Harden the elevation trust checks and narrow what one authorization applies

## Describe your changes

A group could be deleted while a reverse proxy service still referenced
it, silently breaking the service's access control: private services
list groups in `access_groups` as the peer allowlist, and SSO bearer
auth distributes tokens to `distribution_groups`.

Group deletion now runs through the same linkage validation as routes,
policies, and agent network policies: deleting a group that backs a
private service allowlist or an enabled bearer-auth distribution list
fails with a `GroupLinkError` naming the service domain. Disabled bearer
configs and stale `access_groups` on non-private services are inert and
do not block deletion.

Tests cover both linked cases in single and bulk deletion, and pin the
non-blocking cases. The test account seeds decoy services ahead of the
linked ones so the check is proven to scan the full service list.

.github/dependabot.yml

@@ -3,8 +3,8 @@ updates:
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
-      interval: "daily"
-    open-pull-requests-limit: 15
+      interval: "weekly"
+    open-pull-requests-limit: 3
     groups:
       actions:
         patterns:
@@ -22,9 +22,12 @@ updates:
     directories:
       - "/"
     schedule:
-      interval: "daily"
+      interval: "weekly"
     open-pull-requests-limit: 15
     groups:
+      golang-x-packages:
+        patterns:
+          - "golang.org/x/*"
       aws-sdk:
         patterns:
           - "github.com/aws/aws-sdk-go-v2/*"

.github/pull_request_template.md

@@ -2,6 +2,12 @@
 
 ## Issue ticket number and link
 
+<!--
+Required for anything that changes behavior. Link the issue (or the validated
+discussion it came from) that the NetBird team already agreed on. See
+https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#ticket-first-pr-second
+-->
+
 ## Stack
 
 <!-- branch-stack -->
@@ -12,7 +18,9 @@
 - [ ] 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).
+- [ ] I ran and tested this change locally — I did not rely on CI to find out whether it works
+- [ ] This PR has a single purpose (not a fix + refactor + feature in one)
+- [ ] This change is a trivial fix, **OR** it links an issue the NetBird team agreed on beforehand. Changes to the public API, gRPC protocols, functionality behavior, CLI / service flags, or new features always need that agreement first. See [CONTRIBUTING.md](https://github.com/netbirdio/netbird/blob/main/CONTRIBUTING.md#ticket-first-pr-second).
 
 > 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).
 

.github/workflows/agent-network-e2e.yml

@@ -5,6 +5,13 @@ on:
   schedule:
     - cron: "0 3 * * *"
   workflow_dispatch:
+    inputs:
+      bedrock_model:
+        description: >-
+          Bedrock inference-profile id to drive the matrix with, exactly as
+          AWS issues it. Leave empty for the Sonnet 4.6 default.
+        required: false
+        default: ""
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -51,6 +58,9 @@ jobs:
           # token (and URL, for gateways) is unset, so partial coverage is fine.
           OPENAI_TOKEN: ${{ secrets.E2E_OPENAI_TOKEN }}
           ANTHROPIC_TOKEN: ${{ secrets.E2E_ANTHROPIC_TOKEN }}
+          # Moonshot AI platform key (platform.kimi.ai); drives both Kimi wire
+          # shapes (OpenAI /v1 and Anthropic /anthropic) through kimi_api.
+          KIMI_TOKEN: ${{ secrets.E2E_KIMI_TOKEN }}
           VERCEL_URL: ${{ secrets.E2E_VERCEL_URL }}
           VERCEL_TOKEN: ${{ secrets.E2E_VERCEL_TOKEN }}
           OPENROUTER_URL: ${{ secrets.E2E_OPENROUTER_URL }}
@@ -59,6 +69,8 @@ jobs:
           CLOUDFLARE_TOKEN: ${{ secrets.E2E_CLOUDFLARE_TOKEN }}
           AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.E2E_AWS_BEARER_TOKEN_BEDROCK }}
           AWS_REGION: ${{ secrets.E2E_AWS_REGION }}
+          # Bedrock model override: dispatch input wins, then the repo variable, else the test default.
+          AWS_BEDROCK_MODEL: ${{ inputs.bedrock_model || vars.E2E_AWS_BEDROCK_MODEL }}
           # Vertex (Anthropic-on-Vertex): SA + project required; region defaults
           # to "global", model to a pinned claude snapshot.
           GOOGLE_VERTEX_SA_BASE64: ${{ secrets.E2E_GOOGLE_VERTEX_SA_BASE64 }}

.github/workflows/frontend-ui.yml

@@ -86,7 +86,7 @@ jobs:
             ${{ runner.os }}-pnpm-
 
       - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+        run: pnpm install --frozen-lockfile --ignore-scripts
 
       - name: Generate Wails bindings
         run: pnpm run bindings

.github/workflows/golangci-lint.yml

@@ -45,7 +45,7 @@ jobs:
             display_name: Linux
     name: ${{ matrix.display_name }}
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 15
+    timeout-minutes: 25
     steps:
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
@@ -79,4 +79,4 @@ jobs:
           skip-cache: true
           skip-save-cache: true
           cache-invalidation-interval: 0
-          args: --timeout=12m
+          args: --timeout=20m

.github/workflows/pr-title-check.yml

@@ -16,6 +16,8 @@ jobs:
             const allowedTags = [
               'management',
               'client',
+              'android',
+              'ios',
               'signal',
               'proxy',
               'relay',

.github/workflows/test-infrastructure-files.yml

@@ -249,78 +249,35 @@ jobs:
           docker compose exec management ls -l /var/lib/netbird/ | grep -i GeoLite2-City_[0-9]*.mmdb
           docker compose exec management ls -l /var/lib/netbird/ | grep -i geonames_[0-9]*.db
 
-  test-getting-started-script:
+  test-legacy-getting-started-scripts:
     runs-on: ubuntu-latest
     steps:
-      - name: Install jq
-        run: sudo apt-get install -y jq
-
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
         with:
           persist-credentials: false
 
-      - name: run script with Zitadel PostgreSQL
-        run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh
-
-      - name: test Caddy file gen postgres
-        run: test -f Caddyfile
-
-      - name: test docker-compose file gen postgres
-        run: test -f docker-compose.yml
-
-      - name: test management.json file gen postgres
-        run: test -f management.json
-
-      - name: test turnserver.conf file gen postgres
+      - name: Verify Dex retirement notice
         run: |
-          set -x
-          test -f turnserver.conf
-          grep external-ip turnserver.conf
+          if infrastructure_files/getting-started-with-dex.sh >stdout.txt 2>stderr.txt; then
+            echo "Expected the retired Dex installer to fail"
+            exit 1
+          fi
+          test ! -s stdout.txt
+          grep -Fq "Dex support is not deprecated." stderr.txt
+          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
+          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/local" stderr.txt
+          grep -Fq "removed in NetBird v0.80" stderr.txt
 
-      - name: test zitadel.env file gen postgres
-        run: test -f zitadel.env
-
-      - name: test dashboard.env file gen postgres
-        run: test -f dashboard.env
-
-      - name: test relay.env file gen postgres
-        run: test -f relay.env
-
-      - name: test zdb.env file gen postgres
-        run: test -f zdb.env
-
-      - name: Postgres run cleanup
+      - name: Verify Zitadel retirement notice
         run: |
-          docker compose down --volumes --rmi all
-          rm -rf docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json zdb.env
-
-      - name: run script with Zitadel CockroachDB
-        run: bash -x infrastructure_files/getting-started-with-zitadel.sh
-        env:
-          NETBIRD_DOMAIN: use-ip
-          ZITADEL_DATABASE: cockroach
-
-      - name: test Caddy file gen CockroachDB
-        run: test -f Caddyfile
-
-      - name: test docker-compose file gen CockroachDB
-        run: test -f docker-compose.yml
-
-      - name: test management.json file gen CockroachDB
-        run: test -f management.json
-
-      - name: test turnserver.conf file gen CockroachDB
-        run: |
-          set -x
-          test -f turnserver.conf
-          grep external-ip turnserver.conf
-
-      - name: test zitadel.env file gen CockroachDB
-        run: test -f zitadel.env
-
-      - name: test dashboard.env file gen CockroachDB
-        run: test -f dashboard.env
-
-      - name: test relay.env file gen CockroachDB
-        run: test -f relay.env
+          if bash infrastructure_files/getting-started-with-zitadel.sh >stdout.txt 2>stderr.txt; then
+            echo "Expected the retired Zitadel installer to fail"
+            exit 1
+          fi
+          test ! -s stdout.txt
+          grep -Fq "Zitadel support and existing Zitadel deployments are not deprecated." stderr.txt
+          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
+          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/zitadel" stderr.txt
+          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-guide" stderr.txt
+          grep -Fq "removed in NetBird v0.80" stderr.txt

.goreleaser.yaml

@@ -273,8 +273,8 @@ dockers_v2:
        - netbirdio/netbird
        - ghcr.io/netbirdio/netbird
      tags:
-       - "v{{ .Version }}-rootless"
-       - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
+       - "{{ .Version }}-rootless"
+       - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}rootless-latest{{ end }}"
      dockerfile: client/Dockerfile-rootless
      extra_files:
        - client/netbird-entrypoint.sh

.goreleaser_ui.yaml

@@ -24,6 +24,8 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
+    tags:
+      - production
 
   - id: netbird-ui-windows-amd64
     dir: client/ui
@@ -39,6 +41,8 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
+    tags:
+      - production
 
   - id: netbird-ui-windows-arm64
     dir: client/ui
@@ -55,6 +59,8 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
+    tags:
+      - production
 
 archives:
   - id: linux-arch
@@ -86,8 +92,15 @@ nfpms:
         dst: /usr/share/applications/org.wails.netbird.desktop
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
+      # Names the polkit action for the elevation prompt the app raises when an
+      # unprivileged user changes a privileged setting; without it the dialog
+      # shows a raw command line.
+      - src: client/ui/build/linux/polkit/io.netbird.settings.policy
+        dst: /usr/share/polkit-1/actions/io.netbird.settings.policy
     dependencies:
-      - netbird
+      - netbird (>= 0.75.0)
+      - libgtk-4-1 (>= 4.14)
+      - libwebkitgtk-6.0-4
 
   - maintainer: Netbird <dev@netbird.io>
     description: Netbird client UI.
@@ -107,8 +120,15 @@ nfpms:
         dst: /usr/share/applications/org.wails.netbird.desktop
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
+      # Names the polkit action for the elevation prompt the app raises when an
+      # unprivileged user changes a privileged setting; without it the dialog
+      # shows a raw command line.
+      - src: client/ui/build/linux/polkit/io.netbird.settings.policy
+        dst: /usr/share/polkit-1/actions/io.netbird.settings.policy
     dependencies:
-      - netbird
+      - netbird >= 0.75.0
+      - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
+      - (webkitgtk6.0 or libwebkitgtk-6_0-4)
 
     rpm:
       signature:

.goreleaser_ui_darwin.yaml

@@ -29,6 +29,8 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
+    tags:
+      - production
 
 universal_binaries:
   - id: netbird-ui-darwin

AGENTS.md

@@ -0,0 +1,514 @@
+# NetBird Agent Guidelines
+
+**NetBird** is an open-source connectivity platform: a WireGuard®-based overlay
+network with a control plane. The **agent** (`client/`) runs on user machines as
+a privileged daemon and manages the WireGuard interface, routing, firewall, and
+DNS. **Management** (`management/`) is the control plane and REST/gRPC API,
+**Signal** (`signal/`) brokers peer handshakes, **Relay** (`relay/`) carries
+traffic when a direct tunnel is impossible, and **Proxy** (`proxy/`) is the
+identity-aware proxy behind Agent Network.
+
+This file applies to the whole repository, and is the single source of truth for
+agent guidance here. `CLAUDE.md` is a one-line pointer to it — keep the guidance
+in this file, not duplicated there.
+
+## Contents
+
+- [NetBird Agent Guidelines](#netbird-agent-guidelines)
+  - [Contents](#contents)
+  - [STOP and ask the user before](#stop-and-ask-the-user-before)
+  - [Quick reference](#quick-reference)
+  - [Structure](#structure)
+  - [Where to look](#where-to-look)
+  - [Repo-wide principles](#repo-wide-principles)
+  - [Error handling](#error-handling)
+  - [Comments](#comments)
+  - [Testing](#testing)
+  - [Pitfalls](#pitfalls)
+  - [Commits, PRs, releases](#commits-prs-releases)
+  - [After you push: CI and review bots](#after-you-push-ci-and-review-bots)
+  - [Discussion and support](#discussion-and-support)
+
+## STOP and ask the user before
+
+- **Opening a pull request for anything beyond a trivial fix, without an agreed
+  ticket.** Ask the user directly: *"Is there a discussion or issue for this
+  change?"* NetBird is discussion-first — community reports start in
+  [Discussions](https://github.com/netbirdio/netbird/discussions), DevRel
+  validates them, and only validated discussions become issues. A PR that
+  changes behavior with no linked issue may be closed on arrival. If there is no
+  ticket, offer to draft the discussion post **instead of** the PR, and wait for
+  the user's call. Only typos, broken links, documentation corrections, and
+  one-line fixes that already have an issue can skip this.
+- **Designing in any high-risk area** (see
+  [CONTRIBUTING.md](CONTRIBUTING.md#high-risk-areas)): public API and OpenAPI
+  schema, gRPC protos, behavior existing deployments would notice after an
+  upgrade, peer connectivity (ICE, NAT traversal, relay selection, WireGuard® or
+  Rosenpass key handling), client system integration (routing, firewall, DNS,
+  interface), authentication and authorization, CLI or service flags, config
+  file format, daemon IPC, store schema and migrations, or a new feature. The
+  design gets agreed in the ticket before code is written.
+- **Writing a store migration or changing a persisted model.** Migrations are
+  one-way in the field and both the GORM and pgx paths may need the change.
+- **Hand-editing generated code.** `*.pb.go`, `*.gen.go`, and mocks are outputs.
+  Edit the source (`.proto`, `openapi.yml`) and rerun the matching
+  `generate.sh`.
+- **Adding, removing, or bumping a dependency**, and never vendor a fork.
+- **Weakening a security control** — authentication, authorization, certificate
+  verification, privilege dropping, or peer identity checks — even when it is
+  the fastest way to make a test pass.
+- **Force-pushing to `main`**, force-pushing any branch that is already under
+  review, amending pushed commits, or bypassing hooks with `--no-verify`.
+
+## Quick reference
+
+```bash
+# Build
+go build ./...
+cd client && CGO_ENABLED=0 go build .        # agent
+cd management && go build .                  # management service
+cd signal && go build .                      # signal service
+
+# Verify (run before every push)
+go fmt ./...
+make lint            # golangci-lint on files changed vs origin/main (also the pre-push hook)
+make lint-all        # full-repository lint, matches CI
+make test-unit       # host-safe unit tests, -tags devcert, no sudo
+make test-privileged # privileged-tagged suite in a Docker container with NET_ADMIN
+make setup-hooks     # wire make lint into .githooks/pre-push
+
+# Narrow runs
+go test ./client/internal/dns/...
+go test -race -run TestPeerConn ./client/internal/peer/...
+PRIV_RUN=TestNftablesManager PRIV_PKGS=./client/firewall/nftables/... make test-privileged
+
+# Code generation (never hand-edit the output)
+./shared/management/http/api/generate.sh   # REST types from openapi.yml
+./shared/management/proto/generate.sh
+./shared/signal/proto/generate.sh
+./client/proto/generate.sh
+./flow/proto/generate.sh
+
+# Run locally (lab only, never on a machine you rely on)
+sudo ./client/netbird up --log-level debug --log-file console
+sudo ./client/netbird down                   # teardown: restores routing, firewall, DNS
+./signal/signal run --log-level debug --log-file console
+./management/management management --log-level debug --log-file console --config ./management.json
+```
+
+`netbird up` needs root and rewrites the host's routing table, firewall rules,
+DNS configuration, and WireGuard® interface. Run it only in a disposable test
+environment (a VM, container, or throwaway host) that you can rebuild, never on
+a workstation or server whose connectivity matters. Run `sudo netbird down`
+before you stop working, before rebuilding the binary, and on every failure
+path, so the host's networking state is restored instead of left half-applied.
+See [Pitfalls](#pitfalls) for why cleanup on every exit path matters.
+
+## Structure
+
+```text
+netbird/
+├── client/              NetBird agent
+│   ├── cmd/             agent CLI
+│   ├── internal/        agent business logic (engine, peer, dns, routemanager, ...)
+│   ├── server/          daemon for background execution
+│   ├── proto/           daemon gRPC protos
+│   ├── iface/           WireGuard® interface management
+│   ├── firewall/        nftables, iptables, pf, WFP, userspace backends
+│   ├── ssh/             built-in SSH server and client
+│   ├── ui/              desktop UI (Wails v3 + React)
+│   ├── android/, ios/   mobile bindings
+│   ├── wasm/            WebAssembly build
+│   └── mdm/, system/    MDM policy, host information
+├── management/          control plane
+│   └── server/          account, peer, groups, networks, posture, permissions,
+│                        settings, store, http (REST), idp, integrations, migration
+├── signal/              handshake broker (peer/, server/)
+├── relay/               relay service (protocol/, server/, healthcheck/)
+├── proxy/               identity-aware proxy (llm/, acme/, accesslog/, middleware/, tcp/, udp/)
+├── agent-network/       Agent Network overview
+├── shared/              imported by both agent and services
+│   ├── management/      proto/, client/, http/api (OpenAPI + generated types)
+│   ├── signal/          proto/, client/
+│   └── relay/, auth/, sshauth/, metrics/
+├── e2e/                 end-to-end suites and harness
+├── encryption/, dns/, route/, stun/, sharedsock/, util/, flow/
+├── infrastructure_files/  docker compose and getting-started templates
+└── release_files/       files packaged into releases
+```
+
+## Where to look
+
+| Task                        | Location                                                     |
+| --------------------------- | ------------------------------------------------------------ |
+| REST API / OpenAPI          | `shared/management/http/api/` + `management/server/http/`    |
+| Management gRPC protocol    | `shared/management/proto/`                                   |
+| Signal protocol             | `shared/signal/proto/`                                       |
+| Daemon IPC protocol         | `client/proto/`                                              |
+| Peer connection and NAT     | `client/internal/peer/`                                      |
+| Network map handling        | `client/internal/engine.go`, `shared/management/networkmap/` |
+| Routing                     | `client/internal/routemanager/`, `route/`                    |
+| Firewall backends           | `client/firewall/`                                           |
+| DNS                         | `client/internal/dns/`, `dns/`                               |
+| WireGuard® interface        | `client/iface/`                                              |
+| Persistence and migrations  | `management/server/store/`, `management/server/migration/`   |
+| IdP integrations            | `management/server/idp/`                                     |
+| Permissions model           | `management/server/permissions/`                             |
+| LLM routing / Agent Network | `proxy/internal/llm/`, `agent-network/`                      |
+| End-to-end tests            | `e2e/`                                                       |
+
+## Repo-wide principles
+
+1. **Run `go fmt` on every modified Go file.** Formatting is not optional.
+2. **Zero unaddressed diagnostics.** Fix IDE and linter warnings on code you
+   touch, and delete imports, helpers, and parameters your refactor orphaned.
+   Exception: unused parameters in shared code may be consumed by builds outside
+   this repository — do not remove them, ask instead.
+3. **Function comments are mandatory for exported functions**, written as full
+   sentences with a period, starting with the identifier name.
+4. **Prefer private functions and constants.** Export only what a caller outside
+   the package genuinely needs.
+5. **Early returns and guard clauses.** Handle errors and edge cases first
+   instead of nesting `if`/`else` chains.
+6. **Split complex functions.** If a function trips a complexity warning, break
+   it into named helpers rather than silencing the warning.
+7. **Avoid LLM-slop tells:** em dashes, hedging narration, restating the diff in
+   prose, trailing summaries. Defaults, not absolute bans. Applies to code,
+   comments, commit messages, and PR descriptions alike.
+8. **Concurrency: do a two-pass race analysis after every change** that adds
+   shared state. Guard maps and slices with a mutex, keep critical sections
+   short, and run `go test -race` on the touched packages.
+9. **Cross-platform builds must keep working.** The agent targets Linux, macOS,
+   Windows, FreeBSD, Android, and iOS. When you add a platform-specific file,
+   add the counterpart or a build-tagged fallback for the others.
+10. **Never hand-edit generated files.** Change the source and regenerate.
+11. **Never log secrets** — private keys, setup keys, tokens, PAT values — and
+    keep peer IPs and hostnames out of logs above debug level.
+
+## Error handling
+
+Use single-assignment form when the error is only needed inside the `if`:
+
+```go
+// Good
+if err := someCall(); err != nil {
+    return fmt.Errorf("context: %w", err)
+}
+
+// Bad - unnecessary split
+err := someCall()
+if err != nil {
+    return fmt.Errorf("context: %w", err)
+}
+```
+
+Use multiple assignment when the value is needed after the block:
+
+```go
+result, err := someCall()
+if err != nil {
+    return fmt.Errorf("context: %w", err)
+}
+```
+
+Add short, meaningful context, and **do not** start `fmt.Errorf` messages with
+obvious words like "failed to" or "error":
+
+```go
+// Good
+return fmt.Errorf("parse remote address: %w", err)
+return fmt.Errorf("listen on %s: %w", addr, err)
+
+// Bad
+return fmt.Errorf("failed to parse remote address: %w", err)
+return fmt.Errorf("error listening on %s: %w", addr, err)
+
+// "failed" is fine in log messages
+log.Debugf("failed to parse remote address: %v", err)
+```
+
+Skip the wrapping when a function only extracts or delegates and the wrap would
+add nothing:
+
+```go
+func parseAddr(addr string) (string, int, error) {
+    host, portStr, err := net.SplitHostPort(addr)
+    if err != nil {
+        return "", 0, err
+    }
+    // ...
+}
+```
+
+Log the errors you choose not to act on:
+
+- `log.Debugf()` for errors that do not affect program flow but help debugging.
+- `log.Tracef()` for very verbose errors that would otherwise spam logs.
+- **Never ignore** errors from writes, network sends, or critical cleanup.
+- Close errors may be ignored for read-only operations; log them at debug for
+  writes.
+
+## Comments
+
+Comment the **why**, never the **what**. Default to no comment, and add one only
+when a hidden constraint or workaround would surprise a future reader. Never
+reference the current task, PR, or your own changes in a comment.
+
+```go
+// Bad - trailing comments explaining the obvious
+defer localConn.Close() // Close the connection
+if err != nil {         // Check if error occurred
+
+// Good
+defer localConn.Close()
+
+// Good - explains a non-obvious constraint
+// Use incremental checksum update per RFC 1624 for performance.
+checksum = updateChecksum(checksum, oldPort, newPort)
+```
+
+### Length budget
+
+- **90 characters per line.** Wrap the comment, do not run past it.
+- **250 characters per comment**, roughly three wrapped lines. Doc comments on
+  exported identifiers may exceed it when the API genuinely needs the
+  explanation; inline comments inside a function body may not.
+
+The budget is a smell detector, not a rule to game. Do not compress a needed
+explanation into cryptic shorthand to fit — if a block of code needs more than
+250 characters of prose, the code is doing too much. Fix the code:
+
+- **Extract a named function.** A well-named function replaces the comment: the
+  name says *what*, the body shows *how*, and the comment you no longer write
+  was the *what* anyway. Clean Code calls this "explain yourself in code".
+- **Extract a named constant or predicate.** `if isExpiredSetupKey(key)` needs
+  no comment; `if key.ExpiresAt.Before(now) && !key.Revoked && key.UsageLimit > 0`
+  does.
+- **Keep the surviving comment for the why** — the RFC, the kernel quirk, the
+  ordering constraint. That part is usually one or two lines.
+
+### Long switch and if/else chains
+
+A `switch` whose cases carry multi-line explanations is the usual place this
+budget is breached, and the comment is a symptom. In order of preference:
+
+1. **Extract each case body into a named function.** The case becomes one line,
+   the name carries the meaning, and the switch reads as a table of contents.
+2. **Replace the switch with a lookup table** — `map[Kind]handlerFunc` — when the
+   branches are uniform. Adding a case stops meaning editing a growing function.
+3. **Replace conditional with polymorphism** when branches vary by type and the
+   same switch shape starts appearing in more than one place. Clean Code's rule
+   of thumb: tolerate a switch statement if it appears **once**, is buried in a
+   factory that returns an interface, and no other switch dispatches on the same
+   type. A second switch over the same enum is the signal to introduce the
+   interface.
+
+Do not restructure a switch purely to satisfy the budget when the cases are one
+line each and self-evident — a flat, boring `switch` over an enum is fine and
+needs no comments at all.
+
+Explanatory comments in tests are welcome — they document the scenario being set
+up, and the 250-character budget does not apply to them.
+
+## Testing
+
+- **Unit tests** live beside the code as `_test.go`. `make test-unit` runs the
+  host-safe set with `-tags devcert` and no sudo.
+- **Privileged tests** carry the `privileged` build tag and mutate host
+  networking. They run through `make test-privileged`, inside a Docker container
+  with `NET_ADMIN`. Never bypass that harness by running them directly on the
+  host.
+- **End-to-end suites** live in `e2e/` with a shared harness.
+- **Test real behavior, not API existence.** Assert on the observable end state
+  a consumer would see — bytes that arrived, the packet after translation, the
+  row after the write — not merely that a method exists or returns an error.
+- **Avoid mocks for code we own.** Exercise the real store, manager, or
+  controller and assert what the caller actually receives.
+- **`require` for setup and preconditions, `assert` for the conditions under
+  test.** Use `require` whenever a later line would panic or be meaningless
+  otherwise.
+- **Message guidance:** optional for `NoError`/`Error`; always give context for
+  comparison, boolean, and collection assertions.
+
+```go
+server, err := StartTestServer()
+require.NoError(t, err, "Test server setup must succeed")
+defer server.Close()
+
+result, err := client.DoOperation()
+assert.NoError(t, err)
+assert.Equal(t, expectedResult, result, "Result should match expected")
+```
+
+## Pitfalls
+
+- **The agent runs as root.** Anything touching routing, firewall, DNS, or the
+  interface can take a user's machine off the network. Prefer a reversible
+  change and make sure cleanup runs on every exit path.
+- **Management has two account loaders** (GORM and pgx). Adding a relation to an
+  account often means updating both, or it silently comes back empty in
+  production.
+- **`go test ./...` without `-tags devcert` skips tests** that need the
+  development certificate. Use `make test-unit`.
+- **`make lint` only checks the diff against `origin/main`.** CI runs
+  `make lint-all`; run it too before pushing a large change.
+- **Protos are consumed by released clients.** An old agent must keep working
+  against a new Management, so fields are added, never renumbered or removed.
+- **Windows requires the wintun driver**, and the daemon serves a named pipe
+  (`npipe://netbird`) rather than loopback TCP. Loopback TCP carries no caller
+  identity, so privileged operations are refused over it.
+
+## Commits, PRs, releases
+
+- **PR titles must start with a bracketed tag.** Before you propose a title,
+  **read [`.github/workflows/pr-title-check.yml`](.github/workflows/pr-title-check.yml)
+  and take the allowed tags from the `allowedTags` array in that file.** It is
+  the only source of truth, it changes as components are added, and the check
+  runs on every title edit — a tag that is not in that array is a red build. Do
+  not rely on a list memorized from anywhere else, including this file.
+
+  ```text
+  [client] Authorize daemon IPC callers by their local identity
+  [management,client] Add MDM policy support
+  ```
+
+  Multiple tags are comma-separated inside one pair of brackets. Match the tag
+  to the component you actually changed, not to the one you read the most.
+
+- **Use the repository's PR template.** Fill in
+  [`.github/pull_request_template.md`](.github/pull_request_template.md) rather
+  than replacing it with your own summary: describe the change, link the issue,
+  tick the checklist honestly (including "ran locally" and "single purpose"),
+  and complete the documentation section. Do not tick a box you have not
+  verified, and do not delete rows that do not apply.
+
+- **Keep the PR description short.** Under 1000 words on top of the template's
+  own text, and usually far less — a few paragraphs. Reviewers read the diff;
+  the description exists to explain what the diff cannot say for itself. This is
+  well below what an agent will produce by default, so cut before you post.
+
+- **Body: why before what.** Lead with the problem and the reason for this
+  approach, then the shape of the change. No bullet list of files changed, no
+  per-function walkthrough, no restating the diff in prose, no trailing summary
+  section, no self-congratulatory closing line.
+
+- **No `Co-Authored-By` or tool-attribution trailers in the PR description**,
+  and none in commits either. Contributors own their contributions. Whatever
+  tooling produced the diff, the person opening the PR is its author: they have
+  read every line, they can explain why it works, they can answer review
+  questions without going back to a model, and they are accountable for the
+  consequences of merging it. Do not add a trailer, footer, or description line
+  that spreads that ownership onto a tool.
+
+- **Commit subjects follow the same `[scope] Subject` convention.** Keep the
+  subject short, and use the body for why before what. No bullet lists of files
+  changed.
+
+- **Push review fixes as separate commits.** The PR is squashed on merge, so
+  there is no reason to rewrite history mid-review; many small commits make the
+  re-review readable.
+
+- **Do not force-push a branch that is under review.** A force-push detaches
+  existing review comments from the lines they were written against, destroys
+  the "changes since your last review" diff a reviewer relies on, and discards
+  the CI history that showed which commit broke what. Add commits instead —
+  including for fixups and reverts. Force-push only when there is no
+  alternative: a rebase to clear a genuine conflict, or removing a secret or a
+  large binary that was committed by mistake. When you must, ask the user first,
+  then say so in a PR comment so reviewers know their anchors moved. Never
+  force-push `main`, and never force-push a branch you do not own.
+
+- **One PR, one purpose.** Split refactors out of fixes and fixes out of
+  features.
+
+- **Keep the PR small.** Size is the single strongest predictor of how long a PR
+  waits. Aim for **under ~400 changed lines across under ~20 files**; past
+  roughly **1000 lines or 50 files** a community PR is likely to be sent back to
+  be split, or left unreviewed until it is. Large PRs from outside the core team
+  may be blocked outright when the size was never agreed in the ticket —
+  reviewing a sprawling change against a privileged networking daemon is a
+  security risk in itself, not just a time cost.
+
+  Judge the size by hand-written code: exclude generated output, `go.sum`,
+  vendored files, and test fixtures from the estimate, but do not use their
+  presence to argue a 3000-line PR is small.
+
+  When a change genuinely cannot be small — a protocol migration, a
+  cross-component rename — agree the split in the ticket **before** writing
+  code, and land it as a sequence of PRs that each build, test, and make sense
+  on their own. Propose that split to the user rather than opening one large PR
+  and hoping.
+
+- **User-facing changes need a docs PR** in
+  [netbirdio/docs](https://github.com/netbirdio/docs), linked from the PR
+  description.
+
+## After you push: CI and review bots
+
+Opening the PR is not the end of the task. Watch the run, read what the bots
+say, and drive the PR to green before you report the work as done.
+
+```bash
+gh pr checks <pr>            --watch    # all checks, live
+gh run view <run-id> --log-failed       # only the failing steps
+gh pr view <pr> --comments              # bot and human review comments
+```
+
+**Never report a change as finished while checks are pending or red**, and never
+describe a red PR as passing. If you ran out of turn before CI finished, say
+which checks were still running.
+
+### The checks
+
+- **Go tests** — `golang-test-{linux,darwin,windows,freebsd}.yml`, sharded per
+  component. A failure in a component you did not touch is usually a real
+  interaction, not noise; read the log before assuming flake.
+- **golangci-lint** — `golangci-lint.yml` runs the full repository, while
+  `make lint` only checks your diff. A clean local lint does not guarantee green
+  CI on a large change.
+- **PR Title Check** — `pr-title-check.yml`, see above.
+- **Codecov** — uploaded from the Linux test workflow with per-component flags
+  (`unit,client`, `unit,management`, `unit,relay`, `unit,proxy`, `unit,signal`,
+  `integration,management`). Coverage on new code should not go backwards. Add
+  tests for the paths you introduced; do not adjust thresholds or exclude files
+  to clear the report.
+- **CodeRabbit** — configured in [`.coderabbit.yaml`](.coderabbit.yaml): `chill`
+  profile, auto-review on every non-draft PR, TypeScript/JavaScript/SVG paths
+  filtered out. Chat auto-reply is on, so `@coderabbitai` in a comment reaches
+  it.
+- **SonarCloud** — project `netbirdio_netbird`, quality gate on new code (bugs,
+  vulnerabilities, code smells, duplication, coverage).
+- **Snyk** — dependency and code scanning.
+
+Sonar and Snyk report as GitHub App checks rather than workflows in this
+repository, so their detail lives on the PR check, not in the Actions logs.
+
+### Handling bot findings
+
+- **Read every comment and act on it.** Either fix it, or reply with the reason
+  it does not apply. Do not bulk-resolve threads to clear the count, and do not
+  silently ignore a finding because the check is advisory.
+- **Bots are frequently wrong here.** NetBird has privileged, platform-specific,
+  and concurrency-heavy code that static analysis reads poorly. A confident
+  CodeRabbit or Sonar comment can still be nonsense. Verify the claim against
+  the code before you change anything — never edit correct code just to silence
+  a bot.
+- **Security findings get the opposite default.** For a Snyk or Sonar
+  vulnerability, or a CodeRabbit comment about authentication, authorization,
+  certificate verification, or key handling, assume it is real until you have
+  disproved it. Surface it to the user rather than dismissing it yourself.
+- **A new vulnerable dependency is a stop.** Bumping or replacing dependencies
+  needs the user's decision, as above.
+- **Never change a workflow, threshold, lint exclusion, or bot config to make a
+  check pass.** If a check is genuinely wrong, say so and let the user decide.
+- **Do not paper over flakes with blind re-runs.** Identify the failure first. If
+  it is a known flake, name it; if you cannot tell, report it as unresolved
+  rather than re-running until it goes green.
+
+## Discussion and support
+
+- Discussions: <https://github.com/netbirdio/netbird/discussions>
+- Slack: <https://docs.netbird.io/slack-url>
+- Docs: <https://docs.netbird.io>
+- Security: <https://github.com/netbirdio/netbird/security/policy> — never in public
+- Contribution process: [CONTRIBUTING.md](CONTRIBUTING.md)

CLAUDE.md

@@ -0,0 +1 @@
+See [AGENTS.md](AGENTS.md) for the agent guidelines in this repository.

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Contributing to NetBird
 
-Thanks for your interest in contributing to NetBird. 
+Thanks for your interest in contributing to NetBird.
 
 There are many ways that you can contribute:
 - Reporting issues
@@ -10,12 +10,99 @@ There are many ways that you can contribute:
 
 If you haven't already, join our slack workspace [here](https://docs.netbird.io/slack-url), we would love to discuss topics that need community contribution and enhancements to existing features.
 
+## Ticket first, PR second
+
+**Open a ticket and wait for feedback before you open a pull request.** Every PR
+that changes behavior must link to an issue the NetBird team has agreed on. A PR
+that arrives without one may be closed and redirected to a discussion, no matter
+how good the code is.
+
+Issues in this repository are maintainer-curated work items, so the flow starts
+in [Discussions](https://github.com/netbirdio/netbird/discussions):
+
+1. **Open a discussion.** Use
+   [Issue Triage](https://github.com/netbirdio/netbird/discussions/new?category=issue-triage)
+   for a bug, regression, or unexpected behavior, and
+   [Ideas & Feature Requests](https://github.com/netbirdio/netbird/discussions/new?category=ideas-feature-requests)
+   for a feature, enhancement, or integration idea. Setup and usage questions
+   belong in
+   [Q&A / Support](https://github.com/netbirdio/netbird/discussions/new?category=q-a-support).
+   Never report a security vulnerability in public — follow the
+   [security policy](https://github.com/netbirdio/netbird/security/policy)
+   instead.
+2. **Wait for feedback.** DevRel validates and reproduces the report, and a
+   maintainer confirms the direction. We may ask for more detail or propose a
+   different approach. Validated discussions become issues.
+3. **Then write the code**, following the approach agreed in the issue, and open
+   the PR linking that issue.
+
+Trivial fixes — a typo, a broken link, a documentation correction, or a one-line
+fix that already has an issue — can go straight to a PR. Everything else starts
+with a ticket. When in doubt, ask in the discussion or on
+[Slack](https://docs.netbird.io/slack-url); an hour of conversation up front
+regularly saves a week of rework.
+
+### High-risk areas
+
+These always need the design discussed and agreed in the issue **before** you
+write code:
+
+- **Public API** — REST / management API, OpenAPI schema, dashboard-facing contracts
+- **gRPC protocols** — management, signal, relay, and client daemon protos
+- **Functionality behavior** — anything existing deployments would experience differently after an upgrade
+- **Peer connectivity** — ICE and NAT traversal, relay selection, WireGuard® and Rosenpass key handling
+- **Client system integration** — routing, firewall, DNS, and interface management
+- **Authentication and authorization** — IdP integration, tokens, permissions, cryptography
+- **CLI / service flags**, configuration file format, and daemon IPC
+- **Store and database schema** — models and migrations
+- **New features**
+
+These surfaces are NetBird's contract with operators, self-hosters, and
+downstream integrators, and changes to them have compatibility, security, and
+release-planning implications. Agreeing on the direction early lets the PR
+review focus on implementation rather than design.
+
+Typical bug fixes, internal refactors, documentation updates, and tests do not
+need a design discussion, but should still be tied to an issue so the work is
+visible and nobody duplicates it.
+
+### Using AI coding agents
+
+We have no policy for or against using an AI agent to write NetBird code. That
+choice is yours, and we are not going to interrogate anyone about their tools.
+
+What we do have is a lot of incoming contributions that were plainly drafted with
+one, and enough experience reviewing them to see the same avoidable problems
+again and again: no ticket behind the change, a diff far too large to review, a
+description longer than the code it describes, an approach that was never going
+to be accepted, and an author who cannot answer questions about their own PR.
+None of that is caused by the tooling — it is what happens when a tool is pointed
+at a repository whose expectations it has never been told.
+
+So rather than a rule, there is a guide. [AGENTS.md](AGENTS.md) restates the
+expectations from this document in the form agents read automatically
+(`CLAUDE.md` points to it), so pointing your tool at the repository is usually
+enough. Among other things it tells the agent to ask you for the
+discussion or issue before drafting a PR, to keep the change small and
+single-purpose, to run the tests locally, to use this repository's PR template
+and title tags, and to write a description a reviewer can get through.
+
+The guardrails are the point, and they are the same ones we apply to everyone: an
+agreed ticket, a change you have actually run, a diff small enough to review with
+care, and an author who can explain it. Whatever wrote the diff, you are its
+author — you own every line you submit and the consequences of opening a PR with it.
+
+We may assess whether a contribution is maintainable and whether its merged code
+aligns with our security standards and design expectations.
+
 ## Contents
 
 - [Contributing to NetBird](#contributing-to-netbird)
+    - [Ticket first, PR second](#ticket-first-pr-second)
+        - [High-risk areas](#high-risk-areas)
+        - [Using AI coding agents](#using-ai-coding-agents)
     - [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)
@@ -24,6 +111,7 @@ If you haven't already, join our slack workspace [here](https://docs.netbird.io/
         - [Build and start](#build-and-start)
         - [Test suite](#test-suite)
     - [Checklist before submitting a PR](#checklist-before-submitting-a-pr)
+    - [When we close a PR](#when-we-close-a-pr)
     - [Other project repositories](#other-project-repositories)
     - [Contributor License Agreement](#contributor-license-agreement)
 
@@ -34,42 +122,66 @@ 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.
+The NetBird project monorepo keeps most of each component's code within its own
+directory, except for a few auxiliary or shared packages. Protocol definitions
+and the client-side service clients live under [/shared](/shared), because both
+the agent and the services import them.
 
