[client/ui] Update Wails to v3.0.0-alpha2.105

Bump github.com/wailsapp/wails/v3 to v3.0.0-alpha2.105 and the
@wailsio/runtime frontend dependency to 3.0.0-alpha.94 (latest published
on npm), excluding it from the pnpm minimum release age gate.

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

@@ -1,68 +0,0 @@
-name: Agent Network E2E
-
-on:
-  # Nightly at 03:00 UTC, plus on demand from the Actions tab.
-  schedule:
-    - cron: "0 3 * * *"
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  e2e:
-    name: Agent Network E2E
-    runs-on: ubuntu-latest
-    timeout-minutes: 45
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          persist-credentials: false
-
-      - name: Install Go
-        uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c # v6.4.0
-        with:
-          go-version-file: "go.mod"
-
-      # Container-driver builder so the harness can build the combined/proxy/
-      # client images from source with a local layer cache.
-      - name: Set up Buildx
-        uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
-
-      # Persist the Docker layer cache across runs. This caches the base, apt,
-      # and go-mod-download layers; the Go compile still re-runs, as BuildKit
-      # mount caches cannot be exported to the GitHub cache.
-      - name: Cache Docker layers
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
-        with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-anet-e2e-buildx-${{ hashFiles('go.sum', 'combined/Dockerfile.multistage', 'proxy/Dockerfile.multistage', 'e2e/harness/Dockerfile.client') }}
-          restore-keys: |
-            ${{ runner.os }}-anet-e2e-buildx-
-
-      - name: Run agent-network e2e
-        env:
-          # Build the images from source (this branch's code) with the shared
-          # local layer cache.
-          NB_E2E_BUILDX_CACHE: /tmp/.buildx-cache
-          # Provider credentials. Each provider scenario skips if its
-          # token (and URL, for gateways) is unset, so partial coverage is fine.
-          OPENAI_TOKEN: ${{ secrets.E2E_OPENAI_TOKEN }}
-          ANTHROPIC_TOKEN: ${{ secrets.E2E_ANTHROPIC_TOKEN }}
-          VERCEL_URL: ${{ secrets.E2E_VERCEL_URL }}
-          VERCEL_TOKEN: ${{ secrets.E2E_VERCEL_TOKEN }}
-          OPENROUTER_URL: ${{ secrets.E2E_OPENROUTER_URL }}
-          OPENROUTER_TOKEN: ${{ secrets.E2E_OPENROUTER_TOKEN }}
-          CLOUDFLARE_URL: ${{ secrets.E2E_CLOUDFLARE_URL }}
-          CLOUDFLARE_TOKEN: ${{ secrets.E2E_CLOUDFLARE_TOKEN }}
-          AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.E2E_AWS_BEARER_TOKEN_BEDROCK }}
-          AWS_REGION: ${{ secrets.E2E_AWS_REGION }}
-          # Vertex (Anthropic-on-Vertex): SA + project required; region defaults
-          # to "global", model to a pinned claude snapshot.
-          GOOGLE_VERTEX_SA_BASE64: ${{ secrets.E2E_GOOGLE_VERTEX_SA_BASE64 }}
-          GOOGLE_VERTEX_PROJECT: ${{ secrets.E2E_GOOGLE_VERTEX_PROJECT }}
-          GOOGLE_VERTEX_REGION: ${{ secrets.E2E_GOOGLE_VERTEX_REGION }}
-          GOOGLE_VERTEX_MODEL: ${{ secrets.E2E_GOOGLE_VERTEX_MODEL }}
-        run: go test -tags e2e -timeout 40m -v ./e2e/...

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

@@ -20,7 +20,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
@@ -59,12 +59,12 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Set up Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: true

.github/workflows/git-town.yml

@@ -15,7 +15,7 @@ jobs:
       pull-requests: write
 
     steps:
-      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - uses: git-town/action@3d8b878379abb1ee393fb49865a28b4a6c2cd3b0 # v1.2.1

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

@@ -16,18 +16,18 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
 
       - name: Cache Go modules
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: ~/go/pkg/mod
           key: macos-gotest-${{ hashFiles('**/go.sum') }}
@@ -53,10 +53,10 @@ jobs:
         # resolve; the grep then drops the broken package by path. Without -e,
         # go list aborts with empty stdout and `go test` falls back to the repo
         # root, which has no Go files.
-        run: NETBIRD_STORE_ENGINE=${{ matrix.store }} CI=true go test -coverprofile=coverage.txt -tags 'devcert privileged' -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' -timeout 5m -p 1 $(go list -e ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui -e /client/testutil/privileged)
+        run: NETBIRD_STORE_ENGINE=${{ matrix.store }} CI=true go test -coverprofile=coverage.txt -tags=devcert -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' -timeout 5m -p 1 $(go list -e ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui)
 
       - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird

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

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
@@ -28,7 +28,7 @@ jobs:
         id: test
         env:
           GO_VERSION: ${{ steps.goversion.outputs.version }}
-        uses: vmactions/freebsd-vm@b84ab5559b5a1bb4b8ee2737d2506a16e1737636 # v1.4.8
+        uses: vmactions/freebsd-vm@d1e65811565151536c0c894fff74f06351ed26e6 # v1.4.5
         with:
           usesh: true
           copyback: false
@@ -48,14 +48,14 @@ jobs:
             export PATH=$PATH:/usr/local/go/bin:$HOME/go/bin
             time go build -o netbird client/main.go
             # check all component except management, since we do not support management server on freebsd
-            time go test -tags privileged -timeout 1m -failfast ./base62/...
+            time go test -timeout 1m -failfast ./base62/...
             # NOTE: without -p1 `client/internal/dns` will fail because of `listen udp4 :33100: bind: address already in use`
-            time go test -tags privileged -timeout 8m -failfast -v -p 1 ./client/...
-            time go test -tags privileged -timeout 1m -failfast ./dns/...
-            time go test -tags privileged -timeout 1m -failfast ./encryption/...
-            time go test -tags privileged -timeout 1m -failfast ./formatter/...
-            time go test -tags privileged -timeout 1m -failfast ./client/iface/...
-            time go test -tags privileged -timeout 1m -failfast ./route/...
-            time go test -tags privileged -timeout 1m -failfast ./sharedsock/...
-            time go test -tags privileged -timeout 1m -failfast ./util/...
-            time go test -tags privileged -timeout 1m -failfast ./version/...
+            time go test -timeout 8m -failfast -v -p 1 ./client/...
+            time go test -timeout 1m -failfast ./dns/...
+            time go test -timeout 1m -failfast ./encryption/...
+            time go test -timeout 1m -failfast ./formatter/...
+            time go test -timeout 1m -failfast ./client/iface/...
+            time go test -timeout 1m -failfast ./route/...
+            time go test -timeout 1m -failfast ./sharedsock/...
+            time go test -timeout 1m -failfast ./util/...
+            time go test -timeout 1m -failfast ./version/...

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

@@ -18,7 +18,7 @@ jobs:
       management: ${{ steps.filter.outputs.management }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
@@ -30,7 +30,7 @@ jobs:
               - 'management/**'
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -41,7 +41,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         id: cache
         with:
           path: |
@@ -119,12 +119,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -135,7 +135,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -166,11 +166,11 @@ jobs:
         # resolve; the grep then drops the broken package by path. Without -e,
         # go list aborts with empty stdout and `go test` falls back to the repo
         # root, which has no Go files.
-        run: CGO_ENABLED=1 GOARCH=${{ matrix.arch }} CI=true go test -coverprofile=coverage.txt -tags 'devcert privileged' -exec 'sudo --preserve-env=CI,CGO_ENABLED' -timeout 10m -p 1 $(go list -e ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui -e /client/testutil/privileged)
+        run: CGO_ENABLED=1 GOARCH=${{ matrix.arch }} CI=true go test -coverprofile=coverage.txt -tags devcert -exec 'sudo' -timeout 10m -p 1 $(go list -e ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui)
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird
@@ -182,12 +182,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -199,7 +199,7 @@ jobs:
           echo "modcache_dir=$(go env GOMODCACHE)" >> $GITHUB_OUTPUT
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         id: cache-restore
         with:
           path: |
@@ -236,7 +236,7 @@ jobs:
             sh -c ' \
               apk update; apk add --no-cache \
                 ca-certificates iptables ip6tables dbus dbus-dev libpcap-dev build-base; \
-              go test -buildvcs=false -tags "devcert privileged" -v -timeout 10m -p 1 $(go list -e -buildvcs=false ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui -e /upload-server -e /client/testutil/privileged)
+              go test -buildvcs=false -tags devcert -v -timeout 10m -p 1 $(go list -e -buildvcs=false ./... | grep -v -e /management -e /signal -e /relay -e /proxy -e /combined -e /client/ui -e /upload-server)
             '
 
   test_relay:
@@ -253,12 +253,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -273,7 +273,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -297,7 +297,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird
@@ -313,12 +313,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -332,7 +332,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -354,7 +354,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird
@@ -370,12 +370,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -390,7 +390,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -414,7 +414,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird
@@ -431,12 +431,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -447,7 +447,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -491,7 +491,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird
@@ -536,12 +536,12 @@ jobs:
             prom/prometheus
 
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -552,7 +552,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -586,11 +586,10 @@ jobs:
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           NETBIRD_STORE_ENGINE=${{ matrix.store }} \
           CI=true \
+          GIT_BRANCH=${{ github.ref_name }} \
           go test -tags devcert -run=^$ -bench=. \
           -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE,GIT_BRANCH,GITHUB_RUN_ID' \
           -timeout 20m ./management/... ./shared/management/... $(go list ./management/... ./shared/management/... | grep -v -e /management/server/http)
-        env:
-          GIT_BRANCH: ${{ github.ref_name }}
 
   api_benchmark:
     name: "Management / Benchmark (API)"
@@ -631,12 +630,12 @@ jobs:
             prom/prometheus
 
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -647,7 +646,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -681,13 +680,12 @@ jobs:
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           NETBIRD_STORE_ENGINE=${{ matrix.store }} \
           CI=true \
+          GIT_BRANCH=${{ github.ref_name }} \
           go test -tags=benchmark \
             -run=^$ \
             -bench=. \
             -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE,GIT_BRANCH,GITHUB_RUN_ID' \
             -timeout 20m ./management/server/http/...
-        env:
-          GIT_BRANCH: ${{ github.ref_name }}
 
   api_integration_test:
     name: "Management / Integration"
@@ -701,12 +699,12 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
@@ -717,7 +715,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -743,7 +741,7 @@ jobs:
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'
-        uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f #v7.0.0
+        uses: codecov/codecov-action@e79a6962e0d4c0c17b229090214935d2e33f8354 #v6.0.1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: netbirdio/netbird

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

@@ -18,12 +18,12 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         id: go
         with:
           go-version-file: "go.mod"
@@ -35,7 +35,7 @@ jobs:
           echo "modcache=$(go env GOMODCACHE)" >> $env:GITHUB_ENV
 
       - name: Cache Go modules
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ${{ env.cache }}
@@ -75,7 +75,7 @@ jobs:
         run: |
           $packages = go list -e ./... | Where-Object { $_ -notmatch '/management' } | Where-Object { $_ -notmatch '/relay' } | Where-Object { $_ -notmatch '/signal' } | Where-Object { $_ -notmatch '/proxy' } | Where-Object { $_ -notmatch '/combined' } | Where-Object { $_ -notmatch '/client/ui' }
           $goExe = "C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe"
-          $cmd = "$goExe test -tags `"devcert privileged`" -timeout 10m -p 1 $($packages -join ' ') > test-out.txt 2>&1"
+          $cmd = "$goExe test -tags=devcert -timeout 10m -p 1 $($packages -join ' ') > test-out.txt 2>&1"
           Set-Content -Path "${{ github.workspace }}\run-tests.cmd" -Value $cmd
 
       - name: test

.github/workflows/golangci-lint.yml

@@ -15,13 +15,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - name: codespell
         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,flate,recordin,unparseable
+          ignore_words_list: erro,clienta,hastable,iif,groupd,testin,groupe,cros,ans,deriver,te,userA,ede,additionals
           # Non-English UI translations trip codespell on real foreign words
           # (de: "Sie", "oder", "ist"). Only en/common.json is the source of
           # truth that should be spell-checked. List each translated locale
@@ -48,7 +48,7 @@ jobs:
     timeout-minutes: 15
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - name: Check for duplicate constants
@@ -56,7 +56,7 @@ jobs:
         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@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false

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

@@ -22,7 +22,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 

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

@@ -16,11 +16,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: Setup Android SDK
@@ -28,13 +28,13 @@ jobs:
         with:
           cmdline-tools-version: 8512546
       - name: Setup Java
-        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520
+        uses: actions/setup-java@be666c2fcd27ec809703dec50e508c2fdc7f6654
         with:
           java-version: "11"
           distribution: "adopt"
       - name: NDK Cache
         id: ndk-cache
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: /usr/local/lib/android/sdk/ndk
           key: ndk-cache-23.1.7779620
@@ -54,11 +54,11 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: install gomobile

.github/workflows/release.yml

@@ -27,7 +27,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
@@ -64,7 +64,7 @@ jobs:
         if: steps.check_diff.outputs.diff_exists == 'true'
         env:
           GO_VERSION: ${{ steps.goversion.outputs.version }}
-        uses: vmactions/freebsd-vm@b84ab5559b5a1bb4b8ee2737d2506a16e1737636 # v1.4.8
+        uses: vmactions/freebsd-vm@d1e65811565151536c0c894fff74f06351ed26e6 # v1.4.5
         with:
           usesh: true
           copyback: false
@@ -135,7 +135,7 @@ jobs:
       ghcr_images: ${{ steps.tag_and_push_images.outputs.images_markdown }}
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0 # It is required for GoReleaser to work properly
           persist-credentials: false
@@ -166,12 +166,12 @@ jobs:
           fi
 
       - name: Set up Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
       - name: Cache Go modules
-        uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ~/go/pkg/mod
@@ -186,9 +186,9 @@ jobs:
       - name: check git status
         run: git --no-pager diff --exit-code
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@06116385d9baf250c9f4dcb4858b16962ea869c3 #v4.1.0
+        uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a #v4.0.0
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 #v4.1.0
+        uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd #v4.0.0
       - name: Login to Docker hub
         if: github.event_name != 'pull_request'
         uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
@@ -221,7 +221,7 @@ jobs:
         run: goversioninfo -arm -64 -icon client/ui/build/windows/icon.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@5daf1e915a5f0af01ddbcd89a43b8061ff4f1a89 # v7.2.2
+        uses: goreleaser/goreleaser-action@4c6ab561adb47e50c45ef534e2155934e91c40c1 # v7.2.0
         with:
           version: ${{ env.GORELEASER_VER }}
           args: release --clean ${{ env.flags }}
@@ -293,11 +293,8 @@ jobs:
           ${{ steps.goreleaser.outputs.artifacts }}
           JSON
 
-          # dockers_v2 artifacts have no top-level goarch field, so match the
-          # per-platform -amd64 tag suffix instead; it works for both the old
-          # dockers and the new dockers_v2 image naming.
           mapfile -t src_images < <(
-            jq -r '.[] | select(.type == "Docker Image") | .name | select(startswith("ghcr.io/") and endswith("-amd64"))' /tmp/goreleaser-artifacts.json
+            jq -r '.[] | select(.type == "Docker Image") | select(.goarch == "amd64") | .name | select(startswith("ghcr.io/"))' /tmp/goreleaser-artifacts.json
           )
 
           for src in "${src_images[@]}"; do
@@ -350,7 +347,7 @@ jobs:
       release_ui_artifact_url: ${{ steps.upload_release_ui.outputs.artifact-url }}
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0 # It is required for GoReleaser to work properly
           persist-credentials: false
@@ -377,12 +374,12 @@ jobs:
           fi
 
       - name: Set up Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
       - name: Cache Go modules
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ~/go/pkg/mod
@@ -439,7 +436,7 @@ jobs:
         run: goversioninfo -arm -64 -icon client/ui/build/windows/icon.ico -manifest client/ui/build/windows/wails.exe.manifest -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@5daf1e915a5f0af01ddbcd89a43b8061ff4f1a89 # v7.2.2
+        uses: goreleaser/goreleaser-action@4c6ab561adb47e50c45ef534e2155934e91c40c1 # v7.2.0
         with:
           version: ${{ env.GORELEASER_VER }}
           args: release --config .goreleaser_ui.yaml --clean ${{ env.flags }}
@@ -483,17 +480,17 @@ jobs:
       - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
         run: echo "flags=--snapshot" >> $GITHUB_ENV
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           fetch-depth: 0 # It is required for GoReleaser to work properly
           persist-credentials: false
       - name: Set up Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
           cache: false
       - name: Cache Go modules
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: |
             ~/go/pkg/mod
@@ -521,7 +518,7 @@ jobs:
           go install github.com/wailsapp/wails/v3/cmd/wails3@$WAILS_VERSION
       - name: Run GoReleaser
         id: goreleaser
-        uses: goreleaser/goreleaser-action@5daf1e915a5f0af01ddbcd89a43b8061ff4f1a89 # v7.2.2
+        uses: goreleaser/goreleaser-action@4c6ab561adb47e50c45ef534e2155934e91c40c1 # v7.2.0
         with:
           version: ${{ env.GORELEASER_VER }}
           args: release --config .goreleaser_ui_darwin.yaml --clean ${{ env.flags }}
@@ -555,7 +552,7 @@ jobs:
       downloadPath: '${{ github.workspace }}\temp'
     steps:
       - name: Checkout
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
@@ -567,13 +564,13 @@ jobs:
         run: echo "C:\Program Files\7-Zip" | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
 
       - name: Download release artifacts
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.1
         with:
           name: release
           path: release
 
       - name: Download UI release artifacts
-        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
+        uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8.0.1
         with:
           name: release-ui
           path: release-ui

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

@@ -68,17 +68,17 @@ jobs:
         run: sudo apt-get install -y curl
 
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
 
       - name: Cache Go modules
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
         with:
           path: ~/go/pkg/mod
           key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
@@ -207,7 +207,7 @@ jobs:
       - name: Build management docker image
         working-directory: management
         run: |
-          docker build -t netbirdio/management:latest --build-arg TARGETPLATFORM=. .
+          docker build -t netbirdio/management:latest .
 
       - name: Build signal binary
         working-directory: signal
@@ -216,7 +216,7 @@ jobs:
       - name: Build signal docker image
         working-directory: signal
         run: |
-          docker build -t netbirdio/signal:latest --build-arg TARGETPLATFORM=. .
+          docker build -t netbirdio/signal:latest .
 
       - name: Build relay binary
         working-directory: relay
@@ -225,7 +225,7 @@ jobs:
       - name: Build relay docker image
         working-directory: relay
         run: |
-          docker build -t netbirdio/relay:latest --build-arg TARGETPLATFORM=. .
+          docker build -t netbirdio/relay:latest .
 
