[management] enrich context in permissions manager (#6286)

* Pin actions with SHA, replace unmaintained, add dependabot for actions

* Update FreeBSD to version 15 for tests

* Use shared actions

* Update sign-pipelines version

.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') }}
@@ -44,4 +46,3 @@ jobs:
 
       - 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)
-

.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 }}
@@ -158,14 +162,16 @@ jobs:
 
   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 +183,7 @@ 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: |
@@ -231,10 +237,12 @@ 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 +254,10 @@ 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 }}
@@ -277,14 +285,16 @@ 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
@@ -298,7 +308,7 @@ 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 }}
@@ -324,14 +334,16 @@ 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 +355,10 @@ 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 }}
@@ -370,19 +382,21 @@ jobs:
 
   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 +404,10 @@ 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 +424,7 @@ 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 }}
@@ -427,7 +441,7 @@ 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 \
@@ -437,13 +451,13 @@ jobs:
 
   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 +488,12 @@ 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 +501,10 @@ 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 +521,7 @@ 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 +545,13 @@ 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 +582,12 @@ 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 +595,10 @@ 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 +615,7 @@ 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 +641,22 @@ 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 +664,10 @@ 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 }}

.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 +20,66 @@ 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.`
-              );
+            const modifiedPbFiles = files.filter(
+              f => f.filename.endsWith('.pb.go') && f.status === 'modified'
+            );
+            if (modifiedPbFiles.length === 0) {
+              console.log('No modified .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) {
+            const versionPattern = /^\s*\/\/\s+protoc(?:-gen-go)?\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 modifiedPbFiles) {
+              const [base, head] = await Promise.all([
+                getVersionHeader(file.filename, baseSha),
+                getVersionHeader(file.filename, headSha),
+              ]);
+              if (!base.ok || !head.ok) {
+                core.warning(
+                  `Skipping ${file.filename}: base=${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,
+                  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"
@@ -24,7 +24,9 @@ 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
@@ -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
@@ -65,4 +69,3 @@ jobs:
             echo "Wasm binary size (${SIZE_MB}MB) exceeds 56MB 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.

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/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/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,
@@ -405,6 +440,21 @@ 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 isn't in this client's peer
+// roster — callers should treat that as "unknown peer".
+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 +523,25 @@ 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/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/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

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

client/internal/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) == 0 {
+		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 +2667,114 @@ 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"},
+		},
+	}
+
+	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/server_android.go

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

client/internal/dns/server_test.go

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

client/internal/dns/systemd_linux.go

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

client/internal/dns/upstream.go

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

client/internal/dns/upstream_android.go

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

client/internal/dns/upstream_general.go

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

client/internal/dns/upstream_ios.go

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

client/internal/dns/upstream_test.go

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

client/internal/engine.go

@@ -512,16 +512,7 @@ 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())
@@ -1386,9 +1377,6 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	e.networkSerial = serial
 
-	// Test received (upstream) servers for availability right away instead of upon usage.
-	// If no server of a server group responds this will disable the respective handler and retry later.
-	go e.dnsServer.ProbeAvailability()
 	return nil
 }
 
@@ -1932,7 +1920,7 @@ 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 +1967,29 @@ 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 {

client/internal/engine_test.go

@@ -27,7 +27,7 @@ import (
 	"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/server/integrations/integrated_validator/validator"
 
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/update_channel"
@@ -66,8 +66,8 @@ import (
 	"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"
@@ -1641,7 +1641,7 @@ func startManagement(t *testing.T, dataDir, testFile string) (*grpc.Server, stri
 		return nil, "", err
 	}
 
-	ia, _ := integrations.NewIntegratedValidator(context.Background(), peersManager, nil, eventStore, cacheStore)
+	ia, _ := validator.NewIntegratedValidator(context.Background(), peersManager, nil, eventStore, cacheStore)
 
 	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
 	require.NoError(t, err)

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/status.go

@@ -185,9 +185,12 @@ 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
 	changeNotify          map[string]map[string]*StatusChangeSubscription // map[peerID]map[subscriptionID]*StatusChangeSubscription
 	signalState           bool
@@ -283,8 +286,8 @@ func (d *Status) AddPeer(peerPubKey string, fqdn string, ip string, ipv6 string)
 
 // 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 +297,8 @@ 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 {
@@ -305,6 +308,25 @@ 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. Returns the
+// zero State and false when no peer matches or the input is empty.
+func (d *Status) PeerStateByIP(ip string) (State, bool) {
+	if ip == "" {
+		return State{}, false
+	}
+	d.mux.RLock()
+	defer d.mux.RUnlock()
+
+	for _, state := range d.peers {
+		if (state.IP != "" && state.IP == ip) || (state.IPv6 != "" && state.IPv6 == ip) {
+			return state, true
+		}
+	}
+	return State{}, false
+}
+
 // RemovePeer removes peer from Daemon status map
 func (d *Status) RemovePeer(peerPubKey string) error {
 	d.mux.Lock()
@@ -702,8 +724,8 @@ 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 +931,8 @@ 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 +940,14 @@ 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 +973,8 @@ 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 +989,8 @@ 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 +1000,8 @@ 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 +1030,8 @@ 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 +1040,16 @@ 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 +1065,8 @@ 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 +1241,8 @@ 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")
 	}

client/internal/peer/status_test.go

@@ -63,6 +63,33 @@ 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")
+}
+
 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/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()
@@ -704,7 +738,10 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 }
 
 func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
-	return len(routes) > 0 && routes[0].Network.String() == vars.ExitNodeCIDR
+	if len(routes) == 0 {
+		return false
+	}
+	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
 }
 
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {

client/internal/routemanager/mock.go

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

client/internal/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/routeselector/routeselector.go

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

client/internal/routeselector/routeselector_test.go

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

client/internal/sleep/detector_darwin.go

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

client/internal/statemanager/manager.go

@@ -96,17 +96,19 @@ func (m *Manager) Stop(ctx context.Context) error {
 	}
 
 	m.mu.Lock()
-	defer m.mu.Unlock()
+	cancel := m.cancel
+	done := m.done
+	m.mu.Unlock()
 
-	if m.cancel == nil {
+	if cancel == nil {
 		return nil
 	}
-	m.cancel()
+	cancel()
 
 	select {
 	case <-ctx.Done():
 		return ctx.Err()
-	case <-m.done:
+	case <-done:
 	}
 
 	return nil

client/ios/NetBirdSDK/client.go

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

client/server/server_test.go

@@ -13,7 +13,7 @@ import (
 	"github.com/stretchr/testify/require"
 	"go.opentelemetry.io/otel"
 
-	"github.com/netbirdio/management-integrations/integrations"
+	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator/validator"
 
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/update_channel"
@@ -315,7 +315,7 @@ func startManagement(t *testing.T, signalAddr string, counter *int) (*grpc.Serve
 		return nil, "", err
 	}
 
-	ia, _ := integrations.NewIntegratedValidator(context.Background(), peersManager, settingsManagerMock, eventStore, cacheStore)
+	ia, _ := validator.NewIntegratedValidator(context.Background(), peersManager, settingsManagerMock, eventStore, cacheStore)
 
 	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
 	require.NoError(t, err)

client/system/info_linux.go

@@ -3,15 +3,14 @@
 package system
 
 import (
-	"bytes"
 	"context"
 	"os"
-	"os/exec"
 	"regexp"
 	"runtime"
-	"strings"
 	"time"
 
+	"golang.org/x/sys/unix"
+
 	log "github.com/sirupsen/logrus"
 	"github.com/zcalusic/sysinfo"
 
@@ -29,19 +28,11 @@ func UpdateStaticInfoAsync() {
 
 // GetInfo retrieves and parses the system information
 func GetInfo(ctx context.Context) *Info {
-	info := _getInfo()
-	for strings.Contains(info, "broken pipe") {
-		info = _getInfo()
-		time.Sleep(500 * time.Millisecond)
-	}
-
-	osStr := strings.ReplaceAll(info, "\n", "")
-	osStr = strings.ReplaceAll(osStr, "\r\n", "")
-	osInfo := strings.Split(osStr, " ")
+	kernelName, kernelVersion, kernelPlatform := kernelInfo()
 
 	osName, osVersion := readOsReleaseFile()
 	if osName == "" {
-		osName = osInfo[3]
+		osName = kernelName
 	}
 
 	systemHostname, _ := os.Hostname()
@@ -58,8 +49,8 @@ func GetInfo(ctx context.Context) *Info {
 	}
 
 	gio := &Info{
-		Kernel:             osInfo[0],
-		Platform:           osInfo[2],
+		Kernel:             kernelName,
+		Platform:           kernelPlatform,
 		OS:                 osName,
 		OSVersion:          osVersion,
 		Hostname:           extractDeviceName(ctx, systemHostname),
@@ -67,7 +58,7 @@ func GetInfo(ctx context.Context) *Info {
 		CPUs:               runtime.NumCPU(),
 		NetbirdVersion:     version.NetbirdVersion(),
 		UIVersion:          extractUserAgent(ctx),
-		KernelVersion:      osInfo[1],
+		KernelVersion:      kernelVersion,
 		NetworkAddresses:   addrs,
 		SystemSerialNumber: si.SystemSerialNumber,
 		SystemProductName:  si.SystemProductName,
@@ -78,18 +69,12 @@ func GetInfo(ctx context.Context) *Info {
 	return gio
 }
 
-func _getInfo() string {
-	cmd := exec.Command("uname", "-srio")
-	cmd.Stdin = strings.NewReader("some")
-	var out bytes.Buffer
-	var stderr bytes.Buffer
-	cmd.Stdout = &out
-	cmd.Stderr = &stderr
-	err := cmd.Run()
-	if err != nil {
-		log.Warnf("getInfo: %s", err)
+func kernelInfo() (string, string, string) {
+	var uts unix.Utsname
+	if err := unix.Uname(&uts); err != nil {
+		return "", "", ""
 	}
-	return out.String()
+	return unix.ByteSliceToString(uts.Sysname[:]), unix.ByteSliceToString(uts.Release[:]), unix.ByteSliceToString(uts.Machine[:])
 }
 
 func sysInfo() (string, string, string) {

client/ui/network.go

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

client/wasm/internal/rdp/cert_validation.go

@@ -6,6 +6,7 @@ import (
 	"crypto/tls"
 	"crypto/x509"
 	"fmt"
+	"sync"
 	"syscall/js"
 	"time"
 
