[client] fix privileged test CI failures and run the harness on macOS

The host-safe unit run dropped sudo but two privileged test groups were
never tagged, and the Docker privileged job silently never ran the suite:

- Gate the ssh/server PrivilegeDropper command-construction tests behind
  the privileged tag (they require root to target a different UID); split
  them into executor_unix_privileged_test.go.
- Tag sharedsock raw-socket tests privileged (need CAP_NET_RAW).
- Fix the Docker job command: nested single quotes around the build tags
  closed the sh -c wrapper early, dropping the go list package set and the
  privileged tag, so go test ran on the empty repo root. Use double quotes.

Make the self-hosting harness usable from a dev Mac:

- Build it on darwin as well as linux; it only drives Docker.
- Resolve the active docker context endpoint into DOCKER_HOST when the
  default /var/run/docker.sock is absent (Docker Desktop, Colima, OrbStack).
- Rename the misspelled containerGoModache constant to containerGoModCache.

.github/dependabot.yml

@@ -0,0 +1,45 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    open-pull-requests-limit: 15
+    groups:
+      actions:
+        patterns:
+          - "*"
+    ignore:
+      # git-town/action v1.3.x crashes on cyclic PR graphs (self-loop main->main
+      # fork PRs) via its topological-sort visualization. Pinned to v1.2.1 in
+      # git-town.yml; block v1.3.x until upstream tolerates cyclic edges.
+      - dependency-name: "git-town/action"
+        update-types:
+          - "version-update:semver-minor"
+          - "version-update:semver-major"
+
+  - package-ecosystem: "gomod"
+    directories:
+      - "/"
+    schedule:
+      interval: "daily"
+    open-pull-requests-limit: 15
+    groups:
+      aws-sdk:
+        patterns:
+          - "github.com/aws/aws-sdk-go-v2/*"
+      pion:
+        patterns:
+          - "github.com/pion/*"
+      gorm:
+        patterns:
+          - "gorm.io/*"
+      otel:
+        patterns:
+          - "go.opentelemetry.io/*"
+      testcontainers:
+        patterns:
+          - "github.com/testcontainers/testcontainers-go/*"
+      wireguard:
+        patterns:
+          - "golang.zx2c4.com/wireguard*"

.github/pull_request_template.md

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

.github/workflows/check-license-dependencies.yml

@@ -2,16 +2,16 @@ name: Check License Dependencies
 
 on:
   push:
-    branches: [ main ]
+    branches: [main]
     paths:
-      - 'go.mod'
-      - 'go.sum'
-      - '.github/workflows/check-license-dependencies.yml'
+      - "go.mod"
+      - "go.sum"
+      - ".github/workflows/check-license-dependencies.yml"
   pull_request:
     paths:
-      - 'go.mod'
-      - 'go.sum'
-      - '.github/workflows/check-license-dependencies.yml'
+      - "go.mod"
+      - "go.sum"
+      - ".github/workflows/check-license-dependencies.yml"
 
 jobs:
   check-internal-dependencies:
@@ -19,7 +19,10 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Check for problematic license dependencies
         run: |
@@ -56,55 +59,57 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v4
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
-    - name: Set up Go
-      uses: actions/setup-go@v5
-      with:
-        go-version-file: 'go.mod'
-        cache: true
+      - name: Set up Go
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
+        with:
+          go-version-file: "go.mod"
+          cache: true
 
-    - name: Install go-licenses
-      run: go install github.com/google/go-licenses@v1.6.0
+      - name: Install go-licenses
+        run: go install github.com/google/go-licenses@v1.6.0
 
-    - name: Check for GPL/AGPL licensed dependencies
-      run: |
-        echo "Checking for GPL/AGPL/LGPL licensed dependencies..."
-        echo ""
-
-        # Check all Go packages for copyleft licenses, excluding internal netbird packages
-        COPYLEFT_DEPS=$(go-licenses report ./... 2>/dev/null | grep -E 'GPL|AGPL|LGPL' | grep -v 'github.com/netbirdio/netbird/' || true)
-
-        if [ -n "$COPYLEFT_DEPS" ]; then
-          echo "Found copyleft licensed dependencies:"
-          echo "$COPYLEFT_DEPS"
+      - name: Check for GPL/AGPL licensed dependencies
+        run: |
+          echo "Checking for GPL/AGPL/LGPL licensed dependencies..."
           echo ""
 
-          # Filter out dependencies that are only pulled in by internal AGPL packages
-          INCOMPATIBLE=""
-          while IFS=',' read -r package url license; do
-            if echo "$license" | grep -qE 'GPL-[0-9]|AGPL-[0-9]|LGPL-[0-9]'; then
-              # Find ALL packages that import this GPL package using go list
-              IMPORTERS=$(go list -json -deps ./... 2>/dev/null | jq -r "select(.Imports[]? == \"$package\") | .ImportPath")
+          # Check all Go packages for copyleft licenses, excluding internal netbird packages
+          COPYLEFT_DEPS=$(go-licenses report ./... 2>/dev/null | grep -E 'GPL|AGPL|LGPL' | grep -v 'github.com/netbirdio/netbird/' || true)
 
-              # Check if any importer is NOT in management/signal/relay
-              BSD_IMPORTER=$(echo "$IMPORTERS" | grep -v "github.com/netbirdio/netbird/\(management\|signal\|relay\|proxy\|combined\|tools/idp-migrate\)" | head -1)
-
-              if [ -n "$BSD_IMPORTER" ]; then
-                echo "❌ $package ($license) is imported by BSD-licensed code: $BSD_IMPORTER"
-                INCOMPATIBLE="${INCOMPATIBLE}${package},${url},${license}\n"
-              else
-                echo "✓ $package ($license) is only used by internal AGPL packages - OK"
-              fi
-            fi
-          done <<< "$COPYLEFT_DEPS"
-
-          if [ -n "$INCOMPATIBLE" ]; then
+          if [ -n "$COPYLEFT_DEPS" ]; then
+            echo "Found copyleft licensed dependencies:"
+            echo "$COPYLEFT_DEPS"
             echo ""
-            echo "❌ INCOMPATIBLE licenses found that are used by BSD-licensed code:"
-            echo -e "$INCOMPATIBLE"
-            exit 1
-          fi
-        fi
 
-        echo "✅ All external license dependencies are compatible with BSD-3-Clause"
+            # Filter out dependencies that are only pulled in by internal AGPL packages
+            INCOMPATIBLE=""
+            while IFS=',' read -r package url license; do
+              if echo "$license" | grep -qE 'GPL-[0-9]|AGPL-[0-9]|LGPL-[0-9]'; then
+                # Find ALL packages that import this GPL package using go list
+                IMPORTERS=$(go list -json -deps ./... 2>/dev/null | jq -r "select(.Imports[]? == \"$package\") | .ImportPath")
+
+                # Check if any importer is NOT in management/signal/relay
+                BSD_IMPORTER=$(echo "$IMPORTERS" | grep -v "github.com/netbirdio/netbird/\(management\|signal\|relay\|proxy\|combined\|tools/idp-migrate\)" | head -1)
+
+                if [ -n "$BSD_IMPORTER" ]; then
+                  echo "❌ $package ($license) is imported by BSD-licensed code: $BSD_IMPORTER"
+                  INCOMPATIBLE="${INCOMPATIBLE}${package},${url},${license}\n"
+                else
+                  echo "✓ $package ($license) is only used by internal AGPL packages - OK"
+                fi
+              fi
+            done <<< "$COPYLEFT_DEPS"
+
+            if [ -n "$INCOMPATIBLE" ]; then
+              echo ""
+              echo "❌ INCOMPATIBLE licenses found that are used by BSD-licensed code:"
+              echo -e "$INCOMPATIBLE"
+              exit 1
+            fi
+          fi
+
+          echo "✅ All external license dependencies are compatible with BSD-3-Clause"

.github/workflows/docs-ack.yml

@@ -83,7 +83,7 @@ jobs:
 
       - name: Verify docs PR exists (and is open or merged)
         if: steps.validate.outputs.mode == 'added'
-        uses: actions/github-script@v7
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         id: verify
         with:
           pr_number: ${{ steps.extract.outputs.pr_number }}

.github/workflows/forum.yml

@@ -8,11 +8,10 @@ jobs:
   post:
     runs-on: ubuntu-latest
     steps:
-      - uses: roots/discourse-topic-github-release-action@main
+      - uses: roots/discourse-topic-github-release-action@557d74ea05b6cc0c47f555c1d5d28a89d904005b # v1.1.0
         with:
           discourse-api-key: ${{ secrets.DISCOURSE_RELEASES_API_KEY }}
           discourse-base-url: https://forum.netbird.io
           discourse-author-username: NetBird
           discourse-category: 17
-          discourse-tags:
-            releases
+          discourse-tags: releases

.github/workflows/git-town.yml

@@ -3,7 +3,7 @@ name: Git Town
 on:
   pull_request:
     branches:
-      - '**'
+      - "**"
 
 jobs:
   git-town:
@@ -15,7 +15,9 @@ jobs:
       pull-requests: write
 
     steps:
-      - uses: actions/checkout@v4
-      - uses: git-town/action@v1.2.1
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+      - uses: git-town/action@3d8b878379abb1ee393fb49865a28b4a6c2cd3b0 # v1.2.1
         with:
           skip-single-stacks: true

.github/workflows/golang-test-darwin.yml

@@ -16,16 +16,18 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
 
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: ~/go/pkg/mod
           key: macos-gotest-${{ hashFiles('**/go.sum') }}
@@ -43,5 +45,11 @@ jobs:
         run: git --no-pager diff --exit-code
 
       - name: Test
-        run: NETBIRD_STORE_ENGINE=${{ matrix.store }} CI=true go test -tags=devcert -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' -timeout 5m -p 1 $(go list ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined)
+        run: NETBIRD_STORE_ENGINE=${{ matrix.store }} CI=true go test -coverprofile=coverage.txt -tags=devcert -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' -timeout 5m -p 1 $(go list ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined)
 
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: unit,client

.github/workflows/golang-test-freebsd.yml

@@ -15,20 +15,31 @@ jobs:
     name: "Client / Unit"
     runs-on: ubuntu-22.04
     steps:
-      - uses: actions/checkout@v4
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
+      - name: Read Go version from go.mod
+        id: goversion
+        run: echo "version=$(awk '/^go / {print $2}' go.mod)" >> "$GITHUB_OUTPUT"
+
       - name: Test in FreeBSD
         id: test
-        uses: vmactions/freebsd-vm@v1
+        env:
+          GO_VERSION: ${{ steps.goversion.outputs.version }}
+        uses: vmactions/freebsd-vm@d1e65811565151536c0c894fff74f06351ed26e6 # v1.4.5
         with:
           usesh: true
           copyback: false
-          release: "14.2"
+          release: "15.0"
+          envs: "GO_VERSION"
           prepare: |
             pkg install -y curl pkgconf xorg
-            GO_TARBALL="go1.25.3.freebsd-amd64.tar.gz"
+            GO_TARBALL="go${GO_VERSION}.freebsd-amd64.tar.gz"
             GO_URL="https://go.dev/dl/$GO_TARBALL"
             curl -vLO "$GO_URL"
-            tar -C /usr/local -vxzf "$GO_TARBALL"            
+            tar -C /usr/local -vxzf "$GO_TARBALL"
 
           # -x - to print all executed commands
           # -e - to faile on first error

.github/workflows/golang-test-linux.yml

@@ -18,9 +18,11 @@ jobs:
       management: ${{ steps.filter.outputs.management }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
-      - uses: dorny/paths-filter@v3
+      - uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4.0.1
         id: filter
         with:
           filters: |
@@ -28,7 +30,7 @@ jobs:
               - 'management/**'
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -36,10 +38,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         id: cache
         with:
           path: |
@@ -113,14 +115,16 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        arch: [ '386','amd64' ]
+        arch: ["386", "amd64"]
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -128,10 +132,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -154,18 +158,29 @@ jobs:
         run: git --no-pager diff --exit-code
 
       - name: Test
-        run: CGO_ENABLED=1 GOARCH=${{ matrix.arch }} CI=true go test -tags devcert -exec 'sudo' -timeout 10m -p 1 $(go list ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined)
+        run: CGO_ENABLED=1 GOARCH=${{ matrix.arch }} CI=true go test -coverprofile=coverage.txt -tags devcert -timeout 10m -p 1 $(go list ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined)
+
+      - name: Upload coverage reports to Codecov
+        if: matrix.arch == 'amd64'
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: unit,client
+
 
   test_client_on_docker:
     name: "Client (Docker) / Unit"
-    needs: [ build-cache ]
+    needs: [build-cache]
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -177,7 +192,7 @@ jobs:
           echo "modcache_dir=$(go env GOMODCACHE)" >> $GITHUB_OUTPUT
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         id: cache-restore
         with:
           path: |
@@ -214,7 +229,7 @@ jobs:
             sh -c ' \
               apk update; apk add --no-cache \
                 ca-certificates iptables ip6tables dbus dbus-dev libpcap-dev build-base; \
-              go test -buildvcs=false -tags devcert -v -timeout 10m -p 1 $(go list -buildvcs=false ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui -e /upload-server)
+              go test -buildvcs=false -tags "devcert privileged" -v -timeout 10m -p 1 $(go list -buildvcs=false ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui -e /upload-server -e /client/testutil/privileged)
             '
 
   test_relay:
@@ -231,10 +246,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -246,10 +263,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -268,23 +285,33 @@ jobs:
         run: |
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           go test ${{ matrix.raceFlag }} \
-            -exec 'sudo' \
+            -exec 'sudo' -coverprofile=coverage.txt \
             -timeout 10m -p 1 ./relay/... ./shared/relay/...
 
+      - name: Upload coverage reports to Codecov
+        if: matrix.arch == 'amd64'
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: unit,relay
+
   test_proxy:
     name: "Proxy / Unit"
     needs: [build-cache]
     strategy:
       fail-fast: false
       matrix:
-        arch: [ '386','amd64' ]
+        arch: ["386", "amd64"]
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -298,7 +325,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -316,7 +343,15 @@ jobs:
       - name: Test
         run: |
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
-          go test -timeout 10m -p 1 ./proxy/...
+          go test -timeout 10m -p 1 -coverprofile=coverage.txt ./proxy/...
+
+      - name: Upload coverage reports to Codecov
+        if: matrix.arch == 'amd64'
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: unit,proxy
 
   test_signal:
     name: "Signal / Unit"
@@ -324,14 +359,16 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        arch: [ '386','amd64' ]
+        arch: ["386", "amd64"]
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -343,10 +380,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -365,24 +402,34 @@ jobs:
         run: |
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           go test \
-            -exec 'sudo' \
+            -exec 'sudo' -coverprofile=coverage.txt \
             -timeout 10m ./signal/... ./shared/signal/...
 
+      - name: Upload coverage reports to Codecov
+        if: matrix.arch == 'amd64'
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: unit,signal
+
   test_management:
     name: "Management / Unit"
-    needs: [ build-cache ]
+    needs: [build-cache]
     strategy:
       fail-fast: false
       matrix:
-        arch: [ 'amd64' ]
-        store: [ 'sqlite', 'postgres', 'mysql' ]
+        arch: ["amd64"]
+        store: ["sqlite", "postgres", "mysql"]
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -390,10 +437,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -410,7 +457,7 @@ jobs:
 
       - name: Login to Docker hub
         if: github.event.pull_request && github.event.pull_request.head.repo && github.event.pull_request.head.repo.full_name == '' || github.repository == github.event.pull_request.head.repo.full_name || !github.head_ref
-        uses: docker/login-action@v3
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
         with:
           username: ${{ secrets.DOCKER_USER }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -427,23 +474,31 @@ jobs:
         run: docker pull mlsmaycon/warmed-mysql:8
 
       - name: Test
-        run: |          
+        run: |
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           NETBIRD_STORE_ENGINE=${{ matrix.store }} \
             CI=true \
-          go test -tags=devcert \
+          go test -tags=devcert -coverprofile=coverage.txt \
             -exec "sudo --preserve-env=CI,NETBIRD_STORE_ENGINE" \
             -timeout 20m ./management/... ./shared/management/...
 
+      - name: Upload coverage reports to Codecov
+        if: matrix.arch == 'amd64'
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: unit,management
+
   benchmark:
     name: "Management / Benchmark"
-    needs: [ build-cache ]
+    needs: [build-cache]
     if: ${{ needs.build-cache.outputs.management == 'true' || github.event_name != 'pull_request' }}
     strategy:
       fail-fast: false
       matrix:
-        arch: [ 'amd64' ]
-        store: [ 'sqlite', 'postgres' ]
+        arch: ["amd64"]
+        store: ["sqlite", "postgres"]
     runs-on: ubuntu-22.04
     steps:
       - name: Create Docker network
@@ -474,10 +529,12 @@ jobs:
             prom/prometheus
 
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -485,10 +542,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -505,7 +562,7 @@ jobs:
 
       - name: Login to Docker hub
         if: github.event.pull_request && github.event.pull_request.head.repo && github.event.pull_request.head.repo.full_name == '' || github.repository == github.event.pull_request.head.repo.full_name || !github.head_ref
-        uses: docker/login-action@v3
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
         with:
           username: ${{ secrets.DOCKER_USER }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -529,13 +586,13 @@ jobs:
 
   api_benchmark:
     name: "Management / Benchmark (API)"
-    needs: [ build-cache ]
+    needs: [build-cache]
     if: ${{ needs.build-cache.outputs.management == 'true' || github.event_name != 'pull_request' }}
     strategy:
       fail-fast: false
       matrix:
-        arch: [ 'amd64' ]
-        store: [ 'sqlite', 'postgres' ]
+        arch: ["amd64"]
+        store: ["sqlite", "postgres"]
     runs-on: ubuntu-22.04
     steps:
       - name: Create Docker network
@@ -566,10 +623,12 @@ jobs:
             prom/prometheus
 
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -577,10 +636,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -597,7 +656,7 @@ jobs:
 
       - name: Login to Docker hub
         if: github.event.pull_request && github.event.pull_request.head.repo && github.event.pull_request.head.repo.full_name == '' || github.repository == github.event.pull_request.head.repo.full_name || !github.head_ref
-        uses: docker/login-action@v3
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
         with:
           username: ${{ secrets.DOCKER_USER }}
           password: ${{ secrets.DOCKER_TOKEN }}
@@ -623,20 +682,22 @@ jobs:
 
   api_integration_test:
     name: "Management / Integration"
-    needs: [ build-cache ]
+    needs: [build-cache]
     if: ${{ needs.build-cache.outputs.management == 'true' || github.event_name != 'pull_request' }}
     strategy:
       fail-fast: false
       matrix:
-        arch: [ 'amd64' ]
-        store: [ 'sqlite', 'postgres']
+        arch: ["amd64"]
+        store: ["sqlite", "postgres"]
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -644,10 +705,10 @@ jobs:
       - name: Get Go environment
         run: |
           echo "cache=$(go env GOCACHE)" >> $GITHUB_ENV
-          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV     
+          echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -667,6 +728,14 @@ jobs:
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           NETBIRD_STORE_ENGINE=${{ matrix.store }} \
           CI=true \
-          go test -tags=integration \
+          go test -tags=integration -coverprofile=coverage.txt \
           -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' \
           -timeout 20m ./management/server/http/...
+
+      - name: Upload coverage reports to Codecov
+        if: matrix.arch == 'amd64'
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: netbirdio/netbird
+          flags: integration,management

.github/workflows/golang-test-windows.yml

@@ -18,10 +18,12 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         id: go
         with:
           go-version-file: "go.mod"
@@ -33,7 +35,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $env:GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -44,16 +46,15 @@ jobs:
             ${{ runner.os }}-go-
 
       - name: Download wintun
-        uses: carlosperate/download-file-action@v2
         id: download-wintun
+        uses: netbirdio/shared-actions/actions/win-download-and-verify@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
         with:
-          file-url: https://pkgs.netbird.io/wintun/wintun-0.14.1.zip
-          file-name: wintun.zip
-          location: ${{ env.downloadPath }}
-          sha256: '07c256185d6ee3652e09fa55c0b673e2624b565e02c4b9091c79ca7d2f24ef51'
+          url: https://pkgs.netbird.io/wintun/wintun-0.14.1.zip
+          destination: ${{ env.downloadPath }}\wintun.zip
+          sha256: 07c256185d6ee3652e09fa55c0b673e2624b565e02c4b9091c79ca7d2f24ef51
 
       - name: Decompressing wintun files
-        run: tar -zvxf "${{ steps.download-wintun.outputs.file-path }}" -C ${{ env.downloadPath }}
+        run: tar -xvf "${{ steps.download-wintun.outputs.file-path }}" -C ${{ env.downloadPath }}
 
       - run: mv ${{ env.downloadPath }}/wintun/bin/amd64/wintun.dll 'C:\Windows\System32\'
 

.github/workflows/golangci-lint.yml

@@ -15,9 +15,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
       - name: codespell
-        uses: codespell-project/actions-codespell@v2
+        uses: codespell-project/actions-codespell@8f01853be192eb0f849a5c7d721450e7a467c579 # v2.2
         with:
           ignore_words_list: erro,clienta,hastable,iif,groupd,testin,groupe,cros,ans,deriver,te,userA,ede,additionals
           skip: go.mod,go.sum,**/proxy/web/**
@@ -38,13 +40,15 @@ jobs:
     timeout-minutes: 15
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
       - name: Check for duplicate constants
         if: matrix.os == 'ubuntu-latest'
         run: |
           ! awk '/const \(/,/)/{print $0}' management/server/activity/codes.go | grep -o '= [0-9]*' | sort | uniq -d | grep .
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -52,7 +56,7 @@ jobs:
         if: matrix.os == 'ubuntu-latest'
         run: sudo apt update && sudo apt install -y -q libgtk-3-dev libayatana-appindicator3-dev libgl1-mesa-dev xorg-dev libpcap-dev
       - name: golangci-lint
-        uses: golangci/golangci-lint-action@4afd733a84b1f43292c63897423277bb7f4313a9 # v8.0.0
+        uses: golangci/golangci-lint-action@82606bf257cbaff209d206a39f5134f0cfbfd2ee #v9.2.1
         with:
           version: latest
           skip-cache: true

.github/workflows/install-script-test.yml

@@ -22,7 +22,9 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: run install script
         env:

.github/workflows/mobile-build-validation.yml

@@ -16,23 +16,25 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: Setup Android SDK
-        uses: android-actions/setup-android@v3
+        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
         with:
           cmdline-tools-version: 8512546
       - name: Setup Java
-        uses: actions/setup-java@v4
+        uses: actions/setup-java@be666c2fcd27ec809703dec50e508c2fdc7f6654
         with:
           java-version: "11"
           distribution: "adopt"
       - name: NDK Cache
         id: ndk-cache
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: /usr/local/lib/android/sdk/ndk
           key: ndk-cache-23.1.7779620
@@ -52,9 +54,11 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: install gomobile

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

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Validate PR title prefix
-        uses: actions/github-script@v7
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const title = context.payload.pull_request.title;

.github/workflows/proto-version-check.yml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Check for proto tool version changes
-        uses: actions/github-script@v7
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         with:
           script: |
             const files = await github.paginate(github.rest.pulls.listFiles, {
@@ -20,34 +20,83 @@ jobs:
               per_page: 100,
             });
 
-            const pbFiles = files.filter(f => f.filename.endsWith('.pb.go'));
-            const missingPatch = pbFiles.filter(f => !f.patch).map(f => f.filename);
-            if (missingPatch.length > 0) {
-              core.setFailed(
-                `Cannot inspect patch data for:\n` +
-                missingPatch.map(f => `- ${f}`).join('\n') +
-                `\nThis can happen with very large PRs. Verify proto versions manually.`
-              );
+            // Cover renamed .pb.go files in addition to plain edits.
+            // Renamed entries land under the new path with previous_filename
+            // pointing at the base-side name, so we read the base content
+            // from the old path when present.
+            const changedPbFiles = files
+              .filter(f => (f.status === 'modified' || f.status === 'renamed')
+                && f.filename.endsWith('.pb.go'))
+              .map(f => ({
+                headPath: f.filename,
+                basePath: f.previous_filename || f.filename,
+              }));
+            if (changedPbFiles.length === 0) {
+              console.log('No modified or renamed .pb.go files to check');
               return;
             }
-            const versionPattern = /^[+-]\s*\/\/\s+protoc(?:-gen-go)?\s+v[\d.]+/;
-            const violations = [];
 
-            for (const file of pbFiles) {
-              const changed = file.patch
-                .split('\n')
-                .filter(line => versionPattern.test(line));
-              if (changed.length > 0) {
+            // Matches the generator version headers protoc writes at the top
+            // of generated files:
+            //   //   protoc           v3.21.12
+            //   //   protoc-gen-go    v1.26.0
+            //   // - protoc-gen-go-grpc v1.6.1   (grpc files prefix with "- ")
+            // The optional "- " prefix and the optional -gen-go / -gen-go-grpc
+            // suffixes keep the *_grpc.pb.go headers in scope.
+            const versionPattern = /^\s*\/\/\s+(?:-\s+)?protoc(?:-gen-go(?:-grpc)?)?\s+v[\d.]+/;
+            const baseSha = context.payload.pull_request.base.sha;
+            const headSha = context.payload.pull_request.head.sha;
+
+            async function getVersionHeader(path, ref) {
+              try {
+                const res = await github.rest.repos.getContent({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  path,
+                  ref,
+                });
+                if (!res.data.content) {
+                  return { ok: false, reason: 'no inline content (file too large)' };
+                }
+                const content = Buffer.from(res.data.content, 'base64').toString('utf8');
+                const lines = content
+                  .split('\n')
+                  .slice(0, 20)
+                  .filter(line => versionPattern.test(line));
+                return { ok: true, lines };
+              } catch (e) {
+                return { ok: false, reason: e.message };
+              }
+            }
+
+            const violations = [];
+            for (const file of changedPbFiles) {
+              const [base, head] = await Promise.all([
+                getVersionHeader(file.basePath, baseSha),
+                getVersionHeader(file.headPath, headSha),
+              ]);
+              if (!base.ok || !head.ok) {
+                core.warning(
+                  `Skipping ${file.headPath}: base=${base.ok ? 'ok' : base.reason}, head=${head.ok ? 'ok' : head.reason}`
+                );
+                continue;
+              }
+              if (base.lines.join('\n') !== head.lines.join('\n')) {
                 violations.push({
-                  file: file.filename,
-                  lines: changed,
+                  file: file.basePath === file.headPath
+                    ? file.headPath
+                    : `${file.basePath} → ${file.headPath}`,
+                  base: base.lines,
+                  head: head.lines,
                 });
               }
             }
 
             if (violations.length > 0) {
               const details = violations.map(v =>
-                `${v.file}:\n${v.lines.map(l => '  ' + l).join('\n')}`
+                `${v.file}:\n` +
+                `  base:\n${v.base.map(l => '    ' + l).join('\n') || '    (none)'}\n` +
+                `  head:\n${v.head.map(l => '    ' + l).join('\n') || '    (none)'}`
               ).join('\n\n');
 
               core.setFailed(

.github/workflows/release.yml

@@ -9,7 +9,7 @@ on:
   pull_request:
 
 env:
-  SIGN_PIPE_VER: "v0.1.4"
+  SIGN_PIPE_VER: "v0.1.5"
   GORELEASER_VER: "v2.14.3"
   PRODUCT_NAME: "NetBird"
   COPYRIGHT: "NetBird GmbH"
@@ -24,13 +24,15 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Generate FreeBSD port diff
-        run: bash release_files/freebsd-port-diff.sh
+        run: bash -x release_files/freebsd-port-diff.sh
 
       - name: Generate FreeBSD port issue body
-        run: bash release_files/freebsd-port-issue-body.sh
+        run: bash -x release_files/freebsd-port-issue-body.sh
 
       - name: Check if diff was generated
         id: check_diff
@@ -51,19 +53,26 @@ jobs:
           echo "Generated files for version: $VERSION"
           cat netbird-*.diff
 
+      - name: Read Go version from go.mod
+        id: goversion
+        run: echo "version=$(awk '/^go / {print $2}' go.mod)" >> "$GITHUB_OUTPUT"
+
       - name: Test FreeBSD port
         if: steps.check_diff.outputs.diff_exists == 'true'
-        uses: vmactions/freebsd-vm@v1
+        env:
+          GO_VERSION: ${{ steps.goversion.outputs.version }}
+        uses: vmactions/freebsd-vm@d1e65811565151536c0c894fff74f06351ed26e6 # v1.4.5
         with:
           usesh: true
           copyback: false
           release: "15.0"
+          envs: "GO_VERSION"
           prepare: |
             # Install required packages
-            pkg install -y git curl portlint go
+            pkg install -y git curl portlint
 
             # Install Go for building
-            GO_TARBALL="go1.25.5.freebsd-amd64.tar.gz"
+            GO_TARBALL="go${GO_VERSION}.freebsd-amd64.tar.gz"
             GO_URL="https://go.dev/dl/$GO_TARBALL"
             curl -LO "$GO_URL"
             tar -C /usr/local -xzf "$GO_TARBALL"
@@ -93,19 +102,19 @@ jobs:
 
             # Show patched Makefile
             version=$(cat security/netbird/Makefile | grep -E '^DISTVERSION=' | awk '{print $NF}')
-            
+
             cd /usr/ports/security/netbird
             export BATCH=yes
             make package
             pkg add ./work/pkg/netbird-*.pkg
-            
+
             netbird version | grep "$version"
 
             echo "FreeBSD port test completed successfully!"
 