       - name: run docker compose up
         working-directory: infrastructure_files/artifacts
@@ -256,7 +256,7 @@ jobs:
         run: sudo apt-get install -y jq
 
       - name: Checkout code
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
 

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

@@ -19,11 +19,11 @@ jobs:
       GOARCH: wasm
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: Install dependencies
@@ -44,11 +44,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
       - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        uses: actions/setup-go@4b73464bb391d4059bd26b0524d20df3927bd417 # v6.3.0
         with:
           go-version-file: "go.mod"
       - name: Build Wasm client

.gitignore

@@ -1,4 +1,3 @@
-.claude
 .idea
 .run
 *.iml

.goreleaser.yaml

@@ -464,13 +464,9 @@ checksum:
     - glob: ./infrastructure_files/getting-started-with-zitadel.sh
     - glob: ./release_files/install.sh
     - glob: ./infrastructure_files/getting-started.sh
-    - glob: ./infrastructure_files/getting-started-enterprise.sh
-    - glob: ./infrastructure_files/migrate-to-enterprise.sh
 
 release:
   extra_files:
     - glob: ./infrastructure_files/getting-started-with-zitadel.sh
     - glob: ./release_files/install.sh
     - glob: ./infrastructure_files/getting-started.sh
-    - glob: ./infrastructure_files/getting-started-enterprise.sh
-    - glob: ./infrastructure_files/migrate-to-enterprise.sh

CONTRIBUTING.md

@@ -237,7 +237,7 @@ task dev
 Pass daemon flags after `--`:
 
 ```
-task dev -- --daemon-addr=npipe://netbird
+task dev -- --daemon-addr=tcp://127.0.0.1:41731
 ```
 
 Production build (frontend assets embedded into the binary, output in `client/ui/bin/`):

Makefile

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

README.md

@@ -33,15 +33,10 @@
   <br/>
   <br/>
   <strong>
-    🚀 <a href="https://netbird.io/careers">We are hiring! Join us at https://netbird.io/careers</a>
+    🚀 <a href="https://careers.netbird.io">We are hiring! Join us at careers.netbird.io</a>
   </strong>
 </p>
 
-> ### 🤖 NetBird Agent Network (Beta)
-> Identity-aware access control for AI agents — keyless access to LLM APIs and private
-> resources over the encrypted NetBird tunnel. See [`agent-network/`](agent-network/) or
-> read the docs at **[netbird.ai](https://netbird.ai)**.
-
 **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.

agent-network/README.md

@@ -1,73 +0,0 @@
-# NetBird Agent Network
-
-Agent Network is NetBird's access control layer for AI agents and the people who run them. 
-It gives every agent a real identity, tied to an identity provider (IdP), and governs what it can reach: LLM APIs and 
-AI gateways it can call, and the internal resources it can access. Traffic flows only over the encrypted NetBird tunnel, 
-scoped by policy, with no API keys or other credentials to leak. It also gives you control over cost and token usage.
-
-Because every LLM request passes through an
-identity-aware proxy, you can:
-
-- **Set spending and rate limits** per agent, per user, or per team — with hard caps
-  that stop requests once a budget is reached.
-- **Restrict models and providers** so agents can only call approved (and cost-appropriate)
-  endpoints, keeping expensive models off-limits unless explicitly allowed.
-- **Attribute usage** by tracking token consumption and cost per identity, group, or cost center so every
-  request is tied back to the agent and person responsible.
-- **Reuse your existing AI gateway** — point the proxy at a gateway you already run,
-  keeping its routing and config in place while it adds identity on top, so you skip
-  API key distribution.
-
-https://github.com/user-attachments/assets/44d18286-d8ab-49f8-a457-98ccd66f3268
-
-> **Beta.** Agent Network is in beta, but it's stable and already running in
-> production environments. It's fully open source and can be self-hosted on your own
-> infrastructure, with no vendor lock-in and no data leaving your environment.
-
-## How it works
-
-Say you have a simple use case: your Engineering or IT team needs access to Claude Code or Codex, and you want visibility into usage plus the ability to enforce budgets.
-How can you do that without creating a dedicated API key for every team?
-
-With Agent Network you get a private endpoint inside your network, for example: https://mirror.netbird.ai
-Teams configure their agents to point to that endpoint instead of using individual API keys directly. 
-
-This endpoint is only reachable when users are connected to your NetBird network and authenticated through your IdP. Otherwise, it is not accessible from the public internet.
-You can then use this private endpoint to configure your AI agents, whether that is Claude Code, Codex, or another tool.
-
-## Quickstart
-
-Full step-by-step setup:
-**https://docs.netbird.io/agent-network/quickstart**
-
-## Architecture 
-
-Agent Network is built on two existing NetBird capabilities:
-
-- **Overlay network** — the encrypted WireGuard mesh between peers.
-- **Reverse proxy** — a NetBird peer that terminates LLM requests, establishes the
-  caller's identity, evaluates policies/limits/guardrails, injects the upstream provider
-  key server-side, forwards to the API or gateway, and records usage.
-
-LLM traffic is routed through the proxy's identity-aware pipeline, while internal
-resources (databases, internal APIs, self-hosted models) are reached directly over
-peer-to-peer WireGuard tunnels, governed by the same identities and access policies.
-
-<img width="4720" height="2218" alt="image" src="https://github.com/user-attachments/assets/1afa5da1-4b82-4f8a-a7a8-f417efadf1eb" />
-
-
-## Where the code lives
-
-There is no separate "agent-network" service — it reuses the reverse-proxy and management
-components:
-
-- [`proxy/`](../proxy) — the NetBird reverse proxy that serves the agent network endpoint
-  and runs the per-request middleware pipeline.
-- [`management/internals/modules/reverseproxy/`](../management/internals/modules/reverseproxy)
-  — the management-side control plane: providers, policies, guardrails, limits, routing,
-  and usage/access logs.
-
-## Documentation
-
-Full documentation, architecture, and quickstart:
-**https://docs.netbird.io/agent-network**

client/android/client.go

@@ -247,9 +247,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
 		deps.SyncResponse = resp
 
 		if e := cc.Engine(); e != nil {
-			deps.RefreshStatus = func() {
-				e.RunHealthProbes(context.Background(), true)
-			}
 			if cm := e.GetClientMetrics(); cm != nil {
 				deps.ClientMetrics = cm
 			}

client/android/env_list.go

@@ -10,7 +10,7 @@ var (
 	EnvKeyNBForceRelay = peer.EnvKeyNBForceRelay
 
 	// EnvKeyNBLazyConn Exported for Android java client to configure lazy connection
-	EnvKeyNBLazyConn = lazyconn.EnvLazyConn
+	EnvKeyNBLazyConn = lazyconn.EnvEnableLazyConn
 
 	// EnvKeyNBInactivityThreshold Exported for Android java client to configure connection inactivity threshold
 	EnvKeyNBInactivityThreshold = lazyconn.EnvInactivityThreshold

client/android/profile_manager.go

@@ -145,7 +145,7 @@ func (pm *ProfileManager) SwitchProfile(id string) error {
 // AddProfile creates a new profile
 func (pm *ProfileManager) AddProfile(profileName string) error {
 	// Use ServiceManager (creates profile in profiles/ directory)
-	profile, err := pm.serviceMgr.AddProfile(profileName, androidUsername, nil)
+	profile, err := pm.serviceMgr.AddProfile(profileName, androidUsername)
 	if err != nil {
 		return fmt.Errorf("failed to add profile: %w", err)
 	}

client/cmd/debug.go

@@ -130,7 +130,7 @@ func debugConfigDump(cmd *cobra.Command, _ []string) error {
 
 	client := proto.NewDaemonServiceClient(conn)
 	resp, err := client.GetConfig(cmd.Context(), &proto.GetConfigRequest{
-		ProfileName: string(activeProf.ID),
+		ProfileName: activeProf.Name,
 		Username:    currUser.Username,
 	})
 	if err != nil {

client/cmd/elevate.go

@@ -1,58 +0,0 @@
-package cmd
-
-import (
-	"fmt"
-	"os"
-
-	"github.com/spf13/cobra"
-)
-
-// SetSSHConfigCmdName is the hidden subcommand an elevated process runs to apply
-// the privileged SSH settings.
-const SetSSHConfigCmdName = "set-ssh-config"
-
-// sshConfigElevated is set by runInDaemonMode once the dangerous SSH settings
-// have been applied by an elevated helper, so the (unprivileged) up flow does
-// not re-send them and re-trip the daemon gate.
-var sshConfigElevated bool
-
-// wantsDangerousSSH reports whether this invocation is trying to ENABLE SSH root
-// login or DISABLE SSH authentication.
-func wantsDangerousSSH(cmd *cobra.Command) bool {
-	return (cmd.Flags().Changed(enableSSHRootFlag) && enableSSHRoot) ||
-		(cmd.Flags().Changed(disableSSHAuthFlag) && disableSSHAuth)
-}
-
-// buildSetSSHConfigArgs builds the argument list for an elevated
-// `netbird set-ssh-config` invocation.
-func buildSetSSHConfigArgs(profileName, username string, enableSSHRoot, disableSSHAuth *bool, daemonAddr string) []string {
-	args := []string{SetSSHConfigCmdName}
-	if profileName != "" {
-		args = append(args, "--profile", profileName)
-	}
-	if username != "" {
-		args = append(args, "--username", username)
-	}
-	if enableSSHRoot != nil && *enableSSHRoot {
-		args = append(args, "--"+enableSSHRootFlag)
-	}
-	if disableSSHAuth != nil && *disableSSHAuth {
-		args = append(args, "--"+disableSSHAuthFlag)
-	}
-	if daemonAddr != "" {
-		args = append(args, "--daemon-addr", daemonAddr)
-	}
-	return args
-}
-
-// ElevateSSHConfig re-runs the current executable's `set-ssh-config` command with
-// root/administrator privileges via the platform's prompt (pkexec/UAC/osascript),
-// so the elevated process connects to the daemon with a privileged identity and
-// the daemon's requirePrivilegedForDangerousSSH gate passes.
-func ElevateSSHConfig(profileName, username string, enableSSHRoot, disableSSHAuth *bool) error {
-	exe, err := os.Executable()
-	if err != nil {
-		return fmt.Errorf("locate executable for elevation: %w", err)
-	}
-	return runElevated(exe, buildSetSSHConfigArgs(profileName, username, enableSSHRoot, disableSSHAuth, daemonAddr))
-}

client/cmd/elevate_darwin.go

@@ -1,16 +0,0 @@
-//go:build darwin
-
-package cmd
-
-import (
-	"fmt"
-	"os"
-)
-
-// isProcessPrivileged reports whether the current process runs as root.
-func isProcessPrivileged() bool { return os.Geteuid() == 0 }
-
-// TODO(ssh-elevation): implement the osascript admin prompt.
-func runElevated(_ string, _ []string) error {
-	return fmt.Errorf("automatic privilege elevation is not yet implemented on macOS, re-run with sudo")
-}

client/cmd/elevate_linux.go

@@ -1,38 +0,0 @@
-//go:build linux
-
-package cmd
-
-import (
-	"fmt"
-	"os"
-	"os/exec"
-	"strings"
-)
-
-// isProcessPrivileged reports whether the current process runs as root.
-func isProcessPrivileged() bool { return os.Geteuid() == 0 }
-
-// runElevated re-runs exe with args as root. On a graphical session it uses
-// pkexec, which drives the desktop's polkit authentication agent (GUI prompt).
-func runElevated(exe string, args []string) error {
-	if !hasGraphicalSession() {
-		return fmt.Errorf("cannot request privilege elevation without a graphical session. re-run as root: sudo %s %s", exe, strings.Join(args, " "))
-	}
-	pkexec, err := exec.LookPath("pkexec")
-	if err != nil {
-		return fmt.Errorf("pkexec not found for privilege elevation, re-run as root: sudo %s %s", exe, strings.Join(args, " "))
-	}
-
-	c := exec.Command(pkexec, append([]string{exe}, args...)...)
-	c.Stdin, c.Stdout, c.Stderr = os.Stdin, os.Stdout, os.Stderr
-	if err := c.Run(); err != nil {
-		return fmt.Errorf("elevated %s failed (elevation cancelled or denied?): %w", SetSSHConfigCmdName, err)
-	}
-	return nil
-}
-
-// hasGraphicalSession heuristically reports whether a desktop session is present
-// that polkit can prompt in.
-func hasGraphicalSession() bool {
-	return os.Getenv("DISPLAY") != "" || os.Getenv("WAYLAND_DISPLAY") != ""
-}

client/cmd/elevate_other.go

@@ -1,17 +0,0 @@
-//go:build !linux && !darwin && !windows
-
-package cmd
-
-import (
-	"fmt"
-	"os"
-	"strings"
-)
-
-// isProcessPrivileged reports whether the current process runs as root.
-func isProcessPrivileged() bool { return os.Geteuid() == 0 }
-
-// runElevated has no automatic elevation mechanism on these platforms
-func runElevated(exe string, args []string) error {
-	return fmt.Errorf("automatic privilege elevation is not supported on this platform, re-run as root: sudo %s %s", exe, strings.Join(args, " "))
-}

client/cmd/elevate_test.go

@@ -1,99 +0,0 @@
-//go:build !ios && !android
-
-package cmd
-
-import (
-	"testing"
-
-	"github.com/spf13/cobra"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-func TestBuildSetSSHConfigArgs(t *testing.T) {
-	tr, fa := true, false
-
-	t.Run("enable root only, with daemon-addr", func(t *testing.T) {
-		got := buildSetSSHConfigArgs("prof", "alice", &tr, nil, "unix:///x.sock")
-		assert.Equal(t, []string{
-			SetSSHConfigCmdName, "--profile", "prof", "--username", "alice",
-			"--" + enableSSHRootFlag, "--daemon-addr", "unix:///x.sock",
-		}, got)
-	})
-
-	t.Run("disable auth only, no daemon-addr", func(t *testing.T) {
-		got := buildSetSSHConfigArgs("prof", "alice", nil, &tr, "")
-		assert.Equal(t, []string{
-			SetSSHConfigCmdName, "--profile", "prof", "--username", "alice",
-			"--" + disableSSHAuthFlag,
-		}, got)
-	})
-
-	t.Run("false pointers omit the flags", func(t *testing.T) {
-		got := buildSetSSHConfigArgs("", "", &fa, &fa, "")
-		assert.Equal(t, []string{SetSSHConfigCmdName}, got)
-	})
-
-	t.Run("both enabled", func(t *testing.T) {
-		got := buildSetSSHConfigArgs("p", "u", &tr, &tr, "")
-		assert.Equal(t, []string{
-			SetSSHConfigCmdName, "--profile", "p", "--username", "u",
-			"--" + enableSSHRootFlag, "--" + disableSSHAuthFlag,
-		}, got)
-	})
-}
-
-func TestBuildSetSSHConfigRequest(t *testing.T) {
-	tr := true
-
-	req := buildSetSSHConfigRequest("p", "u", &tr, nil)
-	assert.Equal(t, "p", req.ProfileName)
-	assert.Equal(t, "u", req.Username)
-	if assert.NotNil(t, req.EnableSSHRoot) {
-		assert.True(t, *req.EnableSSHRoot)
-	}
-	assert.Nil(t, req.DisableSSHAuth, "an unset flag must leave the daemon value untouched")
-}
-
-func TestWantsDangerousSSH(t *testing.T) {
-	origRoot, origAuth := enableSSHRoot, disableSSHAuth
-	t.Cleanup(func() { enableSSHRoot, disableSSHAuth = origRoot, origAuth })
-
-	newCmd := func() *cobra.Command {
-		enableSSHRoot, disableSSHAuth = false, false
-		c := &cobra.Command{Use: "x"}
-		c.Flags().BoolVar(&enableSSHRoot, enableSSHRootFlag, false, "")
-		c.Flags().BoolVar(&disableSSHAuth, disableSSHAuthFlag, false, "")
-		return c
-	}
-
-	// wantsDangerousSSH fires only in the privileged direction.
-	t.Run("enable root true is dangerous", func(t *testing.T) {
-		c := newCmd()
-		require.NoError(t, c.Flags().Set(enableSSHRootFlag, "true"))
-		assert.True(t, wantsDangerousSSH(c))
-	})
-
-	t.Run("enable root false is not dangerous", func(t *testing.T) {
-		c := newCmd()
-		require.NoError(t, c.Flags().Set(enableSSHRootFlag, "false"))
-		assert.False(t, wantsDangerousSSH(c))
-	})
-
-	t.Run("disable auth true is dangerous", func(t *testing.T) {
-		c := newCmd()
-		require.NoError(t, c.Flags().Set(disableSSHAuthFlag, "true"))
-		assert.True(t, wantsDangerousSSH(c))
-	})
-
-	t.Run("disable auth false is not dangerous", func(t *testing.T) {
-		c := newCmd()
-		require.NoError(t, c.Flags().Set(disableSSHAuthFlag, "false"))
-		assert.False(t, wantsDangerousSSH(c))
-	})
-
-	t.Run("nothing changed is not dangerous", func(t *testing.T) {
-		c := newCmd()
-		assert.False(t, wantsDangerousSSH(c))
-	})
-}

client/cmd/elevate_windows.go

@@ -1,23 +0,0 @@
-//go:build windows
-
-package cmd
-
-import (
-	"fmt"
-
-	"golang.org/x/sys/windows"
-)
-
-// isProcessPrivileged reports whether the current process token is elevated
-// (running as administrator / LocalSystem).
-func isProcessPrivileged() bool {
-	return windows.GetCurrentProcessToken().IsElevated()
-}
-
-// runElevated should re-run exe with args elevated via a UAC prompt
-// (ShellExecuteEx with the "runas" verb).
-//
-// TODO(ssh-elevation): implement ShellExecuteEx("runas") + wait for the child.
-func runElevated(_ string, _ []string) error {
-	return fmt.Errorf("automatic privilege elevation is not yet implemented on Windows, re-run netbird as administrator")
-}

client/cmd/login.go

@@ -17,9 +17,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	nbnet "github.com/netbirdio/netbird/client/net"
 	"github.com/netbirdio/netbird/client/proto"
-	"github.com/netbirdio/netbird/client/server"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/util"
 )
@@ -333,14 +331,6 @@ func doForegroundLogin(ctx context.Context, cmd *cobra.Command, setupKey string,
 		return fmt.Errorf("read config file %s: %v", configFilePath, err)
 	}
 
-	// Mirror runInForegroundMode: recover residual state (DNS, firewall,
-	// ssh config, legacy routing) from a previous unclean shutdown and
-	// enable advanced routing before dialing management.
-	if err := server.RestoreResidualState(ctx, profilemanager.NewServiceManager(configFilePath).GetStatePath()); err != nil {
-		log.Warnf("failed to restore residual state: %v", err)
-	}
-	nbnet.Init()
-
 	err = foregroundLogin(ctx, cmd, config, setupKey, activeProf.ID)
 	if err != nil {
 		return fmt.Errorf("foreground login failed: %v", err)

client/cmd/owner.go

@@ -1,116 +0,0 @@
-package cmd
-
-import (
-	"context"
-	"time"
-
-	log "github.com/sirupsen/logrus"
-	"github.com/spf13/cobra"
-
-	"github.com/netbirdio/netbird/client/proto"
-	"github.com/netbirdio/netbird/util"
-)
-
-var ownerCmd = &cobra.Command{
-	Use:   "owner",
-	Short: "Manage who may control the NetBird daemon",
-	Long: `Manage the daemon-wide owners.
-
-Owners are enforced on the daemon and stored in the service parameters. All owners
-may control the daemon and use the shared default profile (plus root/administrator),
-every other profile stays isolated to the user that created it. An unowned daemon
-is claimed by the first caller (trust-on-first-use).`,
-}
-
-var ownerAddCmd = &cobra.Command{
-	Use:   "add <principal>",
-	Short: "Add a daemon owner principal",
-	Long: `Add a daemon-wide owner principal. Principals are typed:
-  uid:1000               a Unix user ID
-  gid:1000               a Unix group ID
-  group:netbird-admins   a Unix group name (resolved via NSS/getent)
-  sid:S-1-5-21-...       a Windows user or group SID
-
-Requires root/administrator or an existing owner.`,
-	Args: cobra.ExactArgs(1),
-	RunE: func(cmd *cobra.Command, args []string) error {
-		return withDaemon(cmd, func(ctx context.Context, c proto.DaemonServiceClient) error {
-			if _, err := c.AddOwner(ctx, &proto.AddOwnerRequest{Principal: args[0]}); err != nil {
-				return err
-			}
-			cmd.Printf("Added daemon owner %q\n", args[0])
-			return nil
-		})
-	},
-}
-
-var ownerResetCmd = &cobra.Command{
-	Use:   "reset",
-	Short: "Clear the daemon owner list (root/administrator only)",
-	Long: `Clear the daemon-wide owner list, returning the daemon to the unowned
-state. The next caller then claims ownership (trust-on-first-use). Requires
-root/administrator.`,
-	RunE: func(cmd *cobra.Command, args []string) error {
-		return withDaemon(cmd, func(ctx context.Context, c proto.DaemonServiceClient) error {
-			if _, err := c.ResetOwner(ctx, &proto.ResetOwnerRequest{}); err != nil {
-				return err
-			}
-			cmd.Println("Daemon owner list cleared, the next caller will claim ownership")
-			return nil
-		})
-	},
-}
-
-var ownerShareCmd = &cobra.Command{
-	Use:   "share",
-	Short: "Mark the daemon shared (any local user may control it)",
-	RunE: func(cmd *cobra.Command, args []string) error {
-		return withDaemon(cmd, func(ctx context.Context, c proto.DaemonServiceClient) error {
-			if _, err := c.ShareProfile(ctx, &proto.ShareProfileRequest{Shared: true}); err != nil {
-				return err
-			}
-			cmd.Println("Daemon is now shared with all local users")
-			return nil
-		})
-	},
-}
-
-var ownerUnshareCmd = &cobra.Command{
-	Use:   "unshare",
-	Short: "Stop sharing the daemon (restrict to its owners)",
-	RunE: func(cmd *cobra.Command, args []string) error {
-		return withDaemon(cmd, func(ctx context.Context, c proto.DaemonServiceClient) error {
-			if _, err := c.ShareProfile(ctx, &proto.ShareProfileRequest{Shared: false}); err != nil {
-				return err
-			}
-			cmd.Println("Daemon is no longer shared")
-			return nil
-		})
-	},
-}
-
-// withDaemon runs fn with a connected daemon client, handling setup and teardown.
-func withDaemon(cmd *cobra.Command, fn func(context.Context, proto.DaemonServiceClient) error) error {
-	SetFlagsFromEnvVars(rootCmd)
-	cmd.SetOut(cmd.OutOrStdout())
-	if err := util.InitLog(logLevel, util.LogConsole); err != nil {
-		log.Errorf("failed initializing log %v", err)
-		return err
-	}
-
-	ctx, cancel := context.WithTimeout(cmd.Context(), 20*time.Second)
-	defer cancel()
-
-	conn, err := DialClientGRPCServer(ctx, daemonAddr)
-	if err != nil {
-		log.Errorf("failed to connect to service CLI interface %v", err)
-		return err
-	}
-	defer func() {
-		if cerr := conn.Close(); cerr != nil {
-			log.Debugf("close daemon connection: %v", cerr)
-		}
-	}()
-
-	return fn(ctx, proto.NewDaemonServiceClient(conn))
-}

client/cmd/profile.go

@@ -117,12 +117,10 @@ func listProfilesFunc(cmd *cobra.Command, _ []string) error {
 	} else {
 		fmt.Fprintln(tw, "NAME\tACTIVE")
 	}
-	anyActive := false
 	for _, profile := range resp.Profiles {
 		marker := ""
 		if profile.IsActive {
 			marker = "✓"
-			anyActive = true
 		}
 		name := profilemanager.StripCtrlChars(profile.Name)
 		id := profilemanager.ID(profile.Id)
@@ -132,19 +130,7 @@ func listProfilesFunc(cmd *cobra.Command, _ []string) error {
 			fmt.Fprintf(tw, "%s\t%s\n", name, marker)
 		}
 	}
-	if err := tw.Flush(); err != nil {
-		return err
-	}
-
-	// None of the caller's profiles is active: another user may hold the daemon.
-	// Surface it so the empty ACTIVE column is not mistaken for "nothing active".
-	if !anyActive {
-		if active, aerr := daemonClient.GetActiveProfile(cmd.Context(), &proto.GetActiveProfileRequest{}); aerr == nil && active.GetUsername() != "" && !usernamesMatch(active.GetUsername(), currUser.Username) {
-			cmd.Printf("\nActive profile belongs to another user: %s (user %s)\n",
-				profilemanager.StripCtrlChars(active.GetProfileName()), active.GetUsername())
-		}
-	}
-	return nil
+	return tw.Flush()
 }
 
 func addProfileFunc(cmd *cobra.Command, args []string) error {

client/cmd/root.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
-	"net"
 	"os"
 	"os/signal"
 	"path"
@@ -72,14 +71,12 @@ var (
 	extraIFaceBlackList     []string
 	anonymizeFlag           bool
 	dnsRouteInterval        time.Duration
-	// lazyConnEnabled is the parse target for the deprecated --enable-lazy-connection
-	// flag. The flag is inert; the value is no longer read (use NB_LAZY_CONN instead).
-	lazyConnEnabled        bool
-	mtu                    uint16
-	profilesDisabled       bool
-	updateSettingsDisabled bool
-	captureEnabled         bool
-	networksDisabled       bool
+	lazyConnEnabled         bool
+	mtu                     uint16
+	profilesDisabled        bool
+	updateSettingsDisabled  bool
+	captureEnabled          bool
+	networksDisabled        bool
 
 	rootCmd = &cobra.Command{
 		Use:          "netbird",
@@ -144,10 +141,10 @@ func init() {
 
 	defaultDaemonAddr := "unix:///var/run/netbird.sock"
 	if runtime.GOOS == "windows" {
-		defaultDaemonAddr = windowsPipeDaemonAddr
+		defaultDaemonAddr = "tcp://127.0.0.1:41731"
 	}
 
-	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]")
+	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]")
 	rootCmd.PersistentFlags().StringVarP(&managementURL, "management-url", "m", "", fmt.Sprintf("Management Service URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultManagementURL))
 	rootCmd.PersistentFlags().StringVar(&adminURL, "admin-url", "", fmt.Sprintf("Admin Panel URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultAdminURL))
 	rootCmd.PersistentFlags().StringVarP(&logLevel, "log-level", "l", "info", "sets NetBird log level")
@@ -173,11 +170,6 @@ func init() {
 	rootCmd.AddCommand(profileCmd)
 	rootCmd.AddCommand(exposeCmd)
 
-	rootCmd.AddCommand(ownerCmd)
-	ownerCmd.AddCommand(ownerAddCmd, ownerResetCmd, ownerShareCmd, ownerUnshareCmd)
-
-	rootCmd.AddCommand(setSSHConfigCmd)
-
 	networksCMD.AddCommand(routesListCmd)
 	networksCMD.AddCommand(routesSelectCmd, routesDeselectCmd)
 
@@ -218,8 +210,7 @@ func init() {
 	upCmd.PersistentFlags().BoolVar(&rosenpassEnabled, enableRosenpassFlag, false, "[Experimental] Enable Rosenpass feature. If enabled, the connection will be post-quantum secured via Rosenpass.")
 	upCmd.PersistentFlags().BoolVar(&rosenpassPermissive, rosenpassPermissiveFlag, false, "[Experimental] Enable Rosenpass in permissive mode to allow this peer to accept WireGuard connections without requiring Rosenpass functionality from peers that do not have Rosenpass enabled.")
 	upCmd.PersistentFlags().BoolVar(&autoConnectDisabled, disableAutoConnectFlag, false, "Disables auto-connect feature. If enabled, then the client won't connect automatically when the service starts.")
-	upCmd.PersistentFlags().BoolVar(&lazyConnEnabled, enableLazyConnectionFlag, false, "Deprecated: no longer used. Lazy connections are controlled by the server and the NB_LAZY_CONN environment variable.")
-	_ = upCmd.PersistentFlags().MarkDeprecated(enableLazyConnectionFlag, "no longer used; lazy connections are controlled by the server and the NB_LAZY_CONN environment variable")
+	upCmd.PersistentFlags().BoolVar(&lazyConnEnabled, enableLazyConnectionFlag, false, "[Experimental] Enable the lazy connection feature. If enabled, the client will establish connections on-demand. Note: this setting may be overridden by management configuration.")
 