@@ -13,7 +14,7 @@ import (
 )
 
 const (
-	certValidationTimeout = 60 * time.Second
+	certValidationTimeout = 5 * time.Minute
 )
 
 func (p *RDCleanPathProxy) validateCertificateWithJS(conn *proxyConnection, certChain [][]byte) (bool, error) {
@@ -46,17 +47,31 @@ func (p *RDCleanPathProxy) validateCertificateWithJS(conn *proxyConnection, cert
 
 	promise := conn.wsHandlers.Call("onCertificateRequest", certInfo)
 
-	resultChan := make(chan bool)
-	errorChan := make(chan error)
+	resultChan := make(chan bool, 1)
+	errorChan := make(chan error, 1)
 
-	promise.Call("then", js.FuncOf(func(this js.Value, args []js.Value) interface{} {
-		result := args[0].Bool()
-		resultChan <- result
+	// Release from inside the callbacks so a post-timeout promise resolution
+	// does not invoke an already-released func.
+	var thenFn, catchFn js.Func
+	var releaseOnce sync.Once
+	release := func() {
+		releaseOnce.Do(func() {
+			thenFn.Release()
+			catchFn.Release()
+		})
+	}
+	thenFn = js.FuncOf(func(this js.Value, args []js.Value) interface{} {
+		defer release()
+		resultChan <- args[0].Bool()
 		return nil
-	})).Call("catch", js.FuncOf(func(this js.Value, args []js.Value) interface{} {
+	})
+	catchFn = js.FuncOf(func(this js.Value, args []js.Value) interface{} {
+		defer release()
 		errorChan <- fmt.Errorf("certificate validation failed")
 		return nil
-	}))
+	})
+
+	promise.Call("then", thenFn).Call("catch", catchFn)
 
 	select {
 	case result := <-resultChan:

client/wasm/internal/rdp/rdcleanpath.go

@@ -11,6 +11,7 @@ import (
 	"io"
 	"net"
 	"sync"
+	"sync/atomic"
 	"syscall/js"
 	"time"
 
@@ -57,6 +58,8 @@ type RDCleanPathProxy struct {
 	}
 	activeConnections map[string]*proxyConnection
 	destinations      map[string]string
+	pendingHandlers   map[string]js.Func
+	nextID            atomic.Uint64
 	mu                sync.Mutex
 }
 
@@ -66,8 +69,15 @@ type proxyConnection struct {
 	rdpConn     net.Conn
 	tlsConn     *tls.Conn
 	wsHandlers  js.Value
-	ctx         context.Context
-	cancel      context.CancelFunc
+	// Go-side callbacks exposed to JS. js.FuncOf pins the Go closure in a
+	// global handle map and MUST be released, otherwise every connection
+	// leaks the Go memory the closure captures.
+	wsHandlerFn  js.Func
+	onMessageFn  js.Func
+	onCloseFn    js.Func
+	cleanupOnce  sync.Once
+	ctx          context.Context
+	cancel       context.CancelFunc
 }
 
 // NewRDCleanPathProxy creates a new RDCleanPath proxy
@@ -80,7 +90,11 @@ func NewRDCleanPathProxy(client interface {
 	}
 }
 
-// CreateProxy creates a new proxy endpoint for the given destination
+// CreateProxy creates a new proxy endpoint for the given destination.
+// The registered handler fn and its destinations/pendingHandlers entries are
+// only released once a connection is established and cleanupConnection runs.
+// If a caller invokes CreateProxy but never connects to the returned URL,
+// those entries stay pinned for the lifetime of the page.
 func (p *RDCleanPathProxy) CreateProxy(hostname, port string) js.Value {
 	destination := net.JoinHostPort(hostname, port)
 
@@ -88,7 +102,7 @@ func (p *RDCleanPathProxy) CreateProxy(hostname, port string) js.Value {
 		resolve := args[0]
 
 		go func() {
-			proxyID := fmt.Sprintf("proxy_%d", len(p.activeConnections))
+			proxyID := fmt.Sprintf("proxy_%d", p.nextID.Add(1))
 
 			p.mu.Lock()
 			if p.destinations == nil {
@@ -100,7 +114,7 @@ func (p *RDCleanPathProxy) CreateProxy(hostname, port string) js.Value {
 			proxyURL := fmt.Sprintf("%s://%s/%s", RDCleanPathProxyScheme, RDCleanPathProxyHost, proxyID)
 
 			// Register the WebSocket handler for this specific proxy
-			js.Global().Set(fmt.Sprintf("handleRDCleanPathWebSocket_%s", proxyID), js.FuncOf(func(_ js.Value, args []js.Value) any {
+			handlerFn := js.FuncOf(func(_ js.Value, args []js.Value) any {
 				if len(args) < 1 {
 					return js.ValueOf("error: requires WebSocket argument")
 				}
@@ -108,7 +122,14 @@ func (p *RDCleanPathProxy) CreateProxy(hostname, port string) js.Value {
 				ws := args[0]
 				p.HandleWebSocketConnection(ws, proxyID)
 				return nil
-			}))
+			})
+			p.mu.Lock()
+			if p.pendingHandlers == nil {
+				p.pendingHandlers = make(map[string]js.Func)
+			}
+			p.pendingHandlers[proxyID] = handlerFn
+			p.mu.Unlock()
+			js.Global().Set(fmt.Sprintf("handleRDCleanPathWebSocket_%s", proxyID), handlerFn)
 
 			log.Infof("Created RDCleanPath proxy endpoint: %s for destination: %s", proxyURL, destination)
 			resolve.Invoke(proxyURL)
@@ -142,6 +163,10 @@ func (p *RDCleanPathProxy) HandleWebSocketConnection(ws js.Value, proxyID string
 
 	p.mu.Lock()
 	p.activeConnections[proxyID] = conn
+	if fn, ok := p.pendingHandlers[proxyID]; ok {
+		conn.wsHandlerFn = fn
+		delete(p.pendingHandlers, proxyID)
+	}
 	p.mu.Unlock()
 
 	p.setupWebSocketHandlers(ws, conn)
@@ -150,7 +175,7 @@ func (p *RDCleanPathProxy) HandleWebSocketConnection(ws js.Value, proxyID string
 }
 
 func (p *RDCleanPathProxy) setupWebSocketHandlers(ws js.Value, conn *proxyConnection) {
-	ws.Set("onGoMessage", js.FuncOf(func(this js.Value, args []js.Value) any {
+	conn.onMessageFn = js.FuncOf(func(this js.Value, args []js.Value) any {
 		if len(args) < 1 {
 			return nil
 		}
@@ -158,13 +183,15 @@ func (p *RDCleanPathProxy) setupWebSocketHandlers(ws js.Value, conn *proxyConnec
 		data := args[0]
 		go p.handleWebSocketMessage(conn, data)
 		return nil
-	}))
+	})
+	ws.Set("onGoMessage", conn.onMessageFn)
 
-	ws.Set("onGoClose", js.FuncOf(func(_ js.Value, args []js.Value) any {
+	conn.onCloseFn = js.FuncOf(func(_ js.Value, args []js.Value) any {
 		log.Debug("WebSocket closed by JavaScript")
 		conn.cancel()
 		return nil
-	}))
+	})
+	ws.Set("onGoClose", conn.onCloseFn)
 }
 
 func (p *RDCleanPathProxy) handleWebSocketMessage(conn *proxyConnection, data js.Value) {
@@ -261,25 +288,49 @@ func (p *RDCleanPathProxy) handleDirectRDP(conn *proxyConnection, firstPacket []
 }
 
 func (p *RDCleanPathProxy) cleanupConnection(conn *proxyConnection) {
-	log.Debugf("Cleaning up connection %s", conn.id)
-	conn.cancel()
-	if conn.tlsConn != nil {
-		log.Debug("Closing TLS connection")
-		if err := conn.tlsConn.Close(); err != nil {
-			log.Debugf("Error closing TLS connection: %v", err)
+	conn.cleanupOnce.Do(func() {
+		log.Debugf("Cleaning up connection %s", conn.id)
+		conn.cancel()
+		if conn.tlsConn != nil {
+			log.Debug("Closing TLS connection")
+			if err := conn.tlsConn.Close(); err != nil {
+				log.Debugf("Error closing TLS connection: %v", err)
+			}
+			conn.tlsConn = nil
 		}
-		conn.tlsConn = nil
-	}
-	if conn.rdpConn != nil {
-		log.Debug("Closing TCP connection")
-		if err := conn.rdpConn.Close(); err != nil {
-			log.Debugf("Error closing TCP connection: %v", err)
+		if conn.rdpConn != nil {
+			log.Debug("Closing TCP connection")
+			if err := conn.rdpConn.Close(); err != nil {
+				log.Debugf("Error closing TCP connection: %v", err)
+			}
+			conn.rdpConn = nil
 		}
-		conn.rdpConn = nil
-	}
-	p.mu.Lock()
-	delete(p.activeConnections, conn.id)
-	p.mu.Unlock()
+		js.Global().Delete(fmt.Sprintf("handleRDCleanPathWebSocket_%s", conn.id))
+
+		// Detach before releasing so late JS calls surface as TypeError instead
+		// of silent "call to released function".
+		if conn.wsHandlers.Truthy() {
+			conn.wsHandlers.Set("onGoMessage", js.Undefined())
+			conn.wsHandlers.Set("onGoClose", js.Undefined())
+		}
+
+		// wsHandlerFn may be zero-value if the pending handler lookup missed.
+		if conn.wsHandlerFn.Truthy() {
+			conn.wsHandlerFn.Release()
+		}
+		if conn.onMessageFn.Truthy() {
+			conn.onMessageFn.Release()
+		}
+		if conn.onCloseFn.Truthy() {
+			conn.onCloseFn.Release()
+		}
+
+		p.mu.Lock()
+		delete(p.activeConnections, conn.id)
+		delete(p.destinations, conn.id)
+		delete(p.pendingHandlers, conn.id)
+		p.mu.Unlock()
+	})
 }
 
 func (p *RDCleanPathProxy) sendToWebSocket(conn *proxyConnection, data []byte) {

client/wasm/internal/ssh/handlers.go

@@ -13,7 +13,7 @@ import (
 func CreateJSInterface(client *Client) js.Value {
 	jsInterface := js.Global().Get("Object").Call("create", js.Null())
 
-	jsInterface.Set("write", js.FuncOf(func(this js.Value, args []js.Value) any {
+	writeFunc := js.FuncOf(func(this js.Value, args []js.Value) any {
 		if len(args) < 1 {
 			return js.ValueOf(false)
 		}
@@ -32,9 +32,10 @@ func CreateJSInterface(client *Client) js.Value {
 
