fix test

# Conflicts:
#	management/server/peer.go

.github/pull_request_template.md

@@ -12,6 +12,7 @@
 - [ ] Is a feature enhancement
 - [ ] It is a refactor
 - [ ] Created tests that fail without the change (if possible)
+- [ ] This change does **not** modify the public API, gRPC protocols, functionality behavior, CLI / service flags, or introduce a new feature — **OR** I have discussed it with the NetBird team beforehand (link the issue / Slack thread in the description). See [CONTRIBUTING.md](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#discuss-changes-with-the-netbird-team-first).
 
 > By submitting this pull request, you confirm that you have read and agree to the terms of the [Contributor License Agreement](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT.md).
 

CONTRIBUTING.md

@@ -15,6 +15,7 @@ If you haven't already, join our slack workspace [here](https://docs.netbird.io/
 - [Contributing to NetBird](#contributing-to-netbird)
     - [Contents](#contents)
     - [Code of conduct](#code-of-conduct)
+    - [Discuss changes with the NetBird team first](#discuss-changes-with-the-netbird-team-first)
     - [Directory structure](#directory-structure)
     - [Development setup](#development-setup)
         - [Requirements](#requirements)
@@ -33,6 +34,14 @@ Conduct which can be found in the file [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md).
 By participating, you are expected to uphold this code. Please report
 unacceptable behavior to community@netbird.io.
 
+## Discuss changes with the NetBird team first
+
+Changes to the **public API**, **gRPC protocols**, **functionality behavior**, **CLI / service flags**, or **new features** should be discussed with the NetBird team before you start the work. These surfaces are part of NetBird's contract with operators, self-hosters, and downstream integrators, and changes to them have compatibility, security, and release-planning implications that benefit from an early conversation.
+
+Open an issue or reach out on [Slack](https://docs.netbird.io/slack-url) to talk through what you have in mind. We'll help shape the change, flag any constraints we know about, and confirm the direction so the PR review can focus on implementation rather than design.
+
+Typical bug fixes, internal refactors, documentation updates, and tests do not need pre-discussion — open the PR directly.
+
 ## Directory structure
 
 The NetBird project monorepo is organized to maintain most of its individual dependencies code within their directories, except for a few auxiliary or shared packages.

README.md

@@ -1,147 +1,134 @@
 
 <div align="center">
-<br/>
-  <br/>
-<p align="center">
-  <img width="234" src="docs/media/logo-full.png"/>
-</p>
-  <p>
-   <a href="https://img.shields.io/badge/license-BSD--3-blue)">
-       <img src="https://sonarcloud.io/api/project_badges/measure?project=netbirdio_netbird&metric=alert_status" />
-     </a> 
-     <a href="https://github.com/netbirdio/netbird/blob/main/LICENSE">
-       <img src="https://img.shields.io/badge/license-BSD--3-blue" />
-     </a> 
-    <br>
+  <p align="center">
+    <img width="234" src="docs/media/logo-full.png" alt="NetBird logo"/>
+  </p>
+  <p align="center">
+    <a href="https://sonarcloud.io/dashboard?id=netbirdio_netbird">
+      <img src="https://sonarcloud.io/api/project_badges/measure?project=netbirdio_netbird&metric=alert_status" alt="SonarCloud alert status"/>
+    </a>
+    <a href="https://github.com/netbirdio/netbird/blob/main/LICENSE">
+      <img src="https://img.shields.io/badge/license-BSD--3-blue" alt="BSD-3 License"/>
+    </a>
     <a href="https://docs.netbird.io/slack-url">
-        <img src="https://img.shields.io/badge/slack-@netbird-red.svg?logo=slack"/>
-     </a>
+      <img src="https://img.shields.io/badge/slack-@netbird-red.svg?logo=slack" alt="NetBird Slack"/>
+    </a>
     <a href="https://forum.netbird.io">
-        <img src="https://img.shields.io/badge/community forum-@netbird-red.svg?logo=discourse"/>
-     </a>  
-     <br>
+      <img src="https://img.shields.io/badge/community%20forum-@netbird-red.svg?logo=discourse" alt="Community forum"/>
+    </a>
     <a href="https://gurubase.io/g/netbird">
-        <img src="https://img.shields.io/badge/Gurubase-Ask%20NetBird%20Guru-006BFF"/>
-     </a>    
+      <img src="https://img.shields.io/badge/Gurubase-Ask%20NetBird%20Guru-006BFF" alt="Gurubase: Ask NetBird Guru"/>
+    </a>
   </p>
 </div>
 
-
 <p align="center">
-<strong>
-  Start using NetBird at <a href="https://netbird.io/pricing">netbird.io</a>
+  <strong>
+    Start using NetBird at <a href="https://netbird.io/pricing">netbird.io</a>
+    <br/>
+    See <a href="https://netbird.io/docs/">Documentation</a>
+    <br/>
+    Join our <a href="https://docs.netbird.io/slack-url">Slack channel</a> or our <a href="https://forum.netbird.io">Community forum</a>
+  </strong>
   <br/>
-  See <a href="https://netbird.io/docs/">Documentation</a>
   <br/>
-   Join our <a href="https://docs.netbird.io/slack-url">Slack channel</a> or our <a href="https://forum.netbird.io">Community forum</a>
-  <br/>
- 
-</strong>
-<br>
-<strong>
-  🚀 <a href="https://careers.netbird.io">We are hiring! Join us at careers.netbird.io</a>
-</strong>
-<br>
-<br>
-<a href="https://registry.terraform.io/providers/netbirdio/netbird/latest">
-    New: NetBird terraform provider
-  </a> 
+  <strong>
+    🚀 <a href="https://careers.netbird.io">We are hiring! Join us at careers.netbird.io</a>
+  </strong>
 </p>
 
-<br>
-
 **NetBird combines a configuration-free peer-to-peer private network and a centralized access control system in a single platform, making it easy to create secure private networks for your organization or home.**
 
 **Connect.** NetBird creates a WireGuard-based overlay network that automatically connects your machines over an encrypted tunnel, leaving behind the hassle of opening ports, complex firewall rules, VPN gateways, and so forth.
 
 **Secure.** NetBird enables secure remote access by applying granular access policies while allowing you to manage them intuitively from a single place. Works universally on any infrastructure.
 
-### Open Source Network Security in a Single Platform
-
 https://github.com/user-attachments/assets/10cec749-bb56-4ab3-97af-4e38850108d2
 
-### Self-Host NetBird (Video)
+### Self-host NetBird (video)
+
 [![Watch the video](https://img.youtube.com/vi/bZAgpT6nzaQ/0.jpg)](https://youtu.be/bZAgpT6nzaQ)
 
 ### Key features
 
-| Connectivity | Management | Security | Automation| Platforms |
-|----|----|----|----|----|
-| <ul><li>- \[x] Kernel WireGuard</ul></li> | <ul><li>- \[x] [Admin Web UI](https://github.com/netbirdio/dashboard)</ul></li> | <ul><li>- \[x] [SSO & MFA support](https://docs.netbird.io/how-to/installation#running-net-bird-with-sso-login)</ul></li> | <ul><li>- \[x] [Public API](https://docs.netbird.io/api)</ul></li> | <ul><li>- \[x] Linux</ul></li> |
-| <ul><li>- \[x] Peer-to-peer connections</ul></li> | <ul><li>- \[x] Auto peer discovery and configuration</ui></li> | <ul><li>- \[x] [Access control - groups & rules](https://docs.netbird.io/how-to/manage-network-access)</ui></li> | <ul><li>- \[x] [Setup keys for bulk network provisioning](https://docs.netbird.io/how-to/register-machines-using-setup-keys)</ui></li> | <ul><li>- \[x] Mac</ui></li> |
-| <ul><li>- \[x] Connection relay fallback</ui></li> | <ul><li>- \[x] [IdP integrations](https://docs.netbird.io/selfhosted/identity-providers)</ui></li> | <ul><li>- \[x] [Activity logging](https://docs.netbird.io/how-to/audit-events-logging)</ui></li> | <ul><li>- \[x] [Self-hosting quickstart script](https://docs.netbird.io/selfhosted/selfhosted-quickstart)</ui></li> | <ul><li>- \[x] Windows</ui></li> |
-| <ul><li>- \[x] [Routes to external networks](https://docs.netbird.io/how-to/routing-traffic-to-private-networks)</ui></li> | <ul><li>- \[x] [Private DNS](https://docs.netbird.io/how-to/manage-dns-in-your-network)</ui></li> | <ul><li>- \[x] [Device posture checks](https://docs.netbird.io/how-to/manage-posture-checks)</ui></li> | <ul><li>- \[x] IdP groups sync with JWT</ui></li> | <ul><li>- \[x] Android</ui></li> |
-| <ul><li>- \[x] NAT traversal with BPF</ui></li> | <ul><li>- \[x] [Multiuser support](https://docs.netbird.io/how-to/add-users-to-your-network)</ui></li> | <ul><li>- \[x] Peer-to-peer encryption</ui></li> || <ul><li>- \[x] iOS</ui></li> |
-||| <ul><li>- \[x] [Quantum-resistance with Rosenpass](https://netbird.io/knowledge-hub/the-first-quantum-resistant-mesh-vpn)</ui></li> || <ul><li>- \[x] OpenWRT</ui></li> |
-||| <ul><li>- \[x] [Periodic re-authentication](https://docs.netbird.io/how-to/enforce-periodic-user-authentication)</ui></li> || <ul><li>- \[x] [Serverless](https://docs.netbird.io/how-to/netbird-on-faas)</ui></li> |
-||||| <ul><li>- \[x] Docker</ui></li> |
+| Connectivity | Management | Security | Automation | Platforms |
+|---|---|---|---|---|
+| ✓ [Kernel WireGuard](https://docs.netbird.io/about-netbird/why-wireguard-with-netbird) | ✓ [Admin Web UI](https://github.com/netbirdio/dashboard) | ✓ [SSO & MFA support](https://docs.netbird.io/how-to/installation#running-net-bird-with-sso-login) | ✓ [Public API](https://docs.netbird.io/api) | ✓ [Linux](https://docs.netbird.io/get-started/install/linux) |
+| ✓ [Peer-to-peer connections](https://docs.netbird.io/about-netbird/how-netbird-works) | ✓ Auto peer discovery and configuration | ✓ [Access control: groups & rules](https://docs.netbird.io/how-to/manage-network-access) | ✓ [Setup keys for bulk provisioning](https://docs.netbird.io/how-to/register-machines-using-setup-keys) | ✓ [macOS](https://docs.netbird.io/get-started/install/macos) |
+| ✓ Connection relay fallback | ✓ [IdP integrations](https://docs.netbird.io/selfhosted/identity-providers) | ✓ [Activity logging](https://docs.netbird.io/how-to/audit-events-logging) | ✓ [Self-hosting quickstart script](https://docs.netbird.io/selfhosted/selfhosted-quickstart) | ✓ [Windows](https://docs.netbird.io/get-started/install/windows) |
+| ✓ [Routes to external networks](https://docs.netbird.io/how-to/routing-traffic-to-private-networks) | ✓ [Private DNS](https://docs.netbird.io/how-to/manage-dns-in-your-network) | ✓ [Traffic events](https://docs.netbird.io/manage/activity/traffic-events-logging) | ✓ [IdP groups sync with JWT](https://docs.netbird.io/manage/team/idp-sync) | ✓ [Android](https://docs.netbird.io/get-started/install/android) |
+| ✓ [Domain-based DNS routes](https://docs.netbird.io/manage/dns/dns-aliases-for-routed-networks) | ✓ [Custom DNS zones](https://docs.netbird.io/manage/dns/custom-zones) | ✓ [Device posture checks](https://docs.netbird.io/how-to/manage-posture-checks) | ✓ [Terraform provider](https://registry.terraform.io/providers/netbirdio/netbird/latest) | ✓ [Android TV](https://docs.netbird.io/get-started/install/android-tv) |
+| ✓ [Exit nodes](https://docs.netbird.io/manage/network-routes/use-cases/exit-nodes) | ✓ [Multiuser support](https://docs.netbird.io/how-to/add-users-to-your-network) | ✓ Peer-to-peer encryption | ✓ [Ansible collection](https://github.com/netbirdio/ansible-netbird) | ✓ [iOS](https://docs.netbird.io/get-started/install/ios) |
+| ✓ [IPv6 dual-stack overlay](https://docs.netbird.io/manage/settings/ipv6) | ✓ [Multi-account profile switching](https://docs.netbird.io/client/profiles) | ✓ [SSH with central access policies](https://docs.netbird.io/manage/peers/ssh) | | ✓ [Apple TV](https://docs.netbird.io/get-started/install/tvos) |
+| ✓ [Browser SSH & RDP](https://docs.netbird.io/manage/peers/browser-client) | | ✓ [Quantum-resistance with Rosenpass](https://netbird.io/knowledge-hub/the-first-quantum-resistant-mesh-vpn) | | ✓ FreeBSD |
+| ✓ [Reverse proxy with auto-TLS](https://docs.netbird.io/manage/reverse-proxy) | | ✓ [Periodic re-authentication](https://docs.netbird.io/how-to/enforce-periodic-user-authentication) | | ✓ [pfSense](https://docs.netbird.io/get-started/install/pfsense) |
+| | | | | ✓ [OPNsense](https://docs.netbird.io/get-started/install/opnsense) |
+| | | | | ✓ [MikroTik RouterOS](https://docs.netbird.io/use-cases/homelab/client-on-mikrotik-router) |
+| | | | | ✓ OpenWRT |
+| | | | | ✓ [Synology](https://docs.netbird.io/get-started/install/synology) |
+| | | | | ✓ [TrueNAS](https://docs.netbird.io/get-started/install/truenas) |
+| | | | | ✓ [Proxmox](https://docs.netbird.io/get-started/install/proxmox-ve) |
+| | | | | ✓ [Raspberry Pi](https://docs.netbird.io/get-started/install/raspberrypi) |
+| | | | | ✓ [Serverless](https://docs.netbird.io/how-to/netbird-on-faas) |
+| | | | | ✓ [Container](https://docs.netbird.io/get-started/install/docker) |
 
 ### Quickstart with NetBird Cloud
 
-- Download and install NetBird at [https://app.netbird.io/install](https://app.netbird.io/install)
-- Follow the steps to sign-up with Google, Microsoft, GitHub or your email address.
-- Check NetBird [admin UI](https://app.netbird.io/).
-- Add more machines.
+- Download and install NetBird at [https://app.netbird.io/install](https://app.netbird.io/install).
+- Follow the steps to sign up with Google, Microsoft, GitHub or your email address.
+- Check the NetBird [admin UI](https://app.netbird.io/).
 
 ### Quickstart with self-hosted NetBird
 
-> This is the quickest way to try self-hosted NetBird. It should take around 5 minutes to get started if you already have a public domain and a VM.
-Follow the [Advanced guide with a custom identity provider](https://docs.netbird.io/selfhosted/selfhosted-guide#advanced-guide-with-a-custom-identity-provider) for installations with different IDPs.
+This is the quickest way to try self-hosted NetBird. It should take around 5 minutes to get started if you already have a public domain and a VM. Follow the [Advanced guide with a custom identity provider](https://docs.netbird.io/selfhosted/selfhosted-guide#advanced-guide-with-a-custom-identity-provider) for installations with different IdPs.
 
 **Infrastructure requirements:**
-- A Linux VM with at least **1CPU** and **2GB** of memory.
-- The VM should be publicly accessible on TCP ports **80** and **443** and UDP port: **3478**.
-- **Public domain** name pointing to the VM.
+- A Linux VM with at least **1 CPU** and **2 GB** of memory.
+- The VM should be publicly accessible on TCP ports **80** and **443** and UDP port **3478**.
+- A **public domain** name pointing to the VM.
 
 **Software requirements:**
-- Docker installed on the VM with the docker-compose plugin ([Docker installation guide](https://docs.docker.com/engine/install/)) or docker with docker-compose in version 2 or higher.
-- [jq](https://jqlang.github.io/jq/) installed. In most distributions
-  Usually available in the official repositories and can be installed with `sudo apt install jq` or `sudo yum install jq`
-- [curl](https://curl.se/) installed.
-  Usually available in the official repositories and can be installed with `sudo apt install curl` or `sudo yum install curl`
+- Docker with the Compose plugin (Compose v2 or higher). See the [Docker installation guide](https://docs.docker.com/engine/install/).
 
 **Steps**
 - Download and run the installation script:
 ```bash
 export NETBIRD_DOMAIN=netbird.example.com; curl -fsSL https://github.com/netbirdio/netbird/releases/latest/download/getting-started.sh | bash
 ```
-- Once finished, you can manage the resources via `docker-compose`
 
 ### A bit on NetBird internals
--  Every machine in the network runs [NetBird Agent (or Client)](client/) that manages WireGuard.
--  Every agent connects to [Management Service](management/) that holds network state, manages peer IPs, and distributes network updates to agents (peers).
--  NetBird agent uses WebRTC ICE implemented in [pion/ice library](https://github.com/pion/ice) to discover connection candidates when establishing a peer-to-peer connection between machines.
--  Connection candidates are discovered with the help of [STUN](https://en.wikipedia.org/wiki/STUN) servers.
--  Agents negotiate a connection through [Signal Service](signal/) passing p2p encrypted messages with candidates.
--  Sometimes the NAT traversal is unsuccessful due to strict NATs (e.g. mobile carrier-grade NAT) and a p2p connection isn't possible. When this occurs the system falls back to a relay server called [TURN](https://en.wikipedia.org/wiki/Traversal_Using_Relays_around_NAT), and a secure WireGuard tunnel is established via the TURN server. 
- 
-[Coturn](https://github.com/coturn/coturn) is the one that has been successfully used for STUN and TURN in NetBird setups.
+- Every machine in the network runs the [NetBird agent](client/), which manages WireGuard.
+- Every agent connects to the [Management Service](management/), which holds network state, manages peer IPs, and distributes updates to agents.
+- Agents use ICE (via [pion/ice](https://github.com/pion/ice)) to discover connection candidates for peer-to-peer connections.
+- Candidates are discovered with the help of [STUN](https://en.wikipedia.org/wiki/STUN) servers.
+- Agents negotiate a connection through the [Signal Service](signal/), exchanging end-to-end encrypted messages with candidates.
+- When NAT traversal fails (e.g. mobile carrier-grade NAT) and a direct p2p connection isn't possible, the system falls back to a [Relay Service](relay/) and a secure WireGuard tunnel is established through it.
 
 <p float="left" align="middle">
-  <img src="https://docs.netbird.io/docs-static/img/about-netbird/high-level-dia.png" width="700"/>
+  <img src="https://docs.netbird.io/docs-static/img/about-netbird/high-level-dia.png" width="700" alt="NetBird high-level architecture diagram"/>
 </p>
 
 See a complete [architecture overview](https://docs.netbird.io/about-netbird/how-netbird-works#architecture) for details.
 
 ### Community projects
--  [NetBird installer script](https://github.com/physk/netbird-installer)
--  [NetBird ansible collection by Dominion Solutions](https://galaxy.ansible.com/ui/repo/published/dominion_solutions/netbird/)
--  [netbird-tui](https://github.com/n0pashkov/netbird-tui) — terminal UI for managing NetBird peers, routes, and settings
+- [NetBird installer script](https://github.com/physk/netbird-installer)
+- [netbird-tui](https://github.com/n0pashkov/netbird-tui) - terminal UI for managing NetBird peers, routes, and settings
+- [caddy-netbird](https://github.com/lixmal/caddy-netbird) - Caddy plugin that embeds a NetBird client for proxying HTTP and TCP/UDP traffic through NetBird networks
 
 **Note**: The `main` branch may be in an *unstable or even broken state* during development.
 For stable versions, see [releases](https://github.com/netbirdio/netbird/releases).
 
 ### Support acknowledgement
 
-In November 2022, NetBird joined the [StartUpSecure program](https://www.forschung-it-sicherheit-kommunikationssysteme.de/foerderung/bekanntmachungen/startup-secure) sponsored by The Federal Ministry of Education and Research of The Federal Republic of Germany. Together with [CISPA Helmholtz Center for Information Security](https://cispa.de/en) NetBird brings the security best practices and simplicity to private networking.
+In November 2022, NetBird joined the [StartUpSecure program](https://www.forschung-it-sicherheit-kommunikationssysteme.de/foerderung/bekanntmachungen/startup-secure) sponsored by the Federal Ministry of Education and Research of the Federal Republic of Germany. Together with the [CISPA Helmholtz Center for Information Security](https://cispa.de/en), NetBird brings security best practices and simplicity to private networking.
 
 ![CISPA_Logo_BLACK_EN_RZ_RGB (1)](https://user-images.githubusercontent.com/700848/203091324-c6d311a0-22b5-4b05-a288-91cbc6cdcc46.png)
 
-### Testimonials
-We use open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE (WebRTC)](https://github.com/pion/ice), [Coturn](https://github.com/coturn/coturn), and [Rosenpass](https://rosenpass.eu). We very much appreciate the work these guys are doing and we'd greatly appreciate if you could support them in any way (e.g., by giving a star or a contribution).
+### Acknowledgements
+We build on open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
 
 ### Legal
-This repository is licensed under BSD-3-Clause license that applies to all parts of the repository except for the directories management/, signal/ and relay/.
+This repository is licensed under the BSD-3-Clause license, which applies to all parts of the repository except for the directories management/, signal/ and relay/.
 Those directories are licensed under the GNU Affero General Public License version 3.0 (AGPLv3). See the respective LICENSE files inside each directory.
 
 _WireGuard_ and the _WireGuard_ logo are [registered trademarks](https://www.wireguard.com/trademark-policy/) of Jason A. Donenfeld.

client/cmd/status.go

@@ -43,16 +43,16 @@ func init() {
 	ipsFilterMap = make(map[string]struct{})
 	prefixNamesFilterMap = make(map[string]struct{})
 	statusCmd.PersistentFlags().BoolVarP(&detailFlag, "detail", "d", false, "display detailed status information in human-readable format")
-	statusCmd.PersistentFlags().BoolVar(&jsonFlag, "json", false, "display detailed status information in json format")
-	statusCmd.PersistentFlags().BoolVar(&yamlFlag, "yaml", false, "display detailed status information in yaml format")
-	statusCmd.PersistentFlags().BoolVar(&ipv4Flag, "ipv4", false, "display only NetBird IPv4 of this peer, e.g., --ipv4 will output 100.64.0.33")
-	statusCmd.PersistentFlags().BoolVar(&ipv6Flag, "ipv6", false, "display only NetBird IPv6 of this peer")
+	statusCmd.PersistentFlags().BoolVarP(&jsonFlag, "json", "j", false, "display detailed status information in json format")
+	statusCmd.PersistentFlags().BoolVarP(&yamlFlag, "yaml", "y", false, "display detailed status information in yaml format")
+	statusCmd.PersistentFlags().BoolVarP(&ipv4Flag, "ipv4", "4", false, "display only NetBird IPv4 of this peer, e.g., --ipv4 will output 100.64.0.33")
+	statusCmd.PersistentFlags().BoolVarP(&ipv6Flag, "ipv6", "6", false, "display only NetBird IPv6 of this peer")
 	statusCmd.MarkFlagsMutuallyExclusive("detail", "json", "yaml", "ipv4", "ipv6")
-	statusCmd.PersistentFlags().StringSliceVar(&ipsFilter, "filter-by-ips", []string{}, "filters the detailed output by a list of one or more IPs (v4 or v6), e.g., --filter-by-ips 100.64.0.100,fd00::1")
-	statusCmd.PersistentFlags().StringSliceVar(&prefixNamesFilter, "filter-by-names", []string{}, "filters the detailed output by a list of one or more peer FQDN or hostnames, e.g., --filter-by-names peer-a,peer-b.netbird.cloud")
-	statusCmd.PersistentFlags().StringVar(&statusFilter, "filter-by-status", "", "filters the detailed output by connection status(idle|connecting|connected), e.g., --filter-by-status connected")
-	statusCmd.PersistentFlags().StringVar(&connectionTypeFilter, "filter-by-connection-type", "", "filters the detailed output by connection type (P2P|Relayed), e.g., --filter-by-connection-type P2P")
-	statusCmd.PersistentFlags().StringVar(&checkFlag, "check", "", "run a health check and exit with code 0 on success, 1 on failure (live|ready|startup)")
+	statusCmd.PersistentFlags().StringSliceVarP(&ipsFilter, "filter-by-ips", "I", []string{}, "filters the detailed output by a list of one or more IPs (v4 or v6), e.g., --filter-by-ips 100.64.0.100,fd00::1")
+	statusCmd.PersistentFlags().StringSliceVarP(&prefixNamesFilter, "filter-by-names", "N", []string{}, "filters the detailed output by a list of one or more peer FQDN or hostnames, e.g., --filter-by-names peer-a,peer-b.netbird.cloud")
+	statusCmd.PersistentFlags().StringVarP(&statusFilter, "filter-by-status", "S", "", "filters the detailed output by connection status(idle|connecting|connected), e.g., --filter-by-status connected")
+	statusCmd.PersistentFlags().StringVarP(&connectionTypeFilter, "filter-by-connection-type", "T", "", "filters the detailed output by connection type (P2P|Relayed), e.g., --filter-by-connection-type P2P")
+	statusCmd.PersistentFlags().StringVarP(&checkFlag, "check", "C", "", "run a health check and exit with code 0 on success, 1 on failure (live|ready|startup)")
 }
 
 func statusFunc(cmd *cobra.Command, args []string) error {

client/embed/embed.go

@@ -336,7 +336,7 @@ func (c *Client) ListenTCP(address string) (net.Listener, error) {
 	if err != nil {
 		return nil, fmt.Errorf("split host port: %w", err)
 	}
-	listenAddr := fmt.Sprintf("%s:%s", addr, port)
+	listenAddr := net.JoinHostPort(addr.String(), port)
 
 	tcpAddr, err := net.ResolveTCPAddr("tcp", listenAddr)
 	if err != nil {
@@ -357,7 +357,7 @@ func (c *Client) ListenUDP(address string) (net.PacketConn, error) {
 	if err != nil {
 		return nil, fmt.Errorf("split host port: %w", err)
 	}
-	listenAddr := fmt.Sprintf("%s:%s", addr, port)
+	listenAddr := net.JoinHostPort(addr.String(), port)
 
 	udpAddr, err := net.ResolveUDPAddr("udp", listenAddr)
 	if err != nil {

client/firewall/nftables/external_chain_monitor_linux.go

@@ -52,9 +52,10 @@ func (m *externalChainMonitor) start() {
 
 	ctx, cancel := context.WithCancel(context.Background())
 	m.cancel = cancel
-	m.done = make(chan struct{})
+	done := make(chan struct{})
+	m.done = done
 
-	go m.run(ctx)
+	go m.run(ctx, done)
 }
 
 func (m *externalChainMonitor) stop() {
@@ -72,8 +73,8 @@ func (m *externalChainMonitor) stop() {
 	<-done
 }
 
-func (m *externalChainMonitor) run(ctx context.Context) {
-	defer close(m.done)
+func (m *externalChainMonitor) run(ctx context.Context, done chan struct{}) {
+	defer close(done)
 
 	bo := &backoff.ExponentialBackOff{
 		InitialInterval:     externalMonitorInitInterval,

client/installer.nsis

@@ -260,15 +260,23 @@ WriteRegStr ${REG_ROOT} "${UNINSTALL_PATH}"  "Publisher" "${COMP_NAME}"
 
 WriteRegStr ${REG_ROOT} "${UI_REG_APP_PATH}" "" "$INSTDIR\${UI_APP_EXE}"
 
-; Create autostart registry entry based on checkbox
+; Drop Run, App Paths and Uninstall entries left in the 32-bit registry view
+; or HKCU by legacy installers.
+DetailPrint "Cleaning legacy 32-bit / HKCU entries..."
+DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+SetRegView 32
+DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+DeleteRegKey HKLM "${REG_APP_PATH}"
+DeleteRegKey HKLM "${UI_REG_APP_PATH}"
+DeleteRegKey HKLM "${UNINSTALL_PATH}"
+SetRegView 64
+
 DetailPrint "Autostart enabled: $AutostartEnabled"
 ${If} $AutostartEnabled == "1"
     WriteRegStr HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}" '"$INSTDIR\${UI_APP_EXE}.exe"'
     DetailPrint "Added autostart registry entry: $INSTDIR\${UI_APP_EXE}.exe"
 ${Else}
     DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-    ; Legacy: pre-HKLM installs wrote to HKCU; clean that up too.
-    DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
     DetailPrint "Autostart not enabled by user"
 ${EndIf}
 
@@ -299,11 +307,16 @@ ExecWait '"$INSTDIR\${MAIN_APP_EXE}" service uninstall'
 DetailPrint "Terminating Netbird UI process..."
 ExecWait `taskkill /im ${UI_APP_EXE}.exe /f`
 
-; Remove autostart registry entry
+; Remove autostart entries from every view a previous installer may have used.
 DetailPrint "Removing autostart registry entry if exists..."
 DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-; Legacy: pre-HKLM installs wrote to HKCU; clean that up too.
 DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+SetRegView 32
+DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+DeleteRegKey HKLM "${REG_APP_PATH}"
+DeleteRegKey HKLM "${UI_REG_APP_PATH}"
+DeleteRegKey HKLM "${UNINSTALL_PATH}"
+SetRegView 64
 
 ; Handle data deletion based on checkbox
 DetailPrint "Checking if user requested data deletion..."

client/internal/connect.go

@@ -116,7 +116,6 @@ func (c *ConnectClient) RunOniOS(
 	fileDescriptor int32,
 	networkChangeListener listener.NetworkChangeListener,
 	dnsManager dns.IosDnsManager,
-	dnsAddresses []netip.AddrPort,
 	stateFilePath string,
 ) error {
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
@@ -126,7 +125,6 @@ func (c *ConnectClient) RunOniOS(
 		FileDescriptor:        fileDescriptor,
 		NetworkChangeListener: networkChangeListener,
 		DnsManager:            dnsManager,
-		HostDNSAddresses:      dnsAddresses,
 		StateFilePath:         stateFilePath,
 	}
 	return c.run(mobileDependency, nil, "")

client/internal/debug/debug.go

@@ -45,8 +45,11 @@ netbird.out: Most recent, anonymized stdout log file of the NetBird client.
 routes.txt: Detailed system routing table in tabular format including destination, gateway, interface, metrics, and protocol information, if --system-info flag was provided.
 interfaces.txt: Anonymized network interface information, if --system-info flag was provided.
 ip_rules.txt: Detailed IP routing rules in tabular format including priority, source, destination, interfaces, table, and action information (Linux only), if --system-info flag was provided.
-iptables.txt: Anonymized iptables rules with packet counters, if --system-info flag was provided.
-nftables.txt: Anonymized nftables rules with packet counters, if --system-info flag was provided.
+iptables.txt: Anonymized iptables (IPv4) rules with packet counters, if --system-info flag was provided.
+ip6tables.txt: Anonymized ip6tables (IPv6) rules with packet counters, if --system-info flag was provided.
+ipset.txt: Anonymized ipset list output, if --system-info flag was provided.
+nftables.txt: Anonymized nftables rules with packet counters across all families (ip, ip6, inet, etc.), if --system-info flag was provided.
+sysctls.txt: Forwarding, reverse-path filter, source-validation, and conntrack accounting sysctl values that the NetBird client may read or modify, if --system-info flag was provided (Linux only).
 resolv.conf: DNS resolver configuration from /etc/resolv.conf (Unix systems only), if --system-info flag was provided.
 scutil_dns.txt: DNS configuration from scutil --dns (macOS only), if --system-info flag was provided.
 resolved_domains.txt: Anonymized resolved domain IP addresses from the status recorder.
@@ -165,22 +168,33 @@ The config.txt file contains anonymized configuration information of the NetBird
 Other non-sensitive configuration options are included without anonymization.
 
 Firewall Rules (Linux only)
-The bundle includes two separate firewall rule files:
+The bundle includes the following firewall-related files:
 
 iptables.txt:
-- Complete iptables ruleset with packet counters using 'iptables -v -n -L'
+- IPv4 iptables ruleset with packet counters using 'iptables-save' and 'iptables -v -n -L'
 - Includes all tables (filter, nat, mangle, raw, security)
 - Shows packet and byte counters for each rule
 - All IP addresses are anonymized
 - Chain names, table names, and other non-sensitive information remain unchanged
 
+ip6tables.txt:
+- IPv6 ip6tables ruleset with packet counters using 'ip6tables-save' and 'ip6tables -v -n -L'
+- Same table coverage and anonymization as iptables.txt
+- Omitted when ip6tables is not installed or no IPv6 rules are present
+
+ipset.txt:
+- Output of 'ipset list' (family-agnostic)
+- IP addresses are anonymized; set names and types remain unchanged
+
 nftables.txt:
-- Complete nftables ruleset obtained via 'nft -a list ruleset'
+- Complete nftables ruleset across all families (ip, ip6, inet, arp, bridge, netdev) via 'nft -a list ruleset'
 - Includes rule handle numbers and packet counters
-- All tables, chains, and rules are included
-- Shows packet and byte counters for each rule
-- All IP addresses are anonymized
-- Chain names, table names, and other non-sensitive information remain unchanged
+- All IP addresses are anonymized; chain/table names remain unchanged
+
+sysctls.txt:
+- Forwarding (IPv4 + IPv6, global and per-interface), reverse-path filter, source-validation, conntrack accounting, and TCP-related sysctls that netbird may read or modify
+- Per-interface keys are enumerated from /proc/sys/net/ipv{4,6}/conf
+- Interface names anonymized when --anonymize is set
 
 IP Rules (Linux only)
 The ip_rules.txt file contains detailed IP routing rule information:
@@ -412,6 +426,10 @@ func (g *BundleGenerator) addSystemInfo() {
 		log.Errorf("failed to add firewall rules to debug bundle: %v", err)
 	}
 
+	if err := g.addSysctls(); err != nil {
+		log.Errorf("failed to add sysctls to debug bundle: %v", err)
+	}
+
 	if err := g.addDNSInfo(); err != nil {
 		log.Errorf("failed to add DNS info to debug bundle: %v", err)
 	}

client/internal/debug/debug_linux.go

@@ -124,15 +124,18 @@ func getSystemdLogs(serviceName string) (string, error) {
 // addFirewallRules collects and adds firewall rules to the archive
 func (g *BundleGenerator) addFirewallRules() error {
 	log.Info("Collecting firewall rules")
-	iptablesRules, err := collectIPTablesRules()
+	g.addIPTablesRulesToBundle("iptables-save", "iptables", "iptables.txt")
+	g.addIPTablesRulesToBundle("ip6tables-save", "ip6tables", "ip6tables.txt")
+
+	ipsetOutput, err := collectIPSets()
 	if err != nil {
-		log.Warnf("Failed to collect iptables rules: %v", err)
+		log.Warnf("Failed to collect ipset information: %v", err)
 	} else {
 		if g.anonymize {
-			iptablesRules = g.anonymizer.AnonymizeString(iptablesRules)
+			ipsetOutput = g.anonymizer.AnonymizeString(ipsetOutput)
 		}
-		if err := g.addFileToZip(strings.NewReader(iptablesRules), "iptables.txt"); err != nil {
-			log.Warnf("Failed to add iptables rules to bundle: %v", err)
+		if err := g.addFileToZip(strings.NewReader(ipsetOutput), "ipset.txt"); err != nil {
+			log.Warnf("Failed to add ipset output to bundle: %v", err)
 		}
 	}
 
@@ -151,44 +154,65 @@ func (g *BundleGenerator) addFirewallRules() error {
 	return nil
 }
 
-// collectIPTablesRules collects rules using both iptables-save and verbose listing
-func collectIPTablesRules() (string, error) {
-	var builder strings.Builder
-
-	saveOutput, err := collectIPTablesSave()
+// addIPTablesRulesToBundle collects iptables/ip6tables rules and writes them to the bundle.
+func (g *BundleGenerator) addIPTablesRulesToBundle(saveBin, listBin, filename string) {
+	rules, err := collectIPTablesRules(saveBin, listBin)
 	if err != nil {
-		log.Warnf("Failed to collect iptables rules using iptables-save: %v", err)
-	} else {
-		builder.WriteString("=== iptables-save output ===\n")
+		log.Warnf("Failed to collect %s rules: %v", listBin, err)
+		return
+	}
+	if g.anonymize {
+		rules = g.anonymizer.AnonymizeString(rules)
+	}
+	if err := g.addFileToZip(strings.NewReader(rules), filename); err != nil {
+		log.Warnf("Failed to add %s rules to bundle: %v", listBin, err)
+	}
+}
+
+// collectIPTablesRules collects rules using both <saveBin> and verbose listing via <listBin>.
+// Returns an error when neither command produced any output (e.g. the binary is missing),
+// so the caller can skip writing an empty file.
+func collectIPTablesRules(saveBin, listBin string) (string, error) {
+	var builder strings.Builder
+	var collected bool
+	var firstErr error
+
+	saveOutput, err := runCommand(saveBin)
+	switch {
+	case err != nil:
+		firstErr = err
+		log.Warnf("Failed to collect %s output: %v", saveBin, err)
+	case strings.TrimSpace(saveOutput) == "":
+		log.Debugf("%s produced no output, skipping", saveBin)
+	default:
+		builder.WriteString(fmt.Sprintf("=== %s output ===\n", saveBin))
 		builder.WriteString(saveOutput)
 		builder.WriteString("\n")
+		collected = true
 	}
 
-	ipsetOutput, err := collectIPSets()
-	if err != nil {
-		log.Warnf("Failed to collect ipset information: %v", err)
-	} else {
-		builder.WriteString("=== ipset list output ===\n")
-		builder.WriteString(ipsetOutput)
-		builder.WriteString("\n")
-	}
-
-	builder.WriteString("=== iptables -v -n -L output ===\n")
+	listHeader := fmt.Sprintf("=== %s -v -n -L output ===\n", listBin)
+	builder.WriteString(listHeader)
 
 	tables := []string{"filter", "nat", "mangle", "raw", "security"}
-
 	for _, table := range tables {
-		builder.WriteString(fmt.Sprintf("*%s\n", table))
-
-		stats, err := getTableStatistics(table)
+		stats, err := runCommand(listBin, "-v", "-n", "-L", "-t", table)
 		if err != nil {
-			log.Warnf("Failed to get statistics for table %s: %v", table, err)
+			if firstErr == nil {
+				firstErr = err
+			}
+			log.Warnf("Failed to get %s statistics for table %s: %v", listBin, table, err)
 			continue
 		}
+		builder.WriteString(fmt.Sprintf("*%s\n", table))
 		builder.WriteString(stats)
 		builder.WriteString("\n")
+		collected = true
 	}
 
+	if !collected {
+		return "", fmt.Errorf("collect %s rules: %w", listBin, firstErr)
+	}
 	return builder.String(), nil
 }
 
@@ -214,34 +238,15 @@ func collectIPSets() (string, error) {
 	return ipsets, nil
 }
 
-// collectIPTablesSave uses iptables-save to get rule definitions
-func collectIPTablesSave() (string, error) {
-	cmd := exec.Command("iptables-save")
+// runCommand executes a command and returns its stdout, wrapping stderr in the error on failure.
+func runCommand(name string, args ...string) (string, error) {
+	cmd := exec.Command(name, args...)
 	var stdout, stderr bytes.Buffer
 	cmd.Stdout = &stdout
 	cmd.Stderr = &stderr
 
 	if err := cmd.Run(); err != nil {
-		return "", fmt.Errorf("execute iptables-save: %w (stderr: %s)", err, stderr.String())
-	}
-
-	rules := stdout.String()
-	if strings.TrimSpace(rules) == "" {
-		return "", fmt.Errorf("no iptables rules found")
-	}
-
-	return rules, nil
-}
-
-// getTableStatistics gets verbose statistics for an entire table using iptables command
-func getTableStatistics(table string) (string, error) {
-	cmd := exec.Command("iptables", "-v", "-n", "-L", "-t", table)
-	var stdout, stderr bytes.Buffer
-	cmd.Stdout = &stdout
-	cmd.Stderr = &stderr
-
-	if err := cmd.Run(); err != nil {
-		return "", fmt.Errorf("execute iptables -v -n -L: %w (stderr: %s)", err, stderr.String())
+		return "", fmt.Errorf("execute %s: %w (stderr: %s)", name, err, stderr.String())
 	}
 
 	return stdout.String(), nil
@@ -804,3 +809,91 @@ func formatSetKeyType(keyType nftables.SetDatatype) string {
 		return fmt.Sprintf("type-%v", keyType)
 	}
 }
+
+// addSysctls collects forwarding and netbird-managed sysctl values and writes them to the bundle.
+func (g *BundleGenerator) addSysctls() error {
+	log.Info("Collecting sysctls")
+	content := collectSysctls()
+	if g.anonymize {
+		content = g.anonymizer.AnonymizeString(content)
+	}
+	if err := g.addFileToZip(strings.NewReader(content), "sysctls.txt"); err != nil {
+		return fmt.Errorf("add sysctls to bundle: %w", err)
+	}
+	return nil
+}
+
+// collectSysctls reads every sysctl that the netbird client may modify, plus
+// global IPv4/IPv6 forwarding, and returns a formatted dump grouped by topic.
+// Per-interface values are enumerated by listing /proc/sys/net/ipv{4,6}/conf.
+func collectSysctls() string {
+	var builder strings.Builder
+
+	writeSysctlGroup(&builder, "forwarding", []string{
+		"net.ipv4.ip_forward",
+		"net.ipv6.conf.all.forwarding",
+		"net.ipv6.conf.default.forwarding",
+	})
+	writeSysctlGroup(&builder, "ipv4 per-interface forwarding", listInterfaceSysctls("ipv4", "forwarding"))
+	writeSysctlGroup(&builder, "ipv6 per-interface forwarding", listInterfaceSysctls("ipv6", "forwarding"))
+	writeSysctlGroup(&builder, "rp_filter", append(
+		[]string{"net.ipv4.conf.all.rp_filter", "net.ipv4.conf.default.rp_filter"},
+		listInterfaceSysctls("ipv4", "rp_filter")...,
+	))
+	writeSysctlGroup(&builder, "src_valid_mark", append(
+		[]string{"net.ipv4.conf.all.src_valid_mark", "net.ipv4.conf.default.src_valid_mark"},
+		listInterfaceSysctls("ipv4", "src_valid_mark")...,
+	))
+	writeSysctlGroup(&builder, "conntrack", []string{
+		"net.netfilter.nf_conntrack_acct",
+		"net.netfilter.nf_conntrack_tcp_loose",
+	})
+	writeSysctlGroup(&builder, "tcp", []string{
+		"net.ipv4.tcp_tw_reuse",
+	})
+
+	return builder.String()
+}
+
+func writeSysctlGroup(builder *strings.Builder, title string, keys []string) {
+	builder.WriteString(fmt.Sprintf("=== %s ===\n", title))
+	for _, key := range keys {
+		value, err := readSysctl(key)
+		if err != nil {
+			builder.WriteString(fmt.Sprintf("%s = <error: %v>\n", key, err))
+			continue
+		}
+		builder.WriteString(fmt.Sprintf("%s = %s\n", key, value))
+	}
+	builder.WriteString("\n")
+}
+
+// listInterfaceSysctls returns net.ipvX.conf.<iface>.<leaf> keys for every
+// interface present in /proc/sys/net/ipvX/conf, skipping "all" and "default"
+// (callers add those explicitly so they appear first).
+func listInterfaceSysctls(family, leaf string) []string {
+	dir := fmt.Sprintf("/proc/sys/net/%s/conf", family)
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return nil
+	}
+	var keys []string
+	for _, e := range entries {
+		name := e.Name()
+		if name == "all" || name == "default" {
+			continue
+		}
+		keys = append(keys, fmt.Sprintf("net.%s.conf.%s.%s", family, name, leaf))
+	}
+	sort.Strings(keys)
+	return keys
+}
+
+func readSysctl(key string) (string, error) {
+	path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/"))
+	value, err := os.ReadFile(path)
+	if err != nil {
+		return "", err
+	}
+	return strings.TrimSpace(string(value)), nil
+}

client/internal/debug/debug_nonlinux.go

@@ -17,3 +17,8 @@ func (g *BundleGenerator) addIPRules() error {
 	// IP rules are only supported on Linux
 	return nil
 }
+
+func (g *BundleGenerator) addSysctls() error {
+	// Sysctl collection is only supported on Linux
+	return nil
+}

client/internal/dns/host.go

@@ -16,6 +16,10 @@ type hostManager interface {
 	restoreHostDNS() error
 	supportCustomPort() bool
 	string() string
+	// getOriginalNameservers returns the OS-side resolvers used as PriorityFallback
+	// upstreams: pre-takeover snapshots on desktop, the OS-pushed list on Android,
+	// hardcoded Quad9 on iOS, nil for noop / mock.
+	getOriginalNameservers() []netip.Addr
 }
 
 type SystemDNSSettings struct {
@@ -131,3 +135,11 @@ func (n noopHostConfigurator) supportCustomPort() bool {
 func (n noopHostConfigurator) string() string {
 	return "noop"
 }
+
+func (n noopHostConfigurator) getOriginalNameservers() []netip.Addr {
+	return nil
+}
+
+func (m *mockHostConfigurator) getOriginalNameservers() []netip.Addr {
+	return nil
+}

client/internal/dns/host_android.go

@@ -1,14 +1,20 @@
 package dns
 
 import (
+	"net/netip"
+
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 )
 
+// androidHostManager is a noop on the OS side (Android's VPN service handles
+// DNS for us) but tracks the OS-reported resolver list pushed via
+// OnUpdatedHostDNSServer so it can serve as the fallback nameserver source.
 type androidHostManager struct {
+	holder *hostsDNSHolder
 }
 
-func newHostManager() (*androidHostManager, error) {
-	return &androidHostManager{}, nil
+func newHostManager(holder *hostsDNSHolder) (*androidHostManager, error) {
+	return &androidHostManager{holder: holder}, nil
 }
 
 func (a androidHostManager) applyDNSConfig(HostDNSConfig, *statemanager.Manager) error {
@@ -26,3 +32,12 @@ func (a androidHostManager) supportCustomPort() bool {
 func (a androidHostManager) string() string {
 	return "none"
 }
+
+func (a androidHostManager) getOriginalNameservers() []netip.Addr {
+	hosts := a.holder.get()
+	out := make([]netip.Addr, 0, len(hosts))
+	for ap := range hosts {
+		out = append(out, ap.Addr())
+	}
+	return out
+}

client/internal/dns/host_ios.go

@@ -3,6 +3,7 @@ package dns
 import (
 	"encoding/json"
 	"fmt"
+	"net/netip"
 
 	log "github.com/sirupsen/logrus"
 
@@ -20,6 +21,14 @@ func newHostManager(dnsManager IosDnsManager) (*iosHostManager, error) {
 	}, nil
 }
 
+func (a iosHostManager) getOriginalNameservers() []netip.Addr {
+	// Quad9 v4+v6: 9.9.9.9, 2620:fe::fe.
+	return []netip.Addr{
+		netip.AddrFrom4([4]byte{9, 9, 9, 9}),
+		netip.AddrFrom16([16]byte{0x26, 0x20, 0x00, 0xfe, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0xfe}),
+	}
+}
+
 func (a iosHostManager) applyDNSConfig(config HostDNSConfig, _ *statemanager.Manager) error {
 	jsonData, err := json.Marshal(config)
 	if err != nil {

client/internal/dns/host_windows.go

@@ -7,6 +7,7 @@ import (
 	"io"
 	"net/netip"
 	"os/exec"
+	"slices"
 	"strings"
 	"syscall"
 	"time"
@@ -44,9 +45,11 @@ const (
 
 	nrptMaxDomainsPerRule = 50
 
-	interfaceConfigPath          = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`
-	interfaceConfigNameServerKey = "NameServer"
-	interfaceConfigSearchListKey = "SearchList"
+	interfaceConfigPath           = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces`
+	interfaceConfigPathV6         = `SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces`
+	interfaceConfigNameServerKey  = "NameServer"
+	interfaceConfigDhcpNameSrvKey = "DhcpNameServer"
+	interfaceConfigSearchListKey  = "SearchList"
 
 	// Network interface DNS registration settings
 	disableDynamicUpdateKey           = "DisableDynamicUpdate"
@@ -67,10 +70,11 @@ const (
 )
 
 type registryConfigurator struct {
-	guid           string
-	routingAll     bool
-	gpo            bool
-	nrptEntryCount int
+	guid            string
+	routingAll      bool
+	gpo             bool
+	nrptEntryCount  int
+	origNameservers []netip.Addr
 }
 
 func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
@@ -94,6 +98,17 @@ func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
 		gpo:  useGPO,
 	}
 
+	origNameservers, err := configurator.captureOriginalNameservers()
+	switch {
+	case err != nil:
+		log.Warnf("capture original nameservers from non-WG adapters: %v", err)
+	case len(origNameservers) == 0:
+		log.Warnf("no original nameservers captured from non-WG adapters; DNS fallback will be empty")
+	default:
+		log.Debugf("captured %d original nameservers from non-WG adapters: %v", len(origNameservers), origNameservers)
+	}
+	configurator.origNameservers = origNameservers
+
 	if err := configurator.configureInterface(); err != nil {
 		log.Errorf("failed to configure interface settings: %v", err)
 	}
@@ -101,6 +116,98 @@ func newHostManager(wgInterface WGIface) (*registryConfigurator, error) {
 	return configurator, nil
 }
 
+// captureOriginalNameservers reads DNS addresses from every Tcpip(6) interface
+// registry key except the WG adapter. v4 and v6 servers live in separate
+// hives (Tcpip vs Tcpip6) keyed by the same interface GUID.
+func (r *registryConfigurator) captureOriginalNameservers() ([]netip.Addr, error) {
+	seen := make(map[netip.Addr]struct{})
+	var out []netip.Addr
+	var merr *multierror.Error
+	for _, root := range []string{interfaceConfigPath, interfaceConfigPathV6} {
+		addrs, err := r.captureFromTcpipRoot(root)
+		if err != nil {
+			merr = multierror.Append(merr, fmt.Errorf("%s: %w", root, err))
+			continue
+		}
+		for _, addr := range addrs {
+			if _, dup := seen[addr]; dup {
+				continue
+			}
+			seen[addr] = struct{}{}
+			out = append(out, addr)
+		}
+	}
+	return out, nberrors.FormatErrorOrNil(merr)
+}
+
+func (r *registryConfigurator) captureFromTcpipRoot(rootPath string) ([]netip.Addr, error) {
+	root, err := registry.OpenKey(registry.LOCAL_MACHINE, rootPath, registry.READ)
+	if err != nil {
+		return nil, fmt.Errorf("open key: %w", err)
+	}
+	defer closer(root)
+
+	guids, err := root.ReadSubKeyNames(-1)
+	if err != nil {
+		return nil, fmt.Errorf("read subkeys: %w", err)
+	}
+
+	var out []netip.Addr
+	for _, guid := range guids {
+		if strings.EqualFold(guid, r.guid) {
+			continue
+		}
+		out = append(out, readInterfaceNameservers(rootPath, guid)...)
+	}
+	return out, nil
+}
+
+func readInterfaceNameservers(rootPath, guid string) []netip.Addr {
+	keyPath := rootPath + "\\" + guid
+	k, err := registry.OpenKey(registry.LOCAL_MACHINE, keyPath, registry.QUERY_VALUE)
+	if err != nil {
+		return nil
+	}
+	defer closer(k)
+
+	// Static NameServer wins over DhcpNameServer for actual resolution.
+	for _, name := range []string{interfaceConfigNameServerKey, interfaceConfigDhcpNameSrvKey} {
+		raw, _, err := k.GetStringValue(name)
+		if err != nil || raw == "" {
+			continue
+		}
+		if out := parseRegistryNameservers(raw); len(out) > 0 {
+			return out
+		}
+	}
+	return nil
+}
+
+func parseRegistryNameservers(raw string) []netip.Addr {
+	var out []netip.Addr
+	for _, field := range strings.FieldsFunc(raw, func(r rune) bool { return r == ',' || r == ' ' || r == '\t' }) {
+		addr, err := netip.ParseAddr(strings.TrimSpace(field))
+		if err != nil {
+			continue
+		}
+		addr = addr.Unmap()
+		if !addr.IsValid() || addr.IsUnspecified() {
+			continue
+		}
+		// Drop unzoned link-local: not routable without a scope id. If
+		// the user wrote "fe80::1%eth0" ParseAddr preserves the zone.
+		if addr.IsLinkLocalUnicast() && addr.Zone() == "" {
+			continue
+		}
+		out = append(out, addr)
+	}
+	return out
+}
+
+func (r *registryConfigurator) getOriginalNameservers() []netip.Addr {
+	return slices.Clone(r.origNameservers)
+}
+
 func (r *registryConfigurator) supportCustomPort() bool {
 	return false
 }

client/internal/dns/hosts_dns_holder.go

@@ -25,6 +25,7 @@ func (h *hostsDNSHolder) set(list []netip.AddrPort) {
 	h.mutex.Unlock()
 }
 
+//nolint:unused
 func (h *hostsDNSHolder) get() map[netip.AddrPort]struct{} {
 	h.mutex.RLock()
 	l := h.unprotectedDNSList

client/internal/dns/local/local.go

@@ -76,8 +76,6 @@ func (d *Resolver) ID() types.HandlerID {
 	return "local-resolver"
 }
 
-func (d *Resolver) ProbeAvailability(context.Context) {}
-
 // ServeDNS handles a DNS request
 func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	logger := log.WithFields(log.Fields{

client/internal/dns/mock_server.go

@@ -9,6 +9,7 @@ import (
 
 	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
 	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
@@ -70,10 +71,6 @@ func (m *MockServer) SearchDomains() []string {
 	return make([]string, 0)
 }
 
-// ProbeAvailability mocks implementation of ProbeAvailability from the Server interface
-func (m *MockServer) ProbeAvailability() {
-}
-
 func (m *MockServer) UpdateServerConfig(domains dnsconfig.ServerDomains) error {
 	if m.UpdateServerConfigFunc != nil {
 		return m.UpdateServerConfigFunc(domains)
@@ -85,8 +82,8 @@ func (m *MockServer) PopulateManagementDomain(mgmtURL *url.URL) error {
 	return nil
 }
 
-// SetRouteChecker mock implementation of SetRouteChecker from Server interface
-func (m *MockServer) SetRouteChecker(func(netip.Addr) bool) {
+// SetRouteSources mock implementation of SetRouteSources from Server interface
+func (m *MockServer) SetRouteSources(selected, active func() route.HAMap) {
 	// Mock implementation - no-op
 }
 

client/internal/dns/network_manager_unix.go

@@ -8,6 +8,7 @@ import (
 	"errors"
 	"fmt"
 	"net/netip"
+	"slices"
 	"strings"
 	"time"
 
@@ -32,6 +33,15 @@ const (
 	networkManagerDbusDeviceGetAppliedConnectionMethod                              = networkManagerDbusDeviceInterface + ".GetAppliedConnection"
 	networkManagerDbusDeviceReapplyMethod                                           = networkManagerDbusDeviceInterface + ".Reapply"
 	networkManagerDbusDeviceDeleteMethod                                            = networkManagerDbusDeviceInterface + ".Delete"
+	networkManagerDbusDeviceIp4ConfigProperty                                       = networkManagerDbusDeviceInterface + ".Ip4Config"
+	networkManagerDbusDeviceIp6ConfigProperty                                       = networkManagerDbusDeviceInterface + ".Ip6Config"
+	networkManagerDbusDeviceIfaceProperty                                           = networkManagerDbusDeviceInterface + ".Interface"
+	networkManagerDbusGetDevicesMethod                                              = networkManagerDest + ".GetDevices"
+	networkManagerDbusIp4ConfigInterface                                            = "org.freedesktop.NetworkManager.IP4Config"
+	networkManagerDbusIp6ConfigInterface                                            = "org.freedesktop.NetworkManager.IP6Config"
+	networkManagerDbusIp4ConfigNameserverDataProperty                               = networkManagerDbusIp4ConfigInterface + ".NameserverData"
+	networkManagerDbusIp4ConfigNameserversProperty                                  = networkManagerDbusIp4ConfigInterface + ".Nameservers"
+	networkManagerDbusIp6ConfigNameserversProperty                                  = networkManagerDbusIp6ConfigInterface + ".Nameservers"
 	networkManagerDbusDefaultBehaviorFlag              networkManagerConfigBehavior = 0
 	networkManagerDbusIPv4Key                                                       = "ipv4"
 	networkManagerDbusIPv6Key                                                       = "ipv6"
@@ -51,9 +61,10 @@ var supportedNetworkManagerVersionConstraints = []string{
 }
 
 type networkManagerDbusConfigurator struct {
-	dbusLinkObject dbus.ObjectPath
-	routingAll     bool
-	ifaceName      string
+	dbusLinkObject  dbus.ObjectPath
+	routingAll      bool
+	ifaceName       string
+	origNameservers []netip.Addr
 }
 
 // the types below are based on dbus specification, each field is mapped to a dbus type
@@ -92,10 +103,200 @@ func newNetworkManagerDbusConfigurator(wgInterface string) (*networkManagerDbusC
 
 	log.Debugf("got network manager dbus Link Object: %s from net interface %s", s, wgInterface)
 
-	return &networkManagerDbusConfigurator{
+	c := &networkManagerDbusConfigurator{
 		dbusLinkObject: dbus.ObjectPath(s),
 		ifaceName:      wgInterface,
-	}, nil
+	}
+
+	origNameservers, err := c.captureOriginalNameservers()
+	switch {
+	case err != nil:
+		log.Warnf("capture original nameservers from NetworkManager: %v", err)
+	case len(origNameservers) == 0:
+		log.Warnf("no original nameservers captured from non-WG NetworkManager devices; DNS fallback will be empty")
+	default:
+		log.Debugf("captured %d original nameservers from non-WG NetworkManager devices: %v", len(origNameservers), origNameservers)
+	}
+	c.origNameservers = origNameservers
+	return c, nil
+}
+
+// captureOriginalNameservers reads DNS servers from every NM device's
+// IP4Config / IP6Config except our WG device.
+func (n *networkManagerDbusConfigurator) captureOriginalNameservers() ([]netip.Addr, error) {
+	devices, err := networkManagerListDevices()
+	if err != nil {
+		return nil, fmt.Errorf("list devices: %w", err)
+	}
+
+	seen := make(map[netip.Addr]struct{})
+	var out []netip.Addr
+	for _, dev := range devices {
+		if dev == n.dbusLinkObject {
+			continue
+		}
+		ifaceName := readNetworkManagerDeviceInterface(dev)
+		for _, addr := range readNetworkManagerDeviceDNS(dev) {
+			addr = addr.Unmap()
+			if !addr.IsValid() || addr.IsUnspecified() {
+				continue
+			}
+			// IP6Config.Nameservers is a byte slice without zone info;
+			// reattach the device's interface name so a captured fe80::…
+			// stays routable.
+			if addr.IsLinkLocalUnicast() && ifaceName != "" {
+				addr = addr.WithZone(ifaceName)
+			}
+			if _, dup := seen[addr]; dup {
+				continue
+			}
+			seen[addr] = struct{}{}
+			out = append(out, addr)
+		}
+	}
+	return out, nil
+}
+
+func readNetworkManagerDeviceInterface(devicePath dbus.ObjectPath) string {
+	obj, closeConn, err := getDbusObject(networkManagerDest, devicePath)
+	if err != nil {
+		return ""
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(networkManagerDbusDeviceIfaceProperty)
+	if err != nil {
+		return ""
+	}
+	s, _ := v.Value().(string)
+	return s
+}
+
+func networkManagerListDevices() ([]dbus.ObjectPath, error) {
+	obj, closeConn, err := getDbusObject(networkManagerDest, networkManagerDbusObjectNode)
+	if err != nil {
+		return nil, fmt.Errorf("dbus NetworkManager: %w", err)
+	}
+	defer closeConn()
+	var devs []dbus.ObjectPath
+	if err := obj.Call(networkManagerDbusGetDevicesMethod, dbusDefaultFlag).Store(&devs); err != nil {
+		return nil, err
+	}
+	return devs, nil
+}
+
+func readNetworkManagerDeviceDNS(devicePath dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(networkManagerDest, devicePath)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+
+	var out []netip.Addr
+	if path := readNetworkManagerConfigPath(obj, networkManagerDbusDeviceIp4ConfigProperty); path != "" {
+		out = append(out, readIPv4ConfigDNS(path)...)
+	}
+	if path := readNetworkManagerConfigPath(obj, networkManagerDbusDeviceIp6ConfigProperty); path != "" {
+		out = append(out, readIPv6ConfigDNS(path)...)
+	}
+	return out
+}
+
+func readNetworkManagerConfigPath(obj dbus.BusObject, property string) dbus.ObjectPath {
+	v, err := obj.GetProperty(property)
+	if err != nil {
+		return ""
+	}
+	path, ok := v.Value().(dbus.ObjectPath)
+	if !ok || path == "/" {
+		return ""
+	}
+	return path
+}
+
+func readIPv4ConfigDNS(path dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(networkManagerDest, path)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+
+	// NameserverData (NM 1.13+) carries strings; older NMs only expose the
+	// legacy uint32 Nameservers property.
+	if out := readIPv4NameserverData(obj); len(out) > 0 {
+		return out
+	}
+	return readIPv4LegacyNameservers(obj)
+}
+
+func readIPv4NameserverData(obj dbus.BusObject) []netip.Addr {
+	v, err := obj.GetProperty(networkManagerDbusIp4ConfigNameserverDataProperty)
+	if err != nil {
+		return nil
+	}
+	entries, ok := v.Value().([]map[string]dbus.Variant)
+	if !ok {
+		return nil
+	}
+	var out []netip.Addr
+	for _, entry := range entries {
+		addrVar, ok := entry["address"]
+		if !ok {
+			continue
+		}
+		s, ok := addrVar.Value().(string)
+		if !ok {
+			continue
+		}
+		if a, err := netip.ParseAddr(s); err == nil {
+			out = append(out, a)
+		}
+	}
+	return out
+}
+
+func readIPv4LegacyNameservers(obj dbus.BusObject) []netip.Addr {
+	v, err := obj.GetProperty(networkManagerDbusIp4ConfigNameserversProperty)
+	if err != nil {
+		return nil
+	}
+	raw, ok := v.Value().([]uint32)
+	if !ok {
+		return nil
+	}
+	out := make([]netip.Addr, 0, len(raw))
+	for _, n := range raw {
+		var b [4]byte
+		binary.LittleEndian.PutUint32(b[:], n)
+		out = append(out, netip.AddrFrom4(b))
+	}
+	return out
+}
+
+func readIPv6ConfigDNS(path dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(networkManagerDest, path)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(networkManagerDbusIp6ConfigNameserversProperty)
+	if err != nil {
+		return nil
+	}
+	raw, ok := v.Value().([][]byte)
+	if !ok {
+		return nil
+	}
+	out := make([]netip.Addr, 0, len(raw))
+	for _, b := range raw {
+		if a, ok := netip.AddrFromSlice(b); ok {
+			out = append(out, a)
+		}
+	}
+	return out
+}
+
+func (n *networkManagerDbusConfigurator) getOriginalNameservers() []netip.Addr {
+	return slices.Clone(n.origNameservers)
 }
 
 func (n *networkManagerDbusConfigurator) supportCustomPort() bool {

client/internal/dns/server_android.go

@@ -1,5 +1,5 @@
 package dns
 
 func (s *DefaultServer) initialize() (manager hostManager, err error) {
-	return newHostManager()
+	return newHostManager(s.hostsDNSHolder)
 }

client/internal/dns/server_test.go

@@ -6,7 +6,7 @@ import (
 	"net"
 	"net/netip"
 	"os"
-	"strings"
+	"runtime"
 	"testing"
 	"time"
 
@@ -15,6 +15,7 @@ import (
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/mock"
+	"github.com/stretchr/testify/require"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
@@ -31,8 +32,10 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/client/proto"
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/formatter"
+	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
@@ -101,16 +104,17 @@ func init() {
 	formatter.SetTextFormatter(log.StandardLogger())
 }
 
-func generateDummyHandler(domain string, servers []nbdns.NameServer) *upstreamResolverBase {
+func generateDummyHandler(d string, servers []nbdns.NameServer) *upstreamResolverBase {
 	var srvs []netip.AddrPort
 	for _, srv := range servers {
 		srvs = append(srvs, srv.AddrPort())
 	}
-	return &upstreamResolverBase{
-		domain:          domain,
-		upstreamServers: srvs,
-		cancel:          func() {},
+	u := &upstreamResolverBase{
+		domain: domain.Domain(d),
+		cancel: func() {},
 	}
+	u.addRace(srvs)
+	return u
 }
 
 func TestUpdateDNSServer(t *testing.T) {
@@ -653,74 +657,8 @@ func TestDNSServerStartStop(t *testing.T) {
 	}
 }
 
-func TestDNSServerUpstreamDeactivateCallback(t *testing.T) {
-	hostManager := &mockHostConfigurator{}
-	server := DefaultServer{
-		ctx:           context.Background(),
-		service:       NewServiceViaMemory(&mocWGIface{}),
-		localResolver: local.NewResolver(),
-		handlerChain:  NewHandlerChain(),
-		hostManager:   hostManager,
-		currentConfig: HostDNSConfig{
-			Domains: []DomainConfig{
-				{false, "domain0", false},
-				{false, "domain1", false},
-				{false, "domain2", false},
-			},
-		},
-		statusRecorder: peer.NewRecorder("mgm"),
-	}
-
-	var domainsUpdate string
-	hostManager.applyDNSConfigFunc = func(config HostDNSConfig, statemanager *statemanager.Manager) error {
-		domains := []string{}
-		for _, item := range config.Domains {
-			if item.Disabled {
-				continue
-			}
-			domains = append(domains, item.Domain)
-		}
-		domainsUpdate = strings.Join(domains, ",")
-		return nil
-	}
-
-	deactivate, reactivate := server.upstreamCallbacks(&nbdns.NameServerGroup{
-		Domains: []string{"domain1"},
-		NameServers: []nbdns.NameServer{
-			{IP: netip.MustParseAddr("8.8.0.0"), NSType: nbdns.UDPNameServerType, Port: 53},
-		},
-	}, nil, 0)
-
-	deactivate(nil)
-	expected := "domain0,domain2"
-	domains := []string{}
-	for _, item := range server.currentConfig.Domains {
-		if item.Disabled {
-			continue
-		}
-		domains = append(domains, item.Domain)
-	}
-	got := strings.Join(domains, ",")
-	if expected != got {
-		t.Errorf("expected domains list: %q, got %q", expected, got)
-	}
-
-	reactivate()
-	expected = "domain0,domain1,domain2"
-	domains = []string{}
-	for _, item := range server.currentConfig.Domains {
-		if item.Disabled {
-			continue
-		}
-		domains = append(domains, item.Domain)
-	}
-	got = strings.Join(domains, ",")
-	if expected != got {
-		t.Errorf("expected domains list: %q, got %q", expected, domainsUpdate)
-	}
-}
-
 func TestDNSPermanent_updateHostDNS_emptyUpstream(t *testing.T) {
+	skipUnlessAndroid(t)
 	wgIFace, err := createWgInterfaceWithBind(t)
 	if err != nil {
 		t.Fatal("failed to initialize wg interface")
@@ -748,6 +686,7 @@ func TestDNSPermanent_updateHostDNS_emptyUpstream(t *testing.T) {
 }
 
 func TestDNSPermanent_updateUpstream(t *testing.T) {
+	skipUnlessAndroid(t)
 	wgIFace, err := createWgInterfaceWithBind(t)
 	if err != nil {
 		t.Fatal("failed to initialize wg interface")
@@ -841,6 +780,7 @@ func TestDNSPermanent_updateUpstream(t *testing.T) {
 }
 
 func TestDNSPermanent_matchOnly(t *testing.T) {
+	skipUnlessAndroid(t)
 	wgIFace, err := createWgInterfaceWithBind(t)
 	if err != nil {
 		t.Fatal("failed to initialize wg interface")
@@ -913,6 +853,18 @@ func TestDNSPermanent_matchOnly(t *testing.T) {
 	}
 }
 
+// skipUnlessAndroid marks tests that exercise the mobile-permanent DNS path,
+// which only matches a real production setup on android (NewDefaultServerPermanentUpstream
+// + androidHostManager). On non-android the desktop host manager replaces it
+// during Initialize and the assertion stops making sense. Skipped here until we
+// have an android CI runner.
+func skipUnlessAndroid(t *testing.T) {
+	t.Helper()
+	if runtime.GOOS != "android" {
+		t.Skip("requires android runner; mobile-permanent path doesn't match production on this OS")
+	}
+}
+
 func createWgInterfaceWithBind(t *testing.T) (*iface.WGIface, error) {
 	t.Helper()
 	ov := os.Getenv("NB_WG_KERNEL_DISABLED")
@@ -1065,7 +1017,6 @@ type mockHandler struct {
 
 func (m *mockHandler) ServeDNS(dns.ResponseWriter, *dns.Msg) {}
 func (m *mockHandler) Stop()                                 {}
-func (m *mockHandler) ProbeAvailability(context.Context)     {}
 func (m *mockHandler) ID() types.HandlerID                   { return types.HandlerID(m.Id) }
 
 type mockService struct{}
@@ -2085,6 +2036,598 @@ func TestLocalResolverPriorityConstants(t *testing.T) {
 	assert.Equal(t, "local.example.com", localMuxUpdates[0].domain)
 }
 