       - name: Upload FreeBSD port files
         if: steps.check_diff.outputs.diff_exists == 'true'
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: freebsd-port-files
           path: |
@@ -124,26 +133,25 @@ jobs:
     env:
       flags: ""
     steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0 # It is required for GoReleaser to work properly
+          persist-credentials: false
+
       - name: Parse semver string
         id: semver_parser
-        uses: booxmedialtd/ws-action-parse-semver@v1
-        with:
-          input_string: ${{ (startsWith(github.ref, 'refs/tags/v') && github.ref) || 'refs/tags/v0.0.0' }}
-          version_extractor_regex: '\/v(.*)$'
+        uses: netbirdio/shared-actions/actions/parse-semver@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
 
       - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
         run: echo "flags=--snapshot" >> $GITHUB_ENV
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0 # It is required for GoReleaser to work properly
       - name: Set up Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ~/go/pkg/mod
@@ -156,18 +164,18 @@ jobs:
       - name: check git status
         run: git --no-pager diff --exit-code
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v2
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a #v4.0.0
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd #v4.0.0
       - name: Login to Docker hub
         if: github.event_name != 'pull_request'
-        uses: docker/login-action@v1
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
         with:
           username: ${{ secrets.DOCKER_USER }}
           password: ${{ secrets.DOCKER_TOKEN }}
       - name: Log in to the GitHub container registry
         if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository
-        uses: docker/login-action@v3
+        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
         with:
           registry: ghcr.io
           username: ${{ github.actor }}
@@ -191,7 +199,7 @@ jobs:
         run: goversioninfo -arm -64 -icon client/ui/assets/netbird.ico -manifest client/manifest.xml -product-name ${{ env.PRODUCT_NAME }} -copyright "${{ env.COPYRIGHT }}" -ver-major ${{ steps.semver_parser.outputs.major }} -ver-minor ${{ steps.semver_parser.outputs.minor }} -ver-patch ${{ steps.semver_parser.outputs.patch }} -ver-build 0 -file-version ${{ steps.semver_parser.outputs.fullversion }}.0 -product-version ${{ steps.semver_parser.outputs.fullversion }}.0 -o client/resources_windows_arm64.syso
       - name: Run GoReleaser
         id: goreleaser
-        uses: goreleaser/goreleaser-action@v4
+        uses: goreleaser/goreleaser-action@4c6ab561adb47e50c45ef534e2155934e91c40c1 # v7.2.0
         with:
           version: ${{ env.GORELEASER_VER }}
           args: release --clean ${{ env.flags }}
@@ -282,28 +290,28 @@ jobs:
           } >> "$GITHUB_OUTPUT"
       - name: upload non tags for debug purposes
         id: upload_release
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: release
           path: dist/
           retention-days: 7
       - name: upload linux packages
         id: upload_linux_packages
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: linux-packages
           path: dist/netbird_linux**
           retention-days: 7
       - name: upload windows packages
         id: upload_windows_packages
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: windows-packages
           path: dist/netbird_windows**
           retention-days: 7
       - name: upload macos packages
         id: upload_macos_packages
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: macos-packages
           path: dist/netbird_darwin**
@@ -314,27 +322,26 @@ jobs:
     outputs:
       release_ui_artifact_url: ${{ steps.upload_release_ui.outputs.artifact-url }}
     steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          fetch-depth: 0 # It is required for GoReleaser to work properly
+          persist-credentials: false
+
       - name: Parse semver string
         id: semver_parser
-        uses: booxmedialtd/ws-action-parse-semver@v1
-        with:
-          input_string: ${{ (startsWith(github.ref, 'refs/tags/v') && github.ref) || 'refs/tags/v0.0.0' }}
-          version_extractor_regex: '\/v(.*)$'
+        uses: netbirdio/shared-actions/actions/parse-semver@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
 
       - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
         run: echo "flags=--snapshot" >> $GITHUB_ENV
-      - name: Checkout
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0 # It is required for GoReleaser to work properly
 
       - name: Set up Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ~/go/pkg/mod
@@ -375,7 +382,7 @@ jobs:
         run: goversioninfo -arm -64 -icon client/ui/assets/netbird.ico -manifest client/ui/manifest.xml -product-name ${{ env.PRODUCT_NAME }}-"UI" -copyright "${{ env.COPYRIGHT }}" -ver-major ${{ steps.semver_parser.outputs.major }} -ver-minor ${{ steps.semver_parser.outputs.minor }} -ver-patch ${{ steps.semver_parser.outputs.patch }} -ver-build 0 -file-version ${{ steps.semver_parser.outputs.fullversion }}.0 -product-version ${{ steps.semver_parser.outputs.fullversion }}.0 -o client/ui/resources_windows_arm64.syso
 
       - name: Run GoReleaser
-        uses: goreleaser/goreleaser-action@v4
+        uses: goreleaser/goreleaser-action@4c6ab561adb47e50c45ef534e2155934e91c40c1 # v7.2.0
         with:
           version: ${{ env.GORELEASER_VER }}
           args: release --config .goreleaser_ui.yaml --clean ${{ env.flags }}
@@ -404,7 +411,7 @@ jobs:
         run: rm -f /tmp/gpg-rpm-signing-key.asc
       - name: upload non tags for debug purposes
         id: upload_release_ui
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: release-ui
           path: dist/
@@ -418,16 +425,17 @@ jobs:
       - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
         run: echo "flags=--snapshot" >> $GITHUB_ENV
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0 # It is required for GoReleaser to work properly
+          persist-credentials: false
       - name: Set up Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ~/go/pkg/mod
@@ -441,7 +449,7 @@ jobs:
         run: git --no-pager diff --exit-code
       - name: Run GoReleaser
         id: goreleaser
-        uses: goreleaser/goreleaser-action@v4
+        uses: goreleaser/goreleaser-action@4c6ab561adb47e50c45ef534e2155934e91c40c1 # v7.2.0
         with:
           version: ${{ env.GORELEASER_VER }}
           args: release --config .goreleaser_ui_darwin.yaml --clean ${{ env.flags }}
@@ -449,7 +457,7 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       - name: upload non tags for debug purposes
         id: upload_release_ui_darwin
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: release-ui-darwin
           path: dist/
@@ -474,27 +482,26 @@ jobs:
       PackageWorkdir: netbird_windows_${{ matrix.arch }}
       downloadPath: '${{ github.workspace }}\temp'
     steps:
+      - name: Checkout
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
+
       - name: Parse semver string
         id: semver_parser
-        uses: booxmedialtd/ws-action-parse-semver@v1
-        with:
-          input_string: ${{ (startsWith(github.ref, 'refs/tags/v') && github.ref) || 'refs/tags/v0.0.0' }}
-          version_extractor_regex: '\/v(.*)$'
-
-      - name: Checkout
-        uses: actions/checkout@v4
+        uses: netbirdio/shared-actions/actions/parse-semver@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
 
       - name: Add 7-Zip to PATH
         run: echo "C:\Program Files\7-Zip" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
 
       - name: Download release artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.1
         with:
           name: release
           path: release
 
       - name: Download UI release artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.1
         with:
           name: release-ui
           path: release-ui
@@ -514,29 +521,27 @@ jobs:
           Get-ChildItem $workdir
 
       - name: Download wintun
-        uses: carlosperate/download-file-action@v2
         id: download-wintun
+        uses: netbirdio/shared-actions/actions/win-download-and-verify@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
         with:
-          file-url: https://pkgs.netbird.io/wintun/wintun-0.14.1.zip
-          file-name: wintun.zip
-          location: ${{ env.downloadPath }}
-          sha256: '07c256185d6ee3652e09fa55c0b673e2624b565e02c4b9091c79ca7d2f24ef51'
+          url: https://pkgs.netbird.io/wintun/wintun-0.14.1.zip
+          destination: ${{ env.downloadPath }}\wintun.zip
+          sha256: 07c256185d6ee3652e09fa55c0b673e2624b565e02c4b9091c79ca7d2f24ef51
 
       - name: Decompress wintun files
-        run: tar -zvxf "${{ steps.download-wintun.outputs.file-path }}" -C ${{ env.downloadPath }}
+        run: tar -xvf "${{ env.downloadPath }}\wintun.zip" -C ${{ env.downloadPath }}
 
       - name: Move wintun.dll into dist
         run: mv ${{ env.downloadPath }}\wintun\bin\${{ matrix.wintun_arch }}\wintun.dll ${{ github.workspace }}\dist\${{ env.PackageWorkdir }}\
 
       - name: Download Mesa3D (amd64 only)
-        uses: carlosperate/download-file-action@v2
         id: download-mesa3d
         if: matrix.arch == 'amd64'
+        uses: netbirdio/shared-actions/actions/win-download-and-verify@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
         with:
-          file-url: https://downloads.fdossena.com/Projects/Mesa3D/Builds/MesaForWindows-x64-20.1.8.7z
-          file-name: mesa3d.7z
-          location: ${{ env.downloadPath }}
-          sha256: '71c7cb64ec229a1d6b8d62fa08e1889ed2bd17c0eeede8689daf0f25cb31d6b9'
+          url: https://pkgs.netbird.io/mesa3d/MesaForWindows-x64-20.1.8.7z
+          destination: ${{ env.downloadPath }}\mesa3d.7z
+          sha256: 71c7cb64ec229a1d6b8d62fa08e1889ed2bd17c0eeede8689daf0f25cb31d6b9
 
       - name: Extract Mesa3D driver (amd64 only)
         if: matrix.arch == 'amd64'
@@ -547,35 +552,38 @@ jobs:
         run: mv ${{ env.downloadPath }}\opengl32.dll ${{ github.workspace }}\dist\${{ env.PackageWorkdir }}\
 
       - name: Download EnVar plugin for NSIS
-        uses: carlosperate/download-file-action@v2
+        uses: netbirdio/shared-actions/actions/win-download-and-verify@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
         with:
-          file-url: https://nsis.sourceforge.io/mediawiki/images/7/7f/EnVar_plugin.zip
-          file-name: envar_plugin.zip
-          location: ${{ github.workspace }}
+          url: https://pkgs.netbird.io/nsis/EnVar_plugin.zip
+          destination: ${{ github.workspace }}\envar_plugin.zip
+          sha256: e9aa92de351345ed82795251d838f1ae9041ba35af9d381a5780c7843b01f56a
 
       - name: Extract EnVar plugin
         run: 7z x -o"${{ github.workspace }}/NSIS_Plugins" "${{ github.workspace }}/envar_plugin.zip"
 
       - name: Download ShellExecAsUser plugin for NSIS (amd64 only)
-        uses: carlosperate/download-file-action@v2
         if: matrix.arch == 'amd64'
+        uses: netbirdio/shared-actions/actions/win-download-and-verify@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
         with:
-          file-url: https://nsis.sourceforge.io/mediawiki/images/6/68/ShellExecAsUser_amd64-Unicode.7z
-          file-name: ShellExecAsUser_amd64-Unicode.7z
-          location: ${{ github.workspace }}
+          url: https://pkgs.netbird.io/nsis/ShellExecAsUser_amd64-Unicode.7z
+          destination: ${{ github.workspace }}\ShellExecAsUser_amd64-Unicode.7z
+          sha256: 0a55ea25c7330a92cec028eda8afcaf1b1a7092e0dfb77c21c8f654564b4ff9d
 
       - name: Extract ShellExecAsUser plugin (amd64 only)
         if: matrix.arch == 'amd64'
         run: 7z x -o"${{ github.workspace }}/NSIS_Plugins" "${{ github.workspace }}/ShellExecAsUser_amd64-Unicode.7z"
 
       - name: Build NSIS installer
-        uses: joncloud/makensis-action@v3.3
-        with:
-          additional-plugin-paths: ${{ github.workspace }}/NSIS_Plugins/Plugins
-          script-file: client/installer.nsis
-          arguments: "/V4 /DARCH=${{ matrix.arch }}"
+        shell: pwsh
         env:
           APPVER: ${{ steps.semver_parser.outputs.major }}.${{ steps.semver_parser.outputs.minor }}.${{ steps.semver_parser.outputs.patch }}.${{ github.run_id }}
+        run: |
+          $nsisPluginDir = "C:\Program Files (x86)\NSIS\Plugins\x86-unicode"
+          $srcPlugins    = "${{ github.workspace }}\NSIS_Plugins\Plugins"
+          Get-ChildItem -Path $srcPlugins -Recurse -Filter *.dll |
+            Copy-Item -Destination $nsisPluginDir -Force
+          & "C:\Program Files (x86)\NSIS\makensis.exe" /V4 "/DARCH=${{ matrix.arch }}" client\installer.nsis
+          if ($LASTEXITCODE -ne 0) { throw "makensis failed with exit code $LASTEXITCODE" }
 
       - name: Rename NSIS installer
         run: mv netbird-installer.exe netbird_installer_test_windows_${{ matrix.arch }}.exe
@@ -592,7 +600,7 @@ jobs:
 
       - name: Upload installer artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
         with:
           name: windows-installer-test-${{ matrix.arch }}
           path: |
@@ -611,7 +619,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Create or update PR comment
-        uses: actions/github-script@v7
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
         env:
           RELEASE_RESULT: ${{ needs.release.result }}
           RELEASE_UI_RESULT: ${{ needs.release_ui.result }}
@@ -703,7 +711,7 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/')
     steps:
       - name: Trigger binaries sign pipelines
-        uses: benc-uk/workflow-dispatch@v1
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
         with:
           workflow: Sign bin and installer
           repo: netbirdio/sign-pipelines

.github/workflows/sync-main.yml

@@ -14,9 +14,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Trigger main branch sync
-        uses: benc-uk/workflow-dispatch@v1
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
         with:
           workflow: sync-main.yml
           repo: ${{ secrets.UPSTREAM_REPO }}
           token: ${{ secrets.NC_GITHUB_TOKEN }}
-          inputs: '{ "sha": "${{ github.sha }}" }'
+          inputs: '{ "sha": "${{ github.sha }}" }'

.github/workflows/sync-tag.yml

@@ -3,7 +3,7 @@ name: sync tag
 on:
   push:
     tags:
-      - 'v*'
+      - "v*"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Trigger release tag sync
-        uses: benc-uk/workflow-dispatch@v1
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
         with:
           workflow: sync-tag.yml
           ref: main
@@ -29,7 +29,7 @@ jobs:
     if: github.event.created && !github.event.deleted && startsWith(github.ref, 'refs/tags/v') && !contains(github.ref_name, '-')
     steps:
       - name: Trigger android-client submodule bump
-        uses: benc-uk/workflow-dispatch@7a027648b88c2413826b6ddd6c76114894dc5ec4 # v1.3.1
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
         with:
           workflow: bump-netbird.yml
           ref: main
@@ -42,10 +42,10 @@ jobs:
     if: github.event.created && !github.event.deleted && startsWith(github.ref, 'refs/tags/v') && !contains(github.ref_name, '-')
     steps:
       - name: Trigger ios-client submodule bump
-        uses: benc-uk/workflow-dispatch@7a027648b88c2413826b6ddd6c76114894dc5ec4 # v1.3.1
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
         with:
           workflow: bump-netbird.yml
           ref: main
           repo: netbirdio/ios-client
           token: ${{ secrets.NC_GITHUB_TOKEN }}
-          inputs: '{ "tag": "${{ github.ref_name }}" }'
+          inputs: '{ "tag": "${{ github.ref_name }}" }'

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

@@ -6,10 +6,10 @@ on:
       - main
   pull_request:
     paths:
-      - 'infrastructure_files/**'
-      - '.github/workflows/test-infrastructure-files.yml'
-      - 'management/cmd/**'
-      - 'signal/cmd/**'
+      - "infrastructure_files/**"
+      - ".github/workflows/test-infrastructure-files.yml"
+      - "management/cmd/**"
+      - "signal/cmd/**"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
@@ -20,7 +20,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        store: [ 'sqlite', 'postgres', 'mysql' ]
+        store: ["sqlite", "postgres", "mysql"]
     services:
       postgres:
         image: ${{ (matrix.store == 'postgres') && 'postgres' || '' }}
@@ -68,15 +68,17 @@ jobs:
         run: sudo apt-get install -y curl
 
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
 
       - name: Cache Go modules
-        uses: actions/cache@v4
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: ~/go/pkg/mod
           key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
@@ -139,8 +141,8 @@ jobs:
           CI_NETBIRD_IDP_MGMT_CLIENT_SECRET: testing.client.secret
           CI_NETBIRD_SIGNAL_PORT: 12345
           CI_NETBIRD_STORE_CONFIG_ENGINE: ${{ matrix.store }}
-          NETBIRD_STORE_ENGINE_POSTGRES_DSN: '${{ env.NETBIRD_STORE_ENGINE_POSTGRES_DSN }}$'
-          NETBIRD_STORE_ENGINE_MYSQL_DSN: '${{ env.NETBIRD_STORE_ENGINE_MYSQL_DSN }}$'
+          NETBIRD_STORE_ENGINE_POSTGRES_DSN: "${{ env.NETBIRD_STORE_ENGINE_POSTGRES_DSN }}$"
+          NETBIRD_STORE_ENGINE_MYSQL_DSN: "${{ env.NETBIRD_STORE_ENGINE_MYSQL_DSN }}$"
           CI_NETBIRD_MGMT_IDP_SIGNKEY_REFRESH: false
           CI_NETBIRD_TURN_EXTERNAL_IP: "1.2.3.4"
           CI_NETBIRD_MGMT_DISABLE_DEFAULT_POLICY: false
@@ -254,7 +256,9 @@ jobs:
         run: sudo apt-get install -y jq
 
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
 
       - name: run script with Zitadel PostgreSQL
         run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh

.github/workflows/update-docs.yml

@@ -3,9 +3,9 @@ name: update docs
 on:
   push:
     tags:
-      - 'v*'
+      - "v*"
     paths:
-      - 'shared/management/http/api/openapi.yml'
+      - "shared/management/http/api/openapi.yml"
 
 jobs:
   trigger_docs_api_update:
@@ -13,10 +13,10 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/')
     steps:
       - name: Trigger API pages generation
-        uses: benc-uk/workflow-dispatch@v1
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
         with:
           workflow: generate api pages
           repo: netbirdio/docs
           ref: "refs/heads/main"
           token: ${{ secrets.SIGN_GITHUB_TOKEN }}
-          inputs: '{ "tag": "${{ github.ref }}" }'
+          inputs: '{ "tag": "${{ github.ref }}" }'

.github/workflows/wasm-build-validation.yml

@@ -19,15 +19,17 @@ jobs:
       GOARCH: wasm
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: Install dependencies
         run: sudo apt update && sudo apt install -y -q libgtk-3-dev libayatana-appindicator3-dev libgl1-mesa-dev xorg-dev libpcap-dev
       - name: Install golangci-lint
-        uses: golangci/golangci-lint-action@4afd733a84b1f43292c63897423277bb7f4313a9 # v8.0.0
+        uses: golangci/golangci-lint-action@82606bf257cbaff209d206a39f5134f0cfbfd2ee #v9.2.1
         with:
           version: latest
           install-mode: binary
@@ -42,9 +44,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        with:
+          persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@v5
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: Build Wasm client
@@ -61,8 +65,7 @@ jobs:
 
           echo "Size: ${SIZE} bytes (${SIZE_MB} MB)"
 
-          if [ ${SIZE} -gt 58720256 ]; then
-            echo "Wasm binary size (${SIZE_MB}MB) exceeds 56MB limit!"
+          if [ ${SIZE} -gt 62914560 ]; then
+            echo "Wasm binary size (${SIZE_MB}MB) exceeds 60MB limit!"
             exit 1
           fi
-

CONTRIBUTING.md

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

Makefile

@@ -1,4 +1,4 @@
-.PHONY: lint lint-all lint-install setup-hooks
+.PHONY: lint lint-all lint-install setup-hooks test-unit test-privileged
 GOLANGCI_LINT := $(shell pwd)/bin/golangci-lint
 
 # Install golangci-lint locally if needed
@@ -25,3 +25,15 @@ setup-hooks:
 	@git config core.hooksPath .githooks
 	@chmod +x .githooks/pre-push
 	@echo "✅ Git hooks configured! Pre-push will now run 'make lint'"
+
+# Host-safe unit tests: excludes the privileged-tagged tests (root / system-mutating).
+# Runs as a normal user with no sudo and leaves host networking untouched.
+test-unit:
+	@go test -tags devcert -timeout 10m ./...
+
+# Privileged suite: runs the `privileged`-tagged tests inside a --privileged
+# --cap-add=NET_ADMIN container via the ory/dockertest harness. Requires Docker.
+# Narrow the run with env vars, e.g.:
+#   PRIV_RUN=TestNftablesManager PRIV_PKGS=./client/firewall/nftables/... make test-privileged
+test-privileged:
+	@go test -tags 'devcert privileged' -timeout 30m -run TestRunPrivilegedSuiteInDocker -v ./client/testutil/privileged/...

README.md

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

client/cmd/debug.go

@@ -3,12 +3,14 @@ package cmd
 import (
 	"context"
 	"fmt"
+	"os/user"
 	"strings"
 	"time"
 
 	log "github.com/sirupsen/logrus"
 	"github.com/spf13/cobra"
 	"google.golang.org/grpc/status"
+	"google.golang.org/protobuf/encoding/protojson"
 	"google.golang.org/protobuf/types/known/durationpb"
 
 	"github.com/netbirdio/netbird/client/internal"
@@ -19,6 +21,7 @@ import (
 	"github.com/netbirdio/netbird/client/server"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/upload-server/types"
+	"github.com/netbirdio/netbird/version"
 )
 
 const errCloseConnection = "Failed to close connection: %v"
@@ -84,6 +87,73 @@ var persistenceCmd = &cobra.Command{
 	RunE:    setSyncResponsePersistence,
 }
 
+var debugConfigCmd = &cobra.Command{
+	Use:     "config",
+	Example: "  netbird debug config",
+	Short:   "Dump the effective configuration",
+	Long:    "Prints the daemon's resolved configuration (after applying defaults, file, env, CLI input, and MDM policy overrides) as JSON. Includes the list of MDM-managed fields.",
+	RunE:    debugConfigDump,
+}
+
+// debugConfigDump implements `netbird debug config`. It resolves the
+// active profile, queries the daemon for the effective configuration
+// via GetConfig, and prints the resulting GetConfigResponse as JSON
+// (via protojson with EmitUnpopulated=true so the output is stable
+// across runs and includes zero-valued fields).
+//
+// Useful for verifying MDM enforcement end-to-end: the response's
+// mDMManagedFields array is the single source of truth for "which
+// fields is the daemon currently enforcing from the MDM source", and
+// every config field side-by-side with that list confirms the merge
+// result. Secrets in the response (e.g. PreSharedKey) are already
+// redacted by the daemon-side handler.
+func debugConfigDump(cmd *cobra.Command, _ []string) error {
+	pm := profilemanager.NewProfileManager()
+	activeProf, err := pm.GetActiveProfile()
+	if err != nil {
+		return fmt.Errorf("get active profile: %v", err)
+	}
+	currUser, err := user.Current()
+	if err != nil {
+		return fmt.Errorf("get current user: %v", err)
+	}
+
+	conn, err := getClient(cmd)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if err := conn.Close(); err != nil {
+			log.Errorf(errCloseConnection, err)
+		}
+	}()
+
+	client := proto.NewDaemonServiceClient(conn)
+	resp, err := client.GetConfig(cmd.Context(), &proto.GetConfigRequest{
+		ProfileName: activeProf.Name,
+		Username:    currUser.Username,
+	})
+	if err != nil {
+		return fmt.Errorf("failed to get config: %v", status.Convert(err).Message())
+	}
+
+	// Use protojson so well-known fields render correctly; emit defaults so
+	// the operator sees every field even when zero/empty.
+	m := protojson.MarshalOptions{Multiline: true, Indent: "  ", EmitUnpopulated: true}
+	out, err := m.Marshal(resp)
+	if err != nil {
+		return fmt.Errorf("marshal config: %w", err)
+	}
+	cmd.Println(string(out))
+	return nil
+}
+
+// debugBundle requests the daemon to create a debug bundle and prints
+// the resulting local file path and, if uploaded, the uploaded file
+// key. It uses the package flags (anonymize, system info, log file
+// count, CLI version, optional upload URL) to configure the bundle
+// request. Returns an error if the RPC fails or if the daemon reports
+// an upload failure reason.
 func debugBundle(cmd *cobra.Command, _ []string) error {
 	conn, err := getClient(cmd)
 	if err != nil {
@@ -100,6 +170,7 @@ func debugBundle(cmd *cobra.Command, _ []string) error {
 		Anonymize:    anonymizeFlag,
 		SystemInfo:   systemInfoFlag,
 		LogFileCount: logFileCount,
+		CliVersion:   version.NetbirdVersion(),
 	}
 	if uploadBundleFlag {
 		request.UploadURL = uploadBundleURLFlag
@@ -298,6 +369,7 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 		Anonymize:    anonymizeFlag,
 		SystemInfo:   systemInfoFlag,
 		LogFileCount: logFileCount,
+		CliVersion:   version.NetbirdVersion(),
 	}
 	if uploadBundleFlag {
 		request.UploadURL = uploadBundleURLFlag
@@ -432,6 +504,7 @@ func generateDebugBundle(config *profilemanager.Config, recorder *peer.Status, c
 			SyncResponse:   syncResponse,
 			LogPath:        logFilePath,
 			CPUProfile:     nil,
+			DaemonVersion:  version.NetbirdVersion(), // acting as daemon
 		},
 		debug.BundleConfig{
 			IncludeSystemInfo: true,

client/cmd/kubernetes.go

@@ -0,0 +1,301 @@
+package cmd
+
+import (
+	"context"
+	"crypto/tls"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"net/url"
+	"os"
+	"path/filepath"
+	"slices"
+	"strings"
+
+	"github.com/goccy/go-yaml"
+	log "github.com/sirupsen/logrus"
+	"github.com/spf13/cobra"
+
+	"github.com/netbirdio/netbird/client/proto"
+)
+
+const (
+	KubernetesDNSSuffix = "netbird-kubeapi-proxy"
+)
+
+var kubernetesCmd = &cobra.Command{
+	Use:   "kubernetes",
+	Short: "Kubernetes cluster commands.",
+	Long:  "Kubernetes cluster commands.",
+}
+
+var kubernetesListCmd = &cobra.Command{
+	Use:   "list",
+	RunE:  kubernetesList,
+	Short: "List Kubernetes clusters.",
+	Long:  "List Kubernetes clusters by discovering NetBird peers running netbird-kubeapi-proxy.",
+}
+
+var kubernetesWriteKubeconfigCmd = &cobra.Command{
+	Use:   "write-kubeconfig",
+	RunE:  kubernetesWriteKubeconfig,
+	Args:  cobra.ExactArgs(1),
+	Short: "Write kubeconfig for a Kubernetes cluster.",
+	Long:  "Updates kubeconfig in place to allow token-less access to the Kubernetes cluster through NetBird.",
+}
+
+func init() {
+	kubernetesWriteKubeconfigCmd.Flags().String("kubeconfig", "", "path to kubeconfig file")
+}
+
+func kubernetesList(cmd *cobra.Command, _ []string) error {
+	conn, err := getClient(cmd)
+	if err != nil {
+		return err
+	}
+	defer conn.Close()
+	client := proto.NewDaemonServiceClient(conn)
+	statusResp, err := client.Status(cmd.Context(), &proto.StatusRequest{GetFullPeerStatus: true})
+	if err != nil {
+		return err
+	}
+
+	kcs, err := getKubernetesClusters(cmd.Context(), statusResp.FullStatus.Peers, "")
+	if err != nil {
+		return err
+	}
+	if len(kcs) == 0 {
+		cmd.Println("No Kubernetes clusters available.")
+		return nil
+	}
+	cmd.Println("Available Kubernetes clusters:")
+	for _, k := range kcs {
+		cmd.Printf("\n  - Name: %s\n    FQDN: %s\n    Version: %s\n", k.name, k.url.Host, k.version)
+	}
+	return nil
+}
+
+func kubernetesWriteKubeconfig(cmd *cobra.Command, args []string) error {
+	kubeconfigPath, err := resolveKubeconfigPath(cmd)
+	if err != nil {
+		return err
+	}
+
+	conn, err := getClient(cmd)
+	if err != nil {
+		return err
+	}
+	defer conn.Close()
+	client := proto.NewDaemonServiceClient(conn)
+	statusResp, err := client.Status(cmd.Context(), &proto.StatusRequest{GetFullPeerStatus: true})
+	if err != nil {
+		return err
+	}
+
+	clusterName := args[0]
+	kcs, err := getKubernetesClusters(cmd.Context(), statusResp.FullStatus.Peers, clusterName)
+	if err != nil {
+		return err
+	}
+	if len(kcs) == 0 {
+		return fmt.Errorf("kubernetes cluster named %s not found", clusterName)
+	}
+	if len(kcs) > 1 {
+		return fmt.Errorf("too many Kubernetes clusters returned")
+	}
+	err = writeKubeconfig(kubeconfigPath, kcs[0])
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+type kubernetesCluster struct {
+	name    string
+	url     *url.URL
+	version string
+}
+
+func getKubernetesClusters(ctx context.Context, peers []*proto.PeerState, nameFilter string) ([]kubernetesCluster, error) {
+	transport := http.DefaultTransport.(*http.Transport).Clone()
+	transport.TLSClientConfig = &tls.Config{
+		InsecureSkipVerify: true,
+	}
+	httpClient := &http.Client{
+		Transport: transport,
+	}
+	resolver := net.Resolver{
+		// Required so both DNS records are returned.
+		// https://github.com/golang/go/issues/17093
+		PreferGo: true,
+	}
+
+	kcs := []kubernetesCluster{}
+	attempted := map[string]struct{}{}
+	for _, peer := range peers {
+		fqdns, err := resolver.LookupAddr(ctx, peer.IP)
+		if err != nil {
+			return nil, err
+		}
+		for _, fqdn := range fqdns {
+			if _, ok := attempted[fqdn]; ok {
+				continue
+			}
+			attempted[fqdn] = struct{}{}
+			comps := strings.Split(fqdn, ".")
+			if len(comps) < 2 {
+				continue
+			}
+			if comps[1] != KubernetesDNSSuffix {
+				continue
+			}
+			if nameFilter != "" && nameFilter != comps[0] {
+				continue
+			}
+			clusterURL, clusterVersion, err := fingerprintClusters(ctx, httpClient, fqdn)
+			if err != nil {
+				log.Debugf("could not fingerprint Kubernetes cluster %s %q", fqdn, err)
+				continue
+			}
+			kc := kubernetesCluster{
+				name:    comps[0],
+				url:     clusterURL,
+				version: clusterVersion,
+			}
+			if nameFilter != "" {
+				return []kubernetesCluster{kc}, nil
+			}
+			kcs = append(kcs, kc)
+		}
+	}
+	return kcs, nil
+}
+
+func fingerprintClusters(ctx context.Context, httpClient *http.Client, fqdn string) (*url.URL, string, error) {
+	clusterURL, err := url.Parse("https://" + fqdn)
+	if err != nil {
+		return nil, "", err
+	}
+	versionURL, err := clusterURL.Parse("/version")
+	if err != nil {
+		return nil, "", err
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, versionURL.String(), nil)
+	if err != nil {
+		return nil, "", err
+	}
+	resp, err := httpClient.Do(req)
+	if err != nil {
+		return nil, "", err
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return nil, "", fmt.Errorf("expected %d response but got %s", http.StatusOK, resp.Status)
+	}
+	b, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return nil, "", err
+	}
+	versionData := map[string]string{}
+	err = json.Unmarshal(b, &versionData)
+	if err != nil {
+		return nil, "", err
+	}
+	version, ok := versionData["gitVersion"]
+	if !ok {
+		return nil, "", errors.New("no version found in response")
+	}
+	return clusterURL, version, nil
+}
+
+func resolveKubeconfigPath(cmd *cobra.Command) (string, error) {
+	if cmd.Flags().Changed("kubeconfig") {
+		path, err := cmd.Flags().GetString("kubeconfig")
+		if err != nil {
+			return "", err
+		}
+		return path, nil
+	}
+	if env := os.Getenv("KUBECONFIG"); env != "" {
+		return env, nil
+	}
+	home, err := os.UserHomeDir()
+	if err != nil {
+		return "", fmt.Errorf("could not determine home directory: %w", err)
+	}
+	return filepath.Join(home, ".kube", "config"), nil
+}
+
+func writeKubeconfig(kubeconfigPath string, kc kubernetesCluster) error {
+	b, err := os.ReadFile(kubeconfigPath)
+	if err != nil && !errors.Is(err, os.ErrNotExist) {
+		return err
+	}
+	var cfg map[string]any
+	if err := yaml.Unmarshal(b, &cfg); err != nil {
+		return err
+	}
+	if cfg == nil {
+		cfg = map[string]any{
+			"apiVersion": "v1",
+			"kind":       "Config",
+		}
+	}
+
+	cfg["clusters"] = appendWithName(cfg["clusters"], map[string]any{
+		"name": kc.name,
+		"cluster": map[string]any{
+			"server":                   kc.url.String(),
+			"insecure-skip-tls-verify": true,
+		},
+	})
+	cfg["users"] = appendWithName(cfg["users"], map[string]any{
+		"name": "netbird",
+		"user": map[string]any{
+			"token": "none",
+		},
+	})
+	cfg["contexts"] = appendWithName(cfg["contexts"], map[string]any{
+		"name": kc.name,
+		"context": map[string]any{
+			"cluster":   kc.name,
+			"user":      "netbird",
+			"namespace": "default",
+		},
+	})
+	cfg["current-context"] = kc.name
+
+	out, err := yaml.Marshal(cfg)
+	if err != nil {
+		return err
+	}
+	if err := os.WriteFile(kubeconfigPath, out, 0o600); err != nil {
+		return err
+	}
+	return nil
+}
+
+func appendWithName(data any, add map[string]any) any {
+	if data == nil {
+		return []any{add}
+	}
+	v, ok := data.([]any)
+	if !ok {
+		return []any{add}
+	}
+	i := slices.IndexFunc(v, func(item any) bool {
+		m, ok := item.(map[string]any)
+		if !ok {
+			return false
+		}
+		return m["name"] == add["name"]
+	})
+	if i == -1 {
+		return append(v, add)
+	}
+	v[i] = add
+	return v
+}

client/cmd/kubernetes_test.go

@@ -0,0 +1,120 @@
+package cmd
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/spf13/cobra"
+	"github.com/stretchr/testify/require"
+)
+
+func TestFingerprintClusters(t *testing.T) {
+	t.Parallel()
+
+	srv := httptest.NewTLSServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		//nolint: errcheck
+		w.Write([]byte(`{"gitVersion": "foobar"}`))
+	}))
+	defer srv.Close()
+
+	clusterURL, clusterVersion, err := fingerprintClusters(t.Context(), srv.Client(), srv.Listener.Addr().String())
+	require.NoError(t, err)
+	require.Equal(t, srv.URL, clusterURL.String())
+	require.Equal(t, "foobar", clusterVersion)
+}
+
+func TestResolveKubeconfigPath(t *testing.T) {
+	home, err := os.UserHomeDir()
+	if err != nil {
+		t.Fatalf("could not determine home directory: %v", err)
+	}
+	defaultPath := filepath.Join(home, ".kube", "config")
+	path, err := resolveKubeconfigPath(&cobra.Command{})
+	require.NoError(t, err)
+	require.Equal(t, defaultPath, path)
+
+	flagPath := "flag-path"
+	cmd := &cobra.Command{}
+	cmd.Flags().String("kubeconfig", "", "")
+	err = cmd.Flags().Set("kubeconfig", flagPath)
+	require.NoError(t, err)
+	path, err = resolveKubeconfigPath(cmd)
+	require.NoError(t, err)
+	require.Equal(t, flagPath, path)
+
+	envPath := "env-path"
+	t.Setenv("KUBECONFIG", envPath)
+	path, err = resolveKubeconfigPath(&cobra.Command{})
+	require.NoError(t, err)
+	require.Equal(t, envPath, path)
+}
+
+func TestWriteKubeconfig(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name     string
+		existing string
+	}{
+		{
+			name: "empty file",
+		},
+		{
+			name: "existing content",
+			existing: `apiVersion: v1
+clusters:
+- cluster:
+    insecure-skip-tls-verify: true
+    server: https://foobar.com
+  name: foo
+current-context: test
+kind: Config
+users: []
+`,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			kubeconfigPath := filepath.Join(t.TempDir(), "config")
+			err := os.WriteFile(kubeconfigPath, []byte(tt.existing), 0o644)
+			require.NoError(t, err)
+
+			kc := kubernetesCluster{
+				name: "foo",
+				url:  &url.URL{Scheme: "https", Host: "example.com"},
+			}
+			err = writeKubeconfig(kubeconfigPath, kc)
+			require.NoError(t, err)
+
+			b, err := os.ReadFile(kubeconfigPath)
+			require.NoError(t, err)
+			expected := `apiVersion: v1
+clusters:
+- cluster:
+    insecure-skip-tls-verify: true
+    server: https://example.com
+  name: foo
+contexts:
+- context:
+    cluster: foo
+    namespace: default
+    user: netbird
+  name: foo
+current-context: foo
+kind: Config
+users:
+- name: netbird
+  user:
+    token: none
+`
+			require.Equal(t, expected, string(b))
+		})
+	}
+
+}

client/cmd/root.go

@@ -95,7 +95,9 @@ var (
 	}
 )
 
-// Execute executes the root command.
+// Execute runs the appropriate Cobra command for the CLI.
+// If the process is the update binary it delegates to updateCmd; otherwise it runs the root command.
+// It returns any error produced during command execution.
 func Execute() error {
 	if isUpdateBinary() {
 		return updateCmd.Execute()
@@ -103,6 +105,16 @@ func Execute() error {
 	return rootCmd.Execute()
 }
 
+// init initialises package-level defaults and configures the root
+// Cobra command tree. Sets platform-specific config / log directory
+// paths (including legacy Wiretrustee fallbacks) and a default daemon
+// address; registers persistent CLI flags (daemon address,
+// management / admin URLs, logging, setup key (file and inline,
+// mutually exclusive), preshared key, hostname, anonymise, config
+// path); attaches top-level and nested subcommands to the root
+// command; and registers `up`-specific persistent flags (external IP
+// maps, custom DNS resolver address, Rosenpass options, auto-connect
+// disabling, lazy connection).
 func init() {
 	defaultConfigPathDir = "/etc/netbird/"
 	defaultLogFileDir = "/var/log/netbird/"
@@ -168,6 +180,12 @@ func init() {
 	logCmd.AddCommand(logLevelCmd)
 	debugCmd.AddCommand(forCmd)
 	debugCmd.AddCommand(persistenceCmd)
+	debugCmd.AddCommand(debugConfigCmd)
+
+	// kubernetes commands
+	rootCmd.AddCommand(kubernetesCmd)
+	kubernetesCmd.AddCommand(kubernetesListCmd)
+	kubernetesCmd.AddCommand(kubernetesWriteKubeconfigCmd)
 