 		_, err := client.Write(bytes)
 		return js.ValueOf(err == nil)
-	}))
+	})
+	jsInterface.Set("write", writeFunc)
 
-	jsInterface.Set("resize", js.FuncOf(func(this js.Value, args []js.Value) any {
+	resizeFunc := js.FuncOf(func(this js.Value, args []js.Value) any {
 		if len(args) < 2 {
 			return js.ValueOf(false)
 		}
@@ -42,14 +43,26 @@ func CreateJSInterface(client *Client) js.Value {
 		rows := args[1].Int()
 		err := client.Resize(cols, rows)
 		return js.ValueOf(err == nil)
-	}))
+	})
+	jsInterface.Set("resize", resizeFunc)
 
-	jsInterface.Set("close", js.FuncOf(func(this js.Value, args []js.Value) any {
+	closeFunc := js.FuncOf(func(this js.Value, args []js.Value) any {
 		client.Close()
 		return js.Undefined()
-	}))
+	})
+	jsInterface.Set("close", closeFunc)
 
-	go readLoop(client, jsInterface)
+	go func() {
+		readLoop(client, jsInterface)
+		// Detach before releasing so late JS calls surface as TypeError instead
+		// of silent "call to released function".
+		jsInterface.Set("write", js.Undefined())
+		jsInterface.Set("resize", js.Undefined())
+		jsInterface.Set("close", js.Undefined())
+		writeFunc.Release()
+		resizeFunc.Release()
+		closeFunc.Release()
+	}()
 
 	return jsInterface
 }

combined/cmd/root.go

@@ -67,6 +67,10 @@ func init() {
 	rootCmd.AddCommand(newTokenCommands())
 }
 
+func RootCmd() *cobra.Command {
+	return rootCmd
+}
+
 func Execute() error {
 	return rootCmd.Execute()
 }
@@ -168,7 +172,7 @@ func initializeConfig() error {
 // serverInstances holds all server instances created during startup.
 type serverInstances struct {
 	relaySrv      *relayServer.Server
-	mgmtSrv       *mgmtServer.BaseServer
+	mgmtSrv       mgmtServer.Server
 	signalSrv     *signalServer.Server
 	healthcheck   *healthcheck.Server
 	stunServer    *stun.Server
@@ -324,19 +328,24 @@ func setupServerHooks(servers *serverInstances, cfg *CombinedConfig) {
 		return
 	}
 
-	servers.mgmtSrv.AfterInit(func(s *mgmtServer.BaseServer) {
-		grpcSrv := s.GRPCServer()
+	if s, ok := servers.mgmtSrv.GetContainer(mgmtServer.ContainerKeyBaseServer); ok {
+		if baseServer, ok := s.(*mgmtServer.BaseServer); ok {
+			baseServer.AfterInit(func(s *mgmtServer.BaseServer) {
+				grpcSrv := s.GRPCServer()
 
-		if servers.signalSrv != nil {
-			proto.RegisterSignalExchangeServer(grpcSrv, servers.signalSrv)
-			log.Infof("Signal server registered on port %s", cfg.Server.ListenAddress)
-		}
+				if servers.signalSrv != nil {
+					proto.RegisterSignalExchangeServer(grpcSrv, servers.signalSrv)
+					log.Infof("Signal server registered on port %s", cfg.Server.ListenAddress)
+				}
 
-		s.SetHandlerFunc(createCombinedHandler(grpcSrv, s.APIHandler(), servers.relaySrv, servers.metricsServer.Meter, cfg))
-		if servers.relaySrv != nil {
-			log.Infof("Relay WebSocket handler added (path: /relay)")
+				s.SetHandlerFunc(createCombinedHandler(grpcSrv, s.APIHandler(), s.IDPHandler(), servers.relaySrv, servers.metricsServer.Meter, cfg))
+				if servers.relaySrv != nil {
+					log.Infof("Relay WebSocket handler added (path: /relay)")
+				}
+			})
 		}
-	})
+	}
+
 }
 
 func startServers(wg *sync.WaitGroup, srv *relayServer.Server, httpHealthcheck *healthcheck.Server, stunServer *stun.Server, metricsServer *sharedMetrics.Metrics) {
@@ -346,38 +355,32 @@ func startServers(wg *sync.WaitGroup, srv *relayServer.Server, httpHealthcheck *
 		log.Infof("Relay WebSocket multiplexed on management port (no separate relay listener)")
 	}
 
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
+	wg.Go(func() {
 		log.Infof("running metrics server: %s%s", metricsServer.Addr, metricsServer.Endpoint)
 		if err := metricsServer.ListenAndServe(); !errors.Is(err, http.ErrServerClosed) {
 			log.Fatalf("failed to start metrics server: %v", err)
 		}
-	}()
+	})
 
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
+	wg.Go(func() {
 		if err := httpHealthcheck.ListenAndServe(); !errors.Is(err, http.ErrServerClosed) {
 			log.Fatalf("failed to start healthcheck server: %v", err)
 		}
-	}()
+	})
 
 	if stunServer != nil {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
+		wg.Go(func() {
 			if err := stunServer.Listen(); err != nil {
 				if errors.Is(err, stun.ErrServerClosed) {
 					return
 				}
 				log.Errorf("STUN server error: %v", err)
 			}
-		}()
+		})
 	}
 }
 
-func shutdownServers(ctx context.Context, srv *relayServer.Server, httpHealthcheck *healthcheck.Server, stunServer *stun.Server, mgmtSrv *mgmtServer.BaseServer, metricsServer *sharedMetrics.Metrics) error {
+func shutdownServers(ctx context.Context, srv *relayServer.Server, httpHealthcheck *healthcheck.Server, stunServer *stun.Server, mgmtSrv mgmtServer.Server, metricsServer *sharedMetrics.Metrics) error {
 	var errs error
 
 	if err := httpHealthcheck.Shutdown(ctx); err != nil {
@@ -491,7 +494,7 @@ func handleTLSConfig(cfg *CombinedConfig) (*tls.Config, bool, error) {
 	return nil, false, nil
 }
 
-func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (*mgmtServer.BaseServer, error) {
+func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (mgmtServer.Server, error) {
 	mgmt := cfg.Management
 
 	// Extract port from listen address
@@ -502,7 +505,7 @@ func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (*
 	}
 	mgmtPort, _ := strconv.Atoi(portStr)
 
-	mgmtSrv := mgmtServer.NewServer(
+	mgmtSrv := newServer(
 		&mgmtServer.Config{
 			NbConfig:                mgmtConfig,
 			DNSDomain:               "",
@@ -521,7 +524,7 @@ func createManagementServer(cfg *CombinedConfig, mgmtConfig *nbconfig.Config) (*
 }
 
 // createCombinedHandler creates an HTTP handler that multiplexes Management, Signal (via wsproxy), and Relay WebSocket traffic
-func createCombinedHandler(grpcServer *grpc.Server, httpHandler http.Handler, relaySrv *relayServer.Server, meter metric.Meter, cfg *CombinedConfig) http.Handler {
+func createCombinedHandler(grpcServer *grpc.Server, httpHandler http.Handler, idpHandler http.Handler, relaySrv *relayServer.Server, meter metric.Meter, cfg *CombinedConfig) http.Handler {
 	wsProxy := wsproxyserver.New(grpcServer, wsproxyserver.WithOTelMeter(meter))
 
 	var relayAcceptFn func(conn listener.Conn)
@@ -556,6 +559,10 @@ func createCombinedHandler(grpcServer *grpc.Server, httpHandler http.Handler, re
 				http.Error(w, "Relay service not enabled", http.StatusNotFound)
 			}
 
+		// Embedded IdP (Dex)
+		case idpHandler != nil && strings.HasPrefix(r.URL.Path, "/oauth2"):
+			idpHandler.ServeHTTP(w, r)
+
 		// Management HTTP API (default)
 		default:
 			httpHandler.ServeHTTP(w, r)

combined/cmd/server.go

@@ -0,0 +1,13 @@
+package cmd
+
+import (
+	mgmtServer "github.com/netbirdio/netbird/management/internals/server"
+)
+
+var newServer = func(cfg *mgmtServer.Config) mgmtServer.Server {
+	return mgmtServer.NewServer(cfg)
+}
+
+func SetNewServer(fn func(*mgmtServer.Config) mgmtServer.Server) {
+	newServer = fn
+}

go.mod

@@ -3,7 +3,7 @@ module github.com/netbirdio/netbird
 go 1.25.5
 
 require (
-	cunicu.li/go-rosenpass v0.4.0
+	cunicu.li/go-rosenpass v0.5.42
 	github.com/cenkalti/backoff/v4 v4.3.0
 	github.com/cloudflare/circl v1.3.3 // indirect
 	github.com/golang/protobuf v1.5.4
@@ -19,8 +19,8 @@ require (
 	github.com/vishvananda/netlink v1.3.1
 	golang.org/x/crypto v0.50.0
 	golang.org/x/sys v0.43.0
-	golang.zx2c4.com/wireguard v0.0.0-20230704135630-469159ecf7d1
-	golang.zx2c4.com/wireguard/wgctrl v0.0.0-20230429144221-925a1e7659e6
+	golang.zx2c4.com/wireguard v0.0.0-20231211153847-12269c276173
+	golang.zx2c4.com/wireguard/wgctrl v0.0.0-20241231184526-a9ab2273dd10
 	golang.zx2c4.com/wireguard/windows v0.5.3
 	google.golang.org/grpc v1.80.0
 	google.golang.org/protobuf v1.36.11
@@ -38,7 +38,7 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/s3 v1.87.3
 	github.com/c-robinson/iplib v1.0.3
 	github.com/caddyserver/certmagic v0.21.3
-	github.com/cilium/ebpf v0.15.0
+	github.com/cilium/ebpf v0.19.0
 	github.com/coder/websocket v1.8.14
 	github.com/coreos/go-iptables v0.7.0
 	github.com/coreos/go-oidc/v3 v3.18.0
@@ -60,7 +60,7 @@ require (
 	github.com/google/go-cmp v0.7.0
 	github.com/google/gopacket v1.1.19
 	github.com/google/nftables v0.3.0
-	github.com/gopacket/gopacket v1.1.1
+	github.com/gopacket/gopacket v1.4.0
 	github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.0.2-0.20240212192251-757544f21357
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/hashicorp/go-secure-stdlib/base62 v0.1.2
@@ -335,7 +335,7 @@ replace github.com/kardianos/service => github.com/netbirdio/service v0.0.0-2024
 
 replace github.com/getlantern/systray => github.com/netbirdio/systray v0.0.0-20231030152038-ef1ed2a27949
 
