("esp_failure_defanged_continueanyway_with_accountsetup", advisory.Parameters!["advisoryReason"]);
+            var deadline = FindDeadline(step.NewState, DeadlineNames.AdvisoryCompletion);
+            Assert.Equal(T0.AddMinutes(38).AddMinutes(30), deadline!.DueAtUtc);
+        }
+
+        // ========================================== real end: desktop completion ====
+
+        [Fact]
+        public void ObservationAdvisory_ThenRealUserDesktop_CompletesThroughFinalizing()
+        {
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = ApplyDeviceSetupTerminalFailure(engine, state).NewState;
+
+            // User pressed "Continue anyway" → signed in → DAD-validated real-user desktop.
+            var step = engine.Reduce(state, MakeSignal(
+                60, DecisionSignalKind.DesktopArrived, T0.AddMinutes(42)));
+
+            Assert.Equal(SessionStage.Finalizing, step.NewState.Stage);
+            Assert.Contains(":ContinueAnywayObservation", step.Transition.Trigger);
+            // Hello disabled → synthetic skip recorded by the fast-path.
+            Assert.NotNull(step.NewState.HelloResolvedUtc);
+            Assert.NotNull(FindDeadline(step.NewState, DeadlineNames.FinalizingGrace));
+        }
+
+        [Fact]
+        public void ObservationCompletion_EnrollmentComplete_CarriesEspSoftFailureMarker()
+        {
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = ApplyDeviceSetupTerminalFailure(engine, state).NewState;
+            state = engine.Reduce(state, MakeSignal(
+                60, DecisionSignalKind.DesktopArrived, T0.AddMinutes(42))).NewState;
+            Assert.Equal(SessionStage.Finalizing, state.Stage);
+
+            var step = engine.Reduce(state, DeadlineFired(70, T0.AddMinutes(42.1), DeadlineNames.FinalizingGrace));
+
+            Assert.Equal(SessionStage.Completed, step.NewState.Stage);
+            Assert.Equal(SessionOutcome.EnrollmentComplete, step.NewState.Outcome);
+
+            var complete = SingleTimelineEffect(step, "enrollment_complete");
+            var payload = Assert.IsType<Dictionary<string, object>>(complete.TypedPayload);
+            Assert.Equal("true", payload["espSoftFailure"]);
+            Assert.Equal("continue_anyway_observation", payload["completionSource"]);
+            Assert.Equal("DeviceSetup", payload["espSoftFailureCategory"]);
+        }
+
+        [Fact]
+        public void CleanCompletion_EnrollmentComplete_OmitsEspSoftFailureMarker()
+        {
+            // A session without any advisory must not carry the marker — regression guard for
+            // the BuildEnrollmentCompleteEffect change.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = engine.Reduce(state, MakeSignal(
+                20, DecisionSignalKind.EspPhaseChanged, T0.AddMinutes(17),
+                new Dictionary<string, string> { [SignalPayloadKeys.EspPhase] = "AccountSetup" })).NewState;
+            state = engine.Reduce(state, MakeSignal(
+                30, DecisionSignalKind.AccountSetupProvisioningComplete, T0.AddMinutes(20))).NewState;
+            state = engine.Reduce(state, MakeSignal(
+                40, DecisionSignalKind.DesktopArrived, T0.AddMinutes(21))).NewState;
+            Assert.Equal(SessionStage.Finalizing, state.Stage);
+
+            var step = engine.Reduce(state, DeadlineFired(50, T0.AddMinutes(21.1), DeadlineNames.FinalizingGrace));
+
+            Assert.Equal(SessionStage.Completed, step.NewState.Stage);
+            var complete = SingleTimelineEffect(step, "enrollment_complete");
+            var payload = Assert.IsType<Dictionary<string, object>>(complete.TypedPayload);
+            Assert.False(payload.ContainsKey("espSoftFailure"));
+            Assert.False(payload.ContainsKey("completionSource"));
+        }
+
+        // =============================================== window expiry / deadline ====
+
+        [Fact]
+        public void ObservationWindow_ExpiresWithoutDesktop_UnDefangsToEspTerminalFailure()
+        {
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = ApplyDeviceSetupTerminalFailure(engine, state).NewState;
+            Assert.Null(state.DesktopArrivedUtc);
+
+            var step = engine.Reduce(state, DeadlineFired(60, T0.AddMinutes(98), DeadlineNames.AdvisoryCompletion));
+
+            Assert.Equal(SessionStage.Failed, step.NewState.Stage);
+            Assert.Equal(SessionOutcome.EnrollmentFailed, step.NewState.Outcome);
+            // The failure cause IS the original ESP failure — same reason literal, likely-stuck
+            // promotion stays armed via LastFailureTrigger=EspTerminalFailure.
+            Assert.Equal(nameof(DecisionSignalKind.EspTerminalFailure), step.NewState.LastFailureTrigger!.Value);
+
+            var failed = SingleTimelineEffect(step, "enrollment_failed");
+            Assert.Equal("esp_terminal_failure", failed.Parameters!["reason"]);
+            Assert.Equal(
+                "continue_anyway_observation_window_expired_without_completion_evidence",
+                failed.Parameters!["advisoryReason"]);
+        }
+
+        [Fact]
+        public void ObservationWindow_FiresWithDesktopAndDisabledHello_CompletesInsteadOfFailing()
+        {
+            // Ordering variant: desktop arrived but (hypothetically) no eager completion ran —
+            // the deadline-fire conjunction must accept desktop + hello for the observation
+            // variant without the (structurally impossible) IME user-session gate.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine, helloPolicyDisabled: false);
+            state = ApplyDeviceSetupTerminalFailure(engine, state).NewState;
+            // Hello policy lands AFTER the failure; desktop arrives; no eager completion since
+            // the fast-path needs the policy fact at desktop-arrival time.
+            state = engine.Reduce(state, MakeSignal(
+                60, DecisionSignalKind.DesktopArrived, T0.AddMinutes(42))).NewState;
+            Assert.NotEqual(SessionStage.Finalizing, state.Stage);
+            state = engine.Reduce(state, MakeSignal(
+                65, DecisionSignalKind.HelloPolicyDetected, T0.AddMinutes(43),
+                new Dictionary<string, string> { [SignalPayloadKeys.HelloEnabled] = "false" })).NewState;
+
+            var step = engine.Reduce(state, DeadlineFired(70, T0.AddMinutes(98), DeadlineNames.AdvisoryCompletion));
+
+            Assert.Equal(SessionStage.Finalizing, step.NewState.Stage);
+            Assert.Null(step.NewState.Outcome);
+            Assert.NotNull(FindDeadline(step.NewState, DeadlineNames.FinalizingGrace));
+        }
+
+        [Fact]
+        public void ObservationWindow_FiresWithDesktopButUnknownHello_PromotesToAwaitingHello()
+        {
+            // Hello policy never observed (no PassportForWork value) — the hello prerequisite is
+            // structurally unresolvable. The never-observed promote must apply to the observation
+            // variant instead of failing a desktop-proven session.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine, helloPolicyDisabled: false);
+            state = ApplyDeviceSetupTerminalFailure(engine, state).NewState;
+            state = engine.Reduce(state, MakeSignal(
+                60, DecisionSignalKind.DesktopArrived, T0.AddMinutes(42))).NewState;
+            Assert.Null(state.HelloPolicyEnabled);
+
+            var step = engine.Reduce(state, DeadlineFired(70, T0.AddMinutes(98), DeadlineNames.AdvisoryCompletion));
+
+            Assert.Equal(SessionStage.AwaitingHello, step.NewState.Stage);
+            Assert.Null(step.NewState.Outcome);
+            Assert.NotNull(FindDeadline(step.NewState, DeadlineNames.HelloSafety));
+        }
+
+        // ======================================================= category recovery ====
+
+        [Fact]
+        public void ObservationAdvisory_DeviceSetupRecovery_ResolvesAdvisory()
+        {
+            // "Try again" path: the ESP re-runs the device phase and DeviceSetup resolves to
+            // success — the 4910a5a5 recovery hook must match the observation advisory too.
+            var engine = new DecisionEngine();
+            var state = SetupObservationEligibleSession(engine);
+            state = ApplyDeviceSetupTerminalFailure(engine, state).NewState;
+
+            var step = engine.Reduce(state, MakeSignal(
+                60, DecisionSignalKind.DeviceSetupProvisioningComplete, T0.AddMinutes(55)));
+
+            Assert.NotNull(step.NewState.EspAdvisoryFailureResolvedUtc);
+            Assert.Contains(step.Effects, e =>
+                e.Parameters != null
+                && e.Parameters.TryGetValue("eventType", out var et)
+                && et == "esp_failure_advisory_resolved");
+        }
+    }
+}

src/Agent/AutopilotMonitor.DecisionCore.Tests/SerializationTests.cs

@@ -490,7 +490,8 @@ namespace AutopilotMonitor.DecisionCore.Tests
                     .WithShellCoreWhiteGloveSuccessSeen(sourceSignalOrdinal: 3)
                     .WithSkipUserEsp(value: true, sourceSignalOrdinal: 4)
                     .WithEspSyncFailureTimeoutMinutes(value: 90, sourceSignalOrdinal: 5)
-                    .WithRegistrySelfDeployingProfile(value: false, sourceSignalOrdinal: 6))
+                    .WithRegistrySelfDeployingProfile(value: false, sourceSignalOrdinal: 6)
+                    .WithCloudPc(value: true, sourceSignalOrdinal: 7))
                 .Build();
 
             var json = StateSerializer.Serialize(state);
@@ -504,6 +505,8 @@ namespace AutopilotMonitor.DecisionCore.Tests
             Assert.Equal(5, o.EspSyncFailureTimeoutMinutes!.SourceSignalOrdinal);
             Assert.False(o.RegistrySelfDeployingProfile!.Value);
             Assert.Equal(6, o.RegistrySelfDeployingProfile!.SourceSignalOrdinal);
+            Assert.True(o.CloudPc!.Value);
+            Assert.Equal(7, o.CloudPc!.SourceSignalOrdinal);
 
             // Never-observed facts must rehydrate as null (null ≠ veto — session 62e603c9).
             Assert.Null(o.WhiteGloveSealingPatternSeen);

src/Agent/AutopilotMonitor.DecisionCore.Tests/State/EnrollmentScenarioProfileUpdaterTests.cs

@@ -515,6 +515,99 @@ namespace AutopilotMonitor.DecisionCore.Tests.State
 
         // ================================================================== helpers
 
+        // ------------------------------------------------ isCloudPc annotation (W365)
+        // Cloud PC first connect: Device-ESP already ran headless at provisioning, so the
+        // profile records the "no Device-ESP phase expected" expectation as the reason.
+        // Reason-only by design — Mode is classified by AccountSetup/IME signals (Classic),
+        // and EspConfig keeps the CONFIGURED FirstSync semantics.
+
+        [Fact]
+        public void EnrollmentFactsObserved_cloudPc_annotatesReason_keepsModeUnknown()
+        {
+            var signal = MakeSignal(
+                DecisionSignalKind.EnrollmentFactsObserved,
+                ordinal: 0,
+                payload: new Dictionary<string, string>
+                {
+                    [SignalPayloadKeys.EnrollmentType] = "v1",
+                    [SignalPayloadKeys.IsHybridJoin] = "false",
+                    [SignalPayloadKeys.IsCloudPc] = "true",
+                });
+
+            var profile = EnrollmentScenarioProfileUpdater.ApplyEnrollmentFactsObserved(
+                EnrollmentScenarioProfile.Empty, signal);
+
+            Assert.Equal(EnrollmentMode.Unknown, profile.Mode);
+            Assert.Equal(EnrollmentScenarioProfileUpdater.CloudPcNoDeviceEspExpectedReason, profile.Reason);
+            Assert.Equal(EnrollmentJoinMode.AzureAdJoin, profile.JoinMode);
+            Assert.Equal(EspConfig.Unknown, profile.EspConfig);
+        }
+
+        [Fact]
+        public void EnrollmentFactsObserved_cloudPc_repeatPost_isIdempotent()
+        {
+            Dictionary<string, string> Facts() => new Dictionary<string, string>
+            {
+                [SignalPayloadKeys.EnrollmentType] = "v1",
+                [SignalPayloadKeys.IsHybridJoin] = "false",
+                [SignalPayloadKeys.IsCloudPc] = "true",
+            };
+            var first = MakeSignal(DecisionSignalKind.EnrollmentFactsObserved, ordinal: 0, payload: Facts());
+            var second = MakeSignal(DecisionSignalKind.EnrollmentFactsObserved, ordinal: 9, payload: Facts());
+
+            var p1 = EnrollmentScenarioProfileUpdater.ApplyEnrollmentFactsObserved(
+                EnrollmentScenarioProfile.Empty, first);
+            var p2 = EnrollmentScenarioProfileUpdater.ApplyEnrollmentFactsObserved(p1, second);
+
+            // The repeat must be a full no-op: the Cloud PC annotation already owns the
+            // reason slot, and the cloudPcAnnotates gate keeps the generic v1 annotation
+            // from re-claiming it (which would bump EvidenceOrdinal every post).
+            Assert.Same(p1, p2);
+            Assert.Equal(0, p2.EvidenceOrdinal);
+        }
+
+        [Fact]
+        public void EnrollmentFactsObserved_cloudPcFalse_keepsGenericV1Reason()
+        {
+            var signal = MakeSignal(
+                DecisionSignalKind.EnrollmentFactsObserved,
+                ordinal: 0,
+                payload: new Dictionary<string, string>
+                {
+                    [SignalPayloadKeys.EnrollmentType] = "v1",
+                    [SignalPayloadKeys.IsCloudPc] = "false",
+                });
+
+            var profile = EnrollmentScenarioProfileUpdater.ApplyEnrollmentFactsObserved(
+                EnrollmentScenarioProfile.Empty, signal);
+
+            Assert.Equal("enrollment_facts_observed:v1", profile.Reason);
+        }
+
+        [Fact]
+        public void EnrollmentFactsObserved_cloudPc_doesNotDisturbSelfDeployingSeed()
+        {
+            // Defensive combination (not expected in the field — Cloud PCs are never
+            // Autopilot-registered): the deterministic self-deploying Mode seed must
+            // survive; only the reason slot goes to the more specific annotation.
+            var signal = MakeSignal(
+                DecisionSignalKind.EnrollmentFactsObserved,
+                ordinal: 0,
+                payload: new Dictionary<string, string>
+                {
+                    [SignalPayloadKeys.EnrollmentType] = "v1",
+                    [SignalPayloadKeys.IsSelfDeployingProfile] = "true",
+                    [SignalPayloadKeys.IsCloudPc] = "true",
+                });
+
+            var profile = EnrollmentScenarioProfileUpdater.ApplyEnrollmentFactsObserved(
+                EnrollmentScenarioProfile.Empty, signal);
+
+            Assert.Equal(EnrollmentMode.SelfDeploying, profile.Mode);
+            Assert.Equal(ProfileConfidence.High, profile.Confidence);
+            Assert.Equal(EnrollmentScenarioProfileUpdater.CloudPcNoDeviceEspExpectedReason, profile.Reason);
+        }
+
         private static DecisionSignal MakeSignal(
             DecisionSignalKind kind,
             long ordinal,

src/Backend/AutopilotMonitor.Functions.Tests/AdminConfigurationAutoApproveNewTenantsTests.cs

@@ -0,0 +1,34 @@
+using AutopilotMonitor.Shared.Models;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Default-value + round-trip tests for <see cref="AdminConfiguration.AutoApproveNewTenants"/>.
+/// The flag gates the tenant auto-approve queue worker — defaulting to false keeps new tenant
+/// signups on manual Global Admin approval until the operator deliberately opts in.
+/// </summary>
+public class AdminConfigurationAutoApproveNewTenantsTests
+{
+    [Fact]
+    public void AutoApproveNewTenants_defaults_to_false_on_new_config()
+    {
+        var cfg = new AdminConfiguration();
+        Assert.False(cfg.AutoApproveNewTenants);
+    }
+
+    [Fact]
+    public void AutoApproveNewTenants_defaults_to_false_on_CreateDefault()
+    {
+        // CreateDefault() is called when no admin-config row exists yet — if it somehow
+        // enabled auto-approve, tenants would activate without any operator opt-in.
+        var cfg = AdminConfiguration.CreateDefault();
+        Assert.False(cfg.AutoApproveNewTenants);
+    }
+
+    [Fact]
+    public void AutoApproveNewTenants_true_persists_on_the_config()
+    {
+        var cfg = new AdminConfiguration { AutoApproveNewTenants = true };
+        Assert.True(cfg.AutoApproveNewTenants);
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/AdminConfigurationRateLimitSyncTests.cs

@@ -51,5 +51,7 @@ public class AdminConfigurationRateLimitSyncTests
         // ...but NO tenant configuration is enumerated or mutated (sync removed).
         repo.Verify(r => r.GetAllTenantConfigurationsAsync(), Times.Never);
         repo.Verify(r => r.SaveTenantConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        repo.Verify(r => r.SaveTenantConfigurationAsync(
+            It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 }

src/Backend/AutopilotMonitor.Functions.Tests/AdminConfigurationSelfServiceAppHomingTests.cs