+// TestBuildUpstreamHandler_MergesGroupsPerDomain verifies that multiple
+// admin-defined nameserver groups targeting the same domain collapse into a
+// single handler with each group preserved as a sequential inner list.
+func TestBuildUpstreamHandler_MergesGroupsPerDomain(t *testing.T) {
+	wgInterface := &mocWGIface{}
+	service := NewServiceViaMemory(wgInterface)
+	server := &DefaultServer{
+		ctx:           context.Background(),
+		wgInterface:   wgInterface,
+		service:       service,
+		localResolver: local.NewResolver(),
+		handlerChain:  NewHandlerChain(),
+		hostManager:   &noopHostConfigurator{},
+		dnsMuxMap:     make(registeredHandlerMap),
+	}
+
+	groups := []*nbdns.NameServerGroup{
+		{
+			NameServers: []nbdns.NameServer{
+				{IP: netip.MustParseAddr("192.0.2.1"), NSType: nbdns.UDPNameServerType, Port: 53},
+			},
+			Domains: []string{"example.com"},
+		},
+		{
+			NameServers: []nbdns.NameServer{
+				{IP: netip.MustParseAddr("192.0.2.2"), NSType: nbdns.UDPNameServerType, Port: 53},
+				{IP: netip.MustParseAddr("192.0.2.3"), NSType: nbdns.UDPNameServerType, Port: 53},
+			},
+			Domains: []string{"example.com"},
+		},
+	}
+
+	muxUpdates, err := server.buildUpstreamHandlerUpdate(groups)
+	require.NoError(t, err)
+	require.Len(t, muxUpdates, 1, "same-domain groups should merge into one handler")
+	assert.Equal(t, "example.com", muxUpdates[0].domain)
+	assert.Equal(t, PriorityUpstream, muxUpdates[0].priority)
+
+	handler := muxUpdates[0].handler.(*upstreamResolver)
+	require.Len(t, handler.upstreamServers, 2, "handler should have two groups")
+	assert.Equal(t, upstreamRace{netip.MustParseAddrPort("192.0.2.1:53")}, handler.upstreamServers[0])
+	assert.Equal(t, upstreamRace{
+		netip.MustParseAddrPort("192.0.2.2:53"),
+		netip.MustParseAddrPort("192.0.2.3:53"),
+	}, handler.upstreamServers[1])
+}
+
+// TestEvaluateNSGroupHealth covers the records-only verdict. The gate
+// (overlay route selected-but-no-active-peer) is intentionally NOT an
+// input to the evaluator anymore: the verdict drives the Enabled flag,
+// which must always reflect what we actually observed. Gate-aware event
+// suppression is tested separately in the projection test.
+//
+// Matrix per upstream: {no record, fresh Ok, fresh Fail, stale Fail,
+// stale Ok, Ok newer than Fail, Fail newer than Ok}.
+// Group verdict: any fresh-working → Healthy; any fresh-broken with no
+// fresh-working → Unhealthy; otherwise Undecided.
+func TestEvaluateNSGroupHealth(t *testing.T) {
+	now := time.Now()
+	a := netip.MustParseAddrPort("192.0.2.1:53")
+	b := netip.MustParseAddrPort("192.0.2.2:53")
+
+	recentOk := UpstreamHealth{LastOk: now.Add(-2 * time.Second)}
+	recentFail := UpstreamHealth{LastFail: now.Add(-1 * time.Second), LastErr: "timeout"}
+	staleOk := UpstreamHealth{LastOk: now.Add(-10 * time.Minute)}
+	staleFail := UpstreamHealth{LastFail: now.Add(-10 * time.Minute), LastErr: "timeout"}
+	okThenFail := UpstreamHealth{
+		LastOk:   now.Add(-10 * time.Second),
+		LastFail: now.Add(-1 * time.Second),
+		LastErr:  "timeout",
+	}
+	failThenOk := UpstreamHealth{
+		LastOk:   now.Add(-1 * time.Second),
+		LastFail: now.Add(-10 * time.Second),
+		LastErr:  "timeout",
+	}
+
+	tests := []struct {
+		name         string
+		health       map[netip.AddrPort]UpstreamHealth
+		servers      []netip.AddrPort
+		wantVerdict  nsGroupVerdict
+		wantErrSubst string
+	}{
+		{
+			name:        "no record, undecided",
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictUndecided,
+		},
+		{
+			name:        "fresh success, healthy",
+			health:      map[netip.AddrPort]UpstreamHealth{a: recentOk},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictHealthy,
+		},
+		{
+			name:         "fresh failure, unhealthy",
+			health:       map[netip.AddrPort]UpstreamHealth{a: recentFail},
+			servers:      []netip.AddrPort{a},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "timeout",
+		},
+		{
+			name:        "only stale success, undecided",
+			health:      map[netip.AddrPort]UpstreamHealth{a: staleOk},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictUndecided,
+		},
+		{
+			name:        "only stale failure, undecided",
+			health:      map[netip.AddrPort]UpstreamHealth{a: staleFail},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictUndecided,
+		},
+		{
+			name:         "both fresh, fail newer, unhealthy",
+			health:       map[netip.AddrPort]UpstreamHealth{a: okThenFail},
+			servers:      []netip.AddrPort{a},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "timeout",
+		},
+		{
+			name:        "both fresh, ok newer, healthy",
+			health:      map[netip.AddrPort]UpstreamHealth{a: failThenOk},
+			servers:     []netip.AddrPort{a},
+			wantVerdict: nsVerdictHealthy,
+		},
+		{
+			name: "two upstreams, one success wins",
+			health: map[netip.AddrPort]UpstreamHealth{
+				a: recentFail,
+				b: recentOk,
+			},
+			servers:     []netip.AddrPort{a, b},
+			wantVerdict: nsVerdictHealthy,
+		},
+		{
+			name: "two upstreams, one fail one unseen, unhealthy",
+			health: map[netip.AddrPort]UpstreamHealth{
+				a: recentFail,
+			},
+			servers:      []netip.AddrPort{a, b},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "timeout",
+		},
+		{
+			name: "two upstreams, all recent failures, unhealthy",
+			health: map[netip.AddrPort]UpstreamHealth{
+				a: {LastFail: now.Add(-5 * time.Second), LastErr: "timeout"},
+				b: {LastFail: now.Add(-1 * time.Second), LastErr: "SERVFAIL"},
+			},
+			servers:      []netip.AddrPort{a, b},
+			wantVerdict:  nsVerdictUnhealthy,
+			wantErrSubst: "SERVFAIL",
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			verdict, err := evaluateNSGroupHealth(tc.health, tc.servers, now)
+			assert.Equal(t, tc.wantVerdict, verdict, "verdict mismatch")
+			if tc.wantErrSubst != "" {
+				require.Error(t, err)
+				assert.Contains(t, err.Error(), tc.wantErrSubst)
+			} else {
+				assert.NoError(t, err)
+			}
+		})
+	}
+}
+
+// healthStubHandler is a minimal dnsMuxMap entry that exposes a fixed
+// UpstreamHealth snapshot, letting tests drive recomputeNSGroupStates
+// without spinning up real handlers.
+type healthStubHandler struct {
+	health map[netip.AddrPort]UpstreamHealth
+}
+
+func (h *healthStubHandler) ServeDNS(dns.ResponseWriter, *dns.Msg) {}
+func (h *healthStubHandler) Stop()                                 {}
+func (h *healthStubHandler) ID() types.HandlerID                   { return "health-stub" }
+func (h *healthStubHandler) UpstreamHealth() map[netip.AddrPort]UpstreamHealth {
+	return h.health
+}
+
+// TestProjection_SteadyStateIsSilent guards against duplicate events:
+// while a group stays Unhealthy tick after tick, only the first
+// Unhealthy transition may emit. Same for staying Healthy.
+func TestProjection_SteadyStateIsSilent(t *testing.T) {
+	fx := newProjTestFixture(t)
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "first fail emits warning")
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.tick()
+	fx.expectNoEvent("staying unhealthy must not re-emit")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "recovery on transition")
+
+	fx.tick()
+	fx.tick()
+	fx.expectNoEvent("staying healthy must not re-emit")
+}
+
+// projTestFixture is the common setup for the projection tests: a
+// single-upstream group whose route classification the test can flip by
+// assigning to selected/active. Callers drive failures/successes by
+// mutating stub.health and calling refreshHealth.
+type projTestFixture struct {
+	t        *testing.T
+	recorder *peer.Status
+	events   <-chan *proto.SystemEvent
+	server   *DefaultServer
+	stub     *healthStubHandler
+	group    *nbdns.NameServerGroup
+	srv      netip.AddrPort
+	selected route.HAMap
+	active   route.HAMap
+}
+
+func newProjTestFixture(t *testing.T) *projTestFixture {
+	t.Helper()
+	recorder := peer.NewRecorder("mgm")
+	sub := recorder.SubscribeToEvents()
+	t.Cleanup(func() { recorder.UnsubscribeFromEvents(sub) })
+
+	srv := netip.MustParseAddrPort("100.64.0.1:53")
+	fx := &projTestFixture{
+		t:        t,
+		recorder: recorder,
+		events:   sub.Events(),
+		stub:     &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{}},
+		srv:      srv,
+		group: &nbdns.NameServerGroup{
+			Domains:     []string{"example.com"},
+			NameServers: []nbdns.NameServer{{IP: srv.Addr(), NSType: nbdns.UDPNameServerType, Port: int(srv.Port())}},
+		},
+	}
+	fx.server = &DefaultServer{
+		ctx:              context.Background(),
+		wgInterface:      &mocWGIface{},
+		statusRecorder:   recorder,
+		dnsMuxMap:        make(registeredHandlerMap),
+		selectedRoutes:   func() route.HAMap { return fx.selected },
+		activeRoutes:     func() route.HAMap { return fx.active },
+		warningDelayBase: defaultWarningDelayBase,
+	}
+	fx.server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: fx.stub, priority: PriorityUpstream}
+
+	fx.server.mux.Lock()
+	fx.server.updateNSGroupStates([]*nbdns.NameServerGroup{fx.group})
+	fx.server.mux.Unlock()
+	return fx
+}
+
+func (f *projTestFixture) setHealth(h UpstreamHealth) {
+	f.stub.health = map[netip.AddrPort]UpstreamHealth{f.srv: h}
+}
+
+func (f *projTestFixture) tick() []peer.NSGroupState {
+	f.server.refreshHealth()
+	return f.recorder.GetDNSStates()
+}
+
+func (f *projTestFixture) expectNoEvent(why string) {
+	f.t.Helper()
+	select {
+	case evt := <-f.events:
+		f.t.Fatalf("unexpected event (%s): %+v", why, evt)
+	case <-time.After(100 * time.Millisecond):
+	}
+}
+
+func (f *projTestFixture) expectEvent(substr, why string) *proto.SystemEvent {
+	f.t.Helper()
+	select {
+	case evt := <-f.events:
+		assert.Contains(f.t, evt.Message, substr, why)
+		return evt
+	case <-time.After(time.Second):
+		f.t.Fatalf("expected event (%s) with %q", why, substr)
+		return nil
+	}
+}
+
+var overlayNetForTest = netip.MustParsePrefix("100.64.0.0/16")
+var overlayMapForTest = route.HAMap{"overlay": {{Network: overlayNetForTest}}}
+
+// TestProjection_PublicFailEmitsImmediately covers rule 1: an upstream
+// that is not inside any selected route (public DNS) fires the warning
+// on the first Unhealthy tick, no grace period.
+func TestProjection_PublicFailEmitsImmediately(t *testing.T) {
+	fx := newProjTestFixture(t)
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.False(t, states[0].Enabled)
+	fx.expectEvent("unreachable", "public DNS failure")
+}
+
+// TestProjection_OverlayConnectedFailEmitsImmediately covers rule 2:
+// the upstream is inside a selected route AND the route has a Connected
+// peer. Tunnel is up, failure is real, emit immediately.
+func TestProjection_OverlayConnectedFailEmitsImmediately(t *testing.T) {
+	fx := newProjTestFixture(t)
+	fx.selected = overlayMapForTest
+	fx.active = overlayMapForTest
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.False(t, states[0].Enabled)
+	fx.expectEvent("unreachable", "overlay + connected failure")
+}
+
+// TestProjection_OverlayNotConnectedDelaysWarning covers rule 3: the
+// upstream is routed but no peer is Connected (Connecting/Idle/missing).
+// First tick: Unhealthy display, no warning. After the grace window
+// elapses with no recovery, the warning fires.
+func TestProjection_OverlayNotConnectedDelaysWarning(t *testing.T) {
+	grace := 50 * time.Millisecond
+	fx := newProjTestFixture(t)
+	fx.server.warningDelayBase = grace
+	fx.selected = overlayMapForTest
+	// active stays nil: routed but not connected.
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.False(t, states[0].Enabled, "display must reflect failure even during grace window")
+	fx.expectNoEvent("first fail tick within grace window")
+
+	time.Sleep(grace + 10*time.Millisecond)
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "warning after grace window")
+}
+
+// TestProjection_OverlayAddrNoRouteDelaysWarning covers an upstream
+// whose address is inside the WireGuard overlay range but is not
+// covered by any selected route (peer-to-peer DNS without an explicit
+// route). Until a peer reports Connected for that address, startup
+// failures must be held just like the routed case.
+func TestProjection_OverlayAddrNoRouteDelaysWarning(t *testing.T) {
+	recorder := peer.NewRecorder("mgm")
+	sub := recorder.SubscribeToEvents()
+	t.Cleanup(func() { recorder.UnsubscribeFromEvents(sub) })
+
+	overlayPeer := netip.MustParseAddrPort("100.66.100.5:53")
+	server := &DefaultServer{
+		ctx:              context.Background(),
+		wgInterface:      &mocWGIface{},
+		statusRecorder:   recorder,
+		dnsMuxMap:        make(registeredHandlerMap),
+		selectedRoutes:   func() route.HAMap { return nil },
+		activeRoutes:     func() route.HAMap { return nil },
+		warningDelayBase: 50 * time.Millisecond,
+	}
+	group := &nbdns.NameServerGroup{
+		Domains:     []string{"example.com"},
+		NameServers: []nbdns.NameServer{{IP: overlayPeer.Addr(), NSType: nbdns.UDPNameServerType, Port: int(overlayPeer.Port())}},
+	}
+	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{
+		overlayPeer: {LastFail: time.Now(), LastErr: "timeout"},
+	}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+
+	server.mux.Lock()
+	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
+	server.mux.Unlock()
+	server.refreshHealth()
+
+	select {
+	case evt := <-sub.Events():
+		t.Fatalf("unexpected event during grace window: %+v", evt)
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	time.Sleep(60 * time.Millisecond)
+	stub.health = map[netip.AddrPort]UpstreamHealth{overlayPeer: {LastFail: time.Now(), LastErr: "timeout"}}
+	server.refreshHealth()
+
+	select {
+	case evt := <-sub.Events():
+		assert.Contains(t, evt.Message, "unreachable")
+	case <-time.After(time.Second):
+		t.Fatal("expected warning after grace window")
+	}
+}
+
+// TestProjection_StopClearsHealthState verifies that Stop wipes the
+// per-group projection state so a subsequent Start doesn't inherit
+// sticky flags (notably everHealthy) that would bypass the grace
+// window during the next peer handshake.
+func TestProjection_StopClearsHealthState(t *testing.T) {
+	wgIface := &mocWGIface{}
+	server := &DefaultServer{
+		ctx:               context.Background(),
+		wgInterface:       wgIface,
+		service:           NewServiceViaMemory(wgIface),
+		hostManager:       &noopHostConfigurator{},
+		extraDomains:      map[domain.Domain]int{},
+		dnsMuxMap:         make(registeredHandlerMap),
+		statusRecorder:    peer.NewRecorder("mgm"),
+		selectedRoutes:    func() route.HAMap { return nil },
+		activeRoutes:      func() route.HAMap { return nil },
+		warningDelayBase:  defaultWarningDelayBase,
+		currentConfigHash: ^uint64(0),
+	}
+	server.ctx, server.ctxCancel = context.WithCancel(context.Background())
+
+	srv := netip.MustParseAddrPort("8.8.8.8:53")
+	group := &nbdns.NameServerGroup{
+		Domains:     []string{"example.com"},
+		NameServers: []nbdns.NameServer{{IP: srv.Addr(), NSType: nbdns.UDPNameServerType, Port: int(srv.Port())}},
+	}
+	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{srv: {LastOk: time.Now()}}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+
+	server.mux.Lock()
+	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
+	server.mux.Unlock()
+	server.refreshHealth()
+
+	server.healthProjectMu.Lock()
+	p, ok := server.nsGroupProj[generateGroupKey(group)]
+	server.healthProjectMu.Unlock()
+	require.True(t, ok, "projection state should exist after tick")
+	require.True(t, p.everHealthy, "tick with success must set everHealthy")
+
+	server.Stop()
+
+	server.healthProjectMu.Lock()
+	cleared := server.nsGroupProj == nil
+	server.healthProjectMu.Unlock()
+	assert.True(t, cleared, "Stop must clear nsGroupProj")
+}
+
+// TestProjection_OverlayRecoversDuringGrace covers the happy path of
+// rule 3: startup failures while the peer is handshaking, then the peer
+// comes up and a query succeeds before the grace window elapses. No
+// warning should ever have fired, and no recovery either.
+func TestProjection_OverlayRecoversDuringGrace(t *testing.T) {
+	fx := newProjTestFixture(t)
+	fx.server.warningDelayBase = 200 * time.Millisecond
+	fx.selected = overlayMapForTest
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectNoEvent("fail within grace, warning suppressed")
+
+	fx.active = overlayMapForTest
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.True(t, states[0].Enabled)
+	fx.expectNoEvent("recovery without prior warning must not emit")
+}
+
+// TestProjection_RecoveryOnlyAfterWarning enforces the invariant the
+// whole design leans on: recovery events only appear when a warning
+// event was actually emitted for the current streak. A Healthy verdict
+// without a prior warning is silent, so the user never sees "recovered"
+// out of thin air.
+func TestProjection_RecoveryOnlyAfterWarning(t *testing.T) {
+	fx := newProjTestFixture(t)
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	states := fx.tick()
+	require.Len(t, states, 1)
+	assert.True(t, states[0].Enabled)
+	fx.expectNoEvent("first healthy tick should not recover anything")
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "public fail emits immediately")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "recovery follows real warning")
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "second cycle warning")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "second cycle recovery")
+}
+
+// TestProjection_EverHealthyOverridesDelay covers rule 4: once a group
+// has ever been Healthy, subsequent failures skip the grace window even
+// if classification says "routed + not connected". The system has
+// proved it can work, so any new failure is real.
+func TestProjection_EverHealthyOverridesDelay(t *testing.T) {
+	fx := newProjTestFixture(t)
+	// Large base so any emission must come from the everHealthy bypass, not elapsed time.
+	fx.server.warningDelayBase = time.Hour
+	fx.selected = overlayMapForTest
+	fx.active = overlayMapForTest
+
+	// Establish "ever healthy".
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectNoEvent("first healthy tick")
+
+	// Peer drops. Query fails. Routed + not connected → normally grace,
+	// but everHealthy flag bypasses it.
+	fx.active = nil
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "failure after ever-healthy must be immediate")
+}
+
+// TestProjection_ReconnectBlipEmitsPair covers the explicit tradeoff
+// from the design discussion: once a group has been healthy, a brief
+// reconnect that produces a failing tick will fire warning + recovery.
+// This is by design: user-visible blips are accurate signal, not noise.
+func TestProjection_ReconnectBlipEmitsPair(t *testing.T) {
+	fx := newProjTestFixture(t)
+	fx.selected = overlayMapForTest
+	fx.active = overlayMapForTest
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+
+	fx.setHealth(UpstreamHealth{LastFail: time.Now(), LastErr: "timeout"})
+	fx.tick()
+	fx.expectEvent("unreachable", "blip warning")
+
+	fx.setHealth(UpstreamHealth{LastOk: time.Now()})
+	fx.tick()
+	fx.expectEvent("recovered", "blip recovery")
+}
+
+// TestProjection_MixedGroupEmitsImmediately covers the multi-upstream
+// rule: a group with at least one public upstream is in the "immediate"
+// category regardless of the other upstreams' routing, because the
+// public one has no peer-startup excuse. Prevents public-DNS failures
+// from being hidden behind a routed sibling.
+func TestProjection_MixedGroupEmitsImmediately(t *testing.T) {
+	recorder := peer.NewRecorder("mgm")
+	sub := recorder.SubscribeToEvents()
+	t.Cleanup(func() { recorder.UnsubscribeFromEvents(sub) })
+	events := sub.Events()
+
+	public := netip.MustParseAddrPort("8.8.8.8:53")
+	overlay := netip.MustParseAddrPort("100.64.0.1:53")
+	overlayMap := route.HAMap{"overlay": {{Network: netip.MustParsePrefix("100.64.0.0/16")}}}
+
+	server := &DefaultServer{
+		ctx:              context.Background(),
+		statusRecorder:   recorder,
+		dnsMuxMap:        make(registeredHandlerMap),
+		selectedRoutes:   func() route.HAMap { return overlayMap },
+		activeRoutes:     func() route.HAMap { return nil },
+		warningDelayBase: time.Hour,
+	}
+	group := &nbdns.NameServerGroup{
+		Domains: []string{"example.com"},
+		NameServers: []nbdns.NameServer{
+			{IP: public.Addr(), NSType: nbdns.UDPNameServerType, Port: int(public.Port())},
+			{IP: overlay.Addr(), NSType: nbdns.UDPNameServerType, Port: int(overlay.Port())},
+		},
+	}
+	stub := &healthStubHandler{
+		health: map[netip.AddrPort]UpstreamHealth{
+			public:  {LastFail: time.Now(), LastErr: "servfail"},
+			overlay: {LastFail: time.Now(), LastErr: "timeout"},
+		},
+	}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+
+	server.mux.Lock()
+	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
+	server.mux.Unlock()
+	server.refreshHealth()
+
+	select {
+	case evt := <-events:
+		assert.Contains(t, evt.Message, "unreachable")
+	case <-time.After(time.Second):
+		t.Fatal("expected immediate warning because group contains a public upstream")
+	}
+}
+
 func TestDNSLoopPrevention(t *testing.T) {
 	wgInterface := &mocWGIface{}
 	service := NewServiceViaMemory(wgInterface)
@@ -2183,17 +2726,18 @@ func TestDNSLoopPrevention(t *testing.T) {
 
 			if tt.expectedHandlers > 0 {
 				handler := muxUpdates[0].handler.(*upstreamResolver)
-				assert.Len(t, handler.upstreamServers, len(tt.expectedServers))
+				flat := handler.flatUpstreams()
+				assert.Len(t, flat, len(tt.expectedServers))
 
 				if tt.shouldFilterOwnIP {
-					for _, upstream := range handler.upstreamServers {
+					for _, upstream := range flat {
 						assert.NotEqual(t, dnsServerIP, upstream.Addr())
 					}
 				}
 
 				for _, expected := range tt.expectedServers {
 					found := false
-					for _, upstream := range handler.upstreamServers {
+					for _, upstream := range flat {
 						if upstream.Addr() == expected {
 							found = true
 							break

client/internal/dns/systemd_linux.go

@@ -8,6 +8,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"slices"
 	"time"
 
 	"github.com/godbus/dbus/v5"
@@ -40,10 +41,17 @@ const (
 )
 
 type systemdDbusConfigurator struct {
-	dbusLinkObject dbus.ObjectPath
-	ifaceName      string
+	dbusLinkObject  dbus.ObjectPath
+	ifaceName       string
+	wgIndex         int
+	origNameservers []netip.Addr
 }
 
+const (
+	systemdDbusLinkDNSProperty          = systemdDbusLinkInterface + ".DNS"
+	systemdDbusLinkDefaultRouteProperty = systemdDbusLinkInterface + ".DefaultRoute"
+)
+
 // the types below are based on dbus specification, each field is mapped to a dbus type
 // see https://dbus.freedesktop.org/doc/dbus-specification.html#basic-types for more details on dbus types
 // see https://www.freedesktop.org/software/systemd/man/org.freedesktop.resolve1.html on resolve1 input types
@@ -79,10 +87,145 @@ func newSystemdDbusConfigurator(wgInterface string) (*systemdDbusConfigurator, e
 
 	log.Debugf("got dbus Link interface: %s from net interface %s and index %d", s, iface.Name, iface.Index)
 
-	return &systemdDbusConfigurator{
+	c := &systemdDbusConfigurator{
 		dbusLinkObject: dbus.ObjectPath(s),
 		ifaceName:      wgInterface,
-	}, nil
+		wgIndex:        iface.Index,
+	}
+
+	origNameservers, err := c.captureOriginalNameservers()
+	switch {
+	case err != nil:
+		log.Warnf("capture original nameservers from systemd-resolved: %v", err)
+	case len(origNameservers) == 0:
+		log.Warnf("no original nameservers captured from systemd-resolved default-route links; DNS fallback will be empty")
+	default:
+		log.Debugf("captured %d original nameservers from systemd-resolved default-route links: %v", len(origNameservers), origNameservers)
+	}
+	c.origNameservers = origNameservers
+	return c, nil
+}
+
+// captureOriginalNameservers reads per-link DNS from systemd-resolved for
+// every default-route link except our own WG link. Non-default-route links
+// (VPNs, docker bridges) are skipped because their upstreams wouldn't
+// actually serve host queries.
+func (s *systemdDbusConfigurator) captureOriginalNameservers() ([]netip.Addr, error) {
+	ifaces, err := net.Interfaces()
+	if err != nil {
+		return nil, fmt.Errorf("list interfaces: %w", err)
+	}
+
+	seen := make(map[netip.Addr]struct{})
+	var out []netip.Addr
+	for _, iface := range ifaces {
+		if !s.isCandidateLink(iface) {
+			continue
+		}
+		linkPath, err := getSystemdLinkPath(iface.Index)
+		if err != nil || !isSystemdLinkDefaultRoute(linkPath) {
+			continue
+		}
+		for _, addr := range readSystemdLinkDNS(linkPath) {
+			addr = normalizeSystemdAddr(addr, iface.Name)
+			if !addr.IsValid() {
+				continue
+			}
+			if _, dup := seen[addr]; dup {
+				continue
+			}
+			seen[addr] = struct{}{}
+			out = append(out, addr)
+		}
+	}
+	return out, nil
+}
+
+func (s *systemdDbusConfigurator) isCandidateLink(iface net.Interface) bool {
+	if iface.Index == s.wgIndex {
+		return false
+	}
+	if iface.Flags&net.FlagLoopback != 0 || iface.Flags&net.FlagUp == 0 {
+		return false
+	}
+	return true
+}
+
+// normalizeSystemdAddr unmaps v4-mapped-v6, drops unspecified, and reattaches
+// the link's iface name as zone for link-local v6 (Link.DNS strips it).
+// Returns the zero Addr to signal "skip this entry".
+func normalizeSystemdAddr(addr netip.Addr, ifaceName string) netip.Addr {
+	addr = addr.Unmap()
+	if !addr.IsValid() || addr.IsUnspecified() {
+		return netip.Addr{}
+	}
+	if addr.IsLinkLocalUnicast() {
+		return addr.WithZone(ifaceName)
+	}
+	return addr
+}
+
+func getSystemdLinkPath(ifIndex int) (dbus.ObjectPath, error) {
+	obj, closeConn, err := getDbusObject(systemdResolvedDest, systemdDbusObjectNode)
+	if err != nil {
+		return "", fmt.Errorf("dbus resolve1: %w", err)
+	}
+	defer closeConn()
+	var p string
+	if err := obj.Call(systemdDbusGetLinkMethod, dbusDefaultFlag, int32(ifIndex)).Store(&p); err != nil {
+		return "", err
+	}
+	return dbus.ObjectPath(p), nil
+}
+
+func isSystemdLinkDefaultRoute(linkPath dbus.ObjectPath) bool {
+	obj, closeConn, err := getDbusObject(systemdResolvedDest, linkPath)
+	if err != nil {
+		return false
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(systemdDbusLinkDefaultRouteProperty)
+	if err != nil {
+		return false
+	}
+	b, ok := v.Value().(bool)
+	return ok && b
+}
+
+func readSystemdLinkDNS(linkPath dbus.ObjectPath) []netip.Addr {
+	obj, closeConn, err := getDbusObject(systemdResolvedDest, linkPath)
+	if err != nil {
+		return nil
+	}
+	defer closeConn()
+	v, err := obj.GetProperty(systemdDbusLinkDNSProperty)
+	if err != nil {
+		return nil
+	}
+	entries, ok := v.Value().([][]any)
+	if !ok {
+		return nil
+	}
+	var out []netip.Addr
+	for _, entry := range entries {
+		if len(entry) < 2 {
+			continue
+		}
+		raw, ok := entry[1].([]byte)
+		if !ok {
+			continue
+		}
+		addr, ok := netip.AddrFromSlice(raw)
+		if !ok {
+			continue
+		}
+		out = append(out, addr)
+	}
+	return out
+}
+
+func (s *systemdDbusConfigurator) getOriginalNameservers() []netip.Addr {
+	return slices.Clone(s.origNameservers)
 }
 
 func (s *systemdDbusConfigurator) supportCustomPort() bool {

client/internal/dns/upstream.go

@@ -1,3 +1,32 @@
+// Package dns implements the client-side DNS stack: listener/service on the
+// peer's tunnel address, handler chain that routes questions by domain and
+// priority, and upstream resolvers that forward what remains to configured
+// nameservers.
+//
+// # Upstream resolution and the race model
+//
+// When two or more nameserver groups target the same domain, DefaultServer
+// merges them into one upstream handler whose state is:
+//
+//	upstreamResolverBase
+//	  └── upstreamServers []upstreamRace   // one entry per source NS group
+//	        └── []netip.AddrPort           // primary, fallback, ...
+//
+// Each source nameserver group contributes one upstreamRace. Within a race
+// upstreams are tried in order: the next is used only on failure (timeout,
+// SERVFAIL, REFUSED, no response). NXDOMAIN is a valid answer and stops
+// the walk. When more than one race exists, ServeDNS fans out one
+// goroutine per race and returns the first valid answer, cancelling the
+// rest. A handler with a single race skips the fan-out.
+//
+// # Health projection
+//
+// Query outcomes are recorded per-upstream in UpstreamHealth. The server
+// periodically merges these snapshots across handlers and projects them
+// into peer.NSGroupState. There is no active probing: a group is marked
+// unhealthy only when every seen upstream has a recent failure and none
+// has a recent success. Healthy→unhealthy fires a single
+// SystemEvent_WARNING; steady-state refreshes do not duplicate it.
 package dns
 
 import (
@@ -11,11 +40,8 @@ import (
 	"slices"
 	"strings"
 	"sync"
-	"sync/atomic"
 	"time"
 
-	"github.com/cenkalti/backoff/v4"
-	"github.com/hashicorp/go-multierror"
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 	"golang.zx2c4.com/wireguard/tun/netstack"
@@ -25,7 +51,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 	"github.com/netbirdio/netbird/client/internal/dns/types"
 	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/proto"
+	"github.com/netbirdio/netbird/route"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 var currentMTU uint16 = iface.DefaultMTU
@@ -67,15 +94,17 @@ const (
 	// Set longer than UpstreamTimeout to ensure context timeout takes precedence
 	ClientTimeout = 5 * time.Second
 
-	reactivatePeriod = 30 * time.Second
-	probeTimeout     = 2 * time.Second
-
 	// ipv6HeaderSize + udpHeaderSize, used to derive the maximum DNS UDP
 	// payload from the tunnel MTU.
 	ipUDPHeaderSize = 60 + 8
-)
 
-const testRecord = "com."
+	// raceMaxTotalTimeout caps the combined time spent walking all upstreams
+	// within one race, so a slow primary can't eat the whole race budget.
+	raceMaxTotalTimeout = 5 * time.Second
+	// raceMinPerUpstreamTimeout is the floor applied when dividing
+	// raceMaxTotalTimeout across upstreams within a race.
+	raceMinPerUpstreamTimeout = 2 * time.Second
+)
 
 const (
 	protoUDP = "udp"
@@ -84,6 +113,69 @@ const (
 
 type dnsProtocolKey struct{}
 
+type upstreamProtocolKey struct{}
+
+// upstreamProtocolResult holds the protocol used for the upstream exchange.
+// Stored as a pointer in context so the exchange function can set it.
+type upstreamProtocolResult struct {
+	protocol string
+}
+
+type upstreamClient interface {
+	exchange(ctx context.Context, upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
+}
+
+type UpstreamResolver interface {
+	serveDNS(r *dns.Msg) (*dns.Msg, time.Duration, error)
+	upstreamExchange(upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
+}
+
+// upstreamRace is an ordered list of upstreams derived from one configured
+// nameserver group. Order matters: the first upstream is tried first, the
+// second only on failure, and so on. Multiple upstreamRace values coexist
+// inside one resolver when overlapping nameserver groups target the same
+// domain; those races run in parallel and the first valid answer wins.
+type upstreamRace []netip.AddrPort
+
+// UpstreamHealth is the last query-path outcome for a single upstream,
+// consumed by nameserver-group status projection.
+type UpstreamHealth struct {
+	LastOk   time.Time
+	LastFail time.Time
+	LastErr  string
+}
+
+type upstreamResolverBase struct {
+	ctx             context.Context
+	cancel          context.CancelFunc
+	upstreamClient  upstreamClient
+	upstreamServers []upstreamRace
+	domain          domain.Domain
+	upstreamTimeout time.Duration
+
+	healthMu sync.RWMutex
+	health   map[netip.AddrPort]*UpstreamHealth
+
+	statusRecorder *peer.Status
+	// selectedRoutes returns the current set of client routes the admin
+	// has enabled. Called lazily from the query hot path when an upstream
+	// might need a tunnel-bound client (iOS) and from health projection.
+	selectedRoutes func() route.HAMap
+}
+
+type upstreamFailure struct {
+	upstream netip.AddrPort
+	reason   string
+}
+
+type raceResult struct {
+	msg      *dns.Msg
+	upstream netip.AddrPort
+	protocol string
+	ede      string
+	failures []upstreamFailure
+}
+
 // contextWithDNSProtocol stores the inbound DNS protocol ("udp" or "tcp") in context.
 func contextWithDNSProtocol(ctx context.Context, network string) context.Context {
 	return context.WithValue(ctx, dnsProtocolKey{}, network)
@@ -100,16 +192,8 @@ func dnsProtocolFromContext(ctx context.Context) string {
 	return ""
 }
 
-type upstreamProtocolKey struct{}
-
-// upstreamProtocolResult holds the protocol used for the upstream exchange.
-// Stored as a pointer in context so the exchange function can set it.
-type upstreamProtocolResult struct {
-	protocol string
-}
-
-// contextWithupstreamProtocolResult stores a mutable result holder in the context.
-func contextWithupstreamProtocolResult(ctx context.Context) (context.Context, *upstreamProtocolResult) {
+// contextWithUpstreamProtocolResult stores a mutable result holder in the context.
+func contextWithUpstreamProtocolResult(ctx context.Context) (context.Context, *upstreamProtocolResult) {
 	r := &upstreamProtocolResult{}
 	return context.WithValue(ctx, upstreamProtocolKey{}, r), r
 }
@@ -124,67 +208,37 @@ func setUpstreamProtocol(ctx context.Context, protocol string) {
 	}
 }
 
-type upstreamClient interface {
-	exchange(ctx context.Context, upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
-}
-
-type UpstreamResolver interface {
-	serveDNS(r *dns.Msg) (*dns.Msg, time.Duration, error)
-	upstreamExchange(upstream string, r *dns.Msg) (*dns.Msg, time.Duration, error)
-}
-
-type upstreamResolverBase struct {
-	ctx              context.Context
-	cancel           context.CancelFunc
-	upstreamClient   upstreamClient
-	upstreamServers  []netip.AddrPort
-	domain           string
-	disabled         bool
-	successCount     atomic.Int32
-	mutex            sync.Mutex
-	reactivatePeriod time.Duration
-	upstreamTimeout  time.Duration
-	wg               sync.WaitGroup
-
-	deactivate     func(error)
-	reactivate     func()
-	statusRecorder *peer.Status
-	routeMatch     func(netip.Addr) bool
-}
-
-type upstreamFailure struct {
-	upstream netip.AddrPort
-	reason   string
-}
-
-func newUpstreamResolverBase(ctx context.Context, statusRecorder *peer.Status, domain string) *upstreamResolverBase {
+func newUpstreamResolverBase(ctx context.Context, statusRecorder *peer.Status, d domain.Domain) *upstreamResolverBase {
 	ctx, cancel := context.WithCancel(ctx)
 
 	return &upstreamResolverBase{
-		ctx:              ctx,
-		cancel:           cancel,
-		domain:           domain,
-		upstreamTimeout:  UpstreamTimeout,
-		reactivatePeriod: reactivatePeriod,
-		statusRecorder:   statusRecorder,
+		ctx:             ctx,
+		cancel:          cancel,
+		domain:          d,
+		upstreamTimeout: UpstreamTimeout,
+		statusRecorder:  statusRecorder,
 	}
 }
 
 // String returns a string representation of the upstream resolver
 func (u *upstreamResolverBase) String() string {
-	return fmt.Sprintf("Upstream %s", u.upstreamServers)
+	return fmt.Sprintf("Upstream %s", u.flatUpstreams())
 }
 
-// ID returns the unique handler ID
+// ID returns the unique handler ID. Race groupings and within-race
+// ordering are both part of the identity: [[A,B]] and [[A],[B]] query
+// the same servers but with different semantics (serial fallback vs
+// parallel race), so their handlers must not collide.
 func (u *upstreamResolverBase) ID() types.HandlerID {
-	servers := slices.Clone(u.upstreamServers)
-	slices.SortFunc(servers, func(a, b netip.AddrPort) int { return a.Compare(b) })
-
 	hash := sha256.New()
-	hash.Write([]byte(u.domain + ":"))
-	for _, s := range servers {
-		hash.Write([]byte(s.String()))
-		hash.Write([]byte("|"))
+	hash.Write([]byte(u.domain.PunycodeString() + ":"))
+	for _, race := range u.upstreamServers {
+		hash.Write([]byte("["))
+		for _, s := range race {
+			hash.Write([]byte(s.String()))
+			hash.Write([]byte("|"))
+		}
+		hash.Write([]byte("]"))
 	}
 	return types.HandlerID("upstream-" + hex.EncodeToString(hash.Sum(nil)[:8]))
 }
@@ -194,13 +248,31 @@ func (u *upstreamResolverBase) MatchSubdomains() bool {
 }
 
 func (u *upstreamResolverBase) Stop() {
-	log.Debugf("stopping serving DNS for upstreams %s", u.upstreamServers)
+	log.Debugf("stopping serving DNS for upstreams %s", u.flatUpstreams())
 	u.cancel()
+}
 
-	u.mutex.Lock()
-	u.wg.Wait()
-	u.mutex.Unlock()
+// flatUpstreams is for logging and ID hashing only, not for dispatch.
+func (u *upstreamResolverBase) flatUpstreams() []netip.AddrPort {
+	var out []netip.AddrPort
+	for _, g := range u.upstreamServers {
+		out = append(out, g...)
+	}
+	return out
+}
 
+// setSelectedRoutes swaps the accessor used to classify overlay-routed
+// upstreams. Called when route sources are wired after the handler was
+// built (permanent / iOS constructors).
+func (u *upstreamResolverBase) setSelectedRoutes(selected func() route.HAMap) {
+	u.selectedRoutes = selected
+}
+
+func (u *upstreamResolverBase) addRace(servers []netip.AddrPort) {
+	if len(servers) == 0 {
+		return
+	}
+	u.upstreamServers = append(u.upstreamServers, slices.Clone(servers))
 }
 
 // ServeDNS handles a DNS request
@@ -242,82 +314,201 @@ func (u *upstreamResolverBase) prepareRequest(r *dns.Msg) {
 }
 
 func (u *upstreamResolverBase) tryUpstreamServers(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) (bool, []upstreamFailure) {
-	timeout := u.upstreamTimeout
-	if len(u.upstreamServers) > 1 {
-		maxTotal := 5 * time.Second
-		minPerUpstream := 2 * time.Second
-		scaledTimeout := maxTotal / time.Duration(len(u.upstreamServers))
-		if scaledTimeout > minPerUpstream {
-			timeout = scaledTimeout
-		} else {
-			timeout = minPerUpstream
-		}
+	groups := u.upstreamServers
+	switch len(groups) {
+	case 0:
+		return false, nil
+	case 1:
+		return u.tryOnlyRace(ctx, w, r, groups[0], logger)
+	default:
+		return u.raceAll(ctx, w, r, groups, logger)
+	}
+}
+
+func (u *upstreamResolverBase) tryOnlyRace(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, group upstreamRace, logger *log.Entry) (bool, []upstreamFailure) {
+	res := u.tryRace(ctx, r, group)
+	if res.msg == nil {
+		return false, res.failures
+	}
+	if res.ede != "" {
+		resutil.SetMeta(w, "ede", res.ede)
+	}
+	u.writeSuccessResponse(w, res.msg, res.upstream, r.Question[0].Name, res.protocol, logger)
+	return true, res.failures
+}
+
+// raceAll runs one worker per group in parallel, taking the first valid
+// answer and cancelling the rest.
+func (u *upstreamResolverBase) raceAll(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, groups []upstreamRace, logger *log.Entry) (bool, []upstreamFailure) {
+	raceCtx, cancel := context.WithCancel(ctx)
+	defer cancel()
+
+	// Buffer sized to len(groups) so workers never block on send, even
+	// after the coordinator has returned.
+	results := make(chan raceResult, len(groups))
+	for _, g := range groups {
+		// tryRace clones the request per attempt, so workers never share
+		// a *dns.Msg and concurrent EDNS0 mutations can't race.
+		go func(g upstreamRace) {
+			results <- u.tryRace(raceCtx, r, g)
+		}(g)
 	}
 
 	var failures []upstreamFailure
-	for _, upstream := range u.upstreamServers {
-		if failure := u.queryUpstream(ctx, w, r, upstream, timeout, logger); failure != nil {
-			failures = append(failures, *failure)
-		} else {
-			return true, failures
+	for range groups {
+		select {
+		case res := <-results:
+			failures = append(failures, res.failures...)
+			if res.msg != nil {
+				if res.ede != "" {
+					resutil.SetMeta(w, "ede", res.ede)
+				}
+				u.writeSuccessResponse(w, res.msg, res.upstream, r.Question[0].Name, res.protocol, logger)
+				return true, failures
+			}
+		case <-ctx.Done():
+			return false, failures
 		}
 	}
 	return false, failures
 }
 
-// queryUpstream queries a single upstream server. Returns nil on success, or failure info to try next upstream.
-func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, w dns.ResponseWriter, r *dns.Msg, upstream netip.AddrPort, timeout time.Duration, logger *log.Entry) *upstreamFailure {
-	var rm *dns.Msg
-	var t time.Duration
-	var err error
+func (u *upstreamResolverBase) tryRace(ctx context.Context, r *dns.Msg, group upstreamRace) raceResult {
+	timeout := u.upstreamTimeout
+	if len(group) > 1 {
+		// Cap the whole walk at raceMaxTotalTimeout: per-upstream timeouts
+		// still honor raceMinPerUpstreamTimeout as a floor for correctness
+		// on slow links, but the outer context ensures the combined walk
+		// cannot exceed the cap regardless of group size.
+		timeout = max(raceMaxTotalTimeout/time.Duration(len(group)), raceMinPerUpstreamTimeout)
+		var cancel context.CancelFunc
+		ctx, cancel = context.WithTimeout(ctx, raceMaxTotalTimeout)
+		defer cancel()
+	}
+
+	var failures []upstreamFailure
+	for _, upstream := range group {
+		if ctx.Err() != nil {
+			return raceResult{failures: failures}
+		}
+		// Clone the request per attempt: the exchange path mutates EDNS0
+		// options in-place, so reusing the same *dns.Msg across sequential
+		// upstreams would carry those mutations (e.g. a reduced UDP size)
+		// into the next attempt.
+		res, failure := u.queryUpstream(ctx, r.Copy(), upstream, timeout)
+		if failure != nil {
+			failures = append(failures, *failure)
+			continue
+		}
+		res.failures = failures
+		return res
+	}
+	return raceResult{failures: failures}
+}
+
+func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, r *dns.Msg, upstream netip.AddrPort, timeout time.Duration) (raceResult, *upstreamFailure) {
+	ctx, cancel := context.WithTimeout(parentCtx, timeout)
+	defer cancel()
+	ctx, upstreamProto := contextWithUpstreamProtocolResult(ctx)
 
 	// Advertise EDNS0 so the upstream may include Extended DNS Errors
 	// (RFC 8914) in failure responses; we use those to short-circuit
 	// failover for definitive answers like DNSSEC validation failures.
-	// Operate on a copy so the inbound request is unchanged: a client that
-	// did not advertise EDNS0 must not see an OPT in the response.
+	// The caller already passed a per-attempt copy, so we can mutate r
+	// directly; hadEdns reflects the original client request's state and
+	// controls whether we strip the OPT from the response.
 	hadEdns := r.IsEdns0() != nil
-	reqUp := r
 	if !hadEdns {
-		reqUp = r.Copy()
-		reqUp.SetEdns0(upstreamUDPSize(), false)
+		r.SetEdns0(upstreamUDPSize(), false)
 	}
 
-	var startTime time.Time
-	var upstreamProto *upstreamProtocolResult
-	func() {
-		ctx, cancel := context.WithTimeout(parentCtx, timeout)
-		defer cancel()
-		ctx, upstreamProto = contextWithupstreamProtocolResult(ctx)
-		startTime = time.Now()
-		rm, t, err = u.upstreamClient.exchange(ctx, upstream.String(), reqUp)
-	}()
+	startTime := time.Now()
+	rm, _, err := u.upstreamClient.exchange(ctx, upstream.String(), r)
 
 	if err != nil {
-		return u.handleUpstreamError(err, upstream, startTime)
+		// A parent cancellation (e.g., another race won and the coordinator
+		// cancelled the losers) is not an upstream failure. Check both the
+		// error chain and the parent context: a transport may surface the
+		// cancellation as a read/deadline error rather than context.Canceled.
+		if errors.Is(err, context.Canceled) || errors.Is(parentCtx.Err(), context.Canceled) {
+			return raceResult{}, &upstreamFailure{upstream: upstream, reason: "canceled"}
+		}
+		failure := u.handleUpstreamError(err, upstream, startTime)
+		u.markUpstreamFail(upstream, failure.reason)
+		return raceResult{}, failure
 	}
 
 	if rm == nil || !rm.Response {
-		return &upstreamFailure{upstream: upstream, reason: "no response"}
+		u.markUpstreamFail(upstream, "no response")
+		return raceResult{}, &upstreamFailure{upstream: upstream, reason: "no response"}
+	}
+
+	proto := ""
+	if upstreamProto != nil {
+		proto = upstreamProto.protocol
 	}
 
 	if rm.Rcode == dns.RcodeServerFailure || rm.Rcode == dns.RcodeRefused {
 		if code, ok := nonRetryableEDE(rm); ok {
-			resutil.SetMeta(w, "ede", edeName(code))
 			if !hadEdns {
 				stripOPT(rm)
 			}
-			u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
-			return nil
+			u.markUpstreamOk(upstream)
+			return raceResult{msg: rm, upstream: upstream, protocol: proto, ede: edeName(code)}, nil
 		}
-		return &upstreamFailure{upstream: upstream, reason: dns.RcodeToString[rm.Rcode]}
+		reason := dns.RcodeToString[rm.Rcode]
+		u.markUpstreamFail(upstream, reason)
+		return raceResult{}, &upstreamFailure{upstream: upstream, reason: reason}
 	}
 
 	if !hadEdns {
 		stripOPT(rm)
 	}
-	u.writeSuccessResponse(w, rm, upstream, r.Question[0].Name, t, upstreamProto, logger)
-	return nil
+
+	u.markUpstreamOk(upstream)
+	return raceResult{msg: rm, upstream: upstream, protocol: proto}, nil
+}
+
+// healthEntry returns the mutable health record for addr, lazily creating
+// the map and the entry. Caller must hold u.healthMu.
+func (u *upstreamResolverBase) healthEntry(addr netip.AddrPort) *UpstreamHealth {
+	if u.health == nil {
+		u.health = make(map[netip.AddrPort]*UpstreamHealth)
+	}
+	h := u.health[addr]
+	if h == nil {
+		h = &UpstreamHealth{}
+		u.health[addr] = h
+	}
+	return h
+}
+
+func (u *upstreamResolverBase) markUpstreamOk(addr netip.AddrPort) {
+	u.healthMu.Lock()
+	defer u.healthMu.Unlock()
+	h := u.healthEntry(addr)
+	h.LastOk = time.Now()
+	h.LastFail = time.Time{}
+	h.LastErr = ""
+}
+
+func (u *upstreamResolverBase) markUpstreamFail(addr netip.AddrPort, reason string) {
+	u.healthMu.Lock()
+	defer u.healthMu.Unlock()
+	h := u.healthEntry(addr)
+	h.LastFail = time.Now()
+	h.LastErr = reason
+}
+
+// UpstreamHealth returns a snapshot of per-upstream query outcomes.
+func (u *upstreamResolverBase) UpstreamHealth() map[netip.AddrPort]UpstreamHealth {
+	u.healthMu.RLock()
+	defer u.healthMu.RUnlock()
+	out := make(map[netip.AddrPort]UpstreamHealth, len(u.health))
+	for k, v := range u.health {
+		out[k] = *v
+	}
+	return out
 }
 
 // upstreamUDPSize returns the EDNS0 UDP buffer size we advertise to upstreams,
@@ -358,12 +549,23 @@ func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.Add
 	return &upstreamFailure{upstream: upstream, reason: reason}
 }
 
-func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dns.Msg, upstream netip.AddrPort, domain string, t time.Duration, upstreamProto *upstreamProtocolResult, logger *log.Entry) bool {
-	u.successCount.Add(1)
+func (u *upstreamResolverBase) debugUpstreamTimeout(upstream netip.AddrPort) string {
+	if u.statusRecorder == nil {
+		return ""
+	}
 
+	peerInfo := findPeerForIP(upstream.Addr(), u.statusRecorder)
+	if peerInfo == nil {
+		return ""
+	}
+
+	return fmt.Sprintf("(routes through NetBird peer %s)", FormatPeerStatus(peerInfo))
+}
+
+func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dns.Msg, upstream netip.AddrPort, domain string, proto string, logger *log.Entry) {
 	resutil.SetMeta(w, "upstream", upstream.String())
-	if upstreamProto != nil && upstreamProto.protocol != "" {
-		resutil.SetMeta(w, "upstream_protocol", upstreamProto.protocol)
+	if proto != "" {
+		resutil.SetMeta(w, "upstream_protocol", proto)
 	}
 
 	// Clear Zero bit from external responses to prevent upstream servers from
@@ -372,14 +574,11 @@ func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dn
 
 	if err := w.WriteMsg(rm); err != nil {
 		logger.Errorf("failed to write DNS response for question domain=%s: %s", domain, err)
-		return true
 	}
-
-	return true
 }
 
 func (u *upstreamResolverBase) logUpstreamFailures(domain string, failures []upstreamFailure, succeeded bool, logger *log.Entry) {
-	totalUpstreams := len(u.upstreamServers)
+	totalUpstreams := len(u.flatUpstreams())
 	failedCount := len(failures)
 	failureSummary := formatFailures(failures)
 
@@ -434,119 +633,6 @@ func edeName(code uint16) string {
 	return fmt.Sprintf("EDE %d", code)
 }
 
-// ProbeAvailability tests all upstream servers simultaneously and
-// disables the resolver if none work
-func (u *upstreamResolverBase) ProbeAvailability(ctx context.Context) {
-	u.mutex.Lock()
-	defer u.mutex.Unlock()
-
-	// avoid probe if upstreams could resolve at least one query
-	if u.successCount.Load() > 0 {
-		return
-	}
-
-	var success bool
-	var mu sync.Mutex
-	var wg sync.WaitGroup
-
-	var errs *multierror.Error
-	for _, upstream := range u.upstreamServers {
-		wg.Add(1)
-		go func(upstream netip.AddrPort) {
-			defer wg.Done()
-			err := u.testNameserver(u.ctx, ctx, upstream, 500*time.Millisecond)
-			if err != nil {
-				mu.Lock()
-				errs = multierror.Append(errs, err)
-				mu.Unlock()
-				log.Warnf("probing upstream nameserver %s: %s", upstream, err)
-				return
-			}
-
-			mu.Lock()
-			success = true
-			mu.Unlock()
-		}(upstream)
-	}
-
-	wg.Wait()
-
-	select {
-	case <-ctx.Done():
-		return
-	case <-u.ctx.Done():
-		return
-	default:
-	}
-
-	// didn't find a working upstream server, let's disable and try later
-	if !success {
-		u.disable(errs.ErrorOrNil())
-
-		if u.statusRecorder == nil {
-			return
-		}
-
-		u.statusRecorder.PublishEvent(
-			proto.SystemEvent_WARNING,
-			proto.SystemEvent_DNS,
-			"All upstream servers failed (probe failed)",
-			"Unable to reach one or more DNS servers. This might affect your ability to connect to some services.",
-			map[string]string{"upstreams": u.upstreamServersString()},
-		)
-	}
-}
-
-// waitUntilResponse retries, in an exponential interval, querying the upstream servers until it gets a positive response
-func (u *upstreamResolverBase) waitUntilResponse() {
-	exponentialBackOff := &backoff.ExponentialBackOff{
-		InitialInterval:     500 * time.Millisecond,
-		RandomizationFactor: 0.5,
-		Multiplier:          1.1,
-		MaxInterval:         u.reactivatePeriod,
-		MaxElapsedTime:      0,
-		Stop:                backoff.Stop,
-		Clock:               backoff.SystemClock,
-	}
-
-	operation := func() error {
-		select {
-		case <-u.ctx.Done():
-			return backoff.Permanent(fmt.Errorf("exiting upstream retry loop for upstreams %s: parent context has been canceled", u.upstreamServersString()))
-		default:
-		}
-
-		for _, upstream := range u.upstreamServers {
-			if err := u.testNameserver(u.ctx, nil, upstream, probeTimeout); err != nil {
-				log.Tracef("upstream check for %s: %s", upstream, err)
-			} else {
-				// at least one upstream server is available, stop probing
-				return nil
-			}
-		}
-
-		log.Tracef("checking connectivity with upstreams %s failed. Retrying in %s", u.upstreamServersString(), exponentialBackOff.NextBackOff())
-		return fmt.Errorf("upstream check call error")
-	}
-
-	err := backoff.Retry(operation, backoff.WithContext(exponentialBackOff, u.ctx))
-	if err != nil {
-		if errors.Is(err, context.Canceled) {
-			log.Debugf("upstream retry loop exited for upstreams %s", u.upstreamServersString())
-		} else {
-			log.Warnf("upstream retry loop exited for upstreams %s: %v", u.upstreamServersString(), err)
-		}
-		return
-	}
-
-	log.Infof("upstreams %s are responsive again. Adding them back to system", u.upstreamServersString())
-	u.successCount.Add(1)
-	u.reactivate()
-	u.mutex.Lock()
-	u.disabled = false
-	u.mutex.Unlock()
-}
-
 // isTimeout returns true if the given error is a network timeout error.
 //
 // Copied from k8s.io/apimachinery/pkg/util/net.IsTimeout
@@ -558,45 +644,6 @@ func isTimeout(err error) bool {
 	return false
 }
 
-func (u *upstreamResolverBase) disable(err error) {
-	if u.disabled {
-		return
-	}
-
-	log.Warnf("Upstream resolving is Disabled for %v", reactivatePeriod)
-	u.successCount.Store(0)
-	u.deactivate(err)
-	u.disabled = true
-	u.wg.Add(1)
-	go func() {
-		defer u.wg.Done()
-		u.waitUntilResponse()
-	}()
-}
-
-func (u *upstreamResolverBase) upstreamServersString() string {
-	var servers []string
-	for _, server := range u.upstreamServers {
-		servers = append(servers, server.String())
-	}
-	return strings.Join(servers, ", ")
-}
-
-func (u *upstreamResolverBase) testNameserver(baseCtx context.Context, externalCtx context.Context, server netip.AddrPort, timeout time.Duration) error {
-	mergedCtx, cancel := context.WithTimeout(baseCtx, timeout)
-	defer cancel()
-
-	if externalCtx != nil {
-		stop2 := context.AfterFunc(externalCtx, cancel)
-		defer stop2()
-	}
-
-	r := new(dns.Msg).SetQuestion(testRecord, dns.TypeSOA)
-
-	_, _, err := u.upstreamClient.exchange(mergedCtx, server.String(), r)
-	return err
-}
-
 // clientUDPMaxSize returns the maximum UDP response size the client accepts.
 func clientUDPMaxSize(r *dns.Msg) int {
 	if opt := r.IsEdns0(); opt != nil {
@@ -608,13 +655,10 @@ func clientUDPMaxSize(r *dns.Msg) int {
 // ExchangeWithFallback exchanges a DNS message with the upstream server.
 // It first tries to use UDP, and if it is truncated, it falls back to TCP.
 // If the inbound request came over TCP (via context), it skips the UDP attempt.
-// If the passed context is nil, this will use Exchange instead of ExchangeContext.
 func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, upstream string) (*dns.Msg, time.Duration, error) {
 	// If the request came in over TCP, go straight to TCP upstream.
 	if dnsProtocolFromContext(ctx) == protoTCP {
-		tcpClient := *client
-		tcpClient.Net = protoTCP
-		rm, t, err := tcpClient.ExchangeContext(ctx, r, upstream)
+		rm, t, err := toTCPClient(client).ExchangeContext(ctx, r, upstream)
 		if err != nil {
 			return nil, t, fmt.Errorf("with tcp: %w", err)
 		}
@@ -634,18 +678,7 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 		opt.SetUDPSize(maxUDPPayload)
 	}
 
-	var (
-		rm  *dns.Msg
-		t   time.Duration
-		err error
-	)
-
-	if ctx == nil {
-		rm, t, err = client.Exchange(r, upstream)
-	} else {
-		rm, t, err = client.ExchangeContext(ctx, r, upstream)
-	}
-
+	rm, t, err := client.ExchangeContext(ctx, r, upstream)
 	if err != nil {
 		return nil, t, fmt.Errorf("with udp: %w", err)
 	}
@@ -659,15 +692,7 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 	// data than the client's buffer, we could truncate locally and skip
 	// the TCP retry.
 
-	tcpClient := *client
-	tcpClient.Net = protoTCP
-
-	if ctx == nil {
-		rm, t, err = tcpClient.Exchange(r, upstream)
-	} else {
-		rm, t, err = tcpClient.ExchangeContext(ctx, r, upstream)
-	}
-
+	rm, t, err = toTCPClient(client).ExchangeContext(ctx, r, upstream)
 	if err != nil {
 		return nil, t, fmt.Errorf("with tcp: %w", err)
 	}
@@ -681,6 +706,25 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 	return rm, t, nil
 }
 
+// toTCPClient returns a copy of c configured for TCP. If c's Dialer has a
+// *net.UDPAddr bound as LocalAddr (iOS does this to keep the source IP on
+// the tunnel interface), it is converted to the equivalent *net.TCPAddr
+// so net.Dialer doesn't reject the TCP dial with "mismatched local
+// address type".
+func toTCPClient(c *dns.Client) *dns.Client {
+	tcp := *c
+	tcp.Net = protoTCP
+	if tcp.Dialer == nil {
+		return &tcp
+	}
+	d := *tcp.Dialer
+	if ua, ok := d.LocalAddr.(*net.UDPAddr); ok {
+		d.LocalAddr = &net.TCPAddr{IP: ua.IP, Port: ua.Port, Zone: ua.Zone}
+	}
+	tcp.Dialer = &d
+	return &tcp
+}
+
 // ExchangeWithNetstack performs a DNS exchange using netstack for dialing.
 // This is needed when netstack is enabled to reach peer IPs through the tunnel.
 func ExchangeWithNetstack(ctx context.Context, nsNet *netstack.Net, r *dns.Msg, upstream string) (*dns.Msg, error) {
@@ -822,15 +866,36 @@ func findPeerForIP(ip netip.Addr, statusRecorder *peer.Status) *peer.State {
 	return bestMatch
 }
 
-func (u *upstreamResolverBase) debugUpstreamTimeout(upstream netip.AddrPort) string {
-	if u.statusRecorder == nil {
-		return ""
+// haMapRouteCount returns the total number of routes across all HA
+// groups in the map. route.HAMap is keyed by HAUniqueID with slices of
+// routes per key, so len(hm) is the number of HA groups, not routes.
+func haMapRouteCount(hm route.HAMap) int {
+	total := 0
+	for _, routes := range hm {
+		total += len(routes)
 	}
-
-	peerInfo := findPeerForIP(upstream.Addr(), u.statusRecorder)
-	if peerInfo == nil {
-		return ""
-	}
-
-	return fmt.Sprintf("(routes through NetBird peer %s)", FormatPeerStatus(peerInfo))
+	return total
+}
+
+// haMapContains checks whether ip is covered by any concrete prefix in
+// the HA map. haveDynamic is reported separately: dynamic (domain-based)
+// routes carry a placeholder Network that can't be prefix-checked, so we
+// can't know at this point whether ip is reached through one. Callers
+// decide how to interpret the unknown: health projection treats it as
+// "possibly routed" to avoid emitting false-positive warnings during
+// startup, while iOS dial selection requires a concrete match before
+// binding to the tunnel.
+func haMapContains(hm route.HAMap, ip netip.Addr) (matched, haveDynamic bool) {
+	for _, routes := range hm {
+		for _, r := range routes {
+			if r.IsDynamic() {
+				haveDynamic = true
+				continue
+			}
+			if r.Network.Contains(ip) {
+				return true, haveDynamic
+			}
+		}
+	}
+	return false, haveDynamic
 }

client/internal/dns/upstream_android.go

@@ -11,6 +11,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/internal/peer"
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolver struct {
@@ -26,9 +27,9 @@ func newUpstreamResolver(
 	_ WGIface,
 	statusRecorder *peer.Status,
 	hostsDNSHolder *hostsDNSHolder,
-	domain string,
+	d domain.Domain,
 ) (*upstreamResolver, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
 	c := &upstreamResolver{
 		upstreamResolverBase: upstreamResolverBase,
 		hostsDNSHolder:       hostsDNSHolder,

client/internal/dns/upstream_general.go

@@ -12,6 +12,7 @@ import (
 	"golang.zx2c4.com/wireguard/tun/netstack"
 
 	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolver struct {
@@ -24,9 +25,9 @@ func newUpstreamResolver(
 	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
-	domain string,
+	d domain.Domain,
 ) (*upstreamResolver, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
 	nonIOS := &upstreamResolver{
 		upstreamResolverBase: upstreamResolverBase,
 		nsNet:                wgIface.GetNet(),

client/internal/dns/upstream_ios.go

@@ -15,6 +15,7 @@ import (
 	"golang.org/x/sys/unix"
 
 	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 type upstreamResolverIOS struct {
@@ -27,9 +28,9 @@ func newUpstreamResolver(
 	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
-	domain string,
+	d domain.Domain,
 ) (*upstreamResolverIOS, error) {
-	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
+	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, d)
 
 	ios := &upstreamResolverIOS{
 		upstreamResolverBase: upstreamResolverBase,
@@ -62,9 +63,16 @@ func (u *upstreamResolverIOS) exchange(ctx context.Context, upstream string, r *
 		upstreamIP = upstreamIP.Unmap()
 	}
 	addr := u.wgIface.Address()
+	var routed bool
+	if u.selectedRoutes != nil {
+		// Only a concrete prefix match binds to the tunnel: dialing
+		// through a private client for an upstream we can't prove is
+		// routed would break public resolvers.
+		routed, _ = haMapContains(u.selectedRoutes(), upstreamIP)
+	}
 	needsPrivate := addr.Network.Contains(upstreamIP) ||
 		addr.IPv6Net.Contains(upstreamIP) ||
-		(u.routeMatch != nil && u.routeMatch(upstreamIP))
+		routed
 	if needsPrivate {
 		log.Debugf("using private client to query %s via upstream %s", r.Question[0].Name, upstream)
 		client, err = GetClientPrivate(u.wgIface, upstreamIP, timeout)
@@ -73,8 +81,7 @@ func (u *upstreamResolverIOS) exchange(ctx context.Context, upstream string, r *
 		}
 	}
 
-	// Cannot use client.ExchangeContext because it overwrites our Dialer
-	return ExchangeWithFallback(nil, client, r, upstream)
+	return ExchangeWithFallback(ctx, client, r, upstream)
 }
 
 // GetClientPrivate returns a new DNS client bound to the local IP of the Netbird interface.

client/internal/dns/upstream_test.go

@@ -6,6 +6,7 @@ import (
 	"net"
 	"net/netip"
 	"strings"
+	"sync/atomic"
 	"testing"
 	"time"
 
@@ -73,7 +74,7 @@ func TestUpstreamResolver_ServeDNS(t *testing.T) {
 					servers = append(servers, netip.AddrPortFrom(addrPort.Addr().Unmap(), addrPort.Port()))
 				}
 			}
-			resolver.upstreamServers = servers
+			resolver.addRace(servers)
 			resolver.upstreamTimeout = testCase.timeout
 			if testCase.cancelCTX {
 				cancel()
@@ -132,20 +133,10 @@ func (m *mockNetstackProvider) GetInterfaceGUIDString() (string, error) {
 	return "", nil
 }
 
-type mockUpstreamResolver struct {
-	r   *dns.Msg
-	rtt time.Duration
-	err error
-}
-
-// exchange mock implementation of exchange from upstreamResolver
-func (c mockUpstreamResolver) exchange(_ context.Context, _ string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
-	return c.r, c.rtt, c.err
-}
-
 type mockUpstreamResponse struct {
-	msg *dns.Msg
-	err error
+	msg   *dns.Msg
+	err   error
+	delay time.Duration
 }
 
 type mockUpstreamResolverPerServer struct {
@@ -153,63 +144,19 @@ type mockUpstreamResolverPerServer struct {
 	rtt       time.Duration
 }
 
-func (c mockUpstreamResolverPerServer) exchange(_ context.Context, upstream string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
-	if r, ok := c.responses[upstream]; ok {
-		return r.msg, c.rtt, r.err
+func (c mockUpstreamResolverPerServer) exchange(ctx context.Context, upstream string, _ *dns.Msg) (*dns.Msg, time.Duration, error) {
+	r, ok := c.responses[upstream]
+	if !ok {
+		return nil, c.rtt, fmt.Errorf("no mock response for %s", upstream)
 	}
-	return nil, c.rtt, fmt.Errorf("no mock response for %s", upstream)
-}
-
-func TestUpstreamResolver_DeactivationReactivation(t *testing.T) {
-	mockClient := &mockUpstreamResolver{
-		err: dns.ErrTime,
-		r:   new(dns.Msg),
-		rtt: time.Millisecond,
-	}
-
-	resolver := &upstreamResolverBase{
-		ctx:              context.TODO(),
-		upstreamClient:   mockClient,
-		upstreamTimeout:  UpstreamTimeout,
-		reactivatePeriod: time.Microsecond * 100,
-	}
-	addrPort, _ := netip.ParseAddrPort("0.0.0.0:1") // Use valid port for parsing, test will still fail on connection
-	resolver.upstreamServers = []netip.AddrPort{netip.AddrPortFrom(addrPort.Addr().Unmap(), addrPort.Port())}
-
-	failed := false
-	resolver.deactivate = func(error) {
-		failed = true
-		// After deactivation, make the mock client work again
-		mockClient.err = nil
-	}
-
-	reactivated := false
-	resolver.reactivate = func() {
-		reactivated = true
-	}
-
-	resolver.ProbeAvailability(context.TODO())
-
-	if !failed {
-		t.Errorf("expected that resolving was deactivated")
-		return
-	}
-
-	if !resolver.disabled {
-		t.Errorf("resolver should be Disabled")
-		return
-	}
-
-	time.Sleep(time.Millisecond * 200)
-
-	if !reactivated {
-		t.Errorf("expected that resolving was reactivated")
-		return
-	}
-
-	if resolver.disabled {
-		t.Errorf("should be enabled")
+	if r.delay > 0 {
+		select {
+		case <-time.After(r.delay):
+		case <-ctx.Done():
+			return nil, c.rtt, ctx.Err()
+		}
 	}
+	return r.msg, c.rtt, r.err
 }
 
 func TestUpstreamResolver_Failover(t *testing.T) {
@@ -339,9 +286,9 @@ func TestUpstreamResolver_Failover(t *testing.T) {
 			resolver := &upstreamResolverBase{
 				ctx:             ctx,
 				upstreamClient:  trackingClient,
-				upstreamServers: []netip.AddrPort{upstream1, upstream2},
 				upstreamTimeout: UpstreamTimeout,
 			}
+			resolver.addRace([]netip.AddrPort{upstream1, upstream2})
 
 			var responseMSG *dns.Msg
 			responseWriter := &test.MockResponseWriter{
@@ -421,9 +368,9 @@ func TestUpstreamResolver_SingleUpstreamFailure(t *testing.T) {
 	resolver := &upstreamResolverBase{
 		ctx:             ctx,
 		upstreamClient:  mockClient,
-		upstreamServers: []netip.AddrPort{upstream},
 		upstreamTimeout: UpstreamTimeout,
 	}
+	resolver.addRace([]netip.AddrPort{upstream})
 
 	var responseMSG *dns.Msg
 	responseWriter := &test.MockResponseWriter{
@@ -440,6 +387,136 @@ func TestUpstreamResolver_SingleUpstreamFailure(t *testing.T) {
 	assert.Equal(t, dns.RcodeServerFailure, responseMSG.Rcode, "single upstream SERVFAIL should return SERVFAIL")
 }
 