-replace golang.zx2c4.com/wireguard => github.com/netbirdio/wireguard-go v0.0.0-20260107100953-33b7c9d03db0
+replace golang.zx2c4.com/wireguard => github.com/netbirdio/wireguard-go v0.0.0-20260523085312-4b4a4e36017f
 
 replace github.com/cloudflare/circl => codeberg.org/cunicu/circl v0.0.0-20230801113412-fec58fc7b5f6
 

go.sum

@@ -7,8 +7,8 @@ cloud.google.com/go/compute/metadata v0.9.0 h1:pDUj4QMoPejqq20dK0Pg2N4yG9zIkYGdB
 cloud.google.com/go/compute/metadata v0.9.0/go.mod h1:E0bWwX5wTnLPedCKqk3pJmVgCBSM6qQI1yTBdEb3C10=
 codeberg.org/cunicu/circl v0.0.0-20230801113412-fec58fc7b5f6 h1:b8xUw3004wk+3ipBhu0VU4RtUJsegMIiqjxSK4++lzA=
 codeberg.org/cunicu/circl v0.0.0-20230801113412-fec58fc7b5f6/go.mod h1:+CauBF6R70Jqcyl8N2hC8pAXYbWkGIezuSbuGLtRhnw=
-cunicu.li/go-rosenpass v0.4.0 h1:LtPtBgFWY/9emfgC4glKLEqS0MJTylzV6+ChRhiZERw=
-cunicu.li/go-rosenpass v0.4.0/go.mod h1:MPbjH9nxV4l3vEagKVdFNwHOketqgS5/To1VYJplf/M=
+cunicu.li/go-rosenpass v0.5.42 h1:fRDsGwCxd7DhDgZI1Pxeo8GtNyq8BESZJ7w2/BGGJtU=
+cunicu.li/go-rosenpass v0.5.42/go.mod h1:YRBeyKOe/gWpSX2kpDUec5p9t0XOLsshTguId5gTGVg=
 dario.cat/mergo v1.0.1 h1:Ra4+bf83h2ztPIQYNP99R6m+Y7KfnARDfID+a+vLl4s=
 dario.cat/mergo v1.0.1/go.mod h1:uNxQE+84aUszobStD9th8a29P2fMDhsBdgRYvZOxGmk=
 filippo.io/edwards25519 v1.1.1 h1:YpjwWWlNmGIDyXOn8zLzqiD+9TyIlPhGFG96P39uBpw=
@@ -111,8 +111,8 @@ github.com/cenkalti/backoff/v5 v5.0.3 h1:ZN+IMa753KfX5hd8vVaMixjnqRZ3y8CuJKRKj1x
 github.com/cenkalti/backoff/v5 v5.0.3/go.mod h1:rkhZdG3JZukswDf7f0cwqPNk4K0sa+F97BxZthm/crw=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/cilium/ebpf v0.15.0 h1:7NxJhNiBT3NG8pZJ3c+yfrVdHY8ScgKD27sScgjLMMk=
-github.com/cilium/ebpf v0.15.0/go.mod h1:DHp1WyrLeiBh19Cf/tfiSMhqheEiK8fXFZ4No0P1Hso=
+github.com/cilium/ebpf v0.19.0 h1:Ro/rE64RmFBeA9FGjcTc+KmCeY6jXmryu6FfnzPRIao=
+github.com/cilium/ebpf v0.19.0/go.mod h1:fLCgMo3l8tZmAdM3B2XqdFzXBpwkcSTroaVqN08OWVY=
 github.com/coder/websocket v1.8.14 h1:9L0p0iKiNOibykf283eHkKUHHrpG7f65OE3BhhO7v9g=
 github.com/coder/websocket v1.8.14/go.mod h1:NX3SzP+inril6yawo5CQXx8+fk145lPDC6pumgx0mVg=
 github.com/containerd/log v0.1.0 h1:TCJt7ioM2cr/tfR8GPbGf9/VRAX8D2B4PjzCpfX540I=
@@ -225,8 +225,8 @@ github.com/go-openapi/validate v0.24.0 h1:LdfDKwNbpB6Vn40xhTdNZAnfLECL81w+VX3Bum
 github.com/go-openapi/validate v0.24.0/go.mod h1:iyeX1sEufmv3nPbBdX3ieNviWnOZaJ1+zquzJEf2BAQ=
 github.com/go-playground/locales v0.12.1/go.mod h1:IUMDtCfWo/w/mtMfIE/IG2K+Ey3ygWanZIBtBW0W2TM=
 github.com/go-playground/universal-translator v0.16.0/go.mod h1:1AnU7NaIRDWWzGEKwgtJRd2xk99HeFyHw3yid4rvQIY=
-github.com/go-quicktest/qt v1.101.0 h1:O1K29Txy5P2OK0dGo59b7b0LR6wKfIhttaAhHUyn7eI=
-github.com/go-quicktest/qt v1.101.0/go.mod h1:14Bz/f7NwaXPtdYEgzsx46kqSxVwTbzVZsDC26tQJow=
+github.com/go-quicktest/qt v1.101.1-0.20240301121107-c6c8733fa1e6 h1:teYtXy9B7y5lHTp8V9KPxpYRAVA7dozigQcMiBust1s=
+github.com/go-quicktest/qt v1.101.1-0.20240301121107-c6c8733fa1e6/go.mod h1:p4lGIVX+8Wa6ZPNDvqcxq36XpUDLh42FLetFU7odllI=
 github.com/go-sql-driver/mysql v1.7.0/go.mod h1:OXbVy3sEdcQ2Doequ6Z5BW6fXNQTmx+9S1MCJN5yJMI=
 github.com/go-sql-driver/mysql v1.9.3 h1:U/N249h2WzJ3Ukj8SowVFjdtZKfu9vlLZxjPXV1aweo=
 github.com/go-sql-driver/mysql v1.9.3/go.mod h1:qn46aNg1333BRMNU69Lq93t8du/dwxI64Gl8i5p1WMU=
@@ -307,8 +307,8 @@ github.com/googleapis/enterprise-certificate-proxy v0.3.14 h1:yh8ncqsbUY4shRD5dA
 github.com/googleapis/enterprise-certificate-proxy v0.3.14/go.mod h1:vqVt9yG9480NtzREnTlmGSBmFrA+bzb0yl0TxoBQXOg=
 github.com/googleapis/gax-go/v2 v2.21.0 h1:h45NjjzEO3faG9Lg/cFrBh2PgegVVgzqKzuZl/wMbiI=
 github.com/googleapis/gax-go/v2 v2.21.0/go.mod h1:But/NJU6TnZsrLai/xBAQLLz+Hc7fHZJt/hsCz3Fih4=
-github.com/gopacket/gopacket v1.1.1 h1:zbx9F9d6A7sWNkFKrvMBZTfGgxFoY4NgUudFVVHMfcw=
-github.com/gopacket/gopacket v1.1.1/go.mod h1:HavMeONEl7W9036of9LbSWoonqhH7HA1+ZRO+rMIvFs=
+github.com/gopacket/gopacket v1.4.0 h1:cr1OlFpzksCkZHNO0eLjaSSOrMQnpPXg0j6qHIY3y2U=
+github.com/gopacket/gopacket v1.4.0/go.mod h1:EpvsxINeehp5qj4YMKMLf2/dekdhKn2IIAO/ZOifS7o=
 github.com/gorilla/handlers v1.5.2 h1:cLTUSsNkgcwhgRqvCNmdbRWG0A3N4F+M2nWKdScwyEE=
 github.com/gorilla/handlers v1.5.2/go.mod h1:dX+xVpaxdSw+q0Qek8SSsl3dfMk3jNddUkMzo0GtH0w=
 github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
@@ -390,6 +390,8 @@ github.com/jonboulle/clockwork v0.5.0 h1:Hyh9A8u51kptdkR+cqRpT1EebBwTn1oK9YfGYbd
 github.com/jonboulle/clockwork v0.5.0/go.mod h1:3mZlmanh0g2NDKO5TWZVJAfofYk64M7XN3SzBPjZF60=
 github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
+github.com/jsimonetti/rtnetlink/v2 v2.0.1 h1:xda7qaHDSVOsADNouv7ukSuicKZO7GgVUCXxpaIEIlM=
+github.com/jsimonetti/rtnetlink/v2 v2.0.1/go.mod h1:7MoNYNbb3UaDHtF8udiJo/RH6VsTKP1pqKLUTVCvToE=
 github.com/json-iterator/go v1.1.7/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/jsummers/gobmp v0.0.0-20230614200233-a9de23ed2e25 h1:YLvr1eE6cdCqjOe972w/cYF+FjW34v27+9Vo5106B4M=
 github.com/jsummers/gobmp v0.0.0-20230614200233-a9de23ed2e25/go.mod h1:kLgvv7o6UM+0QSf0QjAse3wReFDsb9qbZJdfexWlrQw=
@@ -499,8 +501,8 @@ github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502 h1:3tHlFmhTdX9ax
 github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502/go.mod h1:CIMRFEJVL+0DS1a3Nx06NaMn4Dz63Ng6O7dl0qH0zVM=
 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45 h1:ujgviVYmx243Ksy7NdSwrdGPSRNE3pb8kEDSpH0QuAQ=
 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45/go.mod h1:5/sjFmLb8O96B5737VCqhHyGRzNFIaN/Bu7ZodXc3qQ=
-github.com/netbirdio/wireguard-go v0.0.0-20260107100953-33b7c9d03db0 h1:h/QnNzm7xzHPm+gajcblYUOclrW2FeNeDlUNj6tTWKQ=
-github.com/netbirdio/wireguard-go v0.0.0-20260107100953-33b7c9d03db0/go.mod h1:rpwXGsirqLqN2L0JDJQlwOboGHmptD5ZD6T2VmcqhTw=
+github.com/netbirdio/wireguard-go v0.0.0-20260523085312-4b4a4e36017f h1:ff2D57RBjWtyQ2wVwJOxOgXAXOe/J2lJWtSX0Bz/BRk=
+github.com/netbirdio/wireguard-go v0.0.0-20260523085312-4b4a4e36017f/go.mod h1:rpwXGsirqLqN2L0JDJQlwOboGHmptD5ZD6T2VmcqhTw=
 github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=
 github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646/go.mod h1:jpp1/29i3P1S/RLdc7JQKbRpFeM1dOBd8T9ki5s+AY8=
 github.com/nicksnyder/go-i18n/v2 v2.5.1 h1:IxtPxYsR9Gp60cGXjfuR/llTqV8aYMsC472zD0D1vHk=
@@ -900,8 +902,8 @@ golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 h1:B82qJJgjvYKsXS9jeunTOisW56dUokqW/FOteYJJ/yg=
 golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2/go.mod h1:deeaetjYA+DHMHg+sMSMI58GrEteJUUzzw7en6TJQcI=
-golang.zx2c4.com/wireguard/wgctrl v0.0.0-20230429144221-925a1e7659e6 h1:CawjfCvYQH2OU3/TnxLx97WDSUDRABfT18pCOYwc2GE=
-golang.zx2c4.com/wireguard/wgctrl v0.0.0-20230429144221-925a1e7659e6/go.mod h1:3rxYc4HtVcSG9gVaTs2GEBdehh+sYPOwKtyUWEOTb80=
+golang.zx2c4.com/wireguard/wgctrl v0.0.0-20241231184526-a9ab2273dd10 h1:3GDAcqdIg1ozBNLgPy4SLT84nfcBjr6rhGtXYtrkWLU=
+golang.zx2c4.com/wireguard/wgctrl v0.0.0-20241231184526-a9ab2273dd10/go.mod h1:T97yPqesLiNrOYxkwmhMI0ZIlJDm+p0PMR8eRVeR5tQ=
 golang.zx2c4.com/wireguard/windows v0.5.3 h1:On6j2Rpn3OEMXqBq00QEDC7bWSZrPIHKIus8eIuExIE=
 golang.zx2c4.com/wireguard/windows v0.5.3/go.mod h1:9TEe8TJmtwyQebdFwAkEWOPr3prrtqm+REGFifP60hI=
 gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=