-The most important directories are:
+**Agent**
 
-- [/.github](/.github) - Github actions workflow files and issue templates
 - [/client](/client) - NetBird agent code
-- [/client/cmd](/client/cmd) - NetBird agent cli code
+- [/client/cmd](/client/cmd) - NetBird agent CLI code
 - [/client/internal](/client/internal) - NetBird agent business logic code
-- [/client/proto](/client/proto) - NetBird agent daemon GRPC proto files
 - [/client/server](/client/server) - NetBird agent daemon code for background execution
-- [/client/ui](/client/ui) - NetBird agent UI code
-- [/encryption](/encryption) - Contain main encryption code for agent communication
-- [/iface](/iface) - Wireguard® interface code
-- [/infrastructure_files](/infrastructure_files) - Getting started files containing docker and template scripts
+- [/client/proto](/client/proto) - NetBird agent daemon gRPC proto files
+- [/client/iface](/client/iface) - WireGuard® interface code
+- [/client/firewall](/client/firewall) - Platform firewall backends (nftables, iptables, pf, WFP, userspace)
+- [/client/ssh](/client/ssh) - Built-in SSH server and client
+- [/client/ui](/client/ui) - NetBird agent UI code (Wails v3 + React)
+- [/client/android](/client/android), [/client/ios](/client/ios) - Mobile platform bindings
+- [/client/wasm](/client/wasm) - WebAssembly build of the agent
+- [/client/mdm](/client/mdm) - MDM-delivered policy handling
+- [/client/system](/client/system) - Host and system information collection
+
+**Control plane services**
+
 - [/management](/management) - Management service code
-- [/management/client](/management/client) - Management service client code which is imported by the agent code
-- [/management/proto](/management/proto) - Management service GRPC proto files
 - [/management/server](/management/server) - Management service server code
 - [/management/server/http](/management/server/http) - Management service REST API code
+- [/management/server/store](/management/server/store) - Persistence layer and migrations
 - [/management/server/idp](/management/server/idp) - Management service IDP management code
-- [/release_files](/release_files) - Files that goes into release packages
+- [/management/server/peer](/management/server/peer), [/management/server/groups](/management/server/groups), [/management/server/networks](/management/server/networks), [/management/server/posture](/management/server/posture), [/management/server/permissions](/management/server/permissions) - Core domain packages
 - [/signal](/signal) - Signal service code
-- [/signal/client](/signal/client) - Signal service client code which is imported by the agent code
 - [/signal/peer](/signal/peer) - Signal service peer message logic
-- [/signal/proto](/signal/proto) - Signal service GRPC proto files
 - [/signal/server](/signal/server) - Signal service server code
+- [/relay](/relay) - Relay service code
+- [/relay/protocol](/relay/protocol) - Relay wire protocol
+- [/proxy](/proxy) - Identity-aware proxy used by Agent Network (LLM routing, ACME, access logs)
+- [/agent-network](/agent-network) - Agent Network overview and documentation
+- [/upload-server](/upload-server) - Debug bundle upload service
+
+**Shared code**
+
+- [/shared/management/proto](/shared/management/proto) - Management service gRPC proto files
+- [/shared/management/client](/shared/management/client) - Management service client code which is imported by the agent code
+- [/shared/management/http/api](/shared/management/http/api) - OpenAPI specification and generated REST API types
+- [/shared/signal/proto](/shared/signal/proto) - Signal service gRPC proto files
+- [/shared/signal/client](/shared/signal/client) - Signal service client code which is imported by the agent code
+- [/shared/relay](/shared/relay) - Relay client and shared relay types
+- [/shared/auth](/shared/auth), [/shared/sshauth](/shared/sshauth) - Shared authentication primitives
+- [/encryption](/encryption) - Contain main encryption code for agent communication
+- [/dns](/dns), [/route](/route), [/stun](/stun), [/sharedsock](/sharedsock), [/util](/util) - Shared networking and utility primitives
+- [/flow](/flow) - Flow event protocol shared by the agent and Management
+
+**Build, test, and packaging**
+
+- [/.github](/.github) - Github actions workflow files, issue templates, and the pull request template
+- [/e2e](/e2e) - End-to-end test suites and harness
+- [/infrastructure_files](/infrastructure_files) - Getting started files containing docker and template scripts
+- [/release_files](/release_files) - Files that goes into release packages
+- [/tools](/tools) - Development and maintenance tooling
 
 
 ## Development setup
@@ -234,12 +346,22 @@ cd client/ui
 task dev
 ```
 
-Pass daemon flags after `--`:
+Pass daemon flags after `--`, pointing the UI at the socket the daemon serves:
 
 ```
-task dev -- --daemon-addr=tcp://127.0.0.1:41731
+task dev -- --daemon-addr=unix:///var/run/netbird.sock   # Linux, macOS
+task dev -- --daemon-addr=npipe://netbird                # Windows
 ```
 
+On Windows the daemon serves a named pipe (`npipe://netbird`). Which path that
+ends up being depends on what the daemon may create: as a service or elevated it
+serves `\\.\pipe\ProtectedPrefix\Administrators\netbird`, which no unprivileged
+process can take from it, and otherwise it falls back to `\\.\pipe\netbird`.
+Clients try both and check who owns the pipe before using the plain one. Avoid
+`tcp://127.0.0.1:41731`: loopback TCP carries no caller identity, so the daemon
+refuses the operations that require an administrator and you will not exercise
+those paths.
+
 Production build (frontend assets embedded into the binary, output in `client/ui/bin/`):
 
 ```
@@ -324,23 +446,172 @@ The installer `netbird-installer.exe` will be created in root directory.
 
 ### Test suite
 
-The tests can be started via:
+The host-safe unit tests run as a normal user and leave host networking
+untouched:
 
 ```
-cd netbird
-go test -exec sudo ./...
+make test-unit
 ```
+
+Tests that need root and mutate host networking (firewall, routing, interface
+management) carry the `privileged` build tag and run inside a
+`--privileged --cap-add=NET_ADMIN` Docker container:
+
+```
+make test-privileged
+```
+
+Narrow a privileged run with environment variables:
+
+```
+PRIV_RUN=TestNftablesManager PRIV_PKGS=./client/firewall/nftables/... make test-privileged
+```
+
+Single packages can be run directly, adding `-race` when the change touches
+shared state:
+
+```
+go test -race ./client/internal/dns/...
+```
+
 > On Windows use a powershell with administrator privileges
 
 ## Checklist before submitting a PR
-As a critical network service and open-source project, we must enforce a few things before submitting the pull-requests:
+
+As a critical network service and open-source project, we must enforce a few
+things before submitting a pull request. The
+[pull request template](/.github/pull_request_template.md) mirrors this list —
+fill it in rather than deleting it.
+
+### Link the issue
+
+The PR description must link the agreed issue (or the validated discussion it
+came from). See [Ticket first, PR second](#ticket-first-pr-second).
+
+### Run it locally
+
+**If you can't run it, you can't submit it.** Build the affected components and
+exercise the change on a real setup — see [Build and start](#build-and-start).
+"CI will tell me" is not acceptable for a VPN agent that runs as root on other
+people's machines.
+
+### Green CI, and answer the bots
+
+We do not start reviewing while CI is red. Get the pipeline green first — a
+failing build, lint, or test means the PR is not ready for review.
+
+Alongside the test workflows, your PR is reviewed by CodeRabbit and scanned by
+SonarCloud, Snyk, and Codecov. Read what they report and either fix it or reply
+with why it does not apply; please do not resolve the threads without a
+response. They are not always right — this codebase has privileged,
+platform-specific, and concurrency-heavy paths that static analysis reads poorly
+— so push back when a finding is wrong rather than changing correct code to
+silence it. Security and dependency findings are the exception: treat those as
+real until shown otherwise. Do not edit workflows, thresholds, or scanner
+configuration to make a check pass.
+
+### One PR, one purpose
+
+Bug fix, refactor, feature: separate PRs. Mixed PRs are slow to review, hard to
+revert, and may be closed with a request to split them.
+
+### Keep it small
+
+Size is the strongest predictor of how long a PR waits for review. Aim for under
+roughly 400 changed lines across under 20 files. Past about 1000 lines or 50
+files, expect to be asked to split the change — and large PRs from outside the
+core team may be blocked until the scope has been agreed in a ticket. This is
+not only about reviewer time: NetBird's agent runs as root on other people's
+machines, and a sprawling diff cannot be reviewed with the care that deserves.
+
+Measure by hand-written code, excluding generated output, `go.sum`, and
+fixtures. If a change genuinely cannot be small — a protocol migration, a
+cross-component rename — agree the split in the issue before you start, and land
+it as a series of PRs that each build and make sense on their own.
+
+### Avoid force-pushing during review
+
+Once a PR is open, push new commits instead of rewriting history. A force-push
+detaches existing review comments from their lines, throws away the
+"changes since your last review" diff, and loses the CI history that showed
+which commit broke what. Since we squash on merge, there is nothing to gain from
+a tidy branch history.
+
+Force-pushing is sometimes unavoidable — rebasing to clear a real conflict, or
+removing a secret or large binary committed by mistake. When that happens, leave
+a comment on the PR so reviewers know their anchors moved.
+
+### Quality checks
+
+Run these from the repository root before pushing:
+
+```shell
+go fmt ./...
+make lint        # golangci-lint on files changed against origin/main
+make lint-all    # full-repository lint, matches CI
+make test-unit   # host-safe unit tests
+```
+
+`make setup-hooks` wires `make lint` into a pre-push hook so the fast lint runs
+automatically. If your change touches privileged paths (firewall, routing,
+interface management), also run `make test-privileged`, which executes the
+`privileged`-tagged suite inside a Docker container with `NET_ADMIN`.
+
+### Code standards
+
 - Keep functions as simple as possible, with a single purpose
 - Use private functions and constants where possible
 - Comment on any new public functions
 - Add unit tests for any new public function
+- Comment the **why**, not the **what** — explain non-obvious decisions, invariants, and constraints, not the line below
+- Keep comments within 90 characters per line and roughly 250 characters per comment; when a block needs more explanation than that, extract a named function instead of writing a longer comment (see [AGENTS.md](AGENTS.md#length-budget))
+
+### PR title and commits
+
+PR titles must start with a bracketed tag, enforced by
+[pr-title-check.yml](/.github/workflows/pr-title-check.yml):
+
+```text
+[client] Authorize daemon IPC callers by their local identity
+[management,client] Add MDM policy support
+```
+
+Use a comma-separated list inside a single pair of brackets when a change spans
+components. The `allowedTags` array in
+[pr-title-check.yml](/.github/workflows/pr-title-check.yml) is the source of
+truth — at the time of writing it accepts `management`, `client`, `signal`,
+`proxy`, `relay`, `misc`, `infrastructure`, `self-hosted`, and `doc`.
+
+Commit subjects follow the same convention — keep them short and put the
+reasoning in the body, why before what, with no bullet list of files changed.
+
+Keep the PR description itself under 1000 words on top of the template text.
+Reviewers read the diff; the description explains what the diff cannot.
 
 > When pushing fixes to the PR comments, please push as separate commits; we will squash the PR before merging, so there is no need to squash it before pushing it, and we are more than okay with 10-100 commits in a single PR. This helps review the fixes to the requested changes.
 
+### Documentation
+
+User-facing changes need a matching PR in
+[netbirdio/docs](https://github.com/netbirdio/docs); link it in the PR
+description, or state why documentation is not needed.
+
+## When we close a PR
+
+We would rather redirect early than let a PR sit. We may close one if:
+
+- It changes behavior with no linked issue, or the approach was never agreed with a maintainer
+- The change was clearly never run or tested locally
+- CI has been red without a response
+- It mixes unrelated purposes, or the purpose is not clear
+- It is far too large to review and the scope was never agreed in a ticket
+- The author cannot answer questions about their own change — including PRs that read as unreviewed model output, where review turns into a relay between the maintainer and an LLM. Tooling is fine; unreviewed output is not, you are responsible for the code you sign your name to
+- There has been no activity for 14 days after we requested changes
+
+A closed PR is not a rejected idea. Take it back to the
+[discussion](https://github.com/netbirdio/netbird/discussions), settle the
+approach, and reopen the work from there.
+
 ## Other project repositories
 
 NetBird project is composed of 3 main repositories:

SECURITY.md

@@ -1,12 +1,70 @@
 # Security Policy
 
-NetBird's goal is to provide a secure network. If you find a vulnerability or bug, please report it by opening an issue [here](https://github.com/netbirdio/netbird/issues/new?assignees=&labels=&template=bug-issue-report.md&title=) or by contacting us by email.
-
-There has yet to be an official bug bounty program for the NetBird project.
-
-## Supported Versions
-- We currently support only the latest version
+NetBird's goal is to provide a secure network. The client runs as a privileged service on every machine it is installed on,
+so we take reports about it seriously and we publish what we fix.
 
 ## Reporting a Vulnerability
 
-Please report security issues to `security@netbird.io`
+**Please do not open a public issue for a security vulnerability.** Public issues are visible to everyone, including before
+a fix is available.
+
+Report security issues one of these two ways:
+
+- **GitHub private vulnerability reporting** — [open a private report](https://github.com/netbirdio/netbird/security/advisories/new)
+  on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place.
+- **Email** — `security@netbird.io`.
+
+If the finding affects NetBird Cloud or our hosted infrastructure rather than the open-source code, email us rather than
+filing a repository report.
+
+### What to include
+
+A report is easier to act on when it contains:
+
+- The affected component (client, management, signal, relay, dashboard) and the version or commit you tested
+- The platform and configuration, where relevant — operating system, self-hosted or NetBird Cloud, container or host install
+- What an attacker needs before they can exploit it: network position, an account, local access, a specific privilege level
+- Steps to reproduce, and a proof of concept if you have one
+- The impact you believe it has
+
+Partial reports are still welcome. If you are unsure whether something is a security issue, send it to `security@netbird.io`
+and let us make that call.
+
+## What to expect from us
+
+- **We acknowledge your report** and tell you whether we can reproduce it.
+- **We work with you on severity and scope.** If we assess it differently than you do, we will explain why rather than
+  silently downgrade it.
+- **We fix and release**, then publish a [GitHub Security Advisory](https://github.com/netbirdio/netbird/security/advisories)
+  naming the affected version range and the patched version.
+- **We credit reporters who want to be credited.** Tell us the name or handle you would like used, or that you would rather
+  stay anonymous.
+- **We keep you in the loop** until the advisory is published.
+
+We ask that you give us a reasonable opportunity to ship a fix before disclosing the issue publicly, and that you avoid
+accessing, modifying, or exfiltrating data belonging to other people while testing. Testing against your own installation
+or your own account is always fine.
+
+## Supported Versions
+
+We support the latest release. Security fixes ship in the next version rather than as backports to older releases, so
+upgrading to the current release is how you get them.
+
+Release notifications are available by watching [releases](https://github.com/netbirdio/netbird/releases).
+
+## Published advisories
+
+Every vulnerability we fix is published as a GitHub Security Advisory on the
+[advisories page](https://github.com/netbirdio/netbird/security/advisories), including the affected version range, the
+patched version, and the reporter's credit. Advisories for the Go module are also distributed through the Go vulnerability
+database, so `govulncheck` will report them against your dependencies.
+
+## Bug bounty
+
+There is no official bug bounty program for the NetBird project. We credit reporters in advisories, and we are grateful for
+the work, but we cannot currently offer payment for reports.
+
+## Non-security bugs
+
+For bugs that are not security issues, please use the
+[issue tracker](https://github.com/netbirdio/netbird/discussions/new/choose).

client/android/client.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"os"
 	"slices"
+	"strings"
 	"sync"
 	"time"
 
@@ -56,6 +57,12 @@ type DnsReadyListener interface {
 	dns.ReadyListener
 }
 
+// TunSettings is a snapshot of the settings the TUN device is rebuilt with
+type TunSettings struct {
+	Routes        string
+	SearchDomains string
+}
+
 func init() {
 	formatter.SetLogcatFormatter(log.StandardLogger())
 }
@@ -75,13 +82,34 @@ type Client struct {
 	connectClient *internal.ConnectClient
 	config        *profilemanager.Config
 	cacheDir      string
+	// Identifies the running profile for the SSO login hint; see profile_state.go.
+	cfgPath string
+
+	stateChangeMu    sync.Mutex
+	stateChangeSubID string
+	eventSub         *peer.EventSubscription
+	// Closed to stop the watch goroutines from delivering buffered items to a
+	// listener that has been removed or replaced. See stopStateChangeWatchLocked.
+	stateChangeDone chan struct{}
+
+	// Latched "the server wants an interactive login": survives the engine
+	// restarts that replace the run loop's context state. See Client.Status.
+	// Guarded by loginRequiredMu together with loginCleared, which counts
+	// clears so a stale observation cannot re-latch over one.
+	loginRequiredMu sync.Mutex
+	loginRequired   bool
+	loginCleared    uint64
+
+	extendMu     sync.Mutex
+	extendCancel context.CancelFunc
 }
 
-func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
+func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cfgPath string, cc *internal.ConnectClient) {
 	c.stateMu.Lock()
 	defer c.stateMu.Unlock()
 	c.config = cfg
 	c.cacheDir = cacheDir
+	c.cfgPath = cfgPath
 	c.connectClient = cc
 }
 
@@ -91,6 +119,16 @@ func (c *Client) stateSnapshot() (*profilemanager.Config, string, *internal.Conn
 	return c.config, c.cacheDir, c.connectClient
 }
 
+// authSnapshot returns the config together with the path it was loaded from, in
+// one lock: the path identifies the profile whose account email backs the login
+// hint, so reading it separately could pair one profile's config with another's
+// hint when a profile switch lands in between.
+func (c *Client) authSnapshot() (*profilemanager.Config, string, *internal.ConnectClient) {
+	c.stateMu.RLock()
+	defer c.stateMu.RUnlock()
+	return c.config, c.cfgPath, c.connectClient
+}
+
 func (c *Client) getConnectClient() *internal.ConnectClient {
 	c.stateMu.RLock()
 	defer c.stateMu.RUnlock()
@@ -143,16 +181,21 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	defer c.ctxCancel()
 	c.ctxCancelLock.Unlock()
 
-	auth := NewAuthWithConfig(ctx, cfg)
+	auth := NewAuthWithConfig(ctx, cfg, cfgFile)
 	err = auth.login(urlOpener, isAndroidTV)
 	if err != nil {
 		return err
 	}
-
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
-	c.setState(cfg, cacheDir, connectClient)
+	c.setState(cfg, cacheDir, cfgFile, connectClient)
+	// This path runs the interactive SSO flow, so reaching here means the peer
+	// is authenticated again — release the latch Status() reports from. Clear
+	// only once the fresh connect client is installed: until then Status()
+	// still reads the previous run's context state, which holds the NeedsLogin
+	// that prompted this login, and would re-latch what was just cleared.
+	c.clearLoginRequired()
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
@@ -187,7 +230,7 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
-	c.setState(cfg, cacheDir, connectClient)
+	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
@@ -216,6 +259,24 @@ func (c *Client) RenewTun(fd int) error {
 	return e.RenewTun(fd)
 }
 
+func (c *Client) GetTunSettings() (*TunSettings, error) {
+	cc := c.getConnectClient()
+	if cc == nil {
+		return nil, fmt.Errorf("engine not running")
+	}
+
+	e := cc.Engine()
+	if e == nil {
+		return nil, fmt.Errorf("engine not initialized")
+	}
+
+	routes, searchDomains := e.TunSettings()
+	return &TunSettings{
+		Routes:        strings.Join(routes, ";"),
+		SearchDomains: strings.Join(searchDomains, ";"),
+	}, nil
+}
+
 // DebugBundle generates a debug bundle, uploads it, and returns the upload key.
 // It works both with and without a running engine.
 func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (string, error) {
@@ -277,7 +338,7 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
 	uploadCtx, cancel := context.WithTimeout(context.Background(), 2*time.Minute)
 	defer cancel()
 
-	key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path)
+	key, err := debug.UploadDebugBundle(uploadCtx, types.DefaultBundleURL, cfg.ManagementURL.String(), path, false)
 	if err != nil {
 		return "", fmt.Errorf("upload debug bundle: %w", err)
 	}
@@ -299,6 +360,13 @@ func (c *Client) SetInfoLogLevel() {
 // PeersList return with the list of the PeerInfos
 func (c *Client) PeersList() *PeerInfoArray {
 
+	// The recorder only caches transfer counters and handshake times; nothing
+	// refreshes them on its own, so without this they read as zero. The desktop
+	// daemon does the same before serving a full peer status.
+	if err := c.recorder.RefreshWireGuardStats(); err != nil {
+		log.Debugf("failed to refresh WireGuard stats: %v", err)
+	}
+
 	fullStatus := c.recorder.GetFullStatus()
 
 	peerInfos := make([]PeerInfo, len(fullStatus.Peers))
@@ -309,6 +377,20 @@ func (c *Client) PeersList() *PeerInfoArray {
 			FQDN:       p.FQDN,
 			ConnStatus: int(p.ConnStatus),
 			Routes:     PeerRoutes{routes: maps.Keys(p.GetRoutes())},
+
+			PubKey:                     p.PubKey,
+			Latency:                    formatDuration(p.Latency),
+			LatencyMs:                  p.Latency.Milliseconds(),
+			BytesRx:                    p.BytesRx,
+			BytesTx:                    p.BytesTx,
+			ConnStatusUpdate:           formatTime(p.ConnStatusUpdate),
+			Relayed:                    p.Relayed,
+			RosenpassEnabled:           p.RosenpassEnabled,
+			LastWireguardHandshake:     formatTime(p.LastWireguardHandshake),
+			LocalIceCandidateType:      p.LocalIceCandidateType,
+			RemoteIceCandidateType:     p.RemoteIceCandidateType,
+			LocalIceCandidateEndpoint:  p.LocalIceCandidateEndpoint,
+			RemoteIceCandidateEndpoint: p.RemoteIceCandidateEndpoint,
 		}
 		peerInfos[n] = pi
 	}
@@ -439,10 +521,6 @@ func (c *Client) RemoveConnectionListener() {
 	c.recorder.RemoveConnectionListener()
 }
 
-func (c *Client) toggleRoute(command routeCommand) error {
-	return command.toggleRoute()
-}
-
 func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	client := c.getConnectClient()
 	if client == nil {
@@ -462,22 +540,22 @@ func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	return manager, nil
 }
 
-func (c *Client) SelectRoute(route string) error {
+func (c *Client) SelectRoute(id string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return c.toggleRoute(selectRouteCommand{route: route, manager: manager})
+	return manager.SelectRoutes([]route.NetID{route.NetID(id)}, true)
 }
 
-func (c *Client) DeselectRoute(route string) error {
+func (c *Client) DeselectRoute(id string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return c.toggleRoute(deselectRouteCommand{route: route, manager: manager})
+	return manager.DeselectRoutes([]route.NetID{route.NetID(id)})
 }
 
 // getNetworkDomainsFromRoute extracts domains from a route and enriches each domain
@@ -512,3 +590,28 @@ func exportEnvList(list *EnvList) {
 		}
 	}
 }
+
+// formatDuration renders a duration for display, trimming the fractional part
+// to two digits so latencies read as "12.34ms" rather than "12.345678ms".
+func formatDuration(d time.Duration) string {
+	ds := d.String()
+	dotIndex := strings.Index(ds, ".")
+	if dotIndex == -1 {
+		return ds
+	}
+
+	endIndex := min(dotIndex+3, len(ds))
+
+	// Skip the remaining digits so only the unit suffix is appended back.
+	unitStart := endIndex
+	for unitStart < len(ds) && ds[unitStart] >= '0' && ds[unitStart] <= '9' {
+		unitStart++
+	}
+	return ds[:endIndex] + ds[unitStart:]
+}
+
+// formatTime renders a timestamp in UTC using a fixed layout. The zero time is
+// passed through as-is so the UI can recognise it and show "never" instead.
+func formatTime(t time.Time) string {
+	return t.UTC().Format("2006-01-02 15:04:05")
+}

client/android/login.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"fmt"
 
+	log "github.com/sirupsen/logrus"
+
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/system"
@@ -36,12 +38,20 @@ type Auth struct {
 }
 
 // NewAuth instantiate Auth struct and validate the management URL
+//
+// The configuration at cfgPath is reused when one is already there, and only created when it is
+// not. Building a fresh in-memory config unconditionally gives the client a new WireGuard key on
+// every call: the peer registers under that key, the key is written out, and any peer registered by
+// an earlier call is orphaned on the server. It also breaks a client that enrols and then runs from
+// the persisted config, because the identity it registered is not the one it runs with — the
+// management stream rejects it with "no peer auth method provided".
 func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
 	inputCfg := profilemanager.ConfigInput{
+		ConfigPath:    cfgPath,
 		ManagementURL: mgmURL,
 	}
 
-	cfg, err := profilemanager.CreateInMemoryConfig(inputCfg)
+	cfg, err := profilemanager.UpdateOrCreateConfig(inputCfg)
 	if err != nil {
 		return nil, err
 	}
@@ -53,11 +63,14 @@ func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
 	}, nil
 }
 
-// NewAuthWithConfig instantiate Auth based on existing config
-func NewAuthWithConfig(ctx context.Context, config *profilemanager.Config) *Auth {
+// NewAuthWithConfig instantiate Auth based on existing config. cfgPath is the
+// file the config was loaded from; it identifies the profile whose account email
+// backs the login_hint.
+func NewAuthWithConfig(ctx context.Context, config *profilemanager.Config, cfgPath string) *Auth {
 	return &Auth{
-		ctx:    ctx,
-		config: config,
+		ctx:     ctx,
+		config:  config,
+		cfgPath: cfgPath,
 	}
 }
 
@@ -150,12 +163,14 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 	}
 
 	jwtToken := ""
+	email := ""
 	if needsLogin {
 		tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
 		if err != nil {
 			return fmt.Errorf("interactive sso login failed: %v", err)
 		}
 		jwtToken = tokenInfo.GetTokenToUse()
+		email = tokenInfo.Email
 	}
 
 	err, _ = authClient.Login(a.ctx, "", jwtToken)
@@ -163,17 +178,42 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 		return fmt.Errorf("login failed: %v", err)
 	}
 
+	// Stored after Login, not before: a rejected token must not leave a hint
+	// pointing at an account that cannot be used.
+	if email != "" && a.cfgPath != "" {
+		if err := writeProfileEmail(a.cfgPath, email); err != nil {
+			log.Warnf("failed to store profile account email: %v", err)
+		}
+	}
+
 	go urlOpener.OnLoginSuccess()
 
 	return nil
 }
 
+// loginHintSetter is implemented by both concrete flows (PKCE and device code)
+// but absent from the OAuthFlow interface, hence the assertion below — the same
+// way internal/auth wires it in authenticateWithPKCEFlow.
+type loginHintSetter interface {
+	SetLoginHint(hint string)
+}
+
 func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, isAndroidTV bool) (*auth.TokenInfo, error) {
 	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV)
 	if err != nil {
 		return nil, fmt.Errorf("failed to get OAuth flow: %v", err)
 	}
 
+	// An empty hint is deliberate, not a fallback: a fresh or logged-out profile
+	// leaves the choice to the IdP, which is how accounts get switched.
+	if a.cfgPath != "" {
+		if hint := readProfileEmail(a.cfgPath); hint != "" {
+			if setter, ok := oAuthFlow.(loginHintSetter); ok {
+				setter.SetLoginHint(hint)
+			}
+		}
+	}
+
 	flowInfo, err := oAuthFlow.RequestAuthInfo(context.TODO())
 	if err != nil {
 		return nil, fmt.Errorf("getting a request OAuth flow info failed: %v", err)

client/android/login_test.go

@@ -0,0 +1,51 @@
+package android
+
+import (
+	"path/filepath"
+	"testing"
+)
+
+// NewAuth must reuse the configuration already at cfgPath rather than building a fresh one.
+//
+// Creating a new in-memory config on every call gives the client a new WireGuard private key each
+// time. The peer registers under that key and the key is written out, so a peer registered by an
+// earlier call is orphaned on the server — a client that enrols twice leaves two entries and owns
+// neither. It also breaks enrol-then-run: RunWithoutLogin reloads the configuration from disk, so
+// the identity that registered is not the identity that runs, and the management stream rejects it
+// with "no peer auth method provided, please use a setup key or interactive SSO login".
+func TestNewAuth_ReusesPersistedIdentity(t *testing.T) {
+	cfgPath := filepath.Join(t.TempDir(), "config.json")
+
+	first, err := NewAuth(cfgPath, "https://api.example.com:443")
+	if err != nil {
+		t.Fatalf("first NewAuth: %v", err)
+	}
+	if first.config.PrivateKey == "" {
+		t.Fatal("first NewAuth produced no private key")
+	}
+
+	second, err := NewAuth(cfgPath, "https://api.example.com:443")
+	if err != nil {
+		t.Fatalf("second NewAuth: %v", err)
+	}
+
+	if second.config.PrivateKey != first.config.PrivateKey {
+		t.Errorf("private key changed between calls: a second enrolment would orphan the peer registered by the first")
+	}
+}
+
+// A missing configuration is still created, so a first enrolment works unchanged.
+func TestNewAuth_CreatesConfigWhenAbsent(t *testing.T) {
+	cfgPath := filepath.Join(t.TempDir(), "config.json")
+
+	auth, err := NewAuth(cfgPath, "https://api.example.com:443")
+	if err != nil {
+		t.Fatalf("NewAuth: %v", err)
+	}
+	if auth.config == nil || auth.config.PrivateKey == "" {
+		t.Fatal("NewAuth did not create a usable configuration")
+	}
+	if auth.cfgPath != cfgPath {
+		t.Errorf("cfgPath = %q, want %q", auth.cfgPath, cfgPath)
+	}
+}

client/android/peer_notifier.go

@@ -12,12 +12,30 @@ const (
 )
 
 // PeerInfo describe information about the peers. It designed for the UI usage
+//
+// The fields below ConnStatus back the peer detail screen. Durations and times
+// are pre-formatted into strings so the UI does not have to know Go's layouts;
+// Latency is additionally exposed as LatencyMs for colour coding.
 type PeerInfo struct {
 	IP         string
 	IPv6       string
 	FQDN       string
 	ConnStatus int
 	Routes     PeerRoutes
+
+	PubKey                     string
+	Latency                    string
+	LatencyMs                  int64
+	BytesRx                    int64
+	BytesTx                    int64
+	ConnStatusUpdate           string
+	Relayed                    bool
+	RosenpassEnabled           bool
+	LastWireguardHandshake     string
+	LocalIceCandidateType      string
+	RemoteIceCandidateType     string
+	LocalIceCandidateEndpoint  string
+	RemoteIceCandidateEndpoint string
 }
 
 func (p *PeerInfo) GetPeerRoutes() *PeerRoutes {

client/android/profile_manager.go

@@ -13,18 +13,17 @@ import (
 )
 
 const (
-	// Android-specific config filename (different from desktop default.json)
-	defaultConfigFilename = "netbird.cfg"
-	// Subdirectory for non-default profiles (must match Java Preferences.java)
-	profilesSubdir = "profiles"
 	// Android uses a single user context per app (non-empty username required by ServiceManager)
 	androidUsername = "android"
 )
 
 // Profile represents a profile for gomobile
 type Profile struct {
-	ID       string
-	Name     string
+	ID   string
+	Name string
+	// Email is the account this profile last logged in with, "" if it never
+	// completed an SSO login or was logged out. See profile_state.go.
+	Email    string
 	IsActive bool
 }
 
@@ -101,6 +100,7 @@ func (pm *ProfileManager) ListProfiles() (*ProfileArray, error) {
 		profiles = append(profiles, &Profile{
 			ID:       p.ID.String(),
 			Name:     p.Name,
+			Email:    pm.profileEmail(p.ID.String()),
 			IsActive: p.IsActive,
 		})
 	}
@@ -123,7 +123,22 @@ func (pm *ProfileManager) GetActiveProfile() (*Profile, error) {
 	if err != nil {
 		return nil, fmt.Errorf("failed to resolve active profile %q: %w", activeState.ID, err)
 	}
-	return &Profile{ID: prof.ID.String(), Name: prof.Name, IsActive: true}, nil
+	return &Profile{
+		ID:       prof.ID.String(),
+		Name:     prof.Name,
+		Email:    pm.profileEmail(prof.ID.String()),
+		IsActive: true,
+	}, nil
+}
+
+// profileEmail returns the account email recorded for a profile. Display-only, so
+// an unresolvable path degrades to "" rather than an error.
+func (pm *ProfileManager) profileEmail(id string) string {
+	configPath, err := pm.getProfileConfigPath(id)
+	if err != nil {
+		return ""
+	}
+	return readProfileEmail(configPath)
 }
 
 // SwitchProfile switches to a different profile
@@ -185,10 +200,28 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
 		return fmt.Errorf("failed to save config: %w", err)
 	}
 
+	// Not fatal: a stale hint costs an account switch, not the logout itself.
+	if err := removeProfileEmail(configPath); err != nil {
+		log.Warnf("failed to clear stored account email for profile %s: %v", id, err)
+	}
+
 	log.Infof("logged out from profile: %s", id)
 	return nil
 }
 