 }
 
@@ -270,32 +261,17 @@ func FlagNameToEnvVar(cmdFlag string, prefix string) string {
 	return prefix + upper
 }
 
-// daemonDialTarget returns the gRPC dial target and base options for the daemon
-// address, handling the npipe scheme (Windows named pipe, via a context dialer)
-// and unix/tcp.
-func daemonDialTarget(addr string) (string, []grpc.DialOption) {
-	opts := []grpc.DialOption{grpc.WithTransportCredentials(insecure.NewCredentials())}
-	target := strings.TrimPrefix(addr, "tcp://")
-	if strings.HasPrefix(addr, "npipe://") {
-		path := pipePath(strings.TrimPrefix(addr, "npipe://"))
-		opts = append(opts, grpc.WithContextDialer(func(dialCtx context.Context, _ string) (net.Conn, error) {
-			return dialNamedPipe(dialCtx, path)
-		}))
-		target = "passthrough:///netbird-daemon-pipe"
-	}
-	return target, opts
-}
-
 // DialClientGRPCServer returns client connection to the daemon server.
-func DialClientGRPCServer(ctx context.Context, addr string, opts ...grpc.DialOption) (*grpc.ClientConn, error) {
+func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, error) {
 	ctx, cancel := context.WithTimeout(ctx, time.Second*10)
 	defer cancel()
 
-	target, dialOpts := daemonDialTarget(addr)
-	dialOpts = append(dialOpts, grpc.WithBlock())
-	dialOpts = append(dialOpts, opts...)
-
-	return grpc.DialContext(ctx, target, dialOpts...)
+	return grpc.DialContext(
+		ctx,
+		strings.TrimPrefix(addr, "tcp://"),
+		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithBlock(),
+	)
 }
 
 // WithBackOff execute function in backoff cycle.

client/cmd/service.go

@@ -5,7 +5,6 @@ package cmd
 import (
 	"context"
 	"fmt"
-	"net/http"
 	"runtime"
 	"strings"
 	"sync"
@@ -23,27 +22,15 @@ var serviceCmd = &cobra.Command{
 	Short: "Manage the NetBird daemon service",
 }
 
-const defaultJSONSocket = "unix:///var/run/netbird-http.sock"
-
 var (
-	serviceName      string
-	serviceEnvVars   []string
-	jsonSocket       string
-	enableJSONSocket bool
-	// owners seeds the daemon-wide owner set at install time (--owner). At runtime
-	// the daemon reads and writes owners in service.json directly.
-	owners []string
-	// daemonShared carries the persisted daemon shared flag across
-	// install/reconfigure round-trips (set at runtime via `netbird owner share`).
-	daemonShared bool
+	serviceName    string
+	serviceEnvVars []string
 )
 
 type program struct {
 	ctx              context.Context
 	cancel           context.CancelFunc
 	serv             *grpc.Server
-	jsonServ         *http.Server
-	jsonServMu       sync.Mutex
 	serverInstance   *server.Server
 	serverInstanceMu sync.Mutex
 }
@@ -59,9 +46,6 @@ func init() {
 	serviceCmd.PersistentFlags().BoolVar(&updateSettingsDisabled, "disable-update-settings", false, "Disables update settings feature. If enabled, the client will not be able to change or edit any settings. To persist this setting, use: netbird service install --disable-update-settings")
 	serviceCmd.PersistentFlags().BoolVar(&captureEnabled, "enable-capture", false, "Enables packet capture via 'netbird debug capture'. To persist, use: netbird service install --enable-capture")
 	serviceCmd.PersistentFlags().BoolVar(&networksDisabled, "disable-networks", false, "Disables network selection. If enabled, the client will not allow listing, selecting, or deselecting networks. To persist, use: netbird service install --disable-networks")
-	serviceCmd.PersistentFlags().BoolVar(&enableJSONSocket, "enable-json-socket", false, "Enables the HTTP/JSON API socket served by grpc-gateway. To persist, use: netbird service install --enable-json-socket")
-	serviceCmd.PersistentFlags().StringVar(&jsonSocket, "json-socket", defaultJSONSocket, "HTTP/JSON API socket address [unix|tcp|npipe]://[path|host:port|name]. Requires --enable-json-socket to serve. To persist, use: netbird service install --enable-json-socket --json-socket")
-	serviceCmd.PersistentFlags().StringSliceVar(&owners, "owner", nil, "Principal(s) allowed to control the daemon and its default profile: uid:1000, gid:1000, group:netbird-admins (NSS), or sid:S-1-5-... (Windows). Repeatable. Other profiles stay isolated per user. To persist: netbird service install --owner uid:1000")
 
 	rootCmd.PersistentFlags().StringVarP(&serviceName, "service", "s", defaultServiceName, "Netbird system service name")
 	serviceEnvDesc := `Sets extra environment variables for the service. ` +

client/cmd/service_controller.go

@@ -5,7 +5,9 @@ package cmd
 import (
 	"context"
 	"fmt"
-	"runtime"
+	"net"
+	"os"
+	"strings"
 	"time"
 
 	"github.com/kardianos/service"
@@ -14,131 +16,63 @@ import (
 	"github.com/spf13/cobra"
 	"google.golang.org/grpc"
 
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/server"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/util"
 )
 
-// daemonServerOptions installs peer-identity transport credentials and the
-// authorization interceptor on the daemon ipc if supported.
-func daemonServerOptions(network string, interceptor *ipcauth.Interceptor) []grpc.ServerOption {
-	creds := ipcauth.NewTransportCredentials()
-	if creds == nil {
-		log.Warnf("daemon ipc has no peer-identity primitive on %s, per-caller authorization is disabled", runtime.GOOS)
-		return nil
-	}
-	if network == "tcp" {
-		log.Warnf("daemon is listening on TCP (%s), peer identity cannot be authenticated over TCP, per-caller authorization is disabled", daemonAddr)
-		return nil
-	}
-	return []grpc.ServerOption{
-		grpc.Creds(creds),
-		grpc.ChainUnaryInterceptor(interceptor.UnaryServerInterceptor()),
-		grpc.ChainStreamInterceptor(interceptor.StreamServerInterceptor()),
-	}
-}
-
-func validateJSONSocketFlags() error {
-	if serviceCmd.PersistentFlags().Changed("json-socket") && !enableJSONSocket {
-		return fmt.Errorf("--json-socket requires --enable-json-socket to configure the daemon JSON gateway")
-	}
-	return nil
-}
-
 func (p *program) Start(svc service.Service) error {
 	// Start should not block. Do the actual work async.
 	log.Info("starting NetBird service") //nolint
 
-	if err := validateJSONSocketFlags(); err != nil {
-		return err
-	}
-
 	// Collect static system and platform information
 	system.UpdateStaticInfoAsync()
 
-	// A daemon installed before named-pipe support uses the old loopback-TCP
-	// address as the daemon address. We migrate to a named pipe so an
-	// upgraded daemon enforces per-caller authorization instead of silently
-	// running on identity-less TCP.
-	if migrated, ok := migrateLegacyDaemonAddr(daemonAddr); ok {
-		log.Infof("legacy daemon address %q predates named-pipe support. listening on %q so per-caller authorization is enforced", daemonAddr, migrated)
-		daemonAddr = migrated
+	// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
+	p.serv = grpc.NewServer()
+
+	split := strings.Split(daemonAddr, "://")
+	switch split[0] {
+	case "unix":
+		// cleanup failed close
+		stat, err := os.Stat(split[1])
+		if err == nil && !stat.IsDir() {
+			if err := os.Remove(split[1]); err != nil {
+				log.Debugf("remove socket file: %v", err)
+			}
+		}
+	case "tcp":
+	default:
+		return fmt.Errorf("unsupported daemon address protocol: %v", split[0])
 	}
 
-	network, _, err := parseListenAddress(daemonAddr)
-	if err != nil {
-		return fmt.Errorf("parse daemon address: %w", err)
-	}
-
-	// Owner-authorization interceptor. The ConfigAdapter is a lazy bridge: the
-	// gRPC server is built before the daemon server instance exists, so we set
-	// the real policy backend below once serverInstance is created.
-	ownerAdapter := &ipcauth.ConfigAdapter{}
-	authInterceptor := ipcauth.NewInterceptor(ownerAdapter, ipcauth.NewDefaultGroupResolver())
-
-	// in any case, even if configuration does not exist we run daemon to serve the CLI gRPC API.
-	p.serv = grpc.NewServer(daemonServerOptions(network, authInterceptor)...)
-
-	daemonListener, err := listenOnAddress(daemonAddr)
+	listen, err := net.Listen(split[0], split[1])
 	if err != nil {
 		return fmt.Errorf("listen daemon interface: %w", err)
 	}
-
-	var jsonListener *socketListener
-	if enableJSONSocket {
-		jsonListener, err = listenOnAddress(jsonSocket)
-		if err != nil {
-			_ = daemonListener.Close()
-			return fmt.Errorf("listen daemon JSON interface: %w", err)
-		}
-	} else {
-		removeStaleUnixSocketForAddress(jsonSocket)
-	}
-
 	go func() {
-		defer daemonListener.Close()
-		if jsonListener != nil {
-			defer jsonListener.Close()
-		}
+		defer listen.Close()
 
-		if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
-			log.Error(err)
-			return
-		}
-		if jsonListener != nil {
-			if err := jsonListener.chmodUnixSocket("daemon JSON"); err != nil {
-				log.Error(err)
+		if split[0] == "unix" {
+			if err := os.Chmod(split[1], 0666); err != nil {
+				log.Errorf("failed setting daemon permissions: %v", split[1])
 				return
 			}
 		}
 
 		serverInstance := server.New(p.ctx, util.FindFirstLogPath(logFiles), configPath, profilesDisabled, updateSettingsDisabled, captureEnabled, networksDisabled)
-		// Daemon-wide owners live in service.json (governs the default profile and
-		// daemon access), wire persistence before serving so owner add / TOFU work.
-		serverInstance.SetDaemonOwnerStore(daemonOwnerStore{})
 		if err := serverInstance.Start(); err != nil {
 			log.Fatalf("failed to start daemon: %v", err)
 		}
-		ownerAdapter.SetBackend(serverInstance)
 		proto.RegisterDaemonServiceServer(p.serv, serverInstance)
 
 		p.serverInstanceMu.Lock()
 		p.serverInstance = serverInstance
 		p.serverInstanceMu.Unlock()
 
-		if jsonListener != nil {
-			log.Warnf("JSON gateway (--enable-json-socket) re-dials the daemon locally. The HTTP client's identity is forwarded so per-caller authorization still applies, but restrict access to %s appropriately", jsonSocket)
-			if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
-				log.Fatalf("failed to start daemon JSON server: %v", err)
-			}
-		} else {
-			log.Debug("daemon JSON socket disabled")
-		}
-
-		log.Printf("started daemon server: %v", daemonListener.address)
-		if err := p.serv.Serve(daemonListener.Listener); err != nil {
+		log.Printf("started daemon server: %v", split[1])
+		if err := p.serv.Serve(listen); err != nil {
 			log.Errorf("failed to serve daemon requests: %v", err)
 		}
 	}()
@@ -158,20 +92,6 @@ func (p *program) Stop(srv service.Service) error {
 
 	p.cancel()
 
-	p.jsonServMu.Lock()
-	jsonServ := p.jsonServ
-	p.jsonServMu.Unlock()
-	if jsonServ != nil {
-		shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 2*time.Second)
-		if err := jsonServ.Shutdown(shutdownCtx); err != nil {
-			log.Errorf("failed to stop daemon JSON server gracefully: %v", err)
-			if err := jsonServ.Close(); err != nil {
-				log.Errorf("failed to close daemon JSON server: %v", err)
-			}
-		}
-		shutdownCancel()
-	}
-
 	if p.serv != nil {
 		p.serv.Stop()
 	}
@@ -228,9 +148,6 @@ var runCmd = &cobra.Command{
 		if err != nil {
 			return err
 		}
-		if err := validateJSONSocketFlags(); err != nil {
-			return err
-		}
 
 		return s.Run()
 	},
@@ -245,9 +162,6 @@ var startCmd = &cobra.Command{
 		if err != nil {
 			return err
 		}
-		if err := validateJSONSocketFlags(); err != nil {
-			return err
-		}
 
 		if err := s.Start(); err != nil {
 			return fmt.Errorf("start service: %w", err)
@@ -284,9 +198,6 @@ var restartCmd = &cobra.Command{
 		if err != nil {
 			return err
 		}
-		if err := validateJSONSocketFlags(); err != nil {
-			return err
-		}
 
 		if err := s.Restart(); err != nil {
 			return fmt.Errorf("restart service: %w", err)

client/cmd/service_installer.go

@@ -67,10 +67,6 @@ func buildServiceArguments() []string {
 		args = append(args, "--disable-networks")
 	}
 
-	if enableJSONSocket {
-		args = append(args, "--enable-json-socket", "--json-socket", jsonSocket)
-	}
-
 	return args
 }
 
@@ -110,10 +106,6 @@ func configurePlatformSpecificSettings(svcConfig *service.Config) error {
 
 // Create fully configured service config for install/reconfigure
 func createServiceConfigForInstall() (*service.Config, error) {
-	if err := validateJSONSocketFlags(); err != nil {
-		return nil, err
-	}
-
 	svcConfig, err := newSVCConfig()
 	if err != nil {
 		return nil, fmt.Errorf("create service config: %w", err)

client/cmd/service_json_gateway.go

@@ -1,88 +0,0 @@
-//go:build !ios && !android
-
-package cmd
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"net"
-	"net/http"
-	"time"
-
-	"github.com/grpc-ecosystem/grpc-gateway/v2/runtime"
-	log "github.com/sirupsen/logrus"
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/metadata"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-	"github.com/netbirdio/netbird/client/proto"
-)
-
-// jsonPeerCtxKey keys the HTTP client's kernel identity in the request context.
-type jsonPeerCtxKey struct{}
-
-// jsonConnContext reads the connecting HTTP client's identity from the JSON
-// socket and stashes it so it can be forwarded to the daemon. The gateway
-// re-dials the daemon as the daemon's own identity, so without this the
-// daemon would see every JSON request as privileged.
-func jsonConnContext(ctx context.Context, c net.Conn) context.Context {
-	id, err := ipcauth.ConnIdentity(c)
-	if err != nil {
-		log.Warnf("json gateway: cannot read HTTP client identity, requests won't carry it: %v", err)
-		return ctx
-	}
-	return context.WithValue(ctx, jsonPeerCtxKey{}, id)
-}
-
-// jsonForwardIdentity injects the stashed HTTP client identity as gRPC metadata
-// on the gateway's re-dial to the daemon. The daemon trusts it only because the
-// dial arrives as the daemon's own (self/privileged) identity.
-func jsonForwardIdentity(ctx context.Context, _ *http.Request) metadata.MD {
-	id, ok := ctx.Value(jsonPeerCtxKey{}).(ipcauth.Identity)
-	if !ok {
-		return nil
-	}
-	return ipcauth.ForwardIdentityMetadata(id)
-}
-
-func (p *program) startJSONGateway(jsonListener *socketListener, daemonEndpoint string) error {
-	if jsonListener.network == "tcp" {
-		log.Warnf("json daemon is listening on TCP (%s), peer identity cannot be authenticated over TCP, per-caller authorization is disabled", daemonAddr)
-	}
-
-	mux := runtime.NewServeMux(runtime.WithMetadata(jsonForwardIdentity))
-
-	// Lazy client to the daemon, npipe-aware (grpc.NewClient does not connect
-	// until the first request, so this does not block startup before Serve).
-	target, opts := daemonDialTarget(daemonEndpoint)
-	conn, err := grpc.NewClient(target, opts...)
-	if err != nil {
-		return fmt.Errorf("create daemon client for JSON gateway: %w", err)
-	}
-	if err := proto.RegisterDaemonServiceHandler(p.ctx, mux, conn); err != nil {
-		return err
-	}
-
-	jsonServer := &http.Server{
-		Handler:           mux,
-		ReadHeaderTimeout: 5 * time.Second,
-		BaseContext: func(net.Listener) context.Context {
-			return p.ctx
-		},
-		ConnContext: jsonConnContext,
-	}
-
-	p.jsonServMu.Lock()
-	p.jsonServ = jsonServer
-	p.jsonServMu.Unlock()
-
-	go func() {
-		log.Printf("started daemon JSON server: %v", jsonListener.address)
-		if err := jsonServer.Serve(jsonListener.Listener); err != nil && !errors.Is(err, http.ErrServerClosed) {
-			log.Errorf("failed to serve daemon JSON requests: %v", err)
-		}
-	}()
-
-	return nil
-}