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

@@ -112,7 +112,7 @@ func (c *Controller) CountStreams() int {
 	return c.peersUpdateManager.CountStreams()
 }
 
-func (c *Controller) sendUpdateAccountPeers(ctx context.Context, accountID string) error {
+func (c *Controller) sendUpdateAccountPeers(ctx context.Context, accountID string, reason types.UpdateReason) error {
 	log.WithContext(ctx).Tracef("updating peers for account %s from %s", accountID, util.GetCallerName())
 	account, err := c.requestBuffer.GetAccountWithBackpressure(ctx, accountID)
 	if err != nil {
@@ -175,6 +175,10 @@ func (c *Controller) sendUpdateAccountPeers(ctx context.Context, accountID strin
 			continue
 		}
 
+		if c.accountManagerMetrics != nil {
+			c.accountManagerMetrics.CountNmapTriggered(string(reason.Resource), string(reason.Operation))
+		}
+
 		wg.Add(1)
 		semaphore <- struct{}{}
 		go func(p *nbpeer.Peer) {
@@ -242,14 +246,14 @@ func (c *Controller) bufferSendUpdateAccountPeers(ctx context.Context, accountID
 
 	go func() {
 		defer b.mu.Unlock()
-		_ = c.sendUpdateAccountPeers(ctx, accountID)
+		_ = c.sendUpdateAccountPeers(ctx, accountID, reason)
 		if !b.update.Load() {
 			return
 		}
 		b.update.Store(false)
 		if b.next == nil {
 			b.next = time.AfterFunc(time.Duration(c.updateAccountPeersBufferInterval.Load()), func() {
-				_ = c.sendUpdateAccountPeers(ctx, accountID)
+				_ = c.sendUpdateAccountPeers(ctx, accountID, reason)
 			})
 			return
 		}
@@ -265,7 +269,7 @@ func (c *Controller) UpdateAccountPeers(ctx context.Context, accountID string, r
 	if c.accountManagerMetrics != nil {
 		c.accountManagerMetrics.CountUpdateAccountPeersTriggered(string(reason.Resource), string(reason.Operation))
 	}
-	return c.sendUpdateAccountPeers(ctx, accountID)
+	return c.sendUpdateAccountPeers(ctx, accountID, reason)
 }
 
 func (c *Controller) UpdateAccountPeer(ctx context.Context, accountId string, peerId string) error {
@@ -359,14 +363,14 @@ func (c *Controller) BufferUpdateAccountPeers(ctx context.Context, accountID str
 
 	go func() {
 		defer b.mu.Unlock()
-		_ = c.sendUpdateAccountPeers(ctx, accountID)
+		_ = c.sendUpdateAccountPeers(ctx, accountID, reason)
 		if !b.update.Load() {
 			return
 		}
 		b.update.Store(false)
 		if b.next == nil {
 			b.next = time.AfterFunc(time.Duration(c.updateAccountPeersBufferInterval.Load()), func() {
-				_ = c.sendUpdateAccountPeers(ctx, accountID)
+				_ = c.sendUpdateAccountPeers(ctx, accountID, reason)
 			})
 			return
 		}

management/internals/controllers/network_map/update_channel/updatechannel.go

@@ -51,7 +51,7 @@ func (p *PeersUpdateManager) SendUpdate(ctx context.Context, peerID string, upda
 		found = true
 		select {
 		case channel <- update:
-			log.WithContext(ctx).Debugf("update was sent to channel for peer %s", peerID)
+			log.WithContext(ctx).Tracef("update was sent to channel for peer %s", peerID)
 		default:
 			dropped = true
 			log.WithContext(ctx).Warnf("channel for peer %s is %d full or closed", peerID, len(channel))

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

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

management/internals/modules/peers/manager.go

@@ -5,6 +5,7 @@ package peers
 import (
 	"context"
 	"fmt"
+	"net"
 	"time"
 
 	"github.com/rs/xid"
@@ -35,6 +36,14 @@ type Manager interface {
 	SetAccountManager(accountManager account.Manager)
 	GetPeerID(ctx context.Context, peerKey string) (string, error)
 	CreateProxyPeer(ctx context.Context, accountID string, peerKey string, cluster string) error
+	// GetPeerByTunnelIP looks up a peer in accountID by its WireGuard tunnel IP.
+	// Returns nil with an error when no match exists. No permission check;
+	// callers (the proxy's ValidateTunnelPeer RPC) are trusted server components.
+	GetPeerByTunnelIP(ctx context.Context, accountID string, ip net.IP) (*peer.Peer, error)
+	// GetPeerWithGroups returns the peer and the list of *types.Group it belongs
+	// to. Used by the proxy's auth path to authorise a request by the calling
+	// peer's group memberships.
+	GetPeerWithGroups(ctx context.Context, accountID, peerID string) (*peer.Peer, []*types.Group, error)
 }
 
 type managerImpl struct {
@@ -66,7 +75,7 @@ func (m *managerImpl) SetAccountManager(accountManager account.Manager) {
 }
 
 func (m *managerImpl) GetPeer(ctx context.Context, accountID, userID, peerID string) (*peer.Peer, error) {
-	allowed, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Peers, operations.Read)
+	allowed, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Peers, operations.Read)
 	if err != nil {
 		return nil, fmt.Errorf("failed to validate user permissions: %w", err)
 	}
@@ -79,7 +88,7 @@ func (m *managerImpl) GetPeer(ctx context.Context, accountID, userID, peerID str
 }
 
 func (m *managerImpl) GetAllPeers(ctx context.Context, accountID, userID string) ([]*peer.Peer, error) {
-	allowed, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Peers, operations.Read)
+	allowed, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Peers, operations.Read)
 	if err != nil {
 		return nil, fmt.Errorf("failed to validate user permissions: %w", err)
 	}
@@ -99,6 +108,26 @@ func (m *managerImpl) GetPeersByGroupIDs(ctx context.Context, accountID string,
 	return m.store.GetPeersByGroupIDs(ctx, accountID, groupsIDs)
 }
 
+// GetPeerByTunnelIP delegates to the store's indexed lookup.
+func (m *managerImpl) GetPeerByTunnelIP(ctx context.Context, accountID string, ip net.IP) (*peer.Peer, error) {
+	return m.store.GetPeerByIP(ctx, store.LockingStrengthNone, accountID, ip)
+}
+
+// GetPeerWithGroups returns the peer plus its group memberships. Any store
+// error returns (nil, nil, err) so callers never receive a valid peer
+// alongside a non-nil error.
+func (m *managerImpl) GetPeerWithGroups(ctx context.Context, accountID, peerID string) (*peer.Peer, []*types.Group, error) {
+	p, err := m.store.GetPeerByID(ctx, store.LockingStrengthNone, accountID, peerID)
+	if err != nil {
+		return nil, nil, err
+	}
+	groups, err := m.store.GetPeerGroups(ctx, store.LockingStrengthNone, accountID, peerID)
+	if err != nil {
+		return nil, nil, err
+	}
+	return p, groups, nil
+}
+
 func (m *managerImpl) DeletePeers(ctx context.Context, accountID string, peerIDs []string, userID string, checkConnected bool) error {
 	settings, err := m.store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
 	if err != nil {

management/internals/modules/peers/manager_mock.go

@@ -6,6 +6,7 @@ package peers
 
 import (
 	context "context"
+	net "net"
 	reflect "reflect"
 
 	gomock "github.com/golang/mock/gomock"
@@ -13,6 +14,7 @@ import (
 	account "github.com/netbirdio/netbird/management/server/account"
 	integrated_validator "github.com/netbirdio/netbird/management/server/integrations/integrated_validator"
 	peer "github.com/netbirdio/netbird/management/server/peer"
+	types "github.com/netbirdio/netbird/management/server/types"
 )
 
 // MockManager is a mock of Manager interface.
@@ -38,6 +40,20 @@ func (m *MockManager) EXPECT() *MockManagerMockRecorder {
 	return m.recorder
 }
 
+// CreateProxyPeer mocks base method.
+func (m *MockManager) CreateProxyPeer(ctx context.Context, accountID, peerKey, cluster string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "CreateProxyPeer", ctx, accountID, peerKey, cluster)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// CreateProxyPeer indicates an expected call of CreateProxyPeer.
+func (mr *MockManagerMockRecorder) CreateProxyPeer(ctx, accountID, peerKey, cluster interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateProxyPeer", reflect.TypeOf((*MockManager)(nil).CreateProxyPeer), ctx, accountID, peerKey, cluster)
+}
+
 // DeletePeers mocks base method.
 func (m *MockManager) DeletePeers(ctx context.Context, accountID string, peerIDs []string, userID string, checkConnected bool) error {
 	m.ctrl.T.Helper()
@@ -97,6 +113,21 @@ func (mr *MockManagerMockRecorder) GetPeerAccountID(ctx, peerID interface{}) *go
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerAccountID", reflect.TypeOf((*MockManager)(nil).GetPeerAccountID), ctx, peerID)
 }
 