+// TestUpstreamResolver_RaceAcrossGroups covers two nameserver groups
+// configured for the same domain, with one broken group. The merge+race
+// path should answer as fast as the working group and not pay the timeout
+// of the broken one on every query.
+func TestUpstreamResolver_RaceAcrossGroups(t *testing.T) {
+	broken := netip.MustParseAddrPort("192.0.2.1:53")
+	working := netip.MustParseAddrPort("192.0.2.2:53")
+	successAnswer := "192.0.2.100"
+	timeoutErr := &net.OpError{Op: "read", Err: fmt.Errorf("i/o timeout")}
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			// Force the broken upstream to only unblock via timeout /
+			// cancellation so the assertion below can't pass if races
+			// were run serially.
+			broken.String():  {err: timeoutErr, delay: 500 * time.Millisecond},
+			working.String(): {msg: buildMockResponse(dns.RcodeSuccess, successAnswer)},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamTimeout: 250 * time.Millisecond,
+	}
+	resolver.addRace([]netip.AddrPort{broken})
+	resolver.addRace([]netip.AddrPort{working})
+
+	var responseMSG *dns.Msg
+	responseWriter := &test.MockResponseWriter{
+		WriteMsgFunc: func(m *dns.Msg) error {
+			responseMSG = m
+			return nil
+		},
+	}
+
+	inputMSG := new(dns.Msg).SetQuestion("example.com.", dns.TypeA)
+	start := time.Now()
+	resolver.ServeDNS(responseWriter, inputMSG)
+	elapsed := time.Since(start)
+
+	require.NotNil(t, responseMSG, "should write a response")
+	assert.Equal(t, dns.RcodeSuccess, responseMSG.Rcode)
+	require.NotEmpty(t, responseMSG.Answer)
+	assert.Contains(t, responseMSG.Answer[0].String(), successAnswer)
+	// Working group answers in a single RTT; the broken group's
+	// timeout (100ms) must not block the response.
+	assert.Less(t, elapsed, 100*time.Millisecond, "race must not wait for broken group's timeout")
+}
+
+// TestUpstreamResolver_AllGroupsFail checks that when every group fails the
+// resolver returns SERVFAIL rather than leaking a partial response.
+func TestUpstreamResolver_AllGroupsFail(t *testing.T) {
+	a := netip.MustParseAddrPort("192.0.2.1:53")
+	b := netip.MustParseAddrPort("192.0.2.2:53")
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			a.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			b.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamTimeout: UpstreamTimeout,
+	}
+	resolver.addRace([]netip.AddrPort{a})
+	resolver.addRace([]netip.AddrPort{b})
+
+	var responseMSG *dns.Msg
+	responseWriter := &test.MockResponseWriter{
+		WriteMsgFunc: func(m *dns.Msg) error {
+			responseMSG = m
+			return nil
+		},
+	}
+
+	resolver.ServeDNS(responseWriter, new(dns.Msg).SetQuestion("example.com.", dns.TypeA))
+	require.NotNil(t, responseMSG)
+	assert.Equal(t, dns.RcodeServerFailure, responseMSG.Rcode)
+}
+
+// TestUpstreamResolver_HealthTracking verifies that query-path results are
+// recorded into per-upstream health, which is what projects back to
+// NSGroupState for status reporting.
+func TestUpstreamResolver_HealthTracking(t *testing.T) {
+	ok := netip.MustParseAddrPort("192.0.2.10:53")
+	bad := netip.MustParseAddrPort("192.0.2.11:53")
+
+	mockClient := &mockUpstreamResolverPerServer{
+		responses: map[string]mockUpstreamResponse{
+			ok.String():  {msg: buildMockResponse(dns.RcodeSuccess, "192.0.2.100")},
+			bad.String(): {msg: buildMockResponse(dns.RcodeServerFailure, "")},
+		},
+		rtt: time.Millisecond,
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	resolver := &upstreamResolverBase{
+		ctx:             ctx,
+		upstreamClient:  mockClient,
+		upstreamTimeout: UpstreamTimeout,
+	}
+	resolver.addRace([]netip.AddrPort{ok, bad})
+
+	responseWriter := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { return nil }}
+	resolver.ServeDNS(responseWriter, new(dns.Msg).SetQuestion("example.com.", dns.TypeA))
+
+	health := resolver.UpstreamHealth()
+	require.Contains(t, health, ok)
+	assert.False(t, health[ok].LastOk.IsZero(), "ok upstream should have LastOk set")
+	assert.Empty(t, health[ok].LastErr)
+
+	// bad upstream was never tried because ok answered first; its health
+	// should remain unset.
+	assert.NotContains(t, health, bad, "sibling upstream should not be queried when primary answers")
+}
+
 func TestFormatFailures(t *testing.T) {
 	testCases := []struct {
 		name     string
@@ -665,10 +742,10 @@ func TestExchangeWithFallback_EDNS0Capped(t *testing.T) {
 	// Verify that a client EDNS0 larger than our MTU-derived limit gets
 	// capped in the outgoing request so the upstream doesn't send a
 	// response larger than our read buffer.
-	var receivedUDPSize uint16
+	var receivedUDPSize atomic.Uint32
 	udpHandler := dns.HandlerFunc(func(w dns.ResponseWriter, r *dns.Msg) {
 		if opt := r.IsEdns0(); opt != nil {
-			receivedUDPSize = opt.UDPSize()
+			receivedUDPSize.Store(uint32(opt.UDPSize()))
 		}
 		m := new(dns.Msg)
 		m.SetReply(r)
@@ -699,7 +776,7 @@ func TestExchangeWithFallback_EDNS0Capped(t *testing.T) {
 	require.NotNil(t, rm)
 
 	expectedMax := uint16(currentMTU - ipUDPHeaderSize)
-	assert.Equal(t, expectedMax, receivedUDPSize,
+	assert.Equal(t, expectedMax, uint16(receivedUDPSize.Load()),
 		"upstream should see capped EDNS0, not the client's 4096")
 }
 
@@ -874,7 +951,7 @@ func TestUpstreamResolver_NonRetryableEDEShortCircuits(t *testing.T) {
 	resolver := &upstreamResolverBase{
 		ctx:             ctx,
 		upstreamClient:  tracking,
-		upstreamServers: []netip.AddrPort{upstream1, upstream2},
+		upstreamServers: []upstreamRace{{upstream1, upstream2}},
 		upstreamTimeout: UpstreamTimeout,
 	}
 

client/internal/engine.go

@@ -61,9 +61,11 @@ import (
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/route"
 	mgm "github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/management/domain"
+	nbnetworkmap "github.com/netbirdio/netbird/shared/management/networkmap"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/shared/netiputil"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
@@ -202,6 +204,13 @@ type Engine struct {
 	// networkSerial is the latest CurrentSerial (state ID) of the network sent by the Management service
 	networkSerial uint64
 
+	// latestComponents is the most-recent NetworkMapComponents decoded from
+	// a NetworkMapEnvelope (capability=3 peers only). Held alongside the
+	// NetworkMap that Calculate() produced from it so Step 3 incremental
+	// updates have a base to apply changes against. nil for legacy-format
+	// peers. Guarded by syncMsgMux.
+	latestComponents *types.NetworkMapComponents
+
 	networkMonitor *networkmonitor.NetworkMonitor
 
 	sshServer sshServer
@@ -512,16 +521,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 
 	e.routeManager.SetRouteChangeListener(e.mobileDep.NetworkChangeListener)
 
-	e.dnsServer.SetRouteChecker(func(ip netip.Addr) bool {
-		for _, routes := range e.routeManager.GetSelectedClientRoutes() {
-			for _, r := range routes {
-				if r.Network.Contains(ip) {
-					return true
-				}
-			}
-		}
-		return false
-	})
+	e.dnsServer.SetRouteSources(e.routeManager.GetSelectedClientRoutes, e.routeManager.GetActiveClientRoutes)
 
 	if err = e.wgInterfaceCreate(); err != nil {
 		log.Errorf("failed creating tunnel interface %s: [%s]", e.config.WgIfaceName, err.Error())
@@ -874,8 +874,12 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		return e.ctx.Err()
 	}
 
-	if update.NetworkMap != nil && update.NetworkMap.PeerConfig != nil {
-		e.handleAutoUpdateVersion(update.NetworkMap.PeerConfig.AutoUpdate)
+	// Envelope sync responses carry PeerConfig at the top level; legacy
+	// NetworkMap syncs carry it under NetworkMap.PeerConfig.
+	if pc := update.GetPeerConfig(); pc != nil {
+		e.handleAutoUpdateVersion(pc.GetAutoUpdate())
+	} else if nm := update.GetNetworkMap(); nm != nil && nm.GetPeerConfig() != nil {
+		e.handleAutoUpdateVersion(nm.GetPeerConfig().GetAutoUpdate())
 	}
 
 	if update.GetNetbirdConfig() != nil {
@@ -916,11 +920,45 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		return err
 	}
 
-	nm := update.GetNetworkMap()
+	var (
+		nm         *mgmProto.NetworkMap
+		components *types.NetworkMapComponents
+	)
+	if envelope := update.GetNetworkMapEnvelope(); envelope != nil {
+		// Components-format peer: decode the envelope back to typed
+		// components, run Calculate() locally, and convert to the wire
+		// NetworkMap shape the rest of the engine consumes. Components are
+		// retained so future incremental updates (Step 3) can apply deltas
+		// instead of doing a full reconstruction.
+		localKey := e.config.WgPrivateKey.PublicKey().String()
+		dnsName := ""
+		if pc := update.GetPeerConfig(); pc != nil {
+			// PeerConfig.Fqdn = "<dns_label>.<dns_domain>" — extract the
+			// shared domain by stripping the peer's own label prefix. Falls
+			// back to empty if the FQDN doesn't have the expected shape.
+			dnsName = extractDNSDomainFromFQDN(pc.GetFqdn())
+		}
+		result, err := nbnetworkmap.EnvelopeToNetworkMap(e.ctx, envelope, localKey, dnsName)
+		if err != nil {
+			return fmt.Errorf("decode network map envelope: %w", err)
+		}
+		nm = result.NetworkMap
+		components = result.Components
+	} else {
+		nm = update.GetNetworkMap()
+	}
 	if nm == nil {
 		return nil
 	}
 
+	// Only retain the components view when the server sent the envelope
+	// path. A legacy proto.NetworkMap means components == nil; writing it
+	// here would clobber a previously-cached snapshot, breaking the Step 3
+	// incremental-delta base on a future envelope sync.
+	if components != nil {
+		e.latestComponents = components
+	}
+
 	// Persist sync response under the dedicated lock (syncRespMux), not under syncMsgMux.
 	// Read the storage-enabled flag under the syncRespMux too.
 	e.syncRespMux.RLock()
@@ -946,6 +984,19 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	return nil
 }
 
+// extractDNSDomainFromFQDN returns the trailing dotted domain part of the
+// receiving peer's FQDN — the same value the management server fills as
+// dnsName when it builds the legacy NetworkMap. "peer42.netbird.cloud" →
+// "netbird.cloud". An empty string is returned for unrecognized formats.
+func extractDNSDomainFromFQDN(fqdn string) string {
+	for i := 0; i < len(fqdn); i++ {
+		if fqdn[i] == '.' && i+1 < len(fqdn) {
+			return fqdn[i+1:]
+		}
+	}
+	return ""
+}
+
 func (e *Engine) handleRelayUpdate(update *mgmProto.RelayConfig) error {
 	if update != nil {
 		// when we receive token we expect valid address list too
@@ -1386,9 +1437,6 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	e.networkSerial = serial
 
-	// Test received (upstream) servers for availability right away instead of upon usage.
-	// If no server of a server group responds this will disable the respective handler and retry later.
-	go e.dnsServer.ProbeAvailability()
 	return nil
 }
 
@@ -1932,7 +1980,7 @@ func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
 		return dnsServer, nil
 
 	case "ios":
-		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.mobileDep.HostDNSAddresses, e.statusRecorder, e.config.DisableDNS)
+		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.statusRecorder, e.config.DisableDNS)
 		return dnsServer, nil
 
 	default:

client/internal/routemanager/manager.go

@@ -53,6 +53,7 @@ type Manager interface {
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
 	GetSelectedClientRoutes() route.HAMap
+	GetActiveClientRoutes() route.HAMap
 	GetClientRoutesWithNetID() map[route.NetID][]*route.Route
 	SetRouteChangeListener(listener listener.NetworkChangeListener)
 	InitialRouteRange() []string
@@ -485,6 +486,39 @@ func (m *DefaultManager) GetSelectedClientRoutes() route.HAMap {
 	return m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
 }
 
+// GetActiveClientRoutes returns the subset of selected client routes
+// that are currently reachable: the route's peer is Connected and is
+// the one actively carrying the route (not just an HA sibling).
+func (m *DefaultManager) GetActiveClientRoutes() route.HAMap {
+	m.mux.Lock()
+	selected := m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
+	recorder := m.statusRecorder
+	m.mux.Unlock()
+
+	if recorder == nil {
+		return selected
+	}
+
+	out := make(route.HAMap, len(selected))
+	for id, routes := range selected {
+		for _, r := range routes {
+			st, err := recorder.GetPeer(r.Peer)
+			if err != nil {
+				continue
+			}
+			if st.ConnStatus != peer.StatusConnected {
+				continue
+			}
+			if _, hasRoute := st.GetRoutes()[r.Network.String()]; !hasRoute {
+				continue
+			}
+			out[id] = routes
+			break
+		}
+	}
+	return out
+}
+
 // GetClientRoutesWithNetID returns the current routes from the route map, but the keys consist of the network ID only
 func (m *DefaultManager) GetClientRoutesWithNetID() map[route.NetID][]*route.Route {
 	m.mux.Lock()
@@ -704,7 +738,10 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 }
 
 func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
-	return len(routes) > 0 && routes[0].Network.String() == vars.ExitNodeCIDR
+	if len(routes) == 0 {
+		return false
+	}
+	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
 }
 
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {

client/internal/routemanager/mock.go

@@ -19,6 +19,7 @@ type MockManager struct {
 	GetRouteSelectorFunc         func() *routeselector.RouteSelector
 	GetClientRoutesFunc          func() route.HAMap
 	GetSelectedClientRoutesFunc  func() route.HAMap
+	GetActiveClientRoutesFunc    func() route.HAMap
 	GetClientRoutesWithNetIDFunc func() map[route.NetID][]*route.Route
 	StopFunc                     func(manager *statemanager.Manager)
 }
@@ -78,6 +79,14 @@ func (m *MockManager) GetSelectedClientRoutes() route.HAMap {
 	return nil
 }
 
+// GetActiveClientRoutes mock implementation of GetActiveClientRoutes from the Manager interface
+func (m *MockManager) GetActiveClientRoutes() route.HAMap {
+	if m.GetActiveClientRoutesFunc != nil {
+		return m.GetActiveClientRoutesFunc()
+	}
+	return nil
+}
+
 // GetClientRoutesWithNetID mock implementation of GetClientRoutesWithNetID from Manager interface
 func (m *MockManager) GetClientRoutesWithNetID() map[route.NetID][]*route.Route {
 	if m.GetClientRoutesWithNetIDFunc != nil {

client/internal/routeselector/routeselector.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"slices"
+	"strings"
 	"sync"
 
 	"github.com/hashicorp/go-multierror"
@@ -12,10 +13,6 @@ import (
 	"github.com/netbirdio/netbird/route"
 )
 
-const (
-	exitNodeCIDR = "0.0.0.0/0"
-)
-
 type RouteSelector struct {
 	mu               sync.RWMutex
 	deselectedRoutes map[route.NetID]struct{}
@@ -124,13 +121,7 @@ func (rs *RouteSelector) IsSelected(routeID route.NetID) bool {
 	rs.mu.RLock()
 	defer rs.mu.RUnlock()
 
-	if rs.deselectAll {
-		return false
-	}
-
-	_, deselected := rs.deselectedRoutes[routeID]
-	isSelected := !deselected
-	return isSelected
+	return rs.isSelectedLocked(routeID)
 }
 
 // FilterSelected removes unselected routes from the provided map.
@@ -144,23 +135,22 @@ func (rs *RouteSelector) FilterSelected(routes route.HAMap) route.HAMap {
 
 	filtered := route.HAMap{}
 	for id, rt := range routes {
-		netID := id.NetID()
-		_, deselected := rs.deselectedRoutes[netID]
-		if !deselected {
+		if !rs.isDeselectedLocked(id.NetID()) {
 			filtered[id] = rt
 		}
 	}
 	return filtered
 }
 
-// HasUserSelectionForRoute returns true if the user has explicitly selected or deselected this specific route
+// HasUserSelectionForRoute returns true if the user has explicitly selected or deselected this route.
+// Intended for exit-node code paths: a v6 exit-node pair (e.g. "MyExit-v6") with no explicit state of
+// its own inherits its v4 base's state, so legacy persisted selections that predate v6 pairing
+// transparently apply to the synthesized v6 entry.
 func (rs *RouteSelector) HasUserSelectionForRoute(routeID route.NetID) bool {
 	rs.mu.RLock()
 	defer rs.mu.RUnlock()
 
-	_, selected := rs.selectedRoutes[routeID]
-	_, deselected := rs.deselectedRoutes[routeID]
-	return selected || deselected
+	return rs.hasUserSelectionForRouteLocked(rs.effectiveNetID(routeID))
 }
 
 func (rs *RouteSelector) FilterSelectedExitNodes(routes route.HAMap) route.HAMap {
@@ -174,7 +164,7 @@ func (rs *RouteSelector) FilterSelectedExitNodes(routes route.HAMap) route.HAMap
 	filtered := make(route.HAMap, len(routes))
 	for id, rt := range routes {
 		netID := id.NetID()
-		if rs.isDeselected(netID) {
+		if rs.isDeselectedLocked(netID) {
 			continue
 		}
 
@@ -189,13 +179,48 @@ func (rs *RouteSelector) FilterSelectedExitNodes(routes route.HAMap) route.HAMap
 	return filtered
 }
 
-func (rs *RouteSelector) isDeselected(netID route.NetID) bool {
+// effectiveNetID returns the v4 base for a "-v6" exit pair entry that has no explicit
+// state of its own, so selections made on the v4 entry govern the v6 entry automatically.
+// Only call this from exit-node-specific code paths: applying it to a non-exit "-v6" route
+// would make it inherit unrelated v4 state. Must be called with rs.mu held.
+func (rs *RouteSelector) effectiveNetID(id route.NetID) route.NetID {
+	name := string(id)
+	if !strings.HasSuffix(name, route.V6ExitSuffix) {
+		return id
+	}
+	if _, ok := rs.selectedRoutes[id]; ok {
+		return id
+	}
+	if _, ok := rs.deselectedRoutes[id]; ok {
+		return id
+	}
+	return route.NetID(strings.TrimSuffix(name, route.V6ExitSuffix))
+}
+
+func (rs *RouteSelector) isSelectedLocked(routeID route.NetID) bool {
+	if rs.deselectAll {
+		return false
+	}
+	_, deselected := rs.deselectedRoutes[routeID]
+	return !deselected
+}
+
+func (rs *RouteSelector) isDeselectedLocked(netID route.NetID) bool {
+	if rs.deselectAll {
+		return true
+	}
 	_, deselected := rs.deselectedRoutes[netID]
-	return deselected || rs.deselectAll
+	return deselected
+}
+
+func (rs *RouteSelector) hasUserSelectionForRouteLocked(routeID route.NetID) bool {
+	_, selected := rs.selectedRoutes[routeID]
+	_, deselected := rs.deselectedRoutes[routeID]
+	return selected || deselected
 }
 
 func isExitNode(rt []*route.Route) bool {
-	return len(rt) > 0 && rt[0].Network.String() == exitNodeCIDR
+	return len(rt) > 0 && (route.IsV4DefaultRoute(rt[0].Network) || route.IsV6DefaultRoute(rt[0].Network))
 }
 
 func (rs *RouteSelector) applyExitNodeFilter(
@@ -204,26 +229,23 @@ func (rs *RouteSelector) applyExitNodeFilter(
 	rt []*route.Route,
 	out route.HAMap,
 ) {
-
-	if rs.hasUserSelections() {
-		// user made explicit selects/deselects
-		if rs.IsSelected(netID) {
+	// Exit-node path: apply the v4/v6 pair mirror so a deselect on the v4 base also
+	// drops the synthesized v6 entry that lacks its own explicit state.
+	effective := rs.effectiveNetID(netID)
+	if rs.hasUserSelectionForRouteLocked(effective) {
+		if rs.isSelectedLocked(effective) {
 			out[id] = rt
 		}
 		return
 	}
 
-	// no explicit selections: only include routes marked !SkipAutoApply (=AutoApply)
+	// no explicit selection for this route: defer to management's SkipAutoApply flag
 	sel := collectSelected(rt)
 	if len(sel) > 0 {
 		out[id] = sel
 	}
 }
 
-func (rs *RouteSelector) hasUserSelections() bool {
-	return len(rs.selectedRoutes) > 0 || len(rs.deselectedRoutes) > 0
-}
-
 func collectSelected(rt []*route.Route) []*route.Route {
 	var sel []*route.Route
 	for _, r := range rt {

client/internal/routeselector/routeselector_test.go

@@ -330,6 +330,137 @@ func TestRouteSelector_FilterSelectedExitNodes(t *testing.T) {
 	assert.Len(t, filtered, 0) // No routes should be selected
 }
 
+// TestRouteSelector_V6ExitPairInherits covers the v4/v6 exit-node pair selection
+// mirror. The mirror is scoped to exit-node code paths: HasUserSelectionForRoute
+// and FilterSelectedExitNodes resolve a "-v6" entry without explicit state to its
+// v4 base, so legacy persisted selections that predate v6 pairing transparently
+// apply to the synthesized v6 entry. General lookups (IsSelected, FilterSelected)
+// stay literal so unrelated routes named "*-v6" don't inherit unrelated state.
+func TestRouteSelector_V6ExitPairInherits(t *testing.T) {
+	all := []route.NetID{"exit1", "exit1-v6", "exit2", "exit2-v6", "corp", "corp-v6"}
+
+	t.Run("HasUserSelectionForRoute mirrors deselected v4 base", func(t *testing.T) {
+		rs := routeselector.NewRouteSelector()
+		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
+
+		assert.True(t, rs.HasUserSelectionForRoute("exit1-v6"), "v6 pair sees v4 base's user selection")
+
+		// unrelated v6 with no v4 base touched is unaffected
+		assert.False(t, rs.HasUserSelectionForRoute("exit2-v6"))
+	})
+
+	t.Run("IsSelected stays literal for non-exit lookups", func(t *testing.T) {
+		rs := routeselector.NewRouteSelector()
+		require.NoError(t, rs.DeselectRoutes([]route.NetID{"corp"}, all))
+
+		// A non-exit route literally named "corp-v6" must not inherit "corp"'s state
+		// via the mirror; the mirror only applies in exit-node code paths.
+		assert.False(t, rs.IsSelected("corp"))
+		assert.True(t, rs.IsSelected("corp-v6"), "non-exit *-v6 routes must not inherit unrelated v4 state")
+	})
+
+	t.Run("explicit v6 state overrides v4 base in filter", func(t *testing.T) {
+		rs := routeselector.NewRouteSelector()
+		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
+		require.NoError(t, rs.SelectRoutes([]route.NetID{"exit1-v6"}, true, all))
+
+		v4Route := &route.Route{NetID: "exit1", Network: netip.MustParsePrefix("0.0.0.0/0")}
+		v6Route := &route.Route{NetID: "exit1-v6", Network: netip.MustParsePrefix("::/0")}
+		routes := route.HAMap{
+			"exit1|0.0.0.0/0": {v4Route},
+			"exit1-v6|::/0":   {v6Route},
+		}
+
+		filtered := rs.FilterSelectedExitNodes(routes)
+		assert.NotContains(t, filtered, route.HAUniqueID("exit1|0.0.0.0/0"))
+		assert.Contains(t, filtered, route.HAUniqueID("exit1-v6|::/0"), "explicit v6 select wins over v4 base")
+	})
+
+	t.Run("non-v6-suffix routes unaffected", func(t *testing.T) {
+		rs := routeselector.NewRouteSelector()
+		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
+
+		// A route literally named "exit1-something" must not pair-resolve.
+		assert.False(t, rs.HasUserSelectionForRoute("exit1-something"))
+	})
+
+	t.Run("filter v6 paired with deselected v4 base", func(t *testing.T) {
+		rs := routeselector.NewRouteSelector()
+		require.NoError(t, rs.DeselectRoutes([]route.NetID{"exit1"}, all))
+
+		v4Route := &route.Route{NetID: "exit1", Network: netip.MustParsePrefix("0.0.0.0/0")}
+		v6Route := &route.Route{NetID: "exit1-v6", Network: netip.MustParsePrefix("::/0")}
+		routes := route.HAMap{
+			"exit1|0.0.0.0/0": {v4Route},
+			"exit1-v6|::/0":   {v6Route},
+		}
+
+		filtered := rs.FilterSelectedExitNodes(routes)
+		assert.Empty(t, filtered, "deselecting v4 base must also drop the v6 pair")
+	})
+
+	t.Run("non-exit *-v6 routes pass through FilterSelectedExitNodes", func(t *testing.T) {
+		rs := routeselector.NewRouteSelector()
+		require.NoError(t, rs.DeselectRoutes([]route.NetID{"corp"}, all))
+
+		// A non-default-route entry named "corp-v6" is not an exit node and
+		// must not be skipped because its v4 base "corp" is deselected.
+		corpV6 := &route.Route{NetID: "corp-v6", Network: netip.MustParsePrefix("10.0.0.0/8")}
+		routes := route.HAMap{
+			"corp-v6|10.0.0.0/8": {corpV6},
+		}
+
+		filtered := rs.FilterSelectedExitNodes(routes)
+		assert.Contains(t, filtered, route.HAUniqueID("corp-v6|10.0.0.0/8"),
+			"non-exit *-v6 routes must not inherit unrelated v4 state in FilterSelectedExitNodes")
+	})
+}
+
+// TestRouteSelector_SkipAutoApplyPerRoute verifies that management's
+// SkipAutoApply flag governs each untouched route independently, even when
+// the user has explicit selections on other routes.
+func TestRouteSelector_SkipAutoApplyPerRoute(t *testing.T) {
+	autoApplied := &route.Route{
+		NetID:         "Auto",
+		Network:       netip.MustParsePrefix("0.0.0.0/0"),
+		SkipAutoApply: false,
+	}
+	skipApply := &route.Route{
+		NetID:         "Skip",
+		Network:       netip.MustParsePrefix("0.0.0.0/0"),
+		SkipAutoApply: true,
+	}
+	routes := route.HAMap{
+		"Auto|0.0.0.0/0": {autoApplied},
+		"Skip|0.0.0.0/0": {skipApply},
+	}
+
+	rs := routeselector.NewRouteSelector()
+	// User makes an unrelated explicit selection elsewhere.
+	require.NoError(t, rs.DeselectRoutes([]route.NetID{"Unrelated"}, []route.NetID{"Auto", "Skip", "Unrelated"}))
+
+	filtered := rs.FilterSelectedExitNodes(routes)
+	assert.Contains(t, filtered, route.HAUniqueID("Auto|0.0.0.0/0"), "AutoApply route should be included")
+	assert.NotContains(t, filtered, route.HAUniqueID("Skip|0.0.0.0/0"), "SkipAutoApply route should be excluded without explicit user selection")
+}
+
+// TestRouteSelector_V6ExitIsExitNode verifies that ::/0 routes are recognized
+// as exit nodes by the selector's filter path.
+func TestRouteSelector_V6ExitIsExitNode(t *testing.T) {
+	v6Exit := &route.Route{
+		NetID:         "V6Only",
+		Network:       netip.MustParsePrefix("::/0"),
+		SkipAutoApply: true,
+	}
+	routes := route.HAMap{
+		"V6Only|::/0": {v6Exit},
+	}
+
+	rs := routeselector.NewRouteSelector()
+	filtered := rs.FilterSelectedExitNodes(routes)
+	assert.Empty(t, filtered, "::/0 should be treated as an exit node and respect SkipAutoApply")
+}
+
 func TestRouteSelector_NewRoutesBehavior(t *testing.T) {
 	initialRoutes := []route.NetID{"route1", "route2", "route3"}
 	newRoutes := []route.NetID{"route1", "route2", "route3", "route4", "route5"}

client/internal/sleep/detector_darwin.go

@@ -188,7 +188,9 @@ func (d *Detector) triggerCallback(event EventType, cb func(event EventType), do
 	}
 
 	doneChan := make(chan struct{})
-	timeout := time.NewTimer(500 * time.Millisecond)
+	// macOS forces sleep ~30s after kIOMessageSystemWillSleep, so block long
+	// enough for teardown to finish while staying under that deadline.
+	timeout := time.NewTimer(20 * time.Second)
 	defer timeout.Stop()
 
 	go func() {

client/ios/NetBirdSDK/client.go

@@ -162,11 +162,7 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	cfg.WgIface = interfaceName
 
 	c.connectClient = internal.NewConnectClient(ctx, cfg, c.recorder)
-	hostDNS := []netip.AddrPort{
-		netip.MustParseAddrPort("9.9.9.9:53"),
-		netip.MustParseAddrPort("149.112.112.112:53"),
-	}
-	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, hostDNS, c.stateFile)
+	return c.connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile)
 }
 
 // Stop the internal client and free the resources

client/netbird.wxs

@@ -64,6 +64,13 @@
 					<RegistryValue Name="InstalledByMSI" Type="integer" Value="1" KeyPath="yes" />
 				</RegistryKey>
 			</Component>
+			<!-- Drop the HKCU Run\Netbird value written by legacy NSIS installers. -->
+			<Component Id="NetbirdLegacyHKCUCleanup" Guid="*">
+				<RegistryValue Root="HKCU" Key="Software\NetBird GmbH\Installer"
+					Name="LegacyHKCUCleanup" Type="integer" Value="1" KeyPath="yes" />
+				<RemoveRegistryValue Root="HKCU"
+					Key="Software\Microsoft\Windows\CurrentVersion\Run" Name="Netbird" />
+			</Component>
 		</StandardDirectory>
 
 		<StandardDirectory Id="CommonAppDataFolder">
@@ -76,10 +83,28 @@
 			</Directory>
 		</StandardDirectory>
 
+		<!-- Drop Run, App Paths and Uninstall entries written by legacy NSIS
+		     installers into the 32-bit registry view (HKLM\Software\Wow6432Node). -->
+		<Component Id="NetbirdLegacyWow6432Cleanup" Directory="NetbirdInstallDir"
+			Guid="bda5d628-16bd-4086-b2c1-5099d8d51763" Bitness="always32">
+			<RegistryValue Root="HKLM" Key="Software\NetBird GmbH\Installer"
+				Name="LegacyWow6432Cleanup" Type="integer" Value="1" KeyPath="yes" />
+			<RemoveRegistryValue Root="HKLM"
+				Key="Software\Microsoft\Windows\CurrentVersion\Run" Name="Netbird" />
+			<RemoveRegistryKey Action="removeOnInstall" Root="HKLM"
+				Key="Software\Microsoft\Windows\CurrentVersion\App Paths\Netbird" />
+			<RemoveRegistryKey Action="removeOnInstall" Root="HKLM"
+				Key="Software\Microsoft\Windows\CurrentVersion\App Paths\Netbird-ui" />
+			<RemoveRegistryKey Action="removeOnInstall" Root="HKLM"
+				Key="Software\Microsoft\Windows\CurrentVersion\Uninstall\Netbird" />
+		</Component>
+
 		<ComponentGroup Id="NetbirdFilesComponent">
 			<ComponentRef Id="NetbirdFiles" />
 			<ComponentRef Id="NetbirdAumidRegistry" />
 			<ComponentRef Id="NetbirdAutoStart" />
+			<ComponentRef Id="NetbirdLegacyHKCUCleanup" />
+			<ComponentRef Id="NetbirdLegacyWow6432Cleanup" />
 		</ComponentGroup>
 
 		<util:CloseApplication Id="CloseNetBird" CloseMessage="no" Target="netbird.exe" RebootPrompt="no" />

client/ssh/config/manager.go

@@ -252,6 +252,10 @@ func (m *Manager) writeSSHConfig(sshConfig string) error {
 		return fmt.Errorf("write SSH config file %s: %w", tmpPath, err)
 	}
 
+	if err := os.Chmod(tmpPath, 0644); err != nil {
+		return fmt.Errorf("chmod SSH config file %s: %w", tmpPath, err)
+	}
+
 	if err := os.Rename(tmpPath, sshConfigPath); err != nil {
 		return fmt.Errorf("rename SSH config %s -> %s: %w", tmpPath, sshConfigPath, err)
 	}

client/ui/network.go

@@ -193,7 +193,15 @@ func getOverlappingNetworks(routes []*proto.Network) []*proto.Network {
 }
 
 func isDefaultRoute(routeRange string) bool {
-	return routeRange == "0.0.0.0/0" || routeRange == "::/0"
+	// routeRange is the merged display string from the daemon, e.g. "0.0.0.0/0",
+	// "::/0", or "0.0.0.0/0, ::/0" when a v4 exit node has a paired v6 entry.
+	for _, part := range strings.Split(routeRange, ",") {
+		switch strings.TrimSpace(part) {
+		case "0.0.0.0/0", "::/0":
+			return true
+		}
+	}
+	return false
 }
 
 func getExitNodeNetworks(routes []*proto.Network) []*proto.Network {

dns/nameserver.go

@@ -53,6 +53,9 @@ type NameServerGroup struct {
 	ID string `gorm:"primaryKey"`
 	// AccountID is a reference to Account that this object belongs
 	AccountID string `gorm:"index"`
+	// AccountSeqID is a per-account monotonically increasing identifier used as the
+	// compact wire id when sending NetworkMap components to capable peers.
+	AccountSeqID uint32 `json:"-" gorm:"index:idx_nameserver_groups_account_seq_id;not null;default:0"`
 	// Name group name
 	Name string
 	// Description group description

management/internals/controllers/network_map/controller/controller.go

@@ -44,7 +44,7 @@ type Controller struct {
 	EphemeralPeersManager ephemeral.Manager
 
 	accountUpdateLocks               sync.Map
-	sendAccountUpdateLocks           sync.Map
+	affectedPeerUpdateLocks          sync.Map
 	updateAccountPeersBufferInterval atomic.Int64
 	// dnsDomain is used for peer resolution. This is appended to the peer's name
 	dnsDomain string
@@ -55,6 +55,15 @@ type Controller struct {
 	proxyController port_forwarding.Controller
 
 	integratedPeerValidator integrated_validator.IntegratedValidator
+
+	// componentsDisabled is the kill switch for the component-based wire
+	// format. When true the controller emits legacy proto.NetworkMap to every
+	// peer regardless of capability — used to roll back instantly via a
+	// management restart from a bad components encoder.
+	//
+	// Set once in NewController from NB_NETWORK_MAP_COMPONENTS_DISABLE and
+	// never written after — readers race-free without a mutex.
+	componentsDisabled bool
 }
 
 type bufferUpdate struct {
@@ -63,6 +72,13 @@ type bufferUpdate struct {
 	update atomic.Bool
 }
 
+type bufferAffectedUpdate struct {
+	sendMu  sync.Mutex
+	dataMu  sync.Mutex
+	next    *time.Timer
+	peerIDs map[string]struct{}
+}
+
 var _ network_map.Controller = (*Controller)(nil)
 
 func NewController(ctx context.Context, store store.Store, metrics telemetry.AppMetrics, peersUpdateManager network_map.PeersUpdateManager, requestBuffer account.RequestBuffer, integratedPeerValidator integrated_validator.IntegratedValidator, settingsManager settings.Manager, dnsDomain string, proxyController port_forwarding.Controller, ephemeralPeersManager ephemeral.Manager, config *config.Config) *Controller {
@@ -81,12 +97,30 @@ func NewController(ctx context.Context, store store.Store, metrics telemetry.App
 		settingsManager:         settingsManager,
 		dnsDomain:               dnsDomain,
 		config:                  config,
+		componentsDisabled:      parseBoolEnv("NB_NETWORK_MAP_COMPONENTS_DISABLE"),
 
 		proxyController:       proxyController,
 		EphemeralPeersManager: ephemeralPeersManager,
 	}
 }
 
+// PeerNeedsComponents reports whether the gRPC layer should emit the
+// component-based wire format for this peer. Combines the peer's advertised
+// capability with the controller-level kill switch — callers ask exactly
+// this question, so encapsulating it removes accidental double-checks.
+func (c *Controller) PeerNeedsComponents(p *nbpeer.Peer) bool {
+	return p != nil && p.SupportsComponentNetworkMap() && !c.componentsDisabled
+}
+
+// parseBoolEnv reads an env var via strconv.ParseBool so callers accept the
+// usual "1/t/T/TRUE/true/True" set instead of being strict about a single
+// literal — matches the convention used elsewhere in the codebase
+// (e.g. event.go's NB_TRAFFIC_EVENT_*) and reduces operator surprises.
+func parseBoolEnv(key string) bool {
+	v, _ := strconv.ParseBool(os.Getenv(key))
+	return v
+}
+
 func (c *Controller) OnPeerConnected(ctx context.Context, accountID string, peerID string) (chan *network_map.UpdateMessage, error) {
 	peer, err := c.repo.GetPeerByID(ctx, accountID, peerID)
 	if err != nil {
@@ -192,18 +226,26 @@ func (c *Controller) sendUpdateAccountPeers(ctx context.Context, accountID strin
 			c.metrics.CountCalcPostureChecksDuration(time.Since(start))
 			start = time.Now()
 
-			remotePeerNetworkMap := account.GetPeerNetworkMapFromComponents(ctx, p.ID, peersCustomZone, accountZones, approvedPeersMap, resourcePolicies, routers, c.accountManagerMetrics, groupIDToUserIDs)
+			result := account.GetPeerNetworkMapResult(ctx, p.ID, c.componentsDisabled, peersCustomZone, accountZones, approvedPeersMap, resourcePolicies, routers, c.accountManagerMetrics, groupIDToUserIDs)
 
 			c.metrics.CountCalcPeerNetworkMapDuration(time.Since(start))
 
-			proxyNetworkMap, ok := proxyNetworkMaps[peer.ID]
-			if ok {
-				remotePeerNetworkMap.Merge(proxyNetworkMap)
+			proxyNetworkMap := proxyNetworkMaps[p.ID]
+			if result.NetworkMap != nil && proxyNetworkMap != nil {
+				result.NetworkMap.Merge(proxyNetworkMap)
 			}
 
 			peerGroups := account.GetPeerGroups(p.ID)
 			start = time.Now()
-			update := grpc.ToSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, p, nil, nil, remotePeerNetworkMap, dnsDomain, postureChecks, dnsCache, account.Settings, extraSetting, maps.Keys(peerGroups), dnsFwdPort)
+			var update *proto.SyncResponse
+			if result.IsComponents() {
+				// proxyNetworkMap rides the envelope as a ProxyPatch sidecar;
+				// the client merges it into Calculate()'s output the same
+				// way the legacy server did via NetworkMap.Merge.
+				update = grpc.ToComponentSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, p, nil, nil, result.Components, proxyNetworkMap, dnsDomain, postureChecks, account.Settings, extraSetting, maps.Keys(peerGroups), dnsFwdPort)
+			} else {
+				update = grpc.ToSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, p, nil, nil, result.NetworkMap, dnsDomain, postureChecks, dnsCache, account.Settings, extraSetting, maps.Keys(peerGroups), dnsFwdPort)
+			}
 			c.metrics.CountToSyncResponseDuration(time.Since(start))
 
 			c.peersUpdateManager.SendUpdate(ctx, p.ID, &network_map.UpdateMessage{
@@ -221,44 +263,6 @@ func (c *Controller) sendUpdateAccountPeers(ctx context.Context, accountID strin
 	return nil
 }
 
-func (c *Controller) bufferSendUpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) error {
-	log.WithContext(ctx).Tracef("buffer sending update peers for account %s from %s", accountID, util.GetCallerName())
-
-	if c.accountManagerMetrics != nil {
-		c.accountManagerMetrics.CountUpdateAccountPeersTriggered(string(reason.Resource), string(reason.Operation))
-	}
-
-	bufUpd, _ := c.sendAccountUpdateLocks.LoadOrStore(accountID, &bufferUpdate{})
-	b := bufUpd.(*bufferUpdate)
-
-	if !b.mu.TryLock() {
-		b.update.Store(true)
-		return nil
-	}
-
-	if b.next != nil {
-		b.next.Stop()
-	}
-
-	go func() {
-		defer b.mu.Unlock()
-		_ = c.sendUpdateAccountPeers(ctx, accountID)
-		if !b.update.Load() {
-			return
-		}
-		b.update.Store(false)
-		if b.next == nil {
-			b.next = time.AfterFunc(time.Duration(c.updateAccountPeersBufferInterval.Load()), func() {
-				_ = c.sendUpdateAccountPeers(ctx, accountID)
-			})
-			return
-		}
-		b.next.Reset(time.Duration(c.updateAccountPeersBufferInterval.Load()))
-	}()
-
-	return nil
-}
-
 // UpdatePeers updates all peers that belong to an account.
 // Should be called when changes have to be synced to peers.
 func (c *Controller) UpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) error {
@@ -268,6 +272,148 @@ func (c *Controller) UpdateAccountPeers(ctx context.Context, accountID string, r
 	return c.sendUpdateAccountPeers(ctx, accountID)
 }
 
+// UpdateAffectedPeers updates only the specified peers that belong to an account.
+func (c *Controller) UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string) error {
+	if len(peerIDs) == 0 {
+		return nil
+	}
+	return c.sendUpdateForAffectedPeers(ctx, accountID, peerIDs)
+}
+
+func (c *Controller) sendUpdateForAffectedPeers(ctx context.Context, accountID string, peerIDs []string) error {
+	log.WithContext(ctx).Tracef("sendUpdateForAffectedPeers: account %s, %d affected peers: %v (caller: %s)", accountID, len(peerIDs), peerIDs, util.GetCallerName())
+
+	if !c.hasConnectedPeers(peerIDs) {
+		log.WithContext(ctx).Tracef("sendUpdateForAffectedPeers: no connected peers among %v, skipping", peerIDs)
+		return nil
+	}
+
+	account, err := c.requestBuffer.GetAccountWithBackpressure(ctx, accountID)
+	if err != nil {
+		return fmt.Errorf("failed to get account: %v", err)
+	}
+
+	globalStart := time.Now()
+
+	peersToUpdate := c.filterConnectedAffectedPeers(account, peerIDs)
+	if len(peersToUpdate) == 0 {
+		log.WithContext(ctx).Tracef("sendUpdateForAffectedPeers: no peers to update (affected peers not found in account or no channels)")
+		return nil
+	}
+
+	log.WithContext(ctx).Tracef("sendUpdateForAffectedPeers: sending network map to %d connected peers", len(peersToUpdate))
+
+	approvedPeersMap, err := c.integratedPeerValidator.GetValidatedPeers(ctx, account.Id, maps.Values(account.Groups), maps.Values(account.Peers), account.Settings.Extra)
+	if err != nil {
+		return fmt.Errorf("failed to get validate peers: %v", err)
+	}
+
+	var wg sync.WaitGroup
+	semaphore := make(chan struct{}, 10)
+
+	account.InjectProxyPolicies(ctx)
+	dnsCache := &cache.DNSConfigCache{}
+	dnsDomain := c.GetDNSDomain(account.Settings)
+	peersCustomZone := account.GetPeersCustomZone(ctx, dnsDomain)
+	resourcePolicies := account.GetResourcePoliciesMap()
+	routers := account.GetResourceRoutersMap()
+	groupIDToUserIDs := account.GetActiveGroupUsers()
+
+	proxyNetworkMaps, err := c.proxyController.GetProxyNetworkMapsAll(ctx, accountID, account.Peers)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get proxy network maps: %v", err)
+		return fmt.Errorf("failed to get proxy network maps: %v", err)
+	}
+
+	extraSetting, err := c.settingsManager.GetExtraSettings(ctx, accountID)
+	if err != nil {
+		return fmt.Errorf("failed to get flow enabled status: %v", err)
+	}
+
+	dnsFwdPort := computeForwarderPort(maps.Values(account.Peers), network_map.DnsForwarderPortMinVersion)
+
+	accountZones, err := c.repo.GetAccountZones(ctx, account.Id)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get account zones: %v", err)
+		return fmt.Errorf("failed to get account zones: %v", err)
+	}
+
+	for _, peer := range peersToUpdate {
+		wg.Add(1)
+		semaphore <- struct{}{}
+		go func(p *nbpeer.Peer) {
+			defer wg.Done()
+			defer func() { <-semaphore }()
+
+			start := time.Now()
+
+			postureChecks, err := c.getPeerPostureChecks(account, p.ID)
+			if err != nil {
+				log.WithContext(ctx).Debugf("failed to get posture checks for peer %s: %v", p.ID, err)
+				return
+			}
+
+			c.metrics.CountCalcPostureChecksDuration(time.Since(start))
+			start = time.Now()
+
+			result := account.GetPeerNetworkMapResult(ctx, p.ID, c.componentsDisabled, peersCustomZone, accountZones, approvedPeersMap, resourcePolicies, routers, c.accountManagerMetrics, groupIDToUserIDs)
+
+			c.metrics.CountCalcPeerNetworkMapDuration(time.Since(start))
+
+			proxyNetworkMap := proxyNetworkMaps[p.ID]
+			if result.NetworkMap != nil && proxyNetworkMap != nil {
+				result.NetworkMap.Merge(proxyNetworkMap)
+			}
+
+			peerGroups := account.GetPeerGroups(p.ID)
+			start = time.Now()
+			var update *proto.SyncResponse
+			if result.IsComponents() {
+				update = grpc.ToComponentSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, p, nil, nil, result.Components, proxyNetworkMap, dnsDomain, postureChecks, account.Settings, extraSetting, maps.Keys(peerGroups), dnsFwdPort)
+			} else {
+				update = grpc.ToSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, p, nil, nil, result.NetworkMap, dnsDomain, postureChecks, dnsCache, account.Settings, extraSetting, maps.Keys(peerGroups), dnsFwdPort)
+			}
+			c.metrics.CountToSyncResponseDuration(time.Since(start))
+
+			c.peersUpdateManager.SendUpdate(ctx, p.ID, &network_map.UpdateMessage{
+				Update:      update,
+				MessageType: network_map.MessageTypeNetworkMap,
+			})
+		}(peer)
+	}
+
+	wg.Wait()
+	if c.accountManagerMetrics != nil {
+		c.accountManagerMetrics.CountUpdateAccountPeersDuration(time.Since(globalStart))
+	}
+
+	return nil
+}
+
+func (c *Controller) hasConnectedPeers(peerIDs []string) bool {
+	for _, id := range peerIDs {
+		if c.peersUpdateManager.HasChannel(id) {
+			return true
+		}
+	}
+	return false
+}
+
+func (c *Controller) filterConnectedAffectedPeers(account *types.Account, peerIDs []string) []*nbpeer.Peer {
+	affected := make(map[string]struct{}, len(peerIDs))
+	for _, id := range peerIDs {
+		affected[id] = struct{}{}
+	}
+
+	var result []*nbpeer.Peer
+	for _, peer := range account.Peers {
+		if _, ok := affected[peer.ID]; ok && c.peersUpdateManager.HasChannel(peer.ID) {
+			result = append(result, peer)
+		}
+	}
+	return result
+}
+
 func (c *Controller) UpdateAccountPeer(ctx context.Context, accountId string, peerId string) error {
 	if !c.peersUpdateManager.HasChannel(peerId) {
 		return fmt.Errorf("peer %s doesn't have a channel, skipping network map update", peerId)
@@ -314,11 +460,11 @@ func (c *Controller) UpdateAccountPeer(ctx context.Context, accountId string, pe
 		return err
 	}
 
-	remotePeerNetworkMap := account.GetPeerNetworkMapFromComponents(ctx, peerId, peersCustomZone, accountZones, approvedPeersMap, resourcePolicies, routers, c.accountManagerMetrics, groupIDToUserIDs)
+	result := account.GetPeerNetworkMapResult(ctx, peerId, c.componentsDisabled, peersCustomZone, accountZones, approvedPeersMap, resourcePolicies, routers, c.accountManagerMetrics, groupIDToUserIDs)
 
-	proxyNetworkMap, ok := proxyNetworkMaps[peer.ID]
-	if ok {
-		remotePeerNetworkMap.Merge(proxyNetworkMap)
+	proxyNetworkMap := proxyNetworkMaps[peer.ID]
+	if result.NetworkMap != nil && proxyNetworkMap != nil {
+		result.NetworkMap.Merge(proxyNetworkMap)
 	}
 
 	extraSettings, err := c.settingsManager.GetExtraSettings(ctx, peer.AccountID)
@@ -329,7 +475,12 @@ func (c *Controller) UpdateAccountPeer(ctx context.Context, accountId string, pe
 	peerGroups := account.GetPeerGroups(peerId)
 	dnsFwdPort := computeForwarderPort(maps.Values(account.Peers), network_map.DnsForwarderPortMinVersion)
 
-	update := grpc.ToSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, peer, nil, nil, remotePeerNetworkMap, dnsDomain, postureChecks, dnsCache, account.Settings, extraSettings, maps.Keys(peerGroups), dnsFwdPort)
+	var update *proto.SyncResponse
+	if result.IsComponents() {
+		update = grpc.ToComponentSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, peer, nil, nil, result.Components, proxyNetworkMap, dnsDomain, postureChecks, account.Settings, extraSettings, maps.Keys(peerGroups), dnsFwdPort)
+	} else {
+		update = grpc.ToSyncResponse(ctx, nil, c.config.HttpConfig, c.config.DeviceAuthorizationFlow, peer, nil, nil, result.NetworkMap, dnsDomain, postureChecks, dnsCache, account.Settings, extraSettings, maps.Keys(peerGroups), dnsFwdPort)
+	}
 	c.peersUpdateManager.SendUpdate(ctx, peer.ID, &network_map.UpdateMessage{
 		Update:      update,
 		MessageType: network_map.MessageTypeNetworkMap,
@@ -376,6 +527,161 @@ func (c *Controller) BufferUpdateAccountPeers(ctx context.Context, accountID str
 	return nil
 }
 
+// GetValidatedPeerWithComponents is the components-format counterpart of
+// GetValidatedPeerWithMap. It returns raw NetworkMapComponents for capable
+// peers along with the proxy NetworkMap fragment (BYOP / port-forwarding
+// data the legacy server folds in via NetworkMap.Merge). The gRPC layer
+// encodes both into the wire envelope. The caller is responsible for
+// checking peer capability + componentsDisabled before dispatching here —
+// this method does NOT branch on capability itself.
+func (c *Controller) GetValidatedPeerWithComponents(ctx context.Context, isRequiresApproval bool, accountID string, peer *nbpeer.Peer) (*nbpeer.Peer, *types.NetworkMapComponents, *types.NetworkMap, []*posture.Checks, int64, error) {
+	if isRequiresApproval {
+		network, err := c.repo.GetAccountNetwork(ctx, accountID)
+		if err != nil {
+			return nil, nil, nil, nil, 0, err
+		}
+		return peer, &types.NetworkMapComponents{Network: network.Copy()}, nil, nil, 0, nil
+	}
+
+	account, err := c.requestBuffer.GetAccountWithBackpressure(ctx, accountID)
+	if err != nil {
+		return nil, nil, nil, nil, 0, err
+	}
+
+	account.InjectProxyPolicies(ctx)
+
+	approvedPeersMap, err := c.integratedPeerValidator.GetValidatedPeers(ctx, account.Id, maps.Values(account.Groups), maps.Values(account.Peers), account.Settings.Extra)
+	if err != nil {
+		return nil, nil, nil, nil, 0, err
+	}
+
+	postureChecks, err := c.getPeerPostureChecks(account, peer.ID)
+	if err != nil {
+		return nil, nil, nil, nil, 0, err
+	}
+
+	accountZones, err := c.repo.GetAccountZones(ctx, account.Id)
+	if err != nil {
+		return nil, nil, nil, nil, 0, err
+	}
+
+	// Fetch the proxy network map fragment for this peer alongside the
+	// components — same single-account-load path the streaming controller
+	// uses, so initial-sync delivers BYOP/forwarding patches synchronously
+	// instead of waiting for the next streaming push.
+	proxyNetworkMaps, err := c.proxyController.GetProxyNetworkMaps(ctx, account.Id, peer.ID, account.Peers)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get proxy network maps: %v", err)
+		return nil, nil, nil, nil, 0, err
+	}
+
+	dnsDomain := c.GetDNSDomain(account.Settings)
+	peersCustomZone := account.GetPeersCustomZone(ctx, dnsDomain)
+
+	resourcePolicies := account.GetResourcePoliciesMap()
+	routers := account.GetResourceRoutersMap()
+	groupIDToUserIDs := account.GetActiveGroupUsers()
+	components := account.GetPeerNetworkMapComponents(ctx, peer.ID, peersCustomZone, accountZones, approvedPeersMap, resourcePolicies, routers, groupIDToUserIDs)
+
+	dnsFwdPort := computeForwarderPort(maps.Values(account.Peers), network_map.DnsForwarderPortMinVersion)
+
+	return peer, components, proxyNetworkMaps[peer.ID], postureChecks, dnsFwdPort, nil
+}
+
+// BufferUpdateAffectedPeers accumulates peer IDs and flushes them after the buffer interval.
+func (c *Controller) BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason) error {
+	if len(peerIDs) == 0 {
+		return nil
+	}
+
+	if c.accountManagerMetrics != nil {
+		c.accountManagerMetrics.CountUpdateAccountPeersTriggered(string(reason.Resource), string(reason.Operation))
+	}
+
+	log.WithContext(ctx).Tracef("buffer updating %d affected peers for account %s from %s", len(peerIDs), accountID, util.GetCallerName())
+
+	bufUpd, _ := c.affectedPeerUpdateLocks.LoadOrStore(accountID, &bufferAffectedUpdate{
+		peerIDs: make(map[string]struct{}),
+	})
+	b := bufUpd.(*bufferAffectedUpdate)
+
+	b.addPeerIDs(peerIDs)
+
+	if !b.sendMu.TryLock() {
+		// Another goroutine is already sending; it will pick up our IDs on its next drain.
+		return nil
+	}
+
+	b.stopTimer()
+
+	collected := b.drainPeerIDs()
+	go func() {
+		defer b.sendMu.Unlock()
+		_ = c.sendUpdateForAffectedPeers(ctx, accountID, collected)
+
+		// Check if more peer IDs accumulated while we were sending.
+		if !b.hasPending() {
+			return
+		}
+
+		// Schedule a debounced flush for the newly accumulated IDs.
+		b.setTimer(time.Duration(c.updateAccountPeersBufferInterval.Load()), func() {
+			ids := b.drainPeerIDs()
+			if len(ids) > 0 {
+				_ = c.sendUpdateForAffectedPeers(ctx, accountID, ids)
+			}
+		})
+	}()
+
+	return nil
+}
+
+func (b *bufferAffectedUpdate) addPeerIDs(ids []string) {
+	b.dataMu.Lock()
+	for _, id := range ids {
+		b.peerIDs[id] = struct{}{}
+	}
+	b.dataMu.Unlock()
+}
+
+func (b *bufferAffectedUpdate) drainPeerIDs() []string {
+	b.dataMu.Lock()
+	defer b.dataMu.Unlock()
+	if len(b.peerIDs) == 0 {
+		return nil
+	}
+	ids := make([]string, 0, len(b.peerIDs))
+	for id := range b.peerIDs {
+		ids = append(ids, id)
+	}
+	b.peerIDs = make(map[string]struct{})
+	return ids
+}
+
+func (b *bufferAffectedUpdate) hasPending() bool {
+	b.dataMu.Lock()
+	defer b.dataMu.Unlock()
+	return len(b.peerIDs) > 0
+}
+
+func (b *bufferAffectedUpdate) stopTimer() {
+	b.dataMu.Lock()
+	defer b.dataMu.Unlock()
+	if b.next != nil {
+		b.next.Stop()
+	}
+}
+
+func (b *bufferAffectedUpdate) setTimer(d time.Duration, f func()) {
+	b.dataMu.Lock()
+	defer b.dataMu.Unlock()
+	if b.next == nil {
+		b.next = time.AfterFunc(d, f)
+		return
+	}
+	b.next.Reset(d)
+}
+
 func (c *Controller) GetValidatedPeerWithMap(ctx context.Context, isRequiresApproval bool, accountID string, peer *nbpeer.Peer) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error) {
 	if isRequiresApproval {
 		network, err := c.repo.GetAccountNetwork(ctx, accountID)
@@ -573,21 +879,24 @@ func isPeerInPolicySourceGroups(account *types.Account, peerID string, policy *t
 	return false, nil
 }
 
-func (c *Controller) OnPeersUpdated(ctx context.Context, accountID string, peerIDs []string) error {
-	err := c.bufferSendUpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationUpdate})
-	if err != nil {
-		log.WithContext(ctx).Errorf("failed to buffer update account peers for peer update in account %s: %v", accountID, err)
+func (c *Controller) OnPeersUpdated(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error {
+	if len(affectedPeerIDs) == 0 {
+		log.WithContext(ctx).Tracef("no affected peers for peer update in account %s, skipping", accountID)
+		return nil
 	}
-
-	return nil
+	return c.BufferUpdateAffectedPeers(ctx, accountID, affectedPeerIDs, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationUpdate})
 }
 
-func (c *Controller) OnPeersAdded(ctx context.Context, accountID string, peerIDs []string) error {
+func (c *Controller) OnPeersAdded(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error {
 	log.WithContext(ctx).Debugf("OnPeersAdded call to add peers: %v", peerIDs)
-	return c.bufferSendUpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationCreate})
+	if len(affectedPeerIDs) == 0 {
+		log.WithContext(ctx).Tracef("no affected peers for peer add in account %s, skipping", accountID)
+		return nil
+	}
+	return c.BufferUpdateAffectedPeers(ctx, accountID, affectedPeerIDs, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationCreate})
 }
 
-func (c *Controller) OnPeersDeleted(ctx context.Context, accountID string, peerIDs []string) error {
+func (c *Controller) OnPeersDeleted(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error {
 	network, err := c.repo.GetAccountNetwork(ctx, accountID)
 	if err != nil {
 		return err
@@ -620,7 +929,11 @@ func (c *Controller) OnPeersDeleted(ctx context.Context, accountID string, peerI
 		c.peersUpdateManager.CloseChannel(ctx, peerID)
 	}
 
-	return c.bufferSendUpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationDelete})
+	if len(affectedPeerIDs) == 0 {
+		log.WithContext(ctx).Tracef("no affected peers for peer delete in account %s, skipping network map update", accountID)
+		return nil
+	}
+	return c.BufferUpdateAffectedPeers(ctx, accountID, affectedPeerIDs, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationDelete})
 }
 
 // GetNetworkMap returns Network map for a given peer (omits original peer from the Peers result)

management/internals/controllers/network_map/interface.go

@@ -19,17 +19,23 @@ const (
 
 type Controller interface {
 	UpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) error
+	UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string) error
+	BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason) error
 	UpdateAccountPeer(ctx context.Context, accountId string, peerId string) error
 	BufferUpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) error
 	GetValidatedPeerWithMap(ctx context.Context, isRequiresApproval bool, accountID string, p *nbpeer.Peer) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error)
+	GetValidatedPeerWithComponents(ctx context.Context, isRequiresApproval bool, accountID string, p *nbpeer.Peer) (*nbpeer.Peer, *types.NetworkMapComponents, *types.NetworkMap, []*posture.Checks, int64, error)
+	// PeerNeedsComponents combines the peer's advertised capability with the
+	// kill-switch flag — the only public predicate gRPC layers should ask.
+	PeerNeedsComponents(p *nbpeer.Peer) bool
 	GetDNSDomain(settings *types.Settings) string
 	StartWarmup(context.Context)
 	GetNetworkMap(ctx context.Context, peerID string) (*types.NetworkMap, error)
 	CountStreams() int
 
-	OnPeersUpdated(ctx context.Context, accountId string, peerIDs []string) error
-	OnPeersAdded(ctx context.Context, accountID string, peerIDs []string) error
-	OnPeersDeleted(ctx context.Context, accountID string, peerIDs []string) error
+	OnPeersUpdated(ctx context.Context, accountId string, peerIDs []string, affectedPeerIDs []string) error
+	OnPeersAdded(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error
+	OnPeersDeleted(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error
 	DisconnectPeers(ctx context.Context, accountId string, peerIDs []string)
 	OnPeerConnected(ctx context.Context, accountID string, peerID string) (chan *UpdateMessage, error)
 	OnPeerDisconnected(ctx context.Context, accountID string, peerID string)

management/internals/controllers/network_map/interface_mock.go

@@ -57,6 +57,20 @@ func (mr *MockControllerMockRecorder) BufferUpdateAccountPeers(ctx, accountID, r
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "BufferUpdateAccountPeers", reflect.TypeOf((*MockController)(nil).BufferUpdateAccountPeers), ctx, accountID, reason)
 }
 
+// BufferUpdateAffectedPeers mocks base method.
+func (m *MockController) BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "BufferUpdateAffectedPeers", ctx, accountID, peerIDs, reason)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// BufferUpdateAffectedPeers indicates an expected call of BufferUpdateAffectedPeers.
+func (mr *MockControllerMockRecorder) BufferUpdateAffectedPeers(ctx, accountID, peerIDs, reason any) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "BufferUpdateAffectedPeers", reflect.TypeOf((*MockController)(nil).BufferUpdateAffectedPeers), ctx, accountID, peerIDs, reason)
+}
+
 // CountStreams mocks base method.
 func (m *MockController) CountStreams() int {
 	m.ctrl.T.Helper()
@@ -130,6 +144,39 @@ func (mr *MockControllerMockRecorder) GetValidatedPeerWithMap(ctx, isRequiresApp
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetValidatedPeerWithMap", reflect.TypeOf((*MockController)(nil).GetValidatedPeerWithMap), ctx, isRequiresApproval, accountID, p)
 }
 
+// GetValidatedPeerWithComponents mocks base method.
+func (m *MockController) GetValidatedPeerWithComponents(ctx context.Context, isRequiresApproval bool, accountID string, p *peer.Peer) (*peer.Peer, *types.NetworkMapComponents, *types.NetworkMap, []*posture.Checks, int64, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetValidatedPeerWithComponents", ctx, isRequiresApproval, accountID, p)
+	ret0, _ := ret[0].(*peer.Peer)
+	ret1, _ := ret[1].(*types.NetworkMapComponents)
+	ret2, _ := ret[2].(*types.NetworkMap)
+	ret3, _ := ret[3].([]*posture.Checks)
+	ret4, _ := ret[4].(int64)
+	ret5, _ := ret[5].(error)
+	return ret0, ret1, ret2, ret3, ret4, ret5
+}
+
+// GetValidatedPeerWithComponents indicates an expected call of GetValidatedPeerWithComponents.
+func (mr *MockControllerMockRecorder) GetValidatedPeerWithComponents(ctx, isRequiresApproval, accountID, p any) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetValidatedPeerWithComponents", reflect.TypeOf((*MockController)(nil).GetValidatedPeerWithComponents), ctx, isRequiresApproval, accountID, p)
+}
+
+// PeerNeedsComponents mocks base method.
+func (m *MockController) PeerNeedsComponents(p *peer.Peer) bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "PeerNeedsComponents", p)
+	ret0, _ := ret[0].(bool)
+	return ret0
+}
+
+// PeerNeedsComponents indicates an expected call of PeerNeedsComponents.
+func (mr *MockControllerMockRecorder) PeerNeedsComponents(p any) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "PeerNeedsComponents", reflect.TypeOf((*MockController)(nil).PeerNeedsComponents), p)
+}
+
 // OnPeerConnected mocks base method.
 func (m *MockController) OnPeerConnected(ctx context.Context, accountID, peerID string) (chan *UpdateMessage, error) {
 	m.ctrl.T.Helper()
@@ -158,45 +205,45 @@ func (mr *MockControllerMockRecorder) OnPeerDisconnected(ctx, accountID, peerID
 }
 
 // OnPeersAdded mocks base method.
-func (m *MockController) OnPeersAdded(ctx context.Context, accountID string, peerIDs []string) error {
+func (m *MockController) OnPeersAdded(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "OnPeersAdded", ctx, accountID, peerIDs)
+	ret := m.ctrl.Call(m, "OnPeersAdded", ctx, accountID, peerIDs, affectedPeerIDs)
 	ret0, _ := ret[0].(error)
 	return ret0
 }
 
 // OnPeersAdded indicates an expected call of OnPeersAdded.
-func (mr *MockControllerMockRecorder) OnPeersAdded(ctx, accountID, peerIDs any) *gomock.Call {
+func (mr *MockControllerMockRecorder) OnPeersAdded(ctx, accountID, peerIDs, affectedPeerIDs any) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "OnPeersAdded", reflect.TypeOf((*MockController)(nil).OnPeersAdded), ctx, accountID, peerIDs)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "OnPeersAdded", reflect.TypeOf((*MockController)(nil).OnPeersAdded), ctx, accountID, peerIDs, affectedPeerIDs)
 }
 
 // OnPeersDeleted mocks base method.
-func (m *MockController) OnPeersDeleted(ctx context.Context, accountID string, peerIDs []string) error {
+func (m *MockController) OnPeersDeleted(ctx context.Context, accountID string, peerIDs []string, affectedPeerIDs []string) error {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "OnPeersDeleted", ctx, accountID, peerIDs)
+	ret := m.ctrl.Call(m, "OnPeersDeleted", ctx, accountID, peerIDs, affectedPeerIDs)
 	ret0, _ := ret[0].(error)
 	return ret0
 }
 
 // OnPeersDeleted indicates an expected call of OnPeersDeleted.
-func (mr *MockControllerMockRecorder) OnPeersDeleted(ctx, accountID, peerIDs any) *gomock.Call {
+func (mr *MockControllerMockRecorder) OnPeersDeleted(ctx, accountID, peerIDs, affectedPeerIDs any) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "OnPeersDeleted", reflect.TypeOf((*MockController)(nil).OnPeersDeleted), ctx, accountID, peerIDs)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "OnPeersDeleted", reflect.TypeOf((*MockController)(nil).OnPeersDeleted), ctx, accountID, peerIDs, affectedPeerIDs)
 }
 
 // OnPeersUpdated mocks base method.
-func (m *MockController) OnPeersUpdated(ctx context.Context, accountId string, peerIDs []string) error {
+func (m *MockController) OnPeersUpdated(ctx context.Context, accountId string, peerIDs []string, affectedPeerIDs []string) error {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "OnPeersUpdated", ctx, accountId, peerIDs)
+	ret := m.ctrl.Call(m, "OnPeersUpdated", ctx, accountId, peerIDs, affectedPeerIDs)
 	ret0, _ := ret[0].(error)
 	return ret0
 }
 
 // OnPeersUpdated indicates an expected call of OnPeersUpdated.
-func (mr *MockControllerMockRecorder) OnPeersUpdated(ctx, accountId, peerIDs any) *gomock.Call {
+func (mr *MockControllerMockRecorder) OnPeersUpdated(ctx, accountId, peerIDs, affectedPeerIDs any) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "OnPeersUpdated", reflect.TypeOf((*MockController)(nil).OnPeersUpdated), ctx, accountId, peerIDs)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "OnPeersUpdated", reflect.TypeOf((*MockController)(nil).OnPeersUpdated), ctx, accountId, peerIDs, affectedPeerIDs)
 }
 
 // StartWarmup mocks base method.
@@ -250,3 +297,17 @@ func (mr *MockControllerMockRecorder) UpdateAccountPeers(ctx, accountID, reason
 	mr.mock.ctrl.T.Helper()
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "UpdateAccountPeers", reflect.TypeOf((*MockController)(nil).UpdateAccountPeers), ctx, accountID, reason)
 }
+
+// UpdateAffectedPeers mocks base method.
+func (m *MockController) UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "UpdateAffectedPeers", ctx, accountID, peerIDs)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// UpdateAffectedPeers indicates an expected call of UpdateAffectedPeers.
+func (mr *MockControllerMockRecorder) UpdateAffectedPeers(ctx, accountID, peerIDs any) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "UpdateAffectedPeers", reflect.TypeOf((*MockController)(nil).UpdateAffectedPeers), ctx, accountID, peerIDs)
+}

management/internals/modules/peers/ephemeral/manager/ephemeral.go

@@ -11,6 +11,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral"
 	"github.com/netbirdio/netbird/management/server/activity"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 
 	"github.com/netbirdio/netbird/management/server/store"
 )
@@ -47,6 +48,11 @@ type EphemeralManager struct {
 
 	lifeTime      time.Duration
 	cleanupWindow time.Duration
+
+	// metrics is nil-safe; methods on telemetry.EphemeralPeersMetrics
+	// no-op when the receiver is nil so deployments without an app
+	// metrics provider work unchanged.
+	metrics *telemetry.EphemeralPeersMetrics
 }
 
 // NewEphemeralManager instantiate new EphemeralManager
@@ -60,6 +66,15 @@ func NewEphemeralManager(store store.Store, peersManager peers.Manager) *Ephemer
 	}
 }
 
+// SetMetrics attaches a metrics collector. Safe to call once before
+// LoadInitialPeers; later attachment is fine but earlier loads won't be
+// reflected in the gauge. Pass nil to detach.
+func (e *EphemeralManager) SetMetrics(m *telemetry.EphemeralPeersMetrics) {
+	e.peersLock.Lock()
+	e.metrics = m
+	e.peersLock.Unlock()
+}
+
 // LoadInitialPeers load from the database the ephemeral type of peers and schedule a cleanup procedure to the head
 // of the linked list (to the most deprecated peer). At the end of cleanup it schedules the next cleanup to the new
 // head.
@@ -97,7 +112,9 @@ func (e *EphemeralManager) OnPeerConnected(ctx context.Context, peer *nbpeer.Pee
 	e.peersLock.Lock()
 	defer e.peersLock.Unlock()
 
-	e.removePeer(peer.ID)
+	if e.removePeer(peer.ID) {
+		e.metrics.DecPending(1)
+	}
 
 	// stop the unnecessary timer
 	if e.headPeer == nil && e.timer != nil {
@@ -123,6 +140,7 @@ func (e *EphemeralManager) OnPeerDisconnected(ctx context.Context, peer *nbpeer.
 	}
 
 	e.addPeer(peer.AccountID, peer.ID, e.newDeadLine())
+	e.metrics.IncPending()
 	if e.timer == nil {
 		delay := e.headPeer.deadline.Sub(timeNow()) + e.cleanupWindow
 		if delay < 0 {
@@ -145,6 +163,7 @@ func (e *EphemeralManager) loadEphemeralPeers(ctx context.Context) {
 	for _, p := range peers {
 		e.addPeer(p.AccountID, p.ID, t)
 	}
+	e.metrics.AddPending(int64(len(peers)))
 
 	log.WithContext(ctx).Debugf("loaded ephemeral peer(s): %d", len(peers))
 }
@@ -181,6 +200,15 @@ func (e *EphemeralManager) cleanup(ctx context.Context) {
 
 	e.peersLock.Unlock()
 
+	// Drop the gauge by the number of entries we just took off the list,
+	// regardless of whether the subsequent DeletePeers call succeeds. The
+	// list invariant is what the gauge tracks; failed delete batches are
+	// counted separately via CountCleanupError so we can still see them.
+	if len(deletePeers) > 0 {
+		e.metrics.CountCleanupRun()
+		e.metrics.DecPending(int64(len(deletePeers)))
+	}
+
 	peerIDsPerAccount := make(map[string][]string)
 	for id, p := range deletePeers {
 		peerIDsPerAccount[p.accountID] = append(peerIDsPerAccount[p.accountID], id)
@@ -191,7 +219,10 @@ func (e *EphemeralManager) cleanup(ctx context.Context) {
 		err := e.peersManager.DeletePeers(ctx, accountID, peerIDs, activity.SystemInitiator, true)
 		if err != nil {
 			log.WithContext(ctx).Errorf("failed to delete ephemeral peers: %s", err)
+			e.metrics.CountCleanupError()
+			continue
 		}
+		e.metrics.CountPeersCleaned(int64(len(peerIDs)))
 	}
 }
 
@@ -211,9 +242,12 @@ func (e *EphemeralManager) addPeer(accountID string, peerID string, deadline tim
 	e.tailPeer = ep
 }
 