 	// profile commands
 	profileCmd.AddCommand(profileListCmd)

client/cmd/service_controller.go

@@ -102,7 +102,7 @@ func (p *program) Stop(srv service.Service) error {
 }
 
 // Common setup for service control commands
-func setupServiceControlCommand(cmd *cobra.Command, ctx context.Context, cancel context.CancelFunc) (service.Service, error) {
+func setupServiceControlCommand(cmd *cobra.Command, ctx context.Context, cancel context.CancelFunc, consoleLog bool) (service.Service, error) {
 	// rootCmd env vars are already applied by PersistentPreRunE.
 	SetFlagsFromEnvVars(serviceCmd)
 
@@ -112,8 +112,14 @@ func setupServiceControlCommand(cmd *cobra.Command, ctx context.Context, cancel
 		return nil, err
 	}
 
-	if err := util.InitLog(logLevel, logFiles...); err != nil {
-		return nil, fmt.Errorf("init log: %w", err)
+	if consoleLog {
+		if err := util.InitLog(logLevel, util.LogConsole); err != nil {
+			return nil, fmt.Errorf("init log: %w", err)
+		}
+	} else {
+		if err := util.InitLog(logLevel, logFiles...); err != nil {
+			return nil, fmt.Errorf("init log: %w", err)
+		}
 	}
 
 	cfg, err := newSVCConfig()
@@ -138,7 +144,7 @@ var runCmd = &cobra.Command{
 		SetupCloseHandler(ctx, cancel)
 		SetupDebugHandler(ctx, nil, nil, nil, util.FindFirstLogPath(logFiles))
 
-		s, err := setupServiceControlCommand(cmd, ctx, cancel)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
 		if err != nil {
 			return err
 		}
@@ -152,7 +158,7 @@ var startCmd = &cobra.Command{
 	Short: "starts NetBird service",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
 		if err != nil {
 			return err
 		}
@@ -170,7 +176,7 @@ var stopCmd = &cobra.Command{
 	Short: "stops NetBird service",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
 		if err != nil {
 			return err
 		}
@@ -188,7 +194,7 @@ var restartCmd = &cobra.Command{
 	Short: "restarts NetBird service",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel, false)
 		if err != nil {
 			return err
 		}
@@ -206,7 +212,7 @@ var svcStatusCmd = &cobra.Command{
 	Short: "shows NetBird service status",
 	RunE: func(cmd *cobra.Command, args []string) error {
 		ctx, cancel := context.WithCancel(cmd.Context())
-		s, err := setupServiceControlCommand(cmd, ctx, cancel)
+		s, err := setupServiceControlCommand(cmd, ctx, cancel, true)
 		if err != nil {
 			return err
 		}

client/cmd/service_privileged_test.go

@@ -0,0 +1,196 @@
+//go:build privileged
+
+package cmd
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"runtime"
+	"testing"
+	"time"
+
+	"github.com/kardianos/service"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+const (
+	serviceStartTimeout = 10 * time.Second
+	serviceStopTimeout  = 5 * time.Second
+	statusPollInterval  = 500 * time.Millisecond
+)
+
+// waitForServiceStatus waits for service to reach expected status with timeout
+func waitForServiceStatus(expectedStatus service.Status, timeout time.Duration) (bool, error) {
+	cfg, err := newSVCConfig()
+	if err != nil {
+		return false, err
+	}
+
+	ctxSvc, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
+	if err != nil {
+		return false, err
+	}
+
+	ctx, timeoutCancel := context.WithTimeout(context.Background(), timeout)
+	defer timeoutCancel()
+
+	ticker := time.NewTicker(statusPollInterval)
+	defer ticker.Stop()
+
+	for {
+		select {
+		case <-ctx.Done():
+			return false, fmt.Errorf("timeout waiting for service status %v", expectedStatus)
+		case <-ticker.C:
+			status, err := s.Status()
+			if err != nil {
+				// Continue polling on transient errors
+				continue
+			}
+			if status == expectedStatus {
+				return true, nil
+			}
+		}
+	}
+}
+
+// TestServiceLifecycle tests the complete service lifecycle
+func TestServiceLifecycle(t *testing.T) {
+	// TODO: Add support for Windows and macOS
+	if runtime.GOOS != "linux" && runtime.GOOS != "freebsd" {
+		t.Skipf("Skipping service lifecycle test on unsupported OS: %s", runtime.GOOS)
+	}
+
+	if os.Getenv("CONTAINER") == "true" {
+		t.Skip("Skipping service lifecycle test in container environment")
+	}
+
+	originalServiceName := serviceName
+	serviceName = "netbirdtest" + fmt.Sprintf("%d", time.Now().Unix())
+	defer func() {
+		serviceName = originalServiceName
+	}()
+
+	tempDir := t.TempDir()
+	configPath = fmt.Sprintf("%s/netbird-test-config.json", tempDir)
+	logLevel = "info"
+	daemonAddr = fmt.Sprintf("unix://%s/netbird-test.sock", tempDir)
+
+	// Ensure cleanup even if a subtest fails and Stop/Uninstall subtests don't run.
+	t.Cleanup(func() {
+		cfg, err := newSVCConfig()
+		if err != nil {
+			t.Errorf("cleanup: create service config: %v", err)
+			return
+		}
+		ctxSvc, cancel := context.WithCancel(context.Background())
+		defer cancel()
+		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
+		if err != nil {
+			t.Errorf("cleanup: create service: %v", err)
+			return
+		}
+
+		// If the subtests already cleaned up, there's nothing to do.
+		if _, err := s.Status(); err != nil {
+			return
+		}
+
+		if err := s.Stop(); err != nil {
+			t.Errorf("cleanup: stop service: %v", err)
+		}
+		if err := s.Uninstall(); err != nil {
+			t.Errorf("cleanup: uninstall service: %v", err)
+		}
+	})
+
+	ctx := context.Background()
+
+	t.Run("Install", func(t *testing.T) {
+		installCmd.SetContext(ctx)
+		err := installCmd.RunE(installCmd, []string{})
+		require.NoError(t, err)
+
+		cfg, err := newSVCConfig()
+		require.NoError(t, err)
+
+		ctxSvc, cancel := context.WithCancel(context.Background())
+		defer cancel()
+
+		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
+		require.NoError(t, err)
+
+		status, err := s.Status()
+		assert.NoError(t, err)
+		assert.NotEqual(t, service.StatusUnknown, status)
+	})
+
+	t.Run("Start", func(t *testing.T) {
+		startCmd.SetContext(ctx)
+		err := startCmd.RunE(startCmd, []string{})
+		require.NoError(t, err)
+
+		running, err := waitForServiceStatus(service.StatusRunning, serviceStartTimeout)
+		require.NoError(t, err)
+		assert.True(t, running)
+	})
+
+	t.Run("Restart", func(t *testing.T) {
+		restartCmd.SetContext(ctx)
+		err := restartCmd.RunE(restartCmd, []string{})
+		require.NoError(t, err)
+
+		running, err := waitForServiceStatus(service.StatusRunning, serviceStartTimeout)
+		require.NoError(t, err)
+		assert.True(t, running)
+	})
+
+	t.Run("Reconfigure", func(t *testing.T) {
+		originalLogLevel := logLevel
+		logLevel = "debug"
+		defer func() {
+			logLevel = originalLogLevel
+		}()
+
+		reconfigureCmd.SetContext(ctx)
+		err := reconfigureCmd.RunE(reconfigureCmd, []string{})
+		require.NoError(t, err)
+
+		running, err := waitForServiceStatus(service.StatusRunning, serviceStartTimeout)
+		require.NoError(t, err)
+		assert.True(t, running)
+	})
+
+	t.Run("Stop", func(t *testing.T) {
+		stopCmd.SetContext(ctx)
+		err := stopCmd.RunE(stopCmd, []string{})
+		require.NoError(t, err)
+
+		stopped, err := waitForServiceStatus(service.StatusStopped, serviceStopTimeout)
+		require.NoError(t, err)
+		assert.True(t, stopped)
+	})
+
+	t.Run("Uninstall", func(t *testing.T) {
+		uninstallCmd.SetContext(ctx)
+		err := uninstallCmd.RunE(uninstallCmd, []string{})
+		require.NoError(t, err)
+
+		cfg, err := newSVCConfig()
+		require.NoError(t, err)
+
+		ctxSvc, cancel := context.WithCancel(context.Background())
+		defer cancel()
+
+		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
+		require.NoError(t, err)
+
+		_, err = s.Status()
+		assert.Error(t, err)
+	})
+}

client/cmd/service_test.go

@@ -1,16 +1,12 @@
 package cmd
 
 import (
-	"context"
-	"fmt"
 	"os"
 	"os/signal"
 	"runtime"
 	"syscall"
 	"testing"
-	"time"
 
-	"github.com/kardianos/service"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
@@ -31,186 +27,6 @@ func TestMain(m *testing.M) {
 	os.Exit(m.Run())
 }
 
-const (
-	serviceStartTimeout = 10 * time.Second
-	serviceStopTimeout  = 5 * time.Second
-	statusPollInterval  = 500 * time.Millisecond
-)
-
-// waitForServiceStatus waits for service to reach expected status with timeout
-func waitForServiceStatus(expectedStatus service.Status, timeout time.Duration) (bool, error) {
-	cfg, err := newSVCConfig()
-	if err != nil {
-		return false, err
-	}
-
-	ctxSvc, cancel := context.WithCancel(context.Background())
-	defer cancel()
-
-	s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
-	if err != nil {
-		return false, err
-	}
-
-	ctx, timeoutCancel := context.WithTimeout(context.Background(), timeout)
-	defer timeoutCancel()
-
-	ticker := time.NewTicker(statusPollInterval)
-	defer ticker.Stop()
-
-	for {
-		select {
-		case <-ctx.Done():
-			return false, fmt.Errorf("timeout waiting for service status %v", expectedStatus)
-		case <-ticker.C:
-			status, err := s.Status()
-			if err != nil {
-				// Continue polling on transient errors
-				continue
-			}
-			if status == expectedStatus {
-				return true, nil
-			}
-		}
-	}
-}
-
-// TestServiceLifecycle tests the complete service lifecycle
-func TestServiceLifecycle(t *testing.T) {
-	// TODO: Add support for Windows and macOS
-	if runtime.GOOS != "linux" && runtime.GOOS != "freebsd" {
-		t.Skipf("Skipping service lifecycle test on unsupported OS: %s", runtime.GOOS)
-	}
-
-	if os.Getenv("CONTAINER") == "true" {
-		t.Skip("Skipping service lifecycle test in container environment")
-	}
-
-	originalServiceName := serviceName
-	serviceName = "netbirdtest" + fmt.Sprintf("%d", time.Now().Unix())
-	defer func() {
-		serviceName = originalServiceName
-	}()
-
-	tempDir := t.TempDir()
-	configPath = fmt.Sprintf("%s/netbird-test-config.json", tempDir)
-	logLevel = "info"
-	daemonAddr = fmt.Sprintf("unix://%s/netbird-test.sock", tempDir)
-
-	// Ensure cleanup even if a subtest fails and Stop/Uninstall subtests don't run.
-	t.Cleanup(func() {
-		cfg, err := newSVCConfig()
-		if err != nil {
-			t.Errorf("cleanup: create service config: %v", err)
-			return
-		}
-		ctxSvc, cancel := context.WithCancel(context.Background())
-		defer cancel()
-		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
-		if err != nil {
-			t.Errorf("cleanup: create service: %v", err)
-			return
-		}
-
-		// If the subtests already cleaned up, there's nothing to do.
-		if _, err := s.Status(); err != nil {
-			return
-		}
-
-		if err := s.Stop(); err != nil {
-			t.Errorf("cleanup: stop service: %v", err)
-		}
-		if err := s.Uninstall(); err != nil {
-			t.Errorf("cleanup: uninstall service: %v", err)
-		}
-	})
-
-	ctx := context.Background()
-
-	t.Run("Install", func(t *testing.T) {
-		installCmd.SetContext(ctx)
-		err := installCmd.RunE(installCmd, []string{})
-		require.NoError(t, err)
-
-		cfg, err := newSVCConfig()
-		require.NoError(t, err)
-
-		ctxSvc, cancel := context.WithCancel(context.Background())
-		defer cancel()
-
-		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
-		require.NoError(t, err)
-
-		status, err := s.Status()
-		assert.NoError(t, err)
-		assert.NotEqual(t, service.StatusUnknown, status)
-	})
-
-	t.Run("Start", func(t *testing.T) {
-		startCmd.SetContext(ctx)
-		err := startCmd.RunE(startCmd, []string{})
-		require.NoError(t, err)
-
-		running, err := waitForServiceStatus(service.StatusRunning, serviceStartTimeout)
-		require.NoError(t, err)
-		assert.True(t, running)
-	})
-
-	t.Run("Restart", func(t *testing.T) {
-		restartCmd.SetContext(ctx)
-		err := restartCmd.RunE(restartCmd, []string{})
-		require.NoError(t, err)
-
-		running, err := waitForServiceStatus(service.StatusRunning, serviceStartTimeout)
-		require.NoError(t, err)
-		assert.True(t, running)
-	})
-
-	t.Run("Reconfigure", func(t *testing.T) {
-		originalLogLevel := logLevel
-		logLevel = "debug"
-		defer func() {
-			logLevel = originalLogLevel
-		}()
-
-		reconfigureCmd.SetContext(ctx)
-		err := reconfigureCmd.RunE(reconfigureCmd, []string{})
-		require.NoError(t, err)
-
-		running, err := waitForServiceStatus(service.StatusRunning, serviceStartTimeout)
-		require.NoError(t, err)
-		assert.True(t, running)
-	})
-
-	t.Run("Stop", func(t *testing.T) {
-		stopCmd.SetContext(ctx)
-		err := stopCmd.RunE(stopCmd, []string{})
-		require.NoError(t, err)
-
-		stopped, err := waitForServiceStatus(service.StatusStopped, serviceStopTimeout)
-		require.NoError(t, err)
-		assert.True(t, stopped)
-	})
-
-	t.Run("Uninstall", func(t *testing.T) {
-		uninstallCmd.SetContext(ctx)
-		err := uninstallCmd.RunE(uninstallCmd, []string{})
-		require.NoError(t, err)
-
-		cfg, err := newSVCConfig()
-		require.NoError(t, err)
-
-		ctxSvc, cancel := context.WithCancel(context.Background())
-		defer cancel()
-
-		s, err := newSVC(newProgram(ctxSvc, cancel), cfg)
-		require.NoError(t, err)
-
-		_, err = s.Status()
-		assert.Error(t, err)
-	})
-}
-
 // TestServiceEnvVars tests environment variable parsing
 func TestServiceEnvVars(t *testing.T) {
 	tests := []struct {

client/cmd/testutil_test.go

@@ -11,7 +11,7 @@ import (
 	"go.opentelemetry.io/otel"
 	"google.golang.org/grpc"
 
-	"github.com/netbirdio/management-integrations/integrations"
+	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator/validator"
 
 	nbcache "github.com/netbirdio/netbird/management/server/cache"
 
@@ -109,7 +109,7 @@ func startManagement(t *testing.T, config *config.Config, testFile string) (*grp
 		t.Fatal(err)
 	}
 
-	iv, _ := integrations.NewIntegratedValidator(ctx, peersmanager, settingsManagerMock, eventStore, cacheStore)
+	iv, _ := validator.NewIntegratedValidator(ctx, peersmanager, settingsManagerMock, eventStore, cacheStore)
 
 	metrics, err := telemetry.NewDefaultAppMetrics(ctx)
 	require.NoError(t, err)

client/cmd/version.go

@@ -12,7 +12,13 @@ var (
 		Short: "Print the NetBird's client application version",
 		Run: func(cmd *cobra.Command, args []string) {
 			cmd.SetOut(cmd.OutOrStdout())
-			cmd.Println(version.NetbirdVersion())
+			out := version.NetbirdVersion()
+			if version.IsDevelopmentVersion(out) {
+				if commit := version.NetbirdCommit(); commit != "" {
+					out += "-" + commit
+				}
+			}
+			cmd.Println(out)
 		},
 	}
 )

client/embed/embed.go

@@ -12,6 +12,7 @@ import (
 	"sync"
 
 	"github.com/sirupsen/logrus"
+	wgdevice "golang.zx2c4.com/wireguard/device"
 	wgnetstack "golang.zx2c4.com/wireguard/tun/netstack"
 
 	"github.com/netbirdio/netbird/client/iface"
@@ -84,6 +85,12 @@ type Options struct {
 	DisableIPv6 bool
 	// BlockInbound blocks all inbound connections from peers
 	BlockInbound bool
+	// BlockLANAccess blocks the embedded peer from reaching the host's
+	// LAN (RFC 1918, link-local, loopback) when it's used as a routing
+	// peer. Mirrors profilemanager.ConfigInput.BlockLANAccess. Useful
+	// when the embedded client must never act as a stepping stone into
+	// the host's local network (e.g. the proxy's overlay peer).
+	BlockLANAccess bool
 	// WireguardPort is the port for the tunnel interface. Use 0 for a random port.
 	WireguardPort *int
 	// MTU is the MTU for the tunnel interface.
@@ -94,6 +101,26 @@ type Options struct {
 	MTU *uint16
 	// DNSLabels defines additional DNS labels configured in the peer.
 	DNSLabels []string
+	// Performance configures the tunnel's buffer pool cap and batch size.
+	Performance Performance
+}
+
+// Performance configures the embedded client's tunnel memory/throughput knobs.
+//
+// These settings are process-global: any non-nil field also becomes the
+// default for Clients constructed by later embed.New calls in the same
+// process. Nil fields are ignored.
+type Performance struct {
+	// PreallocatedBuffersPerPool caps the per-tunnel buffer pool. Zero
+	// leaves the pool unbounded. Lower values trade throughput for a
+	// tighter memory ceiling. May also be changed on a running Client via
+	// Client.SetPerformance, provided this field was nonzero at construction.
+	PreallocatedBuffersPerPool *uint32
+	// MaxBatchSize overrides the number of packets the tunnel reads or
+	// writes per syscall, which also bounds eager buffer allocation per
+	// worker. Zero uses the platform default. Applied at construction
+	// only; ignored by Client.SetPerformance.
+	MaxBatchSize *uint32
 }
 
 // validateCredentials checks that exactly one credential type is provided
@@ -175,6 +202,7 @@ func New(opts Options) (*Client, error) {
 		DisableClientRoutes: &opts.DisableClientRoutes,
 		DisableIPv6:         &opts.DisableIPv6,
 		BlockInbound:        &opts.BlockInbound,
+		BlockLANAccess:      &opts.BlockLANAccess,
 		WireguardPort:       opts.WireguardPort,
 		MTU:                 opts.MTU,
 		DNSLabels:           parsedLabels,
@@ -192,6 +220,13 @@ func New(opts Options) (*Client, error) {
 		config.PrivateKey = opts.PrivateKey
 	}
 
+	if opts.Performance.PreallocatedBuffersPerPool != nil {
+		wgdevice.SetPreallocatedBuffersPerPool(*opts.Performance.PreallocatedBuffersPerPool)
+	}
+	if opts.Performance.MaxBatchSize != nil {
+		wgdevice.SetMaxBatchSizeOverride(*opts.Performance.MaxBatchSize)
+	}
+
 	return &Client{
 		deviceName: opts.DeviceName,
 		setupKey:   opts.SetupKey,
@@ -244,6 +279,10 @@ func (c *Client) Start(startCtx context.Context) error {
 
 	select {
 	case <-startCtx.Done():
+		// Cancel the client context before stopping: Engine.Start blocks on the
+		// signal stream while holding the engine mutex and only unblocks on
+		// cancellation. Stopping first would deadlock on that mutex.
+		cancel()
 		if stopErr := client.Stop(); stopErr != nil {
 			return fmt.Errorf("stop error after context done. Stop error: %w. Context done: %w", stopErr, startCtx.Err())
 		}
@@ -405,6 +444,21 @@ func (c *Client) Expose(ctx context.Context, req ExposeRequest) (*ExposeSession,
 	}, nil
 }
 
+// IdentityForIP looks up a remote peer by its tunnel IP using the
+// embedded client's status recorder. Returns the peer's WireGuard public
+// key and FQDN. ok=false means the IP doesn't belong to an active peer
+// — offline roster peers are treated as unknown, same as foreign IPs.
+func (c *Client) IdentityForIP(ip netip.Addr) (pubKey, fqdn string, ok bool) {
+	if !ip.IsValid() || c.recorder == nil {
+		return "", "", false
+	}
+	state, found := c.recorder.PeerStateByIP(ip.String())
+	if !found {
+		return "", "", false
+	}
+	return state.PubKey, state.FQDN, true
+}
+
 // Status returns the current status of the client.
 func (c *Client) Status() (peer.FullStatus, error) {
 	c.mu.Lock()
@@ -473,6 +527,25 @@ func (c *Client) VerifySSHHostKey(peerAddress string, key []byte) error {
 	return sshcommon.VerifyHostKey(storedKey, key, peerAddress)
 }
 
+// SetPerformance retunes a running Client. Only PreallocatedBuffersPerPool
+// takes effect, and only when it was nonzero at construction;
+// MaxBatchSize is construction-only and returns an error if set here.
+//
+// Returns ErrClientNotStarted / ErrEngineNotStarted if the Client is not
+// running yet.
+func (c *Client) SetPerformance(t Performance) error {
+	if t.MaxBatchSize != nil {
+		return errors.New("MaxBatchSize is construction-only and cannot be changed at runtime")
+	}
+	engine, err := c.getEngine()
+	if err != nil {
+		return err
+	}
+	return engine.SetPerformance(internal.Performance{
+		PreallocatedBuffersPerPool: t.PreallocatedBuffersPerPool,
+	})
+}
+
 // StartCapture begins capturing packets on this client's tunnel device.
 // Only one capture can be active at a time; starting a new one stops the previous.
 // Call StopCapture (or CaptureSession.Stop) to end it.

client/embed/embed_test.go

@@ -0,0 +1,168 @@
+package embed
+
+import (
+	"context"
+	"net"
+	"testing"
+	"time"
+
+	"github.com/golang/mock/gomock"
+	"github.com/stretchr/testify/require"
+	"google.golang.org/grpc"
+
+	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
+	"github.com/netbirdio/netbird/management/internals/controllers/network_map/update_channel"
+	"github.com/netbirdio/netbird/management/internals/modules/peers"
+	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral/manager"
+	"github.com/netbirdio/netbird/management/internals/server/config"
+	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
+	mgmt "github.com/netbirdio/netbird/management/server"
+	"github.com/netbirdio/netbird/management/server/activity"
+	nbcache "github.com/netbirdio/netbird/management/server/cache"
+	"github.com/netbirdio/netbird/management/server/groups"
+	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator/validator"
+	"github.com/netbirdio/netbird/management/server/integrations/port_forwarding"
+	"github.com/netbirdio/netbird/management/server/job"
+	"github.com/netbirdio/netbird/management/server/permissions"
+	"github.com/netbirdio/netbird/management/server/settings"
+	"github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/telemetry"
+	"github.com/netbirdio/netbird/management/server/types"
+	mgmtProto "github.com/netbirdio/netbird/shared/management/proto"
+	"github.com/netbirdio/netbird/util"
+)
+
+const testSetupKey = "A2C8E62B-38F5-4553-B31E-DD66C696CEBB"
+
+// TestClientStartTimeoutRollback reproduces a deadlock between Engine.Start and
+// Engine.Stop. The signal endpoint accepts gRPC connections but never serves the
+// SignalExchange service, so Engine.Start parks in WaitStreamConnected while
+// holding the engine mutex. When the Start context expires, the rollback path
+// calls ConnectClient.Stop, which must not block forever acquiring that mutex.
+func TestClientStartTimeoutRollback(t *testing.T) {
+	signalAddr := startBlackholeSignal(t)
+	mgmAddr := startManagement(t, signalAddr)
+
+	wgPort := 0
+	client, err := New(Options{
+		DeviceName:    "embed-rollback-test",
+		SetupKey:      testSetupKey,
+		ManagementURL: "http://" + mgmAddr,
+		WireguardPort: &wgPort,
+	})
+	require.NoError(t, err, "embed client creation must succeed")
+
+	startCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	startErr := make(chan error, 1)
+	go func() {
+		startErr <- client.Start(startCtx)
+	}()
+
+	select {
+	case err := <-startErr:
+		require.ErrorIs(t, err, context.DeadlineExceeded)
+	case <-time.After(60 * time.Second):
+		t.Fatal("client.Start did not return after its context expired: Engine.Stop deadlocked against Engine.Start waiting for the signal stream")
+	}
+}
+
+// startBlackholeSignal starts a gRPC server without the SignalExchange service
+// registered. Connections succeed, but the signal stream can never be
+// established, which keeps Engine.Start parked in WaitStreamConnected.
+func startBlackholeSignal(t *testing.T) string {
+	t.Helper()
+
+	lis, err := net.Listen("tcp", "localhost:0")
+	require.NoError(t, err)
+
+	s := grpc.NewServer()
+	go func() {
+		if err := s.Serve(lis); err != nil {
+			t.Error(err)
+		}
+	}()
+	t.Cleanup(s.Stop)
+
+	return lis.Addr().String()
+}
+
+func startManagement(t *testing.T, signalAddr string) string {
+	t.Helper()
+
+	cfg := &config.Config{
+		Stuns:      []*config.Host{},
+		TURNConfig: &config.TURNConfig{},
+		Relay: &config.Relay{
+			Addresses:      []string{"127.0.0.1:1234"},
+			CredentialsTTL: util.Duration{Duration: time.Hour},
+			Secret:         "222222222222222222",
+		},
+		Signal: &config.Host{
+			Proto: "http",
+			URI:   signalAddr,
+		},
+		Datadir:    t.TempDir(),
+		HttpConfig: nil,
+	}
+
+	lis, err := net.Listen("tcp", "localhost:0")
+	require.NoError(t, err)
+
+	s := grpc.NewServer()
+
+	testStore, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../testdata/store.sql", cfg.Datadir)
+	require.NoError(t, err)
+	t.Cleanup(cleanUp)
+
+	eventStore := &activity.InMemoryEventStore{}
+
+	permissionsManager := permissions.NewManager(testStore)
+	peersManager := peers.NewManager(testStore, permissionsManager)
+	jobManager := job.NewJobManager(nil, testStore, peersManager)
+
+	cacheStore, err := nbcache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
+	require.NoError(t, err)
+
+	iv, err := validator.NewIntegratedValidator(context.Background(), peersManager, nil, eventStore, cacheStore)
+	require.NoError(t, err)
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	ctrl := gomock.NewController(t)
+	t.Cleanup(ctrl.Finish)
+	settingsMockManager := settings.NewMockManager(ctrl)
+	settingsMockManager.EXPECT().
+		GetSettings(gomock.Any(), gomock.Any(), gomock.Any()).
+		Return(&types.Settings{}, nil).
+		AnyTimes()
+	settingsMockManager.EXPECT().
+		GetExtraSettings(gomock.Any(), gomock.Any()).
+		Return(&types.ExtraSettings{}, nil).
+		AnyTimes()
+
+	groupsManager := groups.NewManagerMock()
+
+	updateManager := update_channel.NewPeersUpdateManager(metrics)
+	requestBuffer := mgmt.NewAccountRequestBuffer(context.Background(), testStore)
+	networkMapController := controller.NewController(context.Background(), testStore, metrics, updateManager, requestBuffer, mgmt.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(testStore, peersManager), cfg)
+	accountManager, err := mgmt.BuildManager(context.Background(), cfg, testStore, networkMapController, jobManager, nil, "", eventStore, nil, false, iv, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManager, false, cacheStore)
+	require.NoError(t, err)
+
+	secretsManager, err := nbgrpc.NewTimeBasedAuthSecretsManager(updateManager, cfg.TURNConfig, cfg.Relay, settingsMockManager, groupsManager)
+	require.NoError(t, err)
+
+	mgmtServer, err := nbgrpc.NewServer(cfg, accountManager, settingsMockManager, jobManager, secretsManager, nil, nil, &mgmt.MockIntegratedValidator{}, networkMapController, nil, nil)
+	require.NoError(t, err)
+	mgmtProto.RegisterManagementServiceServer(s, mgmtServer)
+
+	go func() {
+		if err := s.Serve(lis); err != nil {
+			t.Error(err)
+		}
+	}()
+	t.Cleanup(s.Stop)
+
+	return lis.Addr().String()
+}

client/firewall/iptables/acl_linux.go

@@ -3,6 +3,7 @@ package iptables
 import (
 	"errors"
 	"fmt"
+	"maps"
 	"net"
 	"slices"
 
@@ -421,12 +422,17 @@ func (m *aclManager) updateState() {
 	currentState.Lock()
 	defer currentState.Unlock()
 
+	// Clone the maps so the persisted state holds a private snapshot. The
+	// live maps keep being mutated by subsequent rule operations while the
+	// state manager marshals the state from its periodic-save goroutine.
+	// Sharing them by reference races the two and aborts the process with a
+	// concurrent map iteration and write.
 	if m.v6 {
-		currentState.ACLEntries6 = m.entries
-		currentState.ACLIPsetStore6 = m.ipsetStore
+		currentState.ACLEntries6 = maps.Clone(m.entries)
+		currentState.ACLIPsetStore6 = m.ipsetStore.clone()
 	} else {
-		currentState.ACLEntries = m.entries
-		currentState.ACLIPsetStore = m.ipsetStore
+		currentState.ACLEntries = maps.Clone(m.entries)
+		currentState.ACLIPsetStore = m.ipsetStore.clone()
 	}
 
 	if err := m.stateManager.UpdateState(currentState); err != nil {

client/firewall/iptables/manager_linux_test.go

@@ -1,3 +1,5 @@
+//go:build privileged
+
 package iptables
 
 import (

client/firewall/iptables/router_linux.go

@@ -4,6 +4,7 @@ package iptables
 
 import (
 	"fmt"
+	"maps"
 	"net/netip"
 	"strconv"
 	"strings"
@@ -749,11 +750,17 @@ func (r *router) updateState() {
 	currentState.Lock()
 	defer currentState.Unlock()
 
+	// Clone the rule map so the persisted state holds a private snapshot. The
+	// live map keeps being mutated by subsequent rule operations while the
+	// state manager marshals the state from its periodic-save goroutine.
+	// Sharing it by reference races the two and aborts the process with a
+	// concurrent map iteration and write. The ipset counter guards itself
+	// during marshaling, so it can be shared directly.
 	if r.v6 {
-		currentState.RouteRules6 = r.rules
+		currentState.RouteRules6 = maps.Clone(r.rules)
 		currentState.RouteIPsetCounter6 = r.ipsetCounter
 	} else {
-		currentState.RouteRules = r.rules
+		currentState.RouteRules = maps.Clone(r.rules)
 		currentState.RouteIPsetCounter = r.ipsetCounter
 	}
 

client/firewall/iptables/router_linux_test.go

@@ -1,4 +1,4 @@
-//go:build !android
+//go:build !android && privileged
 
 package iptables
 

client/firewall/iptables/rulestore_linux.go

@@ -1,6 +1,9 @@
 package iptables
 
-import "encoding/json"
+import (
+	"encoding/json"
+	"maps"
+)
 
 type ipList struct {
 	ips map[string]struct{}
@@ -19,6 +22,14 @@ func (s *ipList) addIP(ip string) {
 	s.ips[ip] = struct{}{}
 }
 
+// clone returns a deep copy of the ipList with its own ips map.
+func (s *ipList) clone() *ipList {
+	if s == nil {
+		return nil
+	}
+	return &ipList{ips: maps.Clone(s.ips)}
+}
+
 // MarshalJSON implements json.Marshaler
 func (s *ipList) MarshalJSON() ([]byte, error) {
 	return json.Marshal(struct {
@@ -55,6 +66,19 @@ func newIpsetStore() *ipsetStore {
 	}
 }
 
+// clone returns a deep copy of the ipsetStore with its own ipsets map and
+// independent ipList entries.
+func (s *ipsetStore) clone() *ipsetStore {
+	if s == nil {
+		return nil
+	}
+	cloned := &ipsetStore{ipsets: make(map[string]*ipList, len(s.ipsets))}
+	for name, list := range s.ipsets {
+		cloned.ipsets[name] = list.clone()
+	}
+	return cloned
+}
+
 func (s *ipsetStore) ipset(ipsetName string) (*ipList, bool) {
 	r, ok := s.ipsets[ipsetName]
 	return r, ok

client/firewall/nftables/external_chain_monitor_linux.go

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

client/firewall/nftables/manager_linux_test.go

@@ -1,3 +1,5 @@
+//go:build privileged
+
 package nftables
 
 import (

client/firewall/nftables/router_linux_test.go

@@ -1,4 +1,4 @@
-//go:build !android
+//go:build !android && privileged
 
 package nftables
 

client/firewall/uspfilter/forwarder/icmp.go

@@ -362,6 +362,10 @@ func (f *Forwarder) injectICMPv6Reply(id stack.TransportEndpointID, icmpPayload
 		return 0
 	}
 
+	if pc := f.endpoint.capture.Load(); pc != nil {
+		(*pc).Offer(fullPacket, true)
+	}
+
 	return len(fullPacket)
 }
 

client/iface/iface_test.go

@@ -1,3 +1,5 @@
+//go:build privileged
+
 package iface
 
 import (

client/iface/wgproxy/proxy_linux_test.go

@@ -1,4 +1,4 @@
-//go:build linux && !android
+//go:build linux && !android && privileged
 
 package wgproxy
 

client/iface/wgproxy/proxy_seed_test.go

@@ -1,4 +1,4 @@
-//go:build !linux
+//go:build !linux || !privileged
 
 package wgproxy
 

client/iface/wgproxy/redirect_test.go

@@ -1,4 +1,4 @@
-//go:build linux && !android
+//go:build linux && !android && privileged
 
 package wgproxy
 
@@ -26,64 +26,6 @@ func compareUDPAddr(addr1, addr2 net.Addr) bool {
 	return udpAddr1.IP.Equal(udpAddr2.IP) && udpAddr1.Port == udpAddr2.Port
 }
 