+// GetPeerByTunnelIP mocks base method.
+func (m *MockManager) GetPeerByTunnelIP(ctx context.Context, accountID string, ip net.IP) (*peer.Peer, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetPeerByTunnelIP", ctx, accountID, ip)
+	ret0, _ := ret[0].(*peer.Peer)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetPeerByTunnelIP indicates an expected call of GetPeerByTunnelIP.
+func (mr *MockManagerMockRecorder) GetPeerByTunnelIP(ctx, accountID, ip interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerByTunnelIP", reflect.TypeOf((*MockManager)(nil).GetPeerByTunnelIP), ctx, accountID, ip)
+}
+
 // GetPeerID mocks base method.
 func (m *MockManager) GetPeerID(ctx context.Context, peerKey string) (string, error) {
 	m.ctrl.T.Helper()
@@ -112,6 +143,22 @@ func (mr *MockManagerMockRecorder) GetPeerID(ctx, peerKey interface{}) *gomock.C
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerID", reflect.TypeOf((*MockManager)(nil).GetPeerID), ctx, peerKey)
 }
 
+// GetPeerWithGroups mocks base method.
+func (m *MockManager) GetPeerWithGroups(ctx context.Context, accountID, peerID string) (*peer.Peer, []*types.Group, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetPeerWithGroups", ctx, accountID, peerID)
+	ret0, _ := ret[0].(*peer.Peer)
+	ret1, _ := ret[1].([]*types.Group)
+	ret2, _ := ret[2].(error)
+	return ret0, ret1, ret2
+}
+
+// GetPeerWithGroups indicates an expected call of GetPeerWithGroups.
+func (mr *MockManagerMockRecorder) GetPeerWithGroups(ctx, accountID, peerID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerWithGroups", reflect.TypeOf((*MockManager)(nil).GetPeerWithGroups), ctx, accountID, peerID)
+}
+
 // GetPeersByGroupIDs mocks base method.
 func (m *MockManager) GetPeersByGroupIDs(ctx context.Context, accountID string, groupsIDs []string) ([]*peer.Peer, error) {
 	m.ctrl.T.Helper()
@@ -162,17 +209,3 @@ func (mr *MockManagerMockRecorder) SetNetworkMapController(networkMapController
 	mr.mock.ctrl.T.Helper()
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SetNetworkMapController", reflect.TypeOf((*MockManager)(nil).SetNetworkMapController), networkMapController)
 }
-
-// CreateProxyPeer mocks base method.
-func (m *MockManager) CreateProxyPeer(ctx context.Context, accountID string, peerKey string, cluster string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "CreateProxyPeer", ctx, accountID, peerKey, cluster)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// CreateProxyPeer indicates an expected call of CreateProxyPeer.
-func (mr *MockManagerMockRecorder) CreateProxyPeer(ctx, accountID, peerKey, cluster interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateProxyPeer", reflect.TypeOf((*MockManager)(nil).CreateProxyPeer), ctx, accountID, peerKey, cluster)
-}

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

@@ -63,7 +63,7 @@ func (m *managerImpl) SaveAccessLog(ctx context.Context, logEntry *accesslogs.Ac
 
 // GetAllAccessLogs retrieves access logs for an account with pagination and filtering
 func (m *managerImpl) GetAllAccessLogs(ctx context.Context, accountID, userID string, filter *accesslogs.AccessLogFilter) ([]*accesslogs.AccessLogEntry, int64, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, 0, status.NewPermissionValidationError(err)
 	}

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

@@ -23,6 +23,8 @@ type Domain struct {
 	// SupportsCrowdSec is populated at query time from proxy cluster capabilities.
 	// Not persisted.
 	SupportsCrowdSec *bool `gorm:"-"`
+	// SupportsPrivate is populated at query time from proxy cluster capabilities. Not persisted.
+	SupportsPrivate *bool `gorm:"-"`
 }
 
 // EventMeta returns activity event metadata for a domain

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

@@ -49,6 +49,7 @@ func domainToApi(d *domain.Domain) api.ReverseProxyDomain {
 		SupportsCustomPorts: d.SupportsCustomPorts,
 		RequireSubdomain:    d.RequireSubdomain,
 		SupportsCrowdsec:    d.SupportsCrowdSec,
+		SupportsPrivate:     d.SupportsPrivate,
 	}
 	if d.TargetCluster != "" {
 		resp.TargetCluster = &d.TargetCluster

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

@@ -35,6 +35,7 @@ type proxyManager interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 }
 
 type Manager struct {
@@ -56,7 +57,7 @@ func NewManager(store store, proxyMgr proxyManager, permissionsManager permissio
 }
 
 func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*domain.Domain, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -93,6 +94,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 		d.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, cluster)
 		d.RequireSubdomain = m.proxyManager.ClusterRequireSubdomain(ctx, cluster)
 		d.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, cluster)
+		d.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, cluster)
 		ret = append(ret, d)
 	}
 
@@ -109,6 +111,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 		if d.TargetCluster != "" {
 			cd.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, d.TargetCluster)
 			cd.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, d.TargetCluster)
+			cd.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, d.TargetCluster)
 		}
 		// Custom domains never require a subdomain by default since
 		// the account owns them and should be able to use the bare domain.
@@ -119,7 +122,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 }
 
 func (m Manager) CreateDomain(ctx context.Context, accountID, userID, domainName, targetCluster string) (*domain.Domain, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Create)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Create)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -160,7 +163,7 @@ func (m Manager) CreateDomain(ctx context.Context, accountID, userID, domainName
 }
 
 func (m Manager) DeleteDomain(ctx context.Context, accountID, userID, domainID string) error {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
 	if err != nil {
 		return status.NewPermissionValidationError(err)
 	}
@@ -184,7 +187,7 @@ func (m Manager) DeleteDomain(ctx context.Context, accountID, userID, domainID s
 }
 
 func (m Manager) ValidateDomain(ctx context.Context, accountID, userID, domainID string) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Create)
+	ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Create)
 	if err != nil {
 		log.WithFields(log.Fields{
 			"accountID": accountID,

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

@@ -10,7 +10,7 @@ import (
 )
 
 type mockProxyManager struct {
-	getActiveClusterAddressesFunc          func(ctx context.Context) ([]string, error)
+	getActiveClusterAddressesFunc           func(ctx context.Context) ([]string, error)
 	getActiveClusterAddressesForAccountFunc func(ctx context.Context, accountID string) ([]string, error)
 }
 
@@ -40,6 +40,10 @@ func (m *mockProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
 	return nil
 }
 
+func (m *mockProxyManager) ClusterSupportsPrivate(_ context.Context, _ string) *bool {
+	return nil
+}
+
 func TestGetClusterAllowList_BYOPMergedWithPublic(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, accID string) ([]string, error) {
@@ -151,4 +155,3 @@ func TestGetClusterAllowList_PublicEmpty_BYOPOnly(t *testing.T) {
 	require.NoError(t, err)
 	assert.Equal(t, []string{"byop.example.com"}, result)
 }
-

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

@@ -19,6 +19,7 @@ type Manager interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 	CleanupStale(ctx context.Context, inactivityDuration time.Duration) error
 	GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error)
 	CountAccountProxies(ctx context.Context, accountID string) (int64, error)

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

@@ -17,10 +17,11 @@ type store interface {
 	UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error
 	GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error)
 	GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error)
-	GetActiveProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
+	GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
 	GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 	CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error
 	GetProxyByAccountID(ctx context.Context, accountID string) (*proxy.Proxy, error)
 	CountProxiesByAccountID(ctx context.Context, accountID string) (int64, error)
@@ -137,6 +138,11 @@ func (m Manager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string
 	return m.store.GetClusterSupportsCrowdSec(ctx, clusterAddr)
 }
 
+// ClusterSupportsPrivate reports whether any active proxy claims the private capability (nil = unreported).
+func (m Manager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
+	return m.store.GetClusterSupportsPrivate(ctx, clusterAddr)
+}
+
 // CleanupStale removes proxies that haven't sent heartbeat in the specified duration
 func (m *Manager) CleanupStale(ctx context.Context, inactivityDuration time.Duration) error {
 	if err := m.store.CleanupStaleProxies(ctx, inactivityDuration); err != nil {
@@ -178,4 +184,3 @@ func (m *Manager) DeleteAccountCluster(ctx context.Context, clusterAddress, acco
 	}
 	return nil
 }
-

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

@@ -15,16 +15,16 @@ import (
 )
 
 type mockStore struct {
-	saveProxyFunc                              func(ctx context.Context, p *proxy.Proxy) error
-	disconnectProxyFunc                        func(ctx context.Context, proxyID, sessionID string) error
-	updateProxyHeartbeatFunc                   func(ctx context.Context, p *proxy.Proxy) error
-	getActiveProxyClusterAddressesFunc         func(ctx context.Context) ([]string, error)
-	getActiveProxyClusterAddressesForAccFunc   func(ctx context.Context, accountID string) ([]string, error)
-	cleanupStaleProxiesFunc                    func(ctx context.Context, d time.Duration) error
-	getProxyByAccountIDFunc                    func(ctx context.Context, accountID string) (*proxy.Proxy, error)
-	countProxiesByAccountIDFunc                func(ctx context.Context, accountID string) (int64, error)
-	isClusterAddressConflictingFunc            func(ctx context.Context, clusterAddress, accountID string) (bool, error)
-	deleteAccountClusterFunc                   func(ctx context.Context, clusterAddress, accountID string) error
+	saveProxyFunc                            func(ctx context.Context, p *proxy.Proxy) error
+	disconnectProxyFunc                      func(ctx context.Context, proxyID, sessionID string) error
+	updateProxyHeartbeatFunc                 func(ctx context.Context, p *proxy.Proxy) error
+	getActiveProxyClusterAddressesFunc       func(ctx context.Context) ([]string, error)
+	getActiveProxyClusterAddressesForAccFunc func(ctx context.Context, accountID string) ([]string, error)
+	cleanupStaleProxiesFunc                  func(ctx context.Context, d time.Duration) error
+	getProxyByAccountIDFunc                  func(ctx context.Context, accountID string) (*proxy.Proxy, error)
+	countProxiesByAccountIDFunc              func(ctx context.Context, accountID string) (int64, error)
+	isClusterAddressConflictingFunc          func(ctx context.Context, clusterAddress, accountID string) (bool, error)
+	deleteAccountClusterFunc                 func(ctx context.Context, clusterAddress, accountID string) error
 }
 
 func (m *mockStore) SaveProxy(ctx context.Context, p *proxy.Proxy) error {
@@ -57,7 +57,7 @@ func (m *mockStore) GetActiveProxyClusterAddressesForAccount(ctx context.Context
 	}
 	return nil, nil
 }
-func (m *mockStore) GetActiveProxyClusters(_ context.Context, _ string) ([]proxy.Cluster, error) {
+func (m *mockStore) GetProxyClusters(_ context.Context, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 func (m *mockStore) CleanupStaleProxies(ctx context.Context, d time.Duration) error {
@@ -99,6 +99,9 @@ func (m *mockStore) GetClusterRequireSubdomain(_ context.Context, _ string) *boo
 func (m *mockStore) GetClusterSupportsCrowdSec(_ context.Context, _ string) *bool {
 	return nil
 }
+func (m *mockStore) GetClusterSupportsPrivate(_ context.Context, _ string) *bool {
+	return nil
+}
 
 func newTestManager(s store) *Manager {
 	meter := noop.NewMeterProvider().Meter("test")