client/cmd/service_json_socket_test.go

@@ -1,176 +0,0 @@
-//go:build !ios && !android
-
-package cmd
-
-import (
-	"net"
-	"os"
-	"path/filepath"
-	"runtime"
-	"testing"
-
-	"github.com/spf13/cobra"
-	"github.com/spf13/pflag"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-func preserveJSONSocketTestState(t *testing.T) {
-	t.Helper()
-
-	origJSONSocket := jsonSocket
-	origEnableJSONSocket := enableJSONSocket
-	origChanged := map[string]bool{}
-	serviceCmd.PersistentFlags().VisitAll(func(flag *pflag.Flag) {
-		origChanged[flag.Name] = flag.Changed
-	})
-
-	t.Cleanup(func() {
-		jsonSocket = origJSONSocket
-		enableJSONSocket = origEnableJSONSocket
-		serviceCmd.PersistentFlags().VisitAll(func(flag *pflag.Flag) {
-			flag.Changed = origChanged[flag.Name]
-		})
-	})
-}
-
-func TestJSONSocketFlagsArePositiveEnableOnly(t *testing.T) {
-	assert.NotNil(t, serviceCmd.PersistentFlags().Lookup("enable-json-socket"))
-	assert.NotNil(t, serviceCmd.PersistentFlags().Lookup("json-socket"))
-	assert.Nil(t, serviceCmd.PersistentFlags().Lookup("disable-json-socket"))
-	assert.Equal(t, "false", serviceCmd.PersistentFlags().Lookup("enable-json-socket").DefValue)
-}
-
-func TestBuildServiceArgumentsDefaultDisablesJSONSocket(t *testing.T) {
-	preserveJSONSocketTestState(t)
-
-	enableJSONSocket = false
-	jsonSocket = "tcp://127.0.0.1:8080"
-
-	args := buildServiceArguments()
-
-	assert.NotContains(t, args, "--enable-json-socket")
-	assert.NotContains(t, args, "--json-socket")
-}
-
-func TestBuildServiceArgumentsIncludesJSONSocketWhenEnabled(t *testing.T) {
-	preserveJSONSocketTestState(t)
-
-	enableJSONSocket = true
-	jsonSocket = "tcp://127.0.0.1:8080"
-
-	args := buildServiceArguments()
-
-	enableIndex := indexOfArg(args, "--enable-json-socket")
-	jsonIndex := indexOfArg(args, "--json-socket")
-	require.NotEqual(t, -1, enableIndex)
-	require.NotEqual(t, -1, jsonIndex)
-	require.Less(t, enableIndex, jsonIndex)
-	require.Less(t, jsonIndex+1, len(args))
-	assert.Equal(t, "tcp://127.0.0.1:8080", args[jsonIndex+1])
-}
-
-func TestJSONSocketWithoutEnableValidation(t *testing.T) {
-	preserveJSONSocketTestState(t)
-
-	enableJSONSocket = false
-	require.NoError(t, serviceCmd.PersistentFlags().Set("json-socket", "tcp://127.0.0.1:8080"))
-
-	err := validateJSONSocketFlags()
-
-	require.Error(t, err)
-	assert.Contains(t, err.Error(), "--enable-json-socket")
-}
-
-func TestJSONSocketWithEnableValidation(t *testing.T) {
-	preserveJSONSocketTestState(t)
-
-	require.NoError(t, serviceCmd.PersistentFlags().Set("enable-json-socket", "true"))
-	require.NoError(t, serviceCmd.PersistentFlags().Set("json-socket", "tcp://127.0.0.1:8080"))
-
-	assert.NoError(t, validateJSONSocketFlags())
-}
-
-func TestJSONSocketServiceParamsPersistEnableAndAddress(t *testing.T) {
-	preserveJSONSocketTestState(t)
-	serviceCmd.PersistentFlags().VisitAll(func(flag *pflag.Flag) {
-		flag.Changed = false
-	})
-
-	enableJSONSocket = true
-	jsonSocket = "tcp://127.0.0.1:8080"
-
-	params := currentServiceParams()
-	require.True(t, params.EnableJSONSocket)
-	require.Equal(t, "tcp://127.0.0.1:8080", params.JSONSocket)
-
-	enableJSONSocket = false
-	jsonSocket = defaultJSONSocket
-	applyServiceParams(testServiceEnvCommand(), params)
-
-	assert.True(t, enableJSONSocket)
-	assert.Equal(t, "tcp://127.0.0.1:8080", jsonSocket)
-}
-
-func TestRemoveStaleUnixSocketDoesNotRemoveRegularFile(t *testing.T) {
-	path := filepath.Join(t.TempDir(), "netbird-http.sock")
-	require.NoError(t, os.WriteFile(path, []byte("not a socket"), 0600))
-
-	removeStaleUnixSocket(path)
-
-	data, err := os.ReadFile(path)
-	require.NoError(t, err)
-	assert.Equal(t, []byte("not a socket"), data)
-}
-
-func TestRemoveStaleUnixSocketRemovesSocket(t *testing.T) {
-	if runtime.GOOS == "windows" {
-		t.Skip("unix sockets are not available on Windows")
-	}
-
-	path := filepath.Join(t.TempDir(), "netbird-http.sock")
-	addr := &net.UnixAddr{Name: path, Net: "unix"}
-	listener, err := net.ListenUnix("unix", addr)
-	require.NoError(t, err)
-	listener.SetUnlinkOnClose(false)
-	require.NoError(t, listener.Close())
-
-	_, err = os.Lstat(path)
-	require.NoError(t, err, "test setup must leave a stale Unix socket path")
-
-	removeStaleUnixSocket(path)
-
-	_, err = os.Lstat(path)
-	assert.True(t, os.IsNotExist(err), "expected stale Unix socket to be removed, got %v", err)
-}
-
-func TestRemoveStaleUnixSocketDoesNotRemoveLiveSocket(t *testing.T) {
-	if runtime.GOOS == "windows" {
-		t.Skip("unix sockets are not available on Windows")
-	}
-
-	path := filepath.Join(t.TempDir(), "netbird-http.sock")
-	listener, err := net.Listen("unix", path)
-	require.NoError(t, err)
-	defer listener.Close()
-
-	removeStaleUnixSocket(path)
-
-	_, err = os.Lstat(path)
-	assert.NoError(t, err, "expected live Unix socket to be preserved")
-}
-
-func testServiceEnvCommand() *cobra.Command {
-	cmd := &cobra.Command{}
-	cmd.Flags().StringSlice("service-env", nil, "")
-	return cmd
-}
-
-func indexOfArg(args []string, arg string) int {
-	for i, candidate := range args {
-		if candidate == arg {
-			return i
-		}
-	}
-	return -1
-}

client/cmd/service_params.go

@@ -23,7 +23,6 @@ const serviceParamsFile = "service.json"
 type serviceParams struct {
 	LogLevel              string            `json:"log_level"`
 	DaemonAddr            string            `json:"daemon_addr"`
-	JSONSocket            string            `json:"json_socket"`
 	ManagementURL         string            `json:"management_url,omitempty"`
 	ConfigPath            string            `json:"config_path,omitempty"`
 	LogFiles              []string          `json:"log_files,omitempty"`
@@ -31,17 +30,7 @@ type serviceParams struct {
 	DisableUpdateSettings bool              `json:"disable_update_settings,omitempty"`
 	EnableCapture         bool              `json:"enable_capture,omitempty"`
 	DisableNetworks       bool              `json:"disable_networks,omitempty"`
-	EnableJSONSocket      bool              `json:"enable_json_socket,omitempty"`
 	ServiceEnvVars        map[string]string `json:"service_env_vars,omitempty"`
-	// Owners lists the principals allowed to control this profile over the local
-	// IPC, as typed strings: "uid:1000", "gid:1000", "group:netbird-admins"
-	// (Unix, NSS-resolved) or "sid:S-1-5-..." (Windows user or group SID). Empty
-	// with Shared=false means the profile is owned by nobody yet, until claimed
-	Owners []string `json:"owners,omitempty"`
-
-	// Shared, when true, lets any authenticated local caller control this profile
-	// (opt-in). Takes precedence over Owners.
-	Shared bool `json:"shared,omitempty"`
 }
 
 // serviceParamsPath returns the path to the service params file.
@@ -49,38 +38,6 @@ func serviceParamsPath() string {
 	return filepath.Join(configs.StateDir, serviceParamsFile)
 }
 
-// daemonOwnerStore persists the daemon-wide owner set in service.json. It
-// implements server.DaemonOwnerStore so the daemon can read owners at startup and
-// mutate them at runtime (owner add, reset, share, TOFU claim) without server
-// importing cmd. Load-modify-write preserves the other service.json fields.
-type daemonOwnerStore struct{}
-
-func (daemonOwnerStore) Load() ([]string, bool, error) {
-	params, err := loadServiceParams()
-	if err != nil {
-		return nil, false, err
-	}
-	if params == nil {
-		return nil, false, nil
-	}
-	return params.Owners, params.Shared, nil
-}
-
-func (daemonOwnerStore) Save(owners []string, shared bool) error {
-	params, err := loadServiceParams()
-	if err != nil {
-		return err
-	}
-	if params == nil {
-		// No service.json yet (daemon started without `service install`). Seed it
-		// from the running daemon's current parameters so the file stays complete.
-		params = currentServiceParams()
-	}
-	params.Owners = owners
-	params.Shared = shared
-	return saveServiceParams(params)
-}
-
 // loadServiceParams reads saved service parameters from disk.
 // Returns nil with no error if the file does not exist.
 func loadServiceParams() (*serviceParams, error) {
@@ -118,7 +75,6 @@ func currentServiceParams() *serviceParams {
 	params := &serviceParams{
 		LogLevel:              logLevel,
 		DaemonAddr:            daemonAddr,
-		JSONSocket:            jsonSocket,
 		ManagementURL:         managementURL,
 		ConfigPath:            configPath,
 		LogFiles:              logFiles,
@@ -126,9 +82,6 @@ func currentServiceParams() *serviceParams {
 		DisableUpdateSettings: updateSettingsDisabled,
 		EnableCapture:         captureEnabled,
 		DisableNetworks:       networksDisabled,
-		EnableJSONSocket:      enableJSONSocket,
-		Owners:                owners,
-		Shared:                daemonShared,
 	}
 
 	if len(serviceEnvVars) > 0 {
@@ -160,26 +113,15 @@ func applyServiceParams(cmd *cobra.Command, params *serviceParams) {
 		return
 	}
 
-	// For fields with non-empty defaults, keep the != "" guard so that an older
-	// service.json missing the field doesn't clobber the default with an empty string.
+	// For fields with non-empty defaults (log-level, daemon-addr), keep the
+	// != "" guard so that an older service.json missing the field doesn't
+	// clobber the default with an empty string.
 	if !rootCmd.PersistentFlags().Changed("log-level") && params.LogLevel != "" {
 		logLevel = params.LogLevel
 	}
 
 	if !rootCmd.PersistentFlags().Changed("daemon-addr") && params.DaemonAddr != "" {
 		daemonAddr = params.DaemonAddr
-		if migrated, ok := migrateLegacyDaemonAddr(daemonAddr); ok {
-			cmd.Printf("Migrating saved daemon address %q to %q so per-caller authorization can be enforced\n", daemonAddr, migrated)
-			daemonAddr = migrated
-		}
-	}
-
-	if !serviceCmd.PersistentFlags().Changed("json-socket") && params.JSONSocket != "" {
-		jsonSocket = params.JSONSocket
-	}
-
-	if !serviceCmd.PersistentFlags().Changed("enable-json-socket") {
-		enableJSONSocket = params.EnableJSONSocket
 	}
 
 	// For optional fields where empty means "use default", always apply so
@@ -212,14 +154,6 @@ func applyServiceParams(cmd *cobra.Command, params *serviceParams) {
 		networksDisabled = params.DisableNetworks
 	}
 
-	// Carry the daemon-wide owner set forward across install/reconfigure so a
-	// runtime owner add or TOFU claim in service.json is not clobbered. --owner
-	// overrides.
-	if !serviceCmd.PersistentFlags().Changed("owner") && len(params.Owners) > 0 {
-		owners = params.Owners
-	}
-	daemonShared = params.Shared
-
 	applyServiceEnvParams(cmd, params)
 }
 

client/cmd/service_params_test.go

@@ -41,8 +41,6 @@ func TestSaveAndLoadServiceParams(t *testing.T) {
 	params := &serviceParams{
 		LogLevel:              "debug",
 		DaemonAddr:            "unix:///var/run/netbird.sock",
-		JSONSocket:            "tcp://127.0.0.1:8080",
-		EnableJSONSocket:      true,
 		ManagementURL:         "https://my.server.com",
 		ConfigPath:            "/etc/netbird/config.json",
 		LogFiles:              []string{"/var/log/netbird/client.log", "console"},
@@ -65,8 +63,6 @@ func TestSaveAndLoadServiceParams(t *testing.T) {
 
 	assert.Equal(t, params.LogLevel, loaded.LogLevel)
 	assert.Equal(t, params.DaemonAddr, loaded.DaemonAddr)
-	assert.Equal(t, params.JSONSocket, loaded.JSONSocket)
-	assert.Equal(t, params.EnableJSONSocket, loaded.EnableJSONSocket)
 	assert.Equal(t, params.ManagementURL, loaded.ManagementURL)
 	assert.Equal(t, params.ConfigPath, loaded.ConfigPath)
 	assert.Equal(t, params.LogFiles, loaded.LogFiles)
@@ -105,8 +101,6 @@ func TestLoadServiceParams_InvalidJSON(t *testing.T) {
 func TestCurrentServiceParams(t *testing.T) {
 	origLogLevel := logLevel
 	origDaemonAddr := daemonAddr
-	origJSONSocket := jsonSocket
-	origEnableJSONSocket := enableJSONSocket
 	origManagementURL := managementURL
 	origConfigPath := configPath
 	origLogFiles := logFiles
@@ -116,8 +110,6 @@ func TestCurrentServiceParams(t *testing.T) {
 	t.Cleanup(func() {
 		logLevel = origLogLevel
 		daemonAddr = origDaemonAddr
-		jsonSocket = origJSONSocket
-		enableJSONSocket = origEnableJSONSocket
 		managementURL = origManagementURL
 		configPath = origConfigPath
 		logFiles = origLogFiles
@@ -128,8 +120,6 @@ func TestCurrentServiceParams(t *testing.T) {
 
 	logLevel = "trace"
 	daemonAddr = "tcp://127.0.0.1:9999"
-	jsonSocket = "tcp://127.0.0.1:8080"
-	enableJSONSocket = true
 	managementURL = "https://mgmt.example.com"
 	configPath = "/tmp/test-config.json"
 	logFiles = []string{"/tmp/test.log"}
@@ -141,8 +131,6 @@ func TestCurrentServiceParams(t *testing.T) {
 
 	assert.Equal(t, "trace", params.LogLevel)
 	assert.Equal(t, "tcp://127.0.0.1:9999", params.DaemonAddr)
-	assert.Equal(t, "tcp://127.0.0.1:8080", params.JSONSocket)
-	assert.True(t, params.EnableJSONSocket)
 	assert.Equal(t, "https://mgmt.example.com", params.ManagementURL)
 	assert.Equal(t, "/tmp/test-config.json", params.ConfigPath)
 	assert.Equal(t, []string{"/tmp/test.log"}, params.LogFiles)
@@ -154,8 +142,6 @@ func TestCurrentServiceParams(t *testing.T) {
 func TestApplyServiceParams_OnlyUnchangedFlags(t *testing.T) {
 	origLogLevel := logLevel
 	origDaemonAddr := daemonAddr
-	origJSONSocket := jsonSocket
-	origEnableJSONSocket := enableJSONSocket
 	origManagementURL := managementURL
 	origConfigPath := configPath
 	origLogFiles := logFiles
@@ -165,8 +151,6 @@ func TestApplyServiceParams_OnlyUnchangedFlags(t *testing.T) {
 	t.Cleanup(func() {
 		logLevel = origLogLevel
 		daemonAddr = origDaemonAddr
-		jsonSocket = origJSONSocket
-		enableJSONSocket = origEnableJSONSocket
 		managementURL = origManagementURL
 		configPath = origConfigPath
 		logFiles = origLogFiles
@@ -178,8 +162,6 @@ func TestApplyServiceParams_OnlyUnchangedFlags(t *testing.T) {
 	// Reset all flags to defaults.
 	logLevel = "info"
 	daemonAddr = "unix:///var/run/netbird.sock"
-	jsonSocket = defaultJSONSocket
-	enableJSONSocket = false
 	managementURL = ""
 	configPath = "/etc/netbird/config.json"
 	logFiles = []string{"/var/log/netbird/client.log"}
@@ -202,8 +184,6 @@ func TestApplyServiceParams_OnlyUnchangedFlags(t *testing.T) {
 	saved := &serviceParams{
 		LogLevel:              "debug",
 		DaemonAddr:            "tcp://127.0.0.1:5555",
-		JSONSocket:            "tcp://127.0.0.1:8080",
-		EnableJSONSocket:      true,
 		ManagementURL:         "https://saved.example.com",
 		ConfigPath:            "/saved/config.json",
 		LogFiles:              []string{"/saved/client.log"},
@@ -221,8 +201,6 @@ func TestApplyServiceParams_OnlyUnchangedFlags(t *testing.T) {
 
 	// All other fields were not Changed, so they should use saved values.
 	assert.Equal(t, "tcp://127.0.0.1:5555", daemonAddr)
-	assert.Equal(t, "tcp://127.0.0.1:8080", jsonSocket)
-	assert.True(t, enableJSONSocket)
 	assert.Equal(t, "https://saved.example.com", managementURL)
 	assert.Equal(t, "/saved/config.json", configPath)
 	assert.Equal(t, []string{"/saved/client.log"}, logFiles)
@@ -234,17 +212,14 @@ func TestApplyServiceParams_OnlyUnchangedFlags(t *testing.T) {
 func TestApplyServiceParams_BooleanRevertToFalse(t *testing.T) {
 	origProfilesDisabled := profilesDisabled
 	origUpdateSettingsDisabled := updateSettingsDisabled
-	origEnableJSONSocket := enableJSONSocket
 	t.Cleanup(func() {
 		profilesDisabled = origProfilesDisabled
 		updateSettingsDisabled = origUpdateSettingsDisabled
-		enableJSONSocket = origEnableJSONSocket
 	})
 
 	// Simulate current state where booleans are true (e.g. set by previous install).
 	profilesDisabled = true
 	updateSettingsDisabled = true
-	enableJSONSocket = true
 
 	// Reset Changed state so flags appear unset.
 	serviceCmd.PersistentFlags().VisitAll(func(f *pflag.Flag) {
@@ -263,7 +238,6 @@ func TestApplyServiceParams_BooleanRevertToFalse(t *testing.T) {
 
 	assert.False(t, profilesDisabled, "saved false should override current true")
 	assert.False(t, updateSettingsDisabled, "saved false should override current true")
-	assert.False(t, enableJSONSocket, "saved false should override current true")
 }
 
 func TestApplyServiceParams_ClearManagementURL(t *testing.T) {
@@ -431,15 +405,9 @@ func TestServiceParams_BuildArgsCoversAllFlags(t *testing.T) {
 	installerFile, err := parser.ParseFile(fset, "service_installer.go", nil, 0)
 	require.NoError(t, err)
 
-	// Fields that are handled outside of buildServiceArguments.
-	//   - ServiceEnvVars flows through newSVCConfig() EnvVars, not CLI args.
-	//   - Owners/Shared are daemon-wide ownership persisted in service.json and
-	//     read+mutated by the daemon at runtime (owner add / TOFU claim); they are
-	//     deliberately NOT baked into the run args so runtime changes are not lost.
+	// Fields that are handled outside of buildServiceArguments (env vars go through newSVCConfig).
 	fieldsNotInArgs := map[string]bool{
 		"ServiceEnvVars": true,
-		"Owners":         true,
-		"Shared":         true,
 	}
 
 	buildFields := extractFuncGlobalRefs(t, installerFile, "buildServiceArguments")
@@ -562,7 +530,6 @@ func fieldToGlobalVar(field string) string {
 	m := map[string]string{
 		"LogLevel":              "logLevel",
 		"DaemonAddr":            "daemonAddr",
-		"JSONSocket":            "jsonSocket",
 		"ManagementURL":         "managementURL",
 		"ConfigPath":            "configPath",
 		"LogFiles":              "logFiles",
@@ -570,7 +537,6 @@ func fieldToGlobalVar(field string) string {
 		"DisableUpdateSettings": "updateSettingsDisabled",
 		"EnableCapture":         "captureEnabled",
 		"DisableNetworks":       "networksDisabled",
-		"EnableJSONSocket":      "enableJSONSocket",
 		"ServiceEnvVars":        "serviceEnvVars",
 	}
 	if v, ok := m[field]; ok {

client/cmd/service_pipe_other.go

@@ -1,20 +0,0 @@
-//go:build !windows
-
-package cmd
-
-import (
-	"context"
-	"fmt"
-	"net"
-	"runtime"
-)
-
-// listenNamedPipe is unsupported off Windows; named pipes are a Windows-only transport.
-func listenNamedPipe(string) (net.Listener, error) {
-	return nil, fmt.Errorf("named pipe daemon socket is only supported on Windows, not %s", runtime.GOOS)
-}
-
-// dialNamedPipe is unsupported off Windows.
-func dialNamedPipe(context.Context, string) (net.Conn, error) {
-	return nil, fmt.Errorf("named pipe daemon socket is only supported on Windows, not %s", runtime.GOOS)
-}

client/cmd/service_pipe_windows.go

@@ -1,30 +0,0 @@
-//go:build windows
-
-package cmd
-
-import (
-	"context"
-	"net"
-
-	"github.com/Microsoft/go-winio"
-	"golang.org/x/sys/windows"
-
-	"github.com/netbirdio/netbird/client/internal/ipcauth"
-)
-
-// listenNamedPipe creates the daemon control named pipe with a permissive,
-// local-only SDDL. Any local caller may connect, like Unix socket with 0666.
-func listenNamedPipe(path string) (net.Listener, error) {
-	return winio.ListenPipe(path, &winio.PipeConfig{
-		SecurityDescriptor: ipcauth.DefaultPipeSDDL(),
-	})
-}
-
-// dialNamedPipe connects to the daemon ipc named pipe at SECURITY_IDENTIFICATION.
-func dialNamedPipe(ctx context.Context, path string) (net.Conn, error) {
-	access := uint32(windows.GENERIC_READ | windows.GENERIC_WRITE)
-	// winio's plain DialPipe connects at SECURITY_ANONYMOUS, under which the
-	// daemon cannot read the caller's token. Identification lets the daemon
-	// read its SID/groups without granting it the ability to act as the caller.
-	return winio.DialPipeAccessImpLevel(ctx, path, access, winio.PipeImpLevelIdentification)
-}