@@ -0,0 +1,64 @@
+using AutopilotMonitor.Functions.Services;
+using AutopilotMonitor.Shared.DataAccess;
+using AutopilotMonitor.Shared.Models;
+using Microsoft.Extensions.Caching.Memory;
+using Microsoft.Extensions.Logging.Abstractions;
+using Moq;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Default-value + fail-closed tests for <see cref="AdminConfiguration.SelfServiceAppHomingEnabled"/>.
+/// The flag is the kill switch of the dual app-reg self-service homing flip — defaulting to false
+/// keeps the consent funnel and auto-flip off until the operator deliberately opts in, and a
+/// storage error must read as "disabled" (kill switch wins over a blip).
+/// </summary>
+public class AdminConfigurationSelfServiceAppHomingTests
+{
+    [Fact]
+    public void SelfServiceAppHoming_defaults_to_false_on_new_config()
+    {
+        var cfg = new AdminConfiguration();
+        Assert.False(cfg.SelfServiceAppHomingEnabled);
+    }
+
+    [Fact]
+    public void SelfServiceAppHoming_defaults_to_false_on_CreateDefault()
+    {
+        var cfg = AdminConfiguration.CreateDefault();
+        Assert.False(cfg.SelfServiceAppHomingEnabled);
+    }
+
+    [Fact]
+    public void SelfServiceAppHoming_true_persists_on_the_config()
+    {
+        var cfg = new AdminConfiguration { SelfServiceAppHomingEnabled = true };
+        Assert.True(cfg.SelfServiceAppHomingEnabled);
+    }
+
+    [Fact]
+    public async Task Reader_returns_true_when_flag_enabled()
+    {
+        var repo = new Mock<IConfigRepository>();
+        repo.Setup(r => r.GetAdminConfigurationAsync())
+            .ReturnsAsync(new AdminConfiguration { SelfServiceAppHomingEnabled = true });
+        var svc = new AdminConfigurationService(
+            repo.Object, NullLogger<AdminConfigurationService>.Instance,
+            new MemoryCache(new MemoryCacheOptions()));
+
+        Assert.True(await svc.IsSelfServiceAppHomingEnabledAsync());
+    }
+
+    [Fact]
+    public async Task Reader_fails_closed_on_repository_error()
+    {
+        var repo = new Mock<IConfigRepository>();
+        repo.Setup(r => r.GetAdminConfigurationAsync())
+            .ThrowsAsync(new InvalidOperationException("storage down"));
+        var svc = new AdminConfigurationService(
+            repo.Object, NullLogger<AdminConfigurationService>.Instance,
+            new MemoryCache(new MemoryCacheOptions()));
+
+        Assert.False(await svc.IsSelfServiceAppHomingEnabledAsync());
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/AppHomingDecisionTests.cs

@@ -0,0 +1,135 @@
+using AutopilotMonitor.Functions.Services;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Authorization/validation matrix for <see cref="AppHomingService.EvaluateManualFlip"/> — the
+/// pure decision behind <c>POST config/{tenantId}/app-homing</c>. Contract: tenant admins may
+/// only flip TO primary, without force, with the self-service flag on, and only after a
+/// successful consent probe; Global Admins may flip both directions and force past the probe.
+/// </summary>
+public class AppHomingDecisionTests
+{
+    private static readonly AppHomingProbeResult ProbeOk = new(Succeeded: true, IsTransient: false);
+    private static readonly AppHomingProbeResult ProbeFail = new(Succeeded: false, IsTransient: false);
+    private static readonly AppHomingProbeResult ProbeTransient = new(Succeeded: false, IsTransient: true);
+
+    private static AppHomingDecision Evaluate(
+        bool isGlobalAdmin = false,
+        bool selfServiceEnabled = true,
+        bool legacyConfigured = true,
+        bool currentlyPrimary = false,
+        bool targetPrimary = true,
+        bool force = false,
+        AppHomingProbeResult? probe = null)
+        => AppHomingService.EvaluateManualFlip(
+            isGlobalAdmin, selfServiceEnabled, legacyConfigured, currentlyPrimary, targetPrimary, force, probe);
+
+    [Fact]
+    public void ParallelWindowInactive_denies_for_everyone()
+    {
+        var decision = Evaluate(isGlobalAdmin: true, legacyConfigured: false, force: true);
+        Assert.Equal(AppHomingDecisionKind.Deny, decision.Kind);
+        Assert.Equal("parallel-window-inactive", decision.ReasonCode);
+        Assert.Equal(409, decision.StatusCode);
+    }
+
+    [Theory]
+    [InlineData(false, false)] // legacy-homed, target legacy
+    [InlineData(true, true)]   // primary-homed, target primary
+    public void AlreadyAtTarget_is_a_noop(bool currentlyPrimary, bool targetPrimary)
+    {
+        var decision = Evaluate(currentlyPrimary: currentlyPrimary, targetPrimary: targetPrimary);
+        Assert.Equal(AppHomingDecisionKind.AllowNoOp, decision.Kind);
+    }
+
+    [Fact]
+    public void NonGa_revert_to_legacy_is_denied()
+    {
+        var decision = Evaluate(currentlyPrimary: true, targetPrimary: false);
+        Assert.Equal(AppHomingDecisionKind.Deny, decision.Kind);
+        Assert.Equal("revert-is-ga-only", decision.ReasonCode);
+        Assert.Equal(403, decision.StatusCode);
+    }
+
+    [Fact]
+    public void NonGa_force_is_denied()
+    {
+        var decision = Evaluate(force: true);
+        Assert.Equal(AppHomingDecisionKind.Deny, decision.Kind);
+        Assert.Equal("force-is-ga-only", decision.ReasonCode);
+        Assert.Equal(403, decision.StatusCode);
+    }
+
+    [Fact]
+    public void NonGa_with_flag_off_is_denied()
+    {
+        // The kill switch: turning the admin-config flag off must stop tenant-admin flips
+        // immediately, while the GA path below stays open (operator lever survives).
+        var decision = Evaluate(selfServiceEnabled: false);
+        Assert.Equal(AppHomingDecisionKind.Deny, decision.Kind);
+        Assert.Equal("self-service-disabled", decision.ReasonCode);
+        Assert.Equal(409, decision.StatusCode);
+    }
+
+    [Fact]
+    public void Ga_with_flag_off_still_requires_only_the_probe()
+    {
+        var decision = Evaluate(isGlobalAdmin: true, selfServiceEnabled: false);
+        Assert.Equal(AppHomingDecisionKind.RequireProbe, decision.Kind);
+    }
+
+    [Fact]
+    public void FlipToPrimary_without_probe_requires_probe()
+    {
+        var decision = Evaluate();
+        Assert.Equal(AppHomingDecisionKind.RequireProbe, decision.Kind);
+    }
+
+    [Fact]
+    public void FlipToPrimary_with_successful_probe_is_allowed()
+    {
+        var decision = Evaluate(probe: ProbeOk);
+        Assert.Equal(AppHomingDecisionKind.Allow, decision.Kind);
+    }
+
+    [Fact]
+    public void FlipToPrimary_with_failed_probe_is_denied()
+    {
+        var decision = Evaluate(probe: ProbeFail);
+        Assert.Equal(AppHomingDecisionKind.Deny, decision.Kind);
+        Assert.Equal("probe-failed", decision.ReasonCode);
+        Assert.Equal(409, decision.StatusCode);
+    }
+
+    [Fact]
+    public void FlipToPrimary_with_transient_probe_is_denied_as_retryable()
+    {
+        var decision = Evaluate(probe: ProbeTransient);
+        Assert.Equal(AppHomingDecisionKind.Deny, decision.Kind);
+        Assert.Equal("probe-transient", decision.ReasonCode);
+        Assert.Equal(503, decision.StatusCode);
+    }
+
+    [Fact]
+    public void Ga_flip_without_force_also_requires_probe()
+    {
+        var decision = Evaluate(isGlobalAdmin: true);
+        Assert.Equal(AppHomingDecisionKind.RequireProbe, decision.Kind);
+    }
+
+    [Fact]
+    public void Ga_force_skips_the_probe()
+    {
+        var decision = Evaluate(isGlobalAdmin: true, force: true);
+        Assert.Equal(AppHomingDecisionKind.Allow, decision.Kind);
+    }
+
+    [Fact]
+    public void Ga_revert_to_legacy_needs_no_probe()
+    {
+        // The legacy app is consented by construction — probing it would be meaningless.
+        var decision = Evaluate(isGlobalAdmin: true, currentlyPrimary: true, targetPrimary: false);
+        Assert.Equal(AppHomingDecisionKind.Allow, decision.Kind);
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/AppHomingServiceTests.cs

@@ -0,0 +1,289 @@
+using AutopilotMonitor.Functions.Security;
+using AutopilotMonitor.Functions.Services;
+using AutopilotMonitor.Functions.Services.GraphResolution;
+using AutopilotMonitor.Functions.Services.Notifications;
+using AutopilotMonitor.Shared.DataAccess;
+using AutopilotMonitor.Shared.Models;
+using Microsoft.ApplicationInsights;
+using Microsoft.ApplicationInsights.Extensibility;
+using Microsoft.Extensions.Caching.Memory;
+using Microsoft.Extensions.Configuration;
+using Microsoft.Extensions.Logging.Abstractions;
+using Moq;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Unit tests for <see cref="AppHomingService"/> — funnel eligibility, the consent-driven
+/// auto-flip, and the flip persist side-effect chain (save + cache invalidation + audit +
+/// ops events). The consent probe and the kill-switch flag are mocked at their virtual seams.
+/// </summary>
+public class AppHomingServiceTests
+{
+    private const string TenantId = "11111111-1111-1111-1111-111111111111";
+    private const string PrimaryId = "aaaaaaaa-0000-0000-0000-000000000001";
+    private const string LegacyId = "bbbbbbbb-0000-0000-0000-000000000002";
+    private const string Actor = "admin@contoso.com";
+
+    private readonly Mock<AdminConfigurationService> _adminConfigMock;
+    private readonly Mock<TenantConfigurationService> _tenantConfigMock;
+    private readonly Mock<GraphTokenService> _graphTokenMock;
+    private readonly Mock<IGraphFeatureDetector> _detectorMock;
+    private readonly Mock<IMaintenanceRepository> _maintenanceMock;
+    private readonly List<OpsEventEntry> _savedOpsEvents = new();
+    private readonly EntraAppRegistry _registry;
+    private readonly AppHomingService _sut;
+
+    public AppHomingServiceTests() : this(legacyConfigured: true) { }
+
+    private AppHomingServiceTests(bool legacyConfigured)
+    {
+        var configValues = new Dictionary<string, string?>
+        {
+            ["EntraId:ClientId"] = PrimaryId,
+            ["EntraId:ClientSecret"] = "primary-secret",
+        };
+        if (legacyConfigured)
+        {
+            configValues["EntraId:LegacyClientId"] = LegacyId;
+            configValues["EntraId:LegacyClientSecret"] = "legacy-secret";
+        }
+        var configuration = new ConfigurationBuilder().AddInMemoryCollection(configValues).Build();
+        _registry = new EntraAppRegistry(configuration, NullLogger<EntraAppRegistry>.Instance);
+
+        var configRepo = Mock.Of<IConfigRepository>();
+        var cache = new MemoryCache(new MemoryCacheOptions());
+
+        _adminConfigMock = new Mock<AdminConfigurationService>(
+            configRepo, NullLogger<AdminConfigurationService>.Instance, cache)
+        { CallBase = false };
+        _tenantConfigMock = new Mock<TenantConfigurationService>(
+            configRepo, NullLogger<TenantConfigurationService>.Instance, cache)
+        { CallBase = false };
+        _graphTokenMock = new Mock<GraphTokenService>(
+            NullLogger<GraphTokenService>.Instance,
+            Mock.Of<System.Net.Http.IHttpClientFactory>(),
+            cache,
+            configuration,
+            _registry,
+            _tenantConfigMock.Object)
+        { CallBase = false };
+        _detectorMock = new Mock<IGraphFeatureDetector>();
+        _maintenanceMock = new Mock<IMaintenanceRepository>();
+        _maintenanceMock
+            .Setup(m => m.LogAuditEntryAsync(It.IsAny<string>(), It.IsAny<string>(), It.IsAny<string>(),
+                It.IsAny<string>(), It.IsAny<string>(), It.IsAny<Dictionary<string, string>?>()))
+            .ReturnsAsync(true);
+
+        var opsRepo = new Mock<IOpsEventRepository>();
+        opsRepo.Setup(r => r.SaveOpsEventAsync(It.IsAny<OpsEventEntry>()))
+            .Callback<OpsEventEntry>(e => { lock (_savedOpsEvents) _savedOpsEvents.Add(e); })
+            .Returns(Task.CompletedTask);
+        var alertDispatch = new OpsAlertDispatchService(
+            _adminConfigMock.Object,
+            new TelegramNotificationService(new HttpClient(), configRepo,
+                NullLogger<TelegramNotificationService>.Instance),
+            new WebhookNotificationService(new HttpClient(),
+                NullLogger<WebhookNotificationService>.Instance),
+            NullLogger<OpsAlertDispatchService>.Instance);
+        var opsService = new OpsEventService(opsRepo.Object, NullLogger<OpsEventService>.Instance, alertDispatch);
+
+        _sut = new AppHomingService(
+            NullLogger<AppHomingService>.Instance,
+            _adminConfigMock.Object,
+            _tenantConfigMock.Object,
+            _registry,
+            _graphTokenMock.Object,
+            _detectorMock.Object,
+            _maintenanceMock.Object,
+            opsService,
+            new TelemetryClient(new TelemetryConfiguration { DisableTelemetry = true }));
+
+        // Defaults: flag on, legacy-homed config exists, probe succeeds. FlipAsync reads via
+        // the cache-bypassing GetConfigurationFreshAsync (read-modify-write on the whole entity).
+        _adminConfigMock.Setup(x => x.IsSelfServiceAppHomingEnabledAsync()).ReturnsAsync(true);
+        var config = LegacyHomedConfig();
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId)).ReturnsAsync(config);
+        _tenantConfigMock.Setup(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()))
+            .Returns(Task.CompletedTask);
+        SetupProbe(GraphTokenResult.Success("tok"));
+    }
+
+    private static TenantConfiguration LegacyHomedConfig()
+    {
+        var config = TenantConfiguration.CreateDefault(TenantId);
+        config.HomedAppClientId = null;
+        return config;
+    }
+
+    private void SetupProbe(GraphTokenResult result) =>
+        _graphTokenMock
+            .Setup(x => x.GetAccessTokenForAppAsync(TenantId, It.Is<EntraAppCredentials>(c => !c.IsLegacy),
+                It.IsAny<CancellationToken>()))
+            .ReturnsAsync(result);
+
+    // ── IsFunnelEligibleAsync ───────────────────────────────────────────────
+
+    [Fact]
+    public async Task Funnel_is_eligible_for_legacy_homed_tenant_with_flag_on()
+    {
+        Assert.True(await _sut.IsFunnelEligibleAsync(LegacyHomedConfig()));
+    }
+
+    [Fact]
+    public async Task Funnel_is_not_eligible_when_legacy_pair_unconfigured()
+    {
+        var sut = new AppHomingServiceTests(legacyConfigured: false)._sut;
+        Assert.False(await sut.IsFunnelEligibleAsync(LegacyHomedConfig()));
+    }
+
+    [Fact]
+    public async Task Funnel_is_not_eligible_for_primary_homed_tenant()
+    {
+        var config = LegacyHomedConfig();
+        config.HomedAppClientId = PrimaryId;
+        Assert.False(await _sut.IsFunnelEligibleAsync(config));
+    }
+
+    [Fact]
+    public async Task Funnel_is_not_eligible_when_flag_off()
+    {
+        _adminConfigMock.Setup(x => x.IsSelfServiceAppHomingEnabledAsync()).ReturnsAsync(false);
+        Assert.False(await _sut.IsFunnelEligibleAsync(LegacyHomedConfig()));
+    }
+
+    [Fact]
+    public async Task Funnel_does_not_block_on_entra_app_roles()
+    {
+        // Deliberate: app-role tenants may flip (operator informs them personally); the
+        // reminder trail is asserted in the flip test below.
+        var config = LegacyHomedConfig();
+        config.EntraAppRolesEnabled = true;
+        Assert.True(await _sut.IsFunnelEligibleAsync(config));
+    }
+
+    // ── TryAutoFlipToPrimaryAsync ───────────────────────────────────────────
+
+    [Fact]
+    public async Task AutoFlip_flips_on_probe_success_with_full_side_effect_chain()
+    {
+        var outcome = await _sut.TryAutoFlipToPrimaryAsync(LegacyHomedConfig(), Actor);
+
+        Assert.Equal(AppHomingAutoFlipOutcome.Flipped, outcome);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.Is<TenantConfiguration>(c =>
+            string.Equals(c.HomedAppClientId, PrimaryId, StringComparison.OrdinalIgnoreCase)
+            && c.UpdatedBy == Actor), It.IsAny<string?>(), It.IsAny<string?>()), Times.Once);
+        _detectorMock.Verify(x => x.InvalidateTenant(TenantId), Times.Once);
+        _maintenanceMock.Verify(m => m.LogAuditEntryAsync(TenantId, "UPDATE", "TenantConfiguration",
+            TenantId, Actor, It.Is<Dictionary<string, string>?>(d =>
+                d != null && d.ContainsKey("HomedAppClientId"))), Times.Once);
+        Assert.Contains(_savedOpsEvents, e => e.EventType == "AppHomingFlipped");
+        Assert.DoesNotContain(_savedOpsEvents, e => e.EventType == "AppHomingFlippedWithEntraRoles");
+    }
+
+    [Fact]
+    public async Task AutoFlip_does_not_flip_on_permanent_probe_failure()
+    {
+        SetupProbe(GraphTokenResult.PermanentFailure());
+
+        var outcome = await _sut.TryAutoFlipToPrimaryAsync(LegacyHomedConfig(), Actor);
+
+        Assert.Equal(AppHomingAutoFlipOutcome.ProbeFailed, outcome);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task AutoFlip_does_not_flip_on_transient_probe()
+    {
+        SetupProbe(GraphTokenResult.TransientFailure());
+
+        var outcome = await _sut.TryAutoFlipToPrimaryAsync(LegacyHomedConfig(), Actor);
+
+        Assert.Equal(AppHomingAutoFlipOutcome.ProbeTransient, outcome);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task AutoFlip_is_not_eligible_for_primary_homed_tenant_and_never_probes()
+    {
+        var config = LegacyHomedConfig();
+        config.HomedAppClientId = PrimaryId;
+
+        var outcome = await _sut.TryAutoFlipToPrimaryAsync(config, Actor);
+
+        Assert.Equal(AppHomingAutoFlipOutcome.NotEligible, outcome);
+        _graphTokenMock.Verify(x => x.GetAccessTokenForAppAsync(It.IsAny<string>(),
+            It.IsAny<EntraAppCredentials>(), It.IsAny<CancellationToken>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task AutoFlip_is_not_eligible_when_flag_off()
+    {
+        _adminConfigMock.Setup(x => x.IsSelfServiceAppHomingEnabledAsync()).ReturnsAsync(false);
+
+        var outcome = await _sut.TryAutoFlipToPrimaryAsync(LegacyHomedConfig(), Actor);
+
+        Assert.Equal(AppHomingAutoFlipOutcome.NotEligible, outcome);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+    }
+
+    // ── FlipAsync ───────────────────────────────────────────────────────────
+
+    [Fact]
+    public async Task Flip_of_entra_app_roles_tenant_emits_reminder_ops_event()
+    {
+        var config = LegacyHomedConfig();
+        config.EntraAppRolesEnabled = true;
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId)).ReturnsAsync(config);
+
+        await _sut.FlipAsync(TenantId, PrimaryId, Actor, "manual-ga");
+
+        Assert.Contains(_savedOpsEvents, e => e.EventType == "AppHomingFlipped");
+        Assert.Contains(_savedOpsEvents, e => e.EventType == "AppHomingFlippedWithEntraRoles");
+    }
+
+    [Fact]
+    public async Task Flip_noops_when_already_at_target()
+    {
+        var config = LegacyHomedConfig();
+        config.HomedAppClientId = PrimaryId;
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId)).ReturnsAsync(config);
+
+        await _sut.FlipAsync(TenantId, PrimaryId, Actor, "manual-ga");
+
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+        _detectorMock.Verify(x => x.InvalidateTenant(It.IsAny<string>()), Times.Never);
+        Assert.Empty(_savedOpsEvents);
+    }
+
+    [Fact]
+    public async Task Flip_throws_when_config_row_missing_and_saves_nothing()
+    {
+        // A flip must never materialize a default row (e.g. resurrect an offboarded tenant);
+        // the fresh read returning null is a hard stop.
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId))
+            .ReturnsAsync((TenantConfiguration?)null);
+
+        await Assert.ThrowsAsync<InvalidOperationException>(
+            () => _sut.FlipAsync(TenantId, PrimaryId, Actor, "manual-ga"));
+
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+        _detectorMock.Verify(x => x.InvalidateTenant(It.IsAny<string>()), Times.Never);
+        Assert.Empty(_savedOpsEvents);
+    }
+
+    [Fact]
+    public async Task Flip_back_to_legacy_persists_null_homing()
+    {
+        var config = LegacyHomedConfig();
+        config.HomedAppClientId = PrimaryId;
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId)).ReturnsAsync(config);
+
+        await _sut.FlipAsync(TenantId, null, Actor, "manual-ga");
+
+        // The null-homing invariant: legacy is represented as null, never as the legacy GUID.
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.Is<TenantConfiguration>(c =>
+            c.HomedAppClientId == null), It.IsAny<string?>(), It.IsAny<string?>()), Times.Once);
+        _detectorMock.Verify(x => x.InvalidateTenant(TenantId), Times.Once);
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/AuthFunctionSideEffectTests.cs