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

@@ -92,6 +92,20 @@ func (mr *MockManagerMockRecorder) ClusterSupportsCrowdSec(ctx, clusterAddr inte
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCrowdSec", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCrowdSec), ctx, clusterAddr)
 }
 
+// ClusterSupportsPrivate mocks base method.
+func (m *MockManager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "ClusterSupportsPrivate", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// ClusterSupportsPrivate indicates an expected call of ClusterSupportsPrivate.
+func (mr *MockManagerMockRecorder) ClusterSupportsPrivate(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsPrivate", reflect.TypeOf((*MockManager)(nil).ClusterSupportsPrivate), ctx, clusterAddr)
+}
+
 // Connect mocks base method.
 func (m *MockManager) Connect(ctx context.Context, proxyID, sessionID, clusterAddress, ipAddress string, accountID *string, capabilities *Capabilities) (*Proxy, error) {
 	m.ctrl.T.Helper()

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

@@ -20,6 +20,9 @@ type Capabilities struct {
 	RequireSubdomain *bool
 	// SupportsCrowdsec indicates whether this proxy has CrowdSec configured.
 	SupportsCrowdsec *bool
+	// Private indicates whether this proxy supports inbound access via Wireguard
+	// tunnel and netbird-only authentication policies
+	Private *bool
 }
 
 // Proxy represents a reverse proxy instance
@@ -42,10 +45,34 @@ func (Proxy) TableName() string {
 	return "proxies"
 }
 
+// ClusterType is the source of a proxy cluster.
+type ClusterType string
+
+const (
+	// ClusterTypeAccount is a cluster operated by the account itself (BYOP) —
+	// at least one proxy row in the cluster carries a non-NULL account_id.
+	ClusterTypeAccount ClusterType = "account"
+	// ClusterTypeShared is a cluster operated by NetBird and shared across
+	// accounts — all proxy rows in the cluster have account_id IS NULL.
+	ClusterTypeShared ClusterType = "shared"
+)
+
 // Cluster represents a group of proxy nodes serving the same address.
+//
+// Online and ConnectedProxies derive from the same 2-min active window
+// the rest of the module uses, but Cluster rows are not gated on it —
+// the cluster listing surfaces offline clusters too so operators can
+// see and clean them up. The 1-hour heartbeat reaper still bounds the
+// table eventually.
 type Cluster struct {
 	ID               string
 	Address          string
+	Type             ClusterType
+	Online           bool
 	ConnectedProxies int
-	SelfHosted       bool
+	// *bool: nil = no proxy reported the capability; the dashboard renders that as unknown.
+	SupportsCustomPorts *bool
+	RequireSubdomain    *bool
+	SupportsCrowdSec    *bool
+	Private             *bool
 }

management/internals/modules/reverseproxy/proxytoken/handler.go

@@ -37,7 +37,7 @@ func (h *handler) createToken(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	ok, err := h.permissionsManager.ValidateUserPermissions(r.Context(), userAuth.AccountId, userAuth.UserId, modules.Services, operations.Create)
+	ok, ctx, err := h.permissionsManager.ValidateUserPermissions(r.Context(), userAuth.AccountId, userAuth.UserId, modules.Services, operations.Create)
 	if err != nil {
 		util.WriteErrorResponse("failed to validate permissions", http.StatusInternalServerError, w)
 		return
@@ -76,13 +76,13 @@ func (h *handler) createToken(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	if err := h.store.SaveProxyAccessToken(r.Context(), &generated.ProxyAccessToken); err != nil {
+	if err := h.store.SaveProxyAccessToken(ctx, &generated.ProxyAccessToken); err != nil {
 		util.WriteErrorResponse("failed to save token", http.StatusInternalServerError, w)
 		return
 	}
 
 	resp := toProxyTokenCreatedResponse(generated)
-	util.WriteJSONObject(r.Context(), w, resp)
+	util.WriteJSONObject(ctx, w, resp)
 }
 
 func (h *handler) listTokens(w http.ResponseWriter, r *http.Request) {
@@ -92,7 +92,7 @@ func (h *handler) listTokens(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	ok, err := h.permissionsManager.ValidateUserPermissions(r.Context(), userAuth.AccountId, userAuth.UserId, modules.Services, operations.Read)
+	ok, ctx, err := h.permissionsManager.ValidateUserPermissions(r.Context(), userAuth.AccountId, userAuth.UserId, modules.Services, operations.Read)
 	if err != nil {
 		util.WriteErrorResponse("failed to validate permissions", http.StatusInternalServerError, w)
 		return
@@ -102,7 +102,7 @@ func (h *handler) listTokens(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	tokens, err := h.store.GetProxyAccessTokensByAccountID(r.Context(), store.LockingStrengthNone, userAuth.AccountId)
+	tokens, err := h.store.GetProxyAccessTokensByAccountID(ctx, store.LockingStrengthNone, userAuth.AccountId)
 	if err != nil {
 		util.WriteErrorResponse("failed to list tokens", http.StatusInternalServerError, w)
 		return
@@ -113,7 +113,7 @@ func (h *handler) listTokens(w http.ResponseWriter, r *http.Request) {
 		resp = append(resp, toProxyTokenResponse(token))
 	}
 
-	util.WriteJSONObject(r.Context(), w, resp)
+	util.WriteJSONObject(ctx, w, resp)
 }
 
 func (h *handler) revokeToken(w http.ResponseWriter, r *http.Request) {
@@ -123,7 +123,7 @@ func (h *handler) revokeToken(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	ok, err := h.permissionsManager.ValidateUserPermissions(r.Context(), userAuth.AccountId, userAuth.UserId, modules.Services, operations.Delete)
+	ok, ctx, err := h.permissionsManager.ValidateUserPermissions(r.Context(), userAuth.AccountId, userAuth.UserId, modules.Services, operations.Delete)
 	if err != nil {
 		util.WriteErrorResponse("failed to validate permissions", http.StatusInternalServerError, w)
 		return
@@ -139,7 +139,7 @@ func (h *handler) revokeToken(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	token, err := h.store.GetProxyAccessTokenByID(r.Context(), store.LockingStrengthNone, tokenID)
+	token, err := h.store.GetProxyAccessTokenByID(ctx, store.LockingStrengthNone, tokenID)
 	if err != nil {
 		if s, ok := status.FromError(err); ok && s.ErrorType == status.NotFound {
 			util.WriteErrorResponse("token not found", http.StatusNotFound, w)
@@ -154,12 +154,12 @@ func (h *handler) revokeToken(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	if err := h.store.RevokeProxyAccessToken(r.Context(), tokenID); err != nil {
+	if err := h.store.RevokeProxyAccessToken(ctx, tokenID); err != nil {
 		util.WriteErrorResponse("failed to revoke token", http.StatusInternalServerError, w)
 		return
 	}
 
-	util.WriteJSONObject(r.Context(), w, util.EmptyObject{})
+	util.WriteJSONObject(ctx, w, util.EmptyObject{})
 }
 
 func toProxyTokenResponse(token *types.ProxyAccessToken) api.ProxyToken {

management/internals/modules/reverseproxy/proxytoken/handler_test.go

@@ -47,7 +47,7 @@ func TestCreateToken_AccountScoped(t *testing.T) {
 	)
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), accountID, "user-1", modules.Services, operations.Create).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), accountID, "user-1", modules.Services, operations.Create).Return(true, context.Background(), nil)
 
 	h := &handler{
 		store:              mockStore,
@@ -90,7 +90,7 @@ func TestCreateToken_WithExpiration(t *testing.T) {
 	)
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Create).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Create).Return(true, context.Background(), nil)
 
 	h := &handler{
 		store:              mockStore,
@@ -115,7 +115,7 @@ func TestCreateToken_EmptyName(t *testing.T) {
 	defer ctrl.Finish()
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Create).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Create).Return(true, context.Background(), nil)
 
 	h := &handler{
 		permissionsManager: permsMgr,
@@ -135,7 +135,7 @@ func TestCreateToken_PermissionDenied(t *testing.T) {
 	defer ctrl.Finish()
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Create).Return(false, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Create).Return(false, context.Background(), nil)
 
 	h := &handler{
 		permissionsManager: permsMgr,
@@ -164,7 +164,7 @@ func TestListTokens(t *testing.T) {
 	}, nil)
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), accountID, "user-1", modules.Services, operations.Read).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), accountID, "user-1", modules.Services, operations.Read).Return(true, context.Background(), nil)
 
 	h := &handler{
 		store:              mockStore,
@@ -202,7 +202,7 @@ func TestRevokeToken_Success(t *testing.T) {
 	mockStore.EXPECT().RevokeProxyAccessToken(gomock.Any(), "tok-1").Return(nil)
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), accountID, "user-1", modules.Services, operations.Delete).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), accountID, "user-1", modules.Services, operations.Delete).Return(true, context.Background(), nil)
 
 	h := &handler{
 		store:              mockStore,
@@ -231,7 +231,7 @@ func TestRevokeToken_WrongAccount(t *testing.T) {
 	}, nil)
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Delete).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Delete).Return(true, context.Background(), nil)
 
 	h := &handler{
 		store:              mockStore,
@@ -258,7 +258,7 @@ func TestRevokeToken_ManagementWideToken(t *testing.T) {
 	}, nil)
 
 	permsMgr := permissions.NewMockManager(ctrl)
-	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Delete).Return(true, nil)
+	permsMgr.EXPECT().ValidateUserPermissions(gomock.Any(), "acc-123", "user-1", modules.Services, operations.Delete).Return(true, context.Background(), nil)
 
 	h := &handler{
 		store:              mockStore,

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

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

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

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

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

@@ -187,7 +187,7 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	clusters, err := h.manager.GetActiveClusters(r.Context(), userAuth.AccountId, userAuth.UserId)
+	clusters, err := h.manager.GetClusters(r.Context(), userAuth.AccountId, userAuth.UserId)
 	if err != nil {
 		util.WriteError(r.Context(), err, w)
 		return
@@ -196,10 +196,15 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 	apiClusters := make([]api.ProxyCluster, 0, len(clusters))
 	for _, c := range clusters {
 		apiClusters = append(apiClusters, api.ProxyCluster{
-			Id:               c.ID,
-			Address:          c.Address,
-			ConnectedProxies: c.ConnectedProxies,
-			SelfHosted:       c.SelfHosted,
+			Id:                  c.ID,
+			Address:             c.Address,
+			Type:                api.ProxyClusterType(c.Type),
+			Online:              c.Online,
+			ConnectedProxies:    c.ConnectedProxies,
+			SupportsCustomPorts: c.SupportsCustomPorts,
+			RequireSubdomain:    c.RequireSubdomain,
+			SupportsCrowdsec:    c.SupportsCrowdSec,
+			Private:             c.Private,
 		})
 	}
 