+// RenameProfile changes a profile's display name. The profile ID, and therefore
+// its on-disk filename, is left untouched: only the "name" field of the config
+// is rewritten. This works for the default profile too, whose config lives in
+// netbird.cfg rather than under profiles/.
+func (pm *ProfileManager) RenameProfile(id string, newName string) error {
+	if err := pm.serviceMgr.RenameProfile(profilemanager.ID(id), androidUsername, newName); err != nil {
+		return fmt.Errorf("failed to rename profile: %w", err)
+	}
+
+	log.Infof("renamed profile %s to: %s", id, newName)
+	return nil
+}
+
 // RemoveProfile deletes a profile
 func (pm *ProfileManager) RemoveProfile(id string) error {
 	// Use ServiceManager (removes profile from profiles/ directory)

client/android/profile_state.go

@@ -0,0 +1,108 @@
+package android
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/util"
+)
+
+const (
+	// Android-specific config filename (different from desktop default.json)
+	defaultConfigFilename = "netbird.cfg"
+	// Subdirectory for non-default profiles (must match Java Preferences.java)
+	profilesSubdir = "profiles"
+	// profileAccountSuffix names the file holding the profile's account email.
+	// Deliberately not ".state.json", which desktop uses for the same data:
+	// there the email and the engine's state manager live in different
+	// directories, but on Android both resolve under files/, so sharing the name
+	// would have the two overwrite each other — the state manager rewrites the
+	// whole file from its own keys (see statemanager.Manager.PersistState), and
+	// this package's writer does the same in reverse.
+	profileAccountSuffix = ".account.json"
+)
+
+// profileAccountPathFor derives the account file path from a profile's config
+// path: netbird.cfg -> netbird.account.json, <id>.json -> <id>.account.json.
+//
+// Deriving from the config path rather than resolving the active profile keeps
+// the write on the profile the login actually ran for: Auth.login runs in a
+// goroutine, so the active profile can change under a flow already in flight.
+func profileAccountPathFor(configPath string) (string, error) {
+	if configPath == "" {
+		return "", fmt.Errorf("empty config path")
+	}
+
+	base := filepath.Base(configPath)
+	stem := strings.TrimSuffix(base, filepath.Ext(base))
+	if stem == "" || stem == "." {
+		return "", fmt.Errorf("config path %q has no filename stem", configPath)
+	}
+
+	return filepath.Join(filepath.Dir(configPath), stem+profileAccountSuffix), nil
+}
+
+// readProfileEmail returns the account email stored for the profile whose config
+// lives at configPath. A missing or unreadable file yields "", which leaves the
+// account choice to the IdP.
+func readProfileEmail(configPath string) string {
+	accountPath, err := profileAccountPathFor(configPath)
+	if err != nil {
+		log.Debugf("no profile account path for login hint: %v", err)
+		return ""
+	}
+
+	var state profilemanager.ProfileState
+	if _, err := util.ReadJson(accountPath, &state); err != nil {
+		if !os.IsNotExist(err) {
+			log.Debugf("failed to read profile account for login hint: %v", err)
+		}
+		return ""
+	}
+
+	return state.Email
+}
+
+// writeProfileEmail records the account email for the profile whose config lives
+// at configPath, so later logins can pass it as an OIDC login_hint. An empty
+// email is ignored rather than blanking what is already stored.
+func writeProfileEmail(configPath string, email string) error {
+	if email == "" {
+		return nil
+	}
+
+	accountPath, err := profileAccountPathFor(configPath)
+	if err != nil {
+		return fmt.Errorf("resolve profile account path: %w", err)
+	}
+
+	state := profilemanager.ProfileState{Email: email}
+	if err := util.WriteJsonWithRestrictedPermission(context.Background(), accountPath, state); err != nil {
+		return fmt.Errorf("write profile account: %w", err)
+	}
+
+	return nil
+}
+
+// removeProfileEmail drops the stored account email. Called on logout: while the
+// email is on disk it goes out as a login_hint, which would steer the next login
+// straight back into the account just logged out of. Mirrors the desktop UI's
+// RemoveProfileState call.
+func removeProfileEmail(configPath string) error {
+	accountPath, err := profileAccountPathFor(configPath)
+	if err != nil {
+		return fmt.Errorf("resolve profile account path: %w", err)
+	}
+
+	if err := os.Remove(accountPath); err != nil && !os.IsNotExist(err) {
+		return fmt.Errorf("remove profile account: %w", err)
+	}
+
+	return nil
+}

client/android/profile_state_test.go

@@ -0,0 +1,161 @@
+package android
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestProfileAccountPathFor(t *testing.T) {
+	tests := []struct {
+		name       string
+		configPath string
+		want       string
+		wantErr    bool
+	}{
+		{
+			name:       "default profile",
+			configPath: "/data/data/io.netbird.client/files/netbird.cfg",
+			want:       filepath.FromSlash("/data/data/io.netbird.client/files/netbird.account.json"),
+		},
+		{
+			name:       "id profile",
+			configPath: "/data/data/io.netbird.client/files/profiles/4c5f5c8198c3989cffb5b5394f5a7ae0.json",
+			want:       filepath.FromSlash("/data/data/io.netbird.client/files/profiles/4c5f5c8198c3989cffb5b5394f5a7ae0.account.json"),
+		},
+		{
+			name:       "legacy name-keyed profile is handled the same way",
+			configPath: "/data/data/io.netbird.client/files/profiles/work.json",
+			want:       filepath.FromSlash("/data/data/io.netbird.client/files/profiles/work.account.json"),
+		},
+		{
+			name:       "empty path is rejected",
+			configPath: "",
+			wantErr:    true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := profileAccountPathFor(tt.configPath)
+			if tt.wantErr {
+				if err == nil {
+					t.Fatalf("expected an error, got path %q", got)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			if got != tt.want {
+				t.Errorf("got %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestProfileAccountPathForDefaultDoesNotCollide(t *testing.T) {
+	root := "/data/data/io.netbird.client/files"
+
+	defaultAccount, err := profileAccountPathFor(filepath.Join(root, defaultConfigFilename))
+	if err != nil {
+		t.Fatalf("default profile: %v", err)
+	}
+
+	idAccount, err := profileAccountPathFor(filepath.Join(root, profilesSubdir, "abc123.json"))
+	if err != nil {
+		t.Fatalf("id profile: %v", err)
+	}
+
+	if defaultAccount == idAccount {
+		t.Fatalf("default and id profile share an account file: %q", defaultAccount)
+	}
+}
+
+// The account file must never land on the engine state file: on Android both
+// resolve under files/, and the state manager rewrites the whole file from its
+// own keys, so sharing a path would have the two overwrite each other. The
+// expected names here mirror ProfileManager.GetStateFilePath.
+func TestProfileAccountPathAvoidsEngineStateFile(t *testing.T) {
+	root := "/data/data/io.netbird.client/files"
+
+	cases := []struct {
+		configPath  string
+		engineState string
+	}{
+		{
+			configPath:  filepath.Join(root, defaultConfigFilename),
+			engineState: filepath.Join(root, "state.json"),
+		},
+		{
+			configPath:  filepath.Join(root, profilesSubdir, "abc123.json"),
+			engineState: filepath.Join(root, profilesSubdir, "abc123.state.json"),
+		},
+	}
+
+	for _, c := range cases {
+		account, err := profileAccountPathFor(c.configPath)
+		if err != nil {
+			t.Fatalf("%s: %v", c.configPath, err)
+		}
+		if account == c.engineState {
+			t.Errorf("account file collides with the engine state file: %q", account)
+		}
+	}
+}
+
+func TestWriteThenReadProfileEmail(t *testing.T) {
+	configPath := filepath.Join(t.TempDir(), "profiles", "abc123.json")
+	if err := ensureDirFor(t, configPath); err != nil {
+		t.Fatalf("prepare dir: %v", err)
+	}
+
+	if got := readProfileEmail(configPath); got != "" {
+		t.Errorf("expected no email before a login, got %q", got)
+	}
+
+	const email = "user@example.com"
+	if err := writeProfileEmail(configPath, email); err != nil {
+		t.Fatalf("write: %v", err)
+	}
+
+	if got := readProfileEmail(configPath); got != email {
+		t.Errorf("got %q, want %q", got, email)
+	}
+
+	if err := removeProfileEmail(configPath); err != nil {
+		t.Fatalf("remove: %v", err)
+	}
+	if got := readProfileEmail(configPath); got != "" {
+		t.Errorf("expected no email after logout, got %q", got)
+	}
+
+	// Logout may run on a never-logged-in profile, so a second remove must pass.
+	if err := removeProfileEmail(configPath); err != nil {
+		t.Fatalf("second remove should be a no-op: %v", err)
+	}
+}
+
+func TestWriteProfileEmailIgnoresEmpty(t *testing.T) {
+	configPath := filepath.Join(t.TempDir(), "profiles", "abc123.json")
+	if err := ensureDirFor(t, configPath); err != nil {
+		t.Fatalf("prepare dir: %v", err)
+	}
+
+	const email = "user@example.com"
+	if err := writeProfileEmail(configPath, email); err != nil {
+		t.Fatalf("write: %v", err)
+	}
+	if err := writeProfileEmail(configPath, ""); err != nil {
+		t.Fatalf("write empty: %v", err)
+	}
+
+	if got := readProfileEmail(configPath); got != email {
+		t.Errorf("empty write clobbered the stored email: got %q, want %q", got, email)
+	}
+}
+
+func ensureDirFor(t *testing.T, path string) error {
+	t.Helper()
+	return os.MkdirAll(filepath.Dir(path), 0o700)
+}

client/android/route_command.go

@@ -1,70 +0,0 @@
-//go:build android
-
-package android
-
-import (
-	"fmt"
-
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/exp/maps"
-
-	"github.com/netbirdio/netbird/client/internal/routemanager"
-	"github.com/netbirdio/netbird/route"
-)
-
-func executeRouteToggle(id string, manager routemanager.Manager,
-	operationName string,
-	routeOperation func(routes []route.NetID, allRoutes []route.NetID) error) error {
-	netID := route.NetID(id)
-	routes := []route.NetID{netID}
-
-	routesMap := manager.GetClientRoutesWithNetID()
-	routes = route.ExpandV6ExitPairs(routes, routesMap)
-
-	log.Debugf("%s with ids: %v", operationName, routes)
-
-	if err := routeOperation(routes, maps.Keys(routesMap)); err != nil {
-		log.Debugf("error when %s: %s", operationName, err)
-		return fmt.Errorf("error %s: %w", operationName, err)
-	}
-
-	manager.TriggerSelection(manager.GetClientRoutes())
-
-	return nil
-}
-
-type routeCommand interface {
-	toggleRoute() error
-}
-
-type selectRouteCommand struct {
-	route   string
-	manager routemanager.Manager
-}
-
-func (s selectRouteCommand) toggleRoute() error {
-	routeSelector := s.manager.GetRouteSelector()
-	if routeSelector == nil {
-		return fmt.Errorf("no route selector available")
-	}
-
-	routeOperation := func(routes []route.NetID, allRoutes []route.NetID) error {
-		return routeSelector.SelectRoutes(routes, true, allRoutes)
-	}
-
-	return executeRouteToggle(s.route, s.manager, "selecting route", routeOperation)
-}
-
-type deselectRouteCommand struct {
-	route   string
-	manager routemanager.Manager
-}
-
-func (d deselectRouteCommand) toggleRoute() error {
-	routeSelector := d.manager.GetRouteSelector()
-	if routeSelector == nil {
-		return fmt.Errorf("no route selector available")
-	}
-
-	return executeRouteToggle(d.route, d.manager, "deselecting route", routeSelector.DeselectRoutes)
-}

client/android/session.go

@@ -0,0 +1,312 @@
+//go:build android
+
+package android
+
+import (
+	"context"
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal"
+	"github.com/netbirdio/netbird/client/internal/auth"
+	"github.com/netbirdio/netbird/client/internal/auth/sessionwatch"
+	"github.com/netbirdio/netbird/client/internal/peer"
+	cProto "github.com/netbirdio/netbird/client/proto"
+)
+
+// StateChangeListener receives client state notifications.
+//
+// OnStateChanged is a payload-free wake-up whenever the state snapshot
+// changed: connection state, the run-loop status label (e.g. NeedsLogin) or
+// the session deadline. It mirrors the daemon's SubscribeStatus stream
+// trigger — on each signal the consumer pulls the fresh values via
+// Status() / SessionExpiresAtUnix().
+//
+// OnSessionExpiring forwards the engine's session-expiry warnings, fired at
+// sessionwatch.WarningLead before the deadline and again at FinalWarningLead
+// (finalWarning true). The second one is suppressed when the user dismissed
+// the first via DismissSessionWarning. The daemon turns the same events into
+// its tray notification.
+type StateChangeListener interface {
+	OnStateChanged()
+	OnSessionExpiring(expiresAtUnix int64, leadMinutes int64, finalWarning bool)
+}
+
+// Status returns the connect run-loop's status label — the same value the
+// desktop daemon serves in StatusResponse.Status. "NeedsLogin" means the
+// management server rejected the peer and an interactive login is required.
+//
+// The label is latched: the run loop keeps its status in a per-run context
+// state, which a restart replaces with a fresh Idle one, so an engine restart
+// (network change, always-on) would otherwise erase the fact that the peer
+// still needs to log in. Only a successful interactive login or extend clears
+// it — see clearLoginRequired.
+func (c *Client) Status() string {
+	latched, generation := c.loginRequiredState()
+	if latched {
+		return string(internal.StatusNeedsLogin)
+	}
+	cc := c.getConnectClient()
+	if cc == nil {
+		return string(internal.StatusIdle)
+	}
+	status := cc.Status()
+	if status == internal.StatusNeedsLogin {
+		c.latchLoginRequired(generation)
+	}
+	return string(status)
+}
+
+func (c *Client) loginRequiredState() (bool, uint64) {
+	c.loginRequiredMu.Lock()
+	defer c.loginRequiredMu.Unlock()
+	return c.loginRequired, c.loginCleared
+}
+
+// latchLoginRequired records a NeedsLogin observation, unless a clear landed
+// while the caller was reading the run loop's status: cc.Status() is read
+// outside the lock, so a login or extend completing in that window would
+// otherwise be undone by this stale observation, stranding the UI on
+// "login required" over a healthy session.
+func (c *Client) latchLoginRequired(observedGeneration uint64) {
+	c.loginRequiredMu.Lock()
+	defer c.loginRequiredMu.Unlock()
+	if c.loginCleared != observedGeneration {
+		return
+	}
+	c.loginRequired = true
+}
+
+// clearLoginRequired releases the latch after a successful interactive login
+// or session extend, and invalidates any observation already in flight.
+func (c *Client) clearLoginRequired() {
+	c.loginRequiredMu.Lock()
+	defer c.loginRequiredMu.Unlock()
+	c.loginRequired = false
+	c.loginCleared++
+}
+
+// SessionExpiresAtUnix returns the SSO session deadline as unix seconds, or 0
+// when no deadline is known (not SSO-registered, expiry disabled, or the
+// engine has not received one yet). A past value means the session expired.
+// Mirror of StatusResponse.sessionExpiresAt on the desktop daemon.
+func (c *Client) SessionExpiresAtUnix() int64 {
+	deadline := c.recorder.GetSessionExpiresAt()
+	if deadline.IsZero() {
+		return 0
+	}
+	return deadline.Unix()
+}
+
+// SetStateChangeListener registers the state notification listener.
+// Replaces any previously registered listener; remove it with
+// RemoveStateChangeListener.
+func (c *Client) SetStateChangeListener(listener StateChangeListener) {
+	c.stateChangeMu.Lock()
+	defer c.stateChangeMu.Unlock()
+	c.stopStateChangeWatchLocked()
+	if listener == nil {
+		return
+	}
+
+	// Both subscriptions are buffered (one pending tick, ten pending events),
+	// so unsubscribing is not enough to stop callbacks: the loops would drain
+	// what is already queued and deliver it to a listener the caller has
+	// already removed or replaced. Gate every callback on this registration's
+	// own signal, which is closed before unsubscribing.
+	done := make(chan struct{})
+	c.stateChangeDone = done
+
+	id, ch := c.recorder.SubscribeToStateChanges()
+	c.stateChangeSubID = id
+	// The channel is closed by UnsubscribeFromStateChanges, which ends the
+	// goroutine. Ticks are coalesced (buffer of one), so a burst of changes
+	// wakes the listener once.
+	go func() {
+		for range ch {
+			select {
+			case <-done:
+				return
+			default:
+			}
+			listener.OnStateChanged()
+		}
+	}()
+
+	c.eventSub = c.recorder.SubscribeToEvents()
+	go watchSessionWarnings(c.eventSub, listener, done)
+}
+
+// RemoveStateChangeListener unregisters the state notification listener.
+func (c *Client) RemoveStateChangeListener() {
+	c.stateChangeMu.Lock()
+	defer c.stateChangeMu.Unlock()
+	c.stopStateChangeWatchLocked()
+}
+
+// DismissSessionWarning records the user's "Dismiss" on the first expiry
+// warning and suppresses the final one for the current deadline. A refreshed
+// deadline re-arms both. No-op while the engine is not running.
+func (c *Client) DismissSessionWarning() {
+	cc := c.getConnectClient()
+	if cc == nil {
+		return
+	}
+	engine := cc.Engine()
+	if engine == nil {
+		return
+	}
+	engine.DismissSessionWarning()
+}
+
+// ExtendAuthSession runs the interactive SSO flow to obtain a fresh JWT and
+// asks the management server to extend the session deadline. The tunnel is
+// untouched: no resync, no reconnect. Async; the result arrives on the
+// listener. Mirror of the daemon's RequestExtendAuthSession /
+// WaitExtendAuthSession RPC pair, with URLOpener playing the "UI opens the
+// browser" role.
+//
+// Only one flow may be in flight: the PKCE step binds a fixed loopback port,
+// so a second concurrent flow would fail on that bind. Call
+// CancelExtendAuthSession when the user abandons the browser.
+func (c *Client) ExtendAuthSession(urlOpener URLOpener, isAndroidTV bool, resultListener ErrListener) {
+	ctx, err := c.beginExtend()
+	if err != nil {
+		resultListener.OnError(err)
+		return
+	}
+
+	go func() {
+		defer c.endExtend()
+		if err := c.extendAuthSession(ctx, urlOpener, isAndroidTV); err != nil {
+			resultListener.OnError(err)
+			return
+		}
+		resultListener.OnSuccess()
+	}()
+}
+
+// CancelExtendAuthSession aborts an in-flight ExtendAuthSession. The tunnel is
+// left alone — unlike the login flow, which cancels the whole client context
+// by stopping the engine. Without this the abandoned PKCE wait keeps its
+// loopback port for the full flow timeout and blocks every later attempt.
+// No-op when no flow is running.
+func (c *Client) CancelExtendAuthSession() {
+	c.extendMu.Lock()
+	defer c.extendMu.Unlock()
+	if c.extendCancel != nil {
+		c.extendCancel()
+	}
+}
+
+func (c *Client) stopStateChangeWatchLocked() {
+	// Signal first, unsubscribe second: closing the channels only stops new
+	// items, and the loops would still hand whatever is buffered to a listener
+	// that is no longer registered.
+	if c.stateChangeDone != nil {
+		close(c.stateChangeDone)
+		c.stateChangeDone = nil
+	}
+	if c.stateChangeSubID != "" {
+		c.recorder.UnsubscribeFromStateChanges(c.stateChangeSubID)
+		c.stateChangeSubID = ""
+	}
+	if c.eventSub != nil {
+		// Closes the channel, which ends watchSessionWarnings.
+		c.recorder.UnsubscribeFromEvents(c.eventSub)
+		c.eventSub = nil
+	}
+}
+
+// watchSessionWarnings forwards the engine's session-expiry warnings to the
+// listener. The event stream also carries unrelated traffic — network-map
+// updates on every sync, DNS and route errors — so everything but an
+// AUTHENTICATION event carrying the session-warning marker is dropped. Exits
+// when the subscription is closed by UnsubscribeFromEvents, or earlier when
+// done is closed — the stream buffers up to ten events, and a deregistered
+// listener must not receive the ones already queued.
+func watchSessionWarnings(sub *peer.EventSubscription, listener StateChangeListener, done <-chan struct{}) {
+	for ev := range sub.Events() {
+		select {
+		case <-done:
+			return
+		default:
+		}
+		if ev.GetCategory() != cProto.SystemEvent_AUTHENTICATION {
+			continue
+		}
+		meta := ev.GetMetadata()
+		if meta[sessionwatch.MetaSessionWarning] != "true" {
+			// Other AUTHENTICATION events exist (e.g. a deadline rejected as
+			// out of range); they carry no warning marker.
+			continue
+		}
+		deadline, err := sessionwatch.ParseExpiresAt(meta[sessionwatch.MetaSessionExpiresAt])
+		if err != nil {
+			log.Warnf("session warning event with unparsable deadline: %v", err)
+			continue
+		}
+		lead, err := sessionwatch.ParseLeadMinutes(meta[sessionwatch.MetaSessionLeadMinutes])
+		if err != nil {
+			// Informational only — the deadline above is what drives the UI.
+			lead = 0
+		}
+		listener.OnSessionExpiring(deadline.Unix(), int64(lead),
+			meta[sessionwatch.MetaSessionFinal] == "true")
+	}
+}
+
+func (c *Client) beginExtend() (context.Context, error) {
+	c.extendMu.Lock()
+	defer c.extendMu.Unlock()
+	if c.extendCancel != nil {
+		return nil, fmt.Errorf("session extend already in progress")
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	c.extendCancel = cancel
+	return ctx, nil
+}
+
+func (c *Client) endExtend() {
+	c.extendMu.Lock()
+	defer c.extendMu.Unlock()
+	if c.extendCancel != nil {
+		c.extendCancel()
+		c.extendCancel = nil
+	}
+}
+
+func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
+	cfg, cfgPath, cc := c.authSnapshot()
+	if cfg == nil || cc == nil {
+		return fmt.Errorf("engine is not running")
+	}
+	engine := cc.Engine()
+	if engine == nil {
+		return fmt.Errorf("engine is not initialized")
+	}
+
+	authClient, err := auth.NewAuth(ctx, cfg.PrivateKey, cfg.ManagementURL, cfg)
+	if err != nil {
+		return fmt.Errorf("failed to create auth client: %v", err)
+	}
+	defer authClient.Close()
+
+	// Passing the config path makes the flow pick up the login_hint: an extend
+	// renews the session of the account already signed in, so it must not stop to
+	// offer a choice.
+	a := NewAuthWithConfig(ctx, cfg, cfgPath)
+	tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
+	if err != nil {
+		return fmt.Errorf("interactive sso login failed: %v", err)
+	}
+
+	if _, err := engine.ExtendAuthSession(ctx, tokenInfo.GetTokenToUse()); err != nil {
+		return err
+	}
+	c.clearLoginRequired()
+
+	go urlOpener.OnLoginSuccess()
+	return nil
+}

client/cmd/daemon_error.go

@@ -0,0 +1,66 @@
+package cmd
+
+import (
+	"errors"
+	"fmt"
+	"strings"
+
+	"google.golang.org/genproto/googleapis/rpc/errdetails"
+	gstatus "google.golang.org/grpc/status"
+
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+)
+
+// daemonCallError prepares a daemon error for display. A refusal the daemon
+// raised because the operation needs root/administrator is already guidance
+// written for the user, so it is surfaced on its own instead of buried under the
+// gRPC envelope and the name of the RPC that hit it. Anything else is wrapped
+// with context as usual.
+func daemonCallError(context string, err error) error {
+	if guidance, ok := privilegeGuidance(err); ok {
+		return errors.New(guidance)
+	}
+	return fmt.Errorf("%s: %w", context, err)
+}
+
+// privilegeGuidance renders the daemon's privilege refusal as a summary and the
+// command that performs the operation with the privileges it needs. It reports
+// false for any other error.
+func privilegeGuidance(err error) (string, bool) {
+	info, ok := privilegeErrorInfo(err)
+	if !ok {
+		return "", false
+	}
+
+	summary := info.GetMetadata()[ipcauth.ErrorMetaSummary]
+	command := info.GetMetadata()[ipcauth.ErrorMetaCommand]
+	if summary == "" {
+		// Detail without a summary: fall back to the status message, which
+		// carries the same text.
+		summary = strings.TrimSpace(gstatus.Convert(err).Message())
+	}
+	if command == "" {
+		return summary, true
+	}
+
+	return fmt.Sprintf("%s\n\n    %s\n", summary, command), true
+}
+
+// privilegeErrorInfo returns the daemon's privilege-refusal detail, if the error
+// carries one.
+func privilegeErrorInfo(err error) (*errdetails.ErrorInfo, bool) {
+	if err == nil {
+		return nil, false
+	}
+
+	for _, detail := range gstatus.Convert(err).Details() {
+		info, ok := detail.(*errdetails.ErrorInfo)
+		if !ok {
+			continue
+		}
+		if info.GetReason() == ipcauth.ErrorReasonPrivilegeRequired && info.GetDomain() == ipcauth.ErrorDomain {
+			return info, true
+		}
+	}
+	return nil, false
+}

client/cmd/debug.go

@@ -29,8 +29,9 @@ const errCloseConnection = "Failed to close connection: %v"
 var (
 	logFileCount        uint32
 	systemInfoFlag      bool
-	uploadBundleFlag    bool
-	uploadBundleURLFlag string
+	uploadBundleFlag         bool
+	uploadBundleURLFlag      string
+	uploadBundleInsecureFlag bool
 )
 
 var debugCmd = &cobra.Command{
@@ -174,10 +175,11 @@ func debugBundle(cmd *cobra.Command, _ []string) error {
 	}
 	if uploadBundleFlag {
 		request.UploadURL = uploadBundleURLFlag
+		request.UploadInsecure = uploadBundleInsecureFlag
 	}
 	resp, err := client.DebugBundle(cmd.Context(), request)
 	if err != nil {
-		return fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message())
+		return daemonCallError("bundle debug", err)
 	}
 	cmd.Printf("Local file:\n%s\n", resp.GetPath())
 
@@ -373,10 +375,11 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 	}
 	if uploadBundleFlag {
 		request.UploadURL = uploadBundleURLFlag
+		request.UploadInsecure = uploadBundleInsecureFlag
 	}
 	resp, err := client.DebugBundle(cmd.Context(), request)
 	if err != nil {
-		return fmt.Errorf("failed to bundle debug: %v", status.Convert(err).Message())
+		return daemonCallError("bundle debug", err)
 	}
 
 	if needsRestoreUp {
@@ -524,10 +527,12 @@ func init() {
 	debugBundleCmd.Flags().BoolVarP(&systemInfoFlag, "system-info", "S", true, "Adds system information to the debug bundle")
 	debugBundleCmd.Flags().BoolVarP(&uploadBundleFlag, "upload-bundle", "U", false, "Uploads the debug bundle to a server")
 	debugBundleCmd.Flags().StringVar(&uploadBundleURLFlag, "upload-bundle-url", types.DefaultBundleURL, "Service URL to get an URL to upload the debug bundle")
+	debugBundleCmd.Flags().BoolVar(&uploadBundleInsecureFlag, "upload-bundle-insecure", false, "Allow uploading to an http or untrusted-TLS upload server (self-hosted); requires root")
 
 	forCmd.Flags().Uint32VarP(&logFileCount, "log-file-count", "C", 1, "Number of rotated log files to include in debug bundle")
 	forCmd.Flags().BoolVarP(&systemInfoFlag, "system-info", "S", true, "Adds system information to the debug bundle")
 	forCmd.Flags().BoolVarP(&uploadBundleFlag, "upload-bundle", "U", false, "Uploads the debug bundle to a server")
 	forCmd.Flags().StringVar(&uploadBundleURLFlag, "upload-bundle-url", types.DefaultBundleURL, "Service URL to get an URL to upload the debug bundle")
+	forCmd.Flags().BoolVar(&uploadBundleInsecureFlag, "upload-bundle-insecure", false, "Allow uploading to an http or untrusted-TLS upload server (self-hosted); requires root")
 	forCmd.Flags().Bool("capture", false, "Capture packets during the debug duration and include in bundle")
 }

client/cmd/logout.go

@@ -46,7 +46,7 @@ var logoutCmd = &cobra.Command{
 		}
 
 		if _, err := daemonClient.Logout(ctx, req); err != nil {
-			return fmt.Errorf("deregister: %v", err)
+			return daemonCallError("deregister", err)
 		}
 
 		cmd.Println("Deregistered successfully")

client/cmd/root.go

@@ -20,7 +20,6 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
 	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials/insecure"
 
 	daddr "github.com/netbirdio/netbird/client/internal/daemonaddr"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
@@ -91,6 +90,7 @@ var (
 			// Don't resolve for service commands — they create the socket, not connect to it.
 			if !isServiceCmd(cmd) {
 				daemonAddr = daddr.ResolveUnixDaemonAddr(daemonAddr)
+				daemonAddr = daddr.ResolveDaemonAddr(daemonAddr)
 			}
 			return nil
 		},
@@ -143,10 +143,10 @@ func init() {
 
 	defaultDaemonAddr := "unix:///var/run/netbird.sock"
 	if runtime.GOOS == "windows" {
-		defaultDaemonAddr = "tcp://127.0.0.1:41731"
+		defaultDaemonAddr = daddr.WindowsPipeAddr
 	}
 
-	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]")
+	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]")
 	rootCmd.PersistentFlags().StringVarP(&managementURL, "management-url", "m", "", fmt.Sprintf("Management Service URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultManagementURL))
 	rootCmd.PersistentFlags().StringVar(&adminURL, "admin-url", "", fmt.Sprintf("Admin Panel URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultAdminURL))
 	rootCmd.PersistentFlags().StringVarP(&logLevel, "log-level", "l", "info", "sets NetBird log level")
@@ -269,12 +269,10 @@ func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, e
 	ctx, cancel := context.WithTimeout(ctx, time.Second*10)
 	defer cancel()
 
-	return grpc.DialContext(
-		ctx,
-		strings.TrimPrefix(addr, "tcp://"),
-		grpc.WithTransportCredentials(insecure.NewCredentials()),
-		grpc.WithBlock(),
-	)
+	target, opts := daddr.DialTarget(addr)
+	opts = append(opts, grpc.WithBlock())
+
+	return grpc.DialContext(ctx, target, opts...)
 }
 
 // WithBackOff execute function in backoff cycle.

client/cmd/service.go

@@ -33,10 +33,15 @@ var (
 )
 
 type program struct {
-	ctx              context.Context
-	cancel           context.CancelFunc
-	serv             *grpc.Server
-	jsonServ         *http.Server
+	ctx      context.Context
+	cancel   context.CancelFunc
+	serv     *grpc.Server
+	jsonServ *http.Server
+	// jsonClient is the gateway's own connection to the daemon. It is held so
+	// shutting the gateway down also closes it: nothing else references it once
+	// the handlers are registered, so its transport goroutines would otherwise
+	// outlive the server.
+	jsonClient       *grpc.ClientConn
 	jsonServMu       sync.Mutex
 	serverInstance   *server.Server
 	serverInstanceMu sync.Mutex

client/cmd/service_controller.go

@@ -5,6 +5,7 @@ package cmd
 import (
 	"context"
 	"fmt"
+	"runtime"
 	"time"
 
 	"github.com/kardianos/service"
@@ -13,6 +14,8 @@ import (
 	"github.com/spf13/cobra"
 	"google.golang.org/grpc"
 
+	"github.com/netbirdio/netbird/client/internal/daemonaddr"
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/server"
 	"github.com/netbirdio/netbird/client/system"
@@ -26,6 +29,31 @@ func validateJSONSocketFlags() error {
 	return nil
 }
 
+// daemonServerOptions installs the transport credentials that expose each
+// caller's kernel-authenticated identity to the handlers, which is what lets
+// the daemon require root/administrator for privileged operations.
+//
+// The handshake exchanges no bytes, so older CLI and UI binaries still
+// interoperate. Callers on a TCP socket carry no identity at all: the daemon
+// keeps serving them, and the privileged operations deny them, so a warning is
+// logged to make the loss of functionality visible.
+func daemonServerOptions(network string) []grpc.ServerOption {
+	if network == "tcp" {
+		log.Warnf("daemon is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
+			"so privileged operations (SSH root login, SSH auth, enabling the SSH server, management URL changes, "+
+			"deregistration) will be denied. Use a unix socket, or npipe:// on Windows", daemonAddr)
+		return nil
+	}
+
+	creds := ipcauth.NewTransportCredentials()
+	if creds == nil {
+		log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied", runtime.GOOS)
+		return nil
+	}
+
+	return []grpc.ServerOption{grpc.Creds(creds)}
+}
+
 func (p *program) Start(svc service.Service) error {
 	// Start should not block. Do the actual work async.
 	log.Info("starting NetBird service") //nolint
@@ -37,68 +65,106 @@ func (p *program) Start(svc service.Service) error {
 	// Collect static system and platform information
 	system.UpdateStaticInfoAsync()
 
-	// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
-	p.serv = grpc.NewServer()
-
-	daemonListener, err := listenOnAddress(daemonAddr)
-	if err != nil {
-		return fmt.Errorf("listen daemon interface: %w", err)
+	// A daemon installed before named-pipe support has the loopback TCP address
+	// persisted. Move it to the named pipe so an upgraded daemon can identify
+	// its callers instead of silently serving an unauthenticated socket.
+	if migrated, ok := daemonaddr.MigrateLegacy(daemonAddr); ok {
+		log.Infof("daemon address %q predates named-pipe support, listening on %q so callers can be identified", daemonAddr, migrated)
+		daemonAddr = migrated
 	}
 
-	var jsonListener *socketListener
-	if enableJSONSocket {
-		jsonListener, err = listenOnAddress(jsonSocket)
-		if err != nil {
-			_ = daemonListener.Close()
-			return fmt.Errorf("listen daemon JSON interface: %w", err)
-		}
-	} else {
-		removeStaleUnixSocketForAddress(jsonSocket)
+	network, _, err := parseListenAddress(daemonAddr)
+	if err != nil {
+		return fmt.Errorf("parse daemon address: %w", err)
+	}
+
+	// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
+	p.serv = grpc.NewServer(daemonServerOptions(network)...)
+
+	daemonListener, jsonListener, err := listenDaemonSockets()
+	if err != nil {
+		return err
 	}
 
 	go func() {
-		defer daemonListener.Close()
-		if jsonListener != nil {
-			defer jsonListener.Close()
-		}
-
-		if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
-			log.Error(err)
-			return
-		}
-		if jsonListener != nil {
-			if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
-				log.Error(err)
-				return
-			}
-		}
-
-		serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
-		if err := serverInstance.Start(); err != nil {
-			log.Fatalf("failed to start daemon: %v", err)
-		}
-		proto.RegisterDaemonServiceServer(p.serv, serverInstance)
-
-		p.serverInstanceMu.Lock()
-		p.serverInstance = serverInstance
-		p.serverInstanceMu.Unlock()
-
-		if jsonListener != nil {
-			if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
-				log.Fatalf("failed to start daemon JSON server: %v", err)
-			}
-		} else {
-			log.Debug("daemon JSON socket disabled")
-		}
-
-		log.Printf("started daemon server: %v", daemonListener.address)
-		if err := p.serv.Serve(daemonListener.Listener); err != nil {
-			log.Errorf("failed to serve daemon requests: %v", err)
+		// Fatal here rather than inside serve, so serve's deferred listener
+		// closes run before the process exits.
+		if err := p.serve(daemonListener, jsonListener); err != nil {
+			log.Fatalf("failed to %v", err)
 		}
 	}()
 	return nil
 }
 
+// listenDaemonSockets opens the daemon control socket and, when it is enabled, the
+// JSON gateway socket. The control socket is closed again if the second one fails,
+// so a failed start leaves nothing listening. The returned JSON listener is nil
+// when the socket is disabled.
+func listenDaemonSockets() (*socketListener, *socketListener, error) {
+	daemonListener, err := listenOnAddress(daemonAddr)
+	if err != nil {
+		return nil, nil, fmt.Errorf("listen daemon interface: %w", err)
+	}
+
+	if !enableJSONSocket {
+		removeStaleUnixSocketForAddress(jsonSocket)
+		return daemonListener, nil, nil
+	}
+
+	jsonListener, err := listenOnAddress(jsonSocket)
+	if err != nil {
+		if cerr := daemonListener.Close(); cerr != nil {
+			log.Debugf("close daemon listener: %v", cerr)
+		}
+		return nil, nil, fmt.Errorf("listen daemon JSON interface: %w", err)
+	}
+
+	return daemonListener, jsonListener, nil
+}
+
+// serve brings up the daemon server on an already-open control socket and blocks
+// until it stops. jsonListener is nil when the JSON socket is disabled. A returned
+// error means the daemon cannot run at all and the caller is expected to exit; the
+// failures it recovers from on its own are logged here.
+func (p *program) serve(daemonListener, jsonListener *socketListener) error {
+	defer daemonListener.Close()
+	if jsonListener != nil {
+		defer jsonListener.Close()
+	}
+
+	// chmodUnixSocket is a no-op for a nil listener and for a non-unix one.
+	if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
+		log.Error(err)
+		return nil
+	}
+	if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
+		log.Error(err)
+		return nil
+	}
+
+	serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
+	if err := serverInstance.Start(); err != nil {
+		return fmt.Errorf("start daemon: %w", err)
+	}
+	proto.RegisterDaemonServiceServer(p.serv, serverInstance)
+
+	p.serverInstanceMu.Lock()
+	p.serverInstance = serverInstance
+	p.serverInstanceMu.Unlock()
+
+	if jsonListener == nil {
+		log.Debug("daemon JSON socket disabled")
+	} else if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
+		return fmt.Errorf("start daemon JSON server: %w", err)
+	}
+
+	log.Printf("started daemon server: %v", daemonListener.address)
+	if err := p.serv.Serve(daemonListener.Listener); err != nil {
+		log.Errorf("failed to serve daemon requests: %v", err)
+	}
+	return nil
+}
+
 func (p *program) Stop(srv service.Service) error {
 	p.serverInstanceMu.Lock()
 	if p.serverInstance != nil {
@@ -113,8 +179,13 @@ func (p *program) Stop(srv service.Service) error {
 	p.cancel()
 
 	p.jsonServMu.Lock()
-	jsonServ := p.jsonServ
+	jsonServ, jsonClient := p.jsonServ, p.jsonClient
 	p.jsonServMu.Unlock()
+	if jsonClient != nil {
+		if err := jsonClient.Close(); err != nil {
+			log.Debugf("close daemon JSON gateway client: %v", err)
+		}
+	}
 	if jsonServ != nil {
 		shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 2*time.Second)
 		if err := jsonServ.Shutdown(shutdownCtx); err != nil {

client/cmd/service_json_gateway.go

@@ -5,27 +5,123 @@ package cmd
 import (
 	"context"
 	"errors"
+	"fmt"
 	"net"
 	"net/http"
-	"strings"
+	"sync"
 	"time"
 
 	"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials/insecure"
 
+	"github.com/netbirdio/netbird/client/internal/daemonaddr"
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
 )
 