@@ -24,6 +24,7 @@ public class AuthFunctionSideEffectTests
     private readonly Mock<TelegramNotificationService> _telegramMock;
     private readonly Mock<GlobalNotificationService> _globalNotificationMock;
     private readonly Mock<IMetricsRepository> _metricsRepoMock;
+    private readonly Mock<AutopilotMonitor.Functions.Services.Activation.ITenantAutoApproveEnqueuer> _autoApproveEnqueuerMock;
     private readonly AuthFunction _sut;
 
     public AuthFunctionSideEffectTests()
@@ -44,7 +45,7 @@ public class AuthFunctionSideEffectTests
 
         var delegatedAdminMock = new Mock<DelegatedAdminService>(
             adminRepo,
-            new StubTenantEntitlementService(AutopilotMonitor.Functions.Security.TenantEdition.Enterprise),
+            new StubTenantEntitlementService(AutopilotMonitor.Functions.Security.TenantEdition.Pro),
             cache, Mock.Of<ILogger<DelegatedAdminService>>())
         { CallBase = false };
         delegatedAdminMock.Setup(x => x.GetScopeAsync(It.IsAny<string>(), It.IsAny<string?>()))
@@ -76,6 +77,7 @@ public class AuthFunctionSideEffectTests
         { CallBase = false };
 
         _metricsRepoMock = new Mock<IMetricsRepository>();
+        _autoApproveEnqueuerMock = new Mock<AutopilotMonitor.Functions.Services.Activation.ITenantAutoApproveEnqueuer>();
 
         _sut = new AuthFunction(
             Mock.Of<ILogger<AuthFunction>>(),
@@ -87,11 +89,15 @@ public class AuthFunctionSideEffectTests
             previewMock.Object,
             _telegramMock.Object,
             _globalNotificationMock.Object,
-            mcpUserMock.Object);
+            mcpUserMock.Object,
+            _autoApproveEnqueuerMock.Object,
+            new AutopilotMonitor.Functions.Security.EntraAppRegistry(
+                new Microsoft.Extensions.Configuration.ConfigurationBuilder().Build(),
+                Mock.Of<ILogger<AutopilotMonitor.Functions.Security.EntraAppRegistry>>()));
 
         // Default: all fire-and-forget calls succeed
         _tenantConfigMock
-            .Setup(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()))
+            .Setup(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()))
             .Returns(Task.CompletedTask);
         _telegramMock
             .Setup(x => x.SendNewTenantSignupAsync(It.IsAny<string>(), It.IsAny<string>()))
@@ -126,12 +132,89 @@ public class AuthFunctionSideEffectTests
         // OnboardedBy is the immutable copy of the first-login UPN that auto-promote on
         // preview approval reads — UpdatedBy may later be clobbered by background syncs.
         Assert.Equal(Upn, config.OnboardedBy);
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(config), Times.Once);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(config, It.IsAny<string?>(), It.IsAny<string?>()), Times.Once);
         _telegramMock.Verify(x => x.SendNewTenantSignupAsync(TenantId, Upn), Times.Once);
         _globalNotificationMock.Verify(x => x.CreateNotificationAsync(
-            "preview_signup", "New Preview Signup",
+            "preview_signup", "New Tenant Signup",
             It.Is<string>(m => m.Contains(TenantId) && m.Contains("contoso.com") && m.Contains(Upn)),
             $"/admin/tenants/management?tenantId={TenantId}"), Times.Once);
+        // Signup enqueues the delayed auto-approve unconditionally — the worker is the
+        // decision point (flag check at processing time).
+        _autoApproveEnqueuerMock.Verify(x => x.EnqueueAsync(
+            It.Is<AutopilotMonitor.Functions.Services.Activation.TenantAutoApproveEnvelope>(
+                e => e.TenantId == TenantId && e.SignupUpn == Upn),
+            AutopilotMonitor.Functions.Services.Activation.TenantAutoApproveEnvelope.ActivationDelay,
+            It.IsAny<CancellationToken>()), Times.Once);
+    }
+
+    // -------------------------------------------------------------------------
+    // HandleAuthClientIdTrackingAsync — the write must mutate a cache-BYPASSING
+    // read, never the (possibly stale) cached view. Regression for the prod
+    // incident 2026-07-31: the login right after an app-homing flip carries the
+    // changed audience; blind-saving the stale cached entity reverted the flip.
+    // -------------------------------------------------------------------------
+
+    private const string LegacyAppId = "1a400946-62c1-4ab4-aa37-f730ac89704d";
+    private const string PrimaryAppId = "886ab5e2-6144-442c-80cc-9b28e0667731";
+
+    [Fact]
+    public async Task HandleAuthClientIdTracking_MutatesFreshConfig_PreservingConcurrentHomingFlip()
+    {
+        // Cached view: pre-flip (homing null, last-seen legacy). Fresh row: flipped meanwhile.
+        var cached = DefaultConfig();
+        cached.DomainName = "contoso.com";
+        cached.LastAuthClientId = LegacyAppId;
+        cached.HomedAppClientId = null;
+
+        var fresh = DefaultConfig();
+        fresh.DomainName = "contoso.com";
+        fresh.LastAuthClientId = LegacyAppId;
+        fresh.HomedAppClientId = PrimaryAppId; // the concurrent flip that must survive
+
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId)).ReturnsAsync(fresh);
+
+        await _sut.HandleAuthClientIdTrackingAsync(cached, TenantId, $"api://{PrimaryAppId}");
+
+        // The FRESH entity was mutated and saved — the flip survives, the stale view is discarded.
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(fresh, It.IsAny<string?>(), It.IsAny<string?>()), Times.Once);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(cached, It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+        Assert.Equal(PrimaryAppId, fresh.HomedAppClientId);
+        Assert.Equal(PrimaryAppId, fresh.LastAuthClientId);
+        Assert.NotNull(fresh.LastAuthClientIdSince);
+    }
+
+    [Fact]
+    public async Task HandleAuthClientIdTracking_FreshAlreadyCurrent_DoesNotWrite()
+    {
+        // Another instance already recorded the new client id — the fresh re-check must
+        // suppress the redundant write even though the cached view still looks outdated.
+        var cached = DefaultConfig();
+        cached.DomainName = "contoso.com";
+        cached.LastAuthClientId = LegacyAppId;
+
+        var fresh = DefaultConfig();
+        fresh.DomainName = "contoso.com";
+        fresh.LastAuthClientId = PrimaryAppId;
+
+        _tenantConfigMock.Setup(x => x.GetConfigurationFreshAsync(TenantId)).ReturnsAsync(fresh);
+
+        await _sut.HandleAuthClientIdTrackingAsync(cached, TenantId, PrimaryAppId);
+
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task HandleAuthClientIdTracking_UnchangedOnCachedView_SkipsFreshRead()
+    {
+        // Steady state (same app as last time) must stay a zero-I/O no-op.
+        var cached = DefaultConfig();
+        cached.DomainName = "contoso.com";
+        cached.LastAuthClientId = PrimaryAppId;
+
+        await _sut.HandleAuthClientIdTrackingAsync(cached, TenantId, $"api://{PrimaryAppId}");
+
+        _tenantConfigMock.Verify(x => x.GetConfigurationFreshAsync(It.IsAny<string>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 
     [Fact]
@@ -156,7 +239,7 @@ public class AuthFunctionSideEffectTests
 
         await _sut.HandleNewTenantDomainAsync(config, TenantId, Upn);
 
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
         _telegramMock.Verify(x => x.SendNewTenantSignupAsync(It.IsAny<string>(), It.IsAny<string>()), Times.Never);
     }
 
@@ -168,7 +251,7 @@ public class AuthFunctionSideEffectTests
 
         await _sut.HandleNewTenantDomainAsync(config, TenantId, "");
 
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 
     [Fact]
@@ -179,7 +262,7 @@ public class AuthFunctionSideEffectTests
 
         await _sut.HandleNewTenantDomainAsync(config, TenantId, "nodomain");
 
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 
     [Fact]
@@ -196,7 +279,7 @@ public class AuthFunctionSideEffectTests
         await _sut.HandleNewTenantDomainAsync(config, TenantId, Upn);
 
         // SaveConfig should still have been called before the fire-and-forget
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(config), Times.Once);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(config, It.IsAny<string?>(), It.IsAny<string?>()), Times.Once);
     }
 
     // -------------------------------------------------------------------------
@@ -217,7 +300,7 @@ public class AuthFunctionSideEffectTests
         Assert.Null(config.DisabledReason);
         Assert.Null(config.DisabledUntil);
         Assert.Equal("System (auto-re-enable)", config.UpdatedBy);
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(config), Times.Once);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(config, It.IsAny<string?>(), It.IsAny<string?>()), Times.Once);
     }
 
     [Fact]
@@ -230,7 +313,7 @@ public class AuthFunctionSideEffectTests
         await _sut.HandleAutoReEnableAsync(config, TenantId);
 
         Assert.True(config.Disabled);
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 
     [Fact]
@@ -241,7 +324,7 @@ public class AuthFunctionSideEffectTests
 
         await _sut.HandleAutoReEnableAsync(config, TenantId);
 
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 
     [Fact]
@@ -254,7 +337,7 @@ public class AuthFunctionSideEffectTests
         await _sut.HandleAutoReEnableAsync(config, TenantId);
 
         Assert.True(config.Disabled);
-        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>()), Times.Never);
+        _tenantConfigMock.Verify(x => x.SaveConfigurationAsync(It.IsAny<TenantConfiguration>(), It.IsAny<string?>(), It.IsAny<string?>()), Times.Never);
     }
 
     // -------------------------------------------------------------------------

src/Backend/AutopilotMonitor.Functions.Tests/AuthFunctionTests.cs

@@ -223,11 +223,11 @@ public class AuthFunctionTests
     }
 
     // -------------------------------------------------------------------------
-    // Gate 2: Preview Gate
+    // Gate 2: Activation Gate
     // -------------------------------------------------------------------------
 
     [Fact]
-    public void PreviewGate_NotApproved_Returns403PrivatePreview()
+    public void PreviewGate_NotApproved_Returns403PendingActivation()
     {
         var result = AuthFunction.BuildAuthResult(
             DefaultConfig(), isGlobalAdmin: false, isGlobalReader: false, isPreviewApproved: false,
@@ -238,7 +238,7 @@ public class AuthFunctionTests
         Assert.False(result.IsSuccess);
         Assert.Equal(HttpStatusCode.Forbidden, result.StatusCode);
         var body = ToDynamic(result.Body);
-        Assert.Equal("PrivatePreview", (string)body.error);
+        Assert.Equal("PendingActivation", (string)body.error);
     }
 
     [Fact]

src/Backend/AutopilotMonitor.Functions.Tests/AuthenticationMiddlewareTokenValidationTests.cs

@@ -203,6 +203,38 @@ public class AuthenticationMiddlewareTokenValidationTests
             Mint(RsaCreds, audience: "api://some-third-app"), ClientId, SecondaryClientId));
     }
 
+    // ── Dual app-reg window (C4A8 move): primary=new app, legacy=old app via LegacyClientId ──
+    // The middleware folds EntraId:LegacyClientId into the additional-id set via
+    // CombineAdditionalClientIdSources, so both apps' tokens validate in bare AND api:// form.
+
+    private const string NewAppId = "886ab5e2-6144-442c-80cc-9b28e0667731";
+    private const string OldAppId = "1a400946-62c1-4ab4-aa37-f730ac89704d";
+
+    [Theory]
+    [InlineData(NewAppId)]
+    [InlineData("api://" + NewAppId)]
+    [InlineData(OldAppId)]
+    [InlineData("api://" + OldAppId)]
+    public void DualAppWindow_accepts_both_apps_tokens_in_both_audience_forms(string audience)
+    {
+        var clientIds = AuthenticationMiddleware.ResolveConfiguredClientIds(
+            NewAppId,
+            AuthenticationMiddleware.CombineAdditionalClientIdSources(OldAppId, null),
+            out _);
+
+        Assert.NotNull(ValidateWith(Mint(RsaCreds, audience: audience), clientIds));
+    }
+
+    [Fact]
+    public void CombineAdditionalClientIdSources_joins_and_skips_empty_sources()
+    {
+        Assert.Equal($"{OldAppId},{SecondaryClientId}",
+            AuthenticationMiddleware.CombineAdditionalClientIdSources(OldAppId, SecondaryClientId));
+        Assert.Equal(OldAppId,
+            AuthenticationMiddleware.CombineAdditionalClientIdSources($"  {OldAppId} ", null, ""));
+        Assert.Null(AuthenticationMiddleware.CombineAdditionalClientIdSources(null, "", "   "));
+    }
+
     // ── BuildValidAudiences: id → {id, api://id}, deduped, empties dropped ────────────────
 