-// TestRedirectAs_eBPF_IPv4 tests RedirectAs with eBPF proxy using IPv4 addresses
-func TestRedirectAs_eBPF_IPv4(t *testing.T) {
-	wgPort := 51850
-	ebpfProxy := ebpf.NewWGEBPFProxy(wgPort, 1280)
-	if err := ebpfProxy.Listen(); err != nil {
-		t.Fatalf("failed to initialize ebpf proxy: %v", err)
-	}
-	defer func() {
-		if err := ebpfProxy.Free(); err != nil {
-			t.Errorf("failed to free ebpf proxy: %v", err)
-		}
-	}()
-
-	proxy := ebpf.NewProxyWrapper(ebpfProxy)
-
-	// NetBird UDP address of the remote peer
-	nbAddr := &net.UDPAddr{
-		IP:   net.ParseIP("100.108.111.177"),
-		Port: 38746,
-	}
-
-	p2pEndpoint := &net.UDPAddr{
-		IP:   net.ParseIP("192.168.0.56"),
-		Port: 51820,
-	}
-
-	testRedirectAs(t, proxy, wgPort, nbAddr, p2pEndpoint)
-}
-
-// TestRedirectAs_eBPF_IPv6 tests RedirectAs with eBPF proxy using IPv6 addresses
-func TestRedirectAs_eBPF_IPv6(t *testing.T) {
-	wgPort := 51851
-	ebpfProxy := ebpf.NewWGEBPFProxy(wgPort, 1280)
-	if err := ebpfProxy.Listen(); err != nil {
-		t.Fatalf("failed to initialize ebpf proxy: %v", err)
-	}
-	defer func() {
-		if err := ebpfProxy.Free(); err != nil {
-			t.Errorf("failed to free ebpf proxy: %v", err)
-		}
-	}()
-
-	proxy := ebpf.NewProxyWrapper(ebpfProxy)
-
-	// NetBird UDP address of the remote peer
-	nbAddr := &net.UDPAddr{
-		IP:   net.ParseIP("100.108.111.177"),
-		Port: 38746,
-	}
-
-	p2pEndpoint := &net.UDPAddr{
-		IP:   net.ParseIP("fe80::56"),
-		Port: 51820,
-	}
-
-	testRedirectAs(t, proxy, wgPort, nbAddr, p2pEndpoint)
-}
-
 // TestRedirectAs_UDP_IPv4 tests RedirectAs with UDP proxy using IPv4 addresses
 func TestRedirectAs_UDP_IPv4(t *testing.T) {
 	wgPort := 51852
@@ -256,6 +198,64 @@ func testRedirectAs(t *testing.T, proxy Proxy, wgPort int, nbAddr, p2pEndpoint *
 	}
 }
 
+// TestRedirectAs_eBPF_IPv4 tests RedirectAs with eBPF proxy using IPv4 addresses
+func TestRedirectAs_eBPF_IPv4(t *testing.T) {
+	wgPort := 51850
+	ebpfProxy := ebpf.NewWGEBPFProxy(wgPort, 1280)
+	if err := ebpfProxy.Listen(); err != nil {
+		t.Fatalf("failed to initialize ebpf proxy: %v", err)
+	}
+	defer func() {
+		if err := ebpfProxy.Free(); err != nil {
+			t.Errorf("failed to free ebpf proxy: %v", err)
+		}
+	}()
+
+	proxy := ebpf.NewProxyWrapper(ebpfProxy)
+
+	// NetBird UDP address of the remote peer
+	nbAddr := &net.UDPAddr{
+		IP:   net.ParseIP("100.108.111.177"),
+		Port: 38746,
+	}
+
+	p2pEndpoint := &net.UDPAddr{
+		IP:   net.ParseIP("192.168.0.56"),
+		Port: 51820,
+	}
+
+	testRedirectAs(t, proxy, wgPort, nbAddr, p2pEndpoint)
+}
+
+// TestRedirectAs_eBPF_IPv6 tests RedirectAs with eBPF proxy using IPv6 addresses
+func TestRedirectAs_eBPF_IPv6(t *testing.T) {
+	wgPort := 51851
+	ebpfProxy := ebpf.NewWGEBPFProxy(wgPort, 1280)
+	if err := ebpfProxy.Listen(); err != nil {
+		t.Fatalf("failed to initialize ebpf proxy: %v", err)
+	}
+	defer func() {
+		if err := ebpfProxy.Free(); err != nil {
+			t.Errorf("failed to free ebpf proxy: %v", err)
+		}
+	}()
+
+	proxy := ebpf.NewProxyWrapper(ebpfProxy)
+
+	// NetBird UDP address of the remote peer
+	nbAddr := &net.UDPAddr{
+		IP:   net.ParseIP("100.108.111.177"),
+		Port: 38746,
+	}
+
+	p2pEndpoint := &net.UDPAddr{
+		IP:   net.ParseIP("fe80::56"),
+		Port: 51820,
+	}
+
+	testRedirectAs(t, proxy, wgPort, nbAddr, p2pEndpoint)
+}
+
 // TestRedirectAs_Multiple_Switches tests switching between multiple endpoints
 func TestRedirectAs_Multiple_Switches(t *testing.T) {
 	wgPort := 51856

client/internal/auth/pkce_flow.go

@@ -360,7 +360,13 @@ func isRedirectURLPortUsed(redirectURL string, excludedRanges []excludedPortRang
 		return true
 	}
 
-	addr := fmt.Sprintf(":%s", port)
+	// FreeBSD 15 disables connecting to INADDR_ANY (0.0.0.0) as a localhost
+	// alias by default, ensure explicit ip for localhost.
+	host := parsedURL.Hostname()
+	if host == "" {
+		host = "127.0.0.1"
+	}
+	addr := net.JoinHostPort(host, port)
 	conn, err := net.DialTimeout("tcp", addr, 3*time.Second)
 	if err != nil {
 		return false

client/internal/connect.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"path/filepath"
 	"runtime"
 	"runtime/debug"
 	"strings"
@@ -116,7 +117,6 @@ func (c *ConnectClient) RunOniOS(
 	fileDescriptor int32,
 	networkChangeListener listener.NetworkChangeListener,
 	dnsManager dns.IosDnsManager,
-	dnsAddresses []netip.AddrPort,
 	stateFilePath string,
 ) error {
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
@@ -126,7 +126,6 @@ func (c *ConnectClient) RunOniOS(
 		FileDescriptor:        fileDescriptor,
 		NetworkChangeListener: networkChangeListener,
 		DnsManager:            dnsManager,
-		HostDNSAddresses:      dnsAddresses,
 		StateFilePath:         stateFilePath,
 	}
 	return c.run(mobileDependency, nil, "")
@@ -348,6 +347,11 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			return wrapErr(err)
 		}
 		engineConfig.TempDir = mobileDependency.TempDir
+		// Leave StateDir empty when there is no state path so a disk-backed
+		// syncstore falls back to os.TempDir() instead of filepath.Dir("") == ".".
+		if path != "" {
+			engineConfig.StateDir = filepath.Dir(path)
+		}
 
 		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
 		c.statusRecorder.SetRelayMgr(relayManager)

client/internal/debug/debug.go

@@ -254,6 +254,8 @@ type BundleGenerator struct {
 	capturePath    string
 	refreshStatus  func() // Optional callback to refresh status before bundle generation
 	clientMetrics  MetricsExporter
+	daemonVersion  string
+	cliVersion     string
 
 	anonymize         bool
 	includeSystemInfo bool
@@ -278,6 +280,8 @@ type GeneratorDependencies struct {
 	CapturePath    string
 	RefreshStatus  func()
 	ClientMetrics  MetricsExporter
+	DaemonVersion  string
+	CliVersion     string
 }
 
 func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGenerator {
@@ -299,6 +303,8 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		capturePath:    deps.CapturePath,
 		refreshStatus:  deps.RefreshStatus,
 		clientMetrics:  deps.ClientMetrics,
+		daemonVersion:  deps.DaemonVersion,
+		cliVersion:     deps.CliVersion,
 
 		anonymize:         cfg.Anonymize,
 		includeSystemInfo: cfg.IncludeSystemInfo,
@@ -459,9 +465,11 @@ func (g *BundleGenerator) addStatus() error {
 		protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
 		protoFullStatus.Events = g.statusRecorder.GetEventHistory()
 		overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
-			Anonymize:   g.anonymize,
-			ProfileName: profName,
+			Anonymize:     g.anonymize,
+			ProfileName:   profName,
+			DaemonVersion: g.daemonVersion,
 		})
+		overview.CliVersion = g.cliVersion
 		statusOutput := overview.FullDetailSummary()
 
 		statusReader := strings.NewReader(statusOutput)
@@ -508,6 +516,14 @@ func (g *BundleGenerator) addConfig() error {
 		}
 	}
 
+	// Surface the set of MDM-enforced keys so a support engineer reading
+	// the bundle can tell which field values are user-set vs MDM-overridden.
+	// Same semantics as the mDMManagedFields list returned by the
+	// GetConfig RPC consumed by `netbird debug config`.
+	if managed := g.internalConfig.Policy().ManagedKeys(); len(managed) > 0 {
+		configContent.WriteString(fmt.Sprintf("MDMManagedFields: %v\n", managed))
+	}
+
 	configReader := strings.NewReader(configContent.String())
 	if err := g.addFileToZip(configReader, "config.txt"); err != nil {
 		return fmt.Errorf("add config file to zip: %w", err)
@@ -798,6 +814,8 @@ func (g *BundleGenerator) addSyncResponse() error {
 		AllowPartial:    true,
 	}
 
+	g.maskSecrets()
+
 	jsonBytes, err := options.Marshal(g.syncResponse)
 	if err != nil {
 		return fmt.Errorf("generate json: %w", err)
@@ -810,6 +828,27 @@ func (g *BundleGenerator) addSyncResponse() error {
 	return nil
 }
 
+func (g *BundleGenerator) maskSecrets() {
+	if g.syncResponse == nil || g.syncResponse.NetbirdConfig == nil {
+		return
+	}
+
+	if g.syncResponse.NetbirdConfig.Flow != nil {
+		g.syncResponse.NetbirdConfig.Flow.TokenPayload = maskedValue
+
+	}
+
+	if g.syncResponse.NetbirdConfig.Relay != nil {
+		g.syncResponse.NetbirdConfig.Relay.TokenPayload = maskedValue
+	}
+
+	for i := range g.syncResponse.NetbirdConfig.Turns {
+		if g.syncResponse.NetbirdConfig.Turns[i] != nil {
+			g.syncResponse.NetbirdConfig.Turns[i].Password = maskedValue
+		}
+	}
+}
+
 func (g *BundleGenerator) addStateFile() error {
 	sm := profilemanager.NewServiceManager("")
 	path := sm.GetStatePath()
@@ -1039,7 +1078,8 @@ func (g *BundleGenerator) addRotatedLogFiles(logDir string) {
 		return
 	}
 
-	pattern := filepath.Join(logDir, "client-*.log.gz")
+	// This regex will match both logs rotated by us and logrotate on linux
+	pattern := filepath.Join(logDir, "client*.log.*")
 	files, err := filepath.Glob(pattern)
 	if err != nil {
 		log.Warnf("failed to glob rotated logs: %v", err)
@@ -1072,7 +1112,12 @@ func (g *BundleGenerator) addRotatedLogFiles(logDir string) {
 
 	for i := 0; i < maxFiles; i++ {
 		name := filepath.Base(files[i])
-		if err := g.addSingleLogFileGz(files[i], name); err != nil {
+		if strings.HasSuffix(name, ".gz") {
+			err = g.addSingleLogFileGz(files[i], name)
+		} else {
+			err = g.addSingleLogfile(files[i], name)
+		}
+		if err != nil {
 			log.Warnf("failed to add rotated log %s: %v", name, err)
 		}
 	}

client/internal/debug/debug_logfiles_test.go

@@ -0,0 +1,103 @@
+package debug
+
+import (
+	"archive/zip"
+	"bytes"
+	"compress/gzip"
+	"io"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+// TestAddRotatedLogFiles_PicksUpAllVariants asserts that the rotated-log
+// glob picks up logs rotated by timberjack (gzipped) and by logrotate (plain
+// and gzipped), and skips unrelated files.
+func TestAddRotatedLogFiles_PicksUpAllVariants(t *testing.T) {
+	dir := t.TempDir()
+
+	writeFile(t, filepath.Join(dir, "client.log"), "active log\n")
+	writeFile(t, filepath.Join(dir, "other.log"), "unrelated\n")
+
+	timberjackRotated := "client-2026-05-21T10-30-45.000.log.gz"
+	writeGzFile(t, filepath.Join(dir, timberjackRotated), "timberjack rotated content\n")
+
+	logrotatePlain := "client.log.1"
+	writeFile(t, filepath.Join(dir, logrotatePlain), "logrotate plain content\n")
+
+	logrotateGz := "client.log.2.gz"
+	writeGzFile(t, filepath.Join(dir, logrotateGz), "logrotate gz content\n")
+
+	names := runAddRotatedLogFiles(t, dir, 10)
+
+	require.Contains(t, names, timberjackRotated, "timberjack rotated file should be in bundle")
+	require.Contains(t, names, logrotatePlain, "logrotate plain rotated file should be in bundle")
+	require.Contains(t, names, logrotateGz, "logrotate gzipped rotated file should be in bundle")
+	require.NotContains(t, names, "client.log", "active log should not be added by addRotatedLogFiles")
+	require.NotContains(t, names, "other.log", "unrelated files should not be in bundle")
+}
+
+// TestAddRotatedLogFiles_RespectsLogFileCount asserts that only the newest
+// logFileCount rotated files are bundled, ordered by mtime.
+func TestAddRotatedLogFiles_RespectsLogFileCount(t *testing.T) {
+	dir := t.TempDir()
+
+	oldest := filepath.Join(dir, "client.log.3")
+	middle := filepath.Join(dir, "client.log.2")
+	newest := filepath.Join(dir, "client.log.1")
+	writeFile(t, oldest, "old\n")
+	writeFile(t, middle, "mid\n")
+	writeFile(t, newest, "new\n")
+
+	now := time.Now()
+	require.NoError(t, os.Chtimes(oldest, now.Add(-2*time.Hour), now.Add(-2*time.Hour)))
+	require.NoError(t, os.Chtimes(middle, now.Add(-1*time.Hour), now.Add(-1*time.Hour)))
+	require.NoError(t, os.Chtimes(newest, now, now))
+
+	names := runAddRotatedLogFiles(t, dir, 2)
+
+	require.Contains(t, names, "client.log.1")
+	require.Contains(t, names, "client.log.2")
+	require.NotContains(t, names, "client.log.3", "oldest file should be dropped when logFileCount=2")
+}
+
+// runAddRotatedLogFiles calls addRotatedLogFiles against a fresh in-memory
+// zip writer and returns the set of entry names that ended up in the archive.
+func runAddRotatedLogFiles(t *testing.T, dir string, logFileCount uint32) map[string]struct{} {
+	t.Helper()
+
+	var buf bytes.Buffer
+	g := &BundleGenerator{
+		archive:      zip.NewWriter(&buf),
+		logFileCount: logFileCount,
+	}
+	g.addRotatedLogFiles(dir)
+	require.NoError(t, g.archive.Close())
+
+	zr, err := zip.NewReader(bytes.NewReader(buf.Bytes()), int64(buf.Len()))
+	require.NoError(t, err)
+
+	names := make(map[string]struct{}, len(zr.File))
+	for _, f := range zr.File {
+		names[f.Name] = struct{}{}
+	}
+	return names
+}
+
+func writeFile(t *testing.T, path, content string) {
+	t.Helper()
+	require.NoError(t, os.WriteFile(path, []byte(content), 0o644))
+}
+
+func writeGzFile(t *testing.T, path, content string) {
+	t.Helper()
+	var buf bytes.Buffer
+	gw := gzip.NewWriter(&buf)
+	_, err := io.WriteString(gw, content)
+	require.NoError(t, err)
+	require.NoError(t, gw.Close())
+	require.NoError(t, os.WriteFile(path, buf.Bytes(), 0o644))
+}

client/internal/debug/debug_test.go

@@ -843,6 +843,7 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		"PreSharedKey":      "sensitive: WireGuard pre-shared key",
 		"SSHKey":            "sensitive: SSH private key",
 		"ClientCertKeyPair": "non-config: parsed cert pair, not serialized",
+		"policy":            "non-config: in-memory MDM policy snapshot, surfaced via Config.Policy() / GetConfigResponse.MDMManagedFields",
 	}
 
 	mURL, _ := url.Parse("https://api.example.com:443")

client/internal/dns/handler_chain.go

@@ -339,8 +339,7 @@ func (c *HandlerChain) isHandlerMatch(qname string, entry HandlerEntry) bool {
 	case entry.Pattern == ".":
 		return true
 	case entry.IsWildcard:
-		parts := strings.Split(strings.TrimSuffix(qname, entry.Pattern), ".")
-		return len(parts) >= 2 && strings.HasSuffix(qname, entry.Pattern)
+		return strings.HasSuffix(qname, "."+entry.Pattern)
 	default:
 		// For non-wildcard patterns:
 		// If handler wants subdomain matching, allow suffix match

client/internal/dns/handler_chain_test.go

@@ -164,6 +164,54 @@ func TestHandlerChain_ServeDNS_DomainMatching(t *testing.T) {
 			matchSubdomains: true,
 			shouldMatch:     true,
 		},
+		{
+			name:            "wildcard label-boundary mismatch (suffix overlap)",
+			handlerDomain:   "*.b.test.",
+			queryDomain:     "x.ab.test.",
+			isWildcard:      true,
+			matchSubdomains: false,
+			shouldMatch:     false,
+		},
+		{
+			name:            "wildcard label-boundary match",
+			handlerDomain:   "*.b.test.",
+			queryDomain:     "x.b.test.",
+			isWildcard:      true,
+			matchSubdomains: false,
+			shouldMatch:     true,
+		},
+		{
+			name:            "wildcard multi-label match",
+			handlerDomain:   "*.b.test.",
+			queryDomain:     "x.y.b.test.",
+			isWildcard:      true,
+			matchSubdomains: false,
+			shouldMatch:     true,
+		},
+		{
+			name:            "wildcard no match on multi-label apex",
+			handlerDomain:   "*.b.test.",
+			queryDomain:     "b.test.",
+			isWildcard:      true,
+			matchSubdomains: false,
+			shouldMatch:     false,
+		},
+		{
+			name:            "wildcard no match on unrelated suffix containment",
+			handlerDomain:   "*.example.com.",
+			queryDomain:     "notexample.com.",
+			isWildcard:      true,
+			matchSubdomains: false,
+			shouldMatch:     false,
+		},
+		{
+			name:            "wildcard accepts pattern registered without trailing dot",
+			handlerDomain:   "*.b.test",
+			queryDomain:     "x.b.test.",
+			isWildcard:      true,
+			matchSubdomains: false,
+			shouldMatch:     true,
+		},
 	}
 
 	for _, tt := range tests {
@@ -273,6 +321,19 @@ func TestHandlerChain_ServeDNS_OverlappingDomains(t *testing.T) {
 			expectedCalls:   1,
 			expectedHandler: 2, // highest priority matching handler should be called
 		},
+		{
+			name: "overlapping wildcard suffixes route to correct handler",
+			handlers: []struct {
+				pattern  string
+				priority int
+			}{
+				{pattern: "*.b.test.", priority: nbdns.PriorityDNSRoute},
+				{pattern: "*.ab.test.", priority: nbdns.PriorityDNSRoute},
+			},
+			queryDomain:     "app.ab.test.",
+			expectedCalls:   1,
+			expectedHandler: 1,
+		},
 		{
 			name: "root zone with specific domain",
 			handlers: []struct {

client/internal/dns/host.go

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

client/internal/dns/host_android.go

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

client/internal/dns/host_ios.go

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

client/internal/dns/host_windows.go

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

client/internal/dns/hosts_dns_holder.go

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

client/internal/dns/local/local.go

@@ -26,6 +26,19 @@ type resolver interface {
 	LookupNetIP(ctx context.Context, network, host string) ([]netip.Addr, error)
 }
 
+// PeerConnectivity reports whether a tunnel IP belongs to a peer the
+// client knows about and whether that peer is currently connected. The
+// local resolver uses this to suppress A/AAAA answers whose RDATA points
+// at a disconnected peer (typical case: a synthesized private-service
+// record pointing at an embedded proxy peer that just went offline).
+//
+// known=false means the IP isn't in the local peerstore at all — the
+// 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)
+}
+
 type Resolver struct {
 	mu      sync.RWMutex
 	records map[dns.Question][]dns.RR
@@ -33,6 +46,11 @@ type Resolver struct {
 	// zones maps zone domain -> NonAuthoritative (true = non-authoritative, user-created zone)
 	zones    map[domain.Domain]bool
 	resolver resolver
+	// peerConn, when non-nil, is consulted on every A/AAAA answer to
+	// drop records pointing at disconnected peers. nil disables the
+	// filter and preserves the legacy "return whatever is registered"
+	// behaviour for callers that never wire a status source.
+	peerConn PeerConnectivity
 
 	ctx    context.Context
 	cancel context.CancelFunc
@@ -49,6 +67,15 @@ func NewResolver() *Resolver {
 	}
 }
 
+// SetPeerConnectivity wires the per-IP connectivity check used to filter
+// out A/AAAA answers pointing at disconnected peers. Pass nil to disable.
+// Safe to call multiple times; the latest value wins.
+func (d *Resolver) SetPeerConnectivity(p PeerConnectivity) {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+	d.peerConn = p
+}
+
 func (d *Resolver) MatchSubdomains() bool {
 	return true
 }
@@ -76,8 +103,6 @@ func (d *Resolver) ID() types.HandlerID {
 	return "local-resolver"
 }
 
-func (d *Resolver) ProbeAvailability(context.Context) {}
-
 // ServeDNS handles a DNS request
 func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	logger := log.WithFields(log.Fields{
@@ -97,6 +122,7 @@ func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	replyMessage.RecursionAvailable = true
 
 	result := d.lookupRecords(logger, question)
+	result.records = d.filterDisconnectedPeerAnswers(logger, question, result.records)
 	replyMessage.Authoritative = !result.hasExternalData
 	replyMessage.Answer = result.records
 	replyMessage.Rcode = d.determineRcode(question, result)
@@ -438,6 +464,78 @@ func (d *Resolver) logDNSError(logger *log.Entry, hostname string, qtype uint16,
 	}
 }
 
+// filterDisconnectedPeerAnswers drops A/AAAA records whose RDATA matches
+// a known but disconnected peer. The synthesized private-service zones
+// emit one A record per connected proxy peer in a cluster; when a peer
+// goes offline, the server-side refresh removes the record from the
+// next netmap, but the client may still hold the previous netmap for a
+// short window. This filter is the local belt to that braces — even on
+// the stale netmap, the resolver hides the offline target.
+//
+// Records pointing at unknown IPs (outside the local peerstore, e.g.
+// non-mesh upstreams) are never dropped. Non-A/AAAA records pass
+// through untouched.
+//
+// Escape hatch: if filtering would leave the answer empty AND at least
+// one record was filtered, the original list is returned. Better to
+// hand the client a record that may not respond than NXDOMAIN it
+// completely when every proxy peer is offline (the upstream may still
+// be reachable some other way, or the peerstore may be stale).
+func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns.Question, records []dns.RR) []dns.RR {
+	if len(records) < 2 {
+		return records
+	}
+	d.mu.RLock()
+	checker := d.peerConn
+	d.mu.RUnlock()
+	if checker == nil {
+		return records
+	}
+
+	kept := make([]dns.RR, 0, len(records))
+	var dropped int
+	for _, rr := range records {
+		ip := extractRecordIP(rr)
+		if ip == "" {
+			kept = append(kept, rr)
+			continue
+		}
+		known, connected := checker.IsConnectedByIP(ip)
+		if known && !connected {
+			dropped++
+			continue
+		}
+		kept = append(kept, rr)
+	}
+	if dropped == 0 {
+		return records
+	}
+	if len(kept) == 0 {
+		logger.Debugf("all %d answers for %s point at disconnected peers; returning the original list", dropped, question.Name)
+		return records
+	}
+	logger.Tracef("dropped %d disconnected-peer answer(s) for %s, returning %d", dropped, question.Name, len(kept))
+	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 {
+	switch r := rr.(type) {
+	case *dns.A:
+		if r.A == nil {
+			return ""
+		}
+		return r.A.String()
+	case *dns.AAAA:
+		if r.AAAA == nil {
+			return ""
+		}
+		return r.AAAA.String()
+	}
+	return ""
+}
+
 // Update replaces all zones and their records
 func (d *Resolver) Update(customZones []nbdns.CustomZone) {
 	d.mu.Lock()

client/internal/dns/local/local_test.go

@@ -30,6 +30,21 @@ func (m *mockResolver) LookupNetIP(ctx context.Context, network, host string) ([
 	return nil, nil
 }
 
+// mockPeerConnectivity returns canned (known, connected) results per IP.
+// Used by the disconnected-peer filter tests below. IPs not in the map
+// are reported as unknown so the filter leaves them alone.
+type mockPeerConnectivity struct {
+	byIP map[string]struct{ known, connected bool }
+}
+
+func (m mockPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
+	v, ok := m.byIP[ip]
+	if !ok {
+		return false, false
+	}
+	return v.known, v.connected
+}
+
 func TestLocalResolver_ServeDNS(t *testing.T) {
 	recordA := nbdns.SimpleRecord{
 		Name:  "peera.netbird.cloud.",
@@ -2652,3 +2667,125 @@ func BenchmarkIsInManagedZone_ManyZones(b *testing.B) {
 		resolver.isInManagedZone(qname)
 	}
 }
+
+// TestLocalResolver_FilterDisconnectedPeerAnswers verifies the
+// connectivity-aware filtering layered on top of lookupRecords:
+// when an A record's IP belongs to a known peer that's disconnected,
+// the record is dropped from the answer. Records for unknown IPs pass
+// through. If filtering would empty the answer entirely and at least
+// one record was dropped, the original list is restored (escape hatch
+// for the "all proxies offline" case).
+func TestLocalResolver_FilterDisconnectedPeerAnswers(t *testing.T) {
+	zone := "svc.cluster.netbird."
+	connectedRec := nbdns.SimpleRecord{
+		Name:  zone,
+		Type:  int(dns.TypeA),
+		Class: nbdns.DefaultClass,
+		TTL:   5,
+		RData: "100.64.0.10",
+	}
+	disconnectedRec := nbdns.SimpleRecord{
+		Name:  zone,
+		Type:  int(dns.TypeA),
+		Class: nbdns.DefaultClass,
+		TTL:   5,
+		RData: "100.64.0.11",
+	}
+	unknownRec := nbdns.SimpleRecord{
+		Name:  zone,
+		Type:  int(dns.TypeA),
+		Class: nbdns.DefaultClass,
+		TTL:   5,
+		RData: "203.0.113.5",
+	}
+
+	type ipState struct{ known, connected bool }
+	tests := []struct {
+		name        string
+		records     []nbdns.SimpleRecord
+		connByIP    map[string]ipState
+		wantInOrder []string
+	}{
+		{
+			name:    "drops disconnected peer, keeps connected",
+			records: []nbdns.SimpleRecord{connectedRec, disconnectedRec},
+			connByIP: map[string]ipState{
+				"100.64.0.10": {known: true, connected: true},
+				"100.64.0.11": {known: true, connected: false},
+			},
+			wantInOrder: []string{"100.64.0.10"},
+		},
+		{
+			name:    "unknown IPs pass through untouched",
+			records: []nbdns.SimpleRecord{unknownRec, disconnectedRec},
+			connByIP: map[string]ipState{
+				"100.64.0.11": {known: true, connected: false},
+			},
+			wantInOrder: []string{"203.0.113.5"},
+		},
+		{
+			name:    "all disconnected falls back to original list",
+			records: []nbdns.SimpleRecord{disconnectedRec, connectedRec},
+			connByIP: map[string]ipState{
+				"100.64.0.10": {known: true, connected: false},
+				"100.64.0.11": {known: true, connected: false},
+			},
+			wantInOrder: []string{"100.64.0.11", "100.64.0.10"},
+		},
+		{
+			name:        "no checker wired returns all records",
+			records:     []nbdns.SimpleRecord{connectedRec, disconnectedRec},
+			connByIP:    nil,
+			wantInOrder: []string{"100.64.0.10", "100.64.0.11"},
+		},
+		{
+			// A single answer is never filtered: dropping it would only
+			// trigger the empty-answer escape hatch, so the fast path
+			// returns it untouched.
+			name:    "single disconnected answer passes through",
+			records: []nbdns.SimpleRecord{disconnectedRec},
+			connByIP: map[string]ipState{
+				"100.64.0.11": {known: true, connected: false},
+			},
+			wantInOrder: []string{"100.64.0.11"},
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			resolver := NewResolver()
+			if tc.connByIP != nil {
+				cm := mockPeerConnectivity{byIP: make(map[string]struct{ known, connected bool }, len(tc.connByIP))}
+				for ip, st := range tc.connByIP {
+					cm.byIP[ip] = struct{ known, connected bool }{st.known, st.connected}
+				}
+				resolver.SetPeerConnectivity(cm)
+			}
+			resolver.Update([]nbdns.CustomZone{{
+				Domain:           strings.TrimSuffix(zone, "."),
+				Records:          tc.records,
+				NonAuthoritative: true,
+			}})
+
+			var got *dns.Msg
+			writer := &test.MockResponseWriter{
+				WriteMsgFunc: func(m *dns.Msg) error {
+					got = m
+					return nil
+				},
+			}
+			req := new(dns.Msg).SetQuestion(zone, dns.TypeA)
+			resolver.ServeDNS(writer, req)
+
+			require.NotNil(t, got, "resolver must produce a response")
+			require.Len(t, got.Answer, len(tc.wantInOrder),
+				"answer count must match expected: %v", tc.wantInOrder)
+			for i, want := range tc.wantInOrder {
+				a, ok := got.Answer[i].(*dns.A)
+				require.True(t, ok, "answer[%d] must be an A record", i)
+				assert.Equal(t, want, a.A.String(),
+					"answer[%d] expected %s got %s", i, want, a.A.String())
+			}
+		})
+	}
+}

client/internal/dns/mock_server.go

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

client/internal/dns/network_manager_unix.go

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

client/internal/dns/resutil/resolve.go

@@ -14,6 +14,10 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
+// errNoSuitableAddress mirrors the unexported error string the net package
+// uses when a resolved host has no addresses of the requested family.
+const errNoSuitableAddress = "no suitable address found"
+
 // GenerateRequestID creates a random 8-character hex string for request tracing.
 func GenerateRequestID() string {
 	bytes := make([]byte, 4)
@@ -126,6 +130,14 @@ func LookupIP(ctx context.Context, r resolver, network, host string, qtype uint1
 }
 
 func getRcodeForError(ctx context.Context, r resolver, host string, qtype uint16, err error) int {
+	// The net package returns this AddrError when the host resolves but has
+	// no addresses of the requested family. The domain exists, so answer
+	// NODATA instead of SERVFAIL.
+	var addrErr *net.AddrError
+	if errors.As(err, &addrErr) && addrErr.Err == errNoSuitableAddress {
+		return dns.RcodeSuccess
+	}
+
 	var dnsErr *net.DNSError
 	if !errors.As(err, &dnsErr) {
 		return dns.RcodeServerFailure