-func grpcGatewayEndpoint(addr string) string {
-	return strings.TrimPrefix(addr, "tcp://")
+// jsonPeerIdentity is the context key under which the connecting HTTP client's
+// identity is stashed for the lifetime of its connection.
+type jsonPeerIdentity struct{}
+
+// jsonPeerIdentityValue pairs the identity with whether it could be read at
+// all, so an unreadable identity is forwarded as "unknown" rather than omitted.
+type jsonPeerIdentityValue struct {
+	id    ipcauth.Identity
+	known bool
+}
+
+// jsonConnContext reads the identity of the client connecting to the JSON
+// socket and stashes it on the connection's context. The gateway re-dials the
+// daemon in-process, so the daemon would otherwise see every JSON request as
+// coming from the daemon itself.
+func jsonConnContext(ctx context.Context, c net.Conn) context.Context {
+	value := jsonPeerIdentityValue{}
+	id, err := ipcauth.ConnIdentity(c)
+	if err != nil {
+		log.Warnf("json gateway: cannot read HTTP client identity, privileged operations will be denied for this connection: %v", err)
+	} else {
+		value.id = id
+		value.known = true
+	}
+	return context.WithValue(ctx, jsonPeerIdentity{}, value)
+}
+
+// forwardIdentity stamps the HTTP client's identity onto every call the gateway
+// makes to the daemon.
+//
+// It is an interceptor on the gateway's client connection rather than a
+// runtime.WithMetadata annotator because grpc-gateway skips annotators when no
+// request header maps to metadata, which an HTTP/1.0 request with no Host header
+// over a unix socket achieves. The daemon would then receive no marker, see its own
+// identity as the transport peer, and authorize the request as the daemon itself.
+// An interceptor runs for every RPC whatever the request looked like.
+func forwardIdentity(ctx context.Context) context.Context {
+	value, ok := ctx.Value(jsonPeerIdentity{}).(jsonPeerIdentityValue)
+	if !ok {
+		// No ConnContext ran for this request, so forward an unknown identity:
+		// the daemon must not mistake its own identity for the client's.
+		return ipcauth.WithForwardedIdentity(ctx, ipcauth.Identity{}, false)
+	}
+	return ipcauth.WithForwardedIdentity(ctx, value.id, value.known)
+}
+
+func forwardIdentityUnary(ctx context.Context, method string, req, reply any, cc *grpc.ClientConn, invoker grpc.UnaryInvoker, opts ...grpc.CallOption) error {
+	return invoker(forwardIdentity(ctx), method, req, reply, cc, opts...)
+}
+
+func forwardIdentityStream(ctx context.Context, desc *grpc.StreamDesc, cc *grpc.ClientConn, method string, streamer grpc.Streamer, opts ...grpc.CallOption) (grpc.ClientStream, error) {
+	return streamer(forwardIdentity(ctx), desc, cc, method, opts...)
+}
+
+// reservedHeaderWarning limits the dropped-header warning to the first occurrence.
+var reservedHeaderWarning sync.Once
+
+// jsonIncomingHeaderMatcher keeps an HTTP client from supplying the metadata the
+// gateway uses to forward its identity. grpc-gateway turns "Grpc-Metadata-<key>"
+// headers into gRPC metadata and joins them ahead of what its annotators add, so
+// without this filter a JSON client could send its own x-netbird-fwd-uid and the
+// daemon would authorize that instead of the client's real identity.
+func jsonIncomingHeaderMatcher(key string) (string, bool) {
+	mapped, ok := runtime.DefaultHeaderMatcher(key)
+	if !ok {
+		return "", false
+	}
+	if ipcauth.IsReservedForwardKey(mapped) {
+		// Warn once: any client can send these on every request, so warning each
+		// time hands it a way to fill the log. The rest are debug-level.
+		reservedHeaderWarning.Do(func() {
+			log.Warnf("json gateway: dropping reserved header %q from a request: only the gateway may set the caller's identity", key)
+		})
+		log.Debugf("json gateway: dropping reserved header %q", key)
+		return "", false
+	}
+	return mapped, true
 }
 
 func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint string) error {
-	mux := runtime.NewServeMux()
-	opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
-	if err := proto.RegisterDaemonServiceHandlerFromEndpoint(p.ctx, mux, grpcGatewayEndpoint(daemonEndpoint), opts); err != nil {
+	if jsonListener.network == "tcp" {
+		log.Warnf("daemon JSON socket is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
+			"so privileged operations will be denied for JSON clients", jsonListener.address)
+	}
+
+	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
+
+	// grpc.NewClient does not connect until the first request, so registering
+	// the handler here cannot block daemon startup.
+	target, opts := daemonaddr.DialTarget(daemonEndpoint)
+	opts = append(opts,
+		grpc.WithChainUnaryInterceptor(forwardIdentityUnary),
+		grpc.WithChainStreamInterceptor(forwardIdentityStream),
+	)
+	conn, err := grpc.NewClient(target, opts...)
+	if err != nil {
+		return fmt.Errorf("create daemon client for JSON gateway: %w", err)
+	}
+	if err := proto.RegisterDaemonServiceHandler(p.ctx, mux, conn); err != nil {
+		if cerr := conn.Close(); cerr != nil {
+			log.Debugf("close daemon client after failed JSON gateway registration: %v", cerr)
+		}
 		return err
 	}
 
@@ -35,10 +131,12 @@ func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint
 		BaseContext: func(net.Listener) context.Context {
 			return p.ctx
 		},
+		ConnContext: jsonConnContext,
 	}
 
 	p.jsonServMu.Lock()
 	p.jsonServ = jsonServer
+	p.jsonClient = conn
 	p.jsonServMu.Unlock()
 
 	go func() {

client/cmd/service_json_gateway_test.go

@@ -0,0 +1,261 @@
+//go:build !windows && !ios && !android
+
+package cmd
+
+import (
+	"context"
+	"net"
+	"net/http"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
+	"google.golang.org/grpc/credentials"
+	"google.golang.org/grpc/metadata"
+	"google.golang.org/grpc/peer"
+
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+)
+
+// The JSON gateway runs inside the daemon and re-dials it locally, so every JSON
+// request reaches a handler with the daemon's own identity as the transport peer.
+// The gateway therefore forwards its HTTP client's identity as metadata, and the
+// daemon authorizes that instead of itself. These tests drive the real wiring
+// (jsonConnContext, forwardIdentity, jsonIncomingHeaderMatcher) and check the
+// identity a handler would end up authorizing.
+
+// daemonSideCtx is what a handler sees for a gateway-relayed call. The transport
+// peer must be this process's own identity: the gateway is the daemon, so the two
+// cannot differ, and hardcoding root here instead would describe a state that
+// never occurs.
+func daemonSideCtx(t *testing.T, md metadata.MD) context.Context {
+	t.Helper()
+	self, err := ipcauth.CurrentProcessIdentity()
+	if err != nil {
+		t.Skipf("cannot read this process's identity: %v", err)
+	}
+	ctx := peer.NewContext(context.Background(), &peer.Peer{
+		AuthInfo: ipcauth.AuthInfo{
+			CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
+			Identity:       self,
+		},
+	})
+	return metadata.NewIncomingContext(ctx, md)
+}
+
+// gatewayMetadata reproduces what the daemon receives for a JSON request: the
+// mux annotates the context from the request's headers, then the interceptor on the
+// gateway's client connection stamps the caller's identity. The order matters,
+// since the interceptor must win over anything a header put there.
+func gatewayMetadata(t *testing.T, req *http.Request, ctx context.Context) metadata.MD {
+	t.Helper()
+	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
+	annotated, err := runtime.AnnotateContext(ctx, mux, req,
+		"/daemon.DaemonService/SetConfig",
+		runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
+	if err != nil {
+		t.Fatalf("annotate: %v", err)
+	}
+
+	md, ok := metadata.FromOutgoingContext(forwardIdentity(annotated))
+	if !ok {
+		t.Fatal("the interceptor produced no metadata")
+	}
+	return md
+}
+
+// clientCtx is the connection context jsonConnContext would have produced for an
+// HTTP client whose identity the gateway could read.
+func clientCtx(id ipcauth.Identity, known bool) context.Context {
+	return context.WithValue(context.Background(), jsonPeerIdentity{},
+		jsonPeerIdentityValue{id: id, known: known})
+}
+
+// An HTTP client must not be able to name its own identity. grpc-gateway turns
+// Grpc-Metadata-<key> headers into gRPC metadata, so without the header filter and
+// the interceptor overwriting the reserved keys, this request would authorize as
+// uid 0.
+func TestJSONGateway_ForgedIdentityHeaderIsDropped(t *testing.T) {
+	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Uid", "0")
+	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Gid", "0")
+	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd", "1")
+	req.Header.Set("Grpc-Metadata-X-Netbird-Fwd-Sid", "S-1-5-18")
+
+	caller := ipcauth.Identity{UID: 31000, GID: 31000}
+	md := gatewayMetadata(t, req, clientCtx(caller, true))
+
+	id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md))
+	if !ok {
+		t.Fatal("the forwarded identity should be usable")
+	}
+	if id.IsPrivileged() {
+		t.Errorf("forged header was believed: authorized as %v", id)
+	}
+	if id.UID != caller.UID {
+		t.Errorf("authorized as uid %d, want the real client %d", id.UID, caller.UID)
+	}
+}
+
+// A request with no headers at all (HTTP/1.0 needs no Host, and a unix socket
+// yields no host:port) makes grpc-gateway produce no metadata whatsoever and skip
+// its annotators: "if len(pairs) == 0 { return ctx, nil, nil }" in
+// runtime/context.go. That is why the identity is stamped by an interceptor
+// instead. This is the case that previously reached the gate as the daemon itself.
+func TestJSONGateway_HeaderlessRequestIsStillMarkedForwarded(t *testing.T) {
+	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	req.Header = http.Header{}
+	req.Host = ""
+
+	caller := ipcauth.Identity{UID: 31000, GID: 31000}
+	ctx := clientCtx(caller, true)
+
+	// Pin the skip path itself: if grpc-gateway ever produced a pair here, this
+	// test would still pass below while no longer covering what it was written for.
+	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
+	annotated, err := runtime.AnnotateContext(ctx, mux, req,
+		"/daemon.DaemonService/SetConfig",
+		runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
+	if err != nil {
+		t.Fatalf("annotate: %v", err)
+	}
+	if md, ok := metadata.FromOutgoingContext(annotated); ok {
+		t.Fatalf("grpc-gateway produced metadata %v for a headerless request; "+
+			"this test no longer covers the annotator-skip path", md)
+	}
+
+	md := gatewayMetadata(t, req, ctx)
+
+	id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md))
+	if !ok {
+		t.Fatal("the forwarded identity should be usable")
+	}
+	if id.UID != caller.UID || id.IsPrivileged() {
+		t.Errorf("authorized as %v, want the real client uid %d", id, caller.UID)
+	}
+}
+
+// When the gateway cannot read its client's identity (a TCP JSON socket, say) it
+// forwards the marker alone. The daemon must then report "unidentified" so the
+// privileged operations refuse, rather than falling back to the gateway's own
+// identity.
+func TestJSONGateway_UnreadableClientIdentityIsUnidentified(t *testing.T) {
+	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	md := gatewayMetadata(t, req, clientCtx(ipcauth.Identity{}, false))
+
+	if id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md)); ok {
+		t.Errorf("a request with no client identity was authorized as %v", id)
+	}
+}
+
+// A request that never passed through jsonConnContext (no stashed identity) must
+// also come out unidentified rather than as the daemon.
+func TestJSONGateway_MissingConnContextIsUnidentified(t *testing.T) {
+	req, err := http.NewRequest(http.MethodPost, "http://localhost/daemon.DaemonService/SetConfig", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	md := gatewayMetadata(t, req, context.Background())
+
+	if id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, md)); ok {
+		t.Errorf("a request with no connection context was authorized as %v", id)
+	}
+}
+
+// End to end over a real unix socket: the gateway reads the connecting client's
+// identity from the socket itself, so a client cannot present anything else.
+func TestJSONGateway_IdentityComesFromTheSocket(t *testing.T) {
+	mux := runtime.NewServeMux(runtime.WithIncomingHeaderMatcher(jsonIncomingHeaderMatcher))
+
+	type observed struct {
+		md metadata.MD
+	}
+	seen := make(chan observed, 1)
+
+	srv := &http.Server{
+		Handler: http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			ctx, err := runtime.AnnotateContext(r.Context(), mux, r,
+				"/daemon.DaemonService/SetConfig",
+				runtime.WithHTTPPathPattern("/daemon.DaemonService/SetConfig"))
+			if err != nil {
+				t.Errorf("annotate: %v", err)
+				return
+			}
+			md, _ := metadata.FromOutgoingContext(forwardIdentity(ctx))
+			seen <- observed{md: md}
+			w.WriteHeader(http.StatusOK)
+		}),
+		ReadHeaderTimeout: 5 * time.Second,
+		ConnContext:       jsonConnContext,
+	}
+
+	sock := filepath.Join(t.TempDir(), "http.sock")
+	ln, err := net.Listen("unix", sock)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() {
+		if err := srv.Close(); err != nil {
+			t.Logf("close server: %v", err)
+		}
+	})
+	go func() {
+		if err := srv.Serve(ln); err != nil && err != http.ErrServerClosed {
+			t.Logf("serve: %v", err)
+		}
+	}()
+
+	conn, err := net.Dial("unix", sock)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() {
+		if err := conn.Close(); err != nil {
+			t.Logf("close conn: %v", err)
+		}
+	})
+
+	// Forge the identity headers on the wire as well.
+	request := "POST /daemon.DaemonService/SetConfig HTTP/1.1\r\n" +
+		"Host: localhost\r\n" +
+		"Grpc-Metadata-X-Netbird-Fwd: 1\r\n" +
+		"Grpc-Metadata-X-Netbird-Fwd-Uid: 0\r\n" +
+		"Content-Length: 0\r\n\r\n"
+	if _, err := conn.Write([]byte(request)); err != nil {
+		t.Fatal(err)
+	}
+
+	select {
+	case got := <-seen:
+		self, err := ipcauth.CurrentProcessIdentity()
+		if err != nil {
+			t.Skipf("cannot read this process's identity: %v", err)
+		}
+		// The socket peer is this test process, so that is the identity the
+		// gateway must forward, not the uid 0 the request asked for.
+		if uids := got.md.Get("x-netbird-fwd-uid"); len(uids) != 1 {
+			t.Fatalf("x-netbird-fwd-uid = %v, want exactly the gateway's own value", uids)
+		}
+		id, ok := ipcauth.CallerIdentity(daemonSideCtx(t, got.md))
+		if !ok {
+			t.Fatal("the forwarded identity should be usable")
+		}
+		if id.UID != self.UID {
+			t.Errorf("authorized as uid %d, want the socket peer %d", id.UID, self.UID)
+		}
+	case <-time.After(5 * time.Second):
+		t.Fatal("the gateway never handled the request")
+	}
+}

client/cmd/service_params.go

@@ -13,6 +13,7 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/netbirdio/netbird/client/configs"
+	"github.com/netbirdio/netbird/client/internal/daemonaddr"
 	"github.com/netbirdio/netbird/util"
 )
 
@@ -125,6 +126,13 @@ func applyServiceParams(cmd *cobra.Command, params *serviceParams) {
 
 	if !rootCmd.PersistentFlags().Changed("daemon-addr") && params.DaemonAddr != "" {
 		daemonAddr = params.DaemonAddr
+		// An install that predates named-pipe support has the loopback TCP
+		// address saved. Callers carry no identity over TCP, so move it to the
+		// pipe instead of restoring a socket the daemon cannot authorize on.
+		if migrated, ok := daemonaddr.MigrateLegacy(daemonAddr); ok {
+			cmd.Printf("Moving the saved daemon address from %s to %s so the daemon can identify its callers\n", daemonAddr, migrated)
+			daemonAddr = migrated
+		}
 	}
 
 	if !serviceCmd.PersistentFlags().Changed("json-socket") && params.JSONSocket != "" {

client/cmd/service_pipe_other.go

@@ -0,0 +1,14 @@
+//go:build !windows
+
+package cmd
+
+import (
+	"fmt"
+	"net"
+)
+
+// listenNamedPipe is Windows-only: no other platform serves the daemon on a
+// named pipe.
+func listenNamedPipe(string) (net.Listener, string, error) {
+	return nil, "", fmt.Errorf("named pipes are only supported on Windows")
+}

client/cmd/service_pipe_windows.go

@@ -0,0 +1,41 @@
+//go:build windows
+
+package cmd
+
+import (
+	"errors"
+	"fmt"
+	"net"
+
+	"github.com/Microsoft/go-winio"
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/daemonaddr"
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+)
+
+// listenNamedPipe creates the daemon control pipe and reports the path it ended
+// up on. The security descriptor lets any local caller connect, as a Unix socket
+// at 0666 does, and the privileged operations are authorized separately from the
+// caller's token.
+//
+// The protected name comes first so that an unprivileged process cannot take the
+// name before the service does. Creating it requires being an administrator or
+// LocalSystem, so a daemon an ordinary user runs themselves, as in netstack mode,
+// falls back to the plain name; clients try both and check who serves them.
+func listenNamedPipe(name string) (net.Listener, string, error) {
+	var errs []error
+	for _, path := range daemonaddr.PipePaths(name) {
+		listener, err := winio.ListenPipe(path, &winio.PipeConfig{
+			SecurityDescriptor: ipcauth.DefaultPipeSDDL(),
+		})
+		if err != nil {
+			log.Debugf("not serving the daemon on %s: %v", path, err)
+			errs = append(errs, fmt.Errorf("%s: %w", path, err))
+			continue
+		}
+		return listener, path, nil
+	}
+
+	return nil, "", errors.Join(errs...)
+}

client/cmd/service_socket.go

@@ -26,6 +26,14 @@ func listenOnAddress(addr string) (*socketListener, error) {
 		return nil, err
 	}
 
+	if network == "npipe" {
+		listener, path, err := listenNamedPipe(address)
+		if err != nil {
+			return nil, err
+		}
+		return &socketListener{Listener: listener, network: network, address: path}, nil
+	}
+
 	if network == "unix" {
 		removeStaleUnixSocket(address)
 	}
@@ -41,11 +49,11 @@ func listenOnAddress(addr string) (*socketListener, error) {
 func parseListenAddress(addr string) (string, string, error) {
 	network, address, ok := strings.Cut(addr, "://")
 	if !ok || network == "" || address == "" {
-		return "", "", fmt.Errorf("address must be in [unix|tcp]://[path|host:port] format: %q", addr)
+		return "", "", fmt.Errorf("address must be in [unix|tcp|npipe]://[path|host:port|name] format: %q", addr)
 	}
 
 	switch network {
-	case "unix", "tcp":
+	case "unix", "tcp", "npipe":
 		return network, address, nil
 	default:
 		return "", "", fmt.Errorf("unsupported daemon address protocol: %v", network)

client/cmd/up.go

@@ -325,7 +325,7 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
 		if st, ok := gstatus.FromError(err); ok && st.Code() == codes.Unavailable {
 			log.Warnf("setConfig method is not available in the daemon: %s", st.Message())
 		} else {
-			return fmt.Errorf("call service setConfig method: %v", err)
+			return daemonCallError("call service setConfig method", err)
 		}
 	}
 
@@ -379,7 +379,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 	}
 
 	if loginErr != nil {
-		return fmt.Errorf("login failed: %v", loginErr)
+		return daemonCallError("login failed", loginErr)
 	}
 
 	if loginResp.NeedsSSOLogin {
@@ -392,7 +392,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 		ProfileName: &profileID,
 		Username:    &username,
 	}); err != nil {
-		return fmt.Errorf("call service up method: %v", err)
+		return daemonCallError("call service up method", err)
 	}
 
 	return nil

client/configs/configs.go

@@ -6,6 +6,11 @@ import (
 	"runtime"
 )
 
+// UILogFile is the file name the desktop UI writes its log to. It is defined
+// here so the UI (writer), the daemon's RegisterUILog validation, and the debug
+// bundle collector all share one definition.
+const UILogFile = "gui-client.log"
+
 var StateDir string
 
 func init() {

client/firewall/nftables/legacy_rule_linux_test.go

@@ -0,0 +1,60 @@
+package nftables
+
+import (
+	"testing"
+
+	"github.com/google/nftables/expr"
+	"github.com/stretchr/testify/require"
+)
+
+func TestBuildLegacyRouteRuleExpressions(t *testing.T) {
+	sourcePayload := &expr.Payload{}
+	sourceCmp := &expr.Cmp{}
+	destinationPayload := &expr.Payload{}
+	destinationCmp := &expr.Cmp{}
+	nilSourceDestination := &expr.Payload{}
+	nilDestinationSource := &expr.Cmp{}
+
+	tests := []struct {
+		name        string
+		source      []expr.Any
+		destination []expr.Any
+		matches     []expr.Any
+	}{
+		{
+			name:        "both non-empty",
+			source:      []expr.Any{sourcePayload, sourceCmp},
+			destination: []expr.Any{destinationPayload, destinationCmp},
+			matches:     []expr.Any{sourcePayload, sourceCmp, destinationPayload, destinationCmp},
+		},
+		{
+			name:        "nil source",
+			destination: []expr.Any{nilSourceDestination},
+			matches:     []expr.Any{nilSourceDestination},
+		},
+		{
+			name:    "nil destination",
+			source:  []expr.Any{nilDestinationSource},
+			matches: []expr.Any{nilDestinationSource},
+		},
+		{
+			name: "both nil",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := buildLegacyRouteRuleExpressions(tt.source, tt.destination)
+
+			require.Len(t, got, len(tt.matches)+2)
+			for i, match := range tt.matches {
+				require.Same(t, match, got[i])
+			}
+
+			require.IsType(t, &expr.Counter{}, got[len(tt.matches)])
+			verdict, ok := got[len(tt.matches)+1].(*expr.Verdict)
+			require.True(t, ok)
+			require.Equal(t, expr.VerdictAccept, verdict.Kind)
+		})
+	}
+}

client/firewall/nftables/router_linux.go

@@ -953,6 +953,17 @@ func (r *router) addMSSClampingRules() error {
 	return r.conn.Flush()
 }
 
+func buildLegacyRouteRuleExpressions(sourceExp, destExp []expr.Any) []expr.Any {
+	exprs := make([]expr.Any, 0, len(sourceExp)+len(destExp)+2)
+	exprs = append(exprs, sourceExp...)
+	exprs = append(exprs, destExp...)
+	exprs = append(exprs,
+		&expr.Counter{},
+		&expr.Verdict{Kind: expr.VerdictAccept},
+	)
+	return exprs
+}
+
 // addLegacyRouteRule adds a legacy routing rule for mgmt servers pre route acls
 func (r *router) addLegacyRouteRule(pair firewall.RouterPair) error {
 	sourceExp, err := r.applyNetwork(pair.Source, nil, true)
@@ -965,15 +976,7 @@ func (r *router) addLegacyRouteRule(pair firewall.RouterPair) error {
 		return fmt.Errorf("apply destination: %w", err)
 	}
 
-	exprs := []expr.Any{
-		&expr.Counter{},
-		&expr.Verdict{
-			Kind: expr.VerdictAccept,
-		},
-	}
-
-	exprs = append(exprs, sourceExp...)
-	exprs = append(exprs, destExp...)
+	exprs := buildLegacyRouteRuleExpressions(sourceExp, destExp)
 
 	ruleKey := firewall.GenKey(firewall.ForwardingFormat, pair)
 

client/iface/iface_test.go

@@ -464,6 +464,8 @@ func Test_RemovePeer(t *testing.T) {
 }
 
 func Test_ConnectPeers(t *testing.T) {
+	t.Setenv("NB_DISABLE_EBPF_WG_PROXY", "true")
+
 	peer1ifaceName := fmt.Sprintf("utun%d", WgIntNumber+400)
 	peer1wgIP := netip.MustParsePrefix("10.99.99.17/30")
 	peer1Key, _ := wgtypes.GeneratePrivateKey()
@@ -505,12 +507,8 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	localIP, err := getLocalIP()
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer1wgPort))
+	localIP1 := "127.0.0.1"
+	peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP1, peer1wgPort))
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -546,7 +544,8 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer2wgPort))
+	localIP2 := "127.0.0.1"
+	peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP2, peer2wgPort))
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -569,17 +568,17 @@ func Test_ConnectPeers(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	// todo: investigate why in some tests execution we need 30s
+	// The peers use userspace WireGuard (stdnet transport). A tight busy-loop
+	// here starves the wireguard-go goroutines that process the handshake, so
+	// poll on a ticker instead and yield the CPU between checks. WireGuard also
+	// only retries a lost handshake initiation every REKEY_TIMEOUT (5s), which
+	// is why the overall wait can occasionally stretch to tens of seconds.
 	timeout := 30 * time.Second
 	timeoutChannel := time.After(timeout)
+	ticker := time.NewTicker(500 * time.Millisecond)
+	defer ticker.Stop()
 
 	for {
-		select {
-		case <-timeoutChannel:
-			t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
-		default:
-		}
-
 		peer, gpErr := getPeer(peer1ifaceName, peer2Key.PublicKey().String())
 		if gpErr != nil {
 			t.Fatal(gpErr)
@@ -588,6 +587,12 @@ func Test_ConnectPeers(t *testing.T) {
 			t.Log("peers successfully handshake")
 			break
 		}
+
+		select {
+		case <-timeoutChannel:
+			t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
+		case <-ticker.C:
+		}
 	}
 
 }
@@ -615,28 +620,3 @@ func getPeer(ifaceName, peerPubKey string) (wgtypes.Peer, error) {
 	}
 	return wgtypes.Peer{}, fmt.Errorf("peer not found")
 }
-
-func getLocalIP() (string, error) {
-	// Get all interfaces
-	addrs, err := net.InterfaceAddrs()
-	if err != nil {
-		return "", err
-	}
-
-	for _, addr := range addrs {
-		ipNet, ok := addr.(*net.IPNet)
-		if !ok {
-			continue
-		}
-		if ipNet.IP.IsLoopback() {
-			continue
-		}
-
-		if ipNet.IP.To4() == nil {
-			continue
-		}
-		return ipNet.IP.String(), nil
-	}
-
-	return "", fmt.Errorf("no local IP found")
-}

client/internal/auth/auth.go

@@ -351,6 +351,7 @@ func (a *Auth) setSystemInfoFlags(info *system.Info) {
 		a.config.BlockLANAccess,
 		a.config.BlockInbound,
 		a.config.DisableIPv6,
+		a.config.SyncMessageVersion,
 		a.config.EnableSSHRoot,
 		a.config.EnableSSHSFTP,
 		a.config.EnableSSHLocalPortForwarding,

client/internal/auth/sessionwatch/watcher.go

@@ -24,11 +24,7 @@ import (
 )
 
 const (
-	// Skew tolerates a small clock difference between the management
-	// server and this peer before treating a deadline as "in the past".
-	// Slightly above typical NTP drift; tight enough that the UI doesn't
-	// paint a stale expiry as if it were valid.
-	Skew = 30 * time.Second
+	maxPastHorizon = 30 * 24 * time.Hour
 
 	// maxDeadlineHorizon caps how far in the future an accepted deadline
 	// can sit. A timestamp beyond this is almost certainly a protocol
@@ -57,7 +53,7 @@ var (
 	ErrDeadlineTooFarFuture = errors.New("session deadline too far in the future")
 
 	// ErrDeadlineInPast is returned by Update when the supplied deadline
-	// is more than Skew in the past.
+	// is more than maxPastHorizon in the past.
 	ErrDeadlineInPast = errors.New("session deadline in the past")
 )
 
@@ -66,15 +62,14 @@ var (
 // for deadline change/clear, PublishEvent for the two warnings); tests pass
 // a fake recorder so the same surface is observable without an engine.
 //
-// The watcher is the single owner of the deadline propagated to the
-// recorder: every set, clear, sanity-check rejection and Close routes the
-// value through SetSessionExpiresAt, so the SubscribeStatus snapshot the UI
-// reads can never drift from the watcher's timer state. (SetSessionExpiresAt
-// fans out its own state-change notification, so no separate notify is
-// needed.) The recorder is server-scoped and outlives this engine-scoped
-// watcher — without the Close-time clear a teardown (Down, or the Down+Up of
-// a profile switch) would leave the next session showing the previous one's
-// stale "expires in" value.
+// While the watcher runs, it owns the deadline propagated to the recorder:
+// every set, clear and sanity-check rejection routes the value through
+// SetSessionExpiresAt, so the SubscribeStatus snapshot the UI reads can
+// never drift from the watcher's timer state. (SetSessionExpiresAt fans
+// out its own state-change notification, so no separate notify is needed.)
+// The recorder is server-scoped and outlives this engine-scoped watcher;
+// Close deliberately leaves the recorder value in place so transient engine
+// restarts don't blank it — the client run loop clears it on real teardown.
 //
 // PublishEvent's signature mirrors peer.Status.PublishEvent: the watcher
 // composes the metadata internally so the wire format (MetaSession*) is
@@ -135,10 +130,13 @@ func NewWithLeads(lead, final time.Duration, recorder StatusRecorder) *Watcher {
 // was disabled).
 //
 // Same-value updates are no-ops. A different non-zero value cancels any
-// pending timer, resets the "already fired" guard, and arms a new one.
+// pending timer, resets the "already fired" guards, and — when the
+// deadline lies in the future — arms fresh warning timers. A deadline
+// already in the past (within maxPastHorizon) is recorded as-is with no
+// timers: the session has expired and consumers render it that way.
 //
 // Returns one of the sentinel Err* values when the deadline fails the
-// sanity checks (pre-epoch, far future, or in the past beyond Skew).
+// sanity checks (pre-epoch, far future, or past beyond maxPastHorizon).
 // In every error case the watcher first clears its state so it stays
 // consistent with what the caller will push into its other sinks (e.g.
 // applySessionDeadline forces a zero deadline into the status recorder
@@ -163,7 +161,7 @@ func (w *Watcher) Update(deadline time.Time) error {
 	case deadline.After(now.Add(maxDeadlineHorizon)):
 		w.clearLocked()
 		return fmt.Errorf("%w: %v", ErrDeadlineTooFarFuture, deadline)
-	case deadline.Before(now.Add(-Skew)):
+	case deadline.Before(now.Add(-maxPastHorizon)):
 		w.clearLocked()
 		return fmt.Errorf("%w: %v (now=%v)", ErrDeadlineInPast, deadline, now)
 	}
@@ -183,7 +181,9 @@ func (w *Watcher) Update(deadline time.Time) error {
 	w.finalFiredAt = time.Time{}
 	w.dismissedAt = time.Time{}
 
-	w.armTimerLocked(deadline)
+	if deadline.After(now) {
+		w.armTimerLocked(deadline)
+	}
 	recorder := w.recorder
 	w.mu.Unlock()
 	if recorder != nil {
@@ -227,30 +227,25 @@ func (w *Watcher) Dismiss() {
 	log.Infof("auth session final-warning dismissed for deadline %s", w.current.Format(time.RFC3339))
 }
 
-// Close stops any pending timer and drops the deadline on the status
-// recorder. Update calls after Close are ignored. Clearing the recorder
-// here is what keeps a teardown (Down, or the Down+Up of a profile switch)
-// from leaving the next session showing this one's stale "expires in"
-// value — the recorder is server-scoped and outlives this engine-scoped
-// watcher, so nothing else drops the anchor on teardown.
+// Close stops any pending timer. Update calls after Close are ignored.
+// The recorder keeps its deadline: the watcher is engine-scoped and closes
+// on every engine restart (network change, sleep/wake, stream errors)
+// while the SSO deadline stays valid across those, so clearing here would
+// blank the UI's "expires in" row on every transient reconnect. The
+// client run loop clears the server-scoped recorder when it exits for
+// real (Down, profile switch, permanent login failure).
 func (w *Watcher) Close() {
 	w.mu.Lock()
+	defer w.mu.Unlock()
 	if w.closed {
-		w.mu.Unlock()
 		return
 	}
 	w.closed = true
 	w.stopTimerLocked()
-	hadDeadline := !w.current.IsZero()
 	w.current = time.Time{}
 	w.firedAt = time.Time{}
 	w.finalFiredAt = time.Time{}
 	w.dismissedAt = time.Time{}
-	recorder := w.recorder
-	w.mu.Unlock()
-	if recorder != nil && hadDeadline {
-		recorder.SetSessionExpiresAt(time.Time{})
-	}
 }
 
 // clearLocked drops the tracked deadline and notifies the recorder so

client/internal/auth/sessionwatch/watcher_test.go

@@ -224,11 +224,13 @@ func TestNewDeadlineCancelsPriorTimer(t *testing.T) {
 
 func TestRefreshAfterFireArmsNewWarning(t *testing.T) {
 	r := &fakeRecorder{}
-	lead := 30 * time.Millisecond
+	lead := 150 * time.Millisecond
 	w := newWatcher(lead, r)
 	defer w.Close()
 
-	first := time.Now().Add(50 * time.Millisecond)
+	// Warning fires ~20ms in; the deadline itself stays 150ms away so the
+	// replacement below lands well before it.
+	first := time.Now().Add(170 * time.Millisecond)
 	_ = w.Update(first)
 
 	// Wait for stateChange + warning of the first cycle.
@@ -306,7 +308,29 @@ func TestUpdateRejectsTooFarFuture(t *testing.T) {
 	}
 }
 
-func TestUpdateInPastClearsDeadline(t *testing.T) {
+func TestUpdateRecentPastRecordedAsExpired(t *testing.T) {
+	r := &fakeRecorder{}
+	w := newWatcher(50*time.Millisecond, r)
+	defer w.Close()
+
+	d := time.Now().Add(-1 * time.Hour)
+	if err := w.Update(d); err != nil {
+		t.Fatalf("recent-past Update should succeed, got %v", err)
+	}
+	if !w.Deadline().Equal(d) {
+		t.Fatalf("expected deadline to be recorded, got %v want %v", w.Deadline(), d)
+	}
+	if got := r.deadline(); !got.Equal(d) {
+		t.Fatalf("recorder deadline = %v, want %v", got, d)
+	}
+
+	time.Sleep(80 * time.Millisecond)
+	if n := countWhere(r.snapshot(), func(e event) bool { return e.kind == publish }); n != 0 {
+		t.Fatalf("no warning events may fire for an already-past deadline, got %+v", r.snapshot())
+	}
+}
+
+func TestUpdateAncientPastRejected(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(50*time.Millisecond, r)
 	defer w.Close()
@@ -318,12 +342,12 @@ func TestUpdateInPastClearsDeadline(t *testing.T) {
 	// Drain the stateChange from the seed.
 	waitForEvents(t, r, 1)
 
-	err := w.Update(time.Now().Add(-1 * time.Hour))
+	err := w.Update(time.Now().Add(-31 * 24 * time.Hour))
 	if !errors.Is(err, ErrDeadlineInPast) {
 		t.Fatalf("want ErrDeadlineInPast, got %v", err)
 	}
 	if !w.Deadline().IsZero() {
-		t.Fatalf("in-past update must clear the deadline, got %v", w.Deadline())
+		t.Fatalf("rejected ancient-past update must clear the deadline, got %v", w.Deadline())
 	}
 	events := waitForEvents(t, r, 2)
 	if events[1].kind != stateChange {
@@ -331,39 +355,25 @@ func TestUpdateInPastClearsDeadline(t *testing.T) {
 	}
 }
 
-func TestUpdateWithinSkewAccepted(t *testing.T) {
-	r := &fakeRecorder{}
-	w := newWatcher(50*time.Millisecond, r)
-	defer w.Close()
-
-	// 5 seconds in the past is within the 30s Skew tolerance — accept it.
-	d := time.Now().Add(-5 * time.Second)
-	if err := w.Update(d); err != nil {
-		t.Fatalf("within-skew Update should succeed, got %v", err)
-	}
-	if !w.Deadline().Equal(d) {
-		t.Fatalf("expected deadline to be applied, got %v want %v", w.Deadline(), d)
-	}
-}
-
 func TestCloseSilencesUpdates(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(50*time.Millisecond, r)
 	w.Close()
 
-	_ = w.Update(time.Now().Add(time.Hour))
-
-	time.Sleep(20 * time.Millisecond)
+	if err := w.Update(time.Now().Add(time.Hour)); err != nil {
+		t.Fatalf("Update after Close: want nil, got %v", err)
+	}
 	if got := r.snapshot(); len(got) != 0 {
 		t.Fatalf("expected no events after Close, got %+v", got)
 	}
 }
 
-// TestCloseClearsRecorderDeadline pins the profile-switch fix: a watcher
-// holding a live deadline must zero the recorder on Close so the next
-// engine's watcher (and the UI reading the shared server-scoped recorder)
-// doesn't start out showing the previous session's stale "expires in".
-func TestCloseClearsRecorderDeadline(t *testing.T) {
+// TestCloseKeepsRecorderDeadline pins the reconnect-flap fix: the watcher
+// closes on every engine restart (network change, sleep/wake) while the
+// SSO deadline stays valid across those, so Close must leave the
+// server-scoped recorder's value in place. The client run loop clears the
+// recorder when it exits for real.
+func TestCloseKeepsRecorderDeadline(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(time.Hour, r)
 
@@ -377,8 +387,8 @@ func TestCloseClearsRecorderDeadline(t *testing.T) {
 
 	w.Close()
 
-	if got := r.deadline(); !got.IsZero() {
-		t.Fatalf("recorder deadline after Close = %v, want zero", got)
+	if got := r.deadline(); !got.Equal(d) {
+		t.Fatalf("recorder deadline after Close = %v, want %v", got, d)
 	}
 }
 

client/internal/conn_mgr.go

@@ -34,6 +34,8 @@ const (
 // - Handling connection establishment based on peer signaling
 //
 // The implementation is not thread-safe; it is protected by engine.syncMsgMux.
+// The only exception is ActivatePeer, which is safe for concurrent use so the
+// DNS warm-up path can call it without contending on the engine mutex.
 type ConnMgr struct {
 	peerStore        *peerstore.Store
 	statusRecorder   *peer.Status
@@ -42,12 +44,26 @@ type ConnMgr struct {
 	rosenpassEnabled bool
 
 	lazyConnMgr *manager.Manager
+	// lazyConnMgrMu guards the lazyConnMgr pointer for readers outside the
+	// engine loop (ActivatePeer). Writers hold it in addition to
+	// engine.syncMsgMux; all other reads stay under engine.syncMsgMux only.
+	lazyConnMgrMu sync.RWMutex
+
+	// reconcileRoutedIPs re-applies a peer's routed allowed IPs after its lazy wake endpoint is
+	// (re)armed (Mode A at arm time). Injected by the engine; nil disables the reconcile.
+	reconcileRoutedIPs func(peerKey string) error
 
 	wg            sync.WaitGroup
 	lazyCtx       context.Context
 	lazyCtxCancel context.CancelFunc
 }
 
+// SetRoutedIPsReconciler injects the callback used to re-apply a peer's routed allowed IPs when
+// its lazy wake endpoint is (re)armed. Must be called before the lazy manager starts.
+func (e *ConnMgr) SetRoutedIPsReconciler(fn func(peerKey string) error) {
+	e.reconcileRoutedIPs = fn
+}
+
 func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerStore *peerstore.Store, iface lazyconn.WGIface) *ConnMgr {
 	e := &ConnMgr{
 		peerStore:        peerStore,
@@ -238,12 +254,20 @@ func (e *ConnMgr) RemovePeerConn(peerKey string) {
 	conn.Log.Infof("removed peer from lazy conn manager")
 }
 