     [Fact]

src/Backend/AutopilotMonitor.Functions.Tests/CloudPcDeviceValidatorTests.cs

@@ -0,0 +1,117 @@
+using AutopilotMonitor.Functions.Security;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Tests for <see cref="CloudPcDeviceValidator"/> — focused on pure-function pieces:
+/// JSON-to-DTO mapping (incl. exact-match guard on managedDeviceId) and cache key shape.
+/// The HTTP/cache/retry resilience is mirrored 1:1 from <c>AutopilotDeviceValidator</c>;
+/// behavioural drift would surface here. Response shapes match a real
+/// virtualEndpoint/cloudPCs payload (field-captured 2026-08-06 on a W365 tenant).
+/// </summary>
+public class CloudPcDeviceValidatorTests
+{
+    private const string TenantId = "11111111-1111-1111-1111-111111111111";
+    private const string DeviceId = "07623d56-1e77-4948-bff5-5bdac8167560";
+
+    // -- BuildCacheKey --
+
+    [Fact]
+    public void BuildCacheKey_StableShape()
+    {
+        var key = CloudPcDeviceValidator.BuildCacheKey(TenantId, DeviceId);
+        Assert.Equal($"cloudpc-device-validation:{TenantId}:{DeviceId}", key);
+    }
+
+    [Fact]
+    public void BuildCacheKey_DistinctFromOtherValidatorKeys()
+    {
+        // The validators must NOT share cache keys; otherwise a positive hit in one
+        // would incorrectly satisfy a lookup in another.
+        var key = CloudPcDeviceValidator.BuildCacheKey(TenantId, DeviceId);
+        Assert.StartsWith("cloudpc-device-validation:", key);
+        Assert.DoesNotContain("autopilot", key);
+        Assert.DoesNotContain("device-association", key);
+    }
+
+    // -- ParseCloudPcResponse: empty / missing / malformed --
+
+    [Fact]
+    public void Parse_EmptyValueArray_NotFound()
+    {
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse("{\"value\":[]}", DeviceId);
+        Assert.False(result.IsValid);
+        Assert.False(result.IsTransient);
+        Assert.Equal(DeviceId, result.IntuneDeviceId);
+        Assert.Contains("not a Windows 365 Cloud PC", result.ErrorMessage);
+    }
+
+    [Fact]
+    public void Parse_MissingValueProperty_NotFound()
+    {
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse("{}", DeviceId);
+        Assert.False(result.IsValid);
+    }
+
+    [Fact]
+    public void Parse_MalformedJson_NotFound_NotTransient()
+    {
+        // Defensive: bad payload is treated as "not a Cloud PC", not as a transient
+        // — transient handling is only triggered by HTTP-level failures.
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse("this is not json", DeviceId);
+        Assert.False(result.IsValid);
+        Assert.False(result.IsTransient);
+    }
+
+    // -- ParseCloudPcResponse: exact-match guard --
+
+    [Fact]
+    public void Parse_DifferentManagedDeviceId_NotFound()
+    {
+        // Guards against widened filter semantics: even if Graph returns Cloud PCs whose
+        // managedDeviceId does not exactly match the queried id, we must reject.
+        var body = "{\"value\":[{\"id\":\"423a1fb4-6033-4b69-a31f-e7f3f54194dc\",\"managedDeviceId\":\"99999999-9999-9999-9999-999999999999\"}]}";
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse(body, DeviceId);
+        Assert.False(result.IsValid);
+    }
+
+    [Fact]
+    public void Parse_ExactMatch_PopulatesAllFields()
+    {
+        var body = $@"{{
+            ""value"":[{{
+                ""id"":""423a1fb4-6033-4b69-a31f-e7f3f54194dc"",
+                ""displayName"":""GKT-CloudPC - Obi-Wan Kenobi"",
+                ""managedDeviceId"":""{DeviceId}"",
+                ""managedDeviceName"":""CPC-cloud-AY5HT"",
+                ""userPrincipalName"":""cloudadmin@gktatooine.net"",
+                ""servicePlanName"":""Cloud PC Enterprise 2vCPU/4GB/128GB""
+            }}]
+        }}";
+
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse(body, DeviceId);
+
+        Assert.True(result.IsValid);
+        Assert.False(result.IsTransient);
+        Assert.Equal(DeviceId, result.IntuneDeviceId);
+        Assert.Equal("423a1fb4-6033-4b69-a31f-e7f3f54194dc", result.CloudPcId);
+        Assert.Equal("CPC-cloud-AY5HT", result.ManagedDeviceName);
+        Assert.Equal("Cloud PC Enterprise 2vCPU/4GB/128GB", result.ServicePlanName);
+    }
+
+    [Fact]
+    public void Parse_CaseInsensitiveIdMatch()
+    {
+        var body = $@"{{""value"":[{{""id"":""423a1fb4-6033-4b69-a31f-e7f3f54194dc"",""managedDeviceId"":""{DeviceId.ToUpperInvariant()}""}}]}}";
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse(body, DeviceId);
+        Assert.True(result.IsValid);
+    }
+
+    [Fact]
+    public void Parse_TrimsWhitespace_OnGraphIdBeforeMatching()
+    {
+        var body = $@"{{""value"":[{{""id"":""423a1fb4-6033-4b69-a31f-e7f3f54194dc"",""managedDeviceId"":""  {DeviceId}  ""}}]}}";
+        var result = CloudPcDeviceValidator.ParseCloudPcResponse(body, DeviceId);
+        Assert.True(result.IsValid);
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/ConfigBackupHookTests.cs

@@ -0,0 +1,244 @@
+using System;
+using System.Collections.Generic;
+using System.Threading;
+using System.Threading.Tasks;
+using AutopilotMonitor.Functions.DataAccess.TableStorage;
+using AutopilotMonitor.Functions.Services;
+using AutopilotMonitor.Shared;
+using AutopilotMonitor.Shared.DataAccess;
+using AutopilotMonitor.Shared.Models;
+using Azure;
+using Azure.Data.Tables;
+using Microsoft.Extensions.Logging.Abstractions;
+using Moq;
+using Xunit;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// The universal pre-write snapshot hook in <see cref="TableConfigRepository"/>:
+/// every overwriting save of a TenantConfiguration/AdminConfiguration row must first
+/// snapshot the stored row into ConfigurationBackups — except row creations and
+/// noise-only changes — and a backup-storage failure must never break the save (fail-soft).
+/// </summary>
+public class ConfigBackupHookTests
+{
+    private const string TenantId = "11111111-1111-1111-1111-111111111111";
+
+    private sealed class Harness
+    {
+        public TableConfigRepository Sut { get; }
+        public Mock<TableClient> Table { get; } = new();
+        public Mock<IConfigBackupRepository> Backup { get; } = new();
+        public List<TableEntity> Upserts { get; } = new();
+
+        public Harness(TableEntity? stored)
+        {
+            if (stored == null)
+            {
+                Table.Setup(c => c.GetEntityAsync<TableEntity>(
+                        It.IsAny<string>(), It.IsAny<string>(),
+                        It.IsAny<IEnumerable<string>>(), It.IsAny<CancellationToken>()))
+                    .ThrowsAsync(new RequestFailedException(404, "Not Found", "ResourceNotFound", null));
+            }
+            else
+            {
+                Table.Setup(c => c.GetEntityAsync<TableEntity>(
+                        It.IsAny<string>(), It.IsAny<string>(),
+                        It.IsAny<IEnumerable<string>>(), It.IsAny<CancellationToken>()))
+                    .ReturnsAsync(Response.FromValue(stored, Mock.Of<Response>()));
+            }
+
+            Table.Setup(c => c.UpsertEntityAsync(
+                    It.IsAny<TableEntity>(), It.IsAny<TableUpdateMode>(), It.IsAny<CancellationToken>()))
+                .Returns<TableEntity, TableUpdateMode, CancellationToken>((e, _, _) =>
+                {
+                    Upserts.Add(e);
+                    return Task.FromResult(Mock.Of<Response>());
+                });
+
+            var serviceClient = new Mock<TableServiceClient>();
+            serviceClient.Setup(c => c.GetTableClient(It.IsAny<string>())).Returns(Table.Object);
+
+            Sut = new TableConfigRepository(
+                new TableStorageService(serviceClient.Object, NullLogger<TableStorageService>.Instance),
+                Backup.Object,
+                NullLogger<TableConfigRepository>.Instance);
+        }
+    }
+
+    private static TenantConfiguration StoredConfig()
+    {
+        var config = TenantConfiguration.CreateDefault(TenantId);
+        config.DomainName = "contoso.com";
+        config.UpdatedBy = "admin@contoso.com";
+        config.DataRetentionDays = 30;
+        config.TeamsWebhookUrl = "https://contoso.webhook.office.com/hook";
+        return config;
+    }
+
+    /// <summary>
+    /// Mirrors production: every real writer round-trips the STORED row (read-modify-write),
+    /// so time-stamped fields like OnboardedAt match the stored values exactly. Constructing
+    /// a second CreateDefault instead would fabricate an OnboardedAt diff that cannot occur.
+    /// </summary>
+    private static TenantConfiguration RoundtripClone(TenantConfiguration stored)
+        => TableConfigRepository.ConvertFromTenantTableEntity(
+            TableConfigRepository.ConvertToTenantTableEntity(stored));
+
+    [Fact]
+    public async Task RealChange_SnapshotsStoredRow_ThenSaves_ThenPrunes()
+    {
+        var stored = StoredConfig();
+        var harness = new Harness(TableConfigRepository.ConvertToTenantTableEntity(stored));
+
+        var incoming = RoundtripClone(stored);
+        incoming.DataRetentionDays = 90;
+        incoming.UpdatedBy = "ga@operator.example";
+
+        ConfigBackupEntry? snapshot = null;
+        harness.Backup
+            .Setup(b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()))
+            .Callback<ConfigBackupEntry, CancellationToken>((e, _) => snapshot = e)
+            .Returns(Task.CompletedTask);
+
+        var saved = await harness.Sut.SaveTenantConfigurationAsync(incoming, "portal-put", "test change");
+
+        Assert.True(saved);
+        Assert.Single(harness.Upserts); // the config row itself
+        Assert.NotNull(snapshot);
+        Assert.Equal(TenantId, snapshot!.PartitionKey);
+        Assert.Equal("portal-put", snapshot.Source);
+        Assert.Equal("test change", snapshot.Reason);
+        Assert.Equal("ga@operator.example", snapshot.ChangedBy); // identity about to write
+        // The snapshot holds the STORED row (retention 30), not the incoming one.
+        Assert.Contains("\"DataRetentionDays\":30", snapshot.EntityJson);
+        // Raw secrets ARE in EntityJson (full-fidelity restore source)…
+        Assert.Contains("contoso.webhook.office.com", snapshot.EntityJson);
+        // …but the advisory diff masks them by property-name heuristics (ConfigDiffHelper).
+        Assert.DoesNotContain("contoso.webhook.office.com", snapshot.DiffJson ?? string.Empty);
+        harness.Backup.Verify(
+            b => b.PruneAsync(TenantId, Constants.ConfigBackupKeepCount, It.IsAny<CancellationToken>()),
+            Times.Once);
+    }
+
+    [Fact]
+    public async Task RowCreation_NoExistingRow_NoSnapshot()
+    {
+        var harness = new Harness(stored: null);
+
+        var saved = await harness.Sut.SaveTenantConfigurationAsync(StoredConfig(), "portal-put", null);
+
+        Assert.True(saved);
+        Assert.Single(harness.Upserts);
+        harness.Backup.Verify(
+            b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()), Times.Never);
+        harness.Backup.Verify(
+            b => b.PruneAsync(It.IsAny<string>(), It.IsAny<int>(), It.IsAny<CancellationToken>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task NoiseOnlyChange_AuthClientIdFlip_NoSnapshot()
+    {
+        var stored = StoredConfig();
+        var harness = new Harness(TableConfigRepository.ConvertToTenantTableEntity(stored));
+
+        // The auth-side-effect write: only LastAuthClientId/Since + bookkeeping move.
+        var incoming = RoundtripClone(stored);
+        incoming.LastAuthClientId = "886ab5e2-6144-442c-80cc-9b28e0667731";
+        incoming.LastAuthClientIdSince = DateTime.UtcNow;
+        incoming.LastUpdated = DateTime.UtcNow;
+        incoming.UpdatedBy = "System (auth)";
+
+        var saved = await harness.Sut.SaveTenantConfigurationAsync(incoming, "auth", null);
+
+        Assert.True(saved); // the save itself still goes through
+        Assert.Single(harness.Upserts);
+        harness.Backup.Verify(
+            b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task NoOpSave_IdenticalContent_NoSnapshot()
+    {
+        var stored = StoredConfig();
+        var harness = new Harness(TableConfigRepository.ConvertToTenantTableEntity(stored));
+
+        var saved = await harness.Sut.SaveTenantConfigurationAsync(RoundtripClone(stored), "portal-put", null);
+
+        Assert.True(saved);
+        harness.Backup.Verify(
+            b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()), Times.Never);
+    }
+
+    [Fact]
+    public async Task BackupStorageFailure_IsFailSoft_SaveStillSucceeds()
+    {
+        var stored = StoredConfig();
+        var harness = new Harness(TableConfigRepository.ConvertToTenantTableEntity(stored));
+        harness.Backup
+            .Setup(b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()))
+            .ThrowsAsync(new RequestFailedException(503, "backup table throttled"));
+
+        var incoming = RoundtripClone(stored);
+        incoming.DataRetentionDays = 90;
+
+        var saved = await harness.Sut.SaveTenantConfigurationAsync(incoming, "portal-put", null);
+
+        Assert.True(saved);
+        Assert.Single(harness.Upserts); // the config write went through regardless
+    }
+
+    [Fact]
+    public async Task LegacyOneArgOverload_StillSnapshots_WithUnknownSource()
+    {
+        var stored = StoredConfig();
+        var harness = new Harness(TableConfigRepository.ConvertToTenantTableEntity(stored));
+
+        ConfigBackupEntry? snapshot = null;
+        harness.Backup
+            .Setup(b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()))
+            .Callback<ConfigBackupEntry, CancellationToken>((e, _) => snapshot = e)
+            .Returns(Task.CompletedTask);
+
+        var incoming = RoundtripClone(stored);
+        incoming.DataRetentionDays = 90;
+        await harness.Sut.SaveTenantConfigurationAsync(incoming);
+
+        Assert.NotNull(snapshot);
+        Assert.Equal("unknown", snapshot!.Source);
+    }
+
+    [Fact]
+    public async Task AdminConfigSave_SnapshotsUnderGlobalConfigPartition()
+    {
+        var stored = new AdminConfiguration
+        {
+            UpdatedBy = "ga@operator.example",
+            GlobalRateLimitRequestsPerMinute = 100,
+        };
+        var harness = new Harness(TableConfigRepository.ConvertToAdminTableEntity(stored));
+
+        ConfigBackupEntry? snapshot = null;
+        harness.Backup
+            .Setup(b => b.UpsertAsync(It.IsAny<ConfigBackupEntry>(), It.IsAny<CancellationToken>()))
+            .Callback<ConfigBackupEntry, CancellationToken>((e, _) => snapshot = e)
+            .Returns(Task.CompletedTask);
+
+        var incoming = new AdminConfiguration
+        {
+            UpdatedBy = "ga@operator.example",
+            GlobalRateLimitRequestsPerMinute = 200,
+        };
+
+        var saved = await harness.Sut.SaveAdminConfigurationAsync(incoming);
+
+        Assert.True(saved);
+        Assert.NotNull(snapshot);
+        Assert.Equal("GlobalConfig", snapshot!.PartitionKey);
+        Assert.Equal("admin-config", snapshot.Source);
+        harness.Backup.Verify(
+            b => b.PruneAsync("GlobalConfig", Constants.ConfigBackupKeepCount, It.IsAny<CancellationToken>()),
+            Times.Once);
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/ConfigBackupRepositoryTests.cs