-func (e *EphemeralManager) removePeer(id string) {
+// removePeer drops the entry from the linked list. Returns true if a
+// matching entry was found and removed so callers can keep the pending
+// metric gauge in sync.
+func (e *EphemeralManager) removePeer(id string) bool {
 	if e.headPeer == nil {
-		return
+		return false
 	}
 
 	if e.headPeer.id == id {
@@ -221,7 +255,7 @@ func (e *EphemeralManager) removePeer(id string) {
 		if e.tailPeer.id == id {
 			e.tailPeer = nil
 		}
-		return
+		return true
 	}
 
 	for p := e.headPeer; p.next != nil; p = p.next {
@@ -231,9 +265,10 @@ func (e *EphemeralManager) removePeer(id string) {
 				e.tailPeer = p
 			}
 			p.next = p.next.next
-			return
+			return true
 		}
 	}
+	return false
 }
 
 func (e *EphemeralManager) isPeerOnList(id string) bool {

management/internals/modules/reverseproxy/domain/manager/manager.go

@@ -304,10 +304,27 @@ func (m Manager) getClusterAllowList(ctx context.Context, accountID string) ([]s
 	if err != nil {
 		return nil, fmt.Errorf("get BYOP cluster addresses: %w", err)
 	}
-	if len(byopAddresses) > 0 {
-		return byopAddresses, nil
+	publicAddresses, err := m.proxyManager.GetActiveClusterAddresses(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("get public cluster addresses: %w", err)
 	}
-	return m.proxyManager.GetActiveClusterAddresses(ctx)
+	seen := make(map[string]struct{}, len(byopAddresses)+len(publicAddresses))
+	merged := make([]string, 0, len(byopAddresses)+len(publicAddresses))
+	for _, addr := range byopAddresses {
+		if _, ok := seen[addr]; ok {
+			continue
+		}
+		seen[addr] = struct{}{}
+		merged = append(merged, addr)
+	}
+	for _, addr := range publicAddresses {
+		if _, ok := seen[addr]; ok {
+			continue
+		}
+		seen[addr] = struct{}{}
+		merged = append(merged, addr)
+	}
+	return merged, nil
 }
 
 func extractClusterFromCustomDomains(serviceDomain string, customDomains []*domain.Domain) (string, bool) {

management/internals/modules/reverseproxy/domain/manager/manager_test.go

@@ -40,22 +40,37 @@ func (m *mockProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
 	return nil
 }
 
-func TestGetClusterAllowList_BYOPProxy(t *testing.T) {
+func TestGetClusterAllowList_BYOPMergedWithPublic(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, accID string) ([]string, error) {
 			assert.Equal(t, "acc-123", accID)
 			return []string{"byop.example.com"}, nil
 		},
 		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			t.Fatal("should not call GetActiveClusterAddresses when BYOP addresses exist")
-			return nil, nil
+			return []string{"eu.proxy.netbird.io"}, nil
 		},
 	}
 
 	mgr := Manager{proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
-	assert.Equal(t, []string{"byop.example.com"}, result)
+	assert.Equal(t, []string{"byop.example.com", "eu.proxy.netbird.io"}, result)
+}
+
+func TestGetClusterAllowList_DeduplicatesBYOPAndPublic(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"shared.example.com", "byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return []string{"shared.example.com", "eu.proxy.netbird.io"}, nil
+		},
+	}
+
+	mgr := Manager{proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"shared.example.com", "byop.example.com", "eu.proxy.netbird.io"}, result)
 }
 
 func TestGetClusterAllowList_NoBYOP_FallbackToShared(t *testing.T) {
@@ -79,10 +94,6 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
 			return nil, errors.New("db error")
 		},
-		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			t.Fatal("should not call GetActiveClusterAddresses when BYOP lookup fails")
-			return nil, nil
-		},
 	}
 
 	mgr := Manager{proxyManager: pm}
@@ -92,6 +103,23 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 	assert.Contains(t, err.Error(), "BYOP cluster addresses")
 }
 
+func TestGetClusterAllowList_PublicError_ReturnsError(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return nil, errors.New("db error")
+		},
+	}
+
+	mgr := Manager{proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.Error(t, err)
+	assert.Nil(t, result)
+	assert.Contains(t, err.Error(), "public cluster addresses")
+}
+
 func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
@@ -108,3 +136,19 @@ func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 	assert.Equal(t, []string{"eu.proxy.netbird.io"}, result)
 }
 
+func TestGetClusterAllowList_PublicEmpty_BYOPOnly(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return nil, nil
+		},
+	}
+
+	mgr := Manager{proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"byop.example.com"}, result)
+}
+

management/internals/modules/reverseproxy/proxy/manager/manager.go

@@ -17,7 +17,7 @@ type store interface {
 	UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error
 	GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error)
 	GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error)
-	GetActiveProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
+	GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
 	GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool

management/internals/modules/reverseproxy/proxy/manager/manager_test.go

@@ -57,7 +57,7 @@ func (m *mockStore) GetActiveProxyClusterAddressesForAccount(ctx context.Context
 	}
 	return nil, nil
 }
-func (m *mockStore) GetActiveProxyClusters(_ context.Context, _ string) ([]proxy.Cluster, error) {
+func (m *mockStore) GetProxyClusters(_ context.Context, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 func (m *mockStore) CleanupStaleProxies(ctx context.Context, d time.Duration) error {

management/internals/modules/reverseproxy/proxy/proxy.go

@@ -42,10 +42,35 @@ func (Proxy) TableName() string {
 	return "proxies"
 }
 
+// ClusterType is the source of a proxy cluster.
+type ClusterType string
+
+const (
+	// ClusterTypeAccount is a cluster operated by the account itself (BYOP) —
+	// at least one proxy row in the cluster carries a non-NULL account_id.
+	ClusterTypeAccount ClusterType = "account"
+	// ClusterTypeShared is a cluster operated by NetBird and shared across
+	// accounts — all proxy rows in the cluster have account_id IS NULL.
+	ClusterTypeShared ClusterType = "shared"
+)
+
 // Cluster represents a group of proxy nodes serving the same address.
+//
+// Online and ConnectedProxies derive from the same 2-min active window
+// the rest of the module uses, but Cluster rows are not gated on it —
+// the cluster listing surfaces offline clusters too so operators can
+// see and clean them up. The 1-hour heartbeat reaper still bounds the
+// table eventually.
 type Cluster struct {
 	ID               string
 	Address          string
+	Type             ClusterType
+	Online           bool
 	ConnectedProxies int
-	SelfHosted       bool
+	// Capability flags. *bool because nil means "no proxy reported a
+	// capability for this cluster" — the dashboard renders these as
+	// unknown rather than false.
+	SupportsCustomPorts *bool
+	RequireSubdomain    *bool
+	SupportsCrowdSec    *bool
 }

management/internals/modules/reverseproxy/service/interface.go

@@ -9,7 +9,7 @@ import (
 )
 
 type Manager interface {
-	GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error)
+	GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error)
 	DeleteAccountCluster(ctx context.Context, accountID, userID, clusterAddress string) error
 	GetAllServices(ctx context.Context, accountID, userID string) ([]*Service, error)
 	GetService(ctx context.Context, accountID, userID, serviceID string) (*Service, error)

management/internals/modules/reverseproxy/service/interface_mock.go

@@ -65,20 +65,6 @@ func (mr *MockManagerMockRecorder) CreateServiceFromPeer(ctx, accountID, peerID,
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateServiceFromPeer", reflect.TypeOf((*MockManager)(nil).CreateServiceFromPeer), ctx, accountID, peerID, req)
 }
 
-// DeleteAllServices mocks base method.
-func (m *MockManager) DeleteAllServices(ctx context.Context, accountID, userID string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "DeleteAllServices", ctx, accountID, userID)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// DeleteAllServices indicates an expected call of DeleteAllServices.
-func (mr *MockManagerMockRecorder) DeleteAllServices(ctx, accountID, userID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAllServices", reflect.TypeOf((*MockManager)(nil).DeleteAllServices), ctx, accountID, userID)
-}
-
 // DeleteAccountCluster mocks base method.
 func (m *MockManager) DeleteAccountCluster(ctx context.Context, accountID, userID, clusterAddress string) error {
 	m.ctrl.T.Helper()
@@ -93,6 +79,20 @@ func (mr *MockManagerMockRecorder) DeleteAccountCluster(ctx, accountID, userID,
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockManager)(nil).DeleteAccountCluster), ctx, accountID, userID, clusterAddress)
 }
 
+// DeleteAllServices mocks base method.
+func (m *MockManager) DeleteAllServices(ctx context.Context, accountID, userID string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "DeleteAllServices", ctx, accountID, userID)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// DeleteAllServices indicates an expected call of DeleteAllServices.
+func (mr *MockManagerMockRecorder) DeleteAllServices(ctx, accountID, userID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAllServices", reflect.TypeOf((*MockManager)(nil).DeleteAllServices), ctx, accountID, userID)
+}
+
 // DeleteService mocks base method.
 func (m *MockManager) DeleteService(ctx context.Context, accountID, userID, serviceID string) error {
 	m.ctrl.T.Helper()
@@ -122,21 +122,6 @@ func (mr *MockManagerMockRecorder) GetAccountServices(ctx, accountID interface{}
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountServices", reflect.TypeOf((*MockManager)(nil).GetAccountServices), ctx, accountID)
 }
 
-// GetActiveClusters mocks base method.
-func (m *MockManager) GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetActiveClusters", ctx, accountID, userID)
-	ret0, _ := ret[0].([]proxy.Cluster)
-	ret1, _ := ret[1].(error)
-	return ret0, ret1
-}
-
-// GetActiveClusters indicates an expected call of GetActiveClusters.
-func (mr *MockManagerMockRecorder) GetActiveClusters(ctx, accountID, userID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveClusters", reflect.TypeOf((*MockManager)(nil).GetActiveClusters), ctx, accountID, userID)
-}
-
 // GetAllServices mocks base method.
 func (m *MockManager) GetAllServices(ctx context.Context, accountID, userID string) ([]*Service, error) {
 	m.ctrl.T.Helper()
@@ -152,19 +137,19 @@ func (mr *MockManagerMockRecorder) GetAllServices(ctx, accountID, userID interfa
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAllServices", reflect.TypeOf((*MockManager)(nil).GetAllServices), ctx, accountID, userID)
 }
 
-// GetServiceByDomain mocks base method.
-func (m *MockManager) GetServiceByDomain(ctx context.Context, domain string) (*Service, error) {
+// GetClusters mocks base method.
+func (m *MockManager) GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetServiceByDomain", ctx, domain)
-	ret0, _ := ret[0].(*Service)
+	ret := m.ctrl.Call(m, "GetClusters", ctx, accountID, userID)
+	ret0, _ := ret[0].([]proxy.Cluster)
 	ret1, _ := ret[1].(error)
 	return ret0, ret1
 }
 
-// GetServiceByDomain indicates an expected call of GetServiceByDomain.
-func (mr *MockManagerMockRecorder) GetServiceByDomain(ctx, domain interface{}) *gomock.Call {
+// GetClusters indicates an expected call of GetClusters.
+func (mr *MockManagerMockRecorder) GetClusters(ctx, accountID, userID interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetServiceByDomain", reflect.TypeOf((*MockManager)(nil).GetServiceByDomain), ctx, domain)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusters", reflect.TypeOf((*MockManager)(nil).GetClusters), ctx, accountID, userID)
 }
 
 // GetGlobalServices mocks base method.
@@ -197,6 +182,21 @@ func (mr *MockManagerMockRecorder) GetService(ctx, accountID, userID, serviceID
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetService", reflect.TypeOf((*MockManager)(nil).GetService), ctx, accountID, userID, serviceID)
 }
 
+// GetServiceByDomain mocks base method.
+func (m *MockManager) GetServiceByDomain(ctx context.Context, domain string) (*Service, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetServiceByDomain", ctx, domain)
+	ret0, _ := ret[0].(*Service)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetServiceByDomain indicates an expected call of GetServiceByDomain.
+func (mr *MockManagerMockRecorder) GetServiceByDomain(ctx, domain interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetServiceByDomain", reflect.TypeOf((*MockManager)(nil).GetServiceByDomain), ctx, domain)
+}
+
 // GetServiceByID mocks base method.
 func (m *MockManager) GetServiceByID(ctx context.Context, accountID, serviceID string) (*Service, error) {
 	m.ctrl.T.Helper()

management/internals/modules/reverseproxy/service/manager/api.go

@@ -187,7 +187,7 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	clusters, err := h.manager.GetActiveClusters(r.Context(), userAuth.AccountId, userAuth.UserId)
+	clusters, err := h.manager.GetClusters(r.Context(), userAuth.AccountId, userAuth.UserId)
 	if err != nil {
 		util.WriteError(r.Context(), err, w)
 		return
@@ -196,10 +196,14 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 	apiClusters := make([]api.ProxyCluster, 0, len(clusters))
 	for _, c := range clusters {
 		apiClusters = append(apiClusters, api.ProxyCluster{
-			Id:               c.ID,
-			Address:          c.Address,
-			ConnectedProxies: c.ConnectedProxies,
-			SelfHosted:       c.SelfHosted,
+			Id:                  c.ID,
+			Address:             c.Address,
+			Type:                api.ProxyClusterType(c.Type),
+			Online:              c.Online,
+			ConnectedProxies:    c.ConnectedProxies,
+			SupportsCustomPorts: c.SupportsCustomPorts,
+			RequireSubdomain:    c.RequireSubdomain,
+			SupportsCrowdsec:    c.SupportsCrowdSec,
 		})
 	}
 

management/internals/modules/reverseproxy/service/manager/manager.go

@@ -81,6 +81,7 @@ type ClusterDeriver interface {
 type CapabilityProvider interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
 }
 
 type Manager struct {
@@ -112,8 +113,12 @@ func (m *Manager) StartExposeReaper(ctx context.Context) {
 	m.exposeReaper.StartExposeReaper(ctx)
 }
 
-// GetActiveClusters returns all active proxy clusters with their connected proxy count.
-func (m *Manager) GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
+// GetClusters returns every proxy cluster visible to the account
+// (shared + its own BYOP), regardless of whether any proxy in the
+// cluster is currently heartbeating. Each cluster is enriched with the
+// capability flags reported by its active proxies so the dashboard can
+// render feature support without a second round-trip.
+func (m *Manager) GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
 	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
@@ -122,7 +127,18 @@ func (m *Manager) GetActiveClusters(ctx context.Context, accountID, userID strin
 		return nil, status.NewPermissionDeniedError()
 	}
 
-	return m.store.GetActiveProxyClusters(ctx, accountID)
+	clusters, err := m.store.GetProxyClusters(ctx, accountID)
+	if err != nil {
+		return nil, err
+	}
+
+	for i := range clusters {
+		clusters[i].SupportsCustomPorts = m.capabilities.ClusterSupportsCustomPorts(ctx, clusters[i].Address)
+		clusters[i].RequireSubdomain = m.capabilities.ClusterRequireSubdomain(ctx, clusters[i].Address)
+		clusters[i].SupportsCrowdSec = m.capabilities.ClusterSupportsCrowdSec(ctx, clusters[i].Address)
+	}
+
+	return clusters, nil
 }
 
 // DeleteAccountCluster removes all proxy registrations for the given cluster address
@@ -306,6 +322,10 @@ func (m *Manager) validateSubdomainRequirement(ctx context.Context, domain, clus
 func (m *Manager) persistNewService(ctx context.Context, accountID string, svc *service.Service) error {
 	customPorts := m.clusterCustomPorts(ctx, svc)
 
+	if err := validateTargetReferences(ctx, m.store, accountID, svc.Targets); err != nil {
+		return err
+	}
+
 	return m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if svc.Domain != "" {
 			if err := m.checkDomainAvailable(ctx, transaction, svc.Domain, ""); err != nil {
@@ -321,10 +341,6 @@ func (m *Manager) persistNewService(ctx context.Context, accountID string, svc *
 			return err
 		}
 
-		if err := validateTargetReferences(ctx, transaction, accountID, svc.Targets); err != nil {
-			return err
-		}
-
 		if err := transaction.CreateService(ctx, svc); err != nil {
 			return fmt.Errorf("create service: %w", err)
 		}
@@ -435,6 +451,10 @@ func (m *Manager) assignPort(ctx context.Context, tx store.Store, cluster string
 func (m *Manager) persistNewEphemeralService(ctx context.Context, accountID, peerID string, svc *service.Service) error {
 	customPorts := m.clusterCustomPorts(ctx, svc)
 
+	if err := validateTargetReferences(ctx, m.store, accountID, svc.Targets); err != nil {
+		return err
+	}
+
 	return m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err := m.validateEphemeralPreconditions(ctx, transaction, accountID, peerID, svc); err != nil {
 			return err
@@ -448,10 +468,6 @@ func (m *Manager) persistNewEphemeralService(ctx context.Context, accountID, pee
 			return err
 		}
 
-		if err := validateTargetReferences(ctx, transaction, accountID, svc.Targets); err != nil {
-			return err
-		}
-
 		if err := transaction.CreateService(ctx, svc); err != nil {
 			return fmt.Errorf("create service: %w", err)
 		}
@@ -552,10 +568,22 @@ func (m *Manager) persistServiceUpdate(ctx context.Context, accountID string, se
 	svcForCaps.ProxyCluster = effectiveCluster
 	customPorts := m.clusterCustomPorts(ctx, &svcForCaps)
 
+	if err := validateTargetReferences(ctx, m.store, accountID, service.Targets); err != nil {
+		return nil, err
+	}
+
+	// Validate subdomain requirement *before* the transaction: the underlying
+	// capability lookup talks to the main DB pool, and SQLite's single-connection
+	// pool would self-deadlock if this ran while the tx already held the only
+	// connection.
+	if err := m.validateSubdomainRequirement(ctx, service.Domain, effectiveCluster); err != nil {
+		return nil, err
+	}
+
 	var updateInfo serviceUpdateInfo
 
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		return m.executeServiceUpdate(ctx, transaction, accountID, service, &updateInfo, customPorts)
+		return m.executeServiceUpdate(ctx, transaction, accountID, service, &updateInfo, customPorts, effectiveCluster)
 	})
 
 	return &updateInfo, err
@@ -585,7 +613,7 @@ func (m *Manager) resolveEffectiveCluster(ctx context.Context, accountID string,
 	return existing.ProxyCluster, nil
 }
 
-func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.Store, accountID string, service *service.Service, updateInfo *serviceUpdateInfo, customPorts *bool) error {
+func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.Store, accountID string, service *service.Service, updateInfo *serviceUpdateInfo, customPorts *bool, effectiveCluster string) error {
 	existingService, err := transaction.GetServiceByID(ctx, store.LockingStrengthUpdate, accountID, service.ID)
 	if err != nil {
 		return err
@@ -603,17 +631,13 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	updateInfo.domainChanged = existingService.Domain != service.Domain
 
 	if updateInfo.domainChanged {
-		if err := m.handleDomainChange(ctx, transaction, accountID, service); err != nil {
+		if err := m.handleDomainChange(ctx, transaction, service, effectiveCluster); err != nil {
 			return err
 		}
 	} else {
 		service.ProxyCluster = existingService.ProxyCluster
 	}
 
-	if err := m.validateSubdomainRequirement(ctx, service.Domain, service.ProxyCluster); err != nil {
-		return err
-	}
-
 	m.preserveExistingAuthSecrets(service, existingService)
 	if err := validateHeaderAuthValues(service.Auth.HeaderAuths); err != nil {
 		return err
@@ -628,9 +652,6 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	if err := m.checkPortConflict(ctx, transaction, service); err != nil {
 		return err
 	}
-	if err := validateTargetReferences(ctx, transaction, accountID, service.Targets); err != nil {
-		return err
-	}
 	if err := transaction.UpdateService(ctx, service); err != nil {
 		return fmt.Errorf("update service: %w", err)
 	}
@@ -638,20 +659,18 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	return nil
 }
 
-func (m *Manager) handleDomainChange(ctx context.Context, transaction store.Store, accountID string, svc *service.Service) error {
+// handleDomainChange validates the new domain is free inside the transaction
+// and applies the pre-resolved cluster (computed outside the tx by
+// resolveEffectiveCluster). It must NOT call clusterDeriver here: that talks
+// to the main DB pool and would self-deadlock under SQLite (max_open_conns=1)
+// because the transaction already holds the only connection.
+func (m *Manager) handleDomainChange(ctx context.Context, transaction store.Store, svc *service.Service, effectiveCluster string) error {
 	if err := m.checkDomainAvailable(ctx, transaction, svc.Domain, svc.ID); err != nil {
 		return err
 	}
-
-	if m.clusterDeriver != nil {
-		newCluster, err := m.clusterDeriver.DeriveClusterFromDomain(ctx, accountID, svc.Domain)
-		if err != nil {
-			log.WithError(err).Warnf("could not derive cluster from domain %s", svc.Domain)
-		} else {
-			svc.ProxyCluster = newCluster
-		}
+	if effectiveCluster != "" {
+		svc.ProxyCluster = effectiveCluster
 	}
-
 	return nil
 }
 

management/internals/modules/reverseproxy/service/service.go

@@ -381,13 +381,14 @@ func (s *Service) buildPathMappings() []*proto.PathMapping {
 		}
 
 		// HTTP/HTTPS: build full URL
+		hostNoBrackets := strings.TrimSuffix(strings.TrimPrefix(target.Host, "["), "]")
 		targetURL := url.URL{
 			Scheme: target.Protocol,
-			Host:   target.Host,
+			Host:   bracketIPv6Host(hostNoBrackets),
 			Path:   "/",
 		}
 		if target.Port > 0 && !isDefaultPort(target.Protocol, target.Port) {
-			targetURL.Host = net.JoinHostPort(targetURL.Host, strconv.FormatUint(uint64(target.Port), 10))
+			targetURL.Host = net.JoinHostPort(hostNoBrackets, strconv.FormatUint(uint64(target.Port), 10))
 		}
 
 		path := "/"
@@ -405,6 +406,19 @@ func (s *Service) buildPathMappings() []*proto.PathMapping {
 	return pathMappings
 }
 
+// bracketIPv6Host wraps host in square brackets when it is an IPv6 literal, as
+// required for the Host field of net/url.URL (RFC 3986 §3.2.2). v4-mapped IPv6
+// addresses are bracketed too since their textual form contains colons.
+func bracketIPv6Host(host string) string {
+	if strings.HasPrefix(host, "[") {
+		return host
+	}
+	if addr, err := netip.ParseAddr(host); err == nil && addr.Is6() {
+		return "[" + host + "]"
+	}
+	return host
+}
+
 func operationToProtoType(op Operation) proto.ProxyMappingUpdateType {
 	switch op {
 	case Create:

management/internals/modules/reverseproxy/service/service_test.go

@@ -351,6 +351,83 @@ func TestToProtoMapping_PortInTargetURL(t *testing.T) {
 			port:       80,
 			wantTarget: "https://10.0.0.1:80/",
 		},
+		{
+			name:       "domain host without port is unchanged",
+			protocol:   "http",
+			host:       "example.com",
+			port:       0,
+			wantTarget: "http://example.com/",
+		},
+		{
+			name:       "domain host with non-default port is unchanged",
+			protocol:   "http",
+			host:       "example.com",
+			port:       8080,
+			wantTarget: "http://example.com:8080/",
+		},
+		{
+			name:       "ipv6 host without port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe:1::3",
+			port:       0,
+			wantTarget: "http://[fb00:cafe:1::3]/",
+		},
+		{
+			name:       "ipv6 host with default port omits port and brackets host",
+			protocol:   "http",
+			host:       "fb00:cafe:1::3",
+			port:       80,
+			wantTarget: "http://[fb00:cafe:1::3]/",
+		},
+		{
+			name:       "ipv6 host with non-default port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe:1::3",
+			port:       8080,
+			wantTarget: "http://[fb00:cafe:1::3]:8080/",
+		},
+		{
+			name:       "ipv6 loopback without port is bracketed",
+			protocol:   "http",
+			host:       "::1",
+			port:       0,
+			wantTarget: "http://[::1]/",
+		},
+		{
+			name:       "ipv6 host with 5-digit port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe::1",
+			port:       18080,
+			wantTarget: "http://[fb00:cafe::1]:18080/",
+		},
+		{
+			name:       "pre-bracketed ipv6 without port stays single-bracketed",
+			protocol:   "http",
+			host:       "[fb00:cafe::1]",
+			port:       0,
+			wantTarget: "http://[fb00:cafe::1]/",
+		},
+		{
+			name:       "pre-bracketed ipv6 with port is not double-bracketed",
+			protocol:   "http",
+			host:       "[fb00:cafe::1]",
+			port:       8080,
+			wantTarget: "http://[fb00:cafe::1]:8080/",
+		},
+		{
+			name:       "v4-mapped ipv6 host without port is bracketed",
+			protocol:   "http",
+			host:       "::ffff:10.0.0.1",
+			port:       0,
+			wantTarget: "http://[::ffff:10.0.0.1]/",
+		},
+		{
+			name:       "full-form 8-group ipv6 without port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe:1:0:0:0:0:3",
+			port:       0,
+			wantTarget: "http://[fb00:cafe:1:0:0:0:0:3]/",
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {

management/internals/server/controllers.go

@@ -112,7 +112,11 @@ func (s *BaseServer) AuthManager() auth.Manager {
 
 func (s *BaseServer) EphemeralManager() ephemeral.Manager {
 	return Create(s, func() ephemeral.Manager {
-		return manager.NewEphemeralManager(s.Store(), s.PeersManager())
+		em := manager.NewEphemeralManager(s.Store(), s.PeersManager())
+		if metrics := s.Metrics(); metrics != nil {
+			em.SetMetrics(metrics.EphemeralPeersMetrics())
+		}
+		return em
 	})
 }
 

management/internals/shared/grpc/components_encoder.go

@@ -0,0 +1,815 @@
+package grpc
+
+import (
+	"encoding/base64"
+	"strconv"
+
+	nbdns "github.com/netbirdio/netbird/dns"
+	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
+	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/types"
+	nbroute "github.com/netbirdio/netbird/route"
+	"github.com/netbirdio/netbird/shared/management/networkmap"
+	"github.com/netbirdio/netbird/shared/management/proto"
+)
+
+// wgKeyRawLen is the raw byte length of a WireGuard public key.
+const wgKeyRawLen = 32
+
+// ComponentsEnvelopeInput bundles the data the component-format encoder needs.
+// In Step 2 the envelope is fully self-contained — every field needed by the
+// client's local Calculate() comes from the components struct itself. The
+// only externally-supplied data is the receiving peer's PeerConfig (which is
+// computed alongside the components in the network_map controller and reused
+// from the legacy proto path) and the dns_domain string.
+type ComponentsEnvelopeInput struct {
+	Components       *types.NetworkMapComponents
+	PeerConfig       *proto.PeerConfig
+	DNSDomain        string
+	DNSForwarderPort int64
+	// UserIDClaim is the OIDC claim name the client should embed in
+	// SshAuth.UserIDClaim when reconstructing the NetworkMap. Empty value
+	// is OK — client treats empty as "no SshAuth to build".
+	UserIDClaim string
+	// ProxyPatch carries pre-expanded NetworkMap fragments injected by
+	// external controllers (BYOP/port-forwarding). Nil when no proxy data
+	// is present; encoder skips the field in that case.
+	ProxyPatch *proto.ProxyPatch
+}
+
+// EncodeNetworkMapEnvelope converts NetworkMapComponents into the component
+// wire envelope. The encoder is intentionally non-deterministic: it iterates
+// Go maps in their native (random) order. Indexes inside the envelope
+// (peer_indexes, source_group_ids, agent_version_idx, router_peer_indexes)
+// are self-consistent within a single encode, so the decoder reconstructs
+// the same typed objects regardless of emit order. Tests that need to
+// compare envelopes do so semantically via proto round-trip + canonicalize,
+// not byte-equal.
+//
+// Callers must NOT concatenate or merge envelopes from different encodes —
+// index spaces are local to a single envelope. Delta sync (Step 3+) will
+// use a different shape for the same reason.
+func EncodeNetworkMapEnvelope(in ComponentsEnvelopeInput) *proto.NetworkMapEnvelope {
+	c := in.Components
+
+	// Graceful degrade when components is nil — matches the legacy path's
+	// account_components.go:43 behaviour for missing/unvalidated peers
+	// (return a NetworkMap with only Network populated). The receiver gets
+	// an envelope it can decode without crashing; AccountSettings stays
+	// non-nil so client-side dereferences are safe.
+	if c == nil {
+		// Match legacy missing-peer minimum: a NetworkMap with only Network
+		// populated (account_components.go:43). The receiver gets enough to
+		// bootstrap (Network identifier, dns_domain, account_settings) and
+		// nothing else.
+		return &proto.NetworkMapEnvelope{
+			Payload: &proto.NetworkMapEnvelope_Full{
+				Full: &proto.NetworkMapComponentsFull{
+					PeerConfig:       in.PeerConfig,
+					DnsDomain:        in.DNSDomain,
+					DnsForwarderPort: in.DNSForwarderPort,
+					UserIdClaim:      in.UserIDClaim,
+					AccountSettings:  &proto.AccountSettingsCompact{},
+					ProxyPatch:       in.ProxyPatch,
+				},
+			},
+		}
+	}
+
+	// Phase 1: build dedup tables. Every routing peer (in c.RouterPeers) and
+	// every regular peer (in c.Peers) must be indexed before any encoder
+	// looks up indexes via e.peerOrder — otherwise routes / routers_map for
+	// peers that exist only in c.RouterPeers would silently lose their
+	// peer_index reference.
+	enc := newComponentEncoder(c)
+	enc.indexAllPeers()
+	routerIdxs := enc.indexRouterPeers(c.RouterPeers)
+
+	// Phase 2: gather every policy that any consumer references (peer-pair
+	// policies + resource-only policies) so encodeResourcePoliciesMap can
+	// translate every *Policy pointer to a wire index.
+	allPolicies := unionPolicies(c.Policies, c.ResourcePoliciesMap)
+	policies, policyToIdxs := enc.encodePolicies(allPolicies)
+
+	// Phase 3: emit. Order of struct field expressions no longer matters:
+	// every encoder either reads from the dedup tables or works on
+	// independent input.
+	full := &proto.NetworkMapComponentsFull{
+		Serial:              networkSerial(c.Network),
+		PeerConfig:          in.PeerConfig,
+		Network:             toAccountNetwork(c.Network),
+		AccountSettings:     toAccountSettingsCompact(c.AccountSettings),
+		DnsForwarderPort:    in.DNSForwarderPort,
+		UserIdClaim:         in.UserIDClaim,
+		ProxyPatch:          in.ProxyPatch,
+		DnsSettings:         enc.encodeDNSSettings(c.DNSSettings),
+		DnsDomain:           in.DNSDomain,
+		CustomZoneDomain:    c.CustomZoneDomain,
+		AgentVersions:       enc.agentVersions,
+		Peers:               enc.peers,
+		RouterPeerIndexes:   routerIdxs,
+		Policies:            policies,
+		Groups:              enc.encodeGroups(),
+		Routes:              enc.encodeRoutes(c.Routes),
+		NameserverGroups:    enc.encodeNameServerGroups(c.NameServerGroups),
+		AllDnsRecords:       encodeSimpleRecords(c.AllDNSRecords),
+		AccountZones:        encodeCustomZones(c.AccountZones),
+		NetworkResources:    enc.encodeNetworkResources(c.NetworkResources),
+		RoutersMap:          enc.encodeRoutersMap(c.RoutersMap),
+		ResourcePoliciesMap: enc.encodeResourcePoliciesMap(c.ResourcePoliciesMap, policyToIdxs),
+		GroupIdToUserIds:    enc.encodeGroupIDToUserIDs(c.GroupIDToUserIDs),
+		AllowedUserIds:      stringSetToSlice(c.AllowedUserIDs),
+		PostureFailedPeers:  enc.encodePostureFailedPeers(c.PostureFailedPeers),
+	}
+
+	return &proto.NetworkMapEnvelope{
+		Payload: &proto.NetworkMapEnvelope_Full{Full: full},
+	}
+}
+
+// networkSerial returns c.Network.CurrentSerial() with a nil guard. The
+// production path always populates c.Network (account_components.go:86), but
+// the encoder is exported and a hand-built components struct may omit it.
+func networkSerial(n *types.Network) uint64 {
+	if n == nil {
+		return 0
+	}
+	return n.CurrentSerial()
+}
+
+type componentEncoder struct {
+	components *types.NetworkMapComponents
+
+	peerOrder map[string]uint32
+	peers     []*proto.PeerCompact
+
+	agentVersionOrder map[string]uint32
+	agentVersions     []string
+}
+
+func newComponentEncoder(c *types.NetworkMapComponents) *componentEncoder {
+	return &componentEncoder{
+		components:        c,
+		peerOrder:         make(map[string]uint32, len(c.Peers)),
+		peers:             make([]*proto.PeerCompact, 0, len(c.Peers)),
+		agentVersionOrder: make(map[string]uint32),
+	}
+}
+
+func (e *componentEncoder) indexAllPeers() {
+	for _, p := range e.components.Peers {
+		if p == nil {
+			continue
+		}
+		e.appendPeer(p)
+	}
+}
+
+func (e *componentEncoder) appendPeer(p *nbpeer.Peer) uint32 {
+	if idx, ok := e.peerOrder[p.ID]; ok {
+		return idx
+	}
+	idx := uint32(len(e.peers))
+	e.peerOrder[p.ID] = idx
+	e.peers = append(e.peers, toPeerCompact(p, e.agentVersionIndex(p.Meta.WtVersion)))
+	return idx
+}
+
+func (e *componentEncoder) agentVersionIndex(v string) uint32 {
+	if idx, ok := e.agentVersionOrder[v]; ok {
+		return idx
+	}
+	// Lazy-initialise the table with "" at index 0 so the empty string
+	// stays interchangeable with proto3's default uint32=0 — peers without
+	// a WtVersion don't force the table to materialise.
+	if v == "" {
+		idx := uint32(len(e.agentVersions))
+		if idx == 0 {
+			e.agentVersions = append(e.agentVersions, "")
+		}
+		e.agentVersionOrder[""] = idx
+		return idx
+	}
+	if len(e.agentVersions) == 0 {
+		e.agentVersions = append(e.agentVersions, "")
+		e.agentVersionOrder[""] = 0
+	}
+	idx := uint32(len(e.agentVersions))
+	e.agentVersionOrder[v] = idx
+	e.agentVersions = append(e.agentVersions, v)
+	return idx
+}
+
+// indexRouterPeers ensures every router peer is in the peer dedup table
+// (c.RouterPeers may contain peers not in c.Peers when validation rules drop
+// them) and returns their wire indexes for the RouterPeerIndexes field. Must
+// run before any encoder that resolves peer ids via e.peerOrder.
+func (e *componentEncoder) indexRouterPeers(routers map[string]*nbpeer.Peer) []uint32 {
+	if len(routers) == 0 {
+		return nil
+	}
+	out := make([]uint32, 0, len(routers))
+	for _, p := range routers {
+		if p == nil {
+			continue
+		}
+		out = append(out, e.appendPeer(p))
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeGroups() []*proto.GroupCompact {
+	if len(e.components.Groups) == 0 {
+		return nil
+	}
+
+	out := make([]*proto.GroupCompact, 0, len(e.components.Groups))
+	for _, g := range e.components.Groups {
+		if !g.HasSeqID() {
+			continue
+		}
+		peerIdxs := make([]uint32, 0, len(g.Peers))
+		for _, peerID := range g.Peers {
+			if idx, ok := e.peerOrder[peerID]; ok {
+				peerIdxs = append(peerIdxs, idx)
+			}
+		}
+		out = append(out, &proto.GroupCompact{
+			Id:          g.AccountSeqID,
+			Name:        g.Name,
+			PeerIndexes: peerIdxs,
+		})
+	}
+	return out
+}
+
+// encodePolicies flattens Policy{Rules} → []PolicyCompact. Returns the wire
+// list and a map from policy pointer to the indexes of its emitted rules in
+// that list — used by encodeResourcePoliciesMap to translate
+// ResourcePoliciesMap[resourceID][]*Policy into wire-side indexes.
+func (e *componentEncoder) encodePolicies(policies []*types.Policy) ([]*proto.PolicyCompact, map[*types.Policy][]uint32) {
+	if len(policies) == 0 {
+		return nil, nil
+	}
+
+	out := make([]*proto.PolicyCompact, 0, len(policies))
+	idxByPolicy := make(map[*types.Policy][]uint32, len(policies))
+
+	for _, pol := range policies {
+		if !pol.HasSeqID() || !pol.Enabled {
+			continue
+		}
+		for _, r := range pol.Rules {
+			if r == nil || !r.Enabled {
+				continue
+			}
+			idxByPolicy[pol] = append(idxByPolicy[pol], uint32(len(out)))
+			out = append(out, e.encodePolicyRule(pol, r))
+		}
+	}
+	return out, idxByPolicy
+}
+
+// encodePolicyRule maps a single PolicyRule under pol to a PolicyCompact entry.
+func (e *componentEncoder) encodePolicyRule(pol *types.Policy, r *types.PolicyRule) *proto.PolicyCompact {
+	return &proto.PolicyCompact{
+		Id:                       pol.AccountSeqID,
+		Action:                   networkmap.GetProtoAction(string(r.Action)),
+		Protocol:                 networkmap.GetProtoProtocol(string(r.Protocol)),
+		Bidirectional:            r.Bidirectional,
+		Ports:                    portsToUint32(r.Ports),
+		PortRanges:               portRangesToProto(r.PortRanges),
+		SourceGroupIds:           e.groupSeqIDs(r.Sources),
+		DestinationGroupIds:      e.groupSeqIDs(r.Destinations),
+		AuthorizedUser:           r.AuthorizedUser,
+		AuthorizedGroups:         e.encodeAuthorizedGroups(r.AuthorizedGroups),
+		SourceResource:           e.resourceToProto(r.SourceResource),
+		DestinationResource:      e.resourceToProto(r.DestinationResource),
+		SourcePostureCheckSeqIds: e.postureCheckSeqs(pol.SourcePostureChecks),
+	}
+}
+
+// groupSeqIDs maps the xid group IDs in src to their per-account seq ids,
+// dropping any group that has no seq id assigned.
+func (e *componentEncoder) groupSeqIDs(src []string) []uint32 {
+	if len(src) == 0 {
+		return nil
+	}
+	out := make([]uint32, 0, len(src))
+	for _, gid := range src {
+		if seq, ok := e.groupSeq(gid); ok {
+			out = append(out, seq)
+		}
+	}
+	return out
+}
+
+// unionPolicies merges c.Policies with every policy referenced by
+// c.ResourcePoliciesMap, deduplicating by pointer identity. Resource-only
+// policies (relevant to a NetworkResource but not to peer-pair traffic)
+// only live in ResourcePoliciesMap; without this union step they'd be lost
+// from the wire and the client's resource-policy lookup would come back
+// empty.
+func unionPolicies(policies []*types.Policy, resourcePolicies map[string][]*types.Policy) []*types.Policy {
+	// Fast path: non-router peers have no resource-only policies, so the
+	// "union" is identical to `policies`. Skip the dedup map allocation.
+	if len(resourcePolicies) == 0 {
+		return policies
+	}
+	seen := make(map[*types.Policy]struct{}, len(policies))
+	out := make([]*types.Policy, 0, len(policies))
+	for _, p := range policies {
+		if p == nil {
+			continue
+		}
+		if _, ok := seen[p]; ok {
+			continue
+		}
+		seen[p] = struct{}{}
+		out = append(out, p)
+	}
+	for _, list := range resourcePolicies {
+		for _, p := range list {
+			if p == nil {
+				continue
+			}
+			if _, ok := seen[p]; ok {
+				continue
+			}
+			seen[p] = struct{}{}
+			out = append(out, p)
+		}
+	}
+	return out
+}
+
+// encodeAuthorizedGroups translates rule.AuthorizedGroups (map keyed by
+// group xid → local-user names) to the wire form (map keyed by group
+// account_seq_id → UserNameList). Groups without a seq id are dropped —
+// matches how source/destination group references handle the same case.
+func (e *componentEncoder) encodeAuthorizedGroups(m map[string][]string) map[uint32]*proto.UserNameList {
+	if len(m) == 0 {
+		return nil
+	}
+	out := make(map[uint32]*proto.UserNameList, len(m))
+	for groupID, names := range m {
+		seq, ok := e.groupSeq(groupID)
+		if !ok {
+			continue
+		}
+		out[seq] = &proto.UserNameList{Names: append([]string(nil), names...)}
+	}
+	return out
+}
+
+func (e *componentEncoder) groupSeq(groupID string) (uint32, bool) {
+	g, ok := e.components.Groups[groupID]
+	if !ok || !g.HasSeqID() {
+		return 0, false
+	}
+	return g.AccountSeqID, true
+}
+
+// resourceToProto translates types.Resource for the wire. For peer-typed
+// resources the peer id is converted to a peer index into the envelope's
+// peers array. For other resource types only the type string is shipped
+// today (Calculate's resource-typed rule path consults SourceResource only
+// for "peer" — other types fall through to group-based lookup).
+func (e *componentEncoder) resourceToProto(r types.Resource) *proto.ResourceCompact {
+	if r.ID == "" && r.Type == "" {
+		return nil
+	}
+	out := &proto.ResourceCompact{Type: string(r.Type)}
+	if r.Type == types.ResourceTypePeer && r.ID != "" {
+		if idx, ok := e.peerOrder[r.ID]; ok {
+			out.PeerIndexSet = true
+			out.PeerIndex = idx
+		}
+	}
+	return out
+}
+
+// postureCheckSeqs translates a slice of posture-check xids to their
+// per-account integer ids using the NetworkMapComponents.PostureCheckXIDToSeq
+// lookup. Unresolvable xids are silently dropped — matches how group/peer
+// references handle the same case.
+func (e *componentEncoder) postureCheckSeqs(xids []string) []uint32 {
+	if len(xids) == 0 || len(e.components.PostureCheckXIDToSeq) == 0 {
+		return nil
+	}
+	out := make([]uint32, 0, len(xids))
+	for _, xid := range xids {
+		if seq, ok := e.components.PostureCheckXIDToSeq[xid]; ok {
+			out = append(out, seq)
+		}
+	}
+	return out
+}
+
+// networkSeq translates a Network xid to its per-account integer id using
+// the NetworkMapComponents.NetworkXIDToSeq lookup. Returns (0,false) when
+// the xid isn't known — callers decide whether to skip the parent record.
+func (e *componentEncoder) networkSeq(xid string) (uint32, bool) {
+	if xid == "" {
+		return 0, false
+	}
+	seq, ok := e.components.NetworkXIDToSeq[xid]
+	if !ok || seq == 0 {
+		return 0, false
+	}
+	return seq, true
+}
+
+func (e *componentEncoder) encodeDNSSettings(s *types.DNSSettings) *proto.DNSSettingsCompact {
+	if s == nil || len(s.DisabledManagementGroups) == 0 {
+		return nil
+	}
+	out := &proto.DNSSettingsCompact{
+		DisabledManagementGroupIds: make([]uint32, 0, len(s.DisabledManagementGroups)),
+	}
+	for _, gid := range s.DisabledManagementGroups {
+		if seq, ok := e.groupSeq(gid); ok {
+			out.DisabledManagementGroupIds = append(out.DisabledManagementGroupIds, seq)
+		}
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeRoutes(routes []*nbroute.Route) []*proto.RouteRaw {
+	if len(routes) == 0 {
+		return nil
+	}
+	out := make([]*proto.RouteRaw, 0, len(routes))
+	for _, r := range routes {
+		if r == nil {
+			continue
+		}
+		rr := &proto.RouteRaw{
+			Id:                    r.AccountSeqID,
+			NetId:                 string(r.NetID),
+			Description:           r.Description,
+			KeepRoute:             r.KeepRoute,
+			NetworkType:           int32(r.NetworkType),
+			Masquerade:            r.Masquerade,
+			Metric:                int32(r.Metric),
+			Enabled:               r.Enabled,
+			SkipAutoApply:         r.SkipAutoApply,
+			Domains:               r.Domains.ToPunycodeList(),
+			GroupIds:              e.groupIDsToSeq(r.Groups),
+			AccessControlGroupIds: e.groupIDsToSeq(r.AccessControlGroups),
+			PeerGroupIds:          e.groupIDsToSeq(r.PeerGroups),
+		}
+		if r.Network.IsValid() {
+			rr.NetworkCidr = r.Network.String()
+		}
+		if r.Peer != "" {
+			if idx, ok := e.peerOrder[r.Peer]; ok {
+				rr.PeerIndexSet = true
+				rr.PeerIndex = idx
+			}
+		}
+		out = append(out, rr)
+	}
+	return out
+}
+
+func (e *componentEncoder) groupIDsToSeq(groupIDs []string) []uint32 {
+	if len(groupIDs) == 0 {
+		return nil
+	}
+	out := make([]uint32, 0, len(groupIDs))
+	for _, gid := range groupIDs {
+		if seq, ok := e.groupSeq(gid); ok {
+			out = append(out, seq)
+		}
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeNameServerGroups(nsgs []*nbdns.NameServerGroup) []*proto.NameServerGroupRaw {
+	if len(nsgs) == 0 {
+		return nil
+	}
+	out := make([]*proto.NameServerGroupRaw, 0, len(nsgs))
+	for _, nsg := range nsgs {
+		if nsg == nil {
+			continue
+		}
+		entry := &proto.NameServerGroupRaw{
+			Id:                   nsg.AccountSeqID,
+			Name:                 nsg.Name,
+			Description:          nsg.Description,
+			Nameservers:          encodeNameServers(nsg.NameServers),
+			GroupIds:             e.groupIDsToSeq(nsg.Groups),
+			Primary:              nsg.Primary,
+			Domains:              nsg.Domains,
+			Enabled:              nsg.Enabled,
+			SearchDomainsEnabled: nsg.SearchDomainsEnabled,
+		}
+		out = append(out, entry)
+	}
+	return out
+}
+
+func encodeNameServers(servers []nbdns.NameServer) []*proto.NameServer {
+	if len(servers) == 0 {
+		return nil
+	}
+	out := make([]*proto.NameServer, 0, len(servers))
+	for _, s := range servers {
+		out = append(out, &proto.NameServer{
+			IP:     s.IP.String(),
+			NSType: int64(s.NSType),
+			Port:   int64(s.Port),
+		})
+	}
+	return out
+}
+
+func encodeSimpleRecords(records []nbdns.SimpleRecord) []*proto.SimpleRecord {
+	if len(records) == 0 {
+		return nil
+	}
+	out := make([]*proto.SimpleRecord, 0, len(records))
+	for _, r := range records {
+		out = append(out, &proto.SimpleRecord{
+			Name:  r.Name,
+			Type:  int64(r.Type),
+			Class: r.Class,
+			TTL:   int64(r.TTL),
+			RData: r.RData,
+		})
+	}
+	return out
+}
+
+func encodeCustomZones(zones []nbdns.CustomZone) []*proto.CustomZone {
+	if len(zones) == 0 {
+		return nil
+	}
+	out := make([]*proto.CustomZone, 0, len(zones))
+	for _, z := range zones {
+		out = append(out, &proto.CustomZone{
+			Domain:               z.Domain,
+			Records:              encodeSimpleRecords(z.Records),
+			SearchDomainDisabled: z.SearchDomainDisabled,
+			NonAuthoritative:     z.NonAuthoritative,
+		})
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeNetworkResources(resources []*resourceTypes.NetworkResource) []*proto.NetworkResourceRaw {
+	if len(resources) == 0 {
+		return nil
+	}
+	out := make([]*proto.NetworkResourceRaw, 0, len(resources))
+	for _, r := range resources {
+		if r == nil {
+			continue
+		}
+		entry := &proto.NetworkResourceRaw{
+			Id:          r.AccountSeqID,
+			Name:        r.Name,
+			Description: r.Description,
+			Type:        string(r.Type),
+			Address:     r.Address,
+			DomainValue: r.Domain,
+			Enabled:     r.Enabled,
+		}
+		if seq, ok := e.networkSeq(r.NetworkID); ok {
+			entry.NetworkSeq = seq
+		}
+		if r.Prefix.IsValid() {
+			entry.PrefixCidr = r.Prefix.String()
+		}
+		out = append(out, entry)
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeRoutersMap(routersMap map[string]map[string]*routerTypes.NetworkRouter) map[uint32]*proto.NetworkRouterList {
+	if len(routersMap) == 0 {
+		return nil
+	}
+	out := make(map[uint32]*proto.NetworkRouterList, len(routersMap))
+	for networkXID, routers := range routersMap {
+		if len(routers) == 0 {
+			continue
+		}
+		netSeq, ok := e.networkSeq(networkXID)
+		if !ok {
+			continue
+		}
+		entries := make([]*proto.NetworkRouterEntry, 0, len(routers))
+		for peerID, r := range routers {
+			if r == nil {
+				continue
+			}
+			entry := &proto.NetworkRouterEntry{
+				Id:           r.AccountSeqID,
+				PeerGroupIds: e.groupIDsToSeq(r.PeerGroups),
+				Masquerade:   r.Masquerade,
+				Metric:       int32(r.Metric),
+				Enabled:      r.Enabled,
+			}
+			if idx, ok := e.peerOrder[peerID]; ok {
+				entry.PeerIndexSet = true
+				entry.PeerIndex = idx
+			}
+			entries = append(entries, entry)
+		}
+		out[netSeq] = &proto.NetworkRouterList{Entries: entries}
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeResourcePoliciesMap(rpm map[string][]*types.Policy, policyToIdxs map[*types.Policy][]uint32) map[uint32]*proto.PolicyIndexes {
+	if len(rpm) == 0 {
+		return nil
+	}
+	// resourceXIDToSeq is local to one encode — built from components.NetworkResources
+	// (small slice). Network resources without seq id are dropped, matching how
+	// other components-without-seq are silently filtered.
+	resourceXIDToSeq := make(map[string]uint32, len(e.components.NetworkResources))
+	for _, r := range e.components.NetworkResources {
+		if r != nil && r.AccountSeqID != 0 {
+			resourceXIDToSeq[r.ID] = r.AccountSeqID
+		}
+	}
+	out := make(map[uint32]*proto.PolicyIndexes, len(rpm))
+	for resourceXID, policies := range rpm {
+		seq, ok := resourceXIDToSeq[resourceXID]
+		if !ok {
+			continue
+		}
+		idxs := make([]uint32, 0, len(policies)*2)
+		for _, pol := range policies {
+			idxs = append(idxs, policyToIdxs[pol]...)
+		}
+		if len(idxs) == 0 {
+			continue
+		}
+		out[seq] = &proto.PolicyIndexes{Indexes: idxs}
+	}
+	return out
+}
+
+func (e *componentEncoder) encodeGroupIDToUserIDs(m map[string][]string) map[uint32]*proto.UserIDList {
+	if len(m) == 0 {
+		return nil
+	}
+	out := make(map[uint32]*proto.UserIDList, len(m))
+	for groupID, userIDs := range m {
+		seq, ok := e.groupSeq(groupID)
+		if !ok || len(userIDs) == 0 {
+			continue
+		}
+		out[seq] = &proto.UserIDList{UserIds: userIDs}
+	}
+	return out
+}
+
+func stringSetToSlice(s map[string]struct{}) []string {
+	if len(s) == 0 {
+		return nil
+	}
+	out := make([]string, 0, len(s))
+	for k := range s {
+		out = append(out, k)
+	}
+	return out
+}
+
+func (e *componentEncoder) encodePostureFailedPeers(m map[string]map[string]struct{}) map[uint32]*proto.PeerIndexSet {
+	if len(m) == 0 {
+		return nil
+	}
+	out := make(map[uint32]*proto.PeerIndexSet, len(m))
+	for checkXID, failedPeerIDs := range m {
+		seq, ok := e.components.PostureCheckXIDToSeq[checkXID]
+		if !ok || seq == 0 {
+			continue
+		}
+		idxs := make([]uint32, 0, len(failedPeerIDs))
+		for peerID := range failedPeerIDs {
+			if idx, ok := e.peerOrder[peerID]; ok {
+				idxs = append(idxs, idx)
+			}
+		}
+		if len(idxs) == 0 {
+			continue
+		}
+		out[seq] = &proto.PeerIndexSet{PeerIndexes: idxs}
+	}
+	return out
+}
+
+// toAccountSettingsCompact always returns a non-nil message — the client
+// dereferences it unconditionally during Calculate(), so a nil here would
+// crash the receiver. A missing types.AccountSettingsInfo on the server
+// (which shouldn't happen in production but the encoder is exported)
+// degrades to login_expiration_enabled = false, which makes
+// LoginExpired() return false for every peer.
+func toAccountSettingsCompact(s *types.AccountSettingsInfo) *proto.AccountSettingsCompact {
+	if s == nil {
+		return &proto.AccountSettingsCompact{}
+	}
+	return &proto.AccountSettingsCompact{
+		PeerLoginExpirationEnabled: s.PeerLoginExpirationEnabled,
+		PeerLoginExpirationNs:      int64(s.PeerLoginExpiration),
+	}
+}
+
+func toAccountNetwork(n *types.Network) *proto.AccountNetwork {
+	if n == nil {
+		return nil
+	}
+	out := &proto.AccountNetwork{
+		Identifier: n.Identifier,
+		NetCidr:    n.Net.String(),
+		Dns:        n.Dns,
+		Serial:     n.CurrentSerial(),
+	}
+	if len(n.NetV6.IP) > 0 {
+		out.NetV6Cidr = n.NetV6.String()
+	}
+	return out
+}
+
+func toPeerCompact(p *nbpeer.Peer, agentVersionIdx uint32) *proto.PeerCompact {
+	pc := &proto.PeerCompact{
+		WgPubKey:               decodeWgKey(p.Key),
+		SshPubKey:              []byte(p.SSHKey),
+		DnsLabel:               p.DNSLabel,
+		AgentVersionIdx:        agentVersionIdx,
+		AddedWithSsoLogin:      p.UserID != "",
+		LoginExpirationEnabled: p.LoginExpirationEnabled,
+		SshEnabled:             p.SSHEnabled,
+		SupportsIpv6:           p.SupportsIPv6(),
+		SupportsSourcePrefixes: p.SupportsSourcePrefixes(),
+		ServerSshAllowed:       p.Meta.Flags.ServerSSHAllowed,
+	}
+	if p.LastLogin != nil {
+		pc.LastLoginUnixNano = p.LastLogin.UnixNano()
+	}
+	switch {
+	case !p.IP.IsValid():
+		// leave Ip nil
+	case p.IP.Is4() || p.IP.Is4In6():
+		ip := p.IP.Unmap().As4()
+		pc.Ip = ip[:]
+	default:
+		ip := p.IP.As16()
+		pc.Ip = ip[:]
+	}
+	if p.IPv6.IsValid() {
+		ip := p.IPv6.As16()
+		pc.Ipv6 = ip[:]
+	}
+	return pc
+}
+
+// decodeWgKey returns the raw 32 bytes of a base64-encoded WireGuard public
+// key, or nil for an empty / malformed key.
+func decodeWgKey(s string) []byte {
+	if s == "" {
+		return nil
+	}
+	out := make([]byte, wgKeyRawLen)
+	n, err := base64.StdEncoding.Decode(out, []byte(s))
+	if err != nil || n != wgKeyRawLen {
+		return nil
+	}
+	return out
+}
+
+func portsToUint32(ports []string) []uint32 {
+	if len(ports) == 0 {
+		return nil
+	}
+	out := make([]uint32, 0, len(ports))
+	for _, p := range ports {
+		v, err := strconv.ParseUint(p, 10, 16)
+		if err != nil {
+			continue
+		}
+		out = append(out, uint32(v))
+	}
+	return out
+}
+
+func portRangesToProto(ranges []types.RulePortRange) []*proto.PortInfo_Range {
+	if len(ranges) == 0 {
+		return nil
+	}
+	out := make([]*proto.PortInfo_Range, 0, len(ranges))
+	for _, r := range ranges {
+		out = append(out, &proto.PortInfo_Range{
+			Start: uint32(r.Start),
+			End:   uint32(r.End),
+		})
+	}
+	return out
+}