client/internal/dns/resutil/resolve_test.go

@@ -0,0 +1,122 @@
+package resutil
+
+import (
+	"context"
+	"errors"
+	"net"
+	"net/netip"
+	"testing"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+type mockResolver struct {
+	// results maps network ("ip4"/"ip6") to the lookup outcome.
+	results map[string]mockLookup
+}
+
+type mockLookup struct {
+	ips []netip.Addr
+	err error
+}
+
+func (m *mockResolver) LookupNetIP(_ context.Context, network, _ string) ([]netip.Addr, error) {
+	res, ok := m.results[network]
+	if !ok {
+		return nil, errors.New("unexpected network: " + network)
+	}
+	return res.ips, res.err
+}
+
+func TestLookupIP_Success(t *testing.T) {
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip4": {ips: []netip.Addr{netip.MustParseAddr("::ffff:192.0.2.1")}},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip4", "example.com.", dns.TypeA)
+
+	assert.Equal(t, dns.RcodeSuccess, result.Rcode, "successful lookup should return NOERROR")
+	require.Len(t, result.IPs, 1, "should return the resolved address")
+	assert.Equal(t, netip.MustParseAddr("192.0.2.1"), result.IPs[0], "v4-mapped address should be unmapped")
+}
+
+func TestLookupIP_NoSuitableAddress(t *testing.T) {
+	// The net package returns this AddrError when the host resolves but has
+	// no addresses of the requested family (e.g. AAAA query for a v4-only
+	// hosts file entry). The domain exists, so this is NODATA, not SERVFAIL.
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip6": {err: &net.AddrError{Err: "no suitable address found", Addr: "example.com."}},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip6", "example.com.", dns.TypeAAAA)
+
+	assert.Equal(t, dns.RcodeSuccess, result.Rcode, "no suitable address should map to NODATA")
+	assert.Empty(t, result.IPs, "NODATA response should carry no addresses")
+}
+
+// TestErrNoSuitableAddressMatchesNetPackage pins our copy of the error string
+// to what the net package actually emits. A literal IP of the wrong family
+// takes the same filterAddrList path as a resolved hostname, without network
+// access.
+func TestErrNoSuitableAddressMatchesNetPackage(t *testing.T) {
+	_, err := (&net.Resolver{}).LookupNetIP(context.Background(), "ip6", "192.0.2.1")
+	require.Error(t, err)
+
+	var addrErr *net.AddrError
+	require.ErrorAs(t, err, &addrErr, "wrong-family lookup should return AddrError")
+	assert.Equal(t, errNoSuitableAddress, addrErr.Err, "net package error string should match our constant")
+}
+
+func TestLookupIP_OtherAddrError(t *testing.T) {
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip4": {err: &net.AddrError{Err: "some other address problem", Addr: "example.com."}},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip4", "example.com.", dns.TypeA)
+
+	assert.Equal(t, dns.RcodeServerFailure, result.Rcode, "unrecognized AddrError should map to SERVFAIL")
+}
+
+func TestLookupIP_NotFoundNXDomain(t *testing.T) {
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip4": {err: &net.DNSError{Err: "no such host", Name: "example.com.", IsNotFound: true}},
+		"ip6": {err: &net.DNSError{Err: "no such host", Name: "example.com.", IsNotFound: true}},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip4", "example.com.", dns.TypeA)
+
+	assert.Equal(t, dns.RcodeNameError, result.Rcode, "not found for both families should map to NXDOMAIN")
+}
+
+func TestLookupIP_NotFoundNoData(t *testing.T) {
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip6": {err: &net.DNSError{Err: "no such host", Name: "example.com.", IsNotFound: true}},
+		"ip4": {ips: []netip.Addr{netip.MustParseAddr("192.0.2.1")}},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip6", "example.com.", dns.TypeAAAA)
+
+	assert.Equal(t, dns.RcodeSuccess, result.Rcode, "not found with the other family present should map to NODATA")
+}
+
+func TestLookupIP_GenericError(t *testing.T) {
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip4": {err: errors.New("connection refused")},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip4", "example.com.", dns.TypeA)
+
+	assert.Equal(t, dns.RcodeServerFailure, result.Rcode, "generic error should map to SERVFAIL")
+}
+
+func TestLookupIP_DNSErrorNotIsNotFound(t *testing.T) {
+	r := &mockResolver{results: map[string]mockLookup{
+		"ip4": {err: &net.DNSError{Err: "server misbehaving", Name: "example.com.", IsTemporary: true}},
+	}}
+
+	result := LookupIP(context.Background(), r, "ip4", "example.com.", dns.TypeA)
+
+	assert.Equal(t, dns.RcodeServerFailure, result.Rcode, "upstream failure should map to SERVFAIL")
+}

client/internal/dns/server_android.go

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

client/internal/dns/server_privileged_test.go

@@ -0,0 +1,501 @@
+//go:build privileged
+
+package dns
+
+import (
+	"context"
+	"fmt"
+	"net/netip"
+	"os"
+	"testing"
+
+	"github.com/golang/mock/gomock"
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+
+	"github.com/netbirdio/netbird/client/iface"
+	pfmock "github.com/netbirdio/netbird/client/iface/mocks"
+	"github.com/netbirdio/netbird/client/iface/wgaddr"
+	"github.com/netbirdio/netbird/client/internal/dns/local"
+	"github.com/netbirdio/netbird/client/internal/dns/test"
+	"github.com/netbirdio/netbird/client/internal/peer"
+	"github.com/netbirdio/netbird/client/internal/stdnet"
+	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/shared/management/domain"
+)
+
+func generateDummyHandler(d string, servers []nbdns.NameServer) *upstreamResolverBase {
+	var srvs []netip.AddrPort
+	for _, srv := range servers {
+		srvs = append(srvs, srv.AddrPort())
+	}
+	u := &upstreamResolverBase{
+		domain: domain.Domain(d),
+		cancel: func() {},
+	}
+	u.addRace(srvs)
+	return u
+}
+
+func TestUpdateDNSServer(t *testing.T) {
+
+	nameServers := []nbdns.NameServer{
+		{
+			IP:     netip.MustParseAddr("8.8.8.8"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+		{
+			IP:     netip.MustParseAddr("8.8.4.4"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+	}
+
+	dummyHandler := local.NewResolver()
+
+	testCases := []struct {
+		name                string
+		initUpstreamMap     registeredHandlerMap
+		initLocalZones      []nbdns.CustomZone
+		initSerial          uint64
+		inputSerial         uint64
+		inputUpdate         nbdns.Config
+		shouldFail          bool
+		expectedUpstreamMap registeredHandlerMap
+		expectedLocalQs     []dns.Question
+	}{
+		{
+			name:            "Initial Config Should Succeed",
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						Domains:     []string{"netbird.io"},
+						NameServers: nameServers,
+					},
+					{
+						NameServers: nameServers,
+						Primary:     true,
+					},
+				},
+			},
+			expectedUpstreamMap: registeredHandlerMap{
+				generateDummyHandler("netbird.io", nameServers).ID(): handlerWrapper{
+					domain:   "netbird.io",
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+				dummyHandler.ID(): handlerWrapper{
+					domain:   "netbird.cloud",
+					handler:  dummyHandler,
+					priority: PriorityLocal,
+				},
+				generateDummyHandler(".", nameServers).ID(): handlerWrapper{
+					domain:   nbdns.RootZone,
+					handler:  dummyHandler,
+					priority: PriorityDefault,
+				},
+			},
+			expectedLocalQs: []dns.Question{{Name: "peera.netbird.cloud.", Qtype: dns.TypeA, Qclass: dns.ClassINET}},
+		},
+		{
+			name:           "New Config Should Succeed",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
+			initUpstreamMap: registeredHandlerMap{
+				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+					domain:   "netbird.cloud",
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+			},
+			initSerial:  0,
+			inputSerial: 1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						Domains:     []string{"netbird.io"},
+						NameServers: nameServers,
+					},
+				},
+			},
+			expectedUpstreamMap: registeredHandlerMap{
+				generateDummyHandler("netbird.io", nameServers).ID(): handlerWrapper{
+					domain:   "netbird.io",
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+				"local-resolver": handlerWrapper{
+					domain:   "netbird.cloud",
+					handler:  dummyHandler,
+					priority: PriorityLocal,
+				},
+			},
+			expectedLocalQs: []dns.Question{{Name: zoneRecords[0].Name, Qtype: 1, Qclass: 1}},
+		},
+		{
+			name:            "Smaller Config Serial Should Be Skipped",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      2,
+			inputSerial:     1,
+			shouldFail:      true,
+		},
+		{
+			name:            "Empty NS Group Domain Or Not Primary Element Should Fail",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						NameServers: nameServers,
+					},
+				},
+			},
+			shouldFail: true,
+		},
+		{
+			name:            "Invalid NS Group Nameservers list Should Fail",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						NameServers: nameServers,
+					},
+				},
+			},
+			shouldFail: true,
+		},
+		{
+			name:            "Invalid Custom Zone Records list Should Skip",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain: "netbird.cloud",
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						NameServers: nameServers,
+						Primary:     true,
+					},
+				},
+			},
+			expectedUpstreamMap: registeredHandlerMap{generateDummyHandler(".", nameServers).ID(): handlerWrapper{
+				domain:   ".",
+				handler:  dummyHandler,
+				priority: PriorityDefault,
+			}},
+		},
+		{
+			name:           "Empty Config Should Succeed and Clean Maps",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
+			initUpstreamMap: registeredHandlerMap{
+				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+					domain:   zoneRecords[0].Name,
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+			},
+			initSerial:          0,
+			inputSerial:         1,
+			inputUpdate:         nbdns.Config{ServiceEnable: true},
+			expectedUpstreamMap: make(registeredHandlerMap),
+			expectedLocalQs:     []dns.Question{},
+		},
+		{
+			name:           "Disabled Service Should clean map",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
+			initUpstreamMap: registeredHandlerMap{
+				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+					domain:   zoneRecords[0].Name,
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+			},
+			initSerial:          0,
+			inputSerial:         1,
+			inputUpdate:         nbdns.Config{ServiceEnable: false},
+			expectedUpstreamMap: make(registeredHandlerMap),
+			expectedLocalQs:     []dns.Question{},
+		},
+	}
+
+	for n, testCase := range testCases {
+		t.Run(testCase.name, func(t *testing.T) {
+			privKey, _ := wgtypes.GenerateKey()
+			newNet, err := stdnet.NewNet(context.Background(), nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			opts := iface.WGIFaceOpts{
+				IFaceName:    fmt.Sprintf("utun230%d", n),
+				Address:      wgaddr.MustParseWGAddress(fmt.Sprintf("100.66.100.%d/32", n+1)),
+				WGPort:       33100,
+				WGPrivKey:    privKey.String(),
+				MTU:          iface.DefaultMTU,
+				TransportNet: newNet,
+			}
+
+			wgIface, err := iface.NewWGIFace(opts)
+			if err != nil {
+				t.Fatal(err)
+			}
+			err = wgIface.Create()
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer func() {
+				err = wgIface.Close()
+				if err != nil {
+					t.Log(err)
+				}
+			}()
+			dnsServer, err := NewDefaultServer(context.Background(), DefaultServerConfig{
+				WgInterface:    wgIface,
+				CustomAddress:  "",
+				StatusRecorder: peer.NewRecorder("mgm"),
+				StateManager:   nil,
+				DisableSys:     false,
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			err = dnsServer.Initialize()
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer func() {
+				err = dnsServer.hostManager.restoreHostDNS()
+				if err != nil {
+					t.Log(err)
+				}
+			}()
+
+			dnsServer.dnsMuxMap = testCase.initUpstreamMap
+			dnsServer.localResolver.Update(testCase.initLocalZones)
+			dnsServer.updateSerial = testCase.initSerial
+
+			err = dnsServer.UpdateDNSServer(testCase.inputSerial, testCase.inputUpdate)
+			if err != nil {
+				if testCase.shouldFail {
+					return
+				}
+				t.Fatalf("update dns server should not fail, got error: %v", err)
+			}
+
+			if len(dnsServer.dnsMuxMap) != len(testCase.expectedUpstreamMap) {
+				t.Fatalf("update upstream failed, map size is different than expected, want %d, got %d", len(testCase.expectedUpstreamMap), len(dnsServer.dnsMuxMap))
+			}
+
+			for key := range testCase.expectedUpstreamMap {
+				_, found := dnsServer.dnsMuxMap[key]
+				if !found {
+					t.Fatalf("update upstream failed, key %s was not found in the dnsMuxMap: %#v", key, dnsServer.dnsMuxMap)
+				}
+			}
+
+			var responseMSG *dns.Msg
+			responseWriter := &test.MockResponseWriter{
+				WriteMsgFunc: func(m *dns.Msg) error {
+					responseMSG = m
+					return nil
+				},
+			}
+			for _, q := range testCase.expectedLocalQs {
+				dnsServer.localResolver.ServeDNS(responseWriter, &dns.Msg{
+					Question: []dns.Question{q},
+				})
+			}
+
+			if len(testCase.expectedLocalQs) > 0 {
+				assert.NotNil(t, responseMSG, "response message should not be nil")
+				assert.Equal(t, dns.RcodeSuccess, responseMSG.Rcode, "response code should be success")
+				assert.NotEmpty(t, responseMSG.Answer, "response message should have answers")
+			}
+		})
+	}
+}
+
+func TestDNSFakeResolverHandleUpdates(t *testing.T) {
+	ov := os.Getenv("NB_WG_KERNEL_DISABLED")
+	defer t.Setenv("NB_WG_KERNEL_DISABLED", ov)
+
+	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	newNet, err := stdnet.NewNet(context.Background(), []string{"utun2301"})
+	if err != nil {
+		t.Errorf("create stdnet: %v", err)
+		return
+	}
+
+	privKey, _ := wgtypes.GeneratePrivateKey()
+	opts := iface.WGIFaceOpts{
+		IFaceName:    "utun2301",
+		Address:      wgaddr.MustParseWGAddress("100.66.100.1/32"),
+		WGPort:       33100,
+		WGPrivKey:    privKey.String(),
+		MTU:          iface.DefaultMTU,
+		TransportNet: newNet,
+	}
+	wgIface, err := iface.NewWGIFace(opts)
+	if err != nil {
+		t.Errorf("build interface wireguard: %v", err)
+		return
+	}
+
+	err = wgIface.Create()
+	if err != nil {
+		t.Errorf("create and init wireguard interface: %v", err)
+		return
+	}
+	defer func() {
+		if err = wgIface.Close(); err != nil {
+			t.Logf("close wireguard interface: %v", err)
+		}
+	}()
+
+	ctrl := gomock.NewController(t)
+	defer ctrl.Finish()
+
+	packetfilter := pfmock.NewMockPacketFilter(ctrl)
+	packetfilter.EXPECT().FilterOutbound(gomock.Any(), gomock.Any()).AnyTimes()
+	packetfilter.EXPECT().SetUDPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
+	packetfilter.EXPECT().SetTCPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
+
+	if err := wgIface.SetFilter(packetfilter); err != nil {
+		t.Errorf("set packet filter: %v", err)
+		return
+	}
+
+	dnsServer, err := NewDefaultServer(context.Background(), DefaultServerConfig{
+		WgInterface:    wgIface,
+		CustomAddress:  "",
+		StatusRecorder: peer.NewRecorder("mgm"),
+		StateManager:   nil,
+		DisableSys:     false,
+	})
+	if err != nil {
+		t.Errorf("create DNS server: %v", err)
+		return
+	}
+
+	err = dnsServer.Initialize()
+	if err != nil {
+		t.Errorf("run DNS server: %v", err)
+		return
+	}
+	defer func() {
+		if err = dnsServer.hostManager.restoreHostDNS(); err != nil {
+			t.Logf("restore DNS settings on the host: %v", err)
+			return
+		}
+	}()
+
+	dnsServer.dnsMuxMap = registeredHandlerMap{
+		"id1": handlerWrapper{
+			domain:   zoneRecords[0].Name,
+			handler:  &local.Resolver{},
+			priority: PriorityUpstream,
+		},
+	}
+	dnsServer.localResolver.Update([]nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}})
+	dnsServer.updateSerial = 0
+
+	nameServers := []nbdns.NameServer{
+		{
+			IP:     netip.MustParseAddr("8.8.8.8"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+		{
+			IP:     netip.MustParseAddr("8.8.4.4"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+	}
+
+	update := nbdns.Config{
+		ServiceEnable: true,
+		CustomZones: []nbdns.CustomZone{
+			{
+				Domain:  "netbird.cloud",
+				Records: zoneRecords,
+			},
+		},
+		NameServerGroups: []*nbdns.NameServerGroup{
+			{
+				Domains:     []string{"netbird.io"},
+				NameServers: nameServers,
+			},
+			{
+				NameServers: nameServers,
+				Primary:     true,
+			},
+		},
+	}
+
+	// Start the server with regular configuration
+	if err := dnsServer.UpdateDNSServer(1, update); err != nil {
+		t.Fatalf("update dns server should not fail, got error: %v", err)
+		return
+	}
+
+	update2 := update
+	update2.ServiceEnable = false
+	// Disable the server, stop the listener
+	if err := dnsServer.UpdateDNSServer(2, update2); err != nil {
+		t.Fatalf("update dns server should not fail, got error: %v", err)
+		return
+	}
+
+	update3 := update2
+	update3.NameServerGroups = update3.NameServerGroups[:1]
+	// But service still get updates and we checking that we handle
+	// internal state in the right way
+	if err := dnsServer.UpdateDNSServer(3, update3); err != nil {
+		t.Fatalf("update dns server should not fail, got error: %v", err)
+		return
+	}
+}

client/internal/dns/systemd_linux.go

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

client/internal/dns/upstream.go

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

client/internal/dns/upstream_android.go

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

client/internal/dns/upstream_general.go

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

client/internal/dns/upstream_ios.go

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

client/internal/dns/upstream_test.go

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

client/internal/engine.go

@@ -22,7 +22,6 @@ import (
 	log "github.com/sirupsen/logrus"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-	"google.golang.org/protobuf/proto"
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
 	"github.com/netbirdio/netbird/client/firewall"
@@ -56,6 +55,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/routemanager"
 	"github.com/netbirdio/netbird/client/internal/routemanager/systemops"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
+	"github.com/netbirdio/netbird/client/internal/syncstore"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/jobexec"
 	cProto "github.com/netbirdio/netbird/client/proto"
@@ -72,6 +72,7 @@ import (
 	sProto "github.com/netbirdio/netbird/shared/signal/proto"
 	"github.com/netbirdio/netbird/util"
 	"github.com/netbirdio/netbird/util/capture"
+	"github.com/netbirdio/netbird/version"
 )
 
 // PeerConnectionTimeoutMax is a timeout of an initial connection attempt to a remote peer.
@@ -148,6 +149,10 @@ type EngineConfig struct {
 
 	LogPath string
 	TempDir string
+
+	// StateDir is the directory holding the state file. The sync response
+	// (network map) is serialized here on platforms that persist it to disk.
+	StateDir string
 }
 
 // EngineServices holds the external service dependencies required by the Engine.
@@ -226,10 +231,15 @@ type Engine struct {
 
 	afpacketCapture *capture.AFPacketCapture
 
-	// Sync response persistence (protected by syncRespMux)
-	syncRespMux         sync.RWMutex
-	persistSyncResponse bool
-	latestSyncResponse  *mgmProto.SyncResponse
+	// Sync response persistence (protected by syncRespMux).
+	// syncStore is nil unless persistence has been enabled; its presence is
+	// what marks persistence as active. The backend (disk or memory) is
+	// selected per-platform; see the syncstore package. syncStoreDir is where
+	// a disk-backed store serializes to.
+	syncRespMux  sync.RWMutex
+	syncStore    syncstore.Store
+	syncStoreDir string
+
 	flowManager         nftypes.FlowManager
 
 	// auto-update
@@ -292,6 +302,7 @@ func NewEngine(
 		jobExecutor:        jobexec.NewExecutor(),
 		clientMetrics:      services.ClientMetrics,
 		updateManager:      services.UpdateManager,
+		syncStoreDir:       config.StateDir,
 	}
 
 	log.Infof("I am: %s", config.WgPrivateKey.PublicKey().String())
@@ -512,16 +523,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 
 	e.routeManager.SetRouteChangeListener(e.mobileDep.NetworkChangeListener)
 
-	e.dnsServer.SetRouteChecker(func(ip netip.Addr) bool {
-		for _, routes := range e.routeManager.GetSelectedClientRoutes() {
-			for _, r := range routes {
-				if r.Network.Contains(ip) {
-					return true
-				}
-			}
-		}
-		return false
-	})
+	e.dnsServer.SetRouteSources(e.routeManager.GetSelectedClientRoutes, e.routeManager.GetActiveClientRoutes)
 
 	if err = e.wgInterfaceCreate(); err != nil {
 		log.Errorf("failed creating tunnel interface %s: [%s]", e.config.WgIfaceName, err.Error())
@@ -878,63 +880,25 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		e.handleAutoUpdateVersion(update.NetworkMap.PeerConfig.AutoUpdate)
 	}
 
-	if update.GetNetbirdConfig() != nil {
-		wCfg := update.GetNetbirdConfig()
-		err := e.updateTURNs(wCfg.GetTurns())
-		if err != nil {
-			return fmt.Errorf("update TURNs: %w", err)
-		}
+	if err := e.updateNetbirdConfig(update.GetNetbirdConfig()); err != nil {
+		return err
+	}
 
-		err = e.updateSTUNs(wCfg.GetStuns())
-		if err != nil {
-			return fmt.Errorf("update STUNs: %w", err)
-		}
-
-		var stunTurn []*stun.URI
-		stunTurn = append(stunTurn, e.STUNs...)
-		stunTurn = append(stunTurn, e.TURNs...)
-		e.stunTurn.Store(stunTurn)
-
-		err = e.handleRelayUpdate(wCfg.GetRelay())
-		if err != nil {
-			return err
-		}
-
-		err = e.handleFlowUpdate(wCfg.GetFlow())
-		if err != nil {
-			return fmt.Errorf("handle the flow configuration: %w", err)
-		}
-
-		if err := e.PopulateNetbirdConfig(wCfg, nil); err != nil {
-			log.Warnf("Failed to update DNS server config: %v", err)
-		}
-
-		// todo update signal
+	// 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
 	}
 
 	if err := e.updateChecksIfNew(update.Checks); err != nil {
 		return err
 	}
 
-	nm := update.GetNetworkMap()
-	if nm == nil {
-		return nil
-	}
-
-	// Persist sync response under the dedicated lock (syncRespMux), not under syncMsgMux.
-	// Read the storage-enabled flag under the syncRespMux too.
-	e.syncRespMux.RLock()
-	enabled := e.persistSyncResponse
-	e.syncRespMux.RUnlock()
-
-	// Store sync response if persistence is enabled
-	if enabled {
-		e.syncRespMux.Lock()
-		e.latestSyncResponse = update
-		e.syncRespMux.Unlock()
-
-		log.Debugf("sync response persisted with serial %d", nm.GetSerial())
-	}
+	e.persistSyncResponse(update)
 
 	// only apply new changes and ignore old ones
 	if err := e.updateNetworkMap(nm); err != nil {
@@ -946,6 +910,64 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	return nil
 }
 
+// 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.
+func (e *Engine) updateNetbirdConfig(wCfg *mgmProto.NetbirdConfig) error {
+	if wCfg == nil {
+		return nil
+	}
+
+	if err := e.updateTURNs(wCfg.GetTurns()); err != nil {
+		return fmt.Errorf("update TURNs: %w", err)
+	}
+
+	if err := e.updateSTUNs(wCfg.GetStuns()); err != nil {
+		return fmt.Errorf("update STUNs: %w", err)
+	}
+
+	var stunTurn []*stun.URI
+	stunTurn = append(stunTurn, e.STUNs...)
+	stunTurn = append(stunTurn, e.TURNs...)
+	e.stunTurn.Store(stunTurn)
+
+	if err := e.handleRelayUpdate(wCfg.GetRelay()); err != nil {
+		return err
+	}
+
+	if err := e.handleFlowUpdate(wCfg.GetFlow()); err != nil {
+		return fmt.Errorf("handle the flow configuration: %w", err)
+	}
+
+	if err := e.PopulateNetbirdConfig(wCfg, nil); err != nil {
+		log.Warnf("Failed to update DNS server config: %v", err)
+	}
+
+	// todo update signal
+
+	return nil
+}
+
+// persistSyncResponse stores the full sync response so it can be restored on the next
+// startup. Persistence is enabled only when syncStore is set. The dedicated syncRespMux
+// (not syncMsgMux) is held for the whole Set so the store cannot be cleared (disabled /
+// engine close) mid-call and have this write resurrect a file that was just removed.
+func (e *Engine) persistSyncResponse(update *mgmProto.SyncResponse) {
+	e.syncRespMux.RLock()
+	defer e.syncRespMux.RUnlock()
+
+	if e.syncStore == nil {
+		return
+	}
+
+	if err := e.syncStore.Set(update); err != nil {
+		log.Errorf("failed to persist sync response: %v", err)
+		return
+	}
+
+	log.Debugf("sync response persisted with serial %d", update.GetNetworkMap().GetSerial())
+}
+
 func (e *Engine) handleRelayUpdate(update *mgmProto.RelayConfig) error {
 	if update != nil {
 		// when we receive token we expect valid address list too
@@ -1072,6 +1094,7 @@ func (e *Engine) updateConfig(conf *mgmProto.PeerConfig) error {
 	state.PubKey = e.config.WgPrivateKey.PublicKey().String()
 	state.KernelInterface = !e.wgInterface.IsUserspaceBind()
 	state.FQDN = conf.GetFqdn()
+	state.WgPort = e.config.WgPort
 
 	e.statusRecorder.UpdateLocalPeerState(state)
 
@@ -1150,6 +1173,7 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR
 		LogPath:        e.config.LogPath,
 		TempDir:        e.config.TempDir,
 		ClientMetrics:  e.clientMetrics,
+		DaemonVersion:  version.NetbirdVersion(),
 		RefreshStatus: func() {
 			e.RunHealthProbes(true)
 		},
@@ -1386,9 +1410,6 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	e.networkSerial = serial
 
-	// Test received (upstream) servers for availability right away instead of upon usage.
-	// If no server of a server group responds this will disable the respective handler and retry later.
-	go e.dnsServer.ProbeAvailability()
 	return nil
 }
 
@@ -1825,6 +1846,18 @@ func (e *Engine) close() {
 	if err := e.portForwardManager.GracefullyStop(ctx); err != nil {
 		log.Warnf("failed to gracefully stop port forwarding manager: %s", err)
 	}
+
+	// Drop any persisted sync response so its network map does not linger on
+	// disk after the engine stops (and cannot leak into a later run).
+	e.syncRespMux.Lock()
+	store := e.syncStore
+	e.syncStore = nil
+	e.syncRespMux.Unlock()
+	if store != nil {
+		if err := store.Clear(); err != nil {
+			log.Warnf("failed to clear persisted sync response on close: %v", err)
+		}
+	}
 }
 
 func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, error) {
@@ -1932,7 +1965,7 @@ func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
 		return dnsServer, nil
 
 	case "ios":
-		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.mobileDep.HostDNSAddresses, e.statusRecorder, e.config.DisableDNS)
+		dnsServer := dns.NewDefaultServerIos(e.ctx, e.wgInterface, e.mobileDep.DnsManager, e.statusRecorder, e.config.DisableDNS)
 		return dnsServer, nil
 
 	default:
@@ -1979,6 +2012,29 @@ func (e *Engine) GetClientMetrics() *metrics.ClientMetrics {
 	return e.clientMetrics
 }
 
+// Performance bundles runtime-adjustable tunnel pool knobs.
+// See Engine.SetPerformance. Nil fields are ignored.
+type Performance struct {
+	PreallocatedBuffersPerPool *uint32
+}
+
+// SetPerformance applies the given tuning to this engine's live Device.
+func (e *Engine) SetPerformance(t Performance) error {
+	e.syncMsgMux.Lock()
+	defer e.syncMsgMux.Unlock()
+	if e.wgInterface == nil {
+		return fmt.Errorf("wg interface not initialized")
+	}
+	dev := e.wgInterface.GetWGDevice()
+	if dev == nil {
+		return fmt.Errorf("wg device not initialized")
+	}
+	if t.PreallocatedBuffersPerPool != nil {
+		dev.SetPreallocatedBuffersPerPool(*t.PreallocatedBuffersPerPool)
+	}
+	return nil
+}
+
 func findIPFromInterfaceName(ifaceName string) (net.IP, error) {
 	iface, err := net.InterfaceByName(ifaceName)
 	if err != nil {
@@ -2131,45 +2187,42 @@ func (e *Engine) stopDNSServer() {
 	e.statusRecorder.UpdateDNSStates(nsGroupStates)
 }
 
-// SetSyncResponsePersistence enables or disables sync response persistence
+// SetSyncResponsePersistence enables or disables sync response persistence.
+// The store is only instantiated while persistence is enabled; construction
+// itself drops any stale data left over from an earlier run (see syncstore).
 func (e *Engine) SetSyncResponsePersistence(enabled bool) {
 	e.syncRespMux.Lock()
 	defer e.syncRespMux.Unlock()
 
-	if enabled == e.persistSyncResponse {
+	if enabled == (e.syncStore != nil) {
 		return
 	}
-	e.persistSyncResponse = enabled
 	log.Debugf("Sync response persistence is set to %t", enabled)
 
 	if !enabled {
-		e.latestSyncResponse = nil
+		if err := e.syncStore.Clear(); err != nil {
+			log.Warnf("failed to clear persisted sync response: %v", err)
+		}
+		e.syncStore = nil
+		return
 	}
+
+	e.syncStore = syncstore.New(e.syncStoreDir)
 }
 
 // GetLatestSyncResponse returns the stored sync response if persistence is enabled
 func (e *Engine) GetLatestSyncResponse() (*mgmProto.SyncResponse, error) {
+	// Hold the lock for the whole Get so the store cannot be cleared
+	// (disabled / engine close) mid-call.
 	e.syncRespMux.RLock()
-	enabled := e.persistSyncResponse
-	latest := e.latestSyncResponse
-	e.syncRespMux.RUnlock()
+	defer e.syncRespMux.RUnlock()
 
-	if !enabled {
+	if e.syncStore == nil {
 		return nil, errors.New("sync response persistence is disabled")
 	}
 
-	if latest == nil {
-		//nolint:nilnil
-		return nil, nil
-	}
-
-	log.Debugf("Retrieving latest sync response with size %d bytes", proto.Size(latest))
-	sr, ok := proto.Clone(latest).(*mgmProto.SyncResponse)
-	if !ok {
-		return nil, fmt.Errorf("failed to clone sync response")
-	}
-
-	return sr, nil
+	//nolint:nilnil
+	return e.syncStore.Get()
 }
 
 // GetWgAddr returns the wireguard address
@@ -2205,7 +2258,7 @@ func (e *Engine) updateDNSForwarder(
 	enabled bool,
 	fwdEntries []*dnsfwd.ForwarderEntry,
 ) {
-	if e.config.DisableServerRoutes {
+	if e.config.DisableServerRoutes || e.config.BlockInbound {
 		return
 	}
 