+// ActivatePeer wakes an idle lazy connection. Unlike the rest of ConnMgr it is
+// safe for concurrent use: the lazy manager pointer is read under lazyConnMgrMu
+// and the manager itself is internally synchronized, so callers outside the
+// engine loop (DNS warm-up) do not need engine.syncMsgMux.
 func (e *ConnMgr) ActivatePeer(ctx context.Context, conn *peer.Conn) {
-	if !e.isStartedWithLazyMgr() {
+	e.lazyConnMgrMu.RLock()
+	lazyConnMgr := e.lazyConnMgr
+	started := lazyConnMgr != nil && e.lazyCtxCancel != nil
+	e.lazyConnMgrMu.RUnlock()
+	if !started {
 		return
 	}
 
-	if found := e.lazyConnMgr.ActivatePeer(conn.GetKey()); found {
+	if found := lazyConnMgr.ActivatePeer(conn.GetKey()); found {
 		if err := conn.Open(ctx); err != nil {
 			conn.Log.Errorf("failed to open connection: %v", err)
 		}
@@ -268,16 +292,22 @@ func (e *ConnMgr) Close() {
 
 	e.lazyCtxCancel()
 	e.wg.Wait()
+
+	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = nil
+	e.lazyConnMgrMu.Unlock()
 }
 
 func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 	cfg := manager.Config{
 		InactivityThreshold: inactivityThresholdEnv(),
+		ReconcileAllowedIPs: e.reconcileRoutedIPs,
 	}
-	e.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface)
 
+	e.lazyConnMgrMu.Lock()
+	e.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface)
 	e.lazyCtx, e.lazyCtxCancel = context.WithCancel(engineCtx)
+	e.lazyConnMgrMu.Unlock()
 
 	e.wg.Add(1)
 	go func() {
@@ -316,7 +346,10 @@ func (e *ConnMgr) closeManager(ctx context.Context) {
 
 	e.lazyCtxCancel()
 	e.wg.Wait()
+
+	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = nil
+	e.lazyConnMgrMu.Unlock()
 
 	for _, peerID := range e.peerStore.PeersPubKey() {
 		e.peerStore.PeerConnOpen(ctx, peerID)
@@ -352,11 +385,20 @@ func inactivityThresholdEnv() *time.Duration {
 		return nil
 	}
 
-	parsedMinutes, err := strconv.Atoi(envValue)
-	if err != nil || parsedMinutes <= 0 {
-		return nil
+	// Documented format: a Go duration such as "30m" or "1h".
+	if d, err := time.ParseDuration(envValue); err == nil {
+		if d <= 0 {
+			return nil
+		}
+		return &d
 	}
 
-	d := time.Duration(parsedMinutes) * time.Minute
-	return &d
+	// Backwards compatibility: a bare integer used to be interpreted as minutes.
+	if parsedMinutes, err := strconv.Atoi(envValue); err == nil && parsedMinutes > 0 {
+		d := time.Duration(parsedMinutes) * time.Minute
+		return &d
+	}
+
+	log.Warnf("invalid %s value %q: expected a Go duration such as 30m or 1h", lazyconn.EnvInactivityThreshold, envValue)
+	return nil
 }

client/internal/conn_mgr_test.go

@@ -1,10 +1,21 @@
 package internal
 
 import (
+	"context"
+	"net"
+	"net/netip"
 	"os"
+	"sync"
 	"testing"
+	"time"
 
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+
+	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/lazyconn"
+	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/client/internal/peerstore"
+	"github.com/netbirdio/netbird/monotime"
 )
 
 func TestResolveLazyForce(t *testing.T) {
@@ -38,3 +49,93 @@ func TestResolveLazyForce(t *testing.T) {
 		})
 	}
 }
+
+type mockLazyWGIface struct{}
+
+func (mockLazyWGIface) RemovePeer(string) error { return nil }
+func (mockLazyWGIface) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
+	return nil
+}
+func (mockLazyWGIface) IsUserspaceBind() bool                    { return false }
+func (mockLazyWGIface) Address() wgaddr.Address                  { return wgaddr.Address{} }
+func (mockLazyWGIface) LastActivities() map[string]monotime.Time { return nil }
+func (mockLazyWGIface) MTU() uint16                              { return 1280 }
+
+// TestConnMgr_ActivatePeerConcurrentWithLifecycle exercises ActivatePeer from
+// non-engine goroutines (the DNS warm-up path) racing the manager lifecycle,
+// which stays on the engine loop. Run with -race: it fails if ActivatePeer
+// still requires engine.syncMsgMux for safety.
+func TestConnMgr_ActivatePeerConcurrentWithLifecycle(t *testing.T) {
+	t.Setenv(lazyconn.EnvLazyConn, "on")
+
+	status := peer.NewRecorder("https://mgm")
+	store := peerstore.NewConnStore()
+	connMgr := NewConnMgr(&EngineConfig{}, status, store, mockLazyWGIface{})
+
+	conn := newTestPeerConn(t, "peerA")
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	connMgr.Start(ctx)
+
+	done := make(chan struct{})
+	var wg sync.WaitGroup
+	for range 4 {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			for {
+				select {
+				case <-done:
+					return
+				default:
+					connMgr.ActivatePeer(ctx, conn)
+				}
+			}
+		}()
+	}
+
+	// Let the activators spin against the started manager, then tear it down
+	// underneath them and let them spin against the stopped manager.
+	time.Sleep(100 * time.Millisecond)
+	connMgr.Close()
+	time.Sleep(50 * time.Millisecond)
+
+	close(done)
+	wg.Wait()
+}
+
+func TestInactivityThresholdEnv(t *testing.T) {
+	tests := []struct {
+		name string
+		val  string
+		want *time.Duration
+	}{
+		{name: "unset", val: "", want: nil},
+		{name: "go duration minutes", val: "30m", want: durPtr(30 * time.Minute)},
+		{name: "go duration hours", val: "1h", want: durPtr(time.Hour)},
+		{name: "go duration seconds", val: "90s", want: durPtr(90 * time.Second)},
+		{name: "bare integer is minutes (backwards compat)", val: "5", want: durPtr(5 * time.Minute)},
+		{name: "zero duration", val: "0s", want: nil},
+		{name: "zero integer", val: "0", want: nil},
+		{name: "negative duration", val: "-5m", want: nil},
+		{name: "garbage", val: "abc", want: nil},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv(lazyconn.EnvInactivityThreshold, tc.val)
+			got := inactivityThresholdEnv()
+			switch {
+			case tc.want == nil && got != nil:
+				t.Fatalf("want nil, got %v", *got)
+			case tc.want != nil && got == nil:
+				t.Fatalf("want %v, got nil", *tc.want)
+			case tc.want != nil && *got != *tc.want:
+				t.Fatalf("want %v, got %v", *tc.want, *got)
+			}
+		})
+	}
+}
+
+func durPtr(d time.Duration) *time.Duration { return &d }

client/internal/connect.go

@@ -34,6 +34,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/client/internal/tunnelnotifier"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
@@ -112,11 +113,14 @@ func (c *ConnectClient) RunOnAndroid(
 	stateFilePath string,
 	cacheDir string,
 ) error {
+	notifier := tunnelnotifier.New(networkChangeListener, nil)
+	defer notifier.Close()
+
 	// in case of non Android os these variables will be nil
 	mobileDependency := MobileDependency{
 		TunAdapter:            tunAdapter,
 		IFaceDiscover:         iFaceDiscover,
-		NetworkChangeListener: networkChangeListener,
+		NetworkChangeListener: notifier,
 		HostDNSAddresses:      dnsAddresses,
 		DnsReadyListener:      dnsReadyListener,
 		StateFilePath:         stateFilePath,
@@ -136,10 +140,13 @@ func (c *ConnectClient) RunOniOS(
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
 	debug.SetGCPercent(5)
 
+	notifier := tunnelnotifier.New(networkChangeListener, dnsManager)
+	defer notifier.Close()
+
 	mobileDependency := MobileDependency{
 		FileDescriptor:        fileDescriptor,
-		NetworkChangeListener: networkChangeListener,
-		DnsManager:            dnsManager,
+		NetworkChangeListener: notifier,
+		DnsManager:            notifier,
 		StateFilePath:         stateFilePath,
 		TempDir:               cacheDir,
 	}
@@ -257,7 +264,10 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		log.Errorf("failed to clean up temporary installer file: %v", err)
 	}
 
-	defer c.statusRecorder.ClientStop()
+	defer func() {
+		c.statusRecorder.SetSessionExpiresAt(time.Time{})
+		c.statusRecorder.ClientStop()
+	}()
 	operation := func() error {
 		// if context cancelled we not start new backoff cycle
 		if c.ctx.Err() != nil {
@@ -618,6 +628,7 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
 		BlockLANAccess:      config.BlockLANAccess,
 		BlockInbound:        config.BlockInbound,
 		DisableIPv6:         config.DisableIPv6,
+		SyncMessageVersion:  config.SyncMessageVersion,
 
 		LazyConnection: lazyconn.ParseState(config.LazyConnection),
 
@@ -693,6 +704,7 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
 		config.BlockLANAccess,
 		config.BlockInbound,
 		config.DisableIPv6,
+		config.SyncMessageVersion,
 		config.EnableSSHRoot,
 		config.EnableSSHSFTP,
 		config.EnableSSHLocalPortForwarding,

client/internal/daemonaddr/identity.go

@@ -0,0 +1,14 @@
+package daemonaddr
+
+import "strings"
+
+// CarriesIdentity reports whether the control channel at addr conveys the
+// connecting process's identity to the daemon. A Unix socket carries peer
+// credentials and a named pipe carries the client's token; loopback TCP carries
+// neither, so on such an address the daemon cannot authorize a privileged
+// operation for anybody. A client uses this to tell whether becoming privileged
+// would get it anywhere: on an identity-less address it would not, and the only
+// way forward is to move the daemon onto one that carries identity.
+func CarriesIdentity(addr string) bool {
+	return strings.HasPrefix(addr, "unix://") || strings.HasPrefix(addr, pipeScheme)
+}

client/internal/daemonaddr/identity_test.go

@@ -0,0 +1,29 @@
+package daemonaddr
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCarriesIdentity(t *testing.T) {
+	tests := []struct {
+		addr string
+		want bool
+	}{
+		{"unix:///var/run/netbird.sock", true},
+		{"unix:///var/run/netbird/default.sock", true},
+		{"npipe://netbird", true},
+		{`npipe://\\.\pipe\ProtectedPrefix\Administrators\netbird`, true},
+		{"tcp://127.0.0.1:41731", false},
+		{"tcp://localhost:41731", false},
+		{"", false},
+		{"/var/run/netbird.sock", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.addr, func(t *testing.T) {
+			assert.Equal(t, tt.want, CarriesIdentity(tt.addr), "address %q", tt.addr)
+		})
+	}
+}

client/internal/daemonaddr/owner.go

@@ -0,0 +1,15 @@
+package daemonaddr
+
+// DaemonRunsAsSelf reports whether the daemon listening at addr runs as this very
+// user. That is what makes an unprivileged daemon authorize this process for the
+// changes it otherwise restricts to root or an administrator, so a client can tell
+// up front whether those controls are usable instead of letting a save fail.
+//
+// It is answered from the ownership of the socket or pipe the daemon created, so it
+// costs no round trip and needs no cooperation from the daemon. Ownership that
+// cannot be read is reported as false, including for a TCP address, so a caller
+// reading this as "the daemon would allow it" fails closed. The daemon remains the
+// only thing that authorizes anything: this only decides what a client offers.
+func DaemonRunsAsSelf(addr string) bool {
+	return daemonRunsAsSelf(addr)
+}

client/internal/daemonaddr/owner_unix.go

@@ -0,0 +1,40 @@
+//go:build !windows
+
+package daemonaddr
+
+import (
+	"os"
+	"strings"
+	"syscall"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// daemonRunsAsSelf compares the owner of the daemon's Unix socket with this
+// process's uid. Root is not treated specially here: a root caller is privileged
+// on its own merits, and a root-owned socket says nothing about the caller.
+func daemonRunsAsSelf(addr string) bool {
+	path, ok := strings.CutPrefix(addr, "unix://")
+	if !ok {
+		return false
+	}
+
+	info, err := os.Stat(path)
+	if err != nil {
+		log.Debugf("stat daemon socket %s: %v", path, err)
+		return false
+	}
+
+	// Only a socket says anything about a daemon. A directory or a leftover
+	// regular file at that path is not one, and reading it as "the daemon runs as
+	// us" would offer controls the daemon then refuses.
+	if info.Mode()&os.ModeSocket == 0 {
+		return false
+	}
+
+	stat, ok := info.Sys().(*syscall.Stat_t)
+	if !ok {
+		return false
+	}
+	return stat.Uid == uint32(os.Getuid())
+}

client/internal/daemonaddr/owner_unix_test.go

@@ -0,0 +1,62 @@
+//go:build !windows
+
+package daemonaddr
+
+import (
+	"net"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+// A socket this user created means the daemon runs as this user, which is the
+// rootless case where the daemon delegates its authority to its own identity.
+func TestDaemonRunsAsSelf_OwnSocket(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "netbird.sock")
+	ln, err := net.Listen("unix", path)
+	if err != nil {
+		t.Fatalf("listen: %v", err)
+	}
+	t.Cleanup(func() {
+		if err := ln.Close(); err != nil {
+			t.Logf("close listener: %v", err)
+		}
+	})
+
+	if !DaemonRunsAsSelf("unix://" + path) {
+		t.Error("a socket owned by this user must count as the daemon running as us")
+	}
+}
+
+// Everything that is not a readable socket of ours has to answer false, because
+// the caller reads a true as "the daemon would authorize me".
+func TestDaemonRunsAsSelf_FailsClosed(t *testing.T) {
+	dir := t.TempDir()
+
+	// A socket owned by another user, which is what a root-run daemon looks like
+	// to an unprivileged client. Only assertable when we are not root ourselves.
+	rootOwned := "unix:///var/run/netbird.sock"
+	if _, err := os.Stat("/var/run/netbird.sock"); err == nil && os.Getuid() != 0 {
+		if DaemonRunsAsSelf(rootOwned) {
+			t.Error("a socket owned by another user must not count as ours")
+		}
+	}
+
+	for name, addr := range map[string]string{
+		"missing socket":  "unix://" + filepath.Join(dir, "absent.sock"),
+		"tcp address":     "tcp://127.0.0.1:41731",
+		"named pipe":      "npipe://netbird",
+		"empty":           "",
+		"no scheme":       filepath.Join(dir, "absent.sock"),
+		"directory":       "unix://" + dir,
+		"unknown scheme":  "http://localhost:8080",
+		"scheme only":     "unix://",
+		"relative socket": "unix://netbird.sock",
+	} {
+		t.Run(name, func(t *testing.T) {
+			if DaemonRunsAsSelf(addr) {
+				t.Errorf("%q must not count as a daemon running as us", addr)
+			}
+		})
+	}
+}

client/internal/daemonaddr/owner_windows.go

@@ -0,0 +1,42 @@
+//go:build windows
+
+package daemonaddr
+
+import (
+	"context"
+	"strings"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+)
+
+// daemonRunsAsSelf reads the owner of the daemon's pipe. A daemon running as the
+// service account owns its pipe as LocalSystem, and an elevated one as
+// BUILTIN\Administrators, so only a daemon the user started themselves matches.
+func daemonRunsAsSelf(addr string) bool {
+	name, ok := strings.CutPrefix(addr, pipeScheme)
+	if !ok {
+		return false
+	}
+
+	for _, path := range PipePaths(name) {
+		// Bounded: this runs on the UI's path for deciding which controls to
+		// offer, so a pipe that does not answer promptly must not stall it. A
+		// timeout leaves the caller unprivileged, which only disables controls.
+		ctx, cancel := context.WithTimeout(context.Background(), probeTimeout)
+		conn, err := dialPipe(ctx, path)
+		cancel()
+		if err != nil {
+			continue
+		}
+
+		owned := ipcauth.PipeOwnedBySelf(conn)
+		if cerr := conn.Close(); cerr != nil {
+			log.Debugf("close daemon pipe %s after ownership check: %v", path, cerr)
+		}
+		return owned
+	}
+
+	return false
+}

client/internal/daemonaddr/pipe.go

@@ -0,0 +1,103 @@
+package daemonaddr
+
+import (
+	"context"
+	"net"
+	"runtime"
+	"strings"
+
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+const (
+	// WindowsPipeAddr is the default daemon address on Windows. A named pipe
+	// carries the connecting process's token, which loopback TCP does not, so
+	// it is the only Windows transport on which the daemon can tell who is
+	// calling it.
+	WindowsPipeAddr = "npipe://netbird"
+
+	// legacyWindowsAddr is the loopback-TCP address the Windows daemon used
+	// before named-pipe support.
+	legacyWindowsAddr = "tcp://127.0.0.1:41731"
+
+	pipeScheme = "npipe://"
+
+	// protectedPrefix is the NPFS namespace in which only LocalSystem and
+	// members of BUILTIN\Administrators may create a pipe. A daemon running as
+	// the service account creates its pipe there so that an unprivileged process
+	// cannot pre-create the name, which would keep the daemon from starting and
+	// leave callers talking to the squatter. Opening such a pipe needs no
+	// privilege, so unprivileged clients still reach the daemon.
+	protectedPrefix = `ProtectedPrefix\Administrators\`
+)
+
+// DialTarget returns the gRPC dial target and transport options for a daemon
+// address. The npipe scheme needs a context dialer because gRPC has no
+// named-pipe resolver; unix and tcp are handled by gRPC itself.
+func DialTarget(addr string) (string, []grpc.DialOption) {
+	opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
+
+	if name, ok := strings.CutPrefix(addr, pipeScheme); ok {
+		paths := PipePaths(name)
+		opts = append(opts, grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) {
+			return dialPipePaths(ctx, paths)
+		}))
+		return "passthrough:///netbird-daemon-pipe", opts
+	}
+
+	return strings.TrimPrefix(addr, "tcp://"), opts
+}
+
+// PipePath maps an npipe address name ("netbird", from "npipe://netbird") to a
+// Windows named-pipe path (\\.\pipe\netbird). A fully qualified path is left as
+// is.
+func PipePath(name string) string {
+	if strings.HasPrefix(name, `\\`) {
+		return name
+	}
+	return `\\.\pipe\` + name
+}
+
+// PipePaths returns the paths a daemon control pipe may live at for an npipe
+// address name, in the order both sides must try them: the protected name first,
+// then the plain one.
+//
+// The daemon serves the first it can create, which is the protected name when it
+// runs as the service account and the plain one when it runs as an ordinary user,
+// as it does in netstack mode. Clients therefore have to try both, and because a
+// client cannot tell from the name alone who created the pipe, the plain name is
+// only usable once the server's identity has been checked: see
+// verifyPipeServer.
+//
+// A fully qualified path is what the operator asked for and is used as is.
+func PipePaths(name string) []string {
+	if strings.HasPrefix(name, `\\`) {
+		return []string{name}
+	}
+	return []string{PipePath(protectedPrefix + name), PipePath(name)}
+}
+
+// IsProtectedPipePath reports whether a pipe path is in the namespace only an
+// administrator or LocalSystem can create in, which is what lets a client trust
+// such a pipe from its name alone.
+func IsProtectedPipePath(path string) bool {
+	return strings.HasPrefix(path, `\\.\pipe\`+protectedPrefix)
+}
+
+// MigrateLegacy upgrades the pre-named-pipe Windows daemon address to the named
+// pipe, reporting whether it rewrote the address. Existing installs persist the
+// daemon address, so without this an upgraded daemon would keep listening on
+// loopback TCP, where callers carry no identity and privileged operations would
+// have to be refused for everyone. Only the exact legacy default is rewritten:
+// a deliberately chosen custom address is left alone.
+func MigrateLegacy(addr string) (string, bool) {
+	return migrateLegacyForOS(runtime.GOOS, addr)
+}
+
+func migrateLegacyForOS(goos, addr string) (string, bool) {
+	if goos == "windows" && addr == legacyWindowsAddr {
+		return WindowsPipeAddr, true
+	}
+	return addr, false
+}

client/internal/daemonaddr/pipe_other.go

@@ -0,0 +1,15 @@
+//go:build !windows
+
+package daemonaddr
+
+import (
+	"context"
+	"fmt"
+	"net"
+)
+
+// dialPipePaths is Windows-only: no other platform serves the daemon on a named
+// pipe.
+func dialPipePaths(context.Context, []string) (net.Conn, error) {
+	return nil, fmt.Errorf("named pipes are only supported on Windows")
+}

client/internal/daemonaddr/pipe_test.go

@@ -0,0 +1,30 @@
+package daemonaddr
+
+import (
+	"slices"
+	"testing"
+)
+
+// The protected name must be tried before the plain one on both sides: it is the
+// one an unprivileged process cannot create, so preferring it is what keeps a
+// squatter from owning the name the service daemon would otherwise use.
+func TestPipePaths_PrefersTheProtectedName(t *testing.T) {
+	got := PipePaths("netbird")
+	want := []string{
+		`\\.\pipe\ProtectedPrefix\Administrators\netbird`,
+		`\\.\pipe\netbird`,
+	}
+	if !slices.Equal(got, want) {
+		t.Errorf("PipePaths = %q, want %q", got, want)
+	}
+}
+
+// An operator who passes a full path chose exactly one pipe, so neither side may
+// look anywhere else.
+func TestPipePaths_QualifiedPathIsUsedAsIs(t *testing.T) {
+	path := `\\.\pipe\custom-netbird`
+	got := PipePaths(path)
+	if !slices.Equal(got, []string{path}) {
+		t.Errorf("PipePaths = %q, want just %q", got, path)
+	}
+}

client/internal/daemonaddr/pipe_windows.go

@@ -0,0 +1,59 @@
+//go:build windows
+
+package daemonaddr
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+
+	"github.com/Microsoft/go-winio"
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sys/windows"
+
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+)
+
+// dialPipePaths connects to the first path that answers with a pipe server this
+// client may trust, and returns the last error when none does.
+func dialPipePaths(ctx context.Context, paths []string) (net.Conn, error) {
+	var lastErr error
+	for _, path := range paths {
+		conn, err := dialPipe(ctx, path)
+		if err != nil {
+			log.Debugf("dial daemon pipe %s: %v", path, err)
+			lastErr = err
+			continue
+		}
+
+		// A pipe in the protected namespace could only have been created by an
+		// administrator or LocalSystem, so its name is the guarantee. Any other
+		// name has to be checked, because any local user can create one.
+		if !IsProtectedPipePath(path) {
+			if err := ipcauth.PipeServerTrusted(conn); err != nil {
+				if closeErr := conn.Close(); closeErr != nil {
+					log.Debugf("close untrusted pipe %s: %v", path, closeErr)
+				}
+				lastErr = fmt.Errorf("%s: %w", path, err)
+				continue
+			}
+		}
+
+		return conn, nil
+	}
+
+	if lastErr == nil {
+		lastErr = errors.New("no daemon pipe to connect to")
+	}
+	return nil, lastErr
+}
+
+// dialPipe connects to the daemon control pipe at SECURITY_IDENTIFICATION.
+// winio's plain DialPipe connects at SECURITY_ANONYMOUS, under which the daemon
+// cannot read the caller's token at all. Identification lets the daemon read the
+// caller's SID and groups without granting it the ability to act as the caller.
+func dialPipe(ctx context.Context, path string) (net.Conn, error) {
+	access := uint32(windows.GENERIC_READ | windows.GENERIC_WRITE)
+	return winio.DialPipeAccessImpLevel(ctx, path, access, winio.PipeImpLevelIdentification)
+}

client/internal/daemonaddr/resolve_pipe_other.go

@@ -0,0 +1,9 @@
+//go:build !windows
+
+package daemonaddr
+
+// ResolveDaemonAddr is a no-op off Windows, where there is no named-pipe
+// default to fall back from.
+func ResolveDaemonAddr(addr string) string {
+	return addr
+}

client/internal/daemonaddr/resolve_pipe_windows.go

@@ -0,0 +1,82 @@
+//go:build windows
+
+package daemonaddr
+
+import (
+	"net"
+	"strings"
+	"time"
+
+	"github.com/Microsoft/go-winio"
+	log "github.com/sirupsen/logrus"
+)
+
+// probeTimeout bounds each transport probe. Both are local, so a daemon that is
+// listening answers immediately and one that is not fails immediately.
+const probeTimeout = 300 * time.Millisecond
+
+// ResolveDaemonAddr keeps a client on the named pipe and never silently moves it
+// off. When the pipe does not answer it checks the legacy loopback TCP address, so
+// a client meeting a daemon that has not restarted since the upgrade can say what
+// is wrong, but it does not connect there.
+//
+// Using that address automatically would be a downgrade the user never asked for:
+// any local process can bind 127.0.0.1 while the daemon is not listening, and the
+// transport carries no caller identity, so a client that accepted whatever answered
+// would hand a setup key, a pre-shared key or an SSO prompt to a local impostor. An
+// operator who needs the legacy address during the upgrade window can still pass
+// --daemon-addr explicitly, which is a deliberate choice and still refuses the
+// privileged operations.
+//
+// Only the pipe address is resolved. A custom address is left alone, though passing
+// --daemon-addr npipe://netbird explicitly is indistinguishable from the default
+// here, so it is treated the same way.
+func ResolveDaemonAddr(addr string) string {
+	if addr != WindowsPipeAddr {
+		return addr
+	}
+
+	for _, path := range PipePaths("netbird") {
+		if pipeAvailable(path) {
+			return addr
+		}
+	}
+
+	if tcpAvailable(legacyWindowsAddr) {
+		log.Warnf("the daemon is not serving %s, but something is listening on the legacy %s. "+
+			"Restart the NetBird service so it serves the pipe. That address is not used automatically: "+
+			"any local user can bind it and it carries no caller identity, so pass --daemon-addr %s "+
+			"explicitly if you accept that",
+			WindowsPipeAddr, legacyWindowsAddr, legacyWindowsAddr)
+	}
+
+	return addr
+}
+
+func pipeAvailable(path string) bool {
+	timeout := probeTimeout
+	conn, err := winio.DialPipe(path, &timeout)
+	if err != nil {
+		return false
+	}
+	if err := conn.Close(); err != nil {
+		log.Debugf("close daemon pipe probe: %v", err)
+	}
+	return true
+}
+
+func tcpAvailable(addr string) bool {
+	host := addr
+	if _, after, ok := strings.Cut(addr, "://"); ok {
+		host = after
+	}
+
+	conn, err := net.DialTimeout("tcp", host, probeTimeout)
+	if err != nil {
+		return false
+	}
+	if err := conn.Close(); err != nil {
+		log.Debugf("close daemon TCP probe: %v", err)
+	}
+	return true
+}

client/internal/debug/debug.go

@@ -229,7 +229,6 @@ scutil_dns.txt (macOS only):
 
 const (
 	clientLogFile = "client.log"
-	uiLogFile     = "gui-client.log"
 	errorLogFile  = "netbird.err"
 	stdoutLogFile = "netbird.out"
 
@@ -248,6 +247,20 @@ type MetricsExporter interface {
 	Export(w io.Writer) error
 }
 
+// LogOpener opens a log file for inclusion in the bundle. It exists so that log
+// files whose path was supplied by an IPC caller can be opened under a check
+// the daemon defines, instead of being opened with the daemon's privileges
+// unconditionally.
+type LogOpener func(path string) (*os.File, error)
+
+func openLogFile(path string) (*os.File, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, fmt.Errorf("open %s: %w", path, err)
+	}
+	return f, nil
+}
+
 type BundleGenerator struct {
 	anonymizer *anonymize.Anonymizer
 
@@ -257,6 +270,7 @@ type BundleGenerator struct {
 	syncResponse   *mgmProto.SyncResponse
 	logPath        string
 	uiLogPath      string
+	uiLogOpener    LogOpener
 	tempDir        string
 	statePath      string
 	cpuProfile     []byte
@@ -285,14 +299,20 @@ type GeneratorDependencies struct {
 	SyncResponse   *mgmProto.SyncResponse
 	LogPath        string
 	UILogPath      string // Absolute path to the desktop UI's gui-client.log, reported via RegisterUILog. Empty if no UI registered one.
-	TempDir        string // Directory for temporary bundle zip files. If empty, os.TempDir() is used.
-	StatePath      string // Path to the state file. If empty, the ServiceManager default path is used.
-	CPUProfile     []byte
-	CapturePath    string
-	RefreshStatus  func()
-	ClientMetrics  MetricsExporter
-	DaemonVersion  string
-	CliVersion     string
+	// UILogOpener opens the UI log and its rotated siblings. The path comes from
+	// a local IPC caller, so the daemon must not open it with plain os.Open: the
+	// opener is where the caller's right to that file is enforced. Defaults to
+	// os.Open, which is only correct where the path is not caller-supplied
+	// (mobile).
+	UILogOpener   LogOpener
+	TempDir       string // Directory for temporary bundle zip files. If empty, os.TempDir() is used.
+	StatePath     string // Path to the state file. If empty, the ServiceManager default path is used.
+	CPUProfile    []byte
+	CapturePath   string
+	RefreshStatus func()
+	ClientMetrics MetricsExporter
+	DaemonVersion string
+	CliVersion    string
 }
 
 func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGenerator {
@@ -302,6 +322,11 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		logFileCount = 1
 	}
 
+	uiLogOpener := deps.UILogOpener
+	if uiLogOpener == nil {
+		uiLogOpener = openLogFile
+	}
+
 	return &BundleGenerator{
 		anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()),
 
@@ -310,6 +335,7 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		syncResponse:   deps.SyncResponse,
 		logPath:        deps.LogPath,
 		uiLogPath:      deps.UILogPath,
+		uiLogOpener:    uiLogOpener,
 		tempDir:        deps.TempDir,
 		statePath:      deps.StatePath,
 		cpuProfile:     deps.CPUProfile,
@@ -676,6 +702,7 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder)
 	configContent.WriteString(fmt.Sprintf("BlockLANAccess: %v\n", g.internalConfig.BlockLANAccess))
 	configContent.WriteString(fmt.Sprintf("BlockInbound: %v\n", g.internalConfig.BlockInbound))
 	configContent.WriteString(fmt.Sprintf("DisableIPv6: %v\n", g.internalConfig.DisableIPv6))
+	configContent.WriteString(fmt.Sprintf("SyncMessageVersion: %v\n", g.internalConfig.SyncMessageVersion))
 
 	if g.internalConfig.DisableNotifications != nil {
 		configContent.WriteString(fmt.Sprintf("DisableNotifications: %v\n", *g.internalConfig.DisableNotifications))
@@ -995,11 +1022,11 @@ func (g *BundleGenerator) addLogfile() error {
 
 	logDir := filepath.Dir(g.logPath)
 
-	if err := g.addSingleLogfile(g.logPath, clientLogFile); err != nil {
+	if err := g.addSingleLogfile(openLogFile, g.logPath, clientLogFile); err != nil {
 		return fmt.Errorf("add client log file to zip: %w", err)
 	}
 
-	g.addRotatedLogFiles(logDir, clientLogPrefix)
+	g.addRotatedLogFiles(openLogFile, logDir, clientLogPrefix)
 
 	stdErrLogPath := filepath.Join(logDir, errorLogFile)
 	stdoutLogPath := filepath.Join(logDir, stdoutLogFile)
@@ -1008,11 +1035,11 @@ func (g *BundleGenerator) addLogfile() error {
 		stdoutLogPath = darwinStdoutLogPath
 	}
 
-	if err := g.addSingleLogfile(stdErrLogPath, errorLogFile); err != nil {
+	if err := g.addSingleLogfile(openLogFile, stdErrLogPath, errorLogFile); err != nil {
 		log.Warnf("Failed to add %s to zip: %v", errorLogFile, err)
 	}
 
-	if err := g.addSingleLogfile(stdoutLogPath, stdoutLogFile); err != nil {
+	if err := g.addSingleLogfile(openLogFile, stdoutLogPath, stdoutLogFile); err != nil {
 		log.Warnf("Failed to add %s to zip: %v", stdoutLogFile, err)
 	}
 
@@ -1029,18 +1056,18 @@ func (g *BundleGenerator) addUILog() error {
 		return nil
 	}
 
-	if err := g.addSingleLogfile(g.uiLogPath, uiLogFile); err != nil {
+	if err := g.addSingleLogfile(g.uiLogOpener, g.uiLogPath, configs.UILogFile); err != nil {
 		return fmt.Errorf("add UI log file to zip: %w", err)
 	}
 
-	g.addRotatedLogFiles(filepath.Dir(g.uiLogPath), uiLogPrefix)
+	g.addRotatedLogFiles(g.uiLogOpener, filepath.Dir(g.uiLogPath), uiLogPrefix)
 
 	return nil
 }
 
 // addSingleLogfile adds a single log file to the archive
-func (g *BundleGenerator) addSingleLogfile(logPath, targetName string) error {
-	logFile, err := os.Open(logPath)
+func (g *BundleGenerator) addSingleLogfile(open LogOpener, logPath, targetName string) error {
+	logFile, err := open(logPath)
 	if err != nil {
 		return fmt.Errorf("open log file %s: %w", targetName, err)
 	}
@@ -1065,8 +1092,8 @@ func (g *BundleGenerator) addSingleLogfile(logPath, targetName string) error {
 }
 
 // addSingleLogFileGz adds a single gzipped log file to the archive
-func (g *BundleGenerator) addSingleLogFileGz(logPath, targetName string) error {
-	f, err := os.Open(logPath)
+func (g *BundleGenerator) addSingleLogFileGz(open LogOpener, logPath, targetName string) error {
+	f, err := open(logPath)
 	if err != nil {
 		return fmt.Errorf("open gz log file %s: %w", targetName, err)
 	}
@@ -1113,7 +1140,7 @@ func (g *BundleGenerator) addSingleLogFileGz(logPath, targetName string) error {
 // addRotatedLogFiles adds rotated log files to the bundle based on logFileCount.
 // prefix is the base log name without extension (e.g. "client", "gui-client");
 // the glob matches both files rotated by us and by logrotate on linux.
-func (g *BundleGenerator) addRotatedLogFiles(logDir, prefix string) {
+func (g *BundleGenerator) addRotatedLogFiles(open LogOpener, logDir, prefix string) {
 	if g.logFileCount == 0 {
 		return
 	}
@@ -1153,9 +1180,9 @@ func (g *BundleGenerator) addRotatedLogFiles(logDir, prefix string) {
 	for i := 0; i < maxFiles; i++ {
 		name := filepath.Base(files[i])
 		if strings.HasSuffix(name, ".gz") {
-			err = g.addSingleLogFileGz(files[i], name)
+			err = g.addSingleLogFileGz(open, files[i], name)
 		} else {
-			err = g.addSingleLogfile(files[i], name)
+			err = g.addSingleLogfile(open, files[i], name)
 		}
 		if err != nil {
 			log.Warnf("failed to add rotated log %s: %v", name, err)

client/internal/debug/debug_ios.go

@@ -27,7 +27,7 @@ func (g *BundleGenerator) addPlatformLog() error {
 	}
 
 	swiftLogPath := filepath.Join(filepath.Dir(g.logPath), swiftLogFile)
-	if err := g.addSingleLogfile(swiftLogPath, swiftLogFile); err != nil {
+	if err := g.addSingleLogfile(openLogFile, swiftLogPath, swiftLogFile); err != nil {
 		// The Swift log is best-effort: the app may not have written it yet.
 		log.Warnf("failed to add %s to debug bundle: %v", swiftLogFile, err)
 	}

client/internal/debug/debug_logfiles_test.go

@@ -97,7 +97,7 @@ func runAddRotatedLogFilesPrefix(t *testing.T, dir, prefix string, logFileCount
 		archive:      zip.NewWriter(&buf),
 		logFileCount: logFileCount,
 	}
-	g.addRotatedLogFiles(dir, prefix)
+	g.addRotatedLogFiles(openLogFile, dir, prefix)
 	require.NoError(t, g.archive.Close())
 
 	zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))

client/internal/debug/debug_test.go

@@ -887,6 +887,8 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		ClientCertKeyPath:             "/tmp/key",
 		LazyConnection:                "on",
 		MTU:                           1280,
+		DisableIPv6:                   true,
+		SyncMessageVersion:            func(v int) *int { return &v }(1),
 	}
 
 	for _, anonymize := range []bool{false, true} {

client/internal/debug/uilog_test.go

@@ -0,0 +1,64 @@
+package debug
+
+import (
+	"archive/zip"
+	"bytes"
+	"fmt"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/configs"
+)
+
+// bundleEntries generates a bundle with the given generator and returns the
+// set of entry names in the resulting archive.
+func bundleEntries(t *testing.T, g *BundleGenerator) map[string]struct{} {
+	t.Helper()
+
+	path, err := g.Generate()
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = os.Remove(path) })
+
+	data, err := os.ReadFile(path)
+	require.NoError(t, err)
+
+	zr, err := zip.NewReader(bytes.NewReader(data), int64(len(data)))
+	require.NoError(t, err)
+
+	names := make(map[string]struct{}, len(zr.File))
+	for _, f := range zr.File {
+		names[f.Name] = struct{}{}
+	}
+	return names
+}
+
+func TestBundleIncludesUILogWhenOpenerAllows(t *testing.T) {
+	path := filepath.Join(t.TempDir(), configs.UILogFile)
+	require.NoError(t, os.WriteFile(path, []byte("gui log"), 0600))
+
+	g := NewBundleGenerator(GeneratorDependencies{
+		UILogPath:   path,
+		UILogOpener: openLogFile,
+	}, BundleConfig{})
+
+	require.Contains(t, bundleEntries(t, g), configs.UILogFile)
+}
+
+// A UILogOpener that refuses (as the ownership check does for a foreign file)
+// keeps the UI log out of the bundle without failing bundle generation.
+func TestBundleExcludesUILogWhenOpenerRefuses(t *testing.T) {
+	path := filepath.Join(t.TempDir(), configs.UILogFile)
+	require.NoError(t, os.WriteFile(path, []byte("secret"), 0600))
+
+	g := NewBundleGenerator(GeneratorDependencies{
+		UILogPath: path,
+		UILogOpener: func(string) (*os.File, error) {
+			return nil, fmt.Errorf("not owned by the caller")
+		},
+	}, BundleConfig{})
+
+	require.NotContains(t, bundleEntries(t, g), configs.UILogFile)
+}

client/internal/debug/upload.go

@@ -3,10 +3,12 @@ package debug
 import (
 	"context"
 	"crypto/sha256"
+	"crypto/tls"
 	"encoding/json"
 	"fmt"
 	"io"
 	"net/http"
+	neturl "net/url"
 	"os"
 