management/internals/shared/grpc/components_encoder_test.go

@@ -0,0 +1,879 @@
+package grpc
+
+import (
+	"bytes"
+	"cmp"
+	"net"
+	"net/netip"
+	"slices"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	goproto "google.golang.org/protobuf/proto"
+
+	nbdns "github.com/netbirdio/netbird/dns"
+	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
+	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/types"
+	nbroute "github.com/netbirdio/netbird/route"
+	"github.com/netbirdio/netbird/shared/management/proto"
+)
+
+const testWgKeyA = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopq="
+const testWgKeyB = "BBCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopq="
+const testWgKeyC = "CBCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopq="
+
+// canonicalize rewrites a NetworkMapComponentsFull in place into a canonical
+// form: peers reordered by wg_pub_key, with the rest of the message rewritten
+// to reference the new peer indexes. Groups, policies, and router indexes are
+// also sorted. After canonicalize, two envelopes built from the same logical
+// input compare byte-equal via proto.Equal.
+//
+// This lives on the test side — the encoder itself emits in map-iteration
+// order. Test-side normalization is the contract for "two encodes are
+// equivalent".
+func canonicalize(full *proto.NetworkMapComponentsFull) {
+	if full == nil {
+		return
+	}
+
+	// Canonicalize agent_versions first: sort the slice and rewrite each
+	// peer's AgentVersionIdx accordingly. The empty placeholder stays at
+	// index 0 by convention.
+	avRemap := make(map[uint32]uint32, len(full.AgentVersions))
+	if len(full.AgentVersions) > 0 {
+		// Pair version → original index, sort, rebuild.
+		type avEntry struct {
+			version string
+			oldIdx  uint32
+		}
+		entries := make([]avEntry, len(full.AgentVersions))
+		for i, v := range full.AgentVersions {
+			entries[i] = avEntry{version: v, oldIdx: uint32(i)}
+		}
+		// Empty stays at 0; sort the rest by string. Tiebreaker on oldIdx
+		// keeps the canonicalize output stable when two entries compare
+		// equal (the encoder dedups, but defending against future inputs).
+		slices.SortFunc(entries, func(a, b avEntry) int {
+			if a.version == "" && b.version != "" {
+				return -1
+			}
+			if b.version == "" && a.version != "" {
+				return 1
+			}
+			if c := cmp.Compare(a.version, b.version); c != 0 {
+				return c
+			}
+			return cmp.Compare(a.oldIdx, b.oldIdx)
+		})
+		newVersions := make([]string, len(entries))
+		for newIdx, e := range entries {
+			avRemap[e.oldIdx] = uint32(newIdx)
+			newVersions[newIdx] = e.version
+		}
+		full.AgentVersions = newVersions
+	}
+	for _, p := range full.Peers {
+		if newIdx, ok := avRemap[p.AgentVersionIdx]; ok {
+			p.AgentVersionIdx = newIdx
+		}
+	}
+
+	type peerEntry struct {
+		peer   *proto.PeerCompact
+		oldIdx uint32
+	}
+	entries := make([]peerEntry, len(full.Peers))
+	for i, p := range full.Peers {
+		entries[i] = peerEntry{peer: p, oldIdx: uint32(i)}
+	}
+	// DnsLabel is unique per peer; it tiebreaks on equal WgPubKey (e.g. both
+	// nil from malformed keys, or both empty for placeholders).
+	slices.SortFunc(entries, func(a, b peerEntry) int {
+		if c := bytes.Compare(a.peer.WgPubKey, b.peer.WgPubKey); c != 0 {
+			return c
+		}
+		return cmp.Compare(a.peer.DnsLabel, b.peer.DnsLabel)
+	})
+
+	remap := make(map[uint32]uint32, len(entries))
+	newPeers := make([]*proto.PeerCompact, len(entries))
+	for newIdx, e := range entries {
+		remap[e.oldIdx] = uint32(newIdx)
+		newPeers[newIdx] = e.peer
+	}
+	full.Peers = newPeers
+
+	full.RouterPeerIndexes = remapAndSort(full.RouterPeerIndexes, remap)
+	for _, g := range full.Groups {
+		g.PeerIndexes = remapAndSort(g.PeerIndexes, remap)
+	}
+	slices.SortFunc(full.Groups, func(a, b *proto.GroupCompact) int { return cmp.Compare(a.Id, b.Id) })
+
+	for _, r := range full.Routes {
+		if r.PeerIndexSet {
+			if newIdx, ok := remap[r.PeerIndex]; ok {
+				r.PeerIndex = newIdx
+			}
+		}
+		slices.Sort(r.GroupIds)
+		slices.Sort(r.AccessControlGroupIds)
+		slices.Sort(r.PeerGroupIds)
+	}
+	slices.SortFunc(full.Routes, func(a, b *proto.RouteRaw) int { return cmp.Compare(a.Id, b.Id) })
+
+	for _, list := range full.RoutersMap {
+		for _, entry := range list.Entries {
+			if entry.PeerIndexSet {
+				if newIdx, ok := remap[entry.PeerIndex]; ok {
+					entry.PeerIndex = newIdx
+				}
+			}
+			slices.Sort(entry.PeerGroupIds)
+		}
+		slices.SortFunc(list.Entries, func(a, b *proto.NetworkRouterEntry) int { return cmp.Compare(a.Id, b.Id) })
+	}
+
+	for _, set := range full.PostureFailedPeers {
+		set.PeerIndexes = remapAndSort(set.PeerIndexes, remap)
+	}
+
+	for _, p := range full.Policies {
+		slices.Sort(p.SourceGroupIds)
+		slices.Sort(p.DestinationGroupIds)
+	}
+	// Sort policies by (Id, source_group_ids, destination_group_ids) so that
+	// multiple PolicyCompact entries sharing the same Id (one per rule, when
+	// a Policy has multiple rules) still get a deterministic order. After
+	// sorting we remap indexes in ResourcePoliciesMap.
+	policyOldOrder := make(map[*proto.PolicyCompact]uint32, len(full.Policies))
+	for i, p := range full.Policies {
+		policyOldOrder[p] = uint32(i)
+	}
+	slices.SortFunc(full.Policies, func(a, b *proto.PolicyCompact) int {
+		if c := cmp.Compare(a.Id, b.Id); c != 0 {
+			return c
+		}
+		if c := slices.Compare(a.SourceGroupIds, b.SourceGroupIds); c != 0 {
+			return c
+		}
+		return slices.Compare(a.DestinationGroupIds, b.DestinationGroupIds)
+	})
+	policyRemap := make(map[uint32]uint32, len(full.Policies))
+	for newIdx, p := range full.Policies {
+		policyRemap[policyOldOrder[p]] = uint32(newIdx)
+	}
+	for _, idxs := range full.ResourcePoliciesMap {
+		idxs.Indexes = remapAndSort(idxs.Indexes, policyRemap)
+	}
+	for _, list := range full.GroupIdToUserIds {
+		slices.Sort(list.UserIds)
+	}
+	slices.Sort(full.AllowedUserIds)
+}
+
+func remapAndSort(idxs []uint32, remap map[uint32]uint32) []uint32 {
+	out := make([]uint32, 0, len(idxs))
+	for _, i := range idxs {
+		if newIdx, ok := remap[i]; ok {
+			out = append(out, newIdx)
+		}
+	}
+	slices.Sort(out)
+	return out
+}
+
+// envelopesEquivalent decodes both envelopes, canonicalizes them, and reports
+// whether they're proto.Equal. Use instead of byte-comparing marshaled output:
+// the encoder is intentionally non-deterministic.
+func envelopesEquivalent(a, b *proto.NetworkMapEnvelope) bool {
+	canonicalize(a.GetFull())
+	canonicalize(b.GetFull())
+	return goproto.Equal(a, b)
+}
+
+func newTestComponents() *types.NetworkMapComponents {
+	peerA := &nbpeer.Peer{
+		ID:       "peer-a",
+		Key:      testWgKeyA,
+		IP:       netip.AddrFrom4([4]byte{100, 64, 0, 1}),
+		DNSLabel: "peera",
+		SSHKey:   "ssh-a",
+		Status:   &nbpeer.PeerStatus{Connected: true, LastSeen: time.Now()},
+		Meta:     nbpeer.PeerSystemMeta{WtVersion: "0.40.0"},
+	}
+	peerB := &nbpeer.Peer{
+		ID:       "peer-b",
+		Key:      testWgKeyB,
+		IP:       netip.AddrFrom4([4]byte{100, 64, 0, 2}),
+		IPv6:     netip.AddrFrom16([16]byte{0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2}),
+		DNSLabel: "peerb",
+		Meta:     nbpeer.PeerSystemMeta{WtVersion: "0.25.0"},
+	}
+	peerC := &nbpeer.Peer{
+		ID:       "peer-c",
+		Key:      testWgKeyC,
+		IP:       netip.AddrFrom4([4]byte{100, 64, 0, 3}),
+		DNSLabel: "peerc",
+		Meta:     nbpeer.PeerSystemMeta{WtVersion: "0.40.0"},
+	}
+
+	return &types.NetworkMapComponents{
+		PeerID: "peer-a",
+		Network: &types.Network{
+			Identifier: "net-test",
+			Net:        net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)},
+			Serial:     7,
+		},
+		AccountSettings: &types.AccountSettingsInfo{
+			PeerLoginExpirationEnabled: true,
+			PeerLoginExpiration:        2 * time.Hour,
+		},
+		Peers: map[string]*nbpeer.Peer{
+			"peer-a": peerA,
+			"peer-b": peerB,
+			"peer-c": peerC,
+		},
+		Groups: map[string]*types.Group{
+			"group-src": {ID: "group-src", AccountSeqID: 1, Name: "Src", Peers: []string{"peer-a"}},
+			"group-dst": {ID: "group-dst", AccountSeqID: 2, Name: "Dst", Peers: []string{"peer-b", "peer-c"}},
+		},
+		Policies: []*types.Policy{
+			{
+				ID:           "pol-1",
+				AccountSeqID: 10,
+				Enabled:      true,
+				Rules: []*types.PolicyRule{{
+					ID: "rule-1", Enabled: true, Action: types.PolicyTrafficActionAccept,
+					Protocol: types.PolicyRuleProtocolTCP, Bidirectional: true,
+					Ports:        []string{"22", "80"},
+					PortRanges:   []types.RulePortRange{{Start: 8000, End: 8100}},
+					Sources:      []string{"group-src"},
+					Destinations: []string{"group-dst"},
+				}},
+			},
+		},
+		RouterPeers: map[string]*nbpeer.Peer{"peer-c": peerC},
+	}
+}
+
+func TestEncodeNetworkMapEnvelope_Basic(t *testing.T) {
+	c := newTestComponents()
+	env := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{
+		Components: c,
+		DNSDomain:  "netbird.cloud",
+	})
+
+	require.NotNil(t, env)
+	full := env.GetFull()
+	require.NotNil(t, full, "envelope must contain Full payload")
+
+	assert.EqualValues(t, 7, full.Serial)
+	assert.Equal(t, "netbird.cloud", full.DnsDomain)
+
+	require.NotNil(t, full.Network)
+	assert.Equal(t, "net-test", full.Network.Identifier)
+	assert.Equal(t, "100.64.0.0/10", full.Network.NetCidr)
+
+	require.NotNil(t, full.AccountSettings)
+	assert.True(t, full.AccountSettings.PeerLoginExpirationEnabled)
+	assert.EqualValues(t, (2 * time.Hour).Nanoseconds(), full.AccountSettings.PeerLoginExpirationNs)
+
+	require.Len(t, full.Peers, 3)
+	byLabel := map[string]*proto.PeerCompact{}
+	for _, p := range full.Peers {
+		assert.Len(t, p.WgPubKey, 32, "wg key must be raw 32 bytes")
+		assert.Len(t, p.Ip, 4, "ipv4 must be raw 4 bytes")
+		byLabel[p.DnsLabel] = p
+	}
+	assert.Len(t, byLabel["peerb"].Ipv6, 16, "peer-b has ipv6 → 16 bytes")
+}
+
+func TestEncodeNetworkMapEnvelope_RepeatEncodesEquivalent(t *testing.T) {
+	c := newTestComponents()
+
+	expected := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+
+	// Hammer it 100 times — Go map iteration is randomized per call, so each
+	// run produces different wire bytes, but the canonicalized form must
+	// match.
+	for i := 0; i < 100; i++ {
+		got := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+		require.True(t, envelopesEquivalent(expected, got),
+			"encode #%d must be semantically equivalent to first encode", i)
+	}
+}
+
+func TestEncodeNetworkMapEnvelope_ConcurrentEncodesEquivalent(t *testing.T) {
+	c := newTestComponents()
+
+	expected := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+
+	const goroutines = 50
+	var wg sync.WaitGroup
+	wg.Add(goroutines)
+	results := make([]*proto.NetworkMapEnvelope, goroutines)
+	for i := 0; i < goroutines; i++ {
+		i := i
+		go func() {
+			defer wg.Done()
+			results[i] = EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+		}()
+	}
+	wg.Wait()
+
+	for i, got := range results {
+		require.NotNil(t, got, "goroutine %d returned nil", i)
+		require.True(t, envelopesEquivalent(expected, got),
+			"goroutine %d produced inequivalent envelope", i)
+	}
+}
+
+func TestEncodeNetworkMapEnvelope_GroupsByAccountSeqID(t *testing.T) {
+	c := newTestComponents()
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Groups, 2)
+
+	groupByID := map[uint32]*proto.GroupCompact{}
+	for _, g := range full.Groups {
+		groupByID[g.Id] = g
+	}
+	require.Contains(t, groupByID, uint32(1))
+	require.Contains(t, groupByID, uint32(2))
+	assert.Equal(t, "Src", groupByID[1].Name)
+	assert.Equal(t, "Dst", groupByID[2].Name)
+	assert.Len(t, groupByID[1].PeerIndexes, 1)
+	assert.Len(t, groupByID[2].PeerIndexes, 2)
+}
+
+func TestEncodeNetworkMapEnvelope_PolicyExpansion(t *testing.T) {
+	c := newTestComponents()
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Policies, 1)
+	pc := full.Policies[0]
+	assert.EqualValues(t, 10, pc.Id)
+	assert.Equal(t, proto.RuleAction_ACCEPT, pc.Action)
+	assert.Equal(t, proto.RuleProtocol_TCP, pc.Protocol)
+	assert.True(t, pc.Bidirectional)
+	assert.Equal(t, []uint32{22, 80}, pc.Ports)
+	require.Len(t, pc.PortRanges, 1)
+	assert.EqualValues(t, 8000, pc.PortRanges[0].Start)
+	assert.EqualValues(t, 8100, pc.PortRanges[0].End)
+	assert.Equal(t, []uint32{1}, pc.SourceGroupIds)
+	assert.Equal(t, []uint32{2}, pc.DestinationGroupIds)
+}
+
+func TestEncodeNetworkMapEnvelope_RouterIndexes(t *testing.T) {
+	c := newTestComponents()
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.RouterPeerIndexes, 1)
+	idx := full.RouterPeerIndexes[0]
+	require.Less(t, int(idx), len(full.Peers))
+	assert.Equal(t, "peerc", full.Peers[idx].DnsLabel)
+}
+
+func TestEncodeNetworkMapEnvelope_AgentVersionDedup(t *testing.T) {
+	c := newTestComponents()
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.AgentVersions, 3, "empty placeholder + 2 distinct versions")
+	assert.Equal(t, "", full.AgentVersions[0], "index 0 reserved for empty version")
+	assert.ElementsMatch(t, []string{"0.40.0", "0.25.0"}, full.AgentVersions[1:],
+		"two distinct versions, order depends on map iteration")
+
+	idxByLabel := map[string]uint32{}
+	for _, p := range full.Peers {
+		idxByLabel[p.DnsLabel] = p.AgentVersionIdx
+	}
+	assert.Equal(t, idxByLabel["peera"], idxByLabel["peerc"], "peers with the same agent version share an index")
+	assert.NotEqual(t, idxByLabel["peera"], idxByLabel["peerb"])
+}
+
+func TestEncodeNetworkMapEnvelope_DisabledPolicySkipped(t *testing.T) {
+	c := newTestComponents()
+	c.Policies[0].Enabled = false
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	assert.Empty(t, full.Policies)
+}
+
+func TestEncodeNetworkMapEnvelope_GroupZeroSeqIDSkipped(t *testing.T) {
+	c := newTestComponents()
+	c.Groups["group-src"].AccountSeqID = 0
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Groups, 1, "groups with AccountSeqID=0 are not yet persisted and must be skipped")
+	assert.EqualValues(t, 2, full.Groups[0].Id)
+
+	require.Len(t, full.Policies, 1)
+	pc := full.Policies[0]
+	assert.Empty(t, pc.SourceGroupIds, "rule references a group that was filtered out → no group id on wire")
+	assert.Equal(t, []uint32{2}, pc.DestinationGroupIds)
+}
+
+func TestEncodeNetworkMapEnvelope_TwoPeersSameMalformedKey(t *testing.T) {
+	// Both peers have nil WgPubKey after decode; canonicalize must still
+	// produce a stable order using DnsLabel as a tiebreaker, so 100 encodes
+	// canonicalize identically.
+	c := newTestComponents()
+	c.Peers["peer-a"].Key = "garbage-a-!!!"
+	c.Peers["peer-b"].Key = "garbage-b-!!!"
+
+	expected := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+	for i := 0; i < 100; i++ {
+		got := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+		require.True(t, envelopesEquivalent(expected, got),
+			"encode #%d with two same-key peers must canonicalize equivalently", i)
+	}
+}
+
+func TestEncodeNetworkMapEnvelope_MalformedWgKey(t *testing.T) {
+	c := newTestComponents()
+	c.Peers["peer-a"].Key = "not-base64-!!!"
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Peers, 3)
+
+	var byLabel = map[string]*proto.PeerCompact{}
+	for _, p := range full.Peers {
+		byLabel[p.DnsLabel] = p
+	}
+	assert.Nil(t, byLabel["peera"].WgPubKey, "peer with malformed key encodes nil WgPubKey")
+	assert.Len(t, byLabel["peerb"].WgPubKey, 32, "other peers retain their key")
+}
+
+func TestEncodeNetworkMapEnvelope_IPv6OnlyPeer(t *testing.T) {
+	c := newTestComponents()
+	v6Only := &nbpeer.Peer{
+		ID:       "peer-v6",
+		Key:      testWgKeyA,
+		IPv6:     netip.AddrFrom16([16]byte{0xfd, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 9}),
+		DNSLabel: "peerv6",
+		Meta:     nbpeer.PeerSystemMeta{WtVersion: "0.40.0"},
+	}
+	c.Peers["peer-v6"] = v6Only
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	var found *proto.PeerCompact
+	for _, p := range full.Peers {
+		if p.DnsLabel == "peerv6" {
+			found = p
+		}
+	}
+	require.NotNil(t, found, "ipv6-only peer must be present")
+	assert.Empty(t, found.Ip, "no IPv4 address → empty Ip")
+	assert.Len(t, found.Ipv6, 16)
+}
+
+func TestEncodeNetworkMapEnvelope_PeerWithoutIP(t *testing.T) {
+	c := newTestComponents()
+	c.Peers["peer-noip"] = &nbpeer.Peer{
+		ID:       "peer-noip",
+		Key:      testWgKeyA,
+		DNSLabel: "peernoip",
+		Meta:     nbpeer.PeerSystemMeta{WtVersion: "0.40.0"},
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	var found *proto.PeerCompact
+	for _, p := range full.Peers {
+		if p.DnsLabel == "peernoip" {
+			found = p
+		}
+	}
+	require.NotNil(t, found)
+	assert.Empty(t, found.Ip)
+	assert.Empty(t, found.Ipv6)
+}
+
+func TestEncodeNetworkMapEnvelope_EmptyInput(t *testing.T) {
+	c := &types.NetworkMapComponents{
+		Network: &types.Network{Identifier: "x", Net: net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)}},
+	}
+
+	env := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c})
+
+	full := env.GetFull()
+	require.NotNil(t, full)
+	assert.Empty(t, full.Peers)
+	assert.Empty(t, full.Groups)
+	assert.Empty(t, full.Policies)
+	assert.Empty(t, full.RouterPeerIndexes)
+	require.NotNil(t, full.AccountSettings, "AccountSettingsCompact must always be emitted (client dereferences it unconditionally)")
+}
+
+func TestEncodeNetworkMapEnvelope_PeerLoginExpirationFields(t *testing.T) {
+	c := newTestComponents()
+	now := time.Date(2024, 1, 2, 3, 4, 5, 0, time.UTC)
+	c.Peers["peer-a"].UserID = "user-1"
+	c.Peers["peer-a"].LoginExpirationEnabled = true
+	c.Peers["peer-a"].LastLogin = &now
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	var pa *proto.PeerCompact
+	for _, p := range full.Peers {
+		if p.DnsLabel == "peera" {
+			pa = p
+		}
+	}
+	require.NotNil(t, pa)
+	assert.True(t, pa.AddedWithSsoLogin)
+	assert.True(t, pa.LoginExpirationEnabled)
+	assert.Equal(t, now.UnixNano(), pa.LastLoginUnixNano)
+
+	// peer-b has no UserID and no LastLogin → all fields zero-value.
+	var pb *proto.PeerCompact
+	for _, p := range full.Peers {
+		if p.DnsLabel == "peerb" {
+			pb = p
+		}
+	}
+	require.NotNil(t, pb)
+	assert.False(t, pb.AddedWithSsoLogin)
+	assert.False(t, pb.LoginExpirationEnabled)
+	assert.Zero(t, pb.LastLoginUnixNano)
+}
+
+func TestEncodeNetworkMapEnvelope_RoutesRoundTrip(t *testing.T) {
+	c := newTestComponents()
+	c.Routes = []*nbroute.Route{
+		{
+			ID:                  "route-peer",
+			AccountSeqID:        100,
+			NetID:               "net-A",
+			Description:         "via peer-c",
+			Network:             netip.MustParsePrefix("10.0.0.0/16"),
+			Peer:                "peer-c", // peer ID, not WG key
+			Groups:              []string{"group-src"},
+			AccessControlGroups: []string{"group-dst"},
+			Enabled:             true,
+		},
+		{
+			ID:           "route-peergroup",
+			AccountSeqID: 101,
+			NetID:        "net-B",
+			Network:      netip.MustParsePrefix("10.1.0.0/16"),
+			PeerGroups:   []string{"group-src", "group-dst"},
+			Enabled:      true,
+		},
+		{
+			ID:           "route-no-seq",
+			AccountSeqID: 0, // unset — should still ship (no group seq filter on routes)
+			Network:      netip.MustParsePrefix("10.2.0.0/16"),
+			Enabled:      true,
+		},
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Routes, 3)
+	byNetID := map[string]*proto.RouteRaw{}
+	for _, r := range full.Routes {
+		byNetID[r.NetId] = r
+	}
+
+	r1 := byNetID["net-A"]
+	require.NotNil(t, r1)
+	assert.True(t, r1.PeerIndexSet, "route with peer must set peer_index_set")
+	require.Less(t, int(r1.PeerIndex), len(full.Peers))
+	assert.Equal(t, "peerc", full.Peers[r1.PeerIndex].DnsLabel)
+	assert.Equal(t, []uint32{1}, r1.GroupIds, "group-src has AccountSeqID 1")
+	assert.Equal(t, []uint32{2}, r1.AccessControlGroupIds, "group-dst has AccountSeqID 2")
+	assert.Empty(t, r1.PeerGroupIds)
+
+	r2 := byNetID["net-B"]
+	require.NotNil(t, r2)
+	assert.False(t, r2.PeerIndexSet, "route with peer_groups must NOT set peer_index_set")
+	assert.ElementsMatch(t, []uint32{1, 2}, r2.PeerGroupIds)
+}
+
+func TestEncodeNetworkMapEnvelope_RouteWithMissingPeerLeavesIndexUnset(t *testing.T) {
+	c := newTestComponents()
+	c.Routes = []*nbroute.Route{{
+		ID:           "route-x",
+		AccountSeqID: 100,
+		Peer:         "peer-not-in-components",
+		Network:      netip.MustParsePrefix("10.0.0.0/16"),
+		Enabled:      true,
+	}}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Routes, 1)
+	assert.False(t, full.Routes[0].PeerIndexSet,
+		"missing peer reference must not pretend to point at peer index 0")
+}
+
+func TestEncodeNetworkMapEnvelope_ResourceOnlyPolicyShippedAndIndexed(t *testing.T) {
+	c := newTestComponents()
+	// Policy that exists ONLY in ResourcePoliciesMap, not in c.Policies. This
+	// is the I1 case — without unionPolicies the encoder would silently
+	// drop it from the wire.
+	resourceOnlyPolicy := &types.Policy{
+		ID: "pol-resource", AccountSeqID: 99, Enabled: true,
+		Rules: []*types.PolicyRule{{
+			ID: "rule-r", Enabled: true, Action: types.PolicyTrafficActionAccept,
+			Protocol:     types.PolicyRuleProtocolTCP,
+			Sources:      []string{"group-src"},
+			Destinations: []string{"group-dst"},
+		}},
+	}
+	c.ResourcePoliciesMap = map[string][]*types.Policy{
+		"resource-x": {c.Policies[0], resourceOnlyPolicy}, // shared + resource-only
+	}
+	// Resource must appear in components.NetworkResources with a seq id —
+	// encoder uses that to translate the xid map key to uint32.
+	c.NetworkResources = []*resourceTypes.NetworkResource{
+		{ID: "resource-x", AccountSeqID: 77, Name: "res-x", Enabled: true},
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.Policies, 2, "encoded policies must include both peer-traffic and resource-only")
+
+	policyByID := map[uint32]*proto.PolicyCompact{}
+	policyIdxByID := map[uint32]uint32{}
+	for i, p := range full.Policies {
+		policyByID[p.Id] = p
+		policyIdxByID[p.Id] = uint32(i)
+	}
+	require.Contains(t, policyByID, uint32(10), "original peer-traffic policy id 10")
+	require.Contains(t, policyByID, uint32(99), "resource-only policy id 99")
+
+	require.Contains(t, full.ResourcePoliciesMap, uint32(77))
+	idxs := full.ResourcePoliciesMap[77].Indexes
+	require.Len(t, idxs, 2)
+	assert.ElementsMatch(t, []uint32{policyIdxByID[10], policyIdxByID[99]}, idxs,
+		"resource policies map must reference both wire policy indexes")
+}
+
+func TestEncodeNetworkMapEnvelope_NameServerGroups(t *testing.T) {
+	c := newTestComponents()
+	c.NameServerGroups = []*nbdns.NameServerGroup{{
+		ID: "nsg-1", AccountSeqID: 50, Name: "Main", Description: "primary",
+		NameServers: []nbdns.NameServer{{
+			IP: netip.MustParseAddr("8.8.8.8"), NSType: nbdns.UDPNameServerType, Port: 53,
+		}},
+		Groups:  []string{"group-src", "group-not-persisted"},
+		Primary: true, Enabled: true,
+		Domains: []string{"corp.example"},
+	}}
+	c.Groups["group-not-persisted"] = &types.Group{ID: "group-not-persisted", AccountSeqID: 0, Peers: []string{}}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.NameserverGroups, 1)
+	nsg := full.NameserverGroups[0]
+	assert.EqualValues(t, 50, nsg.Id)
+	assert.Equal(t, "Main", nsg.Name)
+	assert.True(t, nsg.Primary)
+	require.Len(t, nsg.Nameservers, 1)
+	assert.Equal(t, "8.8.8.8", nsg.Nameservers[0].IP)
+	assert.Equal(t, []uint32{1}, nsg.GroupIds, "group-not-persisted is filtered out (AccountSeqID=0)")
+}
+
+func TestEncodeNetworkMapEnvelope_PostureFailedPeers(t *testing.T) {
+	c := newTestComponents()
+	c.PostureCheckXIDToSeq = map[string]uint32{"check-1": 33}
+	c.PostureFailedPeers = map[string]map[string]struct{}{
+		"check-1": {
+			"peer-a":              {},
+			"peer-b":              {},
+			"peer-not-in-account": {},
+		},
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Contains(t, full.PostureFailedPeers, uint32(33))
+	idxs := full.PostureFailedPeers[33].PeerIndexes
+	assert.Len(t, idxs, 2, "missing peer is silently dropped (filterPostureFailedPeers guarantees presence in real data)")
+}
+
+func TestEncodeNetworkMapEnvelope_RoutersMap(t *testing.T) {
+	c := newTestComponents()
+	c.NetworkXIDToSeq = map[string]uint32{"net-1": 5}
+	c.RoutersMap = map[string]map[string]*routerTypes.NetworkRouter{
+		"net-1": {
+			"peer-c": {
+				ID: "router-1", AccountSeqID: 200,
+				Peer: "peer-c", Masquerade: true, Metric: 10, Enabled: true,
+			},
+		},
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Contains(t, full.RoutersMap, uint32(5))
+	entries := full.RoutersMap[5].Entries
+	require.Len(t, entries, 1)
+	e := entries[0]
+	assert.EqualValues(t, 200, e.Id)
+	assert.True(t, e.PeerIndexSet)
+	require.Less(t, int(e.PeerIndex), len(full.Peers))
+	assert.Equal(t, "peerc", full.Peers[e.PeerIndex].DnsLabel)
+	assert.True(t, e.Masquerade)
+	assert.EqualValues(t, 10, e.Metric)
+	assert.True(t, e.Enabled)
+}
+
+func TestEncodeNetworkMapEnvelope_RouterPeerNotInComponentsPeers(t *testing.T) {
+	// Router peer in c.RouterPeers but NOT in c.Peers (validation may have
+	// filtered it). indexRouterPeers runs before encodeRoutersMap, so the
+	// peer_index reference must still resolve.
+	c := newTestComponents()
+	delete(c.Peers, "peer-c")
+	routerPeer := &nbpeer.Peer{
+		ID: "peer-c", Key: testWgKeyC, IP: netip.AddrFrom4([4]byte{100, 64, 0, 3}),
+		DNSLabel: "peerc", Meta: nbpeer.PeerSystemMeta{WtVersion: "0.40.0"},
+	}
+	c.RouterPeers = map[string]*nbpeer.Peer{"peer-c": routerPeer}
+	c.NetworkXIDToSeq = map[string]uint32{"net-1": 5}
+	c.RoutersMap = map[string]map[string]*routerTypes.NetworkRouter{
+		"net-1": {"peer-c": {ID: "r-1", AccountSeqID: 1, Peer: "peer-c", Enabled: true}},
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Contains(t, full.RoutersMap, uint32(5))
+	require.Len(t, full.RoutersMap[5].Entries, 1)
+	e := full.RoutersMap[5].Entries[0]
+	assert.True(t, e.PeerIndexSet, "router peer must be indexed even when not in c.Peers")
+}
+
+func TestEncodeNetworkMapEnvelope_DNSSettingsFiltersUnpersistedGroups(t *testing.T) {
+	c := newTestComponents()
+	c.DNSSettings = &types.DNSSettings{
+		DisabledManagementGroups: []string{"group-src", "group-missing", "group-no-seq"},
+	}
+	c.Groups["group-no-seq"] = &types.Group{ID: "group-no-seq", AccountSeqID: 0}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.NotNil(t, full.DnsSettings)
+	assert.Equal(t, []uint32{1}, full.DnsSettings.DisabledManagementGroupIds,
+		"only group-src (AccountSeqID=1) survives — missing and unpersisted are dropped")
+}
+
+func TestEncodeNetworkMapEnvelope_GroupIDToUserIDs(t *testing.T) {
+	c := newTestComponents()
+	c.GroupIDToUserIDs = map[string][]string{
+		"group-src":     {"user-1", "user-2"},
+		"group-no-seq":  {"user-3"}, // group not persisted → drop
+		"group-missing": {"user-4"}, // group not in components → drop
+	}
+	c.Groups["group-no-seq"] = &types.Group{ID: "group-no-seq", AccountSeqID: 0}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.Len(t, full.GroupIdToUserIds, 1, "only persisted+present groups survive")
+	require.Contains(t, full.GroupIdToUserIds, uint32(1))
+	assert.ElementsMatch(t, []string{"user-1", "user-2"}, full.GroupIdToUserIds[1].UserIds)
+}
+
+func TestToProxyPatch_EmptyInputReturnsNil(t *testing.T) {
+	assert.Nil(t, toProxyPatch(nil, "netbird.cloud", false, false))
+	assert.Nil(t, toProxyPatch(&types.NetworkMap{}, "netbird.cloud", false, false),
+		"empty NetworkMap (no peers, rules, routes etc) → nil patch so proto3 omits the field")
+}
+
+func TestToProxyPatch_PopulatesAllFields(t *testing.T) {
+	nm := &types.NetworkMap{
+		Peers: []*nbpeer.Peer{{
+			ID: "ext-peer", Key: testWgKeyA, IP: netip.AddrFrom4([4]byte{100, 64, 0, 9}),
+			DNSLabel: "extpeer", Meta: nbpeer.PeerSystemMeta{WtVersion: "0.40.0"},
+		}},
+		FirewallRules: []*types.FirewallRule{{
+			PeerIP: "100.64.0.9", Action: "accept", Direction: 0, Protocol: "tcp",
+		}},
+	}
+
+	patch := toProxyPatch(nm, "netbird.cloud", false, false)
+
+	require.NotNil(t, patch)
+	assert.Len(t, patch.Peers, 1)
+	assert.Len(t, patch.FirewallRules, 1)
+}
+
+// TestEncodeNetworkMapEnvelope_ProxyPatchPropagated covers the ProxyPatch
+// pass-through in both encoder branches (normal path + nil-Components
+// graceful-degrade). Without this test a regression that drops `ProxyPatch:`
+// from one of the struct literals in components_encoder.go would slip past CI.
+func TestEncodeNetworkMapEnvelope_ProxyPatchPropagated(t *testing.T) {
+	patch := &proto.ProxyPatch{
+		ForwardingRules: []*proto.ForwardingRule{{
+			Protocol:          proto.RuleProtocol_TCP,
+			DestinationPort:   &proto.PortInfo{PortSelection: &proto.PortInfo_Port{Port: 80}},
+			TranslatedAddress: net.IPv4(10, 0, 0, 1).To4(),
+			TranslatedPort:    &proto.PortInfo{PortSelection: &proto.PortInfo_Port{Port: 8080}},
+		}},
+	}
+
+	t.Run("normal_path", func(t *testing.T) {
+		c := newTestComponents()
+		full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{
+			Components: c,
+			ProxyPatch: patch,
+		}).GetFull()
+
+		require.NotNil(t, full.ProxyPatch, "ProxyPatch must propagate through the normal encode path")
+		assert.Len(t, full.ProxyPatch.ForwardingRules, 1)
+	})
+
+	t.Run("nil_components_graceful_degrade", func(t *testing.T) {
+		full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{
+			Components: nil,
+			ProxyPatch: patch,
+		}).GetFull()
+
+		require.NotNil(t, full.ProxyPatch, "ProxyPatch must propagate through the nil-Components branch too")
+		assert.Len(t, full.ProxyPatch.ForwardingRules, 1)
+	})
+}
+
+func TestEncodeNetworkMapEnvelope_NilComponentsGracefulDegrade(t *testing.T) {
+	// nil Components → minimal envelope, no crash. Matches the legacy
+	// account_components.go:43 behaviour for missing/unvalidated peers.
+	env := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{
+		Components: nil,
+		DNSDomain:  "netbird.cloud",
+	})
+
+	require.NotNil(t, env)
+	full := env.GetFull()
+	require.NotNil(t, full)
+	require.NotNil(t, full.AccountSettings, "AccountSettings must always be non-nil")
+	assert.Equal(t, "netbird.cloud", full.DnsDomain)
+	assert.Empty(t, full.Peers)
+	assert.Empty(t, full.Policies)
+}
+
+func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
+	c := &types.NetworkMapComponents{
+		Network: &types.Network{Identifier: "x", Net: net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)}},
+		// AccountSettings deliberately nil
+	}
+
+	full := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{Components: c}).GetFull()
+
+	require.NotNil(t, full.AccountSettings, "client dereferences AccountSettings unconditionally during Calculate(); a nil here would crash the receiver")
+	assert.False(t, full.AccountSettings.PeerLoginExpirationEnabled)
+	assert.Zero(t, full.AccountSettings.PeerLoginExpirationNs)
+}

management/internals/shared/grpc/components_envelope_response.go

@@ -0,0 +1,193 @@
+package grpc
+
+import (
+	"context"
+
+	integrationsConfig "github.com/netbirdio/management-integrations/integrations/config"
+
+	"github.com/netbirdio/netbird/client/ssh/auth"
+	nbconfig "github.com/netbirdio/netbird/management/internals/server/config"
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/posture"
+	"github.com/netbirdio/netbird/management/server/types"
+	"github.com/netbirdio/netbird/shared/management/networkmap"
+	"github.com/netbirdio/netbird/shared/management/proto"
+)
+
+// ToComponentSyncResponse builds a SyncResponse carrying the compact
+// NetworkMapEnvelope for capability-aware peers. The legacy proto.NetworkMap
+// field is intentionally left empty — capable peers ignore it and the
+// envelope alone is the authoritative wire shape.
+//
+// PeerConfig is computed once server-side using the receiving peer's own
+// account-level network metadata. EnableSSH inside PeerConfig is left at
+// peer.SSHEnabled (the peer's local setting); account-policy-driven SSH is
+// computed by the client from the envelope's GroupIDToUserIDs / AllowedUserIDs
+// inside Calculate(), so the SshConfig.SshEnabled bit may flip true on the
+// client even though the server-side PeerConfig reports false.
+func ToComponentSyncResponse(
+	ctx context.Context,
+	config *nbconfig.Config,
+	httpConfig *nbconfig.HttpServerConfig,
+	deviceFlowConfig *nbconfig.DeviceAuthorizationFlow,
+	peer *nbpeer.Peer,
+	turnCredentials *Token,
+	relayCredentials *Token,
+	components *types.NetworkMapComponents,
+	proxyPatch *types.NetworkMap,
+	dnsName string,
+	checks []*posture.Checks,
+	settings *types.Settings,
+	extraSettings *types.ExtraSettings,
+	peerGroups []string,
+	dnsFwdPort int64,
+) *proto.SyncResponse {
+	network := networkOrZero(components)
+	enableSSH := computeSSHEnabledForPeer(components, peer)
+	peerConfig := toPeerConfig(peer, network, dnsName, settings, httpConfig, deviceFlowConfig, enableSSH)
+
+	includeIPv6 := peer.SupportsIPv6() && peer.IPv6.IsValid()
+	useSourcePrefixes := peer.SupportsSourcePrefixes()
+
+	userIDClaim := auth.DefaultUserIDClaim
+	if httpConfig != nil && httpConfig.AuthUserIDClaim != "" {
+		userIDClaim = httpConfig.AuthUserIDClaim
+	}
+
+	envelope := EncodeNetworkMapEnvelope(ComponentsEnvelopeInput{
+		Components:       components,
+		PeerConfig:       peerConfig,
+		DNSDomain:        dnsName,
+		DNSForwarderPort: dnsFwdPort,
+		UserIDClaim:      userIDClaim,
+		ProxyPatch:       toProxyPatch(proxyPatch, dnsName, includeIPv6, useSourcePrefixes),
+	})
+
+	resp := &proto.SyncResponse{
+		PeerConfig:         peerConfig,
+		NetworkMapEnvelope: envelope,
+		Checks:             toProtocolChecks(ctx, checks),
+	}
+
+	nbConfig := toNetbirdConfig(config, turnCredentials, relayCredentials, extraSettings)
+	resp.NetbirdConfig = integrationsConfig.ExtendNetBirdConfig(peer.ID, peerGroups, nbConfig, extraSettings)
+
+	return resp
+}
+
+// networkOrZero returns components.Network or a zero Network — toPeerConfig
+// dereferences network.Net which would panic on nil.
+func networkOrZero(c *types.NetworkMapComponents) *types.Network {
+	if c == nil || c.Network == nil {
+		return &types.Network{}
+	}
+	return c.Network
+}
+
+// toProxyPatch converts a proxy-injected *types.NetworkMap into the wire
+// patch the components envelope ships alongside. Returns nil when there are
+// no fragments to merge — proto3 omits a nil message field, so the receiver
+// sees no patch and skips the merge step entirely.
+//
+// We reuse the legacy proto-conversion helpers (toProtocolRoutes,
+// toProtocolFirewallRules, toProtocolRoutesFirewallRules,
+// appendRemotePeerConfig, ForwardingRule.ToProto) because the proxy
+// delivers fragments pre-expanded — there's no raw component shape to
+// derive them from. Components purity isn't violated: proxy data isn't
+// policy-graph-derived, it's externally injected post-Calculate, so the
+// client merges it on top of its locally-computed NetworkMap.
+func toProxyPatch(nm *types.NetworkMap, dnsName string, includeIPv6, useSourcePrefixes bool) *proto.ProxyPatch {
+	if nm == nil {
+		return nil
+	}
+	if len(nm.Peers) == 0 && len(nm.OfflinePeers) == 0 && len(nm.FirewallRules) == 0 &&
+		len(nm.Routes) == 0 && len(nm.RoutesFirewallRules) == 0 && len(nm.ForwardingRules) == 0 {
+		return nil
+	}
+
+	patch := &proto.ProxyPatch{
+		Peers:              networkmap.AppendRemotePeerConfig(nil, nm.Peers, dnsName, includeIPv6),
+		OfflinePeers:       networkmap.AppendRemotePeerConfig(nil, nm.OfflinePeers, dnsName, includeIPv6),
+		FirewallRules:      networkmap.ToProtocolFirewallRules(nm.FirewallRules, includeIPv6, useSourcePrefixes),
+		Routes:             networkmap.ToProtocolRoutes(nm.Routes),
+		RouteFirewallRules: networkmap.ToProtocolRoutesFirewallRules(nm.RoutesFirewallRules),
+	}
+	if len(nm.ForwardingRules) > 0 {
+		patch.ForwardingRules = make([]*proto.ForwardingRule, 0, len(nm.ForwardingRules))
+		for _, r := range nm.ForwardingRules {
+			patch.ForwardingRules = append(patch.ForwardingRules, r.ToProto())
+		}
+	}
+	return patch
+}
+
+// computeSSHEnabledForPeer mirrors the SSH-server-activation bit that
+// Calculate() folds into NetworkMap.EnableSSH. Components-format peers
+// receive a freshly-computed PeerConfig.SshConfig.SshEnabled at sync time;
+// without this helper the field would be incorrectly false for any peer
+// that's the destination of an SSH-enabling policy without having
+// peer.SSHEnabled set locally.
+//
+// Mirrors the two activation paths in Calculate() (`networkmap_components.go`
+// `getPeerConnectionResources`):
+//  1. Explicit: rule.Protocol == NetbirdSSH and peer is in the rule's
+//     destinations.
+//  2. Legacy implicit: rule covers TCP/22 or TCP/22022 (or ALL), peer is in
+//     destinations, AND the peer has SSHEnabled set locally — this is the
+//     "allow-all/TCP-22 implies SSH activation for SSH-capable peers" path.
+//
+// The full SSH AuthorizedUsers map is still produced by the client when it
+// runs Calculate() over the envelope.
+func computeSSHEnabledForPeer(c *types.NetworkMapComponents, peer *nbpeer.Peer) bool {
+	if c == nil || peer == nil {
+		return false
+	}
+	// Mirror Calculate's `getAllPeersFromGroups` invariant: target peer must
+	// exist in c.Peers, otherwise no rule applies to it.
+	if _, ok := c.Peers[peer.ID]; !ok {
+		return false
+	}
+	for _, policy := range c.Policies {
+		if policy == nil || !policy.Enabled {
+			continue
+		}
+		for _, rule := range policy.Rules {
+			if ruleEnablesSSHForPeer(c, rule, peer) {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+// ruleEnablesSSHForPeer returns true when rule is active, targets peer, and
+// either explicitly authorises SSH or covers the legacy TCP/22 path while the
+// peer itself has SSH enabled locally.
+func ruleEnablesSSHForPeer(c *types.NetworkMapComponents, rule *types.PolicyRule, peer *nbpeer.Peer) bool {
+	if rule == nil || !rule.Enabled {
+		return false
+	}
+	if !peerInDestinations(c, rule, peer.ID) {
+		return false
+	}
+	if rule.Protocol == types.PolicyRuleProtocolNetbirdSSH {
+		return true
+	}
+	return peer.SSHEnabled && types.PolicyRuleImpliesLegacySSH(rule)
+}
+
+// peerInDestinations reports whether peerID is in any of rule.Destinations'
+// groups (or matches DestinationResource if it's a peer-typed resource —
+// for non-peer types Calculate falls through to group lookup, so we mirror
+// that exactly to avoid silent divergence).
+func peerInDestinations(c *types.NetworkMapComponents, rule *types.PolicyRule, peerID string) bool {
+	if rule.DestinationResource.Type == types.ResourceTypePeer && rule.DestinationResource.ID != "" {
+		return rule.DestinationResource.ID == peerID
+	}
+	for _, groupID := range rule.Destinations {
+		if c.IsPeerInGroup(peerID, groupID) {
+			return true
+		}
+	}
+	return false
+}

management/internals/shared/grpc/components_envelope_response_test.go

@@ -0,0 +1,186 @@
+package grpc
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/types"
+)
+
+// TestComputeSSHEnabledForPeer covers both Calculate-mirroring branches:
+// explicit NetbirdSSH protocol, and the legacy implicit case where a
+// TCP/22 (or 22022 / ALL / port-range-covering-22) rule activates SSH when
+// the destination peer has SSHEnabled=true locally. Belt-and-suspenders for
+// the B1 fix that the prod-DB equivalence test alone wouldn't have caught
+// if no account had this combination.
+func TestComputeSSHEnabledForPeer(t *testing.T) {
+	const targetPeerID = "target"
+	const targetGroupID = "g_dst"
+
+	mkComponents := func(rule *types.PolicyRule, sshEnabled bool) (*types.NetworkMapComponents, *nbpeer.Peer) {
+		peer := &nbpeer.Peer{ID: targetPeerID, SSHEnabled: sshEnabled}
+		group := &types.Group{ID: targetGroupID, Name: "dst", Peers: []string{targetPeerID}}
+		return &types.NetworkMapComponents{
+			Peers:  map[string]*nbpeer.Peer{targetPeerID: peer},
+			Groups: map[string]*types.Group{targetGroupID: group},
+			Policies: []*types.Policy{{
+				ID:      "p",
+				Enabled: true,
+				Rules:   []*types.PolicyRule{rule},
+			}},
+		}, peer
+	}
+
+	cases := []struct {
+		name        string
+		peerSSH     bool
+		rule        types.PolicyRule
+		wantEnabled bool
+	}{
+		{
+			name:    "explicit-netbird-ssh-activates-regardless-of-peer-ssh",
+			peerSSH: false,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolNetbirdSSH,
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: true,
+		},
+		{
+			name:    "implicit-tcp-22-with-peer-ssh",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolTCP, Ports: []string{"22"},
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: true,
+		},
+		{
+			name:    "implicit-tcp-22-without-peer-ssh-disabled",
+			peerSSH: false,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolTCP, Ports: []string{"22"},
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: false,
+		},
+		{
+			name:    "implicit-tcp-22022-with-peer-ssh",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolTCP, Ports: []string{"22022"},
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: true,
+		},
+		{
+			name:    "implicit-all-protocol-with-peer-ssh",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolALL,
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: true,
+		},
+		{
+			name:    "implicit-port-range-covers-22",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled:      true,
+				Protocol:     types.PolicyRuleProtocolTCP,
+				PortRanges:   []types.RulePortRange{{Start: 20, End: 30}},
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: true,
+		},
+		{
+			name:    "tcp-80-no-ssh",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolTCP, Ports: []string{"80"},
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: false,
+		},
+		{
+			name:    "disabled-rule-skipped",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled: false, Protocol: types.PolicyRuleProtocolNetbirdSSH,
+				Destinations: []string{targetGroupID},
+			},
+			wantEnabled: false,
+		},
+		{
+			name:    "peer-not-in-destinations",
+			peerSSH: true,
+			rule: types.PolicyRule{
+				Enabled: true, Protocol: types.PolicyRuleProtocolNetbirdSSH,
+				Destinations: []string{"g_other"}, // target not in this group
+			},
+			wantEnabled: false,
+		},
+		{
+			name:    "peer-typed-destination-resource-matches",
+			peerSSH: false,
+			rule: types.PolicyRule{
+				Enabled:             true,
+				Protocol:            types.PolicyRuleProtocolNetbirdSSH,
+				DestinationResource: types.Resource{ID: targetPeerID, Type: types.ResourceTypePeer},
+			},
+			wantEnabled: true,
+		},
+		{
+			name:    "non-peer-destination-resource-falls-through-to-groups",
+			peerSSH: false,
+			rule: types.PolicyRule{
+				Enabled:             true,
+				Protocol:            types.PolicyRuleProtocolNetbirdSSH,
+				DestinationResource: types.Resource{ID: targetPeerID, Type: "host"}, // wrong type
+				Destinations:        []string{targetGroupID},                        // saved by group fallback
+			},
+			wantEnabled: true,
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			c, peer := mkComponents(&tc.rule, tc.peerSSH)
+			got := computeSSHEnabledForPeer(c, peer)
+			assert.Equal(t, tc.wantEnabled, got)
+		})
+	}
+}
+
+// TestComputeSSHEnabledForPeer_TargetMissingFromComponents covers the
+// belt-and-suspenders presence guard mirroring Calculate's
+// getAllPeersFromGroups invariant.
+func TestComputeSSHEnabledForPeer_TargetMissingFromComponents(t *testing.T) {
+	peer := &nbpeer.Peer{ID: "missing", SSHEnabled: true}
+	c := &types.NetworkMapComponents{
+		Peers: map[string]*nbpeer.Peer{}, // target peer NOT present
+		Groups: map[string]*types.Group{
+			"g": {ID: "g", Peers: []string{"missing"}},
+		},
+		Policies: []*types.Policy{{
+			ID: "p", Enabled: true,
+			Rules: []*types.PolicyRule{{
+				Enabled: true, Protocol: types.PolicyRuleProtocolNetbirdSSH,
+				Destinations: []string{"g"},
+			}},
+		}},
+	}
+	assert.False(t, computeSSHEnabledForPeer(c, peer),
+		"missing target peer must short-circuit to false, not consult policies")
+}
+
+// TestComputeSSHEnabledForPeer_NilInputs guards the cheap nil-checks at
+// function entry — Calculate doesn't accept nil either, but the helper is
+// exported indirectly via ToComponentSyncResponse and may receive nil
+// components on graceful-degrade paths.
+func TestComputeSSHEnabledForPeer_NilInputs(t *testing.T) {
+	assert.False(t, computeSSHEnabledForPeer(nil, &nbpeer.Peer{ID: "x"}))
+	assert.False(t, computeSSHEnabledForPeer(&types.NetworkMapComponents{}, nil))
+}

management/internals/shared/grpc/conversion.go

@@ -7,23 +7,18 @@ import (
 	"net/url"
 	"strings"
 
-	log "github.com/sirupsen/logrus"
-	goproto "google.golang.org/protobuf/proto"
-
 	integrationsConfig "github.com/netbirdio/management-integrations/integrations/config"
 
 	"github.com/netbirdio/netbird/client/ssh/auth"
 
-	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller/cache"
 	nbconfig "github.com/netbirdio/netbird/management/internals/server/config"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/posture"
 	"github.com/netbirdio/netbird/management/server/types"
-	nbroute "github.com/netbirdio/netbird/route"
+	"github.com/netbirdio/netbird/shared/management/networkmap"
 	"github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/shared/netiputil"
-	"github.com/netbirdio/netbird/shared/sshauth"
 )
 
 func toNetbirdConfig(config *nbconfig.Config, turnCredentials *Token, relayToken *Token, extraSettings *types.ExtraSettings) *proto.NetbirdConfig {
@@ -138,8 +133,8 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 		PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH),
 		NetworkMap: &proto.NetworkMap{
 			Serial:     networkMap.Network.CurrentSerial(),
-			Routes:     toProtocolRoutes(networkMap.Routes),
-			DNSConfig:  toProtocolDNSConfig(networkMap.DNSConfig, dnsCache, dnsFwdPort),
+			Routes:     networkmap.ToProtocolRoutes(networkMap.Routes),
+			DNSConfig:  networkmap.ToProtocolDNSConfig(networkMap.DNSConfig, dnsCache, dnsFwdPort),
 			PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH),
 		},
 		Checks: toProtocolChecks(ctx, checks),
@@ -152,19 +147,19 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	response.NetworkMap.PeerConfig = response.PeerConfig
 
 	remotePeers := make([]*proto.RemotePeerConfig, 0, len(networkMap.Peers)+len(networkMap.OfflinePeers))
-	remotePeers = appendRemotePeerConfig(remotePeers, networkMap.Peers, dnsName, includeIPv6)
+	remotePeers = networkmap.AppendRemotePeerConfig(remotePeers, networkMap.Peers, dnsName, includeIPv6)
 	response.RemotePeers = remotePeers
 	response.NetworkMap.RemotePeers = remotePeers
 	response.RemotePeersIsEmpty = len(remotePeers) == 0
 	response.NetworkMap.RemotePeersIsEmpty = response.RemotePeersIsEmpty
 
-	response.NetworkMap.OfflinePeers = appendRemotePeerConfig(nil, networkMap.OfflinePeers, dnsName, includeIPv6)
+	response.NetworkMap.OfflinePeers = networkmap.AppendRemotePeerConfig(nil, networkMap.OfflinePeers, dnsName, includeIPv6)
 
-	firewallRules := toProtocolFirewallRules(networkMap.FirewallRules, includeIPv6, useSourcePrefixes)
+	firewallRules := networkmap.ToProtocolFirewallRules(networkMap.FirewallRules, includeIPv6, useSourcePrefixes)
 	response.NetworkMap.FirewallRules = firewallRules
 	response.NetworkMap.FirewallRulesIsEmpty = len(firewallRules) == 0
 
-	routesFirewallRules := toProtocolRoutesFirewallRules(networkMap.RoutesFirewallRules)
+	routesFirewallRules := networkmap.ToProtocolRoutesFirewallRules(networkMap.RoutesFirewallRules)
 	response.NetworkMap.RoutesFirewallRules = routesFirewallRules
 	response.NetworkMap.RoutesFirewallRulesIsEmpty = len(routesFirewallRules) == 0
 
@@ -177,7 +172,7 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	}
 
 	if networkMap.AuthorizedUsers != nil {
-		hashedUsers, machineUsers := buildAuthorizedUsersProto(ctx, networkMap.AuthorizedUsers)
+		hashedUsers, machineUsers := networkmap.BuildAuthorizedUsersProto(ctx, networkMap.AuthorizedUsers)
 		userIDClaim := auth.DefaultUserIDClaim
 		if httpConfig != nil && httpConfig.AuthUserIDClaim != "" {
 			userIDClaim = httpConfig.AuthUserIDClaim
@@ -188,78 +183,6 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	return response
 }
 
-func buildAuthorizedUsersProto(ctx context.Context, authorizedUsers map[string]map[string]struct{}) ([][]byte, map[string]*proto.MachineUserIndexes) {
-	userIDToIndex := make(map[string]uint32)
-	var hashedUsers [][]byte
-	machineUsers := make(map[string]*proto.MachineUserIndexes, len(authorizedUsers))
-
-	for machineUser, users := range authorizedUsers {
-		indexes := make([]uint32, 0, len(users))
-		for userID := range users {
-			idx, exists := userIDToIndex[userID]
-			if !exists {
-				hash, err := sshauth.HashUserID(userID)
-				if err != nil {
-					log.WithContext(ctx).Errorf("failed to hash user id %s: %v", userID, err)
-					continue
-				}
-				idx = uint32(len(hashedUsers))
-				userIDToIndex[userID] = idx
-				hashedUsers = append(hashedUsers, hash[:])
-			}
-			indexes = append(indexes, idx)
-		}
-		machineUsers[machineUser] = &proto.MachineUserIndexes{Indexes: indexes}
-	}
-
-	return hashedUsers, machineUsers
-}
-
-func appendRemotePeerConfig(dst []*proto.RemotePeerConfig, peers []*nbpeer.Peer, dnsName string, includeIPv6 bool) []*proto.RemotePeerConfig {
-	for _, rPeer := range peers {
-		allowedIPs := []string{rPeer.IP.String() + "/32"}
-		if includeIPv6 && rPeer.IPv6.IsValid() {
-			allowedIPs = append(allowedIPs, rPeer.IPv6.String()+"/128")
-		}
-		dst = append(dst, &proto.RemotePeerConfig{
-			WgPubKey:     rPeer.Key,
-			AllowedIps:   allowedIPs,
-			SshConfig:    &proto.SSHConfig{SshPubKey: []byte(rPeer.SSHKey)},
-			Fqdn:         rPeer.FQDN(dnsName),
-			AgentVersion: rPeer.Meta.WtVersion,
-		})
-	}
-	return dst
-}
-
-// toProtocolDNSConfig converts nbdns.Config to proto.DNSConfig using the cache
-func toProtocolDNSConfig(update nbdns.Config, cache *cache.DNSConfigCache, forwardPort int64) *proto.DNSConfig {
-	protoUpdate := &proto.DNSConfig{
-		ServiceEnable:    update.ServiceEnable,
-		CustomZones:      make([]*proto.CustomZone, 0, len(update.CustomZones)),
-		NameServerGroups: make([]*proto.NameServerGroup, 0, len(update.NameServerGroups)),
-		ForwarderPort:    forwardPort,
-	}
-
-	for _, zone := range update.CustomZones {
-		protoZone := convertToProtoCustomZone(zone)
-		protoUpdate.CustomZones = append(protoUpdate.CustomZones, protoZone)
-	}
-
-	for _, nsGroup := range update.NameServerGroups {
-		cacheKey := nsGroup.ID
-		if cachedGroup, exists := cache.GetNameServerGroup(cacheKey); exists {
-			protoUpdate.NameServerGroups = append(protoUpdate.NameServerGroups, cachedGroup)
-		} else {
-			protoGroup := convertToProtoNameServerGroup(nsGroup)
-			cache.SetNameServerGroup(cacheKey, protoGroup)
-			protoUpdate.NameServerGroups = append(protoUpdate.NameServerGroups, protoGroup)
-		}
-	}
-
-	return protoUpdate
-}
-
 func ToResponseProto(configProto nbconfig.Protocol) proto.HostConfig_Protocol {
 	switch configProto {
 	case nbconfig.UDP:
@@ -277,204 +200,6 @@ func ToResponseProto(configProto nbconfig.Protocol) proto.HostConfig_Protocol {
 	}
 }
 
-func toProtocolRoutes(routes []*nbroute.Route) []*proto.Route {
-	protoRoutes := make([]*proto.Route, 0, len(routes))
-	for _, r := range routes {
-		protoRoutes = append(protoRoutes, toProtocolRoute(r))
-	}
-	return protoRoutes
-}
-
-func toProtocolRoute(route *nbroute.Route) *proto.Route {
-	return &proto.Route{
-		ID:            string(route.ID),
-		NetID:         string(route.NetID),
-		Network:       route.Network.String(),
-		Domains:       route.Domains.ToPunycodeList(),
-		NetworkType:   int64(route.NetworkType),
-		Peer:          route.Peer,
-		Metric:        int64(route.Metric),
-		Masquerade:    route.Masquerade,
-		KeepRoute:     route.KeepRoute,
-		SkipAutoApply: route.SkipAutoApply,
-	}
-}
-
-// toProtocolFirewallRules converts the firewall rules to the protocol firewall rules.
-// When useSourcePrefixes is true, the compact SourcePrefixes field is populated
-// alongside the deprecated PeerIP for forward compatibility.
-// Wildcard rules ("0.0.0.0") are expanded into separate v4 and v6 SourcePrefixes
-// when includeIPv6 is true.
-func toProtocolFirewallRules(rules []*types.FirewallRule, includeIPv6, useSourcePrefixes bool) []*proto.FirewallRule {
-	result := make([]*proto.FirewallRule, 0, len(rules))
-	for i := range rules {
-		rule := rules[i]
-
-		fwRule := &proto.FirewallRule{
-			PolicyID:  []byte(rule.PolicyID),
-			PeerIP:    rule.PeerIP, //nolint:staticcheck // populated for backward compatibility
-			Direction: getProtoDirection(rule.Direction),
-			Action:    getProtoAction(rule.Action),
-			Protocol:  getProtoProtocol(rule.Protocol),
-			Port:      rule.Port,
-		}
-
-		if useSourcePrefixes && rule.PeerIP != "" {
-			result = append(result, populateSourcePrefixes(fwRule, rule, includeIPv6)...)
-		}
-
-		if shouldUsePortRange(fwRule) {
-			fwRule.PortInfo = rule.PortRange.ToProto()
-		}
-
-		result = append(result, fwRule)
-	}
-	return result
-}
-
-
-// populateSourcePrefixes sets SourcePrefixes on fwRule and returns any
-// additional rules needed (e.g. a v6 wildcard clone when the peer IP is unspecified).
-func populateSourcePrefixes(fwRule *proto.FirewallRule, rule *types.FirewallRule, includeIPv6 bool) []*proto.FirewallRule {
-	addr, err := netip.ParseAddr(rule.PeerIP)
-	if err != nil {
-		return nil
-	}
-
-	if !addr.IsUnspecified() {
-		fwRule.SourcePrefixes = [][]byte{netiputil.EncodeAddr(addr.Unmap())}
-		return nil
-	}
-
-	// IPv4Unspecified/0 is always valid, error is impossible.
-	v4Wildcard, _ := netiputil.EncodePrefix(netip.PrefixFrom(netip.IPv4Unspecified(), 0))
-	fwRule.SourcePrefixes = [][]byte{v4Wildcard}
-
-	if !includeIPv6 {
-		return nil
-	}
-
-	v6Rule := goproto.Clone(fwRule).(*proto.FirewallRule)
-	v6Rule.PeerIP = "::" //nolint:staticcheck // populated for backward compatibility
-	// IPv6Unspecified/0 is always valid, error is impossible.
-	v6Wildcard, _ := netiputil.EncodePrefix(netip.PrefixFrom(netip.IPv6Unspecified(), 0))
-	v6Rule.SourcePrefixes = [][]byte{v6Wildcard}
-	if shouldUsePortRange(v6Rule) {
-		v6Rule.PortInfo = rule.PortRange.ToProto()
-	}
-	return []*proto.FirewallRule{v6Rule}
-}
-
-// getProtoDirection converts the direction to proto.RuleDirection.
-func getProtoDirection(direction int) proto.RuleDirection {
-	if direction == types.FirewallRuleDirectionOUT {
-		return proto.RuleDirection_OUT
-	}
-	return proto.RuleDirection_IN
-}
-
-func toProtocolRoutesFirewallRules(rules []*types.RouteFirewallRule) []*proto.RouteFirewallRule {
-	result := make([]*proto.RouteFirewallRule, len(rules))
-	for i := range rules {
-		rule := rules[i]
-		result[i] = &proto.RouteFirewallRule{
-			SourceRanges: rule.SourceRanges,
-			Action:       getProtoAction(rule.Action),
-			Destination:  rule.Destination,
-			Protocol:     getProtoProtocol(rule.Protocol),
-			PortInfo:     getProtoPortInfo(rule),
-			IsDynamic:    rule.IsDynamic,
-			Domains:      rule.Domains.ToPunycodeList(),
-			PolicyID:     []byte(rule.PolicyID),
-			RouteID:      string(rule.RouteID),
-		}
-	}
-
-	return result
-}
-
-// getProtoAction converts the action to proto.RuleAction.
-func getProtoAction(action string) proto.RuleAction {
-	if action == string(types.PolicyTrafficActionDrop) {
-		return proto.RuleAction_DROP
-	}
-	return proto.RuleAction_ACCEPT
-}
-
-// getProtoProtocol converts the protocol to proto.RuleProtocol.
-func getProtoProtocol(protocol string) proto.RuleProtocol {
-	switch types.PolicyRuleProtocolType(protocol) {
-	case types.PolicyRuleProtocolALL:
-		return proto.RuleProtocol_ALL
-	case types.PolicyRuleProtocolTCP:
-		return proto.RuleProtocol_TCP
-	case types.PolicyRuleProtocolUDP:
-		return proto.RuleProtocol_UDP
-	case types.PolicyRuleProtocolICMP:
-		return proto.RuleProtocol_ICMP
-	default:
-		return proto.RuleProtocol_UNKNOWN
-	}
-}
-
-// getProtoPortInfo converts the port info to proto.PortInfo.
-func getProtoPortInfo(rule *types.RouteFirewallRule) *proto.PortInfo {
-	var portInfo proto.PortInfo
-	if rule.Port != 0 {
-		portInfo.PortSelection = &proto.PortInfo_Port{Port: uint32(rule.Port)}
-	} else if portRange := rule.PortRange; portRange.Start != 0 && portRange.End != 0 {
-		portInfo.PortSelection = &proto.PortInfo_Range_{
-			Range: &proto.PortInfo_Range{
-				Start: uint32(portRange.Start),
-				End:   uint32(portRange.End),
-			},
-		}
-	}
-	return &portInfo
-}
-
-func shouldUsePortRange(rule *proto.FirewallRule) bool {
-	return rule.Port == "" && (rule.Protocol == proto.RuleProtocol_UDP || rule.Protocol == proto.RuleProtocol_TCP)
-}
-
-// Helper function to convert nbdns.CustomZone to proto.CustomZone
-func convertToProtoCustomZone(zone nbdns.CustomZone) *proto.CustomZone {
-	protoZone := &proto.CustomZone{
-		Domain:               zone.Domain,
-		Records:              make([]*proto.SimpleRecord, 0, len(zone.Records)),
-		SearchDomainDisabled: zone.SearchDomainDisabled,
-		NonAuthoritative:     zone.NonAuthoritative,
-	}
-	for _, record := range zone.Records {
-		protoZone.Records = append(protoZone.Records, &proto.SimpleRecord{
-			Name:  record.Name,
-			Type:  int64(record.Type),
-			Class: record.Class,
-			TTL:   int64(record.TTL),
-			RData: record.RData,
-		})
-	}
-	return protoZone
-}
-
-// Helper function to convert nbdns.NameServerGroup to proto.NameServerGroup
-func convertToProtoNameServerGroup(nsGroup *nbdns.NameServerGroup) *proto.NameServerGroup {
-	protoGroup := &proto.NameServerGroup{
-		Primary:              nsGroup.Primary,
-		Domains:              nsGroup.Domains,
-		SearchDomainsEnabled: nsGroup.SearchDomainsEnabled,
-		NameServers:          make([]*proto.NameServer, 0, len(nsGroup.NameServers)),
-	}
-	for _, ns := range nsGroup.NameServers {
-		protoGroup.NameServers = append(protoGroup.NameServers, &proto.NameServer{
-			IP:     ns.IP.String(),
-			Port:   int64(ns.Port),
-			NSType: int64(ns.NSType),
-		})
-	}
-	return protoGroup
-}
-
 // buildJWTConfig constructs JWT configuration for SSH servers from management server config
 func buildJWTConfig(config *nbconfig.HttpServerConfig, deviceFlowConfig *nbconfig.DeviceAuthorizationFlow) *proto.JWTConfig {
 	if config == nil || config.AuthAudience == "" {

management/internals/shared/grpc/conversion_test.go

@@ -12,6 +12,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller/cache"
 	nbconfig "github.com/netbirdio/netbird/management/internals/server/config"
+	"github.com/netbirdio/netbird/shared/management/networkmap"
 )
 
 func TestToProtocolDNSConfigWithCache(t *testing.T) {
@@ -61,13 +62,13 @@ func TestToProtocolDNSConfigWithCache(t *testing.T) {
 	}
 
 	// First run with config1
-	result1 := toProtocolDNSConfig(config1, &cache, int64(network_map.DnsForwarderPort))
+	result1 := networkmap.ToProtocolDNSConfig(config1, &cache, int64(network_map.DnsForwarderPort))
 
 	// Second run with config2
-	result2 := toProtocolDNSConfig(config2, &cache, int64(network_map.DnsForwarderPort))
+	result2 := networkmap.ToProtocolDNSConfig(config2, &cache, int64(network_map.DnsForwarderPort))
 
 	// Third run with config1 again
-	result3 := toProtocolDNSConfig(config1, &cache, int64(network_map.DnsForwarderPort))
+	result3 := networkmap.ToProtocolDNSConfig(config1, &cache, int64(network_map.DnsForwarderPort))
 
 	// Verify that result1 and result3 are identical
 	if !reflect.DeepEqual(result1, result3) {
@@ -99,7 +100,7 @@ func BenchmarkToProtocolDNSConfig(b *testing.B) {
 
 			b.ResetTimer()
 			for i := 0; i < b.N; i++ {
-				toProtocolDNSConfig(testData, cache, int64(network_map.DnsForwarderPort))
+				networkmap.ToProtocolDNSConfig(testData, cache, int64(network_map.DnsForwarderPort))
 			}
 		})
 
@@ -107,7 +108,7 @@ func BenchmarkToProtocolDNSConfig(b *testing.B) {
 			b.ResetTimer()
 			for i := 0; i < b.N; i++ {
 				cache := &cache.DNSConfigCache{}
-				toProtocolDNSConfig(testData, cache, int64(network_map.DnsForwarderPort))
+				networkmap.ToProtocolDNSConfig(testData, cache, int64(network_map.DnsForwarderPort))
 			}
 		})
 	}

management/internals/shared/grpc/proxy.go

@@ -9,6 +9,7 @@ import (
 	"encoding/hex"
 	"errors"
 	"fmt"
+	"io"
 	"net"
 	"net/http"
 	"net/url"
@@ -136,9 +137,12 @@ type proxyConnection struct {
 	tokenID      string
 	capabilities *proto.ProxyCapabilities
 	stream       proto.ProxyService_GetMappingUpdateServer
-	sendChan     chan *proto.GetMappingUpdateResponse
-	ctx          context.Context
-	cancel       context.CancelFunc
+	// syncStream is set when the proxy connected via SyncMappings.
+	// When non-nil, the sender goroutine uses this instead of stream.
+	syncStream proto.ProxyService_SyncMappingsServer
+	sendChan   chan *proto.GetMappingUpdateResponse
+	ctx        context.Context
+	cancel     context.CancelFunc
 }
 
 func enforceAccountScope(ctx context.Context, requestAccountID string) error {
@@ -206,145 +210,322 @@ func (s *ProxyServiceServer) SetProxyController(proxyController proxy.Controller
 	s.proxyController = proxyController
 }
 
+// proxyConnectParams holds the validated parameters extracted from either
+// a GetMappingUpdateRequest or a SyncMappingsInit message.
+type proxyConnectParams struct {
+	proxyID      string
+	address      string
+	capabilities *proto.ProxyCapabilities
+}
+
 // GetMappingUpdate handles the control stream with proxy clients
 func (s *ProxyServiceServer) GetMappingUpdate(req *proto.GetMappingUpdateRequest, stream proto.ProxyService_GetMappingUpdateServer) error {
-	ctx := stream.Context()
+	params, err := s.validateProxyConnect(req.GetProxyId(), req.GetAddress(), stream.Context())
+	if err != nil {
+		return err
+	}
+	params.capabilities = req.GetCapabilities()
 
-	peerInfo := PeerIPFromContext(ctx)
-	log.Infof("New proxy connection from %s", peerInfo)
+	conn, proxyRecord, err := s.registerProxyConnection(stream.Context(), params, &proxyConnection{
+		stream: stream,
+	})
+	if err != nil {
+		return err
+	}
 
-	proxyID := req.GetProxyId()
+	if err := s.sendSnapshot(stream.Context(), conn); err != nil {
+		s.cleanupFailedSnapshot(stream.Context(), conn)
+		return fmt.Errorf("send snapshot to proxy %s: %w", params.proxyID, err)
+	}
+
+	errChan := make(chan error, 2)
+	go s.sender(conn, errChan)
+
+	return s.serveProxyConnection(conn, proxyRecord, errChan, false)
+}
+
+// SyncMappings implements the bidirectional SyncMappings RPC.
+// It mirrors GetMappingUpdate but provides application-level back-pressure:
+// management waits for an ack from the proxy before sending the next batch.
+func (s *ProxyServiceServer) SyncMappings(stream proto.ProxyService_SyncMappingsServer) error {
+	init, err := recvSyncInit(stream)
+	if err != nil {
+		return err
+	}
+
+	params, err := s.validateProxyConnect(init.GetProxyId(), init.GetAddress(), stream.Context())
+	if err != nil {
+		return err
+	}
+	params.capabilities = init.GetCapabilities()
+
+	conn, proxyRecord, err := s.registerProxyConnection(stream.Context(), params, &proxyConnection{
+		syncStream: stream,
+	})
+	if err != nil {
+		return err
+	}
+
+	if err := s.sendSnapshotSync(stream.Context(), conn, stream); err != nil {
+		s.cleanupFailedSnapshot(stream.Context(), conn)
+		return fmt.Errorf("send snapshot to proxy %s: %w", params.proxyID, err)
+	}
+
+	errChan := make(chan error, 2)
+	go s.sender(conn, errChan)
+	go s.drainRecv(stream, errChan)
+
+	return s.serveProxyConnection(conn, proxyRecord, errChan, true)
+}
+
+// recvSyncInit receives and validates the first message on a SyncMappings stream.
+func recvSyncInit(stream proto.ProxyService_SyncMappingsServer) (*proto.SyncMappingsInit, error) {
+	firstMsg, err := stream.Recv()
+	if err != nil {
+		return nil, status.Errorf(codes.Internal, "receive init: %v", err)
+	}
+	init := firstMsg.GetInit()
+	if init == nil {
+		return nil, status.Errorf(codes.InvalidArgument, "first message must be init")
+	}
+	return init, nil
+}
+
+// validateProxyConnect validates the proxy ID and address, and checks cluster
+// address availability for account-scoped tokens.
+func (s *ProxyServiceServer) validateProxyConnect(proxyID, address string, ctx context.Context) (proxyConnectParams, error) {
 	if proxyID == "" {
-		return status.Errorf(codes.InvalidArgument, "proxy_id is required")
+		return proxyConnectParams{}, status.Errorf(codes.InvalidArgument, "proxy_id is required")
+	}
+	if !isProxyAddressValid(address) {
+		return proxyConnectParams{}, status.Errorf(codes.InvalidArgument, "proxy address is invalid")
 	}
 
-	proxyAddress := req.GetAddress()
-	if !isProxyAddressValid(proxyAddress) {
-		return status.Errorf(codes.InvalidArgument, "proxy address is invalid")
-	}
-
-	var accountID *string
 	token := GetProxyTokenFromContext(ctx)
 	if token != nil && token.AccountID != nil {
-		accountID = token.AccountID
-
-		available, err := s.proxyManager.IsClusterAddressAvailable(ctx, proxyAddress, *accountID)
+		available, err := s.proxyManager.IsClusterAddressAvailable(ctx, address, *token.AccountID)
 		if err != nil {
-			return status.Errorf(codes.Internal, "check cluster address: %v", err)
+			return proxyConnectParams{}, status.Errorf(codes.Internal, "check cluster address: %v", err)
 		}
 		if !available {
-			return status.Errorf(codes.AlreadyExists, "cluster address %s is already in use", proxyAddress)
+			return proxyConnectParams{}, status.Errorf(codes.AlreadyExists, "cluster address %s is already in use", address)
 		}
 	}
 
+	return proxyConnectParams{proxyID: proxyID, address: address}, nil
+}
+
+// registerProxyConnection creates a proxyConnection, registers it with the
+// proxy manager and cluster, and stores it in connectedProxies. The caller
+// provides a partially initialised connSeed with stream-specific fields set;
+// the remaining fields are filled in here.
+func (s *ProxyServiceServer) registerProxyConnection(ctx context.Context, params proxyConnectParams, connSeed *proxyConnection) (*proxyConnection, *proxy.Proxy, error) {
+	peerInfo := PeerIPFromContext(ctx)
+
+	var accountID *string
 	var tokenID string
-	if token != nil {
+	if token := GetProxyTokenFromContext(ctx); token != nil {
+		if token.AccountID != nil {
+			accountID = token.AccountID
+		}
 		tokenID = token.ID
 	}
 
 	sessionID := uuid.NewString()
-
-	if old, loaded := s.connectedProxies.Load(proxyID); loaded {
-		oldConn := old.(*proxyConnection)
-		log.WithFields(log.Fields{
-			"proxy_id":       proxyID,
-			"old_session_id": oldConn.sessionID,
-			"new_session_id": sessionID,
-		}).Info("Superseding existing proxy connection")
-		oldConn.cancel()
-	}
+	s.supersedePriorConnection(params.proxyID, sessionID)
 
 	connCtx, cancel := context.WithCancel(ctx)
-	conn := &proxyConnection{
-		proxyID:      proxyID,
-		sessionID:    sessionID,
-		address:      proxyAddress,
-		accountID:    accountID,
-		tokenID:      tokenID,
-		capabilities: req.GetCapabilities(),
-		stream:       stream,
-		sendChan:     make(chan *proto.GetMappingUpdateResponse, 100),
-		ctx:          connCtx,
-		cancel:       cancel,
-	}
+	connSeed.proxyID = params.proxyID
+	connSeed.sessionID = sessionID
+	connSeed.address = params.address
+	connSeed.accountID = accountID
+	connSeed.tokenID = tokenID
+	connSeed.capabilities = params.capabilities
+	connSeed.sendChan = make(chan *proto.GetMappingUpdateResponse, 100)
+	connSeed.ctx = connCtx
+	connSeed.cancel = cancel
 
 	var caps *proxy.Capabilities
-	if c := req.GetCapabilities(); c != nil {
+	if c := params.capabilities; c != nil {
 		caps = &proxy.Capabilities{
 			SupportsCustomPorts: c.SupportsCustomPorts,
 			RequireSubdomain:    c.RequireSubdomain,
 			SupportsCrowdsec:    c.SupportsCrowdsec,
 		}
 	}
-	proxyRecord, err := s.proxyManager.Connect(ctx, proxyID, sessionID, proxyAddress, peerInfo, accountID, caps)
+
+	proxyRecord, err := s.proxyManager.Connect(ctx, params.proxyID, sessionID, params.address, peerInfo, accountID, caps)
 	if err != nil {
 		cancel()
 		if accountID != nil {
-			return status.Errorf(codes.Internal, "failed to register BYOP proxy: %v", err)
+			return nil, nil, status.Errorf(codes.Internal, "failed to register BYOP proxy: %v", err)
 		}
-		log.WithContext(ctx).Warnf("failed to register proxy %s in database: %v", proxyID, err)
-		return status.Errorf(codes.Internal, "register proxy in database: %v", err)
+		log.WithContext(ctx).Warnf("failed to register proxy %s in database: %v", params.proxyID, err)
+		return nil, nil, status.Errorf(codes.Internal, "register proxy in database: %v", err)
 	}
 
-	s.connectedProxies.Store(proxyID, conn)
-	if err := s.proxyController.RegisterProxyToCluster(ctx, conn.address, proxyID); err != nil {
-		log.WithContext(ctx).Warnf("Failed to register proxy %s in cluster: %v", proxyID, err)
+	s.connectedProxies.Store(params.proxyID, connSeed)
+	if err := s.proxyController.RegisterProxyToCluster(ctx, params.address, params.proxyID); err != nil {
+		log.WithContext(ctx).Warnf("Failed to register proxy %s in cluster: %v", params.proxyID, err)
 	}
 
-	if err := s.sendSnapshot(ctx, conn); err != nil {
-		if s.connectedProxies.CompareAndDelete(proxyID, conn) {
-			if unregErr := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, proxyID); unregErr != nil {
-				log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", proxyID, unregErr)
-			}
-		}
-		cancel()
-		if disconnErr := s.proxyManager.Disconnect(context.Background(), proxyID, sessionID); disconnErr != nil {
-			log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", proxyID, disconnErr)
-		}
-		return fmt.Errorf("send snapshot to proxy %s: %w", proxyID, err)
+	return connSeed, proxyRecord, nil
+}
+
+// supersedePriorConnection cancels any existing connection for the given proxy.
+func (s *ProxyServiceServer) supersedePriorConnection(proxyID, newSessionID string) {
+	if old, loaded := s.connectedProxies.Load(proxyID); loaded {
+		oldConn := old.(*proxyConnection)
+		log.WithFields(log.Fields{
+			"proxy_id":       proxyID,
+			"old_session_id": oldConn.sessionID,
+			"new_session_id": newSessionID,
+		}).Info("Superseding existing proxy connection")
+		oldConn.cancel()
 	}
+}
 
-	errChan := make(chan error, 2)
-	go s.sender(conn, errChan)
+// cleanupFailedSnapshot removes the connection from the cluster and store
+// after a snapshot send failure.
+func (s *ProxyServiceServer) cleanupFailedSnapshot(ctx context.Context, conn *proxyConnection) {
+	if s.connectedProxies.CompareAndDelete(conn.proxyID, conn) {
+		if err := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, conn.proxyID); err != nil {
+			log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", conn.proxyID, err)
+		}
+	}
+	conn.cancel()
+	if err := s.proxyManager.Disconnect(context.Background(), conn.proxyID, conn.sessionID); err != nil {
+		log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", conn.proxyID, err)
+	}
+}
 
-	log.WithFields(log.Fields{
-		"proxy_id":      proxyID,
-		"session_id":    sessionID,
-		"address":       proxyAddress,
-		"cluster_addr":  proxyAddress,
-		"account_id":    accountID,
-		"total_proxies": len(s.GetConnectedProxies()),
-	}).Info("Proxy registered in cluster")
-	defer func() {
-		if !s.connectedProxies.CompareAndDelete(proxyID, conn) {
-			log.Infof("Proxy %s session %s: skipping cleanup, superseded by new connection", proxyID, sessionID)
-			cancel()
+// drainRecv consumes and discards messages from a bidirectional stream.
+// The proxy sends an ack for every incremental update; we don't need them
+// after the snapshot phase. Recv errors are forwarded to errChan.
+func (s *ProxyServiceServer) drainRecv(stream proto.ProxyService_SyncMappingsServer, errChan chan<- error) {
+	for {
+		if _, err := stream.Recv(); err != nil {
+			errChan <- err
 			return
 		}
+	}
+}
 
-		if err := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, proxyID); err != nil {
-			log.Warnf("Failed to unregister proxy %s from cluster: %v", proxyID, err)
-		}
-		if err := s.proxyManager.Disconnect(context.Background(), proxyID, sessionID); err != nil {
-			log.Warnf("Failed to mark proxy %s as disconnected: %v", proxyID, err)
-		}
+// serveProxyConnection runs the post-snapshot lifecycle: heartbeat, sender,
+// and wait for termination. When bidi is true, normal stream closure (EOF,
+// canceled) is treated as a clean disconnect rather than an error.
+func (s *ProxyServiceServer) serveProxyConnection(conn *proxyConnection, proxyRecord *proxy.Proxy, errChan <-chan error, bidi bool) error {
+	log.WithFields(log.Fields{
+		"proxy_id":      conn.proxyID,
+		"session_id":    conn.sessionID,
+		"address":       conn.address,
+		"cluster_addr":  conn.address,
+		"account_id":    conn.accountID,
+		"total_proxies": len(s.GetConnectedProxies()),
+	}).Info("Proxy registered in cluster")
 
-		cancel()
-		log.Infof("Proxy %s session %s disconnected", proxyID, sessionID)
-	}()
-
-	go s.heartbeat(connCtx, conn, proxyRecord)
+	defer s.disconnectProxy(conn)
+	go s.heartbeat(conn.ctx, conn, proxyRecord)
 
 	select {
 	case err := <-errChan:
-		log.WithContext(ctx).Warnf("Failed to send update: %v", err)
-		return fmt.Errorf("send update to proxy %s: %w", proxyID, err)
-	case <-connCtx.Done():
-		log.WithContext(ctx).Infof("Proxy %s context canceled", proxyID)
-		return connCtx.Err()
+		if bidi && isStreamClosed(err) {
+			log.Infof("Proxy %s stream closed", conn.proxyID)
+			return nil
+		}
+		log.Warnf("Failed to send update: %v", err)
+		return fmt.Errorf("send update to proxy %s: %w", conn.proxyID, err)
+	case <-conn.ctx.Done():
+		log.Infof("Proxy %s context canceled", conn.proxyID)
+		return conn.ctx.Err()
 	}
 }
 