client/internal/engine_privileged_test.go

@@ -0,0 +1,565 @@
+//go:build privileged
+
+package internal
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"runtime"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/golang/mock/gomock"
+	"github.com/google/uuid"
+	log "github.com/sirupsen/logrus"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.opentelemetry.io/otel"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/keepalive"
+
+	"github.com/netbirdio/netbird/client/iface"
+	"github.com/netbirdio/netbird/client/iface/device"
+	"github.com/netbirdio/netbird/client/iface/wgaddr"
+	"github.com/netbirdio/netbird/client/internal/dns"
+	"github.com/netbirdio/netbird/client/internal/peer"
+	nbssh "github.com/netbirdio/netbird/client/ssh"
+	"github.com/netbirdio/netbird/client/system"
+	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
+	"github.com/netbirdio/netbird/management/internals/controllers/network_map/update_channel"
+	"github.com/netbirdio/netbird/management/internals/modules/peers"
+	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral/manager"
+	"github.com/netbirdio/netbird/management/internals/server/config"
+	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
+	"github.com/netbirdio/netbird/management/server"
+	"github.com/netbirdio/netbird/management/server/activity"
+	nbcache "github.com/netbirdio/netbird/management/server/cache"
+	"github.com/netbirdio/netbird/management/server/groups"
+	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator/validator"
+	"github.com/netbirdio/netbird/management/server/integrations/port_forwarding"
+	"github.com/netbirdio/netbird/management/server/job"
+	"github.com/netbirdio/netbird/management/server/permissions"
+	"github.com/netbirdio/netbird/management/server/settings"
+	"github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/telemetry"
+	"github.com/netbirdio/netbird/management/server/types"
+	mgmt "github.com/netbirdio/netbird/shared/management/client"
+	mgmtProto "github.com/netbirdio/netbird/shared/management/proto"
+	relayClient "github.com/netbirdio/netbird/shared/relay/client"
+	signal "github.com/netbirdio/netbird/shared/signal/client"
+	"github.com/netbirdio/netbird/shared/signal/proto"
+	signalServer "github.com/netbirdio/netbird/signal/server"
+	"github.com/netbirdio/netbird/util"
+)
+
+func TestEngine_SSH(t *testing.T) {
+	key, err := wgtypes.GeneratePrivateKey()
+	if err != nil {
+		t.Fatal(err)
+		return
+	}
+
+	sshKey, err := nbssh.GeneratePrivateKey(nbssh.ED25519)
+	if err != nil {
+		t.Fatal(err)
+		return
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
+	engine := NewEngine(
+		ctx, cancel,
+		&EngineConfig{
+			WgIfaceName:      "utun101",
+			WgAddr:           wgaddr.MustParseWGAddress("100.64.0.1/24"),
+			WgPrivateKey:     key,
+			WgPort:           33100,
+			ServerSSHAllowed: true,
+			MTU:              iface.DefaultMTU,
+			SSHKey:           sshKey,
+		},
+		EngineServices{
+			SignalClient:   &signal.MockClient{},
+			MgmClient:      &mgmt.MockClient{},
+			RelayManager:   relayMgr,
+			StatusRecorder: peer.NewRecorder("https://mgm"),
+		},
+		MobileDependency{},
+	)
+
+	engine.dnsServer = &dns.MockServer{
+		UpdateDNSServerFunc: func(serial uint64, update nbdns.Config) error { return nil },
+	}
+
+	err = engine.Start(nil, nil)
+	require.NoError(t, err)
+
+	defer func() {
+		err := engine.Stop()
+		if err != nil {
+			return
+		}
+	}()
+
+	peerWithSSH := &mgmtProto.RemotePeerConfig{
+		WgPubKey:   "MNHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
+		AllowedIps: []string{"100.64.0.21/24"},
+		SshConfig: &mgmtProto.SSHConfig{
+			SshPubKey: []byte("ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFATYCqaQw/9id1Qkq3n16JYhDhXraI6Pc1fgB8ynEfQ"),
+		},
+	}
+
+	// SSH server is not enabled so SSH config of a remote peer should be ignored
+	networkMap := &mgmtProto.NetworkMap{
+		Serial:             6,
+		PeerConfig:         nil,
+		RemotePeers:        []*mgmtProto.RemotePeerConfig{peerWithSSH},
+		RemotePeersIsEmpty: false,
+	}
+
+	err = engine.updateNetworkMap(networkMap)
+	require.NoError(t, err)
+
+	assert.Nil(t, engine.sshServer)
+
+	// SSH server is enabled, therefore SSH config should be applied
+	networkMap = &mgmtProto.NetworkMap{
+		Serial: 7,
+		PeerConfig: &mgmtProto.PeerConfig{Address: "100.64.0.1/24",
+			SshConfig: &mgmtProto.SSHConfig{
+				SshEnabled: true,
+				JwtConfig: &mgmtProto.JWTConfig{
+					Issuer:       "test-issuer",
+					Audience:     "test-audience",
+					KeysLocation: "test-keys",
+					MaxTokenAge:  3600,
+				},
+			}},
+		RemotePeers:        []*mgmtProto.RemotePeerConfig{peerWithSSH},
+		RemotePeersIsEmpty: false,
+	}
+
+	err = engine.updateNetworkMap(networkMap)
+	require.NoError(t, err)
+
+	time.Sleep(250 * time.Millisecond)
+	assert.NotNil(t, engine.sshServer)
+
+	// now remove peer
+	networkMap = &mgmtProto.NetworkMap{
+		Serial:             8,
+		RemotePeers:        []*mgmtProto.RemotePeerConfig{},
+		RemotePeersIsEmpty: false,
+	}
+
+	err = engine.updateNetworkMap(networkMap)
+	require.NoError(t, err)
+
+	// time.Sleep(250 * time.Millisecond)
+	assert.NotNil(t, engine.sshServer)
+
+	// now disable SSH server
+	networkMap = &mgmtProto.NetworkMap{
+		Serial: 9,
+		PeerConfig: &mgmtProto.PeerConfig{Address: "100.64.0.1/24",
+			SshConfig: &mgmtProto.SSHConfig{SshEnabled: false}},
+		RemotePeers:        []*mgmtProto.RemotePeerConfig{peerWithSSH},
+		RemotePeersIsEmpty: false,
+	}
+
+	err = engine.updateNetworkMap(networkMap)
+	require.NoError(t, err)
+
+	assert.Nil(t, engine.sshServer)
+}
+
+func TestEngine_Sync(t *testing.T) {
+	key, err := wgtypes.GeneratePrivateKey()
+	if err != nil {
+		t.Fatal(err)
+		return
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	// feed updates to Engine via mocked Management client
+	updates := make(chan *mgmtProto.SyncResponse)
+	defer close(updates)
+	syncFunc := func(ctx context.Context, info *system.Info, msgHandler func(msg *mgmtProto.SyncResponse) error) error {
+		for msg := range updates {
+			err := msgHandler(msg)
+			if err != nil {
+				t.Fatal(err)
+			}
+		}
+		return nil
+	}
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
+	engine := NewEngine(ctx, cancel, &EngineConfig{
+		WgIfaceName:  "utun103",
+		WgAddr:       wgaddr.MustParseWGAddress("100.64.0.1/24"),
+		WgPrivateKey: key,
+		WgPort:       33100,
+		MTU:          iface.DefaultMTU,
+	}, EngineServices{
+		SignalClient:   &signal.MockClient{},
+		MgmClient:      &mgmt.MockClient{SyncFunc: syncFunc},
+		RelayManager:   relayMgr,
+		StatusRecorder: peer.NewRecorder("https://mgm"),
+	}, MobileDependency{})
+	engine.ctx = ctx
+
+	engine.dnsServer = &dns.MockServer{
+		UpdateDNSServerFunc: func(serial uint64, update nbdns.Config) error { return nil },
+	}
+
+	defer func() {
+		err := engine.Stop()
+		if err != nil {
+			return
+		}
+	}()
+
+	err = engine.Start(nil, nil)
+	if err != nil {
+		t.Fatal(err)
+		return
+	}
+
+	peer1 := &mgmtProto.RemotePeerConfig{
+		WgPubKey:   "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
+		AllowedIps: []string{"100.64.0.10/24"},
+	}
+	peer2 := &mgmtProto.RemotePeerConfig{
+		WgPubKey:   "LLHf3Ma6z6mdLbriAJbqhX9+nM/B71lgw2+91q3LlhU=",
+		AllowedIps: []string{"100.64.0.11/24"},
+	}
+	peer3 := &mgmtProto.RemotePeerConfig{
+		WgPubKey:   "GGHf3Ma6z6mdLbriAJbqhX9+nM/B71lgw2+91q3LlhU=",
+		AllowedIps: []string{"100.64.0.12/24"},
+	}
+	// 1st update with just 1 peer and serial larger than the current serial of the engine => apply update
+	updates <- &mgmtProto.SyncResponse{
+		NetworkMap: &mgmtProto.NetworkMap{
+			Serial:             10,
+			PeerConfig:         nil,
+			RemotePeers:        []*mgmtProto.RemotePeerConfig{peer1, peer2, peer3},
+			RemotePeersIsEmpty: false,
+		},
+	}
+
+	timeout := time.After(time.Second * 2)
+	for {
+		select {
+		case <-timeout:
+			t.Fatalf("timeout while waiting for test to finish")
+			return
+		default:
+		}
+
+		if getPeers(engine) == 3 && engine.networkSerial == 10 {
+			break
+		}
+	}
+}
+
+func TestEngine_MultiplePeers(t *testing.T) {
+	// log.SetLevel(log.DebugLevel)
+
+	ctx, cancel := context.WithCancel(CtxInitState(context.Background()))
+	defer cancel()
+
+	sigServer, signalAddr, err := startSignal(t)
+	if err != nil {
+		t.Fatal(err)
+		return
+	}
+	defer sigServer.Stop()
+	mgmtServer, mgmtAddr, err := startManagement(t, t.TempDir(), "../testdata/store.sql")
+	if err != nil {
+		t.Fatal(err)
+		return
+	}
+	defer mgmtServer.GracefulStop()
+
+	setupKey := "A2C8E62B-38F5-4553-B31E-DD66C696CEBB"
+
+	mu := sync.Mutex{}
+	engines := []*Engine{}
+	numPeers := 10
+	wg := sync.WaitGroup{}
+	wg.Add(numPeers)
+	// create and start peers
+	for i := 0; i < numPeers; i++ {
+		j := i
+		go func() {
+			engine, err := createEngine(ctx, cancel, setupKey, j, mgmtAddr, signalAddr)
+			if err != nil {
+				wg.Done()
+				t.Errorf("unable to create the engine for peer %d with error %v", j, err)
+				return
+			}
+			engine.dnsServer = &dns.MockServer{}
+			mu.Lock()
+			defer mu.Unlock()
+			guid := fmt.Sprintf("{%s}", uuid.New().String())
+			device.CustomWindowsGUIDString = strings.ToLower(guid)
+			err = engine.Start(nil, nil)
+			if err != nil {
+				t.Errorf("unable to start engine for peer %d with error %v", j, err)
+				wg.Done()
+				return
+			}
+			engines = append(engines, engine)
+			wg.Done()
+		}()
+	}
+
+	// wait until all have been created and started
+	wg.Wait()
+	if len(engines) != numPeers {
+		t.Fatal("not all peers was started")
+	}
+	// check whether all the peer have expected peers connected
+
+	expectedConnected := numPeers * (numPeers - 1)
+
+	// adjust according to timeouts
+	timeout := 50 * time.Second
+	timeoutChan := time.After(timeout)
+	ticker := time.NewTicker(time.Second)
+	defer ticker.Stop()
+loop:
+	for {
+		select {
+		case <-timeoutChan:
+			t.Fatalf("waiting for expected connections timeout after %s", timeout.String())
+			break loop
+		case <-ticker.C:
+			totalConnected := 0
+			for _, engine := range engines {
+				totalConnected += getConnectedPeers(engine)
+			}
+			if totalConnected == expectedConnected {
+				log.Infof("total connected=%d", totalConnected)
+				break loop
+			}
+			log.Infof("total connected=%d", totalConnected)
+		}
+	}
+	// cleanup test
+	for n, peerEngine := range engines {
+		t.Logf("stopping peer with interface %s from multipeer test, loopIndex %d", peerEngine.wgInterface.Name(), n)
+		errStop := peerEngine.mgmClient.Close()
+		if errStop != nil {
+			log.Infoln("got error trying to close management clients from engine: ", errStop)
+		}
+		errStop = peerEngine.Stop()
+		if errStop != nil {
+			log.Infoln("got error trying to close testing peers engine: ", errStop)
+		}
+	}
+}
+
+var (
+	kaep = keepalive.EnforcementPolicy{
+		MinTime:             15 * time.Second,
+		PermitWithoutStream: true,
+	}
+
+	kasp = keepalive.ServerParameters{
+		MaxConnectionIdle:     15 * time.Second,
+		MaxConnectionAgeGrace: 5 * time.Second,
+		Time:                  5 * time.Second,
+		Timeout:               2 * time.Second,
+	}
+)
+
+func createEngine(ctx context.Context, cancel context.CancelFunc, setupKey string, i int, mgmtAddr string, signalAddr string) (*Engine, error) {
+	key, err := wgtypes.GeneratePrivateKey()
+	if err != nil {
+		return nil, err
+	}
+	mgmtClient, err := mgmt.NewClient(ctx, mgmtAddr, key, false)
+	if err != nil {
+		return nil, err
+	}
+	signalClient, err := signal.NewClient(ctx, signalAddr, key, false)
+	if err != nil {
+		return nil, err
+	}
+
+	info := system.GetInfo(ctx)
+	resp, err := mgmtClient.Register(setupKey, "", info, nil, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	var ifaceName string
+	if runtime.GOOS == "darwin" {
+		ifaceName = fmt.Sprintf("utun1%d", i)
+	} else {
+		ifaceName = fmt.Sprintf("wt%d", i)
+	}
+
+	wgPort := 33100 + i
+	conf := &EngineConfig{
+		WgIfaceName:  ifaceName,
+		WgAddr:       wgaddr.MustParseWGAddress(resp.PeerConfig.Address),
+		WgPrivateKey: key,
+		WgPort:       wgPort,
+		MTU:          iface.DefaultMTU,
+	}
+
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
+	e, err := NewEngine(ctx, cancel, conf, EngineServices{
+		SignalClient:   signalClient,
+		MgmClient:      mgmtClient,
+		RelayManager:   relayMgr,
+		StatusRecorder: peer.NewRecorder("https://mgm"),
+	}, MobileDependency{}), nil
+	e.ctx = ctx
+	return e, err
+}
+
+func startSignal(t *testing.T) (*grpc.Server, string, error) {
+	t.Helper()
+
+	s := grpc.NewServer(grpc.KeepaliveEnforcementPolicy(kaep), grpc.KeepaliveParams(kasp))
+
+	lis, err := net.Listen("tcp", "localhost:0")
+	if err != nil {
+		log.Fatalf("failed to listen: %v", err)
+	}
+
+	srv, err := signalServer.NewServer(context.Background(), otel.Meter(""))
+	require.NoError(t, err)
+	proto.RegisterSignalExchangeServer(s, srv)
+
+	go func() {
+		if err = s.Serve(lis); err != nil {
+			log.Fatalf("failed to serve: %v", err)
+		}
+	}()
+
+	return s, lis.Addr().String(), nil
+}
+
+func startManagement(t *testing.T, dataDir, testFile string) (*grpc.Server, string, error) {
+	t.Helper()
+
+	config := &config.Config{
+		Stuns:      []*config.Host{},
+		TURNConfig: &config.TURNConfig{},
+		Relay: &config.Relay{
+			Addresses:      []string{"127.0.0.1:1234"},
+			CredentialsTTL: util.Duration{Duration: time.Hour},
+			Secret:         "222222222222222222",
+		},
+		Signal: &config.Host{
+			Proto: "http",
+			URI:   "localhost:10000",
+		},
+		Datadir:    dataDir,
+		HttpConfig: nil,
+	}
+
+	lis, err := net.Listen("tcp", "localhost:0")
+	if err != nil {
+		return nil, "", err
+	}
+	s := grpc.NewServer(grpc.KeepaliveEnforcementPolicy(kaep), grpc.KeepaliveParams(kasp))
+
+	store, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), testFile, config.Datadir)
+	if err != nil {
+		return nil, "", err
+	}
+	t.Cleanup(cleanUp)
+
+	eventStore := &activity.InMemoryEventStore{}
+	if err != nil {
+		return nil, "", err
+	}
+
+	permissionsManager := permissions.NewManager(store)
+	peersManager := peers.NewManager(store, permissionsManager)
+	jobManager := job.NewJobManager(nil, store, peersManager)
+
+	cacheStore, err := nbcache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
+	if err != nil {
+		return nil, "", err
+	}
+
+	ia, _ := validator.NewIntegratedValidator(context.Background(), peersManager, nil, eventStore, cacheStore)
+
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	ctrl := gomock.NewController(t)
+	t.Cleanup(ctrl.Finish)
+	settingsMockManager := settings.NewMockManager(ctrl)
+	settingsMockManager.EXPECT().
+		GetSettings(gomock.Any(), gomock.Any(), gomock.Any()).
+		Return(&types.Settings{}, nil).
+		AnyTimes()
+	settingsMockManager.EXPECT().
+		GetExtraSettings(gomock.Any(), gomock.Any()).
+		Return(&types.ExtraSettings{}, nil).
+		AnyTimes()
+
+	groupsManager := groups.NewManagerMock()
+
+	updateManager := update_channel.NewPeersUpdateManager(metrics)
+	requestBuffer := server.NewAccountRequestBuffer(context.Background(), store)
+	networkMapController := controller.NewController(context.Background(), store, metrics, updateManager, requestBuffer, server.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersManager), config)
+	accountManager, err := server.BuildManager(context.Background(), config, store, networkMapController, jobManager, nil, "", eventStore, nil, false, ia, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManager, false, cacheStore)
+	if err != nil {
+		return nil, "", err
+	}
+
+	secretsManager, err := nbgrpc.NewTimeBasedAuthSecretsManager(updateManager, config.TURNConfig, config.Relay, settingsMockManager, groupsManager)
+	if err != nil {
+		return nil, "", err
+	}
+	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, jobManager, secretsManager, nil, nil, &server.MockIntegratedValidator{}, networkMapController, nil, nil)
+	if err != nil {
+		return nil, "", err
+	}
+	mgmtProto.RegisterManagementServiceServer(s, mgmtServer)
+	go func() {
+		if err = s.Serve(lis); err != nil {
+			log.Fatalf("failed to serve: %v", err)
+		}
+	}()
+
+	return s, lis.Addr().String(), nil
+}
+
+// getConnectedPeers returns a connection Status or nil if peer connection wasn't found
+func getConnectedPeers(e *Engine) int {
+	e.syncMsgMux.Lock()
+	defer e.syncMsgMux.Unlock()
+	i := 0
+	for _, id := range e.peerStore.PeersPubKey() {
+		conn, _ := e.peerStore.PeerConn(id)
+		if conn.IsConnected() {
+			i++
+		}
+	}
+	return i
+}
+
+func getPeers(e *Engine) int {
+	e.syncMsgMux.Lock()
+	defer e.syncMsgMux.Unlock()
+
+	return len(e.peerStore.PeersPubKey())
+}

client/internal/engine_test.go

@@ -6,37 +6,18 @@ import (
 	"net"
 	"net/netip"
 	"os"
-	"runtime"
 	"strings"
 	"sync"
 	"testing"
 	"time"
 
-	"github.com/golang/mock/gomock"
-	"github.com/google/uuid"
-	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-	"go.opentelemetry.io/otel"
 	wgdevice "golang.zx2c4.com/wireguard/device"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/keepalive"
 
 	"github.com/netbirdio/netbird/client/internal/stdnet"
-	"github.com/netbirdio/netbird/management/server/job"
-
-	"github.com/netbirdio/management-integrations/integrations"
-
-	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
-	"github.com/netbirdio/netbird/management/internals/controllers/network_map/update_channel"
-	"github.com/netbirdio/netbird/management/internals/modules/peers"
-	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral/manager"
-	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
-
-	"github.com/netbirdio/netbird/management/internals/server/config"
-	"github.com/netbirdio/netbird/management/server/groups"
 
 	"github.com/netbirdio/netbird/client/iface"
 	"github.com/netbirdio/netbird/client/iface/configurer"
@@ -50,44 +31,17 @@ import (
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/routemanager"
-	nbssh "github.com/netbirdio/netbird/client/ssh"
-	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
-	"github.com/netbirdio/netbird/management/server"
-	"github.com/netbirdio/netbird/management/server/activity"
-	nbcache "github.com/netbirdio/netbird/management/server/cache"
-	"github.com/netbirdio/netbird/management/server/integrations/port_forwarding"
-	"github.com/netbirdio/netbird/management/server/permissions"
-	"github.com/netbirdio/netbird/management/server/settings"
-	"github.com/netbirdio/netbird/management/server/store"
-	"github.com/netbirdio/netbird/management/server/telemetry"
-	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/monotime"
 	"github.com/netbirdio/netbird/route"
 	mgmt "github.com/netbirdio/netbird/shared/management/client"
 	mgmtProto "github.com/netbirdio/netbird/shared/management/proto"
-	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 	"github.com/netbirdio/netbird/shared/netiputil"
+	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 	signal "github.com/netbirdio/netbird/shared/signal/client"
-	"github.com/netbirdio/netbird/shared/signal/proto"
-	signalServer "github.com/netbirdio/netbird/signal/server"
 	"github.com/netbirdio/netbird/util"
 )
 
-var (
-	kaep = keepalive.EnforcementPolicy{
-		MinTime:             15 * time.Second,
-		PermitWithoutStream: true,
-	}
-
-	kasp = keepalive.ServerParameters{
-		MaxConnectionIdle:     15 * time.Second,
-		MaxConnectionAgeGrace: 5 * time.Second,
-		Time:                  5 * time.Second,
-		Timeout:               2 * time.Second,
-	}
-)
-
 type MockWGIface struct {
 	CreateFunc                 func() error
 	CreateOnAndroidFunc        func(routeRange []string, ip string, domains []string) error
@@ -234,129 +188,6 @@ func TestMain(m *testing.M) {
 	os.Exit(code)
 }
 
-func TestEngine_SSH(t *testing.T) {
-	key, err := wgtypes.GeneratePrivateKey()
-	if err != nil {
-		t.Fatal(err)
-		return
-	}
-
-	sshKey, err := nbssh.GeneratePrivateKey(nbssh.ED25519)
-	if err != nil {
-		t.Fatal(err)
-		return
-	}
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-
-	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
-	engine := NewEngine(
-		ctx, cancel,
-		&EngineConfig{
-			WgIfaceName:      "utun101",
-			WgAddr:           wgaddr.MustParseWGAddress("100.64.0.1/24"),
-			WgPrivateKey:     key,
-			WgPort:           33100,
-			ServerSSHAllowed: true,
-			MTU:              iface.DefaultMTU,
-			SSHKey:           sshKey,
-		},
-		EngineServices{
-			SignalClient:   &signal.MockClient{},
-			MgmClient:      &mgmt.MockClient{},
-			RelayManager:   relayMgr,
-			StatusRecorder: peer.NewRecorder("https://mgm"),
-		},
-		MobileDependency{},
-	)
-
-	engine.dnsServer = &dns.MockServer{
-		UpdateDNSServerFunc: func(serial uint64, update nbdns.Config) error { return nil },
-	}
-
-	err = engine.Start(nil, nil)
-	require.NoError(t, err)
-
-	defer func() {
-		err := engine.Stop()
-		if err != nil {
-			return
-		}
-	}()
-
-	peerWithSSH := &mgmtProto.RemotePeerConfig{
-		WgPubKey:   "MNHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
-		AllowedIps: []string{"100.64.0.21/24"},
-		SshConfig: &mgmtProto.SSHConfig{
-			SshPubKey: []byte("ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIFATYCqaQw/9id1Qkq3n16JYhDhXraI6Pc1fgB8ynEfQ"),
-		},
-	}
-
-	// SSH server is not enabled so SSH config of a remote peer should be ignored
-	networkMap := &mgmtProto.NetworkMap{
-		Serial:             6,
-		PeerConfig:         nil,
-		RemotePeers:        []*mgmtProto.RemotePeerConfig{peerWithSSH},
-		RemotePeersIsEmpty: false,
-	}
-
-	err = engine.updateNetworkMap(networkMap)
-	require.NoError(t, err)
-
-	assert.Nil(t, engine.sshServer)
-
-	// SSH server is enabled, therefore SSH config should be applied
-	networkMap = &mgmtProto.NetworkMap{
-		Serial: 7,
-		PeerConfig: &mgmtProto.PeerConfig{Address: "100.64.0.1/24",
-			SshConfig: &mgmtProto.SSHConfig{
-				SshEnabled: true,
-				JwtConfig: &mgmtProto.JWTConfig{
-					Issuer:       "test-issuer",
-					Audience:     "test-audience",
-					KeysLocation: "test-keys",
-					MaxTokenAge:  3600,
-				},
-			}},
-		RemotePeers:        []*mgmtProto.RemotePeerConfig{peerWithSSH},
-		RemotePeersIsEmpty: false,
-	}
-
-	err = engine.updateNetworkMap(networkMap)
-	require.NoError(t, err)
-
-	time.Sleep(250 * time.Millisecond)
-	assert.NotNil(t, engine.sshServer)
-
-	// now remove peer
-	networkMap = &mgmtProto.NetworkMap{
-		Serial:             8,
-		RemotePeers:        []*mgmtProto.RemotePeerConfig{},
-		RemotePeersIsEmpty: false,
-	}
-
-	err = engine.updateNetworkMap(networkMap)
-	require.NoError(t, err)
-
-	// time.Sleep(250 * time.Millisecond)
-	assert.NotNil(t, engine.sshServer)
-
-	// now disable SSH server
-	networkMap = &mgmtProto.NetworkMap{
-		Serial: 9,
-		PeerConfig: &mgmtProto.PeerConfig{Address: "100.64.0.1/24",
-			SshConfig: &mgmtProto.SSHConfig{SshEnabled: false}},
-		RemotePeers:        []*mgmtProto.RemotePeerConfig{peerWithSSH},
-		RemotePeersIsEmpty: false,
-	}
-
-	err = engine.updateNetworkMap(networkMap)
-	require.NoError(t, err)
-
-	assert.Nil(t, engine.sshServer)
-}
-
 func TestEngine_SSHUpdateLogic(t *testing.T) {
 	// Test that SSH server start/stop logic works based on config
 	engine := &Engine{
@@ -631,97 +462,6 @@ func TestEngine_UpdateNetworkMap(t *testing.T) {
 	}
 }
 
-func TestEngine_Sync(t *testing.T) {
-	key, err := wgtypes.GeneratePrivateKey()
-	if err != nil {
-		t.Fatal(err)
-		return
-	}
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-
-	// feed updates to Engine via mocked Management client
-	updates := make(chan *mgmtProto.SyncResponse)
-	defer close(updates)
-	syncFunc := func(ctx context.Context, info *system.Info, msgHandler func(msg *mgmtProto.SyncResponse) error) error {
-		for msg := range updates {
-			err := msgHandler(msg)
-			if err != nil {
-				t.Fatal(err)
-			}
-		}
-		return nil
-	}
-	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
-	engine := NewEngine(ctx, cancel, &EngineConfig{
-		WgIfaceName:  "utun103",
-		WgAddr:       wgaddr.MustParseWGAddress("100.64.0.1/24"),
-		WgPrivateKey: key,
-		WgPort:       33100,
-		MTU:          iface.DefaultMTU,
-	}, EngineServices{
-		SignalClient:   &signal.MockClient{},
-		MgmClient:      &mgmt.MockClient{SyncFunc: syncFunc},
-		RelayManager:   relayMgr,
-		StatusRecorder: peer.NewRecorder("https://mgm"),
-	}, MobileDependency{})
-	engine.ctx = ctx
-
-	engine.dnsServer = &dns.MockServer{
-		UpdateDNSServerFunc: func(serial uint64, update nbdns.Config) error { return nil },
-	}
-
-	defer func() {
-		err := engine.Stop()
-		if err != nil {
-			return
-		}
-	}()
-
-	err = engine.Start(nil, nil)
-	if err != nil {
-		t.Fatal(err)
-		return
-	}
-
-	peer1 := &mgmtProto.RemotePeerConfig{
-		WgPubKey:   "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
-		AllowedIps: []string{"100.64.0.10/24"},
-	}
-	peer2 := &mgmtProto.RemotePeerConfig{
-		WgPubKey:   "LLHf3Ma6z6mdLbriAJbqhX9+nM/B71lgw2+91q3LlhU=",
-		AllowedIps: []string{"100.64.0.11/24"},
-	}
-	peer3 := &mgmtProto.RemotePeerConfig{
-		WgPubKey:   "GGHf3Ma6z6mdLbriAJbqhX9+nM/B71lgw2+91q3LlhU=",
-		AllowedIps: []string{"100.64.0.12/24"},
-	}
-	// 1st update with just 1 peer and serial larger than the current serial of the engine => apply update
-	updates <- &mgmtProto.SyncResponse{
-		NetworkMap: &mgmtProto.NetworkMap{
-			Serial:             10,
-			PeerConfig:         nil,
-			RemotePeers:        []*mgmtProto.RemotePeerConfig{peer1, peer2, peer3},
-			RemotePeersIsEmpty: false,
-		},
-	}
-
-	timeout := time.After(time.Second * 2)
-	for {
-		select {
-		case <-timeout:
-			t.Fatalf("timeout while waiting for test to finish")
-			return
-		default:
-		}
-
-		if getPeers(engine) == 3 && engine.networkSerial == 10 {
-			break
-		}
-	}
-}
-
 func TestEngine_UpdateNetworkMapWithRoutes(t *testing.T) {
 	testCases := []struct {
 		name                 string
@@ -1105,104 +845,6 @@ func TestEngine_UpdateNetworkMapWithDNSUpdate(t *testing.T) {
 	}
 }
 
-func TestEngine_MultiplePeers(t *testing.T) {
-	// log.SetLevel(log.DebugLevel)
-
-	ctx, cancel := context.WithCancel(CtxInitState(context.Background()))
-	defer cancel()
-
-	sigServer, signalAddr, err := startSignal(t)
-	if err != nil {
-		t.Fatal(err)
-		return
-	}
-	defer sigServer.Stop()
-	mgmtServer, mgmtAddr, err := startManagement(t, t.TempDir(), "../testdata/store.sql")
-	if err != nil {
-		t.Fatal(err)
-		return
-	}
-	defer mgmtServer.GracefulStop()
-
-	setupKey := "A2C8E62B-38F5-4553-B31E-DD66C696CEBB"
-
-	mu := sync.Mutex{}
-	engines := []*Engine{}
-	numPeers := 10
-	wg := sync.WaitGroup{}
-	wg.Add(numPeers)
-	// create and start peers
-	for i := 0; i < numPeers; i++ {
-		j := i
-		go func() {
-			engine, err := createEngine(ctx, cancel, setupKey, j, mgmtAddr, signalAddr)
-			if err != nil {
-				wg.Done()
-				t.Errorf("unable to create the engine for peer %d with error %v", j, err)
-				return
-			}
-			engine.dnsServer = &dns.MockServer{}
-			mu.Lock()
-			defer mu.Unlock()
-			guid := fmt.Sprintf("{%s}", uuid.New().String())
-			device.CustomWindowsGUIDString = strings.ToLower(guid)
-			err = engine.Start(nil, nil)
-			if err != nil {
-				t.Errorf("unable to start engine for peer %d with error %v", j, err)
-				wg.Done()
-				return
-			}
-			engines = append(engines, engine)
-			wg.Done()
-		}()
-	}
-
-	// wait until all have been created and started
-	wg.Wait()
-	if len(engines) != numPeers {
-		t.Fatal("not all peers was started")
-	}
-	// check whether all the peer have expected peers connected
-
-	expectedConnected := numPeers * (numPeers - 1)
-
-	// adjust according to timeouts
-	timeout := 50 * time.Second
-	timeoutChan := time.After(timeout)
-	ticker := time.NewTicker(time.Second)
-	defer ticker.Stop()
-loop:
-	for {
-		select {
-		case <-timeoutChan:
-			t.Fatalf("waiting for expected connections timeout after %s", timeout.String())
-			break loop
-		case <-ticker.C:
-			totalConnected := 0
-			for _, engine := range engines {
-				totalConnected += getConnectedPeers(engine)
-			}
-			if totalConnected == expectedConnected {
-				log.Infof("total connected=%d", totalConnected)
-				break loop
-			}
-			log.Infof("total connected=%d", totalConnected)
-		}
-	}
-	// cleanup test
-	for n, peerEngine := range engines {
-		t.Logf("stopping peer with interface %s from multipeer test, loopIndex %d", peerEngine.wgInterface.Name(), n)
-		errStop := peerEngine.mgmClient.Close()
-		if errStop != nil {
-			log.Infoln("got error trying to close management clients from engine: ", errStop)
-		}
-		errStop = peerEngine.Stop()
-		if errStop != nil {
-			log.Infoln("got error trying to close testing peers engine: ", errStop)
-		}
-	}
-}
-
 func Test_ParseNATExternalIPMappings(t *testing.T) {
 	ifaceList, err := net.Interfaces()
 	if err != nil {
@@ -1526,187 +1168,6 @@ func TestCompareNetIPLists(t *testing.T) {
 	}
 }
 
-func createEngine(ctx context.Context, cancel context.CancelFunc, setupKey string, i int, mgmtAddr string, signalAddr string) (*Engine, error) {
-	key, err := wgtypes.GeneratePrivateKey()
-	if err != nil {
-		return nil, err
-	}
-	mgmtClient, err := mgmt.NewClient(ctx, mgmtAddr, key, false)
-	if err != nil {
-		return nil, err
-	}
-	signalClient, err := signal.NewClient(ctx, signalAddr, key, false)
-	if err != nil {
-		return nil, err
-	}
-
-	info := system.GetInfo(ctx)
-	resp, err := mgmtClient.Register(setupKey, "", info, nil, nil)
-	if err != nil {
-		return nil, err
-	}
-
-	var ifaceName string
-	if runtime.GOOS == "darwin" {
-		ifaceName = fmt.Sprintf("utun1%d", i)
-	} else {
-		ifaceName = fmt.Sprintf("wt%d", i)
-	}
-
-	wgPort := 33100 + i
-	conf := &EngineConfig{
-		WgIfaceName:  ifaceName,
-		WgAddr:       wgaddr.MustParseWGAddress(resp.PeerConfig.Address),
-		WgPrivateKey: key,
-		WgPort:       wgPort,
-		MTU:          iface.DefaultMTU,
-	}
-
-	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String(), iface.DefaultMTU)
-	e, err := NewEngine(ctx, cancel, conf, EngineServices{
-		SignalClient:   signalClient,
-		MgmClient:      mgmtClient,
-		RelayManager:   relayMgr,
-		StatusRecorder: peer.NewRecorder("https://mgm"),
-	}, MobileDependency{}), nil
-	e.ctx = ctx
-	return e, err
-}
-
-func startSignal(t *testing.T) (*grpc.Server, string, error) {
-	t.Helper()
-
-	s := grpc.NewServer(grpc.KeepaliveEnforcementPolicy(kaep), grpc.KeepaliveParams(kasp))
-
-	lis, err := net.Listen("tcp", "localhost:0")
-	if err != nil {
-		log.Fatalf("failed to listen: %v", err)
-	}
-
-	srv, err := signalServer.NewServer(context.Background(), otel.Meter(""))
-	require.NoError(t, err)
-	proto.RegisterSignalExchangeServer(s, srv)
-
-	go func() {
-		if err = s.Serve(lis); err != nil {
-			log.Fatalf("failed to serve: %v", err)
-		}
-	}()
-
-	return s, lis.Addr().String(), nil
-}
-
-func startManagement(t *testing.T, dataDir, testFile string) (*grpc.Server, string, error) {
-	t.Helper()
-
-	config := &config.Config{
-		Stuns:      []*config.Host{},
-		TURNConfig: &config.TURNConfig{},
-		Relay: &config.Relay{
-			Addresses:      []string{"127.0.0.1:1234"},
-			CredentialsTTL: util.Duration{Duration: time.Hour},
-			Secret:         "222222222222222222",
-		},
-		Signal: &config.Host{
-			Proto: "http",
-			URI:   "localhost:10000",
-		},
-		Datadir:    dataDir,
-		HttpConfig: nil,
-	}
-
-	lis, err := net.Listen("tcp", "localhost:0")
-	if err != nil {
-		return nil, "", err
-	}
-	s := grpc.NewServer(grpc.KeepaliveEnforcementPolicy(kaep), grpc.KeepaliveParams(kasp))
-
-	store, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), testFile, config.Datadir)
-	if err != nil {
-		return nil, "", err
-	}
-	t.Cleanup(cleanUp)
-
-	eventStore := &activity.InMemoryEventStore{}
-	if err != nil {
-		return nil, "", err
-	}
-
-	permissionsManager := permissions.NewManager(store)
-	peersManager := peers.NewManager(store, permissionsManager)
-	jobManager := job.NewJobManager(nil, store, peersManager)
-
-	cacheStore, err := nbcache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
-	if err != nil {
-		return nil, "", err
-	}
-
-	ia, _ := integrations.NewIntegratedValidator(context.Background(), peersManager, nil, eventStore, cacheStore)
-
-	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
-	require.NoError(t, err)
-
-	ctrl := gomock.NewController(t)
-	t.Cleanup(ctrl.Finish)
-	settingsMockManager := settings.NewMockManager(ctrl)
-	settingsMockManager.EXPECT().
-		GetSettings(gomock.Any(), gomock.Any(), gomock.Any()).
-		Return(&types.Settings{}, nil).
-		AnyTimes()
-	settingsMockManager.EXPECT().
-		GetExtraSettings(gomock.Any(), gomock.Any()).
-		Return(&types.ExtraSettings{}, nil).
-		AnyTimes()
-
-	groupsManager := groups.NewManagerMock()
-
-	updateManager := update_channel.NewPeersUpdateManager(metrics)
-	requestBuffer := server.NewAccountRequestBuffer(context.Background(), store)
-	networkMapController := controller.NewController(context.Background(), store, metrics, updateManager, requestBuffer, server.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersManager), config)
-	accountManager, err := server.BuildManager(context.Background(), config, store, networkMapController, jobManager, nil, "", eventStore, nil, false, ia, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManager, false, cacheStore)
-	if err != nil {
-		return nil, "", err
-	}
-
-	secretsManager, err := nbgrpc.NewTimeBasedAuthSecretsManager(updateManager, config.TURNConfig, config.Relay, settingsMockManager, groupsManager)
-	if err != nil {
-		return nil, "", err
-	}
-	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, jobManager, secretsManager, nil, nil, &server.MockIntegratedValidator{}, networkMapController, nil, nil)
-	if err != nil {
-		return nil, "", err
-	}
-	mgmtProto.RegisterManagementServiceServer(s, mgmtServer)
-	go func() {
-		if err = s.Serve(lis); err != nil {
-			log.Fatalf("failed to serve: %v", err)
-		}
-	}()
-
-	return s, lis.Addr().String(), nil
-}
-
-// getConnectedPeers returns a connection Status or nil if peer connection wasn't found
-func getConnectedPeers(e *Engine) int {
-	e.syncMsgMux.Lock()
-	defer e.syncMsgMux.Unlock()
-	i := 0
-	for _, id := range e.peerStore.PeersPubKey() {
-		conn, _ := e.peerStore.PeerConn(id)
-		if conn.IsConnected() {
-			i++
-		}
-	}
-	return i
-}
-
-func getPeers(e *Engine) int {
-	e.syncMsgMux.Lock()
-	defer e.syncMsgMux.Unlock()
-
-	return len(e.peerStore.PeersPubKey())
-}
-
 func mustEncodePrefix(t *testing.T, p netip.Prefix) []byte {
 	t.Helper()
 	b, err := netiputil.EncodePrefix(p)

client/internal/lazyconn/support.go

@@ -4,6 +4,8 @@ import (
 	"strings"
 