@@ -0,0 +1,172 @@
+using System;
+using System.Collections.Generic;
+using System.Linq;
+using System.Threading;
+using System.Threading.Tasks;
+using AutopilotMonitor.Functions.DataAccess.TableStorage;
+using AutopilotMonitor.Functions.Services;
+using AutopilotMonitor.Shared.Models;
+using Azure;
+using Azure.Data.Tables;
+using Microsoft.Extensions.Logging.Abstractions;
+using Moq;
+using Xunit;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// TableConfigBackupRepository: Store↔Map roundtrip (project rule "table-serialization"),
+/// reverse-ticks RowKey ordering (newest-first), and prune-beyond-keep semantics.
+/// </summary>
+public class ConfigBackupRepositoryTests
+{
+    private const string TenantId = "11111111-1111-1111-1111-111111111111";
+
+    private sealed class Harness
+    {
+        public TableConfigBackupRepository Sut { get; }
+        public Mock<TableClient> Table { get; } = new();
+        public List<TableEntity> Upserts { get; } = new();
+        public List<(string Pk, string Rk)> Deletes { get; } = new();
+
+        public Harness()
+        {
+            Table.Setup(c => c.UpsertEntityAsync(
+                    It.IsAny<TableEntity>(), It.IsAny<TableUpdateMode>(), It.IsAny<CancellationToken>()))
+                .Returns<TableEntity, TableUpdateMode, CancellationToken>((e, _, _) =>
+                {
+                    Upserts.Add(e);
+                    return Task.FromResult(Mock.Of<Response>());
+                });
+            Table.Setup(c => c.DeleteEntityAsync(
+                    It.IsAny<string>(), It.IsAny<string>(), It.IsAny<ETag>(), It.IsAny<CancellationToken>()))
+                .Returns<string, string, ETag, CancellationToken>((pk, rk, _, _) =>
+                {
+                    Deletes.Add((pk, rk));
+                    return Task.FromResult(Mock.Of<Response>());
+                });
+
+            var serviceClient = new Mock<TableServiceClient>();
+            serviceClient.Setup(c => c.GetTableClient(It.IsAny<string>())).Returns(Table.Object);
+            Sut = new TableConfigBackupRepository(
+                new TableStorageService(serviceClient.Object, NullLogger<TableStorageService>.Instance),
+                NullLogger<TableConfigBackupRepository>.Instance);
+        }
+
+        public void SetupQuery(params TableEntity[] rows)
+        {
+            var page = Page<TableEntity>.FromValues(rows, continuationToken: null, Mock.Of<Response>());
+            Table.Setup(c => c.QueryAsync<TableEntity>(
+                    It.IsAny<string>(), It.IsAny<int?>(), It.IsAny<IEnumerable<string>>(), It.IsAny<CancellationToken>()))
+                .Returns(AsyncPageable<TableEntity>.FromPages(new[] { page }));
+        }
+    }
+
+    private static ConfigBackupEntry Entry(string rowKey = "0001_abc") => new()
+    {
+        PartitionKey = TenantId,
+        RowKey = rowKey,
+        TenantId = TenantId,
+        EntityJson = "{\"DomainName\":\"contoso.com\"}",
+        ChangedBy = "ga@operator.example",
+        Source = "mcp-patch",
+        Reason = "retention bump",
+        DiffJson = "{\"DataRetentionDays\":\"30 \\u2192 90\"}",
+        BackupTakenAt = new DateTime(2026, 8, 3, 12, 0, 0, DateTimeKind.Utc),
+    };
+
+    [Fact]
+    public async Task Roundtrip_StoreAndMap_PreservesEveryField()
+    {
+        var harness = new Harness();
+        var entry = Entry();
+
+        await harness.Sut.UpsertAsync(entry);
+        var stored = Assert.Single(harness.Upserts);
+
+        // Feed the stored entity back through the read path (TryGetAsync → Map).
+        harness.Table.Setup(c => c.GetEntityAsync<TableEntity>(
+                It.IsAny<string>(), It.IsAny<string>(),
+                It.IsAny<IEnumerable<string>>(), It.IsAny<CancellationToken>()))
+            .ReturnsAsync(Response.FromValue(stored, Mock.Of<Response>()));
+        var mapped = await harness.Sut.TryGetAsync(TenantId, entry.RowKey);
+
+        Assert.NotNull(mapped);
+        Assert.Equal(entry.PartitionKey, mapped!.PartitionKey);
+        Assert.Equal(entry.RowKey, mapped.RowKey);
+        Assert.Equal(entry.TenantId, mapped.TenantId);
+        Assert.Equal(entry.EntityJson, mapped.EntityJson);
+        Assert.Equal(entry.ChangedBy, mapped.ChangedBy);
+        Assert.Equal(entry.Source, mapped.Source);
+        Assert.Equal(entry.Reason, mapped.Reason);
+        Assert.Equal(entry.DiffJson, mapped.DiffJson);
+        Assert.Equal(entry.BackupTakenAt, mapped.BackupTakenAt);
+    }
+
+    [Fact]
+    public void BuildRowKey_LaterTimestamps_SortFirst()
+    {
+        var earlier = TableConfigBackupRepository.BuildRowKey(new DateTime(2026, 8, 3, 12, 0, 0, DateTimeKind.Utc));
+        var later = TableConfigBackupRepository.BuildRowKey(new DateTime(2026, 8, 3, 12, 0, 1, DateTimeKind.Utc));
+
+        // Reverse ticks: the LATER backup gets the LEXICOGRAPHICALLY SMALLER RowKey, so
+        // Azure's RowKey-ascending partition scan returns newest-first.
+        Assert.True(string.CompareOrdinal(later, earlier) < 0);
+    }
+
+    [Fact]
+    public void BuildRowKey_SameTick_DistinctViaGuidSuffix()
+    {
+        var at = new DateTime(2026, 8, 3, 12, 0, 0, DateTimeKind.Utc);
+        Assert.NotEqual(
+            TableConfigBackupRepository.BuildRowKey(at),
+            TableConfigBackupRepository.BuildRowKey(at));
+    }
+
+    [Fact]
+    public async Task Prune_DeletesEverythingBeyondKeep_InScanOrder()
+    {
+        var harness = new Harness();
+        // Scan order = RowKey ascending = newest first (reverse ticks). keep=2 must
+        // delete rows 3 and 4, never the two newest.
+        harness.SetupQuery(
+            new TableEntity(TenantId, "0001_newest"),
+            new TableEntity(TenantId, "0002_second"),
+            new TableEntity(TenantId, "0003_old"),
+            new TableEntity(TenantId, "0004_oldest"));
+
+        var deleted = await harness.Sut.PruneAsync(TenantId, keep: 2);
+
+        Assert.Equal(2, deleted);
+        Assert.Equal(new[] { "0003_old", "0004_oldest" }, harness.Deletes.Select(d => d.Rk).ToArray());
+    }
+
+    [Fact]
+    public async Task Prune_WithinKeep_DeletesNothing()
+    {
+        var harness = new Harness();
+        harness.SetupQuery(
+            new TableEntity(TenantId, "0001_newest"),
+            new TableEntity(TenantId, "0002_second"));
+
+        var deleted = await harness.Sut.PruneAsync(TenantId, keep: 2);
+
+        Assert.Equal(0, deleted);
+        Assert.Empty(harness.Deletes);
+    }
+
+    [Fact]
+    public async Task ListByPartition_CapsAtMax()
+    {
+        var harness = new Harness();
+        harness.SetupQuery(
+            new TableEntity(TenantId, "0001"),
+            new TableEntity(TenantId, "0002"),
+            new TableEntity(TenantId, "0003"));
+
+        var listed = await harness.Sut.ListByPartitionAsync(TenantId, max: 2);
+
+        Assert.Equal(2, listed.Count);
+        Assert.Equal("0001", listed[0].RowKey);
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/ConfigRedactionTests.cs

@@ -192,4 +192,37 @@ public class ConfigRedactionTests
         // Operator/Viewer arrives with IsTenantAdmin=false ⇒ always the redacted copy.
         => Assert.False(GetTenantConfigurationFunction.CanViewSecrets(
             new RequestContext { UserRole = role, TenantId = TenantA, TargetTenantId = TenantA }));
+
+    // ── ?view=redacted opt-in (MCP get_tenant_config): forces redaction even for GA ──
+
+    [Fact]
+    public void ShouldRedact_GlobalAdmin_ViewRedacted_True()
+        => Assert.True(GetTenantConfigurationFunction.ShouldRedact(
+            new RequestContext { IsGlobalAdmin = true, TenantId = TenantA, TargetTenantId = TenantB },
+            "?view=redacted"));
+
+    [Fact]
+    public void ShouldRedact_OwnTenantAdmin_ViewRedacted_True()
+        => Assert.True(GetTenantConfigurationFunction.ShouldRedact(
+            new RequestContext { IsTenantAdmin = true, TenantId = TenantA, TargetTenantId = TenantA },
+            "?view=redacted"));
+
+    [Fact]
+    public void ShouldRedact_GlobalAdmin_NoParam_False()
+        // Without the opt-in the GA clearance stands — the portal Settings UI depends on it.
+        => Assert.False(GetTenantConfigurationFunction.ShouldRedact(
+            new RequestContext { IsGlobalAdmin = true, TenantId = TenantA, TargetTenantId = TenantB },
+            ""));
+
+    [Fact]
+    public void ShouldRedact_GlobalAdmin_OtherViewValue_False()
+        => Assert.False(GetTenantConfigurationFunction.ShouldRedact(
+            new RequestContext { IsGlobalAdmin = true, TenantId = TenantA, TargetTenantId = TenantB },
+            "?view=full"));
+
+    [Fact]
+    public void ShouldRedact_ReaderWithoutClearance_AlwaysTrue_RegardlessOfParam()
+        => Assert.True(GetTenantConfigurationFunction.ShouldRedact(
+            new RequestContext { IsGlobalReader = true, TenantId = TenantA, TargetTenantId = TenantB },
+            "?view=full"));
 }

src/Backend/AutopilotMonitor.Functions.Tests/ContinuationTokenTests.cs

@@ -259,20 +259,21 @@ public class ContinuationTokenTests
     public void TryDecode_rejects_token_signed_with_a_different_key()
     {
         // Simulate key rotation: token issued under key A, validated under key B.
-        // (We toggle the test key around the encode/decode pair.)
+        // The scoped (AsyncLocal) override keeps the swap confined to this test's
+        // execution context — mutating the process-wide test key here raced the
+        // concurrently running pagination test classes.
         var keyA = new byte[32]; for (int i = 0; i < keyA.Length; i++) keyA[i] = (byte)(i * 3 + 1);
         var keyB = new byte[32]; for (int i = 0; i < keyB.Length; i++) keyB[i] = (byte)(i * 5 + 7);
 
         var fp = ContinuationToken.ComputeFingerprint(FilterArgsA());
 
-        ContinuationToken.SetSigningKeyForTesting(keyA);
+        ContinuationToken.SetScopedSigningKeyForTesting(keyA);
         var encoded = ContinuationToken.Encode(AzureToken, TenantA, fp);
 
-        ContinuationToken.SetSigningKeyForTesting(keyB);
+        ContinuationToken.SetScopedSigningKeyForTesting(keyB);
         var ok = ContinuationToken.TryDecode(encoded, TenantA, fp, out _, out var reason);
 
-        // Restore the test default before leaving so subsequent tests aren't affected.
-        TestSetup.Initialize();
+        ContinuationToken.SetScopedSigningKeyForTesting(null);
 
         Assert.False(ok);
         Assert.Equal("bad_signature", reason);

src/Backend/AutopilotMonitor.Functions.Tests/CriticalTableBackupServiceTests.cs

@@ -47,7 +47,7 @@ public class CriticalTableBackupServiceTests
 
         Assert.Equal(BackupOutcome.Success, result.Outcome);
         Assert.True(store.ManifestWritten, "manifest must be written LAST");
-        Assert.Equal(16, result.Manifest.Tables.Count);   // critical-tables catalog count (incl. DelegatedAdmins)
+        Assert.Equal(17, result.Manifest.Tables.Count);   // critical-tables catalog count (incl. DelegatedAdmins + ConfigurationBackups)
         Assert.All(result.Manifest.Tables, t =>
             Assert.True(t.Status == TableBackupStatus.Ok || t.Status == TableBackupStatus.Empty));
     }

src/Backend/AutopilotMonitor.Functions.Tests/DelegatedAdminEditionGateTests.cs

@@ -44,7 +44,7 @@ public class DelegatedAdminEditionGateTests
         return new DelegatedAdminService(
             repo.Object,
             new StubTenantEntitlementService(
-                tenantId => tenantId == EnterpriseHomeTenant ? TenantEdition.Enterprise : TenantEdition.Community),
+                tenantId => tenantId == EnterpriseHomeTenant ? TenantEdition.Pro : TenantEdition.Community),
             new MemoryCache(new MemoryCacheOptions()),
             NullLogger<DelegatedAdminService>.Instance);
     }
@@ -118,7 +118,7 @@ public class DelegatedAdminEditionGateTests
         var svc = new DelegatedAdminService(
             repo.Object,
             new StubTenantEntitlementService(
-                tenantId => tenantId == EnterpriseHomeTenant ? TenantEdition.Enterprise : TenantEdition.Community),
+                tenantId => tenantId == EnterpriseHomeTenant ? TenantEdition.Pro : TenantEdition.Community),
             new MemoryCache(new MemoryCacheOptions()),
             NullLogger<DelegatedAdminService>.Instance);
 

src/Backend/AutopilotMonitor.Functions.Tests/DelegatedAdminServiceTests.cs

@@ -36,7 +36,7 @@ public class DelegatedAdminServiceTests
         // the edition filter has its own dedicated tests (DelegatedAdminEditionGateTests).
         var svc = new DelegatedAdminService(
             repo.Object,
-            new StubTenantEntitlementService(AutopilotMonitor.Functions.Security.TenantEdition.Enterprise),
+            new StubTenantEntitlementService(AutopilotMonitor.Functions.Security.TenantEdition.Pro),
             cache,
             NullLogger<DelegatedAdminService>.Instance);
         return (svc, repo);

src/Backend/AutopilotMonitor.Functions.Tests/EntraAppRegistryTests.cs

@@ -0,0 +1,133 @@
+using System.Collections.Generic;
+using AutopilotMonitor.Functions.Security;
+using AutopilotMonitor.Shared.Models;
+using Microsoft.Extensions.Configuration;
+using Microsoft.Extensions.Logging.Abstractions;
+using Xunit;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Resolution matrix for the dual app-registration window (see EntraAppRegistry):
+/// legacy unconfigured ⇒ always primary (code deploy is a no-op before the config swap);
+/// null homing ⇒ legacy; known ids ⇒ that app; unknown ⇒ primary fallback.
+/// </summary>
+public class EntraAppRegistryTests
+{
+    private const string PrimaryId = "886ab5e2-6144-442c-80cc-9b28e0667731";
+    private const string LegacyId = "1a400946-62c1-4ab4-aa37-f730ac89704d";
+
+    private static EntraAppRegistry Build(Dictionary<string, string?> settings) =>
+        new(new ConfigurationBuilder().AddInMemoryCollection(settings).Build(),
+            NullLogger<EntraAppRegistry>.Instance);
+
+    private static EntraAppRegistry DualApp() => Build(new()
+    {
+        ["EntraId:ClientId"] = PrimaryId,
+        ["EntraId:ClientSecret"] = "primary-secret",
+        ["EntraId:LegacyClientId"] = LegacyId,
+        ["EntraId:LegacyClientSecret"] = "legacy-secret",
+    });
+
+    private static TenantConfiguration Tenant(string? homedAppClientId) => new()
+    {
+        TenantId = "11111111-1111-1111-1111-111111111111",
+        HomedAppClientId = homedAppClientId,
+    };
+
+    [Fact]
+    public void LegacyUnconfigured_AlwaysResolvesPrimary_EvenForNullHoming()
+    {
+        var registry = Build(new()
+        {
+            ["EntraId:ClientId"] = PrimaryId,
+            ["EntraId:ClientSecret"] = "primary-secret",
+        });
+
+        Assert.False(registry.LegacyConfigured);
+        Assert.Equal(PrimaryId, registry.ResolveForTenant(Tenant(null)).ClientId);
+        Assert.Equal(PrimaryId, registry.ResolveForTenant(null).ClientId);
+        Assert.False(registry.ResolveForTenant(Tenant(null)).IsLegacy);
+    }
+
+    [Fact]
+    public void NullHoming_ResolvesLegacy()
+    {
+        var resolved = DualApp().ResolveForTenant(Tenant(null));
+        Assert.True(resolved.IsLegacy);
+        Assert.Equal(LegacyId, resolved.ClientId);
+        Assert.Equal("legacy-secret", resolved.ClientSecret);
+    }
+
+    [Fact]
+    public void MissingConfigRow_ResolvesLegacy_SameAsNullHoming()
+    {
+        Assert.True(DualApp().ResolveForTenant(null).IsLegacy);
+    }
+
+    [Fact]
+    public void PrimaryHoming_ResolvesPrimary_CaseAndBraceInsensitive()
+    {
+        var registry = DualApp();
+        Assert.False(registry.ResolveForTenant(Tenant(PrimaryId)).IsLegacy);
+        Assert.False(registry.ResolveForTenant(Tenant(PrimaryId.ToUpperInvariant())).IsLegacy);
+        Assert.False(registry.ResolveForTenant(Tenant("{" + PrimaryId + "}")).IsLegacy);
+    }
+
+    [Fact]
+    public void LegacyHoming_ResolvesLegacy()
+    {
+        var resolved = DualApp().ResolveForTenant(Tenant(LegacyId));
+        Assert.True(resolved.IsLegacy);
+        Assert.Equal("legacy-secret", resolved.ClientSecret);
+    }
+
+    [Fact]
+    public void UnknownHoming_FallsBackToPrimary()
+    {
+        var resolved = DualApp().ResolveForTenant(Tenant("99999999-9999-9999-9999-999999999999"));
+        Assert.False(resolved.IsLegacy);
+        Assert.Equal(PrimaryId, resolved.ClientId);
+    }
+
+    [Fact]
+    public void MalformedLegacyClientId_TreatedAsUnconfigured()
+    {
+        var registry = Build(new()
+        {
+            ["EntraId:ClientId"] = PrimaryId,
+            ["EntraId:LegacyClientId"] = "not-a-guid",
+            ["EntraId:LegacyClientSecret"] = "legacy-secret",
+        });
+
+        Assert.False(registry.LegacyConfigured);
+        Assert.False(registry.ResolveForTenant(Tenant(null)).IsLegacy);
+    }
+
+    [Theory]
+    [InlineData(PrimaryId, true)]
+    [InlineData("api://" + PrimaryId, true)]
+    [InlineData("API://" + PrimaryId, true)]
+    [InlineData(LegacyId, false)]
+    [InlineData("api://" + LegacyId, false)]
+    [InlineData("https://graph.microsoft.com", false)]
+    [InlineData(null, false)]
+    [InlineData("", false)]
+    public void IsPrimary_MatchesBareAndApiPrefixedAudiences(string? audience, bool expected)
+    {
+        Assert.Equal(expected, DualApp().IsPrimary(audience));
+    }
+
+    [Theory]
+    [InlineData("api://" + LegacyId, LegacyId)]
+    [InlineData(LegacyId, LegacyId)]
+    [InlineData("API://886AB5E2-6144-442C-80CC-9B28E0667731", PrimaryId)]
+    [InlineData("https://graph.microsoft.com", null)] // non-GUID audience must never persist as provenance
+    [InlineData("api://not-a-guid", null)]
+    [InlineData(null, null)]
+    [InlineData("  ", null)]
+    public void NormalizeAudience_StripsApiPrefixAndRequiresGuid(string? audience, string? expected)
+    {
+        Assert.Equal(expected, EntraAppRegistry.NormalizeAudience(audience));
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/FeatureEntitlementCatalogTests.cs