 	"github.com/netbirdio/netbird/upload-server/types"
@@ -14,20 +16,80 @@ import (
 
 const maxBundleUploadSize = 50 * 1024 * 1024
 
-func UploadDebugBundle(ctx context.Context, url, managementURL, filePath string) (key string, err error) {
-	response, err := getUploadURL(ctx, url, managementURL)
+// requireHTTPS refuses any URL the daemon would fetch or upload to that is not
+// https. The daemon runs as root and the bundle carries its logs and state, so a
+// plaintext hop is a place to intercept the bundle or the presigned redirect.
+// The server-side gate already enforces this for the desktop path; this also
+// covers the mobile and job-runner callers that reach this package directly.
+// Skipped when the caller opted into an insecure upload (self-hosted server).
+func requireHTTPS(what, rawURL string) error {
+	parsed, err := neturl.Parse(rawURL)
+	if err != nil {
+		return fmt.Errorf("parse %s: %w", what, err)
+	}
+	if parsed.Scheme != "https" {
+		return fmt.Errorf("%s must use https, got scheme %q", what, parsed.Scheme)
+	}
+	return nil
+}
+
+// uploadClient returns the HTTP client for the upload requests. The default
+// client verifies TLS and refuses a redirect that would downgrade to a non-https
+// hop, so a bundle can never leave over http after an https start. The insecure
+// variant accepts http and untrusted certificates, and is only reachable for a
+// privileged caller that passed --upload-bundle-insecure (see
+// requirePrivilegeForUploadURL).
+func uploadClient(insecure bool) *http.Client {
+	if !insecure {
+		return &http.Client{CheckRedirect: rejectInsecureRedirect}
+	}
+	return &http.Client{
+		Transport: &http.Transport{
+			//nolint:gosec // opt-in, privileged, self-hosted upload servers
+			TLSClientConfig: &tls.Config{InsecureSkipVerify: true, MinVersion: tls.VersionTLS12},
+		},
+	}
+}
+
+// rejectInsecureRedirect refuses a redirect to a non-https target and keeps the
+// standard library's 10-hop limit that a custom CheckRedirect would otherwise
+// disable.
+func rejectInsecureRedirect(req *http.Request, via []*http.Request) error {
+	if req.URL.Scheme != "https" {
+		return fmt.Errorf("refusing redirect to non-https URL %s", req.URL.Redacted())
+	}
+	if len(via) >= 10 {
+		return fmt.Errorf("stopped after 10 redirects")
+	}
+	return nil
+}
+
+func UploadDebugBundle(ctx context.Context, url, managementURL, filePath string, insecure bool) (key string, err error) {
+	if !insecure {
+		if err := requireHTTPS("upload service URL", url); err != nil {
+			return "", err
+		}
+	}
+
+	response, err := getUploadURL(ctx, url, managementURL, insecure)
 	if err != nil {
 		return "", err
 	}
 
-	err = upload(ctx, filePath, response)
+	if !insecure {
+		if err := requireHTTPS("upload URL from service", response.URL); err != nil {
+			return "", err
+		}
+	}
+
+	err = upload(ctx, filePath, response, insecure)
 	if err != nil {
 		return "", err
 	}
 	return response.Key, nil
 }
 
-func upload(ctx context.Context, filePath string, response *types.GetURLResponse) error {
+func upload(ctx context.Context, filePath string, response *types.GetURLResponse, insecure bool) error {
 	fileData, err := os.Open(filePath)
 	if err != nil {
 		return fmt.Errorf("open file: %w", err)
@@ -52,7 +114,7 @@ func upload(ctx context.Context, filePath string, response *types.GetURLResponse
 	req.ContentLength = stat.Size()
 	req.Header.Set("Content-Type", "application/octet-stream")
 
-	putResp, err := http.DefaultClient.Do(req)
+	putResp, err := uploadClient(insecure).Do(req)
 	if err != nil {
 		return fmt.Errorf("upload failed: %v", err)
 	}
@@ -65,16 +127,23 @@ func upload(ctx context.Context, filePath string, response *types.GetURLResponse
 	return nil
 }
 
-func getUploadURL(ctx context.Context, url string, managementURL string) (*types.GetURLResponse, error) {
-	id := getURLHash(managementURL)
-	getReq, err := http.NewRequestWithContext(ctx, "GET", url+"?id="+id, nil)
+func getUploadURL(ctx context.Context, serviceURL string, managementURL string, insecure bool) (*types.GetURLResponse, error) {
+	parsed, err := neturl.Parse(serviceURL)
+	if err != nil {
+		return nil, fmt.Errorf("parse upload service URL: %w", err)
+	}
+	q := parsed.Query()
+	q.Set("id", getURLHash(managementURL))
+	parsed.RawQuery = q.Encode()
+
+	getReq, err := http.NewRequestWithContext(ctx, "GET", parsed.String(), nil)
 	if err != nil {
 		return nil, fmt.Errorf("create GET request: %w", err)
 	}
 
 	getReq.Header.Set(types.ClientHeader, types.ClientHeaderValue)
 
-	resp, err := http.DefaultClient.Do(getReq)
+	resp, err := uploadClient(insecure).Do(getReq)
 	if err != nil {
 		return nil, fmt.Errorf("get presigned URL: %w", err)
 	}

client/internal/debug/upload_test.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"net"
 	"net/http"
+	"net/http/httptest"
 	"os"
 	"path/filepath"
 	"testing"
@@ -43,7 +44,7 @@ func TestUpload(t *testing.T) {
 	fileContent := []byte("test file content")
 	err := os.WriteFile(file, fileContent, 0640)
 	require.NoError(t, err)
-	key, err := UploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file)
+	key, err := UploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file, true)
 	require.NoError(t, err)
 	id := getURLHash(testURL)
 	require.Contains(t, key, id+"/")
@@ -79,3 +80,47 @@ func waitForServer(t *testing.T, addr string) {
 	}
 	t.Fatalf("server did not start listening on %s in time", addr)
 }
+
+func TestRequireHTTPS(t *testing.T) {
+	require.NoError(t, requireHTTPS("upload URL", "https://upload.example/path"))
+	require.Error(t, requireHTTPS("upload URL", "http://upload.example/path"))
+	require.Error(t, requireHTTPS("upload URL", "ftp://upload.example/path"))
+	require.Error(t, requireHTTPS("upload URL", "://malformed"))
+}
+
+func TestRejectInsecureRedirect(t *testing.T) {
+	httpsReq, err := http.NewRequest(http.MethodGet, "https://a.example/", nil)
+	require.NoError(t, err)
+	require.NoError(t, rejectInsecureRedirect(httpsReq, nil), "https redirect target must be allowed")
+
+	httpReq, err := http.NewRequest(http.MethodGet, "http://a.example/", nil)
+	require.NoError(t, err)
+	require.Error(t, rejectInsecureRedirect(httpReq, nil), "http redirect target must be refused")
+
+	require.Error(t, rejectInsecureRedirect(httpsReq, make([]*http.Request, 10)), "the 10-redirect limit must be enforced")
+}
+
+// The secure client refuses to follow an https response that redirects to http,
+// so a bundle can't be downgraded onto plaintext mid-flight.
+func TestUploadClientRefusesHTTPSToHTTPRedirect(t *testing.T) {
+	plain := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.WriteHeader(http.StatusOK)
+	}))
+	t.Cleanup(plain.Close)
+
+	secure := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		http.Redirect(w, r, plain.URL, http.StatusFound)
+	}))
+	t.Cleanup(secure.Close)
+
+	client := uploadClient(false)
+	// Trust the test server's cert without disabling verification globally.
+	client.Transport = secure.Client().Transport
+
+	resp, err := client.Get(secure.URL)
+	if resp != nil {
+		_ = resp.Body.Close()
+	}
+	require.Error(t, err, "redirect from https to http must be refused")
+	require.Contains(t, err.Error(), "non-https")
+}

client/internal/dns/interface_index.go

@@ -0,0 +1,15 @@
+package dns
+
+import (
+	"fmt"
+	"net"
+)
+
+func getInterfaceIndex(interfaceName string) (int, error) {
+	iface, err := net.InterfaceByName(interfaceName)
+	if err != nil {
+		return 0, fmt.Errorf("lookup interface %q: %w", interfaceName, err)
+	}
+
+	return iface.Index, nil
+}

client/internal/dns/interface_index_test.go

@@ -0,0 +1,35 @@
+package dns
+
+import (
+	"net"
+	"testing"
+)
+
+func TestGetInterfaceIndexExisting(t *testing.T) {
+	interfaces, err := net.Interfaces()
+	if err != nil {
+		t.Fatalf("list network interfaces: %v", err)
+	}
+	if len(interfaces) == 0 {
+		t.Fatal("expected at least one network interface")
+	}
+
+	iface := interfaces[0]
+	index, err := getInterfaceIndex(iface.Name)
+	if err != nil {
+		t.Fatalf("look up existing interface %q: %v", iface.Name, err)
+	}
+	if index != iface.Index {
+		t.Fatalf("expected interface index %d, got %d", iface.Index, index)
+	}
+}
+
+func TestGetInterfaceIndexMissing(t *testing.T) {
+	index, err := getInterfaceIndex("netbird-interface-that-does-not-exist")
+	if index != 0 {
+		t.Fatalf("expected missing interface index to be 0, got %d", index)
+	}
+	if err == nil {
+		t.Fatal("expected missing interface lookup to return an error")
+	}
+}

client/internal/dns/local/local.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"os"
 	"slices"
 	"strings"
 	"sync"
@@ -36,7 +37,43 @@ type resolver interface {
 // record is left alone (it points at something outside our mesh, e.g.
 // a non-peer upstream).
 type PeerConnectivity interface {
-	IsConnectedByIP(ip string) (known, connected bool)
+	IsConnectedByIP(ip netip.Addr) (known, connected bool)
+}
+
+// PeerActivator wakes lazy-connection peers on demand. The local resolver calls
+// it with the tunnel IPs an answer points at, so a peer that is idle (lazily
+// disconnected) starts connecting at DNS-resolution time rather than racing the
+// client's first request packet. nil disables warm-up.
+type PeerActivator interface {
+	// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and blocks
+	// until one is connected or ctx (a short per-query budget) expires. It is a
+	// fast no-op for unknown or already-connected addresses.
+	ActivatePeersByIP(ctx context.Context, addrs []netip.Addr)
+}
+
+const (
+	defaultLazyWarmupTimeout = 2 * time.Second
+	envLazyWarmupTimeout     = "NB_DNS_LAZY_WARMUP_TIMEOUT"
+)
+
+// lazyWarmupTimeoutFromEnv returns the per-query budget for waking a
+// lazy-connection peer a DNS answer points at. Tunable via
+// NB_DNS_LAZY_WARMUP_TIMEOUT (a Go duration). Parsed once at construction time.
+func lazyWarmupTimeoutFromEnv() time.Duration {
+	v := os.Getenv(envLazyWarmupTimeout)
+	if v == "" {
+		return defaultLazyWarmupTimeout
+	}
+	d, err := time.ParseDuration(v)
+	if err != nil {
+		log.Warnf("invalid %s value %q, using default %s: %v", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout, err)
+		return defaultLazyWarmupTimeout
+	}
+	if d <= 0 {
+		log.Warnf("non-positive %s value %q, using default %s", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout)
+		return defaultLazyWarmupTimeout
+	}
+	return d
 }
 
 type Resolver struct {
@@ -51,6 +88,12 @@ type Resolver struct {
 	// filter and preserves the legacy "return whatever is registered"
 	// behaviour for callers that never wire a status source.
 	peerConn PeerConnectivity
+	// peerActivator, when non-nil, is called at resolution time to warm the
+	// lazy connection to the peer(s) an answer points at. nil disables warm-up.
+	peerActivator PeerActivator
+	// warmupTimeout is the per-query budget for the lazy-connection warm-up
+	// wait, resolved from the environment once at construction time.
+	warmupTimeout time.Duration
 
 	ctx    context.Context
 	cancel context.CancelFunc
@@ -59,11 +102,12 @@ type Resolver struct {
 func NewResolver() *Resolver {
 	ctx, cancel := context.WithCancel(context.Background())
 	return &Resolver{
-		records: make(map[dns.Question][]dns.RR),
-		domains: make(map[domain.Domain]struct{}),
-		zones:   make(map[domain.Domain]bool),
-		ctx:     ctx,
-		cancel:  cancel,
+		records:       make(map[dns.Question][]dns.RR),
+		domains:       make(map[domain.Domain]struct{}),
+		zones:         make(map[domain.Domain]bool),
+		warmupTimeout: lazyWarmupTimeoutFromEnv(),
+		ctx:           ctx,
+		cancel:        cancel,
 	}
 }
 
@@ -76,6 +120,14 @@ func (d *Resolver) SetPeerConnectivity(p PeerConnectivity) {
 	d.peerConn = p
 }
 
+// SetPeerActivator wires the DNS-time lazy-connection warm-up. Pass nil to
+// disable. Safe to call multiple times; the latest value wins.
+func (d *Resolver) SetPeerActivator(a PeerActivator) {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+	d.peerActivator = a
+}
+
 func (d *Resolver) MatchSubdomains() bool {
 	return true
 }
@@ -122,6 +174,9 @@ func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	replyMessage.RecursionAvailable = true
 
 	result := d.lookupRecords(logger, question)
+	// Warm before filtering: activation flips a lazily-idle target to connected,
+	// which then lets it survive the disconnected-peer filter below.
+	d.warmLazyPeers(question, result.records)
 	result.records = d.filterDisconnectedPeerAnswers(logger, question, result.records)
 	replyMessage.Authoritative = !result.hasExternalData
 	replyMessage.Answer = result.records
@@ -495,8 +550,8 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
 	kept := make([]dns.RR, 0, len(records))
 	var dropped int
 	for _, rr := range records {
-		ip := extractRecordIP(rr)
-		if ip == "" {
+		ip, ok := extractRecordAddr(rr)
+		if !ok {
 			kept = append(kept, rr)
 			continue
 		}
@@ -518,22 +573,57 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
 	return kept
 }
 
-// extractRecordIP returns the dotted-decimal / colon-hex IP carried by
-// an A or AAAA record, or "" for any other record type.
-func extractRecordIP(rr dns.RR) string {
+// warmLazyPeers triggers lazy-connection wake-up for the peers a resolved
+// answer points at and waits briefly for one to connect, so the caller's first
+// request doesn't race the connection establishment. Warm-up is scoped to
+// match-only (non-authoritative) zones — the synthesized private-service zones
+// and user-created zones whose records point at specific peers. The account's
+// peer zone is authoritative, so plain peer-name lookups never trigger warm-up;
+// otherwise resolving any peer's name would wake its idle connection, defeating
+// laziness mesh-wide. No-op when no activator is wired (lazy connections
+// disabled) or the answer carries no peer IPs.
+func (d *Resolver) warmLazyPeers(question dns.Question, records []dns.RR) {
+	if len(records) < 2 {
+		return
+	}
+	d.mu.RLock()
+	activator := d.peerActivator
+	var nonAuth, found bool
+	if activator != nil {
+		nonAuth, found = d.findZone(question.Name)
+	}
+	d.mu.RUnlock()
+	if activator == nil || !found || !nonAuth {
+		return
+	}
+
+	var addrs []netip.Addr
+	for _, rr := range records {
+		if addr, ok := extractRecordAddr(rr); ok {
+			addrs = append(addrs, addr)
+		}
+	}
+	if len(addrs) == 0 {
+		return
+	}
+
+	ctx, cancel := context.WithTimeout(d.ctx, d.warmupTimeout)
+	defer cancel()
+	activator.ActivatePeersByIP(ctx, addrs)
+}
+
+// extractRecordAddr returns the IP address carried by an A or AAAA record.
+// ok is false for any other record type or a record with no address.
+func extractRecordAddr(rr dns.RR) (netip.Addr, bool) {
 	switch r := rr.(type) {
 	case *dns.A:
-		if r.A == nil {
-			return ""
-		}
-		return r.A.String()
+		addr, ok := netip.AddrFromSlice(r.A)
+		return addr.Unmap(), ok
 	case *dns.AAAA:
-		if r.AAAA == nil {
-			return ""
-		}
-		return r.AAAA.String()
+		addr, ok := netip.AddrFromSlice(r.AAAA)
+		return addr.Unmap(), ok
 	}
-	return ""
+	return netip.Addr{}, false
 }
 
 // Update replaces all zones and their records

client/internal/dns/local/local_test.go

@@ -37,8 +37,8 @@ type mockPeerConnectivity struct {
 	byIP map[string]struct{ known, connected bool }
 }
 
-func (m mockPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
-	v, ok := m.byIP[ip]
+func (m mockPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
+	v, ok := m.byIP[ip.String()]
 	if !ok {
 		return false, false
 	}

client/internal/dns/local/warmup_test.go

@@ -0,0 +1,204 @@
+package local
+
+import (
+	"context"
+	"net"
+	"net/netip"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/internal/dns/test"
+	nbdns "github.com/netbirdio/netbird/dns"
+)
+
+// recordingActivator records the addresses it was asked to warm and returns
+// immediately, so ServeDNS is not blocked by the test.
+type recordingActivator struct {
+	mu     sync.Mutex
+	called bool
+	addrs  []netip.Addr
+}
+
+func (r *recordingActivator) ActivatePeersByIP(_ context.Context, addrs []netip.Addr) {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	r.called = true
+	r.addrs = append(r.addrs, addrs...)
+}
+
+func serveA(t *testing.T, resolver *Resolver, name string) *dns.Msg {
+	t.Helper()
+	var resp *dns.Msg
+	w := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { resp = m; return nil }}
+	resolver.ServeDNS(w, new(dns.Msg).SetQuestion(name, dns.TypeA))
+	return resp
+}
+
+// serviceZone registers rec in a match-only (non-authoritative) zone, the shape
+// the synthesized private-service zones arrive in.
+func serviceZone(t *testing.T, resolver *Resolver, zone string, records ...nbdns.SimpleRecord) {
+	t.Helper()
+	resolver.Update([]nbdns.CustomZone{{
+		Domain:           zone,
+		Records:          records,
+		NonAuthoritative: true,
+	}})
+}
+
+func TestLocalResolver_WarmsLazyPeerOnResolve(t *testing.T) {
+	// Warm-up fires only for multi-record answers (the HA / round-robin shape of
+	// the synthesized private-service zones), so register two peer targets.
+	const name = "svc.proxy.netbird.cloud."
+	recs := []nbdns.SimpleRecord{
+		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"},
+		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.8"},
+	}
+	resolver := NewResolver()
+	serviceZone(t, resolver, "proxy.netbird.cloud", recs...)
+
+	act := &recordingActivator{}
+	resolver.SetPeerActivator(act)
+
+	resp := serveA(t, resolver, name)
+	require.NotNil(t, resp, "resolver must answer")
+	require.NotEmpty(t, resp.Answer, "answer must carry the A records")
+
+	act.mu.Lock()
+	defer act.mu.Unlock()
+	assert.True(t, act.called, "activator must be invoked for a multi-record service-zone answer")
+	assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.7"), "activator must receive the first peer IP")
+	assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.8"), "activator must receive the second peer IP")
+}
+
+func TestLocalResolver_NoWarmupForSingleRecord(t *testing.T) {
+	// A single-record answer does not trigger warm-up; the resolver only warms
+	// multi-record answers.
+	rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
+	resolver := NewResolver()
+	serviceZone(t, resolver, "proxy.netbird.cloud", rec)
+
+	act := &recordingActivator{}
+	resolver.SetPeerActivator(act)
+
+	resp := serveA(t, resolver, rec.Name)
+	require.NotNil(t, resp, "resolver must answer")
+	require.NotEmpty(t, resp.Answer, "answer must carry the A record")
+
+	act.mu.Lock()
+	defer act.mu.Unlock()
+	assert.False(t, act.called, "activator must not be invoked for a single-record answer")
+}
+
+func TestLocalResolver_NoActivatorNoWarmup(t *testing.T) {
+	// With no activator wired the resolver behaves exactly as before.
+	rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
+	resolver := NewResolver()
+	serviceZone(t, resolver, "proxy.netbird.cloud", rec)
+
+	resp := serveA(t, resolver, rec.Name)
+	require.NotNil(t, resp, "resolver must still answer without an activator")
+	require.NotEmpty(t, resp.Answer, "answer must carry the A record")
+}
+
+func TestLocalResolver_NoWarmupForMissingRecord(t *testing.T) {
+	// A query that resolves to nothing must not invoke the activator (no IPs).
+	resolver := NewResolver()
+	serviceZone(t, resolver, "proxy.netbird.cloud",
+		nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"})
+
+	act := &recordingActivator{}
+	resolver.SetPeerActivator(act)
+
+	serveA(t, resolver, "absent.proxy.netbird.cloud.")
+
+	act.mu.Lock()
+	defer act.mu.Unlock()
+	assert.False(t, act.called, "activator must not be invoked when there is no answer")
+}
+
+func TestLocalResolver_NoWarmupInAuthoritativeZone(t *testing.T) {
+	// The account's peer zone is authoritative; resolving a peer's name there
+	// must not wake its lazy connection — warm-up is scoped to match-only
+	// (non-authoritative) zones such as the synthesized private-service zones.
+	// Use a multi-record answer so the authoritative-zone scoping is the only
+	// reason warm-up is skipped, not the single-record guard.
+	const name = "peer.netbird.cloud."
+	recs := []nbdns.SimpleRecord{
+		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.9"},
+		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.10"},
+	}
+	resolver := NewResolver()
+	resolver.Update([]nbdns.CustomZone{{
+		Domain:  "netbird.cloud",
+		Records: recs,
+	}})
+
+	act := &recordingActivator{}
+	resolver.SetPeerActivator(act)
+
+	resp := serveA(t, resolver, name)
+	require.NotNil(t, resp, "resolver must answer")
+	require.NotEmpty(t, resp.Answer, "answer must carry the A records")
+
+	act.mu.Lock()
+	defer act.mu.Unlock()
+	assert.False(t, act.called, "activator must not be invoked for authoritative-zone answers")
+}
+
+func TestLazyWarmupTimeoutFromEnv(t *testing.T) {
+	tests := []struct {
+		name   string
+		value  string
+		envSet bool
+		want   time.Duration
+	}{
+		{name: "unset uses default", want: defaultLazyWarmupTimeout},
+		{name: "valid overrides", value: "5s", envSet: true, want: 5 * time.Second},
+		{name: "invalid falls back", value: "not-a-duration", envSet: true, want: defaultLazyWarmupTimeout},
+		{name: "negative falls back", value: "-1s", envSet: true, want: defaultLazyWarmupTimeout},
+		{name: "zero falls back", value: "0s", envSet: true, want: defaultLazyWarmupTimeout},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.envSet {
+				t.Setenv(envLazyWarmupTimeout, tt.value)
+			}
+			assert.Equal(t, tt.want, lazyWarmupTimeoutFromEnv())
+			assert.Equal(t, tt.want, NewResolver().warmupTimeout, "constructor must resolve the timeout once")
+		})
+	}
+}
+
+func TestExtractRecordAddr(t *testing.T) {
+	t.Run("A record yields unmapped v4", func(t *testing.T) {
+		// net.ParseIP returns the 16-byte v4-in-v6 form, the same shape
+		// miekg/dns stores after parsing an A record; the extracted address
+		// must compare equal to a plain v4 netip.Addr.
+		addr, ok := extractRecordAddr(&dns.A{A: net.ParseIP("100.64.0.7")})
+		require.True(t, ok)
+		assert.True(t, addr.Is4())
+		assert.Equal(t, netip.MustParseAddr("100.64.0.7"), addr)
+	})
+
+	t.Run("AAAA record yields v6", func(t *testing.T) {
+		addr, ok := extractRecordAddr(&dns.AAAA{AAAA: net.ParseIP("fd00::1")})
+		require.True(t, ok)
+		assert.Equal(t, netip.MustParseAddr("fd00::1"), addr)
+	})
+
+	t.Run("A record without address", func(t *testing.T) {
+		_, ok := extractRecordAddr(&dns.A{})
+		assert.False(t, ok)
+	})
+
+	t.Run("non-address record", func(t *testing.T) {
+		_, ok := extractRecordAddr(&dns.CNAME{Target: "target.netbird.cloud."})
+		assert.False(t, ok)
+	})
+}

client/internal/dns/mock_server.go

@@ -8,6 +8,7 @@ import (
 	"github.com/miekg/dns"
 
 	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
+	"github.com/netbirdio/netbird/client/internal/dns/local"
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -92,6 +93,11 @@ func (m *MockServer) SetFirewall(Firewall) {
 	// Mock implementation - no-op
 }
 
+// SetPeerActivator mock implementation of SetPeerActivator from Server interface
+func (m *MockServer) SetPeerActivator(local.PeerActivator) {
+	// Mock implementation - no-op
+}
+
 // BeginBatch mock implementation of BeginBatch from Server interface
 func (m *MockServer) BeginBatch() {
 	// Mock implementation - no-op

client/internal/dns/notifier.go

@@ -51,7 +51,5 @@ func (n *notifier) notify() {
 		return
 	}
 
-	go func(l listener.NetworkChangeListener) {
-		l.OnNetworkChanged("")
-	}(n.listener)
+	n.listener.OnNetworkChanged("")
 }

client/internal/dns/server.go

@@ -82,6 +82,7 @@ type Server interface {
 	PopulateManagementDomain(mgmtURL *url.URL) error
 	SetRouteSources(selected, active func() route.HAMap)
 	SetFirewall(Firewall)
+	SetPeerActivator(local.PeerActivator)
 }
 
 type nsGroupsByDomain struct {
@@ -251,7 +252,7 @@ func NewDefaultServerPermanentUpstream(
 	ds.hostsDNSHolder.set(hostsDnsList)
 	ds.permanent = true
 	ds.currentConfig = dnsConfigToHostDNSConfig(config, ds.service.RuntimeIP(), ds.service.RuntimePort())
-	ds.searchDomainNotifier = newNotifier(ds.SearchDomains())
+	ds.searchDomainNotifier = newNotifier(ds.searchDomains())
 	ds.searchDomainNotifier.setListener(listener)
 	setServerDns(ds)
 	return ds
@@ -491,6 +492,13 @@ func (s *DefaultServer) SetFirewall(fw Firewall) {
 	}
 }
 
+// SetPeerActivator wires the DNS-time lazy-connection warm-up on the local
+// resolver. Injected after the connection manager exists (it does not at
+// DNS-server construction time). Pass nil to disable.
+func (s *DefaultServer) SetPeerActivator(a local.PeerActivator) {
+	s.localResolver.SetPeerActivator(a)
+}
+
 // Stop stops the server
 func (s *DefaultServer) Stop() {
 	s.ctxCancel()
@@ -594,6 +602,12 @@ func (s *DefaultServer) UpdateDNSServer(serial uint64, update nbdns.Config) erro
 }
 
 func (s *DefaultServer) SearchDomains() []string {
+	s.mux.Lock()
+	defer s.mux.Unlock()
+	return s.searchDomains()
+}
+
+func (s *DefaultServer) searchDomains() []string {
 	var searchDomains []string
 
 	for _, dConf := range s.currentConfig.Domains {
@@ -678,7 +692,7 @@ func (s *DefaultServer) applyConfiguration(update nbdns.Config) error {
 	}()
 
 	if s.searchDomainNotifier != nil {
-		s.searchDomainNotifier.onNewSearchDomains(s.SearchDomains())
+		s.searchDomainNotifier.onNewSearchDomains(s.searchDomains())
 	}
 
 	s.updateNSGroupStates(update.NameServerGroups)
@@ -1435,11 +1449,11 @@ type localPeerConnectivity struct {
 
 // IsConnectedByIP looks the IP up in the peerstore and surfaces both
 // the known and connected bits. Used by Resolver.filterDisconnectedPeerAnswers.
-func (l localPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
+func (l localPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
 	if l.status == nil {
 		return false, false
 	}
-	state, ok := l.status.PeerStateByIP(ip)
+	state, ok := l.status.PeerStateByIP(ip.String())
 	if !ok {
 		return false, false
 	}

client/internal/dns/upstream_ios.go

@@ -130,8 +130,3 @@ func GetClientPrivate(iface privateClientIface, upstreamIP netip.Addr, dialTimeo
 	}
 	return client, nil
 }
-
-func getInterfaceIndex(interfaceName string) (int, error) {
-	iface, err := net.InterfaceByName(interfaceName)
-	return iface.Index, err
-}

client/internal/dns_peer_activator.go

@@ -0,0 +1,76 @@
+package internal
+
+import (
+	"context"
+	"net/netip"
+	"time"
+
+	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/client/internal/peerstore"
+)
+
+const dnsActivationPollInterval = 50 * time.Millisecond
+
+// dnsPeerActivator wakes lazy-connection peers from the DNS resolution path. It
+// implements dns/local.PeerActivator. DNS queries run on their own goroutines,
+// so it only touches state that is safe for concurrent use — ConnMgr.ActivatePeer,
+// peerstore.Store and peer.Status — and never takes the engine's syncMsgMux,
+// keeping DNS resolution from contending with network-map processing.
+type dnsPeerActivator struct {
+	connMgr   *ConnMgr
+	peerStore *peerstore.Store
+	status    *peer.Status
+	// ctx is the engine's long-lived context. The connection dial is tied to it
+	// (not the per-query DNS wait budget) so a handshake that outlasts the wait
+	// still completes in the background rather than being cancelled at the deadline.
+	ctx context.Context
+}
+
+// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and waits
+// until one is connected or ctx (the per-query DNS wait budget) expires.
+// Activation itself is tied to the engine's long-lived context so the dial
+// survives a wait that times out. Unknown or already-connected addresses are
+// skipped, so the steady-state (warm) path adds no latency.
+func (a *dnsPeerActivator) ActivatePeersByIP(ctx context.Context, addrs []netip.Addr) {
+	if a == nil || a.connMgr == nil {
+		return
+	}
+
+	var pending []string
+	for _, addr := range addrs {
+		ip := addr.String()
+		st, ok := a.status.PeerStateByIP(ip)
+		if !ok || st.ConnStatus == peer.StatusConnected {
+			continue
+		}
+		conn, ok := a.peerStore.PeerConn(st.PubKey)
+		if !ok {
+			continue
+		}
+		a.connMgr.ActivatePeer(a.ctx, conn)
+		pending = append(pending, ip)
+	}
+
+	if len(pending) == 0 {
+		return
+	}
+	a.waitConnected(ctx, pending)
+}
+
+// waitConnected blocks until any of ips reports a connected peer or ctx expires.
+func (a *dnsPeerActivator) waitConnected(ctx context.Context, ips []string) {
+	ticker := time.NewTicker(dnsActivationPollInterval)
+	defer ticker.Stop()
+	for {
+		for _, ip := range ips {
+			if st, ok := a.status.PeerStateByIP(ip); ok && st.ConnStatus == peer.StatusConnected {
+				return
+			}
+		}
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+		}
+	}
+}

client/internal/dns_peer_activator_test.go

@@ -0,0 +1,129 @@
+package internal
+
+import (
+	"context"
+	"net/netip"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/client/internal/peerstore"
+)
+
+func newTestPeerConn(t *testing.T, key string) *peer.Conn {
+	t.Helper()
+	conn, err := peer.NewConn(peer.ConnConfig{
+		Key:      key,
+		LocalKey: "local",
+		WgConfig: peer.WgConfig{
+			AllowedIps: []netip.Prefix{netip.MustParsePrefix("100.64.0.1/32")},
+		},
+	}, peer.ServiceDependencies{})
+	require.NoError(t, err)
+	return conn
+}
+
+func newTestDNSPeerActivator(t *testing.T) (*dnsPeerActivator, *peer.Status, *peerstore.Store) {
+	t.Helper()
+	status := peer.NewRecorder("https://mgm")
+	store := peerstore.NewConnStore()
+	// ConnMgr without Start: the lazy manager is nil, so ActivatePeer is a
+	// no-op — these tests exercise the activator's skip/wait logic.
+	connMgr := NewConnMgr(&EngineConfig{}, status, store, nil)
+	return &dnsPeerActivator{
+		connMgr:   connMgr,
+		peerStore: store,
+		status:    status,
+		ctx:       context.Background(),
+	}, status, store
+}
+
+func TestDNSPeerActivator_NilSafe(t *testing.T) {
+	var a *dnsPeerActivator
+	a.ActivatePeersByIP(context.Background(), []netip.Addr{netip.MustParseAddr("100.64.0.1")})
+}
+
+// TestDNSPeerActivator_SkipsUnknownAndConnectedPeers verifies the steady-state
+// (warm) path adds no latency: already-connected and unknown addresses never
+// enter the wait loop.
+func TestDNSPeerActivator_SkipsUnknownAndConnectedPeers(t *testing.T) {
+	a, status, store := newTestDNSPeerActivator(t)
+
+	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", "fd00::1"))
+	require.NoError(t, status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected}))
+	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	start := time.Now()
+	a.ActivatePeersByIP(ctx, []netip.Addr{
+		netip.MustParseAddr("100.64.0.1"),  // known, connected -> skipped
+		netip.MustParseAddr("fd00::1"),     // known via IPv6, connected -> skipped
+		netip.MustParseAddr("100.64.0.99"), // unknown -> skipped
+	})
+	require.Less(t, time.Since(start), time.Second, "no pending peer must mean no wait")
+}
+
+// TestDNSPeerActivator_WaitsForPendingPeerToConnect verifies the wait loop
+// returns as soon as a pending peer reports connected, well before the
+// per-query budget expires.
+func TestDNSPeerActivator_WaitsForPendingPeerToConnect(t *testing.T) {
+	a, status, store := newTestDNSPeerActivator(t)
+
+	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
+	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
+
+	go func() {
+		time.Sleep(150 * time.Millisecond)
+		_ = status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected})
+	}()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	start := time.Now()
+	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
+	elapsed := time.Since(start)
+
+	require.GreaterOrEqual(t, elapsed, 100*time.Millisecond, "must wait for the pending peer")
+	require.Less(t, elapsed, 5*time.Second, "must return on connect, not at the deadline")
+}
+
+// TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle verifies a peer that
+// never connects releases the DNS response at the per-query budget instead of
+// blocking it indefinitely.
+func TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle(t *testing.T) {
+	a, status, store := newTestDNSPeerActivator(t)
+
+	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
+	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
+
+	ctx, cancel := context.WithTimeout(context.Background(), 300*time.Millisecond)
+	defer cancel()
+
+	start := time.Now()
+	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
+	elapsed := time.Since(start)
+
+	require.GreaterOrEqual(t, elapsed, 250*time.Millisecond, "must wait out the budget for a pending peer")
+	require.Less(t, elapsed, 5*time.Second, "must not block past the budget")
+}
+
+// TestDNSPeerActivator_NoWaitWithoutPeerConn verifies a known-but-idle peer
+// with no connection object in the store is not waited on: there is nothing to
+// activate, so waiting could only ever time out.
+func TestDNSPeerActivator_NoWaitWithoutPeerConn(t *testing.T) {
+	a, status, _ := newTestDNSPeerActivator(t)
+
+	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	start := time.Now()
+	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
+	require.Less(t, time.Since(start), time.Second, "peer without a conn must not be waited on")
+}

client/internal/ebpf/ebpf/src/dns_fwd.c

@@ -52,11 +52,14 @@ int xdp_dns_fwd(struct iphdr  *ip, struct udphdr *udp) {
 
     if (udp->dest == GENERAL_DNS_PORT && ip->daddr == dns_ip) {
         udp->dest = dns_port;
+        // Clear the now-stale checksum; zero means "not computed" for IPv4.
+        udp->check = 0;
         return XDP_PASS;
     }
 
     if (udp->source == dns_port && ip->saddr == dns_ip) {
         udp->source = GENERAL_DNS_PORT;
+        udp->check = 0;
         return XDP_PASS;
     }
 

client/internal/ebpf/ebpf/src/wg_proxy.c

@@ -50,5 +50,11 @@ int xdp_wg_proxy(struct iphdr  *ip, struct udphdr *udp) {
     __be16 new_dst_port = htons(proxy_port);
     udp->dest = new_dst_port;
     udp->source = new_src_port;
+
+    // The ports are covered by the UDP checksum. This is an IPv4 loopback hop
+    // and the payload is already integrity-protected, so clear the checksum (a
+    // zero UDP checksum means "not computed" for IPv4) rather than leave a
+    // stale value the kernel would drop as UDP_CSUM.
+    udp->check = 0;
 	return XDP_PASS;
 }