 	"github.com/hashicorp/go-version"
+
+	nbversion "github.com/netbirdio/netbird/version"
 )
 
 var (
@@ -11,7 +13,7 @@ var (
 )
 
 func IsSupported(agentVersion string) bool {
-	if agentVersion == "development" {
+	if nbversion.IsDevelopmentVersion(agentVersion) {
 		return true
 	}
 

client/internal/networkmonitor/check_change_common.go

@@ -50,7 +50,7 @@ func routeCheck(ctx context.Context, fd int, nexthopv4, nexthopv6 systemops.Next
 		switch msg.Type {
 		// handle route changes
 		case unix.RTM_ADD, syscall.RTM_DELETE:
-			route, err := parseRouteMessage(buf[:n])
+			route, flags, err := parseRouteMessage(buf[:n])
 			if err != nil {
 				log.Debugf("Network monitor: error parsing routing message: %v", err)
 				continue
@@ -66,6 +66,10 @@ func routeCheck(ctx context.Context, fd int, nexthopv4, nexthopv6 systemops.Next
 			}
 			switch msg.Type {
 			case unix.RTM_ADD:
+				if systemops.IgnoreAddedDefaultRoute(flags) {
+					log.Debugf("Network monitor: ignoring added default route via %s, interface %s, flags %#x", route.Gw, intf, flags)
+					continue
+				}
 				log.Infof("Network monitor: default route changed: via %s, interface %s", route.Gw, intf)
 				return nil
 			case unix.RTM_DELETE:
@@ -78,22 +82,26 @@ func routeCheck(ctx context.Context, fd int, nexthopv4, nexthopv6 systemops.Next
 	}
 }
 
-func parseRouteMessage(buf []byte) (*systemops.Route, error) {
+func parseRouteMessage(buf []byte) (*systemops.Route, int, error) {
 	msgs, err := route.ParseRIB(route.RIBTypeRoute, buf)
 	if err != nil {
-		return nil, fmt.Errorf("parse RIB: %v", err)
+		return nil, 0, fmt.Errorf("parse RIB: %v", err)
 	}
 
 	if len(msgs) != 1 {
-		return nil, fmt.Errorf("unexpected RIB message msgs: %v", msgs)
+		return nil, 0, fmt.Errorf("unexpected RIB message msgs: %v", msgs)
 	}
 
 	msg, ok := msgs[0].(*route.RouteMessage)
 	if !ok {
-		return nil, fmt.Errorf("unexpected RIB message type: %T", msgs[0])
+		return nil, 0, fmt.Errorf("unexpected RIB message type: %T", msgs[0])
 	}
 
-	return systemops.MsgToRoute(msg)
+	r, err := systemops.MsgToRoute(msg)
+	if err != nil {
+		return nil, 0, err
+	}
+	return r, msg.Flags, nil
 }
 
 // waitReadable blocks until fd has data to read, or ctx is cancelled.

client/internal/peer/conn.go

@@ -23,6 +23,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer/id"
 	"github.com/netbirdio/netbird/client/internal/peer/worker"
 	"github.com/netbirdio/netbird/client/internal/portforward"
+	"github.com/netbirdio/netbird/client/internal/rosenpass"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
@@ -899,7 +900,7 @@ func (conn *Conn) presharedKey(remoteRosenpassKey []byte) *wgtypes.Key {
 	}
 
 	// Fallback to deterministic key if no NetBird PSK is configured
-	determKey, err := conn.rosenpassDetermKey()
+	determKey, err := rosenpass.DeterministicSeedKey(conn.config.LocalKey, conn.config.Key)
 	if err != nil {
 		conn.Log.Errorf("failed to generate Rosenpass initial key: %v", err)
 		return nil
@@ -908,26 +909,6 @@ func (conn *Conn) presharedKey(remoteRosenpassKey []byte) *wgtypes.Key {
 	return determKey
 }
 
-// todo: move this logic into Rosenpass package
-func (conn *Conn) rosenpassDetermKey() (*wgtypes.Key, error) {
-	lk := []byte(conn.config.LocalKey)
-	rk := []byte(conn.config.Key) // remote key
-	var keyInput []byte
-	if string(lk) > string(rk) {
-		//nolint:gocritic
-		keyInput = append(lk[:16], rk[:16]...)
-	} else {
-		//nolint:gocritic
-		keyInput = append(rk[:16], lk[:16]...)
-	}
-
-	key, err := wgtypes.NewKey(keyInput)
-	if err != nil {
-		return nil, err
-	}
-	return &key, nil
-}
-
 func isController(config ConnConfig) bool {
 	return config.LocalKey > config.Key
 }

client/internal/peer/conn_status.go

@@ -26,7 +26,6 @@ type connStatusInputs struct {
 	iceInProgress       bool // a negotiation is currently in flight
 }
 
-
 // ConnStatus describe the status of a peer's connection
 type ConnStatus int32
 

client/internal/peer/status.go

@@ -111,6 +111,7 @@ type LocalPeerState struct {
 	PubKey          string
 	KernelInterface bool
 	FQDN            string
+	WgPort          int
 	Routes          map[string]struct{}
 }
 
@@ -185,10 +186,14 @@ func (s *StatusChangeSubscription) Events() chan map[string]RouterState {
 	return s.eventsChan
 }
 
-// Status holds a state of peers, signal, management connections and relays
+// Status holds a state of peers, signal, management connections and relays.
+// mux is an RWMutex so hot read paths (notably PeerStateByIP, called for
+// every private-service request) don't contend against each other.
+// Pure read methods take RLock; anything that mutates state takes Lock.
 type Status struct {
-	mux                   sync.Mutex
+	mux                   sync.RWMutex
 	peers                 map[string]State
+	ipToKey               map[string]string
 	changeNotify          map[string]map[string]*StatusChangeSubscription // map[peerID]map[subscriptionID]*StatusChangeSubscription
 	signalState           bool
 	signalError           error
@@ -227,6 +232,7 @@ type Status struct {
 func NewRecorder(mgmAddress string) *Status {
 	return &Status{
 		peers:                 make(map[string]State),
+		ipToKey:               make(map[string]string),
 		changeNotify:          make(map[string]map[string]*StatusChangeSubscription),
 		eventStreams:          make(map[string]chan *proto.SystemEvent),
 		eventQueue:            NewEventQueue(eventQueueSize),
@@ -278,13 +284,19 @@ func (d *Status) AddPeer(peerPubKey string, fqdn string, ip string, ipv6 string)
 		Mux:        new(sync.RWMutex),
 	}
 	d.peerListChangedForNotification = true
+	if ipv6 != "" {
+		d.ipToKey[ipv6] = peerPubKey
+	}
+	if ip != "" {
+		d.ipToKey[ip] = peerPubKey
+	}
 	return nil
 }
 
 // GetPeer adds peer to Daemon status map
 func (d *Status) GetPeer(peerPubKey string) (State, error) {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 
 	state, ok := d.peers[peerPubKey]
 	if !ok {
@@ -294,8 +306,8 @@ func (d *Status) GetPeer(peerPubKey string) (State, error) {
 }
 
 func (d *Status) PeerByIP(ip string) (string, bool) {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 
 	for _, state := range d.peers {
 		if state.IP == ip {
@@ -305,17 +317,45 @@ func (d *Status) PeerByIP(ip string) (string, bool) {
 	return "", false
 }
 
+// PeerStateByIP returns the full peer State for the given tunnel IP.
+// Matches against either the IPv4 (State.IP) or IPv6 (State.IPv6) tunnel
+// address so dual-stack peers are reachable on either family. Only
+// active peers are matched; peers moved into the offline slice by
+// ReplaceOfflinePeers are intentionally treated as unknown.
+func (d *Status) PeerStateByIP(ip string) (State, bool) {
+	if ip == "" {
+		return State{}, false
+	}
+	d.mux.RLock()
+	defer d.mux.RUnlock()
+	key, ok := d.ipToKey[ip]
+	if !ok {
+		return State{}, false
+	}
+	state, ok := d.peers[key]
+	if ok {
+		return state, true
+	}
+	return State{}, false
+}
+
 // RemovePeer removes peer from Daemon status map
 func (d *Status) RemovePeer(peerPubKey string) error {
 	d.mux.Lock()
 	defer d.mux.Unlock()
 
-	_, ok := d.peers[peerPubKey]
+	p, ok := d.peers[peerPubKey]
 	if !ok {
 		return errors.New("no peer with to remove")
 	}
 
 	delete(d.peers, peerPubKey)
+	if mappedKey, exists := d.ipToKey[p.IP]; exists && mappedKey == peerPubKey {
+		delete(d.ipToKey, p.IP)
+	}
+	if mappedKey, exists := d.ipToKey[p.IPv6]; exists && mappedKey == peerPubKey {
+		delete(d.ipToKey, p.IPv6)
+	}
 	d.peerListChangedForNotification = true
 	return nil
 }
@@ -702,8 +742,8 @@ func (d *Status) UnsubscribePeerStateChanges(subscription *StatusChangeSubscript
 
 // GetLocalPeerState returns the local peer state
 func (d *Status) GetLocalPeerState() LocalPeerState {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	return d.localPeer.Clone()
 }
 
@@ -909,8 +949,8 @@ func (d *Status) DeleteResolvedDomainsStates(domain domain.Domain) {
 }
 
 func (d *Status) GetRosenpassState() RosenpassState {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	return RosenpassState{
 		d.rosenpassEnabled,
 		d.rosenpassPermissive,
@@ -918,14 +958,14 @@ func (d *Status) GetRosenpassState() RosenpassState {
 }
 
 func (d *Status) GetLazyConnection() bool {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	return d.lazyConnectionEnabled
 }
 
 func (d *Status) GetManagementState() ManagementState {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	return ManagementState{
 		d.mgmAddress,
 		d.managementState,
@@ -951,8 +991,8 @@ func (d *Status) UpdateLatency(pubKey string, latency time.Duration) error {
 
 // IsLoginRequired determines if a peer's login has expired.
 func (d *Status) IsLoginRequired() bool {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 
 	// if peer is connected to the management then login is not expired
 	if d.managementState {
@@ -967,8 +1007,8 @@ func (d *Status) IsLoginRequired() bool {
 }
 
 func (d *Status) GetSignalState() SignalState {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	return SignalState{
 		d.signalAddress,
 		d.signalState,
@@ -978,8 +1018,8 @@ func (d *Status) GetSignalState() SignalState {
 
 // GetRelayStates returns the stun/turn/permanent relay states
 func (d *Status) GetRelayStates() []relay.ProbeResult {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	if d.relayMgr == nil {
 		return d.relayStates
 	}
@@ -1008,8 +1048,8 @@ func (d *Status) GetRelayStates() []relay.ProbeResult {
 }
 
 func (d *Status) ForwardingRules() []firewall.ForwardRule {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	if d.ingressGwMgr == nil {
 		return nil
 	}
@@ -1018,16 +1058,16 @@ func (d *Status) ForwardingRules() []firewall.ForwardRule {
 }
 
 func (d *Status) GetDNSStates() []NSGroupState {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 
 	// shallow copy is good enough, as slices fields are currently not updated
 	return slices.Clone(d.nsGroupStates)
 }
 
 func (d *Status) GetResolvedDomainsStates() map[domain.Domain]ResolvedDomainInfo {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	return maps.Clone(d.resolvedDomainsStates)
 }
 
@@ -1043,8 +1083,8 @@ func (d *Status) GetFullStatus() FullStatus {
 		LazyConnectionEnabled: d.GetLazyConnection(),
 	}
 
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 
 	fullStatus.LocalPeerState = d.localPeer
 
@@ -1219,8 +1259,8 @@ func (d *Status) SetWgIface(wgInterface WGIfaceStatus) {
 }
 
 func (d *Status) PeersStatus() (*configurer.Stats, error) {
-	d.mux.Lock()
-	defer d.mux.Unlock()
+	d.mux.RLock()
+	defer d.mux.RUnlock()
 	if d.wgIface == nil {
 		return nil, fmt.Errorf("wgInterface is nil, cannot retrieve peers status")
 	}
@@ -1326,6 +1366,7 @@ func (fs FullStatus) ToProto() *proto.FullStatus {
 	pbFullStatus.LocalPeerState.PubKey = fs.LocalPeerState.PubKey
 	pbFullStatus.LocalPeerState.KernelInterface = fs.LocalPeerState.KernelInterface
 	pbFullStatus.LocalPeerState.Fqdn = fs.LocalPeerState.FQDN
+	pbFullStatus.LocalPeerState.WgPort = int32(fs.LocalPeerState.WgPort)
 	pbFullStatus.LocalPeerState.RosenpassPermissive = fs.RosenpassState.Permissive
 	pbFullStatus.LocalPeerState.RosenpassEnabled = fs.RosenpassState.Enabled
 	pbFullStatus.NumberOfForwardingRules = int32(fs.NumOfForwardingRules)

client/internal/peer/status_test.go

@@ -63,6 +63,72 @@ func TestUpdatePeerState(t *testing.T) {
 	assert.Equal(t, ip, state.IP, "ip should be equal")
 }
 
+func TestStatus_PeerStateByIP(t *testing.T) {
+	status := NewRecorder("https://mgm")
+	req := require.New(t)
+
+	req.NoError(status.AddPeer("pk-1", "peer-1.netbird", "100.64.0.10", ""))
+	req.NoError(status.AddPeer("pk-2", "peer-2.netbird", "100.64.0.11", ""))
+
+	state, ok := status.PeerStateByIP("100.64.0.10")
+	req.True(ok, "known tunnel IP should resolve to a peer state")
+	req.Equal("pk-1", state.PubKey, "matching state must carry the right pub key")
+	req.Equal("peer-1.netbird", state.FQDN, "matching state must carry the right FQDN")
+
+	_, ok = status.PeerStateByIP("100.64.0.99")
+	req.False(ok, "unknown IP must report ok=false")
+}
+
+func TestStatus_PeerStateByIP_MatchesIPv6(t *testing.T) {
+	status := NewRecorder("https://mgm")
+	req := require.New(t)
+
+	req.NoError(status.AddPeer("pk-1", "peer-1.netbird", "100.64.0.10", "fd00::1"))
+
+	state, ok := status.PeerStateByIP("fd00::1")
+	req.True(ok, "IPv6-only match must resolve to the peer state")
+	req.Equal("pk-1", state.PubKey, "matching state must carry the right pub key")
+}
+
+// TestStatus_PeerStateByIP_IgnoresOfflinePeers documents that peers
+// moved into the offline slice via ReplaceOfflinePeers are intentionally
+// not resolvable by IP: only active peers can carry traffic, so callers
+// (DNS filter, embed.Client.IdentityForIP) treat them as unknown.
+func TestStatus_PeerStateByIP_IgnoresOfflinePeers(t *testing.T) {
+	status := NewRecorder("https://mgm")
+	req := require.New(t)
+
+	status.ReplaceOfflinePeers([]State{
+		{PubKey: "pk-offline", FQDN: "offline.netbird", IP: "100.64.0.20", IPv6: "fd00::20"},
+	})
+
+	_, ok := status.PeerStateByIP("100.64.0.20")
+	req.False(ok, "offline peer must not resolve by IPv4 tunnel address")
+
+	_, ok = status.PeerStateByIP("fd00::20")
+	req.False(ok, "offline peer must not resolve by IPv6 tunnel address")
+}
+
+// TestStatus_PeerStateByIP_RemovedPeer verifies RemovePeer drops the
+// IP index entries for both address families.
+func TestStatus_PeerStateByIP_RemovedPeer(t *testing.T) {
+	status := NewRecorder("https://mgm")
+	req := require.New(t)
+
+	req.NoError(status.AddPeer("pk-1", "peer-1.netbird", "100.64.0.10", "fd00::1"))
+
+	_, ok := status.PeerStateByIP("100.64.0.10")
+	req.True(ok, "active peer must resolve before removal")
+
+	req.NoError(status.RemovePeer("pk-1"))
+
+	_, ok = status.PeerStateByIP("100.64.0.10")
+	req.False(ok, "removed peer must not resolve by IPv4 tunnel address")
+
+	_, ok = status.PeerStateByIP("fd00::1")
+	req.False(ok, "removed peer must not resolve by IPv6 tunnel address")
+}
+
 func TestStatus_UpdatePeerFQDN(t *testing.T) {
 	key := "abc"
 	fqdn := "peer-a.netbird.local"

client/internal/portforward/pcp/nat.go

@@ -179,8 +179,10 @@ func getDefaultGateway() (gateway net.IP, localIP net.IP, err error) {
 	}
 
 	dst := net.IPv4zero
-	if runtime.GOOS == "linux" {
-		// go-netroute v0.4.0 rejects unspecified destinations client-side on Linux.
+	if runtime.GOOS == "linux" || runtime.GOOS == "android" {
+		// go-netroute v0.4.0 rejects unspecified destinations client-side on Linux/Android.
+		// TODO: on android/ios, use platform APIs (ConnectivityManager.getLinkProperties /
+		// NWPathMonitor) when netlink-based lookup is restricted or unavailable.
 		dst = net.IPv4(0, 0, 0, 1)
 	}
 	_, gateway, localIP, err = router.Route(dst)
@@ -203,7 +205,7 @@ func getDefaultGateway6() (gateway net.IP, localIP net.IP, err error) {
 	}
 
 	dst := net.IPv6zero
-	if runtime.GOOS == "linux" {
+	if runtime.GOOS == "linux" || runtime.GOOS == "android" {
 		// ::2
 		dst = net.IP{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2}
 	}

client/internal/profilemanager/config.go

@@ -22,6 +22,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/iface"
 	"github.com/netbirdio/netbird/client/internal/routemanager/dynamic"
+	"github.com/netbirdio/netbird/client/mdm"
 	"github.com/netbirdio/netbird/client/ssh"
 	mgm "github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -57,6 +58,10 @@ var DefaultInterfaceBlacklist = []string{
 	"Tailscale", "tailscale", "docker", "veth", "br-", "lo",
 }
 
+// loadMDMPolicy is the package-level indirection used by apply() to read the
+// active MDM policy. Tests override this to inject a fake policy.
+var loadMDMPolicy = mdm.LoadPolicy
+
 // ConfigInput carries configuration changes to the client
 type ConfigInput struct {
 	ManagementURL                 string
@@ -174,6 +179,23 @@ type Config struct {
 	LazyConnectionEnabled bool
 
 	MTU uint16
+
+	// policy is the MDM policy that produced the currently-set values for
+	// any MDM-enforced fields. Set by applyMDMPolicy at the tail of apply()
+	// and reset on every apply() invocation. Never persisted to disk.
+	// Callers query enforcement state via Policy() and the mdm.Policy API
+	// (HasKey, ManagedKeys, IsEmpty).
+	policy *mdm.Policy `json:"-"`
+}
+
+// Policy returns the MDM policy applied to this Config. Returns a non-nil
+// empty Policy when MDM enforcement is inactive; callers can always invoke
+// HasKey / ManagedKeys / IsEmpty without a nil check.
+func (config *Config) Policy() *mdm.Policy {
+	if config == nil || config.policy == nil {
+		return mdm.NewPolicy(nil)
+	}
+	return config.policy
 }
 
 var ConfigDirOverride string
@@ -612,10 +634,93 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
 		updated = true
 	}
 
+	// MDM is the last override layer: any key present in the policy
+	// supersedes defaults, on-disk config, env vars and CLI input.
+	config.applyMDMPolicy(loadMDMPolicy())
+
 	return updated, nil
 }
 
-// parseURL parses and validates a service URL
+// applyMDMPolicy overlays MDM-supplied values on top of the resolved Config.
+// The provided Policy is also stored on the Config so callers can later query
+// which fields are enforced. Invalid values (e.g. malformed URLs) are logged
+// and skipped to avoid bricking the client; the field keeps its previous
+// resolved value but is still marked as managed (Policy.HasKey returns true
+// for the key, so per-field rejection of user writes still applies).
+func (config *Config) applyMDMPolicy(policy *mdm.Policy) {
+	config.policy = policy
+	if policy.IsEmpty() {
+		return
+	}
+
+	// Helper: log the application of a single MDM-managed key. Values for
+	// keys in mdm.SecretKeys are redacted.
+	logApplied := func(key string, displayValue any) {
+		if _, secret := mdm.SecretKeys[key]; secret {
+			log.Infof("MDM override %s = ********** (secret)", key)
+			return
+		}
+		log.Infof("MDM override %s = %v", key, displayValue)
+	}
+
+	if v, ok := policy.GetString(mdm.KeyManagementURL); ok {
+		if u, err := parseURL("Management URL", v); err != nil {
+			log.Warnf("MDM management URL %q invalid: %v; keeping previous value", v, err)
+		} else {
+			config.ManagementURL = u
+			logApplied(mdm.KeyManagementURL, u.String())
+		}
+	}
+
+	if v, ok := policy.GetString(mdm.KeyPreSharedKey); ok {
+		// Defensive: refuse the redaction mask in case it round-tripped
+		// through a manifest by mistake.
+		if !isPreSharedKeyHidden(&v) {
+			config.PreSharedKey = v
+			logApplied(mdm.KeyPreSharedKey, "")
+		}
+	}
+
+	// applyBool collapses the per-key "read + set + log" boilerplate
+	// for every plain bool MDM key into a single helper. Keeps the
+	// outer function's cognitive complexity below SonarCube's
+	// threshold; functional behaviour is identical to the inlined
+	// branches it replaces.
+	applyBool := func(key string, setter func(bool)) {
+		v, ok := policy.GetBool(key)
+		if !ok {
+			return
+		}
+		setter(v)
+		logApplied(key, v)
+	}
+
+	applyBool(mdm.KeyAllowServerSSH, func(v bool) { bv := v; config.ServerSSHAllowed = &bv })
+	applyBool(mdm.KeyDisableClientRoutes, func(v bool) { config.DisableClientRoutes = v })
+	applyBool(mdm.KeyDisableServerRoutes, func(v bool) { config.DisableServerRoutes = v })
+	applyBool(mdm.KeyBlockInbound, func(v bool) { config.BlockInbound = v })
+	applyBool(mdm.KeyDisableAutoConnect, func(v bool) { config.DisableAutoConnect = v })
+	applyBool(mdm.KeyRosenpassEnabled, func(v bool) { config.RosenpassEnabled = v })
+	applyBool(mdm.KeyRosenpassPermissive, func(v bool) { config.RosenpassPermissive = v })
+
+	if v, ok := policy.GetInt(mdm.KeyWireguardPort); ok {
+		// REG_DWORD is 32-bit; UDP port range is 1-65535. Clamp at the
+		// upper bound and reject obviously-invalid values to avoid the
+		// engine binding to an unusable port if the admin pushes garbage.
+		if v >= 1 && v <= 65535 {
+			config.WgPort = int(v)
+			logApplied(mdm.KeyWireguardPort, v)
+		} else {
+			log.Warnf("MDM wireguard port %d out of range [1,65535]; keeping previous value", v)
+		}
+	}
+}
+
+// parseURL parses and validates the URL for the named service. The URL
+// must use the http or https scheme; if no port is present, ":443" is
+// appended for https or ":80" for http. The serviceName parameter is
+// used to contextualise error messages. On success returns the parsed
+// *url.URL; on failure returns a non-nil error.
 func parseURL(serviceName, serviceURL string) (*url.URL, error) {
 	parsedMgmtURL, err := url.ParseRequestURI(serviceURL)
 	if err != nil {

client/internal/profilemanager/config_mdm_test.go

@@ -0,0 +1,152 @@
+package profilemanager
+
+import (
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/mdm"
+)
+
+// withMDMPolicy temporarily overrides the package-level loadMDMPolicy hook so
+// apply() observes the supplied Policy. The original loader is restored at
+// test cleanup.
+func withMDMPolicy(t *testing.T, policy *mdm.Policy) {
+	t.Helper()
+	prev := loadMDMPolicy
+	loadMDMPolicy = func() *mdm.Policy { return policy }
+	t.Cleanup(func() { loadMDMPolicy = prev })
+}
+
+func TestApply_MDMEmpty_NoEnforcement(t *testing.T) {
+	withMDMPolicy(t, mdm.NewPolicy(nil))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath: filepath.Join(t.TempDir(), "config.json"),
+	})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	assert.True(t, cfg.Policy().IsEmpty(), "no MDM source ⇒ empty Policy")
+	assert.False(t, cfg.Policy().HasKey(mdm.KeyManagementURL))
+	assert.Empty(t, cfg.Policy().ManagedKeys())
+
+	// Default management URL still resolves.
+	assert.Equal(t, DefaultManagementURL, cfg.ManagementURL.String())
+}
+
+func TestApply_MDMOnly_OverridesDefaults(t *testing.T) {
+	const mdmURL = "https://corp.mdm.example.com:443"
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyManagementURL:       mdmURL,
+		mdm.KeyDisableClientRoutes: true,
+		mdm.KeyBlockInbound:        true,
+	}))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath: filepath.Join(t.TempDir(), "config.json"),
+	})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	assert.Equal(t, mdmURL, cfg.ManagementURL.String())
+	assert.True(t, cfg.DisableClientRoutes)
+	assert.True(t, cfg.BlockInbound)
+
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyManagementURL))
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyDisableClientRoutes))
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyBlockInbound))
+	assert.False(t, cfg.Policy().HasKey(mdm.KeyAllowServerSSH))
+}
+
+func TestApply_MDMBeatsCLIInput(t *testing.T) {
+	const mdmURL = "https://mdm.example.com:443"
+	const cliURL = "https://cli.example.com:443"
+
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyManagementURL: mdmURL,
+	}))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath:    filepath.Join(t.TempDir(), "config.json"),
+		ManagementURL: cliURL,
+	})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	// MDM wins over CLI-supplied management URL.
+	assert.Equal(t, mdmURL, cfg.ManagementURL.String())
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyManagementURL))
+}
+
+func TestApply_MDMInvalidURL_KeepsPreviousValue(t *testing.T) {
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyManagementURL: "not-a-url",
+	}))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath: filepath.Join(t.TempDir(), "config.json"),
+	})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	// Invalid MDM URL is logged and skipped: default URL stays in place
+	// to keep the client functional.
+	assert.Equal(t, DefaultManagementURL, cfg.ManagementURL.String())
+
+	// But the key is still considered MDM-managed (admin intent is to
+	// enforce, daemon rejects user writes to this field — phase-1 scaffolding
+	// reflects this by keeping Policy.HasKey true even on parse failure).
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyManagementURL))
+}
+
+func TestApply_MDMBoolKeysOverrideOnDiskValue(t *testing.T) {
+	tmp := filepath.Join(t.TempDir(), "config.json")
+
+	// Seed without MDM.
+	withMDMPolicy(t, mdm.NewPolicy(nil))
+	_, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath:          tmp,
+		DisableClientRoutes: boolPtr(false),
+		RosenpassEnabled:    boolPtr(false),
+	})
+	require.NoError(t, err)
+
+	// Now enable MDM enforcement for these keys.
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyDisableClientRoutes: true,
+		mdm.KeyRosenpassEnabled:    true,
+	}))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{ConfigPath: tmp})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	assert.True(t, cfg.DisableClientRoutes, "MDM override should flip on-disk false to true")
+	assert.True(t, cfg.RosenpassEnabled)
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyDisableClientRoutes))
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyRosenpassEnabled))
+}
+
+func TestApply_MDMPreSharedKeyRedactionSentinelRejected(t *testing.T) {
+	const maskSentinel = "**********"
+
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyPreSharedKey: maskSentinel,
+	}))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath: filepath.Join(t.TempDir(), "config.json"),
+	})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	// Mask sentinel must not be persisted as the actual PSK.
+	assert.NotEqual(t, maskSentinel, cfg.PreSharedKey)
+	// Key still marked managed so user writes are still rejected.
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyPreSharedKey))
+}
+
+func boolPtr(b bool) *bool { return &b }

client/internal/rosenpass/manager.go

@@ -28,6 +28,15 @@ func hashRosenpassKey(key []byte) string {
 	return hex.EncodeToString(hasher.Sum(nil))
 }
 
+// rpServer is the subset of rp.Server used by Manager. Defined as an interface
+// so tests can substitute a mock without spinning up a real UDP server.
+type rpServer interface {
+	AddPeer(rp.PeerConfig) (rp.PeerID, error)
+	RemovePeer(rp.PeerID) error
+	Run() error
+	Close() error
+}
+
 type Manager struct {
 	ifaceName    string
 	spk          []byte
@@ -36,7 +45,7 @@ type Manager struct {
 	preSharedKey *[32]byte
 	rpPeerIDs    map[string]*rp.PeerID
 	rpWgHandler  *NetbirdHandler
-	server       *rp.Server
+	server       rpServer
 	lock         sync.Mutex
 	port         int
 	wgIface      PresharedKeySetter
@@ -51,7 +60,22 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error)
 
 	rpKeyHash := hashRosenpassKey(public)
 	log.Tracef("generated new rosenpass key pair with public key %s", rpKeyHash)
-	return &Manager{ifaceName: wgIfaceName, rpKeyHash: rpKeyHash, spk: public, ssk: secret, preSharedKey: (*[32]byte)(preSharedKey), rpPeerIDs: make(map[string]*rp.PeerID), lock: sync.Mutex{}}, nil
+	return &Manager{
+		ifaceName:    wgIfaceName,
+		rpKeyHash:    rpKeyHash,
+		spk:          public,
+		ssk:          secret,
+		preSharedKey: (*[32]byte)(preSharedKey),
+		rpPeerIDs:    make(map[string]*rp.PeerID),
+		// rpWgHandler is created here (instead of only in generateConfig) so it
+		// is never nil between NewManager and Run(). Otherwise an early
+		// OnConnected call (race observed on Android, issue #4341) panics on
+		// nil receiver in addPeer -> m.rpWgHandler.AddPeer. generateConfig will
+		// replace it with a fresh handler on each Run() to clear stale peer
+		// state from previous engine sessions.
+		rpWgHandler: NewNetbirdHandler(),
+		lock:        sync.Mutex{},
+	}, nil
 }
 
 func (m *Manager) GetPubKey() []byte {
@@ -65,6 +89,16 @@ func (m *Manager) GetAddress() *net.UDPAddr {
 
 // addPeer adds a new peer to the Rosenpass server
 func (m *Manager) addPeer(rosenpassPubKey []byte, rosenpassAddr string, wireGuardIP string, wireGuardPubKey string) error {
+	// Defense in depth against issue #4341 (Android crash): if Run() has not
+	// completed yet, m.server / m.rpWgHandler may be nil. Return an explicit
+	// error instead of panicking on nil-receiver dereference.
+	if m.server == nil {
+		return fmt.Errorf("rosenpass server not initialized")
+	}
+	if m.rpWgHandler == nil {
+		return fmt.Errorf("rosenpass wg handler not initialized")
+	}
+
 	var err error
 	pcfg := rp.PeerConfig{PublicKey: rosenpassPubKey}
 	if m.preSharedKey != nil {
@@ -79,6 +113,16 @@ func (m *Manager) addPeer(rosenpassPubKey []byte, rosenpassAddr string, wireGuar
 		if pcfg.Endpoint, err = net.ResolveUDPAddr("udp", peerAddr); err != nil {
 			return fmt.Errorf("failed to resolve peer endpoint address: %w", err)
 		}
+		// Our local Rosenpass UDP server binds on the IPv6 wildcard ([::]) — see
+		// GetAddress(). The remote peer's endpoint (pcfg.Endpoint) is the destination
+		// our server will sendto when initiating handshakes. ResolveUDPAddr returns a
+		// 4-byte IPv4 for IPv4 hosts, which the kernel rejects (EDESTADDRREQ) when
+		// sent from an AF_INET6 socket. Normalize the remote endpoint to IPv4-mapped
+		// IPv6 so its address family matches our listening socket.
+		// TODO: maybe bind the Rosenpass UDP server to the peer wg IP addr
+		if v4 := pcfg.Endpoint.IP.To4(); v4 != nil {
+			pcfg.Endpoint.IP = v4.To16()
+		}
 	}
 	peerID, err := m.server.AddPeer(pcfg)
 	if err != nil {
@@ -182,24 +226,31 @@ func (m *Manager) Run() error {
 		return err
 	}
 
-	m.server, err = rp.NewUDPServer(conf)
+	server, err := rp.NewUDPServer(conf)
 	if err != nil {
 		return err
 	}
 
+	m.lock.Lock()
+	m.server = server
+	m.lock.Unlock()
+
 	log.Infof("starting rosenpass server on port %d", m.port)
 
-	return m.server.Run()
+	return server.Run()
 }
 
 // Close closes the Rosenpass server
 func (m *Manager) Close() error {
-	if m.server != nil {
-		err := m.server.Close()
-		if err != nil {
-			log.Errorf("failed closing local rosenpass server")
-		}
-		m.server = nil
+	m.lock.Lock()
+	server := m.server
+	m.server = nil
+	m.lock.Unlock()
+	if server == nil {
+		return nil
+	}
+	if err := server.Close(); err != nil {
+		log.Errorf("failed closing local rosenpass server: %v", err)
 	}
 	return nil
 }

client/internal/rosenpass/manager_test.go

@@ -1,14 +1,412 @@
 package rosenpass
 
 import (
+	"errors"
+	"os"
+	"sync"
 	"testing"
 