@@ -6,8 +6,9 @@ namespace AutopilotMonitor.Functions.Tests;
 /// <summary>
 /// Pins the edition-resolution matrix and the per-edition entitlement values of
 /// <see cref="FeatureEntitlementCatalog"/>. Fail-closed contract: ONLY the exact tier
-/// "enterprise" (or an active trial) yields Enterprise — legacy stored tiers ("free", "pro"),
-/// null/empty and unknown values all resolve to Community without any data migration.
+/// "pro" / the legacy stored value "enterprise" (or an active trial) yields Pro — the legacy
+/// stored tier "free", null/empty and unknown values all resolve to Community without any
+/// data migration.
 /// </summary>
 public class FeatureEntitlementCatalogTests
 {
@@ -16,31 +17,34 @@ public class FeatureEntitlementCatalogTests
     // ── ResolveEdition matrix ────────────────────────────────────────────────────
 
     [Theory]
-    [InlineData("enterprise")]
+    [InlineData("pro")]
+    [InlineData("Pro")]
+    [InlineData("PRO")]
+    [InlineData(" pro ")]
+    [InlineData("enterprise")] // legacy stored value — must stay readable as Pro
     [InlineData("Enterprise")]
     [InlineData("ENTERPRISE")]
     [InlineData(" enterprise ")]
-    public void ResolveEdition_EnterpriseTier_IsEnterprise(string tier)
+    public void ResolveEdition_ProOrLegacyEnterpriseTier_IsPro(string tier)
     {
-        Assert.Equal(TenantEdition.Enterprise, FeatureEntitlementCatalog.ResolveEdition(tier, null, Now));
+        Assert.Equal(TenantEdition.Pro, FeatureEntitlementCatalog.ResolveEdition(tier, null, Now));
     }
 
     [Theory]
     [InlineData("free")]
-    [InlineData("pro")]
     [InlineData("community")]
     [InlineData("")]
     [InlineData(null)]
     [InlineData("premium")] // unknown value → fail-closed
-    public void ResolveEdition_NonEnterpriseTier_IsCommunity(string? tier)
+    public void ResolveEdition_NonProTier_IsCommunity(string? tier)
     {
         Assert.Equal(TenantEdition.Community, FeatureEntitlementCatalog.ResolveEdition(tier, null, Now));
     }
 
     [Fact]
-    public void ResolveEdition_ActiveTrial_IsEnterprise_EvenOnFreeTier()
+    public void ResolveEdition_ActiveTrial_IsPro_EvenOnFreeTier()
     {
-        Assert.Equal(TenantEdition.Enterprise,
+        Assert.Equal(TenantEdition.Pro,
             FeatureEntitlementCatalog.ResolveEdition("free", Now.AddSeconds(1), Now));
     }
 
@@ -59,11 +63,28 @@ public class FeatureEntitlementCatalogTests
             FeatureEntitlementCatalog.ResolveEdition(null, Now.AddDays(-1), Now));
     }
 
-    [Fact]
-    public void ResolveEdition_ExpiredTrial_ButEnterpriseTier_StaysEnterprise()
+    [Theory]
+    [InlineData("pro")]
+    [InlineData("enterprise")]
+    public void ResolveEdition_ExpiredTrial_ButPermanentProTier_StaysPro(string tier)
     {
-        Assert.Equal(TenantEdition.Enterprise,
-            FeatureEntitlementCatalog.ResolveEdition("enterprise", Now.AddDays(-1), Now));
+        Assert.Equal(TenantEdition.Pro,
+            FeatureEntitlementCatalog.ResolveEdition(tier, Now.AddDays(-1), Now));
+    }
+
+    // ── IsPermanentProTier ───────────────────────────────────────────────────────
+
+    [Theory]
+    [InlineData("pro", true)]
+    [InlineData(" PRO ", true)]
+    [InlineData("enterprise", true)] // legacy stored value
+    [InlineData("free", false)]
+    [InlineData("community", false)]
+    [InlineData("", false)]
+    [InlineData(null, false)]
+    public void IsPermanentProTier_Matrix(string? tier, bool expected)
+    {
+        Assert.Equal(expected, FeatureEntitlementCatalog.IsPermanentProTier(tier));
     }
 
     // ── Entitlement values ───────────────────────────────────────────────────────
@@ -76,20 +97,24 @@ public class FeatureEntitlementCatalogTests
         Assert.Null(e.UserRateLimitPerMinute);
         Assert.Null(e.DeviceRateLimitPerMinute);
         Assert.False(e.DelegatedAdminAllowed);
+        Assert.False(e.BootstrapIncluded);
+        Assert.False(e.UnrestrictedModeAvailable);
         Assert.Equal("community", e.McpUsagePlanName);
         Assert.Equal(100, e.McpDailyRequestLimit);
         Assert.Equal(3000, e.McpMonthlyRequestLimit);
     }
 
     [Fact]
-    public void Enterprise_Entitlements_MatchMatrix()
+    public void Pro_Entitlements_MatchMatrix()
     {
-        var e = FeatureEntitlementCatalog.Get(TenantEdition.Enterprise);
+        var e = FeatureEntitlementCatalog.Get(TenantEdition.Pro);
         Assert.Equal(365, e.RetentionCapDays);
         Assert.Equal(150, e.UserRateLimitPerMinute);
         Assert.Equal(150, e.DeviceRateLimitPerMinute);
         Assert.True(e.DelegatedAdminAllowed);
-        Assert.Equal("enterprise", e.McpUsagePlanName);
+        Assert.True(e.BootstrapIncluded);
+        Assert.True(e.UnrestrictedModeAvailable);
+        Assert.Equal("pro", e.McpUsagePlanName);
         Assert.Equal(1000, e.McpDailyRequestLimit);
         Assert.Equal(20000, e.McpMonthlyRequestLimit);
     }

src/Backend/AutopilotMonitor.Functions.Tests/GatherRuleUpdatePartialMergeTests.cs

@@ -16,7 +16,7 @@ namespace AutopilotMonitor.Functions.Tests;
 public class GatherRuleUpdatePartialMergeTests
 {
     private const string TenantId = "a1b2c3d4-e5f6-7890-abcd-ef1234567890";
-    private const string RuleId = "GATHER-CUST-001";
+    private const string RuleId = "GATHER-CUSTOM-001";
 
     private static GatherRule ExistingCustomRule() => new()
     {

src/Backend/AutopilotMonitor.Functions.Tests/GetDeviceNotRegisteredFunctionTests.cs

@@ -164,12 +164,49 @@ public class GetDeviceNotRegisteredFunctionTests
         Assert.Equal(3, (int)item.attemptCount);
     }
 
+    // =========================================================================
+    // Cloud PC marker aggregation
+    // =========================================================================
+
+    [Fact]
+    public void BuildAggregatedResult_IsCloudPc_StickyTrueAcrossGroup()
+    {
+        // One old agent (no field → false) + one new agent reporting the W365 marker:
+        // the aggregate must say Cloud PC even though the MOST RECENT report is false —
+        // same OR semantics as the Sessions-table IsCloudPc merge.
+        var reports = new List<DistressReportEntry>
+        {
+            MakeEntry("DeviceNotRegistered", "Microsoft Corporation", "Virtual Machine", "SN1", T0, isCloudPc: true),
+            MakeEntry("DeviceNotRegistered", "Microsoft Corporation", "Virtual Machine", "SN1", T0.AddMinutes(5), isCloudPc: false),
+        };
+
+        var (aggregated, _) = GetDeviceNotRegisteredFunction.BuildAggregatedResult(reports);
+
+        var item = ToDynamic(aggregated[0]);
+        Assert.True((bool)item.isCloudPc);
+    }
+
+    [Fact]
+    public void BuildAggregatedResult_IsCloudPc_FalseWhenNoReportCarriesMarker()
+    {
+        var reports = new List<DistressReportEntry>
+        {
+            MakeEntry("DeviceNotRegistered", "Lenovo", "ThinkPad T14", "SN1", T0),
+        };
+
+        var (aggregated, _) = GetDeviceNotRegisteredFunction.BuildAggregatedResult(reports);
+
+        var item = ToDynamic(aggregated[0]);
+        Assert.False((bool)item.isCloudPc);
+    }
+
     // =========================================================================
     // Helpers
     // =========================================================================
 
     private static DistressReportEntry MakeEntry(
-        string errorType, string? manufacturer, string? model, string? serial, DateTime ingestedAt) =>
+        string errorType, string? manufacturer, string? model, string? serial, DateTime ingestedAt,
+        bool isCloudPc = false) =>
         new()
         {
             TenantId = "test-tenant",
@@ -179,6 +216,7 @@ public class GetDeviceNotRegisteredFunctionTests
             SerialNumber = serial,
             IngestedAt = ingestedAt,
             AgentTimestamp = ingestedAt,
+            IsCloudPc = isCloudPc,
         };
 
     private static dynamic ToDynamic(object obj)

src/Backend/AutopilotMonitor.Functions.Tests/GetTenantFeatureFlagsPayloadTests.cs

@@ -34,7 +34,13 @@ public class GetTenantFeatureFlagsPayloadTests
         // — and that forces a deliberate code review of whether the new field is non-sensitive.
         Assert.Equal(new[]
         {
+            // Non-sensitive by review: bool only, exposes no client ids (dual app-reg
+            // self-service migration banner).
+            "appHomingFunnelActive",
             "bootstrapTokenEnabled",
+            // Non-sensitive by review: bool only ("is a contact address set"), never the
+            // address itself (admin-gated full config only).
+            "contactEmailSet",
             "diagnosticsUploadConfigured",
             "edition",
             "enableIntegrityBypassAnalyzer",
@@ -54,11 +60,13 @@ public class GetTenantFeatureFlagsPayloadTests
     {
         var config = new TenantConfiguration
         {
+            PlanTier = "pro", // unrestrictedMode is EFFECTIVE — requires Pro + gate + toggle
             BootstrapTokenEnabled = true,
             ValidateAutopilotDevice = true,
             ShowScriptOutput = false,
             EnableSoftwareInventoryAnalyzer = true,
             EnableIntegrityBypassAnalyzer = false,
+            UnrestrictedModeEnabled = true,
             UnrestrictedMode = true,
         };
 
@@ -72,6 +80,55 @@ public class GetTenantFeatureFlagsPayloadTests
         Assert.True(element.GetProperty("unrestrictedMode").GetBoolean());
     }
 
+    // ── Effective feature gates (plan-derived) ──────────────────────────────
+
+    [Fact]
+    public void Payload_Bootstrap_IncludedInPro_WithoutGaFlag()
+    {
+        var element = Serialize(new TenantConfiguration { PlanTier = "pro", BootstrapTokenEnabled = false });
+        Assert.True(element.GetProperty("bootstrapTokenEnabled").GetBoolean());
+    }
+
+    [Fact]
+    public void Payload_Bootstrap_GaFlagStillWorksForCommunity()
+    {
+        var element = Serialize(new TenantConfiguration { PlanTier = "free", BootstrapTokenEnabled = true });
+        Assert.True(element.GetProperty("bootstrapTokenEnabled").GetBoolean());
+    }
+
+    [Fact]
+    public void Payload_Bootstrap_CommunityWithoutFlag_Disabled()
+    {
+        var element = Serialize(new TenantConfiguration { PlanTier = "free", BootstrapTokenEnabled = false });
+        Assert.False(element.GetProperty("bootstrapTokenEnabled").GetBoolean());
+    }
+
+    [Fact]
+    public void Payload_UnrestrictedMode_CommunityTenant_ForcedOff_DespiteBothFlags()
+    {
+        // Fail-closed re-gate: a downgraded/expired tenant keeps its stored flags but the
+        // effective value must be false.
+        var element = Serialize(new TenantConfiguration
+        {
+            PlanTier = "free",
+            UnrestrictedModeEnabled = true,
+            UnrestrictedMode = true,
+        });
+        Assert.False(element.GetProperty("unrestrictedMode").GetBoolean());
+    }
+
+    [Fact]
+    public void Payload_UnrestrictedMode_ProWithoutGaGate_Off()
+    {
+        var element = Serialize(new TenantConfiguration
+        {
+            PlanTier = "pro",
+            UnrestrictedModeEnabled = false,
+            UnrestrictedMode = true,
+        });
+        Assert.False(element.GetProperty("unrestrictedMode").GetBoolean());
+    }
+
     [Fact]
     public void Payload_NullableFlags_FallBackToAgentSideDefaults()
     {
@@ -159,12 +216,14 @@ public class GetTenantFeatureFlagsPayloadTests
         Assert.Equal("community", element.GetProperty("entitlements").GetProperty("mcpUsagePlan").GetString());
     }
 
-    [Fact]
-    public void Payload_EnterpriseTier_NotTrial()
+    [Theory]
+    [InlineData("pro")]
+    [InlineData("enterprise")] // legacy stored value resolves — and reports — as "pro"
+    public void Payload_PermanentProTier_NotTrial(string storedTier)
     {
-        var element = Serialize(new TenantConfiguration { PlanTier = "enterprise" });
+        var element = Serialize(new TenantConfiguration { PlanTier = storedTier });
 
-        Assert.Equal("enterprise", element.GetProperty("edition").GetString());
+        Assert.Equal("pro", element.GetProperty("edition").GetString());
         Assert.False(element.GetProperty("isTrial").GetBoolean());
         Assert.False(element.GetProperty("trialAvailable").GetBoolean());
         Assert.Equal(365, element.GetProperty("entitlements").GetProperty("retentionCapDays").GetInt32());
@@ -178,7 +237,7 @@ public class GetTenantFeatureFlagsPayloadTests
         var expiry = Now.AddDays(10);
         var element = Serialize(new TenantConfiguration { TrialExpiresUtc = expiry, TrialConsumed = true });
 