client/cmd/service_privileged_test.go

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

client/cmd/service_socket.go

@@ -1,154 +0,0 @@
-//go:build !ios && !android
-
-package cmd
-
-import (
-	"errors"
-	"fmt"
-	"net"
-	"os"
-	"runtime"
-	"strings"
-	"syscall"
-	"time"
-
-	log "github.com/sirupsen/logrus"
-)
-
-const (
-	windowsPipeDaemonAddr = "npipe://netbird"
-
-	// legacyWindowsDaemonAddr is the loopback-TCP address the Windows daemon used
-	// before named-pipe support.
-	legacyWindowsDaemonAddr = "tcp://127.0.0.1:41731"
-)
-
-// migrateLegacyDaemonAddr upgrades the pre-named-pipe Windows daemon address to
-// the pipe. Existing installs persist daemon addr, so on upgrade the daemon
-// would otherwise keep listening on TCP and silently run without IPC
-// authorization. Only the exact legacy default is rewritten, while a
-// deliberately-chosen custom TCP address is left alone.
-func migrateLegacyDaemonAddr(addr string) (string, bool) {
-	return migrateLegacyDaemonAddrForOS(runtime.GOOS, addr)
-}
-
-func migrateLegacyDaemonAddrForOS(goos, addr string) (string, bool) {
-	if goos == "windows" && addr == legacyWindowsDaemonAddr {
-		return windowsPipeDaemonAddr, true
-	}
-	return addr, false
-}
-
-type socketListener struct {
-	net.Listener
-	network string
-	address string
-}
-
-func listenOnAddress(addr string) (*socketListener, error) {
-	network, address, err := parseListenAddress(addr)
-	if err != nil {
-		return nil, err
-	}
-
-	if network == "npipe" {
-		path := pipePath(address)
-		listener, err := listenNamedPipe(path)
-		if err != nil {
-			return nil, err
-		}
-		return &socketListener{Listener: listener, network: network, address: path}, nil
-	}
-
-	if network == "unix" {
-		removeStaleUnixSocket(address)
-	}
-
-	listener, err := net.Listen(network, address)
-	if err != nil {
-		return nil, err
-	}
-
-	return &socketListener{Listener: listener, network: network, address: address}, nil
-}
-
-func parseListenAddress(addr string) (string, string, error) {
-	network, address, ok := strings.Cut(addr, "://")
-	if !ok || network == "" || address == "" {
-		return "", "", fmt.Errorf("address must be in [unix|tcp|npipe]://[path|host:port|name] format: %q", addr)
-	}
-
-	switch network {
-	case "unix", "tcp", "npipe":
-		return network, address, nil
-	default:
-		return "", "", fmt.Errorf("unsupported daemon address protocol: %v", network)
-	}
-}
-
-// pipePath maps a daemon-addr npipe name ("npipe://netbird") to a Windows
-// named-pipe path (\\.\pipe\netbird).
-func pipePath(name string) string {
-	if strings.HasPrefix(name, `\\`) {
-		return name
-	}
-	return `\\.\pipe\` + name
-}
-
-func removeStaleUnixSocket(path string) {
-	stat, err := os.Lstat(path)
-	if err != nil {
-		if !os.IsNotExist(err) {
-			log.Debugf("stat socket file: %v", err)
-		}
-		return
-	}
-
-	if stat.Mode()&os.ModeSocket == 0 {
-		return
-	}
-
-	if !isStaleUnixSocket(path) {
-		return
-	}
-
-	if err := os.Remove(path); err != nil {
-		log.Debugf("remove socket file: %v", err)
-	}
-}
-
-func isStaleUnixSocket(path string) bool {
-	conn, err := net.DialTimeout("unix", path, 100*time.Millisecond)
-	if err == nil {
-		if closeErr := conn.Close(); closeErr != nil {
-			log.Debugf("close unix socket probe: %v", closeErr)
-		}
-		return false
-	}
-
-	if os.IsNotExist(err) || os.IsPermission(err) || os.IsTimeout(err) {
-		log.Debugf("not removing unix socket %s after probe error: %v", path, err)
-		return false
-	}
-
-	return errors.Is(err, syscall.ECONNREFUSED)
-}
-
-func removeStaleUnixSocketForAddress(addr string) {
-	network, address, err := parseListenAddress(addr)
-	if err != nil || network != "unix" {
-		return
-	}
-	removeStaleUnixSocket(address)
-}
-
-func (l *socketListener) chmodUnixSocket(description string) error {
-	if l == nil || l.network != "unix" {
-		return nil
-	}
-
-	if err := os.Chmod(l.address, 0666); err != nil {
-		return fmt.Errorf("failed setting %s permissions for %s: %w", description, l.address, err)
-	}
-	return nil
-}

client/cmd/service_socket_test.go

@@ -1,63 +0,0 @@
-//go:build !ios && !android
-
-package cmd
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-func TestMigrateLegacyDaemonAddrForOS(t *testing.T) {
-	cases := []struct {
-		name    string
-		goos    string
-		addr    string
-		want    string
-		migrate bool
-	}{
-		{
-			name:    "windows legacy tcp migrates to pipe",
-			goos:    "windows",
-			addr:    legacyWindowsDaemonAddr,
-			want:    windowsPipeDaemonAddr,
-			migrate: true,
-		},
-		{
-			name:    "windows pipe already migrated stays",
-			goos:    "windows",
-			addr:    windowsPipeDaemonAddr,
-			want:    windowsPipeDaemonAddr,
-			migrate: false,
-		},
-		{
-			name:    "windows custom tcp left alone",
-			goos:    "windows",
-			addr:    "tcp://127.0.0.1:9999",
-			want:    "tcp://127.0.0.1:9999",
-			migrate: false,
-		},
-		{
-			name:    "linux legacy-looking tcp not migrated",
-			goos:    "linux",
-			addr:    legacyWindowsDaemonAddr,
-			want:    legacyWindowsDaemonAddr,
-			migrate: false,
-		},
-		{
-			name:    "linux unix socket untouched",
-			goos:    "linux",
-			addr:    "unix:///var/run/netbird.sock",
-			want:    "unix:///var/run/netbird.sock",
-			migrate: false,
-		},
-	}
-
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			got, ok := migrateLegacyDaemonAddrForOS(tc.goos, tc.addr)
-			assert.Equal(t, tc.want, got)
-			assert.Equal(t, tc.migrate, ok)
-		})
-	}
-}

client/cmd/service_test.go

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

client/cmd/ssh_config_cmd.go

@@ -1,73 +0,0 @@
-package cmd
-
-import (
-	"fmt"
-
-	log "github.com/sirupsen/logrus"
-	"github.com/spf13/cobra"
-
-	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/proto"
-)
-
-var (
-	setSSHConfigProfile     string
-	setSSHConfigUsername    string
-	setSSHConfigEnableRoot  bool
-	setSSHConfigDisableAuth bool
-)
-
-// setSSHConfigCmd applies the privileged SSH settings (enable root login /
-// disable auth) to a profile over the daemon IPC. Hidden because users
-// interact via `netbird up` / the UI, not directly.
-var setSSHConfigCmd = &cobra.Command{
-	Use:    SetSSHConfigCmdName,
-	Short:  "Apply privileged SSH settings to a profile (internal elevation target)",
-	Hidden: true,
-	RunE: func(cmd *cobra.Command, _ []string) error {
-		ctx := internal.CtxInitState(cmd.Context())
-
-		conn, err := DialClientGRPCServer(ctx, daemonAddr)
-		if err != nil {
-			return fmt.Errorf("connect to daemon: %w", err)
-		}
-		defer func() {
-			if cerr := conn.Close(); cerr != nil {
-				log.Warnf("failed closing daemon gRPC client connection: %v", cerr)
-			}
-		}()
-
-		var enableRoot, disableAuth *bool
-		if cmd.Flags().Changed(enableSSHRootFlag) {
-			enableRoot = &setSSHConfigEnableRoot
-		}
-		if cmd.Flags().Changed(disableSSHAuthFlag) {
-			disableAuth = &setSSHConfigDisableAuth
-		}
-
-		req := buildSetSSHConfigRequest(setSSHConfigProfile, setSSHConfigUsername, enableRoot, disableAuth)
-		if _, err := proto.NewDaemonServiceClient(conn).SetConfig(ctx, req); err != nil {
-			return fmt.Errorf("apply SSH config: %w", err)
-		}
-		return nil
-	},
-}
-
-// buildSetSSHConfigRequest builds a minimal SetConfigRequest that touches only
-// the SSH fields that were provided (nil pointers leave the daemon's stored
-// value untouched, matching setupSetConfigReq's pointer semantics).
-func buildSetSSHConfigRequest(profileName, username string, enableSSHRoot, disableSSHAuth *bool) *proto.SetConfigRequest {
-	return &proto.SetConfigRequest{
-		ProfileName:    profileName,
-		Username:       username,
-		EnableSSHRoot:  enableSSHRoot,
-		DisableSSHAuth: disableSSHAuth,
-	}
-}
-
-func init() {
-	setSSHConfigCmd.Flags().StringVar(&setSSHConfigProfile, "profile", "", "profile name to apply the SSH settings to")
-	setSSHConfigCmd.Flags().StringVar(&setSSHConfigUsername, "username", "", "owning username of the profile")
-	setSSHConfigCmd.Flags().BoolVar(&setSSHConfigEnableRoot, enableSSHRootFlag, false, "enable root login for the SSH server")
-	setSSHConfigCmd.Flags().BoolVar(&setSSHConfigDisableAuth, disableSSHAuthFlag, false, "disable SSH authentication")
-}

client/cmd/status.go

@@ -5,8 +5,6 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"os/user"
-	"runtime"
 	"strings"
 	"time"
 
@@ -174,9 +172,10 @@ func getStatus(ctx context.Context, fullPeerStatus bool, shouldRunProbes bool) (
 	return resp, nil
 }
 
-// getActiveProfileName asks the daemon for the active profile's display name,
-// annotated with the owning user when the active profile belongs to someone else.
-// Returns an empty string on any error so status output degrades gracefully.
+// getActiveProfileName asks the daemon for the active profile's display
+// name. The daemon runs as root and can read the per-user profile files to
+// resolve the ID to its human-readable name. Returns an empty string on any
+// error so status output degrades gracefully.
 func getActiveProfileName(ctx context.Context) string {
 	conn, err := DialClientGRPCServer(ctx, daemonAddr)
 	if err != nil {
@@ -189,22 +188,7 @@ func getActiveProfileName(ctx context.Context) string {
 		return ""
 	}
 
-	name := resp.GetProfileName()
-	if owner := resp.GetUsername(); owner != "" {
-		if curr, uerr := user.Current(); uerr != nil || !usernamesMatch(owner, curr.Username) {
-			name = fmt.Sprintf("%s (user %s)", name, owner)
-		}
-	}
-	return name
-}
-
-// usernamesMatch compares usernames case-insensitively on Windows (domain
-// accounts) and exactly elsewhere.
-func usernamesMatch(a, b string) bool {
-	if runtime.GOOS == "windows" {
-		return strings.EqualFold(a, b)
-	}
-	return a == b
+	return resp.GetProfileName()
 }
 
 func parseFilters() error {

client/cmd/up.go

@@ -21,9 +21,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	nbnet "github.com/netbirdio/netbird/client/net"
 	"github.com/netbirdio/netbird/client/proto"
-	"github.com/netbirdio/netbird/client/server"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/shared/management/domain"
 	"github.com/netbirdio/netbird/util"
@@ -56,7 +54,6 @@ var (
 	showQR             bool
 	profileName        string
 	configPath         string
-	claimOwner         bool
 
 	upCmd = &cobra.Command{
 		Use:   "up",
@@ -68,7 +65,6 @@ var (
 
 func init() {
 	upCmd.PersistentFlags().BoolVarP(&foregroundMode, "foreground-mode", "F", false, "start service in foreground")
-	upCmd.PersistentFlags().BoolVar(&claimOwner, "owner", false, "claim ownership of this profile for the current user, restricting daemon control of it to you and root/administrator")
 	upCmd.PersistentFlags().StringVar(&interfaceName, interfaceNameFlag, iface.WgInterfaceDefault, "WireGuard interface name")
 	upCmd.PersistentFlags().Uint16Var(&wireguardPort, wireguardPortFlag, iface.DefaultWgPort, "WireGuard interface listening port")
 	upCmd.PersistentFlags().Uint16Var(&mtu, mtuFlag, iface.DefaultMTU, "Set MTU (Maximum Transmission Unit) for the WireGuard interface")
@@ -233,24 +229,6 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *pr
 
 	_, _ = profilemanager.UpdateOldManagementURL(ctx, config, configFilePath)
 
-	// Restore residual state left by a previous run that did not shut down
-	// cleanly, mirroring what the daemon does before connecting: it recovers
-	// DNS config (a stale resolv.conf takeover can make the management
-	// hostname unresolvable), firewall rules, ssh config and legacy routing.
-	// Route cleanup itself happens at engine start; nbnet.Init() below lets
-	// the management dial bypass a leftover fwmark rule until then.
-	// Foreground mode is particularly exposed in containers: a crashed
-	// container restarts inside the same (pod) network namespace, so stale
-	// state survives while the process does not.
-	if err := server.RestoreResidualState(ctx, profilemanager.NewServiceManager(configPath).GetStatePath()); err != nil {
-		log.Warnf("failed to restore residual state: %v", err)
-	}
-
-	// Enable advanced routing (as the daemon does on startup) so the
-	// management dial bypasses a leftover fwmark rule instead of being
-	// shunted into a stale routing table.
-	nbnet.Init()
-
 	err = foregroundLogin(ctx, cmd, config, providedSetupKey, activeProf.ID)
 	if err != nil {
 		return fmt.Errorf("foreground login failed: %v", err)
@@ -321,24 +299,6 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
 		return fmt.Errorf("get current user: %v", err)
 	}
 
-	// Enabling SSH root login / disabling SSH auth is a privileged change the
-	// daemon rejects from a non-privileged caller. Offer to elevate (polkit/UAC/
-	// osascript) so an elevated helper applies just those settings.
-	if wantsDangerousSSH(cmd) && !isProcessPrivileged() {
-		cmd.Println("Enabling SSH root login / disabling SSH authentication requires administrator privileges, requesting elevation...")
-		var enableRoot, disableAuth *bool
-		if cmd.Flag(enableSSHRootFlag).Changed {
-			enableRoot = &enableSSHRoot
-		}
-		if cmd.Flag(disableSSHAuthFlag).Changed {
-			disableAuth = &disableSSHAuth
-		}
-		if err := ElevateSSHConfig(activeProf.ID.String(), username.Username, enableRoot, disableAuth); err != nil {
-			return fmt.Errorf("apply privileged SSH settings: %w", err)
-		}
-		sshConfigElevated = true
-	}
-
 	// set the new config
 	req := setupSetConfigReq(customDNSAddressConverted, cmd, activeProf.ID.String(), username.Username)
 	if _, err := client.SetConfig(ctx, req); err != nil {
@@ -411,7 +371,6 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 	if _, err := client.Up(ctx, &proto.UpRequest{
 		ProfileName: &profileID,
 		Username:    &username,
-		ClaimOwner:  claimOwner,
 	}); err != nil {
 		return fmt.Errorf("call service up method: %v", err)
 	}
@@ -442,7 +401,7 @@ func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, pro
 	if cmd.Flag(serverSSHAllowedFlag).Changed {
 		req.ServerSSHAllowed = &serverSSHAllowed
 	}
-	if cmd.Flag(enableSSHRootFlag).Changed && !sshConfigElevated {
+	if cmd.Flag(enableSSHRootFlag).Changed {
 		req.EnableSSHRoot = &enableSSHRoot
 	}
 	if cmd.Flag(enableSSHSFTPFlag).Changed {
@@ -454,7 +413,7 @@ func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, pro
 	if cmd.Flag(enableSSHRemotePortForwardFlag).Changed {
 		req.EnableSSHRemotePortForwarding = &enableSSHRemotePortForward
 	}
-	if cmd.Flag(disableSSHAuthFlag).Changed && !sshConfigElevated {
+	if cmd.Flag(disableSSHAuthFlag).Changed {
 		req.DisableSSHAuth = &disableSSHAuth
 	}
 	if cmd.Flag(sshJWTCacheTTLFlag).Changed {
@@ -520,6 +479,10 @@ func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, pro
 		req.DisableIpv6 = &disableIPv6
 	}
 
+	if cmd.Flag(enableLazyConnectionFlag).Changed {
+		req.LazyConnectionEnabled = &lazyConnEnabled
+	}
+
 	return &req
 }
 
@@ -637,6 +600,9 @@ func setupConfig(customDNSAddressConverted []byte, cmd *cobra.Command, configFil
 		ic.DisableIPv6 = &disableIPv6
 	}
 
+	if cmd.Flag(enableLazyConnectionFlag).Changed {
+		ic.LazyConnectionEnabled = &lazyConnEnabled
+	}
 	return &ic, nil
 }
 
@@ -670,7 +636,7 @@ func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte
 		loginRequest.ServerSSHAllowed = &serverSSHAllowed
 	}
 
-	if cmd.Flag(enableSSHRootFlag).Changed && !sshConfigElevated {
+	if cmd.Flag(enableSSHRootFlag).Changed {
 		loginRequest.EnableSSHRoot = &enableSSHRoot
 	}
 
@@ -686,7 +652,7 @@ func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte
 		loginRequest.EnableSSHRemotePortForwarding = &enableSSHRemotePortForward
 	}
 
-	if cmd.Flag(disableSSHAuthFlag).Changed && !sshConfigElevated {
+	if cmd.Flag(disableSSHAuthFlag).Changed {
 		loginRequest.DisableSSHAuth = &disableSSHAuth
 	}
 
@@ -752,6 +718,9 @@ func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte
 		loginRequest.DisableIpv6 = &disableIPv6
 	}
 
+	if cmd.Flag(enableLazyConnectionFlag).Changed {
+		loginRequest.LazyConnectionEnabled = &lazyConnEnabled
+	}
 	return &loginRequest, nil
 }
 

client/cmd/up_daemon_test.go

@@ -29,7 +29,7 @@ func TestUpDaemon(t *testing.T) {
 	}
 
 	sm := profilemanager.ServiceManager{}
-	created, err := sm.AddProfile("test1", currUser.Username, nil)
+	created, err := sm.AddProfile("test1", currUser.Username)
 	if err != nil {
 		t.Fatalf("failed to add profile: %v", err)
 		return

client/embed/embed.go

@@ -279,11 +279,9 @@ func (c *Client) Start(startCtx context.Context) error {
 
 	select {
 	case <-startCtx.Done():
-		// ConnectClient.Stop now cancels its own run context and waits for the
-		// run loop to tear the engine down, so this cancel() is no longer
-		// required to break the deadlock and could be removed. It is kept as a
-		// defensive belt-and-suspenders: cancelling the parent context first
-		// guarantees the run loop is unblocked even if Stop's contract regresses.
+		// Cancel the client context before stopping: Engine.Start blocks on the
+		// signal stream while holding the engine mutex and only unblocks on
+		// cancellation. Stopping first would deadlock on that mutex.
 		cancel()
 		if stopErr := client.Stop(); stopErr != nil {
 			return fmt.Errorf("stop error after context done. Stop error: %w. Context done: %w", stopErr, startCtx.Err())

client/firewall/iptables/manager_linux_test.go

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

client/firewall/iptables/router_linux_test.go

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

client/firewall/nftables/manager_linux_test.go

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

client/firewall/nftables/router_linux_test.go

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

client/firewall/uspfilter/filter.go

@@ -121,7 +121,6 @@ type Manager struct {
 	udpTracker     *conntrack.UDPTracker
 	icmpTracker    *conntrack.ICMPTracker
 	tcpTracker     *conntrack.TCPTracker
-	fragments      *fragmentTracker
 	forwarder      atomic.Pointer[forwarder.Forwarder]
 	pendingCapture atomic.Pointer[forwarder.PacketCapture]
 	logger         *nblog.Logger
@@ -184,41 +183,6 @@ func (d *decoder) decodePacket(data []byte) error {
 	}
 }
 
-// decodeTransport decodes the transport header of a first fragment (which
-// gopacket leaves undecoded) into the decoder and appends its layer type to
-// decoded, so the ACL pipeline can evaluate it like a normal packet. It returns
-// false if the protocol is unsupported or the header is truncated.
-func (d *decoder) decodeTransport(proto layers.IPProtocol, payload []byte) bool {
-	var l4 gopacket.DecodingLayer
-	var layerType gopacket.LayerType
-	var minLen int
-	switch proto {
-	case layers.IPProtocolTCP:
-		l4, layerType, minLen = &d.tcp, layers.LayerTypeTCP, 20
-	case layers.IPProtocolUDP:
-		l4, layerType, minLen = &d.udp, layers.LayerTypeUDP, 8
-	case layers.IPProtocolICMPv4:
-		l4, layerType, minLen = &d.icmp4, layers.LayerTypeICMPv4, 8
-	case layers.IPProtocolICMPv6:
-		l4, layerType, minLen = &d.icmp6, layers.LayerTypeICMPv6, 8
-	default:
-		return false
-	}
-
-	// Reject a fragment too small to hold the full transport header before
-	// decoding: it can't be ACL-evaluated (tiny-fragment attack), and skipping
-	// the decode avoids gopacket allocating an error on the drop path.
-	if len(payload) < minLen {
-		return false
-	}
-
-	if err := l4.DecodeFromBytes(payload, gopacket.NilDecodeFeedback); err != nil {
-		return false
-	}
-	d.decoded = append(d.decoded, layerType)
-	return true
-}
-
 // Create userspace firewall manager constructor
 func Create(iface common.IFaceMapper, disableServerRoutes bool, flowLogger nftypes.FlowLogger, mtu uint16) (*Manager, error) {
 	return create(iface, nil, disableServerRoutes, flowLogger, mtu)
@@ -322,8 +286,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
 	if err := m.localipmanager.UpdateLocalIPs(iface); err != nil {
 		return nil, fmt.Errorf("update local IPs: %w", err)
 	}
-	m.fragments = newFragmentTracker(m.logger)
-
 	if disableConntrack {
 		log.Info("conntrack is disabled")
 	} else {
@@ -337,7 +299,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
 		}
 	}
 	if err := iface.SetFilter(m); err != nil {
-		m.fragments.Close()
 		return nil, fmt.Errorf("set filter: %w", err)
 	}
 	return m, nil
@@ -733,10 +694,6 @@ func (m *Manager) resetState() {
 		m.tcpTracker.Close()
 	}
 
-	if m.fragments != nil {
-		m.fragments.Close()
-	}
-
 	if fwder := m.forwarder.Load(); fwder != nil {
 		fwder.SetCapture(nil)
 		fwder.Stop()
@@ -1089,20 +1046,19 @@ func (m *Manager) filterInbound(packetData []byte, size int) bool {
 		return true
 	}
 
-	// gopacket does not decode the transport header of any IP fragment, so
-	// fragments take a dedicated path: the first fragment's header is decoded
-	// and ACL-evaluated here, and the remaining fragments inherit its verdict.
+	// TODO: pass fragments of routed packets to forwarder
 	if fragment {
-		return m.filterInboundFragment(d, srcIP, dstIP, size)
+		if m.logger.Enabled(nblog.LevelTrace) {
+			if d.decoded[0] == layers.LayerTypeIPv4 {
+				m.logger.Trace4("packet is a fragment: src=%v dst=%v id=%v flags=%v",
+					srcIP, dstIP, d.ip4.Id, d.ip4.Flags)
+			} else {
+				m.logger.Trace2("packet is an IPv6 fragment: src=%v dst=%v", srcIP, dstIP)
+			}
+		}
+		return false
 	}
 