+// disconnectProxy removes the connection from cluster and store, unless it
+// has already been superseded by a newer connection.
+func (s *ProxyServiceServer) disconnectProxy(conn *proxyConnection) {
+	if !s.connectedProxies.CompareAndDelete(conn.proxyID, conn) {
+		log.Infof("Proxy %s session %s: skipping cleanup, superseded by new connection", conn.proxyID, conn.sessionID)
+		conn.cancel()
+		return
+	}
+
+	if err := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, conn.proxyID); err != nil {
+		log.Warnf("Failed to unregister proxy %s from cluster: %v", conn.proxyID, err)
+	}
+	if err := s.proxyManager.Disconnect(context.Background(), conn.proxyID, conn.sessionID); err != nil {
+		log.Warnf("Failed to mark proxy %s as disconnected: %v", conn.proxyID, err)
+	}
+
+	conn.cancel()
+	log.Infof("Proxy %s session %s disconnected", conn.proxyID, conn.sessionID)
+}
+
+// sendSnapshotSync sends the initial snapshot with back-pressure: it sends
+// one batch, then waits for the proxy to ack before sending the next.
+func (s *ProxyServiceServer) sendSnapshotSync(ctx context.Context, conn *proxyConnection, stream proto.ProxyService_SyncMappingsServer) error {
+	if !isProxyAddressValid(conn.address) {
+		return fmt.Errorf("proxy address is invalid")
+	}
+	if s.snapshotBatchSize <= 0 {
+		return fmt.Errorf("invalid snapshot batch size: %d", s.snapshotBatchSize)
+	}
+
+	mappings, err := s.snapshotServiceMappings(ctx, conn)
+	if err != nil {
+		return err
+	}
+
+	for i := 0; i < len(mappings); i += s.snapshotBatchSize {
+		end := i + s.snapshotBatchSize
+		if end > len(mappings) {
+			end = len(mappings)
+		}
+		for _, m := range mappings[i:end] {
+			token, err := s.tokenStore.GenerateToken(m.AccountId, m.Id, s.proxyTokenTTL())
+			if err != nil {
+				return fmt.Errorf("generate auth token for service %s: %w", m.Id, err)
+			}
+			m.AuthToken = token
+		}
+		if err := stream.Send(&proto.SyncMappingsResponse{
+			Mapping:             mappings[i:end],
+			InitialSyncComplete: end == len(mappings),
+		}); err != nil {
+			return fmt.Errorf("send snapshot batch: %w", err)
+		}
+
+		if err := waitForAck(stream); err != nil {
+			return err
+		}
+	}
+
+	if len(mappings) == 0 {
+		if err := stream.Send(&proto.SyncMappingsResponse{
+			InitialSyncComplete: true,
+		}); err != nil {
+			return fmt.Errorf("send snapshot completion: %w", err)
+		}
+
+		if err := waitForAck(stream); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+func waitForAck(stream proto.ProxyService_SyncMappingsServer) error {
+	msg, err := stream.Recv()
+	if err != nil {
+		return fmt.Errorf("receive ack: %w", err)
+	}
+	if msg.GetAck() == nil {
+		return fmt.Errorf("expected ack, got %T", msg.GetMsg())
+	}
+	return nil
+}
+
 // heartbeat updates the proxy's last_seen timestamp every minute and
 // disconnects the proxy if its access token has been revoked.
 func (s *ProxyServiceServer) heartbeat(ctx context.Context, conn *proxyConnection, p *proxy.Proxy) {
@@ -381,6 +562,9 @@ func (s *ProxyServiceServer) sendSnapshot(ctx context.Context, conn *proxyConnec
 	if !isProxyAddressValid(conn.address) {
 		return fmt.Errorf("proxy address is invalid")
 	}
+	if s.snapshotBatchSize <= 0 {
+		return fmt.Errorf("invalid snapshot batch size: %d", s.snapshotBatchSize)
+	}
 
 	mappings, err := s.snapshotServiceMappings(ctx, conn)
 	if err != nil {
@@ -394,6 +578,13 @@ func (s *ProxyServiceServer) sendSnapshot(ctx context.Context, conn *proxyConnec
 		if end > len(mappings) {
 			end = len(mappings)
 		}
+		for _, m := range mappings[i:end] {
+			token, err := s.tokenStore.GenerateToken(m.AccountId, m.Id, s.proxyTokenTTL())
+			if err != nil {
+				return fmt.Errorf("generate auth token for service %s: %w", m.Id, err)
+			}
+			m.AuthToken = token
+		}
 		if err := conn.stream.Send(&proto.GetMappingUpdateResponse{
 			Mapping:             mappings[i:end],
 			InitialSyncComplete: end == len(mappings),
@@ -425,18 +616,14 @@ func (s *ProxyServiceServer) snapshotServiceMappings(ctx context.Context, conn *
 		return nil, fmt.Errorf("get services from store: %w", err)
 	}
 
+	oidcCfg := s.GetOIDCValidationConfig()
 	var mappings []*proto.ProxyMapping
 	for _, service := range services {
 		if !service.Enabled || service.ProxyCluster == "" || service.ProxyCluster != conn.address {
 			continue
 		}
 
-		token, err := s.tokenStore.GenerateToken(service.AccountID, service.ID, s.proxyTokenTTL())
-		if err != nil {
-			return nil, fmt.Errorf("generate auth token for service %s: %w", service.ID, err)
-		}
-
-		m := service.ToProtoMapping(rpservice.Create, token, s.GetOIDCValidationConfig())
+		m := service.ToProtoMapping(rpservice.Create, "", oidcCfg)
 		if !proxyAcceptsMapping(conn, m) {
 			continue
 		}
@@ -457,12 +644,26 @@ func isProxyAddressValid(addr string) bool {
 	return err == nil
 }
 
-// sender handles sending messages to proxy
+// isStreamClosed returns true for errors that indicate normal stream
+// termination: io.EOF, context cancellation, or gRPC Canceled.
+func isStreamClosed(err error) bool {
+	if err == nil {
+		return false
+	}
+	if errors.Is(err, io.EOF) || errors.Is(err, context.Canceled) {
+		return true
+	}
+	return status.Code(err) == codes.Canceled
+}
+
+// sender handles sending messages to proxy.
+// When conn.syncStream is set the message is sent as SyncMappingsResponse;
+// otherwise the legacy GetMappingUpdateResponse stream is used.
 func (s *ProxyServiceServer) sender(conn *proxyConnection, errChan chan<- error) {
 	for {
 		select {
 		case resp := <-conn.sendChan:
-			if err := conn.stream.Send(resp); err != nil {
+			if err := conn.sendResponse(resp); err != nil {
 				errChan <- err
 				return
 			}
@@ -472,6 +673,17 @@ func (s *ProxyServiceServer) sender(conn *proxyConnection, errChan chan<- error)
 	}
 }
 
+// sendResponse sends a mapping update on whichever stream the proxy connected with.
+func (conn *proxyConnection) sendResponse(resp *proto.GetMappingUpdateResponse) error {
+	if conn.syncStream != nil {
+		return conn.syncStream.Send(&proto.SyncMappingsResponse{
+			Mapping:             resp.Mapping,
+			InitialSyncComplete: resp.InitialSyncComplete,
+		})
+	}
+	return conn.stream.Send(resp)
+}
+
 // SendAccessLog processes access log from proxy
 func (s *ProxyServiceServer) SendAccessLog(ctx context.Context, req *proto.SendAccessLogRequest) (*proto.SendAccessLogResponse, error) {
 	accessLog := req.GetLog()
@@ -538,8 +750,8 @@ func (s *ProxyServiceServer) SendServiceUpdate(update *proto.GetMappingUpdateRes
 				return true
 			}
 			connUpdate = &proto.GetMappingUpdateResponse{
-				Mapping:              filtered,
-				InitialSyncComplete:  update.InitialSyncComplete,
+				Mapping:             filtered,
+				InitialSyncComplete: update.InitialSyncComplete,
 			}
 		}
 		resp := s.perProxyMessage(connUpdate, conn.proxyID)

management/internals/shared/grpc/proxy_group_access_test.go

@@ -109,7 +109,7 @@ func (m *mockReverseProxyManager) GetServiceByDomain(_ context.Context, domain s
 	return nil, errors.New("service not found for domain: " + domain)
 }
 
-func (m *mockReverseProxyManager) GetActiveClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
+func (m *mockReverseProxyManager) GetClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 

management/internals/shared/grpc/proxy_snapshot_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"testing"
+	"time"
 
 	"github.com/golang/mock/gomock"
 	"github.com/stretchr/testify/assert"
@@ -172,3 +173,55 @@ func TestSendSnapshot_EmptySnapshot(t *testing.T) {
 	assert.Empty(t, stream.messages[0].Mapping)
 	assert.True(t, stream.messages[0].InitialSyncComplete)
 }
+
+type hookingStream struct {
+	grpc.ServerStream
+	onSend func(*proto.GetMappingUpdateResponse)
+}
+
+func (s *hookingStream) Send(m *proto.GetMappingUpdateResponse) error {
+	if s.onSend != nil {
+		s.onSend(m)
+	}
+	return nil
+}
+
+func (s *hookingStream) Context() context.Context     { return context.Background() }
+func (s *hookingStream) SetHeader(metadata.MD) error  { return nil }
+func (s *hookingStream) SendHeader(metadata.MD) error { return nil }
+func (s *hookingStream) SetTrailer(metadata.MD)       {}
+func (s *hookingStream) SendMsg(any) error            { return nil }
+func (s *hookingStream) RecvMsg(any) error            { return nil }
+
+func TestSendSnapshot_TokensRemainValidUnderSlowSend(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 6
+	const ttl = 100 * time.Millisecond
+	const sendDelay = 200 * time.Millisecond
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+	s.tokenTTL = ttl
+
+	var validateErrs []error
+	stream := &hookingStream{
+		onSend: func(resp *proto.GetMappingUpdateResponse) {
+			for _, m := range resp.Mapping {
+				if err := s.tokenStore.ValidateAndConsume(m.AuthToken, m.AccountId, m.Id); err != nil {
+					validateErrs = append(validateErrs, fmt.Errorf("svc %s: %w", m.Id, err))
+				}
+			}
+			time.Sleep(sendDelay)
+		},
+	}
+	conn := &proxyConnection{proxyID: "proxy-a", address: cluster, stream: stream}
+
+	require.NoError(t, s.sendSnapshot(context.Background(), conn))
+	require.Empty(t, validateErrs,
+		"tokens must remain valid even when batches are sent slowly: lazy per-batch generation guarantees freshness")
+}

management/internals/shared/grpc/server.go

@@ -522,10 +522,11 @@ func (s *Server) sendJob(ctx context.Context, peerKey wgtypes.Key, job *job.Even
 }
 
 func (s *Server) cancelPeerRoutines(ctx context.Context, accountID string, peer *nbpeer.Peer, streamStartTime time.Time) {
-	unlock := s.acquirePeerLockByUID(ctx, peer.Key)
+	uncanceledCTX := context.WithoutCancel(ctx)
+	unlock := s.acquirePeerLockByUID(uncanceledCTX, peer.Key)
 	defer unlock()
 
-	s.cancelPeerRoutinesWithoutLock(ctx, accountID, peer, streamStartTime)
+	s.cancelPeerRoutinesWithoutLock(uncanceledCTX, accountID, peer, streamStartTime)
 }
 
 func (s *Server) cancelPeerRoutinesWithoutLock(ctx context.Context, accountID string, peer *nbpeer.Peer, streamStartTime time.Time) {
@@ -931,7 +932,31 @@ func (s *Server) sendInitialSync(ctx context.Context, peerKey wgtypes.Key, peer
 		return status.Errorf(codes.Internal, "failed to get peer groups %s", err)
 	}
 
-	plainResp := ToSyncResponse(ctx, s.config, s.config.HttpConfig, s.config.DeviceAuthorizationFlow, peer, turnToken, relayToken, networkMap, s.networkMapController.GetDNSDomain(settings), postureChecks, nil, settings, settings.Extra, peerGroups, dnsFwdPort)
+	dnsName := s.networkMapController.GetDNSDomain(settings)
+
+	var plainResp *proto.SyncResponse
+	if s.networkMapController.PeerNeedsComponents(peer) {
+		// Capable peer: discard the legacy NetworkMap that SyncAndMarkPeer
+		// computed and recompute the raw components instead. This wastes one
+		// Calculate() call per initial-sync — the component-based wire
+		// format is what the peer actually consumes. The streaming path
+		// (network_map.Controller.UpdateAccountPeers) skips this duplication
+		// because it dispatches by capability before computing.
+		//
+		// TODO(step-4-sync): refactor SyncPeer / SyncAndMarkPeer / their
+		// mocks + manager interfaces to return PeerNetworkMapResult so the
+		// initial-sync path stops doing duplicate work. ~13 files of churn,
+		// deferred until the client-side decoder lands and there's a real
+		// deployment of capability=3 peers worth optimizing for.
+		_, components, proxyPatch, _, _, err := s.networkMapController.GetValidatedPeerWithComponents(ctx, false, peer.AccountID, peer)
+		if err != nil {
+			log.WithContext(ctx).Errorf("failed to build components for peer %s on initial sync: %v", peer.ID, err)
+			return status.Errorf(codes.Internal, "failed to build initial sync envelope")
+		}
+		plainResp = ToComponentSyncResponse(ctx, s.config, s.config.HttpConfig, s.config.DeviceAuthorizationFlow, peer, turnToken, relayToken, components, proxyPatch, dnsName, postureChecks, settings, settings.Extra, peerGroups, dnsFwdPort)
+	} else {
+		plainResp = ToSyncResponse(ctx, s.config, s.config.HttpConfig, s.config.DeviceAuthorizationFlow, peer, turnToken, relayToken, networkMap, dnsName, postureChecks, nil, settings, settings.Extra, peerGroups, dnsFwdPort)
+	}
 
 	key, err := s.secretsManager.GetWGKey()
 	if err != nil {

management/internals/shared/grpc/sync_mappings_test.go

@@ -0,0 +1,411 @@
+package grpc
+
+import (
+	"context"
+	"fmt"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/golang/mock/gomock"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/metadata"
+
+	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
+	"github.com/netbirdio/netbird/shared/management/proto"
+)
+
+// syncRecordingStream is a mock ProxyService_SyncMappingsServer that records
+// sent messages and returns pre-loaded ack responses from Recv.
+type syncRecordingStream struct {
+	grpc.ServerStream
+
+	mu       sync.Mutex
+	sent     []*proto.SyncMappingsResponse
+	recvMsgs []*proto.SyncMappingsRequest
+	recvIdx  int
+}
+
+func (s *syncRecordingStream) Send(m *proto.SyncMappingsResponse) error {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.sent = append(s.sent, m)
+	return nil
+}
+
+func (s *syncRecordingStream) Recv() (*proto.SyncMappingsRequest, error) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	if s.recvIdx >= len(s.recvMsgs) {
+		return nil, fmt.Errorf("no more recv messages")
+	}
+	msg := s.recvMsgs[s.recvIdx]
+	s.recvIdx++
+	return msg, nil
+}
+
+func (s *syncRecordingStream) Context() context.Context     { return context.Background() }
+func (s *syncRecordingStream) SetHeader(metadata.MD) error  { return nil }
+func (s *syncRecordingStream) SendHeader(metadata.MD) error { return nil }
+func (s *syncRecordingStream) SetTrailer(metadata.MD)       {}
+func (s *syncRecordingStream) SendMsg(any) error            { return nil }
+func (s *syncRecordingStream) RecvMsg(any) error            { return nil }
+
+func ackMsg() *proto.SyncMappingsRequest {
+	return &proto.SyncMappingsRequest{
+		Msg: &proto.SyncMappingsRequest_Ack{Ack: &proto.SyncMappingsAck{}},
+	}
+}
+
+func TestSendSnapshotSync_BatchesWithAcks(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 3
+	const totalServices = 7 // 3 + 3 + 1 → 3 batches, 3 acks (one per batch, including final)
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{ackMsg(), ackMsg(), ackMsg()},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 3, "should send ceil(7/3) = 3 batches")
+
+	assert.Len(t, stream.sent[0].Mapping, 3)
+	assert.False(t, stream.sent[0].InitialSyncComplete)
+
+	assert.Len(t, stream.sent[1].Mapping, 3)
+	assert.False(t, stream.sent[1].InitialSyncComplete)
+
+	assert.Len(t, stream.sent[2].Mapping, 1)
+	assert.True(t, stream.sent[2].InitialSyncComplete)
+
+	// All 3 acks consumed — including the final batch.
+	assert.Equal(t, 3, stream.recvIdx)
+}
+
+func TestSendSnapshotSync_SingleBatchWaitsForAck(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 100
+	const totalServices = 5
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{ackMsg()},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 1)
+	assert.Len(t, stream.sent[0].Mapping, totalServices)
+	assert.True(t, stream.sent[0].InitialSyncComplete)
+	assert.Equal(t, 1, stream.recvIdx, "final batch ack must be consumed")
+}
+
+func TestSendSnapshotSync_EmptySnapshot(t *testing.T) {
+	const cluster = "cluster.example.com"
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(nil, nil)
+
+	s := newSnapshotTestServer(t, 500)
+	s.serviceManager = mgr
+
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{ackMsg()},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 1, "empty snapshot must still send sync-complete")
+	assert.Empty(t, stream.sent[0].Mapping)
+	assert.True(t, stream.sent[0].InitialSyncComplete)
+	assert.Equal(t, 1, stream.recvIdx, "empty snapshot ack must be consumed")
+}
+
+func TestSendSnapshotSync_MissingAckReturnsError(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 4 // 2 batches → 1 ack needed, but we provide none
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	// No acks available — Recv will return error.
+	stream := &syncRecordingStream{}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "receive ack")
+	// First batch should have been sent before the error.
+	require.Len(t, stream.sent, 1)
+}
+
+func TestSendSnapshotSync_WrongMessageInsteadOfAck(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 4
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	// Send an init message instead of an ack.
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{
+			{Msg: &proto.SyncMappingsRequest_Init{Init: &proto.SyncMappingsInit{ProxyId: "bad"}}},
+		},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "expected ack")
+}
+
+func TestSendSnapshotSync_BackPressureOrdering(t *testing.T) {
+	// Verify batches are sent strictly sequentially — batch N+1 is not sent
+	// until the ack for batch N is received, including the final batch.
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 6 // 3 batches, 3 acks
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	var mu sync.Mutex
+	var events []string
+
+	// Build a stream that logs send/recv events so we can verify ordering.
+	ackCh := make(chan struct{}, 3)
+	stream := &orderTrackingStream{
+		mu:     &mu,
+		events: &events,
+		ackCh:  ackCh,
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	// Feed acks asynchronously after a short delay to simulate real proxy.
+	go func() {
+		for range 3 {
+			time.Sleep(10 * time.Millisecond)
+			ackCh <- struct{}{}
+		}
+	}()
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	mu.Lock()
+	defer mu.Unlock()
+
+	// Expected: send, recv-ack, send, recv-ack, send, recv-ack.
+	require.Len(t, events, 6)
+	assert.Equal(t, "send", events[0])
+	assert.Equal(t, "recv", events[1])
+	assert.Equal(t, "send", events[2])
+	assert.Equal(t, "recv", events[3])
+	assert.Equal(t, "send", events[4])
+	assert.Equal(t, "recv", events[5])
+}
+
+// orderTrackingStream logs "send" and "recv" events and blocks Recv until
+// an ack is signaled via ackCh.
+type orderTrackingStream struct {
+	grpc.ServerStream
+	mu     *sync.Mutex
+	events *[]string
+	ackCh  chan struct{}
+}
+
+func (s *orderTrackingStream) Send(_ *proto.SyncMappingsResponse) error {
+	s.mu.Lock()
+	*s.events = append(*s.events, "send")
+	s.mu.Unlock()
+	return nil
+}
+
+func (s *orderTrackingStream) Recv() (*proto.SyncMappingsRequest, error) {
+	<-s.ackCh
+	s.mu.Lock()
+	*s.events = append(*s.events, "recv")
+	s.mu.Unlock()
+	return ackMsg(), nil
+}
+
+func (s *orderTrackingStream) Context() context.Context     { return context.Background() }
+func (s *orderTrackingStream) SetHeader(metadata.MD) error  { return nil }
+func (s *orderTrackingStream) SendHeader(metadata.MD) error { return nil }
+func (s *orderTrackingStream) SetTrailer(metadata.MD)       {}
+func (s *orderTrackingStream) SendMsg(any) error            { return nil }
+func (s *orderTrackingStream) RecvMsg(any) error            { return nil }
+
+func TestSendSnapshotSync_TokensGeneratedPerBatch(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 4
+	const ttl = 100 * time.Millisecond
+	const ackDelay = 200 * time.Millisecond
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+	s.tokenTTL = ttl
+
+	// Build a stream that validates tokens immediately on Send, then
+	// delays the ack to ensure the next batch's tokens are generated fresh.
+	var validateErrs []error
+	ackCh := make(chan struct{}, 2)
+	stream := &tokenValidatingSyncStream{
+		tokenStore:   s.tokenStore,
+		validateErrs: &validateErrs,
+		ackCh:        ackCh,
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	go func() {
+		// Delay first ack so that if tokens were all generated upfront they'd expire.
+		time.Sleep(ackDelay)
+		ackCh <- struct{}{}
+		// Final batch ack — immediate.
+		ackCh <- struct{}{}
+	}()
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+	require.Empty(t, validateErrs,
+		"tokens must remain valid: per-batch generation guarantees freshness")
+}
+
+type tokenValidatingSyncStream struct {
+	grpc.ServerStream
+	tokenStore   *OneTimeTokenStore
+	validateErrs *[]error
+	ackCh        chan struct{}
+}
+
+func (s *tokenValidatingSyncStream) Send(m *proto.SyncMappingsResponse) error {
+	for _, mapping := range m.Mapping {
+		if err := s.tokenStore.ValidateAndConsume(mapping.AuthToken, mapping.AccountId, mapping.Id); err != nil {
+			*s.validateErrs = append(*s.validateErrs, fmt.Errorf("svc %s: %w", mapping.Id, err))
+		}
+	}
+	return nil
+}
+
+func (s *tokenValidatingSyncStream) Recv() (*proto.SyncMappingsRequest, error) {
+	<-s.ackCh
+	return ackMsg(), nil
+}
+
+func (s *tokenValidatingSyncStream) Context() context.Context     { return context.Background() }
+func (s *tokenValidatingSyncStream) SetHeader(metadata.MD) error  { return nil }
+func (s *tokenValidatingSyncStream) SendHeader(metadata.MD) error { return nil }
+func (s *tokenValidatingSyncStream) SetTrailer(metadata.MD)       {}
+func (s *tokenValidatingSyncStream) SendMsg(any) error            { return nil }
+func (s *tokenValidatingSyncStream) RecvMsg(any) error            { return nil }
+
+func TestConnectionSendResponse_RoutesToSyncStream(t *testing.T) {
+	stream := &syncRecordingStream{}
+	conn := &proxyConnection{
+		syncStream: stream,
+	}
+
+	resp := &proto.GetMappingUpdateResponse{
+		Mapping: []*proto.ProxyMapping{
+			{Id: "svc-1", AccountId: "acct-1", Domain: "example.com"},
+		},
+		InitialSyncComplete: true,
+	}
+
+	err := conn.sendResponse(resp)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 1)
+	assert.Len(t, stream.sent[0].Mapping, 1)
+	assert.Equal(t, "svc-1", stream.sent[0].Mapping[0].Id)
+	assert.True(t, stream.sent[0].InitialSyncComplete)
+}
+
+func TestConnectionSendResponse_RoutesToLegacyStream(t *testing.T) {
+	stream := &recordingStream{}
+	conn := &proxyConnection{
+		stream: stream,
+	}
+
+	resp := &proto.GetMappingUpdateResponse{
+		Mapping: []*proto.ProxyMapping{
+			{Id: "svc-2", AccountId: "acct-2"},
+		},
+	}
+
+	err := conn.sendResponse(resp)
+	require.NoError(t, err)
+
+	require.Len(t, stream.messages, 1)
+	assert.Equal(t, "svc-2", stream.messages[0].Mapping[0].Id)
+}

management/internals/shared/grpc/validate_session_test.go

@@ -322,21 +322,29 @@ func (m *testValidateSessionServiceManager) GetServiceByDomain(ctx context.Conte
 	return m.store.GetServiceByDomain(ctx, domain)
 }
 
-func (m *testValidateSessionServiceManager) GetActiveClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
+func (m *testValidateSessionServiceManager) GetClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 
+func (m *testValidateSessionServiceManager) DeleteAccountCluster(_ context.Context, _, _, _ string) error {
+	return nil
+}
+
 type testValidateSessionProxyManager struct{}
 
-func (m *testValidateSessionProxyManager) Connect(_ context.Context, _, _, _ string, _ *string, _ *proxy.Capabilities) error {
+func (m *testValidateSessionProxyManager) Connect(_ context.Context, _, _, _, _ string, _ *string, _ *proxy.Capabilities) (*proxy.Proxy, error) {
+	return nil, nil
+}
+
+func (m *testValidateSessionProxyManager) Disconnect(_ context.Context, _, _ string) error {
 	return nil
 }
 
-func (m *testValidateSessionProxyManager) Disconnect(_ context.Context, _ string) error {
+func (m *testValidateSessionProxyManager) Heartbeat(_ context.Context, _ *proxy.Proxy) error {
 	return nil
 }
 
-func (m *testValidateSessionProxyManager) Heartbeat(_ context.Context, _, _, _ string) error {
+func (m *testValidateSessionProxyManager) DeleteAccountCluster(_ context.Context, _, _ string) error {
 	return nil
 }
 

management/server/account.go

@@ -291,10 +291,15 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 		return nil, status.NewPermissionDeniedError()
 	}
 
+	// Canonicalize the incoming range so a caller-supplied prefix with host bits
+	// (e.g. 100.64.1.1/16) compares equal to the masked form stored on network.Net.
+	newSettings.NetworkRange = newSettings.NetworkRange.Masked()
+
 	var oldSettings *types.Settings
 	var updateAccountPeers bool
 	var groupChangesAffectPeers bool
 	var reloadReverseProxy bool
+	var effectiveOldNetworkRange netip.Prefix
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		var groupsUpdated bool
@@ -308,6 +313,16 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 			return err
 		}
 
+		// No lock: the transaction already holds Settings(Update), and network.Net is
+		// only mutated by reallocateAccountPeerIPs, which is reachable only through
+		// this same code path. A Share lock here would extend an unnecessary row lock
+		// and complicate ordering against updatePeerIPv6InTransaction.
+		network, err := transaction.GetAccountNetwork(ctx, store.LockingStrengthNone, accountID)
+		if err != nil {
+			return fmt.Errorf("get account network: %w", err)
+		}
+		effectiveOldNetworkRange = prefixFromIPNet(network.Net)
+
 		if oldSettings.Extra != nil && newSettings.Extra != nil &&
 			oldSettings.Extra.PeerApprovalEnabled && !newSettings.Extra.PeerApprovalEnabled {
 			approvedCount, err := transaction.ApproveAccountPeers(ctx, accountID)
@@ -321,7 +336,7 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 			}
 		}
 
-		if oldSettings.NetworkRange != newSettings.NetworkRange {
+		if newSettings.NetworkRange.IsValid() && newSettings.NetworkRange != effectiveOldNetworkRange {
 			if err = am.reallocateAccountPeerIPs(ctx, transaction, accountID, newSettings.NetworkRange); err != nil {
 				return err
 			}
@@ -396,9 +411,9 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 		}
 		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountDNSDomainUpdated, eventMeta)
 	}
-	if oldSettings.NetworkRange != newSettings.NetworkRange {
+	if newSettings.NetworkRange.IsValid() && newSettings.NetworkRange != effectiveOldNetworkRange {
 		eventMeta := map[string]any{
-			"old_network_range": oldSettings.NetworkRange.String(),
+			"old_network_range": effectiveOldNetworkRange.String(),
 			"new_network_range": newSettings.NetworkRange.String(),
 		}
 		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountNetworkRangeUpdated, eventMeta)
@@ -443,6 +458,22 @@ func ipv6SettingsChanged(old, updated *types.Settings) bool {
 	return !slices.Equal(oldGroups, newGroups)
 }
 
+// prefixFromIPNet returns the overlay prefix actually allocated on the account
+// network, or an invalid prefix if none is set. Settings.NetworkRange is a
+// user-facing override that is empty on legacy accounts, so the effective
+// range must be read from network.Net to compare against an incoming update.
+func prefixFromIPNet(ipNet net.IPNet) netip.Prefix {
+	if ipNet.IP == nil {
+		return netip.Prefix{}
+	}
+	addr, ok := netip.AddrFromSlice(ipNet.IP)
+	if !ok {
+		return netip.Prefix{}
+	}
+	ones, _ := ipNet.Mask.Size()
+	return netip.PrefixFrom(addr.Unmap(), ones)
+}
+
 func (am *DefaultAccountManager) validateSettingsUpdate(ctx context.Context, transaction store.Store, newSettings, oldSettings *types.Settings, userID, accountID string) error {
 	halfYearLimit := 180 * 24 * time.Hour
 	if newSettings.PeerLoginExpiration > halfYearLimit {
@@ -1590,6 +1621,14 @@ func (am *DefaultAccountManager) SyncUserJWTGroups(ctx context.Context, userAuth
 			return nil
 		}
 
+		for _, g := range newGroupsToCreate {
+			seq, err := transaction.AllocateAccountSeqID(ctx, userAuth.AccountId, types.AccountSeqEntityGroup)
+			if err != nil {
+				return fmt.Errorf("error allocating group seq id: %w", err)
+			}
+			g.AccountSeqID = seq
+		}
+
 		if err = transaction.CreateGroups(ctx, userAuth.AccountId, newGroupsToCreate); err != nil {
 			return fmt.Errorf("error saving groups: %w", err)
 		}
@@ -1837,35 +1876,32 @@ func domainIsUpToDate(domain string, domainCategory string, userAuth auth.UserAu
 	return domainCategory == types.PrivateCategory || userAuth.DomainCategory != types.PrivateCategory || domain != userAuth.Domain
 }
 
+// SyncAndMarkPeer is the per-Sync entry point: it refreshes the peer's
+// network map and then marks the peer connected with a session token
+// derived from syncTime (the moment the gRPC stream opened). Any
+// concurrent stream that started earlier loses the optimistic-lock race
+// in MarkPeerConnected and bails without writing.
 func (am *DefaultAccountManager) SyncAndMarkPeer(ctx context.Context, accountID string, peerPubKey string, meta nbpeer.PeerSystemMeta, realIP net.IP, syncTime time.Time) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error) {
 	peer, netMap, postureChecks, dnsfwdPort, err := am.SyncPeer(ctx, types.PeerSync{WireGuardPubKey: peerPubKey, Meta: meta}, accountID)
 	if err != nil {
 		return nil, nil, nil, 0, fmt.Errorf("error syncing peer: %w", err)
 	}
 
-	err = am.MarkPeerConnected(ctx, peerPubKey, true, realIP, accountID, syncTime)
-	if err != nil {
+	if err := am.MarkPeerConnected(ctx, peerPubKey, realIP, accountID, syncTime.UnixNano()); err != nil {
 		log.WithContext(ctx).Warnf("failed marking peer as connected %s %v", peerPubKey, err)
 	}
 
 	return peer, netMap, postureChecks, dnsfwdPort, nil
 }
 
+// OnPeerDisconnected is invoked when a sync stream ends. It marks the
+// peer disconnected only when the stored SessionStartedAt matches the
+// nanosecond token derived from streamStartTime — i.e. only when this
+// is the stream that currently owns the peer's session. A mismatch
+// means a newer stream has already replaced us, so the disconnect is
+// dropped.
 func (am *DefaultAccountManager) OnPeerDisconnected(ctx context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
-	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
-	if err != nil {
-		log.WithContext(ctx).Warnf("failed to get peer %s for disconnect check: %v", peerPubKey, err)
-		return nil
-	}
-
-	if peer.Status.LastSeen.After(streamStartTime) {
-		log.WithContext(ctx).Tracef("peer %s has newer activity (lastSeen=%s > streamStart=%s), skipping disconnect",
-			peerPubKey, peer.Status.LastSeen.Format(time.RFC3339), streamStartTime.Format(time.RFC3339))
-		return nil
-	}
-
-	err = am.MarkPeerConnected(ctx, peerPubKey, false, nil, accountID, time.Now().UTC())
-	if err != nil {
+	if err := am.MarkPeerDisconnected(ctx, peerPubKey, accountID, streamStartTime.UnixNano()); err != nil {
 		log.WithContext(ctx).Warnf("failed marking peer as disconnected %s %v", peerPubKey, err)
 	}
 	return nil
@@ -2487,6 +2523,18 @@ func (am *DefaultAccountManager) buildIPv6AllowedPeers(ctx context.Context, tran
 			allowedPeers[peerID] = struct{}{}
 		}
 	}
+
+	// Embedded proxy peers sit outside regular group membership but must
+	// participate in any v6-enabled overlay to reach v6-only peers.
+	peers, err := transaction.GetAccountPeers(ctx, store.LockingStrengthNone, accountID, "", "")
+	if err != nil {
+		return nil, fmt.Errorf("get peers: %w", err)
+	}
+	for _, p := range peers {
+		if p.ProxyMeta.Embedded {
+			allowedPeers[p.ID] = struct{}{}
+		}
+	}
 	return allowedPeers, nil
 }
 
@@ -2522,7 +2570,9 @@ func (am *DefaultAccountManager) UpdatePeerIP(ctx context.Context, accountID, us
 		if err != nil {
 			return err
 		}
-		err = am.networkMapController.OnPeersUpdated(ctx, peer.AccountID, []string{peerID})
+		changedPeerIDs := []string{peerID}
+		affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+		err = am.networkMapController.OnPeersUpdated(ctx, peer.AccountID, changedPeerIDs, affectedPeerIDs)
 		if err != nil {
 			return fmt.Errorf("notify network map controller of peer update: %w", err)
 		}
@@ -2613,7 +2663,9 @@ func (am *DefaultAccountManager) UpdatePeerIPv6(ctx context.Context, accountID,
 	}
 
 	if updateNetworkMap {
-		if err := am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peerID}); err != nil {
+		changedPeerIDs := []string{peerID}
+		affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+		if err := am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs); err != nil {
 			return fmt.Errorf("notify network map controller: %w", err)
 		}
 	}

management/server/account/manager.go

@@ -61,7 +61,8 @@ type Manager interface {
 	GetUserFromUserAuth(ctx context.Context, userAuth auth.UserAuth) (*types.User, error)
 	ListUsers(ctx context.Context, accountID string) ([]*types.User, error)
 	GetPeers(ctx context.Context, accountID, userID, nameFilter, ipFilter string) ([]*nbpeer.Peer, error)
-	MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error
+	MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error
+	MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error
 	DeletePeer(ctx context.Context, accountID, peerID, userID string) error
 	UpdatePeer(ctx context.Context, accountID, userID string, p *nbpeer.Peer) (*nbpeer.Peer, error)
 	UpdatePeerIP(ctx context.Context, accountID, userID, peerID string, newIP netip.Addr) error
@@ -126,6 +127,8 @@ type Manager interface {
 	GetAccountSettings(ctx context.Context, accountID string, userID string) (*types.Settings, error)
 	DeleteSetupKey(ctx context.Context, accountID, userID, keyID string) error
 	UpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason)
+	UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string)
+	BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason)
 	BufferUpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason)
 	BuildUserInfosForAccount(ctx context.Context, accountID, initiatorUserID string, accountUsers []*types.User) (map[string]*types.UserInfo, error)
 	SyncUserJWTGroups(ctx context.Context, userAuth auth.UserAuth) error

management/server/account/manager_mock.go

@@ -122,6 +122,18 @@ func (mr *MockManagerMockRecorder) BufferUpdateAccountPeers(ctx, accountID, reas
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "BufferUpdateAccountPeers", reflect.TypeOf((*MockManager)(nil).BufferUpdateAccountPeers), ctx, accountID, reason)
 }
 
+// BufferUpdateAffectedPeers mocks base method.
+func (m *MockManager) BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason) {
+	m.ctrl.T.Helper()
+	m.ctrl.Call(m, "BufferUpdateAffectedPeers", ctx, accountID, peerIDs, reason)
+}
+
+// BufferUpdateAffectedPeers indicates an expected call of BufferUpdateAffectedPeers.
+func (mr *MockManagerMockRecorder) BufferUpdateAffectedPeers(ctx, accountID, peerIDs, reason interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "BufferUpdateAffectedPeers", reflect.TypeOf((*MockManager)(nil).BufferUpdateAffectedPeers), ctx, accountID, peerIDs, reason)
+}
+
 // BuildUserInfosForAccount mocks base method.
 func (m *MockManager) BuildUserInfosForAccount(ctx context.Context, accountID, initiatorUserID string, accountUsers []*types.User) (map[string]*types.UserInfo, error) {
 	m.ctrl.T.Helper()
@@ -1305,17 +1317,31 @@ func (mr *MockManagerMockRecorder) LoginPeer(ctx, login interface{}) *gomock.Cal
 }
 
 // MarkPeerConnected mocks base method.
-func (m *MockManager) MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
+func (m *MockManager) MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "MarkPeerConnected", ctx, peerKey, connected, realIP, accountID, syncTime)
+	ret := m.ctrl.Call(m, "MarkPeerConnected", ctx, peerKey, realIP, accountID, sessionStartedAt)
 	ret0, _ := ret[0].(error)
 	return ret0
 }
 
 // MarkPeerConnected indicates an expected call of MarkPeerConnected.
-func (mr *MockManagerMockRecorder) MarkPeerConnected(ctx, peerKey, connected, realIP, accountID, syncTime interface{}) *gomock.Call {
+func (mr *MockManagerMockRecorder) MarkPeerConnected(ctx, peerKey, realIP, accountID, sessionStartedAt interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerConnected", reflect.TypeOf((*MockManager)(nil).MarkPeerConnected), ctx, peerKey, connected, realIP, accountID, syncTime)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerConnected", reflect.TypeOf((*MockManager)(nil).MarkPeerConnected), ctx, peerKey, realIP, accountID, sessionStartedAt)
+}
+
+// MarkPeerDisconnected mocks base method.
+func (m *MockManager) MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "MarkPeerDisconnected", ctx, peerKey, accountID, sessionStartedAt)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// MarkPeerDisconnected indicates an expected call of MarkPeerDisconnected.
+func (mr *MockManagerMockRecorder) MarkPeerDisconnected(ctx, peerKey, accountID, sessionStartedAt interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerDisconnected", reflect.TypeOf((*MockManager)(nil).MarkPeerDisconnected), ctx, peerKey, accountID, sessionStartedAt)
 }
 
 // OnPeerDisconnected mocks base method.
@@ -1608,6 +1634,18 @@ func (mr *MockManagerMockRecorder) UpdateAccountPeers(ctx, accountID, reason int
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "UpdateAccountPeers", reflect.TypeOf((*MockManager)(nil).UpdateAccountPeers), ctx, accountID, reason)
 }
 
+// UpdateAffectedPeers mocks base method.
+func (m *MockManager) UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string) {
+	m.ctrl.T.Helper()
+	m.ctrl.Call(m, "UpdateAffectedPeers", ctx, accountID, peerIDs)
+}
+
+// UpdateAffectedPeers indicates an expected call of UpdateAffectedPeers.
+func (mr *MockManagerMockRecorder) UpdateAffectedPeers(ctx, accountID, peerIDs interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "UpdateAffectedPeers", reflect.TypeOf((*MockManager)(nil).UpdateAffectedPeers), ctx, accountID, peerIDs)
+}
+
 // UpdateAccountSettings mocks base method.
 func (m *MockManager) UpdateAccountSettings(ctx context.Context, accountID, userID string, newSettings *types.Settings) (*types.Settings, error) {
 	m.ctrl.T.Helper()

management/server/account_test.go

@@ -1813,7 +1813,7 @@ func TestDefaultAccountManager_UpdatePeer_PeerLoginExpiration(t *testing.T) {
 	accountID, err := manager.GetAccountIDByUserID(context.Background(), auth.UserAuth{UserId: userID})
 	require.NoError(t, err, "unable to get the account")
 
-	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), true, nil, accountID, time.Now().UTC())
+	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), nil, accountID, time.Now().UTC().UnixNano())
 	require.NoError(t, err, "unable to mark peer connected")
 
 	_, err = manager.UpdateAccountSettings(context.Background(), accountID, userID, &types.Settings{
@@ -1884,7 +1884,7 @@ func TestDefaultAccountManager_MarkPeerConnected_PeerLoginExpiration(t *testing.
 	require.NoError(t, err, "unable to get the account")
 
 	// when we mark peer as connected, the peer login expiration routine should trigger
-	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), true, nil, accountID, time.Now().UTC())
+	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), nil, accountID, time.Now().UTC().UnixNano())
 	require.NoError(t, err, "unable to mark peer connected")
 
 	failed := waitTimeout(wg, time.Second)
@@ -1910,15 +1910,16 @@ func TestDefaultAccountManager_OnPeerDisconnected_LastSeenCheck(t *testing.T) {
 	}, false)
 	require.NoError(t, err, "unable to add peer")
 
-	t.Run("disconnect peer when streamStartTime is after LastSeen", func(t *testing.T) {
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, time.Now().UTC())
+	t.Run("disconnect peer when session token matches", func(t *testing.T) {
+		streamStartTime := time.Now().UTC()
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, streamStartTime.UnixNano())
 		require.NoError(t, err, "unable to mark peer connected")
 
 		peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err, "unable to get peer")
 		require.True(t, peer.Status.Connected, "peer should be connected")
-
-		streamStartTime := time.Now().UTC()
+		require.Equal(t, streamStartTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should equal the token we passed in")
 
 		err = manager.OnPeerDisconnected(context.Background(), accountID, peerPubKey, streamStartTime)
 		require.NoError(t, err)
@@ -1926,49 +1927,127 @@ func TestDefaultAccountManager_OnPeerDisconnected_LastSeenCheck(t *testing.T) {
 		peer, err = manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.False(t, peer.Status.Connected, "peer should be disconnected")
+		require.Equal(t, int64(0), peer.Status.SessionStartedAt, "SessionStartedAt should be reset to 0")
 	})
 
-	t.Run("skip disconnect when LastSeen is after streamStartTime (zombie stream protection)", func(t *testing.T) {
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, time.Now().UTC())
+	t.Run("skip disconnect when stored session is newer (zombie stream protection)", func(t *testing.T) {
+		// Newer stream wins on connect (sets SessionStartedAt = now ns).
+		streamStartTime := time.Now().UTC()
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, streamStartTime.UnixNano())
 		require.NoError(t, err, "unable to mark peer connected")
 
 		peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected, "peer should be connected")
 
-		streamStartTime := peer.Status.LastSeen.Add(-1 * time.Hour)
+		// Older stream tries to mark disconnect with its own (older) session token —
+		// fencing kicks in and the write is dropped.
+		staleStreamStartTime := streamStartTime.Add(-1 * time.Hour)
 
-		err = manager.OnPeerDisconnected(context.Background(), accountID, peerPubKey, streamStartTime)
+		err = manager.OnPeerDisconnected(context.Background(), accountID, peerPubKey, staleStreamStartTime)
 		require.NoError(t, err)
 
 		peer, err = manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected,
-			"peer should remain connected because LastSeen > streamStartTime (zombie stream protection)")
+			"peer should remain connected because the stored session is newer than the disconnect token")
+		require.Equal(t, streamStartTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should still hold the winning stream's token")
 	})
 
-	t.Run("skip stale connect when peer already has newer LastSeen (blocked goroutine protection)", func(t *testing.T) {
+	t.Run("skip stale connect when stored session is newer (blocked goroutine protection)", func(t *testing.T) {
 		node2SyncTime := time.Now().UTC()
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, node2SyncTime)
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, node2SyncTime.UnixNano())
 		require.NoError(t, err, "node 2 should connect peer")
 
 		peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected, "peer should be connected")
-		require.Equal(t, node2SyncTime.Unix(), peer.Status.LastSeen.Unix(), "LastSeen should be node2SyncTime")
+		require.Equal(t, node2SyncTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should equal node2SyncTime token")
 
 		node1StaleSyncTime := node2SyncTime.Add(-1 * time.Minute)
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, node1StaleSyncTime)
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, node1StaleSyncTime.UnixNano())
 		require.NoError(t, err, "stale connect should not return error")
 
 		peer, err = manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected, "peer should still be connected")
-		require.Equal(t, node2SyncTime.Unix(), peer.Status.LastSeen.Unix(),
-			"LastSeen should NOT be overwritten by stale syncTime from blocked goroutine")
+		require.Equal(t, node2SyncTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should NOT be overwritten by stale token from blocked goroutine")
 	})
 }
 
+// TestDefaultAccountManager_MarkPeerConnected_ConcurrentRace exercises the
+// fencing protocol under contention: many goroutines race to mark the
+// same peer connected with distinct session tokens at the same time.
+// The contract is that the highest token always wins and is what remains
+// in the store, regardless of execution order.
+func TestDefaultAccountManager_MarkPeerConnected_ConcurrentRace(t *testing.T) {
+	manager, _, err := createManager(t)
+	require.NoError(t, err, "unable to create account manager")
+
+	accountID, err := manager.GetAccountIDByUserID(context.Background(), auth.UserAuth{UserId: userID})
+	require.NoError(t, err, "unable to get account")
+
+	key, err := wgtypes.GenerateKey()
+	require.NoError(t, err, "unable to generate WireGuard key")
+	peerPubKey := key.PublicKey().String()
+
+	_, _, _, err = manager.AddPeer(context.Background(), "", "", userID, &nbpeer.Peer{
+		Key:  peerPubKey,
+		Meta: nbpeer.PeerSystemMeta{Hostname: "race-peer"},
+	}, false)
+	require.NoError(t, err, "unable to add peer")
+
+	const workers = 16
+	base := time.Now().UTC().UnixNano()
+	tokens := make([]int64, workers)
+	for i := range tokens {
+		// Spread tokens by 1ms so the comparison is unambiguous; the
+		// largest is index workers-1.
+		tokens[i] = base + int64(i)*int64(time.Millisecond)
+	}
+	expected := tokens[workers-1]
+
+	var ready sync.WaitGroup
+	ready.Add(workers)
+	var start sync.WaitGroup
+	start.Add(1)
+	var done sync.WaitGroup
+	done.Add(workers)
+
+	// require.* calls t.FailNow which is documented as unsafe from
+	// non-test goroutines (it calls runtime.Goexit on the wrong stack and
+	// races with the WaitGroup). Collect errors here and assert from the
+	// main goroutine after done.Wait().
+	errs := make(chan error, workers)
+
+	for i := 0; i < workers; i++ {
+		token := tokens[i]
+		go func() {
+			defer done.Done()
+			ready.Done()
+			start.Wait()
+			errs <- manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, token)
+		}()
+	}
+
+	ready.Wait()
+	start.Done()
+	done.Wait()
+	close(errs)
+	for err := range errs {
+		require.NoError(t, err, "MarkPeerConnected must not error under contention")
+	}
+
+	peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
+	require.NoError(t, err)
+	require.True(t, peer.Status.Connected, "peer should be connected after the race")
+	require.Equal(t, expected, peer.Status.SessionStartedAt,
+		"the largest token must win regardless of execution order")
+}
+
 func TestDefaultAccountManager_UpdateAccountSettings_PeerLoginExpiration(t *testing.T) {
 	manager, _, err := createManager(t)
 	require.NoError(t, err, "unable to create account manager")
@@ -1991,7 +2070,7 @@ func TestDefaultAccountManager_UpdateAccountSettings_PeerLoginExpiration(t *test
 	account, err := manager.Store.GetAccount(context.Background(), accountID)
 	require.NoError(t, err, "unable to get the account")
 
-	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), true, nil, accountID, time.Now().UTC())
+	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), nil, accountID, time.Now().UTC().UnixNano())
 	require.NoError(t, err, "unable to mark peer connected")
 
 	wg := &sync.WaitGroup{}
@@ -2957,6 +3036,16 @@ func TestAccount_SetJWTGroups(t *testing.T) {
 		user, err := manager.Store.GetUserByUserID(context.Background(), store.LockingStrengthNone, "user2")
 		assert.NoError(t, err, "unable to get user")
 		assert.Len(t, user.AutoGroups, 1, "new group should be added")
+
+		var newJWTGroup *types.Group
+		for _, g := range groups {
+			if g.Name == "group3" {
+				newJWTGroup = g
+				break
+			}
+		}
+		require.NotNil(t, newJWTGroup, "JIT-created JWT group not found")
+		assert.NotZero(t, newJWTGroup.AccountSeqID, "JIT-created JWT group must have a non-zero AccountSeqID")
 	})
 
 	t.Run("remove all JWT groups when list is empty", func(t *testing.T) {
@@ -3203,6 +3292,16 @@ func setupNetworkMapTest(t *testing.T) (*DefaultAccountManager, *update_channel.
 // when the channel delivers.
 const peerUpdateTimeout = 5 * time.Second
 
+func drainPeerUpdates(ch <-chan *network_map.UpdateMessage) {
+	for {
+		select {
+		case <-ch:
+		case <-time.After(200 * time.Millisecond):
+			return
+		}
+	}
+}
+
 func peerShouldNotReceiveUpdate(t *testing.T, updateMessage <-chan *network_map.UpdateMessage) {
 	t.Helper()
 	select {
@@ -3970,6 +4069,96 @@ func TestDefaultAccountManager_UpdateAccountSettings_NetworkRangeChange(t *testi
 	}
 }
 
+// TestDefaultAccountManager_UpdateAccountSettings_NetworkRangePreserved guards against
+// peer IP reallocation when a settings update carries the network range that is already
+// in use. Legacy accounts have Settings.NetworkRange unset in the DB while network.Net
+// holds the actual allocated overlay; the dashboard backfills the GET response from
+// network.Net and echoes the value back on PUT, so the diff must be against the
+// effective range to avoid renumbering every peer on an unrelated settings change.
+func TestDefaultAccountManager_UpdateAccountSettings_NetworkRangePreserved(t *testing.T) {
+	manager, _, account, peer1, peer2, peer3 := setupNetworkMapTest(t)
+	ctx := context.Background()
+
+	settings, err := manager.Store.GetAccountSettings(ctx, store.LockingStrengthNone, account.Id)
+	require.NoError(t, err)
+	require.False(t, settings.NetworkRange.IsValid(), "precondition: new accounts leave Settings.NetworkRange unset")
+
+	network, err := manager.Store.GetAccountNetwork(ctx, store.LockingStrengthNone, account.Id)
+	require.NoError(t, err)
+	require.NotNil(t, network.Net.IP, "precondition: network.Net should be allocated")
+	addr, ok := netip.AddrFromSlice(network.Net.IP)
+	require.True(t, ok)
+	ones, _ := network.Net.Mask.Size()
+	effective := netip.PrefixFrom(addr.Unmap(), ones)
+	require.True(t, effective.IsValid())
+
+	before := map[string]netip.Addr{peer1.ID: peer1.IP, peer2.ID: peer2.IP, peer3.ID: peer3.IP}
+
+	// Round-trip the effective range as if the dashboard echoed back the GET-backfilled value.
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		NetworkRange:               effective,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err := manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	require.Len(t, peers, len(before))
+	for _, p := range peers {
+		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change when range matches effective", p.ID)
+	}
+
+	// Carrying the same range with host bits set must also be a no-op once canonicalized.
+	hostBitsForm := netip.PrefixFrom(peer1.IP, ones)
+	require.NotEqual(t, effective, hostBitsForm, "precondition: host-bit form should differ before masking")
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		NetworkRange:               hostBitsForm,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	for _, p := range peers {
+		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change for host-bit-set equivalent range", p.ID)
+	}
+
+	// Omitting NetworkRange (invalid prefix) must also be a no-op.
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	for _, p := range peers {
+		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change when NetworkRange omitted", p.ID)
+	}
+
+	// Sanity: an actually different range still triggers reallocation.
+	newRange := netip.MustParsePrefix("100.99.0.0/16")
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		NetworkRange:               newRange,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	for _, p := range peers {
+		assert.True(t, newRange.Contains(p.IP), "peer %s should be in new range %s, got %s", p.ID, newRange, p.IP)
+		assert.NotEqual(t, before[p.ID], p.IP, "peer %s IP should change on real range update", p.ID)
+	}
+}
+
 func TestDefaultAccountManager_UpdateAccountSettings_IPv6EnabledGroups(t *testing.T) {
 	manager, _, account, peer1, peer2, peer3 := setupNetworkMapTest(t)
 	ctx := context.Background()

management/server/affected_groups.go

@@ -0,0 +1,223 @@
+package server
+
+import (
+	"context"
+
+	log "github.com/sirupsen/logrus"
+
+	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
+	"github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/types"
+	"github.com/netbirdio/netbird/route"
+)
+
+// collectPeerChangeAffectedGroups walks policies, routes, nameservers, DNS settings,
+// and network routers to collect all group IDs and direct peer IDs affected by the
+// changed groups and/or changed peers. Each collection is fetched from the store exactly once.
+func collectPeerChangeAffectedGroups(ctx context.Context, transaction store.Store, accountID string, changedGroupIDs, changedPeerIDs []string) (allGroupIDs []string, directPeerIDs []string) {
+	if len(changedGroupIDs) == 0 && len(changedPeerIDs) == 0 {
+		return nil, nil
+	}
+
+	changedGroupSet := toSet(changedGroupIDs)
+	changedPeerSet := toSet(changedPeerIDs)
+
+	groupSet := make(map[string]struct{})
+	peerSet := make(map[string]struct{})
+
+	collectAffectedFromPolicies(ctx, transaction, accountID, changedGroupSet, changedPeerSet, groupSet, peerSet)
+	collectAffectedFromRoutes(ctx, transaction, accountID, changedGroupSet, changedPeerSet, groupSet, peerSet)
+	collectAffectedFromNameServers(ctx, transaction, accountID, changedGroupSet, groupSet)
+	collectAffectedFromDNSSettings(ctx, transaction, accountID, changedGroupSet, groupSet)
+	collectAffectedFromNetworkRouters(ctx, transaction, accountID, changedGroupSet, changedPeerSet, groupSet, peerSet)
+
+	allGroupIDs = setToSlice(groupSet)
+	directPeerIDs = setToSlice(peerSet)
+
+	log.WithContext(ctx).Tracef("affected groups resolution: changedGroups=%v changedPeers=%v -> affectedGroups=%v, directPeers=%v",
+		changedGroupIDs, changedPeerIDs, allGroupIDs, directPeerIDs)
+
+	return allGroupIDs, directPeerIDs
+}
+
+// collectGroupChangeAffectedGroups is a convenience wrapper used by callers that only have changed groups.
+func collectGroupChangeAffectedGroups(ctx context.Context, transaction store.Store, accountID string, changedGroupIDs []string) ([]string, []string) {
+	return collectPeerChangeAffectedGroups(ctx, transaction, accountID, changedGroupIDs, nil)
+}
+
+func collectAffectedFromPolicies(ctx context.Context, transaction store.Store, accountID string, changedGroupSet, changedPeerSet map[string]struct{}, groupSet, peerSet map[string]struct{}) {
+	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get policies for affected group resolution: %v", err)
+		return
+	}
+
+	for _, policy := range policies {
+		matchedByGroup := policyReferencesGroups(policy, changedGroupSet)
+		matchedByPeer := len(changedPeerSet) > 0 && policyReferencesDirectPeers(policy, changedPeerSet)
+		if !matchedByGroup && !matchedByPeer {
+			continue
+		}
+		addAllToSet(groupSet, policy.RuleGroups())
+		collectPolicyDirectPeers(policy, peerSet)
+	}
+}
+
+func collectAffectedFromRoutes(ctx context.Context, transaction store.Store, accountID string, changedGroupSet, changedPeerSet map[string]struct{}, groupSet, peerSet map[string]struct{}) {
+	routes, err := transaction.GetAccountRoutes(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get routes for affected group resolution: %v", err)
+		return
+	}
+
+	for _, r := range routes {
+		matchedByGroup := routeReferencesGroups(r, changedGroupSet)
+		matchedByPeer := r.Peer != "" && len(changedPeerSet) > 0 && isInSet(r.Peer, changedPeerSet)
+		if !matchedByGroup && !matchedByPeer {
+			continue
+		}
+		addAllToSet(groupSet, r.Groups, r.PeerGroups, r.AccessControlGroups)
+		if r.Peer != "" {
+			peerSet[r.Peer] = struct{}{}
+		}
+	}
+}
+
+func collectAffectedFromNameServers(ctx context.Context, transaction store.Store, accountID string, changedGroupSet map[string]struct{}, groupSet map[string]struct{}) {
+	if len(changedGroupSet) == 0 {
+		return
+	}
+
+	nsGroups, err := transaction.GetAccountNameServerGroups(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get nameserver groups for affected group resolution: %v", err)
+		return
+	}
+
+	for _, ns := range nsGroups {
+		if anyInSet(ns.Groups, changedGroupSet) {
+			addAllToSet(groupSet, ns.Groups)
+		}
+	}
+}
+
+func collectAffectedFromDNSSettings(ctx context.Context, transaction store.Store, accountID string, changedGroupSet map[string]struct{}, groupSet map[string]struct{}) {
+	if len(changedGroupSet) == 0 {
+		return
+	}
+
+	dnsSettings, err := transaction.GetAccountDNSSettings(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get DNS settings for affected group resolution: %v", err)
+		return
+	}
+
+	for _, gID := range dnsSettings.DisabledManagementGroups {
+		if _, ok := changedGroupSet[gID]; ok {
+			groupSet[gID] = struct{}{}
+		}
+	}
+}
+
+func collectAffectedFromNetworkRouters(ctx context.Context, transaction store.Store, accountID string, changedGroupSet, changedPeerSet map[string]struct{}, groupSet, peerSet map[string]struct{}) {
+	routers, err := transaction.GetNetworkRoutersByAccountID(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get network routers for affected group resolution: %v", err)
+		return
+	}
+
+	for _, router := range routers {
+		matchedByGroup := routerReferencesGroups(router, changedGroupSet)
+		matchedByPeer := router.Peer != "" && len(changedPeerSet) > 0 && isInSet(router.Peer, changedPeerSet)
+		if !matchedByGroup && !matchedByPeer {
+			continue
+		}
+		addAllToSet(groupSet, router.PeerGroups)
+		if router.Peer != "" {
+			peerSet[router.Peer] = struct{}{}
+		}
+	}
+}
+
+func collectPolicyDirectPeers(policy *types.Policy, peerSet map[string]struct{}) {
+	for _, rule := range policy.Rules {
+		if rule.SourceResource.Type == types.ResourceTypePeer && rule.SourceResource.ID != "" {
+			peerSet[rule.SourceResource.ID] = struct{}{}
+		}
+		if rule.DestinationResource.Type == types.ResourceTypePeer && rule.DestinationResource.ID != "" {
+			peerSet[rule.DestinationResource.ID] = struct{}{}
+		}
+	}
+}
+
+func policyReferencesGroups(policy *types.Policy, groupSet map[string]struct{}) bool {
+	for _, rule := range policy.Rules {
+		if anyInSet(rule.Sources, groupSet) || anyInSet(rule.Destinations, groupSet) {
+			return true
+		}
+	}
+	return false
+}
+
+func policyReferencesDirectPeers(policy *types.Policy, changedSet map[string]struct{}) bool {
+	for _, rule := range policy.Rules {
+		if isDirectPeerInSet(rule.SourceResource, changedSet) || isDirectPeerInSet(rule.DestinationResource, changedSet) {
+			return true
+		}
+	}
+	return false
+}
+
+func isDirectPeerInSet(res types.Resource, set map[string]struct{}) bool {
+	if res.Type != types.ResourceTypePeer || res.ID == "" {
+		return false
+	}
+	_, ok := set[res.ID]
+	return ok
+}
+
+func routeReferencesGroups(r *route.Route, groupSet map[string]struct{}) bool {
+	return anyInSet(r.Groups, groupSet) || anyInSet(r.PeerGroups, groupSet) || anyInSet(r.AccessControlGroups, groupSet)
+}
+
+func routerReferencesGroups(router *routerTypes.NetworkRouter, groupSet map[string]struct{}) bool {
+	return anyInSet(router.PeerGroups, groupSet)
+}
+
+func anyInSet(ids []string, set map[string]struct{}) bool {
+	for _, id := range ids {
+		if _, ok := set[id]; ok {
+			return true
+		}
+	}
+	return false
+}
+
+func isInSet(id string, set map[string]struct{}) bool {
+	_, ok := set[id]
+	return ok
+}
+
+func addAllToSet(set map[string]struct{}, slices ...[]string) {
+	for _, s := range slices {
+		for _, id := range s {
+			set[id] = struct{}{}
+		}
+	}
+}
+
+func toSet(ids []string) map[string]struct{} {
+	set := make(map[string]struct{}, len(ids))
+	for _, id := range ids {
+		set[id] = struct{}{}
+	}
+	return set
+}
+
+func setToSlice(set map[string]struct{}) []string {
+	s := make([]string, 0, len(set))
+	for id := range set {
+		s = append(s, id)
+	}
+	return s
+}

management/server/dns.go

@@ -47,8 +47,8 @@ func (am *DefaultAccountManager) SaveDNSSettings(ctx context.Context, accountID
 		return status.NewPermissionDeniedError()
 	}
 
-	var updateAccountPeers bool
 	var eventsToStore []func()
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err = validateDNSSettings(ctx, transaction, accountID, dnsSettingsToSave); err != nil {
@@ -63,11 +63,6 @@ func (am *DefaultAccountManager) SaveDNSSettings(ctx context.Context, accountID
 		addedGroups := util.Difference(dnsSettingsToSave.DisabledManagementGroups, oldSettings.DisabledManagementGroups)
 		removedGroups := util.Difference(oldSettings.DisabledManagementGroups, dnsSettingsToSave.DisabledManagementGroups)
 
-		updateAccountPeers, err = areDNSSettingChangesAffectPeers(ctx, transaction, accountID, addedGroups, removedGroups)
-		if err != nil {
-			return err
-		}
-
 		events := am.prepareDNSSettingsEvents(ctx, transaction, accountID, userID, addedGroups, removedGroups)
 		eventsToStore = append(eventsToStore, events...)
 
@@ -75,6 +70,9 @@ func (am *DefaultAccountManager) SaveDNSSettings(ctx context.Context, accountID
 			return err
 		}
 
+		allGroups := slices.Concat(addedGroups, removedGroups)
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, allGroups, nil)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
@@ -85,8 +83,11 @@ func (am *DefaultAccountManager) SaveDNSSettings(ctx context.Context, accountID
 		storeEvent()
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceDNSSettings, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("SaveDNSSettings: updating %d affected peers: %v", len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("SaveDNSSettings: no affected peers")
 	}
 
 	return nil
@@ -133,20 +134,6 @@ func (am *DefaultAccountManager) prepareDNSSettingsEvents(ctx context.Context, t
 	return eventsToStore
 }
 
-// areDNSSettingChangesAffectPeers checks if the DNS settings changes affect any peers.
-func areDNSSettingChangesAffectPeers(ctx context.Context, transaction store.Store, accountID string, addedGroups, removedGroups []string) (bool, error) {
-	hasPeers, err := anyGroupHasPeersOrResources(ctx, transaction, accountID, addedGroups)
-	if err != nil {
-		return false, err
-	}
-
-	if hasPeers {
-		return true, nil
-	}
-
-	return anyGroupHasPeersOrResources(ctx, transaction, accountID, removedGroups)
-}
-
 // validateDNSSettings validates the DNS settings.
 func validateDNSSettings(ctx context.Context, transaction store.Store, accountID string, settings *types.DNSSettings) error {
 	if len(settings.DisabledManagementGroups) == 0 {

management/server/group.go

@@ -9,15 +9,12 @@ import (
 	"github.com/rs/xid"
 	log "github.com/sirupsen/logrus"
 
-	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/management/server/activity"
-	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
 	"github.com/netbirdio/netbird/management/server/permissions/operations"
 	"github.com/netbirdio/netbird/management/server/store"
 	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/management/server/util"
-	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
@@ -79,7 +76,7 @@ func (am *DefaultAccountManager) CreateGroup(ctx context.Context, accountID, use
 	}
 
 	var eventsToStore []func()
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err = validateNewGroup(ctx, transaction, accountID, newGroup); err != nil {
@@ -91,10 +88,11 @@ func (am *DefaultAccountManager) CreateGroup(ctx context.Context, accountID, use
 		events := am.prepareGroupEvents(ctx, transaction, accountID, userID, newGroup)
 		eventsToStore = append(eventsToStore, events...)
 