-        Assert.Equal("enterprise", element.GetProperty("edition").GetString());
+        Assert.Equal("pro", element.GetProperty("edition").GetString());
         Assert.True(element.GetProperty("isTrial").GetBoolean());
         Assert.False(element.GetProperty("trialAvailable").GetBoolean());
         Assert.Equal(expiry, element.GetProperty("trialExpiresUtc").GetDateTime());
@@ -193,4 +252,27 @@ public class GetTenantFeatureFlagsPayloadTests
         Assert.False(element.GetProperty("isTrial").GetBoolean());
         Assert.False(element.GetProperty("trialAvailable").GetBoolean(), "consumed trial must not be offered again");
     }
+
+    // ── contactEmailSet (drives the Pro-requires-contact trial gate + banner) ──
+
+    [Theory]
+    [InlineData(null, false)]
+    [InlineData("", false)]
+    [InlineData("   ", false)]
+    [InlineData("it-ops@contoso.com", true)]
+    public void Payload_ContactEmailSet_ReflectsWhetherAnAddressIsStored(string? stored, bool expected)
+    {
+        var element = Serialize(new TenantConfiguration { ContactEmail = stored });
+
+        Assert.Equal(expected, element.GetProperty("contactEmailSet").GetBoolean());
+    }
+
+    [Fact]
+    public void Payload_ContactEmailSet_NeverLeaksTheAddress()
+    {
+        var json = JsonSerializer.Serialize(GetTenantFeatureFlagsFunction.BuildPayload(
+            new TenantConfiguration { ContactEmail = "secret-contact@contoso.com" }, Now));
+
+        Assert.DoesNotContain("secret-contact", json);
+    }
 }

src/Backend/AutopilotMonitor.Functions.Tests/GraphFeatureCatalogSyncTests.cs

@@ -0,0 +1,79 @@
+using System.Text.RegularExpressions;
+using AutopilotMonitor.Shared.Models.Graph;
+
+namespace AutopilotMonitor.Functions.Tests;
+
+/// <summary>
+/// Guard: the customer-side grant script (scripts/CustomerSetup/Grant-AutopilotMonitorAddOn.ps1)
+/// duplicates the feature→permission catalog from <see cref="GraphFeatureCatalog"/> — in its
+/// <c>$FeatureCatalog</c> hashtable AND in the <c>[ValidateSet(...)]</c> of <c>-Features</c>.
+/// The sync was previously comment-only ("Keep in lock-step with …") and had no enforcement;
+/// this test fails the build when either side drifts.
+/// </summary>
+public class GraphFeatureCatalogSyncTests
+{
+    [Fact]
+    public void GrantScript_FeatureCatalog_MatchesSharedCatalog()
+    {
+        var script = ReadGrantScript();
+
+        // Parse: $FeatureCatalog = @{ 'Name' = @('Perm', ...) ... }
+        var blockMatch = Regex.Match(script, @"\$FeatureCatalog\s*=\s*@\{(?<body>[^}]*)\}", RegexOptions.Singleline);
+        Assert.True(blockMatch.Success, "Could not locate the $FeatureCatalog hashtable in the grant script.");
+
+        var scriptCatalog = new Dictionary<string, string[]>(StringComparer.OrdinalIgnoreCase);
+        foreach (Match entry in Regex.Matches(blockMatch.Groups["body"].Value, @"'(?<feature>[^']+)'\s*=\s*@\((?<perms>[^)]*)\)"))
+        {
+            var perms = Regex.Matches(entry.Groups["perms"].Value, @"'(?<p>[^']+)'")
+                .Select(m => m.Groups["p"].Value)
+                .ToArray();
+            scriptCatalog[entry.Groups["feature"].Value] = perms;
+        }
+
+        Assert.Equal(
+            GraphFeatureCatalog.Features.OrderBy(f => f, StringComparer.OrdinalIgnoreCase),
+            scriptCatalog.Keys.OrderBy(f => f, StringComparer.OrdinalIgnoreCase));
+
+        foreach (var feature in GraphFeatureCatalog.Features)
+        {
+            Assert.Equal(
+                GraphFeatureCatalog.RequiredPermissions(feature).OrderBy(p => p, StringComparer.OrdinalIgnoreCase),
+                scriptCatalog[feature].OrderBy(p => p, StringComparer.OrdinalIgnoreCase));
+        }
+    }
+
+    [Fact]
+    public void GrantScript_ValidateSet_MatchesSharedCatalog()
+    {
+        var script = ReadGrantScript();
+
+        var vsMatch = Regex.Match(script, @"\[ValidateSet\((?<body>[^\)]*)\)\]");
+        Assert.True(vsMatch.Success, "Could not locate the [ValidateSet(...)] of -Features in the grant script.");
+
+        var scriptFeatures = Regex.Matches(vsMatch.Groups["body"].Value, @"'(?<f>[^']+)'")
+            .Select(m => m.Groups["f"].Value)
+            .ToArray();
+
+        Assert.Equal(
+            GraphFeatureCatalog.Features.OrderBy(f => f, StringComparer.OrdinalIgnoreCase),
+            scriptFeatures.OrderBy(f => f, StringComparer.OrdinalIgnoreCase));
+    }
+
+    private static string ReadGrantScript()
+    {
+        var path = Path.Combine(FindRepoRoot(), "scripts", "CustomerSetup", "Grant-AutopilotMonitorAddOn.ps1");
+        Assert.True(File.Exists(path), $"Grant script not found at {path}");
+        return File.ReadAllText(path);
+    }
+
+    private static string FindRepoRoot()
+    {
+        var dir = new DirectoryInfo(AppContext.BaseDirectory);
+        while (dir != null && !File.Exists(Path.Combine(dir.FullName, "AutopilotMonitor.sln")))
+        {
+            dir = dir.Parent;
+        }
+        Assert.NotNull(dir);
+        return dir!.FullName;
+    }
+}

src/Backend/AutopilotMonitor.Functions.Tests/GraphResolution/GraphFeatureDetectorTests.cs

@@ -327,17 +327,23 @@ public class GraphFeatureDetectorTests
         var handler = new SwappableTokenHandler(
             BuildJwt(Array.Empty<Claim>(), expires: DateTime.UtcNow.AddHours(1))); // pre-grant: no roles
         var cache = new MemoryCache(new MemoryCacheOptions());
+        var tokenConfig = new ConfigurationBuilder()
+            .AddInMemoryCollection(new Dictionary<string, string?>
+            {
+                ["EntraId:ClientId"] = "test-client",
+                ["EntraId:ClientSecret"] = "test-secret",
+            })
+            .Build();
         var tokenService = new GraphTokenService(
             NullLogger<GraphTokenService>.Instance,
             new SingleHandlerFactory(handler),
             cache,
-            new ConfigurationBuilder()
-                .AddInMemoryCollection(new Dictionary<string, string?>
-                {
-                    ["EntraId:ClientId"] = "test-client",
-                    ["EntraId:ClientSecret"] = "test-secret",
-                })
-                .Build());
+            tokenConfig,
+            new EntraAppRegistry(tokenConfig, NullLogger<EntraAppRegistry>.Instance),
+            new AutopilotMonitor.Functions.Services.TenantConfigurationService(
+                Moq.Mock.Of<AutopilotMonitor.Shared.DataAccess.IConfigRepository>(),
+                NullLogger<AutopilotMonitor.Functions.Services.TenantConfigurationService>.Instance,
+                new MemoryCache(new MemoryCacheOptions())));
         var telemetry = new TelemetryClient(new TelemetryConfiguration { DisableTelemetry = true });
         var detector = new GraphFeatureDetector(
             tokenService, cache, NullLogger<GraphFeatureDetector>.Instance, telemetry);
@@ -454,6 +460,28 @@ public class GraphFeatureDetectorTests
 
     // ── Test seam: token service stub + detector factory ──────────────────────────────
 
+    /// <summary>Minimal EntraId config for the GraphTokenService base ctor (no legacy app).</summary>
+    private static Microsoft.Extensions.Configuration.IConfiguration StubEntraConfig() =>
+        new ConfigurationBuilder()
+            .AddInMemoryCollection(new Dictionary<string, string?>
+            {
+                ["EntraId:ClientId"] = "test-client-id",
+                ["EntraId:ClientSecret"] = "test-secret",
+            })
+            .Build();
+
+    /// <summary>
+    /// Dual app-reg dependencies for the GraphTokenService base ctor. No legacy app configured
+    /// ⇒ the registry always resolves primary and the tenant-config lookup is never consulted.
+    /// </summary>
+    private static EntraAppRegistry StubAppRegistry() =>
+        new(StubEntraConfig(), NullLogger<EntraAppRegistry>.Instance);
+
+    private static AutopilotMonitor.Functions.Services.TenantConfigurationService StubTenantConfigService() =>
+        new(Moq.Mock.Of<AutopilotMonitor.Shared.DataAccess.IConfigRepository>(),
+            NullLogger<AutopilotMonitor.Functions.Services.TenantConfigurationService>.Instance,
+            new MemoryCache(new MemoryCacheOptions()));
+
     /// <summary>
     /// Subclass that bypasses the real AAD HTTP call so tests can drive the detector with
     /// canned <see cref="GraphTokenResult"/> values. Base ctor dependencies are satisfied
@@ -469,13 +497,9 @@ public class GraphFeatureDetectorTests
                 NullLogger<GraphTokenService>.Instance,
                 new NoopHttpClientFactory(),
                 new MemoryCache(new MemoryCacheOptions()),
-                new ConfigurationBuilder()
-                    .AddInMemoryCollection(new Dictionary<string, string?>
-                    {
-                        ["EntraId:ClientId"] = "test-client-id",
-                        ["EntraId:ClientSecret"] = "test-secret",
-                    })
-                    .Build())
+                StubEntraConfig(),
+                StubAppRegistry(),
+                StubTenantConfigService())
         {
         }
 
@@ -506,13 +530,9 @@ public class GraphFeatureDetectorTests
                 NullLogger<GraphTokenService>.Instance,
                 new NoopHttpClientFactory(),
                 new MemoryCache(new MemoryCacheOptions()),
-                new ConfigurationBuilder()
-                    .AddInMemoryCollection(new Dictionary<string, string?>
-                    {
-                        ["EntraId:ClientId"] = "test-client-id",
-                        ["EntraId:ClientSecret"] = "test-secret",
-                    })
-                    .Build())
+                StubEntraConfig(),
+                StubAppRegistry(),
+                StubTenantConfigService())
         {
             _firstToken = firstToken;
             _laterToken = laterToken;
@@ -549,13 +569,9 @@ public class GraphFeatureDetectorTests
                 NullLogger<GraphTokenService>.Instance,
                 factory,
                 cache,
-                new ConfigurationBuilder()
-                    .AddInMemoryCollection(new Dictionary<string, string?>
-                    {
-                        ["EntraId:ClientId"] = "test-client-id",
-                        ["EntraId:ClientSecret"] = "test-secret",
-                    })
-                    .Build())
+                StubEntraConfig(),
+                StubAppRegistry(),
+                StubTenantConfigService())
         {
             _onInvalidate = onInvalidate;
         }

src/Backend/AutopilotMonitor.Functions.Tests/GraphTokenServiceTests.cs

@@ -33,15 +33,28 @@ public class GraphTokenServiceTests
             })
             .Build();
 
-        var svc = new GraphTokenService(
-            NullLogger<GraphTokenService>.Instance,
-            new StubHttpClientFactory(handler),
-            new MemoryCache(new MemoryCacheOptions()),
-            config);
+        var svc = NewService(config, new StubHttpClientFactory(handler));
 
         return (svc, handler);
     }
 
+    /// <summary>
+    /// Builds the service with the dual app-reg dependencies. No legacy app is configured in
+    /// these tests ⇒ the registry always resolves the primary credentials and the tenant-config
+    /// lookup is never consulted for the decision — a null-returning repo is fine.
+    /// </summary>
+    private static GraphTokenService NewService(IConfiguration config, System.Net.Http.IHttpClientFactory factory) =>
+        new GraphTokenService(
+            NullLogger<GraphTokenService>.Instance,
+            factory,
+            new MemoryCache(new MemoryCacheOptions()),
+            config,
+            new EntraAppRegistry(config, NullLogger<EntraAppRegistry>.Instance),
+            new AutopilotMonitor.Functions.Services.TenantConfigurationService(
+                Moq.Mock.Of<AutopilotMonitor.Shared.DataAccess.IConfigRepository>(),
+                NullLogger<AutopilotMonitor.Functions.Services.TenantConfigurationService>.Instance,
+                new MemoryCache(new MemoryCacheOptions())));
+
     private static int TokenPosts(StubHttpMessageHandler handler, string tenantId)
         => handler.Requests.Count(u => u.Contains($"/{tenantId}/oauth2/v2.0/token"));
 
@@ -148,11 +161,7 @@ public class GraphTokenServiceTests
                 ["EntraId:ClientSecret"] = "test-secret",
             })
             .Build();
-        var svc = new GraphTokenService(
-            NullLogger<GraphTokenService>.Instance,
-            new SingleHandlerFactory(handler),
-            new MemoryCache(new MemoryCacheOptions()),
-            config);
+        var svc = NewService(config, new SingleHandlerFactory(handler));
 
         // R1 starts; its POST parks in flight (holding the gate, before writing to the cache).
         var inflight = svc.GetAccessTokenAsync(TenantA);
@@ -188,11 +197,7 @@ public class GraphTokenServiceTests
                 ["EntraId:ClientSecret"] = "test-secret",
             })
             .Build();
-        var svc = new GraphTokenService(
-            NullLogger<GraphTokenService>.Instance,
-            new SingleHandlerFactory(handler),
-            new MemoryCache(new MemoryCacheOptions()),
-            config);
+        var svc = NewService(config, new SingleHandlerFactory(handler));
 
         var tasks = Enumerable.Range(0, 10).Select(_ => svc.GetAccessTokenAsync(TenantA)).ToArray();
 
@@ -209,6 +214,54 @@ public class GraphTokenServiceTests
         Assert.Equal(1, handler.Entered);
     }
 
+    [Fact]
+    public async Task GetAccessTokenForAppAsync_caches_under_the_supplied_app_without_cross_app_poisoning()
+    {
+        // Dual app-reg window: the homing-flip consent probe mints under EXPLICIT primary
+        // credentials for a still-legacy-homed tenant. Contract: the probe token caches under the
+        // primary key, a second probe is served from cache, and the tenant's normal (legacy-
+        // resolved) path still mints its own token — never the probe's.
+        var handler = new StubHttpMessageHandler()
+            .When($"/{TenantA}/oauth2", HttpStatusCode.OK, "{\"access_token\":\"tok\",\"expires_in\":3599}");
+        var config = new ConfigurationBuilder()
+            .AddInMemoryCollection(new Dictionary<string, string?>
+            {
+                ["EntraId:ClientId"] = "aaaaaaaa-0000-0000-0000-000000000001",
+                ["EntraId:ClientSecret"] = "primary-secret",
+                ["EntraId:LegacyClientId"] = "bbbbbbbb-0000-0000-0000-000000000002",
+                ["EntraId:LegacyClientSecret"] = "legacy-secret",
+            })
+            .Build();
+        var registry = new EntraAppRegistry(config, NullLogger<EntraAppRegistry>.Instance);
+        var svc = new GraphTokenService(
+            NullLogger<GraphTokenService>.Instance,
+            new StubHttpClientFactory(handler),
+            new MemoryCache(new MemoryCacheOptions()),
+            config,
+            registry,
+            new AutopilotMonitor.Functions.Services.TenantConfigurationService(
+                Moq.Mock.Of<AutopilotMonitor.Shared.DataAccess.IConfigRepository>(),
+                NullLogger<AutopilotMonitor.Functions.Services.TenantConfigurationService>.Instance,
+                new MemoryCache(new MemoryCacheOptions())));
+
+        var probe1 = await svc.GetAccessTokenForAppAsync(TenantA, registry.Primary);
+        var probe2 = await svc.GetAccessTokenForAppAsync(TenantA, registry.Primary);
+        Assert.Equal("tok", probe1.AccessToken);
+        Assert.Equal("tok", probe2.AccessToken);
+        Assert.Equal(1, TokenPosts(handler, TenantA)); // second probe served from the primary-keyed cache
+
+        // Normal path resolves LEGACY for this tenant (no homing stored) — must be a cache miss
+        // against the probe's primary-keyed entry and mint its own token.
+        var homed = await svc.GetAccessTokenAsync(TenantA);
+        Assert.Equal("tok", homed.AccessToken);
+        Assert.Equal(2, TokenPosts(handler, TenantA));
+
+        // InvalidateTenant drops BOTH apps' entries — the next probe re-mints fresh.
+        svc.InvalidateTenant(TenantA);
+        await svc.GetAccessTokenForAppAsync(TenantA, registry.Primary);
+        Assert.Equal(3, TokenPosts(handler, TenantA));
+    }
+
     private static async Task WaitUntilAsync(Func<bool> condition, TimeSpan timeout)
     {
         var deadline = DateTime.UtcNow + timeout;

src/Backend/AutopilotMonitor.Functions.Tests/HealthCheckServicePoisonQueueTests.cs

@@ -1,5 +1,6 @@
 using System;
 using System.Collections.Generic;
+using System.Linq;
 using System.Threading;
 using System.Threading.Tasks;
 using AutopilotMonitor.Functions.Services;
@@ -22,9 +23,11 @@ public class HealthCheckServicePoisonQueueTests
     [Fact]
     public async Task Check_AllPoisonQueuesEmpty_ReportsHealthy()
     {
+        // Existing-but-drained poison queues: enumerated, probed, all zero.
         var probe = new FakePoisonQueueProbe();
-        foreach (var q in MaintenanceService.MonitoredPoisonQueues)
-            probe.Counts[q] = 0;
+        probe.Counts[Constants.QueueNames.AnalyzeOnEnrollmentEnd + "-poison"] = 0;
+        probe.Counts[Constants.QueueNames.VulnerabilityCorrelate + "-poison"] = 0;
+        probe.Counts[Constants.QueueNames.TenantAutoApprove + "-poison"] = 0;
 
         var svc = BuildService(probe);
         var check = await svc.CheckPoisonQueuesAsync();
@@ -32,10 +35,40 @@ public class HealthCheckServicePoisonQueueTests
         Assert.Equal("Poison Queues", check.Name);
         Assert.Equal("healthy", check.Status);
         Assert.Equal("All poison queues empty", check.Message);
-        Assert.Equal(MaintenanceService.MonitoredPoisonQueues.Length, check.Details!.Count);
+        Assert.Equal(3, check.Details!.Count);
         Assert.All(check.Details.Values, v => Assert.Equal("0 messages", v));
     }
 