-	return m.filterInboundDecoded(d, srcIP, dstIP, packetData, size)
-}
-
-// filterInboundDecoded runs the ACL, DNAT and conntrack pipeline on a fully
-// decoded (non-fragment) inbound packet. It returns true if the packet should
-// be dropped.
-func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
 	// TODO: optimize port DNAT by caching matched rules in conntrack
 	if translated := m.translateInboundPortDNAT(packetData, d, srcIP, dstIP); translated {
 		// Re-decode after port DNAT translation to update port information
@@ -1133,226 +1089,33 @@ func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, pack
 	return m.handleRoutedTraffic(d, srcIP, dstIP, packetData, size)
 }
 
-// fragmentMeta holds the reassembly identity and layout of an IP fragment,
-// extracted uniformly for IPv4 and IPv6.
-type fragmentMeta struct {
-	key fragmentKey
-	// offset is the fragment offset in 8-byte units (zero for the first
-	// fragment).
-	offset uint16
-	// moreFragments is the More Fragments bit. A first fragment with it unset is
-	// an IPv6 atomic fragment (a complete datagram, RFC 6946): it has no trailing
-	// fragments to inherit a verdict, so it must not be recorded.
-	moreFragments bool
-	proto         layers.IPProtocol
-	// l4payload is the fragmentable payload of this fragment. For the first
-	// fragment it starts with the transport header.
-	l4payload []byte
-	// headerEndOctets is the first fragment's payload length in 8-byte units:
-	// the smallest offset a trailing fragment may start at without overlapping
-	// the inspected transport header.
-	headerEndOctets uint16
-}
-
-// fragmentMetadata extracts the fragment identity and layout from a decoded IP
-// fragment. It returns false for fragments it can't interpret (e.g. an IPv6
-// fragment header shorter than 8 bytes), which are then dropped.
-func fragmentMetadata(d *decoder, srcIP, dstIP netip.Addr) (fragmentMeta, bool) {
-	switch d.decoded[0] {
-	case layers.LayerTypeIPv4:
-		payload := d.ip4.Payload
-		return fragmentMeta{
-			key:             fragmentKey{srcIP: srcIP, dstIP: dstIP, id: uint32(d.ip4.Id), proto: uint8(d.ip4.Protocol)},
-			offset:          d.ip4.FragOffset,
-			moreFragments:   d.ip4.Flags&layers.IPv4MoreFragments != 0,
-			proto:           d.ip4.Protocol,
-			l4payload:       payload,
-			headerEndOctets: octets(len(payload)),
-		}, true
-
-	case layers.LayerTypeIPv6:
-		// IPv6 fragment extension header: 8 bytes, followed by the fragmentable
-		// payload. Layout: next header (1), reserved (1), offset+flags (2), id (4).
-		payload := d.ip6.Payload
-		if len(payload) < 8 {
-			return fragmentMeta{}, false
-		}
-		nextHeader := layers.IPProtocol(payload[0])
-		offsetFlags := binary.BigEndian.Uint16(payload[2:4])
-		id := binary.BigEndian.Uint32(payload[4:8])
-		l4 := payload[8:]
-		return fragmentMeta{
-			key:             fragmentKey{srcIP: srcIP, dstIP: dstIP, id: id, proto: uint8(nextHeader)},
-			offset:          offsetFlags >> 3,
-			moreFragments:   offsetFlags&1 != 0,
-			proto:           nextHeader,
-			l4payload:       l4,
-			headerEndOctets: octets(len(l4)),
-		}, true
-
-	default:
-		return fragmentMeta{}, false
-	}
-}
-
-// octets rounds a byte length up to whole 8-byte units, the granularity of the
-// IP fragment offset field.
-func octets(nbytes int) uint16 {
-	return uint16((nbytes + 7) / 8)
-}
-
-// filterInboundFragment decides the fate of an IP fragment. gopacket stops
-// decoding at the network layer for every fragment, so the first fragment's
-// transport header is decoded and ACL-evaluated here and its verdict recorded;
-// the remaining (headerless) fragments inherit that verdict. Anything that
-// cannot be tied to an allowed, non-overlapping first fragment is dropped.
-func (m *Manager) filterInboundFragment(d *decoder, srcIP, dstIP netip.Addr, size int) bool {
-	meta, ok := fragmentMetadata(d, srcIP, dstIP)
-	if !ok {
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace2("dropping unsupported fragment: src=%v dst=%v", srcIP, dstIP)
-		}
-		return true
-	}
-
-	if meta.offset != 0 {
-		return m.filterTrailingFragment(meta, srcIP, dstIP)
-	}
-
-	// A new first fragment supersedes any recorded verdict for this datagram, so
-	// a re-sent or overlapping offset-zero fragment can't inherit the old one.
-	m.fragments.poison(meta.key)
-
-	// First fragment: decode its transport header so the ACL can evaluate it. A
-	// decode failure means the fragment is too small to hold the full transport
-	// header (RFC 1858 §3 tiny-fragment attack); it can't be evaluated, so drop it.
-	if !d.decodeTransport(meta.proto, meta.l4payload) {
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace3("dropping first fragment without full L4 header: src=%v dst=%v id=%v",
-				srcIP, dstIP, meta.key.id)
-		}
-		return true
-	}
-
-	return m.filterFirstFragment(d, meta, srcIP, dstIP, size)
-}
-
-// filterTrailingFragment applies a recorded first-fragment verdict to a
-// non-first fragment.
-func (m *Manager) filterTrailingFragment(meta fragmentMeta, srcIP, dstIP netip.Addr) bool {
-	switch m.fragments.verdict(meta.key, meta.offset) {
-	case fragmentAllow:
-		return false
-	case fragmentOverlap:
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace3("dropping overlapping fragment rewriting inspected header: src=%v dst=%v id=%v",
-				srcIP, dstIP, meta.key.id)
-		}
-		return true
-	default:
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace3("dropping fragment with no allowed first fragment: src=%v dst=%v id=%v",
-				srcIP, dstIP, meta.key.id)
-		}
-		return true
-	}
-}
-
-// filterFirstFragment runs the verdict part of the inbound pipeline on a first
-// fragment with its transport header decoded. It mirrors filterInboundDecoded
-// but skips DNAT (port rewriting on fragments is unsupported) and forwarder
-// injection (fragments are left to the stack to reassemble, not forwarded).
-// Allowed fragments have their verdict recorded so the datagram's trailing
-// fragments inherit it.
-func (m *Manager) filterFirstFragment(d *decoder, meta fragmentMeta, srcIP, dstIP netip.Addr, size int) bool {
-	if m.stateful && m.isValidTrackedConnection(d, srcIP, dstIP, size) {
-		m.recordFirstFragment(meta)
-		return false
-	}
-
-	if m.localipmanager.IsLocalIP(dstIP) {
-		ruleID, blocked := m.peerACLsBlock(srcIP, d, nil)
-		if blocked {
-			m.storeDropFlow("Dropping local first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-				d, srcIP, dstIP, ruleID, size)
-			return true
-		}
-		m.trackInbound(d, srcIP, dstIP, ruleID, size)
-		m.recordFirstFragment(meta)
-		return false
-	}
-
-	if !m.routingEnabled.Load() {
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace2("Dropping routed fragment (routing disabled): src=%s dst=%s", srcIP, dstIP)
-		}
-		return true
-	}
-	if m.nativeRouter.Load() {
-		m.trackInbound(d, srcIP, dstIP, nil, size)
-		m.recordFirstFragment(meta)
-		return false
-	}
-
-	// TODO: pass fragments of routed packets to the forwarder; until then
-	// allowed routed fragments go to the native stack.
-	srcPort, dstPort := getPortsFromPacket(d)
-	ruleID, pass := m.routeACLsPass(srcIP, dstIP, d.decoded[1], srcPort, dstPort)
-	if !pass {
-		m.storeDropFlow("Dropping routed first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-			d, srcIP, dstIP, ruleID, size)
-		return true
-	}
-
-	m.recordFirstFragment(meta)
-	return false
-}
-
-// recordFirstFragment caches an allowed first fragment's verdict for its
-// trailing fragments to inherit. Atomic fragments (no More Fragments bit) are
-// complete datagrams with no trailing fragments, so they are not cached and
-// cannot exhaust the verdict table.
-func (m *Manager) recordFirstFragment(meta fragmentMeta) {
-	if !meta.moreFragments {
-		return
-	}
-	m.fragments.recordAllowed(meta.key, meta.headerEndOctets)
-}
-
-// storeDropFlow logs and records a netflow drop event for an inbound packet
-// denied by the ACLs. msg is the trace format taking rule id, protocol, source
-// and destination.
-func (m *Manager) storeDropFlow(msg string, d *decoder, srcIP, dstIP netip.Addr, ruleID []byte, size int) {
-	pnum := getProtocolFromPacket(d)
-	srcPort, dstPort := getPortsFromPacket(d)
-
-	if m.logger.Enabled(nblog.LevelTrace) {
-		m.logger.Trace6(msg, ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
-	}
-
-	m.flowLogger.StoreEvent(nftypes.EventFields{
-		FlowID:     uuid.New(),
-		Type:       nftypes.TypeDrop,
-		RuleID:     ruleID,
-		Direction:  nftypes.Ingress,
-		Protocol:   pnum,
-		SourceIP:   srcIP,
-		DestIP:     dstIP,
-		SourcePort: srcPort,
-		DestPort:   dstPort,
-		// TODO: icmp type/code
-		RxPackets: 1,
-		RxBytes:   uint64(size),
-	})
-}
-
 // handleLocalTraffic handles local traffic.
 // If it returns true, the packet should be dropped.
 func (m *Manager) handleLocalTraffic(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
 	ruleID, blocked := m.peerACLsBlock(srcIP, d, packetData)
 	if blocked {
-		m.storeDropFlow("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-			d, srcIP, dstIP, ruleID, size)
+		pnum := getProtocolFromPacket(d)
+		srcPort, dstPort := getPortsFromPacket(d)
+
+		if m.logger.Enabled(nblog.LevelTrace) {
+			m.logger.Trace6("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
+				ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
+		}
+
+		m.flowLogger.StoreEvent(nftypes.EventFields{
+			FlowID:     uuid.New(),
+			Type:       nftypes.TypeDrop,
+			RuleID:     ruleID,
+			Direction:  nftypes.Ingress,
+			Protocol:   pnum,
+			SourceIP:   srcIP,
+			DestIP:     dstIP,
+			SourcePort: srcPort,
+			DestPort:   dstPort,
+			// TODO: icmp type/code
+			RxPackets: 1,
+			RxBytes:   uint64(size),
+		})
 		return true
 	}
 
@@ -1405,8 +1168,27 @@ func (m *Manager) handleRoutedTraffic(d *decoder, srcIP, dstIP netip.Addr, packe
 
 	ruleID, pass := m.routeACLsPass(srcIP, dstIP, protoLayer, srcPort, dstPort)
 	if !pass {
-		m.storeDropFlow("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-			d, srcIP, dstIP, ruleID, size)
+		proto := getProtocolFromPacket(d)
+
+		if m.logger.Enabled(nblog.LevelTrace) {
+			m.logger.Trace6("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
+				ruleID, proto, srcIP, srcPort, dstIP, dstPort)
+		}
+
+		m.flowLogger.StoreEvent(nftypes.EventFields{
+			FlowID:     uuid.New(),
+			Type:       nftypes.TypeDrop,
+			RuleID:     ruleID,
+			Direction:  nftypes.Ingress,
+			Protocol:   proto,
+			SourceIP:   srcIP,
+			DestIP:     dstIP,
+			SourcePort: srcPort,
+			DestPort:   dstPort,
+			// TODO: icmp type/code
+			RxPackets: 1,
+			RxBytes:   uint64(size),
+		})
 		return true
 	}
 

client/firewall/uspfilter/forwarder/forwarder.go

@@ -5,9 +5,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"os"
 	"runtime"
-	"strconv"
 	"sync"
 	"time"
 
@@ -33,11 +31,6 @@ const (
 	defaultMaxInFlight   = 1024
 	iosReceiveWindow     = 16384
 	iosMaxInFlight       = 256
-
-	// envForceTCPRACK overrides the platform default for gVisor's RACK loss
-	// detection. Set to a truthy value to force RACK on, or a falsy value to
-	// force it off, on any platform.
-	envForceTCPRACK = "NB_FORCE_TCP_RACK"
 )
 
 type Forwarder struct {
@@ -159,8 +152,6 @@ func New(iface common.IFaceMapper, logger *nblog.Logger, flowLogger nftypes.Flow
 		maxInFlight = iosMaxInFlight
 	}
 
-	configureTCPRecovery(s)
-
 	tcpForwarder := tcp.NewForwarder(s, receiveWindow, maxInFlight, f.handleTCP)
 	s.SetTransportProtocolHandler(tcp.ProtocolNumber, tcpForwarder.HandlePacket)
 
@@ -475,31 +466,3 @@ func probeRawICMP(network, addr string, logger *nblog.Logger) bool {
 	logger.Debug1("forwarder: raw %s socket access available", network)
 	return true
 }
-
-// configureTCPRecovery disables gVisor's RACK loss detection on Windows, where
-// it interacts poorly with the host and collapses throughput on routed TCP
-// connections (gVisor issue #9778). Other platforms keep the default. The
-// EnvForceTCPRACK environment variable overrides the platform default.
-func configureTCPRecovery(s *stack.Stack) {
-	disableRACK := runtime.GOOS == "windows"
-
-	if val := os.Getenv(envForceTCPRACK); val != "" {
-		force, err := strconv.ParseBool(val)
-		if err != nil {
-			log.Warnf("parse %s: %v", envForceTCPRACK, err)
-		} else {
-			disableRACK = !force
-		}
-	}
-
-	if !disableRACK {
-		return
-	}
-
-	opt := tcpip.TCPRecovery(0)
-	if err := s.SetTransportProtocolOption(tcp.ProtocolNumber, &opt); err != nil {
-		log.Warnf("disable TCP RACK loss detection: %v", err)
-		return
-	}
-	log.Info("forwarder: TCP RACK loss detection disabled")
-}

client/firewall/uspfilter/fragment.go

@@ -1,204 +0,0 @@
-package uspfilter
-
-import (
-	"context"
-	"net/netip"
-	"os"
-	"strconv"
-	"sync"
-	"time"
-
-	nblog "github.com/netbirdio/netbird/client/firewall/uspfilter/log"
-)
-
-const (
-	// defaultFragmentTimeout bounds how long a first-fragment verdict is kept
-	// while the remaining fragments arrive. It mirrors the Linux IP reassembly
-	// timeout (net.ipv4.ipfrag_time).
-	defaultFragmentTimeout = 30 * time.Second
-	// fragmentCleanupInterval is how often expired verdicts are purged.
-	fragmentCleanupInterval = 10 * time.Second
-	// defaultMaxFragmentEntries caps the number of concurrently tracked
-	// fragmented datagrams. The table stays bounded because each datagram is a
-	// single small entry regardless of how many fragments it is split into, and
-	// the 13-bit IPv4 fragment-offset field limits any datagram to 64 KiB.
-	defaultMaxFragmentEntries = 16384
-
-	// EnvFragmentMaxEntries overrides defaultMaxFragmentEntries.
-	EnvFragmentMaxEntries = "NB_FRAGMENT_MAX_ENTRIES"
-)
-
-// fragmentVerdict is the decision for a trailing (headerless) fragment.
-type fragmentVerdict int
-
-const (
-	// fragmentDeny drops the fragment: no allowed first fragment is on record.
-	fragmentDeny fragmentVerdict = iota
-	// fragmentAllow passes the fragment: it belongs to an allowed datagram and
-	// does not overlap the already-inspected transport header.
-	fragmentAllow
-	// fragmentOverlap drops the fragment and poisons its datagram: it overlaps
-	// the transport header the ACL inspected (RFC 1858 §4, RFC 3128; RFC 5722
-	// requires discarding the whole datagram on overlap for IPv6).
-	fragmentOverlap
-)
-
-// fragmentKey identifies a fragmented datagram. It matches the RFC 791 / RFC
-// 8200 reassembly key: source, destination, protocol and identification. The id
-// is 32-bit to hold both the IPv4 (16-bit) and IPv6 (32-bit) identification.
-type fragmentKey struct {
-	srcIP netip.Addr
-	dstIP netip.Addr
-	id    uint32
-	proto uint8
-}
-
-// fragmentEntry records the verdict of an allowed first fragment.
-type fragmentEntry struct {
-	// headerEndOctets is the offset, in 8-byte units, at which the first
-	// fragment's payload ended. A trailing fragment starting before this
-	// overlaps bytes the ACL already inspected and is rejected.
-	headerEndOctets uint16
-	// recordedAt is when the first fragment was accepted. The verdict expires a
-	// fixed timeout later and is not refreshed, mirroring the kernel reassembly
-	// timer so a trailing-fragment flood can't keep a datagram alive.
-	recordedAt time.Time
-}
-
-// fragmentTracker records the ACL verdict of a datagram's first fragment so the
-// remaining fragments, which carry no L4 header, can inherit the decision
-// without reassembling the datagram. Only allowed first fragments are stored;
-// anything that cannot be tied to an allowed, non-overlapping first fragment is
-// dropped (fail closed).
-type fragmentTracker struct {
-	logger  *nblog.Logger
-	mutex   sync.Mutex
-	entries map[fragmentKey]fragmentEntry
-	timeout time.Duration
-	// maxEntries caps the table; atCapacity dedups the capacity warning until
-	// the table drains below the cap again.
-	maxEntries    int
-	atCapacity    bool
-	cleanupTicker *time.Ticker
-	cancel        context.CancelFunc
-}
-
-func newFragmentTracker(logger *nblog.Logger) *fragmentTracker {
-	ctx, cancel := context.WithCancel(context.Background())
-	t := &fragmentTracker{
-		logger:        logger,
-		entries:       make(map[fragmentKey]fragmentEntry),
-		timeout:       defaultFragmentTimeout,
-		maxEntries:    fragmentMaxEntries(logger),
-		cleanupTicker: time.NewTicker(fragmentCleanupInterval),
-		cancel:        cancel,
-	}
-	go t.cleanupRoutine(ctx)
-	return t
-}
-
-func fragmentMaxEntries(logger *nblog.Logger) int {
-	v := os.Getenv(EnvFragmentMaxEntries)
-	if v == "" {
-		return defaultMaxFragmentEntries
-	}
-	n, err := strconv.Atoi(v)
-	if err != nil || n <= 0 {
-		logger.Warn2("invalid %s=%q, using default", EnvFragmentMaxEntries, v)
-		return defaultMaxFragmentEntries
-	}
-	return n
-}
-
-// recordAllowed stores the verdict of an allowed first fragment. headerEndOctets
-// is the first fragment's payload length in 8-byte units. When the table is full
-// the record is dropped, which fails closed: the datagram's trailing fragments
-// will be denied.
-func (t *fragmentTracker) recordAllowed(key fragmentKey, headerEndOctets uint16) {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-
-	if t.entries == nil {
-		return
-	}
-	if _, ok := t.entries[key]; !ok && len(t.entries) >= t.maxEntries {
-		if !t.atCapacity {
-			t.atCapacity = true
-			t.logger.Warn2("fragment verdict table at capacity (%d/%d): trailing fragments of new datagrams will be dropped",
-				len(t.entries), t.maxEntries)
-		}
-		return
-	}
-	t.entries[key] = fragmentEntry{
-		headerEndOctets: headerEndOctets,
-		recordedAt:      time.Now(),
-	}
-}
-
-// poison drops any recorded verdict for a datagram, so its later fragments are
-// denied until a new allowed first fragment is recorded. Called on every
-// offset-zero fragment to defeat offset-zero overlap rewrites (RFC 3128).
-func (t *fragmentTracker) poison(key fragmentKey) {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-	delete(t.entries, key)
-}
-
-// verdict decides the fate of a trailing fragment at fragOffsetOctets (the IPv4
-// fragment offset, in 8-byte units). A fragment overlapping the inspected
-// header poisons the datagram: the entry is removed so all further fragments of
-// that datagram are denied too.
-func (t *fragmentTracker) verdict(key fragmentKey, fragOffsetOctets uint16) fragmentVerdict {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-
-	entry, ok := t.entries[key]
-	if !ok {
-		return fragmentDeny
-	}
-	if time.Since(entry.recordedAt) > t.timeout {
-		delete(t.entries, key)
-		return fragmentDeny
-	}
-	if fragOffsetOctets < entry.headerEndOctets {
-		delete(t.entries, key)
-		return fragmentOverlap
-	}
-	return fragmentAllow
-}
-
-func (t *fragmentTracker) cleanupRoutine(ctx context.Context) {
-	defer t.cleanupTicker.Stop()
-	for {
-		select {
-		case <-t.cleanupTicker.C:
-			t.cleanup()
-		case <-ctx.Done():
-			return
-		}
-	}
-}
-
-func (t *fragmentTracker) cleanup() {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-
-	for key, entry := range t.entries {
-		if time.Since(entry.recordedAt) > t.timeout {
-			delete(t.entries, key)
-		}
-	}
-
-	if len(t.entries) < t.maxEntries {
-		t.atCapacity = false
-	}
-}
-
-// Close stops the cleanup routine and releases resources.
-func (t *fragmentTracker) Close() {
-	t.cancel()
-
-	t.mutex.Lock()
-	t.entries = nil
-	t.mutex.Unlock()
-}