-		updateAccountPeers, err = areGroupChangesAffectPeers(ctx, transaction, accountID, []string{newGroup.ID})
+		seq, err := transaction.AllocateAccountSeqID(ctx, accountID, types.AccountSeqEntityGroup)
 		if err != nil {
-			return err
+			return status.Errorf(status.Internal, "failed to allocate group seq id: %v", err)
 		}
+		newGroup.AccountSeqID = seq
 
 		if err := transaction.CreateGroup(ctx, newGroup); err != nil {
 			return status.Errorf(status.Internal, "failed to create group: %v", err)
@@ -106,6 +104,9 @@ func (am *DefaultAccountManager) CreateGroup(ctx context.Context, accountID, use
 			}
 		}
 
+		groupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, transaction, accountID, []string{newGroup.ID})
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, groupIDs, directPeerIDs)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
@@ -116,8 +117,11 @@ func (am *DefaultAccountManager) CreateGroup(ctx context.Context, accountID, use
 		storeEvent()
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationCreate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("CreateGroup %s: updating %d affected peers: %v", newGroup.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("CreateGroup %s: no affected peers", newGroup.ID)
 	}
 
 	return nil
@@ -134,7 +138,7 @@ func (am *DefaultAccountManager) UpdateGroup(ctx context.Context, accountID, use
 	}
 
 	var eventsToStore []func()
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err = validateNewGroup(ctx, transaction, accountID, newGroup); err != nil {
@@ -165,10 +169,7 @@ func (am *DefaultAccountManager) UpdateGroup(ctx context.Context, accountID, use
 			}
 		}
 
-		updateAccountPeers, err = areGroupChangesAffectPeers(ctx, transaction, accountID, []string{newGroup.ID})
-		if err != nil {
-			return err
-		}
+		newGroup.AccountSeqID = oldGroup.AccountSeqID
 
 		if err = transaction.UpdateGroup(ctx, newGroup); err != nil {
 			return err
@@ -178,6 +179,9 @@ func (am *DefaultAccountManager) UpdateGroup(ctx context.Context, accountID, use
 			return err
 		}
 
+		groupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, transaction, accountID, []string{newGroup.ID})
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, groupIDs, directPeerIDs)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
@@ -188,8 +192,11 @@ func (am *DefaultAccountManager) UpdateGroup(ctx context.Context, accountID, use
 		storeEvent()
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("UpdateGroup %s: updating %d affected peers: %v", newGroup.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("UpdateGroup %s: no affected peers", newGroup.ID)
 	}
 
 	return nil
@@ -209,7 +216,6 @@ func (am *DefaultAccountManager) CreateGroups(ctx context.Context, accountID, us
 	}
 
 	var eventsToStore []func()
-	var updateAccountPeers bool
 
 	var globalErr error
 	groupIDs := make([]string, 0, len(groups))
@@ -221,6 +227,12 @@ func (am *DefaultAccountManager) CreateGroups(ctx context.Context, accountID, us
 
 			newGroup.AccountID = accountID
 
+			seq, err := transaction.AllocateAccountSeqID(ctx, accountID, types.AccountSeqEntityGroup)
+			if err != nil {
+				return err
+			}
+			newGroup.AccountSeqID = seq
+
 			if err = transaction.CreateGroup(ctx, newGroup); err != nil {
 				return err
 			}
@@ -247,17 +259,17 @@ func (am *DefaultAccountManager) CreateGroups(ctx context.Context, accountID, us
 		}
 	}
 
-	updateAccountPeers, err = areGroupChangesAffectPeers(ctx, am.Store, accountID, groupIDs)
-	if err != nil {
-		return err
-	}
-
 	for _, storeEvent := range eventsToStore {
 		storeEvent()
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationCreate})
+	allGroupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, am.Store, accountID, groupIDs)
+	affectedPeerIDs := am.resolvePeerIDs(ctx, am.Store, accountID, allGroupIDs, directPeerIDs)
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("CreateGroups %v: updating %d affected peers: %v", groupIDs, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("CreateGroups %v: no affected peers", groupIDs)
 	}
 
 	return globalErr
@@ -277,7 +289,6 @@ func (am *DefaultAccountManager) UpdateGroups(ctx context.Context, accountID, us
 	}
 
 	var eventsToStore []func()
-	var updateAccountPeers bool
 
 	var globalErr error
 	groupIDs := make([]string, 0, len(groups))
@@ -295,17 +306,17 @@ func (am *DefaultAccountManager) UpdateGroups(ctx context.Context, accountID, us
 		groupIDs = append(groupIDs, newGroup.ID)
 	}
 
-	updateAccountPeers, err = areGroupChangesAffectPeers(ctx, am.Store, accountID, groupIDs)
-	if err != nil {
-		return err
-	}
-
 	for _, storeEvent := range eventsToStore {
 		storeEvent()
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationUpdate})
+	allGroupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, am.Store, accountID, groupIDs)
+	affectedPeerIDs := am.resolvePeerIDs(ctx, am.Store, accountID, allGroupIDs, directPeerIDs)
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("UpdateGroups %v: updating %d affected peers: %v", groupIDs, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("UpdateGroups %v: no affected peers", groupIDs)
 	}
 
 	return globalErr
@@ -320,6 +331,12 @@ func (am *DefaultAccountManager) updateSingleGroup(ctx context.Context, accountI
 
 		newGroup.AccountID = accountID
 
+		oldGroup, err := transaction.GetGroupByID(ctx, store.LockingStrengthNone, accountID, newGroup.ID)
+		if err != nil {
+			return err
+		}
+		newGroup.AccountSeqID = oldGroup.AccountSeqID
+
 		if err := transaction.UpdateGroup(ctx, newGroup); err != nil {
 			return err
 		}
@@ -488,15 +505,10 @@ func (am *DefaultAccountManager) DeleteGroups(ctx context.Context, accountID, us
 
 // GroupAddPeer appends peer to the group
 func (am *DefaultAccountManager) GroupAddPeer(ctx context.Context, accountID, groupID, peerID string) error {
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 	var err error
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		updateAccountPeers, err = areGroupChangesAffectPeers(ctx, transaction, accountID, []string{groupID})
-		if err != nil {
-			return err
-		}
-
 		if err = transaction.AddPeerToGroup(ctx, accountID, peerID, groupID); err != nil {
 			return err
 		}
@@ -505,14 +517,20 @@ func (am *DefaultAccountManager) GroupAddPeer(ctx context.Context, accountID, gr
 			return err
 		}
 
+		allGroupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, transaction, accountID, []string{groupID})
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, allGroupIDs, directPeerIDs)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
 		return err
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("GroupAddPeer group=%s peer=%s: updating %d affected peers: %v", groupID, peerID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("GroupAddPeer group=%s peer=%s: no affected peers", groupID, peerID)
 	}
 
 	return nil
@@ -521,7 +539,7 @@ func (am *DefaultAccountManager) GroupAddPeer(ctx context.Context, accountID, gr
 // GroupAddResource appends resource to the group
 func (am *DefaultAccountManager) GroupAddResource(ctx context.Context, accountID, groupID string, resource types.Resource) error {
 	var group *types.Group
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 	var err error
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
@@ -534,23 +552,24 @@ func (am *DefaultAccountManager) GroupAddResource(ctx context.Context, accountID
 			return nil
 		}
 
-		updateAccountPeers, err = areGroupChangesAffectPeers(ctx, transaction, accountID, []string{groupID})
-		if err != nil {
-			return err
-		}
-
 		if err = transaction.UpdateGroup(ctx, group); err != nil {
 			return err
 		}
 
+		allGroupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, transaction, accountID, []string{groupID})
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, allGroupIDs, directPeerIDs)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
 		return err
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("GroupAddResource group=%s resource=%s: updating %d affected peers: %v", groupID, resource.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("GroupAddResource group=%s resource=%s: no affected peers", groupID, resource.ID)
 	}
 
 	return nil
@@ -558,14 +577,13 @@ func (am *DefaultAccountManager) GroupAddResource(ctx context.Context, accountID
 
 // GroupDeletePeer removes peer from the group
 func (am *DefaultAccountManager) GroupDeletePeer(ctx context.Context, accountID, groupID, peerID string) error {
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 	var err error
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		updateAccountPeers, err = areGroupChangesAffectPeers(ctx, transaction, accountID, []string{groupID})
-		if err != nil {
-			return err
-		}
+		// Resolve before removing, so the peer being removed is still included
+		allGroupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, transaction, accountID, []string{groupID})
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, allGroupIDs, directPeerIDs)
 
 		if err = transaction.RemovePeerFromGroup(ctx, peerID, groupID); err != nil {
 			return err
@@ -581,8 +599,11 @@ func (am *DefaultAccountManager) GroupDeletePeer(ctx context.Context, accountID,
 		return err
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("GroupDeletePeer group=%s peer=%s: updating %d affected peers: %v", groupID, peerID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("GroupDeletePeer group=%s peer=%s: no affected peers", groupID, peerID)
 	}
 
 	return nil
@@ -591,7 +612,7 @@ func (am *DefaultAccountManager) GroupDeletePeer(ctx context.Context, accountID,
 // GroupDeleteResource removes resource from the group
 func (am *DefaultAccountManager) GroupDeleteResource(ctx context.Context, accountID, groupID string, resource types.Resource) error {
 	var group *types.Group
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 	var err error
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
@@ -604,23 +625,24 @@ func (am *DefaultAccountManager) GroupDeleteResource(ctx context.Context, accoun
 			return nil
 		}
 
-		updateAccountPeers, err = areGroupChangesAffectPeers(ctx, transaction, accountID, []string{groupID})
-		if err != nil {
-			return err
-		}
-
 		if err = transaction.UpdateGroup(ctx, group); err != nil {
 			return err
 		}
 
+		allGroupIDs, directPeerIDs := collectGroupChangeAffectedGroups(ctx, transaction, accountID, []string{groupID})
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, allGroupIDs, directPeerIDs)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
 		return err
 	}
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceGroup, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("GroupDeleteResource group=%s resource=%s: updating %d affected peers: %v", groupID, resource.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("GroupDeleteResource group=%s resource=%s: no affected peers", groupID, resource.ID)
 	}
 
 	return nil
@@ -651,230 +673,3 @@ func validateNewGroup(ctx context.Context, transaction store.Store, accountID st
 
 	return nil
 }
-
-func validateDeleteGroup(ctx context.Context, transaction store.Store, group *types.Group, userID string, flowGroups []string) error {
-	// disable a deleting integration group if the initiator is not an admin service user
-	if group.Issued == types.GroupIssuedIntegration {
-		executingUser, err := transaction.GetUserByUserID(ctx, store.LockingStrengthNone, userID)
-		if err != nil {
-			return status.Errorf(status.Internal, "failed to get user")
-		}
-		if executingUser.Role != types.UserRoleAdmin || !executingUser.IsServiceUser {
-			return status.Errorf(status.PermissionDenied, "only service users with admin power can delete integration group")
-		}
-	}
-
-	if group.IsGroupAll() {
-		return status.Errorf(status.InvalidArgument, "deleting group ALL is not allowed")
-	}
-
-	if len(group.Resources) > 0 {
-		return &GroupLinkError{"network resource", group.Resources[0].ID}
-	}
-
-	if slices.Contains(flowGroups, group.ID) {
-		return &GroupLinkError{"settings", "traffic event logging"}
-	}
-
-	if isLinked, linkedRoute := isGroupLinkedToRoute(ctx, transaction, group.AccountID, group.ID); isLinked {
-		return &GroupLinkError{"route", string(linkedRoute.NetID)}
-	}
-
-	if isLinked, linkedDns := isGroupLinkedToDns(ctx, transaction, group.AccountID, group.ID); isLinked {
-		return &GroupLinkError{"name server groups", linkedDns.Name}
-	}
-
-	if isLinked, linkedPolicy := isGroupLinkedToPolicy(ctx, transaction, group.AccountID, group.ID); isLinked {
-		return &GroupLinkError{"policy", linkedPolicy.Name}
-	}
-
-	if isLinked, linkedSetupKey := isGroupLinkedToSetupKey(ctx, transaction, group.AccountID, group.ID); isLinked {
-		return &GroupLinkError{"setup key", linkedSetupKey.Name}
-	}
-
-	if isLinked, linkedUser := isGroupLinkedToUser(ctx, transaction, group.AccountID, group.ID); isLinked {
-		return &GroupLinkError{"user", linkedUser.Id}
-	}
-
-	if isLinked, linkedRouter := isGroupLinkedToNetworkRouter(ctx, transaction, group.AccountID, group.ID); isLinked {
-		return &GroupLinkError{"network router", linkedRouter.ID}
-	}
-
-	return checkGroupLinkedToSettings(ctx, transaction, group)
-}
-
-// checkGroupLinkedToSettings verifies if a group is linked to any settings in the account.
-func checkGroupLinkedToSettings(ctx context.Context, transaction store.Store, group *types.Group) error {
-	dnsSettings, err := transaction.GetAccountDNSSettings(ctx, store.LockingStrengthNone, group.AccountID)
-	if err != nil {
-		return status.Errorf(status.Internal, "failed to get DNS settings")
-	}
-
-	if slices.Contains(dnsSettings.DisabledManagementGroups, group.ID) {
-		return &GroupLinkError{"disabled DNS management groups", group.Name}
-	}
-
-	settings, err := transaction.GetAccountSettings(ctx, store.LockingStrengthNone, group.AccountID)
-	if err != nil {
-		return status.Errorf(status.Internal, "failed to get account settings")
-	}
-
-	if settings.Extra != nil && slices.Contains(settings.Extra.IntegratedValidatorGroups, group.ID) {
-		return &GroupLinkError{"integrated validator", group.Name}
-	}
-
-	return nil
-}
-
-// isGroupLinkedToRoute checks if a group is linked to any route in the account.
-func isGroupLinkedToRoute(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *route.Route) {
-	routes, err := transaction.GetAccountRoutes(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		log.WithContext(ctx).Errorf("error retrieving routes while checking group linkage: %v", err)
-		return false, nil
-	}
-
-	for _, r := range routes {
-		isLinked := slices.Contains(r.Groups, groupID) ||
-			slices.Contains(r.PeerGroups, groupID) ||
-			slices.Contains(r.AccessControlGroups, groupID)
-		if isLinked {
-			return true, r
-		}
-	}
-
-	return false, nil
-}
-
-// isGroupLinkedToPolicy checks if a group is linked to any policy in the account.
-func isGroupLinkedToPolicy(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *types.Policy) {
-	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		log.WithContext(ctx).Errorf("error retrieving policies while checking group linkage: %v", err)
-		return false, nil
-	}
-
-	for _, policy := range policies {
-		for _, rule := range policy.Rules {
-			if slices.Contains(rule.Sources, groupID) || slices.Contains(rule.Destinations, groupID) {
-				return true, policy
-			}
-		}
-	}
-	return false, nil
-}
-
-// isGroupLinkedToDns checks if a group is linked to any nameserver group in the account.
-func isGroupLinkedToDns(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *nbdns.NameServerGroup) {
-	nameServerGroups, err := transaction.GetAccountNameServerGroups(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		log.WithContext(ctx).Errorf("error retrieving name server groups while checking group linkage: %v", err)
-		return false, nil
-	}
-
-	for _, dns := range nameServerGroups {
-		for _, g := range dns.Groups {
-			if g == groupID {
-				return true, dns
-			}
-		}
-	}
-
-	return false, nil
-}
-
-// isGroupLinkedToSetupKey checks if a group is linked to any setup key in the account.
-func isGroupLinkedToSetupKey(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *types.SetupKey) {
-	setupKeys, err := transaction.GetAccountSetupKeys(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		log.WithContext(ctx).Errorf("error retrieving setup keys while checking group linkage: %v", err)
-		return false, nil
-	}
-
-	for _, setupKey := range setupKeys {
-		if slices.Contains(setupKey.AutoGroups, groupID) {
-			return true, setupKey
-		}
-	}
-	return false, nil
-}
-
-// isGroupLinkedToUser checks if a group is linked to any user in the account.
-func isGroupLinkedToUser(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *types.User) {
-	users, err := transaction.GetAccountUsers(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		log.WithContext(ctx).Errorf("error retrieving users while checking group linkage: %v", err)
-		return false, nil
-	}
-
-	for _, user := range users {
-		if slices.Contains(user.AutoGroups, groupID) {
-			return true, user
-		}
-	}
-	return false, nil
-}
-
-// isGroupLinkedToNetworkRouter checks if a group is linked to any network router in the account.
-func isGroupLinkedToNetworkRouter(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *routerTypes.NetworkRouter) {
-	routers, err := transaction.GetNetworkRoutersByAccountID(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		log.WithContext(ctx).Errorf("error retrieving network routers while checking group linkage: %v", err)
-		return false, nil
-	}
-
-	for _, router := range routers {
-		if slices.Contains(router.PeerGroups, groupID) {
-			return true, router
-		}
-	}
-	return false, nil
-}
-
-// areGroupChangesAffectPeers checks if any changes to the specified groups will affect peers.
-func areGroupChangesAffectPeers(ctx context.Context, transaction store.Store, accountID string, groupIDs []string) (bool, error) {
-	if len(groupIDs) == 0 {
-		return false, nil
-	}
-
-	dnsSettings, err := transaction.GetAccountDNSSettings(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		return false, err
-	}
-
-	for _, groupID := range groupIDs {
-		if slices.Contains(dnsSettings.DisabledManagementGroups, groupID) {
-			return true, nil
-		}
-		if linked, _ := isGroupLinkedToDns(ctx, transaction, accountID, groupID); linked {
-			return true, nil
-		}
-		if linked, _ := isGroupLinkedToPolicy(ctx, transaction, accountID, groupID); linked {
-			return true, nil
-		}
-		if linked, _ := isGroupLinkedToRoute(ctx, transaction, accountID, groupID); linked {
-			return true, nil
-		}
-		if linked, _ := isGroupLinkedToNetworkRouter(ctx, transaction, accountID, groupID); linked {
-			return true, nil
-		}
-	}
-
-	return false, nil
-}
-
-// anyGroupHasPeersOrResources checks if any of the given groups in the account have peers or resources.
-func anyGroupHasPeersOrResources(ctx context.Context, transaction store.Store, accountID string, groupIDs []string) (bool, error) {
-	groups, err := transaction.GetGroupsByIDs(ctx, store.LockingStrengthNone, accountID, groupIDs)
-	if err != nil {
-		return false, err
-	}
-
-	for _, group := range groups {
-		if group.HasPeers() || group.HasResources() {
-			return true, nil
-		}
-	}
-
-	return false, nil
-}

management/server/group_linkage.go

@@ -0,0 +1,287 @@
+package server
+
+import (
+	"context"
+	"slices"
+
+	log "github.com/sirupsen/logrus"
+
+	nbdns "github.com/netbirdio/netbird/dns"
+	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
+	"github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/types"
+	"github.com/netbirdio/netbird/route"
+	"github.com/netbirdio/netbird/shared/management/status"
+)
+
+func validateDeleteGroup(ctx context.Context, transaction store.Store, group *types.Group, userID string, flowGroups []string) error {
+	// disable a deleting integration group if the initiator is not an admin service user
+	if group.Issued == types.GroupIssuedIntegration {
+		executingUser, err := transaction.GetUserByUserID(ctx, store.LockingStrengthNone, userID)
+		if err != nil {
+			return status.Errorf(status.Internal, "failed to get user")
+		}
+		if executingUser.Role != types.UserRoleAdmin || !executingUser.IsServiceUser {
+			return status.Errorf(status.PermissionDenied, "only service users with admin power can delete integration group")
+		}
+	}
+
+	if group.IsGroupAll() {
+		return status.Errorf(status.InvalidArgument, "deleting group ALL is not allowed")
+	}
+
+	if len(group.Resources) > 0 {
+		return &GroupLinkError{"network resource", group.Resources[0].ID}
+	}
+
+	if slices.Contains(flowGroups, group.ID) {
+		return &GroupLinkError{"settings", "traffic event logging"}
+	}
+
+	if isLinked, linkedRoute := isGroupLinkedToRoute(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"route", string(linkedRoute.NetID)}
+	}
+
+	if isLinked, linkedDns := isGroupLinkedToDns(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"name server groups", linkedDns.Name}
+	}
+
+	if isLinked, linkedPolicy := isGroupLinkedToPolicy(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"policy", linkedPolicy.Name}
+	}
+
+	if isLinked, linkedSetupKey := isGroupLinkedToSetupKey(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"setup key", linkedSetupKey.Name}
+	}
+
+	if isLinked, linkedUser := isGroupLinkedToUser(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"user", linkedUser.Id}
+	}
+
+	if isLinked, linkedRouter := isGroupLinkedToNetworkRouter(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"network router", linkedRouter.ID}
+	}
+
+	return checkGroupLinkedToSettings(ctx, transaction, group)
+}
+
+// checkGroupLinkedToSettings verifies if a group is linked to any settings in the account.
+func checkGroupLinkedToSettings(ctx context.Context, transaction store.Store, group *types.Group) error {
+	dnsSettings, err := transaction.GetAccountDNSSettings(ctx, store.LockingStrengthNone, group.AccountID)
+	if err != nil {
+		return status.Errorf(status.Internal, "failed to get DNS settings")
+	}
+
+	if slices.Contains(dnsSettings.DisabledManagementGroups, group.ID) {
+		return &GroupLinkError{"disabled DNS management groups", group.Name}
+	}
+
+	settings, err := transaction.GetAccountSettings(ctx, store.LockingStrengthNone, group.AccountID)
+	if err != nil {
+		return status.Errorf(status.Internal, "failed to get account settings")
+	}
+
+	if settings.Extra != nil && slices.Contains(settings.Extra.IntegratedValidatorGroups, group.ID) {
+		return &GroupLinkError{"integrated validator", group.Name}
+	}
+
+	return nil
+}
+
+// isGroupLinkedToRoute checks if a group is linked to any route in the account.
+func isGroupLinkedToRoute(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *route.Route) {
+	routes, err := transaction.GetAccountRoutes(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving routes while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, r := range routes {
+		isLinked := slices.Contains(r.Groups, groupID) ||
+			slices.Contains(r.PeerGroups, groupID) ||
+			slices.Contains(r.AccessControlGroups, groupID)
+		if isLinked {
+			return true, r
+		}
+	}
+
+	return false, nil
+}
+
+// isGroupLinkedToPolicy checks if a group is linked to any policy in the account.
+func isGroupLinkedToPolicy(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *types.Policy) {
+	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving policies while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, policy := range policies {
+		for _, rule := range policy.Rules {
+			if slices.Contains(rule.Sources, groupID) || slices.Contains(rule.Destinations, groupID) {
+				return true, policy
+			}
+		}
+	}
+	return false, nil
+}
+
+// isGroupLinkedToDns checks if a group is linked to any nameserver group in the account.
+func isGroupLinkedToDns(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *nbdns.NameServerGroup) {
+	nameServerGroups, err := transaction.GetAccountNameServerGroups(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving name server groups while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, dns := range nameServerGroups {
+		for _, g := range dns.Groups {
+			if g == groupID {
+				return true, dns
+			}
+		}
+	}
+
+	return false, nil
+}
+
+// isGroupLinkedToSetupKey checks if a group is linked to any setup key in the account.
+func isGroupLinkedToSetupKey(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *types.SetupKey) {
+	setupKeys, err := transaction.GetAccountSetupKeys(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving setup keys while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, setupKey := range setupKeys {
+		if slices.Contains(setupKey.AutoGroups, groupID) {
+			return true, setupKey
+		}
+	}
+	return false, nil
+}
+
+// isGroupLinkedToUser checks if a group is linked to any user in the account.
+func isGroupLinkedToUser(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *types.User) {
+	users, err := transaction.GetAccountUsers(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving users while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, user := range users {
+		if slices.Contains(user.AutoGroups, groupID) {
+			return true, user
+		}
+	}
+	return false, nil
+}
+
+// isGroupLinkedToNetworkRouter checks if a group is linked to any network router in the account.
+func isGroupLinkedToNetworkRouter(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *routerTypes.NetworkRouter) {
+	routers, err := transaction.GetNetworkRoutersByAccountID(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving network routers while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, router := range routers {
+		if slices.Contains(router.PeerGroups, groupID) {
+			return true, router
+		}
+	}
+	return false, nil
+}
+
+// areGroupChangesAffectPeers checks if any changes to the specified groups will affect peers.
+// It fetches each collection once and checks all groupIDs against them in memory.
+func areGroupChangesAffectPeers(ctx context.Context, transaction store.Store, accountID string, groupIDs []string) (bool, error) {
+	if len(groupIDs) == 0 {
+		return false, nil
+	}
+
+	groupSet := make(map[string]struct{}, len(groupIDs))
+	for _, id := range groupIDs {
+		groupSet[id] = struct{}{}
+	}
+
+	if affected, err := dnsSettingsReferenceGroups(ctx, transaction, accountID, groupSet); affected || err != nil {
+		return affected, err
+	}
+	if affected, err := nameServersReferenceGroups(ctx, transaction, accountID, groupSet); affected || err != nil {
+		return affected, err
+	}
+	if affected, err := policiesReferenceGroups(ctx, transaction, accountID, groupSet); affected || err != nil {
+		return affected, err
+	}
+	if affected, err := routesReferenceGroups(ctx, transaction, accountID, groupSet); affected || err != nil {
+		return affected, err
+	}
+	if affected, err := networkRoutersReferenceGroups(ctx, transaction, accountID, groupSet); affected || err != nil {
+		return affected, err
+	}
+
+	return false, nil
+}
+
+func dnsSettingsReferenceGroups(ctx context.Context, transaction store.Store, accountID string, groupSet map[string]struct{}) (bool, error) {
+	dnsSettings, err := transaction.GetAccountDNSSettings(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		return false, err
+	}
+	return anyInSet(dnsSettings.DisabledManagementGroups, groupSet), nil
+}
+
+func nameServersReferenceGroups(ctx context.Context, transaction store.Store, accountID string, groupSet map[string]struct{}) (bool, error) {
+	nameServerGroups, err := transaction.GetAccountNameServerGroups(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		return false, err
+	}
+	for _, ns := range nameServerGroups {
+		if anyInSet(ns.Groups, groupSet) {
+			return true, nil
+		}
+	}
+	return false, nil
+}
+
+func policiesReferenceGroups(ctx context.Context, transaction store.Store, accountID string, groupSet map[string]struct{}) (bool, error) {
+	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		return false, err
+	}
+	for _, policy := range policies {
+		for _, rule := range policy.Rules {
+			if anyInSet(rule.Sources, groupSet) || anyInSet(rule.Destinations, groupSet) {
+				return true, nil
+			}
+		}
+	}
+	return false, nil
+}
+
+func routesReferenceGroups(ctx context.Context, transaction store.Store, accountID string, groupSet map[string]struct{}) (bool, error) {
+	routes, err := transaction.GetAccountRoutes(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		return false, err
+	}
+	for _, r := range routes {
+		if anyInSet(r.Groups, groupSet) || anyInSet(r.PeerGroups, groupSet) || anyInSet(r.AccessControlGroups, groupSet) {
+			return true, nil
+		}
+	}
+	return false, nil
+}
+
+func networkRoutersReferenceGroups(ctx context.Context, transaction store.Store, accountID string, groupSet map[string]struct{}) (bool, error) {
+	routers, err := transaction.GetNetworkRoutersByAccountID(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		return false, err
+	}
+	for _, router := range routers {
+		if anyInSet(router.PeerGroups, groupSet) {
+			return true, nil
+		}
+	}
+	return false, nil
+}

management/server/http/handlers/proxy/auth_callback_integration_test.go

@@ -444,7 +444,7 @@ func (m *testServiceManager) GetServiceByDomain(ctx context.Context, domain stri
 	return m.store.GetServiceByDomain(ctx, domain)
 }
 
-func (m *testServiceManager) GetActiveClusters(_ context.Context, _, _ string) ([]nbproxy.Cluster, error) {
+func (m *testServiceManager) GetClusters(_ context.Context, _, _ string) ([]nbproxy.Cluster, error) {
 	return nil, nil
 }
 

management/server/http/testing/integration/networks_handler_integration_test.go

@@ -1319,7 +1319,7 @@ func Test_NetworkRouters_Update(t *testing.T) {
 			},
 		},
 		{
-			name:      "Update non-existing router creates it",
+			name:      "Update non-existing router returns not found",
 			networkId: "testNetworkId",
 			routerId:  "nonExistingRouterId",
 			requestBody: &api.NetworkRouterRequest{
@@ -1328,11 +1328,7 @@ func Test_NetworkRouters_Update(t *testing.T) {
 				Metric:     100,
 				Enabled:    true,
 			},
-			expectedStatus: http.StatusOK,
-			verifyResponse: func(t *testing.T, router *api.NetworkRouter) {
-				t.Helper()
-				assert.Equal(t, "nonExistingRouterId", router.Id)
-			},
+			expectedStatus: http.StatusNotFound,
 		},
 		{
 			name:      "Update router with both peer and peer_groups",

management/server/idp/embedded.go

@@ -6,7 +6,9 @@ import (
 	"errors"
 	"fmt"
 	"net/http"
+	"net/url"
 	"os"
+	"path"
 	"strings"
 
 	"github.com/dexidp/dex/storage"
@@ -138,10 +140,13 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 		return nil, fmt.Errorf("invalid IdP storage config: %w", err)
 	}
 
-	// Build CLI redirect URIs including the device callback (both relative and absolute)
+	// Build CLI redirect URIs including the device callback. Dex uses the issuer-relative
+	// path (for example, /oauth2/device/callback) when completing the device flow, so
+	// include it explicitly in addition to the legacy bare path and absolute URL.
 	cliRedirectURIs := c.CLIRedirectURIs
 	cliRedirectURIs = append(cliRedirectURIs, "/device/callback")
-	cliRedirectURIs = append(cliRedirectURIs, c.Issuer+"/device/callback")
+	cliRedirectURIs = append(cliRedirectURIs, issuerRelativeDeviceCallback(c.Issuer))
+	cliRedirectURIs = append(cliRedirectURIs, strings.TrimSuffix(c.Issuer, "/")+"/device/callback")
 
 	// Build dashboard redirect URIs including the OAuth callback for proxy authentication
 	dashboardRedirectURIs := c.DashboardRedirectURIs
@@ -154,6 +159,10 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 	// MGMT api and the dashboard, adding baseURL means less configuration for the instance admin
 	dashboardPostLogoutRedirectURIs = append(dashboardPostLogoutRedirectURIs, baseURL)
 
+	redirectURIs := make([]string, 0)
+	redirectURIs = append(redirectURIs, cliRedirectURIs...)
+	redirectURIs = append(redirectURIs, dashboardRedirectURIs...)
+
 	cfg := &dex.YAMLConfig{
 		Issuer: c.Issuer,
 		Storage: dex.Storage{
@@ -179,14 +188,14 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 				ID:                     staticClientDashboard,
 				Name:                   "NetBird Dashboard",
 				Public:                 true,
-				RedirectURIs:           dashboardRedirectURIs,
+				RedirectURIs:           redirectURIs,
 				PostLogoutRedirectURIs: sanitizePostLogoutRedirectURIs(dashboardPostLogoutRedirectURIs),
 			},
 			{
 				ID:           staticClientCLI,
 				Name:         "NetBird CLI",
 				Public:       true,
-				RedirectURIs: cliRedirectURIs,
+				RedirectURIs: redirectURIs,
 			},
 		},
 		StaticConnectors: c.StaticConnectors,
@@ -217,6 +226,14 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 	return cfg, nil
 }
 
+func issuerRelativeDeviceCallback(issuer string) string {
+	u, err := url.Parse(issuer)
+	if err != nil || u.Path == "" {
+		return "/device/callback"
+	}
+	return path.Join(u.Path, "/device/callback")
+}
+
 // Due to how the frontend generates the logout, sometimes it appends a trailing slash
 // and because Dex only allows exact matches, we need to make sure we always have both
 // versions of each provided uri
@@ -299,7 +316,7 @@ func resolveSessionCookieEncryptionKey(configuredKey string) (string, error) {
 		}
 	}
 
-	return "", fmt.Errorf("invalid embedded IdP session cookie encryption key: %s (or sessionCookieEncryptionKey) must be 16, 24, or 32 bytes as a raw string or base64-encoded to one of those lengths; got %d raw bytes", sessionCookieEncryptionKeyEnv, len([]byte(key)))
+	return "", fmt.Errorf("invalid embedded IdP session cookie encryption key:%s (or sessionCookieEncryptionKey) must be 16, 24, or 32 bytes as a raw string or base64-encoded to one of those lengths; got %d raw bytes", sessionCookieEncryptionKeyEnv, len([]byte(key)))
 }
 
 func validSessionCookieEncryptionKeyLength(length int) bool {

management/server/idp/embedded_test.go

@@ -314,6 +314,34 @@ func TestEmbeddedIdPManager_UpdateUserPassword(t *testing.T) {
 	})
 }
 
+func TestEmbeddedIdPConfig_ToYAMLConfig_IncludesDeviceCallbackRedirectURI(t *testing.T) {
+	config := &EmbeddedIdPConfig{
+		Enabled: true,
+		Issuer:  "https://example.com/oauth2",
+		Storage: EmbeddedStorageConfig{
+			Type: "sqlite3",
+			Config: EmbeddedStorageTypeConfig{
+				File: filepath.Join(t.TempDir(), "dex.db"),
+			},
+		},
+	}
+
+	yamlConfig, err := config.ToYAMLConfig()
+	require.NoError(t, err)
+
+	var cliRedirectURIs []string
+	for _, client := range yamlConfig.StaticClients {
+		if client.ID == staticClientCLI {
+			cliRedirectURIs = client.RedirectURIs
+			break
+		}
+	}
+	require.NotEmpty(t, cliRedirectURIs)
+	assert.Contains(t, cliRedirectURIs, "/device/callback")
+	assert.Contains(t, cliRedirectURIs, "/oauth2/device/callback")
+	assert.Contains(t, cliRedirectURIs, "https://example.com/oauth2/device/callback")
+}
+
 func TestEmbeddedIdPConfig_ToYAMLConfig_SessionCookieEncryptionKey(t *testing.T) {
 	t.Setenv(sessionCookieEncryptionKeyEnv, "")
 

management/server/migration/account_seq.go

@@ -0,0 +1,156 @@
+package migration
+
+import (
+	"context"
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+	"gorm.io/gorm"
+
+	"github.com/netbirdio/netbird/management/server/types"
+)
+
+// BackfillAccountSeqIDs assigns a deterministic per-account sequential id to all
+// rows of `model` whose account_seq_id is zero, then seeds account_seq_counters
+// with the next free id per account. Idempotent: safe to re-run; both steps
+// no-op once everything is consistent.
+//
+// Implemented as two table-wide SQL statements with window functions, one
+// transaction. Backfilling 246k rows across 154k accounts on Postgres takes
+// well under a second instead of the per-account-loop ~2 minutes.
+//
+// orderColumn is the column to use when assigning the deterministic ordering
+// (typically the primary-key string id).
+func BackfillAccountSeqIDs[T any](
+	ctx context.Context,
+	db *gorm.DB,
+	entity types.AccountSeqEntity,
+	orderColumn string,
+) error {
+	var model T
+	if !db.Migrator().HasTable(&model) {
+		log.WithContext(ctx).Debugf("backfill seq id: table for %T missing, skip", model)
+		return nil
+	}
+
+	stmt := &gorm.Statement{DB: db}
+	if err := stmt.Parse(&model); err != nil {
+		return fmt.Errorf("parse model: %w", err)
+	}
+	table := quoteIdent(db, stmt.Schema.Table)
+	orderCol := quoteIdent(db, orderColumn)
+
+	return db.Transaction(func(tx *gorm.DB) error {
+		var pending int64
+		if err := tx.Raw(
+			fmt.Sprintf("SELECT count(*) FROM %s WHERE account_seq_id IS NULL OR account_seq_id = 0", table),
+		).Scan(&pending).Error; err != nil {
+			return fmt.Errorf("count pending on %s: %w", table, err)
+		}
+
+		if pending > 0 {
+			log.WithContext(ctx).Infof("backfill seq id: %s — %d rows pending", table, pending)
+			if err := backfillRankSQL(tx, table, orderCol); err != nil {
+				return fmt.Errorf("rank %s: %w", table, err)
+			}
+		}
+
+		if err := seedCountersSQL(tx, table, entity); err != nil {
+			return fmt.Errorf("seed counters for %s: %w", entity, err)
+		}
+		return nil
+	})
+}
+
+func quoteIdent(db *gorm.DB, name string) string {
+	switch db.Dialector.Name() {
+	case "mysql":
+		return "`" + name + "`"
+	case "postgres":
+		return `"` + name + `"`
+	default:
+		return name
+	}
+}
+
+func backfillRankSQL(db *gorm.DB, table, orderCol string) error {
+	dialect := db.Dialector.Name()
+	var sql string
+	switch dialect {
+	case "postgres", "sqlite":
+		sql = fmt.Sprintf(`
+WITH max_seq AS (
+    SELECT account_id, COALESCE(MAX(account_seq_id), 0) AS max_seq
+    FROM %s
+    GROUP BY account_id
+),
+ranked AS (
+    SELECT p.id,
+           m.max_seq + ROW_NUMBER() OVER (PARTITION BY p.account_id ORDER BY p.%s) AS new_seq
+    FROM %s p
+    JOIN max_seq m ON p.account_id = m.account_id
+    WHERE p.account_seq_id IS NULL OR p.account_seq_id = 0
+)
+UPDATE %s SET account_seq_id = ranked.new_seq
+FROM ranked
+WHERE %s.id = ranked.id
+`, table, orderCol, table, table, table)
+	case "mysql":
+		sql = fmt.Sprintf(`
+UPDATE %s p
+JOIN (
+    SELECT account_id, COALESCE(MAX(account_seq_id), 0) AS max_seq
+    FROM %s
+    GROUP BY account_id
+) m ON p.account_id = m.account_id
+JOIN (
+    SELECT id, ROW_NUMBER() OVER (PARTITION BY account_id ORDER BY %s) AS rn
+    FROM %s
+    WHERE account_seq_id IS NULL OR account_seq_id = 0
+) r ON p.id = r.id
+SET p.account_seq_id = m.max_seq + r.rn
+`, table, table, orderCol, table)
+	default:
+		return fmt.Errorf("unsupported dialect: %s", dialect)
+	}
+	return db.Exec(sql).Error
+}
+
+func seedCountersSQL(db *gorm.DB, table string, entity types.AccountSeqEntity) error {
+	dialect := db.Dialector.Name()
+	var sql string
+	switch dialect {
+	case "postgres":
+		sql = fmt.Sprintf(`
+INSERT INTO account_seq_counters (account_id, entity, next_id)
+SELECT account_id, ?, MAX(account_seq_id) + 1
+FROM %s
+WHERE account_seq_id IS NOT NULL AND account_seq_id > 0
+GROUP BY account_id
+ON CONFLICT (account_id, entity) DO UPDATE
+    SET next_id = GREATEST(account_seq_counters.next_id, EXCLUDED.next_id)
+`, table)
+	case "sqlite":
+		sql = fmt.Sprintf(`
+INSERT INTO account_seq_counters (account_id, entity, next_id)
+SELECT account_id, ?, MAX(account_seq_id) + 1
+FROM %s
+WHERE account_seq_id IS NOT NULL AND account_seq_id > 0
+GROUP BY account_id
+ON CONFLICT (account_id, entity) DO UPDATE
+    SET next_id = max(account_seq_counters.next_id, excluded.next_id)
+`, table)
+	case "mysql":
+		sql = fmt.Sprintf(`
+INSERT INTO account_seq_counters (account_id, entity, next_id)
+SELECT account_id, ?, MAX(account_seq_id) + 1
+FROM %s
+WHERE account_seq_id IS NOT NULL AND account_seq_id > 0
+GROUP BY account_id
+ON DUPLICATE KEY UPDATE next_id = GREATEST(next_id, VALUES(next_id))
+`, table)
+	default:
+		return fmt.Errorf("unsupported dialect: %s", dialect)
+	}
+	return db.Exec(sql, string(entity)).Error
+}

management/server/migration/migration_test.go

@@ -198,7 +198,11 @@ func TestMigrateNetIPFieldFromBlobToJSON_WithJSONData(t *testing.T) {
 	require.NoError(t, err, "Failed to insert account")
 
 	account.PeersG = []nbpeer.Peer{
-		{AccountID: "1234", Location: nbpeer.Location{ConnectionIP: net.IP{10, 0, 0, 1}}},
+		{
+			AccountID: "1234",
+			Location:  nbpeer.Location{ConnectionIP: net.IP{10, 0, 0, 1}},
+			Status:    &nbpeer.PeerStatus{LastSeen: time.Now()},
+		},
 	}
 
 	err = db.Save(account).Error

management/server/mock_server/account_mock.go

@@ -38,7 +38,8 @@ type MockAccountManager struct {
 	GetUserFromUserAuthFunc               func(ctx context.Context, userAuth auth.UserAuth) (*types.User, error)
 	ListUsersFunc                         func(ctx context.Context, accountID string) ([]*types.User, error)
 	GetPeersFunc                          func(ctx context.Context, accountID, userID, nameFilter, ipFilter string) ([]*nbpeer.Peer, error)
-	MarkPeerConnectedFunc                 func(ctx context.Context, peerKey string, connected bool, realIP net.IP, syncTime time.Time) error
+	MarkPeerConnectedFunc                 func(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error
+	MarkPeerDisconnectedFunc              func(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error
 	SyncAndMarkPeerFunc                   func(ctx context.Context, accountID string, peerPubKey string, meta nbpeer.PeerSystemMeta, realIP net.IP, syncTime time.Time) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error)
 	DeletePeerFunc                        func(ctx context.Context, accountID, peerKey, userID string) error
 	GetNetworkMapFunc                     func(ctx context.Context, peerKey string) (*types.NetworkMap, error)
@@ -130,6 +131,8 @@ type MockAccountManager struct {
 
 	AllowSyncFunc                  func(string, uint64) bool
 	UpdateAccountPeersFunc         func(ctx context.Context, accountID string, reason types.UpdateReason)
+	UpdateAffectedPeersFunc        func(ctx context.Context, accountID string, peerIDs []string)
+	BufferUpdateAffectedPeersFunc  func(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason)
 	BufferUpdateAccountPeersFunc   func(ctx context.Context, accountID string, reason types.UpdateReason)
 	RecalculateNetworkMapCacheFunc func(ctx context.Context, accountId string) error
 
@@ -207,6 +210,18 @@ func (am *MockAccountManager) UpdateAccountPeers(ctx context.Context, accountID
 	}
 }
 
+func (am *MockAccountManager) UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string) {
+	if am.UpdateAffectedPeersFunc != nil {
+		am.UpdateAffectedPeersFunc(ctx, accountID, peerIDs)
+	}
+}
+
+func (am *MockAccountManager) BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason) {
+	if am.BufferUpdateAffectedPeersFunc != nil {
+		am.BufferUpdateAffectedPeersFunc(ctx, accountID, peerIDs, reason)
+	}
+}
+
 func (am *MockAccountManager) BufferUpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) {
 	if am.BufferUpdateAccountPeersFunc != nil {
 		am.BufferUpdateAccountPeersFunc(ctx, accountID, reason)
@@ -227,7 +242,14 @@ func (am *MockAccountManager) SyncAndMarkPeer(ctx context.Context, accountID str
 	return nil, nil, nil, 0, status.Errorf(codes.Unimplemented, "method MarkPeerConnected is not implemented")
 }
 
-func (am *MockAccountManager) OnPeerDisconnected(_ context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
+func (am *MockAccountManager) OnPeerDisconnected(ctx context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
+	// Mirror DefaultAccountManager.OnPeerDisconnected: drive the fencing
+	// hook so tests that inject MarkPeerDisconnectedFunc actually observe
+	// disconnect events. Falls through to nil when no hook is set, which
+	// is the original behaviour.
+	if am.MarkPeerDisconnectedFunc != nil {
+		return am.MarkPeerDisconnectedFunc(ctx, peerPubKey, accountID, streamStartTime.UnixNano())
+	}
 	return nil
 }
 
@@ -328,13 +350,21 @@ func (am *MockAccountManager) GetAccountIDByUserID(ctx context.Context, userAuth
 }
 
 // MarkPeerConnected mock implementation of MarkPeerConnected from server.AccountManager interface
-func (am *MockAccountManager) MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
+func (am *MockAccountManager) MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
 	if am.MarkPeerConnectedFunc != nil {
-		return am.MarkPeerConnectedFunc(ctx, peerKey, connected, realIP, syncTime)
+		return am.MarkPeerConnectedFunc(ctx, peerKey, realIP, accountID, sessionStartedAt)
 	}
 	return status.Errorf(codes.Unimplemented, "method MarkPeerConnected is not implemented")
 }
 
+// MarkPeerDisconnected mock implementation of MarkPeerDisconnected from server.AccountManager interface
+func (am *MockAccountManager) MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error {
+	if am.MarkPeerDisconnectedFunc != nil {
+		return am.MarkPeerDisconnectedFunc(ctx, peerKey, accountID, sessionStartedAt)
+	}
+	return status.Errorf(codes.Unimplemented, "method MarkPeerDisconnected is not implemented")
+}
+
 // DeleteAccount mock implementation of DeleteAccount from server.AccountManager interface
 func (am *MockAccountManager) DeleteAccount(ctx context.Context, accountID, userID string) error {
 	if am.DeleteAccountFunc != nil {

management/server/nameserver.go

@@ -4,10 +4,12 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"slices"
 	"strings"
 	"unicode/utf8"
 
 	"github.com/rs/xid"
+	log "github.com/sirupsen/logrus"
 
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/management/server/activity"
@@ -57,22 +59,25 @@ func (am *DefaultAccountManager) CreateNameServerGroup(ctx context.Context, acco
 		SearchDomainsEnabled: searchDomainEnabled,
 	}
 
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err = validateNameServerGroup(ctx, transaction, accountID, newNSGroup); err != nil {
 			return err
 		}
 
-		updateAccountPeers, err = anyGroupHasPeersOrResources(ctx, transaction, accountID, newNSGroup.Groups)
+		seq, err := transaction.AllocateAccountSeqID(ctx, accountID, types.AccountSeqEntityNameserverGroup)
 		if err != nil {
 			return err
 		}
+		newNSGroup.AccountSeqID = seq
 
 		if err = transaction.SaveNameServerGroup(ctx, newNSGroup); err != nil {
 			return err
 		}
 
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, newNSGroup.Groups, nil)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
@@ -81,8 +86,11 @@ func (am *DefaultAccountManager) CreateNameServerGroup(ctx context.Context, acco
 
 	am.StoreEvent(ctx, userID, newNSGroup.ID, accountID, activity.NameserverGroupCreated, newNSGroup.EventMeta())
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceNameServerGroup, Operation: types.UpdateOperationCreate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("CreateNameServerGroup %s: updating %d affected peers: %v", newNSGroup.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("CreateNameServerGroup %s: no affected peers", newNSGroup.ID)
 	}
 
 	return newNSGroup.Copy(), nil
@@ -102,7 +110,7 @@ func (am *DefaultAccountManager) SaveNameServerGroup(ctx context.Context, accoun
 		return status.NewPermissionDeniedError()
 	}
 
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		oldNSGroup, err := transaction.GetNameServerGroupByID(ctx, store.LockingStrengthNone, accountID, nsGroupToSave.ID)
@@ -115,15 +123,15 @@ func (am *DefaultAccountManager) SaveNameServerGroup(ctx context.Context, accoun
 			return err
 		}
 
-		updateAccountPeers, err = areNameServerGroupChangesAffectPeers(ctx, transaction, nsGroupToSave, oldNSGroup)
-		if err != nil {
-			return err
-		}
+		nsGroupToSave.AccountSeqID = oldNSGroup.AccountSeqID
 
 		if err = transaction.SaveNameServerGroup(ctx, nsGroupToSave); err != nil {
 			return err
 		}
 
+		allGroups := slices.Concat(nsGroupToSave.Groups, oldNSGroup.Groups)
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, allGroups, nil)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
@@ -132,8 +140,11 @@ func (am *DefaultAccountManager) SaveNameServerGroup(ctx context.Context, accoun
 
 	am.StoreEvent(ctx, userID, nsGroupToSave.ID, accountID, activity.NameserverGroupUpdated, nsGroupToSave.EventMeta())
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceNameServerGroup, Operation: types.UpdateOperationUpdate})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("SaveNameServerGroup %s: updating %d affected peers: %v", nsGroupToSave.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("SaveNameServerGroup %s: no affected peers", nsGroupToSave.ID)
 	}
 
 	return nil
@@ -150,7 +161,7 @@ func (am *DefaultAccountManager) DeleteNameServerGroup(ctx context.Context, acco
 	}
 
 	var nsGroup *nbdns.NameServerGroup
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		nsGroup, err = transaction.GetNameServerGroupByID(ctx, store.LockingStrengthUpdate, accountID, nsGroupID)
@@ -158,10 +169,7 @@ func (am *DefaultAccountManager) DeleteNameServerGroup(ctx context.Context, acco
 			return err
 		}
 
-		updateAccountPeers, err = anyGroupHasPeersOrResources(ctx, transaction, accountID, nsGroup.Groups)
-		if err != nil {
-			return err
-		}
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, nsGroup.Groups, nil)
 
 		if err = transaction.DeleteNameServerGroup(ctx, accountID, nsGroupID); err != nil {
 			return err
@@ -175,8 +183,11 @@ func (am *DefaultAccountManager) DeleteNameServerGroup(ctx context.Context, acco
 
 	am.StoreEvent(ctx, userID, nsGroup.ID, accountID, activity.NameserverGroupDeleted, nsGroup.EventMeta())
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourceNameServerGroup, Operation: types.UpdateOperationDelete})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("DeleteNameServerGroup %s: updating %d affected peers: %v", nsGroupID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("DeleteNameServerGroup %s: no affected peers", nsGroupID)
 	}
 
 	return nil
@@ -224,24 +235,6 @@ func validateNameServerGroup(ctx context.Context, transaction store.Store, accou
 	return validateGroups(nameserverGroup.Groups, groups)
 }
 
-// areNameServerGroupChangesAffectPeers checks if the changes in the nameserver group affect the peers.
-func areNameServerGroupChangesAffectPeers(ctx context.Context, transaction store.Store, newNSGroup, oldNSGroup *nbdns.NameServerGroup) (bool, error) {
-	if !newNSGroup.Enabled && !oldNSGroup.Enabled {
-		return false, nil
-	}
-
-	hasPeers, err := anyGroupHasPeersOrResources(ctx, transaction, newNSGroup.AccountID, newNSGroup.Groups)
-	if err != nil {
-		return false, err
-	}
-
-	if hasPeers {
-		return true, nil
-	}
-
-	return anyGroupHasPeersOrResources(ctx, transaction, oldNSGroup.AccountID, oldNSGroup.Groups)
-}
-
 func validateDomainInput(primary bool, domains []string, searchDomainsEnabled bool) error {
 	if !primary && len(domains) == 0 {
 		return status.Errorf(status.InvalidArgument, "nameserver group primary status is false and domains are empty,"+

management/server/networks/manager.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 
 	"github.com/rs/xid"
+	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/management/server/account"
 	"github.com/netbirdio/netbird/management/server/activity"
@@ -15,7 +16,7 @@ import (
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
 	"github.com/netbirdio/netbird/management/server/permissions/operations"
 	"github.com/netbirdio/netbird/management/server/store"
-	serverTypes "github.com/netbirdio/netbird/management/server/types"
+	nbTypes "github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
@@ -71,9 +72,20 @@ func (m *managerImpl) CreateNetwork(ctx context.Context, userID string, network
 
 	network.ID = xid.New().String()
 
-	err = m.store.SaveNetwork(ctx, network)
+	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
+		seq, err := transaction.AllocateAccountSeqID(ctx, network.AccountID, nbTypes.AccountSeqEntityNetwork)
+		if err != nil {
+			return fmt.Errorf("failed to allocate network seq id: %w", err)
+		}
+		network.AccountSeqID = seq
+
+		if err := transaction.SaveNetwork(ctx, network); err != nil {
+			return fmt.Errorf("failed to save network: %w", err)
+		}
+		return nil
+	})
 	if err != nil {
-		return nil, fmt.Errorf("failed to save network: %w", err)
+		return nil, err
 	}
 
 	m.accountManager.StoreEvent(ctx, userID, network.ID, network.AccountID, activity.NetworkCreated, network.EventMeta())
@@ -102,14 +114,33 @@ func (m *managerImpl) UpdateNetwork(ctx context.Context, userID string, network
 		return nil, status.NewPermissionDeniedError()
 	}
 
-	_, err = m.store.GetNetworkByID(ctx, store.LockingStrengthUpdate, network.AccountID, network.ID)
+	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
+		existing, err := transaction.GetNetworkByID(ctx, store.LockingStrengthUpdate, network.AccountID, network.ID)
+		if err != nil {
+			return fmt.Errorf("failed to get network: %w", err)
+		}
+		network.AccountSeqID = existing.AccountSeqID
+
+		if err := transaction.SaveNetwork(ctx, network); err != nil {
+			return fmt.Errorf("failed to save network: %w", err)
+		}
+		return nil
+	})
 	if err != nil {
-		return nil, fmt.Errorf("failed to get network: %w", err)
+		return nil, err
 	}
 
 	m.accountManager.StoreEvent(ctx, userID, network.ID, network.AccountID, activity.NetworkUpdated, network.EventMeta())
 
-	return network, m.store.SaveNetwork(ctx, network)
+	return network, nil
+}
+
+// networkAffectedPeersData holds data loaded inside the transaction for affected peer resolution.
+type networkAffectedPeersData struct {
+	resourceGroupIDs []string
+	routerPeerGroups []string
+	directPeerIDs    []string
+	policies         []*nbTypes.Policy
 }
 
 func (m *managerImpl) DeleteNetwork(ctx context.Context, accountID, userID, networkID string) error {
@@ -127,13 +158,22 @@ func (m *managerImpl) DeleteNetwork(ctx context.Context, accountID, userID, netw
 	}
 
 	var eventsToStore []func()
+	var affectedData *networkAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		resources, err := transaction.GetNetworkResourcesByNetID(ctx, store.LockingStrengthUpdate, accountID, networkID)
 		if err != nil {
 			return fmt.Errorf("failed to get resources in network: %w", err)
 		}
 
+		var resourceGroupIDs []string
 		for _, resource := range resources {
+			groups, err := transaction.GetResourceGroups(ctx, store.LockingStrengthNone, accountID, resource.ID)
+			if err == nil {
+				for _, g := range groups {
+					resourceGroupIDs = append(resourceGroupIDs, g.ID)
+				}
+			}
+
 			event, err := m.resourcesManager.DeleteResourceInTransaction(ctx, transaction, accountID, userID, networkID, resource.ID)
 			if err != nil {
 				return fmt.Errorf("failed to delete resource: %w", err)
@@ -141,12 +181,19 @@ func (m *managerImpl) DeleteNetwork(ctx context.Context, accountID, userID, netw
 			eventsToStore = append(eventsToStore, event...)
 		}
 
-		routers, err := transaction.GetNetworkRoutersByNetID(ctx, store.LockingStrengthUpdate, accountID, networkID)
+		netRouters, err := transaction.GetNetworkRoutersByNetID(ctx, store.LockingStrengthUpdate, accountID, networkID)
 		if err != nil {
 			return fmt.Errorf("failed to get routers in network: %w", err)
 		}
 
-		for _, router := range routers {
+		var routerPeerGroups []string
+		var directPeerIDs []string
+		for _, router := range netRouters {
+			routerPeerGroups = append(routerPeerGroups, router.PeerGroups...)
+			if router.Peer != "" {
+				directPeerIDs = append(directPeerIDs, router.Peer)
+			}
+
 			event, err := m.routersManager.DeleteRouterInTransaction(ctx, transaction, accountID, userID, networkID, router.ID)
 			if err != nil {
 				return fmt.Errorf("failed to delete router: %w", err)
@@ -154,6 +201,24 @@ func (m *managerImpl) DeleteNetwork(ctx context.Context, accountID, userID, netw
 			eventsToStore = append(eventsToStore, event)
 		}
 
+		// load policies before deleting so group memberships are still present
+		var policies []*nbTypes.Policy
+		if len(resourceGroupIDs) > 0 {
+			policies, err = transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
+			if err != nil {
+				log.WithContext(ctx).Errorf("failed to get policies for affected peers: %v", err)
+			}
+		}
+
+		if len(resourceGroupIDs) > 0 || len(routerPeerGroups) > 0 || len(directPeerIDs) > 0 {
+			affectedData = &networkAffectedPeersData{
+				resourceGroupIDs: resourceGroupIDs,
+				routerPeerGroups: routerPeerGroups,
+				directPeerIDs:    directPeerIDs,
+				policies:         policies,
+			}
+		}
+
 		err = transaction.DeleteNetwork(ctx, accountID, networkID)
 		if err != nil {
 			return fmt.Errorf("failed to delete network: %w", err)
@@ -178,11 +243,111 @@ func (m *managerImpl) DeleteNetwork(ctx context.Context, accountID, userID, netw
 		event()
 	}
 
-	go m.accountManager.UpdateAccountPeers(ctx, accountID, serverTypes.UpdateReason{Resource: serverTypes.UpdateResourceNetwork, Operation: serverTypes.UpdateOperationDelete})
+	if affectedData != nil {
+		affectedPeerIDs := resolveNetworkAffectedPeers(ctx, m.store, accountID, affectedData)
+		if len(affectedPeerIDs) > 0 {
+			log.WithContext(ctx).Debugf("DeleteNetwork %s: updating %d affected peers: %v", networkID, len(affectedPeerIDs), affectedPeerIDs)
+			go m.accountManager.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+		} else {
+			log.WithContext(ctx).Tracef("DeleteNetwork %s: no affected peers", networkID)
+		}
+	}
 
 	return nil
 }
 
+// resolveNetworkAffectedPeers computes affected peer IDs from preloaded data outside the transaction.
+func resolveNetworkAffectedPeers(ctx context.Context, s store.Store, accountID string, data *networkAffectedPeersData) []string {
+	log.WithContext(ctx).Tracef("resolveNetworkAffectedPeers: routerPeerGroups=%v, resourceGroupIDs=%v, directPeerIDs=%v, policies=%d",
+		data.routerPeerGroups, data.resourceGroupIDs, data.directPeerIDs, len(data.policies))
+	groupSet := make(map[string]struct{})
+
+	for _, gID := range data.routerPeerGroups {
+		groupSet[gID] = struct{}{}
+	}
+
+	if len(data.resourceGroupIDs) > 0 {
+		for _, gID := range data.resourceGroupIDs {
+			groupSet[gID] = struct{}{}
+		}
+		collectPolicySourceGroups(data.policies, data.resourceGroupIDs, groupSet)
+	}
+
+	if len(groupSet) == 0 && len(data.directPeerIDs) == 0 {
+		return nil
+	}
+
+	peerIDs := resolveGroupsAndDirectPeers(ctx, s, accountID, groupSet, data.directPeerIDs)
+
+	log.WithContext(ctx).Tracef("resolveNetworkAffectedPeers: result %d peers: %v", len(peerIDs), peerIDs)
+	return peerIDs
+}
+
+// collectPolicySourceGroups finds policies whose rules reference any of the destination group IDs
+// and adds their source groups to the groupSet.
+func collectPolicySourceGroups(policies []*nbTypes.Policy, destGroupIDs []string, groupSet map[string]struct{}) {
+	destSet := make(map[string]struct{}, len(destGroupIDs))
+	for _, gID := range destGroupIDs {
+		destSet[gID] = struct{}{}
+	}
+
+	for _, policy := range policies {
+		if policy == nil || !policy.Enabled {
+			continue
+		}
+		for _, rule := range policy.Rules {
+			if rule == nil || !rule.Enabled {
+				continue
+			}
+			if ruleMatchesDestinations(rule, destSet) {
+				for _, gID := range rule.Sources {
+					groupSet[gID] = struct{}{}
+				}
+			}
+		}
+	}
+}
+
+// ruleMatchesDestinations checks if a policy rule references any of the destination groups.
+func ruleMatchesDestinations(rule *nbTypes.PolicyRule, destSet map[string]struct{}) bool {
+	for _, gID := range rule.Destinations {
+		if _, ok := destSet[gID]; ok {
+			return true
+		}
+	}
+	return false
+}
+
+// resolveGroupsAndDirectPeers resolves group IDs and direct peer IDs into a deduplicated peer ID list.
+func resolveGroupsAndDirectPeers(ctx context.Context, s store.Store, accountID string, groupSet map[string]struct{}, directPeerIDs []string) []string {
+	groupIDs := make([]string, 0, len(groupSet))
+	for gID := range groupSet {
+		groupIDs = append(groupIDs, gID)
+	}
+
+	peerIDs, err := s.GetPeerIDsByGroups(ctx, accountID, groupIDs)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to resolve peer IDs: %v", err)
+		return nil
+	}
+
+	if len(directPeerIDs) == 0 {
+		return peerIDs
+	}
+
+	seen := make(map[string]struct{}, len(peerIDs))
+	for _, id := range peerIDs {
+		seen[id] = struct{}{}
+	}
+	for _, id := range directPeerIDs {
+		if _, exists := seen[id]; !exists {
+			peerIDs = append(peerIDs, id)
+			seen[id] = struct{}{}
+		}
+	}
+	return peerIDs
+}
+
 func NewManagerMock() Manager {
 	return &mockManager{}
 }

management/server/networks/manager_test.go

@@ -34,8 +34,11 @@ func Test_GetAllNetworksReturnsNetworks(t *testing.T) {
 
 	networks, err := manager.GetAllNetworks(ctx, accountID, userID)
 	require.NoError(t, err)
-	require.Len(t, networks, 1)
-	require.Equal(t, "testNetworkId", networks[0].ID)
+	ids := make([]string, 0, len(networks))
+	for _, n := range networks {
+		ids = append(ids, n.ID)
+	}
+	require.ElementsMatch(t, []string{"testNetworkId", "secondNetworkId"}, ids)
 }
 
 func Test_GetAllNetworksReturnsPermissionDenied(t *testing.T) {
@@ -252,3 +255,73 @@ func Test_UpdateNetworkFailsWithPermissionDenied(t *testing.T) {
 	require.Error(t, err)
 	require.Nil(t, updatedNetwork)
 }
+
+// Test_CreateNetworkAllocatesSeqID verifies that CreateNetwork sets a
+// non-zero AccountSeqID on the persisted network (allocated through the
+// account_seq_counters table).
+func Test_CreateNetworkAllocatesSeqID(t *testing.T) {
+	ctx := context.Background()
+	const accountID = "testAccountId"
+	const userID = "testAdminId"
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(ctx, "../testdata/networks.sql", t.TempDir())
+	require.NoError(t, err)
+	t.Cleanup(cleanUp)
+
+	am := mock_server.MockAccountManager{}
+	permissionsManager := permissions.NewManager(s)
+	groupsManager := groups.NewManagerMock()
+	routerManager := routers.NewManagerMock()
+	resourcesManager := resources.NewManager(s, permissionsManager, groupsManager, &am, nil)
+	manager := NewManager(s, permissionsManager, resourcesManager, routerManager, &am)
+
+	created, err := manager.CreateNetwork(ctx, userID, &types.Network{
+		AccountID: accountID,
+		Name:      "seq-allocation-test",
+	})
+	require.NoError(t, err)
+	require.NotZero(t, created.AccountSeqID, "CreateNetwork must allocate a non-zero AccountSeqID")
+}
+
+// Test_UpdateNetworkPreservesSeqID verifies UpdateNetwork does not reset
+// AccountSeqID even when the caller passes a zero value (the shape REST
+// handlers produce because the field is `json:"-"`).
+func Test_UpdateNetworkPreservesSeqID(t *testing.T) {
+	ctx := context.Background()
+	const accountID = "testAccountId"
+	const userID = "testAdminId"
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(ctx, "../testdata/networks.sql", t.TempDir())
+	require.NoError(t, err)
+	t.Cleanup(cleanUp)
+
+	am := mock_server.MockAccountManager{}
+	permissionsManager := permissions.NewManager(s)
+	groupsManager := groups.NewManagerMock()
+	routerManager := routers.NewManagerMock()
+	resourcesManager := resources.NewManager(s, permissionsManager, groupsManager, &am, nil)
+	manager := NewManager(s, permissionsManager, resourcesManager, routerManager, &am)
+
+	created, err := manager.CreateNetwork(ctx, userID, &types.Network{
+		AccountID: accountID,
+		Name:      "seq-preserve-original",
+	})
+	require.NoError(t, err)
+	originalSeq := created.AccountSeqID
+	require.NotZero(t, originalSeq)
+
+	update := &types.Network{
+		AccountID: accountID,
+		ID:        created.ID,
+		Name:      "seq-preserve-renamed",
+	}
+	require.Zero(t, update.AccountSeqID, "incoming struct must mirror an HTTP handler shape")
+
+	_, err = manager.UpdateNetwork(ctx, userID, update)
+	require.NoError(t, err)
+
+	got, err := manager.GetNetwork(ctx, accountID, userID, created.ID)
+	require.NoError(t, err)
+	require.Equal(t, originalSeq, got.AccountSeqID, "AccountSeqID must survive UpdateNetwork")
+	require.Equal(t, "seq-preserve-renamed", got.Name)
+}

management/server/networks/resources/manager.go

@@ -114,45 +114,11 @@ func (m *managerImpl) CreateResource(ctx context.Context, userID string, resourc
 	}
 
 	var eventsToStore []func()
+	var affectedData *resourceAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		_, err = transaction.GetNetworkResourceByName(ctx, store.LockingStrengthNone, resource.AccountID, resource.Name)
-		if err == nil {
-			return status.Errorf(status.InvalidArgument, "resource with name %s already exists", resource.Name)
-		}
-
-		network, err := transaction.GetNetworkByID(ctx, store.LockingStrengthUpdate, resource.AccountID, resource.NetworkID)
-		if err != nil {
-			return fmt.Errorf("failed to get network: %w", err)
-		}
-
-		err = transaction.SaveNetworkResource(ctx, resource)
-		if err != nil {
-			return fmt.Errorf("failed to save network resource: %w", err)
-		}
-
-		event := func() {
-			m.accountManager.StoreEvent(ctx, userID, resource.ID, resource.AccountID, activity.NetworkResourceCreated, resource.EventMeta(network))
-		}
-		eventsToStore = append(eventsToStore, event)
-
-		res := nbtypes.Resource{
-			ID:   resource.ID,
-			Type: nbtypes.ResourceType(resource.Type.String()),
-		}
-		for _, groupID := range resource.GroupIDs {
-			event, err := m.groupsManager.AddResourceToGroupInTransaction(ctx, transaction, resource.AccountID, userID, groupID, &res)
-			if err != nil {
-				return fmt.Errorf("failed to add resource to group: %w", err)
-			}
-			eventsToStore = append(eventsToStore, event)
-		}
-
-		err = transaction.IncrementNetworkSerial(ctx, resource.AccountID)
-		if err != nil {
-			return fmt.Errorf("failed to increment network serial: %w", err)
-		}
-
-		return nil
+		var txErr error
+		eventsToStore, affectedData, txErr = m.createResourceInTransaction(ctx, transaction, userID, resource)
+		return txErr
 	})
 	if err != nil {
 		return nil, fmt.Errorf("failed to create network resource: %w", err)
@@ -162,11 +128,66 @@ func (m *managerImpl) CreateResource(ctx context.Context, userID string, resourc
 		event()
 	}
 
-	go m.accountManager.UpdateAccountPeers(ctx, resource.AccountID, nbtypes.UpdateReason{Resource: nbtypes.UpdateResourceNetworkResource, Operation: nbtypes.UpdateOperationCreate})
+	if affectedPeerIDs := m.resolveResourceAffectedPeers(ctx, resource.AccountID, affectedData); len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("CreateResource %s: updating %d affected peers: %v", resource.ID, len(affectedPeerIDs), affectedPeerIDs)
+		go m.accountManager.UpdateAffectedPeers(ctx, resource.AccountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("CreateResource %s: no affected peers", resource.ID)
+	}
 
 	return resource, nil
 }
 
+func (m *managerImpl) createResourceInTransaction(ctx context.Context, transaction store.Store, userID string, resource *types.NetworkResource) ([]func(), *resourceAffectedPeersData, error) {
+	_, err := transaction.GetNetworkResourceByName(ctx, store.LockingStrengthNone, resource.AccountID, resource.Name)
+	if err == nil {
+		return nil, nil, status.Errorf(status.InvalidArgument, "resource with name %s already exists", resource.Name)
+	}
+
+	network, err := transaction.GetNetworkByID(ctx, store.LockingStrengthUpdate, resource.AccountID, resource.NetworkID)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to get network: %w", err)
+	}
+
+	seq, err := transaction.AllocateAccountSeqID(ctx, resource.AccountID, nbtypes.AccountSeqEntityNetworkResource)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to allocate network resource seq id: %w", err)
+	}
+	resource.AccountSeqID = seq
+
+	if err = transaction.SaveNetworkResource(ctx, resource); err != nil {
+		return nil, nil, fmt.Errorf("failed to save network resource: %w", err)
+	}
+
+	var eventsToStore []func()
+	eventsToStore = append(eventsToStore, func() {
+		m.accountManager.StoreEvent(ctx, userID, resource.ID, resource.AccountID, activity.NetworkResourceCreated, resource.EventMeta(network))
+	})
+
+	res := nbtypes.Resource{
+		ID:   resource.ID,
+		Type: nbtypes.ResourceType(resource.Type.String()),
+	}
+	for _, groupID := range resource.GroupIDs {
+		event, err := m.groupsManager.AddResourceToGroupInTransaction(ctx, transaction, resource.AccountID, userID, groupID, &res)
+		if err != nil {
+			return nil, nil, fmt.Errorf("failed to add resource to group: %w", err)
+		}
+		eventsToStore = append(eventsToStore, event)
+	}
+
+	if err = transaction.IncrementNetworkSerial(ctx, resource.AccountID); err != nil {
+		return nil, nil, fmt.Errorf("failed to increment network serial: %w", err)
+	}
+
+	affectedData, err := loadResourceAffectedPeersData(ctx, transaction, resource.AccountID, resource.NetworkID, resource.GroupIDs)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to load affected peers data: %v", err)
+	}
+
+	return eventsToStore, affectedData, nil
+}
+
 func (m *managerImpl) GetResource(ctx context.Context, accountID, userID, networkID, resourceID string) (*types.NetworkResource, error) {
 	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Networks, operations.Read)
 	if err != nil {
@@ -207,6 +228,7 @@ func (m *managerImpl) UpdateResource(ctx context.Context, userID string, resourc
 	resource.Prefix = prefix
 
 	var eventsToStore []func()
+	var affectedData *resourceAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		network, err := transaction.GetNetworkByID(ctx, store.LockingStrengthUpdate, resource.AccountID, resource.NetworkID)
 		if err != nil {
@@ -231,6 +253,16 @@ func (m *managerImpl) UpdateResource(ctx context.Context, userID string, resourc
 		if err != nil {
 			return fmt.Errorf("failed to get network resource: %w", err)
 		}
+		resource.AccountSeqID = oldResource.AccountSeqID
+
+		oldGroups, err := m.groupsManager.GetResourceGroupsInTransaction(ctx, transaction, store.LockingStrengthNone, oldResource.AccountID, oldResource.ID)
+		if err != nil {
+			return fmt.Errorf("failed to get old resource groups: %w", err)
+		}
+		var oldGroupIDs []string
+		for _, g := range oldGroups {
+			oldGroupIDs = append(oldGroupIDs, g.ID)
+		}
 
 		err = transaction.SaveNetworkResource(ctx, resource)
 		if err != nil {
@@ -247,6 +279,11 @@ func (m *managerImpl) UpdateResource(ctx context.Context, userID string, resourc
 			m.accountManager.StoreEvent(ctx, userID, resource.ID, resource.AccountID, activity.NetworkResourceUpdated, resource.EventMeta(network))
 		})
 
+		affectedData, err = loadResourceAffectedPeersData(ctx, transaction, resource.AccountID, resource.NetworkID, append(resource.GroupIDs, oldGroupIDs...))
+		if err != nil {
+			log.WithContext(ctx).Errorf("failed to load affected peers data: %v", err)
+		}
+
 		err = transaction.IncrementNetworkSerial(ctx, resource.AccountID)
 		if err != nil {
 			return fmt.Errorf("failed to increment network serial: %w", err)
@@ -270,7 +307,12 @@ func (m *managerImpl) UpdateResource(ctx context.Context, userID string, resourc
 		}
 	}()
 
-	go m.accountManager.UpdateAccountPeers(ctx, resource.AccountID, nbtypes.UpdateReason{Resource: nbtypes.UpdateResourceNetworkResource, Operation: nbtypes.UpdateOperationUpdate})
+	if affectedPeerIDs := m.resolveResourceAffectedPeers(ctx, resource.AccountID, affectedData); len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("UpdateResource %s: updating %d affected peers: %v", resource.ID, len(affectedPeerIDs), affectedPeerIDs)
+		go m.accountManager.UpdateAffectedPeers(ctx, resource.AccountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("UpdateResource %s: no affected peers", resource.ID)
+	}
 
 	return resource, nil
 }
@@ -331,7 +373,22 @@ func (m *managerImpl) DeleteResource(ctx context.Context, accountID, userID, net
 	}
 
 	var events []func()
+	var affectedData *resourceAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
+		groups, err := m.groupsManager.GetResourceGroupsInTransaction(ctx, transaction, store.LockingStrengthNone, accountID, resourceID)
+		if err != nil {
+			return fmt.Errorf("failed to get resource groups: %w", err)
+		}
+		var resourceGroupIDs []string
+		for _, g := range groups {
+			resourceGroupIDs = append(resourceGroupIDs, g.ID)
+		}
+
+		affectedData, err = loadResourceAffectedPeersData(ctx, transaction, accountID, networkID, resourceGroupIDs)
+		if err != nil {
+			log.WithContext(ctx).Errorf("failed to load affected peers data: %v", err)
+		}
+
 		events, err = m.DeleteResourceInTransaction(ctx, transaction, accountID, userID, networkID, resourceID)
 		if err != nil {
 			return fmt.Errorf("failed to delete resource: %w", err)
@@ -352,7 +409,12 @@ func (m *managerImpl) DeleteResource(ctx context.Context, accountID, userID, net
 		event()
 	}
 
-	go m.accountManager.UpdateAccountPeers(ctx, accountID, nbtypes.UpdateReason{Resource: nbtypes.UpdateResourceNetworkResource, Operation: nbtypes.UpdateOperationDelete})
+	if affectedPeerIDs := m.resolveResourceAffectedPeers(ctx, accountID, affectedData); len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("DeleteResource %s: updating %d affected peers: %v", resourceID, len(affectedPeerIDs), affectedPeerIDs)
+		go m.accountManager.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("DeleteResource %s: no affected peers", resourceID)
+	}
 
 	return nil
 }
@@ -399,6 +461,151 @@ func (m *managerImpl) DeleteResourceInTransaction(ctx context.Context, transacti
 	return eventsToStore, nil
 }
 