client/internal/elevate/elevate.go

@@ -0,0 +1,74 @@
+// Package elevate re-runs this very executable under the operating system's own
+// privilege-elevation mechanism and waits for it to finish.
+//
+// It exists so that a change the daemon restricts to root/administrator can be
+// authorized from the GUI, by the user, at the moment they ask for it: Windows
+// shows the UAC consent dialog, macOS the system authentication dialog, and
+// Linux/FreeBSD the session's polkit agent. The credentials, where any are
+// asked for, are collected by the operating system and never pass through
+// NetBird.
+//
+// What the elevated process then does is the caller's business: it is the same
+// binary, in a one-shot mode, and it is authorized by the daemon exactly like
+// any other privileged caller, from the identity the kernel reports on the
+// control channel. Nothing here grants privilege, and the daemon gains no new
+// way to be talked into something: elevation only changes who is calling it.
+package elevate
+
+import (
+	"context"
+	"errors"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// AppliedMarker is what the elevated process prints on standard output once it has
+// done what it was run for.
+//
+// macOS's AuthorizationExecuteWithPrivileges reports no exit status and does not
+// say which process it started, so there this line is the only evidence that the
+// change was applied. The other platforms have an exit code and ignore it.
+const AppliedMarker = "netbird-elevated: applied"
+
+var (
+	// ErrDeclined reports that the user dismissed the prompt or did not
+	// authenticate. Nothing happened and nothing is wrong: a caller undoes its
+	// optimistic update and stays quiet.
+	ErrDeclined = errors.New("authorization declined")
+
+	// ErrUnavailable reports that this host has no elevation mechanism we can
+	// drive: no polkit on a Unix desktop, or an executable we decline to run as
+	// root. A caller falls back to telling the user which command to run.
+	ErrUnavailable = errors.New("no privilege elevation mechanism available")
+)
+
+// Run runs this executable with args under the platform's elevation mechanism
+// and waits for it to exit. A non-zero exit is returned as an error, so the
+// caller can treat a completed Run as the operation having succeeded.
+//
+// The args are the caller's own command line, so they cross no privilege
+// boundary: only a user who has just authenticated as an administrator can get
+// them run at all.
+func Run(ctx context.Context, args ...string) error {
+	self, err := trustedSelf()
+	if err != nil {
+		return err
+	}
+	return run(ctx, self, args)
+}
+
+// Available reports whether Run has a mechanism to use on this host, so a caller
+// can offer the prompt only when there is one and otherwise fall back to
+// guidance the user can act on. It answers from what is installed, not from what
+// the user is allowed to do: an administrator's password may still be required
+// and may still not be given, which is ErrDeclined from Run.
+func Available() bool {
+	if _, err := trustedSelf(); err != nil {
+		// Worth a line: this is also what a build run from a group-writable
+		// directory hits, and there is nothing in the UI to say why the offer is
+		// missing.
+		log.Debugf("not offering privilege elevation: %v", err)
+		return false
+	}
+	return mechanismAvailable()
+}

client/internal/elevate/output.go

@@ -0,0 +1,19 @@
+package elevate
+
+import "strings"
+
+// noOutput stands in for a process that said nothing, so that a report of what it
+// said still reads as a sentence.
+const noOutput = "no output"
+
+// firstLine trims captured output to something that reads in one line.
+func firstLine(s string) string {
+	s = strings.TrimSpace(s)
+	if s == "" {
+		return noOutput
+	}
+	if i := strings.IndexByte(s, '\n'); i >= 0 {
+		return s[:i]
+	}
+	return s
+}

client/internal/elevate/output_test.go

@@ -0,0 +1,21 @@
+package elevate
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestFirstLine(t *testing.T) {
+	tests := []struct{ in, want string }{
+		{in: "", want: noOutput},
+		{in: "  \n ", want: noOutput},
+		{in: "one line", want: "one line"},
+		{in: "first\nsecond", want: "first"},
+		{in: "\nsecond\n", want: "second"},
+	}
+
+	for _, tt := range tests {
+		assert.Equal(t, tt.want, firstLine(tt.in), "input %q", tt.in)
+	}
+}

client/internal/elevate/run_darwin.go

@@ -0,0 +1,359 @@
+package elevate
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"runtime"
+	"strings"
+	"sync"
+	"syscall"
+	"unsafe"
+
+	"github.com/ebitengine/purego"
+	log "github.com/sirupsen/logrus"
+)
+
+// Authorization Services, reached through purego rather than cgo so the released
+// binaries keep building with CGO_ENABLED=0.
+//
+// The prompt belongs to this process, which is what makes it carry the
+// application's name and our own explanation. Going through osascript instead puts
+// the very same trampoline behind a dialog attributed to osascript, and means
+// handing a shell a command line to re-parse.
+//
+// # On AuthorizationExecuteWithPrivileges
+//
+// It is deprecated, and Apple's guidance (Quinn, "BSD Privilege Escalation on
+// macOS", developer.apple.com/forums/thread/708765) is "while it still works, it's
+// been deprecated for many years. Do not use it in a widely distributed product."
+// It is used here anyway, knowingly, because the alternatives Apple offers are for
+// *obtaining* ongoing privileges — an installer package, SMAppService, SMJobBless —
+// and NetBird already has what they would install: a launchd daemon running as
+// root. What is missing is only a way for an unprivileged client to ask it to act.
+//
+// The way to that without a deprecated call is to authorize the client instead of
+// elevating one: the app takes the right with AuthorizationCreate, passes the
+// AuthorizationExternalForm to the daemon, and the daemon checks it with
+// AuthorizationCopyRights before acting — none of which is deprecated. It is the
+// better design and it is where this should end up. It also means the daemon
+// accepting an authorization over its control socket, which is a new way to be
+// asked for privileged work and wants reviewing as such, so it is deliberately not
+// bundled in with the rest of this.
+//
+// Until then, three things keep the deprecation from being a trap. Every symbol is
+// resolved with an error rather than a panic, so a macOS that has dropped this
+// function leaves the app offering the user a command instead of crashing on the
+// way to a prompt. A failure to run the tool is reported as ErrUnavailable, so the
+// fallback is the same one an agent-less Linux session gets. And the whole path
+// runs under guard, which turns a panic out of the FFI layer into that same
+// fallback.
+//
+// The trampoline passes on the environment it was given, so what it starts as root
+// must be an executable this user's peers cannot influence: that is what
+// trustedSelf refuses, and what signing the binary settles for the loader.
+
+const (
+	securityFramework = "/System/Library/Frameworks/Security.framework/Security"
+	libSystem         = "/usr/lib/libSystem.B.dylib"
+
+	// trampoline is what the framework hands the tool to. Present on every macOS,
+	// and worth confirming before offering a prompt rather than mid-prompt.
+	trampoline = "/usr/libexec/security_authtrampoline"
+)
+
+// rightExecute is the right an administrator holds, and what
+// AuthorizationExecuteWithPrivileges requires of us.
+const rightExecute = "system.privilege.admin"
+
+// promptKey is kAuthorizationEnvironmentPrompt, which puts a sentence of ours above
+// the system's in the dialog. It is about the change rather than the mechanism.
+const (
+	promptKey  = "prompt"
+	promptText = "NetBird needs to change a setting that grants SSH access to this computer."
+)
+
+// OSStatus values from SecBase.h that mean something to us; anything else is
+// reported as it comes.
+const (
+	errAuthorizationSuccess               = 0
+	errAuthorizationDenied                = -60005
+	errAuthorizationCanceled              = -60006
+	errAuthorizationInteractionNotAllowed = -60007
+	errAuthorizationToolExecuteFailure    = -60031
+	errAuthorizationToolEnvironmentError  = -60032
+)
+
+// AuthorizationFlags from Authorization.h.
+const (
+	flagDefaults           = 0
+	flagInteractionAllowed = 1 << 0
+	flagExtendRights       = 1 << 1
+	flagDestroyRights      = 1 << 3
+	flagPreAuthorize       = 1 << 4
+)
+
+// authorizationItem mirrors AuthorizationItem: a name, and a value the name gives
+// meaning to. 32 bytes on both amd64 and arm64.
+type authorizationItem struct {
+	name        *byte
+	valueLength uintptr
+	value       unsafe.Pointer
+	// flags is reserved by the API and always zero. Declared because the layout
+	// is the contract: without it the struct is 24 bytes where C reads 32.
+	flags uint32 //nolint:unused // part of the C layout
+}
+
+// authorizationItemSet mirrors AuthorizationItemSet, which serves as both an
+// AuthorizationRights and an AuthorizationEnvironment.
+type authorizationItemSet struct {
+	count uint32
+	items *authorizationItem
+}
+
+var (
+	authorizationCreate                func(rights, environment *authorizationItemSet, flags uint32, authorization *uintptr) int32
+	authorizationExecuteWithPrivileges func(authorization uintptr, pathToTool string, options uint32, arguments *uintptr, communicationsPipe *uintptr) int32
+	authorizationFree                  func(authorization uintptr, flags uint32) int32
+	fileno                             func(stream uintptr) int32
+	fclose                             func(stream uintptr) int32
+
+	loadOnce sync.Once
+	loadErr  error
+)
+
+// load resolves the functions once. A framework that cannot be opened, or a symbol
+// that is no longer there, leaves the host without a mechanism rather than taking
+// the process down with it: see the note on deprecation above.
+func load() error {
+	loadOnce.Do(func() { loadErr = guard("loading Security.framework", resolve) })
+	return loadErr
+}
+
+// guard turns a panic out of the FFI layer into an error, so an API that has
+// changed under us costs the user a prompt rather than the window they were
+// clicking in. purego panics on a signature it cannot map, and this is the one
+// place in the client that calls a deprecated system function.
+//
+// It catches Go panics, which is what purego raises. A fault inside the framework
+// itself is not a panic and not recoverable; the layout the tests pin down is what
+// stands between us and that.
+func guard(what string, fn func() error) (err error) {
+	defer func() {
+		r := recover()
+		if r == nil {
+			return
+		}
+		log.Errorf("%s panicked: %v", what, r)
+		err = fmt.Errorf("%w: %s: %v", ErrUnavailable, what, r)
+	}()
+	return fn()
+}
+
+func resolve() error {
+	security, err := purego.Dlopen(securityFramework, purego.RTLD_LAZY|purego.RTLD_GLOBAL)
+	if err != nil {
+		return fmt.Errorf("open %s: %w", securityFramework, err)
+	}
+	system, err := purego.Dlopen(libSystem, purego.RTLD_LAZY|purego.RTLD_GLOBAL)
+	if err != nil {
+		return fmt.Errorf("open %s: %w", libSystem, err)
+	}
+
+	// purego.RegisterLibFunc panics on a symbol it cannot find, which is not how a
+	// deprecated function's disappearance should reach the user.
+	for _, fn := range []struct {
+		ptr    any
+		handle uintptr
+		name   string
+	}{
+		{&authorizationCreate, security, "AuthorizationCreate"},
+		{&authorizationExecuteWithPrivileges, security, "AuthorizationExecuteWithPrivileges"},
+		{&authorizationFree, security, "AuthorizationFree"},
+		{&fileno, system, "fileno"},
+		{&fclose, system, "fclose"},
+	} {
+		symbol, err := purego.Dlsym(fn.handle, fn.name)
+		if err != nil {
+			return fmt.Errorf("resolve %s: %w", fn.name, err)
+		}
+		if symbol == 0 {
+			return fmt.Errorf("resolve %s: not present on this system", fn.name)
+		}
+		purego.RegisterFunc(fn.ptr, symbol)
+	}
+	return nil
+}
+
+// run asks the system to run self as root: first for the right, which is what puts
+// up the authentication dialog and collects the password or takes the Touch ID,
+// then for the tool. The credentials go to the system's authorization trampoline
+// and never to us.
+//
+// The context bounds only our own waiting; the dialog belongs to the system and
+// closes when the user answers it.
+func run(ctx context.Context, self string, args []string) error {
+	if err := load(); err != nil {
+		return fmt.Errorf("%w: %v", ErrUnavailable, err)
+	}
+
+	return guard("asking for privileges", func() error {
+		authorization, err := authorize()
+		if err != nil {
+			return err
+		}
+		defer authorizationFree(authorization, flagDestroyRights)
+
+		return execute(ctx, authorization, self, args)
+	})
+}
+
+func mechanismAvailable() bool {
+	if err := load(); err != nil {
+		return false
+	}
+	info, err := os.Stat(trampoline)
+	return err == nil && !info.IsDir()
+}
+
+// authorize obtains the right, prompting for it. A dismissed dialog comes back as
+// errAuthorizationCanceled and a password given up on as errAuthorizationDenied;
+// both are the user's answer rather than a failure.
+func authorize() (uintptr, error) {
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, rightExecute)})
+	environment := itemSet(&pinner, promptItem(&pinner))
+
+	var authorization uintptr
+	status := authorizationCreate(rights, environment,
+		flagDefaults|flagInteractionAllowed|flagPreAuthorize|flagExtendRights, &authorization)
+
+	switch status {
+	case errAuthorizationSuccess:
+		return authorization, nil
+	case errAuthorizationCanceled, errAuthorizationDenied:
+		return 0, ErrDeclined
+	case errAuthorizationInteractionNotAllowed:
+		// Nowhere to put a dialog, so there is nobody to ask: a launch daemon, or
+		// a session with no window server.
+		return 0, fmt.Errorf("%w: this session cannot show an authorization prompt", ErrUnavailable)
+	default:
+		return 0, fmt.Errorf("request %s: OSStatus %d", rightExecute, status)
+	}
+}
+
+// execute runs the tool with the right in hand and waits for it by reading the pipe
+// it is given until the tool closes it.
+//
+// AuthorizationExecuteWithPrivileges reports no exit status and does not say what
+// process it started, which is why the one-shot says so itself: what it prints is
+// the only evidence that the change was applied.
+func execute(ctx context.Context, authorization uintptr, self string, args []string) error {
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	argv := make([]uintptr, 0, len(args)+1)
+	for _, arg := range args {
+		argv = append(argv, uintptr(unsafe.Pointer(cString(&pinner, arg))))
+	}
+	argv = append(argv, 0)
+	pinner.Pin(&argv[0])
+
+	var pipe uintptr
+	status := authorizationExecuteWithPrivileges(authorization, self, flagDefaults, &argv[0], &pipe)
+	switch status {
+	case errAuthorizationSuccess:
+	case errAuthorizationCanceled:
+		return ErrDeclined
+	case errAuthorizationToolExecuteFailure, errAuthorizationToolEnvironmentError:
+		// The right was granted and the tool still did not start. Nothing the user
+		// can do about it from here, so point them at the command instead.
+		return fmt.Errorf("%w: the system would not run %s elevated (OSStatus %d)", ErrUnavailable, self, status)
+	default:
+		return fmt.Errorf("run %s elevated: OSStatus %d", self, status)
+	}
+
+	out, err := readPipe(ctx, pipe)
+	if err != nil {
+		return err
+	}
+	return checkApplied(out)
+}
+
+// checkApplied reads the one-shot's report, which stands in for the exit status
+// there is no way to ask for here. A run that said nothing did not apply the
+// change, whatever else went on.
+func checkApplied(out string) error {
+	if !strings.Contains(out, AppliedMarker) {
+		return fmt.Errorf("elevated netbird did not report the change as applied: %s", firstLine(out))
+	}
+	return nil
+}
+
+// readPipe drains the tool's output, which ends when the tool exits and is
+// therefore also how we wait for it.
+func readPipe(ctx context.Context, pipe uintptr) (string, error) {
+	if pipe == 0 {
+		return "", nil
+	}
+	defer fclose(pipe)
+
+	fd := int(fileno(pipe))
+	if fd < 0 {
+		return "", nil
+	}
+
+	var out strings.Builder
+	buf := make([]byte, 4096)
+	for {
+		if err := ctx.Err(); err != nil {
+			return out.String(), err
+		}
+		n, err := syscall.Read(fd, buf)
+		if n > 0 {
+			out.Write(buf[:n])
+		}
+		switch {
+		case errors.Is(err, syscall.EINTR):
+			// A signal landed mid-read, which says nothing about the tool.
+			continue
+		case err != nil:
+			log.Debugf("read the elevated process's output: %v", err)
+			return out.String(), nil
+		case n <= 0:
+			// End of file: the tool closed the pipe, which is how it exiting
+			// reaches us.
+			return out.String(), nil
+		}
+	}
+}
+
+// itemSet builds an AuthorizationItemSet over items, pinned for the call.
+func itemSet(pinner *runtime.Pinner, items ...authorizationItem) *authorizationItemSet {
+	pinner.Pin(&items[0])
+	set := &authorizationItemSet{count: uint32(len(items)), items: &items[0]}
+	pinner.Pin(set)
+	return set
+}
+
+// promptItem is the environment entry carrying our sentence for the dialog.
+func promptItem(pinner *runtime.Pinner) authorizationItem {
+	value := []byte(promptText)
+	pinner.Pin(&value[0])
+	return authorizationItem{
+		name:        cString(pinner, promptKey),
+		valueLength: uintptr(len(value)),
+		value:       unsafe.Pointer(&value[0]),
+	}
+}
+
+// cString returns a NUL-terminated copy of s, pinned so the C side may hold it for
+// the duration of the call.
+func cString(pinner *runtime.Pinner, s string) *byte {
+	b := append([]byte(s), 0)
+	pinner.Pin(&b[0])
+	return &b[0]
+}

client/internal/elevate/run_darwin_test.go

@@ -0,0 +1,111 @@
+package elevate
+
+import (
+	"errors"
+	"runtime"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// The framework has to load and the symbols have to resolve, or nothing else here
+// means anything.
+func TestSecurityFrameworkLoads(t *testing.T) {
+	require.NoError(t, load(), "Security.framework must open")
+
+	for name, fn := range map[string]any{
+		"AuthorizationCreate":                authorizationCreate,
+		"AuthorizationExecuteWithPrivileges": authorizationExecuteWithPrivileges,
+		"AuthorizationFree":                  authorizationFree,
+		"fileno":                             fileno,
+		"fclose":                             fclose,
+	} {
+		assert.NotNil(t, fn, "%s must resolve", name)
+	}
+}
+
+// A request with no interaction allowed exercises the whole call — the rights and
+// environment structs, and the OSStatus that comes back — without a dialog anybody
+// has to answer. What the system decides is its business; that it decides at all is
+// what this asserts.
+func TestAuthorizationCreateWithoutInteraction(t *testing.T) {
+	if err := load(); err != nil {
+		t.Skipf("Security.framework did not open: %v", err)
+	}
+
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, rightExecute)})
+	environment := itemSet(&pinner, promptItem(&pinner))
+	require.EqualValues(t, 1, rights.count, "the rights struct layout must match the C one")
+
+	var authorization uintptr
+	status := authorizationCreate(rights, environment, flagDefaults|flagExtendRights, &authorization)
+
+	switch status {
+	case errAuthorizationSuccess:
+		// Credentials were already cached for this session.
+		authorizationFree(authorization, flagDestroyRights)
+	case errAuthorizationDenied, errAuthorizationInteractionNotAllowed:
+		// The expected answers when nobody may be asked.
+	default:
+		require.Failf(t, "unknown OSStatus", "AuthorizationCreate returned %d, want a status we recognise", status)
+	}
+}
+
+// Asking with a right nobody has must not be mistaken for a declined prompt: the
+// caller would report nothing at all.
+func TestAuthorizeUnknownRightIsNotDeclined(t *testing.T) {
+	if err := load(); err != nil {
+		t.Skipf("Security.framework did not open: %v", err)
+	}
+
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, "io.netbird.right.that.does.not.exist")})
+
+	var authorization uintptr
+	status := authorizationCreate(rights, nil, flagDefaults|flagExtendRights, &authorization)
+	if status == errAuthorizationSuccess {
+		authorizationFree(authorization, flagDestroyRights)
+	}
+	assert.NotEqual(t, int32(errAuthorizationSuccess), status, "a right that does not exist must not be granted")
+}
+
+func TestMechanismAvailable(t *testing.T) {
+	assert.True(t, mechanismAvailable(), "the trampoline exists on every macOS")
+}
+
+// The one-shot's report is what stands in for an exit status here, so a run that
+// says nothing must not read as success.
+func TestCheckApplied(t *testing.T) {
+	require.NoError(t, checkApplied(AppliedMarker+"\n"), "the report the one-shot prints")
+	require.NoError(t, checkApplied("some warning\n"+AppliedMarker+"\n"), "the report after other output")
+
+	assert.Error(t, checkApplied(""), "a run that printed nothing did not apply the change")
+	assert.Error(t, checkApplied("dyld: library not loaded\n"), "output that is not the report")
+}
+
+// A panic out of the FFI layer has to reach the caller as "no mechanism", which is
+// the outcome that offers the user the command instead of taking the window down.
+func TestGuardTurnsAPanicIntoUnavailable(t *testing.T) {
+	err := guard("pretending to call something", func() error {
+		panic("purego: signature it cannot map")
+	})
+
+	require.ErrorIs(t, err, ErrUnavailable, "a panic must read as a missing mechanism")
+	assert.Contains(t, err.Error(), "pretending to call something", "what panicked")
+}
+
+// guard wraps every darwin path, so what a caller switches on has to survive it.
+func TestGuardPassesErrorsThrough(t *testing.T) {
+	sentinel := errors.New("the call itself failed")
+	assert.ErrorIs(t, guard("calling", func() error { return sentinel }), sentinel,
+		"the error it was given")
+	assert.ErrorIs(t, guard("calling", func() error { return ErrDeclined }), ErrDeclined,
+		"a declined prompt stays declined")
+	assert.NoError(t, guard("calling", func() error { return nil }), "a call that worked")
+}

client/internal/elevate/run_unix.go

@@ -0,0 +1,117 @@
+//go:build linux || freebsd
+
+package elevate
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"strings"
+)
+
+// pkexec exit codes that are about the authorization rather than about the program
+// we asked it to run. The manual page reserves both.
+const (
+	// exitDismissed is returned when the user dismissed the authentication
+	// dialog.
+	exitDismissed = 126
+	// exitNotAuthorized is returned when the authorization was not obtained. That
+	// covers the user saying no as well as pkexec having had nobody to ask: see
+	// noAgentMarkers.
+	exitNotAuthorized = 127
+)
+
+// exitNotAuthorized covers three different endings that only pkexec's own words
+// tell apart, so they are matched here. Read with LC_ALL=C so the words are the
+// ones written below.
+//
+// refusedMarker is a refusal: the user said no, gave up on the password, or holds
+// an account that may not elevate at all.
+const refusedMarker = "Not authorized"
+
+// noAgentMarkers say pkexec had no way to ask: no agent registered for the
+// session, and no controlling terminal for the textual agent it falls back to.
+var noAgentMarkers = []string{"authentication agent", "controlling terminal"}
+
+// run asks polkit to run self as root. pkexec hands the request to the session's
+// polkit agent, which is what prompts and what collects any password; we see only
+// its verdict.
+//
+// The environment is otherwise deliberately not passed through: pkexec clears it
+// bar a small allowlist, and the one-shot needs nothing from it.
+func run(ctx context.Context, self string, args []string) error {
+	pkexec, err := exec.LookPath("pkexec")
+	if err != nil {
+		return fmt.Errorf("%w: pkexec is not installed", ErrUnavailable)
+	}
+
+	cmd := exec.CommandContext(ctx, pkexec, append([]string{self}, args...)...)
+	// C locale so pkexec's own diagnostics are the ones noAgentMarkers knows.
+	cmd.Env = append(os.Environ(), "LC_ALL=C")
+	var stderr strings.Builder
+	cmd.Stderr = &stderr
+	// The one-shot reports itself on stdout for macOS's sake, where there is no
+	// exit status to read. Here there is one, so that line is noise.
+	cmd.Stdout = io.Discard
+
+	err = cmd.Run()
+	if err == nil {
+		return nil
+	}
+
+	var exitErr *exec.ExitError
+	if !errors.As(err, &exitErr) {
+		return fmt.Errorf("run pkexec: %w", err)
+	}
+
+	// Matched against everything pkexec said, reported as one line: a complaint
+	// that is not the first thing printed still has to be recognised, and reading
+	// it as a refusal would swallow it.
+	full := stderr.String()
+	out := firstLine(full)
+
+	switch exitErr.ExitCode() {
+	case exitDismissed:
+		return ErrDeclined
+	case exitNotAuthorized:
+		return notAuthorized(full, out)
+	default:
+		return fmt.Errorf("elevated netbird exited with %d: %s", exitErr.ExitCode(), out)
+	}
+}
+
+// notAuthorized sorts out the three endings pkexec reports as exitNotAuthorized.
+//
+// It also returns that code when the authorization succeeded and it then could
+// not run the program, so a refusal has to be recognised rather than assumed:
+// reading every one of these as "the user said no" would revert the control in
+// silence on a host where elevation is broken.
+func notAuthorized(full, out string) error {
+	switch {
+	case hasAny(full, noAgentMarkers):
+		return fmt.Errorf("%w: polkit had no way to ask: %s", ErrUnavailable, out)
+	case out == noOutput, strings.Contains(full, refusedMarker):
+		// The user said no, which needs no message; that an account barred from
+		// elevating altogether lands here too is why the reason is kept.
+		return fmt.Errorf("%w: %s", ErrDeclined, out)
+	default:
+		return fmt.Errorf("pkexec could not run elevated netbird: %s", out)
+	}
+}
+
+func hasAny(s string, markers []string) bool {
+	for _, marker := range markers {
+		if strings.Contains(s, marker) {
+			return true
+		}
+	}
+	return false
+}
+
+func mechanismAvailable() bool {
+	_, err := exec.LookPath("pkexec")
+	return err == nil
+}

client/internal/elevate/run_unix_test.go

@@ -0,0 +1,110 @@
+//go:build linux || freebsd
+
+package elevate
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// fakePkexec puts a pkexec on PATH that exits with the given code, so the
+// mapping from polkit's exit codes onto our errors can be exercised without a
+// polkit agent.
+func fakePkexec(t *testing.T, exitCode int, stderr string) {
+	t.Helper()
+
+	dir := t.TempDir()
+	script := fmt.Sprintf("#!/bin/sh\necho %s >&2\nexit %d\n", shellQuote(stderr), exitCode)
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "pkexec"), []byte(script), 0o700), "write the fake pkexec")
+	t.Setenv("PATH", dir)
+}
+
+func shellQuote(s string) string {
+	return "'" + strings.ReplaceAll(s, "'", `'\''`) + "'"
+}
+
+func TestRunMapsPkexecExitCodes(t *testing.T) {
+	tests := []struct {
+		name     string
+		exitCode int
+		stderr   string
+		wantErr  error
+	}{
+		{name: "applied", exitCode: 0},
+		{
+			name:     "dialog dismissed",
+			exitCode: exitDismissed,
+			stderr:   "Error executing command as another user: Request dismissed",
+			wantErr:  ErrDeclined,
+		},
+		{
+			// What a graphical agent reports for a cancelled prompt. Not a
+			// failure: the user was asked and answered.
+			name:     "prompt cancelled",
+			exitCode: exitNotAuthorized,
+			stderr:   "Error executing command as another user: Not authorized",
+			wantErr:  ErrDeclined,
+		},
+		{
+			// The same status, but pkexec never got to ask anybody.
+			name:     "no agent and no terminal to fall back on",
+			exitCode: exitNotAuthorized,
+			stderr:   "Error creating textual authentication agent: Error opening current controlling terminal for the process (`/dev/tty'): No such device or address",
+			wantErr:  ErrUnavailable,
+		},
+		{
+			// And the same status again once the authorization succeeded and
+			// pkexec could not run what it had been authorized to run. Reading
+			// that as a refusal would revert the control in silence on a host
+			// where elevation is broken.
+			name:     "authorized but not runnable",
+			exitCode: exitNotAuthorized,
+			stderr:   "Error executing command as another user: No such file or directory",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			fakePkexec(t, tt.exitCode, tt.stderr)
+
+			err := run(context.Background(), "/nonexistent/netbird-ui", []string{"--flag"})
+			switch {
+			case tt.wantErr != nil:
+				require.ErrorIs(t, err, tt.wantErr, "exit %d said %q", tt.exitCode, tt.stderr)
+			case tt.exitCode == 0:
+				require.NoError(t, err, "a pkexec that exited cleanly applied the change")
+			default:
+				require.Error(t, err, "exit %d said %q", tt.exitCode, tt.stderr)
+				assert.NotErrorIs(t, err, ErrDeclined, "not the user's answer")
+				assert.NotErrorIs(t, err, ErrUnavailable, "not a missing mechanism")
+			}
+		})
+	}
+}
+
+// An exit code that is not polkit's is the one-shot's own failure, and has to
+// stay distinguishable from a declined prompt: the caller reports it.
+func TestRunReportsOneShotFailure(t *testing.T) {
+	fakePkexec(t, 3, "the one-shot said no")
+
+	err := run(context.Background(), "/nonexistent/netbird-ui", nil)
+
+	require.Error(t, err, "a one-shot that failed is not a prompt that was answered")
+	assert.NotErrorIs(t, err, ErrDeclined, "not the user's answer")
+	assert.NotErrorIs(t, err, ErrUnavailable, "not a missing mechanism")
+}
+
+func TestRunWithoutPkexecIsUnavailable(t *testing.T) {
+	t.Setenv("PATH", t.TempDir())
+
+	err := run(context.Background(), "/nonexistent/netbird-ui", nil)
+	require.ErrorIs(t, err, ErrUnavailable, "no pkexec means no mechanism")
+	assert.False(t, mechanismAvailable(), "mechanismAvailable without pkexec on PATH")
+}

client/internal/elevate/run_unsupported.go

@@ -0,0 +1,15 @@
+//go:build !windows && !darwin && !linux && !freebsd
+
+package elevate
+
+import "context"
+
+// run reports that this platform has no elevation prompt to drive. Mobile and
+// WASM builds have no local user to ask in the first place.
+func run(context.Context, string, []string) error {
+	return ErrUnavailable
+}
+
+func mechanismAvailable() bool {
+	return false
+}

client/internal/elevate/run_windows.go

@@ -0,0 +1,193 @@
+package elevate
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"runtime"
+	"unsafe"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sys/windows"
+)
+
+const (
+	// seeMaskNoCloseProcess keeps the started process's handle open in
+	// hProcess so we can wait for it.
+	seeMaskNoCloseProcess = 0x00000040
+	// seeMaskNoAsync makes ShellExecuteExW finish its work before returning,
+	// which it must when the calling thread does not pump messages.
+	seeMaskNoAsync = 0x00000100
+	// seeMaskFlagNoUI suppresses the shell's own error dialogs; the UAC consent
+	// dialog is not one of them and still appears.
+	seeMaskFlagNoUI = 0x00000400
+
+	// swHide: the one-shot has no window to show.
+	swHide = 0
+
+	// sFalse (S_FALSE) answers CoInitializeEx when COM is already up on this
+	// thread in the mode we asked for; rpcChangedMode (RPC_E_CHANGED_MODE) when
+	// it is up in the other one.
+	sFalse         = 1
+	rpcChangedMode = 0x80010106
+)
+
+// shellExecuteInfoW mirrors SHELLEXECUTEINFOW. The field order and Go's own
+// padding match the C layout on both 386 and amd64.
+type shellExecuteInfoW struct {
+	cbSize         uint32
+	fMask          uint32
+	hwnd           windows.HWND
+	lpVerb         *uint16
+	lpFile         *uint16
+	lpParameters   *uint16
+	lpDirectory    *uint16
+	nShow          int32
+	hInstApp       windows.Handle
+	lpIDList       uintptr
+	lpClass        *uint16
+	hkeyClass      windows.Handle
+	dwHotKey       uint32
+	hIconOrMonitor windows.Handle
+	hProcess       windows.Handle
+}
+
+var (
+	shell32            = windows.NewLazySystemDLL("shell32.dll")
+	procShellExecuteEx = shell32.NewProc("ShellExecuteExW")
+)
+
+// run starts self elevated with the "runas" verb, which is what raises the UAC
+// consent dialog, and waits for it to finish. Windows decides whether consent is
+// enough or an administrator's credentials are needed, and collects them itself.
+func run(ctx context.Context, self string, args []string) error {
+	verb, err := windows.UTF16PtrFromString("runas")
+	if err != nil {
+		return fmt.Errorf("encode verb: %w", err)
+	}
+	file, err := windows.UTF16PtrFromString(self)
+	if err != nil {
+		return fmt.Errorf("encode %s: %w", self, err)
+	}
+	params, err := windows.UTF16PtrFromString(windows.ComposeCommandLine(args))
+	if err != nil {
+		return fmt.Errorf("encode arguments: %w", err)
+	}
+
+	info := shellExecuteInfoW{
+		fMask:        seeMaskNoCloseProcess | seeMaskNoAsync | seeMaskFlagNoUI,
+		hwnd:         ownerWindow(),
+		lpVerb:       verb,
+		lpFile:       file,
+		lpParameters: params,
+		nShow:        swHide,
+	}
+	info.cbSize = uint32(unsafe.Sizeof(info))
+
+	process, err := shellExecute(&info)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if err := windows.CloseHandle(process); err != nil {
+			log.Debugf("close elevated process handle: %v", err)
+		}
+	}()
+
+	return waitForProcess(ctx, process)
+}
+
+// shellExecute performs the call itself. ShellExecuteExW wants COM initialised on
+// the calling thread, so the goroutine is pinned to one for the duration and COM
+// is set up on it; an "already initialised, different mode" answer is fine,
+// because then somebody else has done it for us.
+func shellExecute(info *shellExecuteInfoW) (windows.Handle, error) {
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+
+	switch err := windows.CoInitializeEx(0, windows.COINIT_APARTMENTTHREADED); {
+	case err == nil, isHResult(err, sFalse):
+		// Ours, or already initialised in the same mode: either way this call
+		// counts and has to be balanced.
+		defer windows.CoUninitialize()
+	case isHResult(err, rpcChangedMode):
+		// The thread is already in the other apartment model. ShellExecuteExW
+		// works there too, and there is nothing of ours to balance.
+	default:
+		return 0, fmt.Errorf("initialise COM: %w", err)
+	}
+
+	ret, _, lastErr := procShellExecuteEx.Call(uintptr(unsafe.Pointer(info)))
+	if ret != 0 {
+		return info.hProcess, nil
+	}
+
+	if errors.Is(lastErr, windows.ERROR_CANCELLED) {
+		return 0, ErrDeclined
+	}
+	return 0, fmt.Errorf("run elevated: %w", lastErr)
+}
+
+// ownerWindow returns this process's foreground window, and 0 when the window in
+// front belongs to somebody else or cannot be attributed. ShellExecuteExW takes it
+// as the parent for the UI it raises, which is what keeps the consent dialog in
+// front of the window the user was just clicking in instead of behind it. It is
+// also what a remote-desktop session needs to place the dialog at all when the
+// secure desktop is switched off.
+func ownerWindow() windows.HWND {
+	hwnd := windows.GetForegroundWindow()
+	if hwnd == 0 {
+		return 0
+	}
+
+	var pid uint32
+	if _, err := windows.GetWindowThreadProcessId(hwnd, &pid); err != nil {
+		log.Debugf("cannot attribute the foreground window, raising the prompt without an owner: %v", err)
+		return 0
+	}
+	if pid != windows.GetCurrentProcessId() {
+		return 0
+	}
+	return hwnd
+}
+
+// isHResult reports whether err carries the given HRESULT. CoInitializeEx
+// returns its HRESULT as an Errno, so the comparison is on the raw value.
+func isHResult(err error, hresult uintptr) bool {
+	var errno windows.Errno
+	return errors.As(err, &errno) && uintptr(errno) == hresult
+}
+
+func waitForProcess(ctx context.Context, process windows.Handle) error {
+	// The wait is interruptible so a cancelled context stops us waiting on a
+	// consent dialog nobody is going to answer. The elevated process is not
+	// ours to kill, and it either applies the change or does not.
+	for {
+		event, err := windows.WaitForSingleObject(process, 250)
+		if err != nil {
+			return fmt.Errorf("wait for the elevated process: %w", err)
+		}
+		if event == uint32(windows.WAIT_OBJECT_0) {
+			break
+		}
+		if err := ctx.Err(); err != nil {
+			return err
+		}
+	}
+
+	var code uint32
+	if err := windows.GetExitCodeProcess(process, &code); err != nil {
+		return fmt.Errorf("read the elevated process's exit code: %w", err)
+	}
+	if code != 0 {
+		return fmt.Errorf("elevated netbird exited with %d", code)
+	}
+	return nil
+}
+
+// mechanismAvailable is true on Windows: UAC prompts for consent when the user
+// is an administrator and for an administrator's credentials when they are not,
+// so there is always something to ask.
+func mechanismAvailable() bool {
+	return true
+}

client/internal/elevate/trusted.go

@@ -0,0 +1,40 @@
+package elevate
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+)
+
+// trustedSelf returns the path of this executable, provided it is one we are
+// willing to have run as root.
+//
+// The check is what keeps elevation from becoming a way to launder someone
+// else's code into a root process: the user consents to NetBird being elevated,
+// having been shown NetBird's name, so what runs must be the file NetBird was
+// installed as and not something a third party could have swapped for it. An
+// executable only its owner can write is that; anything wider is refused, and
+// the caller falls back to showing the command instead.
+//
+// The owner writing to their own executable is not part of that threat: code
+// running as the user can already prompt them for anything, and could just as
+// well ask them to run the command by hand. What matters is that no *other*
+// unprivileged account can reach it.
+func trustedSelf() (string, error) {
+	exe, err := os.Executable()
+	if err != nil {
+		return "", fmt.Errorf("locate this executable: %w", err)
+	}
+
+	// Resolve symlinks so the checks below apply to the file that would actually
+	// be executed, not to a link somebody else may control.
+	resolved, err := filepath.EvalSymlinks(exe)
+	if err != nil {
+		return "", fmt.Errorf("resolve %s: %w", exe, err)
+	}
+
+	if err := checkOnlyOwnerWritable(resolved); err != nil {
+		return "", fmt.Errorf("%w: %s cannot be trusted to run as root: %w", ErrUnavailable, resolved, err)
+	}
+	return resolved, nil
+}

client/internal/elevate/trusted_group_darwin.go

@@ -0,0 +1,10 @@
+package elevate
+
+// adminWriteGIDs are the groups whose write access to an executable does not
+// widen who could authorize elevating it.
+//
+// macOS installs applications as root:admin, mode 0775, /Applications included,
+// so requiring owner-only write would reject every normal install. Group admin
+// (gid 80) is exactly the set of accounts that can answer the authentication
+// dialog, so its write access grants nothing the prompt would not.
+var adminWriteGIDs = []uint32{0, 80}