client/firewall/uspfilter/fragment_bench_test.go

@@ -1,115 +0,0 @@
-package uspfilter
-
-import (
-	"encoding/binary"
-	"testing"
-)
-
-// benchFilterInbound drives filterInbound over a fixed packet in a tight loop.
-// Packets are built once, outside the timed region, so the benchmark measures
-// only pipeline cost, which is what an attacker can amplify.
-func benchFilterInbound(b *testing.B, pkt []byte) {
-	b.Helper()
-	b.ReportAllocs()
-	b.SetBytes(int64(len(pkt)))
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		m := benchManager
-		m.filterInbound(pkt, len(pkt))
-	}
-}
-
-// benchManager is a package-level manager reused across fragment benchmarks so
-// setup cost stays out of the timed region.
-var benchManager *Manager
-
-func setupBenchManager(b *testing.B) *Manager {
-	b.Helper()
-	m := newFragmentTestManager(b)
-	allowUDP(b, m, 8080)
-	// Disable conntrack so the allowed-first-fragment path measures transport
-	// decode + ACL every iteration instead of matching the connection tracked
-	// on the first iteration.
-	m.stateful = false
-	benchManager = m
-	return m
-}
-
-// BenchmarkInbound_NormalPacket is the baseline: a full, non-fragmented UDP
-// packet that passes the ACL. Fragment paths should stay comparable to this.
-func BenchmarkInbound_NormalPacket(b *testing.B) {
-	setupBenchManager(b)
-	pkt := normalUDPPacket(b, 8080, 32)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_FirstFragmentAllowed measures the first-fragment path:
-// transport decode + ACL evaluation + verdict record.
-func BenchmarkInbound_FirstFragmentAllowed(b *testing.B) {
-	setupBenchManager(b)
-	pkt := firstFragmentUDP(b, 0x2000, 8080, 32)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TrailingFragmentAllowed measures the common trailing-fragment
-// path: a single map lookup after the first fragment is on record.
-func BenchmarkInbound_TrailingFragmentAllowed(b *testing.B) {
-	m := setupBenchManager(b)
-	first := firstFragmentUDP(b, 0x3000, 8080, 32)
-	m.filterInbound(first, len(first))
-	pkt := trailingFragment(b, 0x3000, 5, false, 24)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TrailingFragmentNoFirst is the primary DoS vector: an
-// attacker floods trailing fragments with no first fragment on record. Each is
-// a map miss and must be cheap.
-func BenchmarkInbound_TrailingFragmentNoFirst(b *testing.B) {
-	setupBenchManager(b)
-	pkt := trailingFragment(b, 0x4000, 185, false, 40)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TinyFirstFragment measures the tiny-fragment drop path: a
-// first fragment too small to decode a transport header.
-func BenchmarkInbound_TinyFirstFragment(b *testing.B) {
-	setupBenchManager(b)
-	pkt := trailingFragment(b, 0x5000, 0, true, 4)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TrailingFragmentDistinctIDs is the worst case for the
-// verdict table: an attacker varies the datagram id on every packet so no first
-// fragment ever matches. Verdict lookups always miss and nothing is recorded,
-// so the table cannot grow. Each iteration rewrites the id field in place.
-func BenchmarkInbound_TrailingFragmentDistinctIDs(b *testing.B) {
-	setupBenchManager(b)
-	pkt := trailingFragment(b, 0x6000, 185, false, 40)
-	m := benchManager
-
-	b.ReportAllocs()
-	b.SetBytes(int64(len(pkt)))
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		// IPv4 identification field is at bytes 4:6.
-		binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
-		m.filterInbound(pkt, len(pkt))
-	}
-}
-
-// BenchmarkInbound_FirstFragmentDistinctIDs measures sustained first-fragment
-// pressure with distinct ids: transport decode + ACL + verdict insert until the
-// table caps, exercising the map growth and capacity guard.
-func BenchmarkInbound_FirstFragmentDistinctIDs(b *testing.B) {
-	setupBenchManager(b)
-	pkt := firstFragmentUDP(b, 0x7000, 8080, 32)
-	m := benchManager
-
-	b.ReportAllocs()
-	b.SetBytes(int64(len(pkt)))
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
-		m.filterInbound(pkt, len(pkt))
-	}
-}

client/firewall/uspfilter/fragment_test.go

@@ -1,554 +0,0 @@
-package uspfilter
-
-import (
-	"encoding/binary"
-	"net"
-	"net/netip"
-	"testing"
-	"time"
-
-	"github.com/google/gopacket"
-	"github.com/google/gopacket/layers"
-	"github.com/stretchr/testify/require"
-
-	fw "github.com/netbirdio/netbird/client/firewall/manager"
-	nbiface "github.com/netbirdio/netbird/client/iface"
-	"github.com/netbirdio/netbird/client/iface/device"
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
-)
-
-const (
-	fragTestSrc   = "100.10.0.1"
-	fragTestDst   = "100.10.0.100"
-	fragTestSrcV6 = "fd00::1"
-	fragTestDstV6 = "fd00::100"
-)
-
-func newFragmentTestManager(tb testing.TB) *Manager {
-	tb.Helper()
-
-	ifaceMock := &IFaceMock{
-		SetFilterFunc: func(device.PacketFilter) error { return nil },
-		AddressFunc: func() wgaddr.Address {
-			return wgaddr.Address{
-				IP:      netip.MustParseAddr(fragTestDst),
-				Network: netip.MustParsePrefix("100.10.0.0/16"),
-				IPv6:    netip.MustParseAddr(fragTestDstV6),
-				IPv6Net: netip.MustParsePrefix("fd00::/64"),
-			}
-		},
-	}
-
-	m, err := Create(ifaceMock, false, flowLogger, nbiface.DefaultMTU)
-	require.NoError(tb, err)
-	require.NoError(tb, m.UpdateLocalIPs())
-	tb.Cleanup(func() { require.NoError(tb, m.Close(nil)) })
-	return m
-}
-
-// firstFragmentUDPTo builds the first fragment of a fragmented UDP datagram to
-// the given destination: it carries the full UDP header plus payloadLen bytes
-// of data, with the More Fragments flag set and offset zero.
-func firstFragmentUDPTo(tb testing.TB, dst string, id uint16, dstPort uint16, payloadLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       id,
-		Protocol: layers.IPProtocolUDP,
-		SrcIP:    net.ParseIP(fragTestSrc),
-		DstIP:    net.ParseIP(dst),
-		Flags:    layers.IPv4MoreFragments,
-	}
-	udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
-	require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
-	return buf.Bytes()
-}
-
-func firstFragmentUDP(tb testing.TB, id uint16, dstPort uint16, payloadLen int) []byte {
-	tb.Helper()
-	return firstFragmentUDPTo(tb, fragTestDst, id, dstPort, payloadLen)
-}
-
-// firstFragmentTCP builds the first fragment of a fragmented TCP datagram: the
-// full 20-byte TCP header plus 12 bytes of data, with the More Fragments flag
-// set and offset zero.
-func firstFragmentTCP(tb testing.TB, id uint16, dstPort uint16) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       id,
-		Protocol: layers.IPProtocolTCP,
-		SrcIP:    net.ParseIP(fragTestSrc),
-		DstIP:    net.ParseIP(fragTestDst),
-		Flags:    layers.IPv4MoreFragments,
-	}
-	tcp := &layers.TCP{SrcPort: 40000, DstPort: layers.TCPPort(dstPort), SYN: true, Window: 64240}
-	require.NoError(tb, tcp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, tcp, gopacket.Payload(make([]byte, 12))))
-	return buf.Bytes()
-}
-
-// trailingFragmentTo builds a non-first fragment to the given destination: an
-// IPv4 header at the given fragment offset (in 8-byte units) carrying raw
-// payload and no L4 header.
-func trailingFragmentTo(tb testing.TB, dst string, proto layers.IPProtocol, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:    4,
-		TTL:        64,
-		Id:         id,
-		Protocol:   proto,
-		SrcIP:      net.ParseIP(fragTestSrc),
-		DstIP:      net.ParseIP(dst),
-		FragOffset: fragOffsetOctets,
-	}
-	if moreFragments {
-		ip.Flags = layers.IPv4MoreFragments
-	}
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, gopacket.Payload(make([]byte, payloadLen))))
-	return buf.Bytes()
-}
-
-func trailingFragment(tb testing.TB, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
-	tb.Helper()
-	return trailingFragmentTo(tb, fragTestDst, layers.IPProtocolUDP, id, fragOffsetOctets, moreFragments, payloadLen)
-}
-
-// outboundUDPPacket builds a complete outbound UDP packet from the local
-// address, used to establish conntrack state for reply-direction tests.
-func outboundUDPPacket(tb testing.TB, srcPort, dstPort uint16) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       1,
-		Protocol: layers.IPProtocolUDP,
-		SrcIP:    net.ParseIP(fragTestDst),
-		DstIP:    net.ParseIP(fragTestSrc),
-	}
-	udp := &layers.UDP{SrcPort: layers.UDPPort(srcPort), DstPort: layers.UDPPort(dstPort)}
-	require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, 16))))
-	return buf.Bytes()
-}
-
-// normalUDPPacket builds a complete, non-fragmented UDP packet for baseline
-// comparisons against the fragment paths.
-func normalUDPPacket(tb testing.TB, dstPort uint16, payloadLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       1,
-		Protocol: layers.IPProtocolUDP,
-		SrcIP:    net.ParseIP(fragTestSrc),
-		DstIP:    net.ParseIP(fragTestDst),
-	}
-	udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
-	require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
-	return buf.Bytes()
-}
-
-func allowUDP(tb testing.TB, m *Manager, dstPort uint16) {
-	tb.Helper()
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolUDP, nil,
-		&fw.Port{Values: []uint16{dstPort}}, fw.ActionAccept, "")
-	require.NoError(tb, err)
-}
-
-// TestFragment_TrailingWithoutFirstDropped is the core bypass repro: a trailing
-// fragment with no allowed first fragment on record must be dropped. Before the
-// fix, filterInbound returned false (allow) for any fragment.
-func TestFragment_TrailingWithoutFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-
-	frag := trailingFragment(t, 0x1234, 185, false, 40)
-	require.True(t, m.filterInbound(frag, len(frag)),
-		"trailing fragment without an allowed first fragment must be dropped")
-}
-
-// TestFragment_AllowedFirstPassesTrailing verifies that once a first fragment
-// passes the ACL, its trailing fragments inherit the allow verdict.
-func TestFragment_AllowedFirstPassesTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	// First fragment: UDP header (8) + 32 payload = 40 octets -> headerEnd = 5.
-	first := firstFragmentUDP(t, 0x2222, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"allowed first fragment should pass and be recorded")
-
-	trailing := trailingFragment(t, 0x2222, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed datagram should pass")
-}
-
-// TestFragment_DeniedFirstDropsTrailing verifies that a first fragment blocked
-// by the ACL leaves no verdict, so its trailing fragments are dropped.
-func TestFragment_DeniedFirstDropsTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	// No accept rule: local traffic defaults to deny.
-
-	first := firstFragmentUDP(t, 0x3333, 9999, 32)
-	require.True(t, m.filterInbound(first, len(first)),
-		"first fragment to a blocked port should be dropped by the ACL")
-
-	trailing := trailingFragment(t, 0x3333, 5, false, 24)
-	require.True(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of a denied datagram must be dropped")
-}
-
-// TestFragment_OverlappingHeaderDropped covers the RFC 1858 §4 / RFC 3128
-// overlapping-fragment rewrite: a trailing fragment starting inside the range
-// the ACL already inspected is dropped and poisons the datagram. TCP is used so
-// the overlap lands on real header bytes (the flags at byte 13).
-func TestFragment_OverlappingHeaderDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	// First fragment: TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
-	first := firstFragmentTCP(t, 0x4444, 8080)
-	require.False(t, m.filterInbound(first, len(first)))
-
-	// Overlapping fragment at offset 1 (byte 8) falls inside the inspected TCP
-	// header, so it could rewrite the flags or port on reassembly.
-	overlap := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 1, true, 32)
-	require.True(t, m.filterInbound(overlap, len(overlap)),
-		"fragment overlapping the inspected header must be dropped")
-
-	// The datagram is now poisoned: a later, non-overlapping fragment is also
-	// dropped because the verdict was removed.
-	later := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 4, false, 24)
-	require.True(t, m.filterInbound(later, len(later)),
-		"fragments after an overlap must be dropped (datagram poisoned)")
-}
-
-// TestFragment_OffsetZeroOverlapPoisons covers the RFC 3128 offset-zero rewrite:
-// an allowed first fragment followed by a denied offset-zero fragment for the
-// same datagram must not leave the earlier allow verdict in place.
-func TestFragment_OffsetZeroOverlapPoisons(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	allowed := firstFragmentUDP(t, 0x5A5A, 8080, 32)
-	require.False(t, m.filterInbound(allowed, len(allowed)),
-		"allowed first fragment should pass and be recorded")
-
-	// A second offset-zero fragment to a denied port supersedes the datagram's
-	// verdict; it is dropped and must not leave the allow in place.
-	denied := firstFragmentUDP(t, 0x5A5A, 9999, 32)
-	require.True(t, m.filterInbound(denied, len(denied)),
-		"denied offset-zero fragment must be dropped")
-
-	trailing := trailingFragment(t, 0x5A5A, 5, false, 24)
-	require.True(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment must be denied after the datagram was poisoned")
-}
-
-// TestFragment_TinyFirstDropped covers the tiny-fragment attack: a first
-// fragment too small to contain the full transport header can't be
-// ACL-evaluated and must be dropped.
-func TestFragment_TinyFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	// IPv4 header + 4 raw bytes, MF set, offset 0: too small for the 8-byte UDP
-	// header, so it decodes to L3 only.
-	tiny := trailingFragment(t, 0x5555, 0, true, 4)
-	require.True(t, m.filterInbound(tiny, len(tiny)),
-		"tiny first fragment without a full L4 header must be dropped")
-}
-
-// TestFragment_TCPFirstFragment verifies the TCP arm of the transport decode: a
-// first fragment carrying the full 20-byte TCP header is ACL-evaluated and its
-// trailing fragments inherit the verdict.
-func TestFragment_TCPFirstFragment(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	// TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
-	first := firstFragmentTCP(t, 0x6666, 8080)
-	require.False(t, m.filterInbound(first, len(first)),
-		"allowed TCP first fragment should pass and be recorded")
-
-	trailing := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x6666, 4, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed TCP datagram should pass")
-}
-
-// TestFragment_TCPTinyFirstDropped verifies the TCP minimum header length: 12
-// bytes would satisfy a UDP header but falls short of the 20-byte TCP header.
-func TestFragment_TCPTinyFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	tiny := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x7777, 0, true, 12)
-	require.True(t, m.filterInbound(tiny, len(tiny)),
-		"first fragment shorter than the TCP header must be dropped")
-}
-
-// TestFragment_ConntrackAllowsFirstFragment verifies the conntrack branch: reply
-// fragments of an outbound-established UDP flow pass without any inbound rule.
-func TestFragment_ConntrackAllowsFirstFragment(t *testing.T) {
-	m := newFragmentTestManager(t)
-
-	out := outboundUDPPacket(t, 12345, 40000)
-	require.False(t, m.filterOutbound(out, len(out)))
-
-	first := firstFragmentUDP(t, 0x8888, 12345, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"reply first fragment should pass via conntrack")
-
-	trailing := trailingFragment(t, 0x8888, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of a tracked flow should pass")
-}
-
-// TestFragment_RoutingDisabledDropsFragment verifies routed first fragments are
-// dropped when routing is disabled.
-func TestFragment_RoutingDisabledDropsFragment(t *testing.T) {
-	m := newFragmentTestManager(t)
-	m.routingEnabled.Store(false)
-
-	first := firstFragmentUDPTo(t, "198.51.100.10", 0x9999, 8080, 32)
-	require.True(t, m.filterInbound(first, len(first)),
-		"routed first fragment must be dropped when routing is disabled")
-}
-
-// TestFragment_RouteACL verifies the route-ACL branch: fragments to a non-local
-// destination follow the route rules, allowed datagrams pass their trailing
-// fragments and denied ones don't.
-func TestFragment_RouteACL(t *testing.T) {
-	m := newFragmentTestManager(t)
-	m.routingEnabled.Store(true)
-	m.nativeRouter.Store(false)
-
-	_, err := m.AddRouteFiltering(
-		[]byte("rt-1"),
-		[]netip.Prefix{netip.MustParsePrefix("100.10.0.0/16")},
-		fw.Network{Prefix: netip.MustParsePrefix("198.51.100.0/24")},
-		fw.ProtocolUDP,
-		nil,
-		&fw.Port{Values: []uint16{8080}},
-		fw.ActionAccept,
-	)
-	require.NoError(t, err)
-
-	first := firstFragmentUDPTo(t, "198.51.100.10", 0xAAAA, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"route-ACL-allowed first fragment should pass")
-	trailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xAAAA, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed routed datagram should pass")
-
-	denied := firstFragmentUDPTo(t, "198.51.100.10", 0xBBBB, 9999, 32)
-	require.True(t, m.filterInbound(denied, len(denied)),
-		"route-ACL-denied first fragment must be dropped")
-	deniedTrailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xBBBB, 5, false, 24)
-	require.True(t, m.filterInbound(deniedTrailing, len(deniedTrailing)),
-		"trailing fragment of a denied routed datagram must be dropped")
-}
-
-// TestFragment_ExpiredVerdictDropsTrailing verifies a verdict older than the
-// tracker timeout no longer admits trailing fragments.
-func TestFragment_ExpiredVerdictDropsTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	first := firstFragmentUDP(t, 0xCCCC, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)))
-
-	m.fragments.mutex.Lock()
-	for key, entry := range m.fragments.entries {
-		entry.recordedAt = time.Now().Add(-defaultFragmentTimeout - time.Second)
-		m.fragments.entries[key] = entry
-	}
-	m.fragments.mutex.Unlock()
-
-	trailing := trailingFragment(t, 0xCCCC, 5, false, 24)
-	require.True(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment after verdict expiry must be dropped")
-}
-
-// TestFragment_CapacityFailsClosed verifies the table cap: at capacity, new
-// datagram verdicts are not recorded (their trailing fragments are dropped)
-// while already-recorded datagrams keep working.
-func TestFragment_CapacityFailsClosed(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	m.fragments.mutex.Lock()
-	m.fragments.maxEntries = 1
-	m.fragments.mutex.Unlock()
-
-	first1 := firstFragmentUDP(t, 0x0101, 8080, 32)
-	require.False(t, m.filterInbound(first1, len(first1)))
-
-	first2 := firstFragmentUDP(t, 0x0202, 8080, 32)
-	require.False(t, m.filterInbound(first2, len(first2)),
-		"first fragment itself still passes at capacity")
-
-	trailing2 := trailingFragment(t, 0x0202, 5, false, 24)
-	require.True(t, m.filterInbound(trailing2, len(trailing2)),
-		"trailing fragment of an unrecorded datagram must be dropped at capacity")
-
-	trailing1 := trailingFragment(t, 0x0101, 5, false, 24)
-	require.False(t, m.filterInbound(trailing1, len(trailing1)),
-		"already-recorded datagram should keep passing at capacity")
-}
-
-// v6FragmentHeader builds the 8-byte IPv6 fragment extension header for the
-// given inner protocol, offset (8-byte units), More Fragments bit and id.
-func v6FragmentHeader(proto layers.IPProtocol, offsetOctets uint16, moreFragments bool, id uint32) []byte {
-	offsetFlags := offsetOctets << 3
-	if moreFragments {
-		offsetFlags |= 1
-	}
-	hdr := make([]byte, 8)
-	hdr[0] = uint8(proto)
-	binary.BigEndian.PutUint16(hdr[2:4], offsetFlags)
-	binary.BigEndian.PutUint32(hdr[4:8], id)
-	return hdr
-}
-
-func v6UDPHeader(dstPort uint16, dataLen int) []byte {
-	hdr := make([]byte, 8)
-	binary.BigEndian.PutUint16(hdr[0:2], 40000)
-	binary.BigEndian.PutUint16(hdr[2:4], dstPort)
-	binary.BigEndian.PutUint16(hdr[4:6], uint16(8+dataLen))
-	return hdr
-}
-
-// firstFragmentUDPv6 builds the first fragment of a fragmented IPv6 UDP
-// datagram: fragment header (offset 0, More Fragments set) + full UDP header +
-// data.
-func firstFragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int) []byte {
-	tb.Helper()
-	return fragmentUDPv6(tb, id, dstPort, dataLen, true)
-}
-
-// fragmentUDPv6 builds an offset-zero IPv6 UDP fragment. With moreFragments
-// false it is an atomic fragment (a complete datagram, RFC 6946).
-func fragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int, moreFragments bool) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv6{
-		Version:    6,
-		NextHeader: layers.IPProtocolIPv6Fragment,
-		HopLimit:   64,
-		SrcIP:      net.ParseIP(fragTestSrcV6),
-		DstIP:      net.ParseIP(fragTestDstV6),
-	}
-	payload := append(v6FragmentHeader(layers.IPProtocolUDP, 0, moreFragments, id), v6UDPHeader(dstPort, dataLen)...)
-	payload = append(payload, make([]byte, dataLen)...)
-
-	buf := gopacket.NewSerializeBuffer()
-	require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
-	return buf.Bytes()
-}
-
-// trailingFragmentV6 builds a non-first IPv6 fragment: fragment header at the
-// given offset carrying raw data and no transport header.
-func trailingFragmentV6(tb testing.TB, id uint32, offsetOctets uint16, moreFragments bool, dataLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv6{
-		Version:    6,
-		NextHeader: layers.IPProtocolIPv6Fragment,
-		HopLimit:   64,
-		SrcIP:      net.ParseIP(fragTestSrcV6),
-		DstIP:      net.ParseIP(fragTestDstV6),
-	}
-	payload := append(v6FragmentHeader(layers.IPProtocolUDP, offsetOctets, moreFragments, id), make([]byte, dataLen)...)
-
-	buf := gopacket.NewSerializeBuffer()
-	require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
-	return buf.Bytes()
-}
-
-// TestFragmentV6_TrailingWithoutFirstDropped verifies the IPv6 bypass is closed:
-// a trailing fragment with no allowed first fragment is dropped.
-func TestFragmentV6_TrailingWithoutFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-
-	frag := trailingFragmentV6(t, 0xAABBCCDD, 100, false, 40)
-	require.True(t, m.filterInbound(frag, len(frag)),
-		"IPv6 trailing fragment without an allowed first fragment must be dropped")
-}
-
-// TestFragmentV6_AllowedFirstPassesTrailing verifies IPv6 fragments are
-// evaluated like IPv4: an allowed first fragment lets its trailing fragments
-// through.
-func TestFragmentV6_AllowedFirstPassesTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	// First fragment: UDP header (8) + 32 data = 40 octets -> headerEnd = 5.
-	first := firstFragmentUDPv6(t, 0xAABBCCDD, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"allowed IPv6 first fragment should pass and be recorded")
-
-	trailing := trailingFragmentV6(t, 0xAABBCCDD, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed IPv6 datagram should pass")
-}
-
-// TestFragmentV6_AtomicNotCached verifies an IPv6 atomic fragment (fragment
-// header with offset 0 and no More Fragments, a complete datagram per RFC 6946)
-// is evaluated but not recorded, so a flood of allowed atomic fragments can't
-// exhaust the verdict table.
-func TestFragmentV6_AtomicNotCached(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	atomic := fragmentUDPv6(t, 0xA70301C, 8080, 16, false)
-	require.False(t, m.filterInbound(atomic, len(atomic)),
-		"allowed IPv6 atomic fragment should pass")
-
-	m.fragments.mutex.Lock()
-	n := len(m.fragments.entries)
-	m.fragments.mutex.Unlock()
-	require.Zero(t, n, "atomic fragment must not create a verdict entry")
-
-	// A genuine fragmented datagram (More Fragments set) is still recorded.
-	first := fragmentUDPv6(t, 0xBEEF, 8080, 32, true)
-	require.False(t, m.filterInbound(first, len(first)))
-	m.fragments.mutex.Lock()
-	n = len(m.fragments.entries)
-	m.fragments.mutex.Unlock()
-	require.Equal(t, 1, n, "genuine first fragment must record a verdict")
-}

client/iface/configurer/kernel_unix.go

@@ -17,15 +17,12 @@ import (
 
 type KernelConfigurer struct {
 	deviceName string
-	statsCache *statsCache
 }
 
 func NewKernelConfigurer(deviceName string) *KernelConfigurer {
-	c := &KernelConfigurer{
+	return &KernelConfigurer{
 		deviceName: deviceName,
 	}
-	c.statsCache = newStatsCache(statsCacheTTL, c.fetchStats)
-	return c
 }
 
 func (c *KernelConfigurer) ConfigureInterface(privateKey string, port int) error {
@@ -249,6 +246,12 @@ func (c *KernelConfigurer) configure(config wgtypes.Config) error {
 		}
 	}()
 