+	rp "cunicu.li/go-rosenpass"
 	"github.com/stretchr/testify/require"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 )
 
+// --- test doubles -----------------------------------------------------------
+
+type addPeerCall struct {
+	cfg rp.PeerConfig
+}
+
+type removePeerCall struct {
+	id rp.PeerID
+}
+
+type mockServer struct {
+	mu         sync.Mutex
+	addCalls   []addPeerCall
+	removed    []removePeerCall
+	nextID     rp.PeerID
+	addErr     error
+	removeErr  error
+	closed     bool
+	ran        bool
+}
+
+func (m *mockServer) AddPeer(cfg rp.PeerConfig) (rp.PeerID, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.addCalls = append(m.addCalls, addPeerCall{cfg: cfg})
+	if m.addErr != nil {
+		return rp.PeerID{}, m.addErr
+	}
+	// Increment a byte in nextID so distinct peers get distinct IDs.
+	m.nextID[0]++
+	return m.nextID, nil
+}
+
+func (m *mockServer) RemovePeer(id rp.PeerID) error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.removed = append(m.removed, removePeerCall{id: id})
+	return m.removeErr
+}
+
+func (m *mockServer) Run() error  { m.ran = true; return nil }
+func (m *mockServer) Close() error { m.closed = true; return nil }
+
+type setPSKCall struct {
+	peerKey    string
+	psk        wgtypes.Key
+	updateOnly bool
+}
+
+type mockIface struct {
+	mu    sync.Mutex
+	calls []setPSKCall
+	err   error
+}
+
+func (m *mockIface) SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.calls = append(m.calls, setPSKCall{peerKey: peerKey, psk: psk, updateOnly: updateOnly})
+	return m.err
+}
+
+// newTestManager builds a Manager with deterministic spk so tie-break
+// against a peer pubkey is controllable from tests. The provided spk byte
+// becomes the first byte; remaining bytes are zero.
+func newTestManager(spkFirstByte byte, mock *mockServer) *Manager {
+	spk := make([]byte, 32)
+	spk[0] = spkFirstByte
+	return &Manager{
+		ifaceName:   "wt0",
+		spk:         spk,
+		ssk:         make([]byte, 32),
+		rpKeyHash:   "test-hash",
+		rpPeerIDs:   make(map[string]*rp.PeerID),
+		rpWgHandler: NewNetbirdHandler(),
+		server:      mock,
+	}
+}
+
+// validWGKey returns a deterministic 32-byte wireguard public key (base64).
+func validWGKey(t *testing.T, lastByte byte) string {
+	t.Helper()
+	var k wgtypes.Key
+	k[31] = lastByte
+	return k.String()
+}
+
+// --- pure helpers ----------------------------------------------------------
+
+func TestHashRosenpassKey_Deterministic(t *testing.T) {
+	key := []byte("hello-rosenpass")
+	require.Equal(t, hashRosenpassKey(key), hashRosenpassKey(key))
+	require.Len(t, hashRosenpassKey(key), 64) // sha256 hex
+}
+
+func TestHashRosenpassKey_DifferentInputsDifferOutputs(t *testing.T) {
+	require.NotEqual(t, hashRosenpassKey([]byte("a")), hashRosenpassKey([]byte("b")))
+}
+
+func TestGetLogLevel_DefaultWhenUnset(t *testing.T) {
+	// Snapshot + unset to exercise the LookupEnv ok=false branch. t.Setenv
+	// can only set, not delete, so do it manually with restore via t.Cleanup.
+	prev, hadPrev := os.LookupEnv(defaultLogLevelVar)
+	require.NoError(t, os.Unsetenv(defaultLogLevelVar))
+	t.Cleanup(func() {
+		if hadPrev {
+			_ = os.Setenv(defaultLogLevelVar, prev)
+		} else {
+			_ = os.Unsetenv(defaultLogLevelVar)
+		}
+	})
+	require.Equal(t, defaultLog.String(), getLogLevel().String())
+}
+
+func TestGetLogLevel_Cases(t *testing.T) {
+	cases := map[string]string{
+		"debug":   "DEBUG",
+		"info":    "INFO",
+		"warn":    "WARN",
+		"error":   "ERROR",
+		"unknown": "INFO", // default fallback
+	}
+	for input, wantStr := range cases {
+		input, wantStr := input, wantStr
+		t.Run(input, func(t *testing.T) {
+			t.Setenv(defaultLogLevelVar, input)
+			require.Equal(t, wantStr, getLogLevel().String())
+		})
+	}
+}
+
 func TestFindRandomAvailableUDPPort(t *testing.T) {
 	port, err := findRandomAvailableUDPPort()
 	require.NoError(t, err)
 	require.Greater(t, port, 0)
 	require.LessOrEqual(t, port, 65535)
 }
+
+// --- addPeer ---------------------------------------------------------------
+
+func TestAddPeer_HigherLocalPubkey_SetsEndpoint(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv) // local spk lexicographically larger
+
+	remotePubKey := make([]byte, 32) // remote spk = all zeros (smaller)
+	err := m.addPeer(remotePubKey, "rosenpass-host:7000", "100.1.1.1", validWGKey(t, 1))
+	require.NoError(t, err)
+	require.Len(t, srv.addCalls, 1)
+
+	ep := srv.addCalls[0].cfg.Endpoint
+	require.NotNil(t, ep, "initiator side must set Endpoint")
+	require.Equal(t, 7000, ep.Port)
+	require.Equal(t, "100.1.1.1", ep.IP.String())
+}
+
+func TestAddPeer_HigherLocalPubkey_EndpointIPIsIPv4Mapped(t *testing.T) {
+	// Regression guard for the EDESTADDRREQ fix: Endpoint.IP must be 16-byte
+	// (IPv4-mapped IPv6) so it matches the AF_INET6 listening socket family.
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", validWGKey(t, 1))
+	require.NoError(t, err)
+
+	ep := srv.addCalls[0].cfg.Endpoint
+	require.NotNil(t, ep)
+	require.Len(t, ep.IP, 16, "IPv4 endpoint must be normalized to 16-byte v4-mapped form")
+	require.True(t, ep.IP.To4() != nil, "Endpoint must still be detected as IPv4")
+}
+
+func TestAddPeer_LowerLocalPubkey_LeavesEndpointNil(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0x00, srv) // local spk smaller
+
+	remotePubKey := make([]byte, 32)
+	remotePubKey[0] = 0xFF
+	err := m.addPeer(remotePubKey, "rp:5000", "100.1.1.1", validWGKey(t, 2))
+	require.NoError(t, err)
+
+	require.Nil(t, srv.addCalls[0].cfg.Endpoint, "responder side must NOT set Endpoint")
+}
+
+func TestAddPeer_PresharedKeyPropagated(t *testing.T) {
+	srv := &mockServer{}
+	psk := &wgtypes.Key{0x42}
+	m := newTestManager(0xFF, srv)
+	m.preSharedKey = (*[32]byte)(psk)
+
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", validWGKey(t, 3))
+	require.NoError(t, err)
+	require.Equal(t, [32]byte(*psk), [32]byte(srv.addCalls[0].cfg.PresharedKey))
+}
+
+func TestAddPeer_InvalidRosenpassAddr_ReturnsError(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv) // initiator path → parses rosenpassAddr
+
+	err := m.addPeer(make([]byte, 32), "not-a-host-port", "100.1.1.1", validWGKey(t, 1))
+	require.Error(t, err)
+	require.Empty(t, srv.addCalls, "server.AddPeer must not run when address parse fails")
+}
+
+func TestAddPeer_InvalidWireGuardPubKey_ReturnsError(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", "not-a-valid-key")
+	require.Error(t, err)
+}
+
+func TestAddPeer_ServerError_Propagates(t *testing.T) {
+	srv := &mockServer{addErr: errors.New("boom")}
+	m := newTestManager(0xFF, srv)
+
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", validWGKey(t, 1))
+	require.Error(t, err)
+}
+
+// Regression guard for issue #4341 (Android crash). If Run() has not completed
+// before OnConnected fires, m.rpWgHandler or m.server may be nil. Without the
+// nil guards, m.rpWgHandler.AddPeer panics on nil receiver.
+func TestAddPeer_NilHandler_ReturnsErrorNoCrash(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+	m.rpWgHandler = nil // simulate Run() not yet completed
+
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", validWGKey(t, 1))
+	require.Error(t, err)
+	require.Contains(t, err.Error(), "wg handler not initialized")
+}
+
+func TestAddPeer_NilServer_ReturnsErrorNoCrash(t *testing.T) {
+	m := newTestManager(0xFF, nil)
+	m.server = nil // simulate Run() not yet completed
+
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", validWGKey(t, 1))
+	require.Error(t, err)
+	require.Contains(t, err.Error(), "server not initialized")
+}
+
+// NewManager must pre-initialize rpWgHandler so the nil-receiver crash from
+// issue #4341 cannot occur in the window between NewManager and Run().
+func TestNewManager_PreInitializesHandler(t *testing.T) {
+	psk := wgtypes.Key{}
+	m, err := NewManager(&psk, "wt0")
+	require.NoError(t, err)
+	require.NotNil(t, m.rpWgHandler, "rpWgHandler must be initialized in NewManager")
+}
+
+func TestAddPeer_RecordsPeerID(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	wgKey := validWGKey(t, 5)
+	err := m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", wgKey)
+	require.NoError(t, err)
+	require.Contains(t, m.rpPeerIDs, wgKey)
+}
+
+// --- OnConnected / OnDisconnected ------------------------------------------
+
+func TestOnConnected_NilRemotePubKey_NoAddPeer(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	m.OnConnected(validWGKey(t, 1), nil, "100.1.1.1", "rp:5000")
+	require.Empty(t, srv.addCalls, "nil remote rosenpass pubkey must skip AddPeer")
+	require.Empty(t, m.rpPeerIDs)
+}
+
+func TestOnConnected_ValidPubKey_CallsAddPeer(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	wgKey := validWGKey(t, 1)
+	m.OnConnected(wgKey, make([]byte, 32), "100.1.1.1", "rp:5000")
+	require.Len(t, srv.addCalls, 1)
+	require.Contains(t, m.rpPeerIDs, wgKey)
+}
+
+func TestOnDisconnected_UnknownPeer_NoOp(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	m.OnDisconnected(validWGKey(t, 99))
+	require.Empty(t, srv.removed, "unknown peer key must not call RemovePeer")
+}
+
+func TestOnDisconnected_KnownPeer_CallsRemoveAndForgets(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	wgKey := validWGKey(t, 1)
+	require.NoError(t, m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", wgKey))
+	require.Contains(t, m.rpPeerIDs, wgKey)
+
+	m.OnDisconnected(wgKey)
+	require.Len(t, srv.removed, 1)
+	require.NotContains(t, m.rpPeerIDs, wgKey, "peer must be forgotten after disconnect")
+}
+
+// --- IsPresharedKeyInitialized ---------------------------------------------
+
+func TestIsPresharedKeyInitialized_UnknownPeer_ReturnsFalse(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+	require.False(t, m.IsPresharedKeyInitialized(validWGKey(t, 1)))
+}
+
+func TestIsPresharedKeyInitialized_AddedButNotHandshaken_ReturnsFalse(t *testing.T) {
+	srv := &mockServer{}
+	m := newTestManager(0xFF, srv)
+
+	wgKey := validWGKey(t, 2)
+	require.NoError(t, m.addPeer(make([]byte, 32), "rp:5000", "100.1.1.1", wgKey))
+	require.False(t, m.IsPresharedKeyInitialized(wgKey))
+}
+
+// --- NetbirdHandler.outputKey ----------------------------------------------
+
+func TestHandler_OutputKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
+	h := NewNetbirdHandler()
+	iface := &mockIface{}
+	h.SetInterface(iface)
+
+	pid := rp.PeerID{0x01}
+	wgKey := wgtypes.Key{0xAA}
+	h.AddPeer(pid, "wt0", rp.Key(wgKey))
+
+	psk := rp.Key{0xBB}
+	h.HandshakeCompleted(pid, psk)
+
+	require.Len(t, iface.calls, 1)
+	require.False(t, iface.calls[0].updateOnly, "first PSK rotation must use updateOnly=false")
+	require.Equal(t, wgKey.String(), iface.calls[0].peerKey)
+}
+
+func TestHandler_OutputKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
+	h := NewNetbirdHandler()
+	iface := &mockIface{}
+	h.SetInterface(iface)
+
+	pid := rp.PeerID{0x02}
+	h.AddPeer(pid, "wt0", rp.Key(wgtypes.Key{0xCC}))
+
+	h.HandshakeCompleted(pid, rp.Key{0x01}) // first
+	h.HandshakeCompleted(pid, rp.Key{0x02}) // second
+
+	require.Len(t, iface.calls, 2)
+	require.False(t, iface.calls[0].updateOnly)
+	require.True(t, iface.calls[1].updateOnly, "subsequent rotations must use updateOnly=true")
+}
+
+func TestHandler_OutputKey_NilInterface_NoCrashNoCall(t *testing.T) {
+	h := NewNetbirdHandler()
+	// no SetInterface — iface remains nil
+	pid := rp.PeerID{0x03}
+	h.AddPeer(pid, "wt0", rp.Key(wgtypes.Key{}))
+
+	// Must not panic.
+	h.HandshakeCompleted(pid, rp.Key{})
+}
+
+func TestHandler_OutputKey_UnknownPeer_NoCall(t *testing.T) {
+	h := NewNetbirdHandler()
+	iface := &mockIface{}
+	h.SetInterface(iface)
+
+	h.HandshakeCompleted(rp.PeerID{0xFF}, rp.Key{})
+	require.Empty(t, iface.calls, "unknown peer id must not trigger SetPresharedKey")
+}
+
+func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) {
+	h := NewNetbirdHandler()
+	iface := &mockIface{}
+	h.SetInterface(iface)
+
+	pid := rp.PeerID{0x04}
+	h.AddPeer(pid, "wt0", rp.Key(wgtypes.Key{0xDD}))
+	h.HandshakeCompleted(pid, rp.Key{0x01})
+	require.True(t, h.IsPeerInitialized(pid))
+
+	h.RemovePeer(pid)
+	require.False(t, h.IsPeerInitialized(pid), "RemovePeer must clear initialized flag")
+}
+
+func TestHandler_SetInterfaceAfterAddPeer_StillReceivesKey(t *testing.T) {
+	h := NewNetbirdHandler()
+	pid := rp.PeerID{0x05}
+	wgKey := wgtypes.Key{0xEE}
+	h.AddPeer(pid, "wt0", rp.Key(wgKey))
+
+	iface := &mockIface{}
+	h.SetInterface(iface) // set after AddPeer
+
+	h.HandshakeCompleted(pid, rp.Key{0x42})
+	require.Len(t, iface.calls, 1)
+	require.Equal(t, wgKey.String(), iface.calls[0].peerKey)
+}

client/internal/rosenpass/seed.go

@@ -0,0 +1,42 @@
+package rosenpass
+
+import (
+	"fmt"
+
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+)
+
+// DeterministicSeedKey derives a 32-byte WireGuard preshared key from a pair
+// of peer public keys. Both peers, given the same key pair, produce the same
+// output regardless of which side runs the function: the inputs are ordered
+// lexicographically before concatenation.
+//
+// NetBird uses this value as the initial Rosenpass-side preshared key when no
+// explicit account-level PSK is configured, so both peers converge on the same
+// PSK before the first post-quantum handshake completes.
+//
+// The resulting key MUST NOT be treated as quantum-safe: it is deterministic
+// from public keys and exists only to seed WireGuard until Rosenpass rotates
+// in a real post-quantum PSK.
+func DeterministicSeedKey(localKey, remoteKey string) (*wgtypes.Key, error) {
+	lk := []byte(localKey)
+	rk := []byte(remoteKey)
+	if len(lk) < 16 || len(rk) < 16 {
+		return nil, fmt.Errorf("rosenpass: peer keys must be at least 16 bytes (got local=%d, remote=%d)", len(lk), len(rk))
+	}
+
+	var keyInput []byte
+	if localKey > remoteKey {
+		keyInput = append(keyInput, lk[:16]...)
+		keyInput = append(keyInput, rk[:16]...)
+	} else {
+		keyInput = append(keyInput, rk[:16]...)
+		keyInput = append(keyInput, lk[:16]...)
+	}
+
+	key, err := wgtypes.NewKey(keyInput)
+	if err != nil {
+		return nil, fmt.Errorf("rosenpass: deterministic seed key: %w", err)
+	}
+	return &key, nil
+}

client/internal/rosenpass/seed_test.go

@@ -0,0 +1,44 @@
+package rosenpass
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestDeterministicSeedKey_SameForBothSides(t *testing.T) {
+	// Peer A and peer B must derive the same PSK regardless of which side
+	// computes it: the function orders inputs internally.
+	a := strings.Repeat("a", 32)
+	b := strings.Repeat("b", 32)
+
+	keyAB, err := DeterministicSeedKey(a, b)
+	require.NoError(t, err)
+	keyBA, err := DeterministicSeedKey(b, a)
+	require.NoError(t, err)
+	require.Equal(t, keyAB.String(), keyBA.String(), "swapping arguments must yield identical key")
+}
+
+func TestDeterministicSeedKey_ChangesWithKeys(t *testing.T) {
+	a := strings.Repeat("a", 32)
+	b := strings.Repeat("b", 32)
+	c := strings.Repeat("c", 32)
+
+	keyAB, err := DeterministicSeedKey(a, b)
+	require.NoError(t, err)
+	keyAC, err := DeterministicSeedKey(a, c)
+	require.NoError(t, err)
+	require.NotEqual(t, keyAB.String(), keyAC.String(), "different peer pair must yield different key")
+}
+
+func TestDeterministicSeedKey_TooShortKey_ReturnsError(t *testing.T) {
+	short := "short" // < 16 bytes
+	long := strings.Repeat("x", 32)
+
+	_, err := DeterministicSeedKey(short, long)
+	require.Error(t, err)
+	_, err = DeterministicSeedKey(long, short)
+	require.Error(t, err)
+}
+

client/internal/routemanager/manager.go

@@ -53,6 +53,7 @@ type Manager interface {
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
 	GetSelectedClientRoutes() route.HAMap
+	GetActiveClientRoutes() route.HAMap
 	GetClientRoutesWithNetID() map[route.NetID][]*route.Route
 	SetRouteChangeListener(listener listener.NetworkChangeListener)
 	InitialRouteRange() []string
@@ -485,6 +486,39 @@ func (m *DefaultManager) GetSelectedClientRoutes() route.HAMap {
 	return m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
 }
 
+// GetActiveClientRoutes returns the subset of selected client routes
+// that are currently reachable: the route's peer is Connected and is
+// the one actively carrying the route (not just an HA sibling).
+func (m *DefaultManager) GetActiveClientRoutes() route.HAMap {
+	m.mux.Lock()
+	selected := m.routeSelector.FilterSelectedExitNodes(maps.Clone(m.clientRoutes))
+	recorder := m.statusRecorder
+	m.mux.Unlock()
+
+	if recorder == nil {
+		return selected
+	}
+
+	out := make(route.HAMap, len(selected))
+	for id, routes := range selected {
+		for _, r := range routes {
+			st, err := recorder.GetPeer(r.Peer)
+			if err != nil {
+				continue
+			}
+			if st.ConnStatus != peer.StatusConnected {
+				continue
+			}
+			if _, hasRoute := st.GetRoutes()[r.Network.String()]; !hasRoute {
+				continue
+			}
+			out[id] = routes
+			break
+		}
+	}
+	return out
+}
+
 // GetClientRoutesWithNetID returns the current routes from the route map, but the keys consist of the network ID only
 func (m *DefaultManager) GetClientRoutesWithNetID() map[route.NetID][]*route.Route {
 	m.mux.Lock()
@@ -666,6 +700,13 @@ func resolveURLsToIPs(urls []string) []net.IP {
 
 // updateRouteSelectorFromManagement updates the route selector based on the isSelected status from the management server
 func (m *DefaultManager) updateRouteSelectorFromManagement(clientRoutes route.HAMap) {
+	// An explicit user "deselect all" must not be overridden by management auto-apply.
+	// Auto-applying an exit node here would call SelectRoutes, which clears the
+	// deselect-all flag and re-enables every route the user turned off.
+	if m.routeSelector.IsDeselectAll() {
+		return
+	}
+
 	exitNodeInfo := m.collectExitNodeInfo(clientRoutes)
 	if len(exitNodeInfo.allIDs) == 0 {
 		return
@@ -704,7 +745,10 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 }
 
 func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
-	return len(routes) > 0 && routes[0].Network.String() == vars.ExitNodeCIDR
+	if len(routes) == 0 {
+		return false
+	}
+	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
 }
 
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {

client/internal/routemanager/manager_test.go

@@ -1,3 +1,5 @@
+//go:build privileged
+
 package routemanager
 
 import (

client/internal/routemanager/mock.go

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

client/internal/routemanager/selector_management_test.go

@@ -0,0 +1,71 @@
+package routemanager
+
+import (
+	"net/netip"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/internal/routeselector"
+	"github.com/netbirdio/netbird/route"
+)
+
+func exitNodeRoutes(netID route.NetID, skipAutoApply bool) route.HAMap {
+	haID := route.HAUniqueID(string(netID) + "|0.0.0.0/0")
+	return route.HAMap{
+		haID: []*route.Route{
+			{
+				ID:            "r-" + route.ID(netID),
+				NetID:         netID,
+				Network:       netip.MustParsePrefix("0.0.0.0/0"),
+				NetworkType:   route.IPv4Network,
+				Enabled:       true,
+				SkipAutoApply: skipAutoApply,
+			},
+		},
+	}
+}
+
+func TestUpdateRouteSelectorFromManagement(t *testing.T) {
+	t.Run("management auto-apply selects exit node without user selection", func(t *testing.T) {
+		m := &DefaultManager{routeSelector: routeselector.NewRouteSelector()}
+		routes := exitNodeRoutes("exit1", false)
+
+		m.updateRouteSelectorFromManagement(routes)
+
+		require.True(t, m.routeSelector.IsSelected("exit1"), "auto-apply exit node should be selected")
+		require.Len(t, m.routeSelector.FilterSelectedExitNodes(routes), 1, "selected exit node should pass the filter")
+	})
+
+	t.Run("management SkipAutoApply leaves exit node deselected", func(t *testing.T) {
+		m := &DefaultManager{routeSelector: routeselector.NewRouteSelector()}
+		routes := exitNodeRoutes("exit1", true)
+
+		m.updateRouteSelectorFromManagement(routes)
+
+		require.False(t, m.routeSelector.IsSelected("exit1"), "SkipAutoApply exit node should not be selected")
+		require.Empty(t, m.routeSelector.FilterSelectedExitNodes(routes), "deselected exit node should be filtered out")
+	})
+
+	t.Run("user selection is not overridden by management", func(t *testing.T) {
+		m := &DefaultManager{routeSelector: routeselector.NewRouteSelector()}
+		require.NoError(t, m.routeSelector.SelectRoutes([]route.NetID{"exit1"}, true, []route.NetID{"exit1"}))
+		routes := exitNodeRoutes("exit1", true)
+
+		m.updateRouteSelectorFromManagement(routes)
+
+		require.True(t, m.routeSelector.IsSelected("exit1"), "explicit user selection must survive a management sync that wants to skip auto-apply")
+		require.Len(t, m.routeSelector.FilterSelectedExitNodes(routes), 1, "user-selected exit node should pass the filter")
+	})
+
+	t.Run("deselect-all is preserved across a management sync", func(t *testing.T) {
+		m := &DefaultManager{routeSelector: routeselector.NewRouteSelector()}
+		m.routeSelector.DeselectAllRoutes()
+		routes := exitNodeRoutes("exit1", false)
+
+		m.updateRouteSelectorFromManagement(routes)
+
+		require.True(t, m.routeSelector.IsDeselectAll(), "an explicit deselect-all must not be cleared by management auto-apply")
+		require.Empty(t, m.routeSelector.FilterSelectedExitNodes(routes), "no routes should be selected while deselect-all is set")
+	})
+}

client/internal/routemanager/systemops/routeflags_addfilter_bsd.go

@@ -0,0 +1,9 @@
+//go:build dragonfly || freebsd || netbsd || openbsd
+
+package systemops
+
+// IgnoreAddedDefaultRoute reports whether an RTM_ADD default route with the
+// given flags should be ignored by the network monitor.
+func IgnoreAddedDefaultRoute(flags int) bool {
+	return filterRoutesByFlags(flags)
+}

client/internal/routemanager/systemops/routeflags_addfilter_darwin.go

@@ -0,0 +1,21 @@
+//go:build darwin
+
+package systemops
+
+import "golang.org/x/sys/unix"
+
+// IgnoreAddedDefaultRoute reports whether an RTM_ADD default route with the
+// given flags should be ignored by the network monitor. Scoped routes
+// (RTF_IFSCOPE) are tied to a specific interface index and cannot replace the
+// unscoped default the kernel uses for general egress, so flapping ones (e.g.
+// Wi-Fi calling IMS tunnels on ipsec0, Docker bridges, scoped utun defaults)
+// must not trigger an engine restart.
+func IgnoreAddedDefaultRoute(flags int) bool {
+	if filterRoutesByFlags(flags) {
+		return true
+	}
+	if flags&unix.RTF_IFSCOPE != 0 {
+		return true
+	}
+	return false
+}

client/internal/routemanager/systemops/rt_tables_linux_test.go

@@ -0,0 +1,69 @@
+//go:build linux && !android
+
+package systemops
+
+import (
+	"fmt"
+	"os"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestEntryExists(t *testing.T) {
+	tempDir := t.TempDir()
+	tempFilePath := fmt.Sprintf("%s/rt_tables", tempDir)
+
+	content := []string{
+		"1000 reserved",
+		fmt.Sprintf("%d %s", NetbirdVPNTableID, NetbirdVPNTableName),
+		"9999 other_table",
+	}
+	require.NoError(t, os.WriteFile(tempFilePath, []byte(strings.Join(content, "\n")), 0644))
+
+	file, err := os.Open(tempFilePath)
+	require.NoError(t, err)
+	defer func() {
+		assert.NoError(t, file.Close())
+	}()
+
+	tests := []struct {
+		name        string
+		id          int
+		shouldExist bool
+		err         error
+	}{
+		{
+			name:        "ExistsWithNetbirdPrefix",
+			id:          7120,
+			shouldExist: true,
+			err:         nil,
+		},
+		{
+			name:        "ExistsWithDifferentName",
+			id:          1000,
+			shouldExist: true,
+			err:         ErrTableIDExists,
+		},
+		{
+			name:        "DoesNotExist",
+			id:          1234,
+			shouldExist: false,
+			err:         nil,
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			exists, err := entryExists(file, tc.id)
+			if tc.err != nil {
+				assert.ErrorIs(t, err, tc.err)
+			} else {
+				assert.NoError(t, err)
+			}
+			assert.Equal(t, tc.shouldExist, exists)
+		})
+	}
+}

client/internal/routemanager/systemops/systemops_bsd_privileged_test.go

@@ -0,0 +1,191 @@
+//go:build (darwin || dragonfly || freebsd || netbsd || openbsd) && privileged
+
+package systemops
+
+import (
+	"fmt"
+	"net"
+	"net/netip"
+	"os/exec"
+	"regexp"
+	"runtime"
+	"strings"
+	"sync"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func init() {
+	testCases = append(testCases, []testCase{
+		{
+			name:              "To more specific route without custom dialer via vpn",
+			expectedInterface: expectedVPNint,
+			dialer:            &net.Dialer{},
+			expectedPacket:    createPacketExpectation("100.64.0.1", 12345, "10.10.0.2", 53),
+		},
+	}...)
+}
+
+func TestConcurrentRoutes(t *testing.T) {
+	baseIP := netip.MustParseAddr("192.0.2.0")
+
+	var intf *net.Interface
+	var nexthop Nexthop
+
+	_, intf = setupDummyInterface(t)
+	nexthop = Nexthop{netip.Addr{}, intf}
+
+	r := New(nil, nil)
+
+	var wg sync.WaitGroup
+	for i := 0; i < 1024; i++ {
+		wg.Add(1)
+		go func(ip netip.Addr) {
+			defer wg.Done()
+			prefix := netip.PrefixFrom(ip, 32)
+			if err := r.addToRouteTable(prefix, nexthop); err != nil {
+				t.Errorf("Failed to add route for %s: %v", prefix, err)
+			}
+		}(baseIP)
+		baseIP = baseIP.Next()
+	}
+
+	wg.Wait()
+
+	baseIP = netip.MustParseAddr("192.0.2.0")
+
+	for i := 0; i < 1024; i++ {
+		wg.Add(1)
+		go func(ip netip.Addr) {
+			defer wg.Done()
+			prefix := netip.PrefixFrom(ip, 32)
+			if err := r.removeFromRouteTable(prefix, nexthop); err != nil {
+				t.Errorf("Failed to remove route for %s: %v", prefix, err)
+			}
+		}(baseIP)
+		baseIP = baseIP.Next()
+	}
+
+	wg.Wait()
+}
+
+func createAndSetupDummyInterface(t *testing.T, intf string, ipAddressCIDR string) string {
+	t.Helper()
+
+	if runtime.GOOS == "darwin" {
+		err := exec.Command("ifconfig", intf, "alias", ipAddressCIDR).Run()
+		require.NoError(t, err, "Failed to create loopback alias")
+
+		t.Cleanup(func() {
+			err := exec.Command("ifconfig", intf, ipAddressCIDR, "-alias").Run()
+			assert.NoError(t, err, "Failed to remove loopback alias")
+		})
+
+		return intf
+	}
+
+	prefix, err := netip.ParsePrefix(ipAddressCIDR)
+	require.NoError(t, err, "Failed to parse prefix")
+
+	netIntf, err := net.InterfaceByName(intf)
+	require.NoError(t, err, "Failed to get interface by name")
+
+	nexthop := Nexthop{netip.Addr{}, netIntf}
+
+	r := New(nil, nil)
+	err = r.addToRouteTable(prefix, nexthop)
+	require.NoError(t, err, "Failed to add route to table")
+
+	t.Cleanup(func() {
+		err := r.removeFromRouteTable(prefix, nexthop)
+		assert.NoError(t, err, "Failed to remove route from table")
+	})
+
+	return intf
+}
+
+func addDummyRoute(t *testing.T, dstCIDR string, gw netip.Addr, _ string) {
+	t.Helper()
+
+	var originalNexthop net.IP
+	if dstCIDR == "0.0.0.0/0" {
+		var err error
+		originalNexthop, err = fetchOriginalGateway()
+		if err != nil {
+			t.Logf("Failed to fetch original gateway: %v", err)
+		}
+
+		if output, err := exec.Command("route", "delete", "-net", dstCIDR).CombinedOutput(); err != nil {
+			t.Logf("Failed to delete route: %v, output: %s", err, output)
+		}
+	}
+
+	t.Cleanup(func() {
+		if originalNexthop != nil {
+			err := exec.Command("route", "add", "-net", dstCIDR, originalNexthop.String()).Run()
+			assert.NoError(t, err, "Failed to restore original route")
+		}
+	})
+
+	err := exec.Command("route", "add", "-net", dstCIDR, gw.String()).Run()
+	require.NoError(t, err, "Failed to add route")
+
+	t.Cleanup(func() {
+		err := exec.Command("route", "delete", "-net", dstCIDR).Run()
+		assert.NoError(t, err, "Failed to remove route")
+	})
+}
+
+func fetchOriginalGateway() (net.IP, error) {
+	output, err := exec.Command("route", "-n", "get", "default").CombinedOutput()
+	if err != nil {
+		return nil, err
+	}
+
+	matches := regexp.MustCompile(`gateway: (\S+)`).FindStringSubmatch(string(output))
+	if len(matches) == 0 {
+		return nil, fmt.Errorf("gateway not found")
+	}
+
+	return net.ParseIP(matches[1]), nil
+}
+
+// setupDummyInterface creates a dummy tun interface for FreeBSD route testing
+func setupDummyInterface(t *testing.T) (netip.Addr, *net.Interface) {
+	t.Helper()
+
+	if runtime.GOOS == "darwin" {
+		return netip.AddrFrom4([4]byte{192, 168, 1, 2}), &net.Interface{Name: "lo0"}
+	}
+
+	output, err := exec.Command("ifconfig", "tun", "create").CombinedOutput()
+	require.NoError(t, err, "Failed to create tun interface: %s", string(output))
+
+	tunName := strings.TrimSpace(string(output))
+
+	output, err = exec.Command("ifconfig", tunName, "192.168.1.1", "netmask", "255.255.0.0", "192.168.1.2", "up").CombinedOutput()
+	require.NoError(t, err, "Failed to configure tun interface: %s", string(output))
+
+	intf, err := net.InterfaceByName(tunName)
+	require.NoError(t, err, "Failed to get interface by name")
+
+	t.Cleanup(func() {
+		if err := exec.Command("ifconfig", tunName, "destroy").Run(); err != nil {
+			t.Logf("Failed to destroy tun interface %s: %v", tunName, err)
+		}
+	})
+
+	return netip.AddrFrom4([4]byte{192, 168, 1, 2}), intf
+}
+
+func setupDummyInterfacesAndRoutes(t *testing.T) {
+	t.Helper()
+
+	defaultDummy := createAndSetupDummyInterface(t, expectedExternalInt, "192.168.0.1/24")
+	addDummyRoute(t, "0.0.0.0/0", netip.AddrFrom4([4]byte{192, 168, 0, 1}), defaultDummy)
+
+	otherDummy := createAndSetupDummyInterface(t, expectedInternalInt, "192.168.1.1/24")
+	addDummyRoute(t, "10.0.0.0/8", netip.AddrFrom4([4]byte{192, 168, 1, 1}), otherDummy)
+}