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

@@ -81,6 +81,8 @@ type ClusterDeriver interface {
 type CapabilityProvider interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 }
 
 type Manager struct {
@@ -112,9 +114,13 @@ func (m *Manager) StartExposeReaper(ctx context.Context) {
 	m.exposeReaper.StartExposeReaper(ctx)
 }
 
-// GetActiveClusters returns all active proxy clusters with their connected proxy count.
-func (m *Manager) GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
+// GetClusters returns every proxy cluster visible to the account
+// (shared + its own BYOP), regardless of whether any proxy in the
+// cluster is currently heartbeating. Each cluster is enriched with the
+// capability flags reported by its active proxies so the dashboard can
+// render feature support without a second round-trip.
+func (m *Manager) GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -122,13 +128,25 @@ func (m *Manager) GetActiveClusters(ctx context.Context, accountID, userID strin
 		return nil, status.NewPermissionDeniedError()
 	}
 
-	return m.store.GetActiveProxyClusters(ctx, accountID)
+	clusters, err := m.store.GetProxyClusters(ctx, accountID)
+	if err != nil {
+		return nil, err
+	}
+
+	for i := range clusters {
+		clusters[i].SupportsCustomPorts = m.capabilities.ClusterSupportsCustomPorts(ctx, clusters[i].Address)
+		clusters[i].RequireSubdomain = m.capabilities.ClusterRequireSubdomain(ctx, clusters[i].Address)
+		clusters[i].SupportsCrowdSec = m.capabilities.ClusterSupportsCrowdSec(ctx, clusters[i].Address)
+		clusters[i].Private = m.capabilities.ClusterSupportsPrivate(ctx, clusters[i].Address)
+	}
+
+	return clusters, nil
 }
 
 // DeleteAccountCluster removes all proxy registrations for the given cluster address
 // owned by the account.
 func (m *Manager) DeleteAccountCluster(ctx context.Context, accountID, userID, clusterAddress string) error {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
 	if err != nil {
 		return status.NewPermissionValidationError(err)
 	}
@@ -140,7 +158,7 @@ func (m *Manager) DeleteAccountCluster(ctx context.Context, accountID, userID, c
 }
 
 func (m *Manager) GetAllServices(ctx context.Context, accountID, userID string) ([]*service.Service, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -192,6 +210,9 @@ func (m *Manager) replaceHostByLookup(ctx context.Context, accountID string, s *
 			target.Host = resource.Domain
 		case service.TargetTypeSubnet:
 			// For subnets we do not do any lookups on the resource
+		case service.TargetTypeCluster:
+			// Cluster targets carry the upstream address on target_id; the
+			// proxy resolves the destination at request time.
 		default:
 			return fmt.Errorf("unknown target type: %s", target.TargetType)
 		}
@@ -201,7 +222,7 @@ func (m *Manager) replaceHostByLookup(ctx context.Context, accountID string, s *
 }
 
 func (m *Manager) GetService(ctx context.Context, accountID, userID, serviceID string) (*service.Service, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -222,7 +243,7 @@ func (m *Manager) GetService(ctx context.Context, accountID, userID, serviceID s
 }
 
 func (m *Manager) CreateService(ctx context.Context, accountID, userID string, s *service.Service) (*service.Service, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Create)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Create)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -507,7 +528,7 @@ func (m *Manager) checkDomainAvailable(ctx context.Context, transaction store.St
 }
 
 func (m *Manager) UpdateService(ctx context.Context, accountID, userID string, service *service.Service) (*service.Service, error) {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Update)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Update)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
 	}
@@ -763,6 +784,10 @@ func validateTargetReferences(ctx context.Context, transaction store.Store, acco
 			if err := validateResourceTarget(ctx, transaction, accountID, target); err != nil {
 				return err
 			}
+		case service.TargetTypeCluster:
+			if err := validateClusterTarget(target); err != nil {
+				return err
+			}
 		default:
 			return status.Errorf(status.InvalidArgument, "unknown target type %q for target %q", target.TargetType, target.TargetId)
 		}
@@ -770,6 +795,13 @@ func validateTargetReferences(ctx context.Context, transaction store.Store, acco
 	return nil
 }
 
+func validateClusterTarget(target *service.Target) error {
+	if !target.Options.DirectUpstream {
+		return status.Errorf(status.InvalidArgument, "cluster target %s has direct upstream disabled", target.Host)
+	}
+	return nil
+}
+
 func validatePeerTarget(ctx context.Context, transaction store.Store, accountID string, target *service.Target) error {
 	if _, err := transaction.GetPeerByID(ctx, store.LockingStrengthShare, accountID, target.TargetId); err != nil {
 		if sErr, ok := status.FromError(err); ok && sErr.Type() == status.NotFound {
@@ -804,7 +836,7 @@ func validateResourceTargetType(target *service.Target, resource *resourcetypes.
 }
 
 func (m *Manager) DeleteService(ctx context.Context, accountID, userID, serviceID string) error {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
 	if err != nil {
 		return status.NewPermissionValidationError(err)
 	}
@@ -844,7 +876,7 @@ func (m *Manager) DeleteService(ctx context.Context, accountID, userID, serviceI
 }
 
 func (m *Manager) DeleteAllServices(ctx context.Context, accountID, userID string) error {
-	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
+	ok, ctx, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete)
 	if err != nil {
 		return status.NewPermissionValidationError(err)
 	}
@@ -946,12 +978,14 @@ func (m *Manager) ReloadAllServicesForAccount(ctx context.Context, accountID str
 		return fmt.Errorf("failed to get services: %w", err)
 	}
 
+	oidcCfg := m.proxyController.GetOIDCValidationConfig()
+
 	for _, s := range services {
 		err = m.replaceHostByLookup(ctx, accountID, s)
 		if err != nil {
 			return fmt.Errorf("failed to replace host by lookup for service %s: %w", s.ID, err)
 		}
-		m.proxyController.SendServiceUpdateToCluster(ctx, accountID, s.ToProtoMapping(service.Update, "", m.proxyController.GetOIDCValidationConfig()), s.ProxyCluster)
+		m.proxyController.SendServiceUpdateToCluster(ctx, accountID, s.ToProtoMapping(service.Update, "", oidcCfg), s.ProxyCluster)
 	}
 
 	return nil

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

@@ -1172,7 +1172,7 @@ func TestDeleteService_DeletesTargets(t *testing.T) {
 
 	mockPerms.EXPECT().
 		ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Delete).
-		Return(true, nil)
+		Return(true, ctx, nil)
 	mockAcct.EXPECT().
 		StoreEvent(ctx, userID, service.ID, accountID, activity.ServiceDeleted, gomock.Any())
 	mockAcct.EXPECT().
@@ -1344,3 +1344,66 @@ func TestValidateSubdomainRequirement(t *testing.T) {
 		})
 	}
 }
+
+func TestValidateTargetReferences_ClusterTargetSkipsLookup(t *testing.T) {
+	ctx := context.Background()
+	ctrl := gomock.NewController(t)
+	mockStore := store.NewMockStore(ctrl)
+	accountID := "test-account"
+
+	// No peer or resource lookups must be issued for cluster targets.
+	targets := []*rpservice.Target{
+		{
+			TargetId:   "eu.proxy.netbird.io",
+			TargetType: rpservice.TargetTypeCluster,
+			Options:    rpservice.TargetOptions{DirectUpstream: true},
+		},
+	}
+	require.NoError(t, validateTargetReferences(ctx, mockStore, accountID, targets), "cluster target must validate without store lookups")
+}
+
+// TestValidateTargetReferences_ClusterTargetRequiresDirectUpstream pins the
+// store-side check that cluster targets must opt into the host-stack dial
+// path. Without DirectUpstream the proxy would route this target through
+// the embedded NetBird client and fail on every request.
+func TestValidateTargetReferences_ClusterTargetRequiresDirectUpstream(t *testing.T) {
+	ctx := context.Background()
+	ctrl := gomock.NewController(t)
+	mockStore := store.NewMockStore(ctrl)
+	accountID := "test-account"
+
+	targets := []*rpservice.Target{
+		{
+			TargetId:   "eu.proxy.netbird.io",
+			TargetType: rpservice.TargetTypeCluster,
+			Host:       "backend.lan",
+		},
+	}
+	err := validateTargetReferences(ctx, mockStore, accountID, targets)
+	require.Error(t, err, "cluster target without direct_upstream must be rejected")
+	assert.ErrorContains(t, err, "direct upstream disabled")
+}
+
+func TestReplaceHostByLookup_SkipsClusterTarget(t *testing.T) {
+	ctx := context.Background()
+	ctrl := gomock.NewController(t)
+	mockStore := store.NewMockStore(ctrl)
+	accountID := "test-account"
+
+	mgr := &Manager{store: mockStore}
+
+	svc := &rpservice.Service{
+		ID:        "svc-1",
+		AccountID: accountID,
+		Targets: []*rpservice.Target{
+			{
+				TargetId:   "eu.proxy.netbird.io",
+				TargetType: rpservice.TargetTypeCluster,
+				Host:       "127.0.0.1",
+			},
+		},
+	}
+
+	require.NoError(t, mgr.replaceHostByLookup(ctx, accountID, svc), "cluster target must not trigger peer/resource lookup")
+	assert.Equal(t, "127.0.0.1", svc.Targets[0].Host, "operator-supplied host must be preserved for cluster target")
+}