+    [Fact]
+    public async Task Check_NoPoisonQueuesExist_ReportsHealthy()
+    {
+        // Steady state on a healthy system: poison queues are created lazily on
+        // first poison-move, so an empty enumeration means nothing ever failed.
+        var svc = BuildService(new FakePoisonQueueProbe());
+        var check = await svc.CheckPoisonQueuesAsync();
+
+        Assert.Equal("healthy", check.Status);
+        Assert.Equal("All poison queues empty", check.Message);
+        Assert.Empty(check.Details!);
+    }
+
+    [Fact]
+    public async Task Check_EnumerationFails_ReportsWarningWithError()
+    {
+        // A failed listing must never read as an all-clear.
+        var probe = new FakePoisonQueueProbe
+        {
+            ListException = new InvalidOperationException("auth denied")
+        };
+
+        var svc = BuildService(probe);
+        var check = await svc.CheckPoisonQueuesAsync();
+
+        Assert.Equal("warning", check.Status);
+        Assert.Contains("enumeration failed", check.Message);
+        Assert.Contains("auth denied", (string)check.Details!["error"]);
+    }
+
     [Fact]
     public async Task Check_SingleQueueWithBacklog_ReportsWarning()
     {
@@ -155,6 +188,19 @@ public class HealthCheckServicePoisonQueueTests
     {
         public Dictionary<string, long> Counts { get; } = new();
         public Dictionary<string, Exception> ExceptionFor { get; } = new();
+        public Exception? ListException { get; set; }
+
+        public Task<IReadOnlyList<string>> ListPoisonQueuesAsync(CancellationToken ct)
+        {
+            if (ListException is not null)
+                throw ListException;
+            IReadOnlyList<string> names = Counts.Keys
+                .Concat(ExceptionFor.Keys)
+                .Distinct()
+                .OrderBy(n => n, StringComparer.Ordinal)
+                .ToList();
+            return Task.FromResult(names);
+        }
 
         public Task<long> GetApproximateMessageCountAsync(string queueName, CancellationToken ct)
         {

src/Backend/AutopilotMonitor.Functions.Tests/MaintenanceServicePoisonQueueTests.cs

@@ -1,6 +1,5 @@
 using System.Text.Json;
 using AutopilotMonitor.Functions.Services;
-using AutopilotMonitor.Shared;
 
 namespace AutopilotMonitor.Functions.Tests;
 
@@ -10,7 +9,9 @@ namespace AutopilotMonitor.Functions.Tests;
 /// of the parts that decide whether an operator gets paged, without standing up
 /// the full MaintenanceService dependency graph. Full-service integration is
 /// exercised by the live timer + ops event tables — what we guard here is the
-/// classifier math, the dedup-key extractor, and the watch-list inventory.
+/// classifier math and the dedup-key extractor. The watched queues themselves are
+/// enumerated dynamically at runtime (every existing <c>-poison</c> queue), so
+/// there is no static inventory left to guard.
 /// </summary>
 public class MaintenanceServicePoisonQueueTests
 {
@@ -116,36 +117,6 @@ public class MaintenanceServicePoisonQueueTests
         Assert.Equal(string.Empty, MaintenanceService.ExtractQueueName(detailsJson));
     }
 
-    // --- Watch-list inventory ---
-
-    [Fact]
-    public void MonitoredPoisonQueues_CoversAllProducerQueues()
-    {
-        // Guard against silently adding a new producer queue without a poison entry.
-        // If a new queue is introduced, MonitoredPoisonQueues + this assertion must move together.
-        Assert.Equal(6, MaintenanceService.MonitoredPoisonQueues.Length);
-        Assert.Contains(
-            Constants.QueueNames.AnalyzeOnEnrollmentEnd + "-poison",
-            MaintenanceService.MonitoredPoisonQueues);
-        Assert.Contains(
-            Constants.QueueNames.VulnerabilityCorrelate + "-poison",
-            MaintenanceService.MonitoredPoisonQueues);
-        Assert.Contains(
-            Constants.QueueNames.TelemetryIndexReconcile + "-poison",
-            MaintenanceService.MonitoredPoisonQueues);
-        // PR1 critical-table backup queue (plan §Wave5 #2).
-        Assert.Contains(
-            Constants.QueueNames.CriticalTableBackupPoison,
-            MaintenanceService.MonitoredPoisonQueues);
-        // Self-hosted poll-loop workers (no QueueTrigger) — see SessionDeletionWorker / TenantOffboardingWorker.
-        Assert.Contains(
-            Constants.QueueNames.SessionDeletion + "-poison",
-            MaintenanceService.MonitoredPoisonQueues);
-        Assert.Contains(
-            Constants.QueueNames.TenantOffboardingPoison,
-            MaintenanceService.MonitoredPoisonQueues);
-    }
-
     [Fact]
     public void Defaults_AreCalibratedForStrictMode()
     {

src/Backend/AutopilotMonitor.Functions.Tests/McpQuotaServiceTests.cs

@@ -131,14 +131,14 @@ public class McpQuotaServiceTests
     }
 
     [Fact]
-    public async Task Check_EnterpriseEdition_UsesEnterpriseFallbackLimits()
+    public async Task Check_ProEdition_UsesProFallbackLimits()
     {
-        var svc = Build(UsageRepo(("20260707", 100)), edition: TenantEdition.Enterprise);
+        var svc = Build(UsageRepo(("20260707", 100)), edition: TenantEdition.Pro);
 
         var d = await svc.CheckAsync(Oid, Upn, TenantId);
 
         Assert.True(d.Allowed);
-        Assert.Equal("enterprise", d.Plan);
+        Assert.Equal("pro", d.Plan);
         Assert.Equal(1000, d.DailyLimit);
         Assert.Equal(20000, d.MonthlyLimit);
     }

src/Backend/AutopilotMonitor.Functions.Tests/McpUserServiceDelegatedTests.cs

@@ -36,7 +36,7 @@ public class McpUserServiceDelegatedTests
             _adminRepo.Object, cache, NullLogger<GlobalAdminService>.Instance) { CallBase = false };
         _delegatedAdmin = new Mock<DelegatedAdminService>(
             _adminRepo.Object,
-            new StubTenantEntitlementService(AutopilotMonitor.Functions.Security.TenantEdition.Enterprise),
+            new StubTenantEntitlementService(AutopilotMonitor.Functions.Security.TenantEdition.Pro),
             cache, NullLogger<DelegatedAdminService>.Instance) { CallBase = false };
         _adminConfig = new Mock<AdminConfigurationService>(
             Mock.Of<IConfigRepository>(), NullLogger<AdminConfigurationService>.Instance, cache) { CallBase = false };

src/Backend/AutopilotMonitor.Functions.Tests/Offboarding/OffboardingMarkerCleanupFunctionTests.cs

@@ -180,10 +180,14 @@ public class OffboardingMarkerCleanupFunctionTests
         Assert.Equal(0, result.TenantConfigsSpared);
         Assert.Equal(0, result.TenantConfigSweepRetries);
 
-        // The sweep ran with the right table + tenant id.
-        Assert.Single(fixture.SafeWipe.WipeCalls);
+        // The sweep ran with the right tables + tenant id: the tombstone itself, plus the
+        // tenant's config-backup partition (a save against the lingering tombstone may have
+        // re-created snapshots after the cascade's bulk wipe).
+        Assert.Equal(2, fixture.SafeWipe.WipeCalls.Count);
         Assert.Equal(Constants.TableNames.TenantConfiguration, fixture.SafeWipe.WipeCalls[0].Table);
         Assert.Equal(TenantId, fixture.SafeWipe.WipeCalls[0].TenantId);
+        Assert.Equal(Constants.TableNames.ConfigurationBackups, fixture.SafeWipe.WipeCalls[1].Table);
+        Assert.Equal(TenantId, fixture.SafeWipe.WipeCalls[1].TenantId);
         Assert.False(fixture.Repo.Markers.ContainsKey(TenantId));
     }
 

src/Backend/AutopilotMonitor.Functions.Tests/Offboarding/TenantCustomsArchiveContractTests.cs

@@ -42,6 +42,7 @@ public sealed class TenantCustomsArchiveContractTests
             reEnqueuer: null!,
             opsEvents: null!,
             customsArchive: archive,
+            configRepo: null!,
             farewellEmail: new FakeOffboardFarewellEmailSender(),
             logger: NullLogger<TenantOffboardingHandler>.Instance);
     }

src/Backend/AutopilotMonitor.Functions.Tests/Offboarding/TenantOffboardingHandlerDrainContractTests.cs

@@ -9,6 +9,7 @@ using Azure;
 using Azure.Data.Tables;
 using Azure.Storage.Blobs;
 using AutopilotMonitor.Functions.DataAccess.TableStorage;
+using AutopilotMonitor.Functions.Functions.Admin;
 using AutopilotMonitor.Functions.Services;
 using AutopilotMonitor.Functions.Services.Deletion;
 using AutopilotMonitor.Functions.Services.Notifications;
@@ -301,6 +302,47 @@ public class TenantOffboardingHandlerDrainContractTests
             "Phase 2.G must delete the Expectations blob as its last step");
     }
 
+    [Fact]
+    public async Task UnoffboardRace_ConfigNoLongerTombstone_FailsClosed_NoSafeWipe()
+    {
+        // 2.D-guard: an operator re-enabled the tenant while the cascade was queued/draining
+        // (the config write paths refuse this, but the guard is the last line of defense).
+        // Wiping now would destroy data of a live tenant → fail-closed, zero wipes.
+        var harness = Harness.New();
+        harness.ConfigRepo
+            .Setup(r => r.GetTenantConfigurationAsync(TenantId))
+            .ReturnsAsync(new TenantConfiguration { TenantId = TenantId, Disabled = false });
+
+        await Assert.ThrowsAsync<InvalidOperationException>(() =>
+            harness.Sut.HandleAsync(harness.Envelope(drainPollCount: 0)));
+
+        Assert.Equal("Failed", harness.Repo.Markers[TenantId].Status);
+        Assert.Equal("unoffboard_race", harness.Repo.Markers[TenantId].FailedPhase);
+        Assert.Equal("Failed", harness.Repo.History[HistoryRowKey].Status);
+        Assert.Equal(0, harness.SafeWipeProbe.WipeCallCount);
+    }
+
+    [Fact]
+    public async Task UnoffboardGuard_TombstoneStillInPlace_ProceedsToWipeAndCompleted()
+    {
+        // The normal case: Phase 1's tombstone is untouched → the guard must NOT get in
+        // the way of a legitimate offboarding.
+        var harness = Harness.New();
+        harness.ConfigRepo
+            .Setup(r => r.GetTenantConfigurationAsync(TenantId))
+            .ReturnsAsync(new TenantConfiguration
+            {
+                TenantId = TenantId,
+                Disabled = true,
+                DisabledReason = TenantOffboardFunction.OffboardingDisabledReason,
+            });
+
+        await harness.Sut.HandleAsync(harness.Envelope(drainPollCount: 0));
+
+        Assert.Equal("Completed", harness.Repo.Markers[TenantId].Status);
+        Assert.True(harness.SafeWipeProbe.WipeCallCount > 0);
+    }
+
     [Fact]
     public async Task SessionNotFound_CountsAsSatisfied_NoDrainProbeCall()
     {
@@ -393,6 +435,7 @@ public class TenantOffboardingHandlerDrainContractTests
         public Mock<OffboardingSessionEnumerator> Enumerator { get; }
         public CountingSafeWipeService SafeWipeProbe { get; } = new();
         public Mock<IMaintenanceRepository> Maintenance { get; } = new();
+        public Mock<IConfigRepository> ConfigRepo { get; } = new();
         public List<string> EnumeratorYields { get; } = new();
         public Exception? EnumeratorThrow { get; set; }
 
@@ -450,6 +493,7 @@ public class TenantOffboardingHandlerDrainContractTests
                 h.ReEnqueuer.Object,
                 opsService,
                 Mock.Of<ITenantCustomsArchiveRepository>(),
+                h.ConfigRepo.Object,
                 new FakeOffboardFarewellEmailSender(),
                 NullLogger<TenantOffboardingHandler>.Instance);
 
@@ -622,10 +666,11 @@ public class TenantOffboardingHandlerDrainContractTests
             ITenantOffboardingEnqueuer reEnqueuer,
             OpsEventService opsEvents,
             ITenantCustomsArchiveRepository customsArchive,
+            IConfigRepository configRepo,
             IOffboardFarewellEmailSender farewellEmail,
             ILogger<TenantOffboardingHandler> logger)
             : base(auditRepo, enumerator, cascadeEnqueuer, expectations, drainProbe, safeWipe,
-                   storage, maintenance, reEnqueuer, opsEvents, customsArchive, farewellEmail, logger)
+                   storage, maintenance, reEnqueuer, opsEvents, customsArchive, configRepo, farewellEmail, logger)
         {
         }
 

src/Backend/AutopilotMonitor.Functions.Tests/Offboarding/TenantOffboardingHandlerOrderingTests.cs

@@ -279,6 +279,20 @@ public class TenantOffboardingHandlerOrderingTests
         Assert.Contains(Constants.TableNames.TenantGroups, harness.SafeWipeProbe.PropertyOnlyWipes);
     }
 
+    [Fact]
+    public async Task PostDrain_ExactPartitionWipe_CoversConfigurationBackups()
+    {
+        // Pre-write config snapshots (PK=tenantId) must die with the tenant — the row
+        // contents include webhook URLs and the contact address. The bulk wipe runs
+        // before the final TenantConfiguration delete, so no snapshot can be re-created
+        // afterwards by the cascade itself.
+        var harness = Harness.New();
+
+        await harness.Sut.HandleAsync(harness.Envelope());
+
+        Assert.Contains(Constants.TableNames.ConfigurationBackups, harness.SafeWipeProbe.ExactPartitionWipes);
+    }
+
     // ── Harness (copied minimal — only what these tests need) ───────────────────
 
     private sealed class Harness
@@ -344,6 +358,7 @@ public class TenantOffboardingHandlerOrderingTests
                 h.ReEnqueuer.Object,
                 BuildOpsService(),
                 Mock.Of<ITenantCustomsArchiveRepository>(),
+                Mock.Of<IConfigRepository>(),
                 h.FarewellEmail,
                 NullLogger<TenantOffboardingHandler>.Instance);
 
@@ -425,12 +440,14 @@ public class TenantOffboardingHandlerOrderingTests
         public int WipeCallCount { get; private set; }
         /// <summary>Table names passed to the property-only (Variant C) wipe — lets tests assert coverage.</summary>
         public List<string> PropertyOnlyWipes { get; } = new();
+        /// <summary>Table names passed to the exact-partition (Variant A) wipe — lets tests assert coverage.</summary>
+        public List<string> ExactPartitionWipes { get; } = new();
         public CountingSafeWipeService() : base(
             new TableStorageService(Mock.Of<TableServiceClient>(), NullLogger<TableStorageService>.Instance),
             new BlobStorageService(new BlobServiceClient("UseDevelopmentStorage=true"),
                 NullLogger<BlobStorageService>.Instance, usesManagedIdentity: false),
             NullLogger<SafeWipeService>.Instance) { }
-        public override Task<int> WipeByExactPartitionAsync(string t, string i, CancellationToken c = default) { WipeCallCount++; return Task.FromResult(0); }
+        public override Task<int> WipeByExactPartitionAsync(string t, string i, CancellationToken c = default) { WipeCallCount++; ExactPartitionWipes.Add(t); return Task.FromResult(0); }
         public override Task<int> WipeByCompositePartitionRangeAsync(string t, string i, CancellationToken c = default) { WipeCallCount++; return Task.FromResult(0); }
         public override Task<int> WipeByDiscriminatorAndTenantPropertyAsync(string t, string d, string i, CancellationToken c = default) { WipeCallCount++; return Task.FromResult(0); }
         public override Task<int> WipeByTenantIdPropertyAsync(string t, string i, CancellationToken c = default) { WipeCallCount++; PropertyOnlyWipes.Add(t); return Task.FromResult(0); }
@@ -443,9 +460,9 @@ public class TenantOffboardingHandlerOrderingTests
             IOffboardingAuditRepository a, OffboardingSessionEnumerator e, ISessionDeletionEnqueuer c,
             IOffboardingExpectationsStore exp, IDeletionProgressDrainProbe d, SafeWipeService sw,
             TableStorageService s, IMaintenanceRepository m, ITenantOffboardingEnqueuer re,
-            OpsEventService o, ITenantCustomsArchiveRepository ca, IOffboardFarewellEmailSender fe,
-            ILogger<TenantOffboardingHandler> log)
-            : base(a, e, c, exp, d, sw, s, m, re, o, ca, fe, log) { }
+            OpsEventService o, ITenantCustomsArchiveRepository ca, IConfigRepository cr,
+            IOffboardFarewellEmailSender fe, ILogger<TenantOffboardingHandler> log)
+            : base(a, e, c, exp, d, sw, s, m, re, o, ca, cr, fe, log) { }
 
         internal override Task ArchiveAndWipeRulesTableAsync(
             string tableName, string tenantId, string historyRowKey, CancellationToken ct)