client/internal/elevate/trusted_group_unix.go

@@ -0,0 +1,9 @@
+//go:build !windows && !darwin
+
+package elevate
+
+// adminWriteGIDs are the groups whose write access to an executable does not
+// widen who could authorize elevating it. Only root's own group qualifies here:
+// a distribution installs into root-owned directories, and there is no
+// system-wide administrators group that both writes them and answers polkit.
+var adminWriteGIDs = []uint32{0}

client/internal/elevate/trusted_unix.go

@@ -0,0 +1,146 @@
+//go:build !windows
+
+package elevate
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"os"
+	"os/user"
+	"path/filepath"
+	"slices"
+	"strconv"
+	"strings"
+	"syscall"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// groupFile lists which accounts are in which group, for the membership a user
+// private group's name does not state: see groupHasOtherMembers.
+const groupFile = "/etc/group"
+
+// checkOnlyOwnerWritable reports an error unless path, and every directory leading
+// to it, is owned by either root or this user and writable by nobody who could not
+// already act as its owner. A writable directory is as good as a writable file,
+// since anything in it can be replaced, so the whole chain is checked.
+func checkOnlyOwnerWritable(path string) error {
+	self := uint32(os.Getuid())
+
+	for dir := path; ; dir = filepath.Dir(dir) {
+		info, err := os.Lstat(dir)
+		if err != nil {
+			return fmt.Errorf("stat %s: %w", dir, err)
+		}
+
+		stat, ok := info.Sys().(*syscall.Stat_t)
+		if !ok {
+			return errors.New("file ownership is unavailable on this platform")
+		}
+		if stat.Uid != 0 && stat.Uid != self {
+			return fmt.Errorf("%s is owned by uid %d, neither root nor this user", dir, stat.Uid)
+		}
+
+		if err := checkWriteBits(dir, info, stat.Uid, stat.Gid); err != nil {
+			return err
+		}
+
+		if parent := filepath.Dir(dir); parent == dir {
+			return nil
+		}
+	}
+}
+
+func checkWriteBits(path string, info os.FileInfo, uid, gid uint32) error {
+	// On a directory the sticky bit stands in for the write bits: whoever may
+	// write there still cannot replace an entry they do not own, which is the
+	// only thing that would matter to us. /tmp is the usual example.
+	sticky := info.IsDir() && info.Mode()&os.ModeSticky != 0
+
+	return writeBitsAllow(path, info.Mode().Perm(), sticky, groupWriteAllowed(uid, gid))
+}
+
+// writeBitsAllow decides on the permission bits alone, given whether the group's
+// write access has been vouched for.
+func writeBitsAllow(path string, perm os.FileMode, sticky, groupAllowed bool) error {
+	if sticky {
+		return nil
+	}
+	if perm&0o020 != 0 && !groupAllowed {
+		return fmt.Errorf("%s is writable by a group with members other than its owner (%v)", path, perm)
+	}
+	if perm&0o002 != 0 {
+		return fmt.Errorf("%s is world-writable (%v)", path, perm)
+	}
+	return nil
+}
+
+// groupWriteAllowed reports whether a group's write access to a file owned by uid
+// puts it in reach of anyone who could not already act as that owner.
+//
+// Two ways it does not. A group in adminWriteGIDs holds the accounts that can
+// answer the elevation prompt anyway. And a user private group is how Debian,
+// Ubuntu and Fedora ship: their umask of 002 makes a home directory and
+// everything built in it group-writable, so refusing that would refuse every
+// build not installed from a package.
+func groupWriteAllowed(uid, gid uint32) bool {
+	if slices.Contains(adminWriteGIDs, gid) {
+		return true
+	}
+
+	group, err := user.LookupGroupId(strconv.FormatUint(uint64(gid), 10))
+	if err != nil {
+		log.Debugf("cannot look up group %d, treating it as shared: %v", gid, err)
+		return false
+	}
+	owner, err := user.LookupId(strconv.FormatUint(uint64(uid), 10))
+	if err != nil {
+		log.Debugf("cannot look up uid %d, treating its group as shared: %v", uid, err)
+		return false
+	}
+
+	if group.Name != owner.Username {
+		return false
+	}
+	return !groupHasOtherMembers(groupFile, group.Name, owner.Username)
+}
+
+// groupHasOtherMembers reports whether the group lists a member besides owner.
+//
+// Sharing the owner's name is what a user private group is recognised by, and it
+// says nothing about who is in it: a group that has since gained a member is
+// still named that way, and that member can write whatever the group can. So the
+// membership is read rather than assumed. A group this file does not describe,
+// because it comes from LDAP or another NSS source, cannot be answered here and
+// leaves the name as the only thing to go on.
+func groupHasOtherMembers(path, name, owner string) bool {
+	file, err := os.Open(path)
+	if err != nil {
+		log.Debugf("cannot read %s for the members of group %q: %v", path, name, err)
+		return false
+	}
+	defer func() {
+		if err := file.Close(); err != nil {
+			log.Debugf("close %s: %v", path, err)
+		}
+	}()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		// name:password:gid:member,member
+		fields := strings.Split(scanner.Text(), ":")
+		if len(fields) < 4 || fields[0] != name {
+			continue
+		}
+		for member := range strings.SplitSeq(fields[3], ",") {
+			if member != "" && member != owner {
+				return true
+			}
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		log.Debugf("read %s: %v", path, err)
+	}
+	return false
+}

client/internal/elevate/trusted_unix_test.go

@@ -0,0 +1,177 @@
+//go:build !windows
+
+package elevate
+
+import (
+	"os"
+	"os/user"
+	"path/filepath"
+	"strconv"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// ownerOnlyDir is t.TempDir() with the write bits tightened. testing creates its
+// numbered directory with 0777 minus the umask, so under the common 002 umask it
+// is group-writable and would fail the check under test on its own.
+func ownerOnlyDir(t *testing.T) string {
+	t.Helper()
+	dir := t.TempDir()
+	require.NoError(t, os.Chmod(dir, 0o755), "tighten the temporary directory")
+	return dir
+}
+
+// writeExecutable creates a plain executable file, the shape trustedSelf checks.
+func writeExecutable(t *testing.T, dir string) string {
+	t.Helper()
+	path := filepath.Join(dir, "netbird-ui")
+	require.NoError(t, os.WriteFile(path, []byte("#!/bin/sh\n"), 0o755), "write the executable")
+	require.NoError(t, os.Chmod(path, 0o755), "set the executable's mode")
+	return path
+}
+
+func TestCheckOnlyOwnerWritableAcceptsOwnerOnly(t *testing.T) {
+	err := checkOnlyOwnerWritable(writeExecutable(t, ownerOnlyDir(t)))
+	assert.NoError(t, err, "an owner-only writable executable is trustworthy")
+}
+
+func TestCheckOnlyOwnerWritableRejectsWorldWritableFile(t *testing.T) {
+	path := writeExecutable(t, ownerOnlyDir(t))
+	require.NoError(t, os.Chmod(path, 0o777), "make the executable world-writable")
+
+	assert.Error(t, checkOnlyOwnerWritable(path), "a world-writable executable must be refused")
+}
+
+// The permission policy on its own, without a filesystem to arrange: whether the
+// group has been vouched for is the only thing that makes group write acceptable.
+func TestWriteBitsAllow(t *testing.T) {
+	tests := []struct {
+		name         string
+		perm         os.FileMode
+		sticky       bool
+		groupAllowed bool
+		wantErr      bool
+	}{
+		{name: "owner only", perm: 0o755},
+		{name: "group write in a private group", perm: 0o775, groupAllowed: true},
+		{name: "group write in a shared group", perm: 0o775, wantErr: true},
+		{name: "world write", perm: 0o777, groupAllowed: true, wantErr: true},
+		{name: "world write on a sticky directory", perm: 0o777, sticky: true},
+		{name: "group write on a sticky directory", perm: 0o775, sticky: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := writeBitsAllow("/path", tt.perm, tt.sticky, tt.groupAllowed)
+			if tt.wantErr {
+				assert.Error(t, err, "perm %v, sticky %v, group allowed %v", tt.perm, tt.sticky, tt.groupAllowed)
+				return
+			}
+			assert.NoError(t, err, "perm %v, sticky %v, group allowed %v", tt.perm, tt.sticky, tt.groupAllowed)
+		})
+	}
+}
+
+// A build under a home directory on a distribution with a 002 umask, which is what
+// a locally built or tarball-installed binary looks like. Its group has no members
+// but its owner, so it is as good as owner-only.
+//
+// Whether this host is such a distribution is read from the environment rather than
+// from groupWriteAllowed: asking the function under test whether to run would let
+// it skip its own coverage away if it regressed to refusing everything.
+func TestCheckOnlyOwnerWritableAcceptsOwnPrivateGroup(t *testing.T) {
+	requirePrivatePrimaryGroup(t)
+
+	dir := ownerOnlyDir(t)
+	path := writeExecutable(t, dir)
+	require.NoError(t, os.Chmod(dir, 0o775), "make the directory group-writable")
+	require.NoError(t, os.Chmod(path, 0o775), "make the executable group-writable")
+
+	err := checkOnlyOwnerWritable(path)
+	assert.NoError(t, err, "group write in the owner's own private group reaches nobody else")
+}
+
+// A group that shares its owner's name but has gained another member is no longer
+// private, and its write access reaches an account that could not elevate.
+func TestGroupHasOtherMembers(t *testing.T) {
+	tests := []struct {
+		name  string
+		entry string
+		want  bool
+	}{
+		{name: "no members", entry: "vma:x:1000:"},
+		{name: "only the owner", entry: "vma:x:1000:vma"},
+		{name: "another member", entry: "vma:x:1000:bob", want: true},
+		{name: "the owner and another", entry: "vma:x:1000:vma,bob", want: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			path := filepath.Join(t.TempDir(), "group")
+			body := "root:x:0:\n" + tt.entry + "\nsudo:x:27:vma\n"
+			require.NoError(t, os.WriteFile(path, []byte(body), 0o644), "write the group file")
+
+			assert.Equal(t, tt.want, groupHasOtherMembers(path, "vma", "vma"), "entry %q", tt.entry)
+		})
+	}
+}
+
+// A group file that says nothing about the group leaves the name as the only thing
+// to go on, so the private-group allowance stands rather than collapsing on every
+// host whose groups come from LDAP.
+func TestGroupHasOtherMembersTolerantOfAnUnknownGroup(t *testing.T) {
+	path := filepath.Join(t.TempDir(), "group")
+	require.NoError(t, os.WriteFile(path, []byte("root:x:0:\n"), 0o644), "write the group file")
+
+	assert.False(t, groupHasOtherMembers(path, "vma", "vma"), "a group the file does not describe")
+	assert.False(t, groupHasOtherMembers(filepath.Join(t.TempDir(), "absent"), "vma", "vma"),
+		"no group file at all")
+}
+
+// A writable directory is as good as a writable file: whoever can write the
+// directory can put a different binary at the same path.
+func TestCheckOnlyOwnerWritableRejectsWritableDirectory(t *testing.T) {
+	dir := filepath.Join(ownerOnlyDir(t), "bin")
+	require.NoError(t, os.Mkdir(dir, 0o755), "create the directory")
+	path := writeExecutable(t, dir)
+	require.NoError(t, os.Chmod(dir, 0o777), "make the directory world-writable")
+
+	assert.Error(t, checkOnlyOwnerWritable(path), "an executable in a world-writable directory must be refused")
+}
+
+// A sticky world-writable directory is exempt: the sticky bit is what stops one
+// user replacing another's entries. /tmp is why this matters.
+func TestCheckOnlyOwnerWritableAcceptsStickyDirectory(t *testing.T) {
+	dir := filepath.Join(ownerOnlyDir(t), "sticky")
+	require.NoError(t, os.Mkdir(dir, 0o755), "create the directory")
+	path := writeExecutable(t, dir)
+	require.NoError(t, os.Chmod(dir, 0o777|os.ModeSticky), "make the directory sticky and world-writable")
+
+	err := checkOnlyOwnerWritable(path)
+	assert.NoError(t, err, "the sticky bit stops another user replacing the executable")
+}
+
+func TestCheckOnlyOwnerWritableRejectsMissingFile(t *testing.T) {
+	err := checkOnlyOwnerWritable(filepath.Join(ownerOnlyDir(t), "absent"))
+	assert.Error(t, err, "an executable that is not there must be refused")
+}
+
+// requirePrivatePrimaryGroup skips unless this user's primary group is their own,
+// which is what the user-private-group allowance is about.
+func requirePrivatePrimaryGroup(t *testing.T) {
+	t.Helper()
+
+	self, err := user.Current()
+	require.NoError(t, err, "look up the test user")
+	group, err := user.LookupGroupId(strconv.Itoa(os.Getgid()))
+	require.NoError(t, err, "look up the test user's primary group")
+
+	if group.Name != self.Username {
+		t.Skipf("the test user's primary group is %q, not their own, so there is nothing to assert here", group.Name)
+	}
+	if groupHasOtherMembers(groupFile, group.Name, self.Username) {
+		t.Skipf("group %q has other members, so it is not a private group", group.Name)
+	}
+}

client/internal/elevate/trusted_windows.go

@@ -0,0 +1,215 @@
+package elevate
+
+import (
+	"errors"
+	"fmt"
+	"path/filepath"
+	"slices"
+	"unsafe"
+
+	"golang.org/x/sys/windows"
+)
+
+const (
+	// fileDeleteChild is FILE_DELETE_CHILD, which x/sys does not define: the
+	// right to delete an entry of a directory without holding DELETE on it.
+	fileDeleteChild = 0x00000040
+
+	// accessAllowedCallbackACEType is an allow ACE with a condition appended to
+	// the ACCESS_ALLOWED_ACE layout, so its trustee is still at SidStart.
+	accessAllowedCallbackACEType = 0x9
+
+	// The allow ACE types that carry object GUIDs ahead of the trustee, so the
+	// SID is not at SidStart. They occur on directory-service objects rather
+	// than files, and are refused rather than skipped: see aceTrustee.
+	accessAllowedObjectACEType         = 0x5
+	accessAllowedCallbackObjectACEType = 0xB
+)
+
+// fileWriteAccess are the rights that let a trustee rewrite or replace a file,
+// or take it over and then do so.
+const fileWriteAccess = windows.FILE_WRITE_DATA | windows.FILE_APPEND_DATA |
+	windows.DELETE | windows.WRITE_DAC | windows.WRITE_OWNER |
+	windows.GENERIC_WRITE | windows.GENERIC_ALL
+
+// dirWriteAccess are the rights over a directory that let a trustee replace an
+// entry somebody else owns. Creating a new entry is not one of them, which is
+// what the Unix sticky bit says in one bit: the root of every volume grants
+// BUILTIN\Users the right to add directories under it, and that reaches nothing
+// already there.
+const dirWriteAccess = fileDeleteChild | windows.DELETE |
+	windows.WRITE_DAC | windows.WRITE_OWNER | windows.GENERIC_ALL
+
+// trustedInstallerSID owns much of what Windows itself installs. x/sys has no
+// well-known constant for it.
+const trustedInstallerSID = "S-1-5-80-956008885-3418522649-1831038044-1853292631-2271478464"
+
+// checkOnlyOwnerWritable reports an error unless path, and every directory
+// leading to it, is owned by an account that can elevate (or by this user) and
+// grants write access to nobody else. A writable directory is as good as a
+// writable file, since an entry in it can be replaced, so the whole chain is
+// checked.
+func checkOnlyOwnerWritable(path string) error {
+	owners, err := trustedOwners()
+	if err != nil {
+		return err
+	}
+	writers, err := trustedWriters(owners)
+	if err != nil {
+		return err
+	}
+
+	writeAccess := windows.ACCESS_MASK(fileWriteAccess)
+	for target := path; ; target = filepath.Dir(target) {
+		if err := checkSecurity(target, writeAccess, owners, writers); err != nil {
+			return err
+		}
+		if parent := filepath.Dir(target); parent == target {
+			return nil
+		}
+		writeAccess = dirWriteAccess
+	}
+}
+
+// trustedOwners are the accounts we accept as the owner of the executable and of
+// the directories above it: the ones that can already answer the UAC prompt,
+// plus this user, whose own executable is theirs to write. Code running as the
+// user could prompt them for anything anyway; what matters is that no *other*
+// unprivileged account can reach it.
+func trustedOwners() ([]*windows.SID, error) {
+	self, err := currentUserSID()
+	if err != nil {
+		return nil, err
+	}
+
+	owners := []*windows.SID{self}
+	for _, wellKnown := range []windows.WELL_KNOWN_SID_TYPE{
+		windows.WinLocalSystemSid,
+		windows.WinBuiltinAdministratorsSid,
+	} {
+		sid, err := windows.CreateWellKnownSid(wellKnown)
+		if err != nil {
+			return nil, fmt.Errorf("build well-known SID %d: %w", wellKnown, err)
+		}
+		owners = append(owners, sid)
+	}
+
+	installer, err := windows.StringToSid(trustedInstallerSID)
+	if err != nil {
+		return nil, fmt.Errorf("parse TrustedInstaller SID: %w", err)
+	}
+	return append(owners, installer), nil
+}
+
+// trustedWriters are the trustees whose write access does not widen who could
+// decide what runs behind the prompt. The owners, and CREATOR OWNER, which
+// resolves to the object's owner and is therefore already vetted.
+func trustedWriters(owners []*windows.SID) ([]*windows.SID, error) {
+	creatorOwner, err := windows.CreateWellKnownSid(windows.WinCreatorOwnerSid)
+	if err != nil {
+		return nil, fmt.Errorf("build the CREATOR OWNER SID: %w", err)
+	}
+	return append(slices.Clone(owners), creatorOwner), nil
+}
+
+func checkSecurity(path string, writeAccess windows.ACCESS_MASK, owners, writers []*windows.SID) error {
+	sd, err := windows.GetNamedSecurityInfo(path, windows.SE_FILE_OBJECT,
+		windows.OWNER_SECURITY_INFORMATION|windows.DACL_SECURITY_INFORMATION)
+	if err != nil {
+		return fmt.Errorf("read security descriptor of %s: %w", path, err)
+	}
+
+	owner, _, err := sd.Owner()
+	if err != nil {
+		return fmt.Errorf("read owner of %s: %w", path, err)
+	}
+	if !containsSID(owners, owner) {
+		return fmt.Errorf("%s is owned by %s, which is neither this user nor an account that can elevate", path, owner)
+	}
+
+	dacl, _, err := sd.DACL()
+	if err != nil {
+		return fmt.Errorf("read DACL of %s: %w", path, err)
+	}
+	// A NULL DACL grants everyone everything; only an absent security
+	// descriptor would have got us here without one, and neither is trustworthy.
+	if dacl == nil {
+		return fmt.Errorf("%s has no DACL, so it grants write access to everyone", path)
+	}
+
+	return checkDACL(path, dacl, writeAccess, writers)
+}
+
+// checkDACL refuses an ACL that grants write access to a trustee outside
+// writers.
+//
+// An allowlist, because the trustees that must not have it cannot be listed: an
+// ACE naming an ordinary user account hands that account the same power as one
+// naming Everyone, and only the accounts that may hold it are knowable.
+func checkDACL(path string, dacl *windows.ACL, writeAccess windows.ACCESS_MASK, writers []*windows.SID) error {
+	for i := uint32(0); i < uint32(dacl.AceCount); i++ {
+		var ace *windows.ACCESS_ALLOWED_ACE
+		if err := windows.GetAce(dacl, i, &ace); err != nil {
+			return fmt.Errorf("read ACE %d of %s: %w", i, path, err)
+		}
+		// An inherit-only ACE says what children of this object get, not what
+		// this object grants.
+		if ace.Header.AceFlags&windows.INHERIT_ONLY_ACE != 0 {
+			continue
+		}
+		if ace.Mask&writeAccess == 0 {
+			continue
+		}
+		// Only an allow ACE grants anything; a deny ACE narrows what one gave.
+		if !isAllowACE(ace.Header.AceType) {
+			continue
+		}
+
+		trustee, err := aceTrustee(ace)
+		if err != nil {
+			return fmt.Errorf("read the trustee of ACE %d of %s: %w", i, path, err)
+		}
+		if !containsSID(writers, trustee) {
+			return fmt.Errorf("%s grants write access to %s", path, trustee)
+		}
+	}
+	return nil
+}
+
+// isAllowACE reports whether an ACE type grants rights, rather than denying,
+// auditing or labelling them.
+func isAllowACE(aceType uint8) bool {
+	switch aceType {
+	case windows.ACCESS_ALLOWED_ACE_TYPE, accessAllowedCallbackACEType,
+		accessAllowedObjectACEType, accessAllowedCallbackObjectACEType:
+		return true
+	default:
+		return false
+	}
+}
+
+// aceTrustee returns who an allow ACE grants its rights to. An ACE whose trustee
+// cannot be located is an error rather than something to skip past: being unable
+// to read who is being given write access is a refusal.
+func aceTrustee(ace *windows.ACCESS_ALLOWED_ACE) (*windows.SID, error) {
+	switch ace.Header.AceType {
+	case windows.ACCESS_ALLOWED_ACE_TYPE, accessAllowedCallbackACEType:
+		//nolint:gosec // SidStart is the first uint32 of the variable-length SID that follows the ACE header.
+		return (*windows.SID)(unsafe.Pointer(&ace.SidStart)), nil
+	default:
+		return nil, errors.New("an object-type allow ACE does not carry its trustee where we can read it")
+	}
+}
+
+func containsSID(sids []*windows.SID, sid *windows.SID) bool {
+	return slices.ContainsFunc(sids, sid.Equals)
+}
+
+func currentUserSID() (*windows.SID, error) {
+	token := windows.GetCurrentProcessToken()
+	user, err := token.GetTokenUser()
+	if err != nil {
+		return nil, fmt.Errorf("read this process's user: %w", err)
+	}
+	return user.User.Sid, nil
+}

client/internal/elevate/trusted_windows_test.go

@@ -0,0 +1,126 @@
+package elevate
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"golang.org/x/sys/windows"
+)
+
+// A file the test user created under their own profile, which is what a per-user
+// install looks like. The whole chain up to the volume root is walked, so this is
+// also what says the walk does not refuse an ordinary Windows installation: the
+// root of every volume grants BUILTIN\Users rights that are not ours to worry
+// about.
+func TestCheckOnlyOwnerWritableAcceptsOwnFile(t *testing.T) {
+	err := checkOnlyOwnerWritable(writeExecutable(t))
+	assert.NoError(t, err, "a file the test user owns, under directories only administrators can write")
+}
+
+// Write access held by an account that cannot answer the UAC prompt means that
+// account decides what runs behind it, whoever the ACE names. The trustees that
+// must not have it cannot be listed, so the check names the ones that may.
+func TestCheckOnlyOwnerWritableRejectsUntrustedWriters(t *testing.T) {
+	tests := []struct {
+		name      string
+		wellKnown windows.WELL_KNOWN_SID_TYPE
+	}{
+		{name: "everyone", wellKnown: windows.WinWorldSid},
+		{name: "authenticated users", wellKnown: windows.WinAuthenticatedUserSid},
+		{name: "builtin users", wellKnown: windows.WinBuiltinUsersSid},
+		// A service account, which no denylist of the obvious groups would name
+		// and which cannot elevate any more than Everyone can.
+		{name: "local service", wellKnown: windows.WinLocalServiceSid},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			path := writeExecutable(t)
+			grantWrite(t, path, tt.wellKnown)
+
+			assert.Error(t, checkOnlyOwnerWritable(path),
+				"write access for %s must be refused", tt.name)
+		})
+	}
+}
+
+// The masks are the policy: on a file any write reaches its contents, while on a
+// directory only deleting or taking over an entry reaches something already
+// there. Adding an entry does not, which is why the walk survives a volume root.
+func TestWriteAccessMasks(t *testing.T) {
+	assert.NotZero(t, fileWriteAccess&windows.FILE_WRITE_DATA, "writing a file's data reaches its contents")
+	assert.NotZero(t, fileWriteAccess&windows.FILE_APPEND_DATA, "appending to a file reaches its contents")
+
+	assert.Zero(t, dirWriteAccess&windows.FILE_WRITE_DATA, "adding a file to a directory replaces nothing")
+	assert.Zero(t, dirWriteAccess&windows.FILE_APPEND_DATA, "adding a subdirectory replaces nothing")
+	assert.NotZero(t, dirWriteAccess&fileDeleteChild, "deleting an entry replaces it")
+	assert.NotZero(t, dirWriteAccess&windows.DELETE, "deleting the directory takes its entries with it")
+}
+
+func TestIsAllowACE(t *testing.T) {
+	tests := []struct {
+		name    string
+		aceType uint8
+		want    bool
+	}{
+		{name: "allowed", aceType: windows.ACCESS_ALLOWED_ACE_TYPE, want: true},
+		{name: "allowed callback", aceType: accessAllowedCallbackACEType, want: true},
+		{name: "allowed object", aceType: accessAllowedObjectACEType, want: true},
+		{name: "allowed callback object", aceType: accessAllowedCallbackObjectACEType, want: true},
+		{name: "denied", aceType: windows.ACCESS_DENIED_ACE_TYPE},
+		// SYSTEM_AUDIT_ACE_TYPE, which x/sys does not define: an ACE that records
+		// access rather than granting it.
+		{name: "audit", aceType: 0x2},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.want, isAllowACE(tt.aceType), "ACE type %#x", tt.aceType)
+		})
+	}
+}
+
+// writeExecutable creates a plain file under the test's own directory, the shape
+// trustedSelf checks.
+func writeExecutable(t *testing.T) string {
+	t.Helper()
+	path := filepath.Join(t.TempDir(), "netbird-ui.exe")
+	require.NoError(t, os.WriteFile(path, []byte("MZ"), 0o755), "write the executable")
+	return path
+}
+
+// grantWrite replaces the file's DACL with one that grants a well-known trustee
+// everything, keeping the test user's own access so the file stays deletable.
+func grantWrite(t *testing.T, path string, wellKnown windows.WELL_KNOWN_SID_TYPE) {
+	t.Helper()
+
+	trustee, err := windows.CreateWellKnownSid(wellKnown)
+	require.NoError(t, err, "build the trustee SID")
+	self, err := currentUserSID()
+	require.NoError(t, err, "read the test user's SID")
+
+	acl, err := windows.ACLFromEntries([]windows.EXPLICIT_ACCESS{
+		fullControl(self, windows.TRUSTEE_IS_USER),
+		fullControl(trustee, windows.TRUSTEE_IS_WELL_KNOWN_GROUP),
+	}, nil)
+	require.NoError(t, err, "build the ACL")
+
+	require.NoError(t, windows.SetNamedSecurityInfo(path, windows.SE_FILE_OBJECT,
+		windows.DACL_SECURITY_INFORMATION|windows.PROTECTED_DACL_SECURITY_INFORMATION,
+		nil, nil, acl, nil), "set the DACL")
+}
+
+func fullControl(sid *windows.SID, trusteeType uint32) windows.EXPLICIT_ACCESS {
+	return windows.EXPLICIT_ACCESS{
+		AccessPermissions: windows.GENERIC_ALL,
+		AccessMode:        windows.GRANT_ACCESS,
+		Trustee: windows.TRUSTEE{
+			TrusteeForm:  windows.TRUSTEE_IS_SID,
+			TrusteeType:  windows.TRUSTEE_TYPE(trusteeType),
+			TrusteeValue: windows.TrusteeValueFromSID(sid),
+		},
+	}
+}

client/internal/engine.go

@@ -64,7 +64,10 @@ import (
 	"github.com/netbirdio/netbird/route"
 	mgm "github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/management/domain"
+	sharedgrpc "github.com/netbirdio/netbird/shared/management/grpc"
+	nbnetworkmap "github.com/netbirdio/netbird/shared/management/networkmap"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
+	types "github.com/netbirdio/netbird/shared/management/types"
 	"github.com/netbirdio/netbird/shared/netiputil"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
@@ -147,6 +150,7 @@ type EngineConfig struct {
 	BlockLANAccess      bool
 	BlockInbound        bool
 	DisableIPv6         bool
+	SyncMessageVersion  *int
 
 	// LazyConnection is the MDM-sourced lazy-connection override; StateUnset defers to
 	// the env var and management feature flag.
@@ -220,6 +224,13 @@ 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 future 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
@@ -561,12 +572,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	}
 	e.stateManager.Start()
 
-	initialRoutes, dnsConfig, dnsFeatureFlag, err := e.readInitialSettings()
-	if err != nil {
-		return fmt.Errorf("read initial settings: %w", err)
-	}
-
-	dnsServer, err := e.newDnsServer(dnsConfig)
+	dnsServer, err := e.newDnsServer()
 	if err != nil {
 		return fmt.Errorf("create dns server: %w", err)
 	}
@@ -584,10 +590,8 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		WGInterface:         e.wgInterface,
 		StatusRecorder:      e.statusRecorder,
 		RelayManager:        e.relayManager,
-		InitialRoutes:       initialRoutes,
 		StateManager:        e.stateManager,
 		DNSServer:           dnsServer,
-		DNSFeatureFlag:      dnsFeatureFlag,
 		PeerStore:           e.peerStore,
 		DisableClientRoutes: e.config.DisableClientRoutes,
 		DisableServerRoutes: e.config.DisableServerRoutes,
@@ -652,8 +656,24 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	iceCfg := e.createICEConfig()
 
 	e.connMgr = NewConnMgr(e.config, e.statusRecorder, e.peerStore, wgIface)
+	e.connMgr.SetRoutedIPsReconciler(func(peerKey string) error {
+		if e.routeManager == nil {
+			return nil
+		}
+		return e.routeManager.ReconcilePeerAllowedIPs(peerKey)
+	})
 	e.connMgr.Start(e.ctx)
 
+	// Wire DNS-time lazy-connection warm-up now that the connection manager
+	// exists (it does not at DNS-server construction time). A DNS answer that
+	// points at an idle peer then wakes it before the client's first request.
+	e.dnsServer.SetPeerActivator(&dnsPeerActivator{
+		connMgr:   e.connMgr,
+		peerStore: e.peerStore,
+		status:    e.statusRecorder,
+		ctx:       e.ctx,
+	})
+
 	e.srWatcher = guard.NewSRWatcher(e.signal, e.relayManager, e.mobileDep.IFaceDiscover, iceCfg)
 	e.srWatcher.Start(peer.IsForceRelayed())
 
@@ -963,8 +983,12 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 
 	e.ApplySessionDeadline(update.GetSessionExpiresAt())
 
-	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())
 	}
 
 	done := e.phase("netbird_config")
@@ -974,12 +998,47 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		return err
 	}
 
+	// Decode the network map from either the components envelope or the
+	// legacy proto.NetworkMap before the posture-check gating below, so the
+	// "is there a network map" decision covers both wire shapes.
+	var (
+		nm         *mgmProto.NetworkMap
+		components *types.NetworkMapComponents
+	)
+	if version := update.GetVersion(); version == int32(sharedgrpc.ComponentNetworkMap) {
+		// 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 can apply deltas instead
+		// of doing a full reconstruction.
+		envelope := update.GetNetworkMapEnvelope()
+		if envelope == nil {
+			return fmt.Errorf("received a SyncReponse indicating use of components network map, but components are missing")
+		}
+
+		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()
+	}
+
 	// Posture checks are bound to the network map presence:
 	//   NetworkMap != nil, checks present -> apply the received checks
 	//   NetworkMap != nil, checks nil     -> posture checks were removed, clear them
 	//   NetworkMap == nil                 -> config-only update (e.g. relay token rotation),
 	//                                        leave the previously applied checks untouched
-	nm := update.GetNetworkMap()
 	if nm == nil {
 		return nil
 	}
@@ -992,6 +1051,14 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	}
 
 	done = e.phase("persist")
+	// 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
+	// incremental-delta base on a future envelope sync.
+	if components != nil {
+		e.latestComponents = components
+	}
+
 	e.persistSyncResponse(update)
 	done()
 
@@ -1005,6 +1072,19 @@ 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 ""
+}
+
 // updateNetbirdConfig applies the management-provided NetBird configuration:
 // STUN/TURN and relay servers, flow logging and DNS settings. A nil config is a no-op,
 // which is the case for sync updates carrying only a network map.
@@ -1164,6 +1244,7 @@ func (e *Engine) applyInfoFlags(info *system.Info) {
 		e.config.BlockLANAccess,
 		e.config.BlockInbound,
 		e.config.DisableIPv6,
+		e.config.SyncMessageVersion,
 		e.config.EnableSSHRoot,
 		e.config.EnableSSHSFTP,
 		e.config.EnableSSHLocalPortForwarding,
@@ -2014,41 +2095,6 @@ func (e *Engine) close() {
 	}
 }
 
-func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, error) {
-	if runtime.GOOS != "android" {
-		// nolint:nilnil
-		return nil, nil, false, nil
-	}
-
-	info := system.GetInfo(e.ctx)
-	info.SetFlags(
-		e.config.RosenpassEnabled,
-		e.config.RosenpassPermissive,
-		&e.config.ServerSSHAllowed,
-		e.config.DisableClientRoutes,
-		e.config.DisableServerRoutes,
-		e.config.DisableDNS,
-		e.config.DisableFirewall,
-		e.config.BlockLANAccess,
-		e.config.BlockInbound,
-		e.config.DisableIPv6,
-		e.config.EnableSSHRoot,
-		e.config.EnableSSHSFTP,
-		e.config.EnableSSHLocalPortForwarding,
-		e.config.EnableSSHRemotePortForwarding,
-		e.config.DisableSSHAuth,
-	)
-
-	netMap, err := e.mgmClient.GetNetworkMap(info)
-	if err != nil {
-		return nil, nil, false, err
-	}
-	routes := toRoutes(netMap.GetRoutes())
-	dnsCfg := toDNSConfig(netMap.GetDNSConfig(), e.wgInterface.Address())
-	dnsFeatureFlag := toDNSFeatureFlag(netMap)
-	return routes, &dnsCfg, dnsFeatureFlag, nil
-}
-
 func (e *Engine) newWgIface() (*iface.WGIface, error) {
 	transportNet, err := e.newStdNet()
 	if err != nil {
@@ -2083,7 +2129,7 @@ func (e *Engine) newWgIface() (*iface.WGIface, error) {
 func (e *Engine) wgInterfaceCreate() (err error) {
 	switch runtime.GOOS {
 	case "android":
-		err = e.wgInterface.CreateOnAndroid(e.routeManager.InitialRouteRange(), e.dnsServer.DnsIP().String(), e.dnsServer.SearchDomains())
+		err = e.wgInterface.CreateOnAndroid(e.routeManager.CurrentRouteRange(), e.dnsServer.DnsIP().String(), e.dnsServer.SearchDomains())
 	case "ios":
 		e.mobileDep.NetworkChangeListener.SetInterfaceIP(e.config.WgAddr.String())
 		if e.config.WgAddr.HasIPv6() {
@@ -2096,7 +2142,7 @@ func (e *Engine) wgInterfaceCreate() (err error) {
 	return err
 }
 
-func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
+func (e *Engine) newDnsServer() (dns.Server, error) {
 	// due to tests where we are using a mocked version of the DNS server
 	if e.dnsServer != nil {
 		return e.dnsServer, nil
@@ -2108,7 +2154,7 @@ func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
 			e.ctx,
 			e.wgInterface,
 			e.mobileDep.HostDNSAddresses,
-			*dnsConfig,
+			nbdns.Config{},
 			e.mobileDep.NetworkChangeListener,
 			e.statusRecorder,
 			e.config.DisableDNS,

client/internal/engine_session_deadline_test.go

@@ -75,4 +75,14 @@ func TestApplySessionDeadline_ThreeState(t *testing.T) {
 		require.True(t, e.statusRecorder.GetSessionExpiresAt().IsZero(),
 			"invalid timestamp must clear the deadline")
 	})
+
+	t.Run("recently expired timestamp stays visible as expired", func(t *testing.T) {
+		e := newEngine()
+		expired := time.Now().Add(-5 * time.Minute).UTC().Truncate(time.Second)
+
+		e.ApplySessionDeadline(timestamppb.New(expired))
+
+		require.True(t, e.statusRecorder.GetSessionExpiresAt().Equal(expired),
+			"recently-expired deadline must stay on the recorder so consumers render it as expired")
+	})
 }

client/internal/engine_tunsettings.go

@@ -0,0 +1,20 @@
+package internal
+
+func (e *Engine) TunSettings() ([]string, []string) {
+	e.syncMsgMux.Lock()
+	routeManager := e.routeManager
+	dnsServer := e.dnsServer
+	e.syncMsgMux.Unlock()
+
+	var routes []string
+	if routeManager != nil {
+		routes = routeManager.CurrentRouteRange()
+	}
+
+	var searchDomains []string
+	if dnsServer != nil {
+		searchDomains = dnsServer.SearchDomains()
+	}
+
+	return routes, searchDomains
+}

client/internal/ipcauth/creds_stub.go

@@ -0,0 +1,31 @@
+//go:build !linux && !darwin && !freebsd && !windows
+
+package ipcauth
+
+import (
+	"errors"
+	"net"
+
+	"google.golang.org/grpc/credentials"
+)
+
+// errUnsupported is returned on platforms with no local peer-identity
+// primitive, so consumers fail closed instead of guessing an identity.
+var errUnsupported = errors.New("peer identity is not available on this platform")
+
+// NewTransportCredentials returns nil: without a peer-identity primitive the
+// daemon cannot authenticate local callers, and the caller must treat that as
+// "authorization cannot be enforced".
+func NewTransportCredentials() credentials.TransportCredentials {
+	return nil
+}
+
+// PeerIdentity always fails on this platform.
+func PeerIdentity(net.Conn) (Identity, error) {
+	return Identity{}, errUnsupported
+}
+
+// ConnIdentity always fails on this platform.
+func ConnIdentity(net.Conn) (Identity, error) {
+	return Identity{}, errUnsupported
+}