+// resourceAffectedPeersData holds data loaded inside a transaction for affected peer resolution.
+type resourceAffectedPeersData struct {
+	resourceGroupIDs  []string
+	policies          []*nbtypes.Policy
+	routerPeerGroups  []string
+	routerDirectPeers []string
+}
+
+// loadResourceAffectedPeersData loads the data needed to determine affected peers within a transaction.
+func loadResourceAffectedPeersData(ctx context.Context, transaction store.Store, accountID, networkID string, resourceGroupIDs []string) (*resourceAffectedPeersData, error) {
+	if len(resourceGroupIDs) == 0 {
+		return &resourceAffectedPeersData{}, nil
+	}
+
+	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		return nil, fmt.Errorf("failed to get policies: %w", err)
+	}
+
+	routers, err := transaction.GetNetworkRoutersByNetID(ctx, store.LockingStrengthNone, accountID, networkID)
+	if err != nil {
+		return nil, fmt.Errorf("failed to get routers: %w", err)
+	}
+
+	var routerPeerGroups []string
+	var routerDirectPeers []string
+	for _, router := range routers {
+		if !router.Enabled {
+			continue
+		}
+		routerPeerGroups = append(routerPeerGroups, router.PeerGroups...)
+		if router.Peer != "" {
+			routerDirectPeers = append(routerDirectPeers, router.Peer)
+		}
+	}
+
+	return &resourceAffectedPeersData{
+		resourceGroupIDs:  resourceGroupIDs,
+		policies:          policies,
+		routerPeerGroups:  routerPeerGroups,
+		routerDirectPeers: routerDirectPeers,
+	}, nil
+}
+
+// resolveResourceAffectedPeers computes affected peer IDs from preloaded data outside the transaction.
+func (m *managerImpl) resolveResourceAffectedPeers(ctx context.Context, accountID string, data *resourceAffectedPeersData) []string {
+	if data == nil {
+		return nil
+	}
+
+	log.WithContext(ctx).Tracef("resolveResourceAffectedPeers: resourceGroupIDs=%v, routerPeerGroups=%v, routerDirectPeers=%v, policies=%d",
+		data.resourceGroupIDs, data.routerPeerGroups, data.routerDirectPeers, len(data.policies))
+
+	groupSet := make(map[string]struct{})
+	directPeerIDs := collectResourcePolicySourceGroups(data.policies, data.resourceGroupIDs, groupSet)
+
+	for _, gID := range data.routerPeerGroups {
+		groupSet[gID] = struct{}{}
+	}
+	directPeerIDs = append(directPeerIDs, data.routerDirectPeers...)
+
+	if len(groupSet) == 0 && len(directPeerIDs) == 0 {
+		return nil
+	}
+
+	peerIDs := resolveGroupsAndDirectPeers(ctx, m.store, accountID, groupSet, directPeerIDs)
+
+	log.WithContext(ctx).Tracef("resolveResourceAffectedPeers: result %d peers: %v", len(peerIDs), peerIDs)
+	return peerIDs
+}
+
+// collectResourcePolicySourceGroups finds policies whose rules reference the resource destination groups,
+// adds their source groups to groupSet, and returns any direct peer IDs from source resources.
+func collectResourcePolicySourceGroups(policies []*nbtypes.Policy, destGroupIDs []string, groupSet map[string]struct{}) []string {
+	destSet := make(map[string]struct{}, len(destGroupIDs))
+	for _, gID := range destGroupIDs {
+		destSet[gID] = struct{}{}
+	}
+
+	var directPeerIDs []string
+	for _, policy := range policies {
+		if policy == nil || !policy.Enabled {
+			continue
+		}
+		directPeerIDs = collectSourcesFromPolicyRules(policy.Rules, destSet, groupSet, directPeerIDs)
+	}
+	return directPeerIDs
+}
+
+func collectSourcesFromPolicyRules(rules []*nbtypes.PolicyRule, destSet map[string]struct{}, groupSet map[string]struct{}, directPeerIDs []string) []string {
+	for _, rule := range rules {
+		if rule == nil || !rule.Enabled {
+			continue
+		}
+		if !ruleMatchesDestinations(rule, destSet) {
+			continue
+		}
+		for _, gID := range rule.Sources {
+			groupSet[gID] = struct{}{}
+		}
+		if rule.SourceResource.Type == nbtypes.ResourceTypePeer && rule.SourceResource.ID != "" {
+			directPeerIDs = append(directPeerIDs, rule.SourceResource.ID)
+		}
+	}
+	return directPeerIDs
+}
+
+func ruleMatchesDestinations(rule *nbtypes.PolicyRule, destSet map[string]struct{}) bool {
+	for _, gID := range rule.Destinations {
+		if _, ok := destSet[gID]; ok {
+			return true
+		}
+	}
+	return false
+}
+
+func resolveGroupsAndDirectPeers(ctx context.Context, s store.Store, accountID string, groupSet map[string]struct{}, directPeerIDs []string) []string {
+	groupIDs := make([]string, 0, len(groupSet))
+	for gID := range groupSet {
+		groupIDs = append(groupIDs, gID)
+	}
+
+	peerIDs, err := s.GetPeerIDsByGroups(ctx, accountID, groupIDs)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to resolve peer IDs: %v", err)
+		return nil
+	}
+
+	if len(directPeerIDs) == 0 {
+		return peerIDs
+	}
+
+	seen := make(map[string]struct{}, len(peerIDs))
+	for _, id := range peerIDs {
+		seen[id] = struct{}{}
+	}
+	for _, id := range directPeerIDs {
+		if _, exists := seen[id]; !exists {
+			peerIDs = append(peerIDs, id)
+			seen[id] = struct{}{}
+		}
+	}
+	return peerIDs
+}
+
 func NewManagerMock() Manager {
 	return &mockManager{}
 }

management/server/networks/resources/types/resource.go

@@ -32,6 +32,9 @@ type NetworkResource struct {
 	ID          string `gorm:"primaryKey"`
 	NetworkID   string `gorm:"index"`
 	AccountID   string `gorm:"index"`
+	// AccountSeqID is a per-account monotonically increasing identifier used as the
+	// compact wire id when sending NetworkMap components to capable peers.
+	AccountSeqID uint32 `json:"-" gorm:"index:idx_network_resources_account_seq_id;not null;default:0"`
 	Name        string
 	Description string
 	Type        NetworkResourceType
@@ -93,17 +96,18 @@ func (n *NetworkResource) FromAPIRequest(req *api.NetworkResourceRequest) {
 
 func (n *NetworkResource) Copy() *NetworkResource {
 	return &NetworkResource{
-		ID:          n.ID,
-		AccountID:   n.AccountID,
-		NetworkID:   n.NetworkID,
-		Name:        n.Name,
-		Description: n.Description,
-		Type:        n.Type,
-		Address:     n.Address,
-		Domain:      n.Domain,
-		Prefix:      n.Prefix,
-		GroupIDs:    n.GroupIDs,
-		Enabled:     n.Enabled,
+		ID:           n.ID,
+		AccountID:    n.AccountID,
+		NetworkID:    n.NetworkID,
+		AccountSeqID: n.AccountSeqID,
+		Name:         n.Name,
+		Description:  n.Description,
+		Type:         n.Type,
+		Address:      n.Address,
+		Domain:       n.Domain,
+		Prefix:       n.Prefix,
+		GroupIDs:     n.GroupIDs,
+		Enabled:      n.Enabled,
 	}
 }
 

management/server/networks/routers/manager.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 
 	"github.com/rs/xid"
+	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/management/server/account"
 	"github.com/netbirdio/netbird/management/server/activity"
@@ -15,7 +16,7 @@ import (
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
 	"github.com/netbirdio/netbird/management/server/permissions/operations"
 	"github.com/netbirdio/netbird/management/server/store"
-	serverTypes "github.com/netbirdio/netbird/management/server/types"
+	nbtypes "github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
@@ -90,6 +91,7 @@ func (m *managerImpl) CreateRouter(ctx context.Context, userID string, router *t
 	}
 
 	var network *networkTypes.Network
+	var affectedData *routerAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		network, err = transaction.GetNetworkByID(ctx, store.LockingStrengthNone, router.AccountID, router.NetworkID)
 		if err != nil {
@@ -102,7 +104,13 @@ func (m *managerImpl) CreateRouter(ctx context.Context, userID string, router *t
 
 		router.ID = xid.New().String()
 
-		err = transaction.SaveNetworkRouter(ctx, router)
+		seq, err := transaction.AllocateAccountSeqID(ctx, router.AccountID, nbtypes.AccountSeqEntityNetworkRouter)
+		if err != nil {
+			return fmt.Errorf("failed to allocate network router seq id: %w", err)
+		}
+		router.AccountSeqID = seq
+
+		err = transaction.CreateNetworkRouter(ctx, router)
 		if err != nil {
 			return fmt.Errorf("failed to create network router: %w", err)
 		}
@@ -112,6 +120,11 @@ func (m *managerImpl) CreateRouter(ctx context.Context, userID string, router *t
 			return fmt.Errorf("failed to increment network serial: %w", err)
 		}
 
+		affectedData, err = loadRouterAffectedPeersData(ctx, transaction, router.AccountID, router.NetworkID, router.PeerGroups, router.Peer)
+		if err != nil {
+			log.WithContext(ctx).Errorf("failed to load affected peers data: %v", err)
+		}
+
 		return nil
 	})
 	if err != nil {
@@ -120,7 +133,12 @@ func (m *managerImpl) CreateRouter(ctx context.Context, userID string, router *t
 
 	m.accountManager.StoreEvent(ctx, userID, router.ID, router.AccountID, activity.NetworkRouterCreated, router.EventMeta(network))
 
-	go m.accountManager.UpdateAccountPeers(ctx, router.AccountID, serverTypes.UpdateReason{Resource: serverTypes.UpdateResourceNetworkRouter, Operation: serverTypes.UpdateOperationCreate})
+	if affectedPeerIDs := m.resolveRouterAffectedPeers(ctx, router.AccountID, affectedData); len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("CreateRouter %s: updating %d affected peers: %v", router.ID, len(affectedPeerIDs), affectedPeerIDs)
+		go m.accountManager.UpdateAffectedPeers(ctx, router.AccountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("CreateRouter %s: no affected peers", router.ID)
+	}
 
 	return router, nil
 }
@@ -156,27 +174,11 @@ func (m *managerImpl) UpdateRouter(ctx context.Context, userID string, router *t
 	}
 
 	var network *networkTypes.Network
+	var affectedData *routerAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		network, err = transaction.GetNetworkByID(ctx, store.LockingStrengthNone, router.AccountID, router.NetworkID)
-		if err != nil {
-			return fmt.Errorf("failed to get network: %w", err)
-		}
-
-		if network.ID != router.NetworkID {
-			return status.NewRouterNotPartOfNetworkError(router.ID, router.NetworkID)
-		}
-
-		err = transaction.SaveNetworkRouter(ctx, router)
-		if err != nil {
-			return fmt.Errorf("failed to update network router: %w", err)
-		}
-
-		err = transaction.IncrementNetworkSerial(ctx, router.AccountID)
-		if err != nil {
-			return fmt.Errorf("failed to increment network serial: %w", err)
-		}
-
-		return nil
+		var txErr error
+		network, affectedData, txErr = m.updateRouterInTransaction(ctx, transaction, router)
+		return txErr
 	})
 	if err != nil {
 		return nil, err
@@ -184,11 +186,62 @@ func (m *managerImpl) UpdateRouter(ctx context.Context, userID string, router *t
 
 	m.accountManager.StoreEvent(ctx, userID, router.ID, router.AccountID, activity.NetworkRouterUpdated, router.EventMeta(network))
 
-	go m.accountManager.UpdateAccountPeers(ctx, router.AccountID, serverTypes.UpdateReason{Resource: serverTypes.UpdateResourceNetworkRouter, Operation: serverTypes.UpdateOperationUpdate})
+	if affectedPeerIDs := m.resolveRouterAffectedPeers(ctx, router.AccountID, affectedData); len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("UpdateRouter %s: updating %d affected peers: %v", router.ID, len(affectedPeerIDs), affectedPeerIDs)
+		go m.accountManager.UpdateAffectedPeers(ctx, router.AccountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("UpdateRouter %s: no affected peers", router.ID)
+	}
 
 	return router, nil
 }
 
+func (m *managerImpl) updateRouterInTransaction(ctx context.Context, transaction store.Store, router *types.NetworkRouter) (*networkTypes.Network, *routerAffectedPeersData, error) {
+	network, err := transaction.GetNetworkByID(ctx, store.LockingStrengthNone, router.AccountID, router.NetworkID)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to get network: %w", err)
+	}
+
+	oldRouter, err := transaction.GetNetworkRouterByID(ctx, store.LockingStrengthUpdate, router.AccountID, router.ID)
+	if err != nil {
+		return nil, nil, fmt.Errorf("failed to get network router: %w", err)
+	}
+
+	if oldRouter.AccountID != router.AccountID {
+		return nil, nil, status.NewNetworkRouterNotFoundError(router.ID)
+	}
+
+	if oldRouter.NetworkID != router.NetworkID {
+		return nil, nil, status.NewRouterNotPartOfNetworkError(router.ID, router.NetworkID)
+	}
+
+	router.AccountSeqID = oldRouter.AccountSeqID
+
+	allPeerGroups := append(router.PeerGroups, oldRouter.PeerGroups...)
+	var directPeers []string
+	if router.Peer != "" {
+		directPeers = append(directPeers, router.Peer)
+	}
+	if oldRouter.Peer != "" {
+		directPeers = append(directPeers, oldRouter.Peer)
+	}
+
+	if err = transaction.UpdateNetworkRouter(ctx, router); err != nil {
+		return nil, nil, fmt.Errorf("failed to update network router: %w", err)
+	}
+
+	if err = transaction.IncrementNetworkSerial(ctx, router.AccountID); err != nil {
+		return nil, nil, fmt.Errorf("failed to increment network serial: %w", err)
+	}
+
+	affectedData, err := loadRouterAffectedPeersData(ctx, transaction, router.AccountID, router.NetworkID, allPeerGroups, directPeers...)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to load affected peers data: %v", err)
+	}
+
+	return network, affectedData, nil
+}
+
 func (m *managerImpl) DeleteRouter(ctx context.Context, accountID, userID, networkID, routerID string) error {
 	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Networks, operations.Delete)
 	if err != nil {
@@ -199,7 +252,19 @@ func (m *managerImpl) DeleteRouter(ctx context.Context, accountID, userID, netwo
 	}
 
 	var event func()
+	var affectedData *routerAffectedPeersData
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
+		router, err := transaction.GetNetworkRouterByID(ctx, store.LockingStrengthNone, accountID, routerID)
+		if err != nil {
+			return fmt.Errorf("failed to get router: %w", err)
+		}
+
+		// load before delete so group memberships are still present
+		affectedData, err = loadRouterAffectedPeersData(ctx, transaction, accountID, networkID, router.PeerGroups, router.Peer)
+		if err != nil {
+			log.WithContext(ctx).Errorf("failed to load affected peers data: %v", err)
+		}
+
 		event, err = m.DeleteRouterInTransaction(ctx, transaction, accountID, userID, networkID, routerID)
 		if err != nil {
 			return fmt.Errorf("failed to delete network router: %w", err)
@@ -218,7 +283,12 @@ func (m *managerImpl) DeleteRouter(ctx context.Context, accountID, userID, netwo
 
 	event()
 
-	go m.accountManager.UpdateAccountPeers(ctx, accountID, serverTypes.UpdateReason{Resource: serverTypes.UpdateResourceNetworkRouter, Operation: serverTypes.UpdateOperationDelete})
+	if affectedPeerIDs := m.resolveRouterAffectedPeers(ctx, accountID, affectedData); len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("DeleteRouter %s: updating %d affected peers: %v", routerID, len(affectedPeerIDs), affectedPeerIDs)
+		go m.accountManager.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("DeleteRouter %s: no affected peers", routerID)
+	}
 
 	return nil
 }
@@ -250,6 +320,153 @@ func (m *managerImpl) DeleteRouterInTransaction(ctx context.Context, transaction
 	return event, nil
 }
 
+// routerAffectedPeersData holds data loaded inside a transaction for affected peer resolution.
+type routerAffectedPeersData struct {
+	routerPeerGroups []string
+	directPeerIDs    []string
+	resourceGroupIDs []string
+	policies         []*nbtypes.Policy
+}
+
+// loadRouterAffectedPeersData loads the data needed to determine affected peers within a transaction.
+func loadRouterAffectedPeersData(ctx context.Context, transaction store.Store, accountID, networkID string, routerPeerGroups []string, directPeers ...string) (*routerAffectedPeersData, error) {
+	var directPeerIDs []string
+	for _, p := range directPeers {
+		if p != "" {
+			directPeerIDs = append(directPeerIDs, p)
+		}
+	}
+
+	if len(routerPeerGroups) == 0 && len(directPeerIDs) == 0 {
+		return &routerAffectedPeersData{}, nil
+	}
+
+	resources, err := transaction.GetNetworkResourcesByNetID(ctx, store.LockingStrengthNone, accountID, networkID)
+	if err != nil {
+		return nil, fmt.Errorf("failed to get network resources: %w", err)
+	}
+
+	var resourceGroupIDs []string
+	for _, resource := range resources {
+		if !resource.Enabled {
+			continue
+		}
+		groups, err := transaction.GetResourceGroups(ctx, store.LockingStrengthNone, accountID, resource.ID)
+		if err != nil {
+			return nil, fmt.Errorf("failed to get groups for resource %s: %w", resource.ID, err)
+		}
+		for _, g := range groups {
+			resourceGroupIDs = append(resourceGroupIDs, g.ID)
+		}
+	}
+
+	var policies []*nbtypes.Policy
+	if len(resourceGroupIDs) > 0 {
+		policies, err = transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
+		if err != nil {
+			return nil, fmt.Errorf("failed to get policies: %w", err)
+		}
+	}
+
+	return &routerAffectedPeersData{
+		routerPeerGroups: routerPeerGroups,
+		directPeerIDs:    directPeerIDs,
+		resourceGroupIDs: resourceGroupIDs,
+		policies:         policies,
+	}, nil
+}
+
+// resolveRouterAffectedPeers computes affected peer IDs from preloaded data outside the transaction.
+func (m *managerImpl) resolveRouterAffectedPeers(ctx context.Context, accountID string, data *routerAffectedPeersData) []string {
+	if data == nil {
+		return nil
+	}
+
+	log.WithContext(ctx).Tracef("resolveRouterAffectedPeers: routerPeerGroups=%v, directPeerIDs=%v, resourceGroupIDs=%v, policies=%d",
+		data.routerPeerGroups, data.directPeerIDs, data.resourceGroupIDs, len(data.policies))
+	groupSet := make(map[string]struct{})
+
+	for _, gID := range data.routerPeerGroups {
+		groupSet[gID] = struct{}{}
+	}
+
+	if len(data.resourceGroupIDs) > 0 {
+		collectPolicySourceGroups(data.policies, data.resourceGroupIDs, groupSet)
+	}
+
+	if len(groupSet) == 0 && len(data.directPeerIDs) == 0 {
+		return nil
+	}
+
+	peerIDs := resolveGroupsAndDirectPeers(ctx, m.store, accountID, groupSet, data.directPeerIDs)
+
+	log.WithContext(ctx).Tracef("resolveRouterAffectedPeers: result %d peers: %v", len(peerIDs), peerIDs)
+	return peerIDs
+}
+
+// collectPolicySourceGroups finds policies whose rules reference any of the destination group IDs
+// and adds their source groups to the groupSet.
+func collectPolicySourceGroups(policies []*nbtypes.Policy, destGroupIDs []string, groupSet map[string]struct{}) {
+	destSet := make(map[string]struct{}, len(destGroupIDs))
+	for _, gID := range destGroupIDs {
+		destSet[gID] = struct{}{}
+	}
+
+	for _, policy := range policies {
+		if policy == nil || !policy.Enabled {
+			continue
+		}
+		for _, rule := range policy.Rules {
+			if rule == nil || !rule.Enabled {
+				continue
+			}
+			if ruleMatchesDestinations(rule, destSet) {
+				for _, gID := range rule.Sources {
+					groupSet[gID] = struct{}{}
+				}
+			}
+		}
+	}
+}
+
+func ruleMatchesDestinations(rule *nbtypes.PolicyRule, destSet map[string]struct{}) bool {
+	for _, gID := range rule.Destinations {
+		if _, ok := destSet[gID]; ok {
+			return true
+		}
+	}
+	return false
+}
+
+func resolveGroupsAndDirectPeers(ctx context.Context, s store.Store, accountID string, groupSet map[string]struct{}, directPeerIDs []string) []string {
+	groupIDs := make([]string, 0, len(groupSet))
+	for gID := range groupSet {
+		groupIDs = append(groupIDs, gID)
+	}
+
+	peerIDs, err := s.GetPeerIDsByGroups(ctx, accountID, groupIDs)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to resolve peer IDs: %v", err)
+		return nil
+	}
+
+	if len(directPeerIDs) == 0 {
+		return peerIDs
+	}
+
+	seen := make(map[string]struct{}, len(peerIDs))
+	for _, id := range peerIDs {
+		seen[id] = struct{}{}
+	}
+	for _, id := range directPeerIDs {
+		if _, exists := seen[id]; !exists {
+			peerIDs = append(peerIDs, id)
+			seen[id] = struct{}{}
+		}
+	}
+	return peerIDs
+}
+
 func NewManagerMock() Manager {
 	return &mockManager{}
 }

management/server/networks/routers/manager_test.go

@@ -195,6 +195,7 @@ func Test_UpdateRouterSuccessfully(t *testing.T) {
 	if err != nil {
 		require.NoError(t, err)
 	}
+	router.ID = "testRouterId"
 
 	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
 	if err != nil {
@@ -210,6 +211,102 @@ func Test_UpdateRouterSuccessfully(t *testing.T) {
 	require.Equal(t, router.Metric, updatedRouter.Metric)
 }
 
+func Test_UpdateRouterRejectsCrossAccountID(t *testing.T) {
+	ctx := context.Background()
+	userID := "testAdminId"
+
+	// Admin of testAccountId tries to update a router that belongs to otherAccountId
+	// by passing the other account's router ID through the URL.
+	router, err := types.NewNetworkRouter("testAccountId", "testNetworkId", "testPeerId", []string{}, false, 1, true)
+	if err != nil {
+		require.NoError(t, err)
+	}
+	router.ID = "otherRouterId"
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(cleanUp)
+	permissionsManager := permissions.NewManager(s)
+	am := mock_server.MockAccountManager{}
+	manager := NewManager(s, permissionsManager, &am)
+
+	updatedRouter, err := manager.UpdateRouter(ctx, userID, router)
+	require.Error(t, err)
+	require.Nil(t, updatedRouter)
+
+	// The other account's router must be untouched.
+	stored, err := s.GetNetworkRouterByID(ctx, store.LockingStrengthNone, "otherAccountId", "otherRouterId")
+	require.NoError(t, err)
+	require.Equal(t, "otherAccountId", stored.AccountID)
+	require.Equal(t, "otherNetworkId", stored.NetworkID)
+	require.Equal(t, "otherPeer", stored.Peer)
+	require.Equal(t, 1, stored.Metric)
+}
+
+func Test_CreateRouterRejectsCrossAccountID(t *testing.T) {
+	ctx := context.Background()
+	userID := "testAdminId"
+
+	// Admin of testAccountId tries to create a router in otherAccountId's network.
+	// The permission check is on router.AccountID (their own), but the network
+	// lookup must fail because (testAccountId, otherNetworkId) does not exist.
+	router, err := types.NewNetworkRouter("testAccountId", "otherNetworkId", "testPeerId", []string{}, false, 1, true)
+	if err != nil {
+		require.NoError(t, err)
+	}
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(cleanUp)
+	permissionsManager := permissions.NewManager(s)
+	am := mock_server.MockAccountManager{}
+	manager := NewManager(s, permissionsManager, &am)
+
+	createdRouter, err := manager.CreateRouter(ctx, userID, router)
+	require.Error(t, err)
+	require.Nil(t, createdRouter)
+
+	// No router should have been created in either account's scope under otherNetworkId.
+	routersInOther, err := s.GetNetworkRoutersByNetID(ctx, store.LockingStrengthNone, "otherAccountId", "otherNetworkId")
+	require.NoError(t, err)
+	require.Len(t, routersInOther, 1)
+	require.Equal(t, "otherRouterId", routersInOther[0].ID)
+}
+
+func Test_UpdateRouterRejectsNetworkMismatch(t *testing.T) {
+	ctx := context.Background()
+	userID := "testAdminId"
+
+	// The router exists in testNetworkId, but the caller submits secondNetworkId
+	// (a different network in the same account). The update must be refused.
+	router, err := types.NewNetworkRouter("testAccountId", "secondNetworkId", "testPeerId", []string{}, false, 1, true)
+	if err != nil {
+		require.NoError(t, err)
+	}
+	router.ID = "testRouterId"
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(cleanUp)
+	permissionsManager := permissions.NewManager(s)
+	am := mock_server.MockAccountManager{}
+	manager := NewManager(s, permissionsManager, &am)
+
+	updatedRouter, err := manager.UpdateRouter(ctx, userID, router)
+	require.Error(t, err)
+	require.Nil(t, updatedRouter)
+
+	stored, err := s.GetNetworkRouterByID(ctx, store.LockingStrengthNone, "testAccountId", "testRouterId")
+	require.NoError(t, err)
+	require.Equal(t, "testNetworkId", stored.NetworkID)
+}
+
 func Test_UpdateRouterFailsWithPermissionDenied(t *testing.T) {
 	ctx := context.Background()
 	userID := "testUserId"

management/server/networks/routers/types/router.go

@@ -13,6 +13,9 @@ type NetworkRouter struct {
 	ID         string `gorm:"primaryKey"`
 	NetworkID  string `gorm:"index"`
 	AccountID  string `gorm:"index"`
+	// AccountSeqID is a per-account monotonically increasing identifier used as the
+	// compact wire id when sending NetworkMap components to capable peers.
+	AccountSeqID uint32 `json:"-" gorm:"index:idx_network_routers_account_seq_id;not null;default:0"`
 	Peer       string
 	PeerGroups []string `gorm:"serializer:json"`
 	Masquerade bool
@@ -78,14 +81,15 @@ func (n *NetworkRouter) FromAPIRequest(req *api.NetworkRouterRequest) {
 
 func (n *NetworkRouter) Copy() *NetworkRouter {
 	return &NetworkRouter{
-		ID:         n.ID,
-		NetworkID:  n.NetworkID,
-		AccountID:  n.AccountID,
-		Peer:       n.Peer,
-		PeerGroups: n.PeerGroups,
-		Masquerade: n.Masquerade,
-		Metric:     n.Metric,
-		Enabled:    n.Enabled,
+		ID:           n.ID,
+		NetworkID:    n.NetworkID,
+		AccountID:    n.AccountID,
+		AccountSeqID: n.AccountSeqID,
+		Peer:         n.Peer,
+		PeerGroups:   n.PeerGroups,
+		Masquerade:   n.Masquerade,
+		Metric:       n.Metric,
+		Enabled:      n.Enabled,
 	}
 }
 

management/server/networks/types/network.go

@@ -7,12 +7,24 @@ import (
 )
 
 type Network struct {
-	ID          string `gorm:"primaryKey"`
-	AccountID   string `gorm:"index"`
+	ID        string `gorm:"primaryKey"`
+	AccountID string `gorm:"index"`
+
+	// AccountSeqID is a per-account monotonically increasing identifier used as the
+	// compact wire id when sending NetworkMap components to capable peers.
+	AccountSeqID uint32 `json:"-" gorm:"index:idx_networks_account_seq_id;not null;default:0"`
+
 	Name        string
 	Description string
 }
 
+// HasSeqID reports whether the network has been persisted long enough to have
+// a per-account sequence id allocated. Wire encoders that key off AccountSeqID
+// must skip networks that return false here.
+func (n *Network) HasSeqID() bool {
+	return n != nil && n.AccountSeqID != 0
+}
+
 func NewNetwork(accountId, name, description string) *Network {
 	return &Network{
 		ID:          xid.New().String(),
@@ -41,13 +53,14 @@ func (n *Network) FromAPIRequest(req *api.NetworkRequest) {
 	}
 }
 
-// Copy returns a copy of a posture checks.
+// Copy returns a copy of a network.
 func (n *Network) Copy() *Network {
 	return &Network{
-		ID:          n.ID,
-		AccountID:   n.AccountID,
-		Name:        n.Name,
-		Description: n.Description,
+		ID:           n.ID,
+		AccountID:    n.AccountID,
+		AccountSeqID: n.AccountSeqID,
+		Name:         n.Name,
+		Description:  n.Description,
 	}
 }
 

management/server/peer.go

@@ -16,7 +16,6 @@ import (
 	"golang.org/x/exp/maps"
 
 	nbdns "github.com/netbirdio/netbird/dns"
-	"github.com/netbirdio/netbird/management/server/geolocation"
 	"github.com/netbirdio/netbird/management/server/idp"
 	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
@@ -29,6 +28,7 @@ import (
 
 	"github.com/netbirdio/netbird/management/server/activity"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
@@ -63,55 +63,66 @@ func (am *DefaultAccountManager) GetPeers(ctx context.Context, accountID, userID
 	return am.Store.GetUserPeers(ctx, store.LockingStrengthNone, accountID, userID)
 }
 
-// MarkPeerConnected marks peer as connected (true) or disconnected (false)
-// syncTime is used as the LastSeen timestamp and for stale request detection
-func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
-	var peer *nbpeer.Peer
-	var settings *types.Settings
-	var expired bool
-	var err error
-	var skipped bool
+// MarkPeerConnected marks a peer as connected with optimistic-locked
+// fencing on PeerStatus.SessionStartedAt. The sessionStartedAt argument
+// is the start time of the gRPC sync stream that owns this update,
+// expressed as Unix nanoseconds — only the call whose token is greater
+// than what's stored wins. LastSeen is written by the database itself;
+// we never pass it down.
+//
+// Disconnects use MarkPeerDisconnected and require the session to match
+// exactly; see PeerStatus.SessionStartedAt for the protocol.
+func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
+	start := time.Now()
+	defer func() {
+		am.metrics.AccountManagerMetrics().RecordPeerStatusUpdateDuration(telemetry.PeerStatusConnect, time.Since(start))
+	}()
 
-	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		peer, err = transaction.GetPeerByPeerPubKey(ctx, store.LockingStrengthUpdate, peerPubKey)
-		if err != nil {
-			return err
+	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
+	if err != nil {
+		outcome := telemetry.PeerStatusError
+		if s, ok := status.FromError(err); ok && s.Type() == status.NotFound {
+			outcome = telemetry.PeerStatusPeerNotFound
 		}
-
-		if connected && !syncTime.After(peer.Status.LastSeen) {
-			log.WithContext(ctx).Tracef("peer %s has newer activity (lastSeen=%s >= syncTime=%s), skipping connect",
-				peer.ID, peer.Status.LastSeen.Format(time.RFC3339), syncTime.Format(time.RFC3339))
-			skipped = true
-			return nil
-		}
-
-		expired, err = updatePeerStatusAndLocation(ctx, am.geo, transaction, peer, connected, realIP, accountID, syncTime)
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, outcome)
 		return err
-	})
-	if skipped {
+	}
+
+	updated, err := am.Store.MarkPeerConnectedIfNewerSession(ctx, accountID, peer.ID, sessionStartedAt)
+	if err != nil {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusError)
+		return err
+	}
+	if !updated {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusStale)
+		log.WithContext(ctx).Tracef("peer %s already has a newer session in store, skipping connect", peer.ID)
 		return nil
 	}
-	if err != nil {
-		return err
+	am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusApplied)
+
+	if am.geo != nil && realIP != nil {
+		am.updatePeerLocationIfChanged(ctx, accountID, peer, realIP)
 	}
 
+	expired := peer.Status != nil && peer.Status.LoginExpired
+
 	if peer.AddedWithSSOLogin() {
-		settings, err = am.Store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
+		settings, err := am.Store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
 		if err != nil {
 			return err
 		}
-
 		if peer.LoginExpirationEnabled && settings.PeerLoginExpirationEnabled {
 			am.schedulePeerLoginExpiration(ctx, accountID)
 		}
-
 		if peer.InactivityExpirationEnabled && settings.PeerInactivityExpirationEnabled {
 			am.checkAndSchedulePeerInactivityExpiration(ctx, accountID)
 		}
 	}
 
 	if expired {
-		err = am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID})
+		changedPeerIDs := []string{peer.ID}
+		affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+		err = am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs)
 		if err != nil {
 			return fmt.Errorf("notify network map controller of peer update: %w", err)
 		}
@@ -120,41 +131,60 @@ func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubK
 	return nil
 }
 
-func updatePeerStatusAndLocation(ctx context.Context, geo geolocation.Geolocation, transaction store.Store, peer *nbpeer.Peer, connected bool, realIP net.IP, accountID string, syncTime time.Time) (bool, error) {
-	oldStatus := peer.Status.Copy()
-	newStatus := oldStatus
-	newStatus.LastSeen = syncTime
-	newStatus.Connected = connected
-	// whenever peer got connected that means that it logged in successfully
-	if newStatus.Connected {
-		newStatus.LoginExpired = false
-	}
-	peer.Status = newStatus
+// MarkPeerDisconnected marks a peer as disconnected, but only when the
+// stored session token matches the one passed in. A mismatch means a
+// newer stream has already taken ownership of the peer — disconnects from
+// the older stream are ignored. LastSeen is written by the database.
+func (am *DefaultAccountManager) MarkPeerDisconnected(ctx context.Context, peerPubKey string, accountID string, sessionStartedAt int64) error {
+	start := time.Now()
+	defer func() {
+		am.metrics.AccountManagerMetrics().RecordPeerStatusUpdateDuration(telemetry.PeerStatusDisconnect, time.Since(start))
+	}()
 
-	if geo != nil && realIP != nil {
-		location, err := geo.Lookup(realIP)
-		if err != nil {
-			log.WithContext(ctx).Warnf("failed to get location for peer %s realip: [%s]: %v", peer.ID, realIP.String(), err)
-		} else {
-			peer.Location.ConnectionIP = realIP
-			peer.Location.CountryCode = location.Country.ISOCode
-			peer.Location.CityName = location.City.Names.En
-			peer.Location.GeoNameID = location.City.GeonameID
-			err = transaction.SavePeerLocation(ctx, accountID, peer)
-			if err != nil {
-				log.WithContext(ctx).Warnf("could not store location for peer %s: %s", peer.ID, err)
-			}
-		}
-	}
-
-	log.WithContext(ctx).Debugf("saving peer status for peer %s is connected: %t", peer.ID, connected)
-
-	err := transaction.SavePeerStatus(ctx, accountID, peer.ID, *newStatus)
+	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
 	if err != nil {
-		return false, err
+		outcome := telemetry.PeerStatusError
+		if s, ok := status.FromError(err); ok && s.Type() == status.NotFound {
+			outcome = telemetry.PeerStatusPeerNotFound
+		}
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, outcome)
+		return err
 	}
 
-	return oldStatus.LoginExpired, nil
+	updated, err := am.Store.MarkPeerDisconnectedIfSameSession(ctx, accountID, peer.ID, sessionStartedAt)
+	if err != nil {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusError)
+		return err
+	}
+	if !updated {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusStale)
+		log.WithContext(ctx).Tracef("peer %s session token mismatch on disconnect (token=%d), skipping",
+			peer.ID, sessionStartedAt)
+		return nil
+	}
+	am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusApplied)
+	return nil
+}
+
+// updatePeerLocationIfChanged refreshes the geolocation on a separate
+// row update, only when the connection IP actually changed. Geo lookups
+// are expensive so we skip same-IP reconnects.
+func (am *DefaultAccountManager) updatePeerLocationIfChanged(ctx context.Context, accountID string, peer *nbpeer.Peer, realIP net.IP) {
+	if peer.Location.ConnectionIP != nil && peer.Location.ConnectionIP.Equal(realIP) {
+		return
+	}
+	location, err := am.geo.Lookup(realIP)
+	if err != nil {
+		log.WithContext(ctx).Warnf("failed to get location for peer %s realip: [%s]: %v", peer.ID, realIP.String(), err)
+		return
+	}
+	peer.Location.ConnectionIP = realIP
+	peer.Location.CountryCode = location.Country.ISOCode
+	peer.Location.CityName = location.City.Names.En
+	peer.Location.GeoNameID = location.City.GeonameID
+	if err := am.Store.SavePeerLocation(ctx, accountID, peer); err != nil {
+		log.WithContext(ctx).Warnf("could not store location for peer %s: %s", peer.ID, err)
+	}
 }
 
 // UpdatePeer updates peer. Only Peer.Name, Peer.SSHEnabled, Peer.LoginExpirationEnabled and Peer.InactivityExpirationEnabled can be updated.
@@ -295,7 +325,10 @@ func (am *DefaultAccountManager) UpdatePeer(ctx context.Context, accountID, user
 		}
 	}
 
-	err = am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID})
+	changedPeerIDs := []string{peer.ID}
+	affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+	affectedPeerIDs = append(affectedPeerIDs, peer.ID)
+	err = am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs)
 	if err != nil {
 		return nil, fmt.Errorf("notify network map controller of peer update: %w", err)
 	}
@@ -453,6 +486,7 @@ func (am *DefaultAccountManager) DeletePeer(ctx context.Context, accountID, peer
 	var peer *nbpeer.Peer
 	var settings *types.Settings
 	var eventsToStore []func()
+	var affectedPeerIDs []string
 
 	serviceID, err := am.serviceManager.GetServiceIDByTargetID(ctx, accountID, peerID)
 	if err != nil {
@@ -477,6 +511,8 @@ func (am *DefaultAccountManager) DeletePeer(ctx context.Context, accountID, peer
 			return err
 		}
 
+		affectedPeerIDs = am.resolveAffectedPeersForPeerChanges(ctx, transaction, accountID, []string{peerID})
+
 		eventsToStore, err = deletePeers(ctx, am, transaction, accountID, userID, []*nbpeer.Peer{peer}, settings)
 		if err != nil {
 			return fmt.Errorf("failed to delete peer: %w", err)
@@ -500,7 +536,7 @@ func (am *DefaultAccountManager) DeletePeer(ctx context.Context, accountID, peer
 		log.WithContext(ctx).Errorf("failed to delete peer %s from integrated validator: %v", peerID, err)
 	}
 
-	if err = am.networkMapController.OnPeersDeleted(ctx, accountID, []string{peerID}); err != nil {
+	if err = am.networkMapController.OnPeersDeleted(ctx, accountID, []string{peerID}, affectedPeerIDs); err != nil {
 		log.WithContext(ctx).Errorf("failed to delete peer %s from network map: %v", peerID, err)
 	}
 
@@ -762,16 +798,19 @@ func (am *DefaultAccountManager) AddPeer(ctx context.Context, accountID, setupKe
 		newPeer.IP = freeIP
 
 		if len(settings.IPv6EnabledGroups) > 0 && network.NetV6.IP != nil {
-			var allGroupID string
-			if !peer.ProxyMeta.Embedded {
-				allGroup, err := am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, "All")
-				if err != nil {
-					log.WithContext(ctx).Debugf("get All group for IPv6 allocation: %v", err)
-				} else {
+			// Embedded proxy peers are not group members but participate in any
+			// IPv6-enabled overlay so reverse-proxy traffic reaches v6-only peers.
+			allocate := peer.ProxyMeta.Embedded
+			if !allocate {
+				var allGroupID string
+				if allGroup, err := am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, types.GroupAllName); err == nil {
 					allGroupID = allGroup.ID
+				} else {
+					log.WithContext(ctx).Debugf("get All group for IPv6 allocation: %v", err)
 				}
+				allocate = peerWillHaveIPv6(settings, peerAddConfig.GroupsToAdd, allGroupID)
 			}
-			if peerWillHaveIPv6(settings, peerAddConfig.GroupsToAdd, allGroupID) {
+			if allocate {
 				v6Prefix, err := netip.ParsePrefix(network.NetV6.String())
 				if err != nil {
 					return nil, nil, nil, fmt.Errorf("parse IPv6 prefix: %w", err)
@@ -870,7 +909,9 @@ func (am *DefaultAccountManager) AddPeer(ctx context.Context, accountID, setupKe
 		am.StoreEvent(ctx, opEvent.InitiatorID, opEvent.TargetID, opEvent.AccountID, opEvent.Activity, opEvent.Meta)
 	}
 
-	if err := am.networkMapController.OnPeersAdded(ctx, accountID, []string{newPeer.ID}); err != nil {
+	changedPeerIDs := []string{newPeer.ID}
+	affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+	if err := am.networkMapController.OnPeersAdded(ctx, accountID, changedPeerIDs, affectedPeerIDs); err != nil {
 		log.WithContext(ctx).Errorf("failed to update network map cache for peer %s: %v", newPeer.ID, err)
 	}
 
@@ -958,7 +999,9 @@ func (am *DefaultAccountManager) SyncPeer(ctx context.Context, sync types.PeerSy
 	}
 
 	if isStatusChanged || sync.UpdateAccountPeers || ipv6CapabilityChanged || (updated && (len(postureChecks) > 0 || versionChanged)) {
-		err = am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID})
+		changedPeerIDs := []string{peer.ID}
+		affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+		err = am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs)
 		if err != nil {
 			return nil, nil, nil, 0, fmt.Errorf("notify network map controller of peer update: %w", err)
 		}
@@ -1088,7 +1131,9 @@ func (am *DefaultAccountManager) LoginPeer(ctx context.Context, login types.Peer
 	}
 
 	if updateRemotePeers || isStatusChanged || ipv6CapabilityChanged || (isPeerUpdated && len(postureChecks) > 0) {
-		err = am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID})
+		changedPeerIDs := []string{peer.ID}
+		affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
+		err = am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs)
 		if err != nil {
 			return nil, nil, nil, fmt.Errorf("notify network map controller of peer update: %w", err)
 		}
@@ -1280,6 +1325,63 @@ func (am *DefaultAccountManager) UpdateAccountPeers(ctx context.Context, account
 	_ = am.networkMapController.UpdateAccountPeers(ctx, accountID, reason)
 }
 
+// UpdateAffectedPeers updates only the specified peers that belong to an account.
+func (am *DefaultAccountManager) UpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string) {
+	log.WithContext(ctx).Tracef("UpdateAffectedPeers: %d peers for account %s", len(peerIDs), accountID)
+	_ = am.networkMapController.UpdateAffectedPeers(ctx, accountID, peerIDs)
+}
+
+// resolvePeerIDs resolves group IDs and direct peer IDs into a deduplicated peer ID list.
+func (am *DefaultAccountManager) resolvePeerIDs(ctx context.Context, s store.Store, accountID string, groupIDs []string, directPeerIDs []string) []string {
+	peerIDs, err := s.GetPeerIDsByGroups(ctx, accountID, groupIDs)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to resolve peer IDs by groups: %v", err)
+		return nil
+	}
+
+	if len(directPeerIDs) == 0 {
+		log.WithContext(ctx).Tracef("resolvePeerIDs: groups=%v -> %d peers: %v", groupIDs, len(peerIDs), peerIDs)
+		return peerIDs
+	}
+
+	seen := make(map[string]struct{}, len(peerIDs))
+	for _, id := range peerIDs {
+		seen[id] = struct{}{}
+	}
+	for _, id := range directPeerIDs {
+		if _, exists := seen[id]; !exists {
+			peerIDs = append(peerIDs, id)
+			seen[id] = struct{}{}
+		}
+	}
+
+	log.WithContext(ctx).Tracef("resolvePeerIDs: groups=%v + directPeers=%v -> %d peers: %v", groupIDs, directPeerIDs, len(peerIDs), peerIDs)
+	return peerIDs
+}
+
+// BufferUpdateAffectedPeers accumulates peer IDs and flushes them after the buffer interval.
+func (am *DefaultAccountManager) BufferUpdateAffectedPeers(ctx context.Context, accountID string, peerIDs []string, reason types.UpdateReason) {
+	_ = am.networkMapController.BufferUpdateAffectedPeers(ctx, accountID, peerIDs, reason)
+}
+
+// resolveAffectedPeersForPeerChanges resolves changed peer IDs into the full set of affected peer IDs.
+func (am *DefaultAccountManager) resolveAffectedPeersForPeerChanges(ctx context.Context, s store.Store, accountID string, changedPeerIDs []string) []string {
+	groupIDs, err := s.GetGroupIDsByPeerIDs(ctx, accountID, changedPeerIDs)
+	if err != nil {
+		log.WithContext(ctx).Errorf("failed to get group IDs for changed peers: %v", err)
+		return nil
+	}
+
+	log.WithContext(ctx).Tracef("resolveAffectedPeersForPeerChanges: changedPeers=%v -> groups=%v", changedPeerIDs, groupIDs)
+
+	// Single pass: find entities referencing the changed groups OR the changed peers directly
+	allGroupIDs, directPeerIDs := collectPeerChangeAffectedGroups(ctx, s, accountID, groupIDs, changedPeerIDs)
+	result := am.resolvePeerIDs(ctx, s, accountID, allGroupIDs, directPeerIDs)
+
+	log.WithContext(ctx).Tracef("resolveAffectedPeersForPeerChanges: changedPeers=%v -> %d affected peers", changedPeerIDs, len(result))
+	return result
+}
+
 func (am *DefaultAccountManager) BufferUpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) {
 	_ = am.networkMapController.BufferUpdateAccountPeers(ctx, accountID, reason)
 }

management/server/peer/peer.go

@@ -13,8 +13,9 @@ import (
 
 // Peer capability constants mirror the proto enum values.
 const (
-	PeerCapabilitySourcePrefixes int32 = 1
-	PeerCapabilityIPv6Overlay    int32 = 2
+	PeerCapabilitySourcePrefixes      int32 = 1
+	PeerCapabilityIPv6Overlay         int32 = 2
+	PeerCapabilityComponentNetworkMap int32 = 3
 )
 
 // Peer represents a machine connected to the network.
@@ -74,8 +75,19 @@ type ProxyMeta struct {
 }
 
 type PeerStatus struct { //nolint:revive
-	// LastSeen is the last time peer was connected to the management service
+	// LastSeen is the last time the peer status was updated (i.e. the last
+	// time we observed the peer being alive on a sync stream). Written by
+	// the database (CURRENT_TIMESTAMP) — callers do not supply it.
 	LastSeen time.Time
+	// SessionStartedAt records when the currently-active sync stream began,
+	// stored as Unix nanoseconds. It acts as the optimistic-locking token
+	// for status updates: a stream is only allowed to mutate the peer's
+	// status when its own token strictly exceeds the stored token (when connecting)
+	// or matches it exactly (for disconnects). Zero means "no
+	// active session". Integer nanoseconds are used so equality is
+	// precision-safe across drivers, and so the predicates compose to a
+	// single bigint comparison.
+	SessionStartedAt int64 `gorm:"not null;default:0"`
 	// Connected indicates whether peer is connected to the management service or not
 	Connected bool
 	// LoginExpired
@@ -236,6 +248,14 @@ func (p *Peer) SupportsSourcePrefixes() bool {
 	return p.HasCapability(PeerCapabilitySourcePrefixes)
 }
 
+// SupportsComponentNetworkMap reports whether the peer assembles its
+// NetworkMap from server-shipped components instead of consuming a fully
+// expanded NetworkMap. Determines whether the network_map controller skips
+// Calculate() server-side and emits the components envelope.
+func (p *Peer) SupportsComponentNetworkMap() bool {
+	return p.HasCapability(PeerCapabilityComponentNetworkMap)
+}
+
 func capabilitiesEqual(a, b []int32) bool {
 	if len(a) != len(b) {
 		return false
@@ -375,10 +395,14 @@ func (p *Peer) EventMeta(dnsDomain string) map[string]any {
 	return meta
 }
 
-// Copy PeerStatus
+// Copy PeerStatus. SessionStartedAt must be propagated so clone-based
+// callers (Peer.Copy, MarkLoginExpired, UpdateLastLogin) don't silently
+// reset the fencing token to zero — that would let any subsequent
+// SavePeerStatus write reopen the optimistic-lock window.
 func (p *PeerStatus) Copy() *PeerStatus {
 	return &PeerStatus{
 		LastSeen:         p.LastSeen,
+		SessionStartedAt: p.SessionStartedAt,
 		Connected:        p.Connected,
 		LoginExpired:     p.LoginExpired,
 		RequiresApproval: p.RequiresApproval,

management/server/peer_test.go

@@ -1855,7 +1855,7 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 	t.Run("adding peer to unlinked group", func(t *testing.T) {
 		done := make(chan struct{})
 		go func() {
-			peerShouldReceiveUpdate(t, updMsg) //
+			peerShouldNotReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -1880,7 +1880,7 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 	t.Run("deleting peer with unlinked group", func(t *testing.T) {
 		done := make(chan struct{})
 		go func() {
-			peerShouldReceiveUpdate(t, updMsg)
+			peerShouldNotReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -2018,7 +2018,10 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 		}
 	})
 
-	// Adding peer to group linked with route should update account peers and send peer update
+	// drain any buffered updates from previous subtests
+	drainPeerUpdates(updMsg)
+
+	// Adding peer to group linked with route should update peers in that group, not unrelated peers
 	t.Run("adding peer to group linked with route", func(t *testing.T) {
 		route := nbroute.Route{
 			ID:          "testingRoute1",
@@ -2042,7 +2045,7 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 
 		done := make(chan struct{})
 		go func() {
-			peerShouldReceiveUpdate(t, updMsg)
+			peerShouldNotReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -2059,16 +2062,16 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 
 		select {
 		case <-done:
-		case <-time.After(peerUpdateTimeout):
-			t.Error("timeout waiting for peerShouldReceiveUpdate")
+		case <-time.After(time.Second):
+			t.Error("timeout waiting for peerShouldNotReceiveUpdate")
 		}
 	})
 
-	// Deleting peer with linked group to route should update account peers and send peer update
+	// Deleting peer with linked group to route should update peers in that group, not unrelated peers
 	t.Run("deleting peer with linked group to route", func(t *testing.T) {
 		done := make(chan struct{})
 		go func() {
-			peerShouldReceiveUpdate(t, updMsg)
+			peerShouldNotReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -2077,12 +2080,12 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 
 		select {
 		case <-done:
-		case <-time.After(peerUpdateTimeout):
-			t.Error("timeout waiting for peerShouldReceiveUpdate")
+		case <-time.After(time.Second):
+			t.Error("timeout waiting for peerShouldNotReceiveUpdate")
 		}
 	})
 
-	// Adding peer to group linked with name server group should update account peers and send peer update
+	// Adding peer to group linked with name server group should update peers in that group, not unrelated peers
 	t.Run("adding peer to group linked with name server group", func(t *testing.T) {
 		_, err = manager.CreateNameServerGroup(
 			context.Background(), account.Id, "nsGroup", "nsGroup", []nbdns.NameServer{{
@@ -2097,7 +2100,7 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 
 		done := make(chan struct{})
 		go func() {
-			peerShouldReceiveUpdate(t, updMsg)
+			peerShouldNotReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -2114,16 +2117,16 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 
 		select {
 		case <-done:
-		case <-time.After(peerUpdateTimeout):
-			t.Error("timeout waiting for peerShouldReceiveUpdate")
+		case <-time.After(time.Second):
+			t.Error("timeout waiting for peerShouldNotReceiveUpdate")
 		}
 	})
 
-	// Deleting peer with linked group to name server group should update account peers and send peer update
+	// Deleting peer with linked group to name server group should update peers in that group, not unrelated peers
 	t.Run("deleting peer with linked group to route", func(t *testing.T) {
 		done := make(chan struct{})
 		go func() {
-			peerShouldReceiveUpdate(t, updMsg)
+			peerShouldNotReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -2132,8 +2135,8 @@ func TestPeerAccountPeersUpdate(t *testing.T) {
 
 		select {
 		case <-done:
-		case <-time.After(peerUpdateTimeout):
-			t.Error("timeout waiting for peerShouldReceiveUpdate")
+		case <-time.After(time.Second):
+			t.Error("timeout waiting for peerShouldNotReceiveUpdate")
 		}
 	})
 }
@@ -2218,6 +2221,9 @@ func Test_IsUniqueConstraintError(t *testing.T) {
 		ID:        "test-peer-id",
 		AccountID: "bf1c8084-ba50-4ce7-9439-34653001fc3b",
 		DNSLabel:  "test-peer-dns-label",
+		Status: &nbpeer.PeerStatus{
+			LastSeen: time.Now(),
+		},
 	}
 
 	for _, tt := range tests {

management/server/policy.go

@@ -5,7 +5,7 @@ import (
 	_ "embed"
 
 	"github.com/rs/xid"
-	"github.com/sirupsen/logrus"
+	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
 	"github.com/netbirdio/netbird/management/server/permissions/operations"
@@ -45,44 +45,46 @@ func (am *DefaultAccountManager) SavePolicy(ctx context.Context, accountID, user
 	}
 
 	var isUpdate = policy.ID != ""
-	var updateAccountPeers bool
+	var existingPolicy *types.Policy
 	var action = activity.PolicyAdded
 	var unchanged bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		existingPolicy, err := validatePolicy(ctx, transaction, accountID, policy)
+		existingPolicy, err = validatePolicy(ctx, transaction, accountID, policy)
 		if err != nil {
 			return err
 		}
 
 		if isUpdate {
 			if policy.Equal(existingPolicy) {
-				logrus.WithContext(ctx).Tracef("policy update skipped because equal to stored one - policy id %s", policy.ID)
+				log.WithContext(ctx).Tracef("policy update skipped because equal to stored one - policy id %s", policy.ID)
 				unchanged = true
 				return nil
 			}
 
 			action = activity.PolicyUpdated
 
-			updateAccountPeers, err = arePolicyChangesAffectPeersWithExisting(ctx, transaction, policy, existingPolicy)
-			if err != nil {
-				return err
-			}
+			policy.AccountSeqID = existingPolicy.AccountSeqID
 
 			if err = transaction.SavePolicy(ctx, policy); err != nil {
 				return err
 			}
 		} else {
-			updateAccountPeers, err = arePolicyChangesAffectPeers(ctx, transaction, policy)
+			seq, err := transaction.AllocateAccountSeqID(ctx, accountID, types.AccountSeqEntityPolicy)
 			if err != nil {
 				return err
 			}
+			policy.AccountSeqID = seq
 
 			if err = transaction.CreatePolicy(ctx, policy); err != nil {
 				return err
 			}
 		}
 
+		groupIDs, directPeerIDs := collectPolicyAffectedGroupsAndPeers(ctx, policy, existingPolicy)
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, groupIDs, directPeerIDs)
+
 		return transaction.IncrementNetworkSerial(ctx, accountID)
 	})
 	if err != nil {
@@ -95,12 +97,11 @@ func (am *DefaultAccountManager) SavePolicy(ctx context.Context, accountID, user
 
 	am.StoreEvent(ctx, userID, policy.ID, accountID, action, policy.EventMeta())
 
-	if updateAccountPeers {
-		policyOp := types.UpdateOperationCreate
-		if isUpdate {
-			policyOp = types.UpdateOperationUpdate
-		}
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePolicy, Operation: policyOp})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Tracef("SavePolicy %s: updating %d affected peers: %v", policy.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("SavePolicy %s: no affected peers", policy.ID)
 	}
 
 	return policy, nil
@@ -117,7 +118,7 @@ func (am *DefaultAccountManager) DeletePolicy(ctx context.Context, accountID, po
 	}
 
 	var policy *types.Policy
-	var updateAccountPeers bool
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		policy, err = transaction.GetPolicyByID(ctx, store.LockingStrengthUpdate, accountID, policyID)
@@ -125,10 +126,8 @@ func (am *DefaultAccountManager) DeletePolicy(ctx context.Context, accountID, po
 			return err
 		}
 
-		updateAccountPeers, err = arePolicyChangesAffectPeers(ctx, transaction, policy)
-		if err != nil {
-			return err
-		}
+		groupIDs, directPeerIDs := collectPolicyAffectedGroupsAndPeers(ctx, policy)
+		affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, groupIDs, directPeerIDs)
 
 		if err = transaction.DeletePolicy(ctx, accountID, policyID); err != nil {
 			return err
@@ -142,8 +141,11 @@ func (am *DefaultAccountManager) DeletePolicy(ctx context.Context, accountID, po
 
 	am.StoreEvent(ctx, userID, policyID, accountID, activity.PolicyRemoved, policy.EventMeta())
 
-	if updateAccountPeers {
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePolicy, Operation: types.UpdateOperationDelete})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("DeletePolicy %s: updating %d affected peers: %v", policyID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("DeletePolicy %s: no affected peers", policyID)
 	}
 
 	return nil
@@ -162,44 +164,28 @@ func (am *DefaultAccountManager) ListPolicies(ctx context.Context, accountID, us
 	return am.Store.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
 }
 
-// arePolicyChangesAffectPeers checks if a policy (being created or deleted) will affect any associated peers.
-func arePolicyChangesAffectPeers(ctx context.Context, transaction store.Store, policy *types.Policy) (bool, error) {
-	for _, rule := range policy.Rules {
-		if rule.SourceResource.Type != "" || rule.DestinationResource.Type != "" {
-			return true, nil
+// collectPolicyAffectedGroupsAndPeers returns group IDs and direct peer IDs from the given policies.
+func collectPolicyAffectedGroupsAndPeers(ctx context.Context, policies ...*types.Policy) (groupIDs []string, directPeerIDs []string) {
+	for _, policy := range policies {
+		if policy == nil {
+			continue
+		}
+		ruleGroups := policy.RuleGroups()
+		log.WithContext(ctx).Tracef("collectPolicyAffectedGroupsAndPeers: policy %s (%s) ruleGroups=%v", policy.ID, policy.Name, ruleGroups)
+		groupIDs = append(groupIDs, ruleGroups...)
+		for _, rule := range policy.Rules {
+			if rule.SourceResource.Type == types.ResourceTypePeer && rule.SourceResource.ID != "" {
+				log.WithContext(ctx).Tracef("collectPolicyAffectedGroupsAndPeers: policy %s rule %s direct source peer %s", policy.ID, rule.ID, rule.SourceResource.ID)
+				directPeerIDs = append(directPeerIDs, rule.SourceResource.ID)
+			}
+			if rule.DestinationResource.Type == types.ResourceTypePeer && rule.DestinationResource.ID != "" {
+				log.WithContext(ctx).Tracef("collectPolicyAffectedGroupsAndPeers: policy %s rule %s direct destination peer %s", policy.ID, rule.ID, rule.DestinationResource.ID)
+				directPeerIDs = append(directPeerIDs, rule.DestinationResource.ID)
+			}
 		}
 	}
-
-	return anyGroupHasPeersOrResources(ctx, transaction, policy.AccountID, policy.RuleGroups())
-}
-
-func arePolicyChangesAffectPeersWithExisting(ctx context.Context, transaction store.Store, policy *types.Policy, existingPolicy *types.Policy) (bool, error) {
-	if !policy.Enabled && !existingPolicy.Enabled {
-		return false, nil
-	}
-
-	for _, rule := range existingPolicy.Rules {
-		if rule.SourceResource.Type != "" || rule.DestinationResource.Type != "" {
-			return true, nil
-		}
-	}
-
-	hasPeers, err := anyGroupHasPeersOrResources(ctx, transaction, policy.AccountID, existingPolicy.RuleGroups())
-	if err != nil {
-		return false, err
-	}
-
-	if hasPeers {
-		return true, nil
-	}
-
-	for _, rule := range policy.Rules {
-		if rule.SourceResource.Type != "" || rule.DestinationResource.Type != "" {
-			return true, nil
-		}
-	}
-
-	return anyGroupHasPeersOrResources(ctx, transaction, policy.AccountID, policy.RuleGroups())
+	log.WithContext(ctx).Tracef("collectPolicyAffectedGroupsAndPeers: result groupIDs=%v, directPeerIDs=%v", groupIDs, directPeerIDs)
+	return
 }
 
 // validatePolicy validates the policy and its rules. For updates it returns

management/server/policy_test.go

@@ -1319,12 +1319,14 @@ func TestPolicyAccountPeersUpdate(t *testing.T) {
 		}
 	})
 
-	// Updating disabled policy with destination and source groups containing peers should not update account's peers
-	// or send peer update
+	// Updating disabled policy with destination and source groups containing peers should still update account's peers
+	// because affected peer resolution does not filter by policy enabled state
 	t.Run("updating disabled policy with source and destination groups with peers", func(t *testing.T) {
+		drainPeerUpdates(updMsg)
+
 		done := make(chan struct{})
 		go func() {
-			peerShouldNotReceiveUpdate(t, updMsg)
+			peerShouldReceiveUpdate(t, updMsg)
 			close(done)
 		}()
 
@@ -1335,8 +1337,8 @@ func TestPolicyAccountPeersUpdate(t *testing.T) {
 
 		select {
 		case <-done:
-		case <-time.After(time.Second):
-			t.Error("timeout waiting for peerShouldNotReceiveUpdate")
+		case <-time.After(peerUpdateTimeout):
+			t.Error("timeout waiting for peerShouldReceiveUpdate")
 		}
 	})
 

management/server/posture/checks.go

@@ -47,10 +47,21 @@ type Checks struct {
 	// AccountID is a reference to the Account that this object belongs
 	AccountID string `json:"-" gorm:"index"`
 
+	// AccountSeqID is a per-account monotonically increasing identifier used as the
+	// compact wire id when sending NetworkMap components to capable peers.
+	AccountSeqID uint32 `json:"-" gorm:"index:idx_posture_checks_account_seq_id;not null;default:0"`
+
 	// Checks is a set of objects that perform the actual checks
 	Checks ChecksDefinition `gorm:"serializer:json"`
 }
 
+// HasSeqID reports whether the posture check has been persisted long enough
+// to have a per-account sequence id allocated. Wire encoders that key off
+// AccountSeqID must skip checks that return false here.
+func (pc *Checks) HasSeqID() bool {
+	return pc != nil && pc.AccountSeqID != 0
+}
+
 // ChecksDefinition contains definition of actual check
 type ChecksDefinition struct {
 	NBVersionCheck        *NBVersionCheck        `json:",omitempty"`
@@ -121,11 +132,12 @@ func (*Checks) TableName() string {
 // Copy returns a copy of a posture checks.
 func (pc *Checks) Copy() *Checks {
 	checks := &Checks{
-		ID:          pc.ID,
-		Name:        pc.Name,
-		Description: pc.Description,
-		AccountID:   pc.AccountID,
-		Checks:      pc.Checks.Copy(),
+		ID:           pc.ID,
+		Name:         pc.Name,
+		Description:  pc.Description,
+		AccountID:    pc.AccountID,
+		AccountSeqID: pc.AccountSeqID,
+		Checks:       pc.Checks.Copy(),
 	}
 	return checks
 }

management/server/posture_checks.go

@@ -5,6 +5,7 @@ import (
 	"slices"
 
 	"github.com/rs/xid"
+	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/management/server/activity"
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
@@ -41,9 +42,9 @@ func (am *DefaultAccountManager) SavePostureChecks(ctx context.Context, accountI
 		return nil, status.NewPermissionDeniedError()
 	}
 
-	var updateAccountPeers bool
 	var isUpdate = postureChecks.ID != ""
 	var action = activity.PostureCheckCreated
+	var affectedPeerIDs []string
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err = validatePostureChecks(ctx, transaction, accountID, postureChecks); err != nil {
@@ -51,12 +52,22 @@ func (am *DefaultAccountManager) SavePostureChecks(ctx context.Context, accountI
 		}
 
 		if isUpdate {
-			updateAccountPeers, err = arePostureCheckChangesAffectPeers(ctx, transaction, accountID, postureChecks.ID)
+			existing, err := transaction.GetPostureChecksByID(ctx, store.LockingStrengthNone, accountID, postureChecks.ID)
 			if err != nil {
 				return err
 			}
+			postureChecks.AccountSeqID = existing.AccountSeqID
 
 			action = activity.PostureCheckUpdated
+
+			groupIDs, directPeerIDs := collectPostureCheckAffectedGroupsAndPeers(ctx, transaction, accountID, postureChecks.ID)
+			affectedPeerIDs = am.resolvePeerIDs(ctx, transaction, accountID, groupIDs, directPeerIDs)
+		} else {
+			seq, err := transaction.AllocateAccountSeqID(ctx, accountID, types.AccountSeqEntityPostureCheck)
+			if err != nil {
+				return err
+			}
+			postureChecks.AccountSeqID = seq
 		}
 
 		postureChecks.AccountID = accountID
@@ -76,12 +87,11 @@ func (am *DefaultAccountManager) SavePostureChecks(ctx context.Context, accountI
 
 	am.StoreEvent(ctx, userID, postureChecks.ID, accountID, action, postureChecks.EventMeta())
 
-	if updateAccountPeers {
-		postureOp := types.UpdateOperationCreate
-		if isUpdate {
-			postureOp = types.UpdateOperationUpdate
-		}
-		am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePostureCheck, Operation: postureOp})
+	if len(affectedPeerIDs) > 0 {
+		log.WithContext(ctx).Debugf("SavePostureChecks %s: updating %d affected peers: %v", postureChecks.ID, len(affectedPeerIDs), affectedPeerIDs)
+		am.UpdateAffectedPeers(ctx, accountID, affectedPeerIDs)
+	} else {
+		log.WithContext(ctx).Tracef("SavePostureChecks %s: no affected peers", postureChecks.ID)
 	}
 
 	return postureChecks, nil
@@ -137,27 +147,25 @@ func (am *DefaultAccountManager) ListPostureChecks(ctx context.Context, accountI
 	return am.Store.GetAccountPostureChecks(ctx, store.LockingStrengthNone, accountID)
 }
 
-// arePostureCheckChangesAffectPeers checks if the changes in posture checks are affecting peers.
-func arePostureCheckChangesAffectPeers(ctx context.Context, transaction store.Store, accountID, postureCheckID string) (bool, error) {
+// collectPostureCheckAffectedGroupsAndPeers returns group IDs and peer IDs from policies referencing the posture check.
+func collectPostureCheckAffectedGroupsAndPeers(ctx context.Context, transaction store.Store, accountID, postureCheckID string) (groupIDs []string, directPeerIDs []string) {
 	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
 	if err != nil {
-		return false, err
+		log.WithContext(ctx).Errorf("failed to get policies for posture check affected peers resolution: %v", err)
+		return nil, nil
 	}
 
 	for _, policy := range policies {
 		if slices.Contains(policy.SourcePostureChecks, postureCheckID) {
-			hasPeers, err := anyGroupHasPeersOrResources(ctx, transaction, accountID, policy.RuleGroups())
-			if err != nil {
-				return false, err
-			}
-
-			if hasPeers {
-				return true, nil
-			}
+			log.WithContext(ctx).Tracef("collectPostureCheckAffectedGroupsAndPeers: posture check %s referenced by policy %s (%s)", postureCheckID, policy.ID, policy.Name)
+			gIDs, pIDs := collectPolicyAffectedGroupsAndPeers(ctx, policy)
+			groupIDs = append(groupIDs, gIDs...)
+			directPeerIDs = append(directPeerIDs, pIDs...)
 		}
 	}
 
-	return false, nil
+	log.WithContext(ctx).Tracef("collectPostureCheckAffectedGroupsAndPeers: postureCheck=%s -> groupIDs=%v, directPeerIDs=%v", postureCheckID, groupIDs, directPeerIDs)
+	return groupIDs, directPeerIDs
 }
 
 // validatePostureChecks validates the posture checks.

management/server/posture_checks_test.go

@@ -503,21 +503,20 @@ func TestArePostureCheckChangesAffectPeers(t *testing.T) {
 	require.NoError(t, err, "failed to save policy")
 
 	t.Run("posture check exists and is linked to policy with peers", func(t *testing.T) {
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
-		require.NoError(t, err)
-		assert.True(t, result)
+		groupIDs, _ := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
+		assert.NotEmpty(t, groupIDs)
 	})
 
 	t.Run("posture check exists but is not linked to any policy", func(t *testing.T) {
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, postureCheckB.ID)
-		require.NoError(t, err)
-		assert.False(t, result)
+		groupIDs, directPeerIDs := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, postureCheckB.ID)
+		assert.Empty(t, groupIDs)
+		assert.Empty(t, directPeerIDs)
 	})
 
 	t.Run("posture check does not exist", func(t *testing.T) {
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, "unknown")
-		require.NoError(t, err)
-		assert.False(t, result)
+		groupIDs, directPeerIDs := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, "unknown")
+		assert.Empty(t, groupIDs)
+		assert.Empty(t, directPeerIDs)
 	})
 
 	t.Run("posture check is linked to policy with no peers in source groups", func(t *testing.T) {
@@ -526,9 +525,8 @@ func TestArePostureCheckChangesAffectPeers(t *testing.T) {
 		_, err = manager.SavePolicy(context.Background(), account.Id, adminUserID, policy, true)
 		require.NoError(t, err, "failed to update policy")
 
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
-		require.NoError(t, err)
-		assert.True(t, result)
+		groupIDs, _ := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
+		assert.NotEmpty(t, groupIDs)
 	})
 
 	t.Run("posture check is linked to policy with no peers in destination groups", func(t *testing.T) {
@@ -537,9 +535,8 @@ func TestArePostureCheckChangesAffectPeers(t *testing.T) {
 		_, err = manager.SavePolicy(context.Background(), account.Id, adminUserID, policy, true)
 		require.NoError(t, err, "failed to update policy")
 
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
-		require.NoError(t, err)
-		assert.True(t, result)
+		groupIDs, _ := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
+		assert.NotEmpty(t, groupIDs)
 	})
 
 	t.Run("posture check is linked to policy but no peers in groups", func(t *testing.T) {
@@ -547,9 +544,9 @@ func TestArePostureCheckChangesAffectPeers(t *testing.T) {
 		err = manager.UpdateGroup(context.Background(), account.Id, adminUserID, groupA)
 		require.NoError(t, err, "failed to save groups")
 
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
-		require.NoError(t, err)
-		assert.False(t, result)
+		// The collector returns groups even if they have no peers — the groups are still referenced
+		groupIDs, _ := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
+		assert.NotEmpty(t, groupIDs)
 	})
 
 	t.Run("posture check is linked to policy with non-existent group", func(t *testing.T) {
@@ -558,8 +555,68 @@ func TestArePostureCheckChangesAffectPeers(t *testing.T) {
 		_, err = manager.SavePolicy(context.Background(), account.Id, adminUserID, policy, true)
 		require.NoError(t, err, "failed to update policy")
 
-		result, err := arePostureCheckChangesAffectPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
-		require.NoError(t, err)
-		assert.False(t, result)
+		// Non-existent groups are filtered out during SavePolicy validation,
+		// so the saved policy has empty Sources/Destinations
+		groupIDs, directPeerIDs := collectPostureCheckAffectedGroupsAndPeers(context.Background(), manager.Store, account.Id, postureCheckA.ID)
+		assert.Empty(t, groupIDs)
+		assert.Empty(t, directPeerIDs)
 	})
 }
+
+// TestSavePostureChecks_AllocatesSeqIDOnCreate verifies that the create path
+// (no incoming ID) allocates a non-zero AccountSeqID via the
+// account_seq_counters table.
+func TestSavePostureChecks_AllocatesSeqIDOnCreate(t *testing.T) {
+	am, _, err := createManager(t)
+	require.NoError(t, err)
+
+	account, err := initTestPostureChecksAccount(am)
+	require.NoError(t, err)
+
+	created, err := am.SavePostureChecks(context.Background(), account.Id, adminUserID, &posture.Checks{
+		Name: "seq-allocation-test",
+		Checks: posture.ChecksDefinition{
+			NBVersionCheck: &posture.NBVersionCheck{MinVersion: "0.26.0"},
+		},
+	}, true)
+	require.NoError(t, err)
+	require.NotZero(t, created.AccountSeqID, "SavePostureChecks on create must allocate a non-zero AccountSeqID")
+}
+
+// TestSavePostureChecks_PreservesSeqIDOnUpdate verifies the update path does
+// not reset AccountSeqID even when the caller passes a zero value (REST
+// handler shape, because the field is `json:"-"`).
+func TestSavePostureChecks_PreservesSeqIDOnUpdate(t *testing.T) {
+	am, _, err := createManager(t)
+	require.NoError(t, err)
+
+	account, err := initTestPostureChecksAccount(am)
+	require.NoError(t, err)
+
+	created, err := am.SavePostureChecks(context.Background(), account.Id, adminUserID, &posture.Checks{
+		Name: "seq-preserve-original",
+		Checks: posture.ChecksDefinition{
+			NBVersionCheck: &posture.NBVersionCheck{MinVersion: "0.26.0"},
+		},
+	}, true)
+	require.NoError(t, err)
+	originalSeq := created.AccountSeqID
+	require.NotZero(t, originalSeq)
+
+	update := &posture.Checks{
+		ID:   created.ID,
+		Name: "seq-preserve-renamed",
+		Checks: posture.ChecksDefinition{
+			NBVersionCheck: &posture.NBVersionCheck{MinVersion: "0.27.0"},
+		},
+	}
+	require.Zero(t, update.AccountSeqID, "incoming struct must mirror an HTTP handler shape")
+
+	_, err = am.SavePostureChecks(context.Background(), account.Id, adminUserID, update, false)
+	require.NoError(t, err)
+
+	got, err := am.GetPostureChecks(context.Background(), account.Id, created.ID, adminUserID)
+	require.NoError(t, err)
+	require.Equal(t, originalSeq, got.AccountSeqID, "AccountSeqID must survive SavePostureChecks update")
+	require.Equal(t, "seq-preserve-renamed", got.Name)
+}