+	// validate if device with name exists
+	_, err = wg.Device(c.deviceName)
+	if err != nil {
+		return err
+	}
+
 	return wg.ConfigureDevice(c.deviceName, config)
 }
 
@@ -297,14 +300,6 @@ func (c *KernelConfigurer) FullStats() (*Stats, error) {
 }
 
 func (c *KernelConfigurer) GetStats() (map[string]WGStats, error) {
-	return c.statsCache.get()
-}
-
-func (c *KernelConfigurer) LastActivities() map[string]monotime.Time {
-	return nil
-}
-
-func (c *KernelConfigurer) fetchStats() (map[string]WGStats, error) {
 	stats := make(map[string]WGStats)
 	wg, err := wgctrl.New()
 	if err != nil {
@@ -331,3 +326,7 @@ func (c *KernelConfigurer) fetchStats() (map[string]WGStats, error) {
 	}
 	return stats, nil
 }
+
+func (c *KernelConfigurer) LastActivities() map[string]monotime.Time {
+	return nil
+}

client/iface/configurer/stats_cache.go

@@ -1,52 +0,0 @@
-package configurer
-
-import (
-	"sync"
-	"time"
-
-	"golang.org/x/sync/singleflight"
-)
-
-const statsCacheTTL = 1 * time.Second
-
-type statsCache struct {
-	ttl   time.Duration
-	fetch func() (map[string]WGStats, error)
-
-	mu       sync.RWMutex
-	value    map[string]WGStats
-	expireAt time.Time
-
-	sf singleflight.Group
-}
-
-func newStatsCache(ttl time.Duration, fetch func() (map[string]WGStats, error)) *statsCache {
-	return &statsCache{ttl: ttl, fetch: fetch}
-}
-
-func (c *statsCache) get() (map[string]WGStats, error) {
-	c.mu.RLock()
-	if c.value != nil && time.Now().Before(c.expireAt) {
-		value := c.value
-		c.mu.RUnlock()
-		return value, nil
-	}
-	c.mu.RUnlock()
-
-	value, err, _ := c.sf.Do("stats", func() (interface{}, error) {
-		res, err := c.fetch()
-		if err != nil {
-			return nil, err
-		}
-
-		c.mu.Lock()
-		c.value = res
-		c.expireAt = time.Now().Add(c.ttl)
-		c.mu.Unlock()
-		return res, nil
-	})
-	if err != nil {
-		return nil, err
-	}
-	return value.(map[string]WGStats), nil
-}

client/iface/configurer/stats_cache_test.go

@@ -1,70 +0,0 @@
-package configurer
-
-import (
-	"errors"
-	"sync"
-	"sync/atomic"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/require"
-)
-
-func TestStatsCache_CachesWithinTTL(t *testing.T) {
-	var calls atomic.Int64
-	c := newStatsCache(50*time.Millisecond, func() (map[string]WGStats, error) {
-		calls.Add(1)
-		return map[string]WGStats{"p": {}}, nil
-	})
-
-	for i := 0; i < 10; i++ {
-		_, err := c.get()
-		require.NoError(t, err)
-	}
-	require.Equal(t, int64(1), calls.Load(), "within TTL only one underlying fetch")
-
-	time.Sleep(60 * time.Millisecond)
-	_, err := c.get()
-	require.NoError(t, err)
-	require.Equal(t, int64(2), calls.Load(), "after TTL expiry a fresh fetch happens")
-}
-
-func TestStatsCache_SingleFlight(t *testing.T) {
-	var calls atomic.Int64
-	release := make(chan struct{})
-	c := newStatsCache(time.Minute, func() (map[string]WGStats, error) {
-		calls.Add(1)
-		<-release
-		return map[string]WGStats{}, nil
-	})
-
-	const n = 50
-	var wg sync.WaitGroup
-	wg.Add(n)
-	for i := 0; i < n; i++ {
-		go func() {
-			defer wg.Done()
-			_, _ = c.get()
-		}()
-	}
-	time.Sleep(20 * time.Millisecond)
-	close(release)
-	wg.Wait()
-
-	require.Equal(t, int64(1), calls.Load(), "concurrent misses collapse into one fetch")
-}
-
-func TestStatsCache_ErrorNotCached(t *testing.T) {
-	var calls atomic.Int64
-	wantErr := errors.New("dump failed")
-	c := newStatsCache(time.Minute, func() (map[string]WGStats, error) {
-		calls.Add(1)
-		return nil, wantErr
-	})
-
-	_, err := c.get()
-	require.ErrorIs(t, err, wantErr)
-	_, err = c.get()
-	require.ErrorIs(t, err, wantErr)
-	require.Equal(t, int64(2), calls.Load(), "errors are not cached; each call retries")
-}

client/iface/configurer/usp.go

@@ -40,7 +40,6 @@ type WGUSPConfigurer struct {
 	device           *device.Device
 	deviceName       string
 	activityRecorder *bind.ActivityRecorder
-	statsCache       *statsCache
 
 	uapiListener net.Listener
 }
@@ -51,19 +50,16 @@ func NewUSPConfigurer(device *device.Device, deviceName string, activityRecorder
 		deviceName:       deviceName,
 		activityRecorder: activityRecorder,
 	}
-	wgCfg.statsCache = newStatsCache(statsCacheTTL, wgCfg.fetchStats)
 	wgCfg.startUAPI()
 	return wgCfg
 }
 
 func NewUSPConfigurerNoUAPI(device *device.Device, deviceName string, activityRecorder *bind.ActivityRecorder) *WGUSPConfigurer {
-	wgCfg := &WGUSPConfigurer{
+	return &WGUSPConfigurer{
 		device:           device,
 		deviceName:       deviceName,
 		activityRecorder: activityRecorder,
 	}
-	wgCfg.statsCache = newStatsCache(statsCacheTTL, wgCfg.fetchStats)
-	return wgCfg
 }
 
 func (c *WGUSPConfigurer) ConfigureInterface(privateKey string, port int) error {
@@ -352,10 +348,6 @@ func (t *WGUSPConfigurer) Close() {
 }
 
 func (t *WGUSPConfigurer) GetStats() (map[string]WGStats, error) {
-	return t.statsCache.get()
-}
-
-func (t *WGUSPConfigurer) fetchStats() (map[string]WGStats, error) {
 	ipc, err := t.device.IpcGet()
 	if err != nil {
 		return nil, fmt.Errorf("ipc get: %w", err)

client/iface/iface_test.go

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

client/iface/netstack/env.go

@@ -3,31 +3,14 @@
 package netstack
 
 import (
-	"net"
+	"fmt"
 	"os"
 	"strconv"
 
 	log "github.com/sirupsen/logrus"
 )
 
-const (
-	EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
-
-	// EnvSocks5ListenerPort overrides the port the SOCKS5 proxy listens on.
-	EnvSocks5ListenerPort = "NB_SOCKS5_LISTENER_PORT"
-
-	// EnvSocks5ListenerAddress overrides the host/IP the SOCKS5 proxy binds to.
-	// The proxy is a bridge for local host applications into the userspace
-	// WireGuard netstack, so it binds to loopback by default. Override this only
-	// when the proxy must be reachable from other hosts (e.g. a container
-	// gateway); doing so exposes an unauthenticated SOCKS5 proxy on that
-	// address.
-	EnvSocks5ListenerAddress = "NB_SOCKS5_LISTENER_ADDRESS"
-
-	// defaultSocks5Host is the loopback address the SOCKS5 proxy binds to unless
-	// overridden via EnvSocks5ListenerAddress.
-	defaultSocks5Host = "127.0.0.1"
-)
+const EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
 
 // IsEnabled todo: move these function to cmd layer
 func IsEnabled() bool {
@@ -35,40 +18,24 @@ func IsEnabled() bool {
 }
 
 func ListenAddr() string {
-	return net.JoinHostPort(listenHost(), strconv.Itoa(listenPort()))
-}
-
-// listenHost returns the host/IP the SOCKS5 proxy binds to. It defaults to
-// loopback and only honors EnvSocks5ListenerAddress when it holds a valid IP.
-func listenHost() string {
-	addr := os.Getenv(EnvSocks5ListenerAddress)
-	if addr == "" {
-		return defaultSocks5Host
-	}
-	if net.ParseIP(addr) == nil {
-		log.Warnf("invalid socks5 listener address %q, falling back to default: %s", addr, defaultSocks5Host)
-		return defaultSocks5Host
-	}
-	return addr
-}
-
-// listenPort returns the port the SOCKS5 proxy binds to, defaulting to
-// DefaultSocks5Port when EnvSocks5ListenerPort is unset or invalid.
-func listenPort() int {
-	sPort := os.Getenv(EnvSocks5ListenerPort)
+	sPort := os.Getenv("NB_SOCKS5_LISTENER_PORT")
 	if sPort == "" {
-		return DefaultSocks5Port
+		return listenAddr(DefaultSocks5Port)
 	}
 
 	port, err := strconv.Atoi(sPort)
 	if err != nil {
 		log.Warnf("invalid socks5 listener port, unable to convert it to int, falling back to default: %d", DefaultSocks5Port)
-		return DefaultSocks5Port
+		return listenAddr(DefaultSocks5Port)
 	}
 	if port < 1 || port > 65535 {
 		log.Warnf("invalid socks5 listener port, it should be in the range 1-65535, falling back to default: %d", DefaultSocks5Port)
-		return DefaultSocks5Port
+		return listenAddr(DefaultSocks5Port)
 	}
 
-	return port
+	return listenAddr(port)
+}
+
+func listenAddr(port int) string {
+	return fmt.Sprintf("0.0.0.0:%d", port)
 }

client/iface/netstack/env_test.go

@@ -1,63 +0,0 @@
-//go:build !js
-
-package netstack
-
-import (
-	"net"
-	"strconv"
-	"testing"
-)
-
-func TestListenAddr_DefaultsToLoopback(t *testing.T) {
-	// No env overrides: must bind loopback, never all interfaces.
-	got := ListenAddr()
-	want := net.JoinHostPort("127.0.0.1", strconv.Itoa(DefaultSocks5Port))
-	if got != want {
-		t.Fatalf("ListenAddr() = %q, want %q", got, want)
-	}
-}
-
-func TestListenAddr_AddressOverride(t *testing.T) {
-	tests := []struct {
-		name string
-		env  string
-		want string
-	}{
-		{name: "valid override honored", env: "0.0.0.0", want: "0.0.0.0"},
-		{name: "valid specific ip honored", env: "10.0.0.5", want: "10.0.0.5"},
-		{name: "ipv6 loopback bracketed", env: "::1", want: "::1"},
-		{name: "invalid falls back to loopback", env: "not-an-ip", want: "127.0.0.1"},
-		{name: "empty falls back to loopback", env: "", want: "127.0.0.1"},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(EnvSocks5ListenerAddress, tc.env)
-			want := net.JoinHostPort(tc.want, strconv.Itoa(DefaultSocks5Port))
-			if got := ListenAddr(); got != want {
-				t.Fatalf("ListenAddr() = %q, want %q", got, want)
-			}
-		})
-	}
-}
-
-func TestListenAddr_PortOverride(t *testing.T) {
-	tests := []struct {
-		name string
-		env  string
-		want int
-	}{
-		{name: "valid port honored", env: "1081", want: 1081},
-		{name: "non-numeric falls back", env: "abc", want: DefaultSocks5Port},
-		{name: "out of range falls back", env: "70000", want: DefaultSocks5Port},
-		{name: "zero falls back", env: "0", want: DefaultSocks5Port},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(EnvSocks5ListenerPort, tc.env)
-			want := net.JoinHostPort("127.0.0.1", strconv.Itoa(tc.want))
-			if got := ListenAddr(); got != want {
-				t.Fatalf("ListenAddr() = %q, want %q", got, want)
-			}
-		})
-	}
-}

client/iface/wgproxy/bind/proxy.go

@@ -136,11 +136,6 @@ func (p *ProxyBind) CloseConn() error {
 	return p.close()
 }
 
-// InjectPacket is a no-op for the userspace proxy: first-packet reinjection is kernel-only.
-func (p *ProxyBind) InjectPacket(_ []byte) error {
-	return nil
-}
-
 func (p *ProxyBind) close() error {
 	if p.remoteConn == nil {
 		return nil

client/iface/wgproxy/ebpf/wrapper.go

@@ -219,17 +219,6 @@ func (p *ProxyWrapper) RedirectAs(endpoint *net.UDPAddr) {
 	p.pausedCond.L.Unlock()
 }
 
-// InjectPacket writes b to the remote peer over the underlying transport.
-func (p *ProxyWrapper) InjectPacket(b []byte) error {
-	if p.remoteConn == nil {
-		return errors.New("proxy not started")
-	}
-	if _, err := p.remoteConn.Write(b); err != nil {
-		return err
-	}
-	return nil
-}
-
 // CloseConn close the remoteConn and automatically remove the conn instance from the map
 func (p *ProxyWrapper) CloseConn() error {
 	if p.cancel == nil {

client/iface/wgproxy/proxy.go

@@ -18,9 +18,4 @@ type Proxy interface {
 	RedirectAs(endpoint *net.UDPAddr)
 	CloseConn() error
 	SetDisconnectListener(disconnected func())
-
-	// InjectPacket writes a raw packet directly to the remote peer over the underlying transport,
-	// bypassing WireGuard. Used to replay the captured lazyconn handshake initiation. Only the
-	// kernel-mode proxies act on it; the userspace proxy is a no-op since reinjection is kernel-only.
-	InjectPacket(b []byte) error
 }

client/iface/wgproxy/proxy_linux_test.go

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

client/iface/wgproxy/proxy_seed_test.go

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

client/iface/wgproxy/redirect_test.go

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

client/iface/wgproxy/udp/proxy.go

@@ -147,17 +147,6 @@ func (p *WGUDPProxy) RedirectAs(endpoint *net.UDPAddr) {
 	p.sendPkg = p.srcFakerConn.SendPkg
 }
 
-// InjectPacket writes b to the remote peer over the underlying transport.
-func (p *WGUDPProxy) InjectPacket(b []byte) error {
-	if p.remoteConn == nil {
-		return errors.New("proxy not started")
-	}
-	if _, err := p.remoteConn.Write(b); err != nil {
-		return err
-	}
-	return nil
-}
-
 // CloseConn close the localConn
 func (p *WGUDPProxy) CloseConn() error {
 	if p.cancel == nil {

client/installer.nsis

@@ -79,6 +79,8 @@ ShowInstDetails Show
 
 !insertmacro MUI_PAGE_DIRECTORY
 
+Page custom AutostartPage AutostartPageLeave
+
 !insertmacro MUI_PAGE_INSTFILES
 
 !insertmacro MUI_PAGE_FINISH
@@ -95,12 +97,40 @@ UninstPage custom un.DeleteDataPage un.DeleteDataPageLeave
 
 !insertmacro MUI_LANGUAGE "English"
 
+; Variables for autostart option
+Var AutostartCheckbox
+Var AutostartEnabled
+
 ; Variables for uninstall data deletion option
 Var DeleteDataCheckbox
 Var DeleteDataEnabled
 
 ######################################################################
 
+; Function to create the autostart options page
+Function AutostartPage
+  !insertmacro MUI_HEADER_TEXT "Startup Options" "Configure how ${APP_NAME} launches with Windows."
+
+  nsDialogs::Create 1018
+  Pop $0
+
+  ${If} $0 == error
+    Abort
+  ${EndIf}
+
+  ${NSD_CreateCheckbox} 0 20u 100% 10u "Start ${APP_NAME} UI automatically when Windows starts"
+  Pop $AutostartCheckbox
+  ${NSD_Check} $AutostartCheckbox
+  StrCpy $AutostartEnabled "1"
+
+  nsDialogs::Show
+FunctionEnd
+
+; Function to handle leaving the autostart page
+Function AutostartPageLeave
+  ${NSD_GetState} $AutostartCheckbox $AutostartEnabled
+FunctionEnd
+
 ; Function to create the uninstall data deletion page
 Function un.DeleteDataPage
   !insertmacro MUI_HEADER_TEXT "Uninstall Options" "Choose whether to delete ${APP_NAME} data."
@@ -171,6 +201,8 @@ Pop $0
 
 Function .onInit
 StrCpy $INSTDIR "${INSTALL_DIR}"
+; Default autostart to enabled so silent installs (/S) match the interactive default
+StrCpy $AutostartEnabled "1"
 
 ; Pre-0.70.1 installers ran without SetRegView, so their uninstall keys live
 ; in the 32-bit view. Fall back to it so upgrades still find them.
@@ -228,12 +260,17 @@ WriteRegStr ${REG_ROOT} "${UNINSTALL_PATH}"  "Publisher" "${COMP_NAME}"
 
 WriteRegStr ${REG_ROOT} "${UI_REG_APP_PATH}" "" "$INSTDIR\${UI_APP_EXE}"
 
-; Autostart is owned by the UI's per-user setting (HKCU\...\Run via Wails),
-; not the installer. Drop the machine-wide entry older installers wrote so the
-; toggle is the single source of truth. HKCU is left untouched -- it may hold
-; the user's own toggle state, which must survive upgrades.
-DetailPrint "Removing installer-managed autostart registry entry if present..."
-DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+; Create autostart registry entry based on checkbox
+DetailPrint "Autostart enabled: $AutostartEnabled"
+${If} $AutostartEnabled == "1"
+    WriteRegStr HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}" '"$INSTDIR\${UI_APP_EXE}.exe"'
+    DetailPrint "Added autostart registry entry: $INSTDIR\${UI_APP_EXE}.exe"
+${Else}
+    DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+    ; Legacy: pre-HKLM installs wrote to HKCU; clean that up too.
+    DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
+    DetailPrint "Autostart not enabled by user"
+${EndIf}
 
 EnVar::SetHKLM
 EnVar::AddValueEx "path" "$INSTDIR"
@@ -299,14 +336,11 @@ ExecWait '"$INSTDIR\${MAIN_APP_EXE}" service uninstall'
 DetailPrint "Terminating Netbird UI process..."
 ExecWait `taskkill /im ${UI_APP_EXE}.exe /f`
 
-; Remove autostart registry entries
-DetailPrint "Removing autostart registry entries if they exist..."
-; Legacy machine-wide entry written by older installers.
+; Remove autostart registry entry
+DetailPrint "Removing autostart registry entry if exists..."
 DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-; Per-user entry the UI toggle writes via Wails (value name is the lowercase
-; app-name slug). Uninstall removes the app, so drop it too.
+; Legacy: pre-HKLM installs wrote to HKCU; clean that up too.
 DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}"
-DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "netbird"
 
 ; Handle data deletion based on checkbox
 DetailPrint "Checking if user requested data deletion..."

client/internal/acl/manager.go

@@ -11,7 +11,6 @@ import (
 	"time"
 
 	"github.com/hashicorp/go-multierror"
-	"github.com/mitchellh/hashstructure/v2"
 	log "github.com/sirupsen/logrus"
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
@@ -31,13 +30,11 @@ type Manager interface {
 
 // DefaultManager uses firewall manager to handle
 type DefaultManager struct {
-	firewall           firewall.Manager
-	ipsetCounter       int
-	peerRulesPairs     map[id.RuleID][]firewall.Rule
-	routeRules         map[id.RuleID]struct{}
-	previousConfigHash uint64
-	hasAppliedConfig   bool
-	mutex              sync.Mutex
+	firewall       firewall.Manager
+	ipsetCounter   int
+	peerRulesPairs map[id.RuleID][]firewall.Rule
+	routeRules     map[id.RuleID]struct{}
+	mutex          sync.Mutex
 }
 
 func NewDefaultManager(fm firewall.Manager) *DefaultManager {
@@ -60,23 +57,6 @@ func (d *DefaultManager) ApplyFiltering(networkMap *mgmProto.NetworkMap, dnsRout
 		return
 	}
 
-	// Skip the full rebuild + flush when the inputs that drive the firewall
-	// state are byte-for-byte identical to the last successfully applied
-	// update. Management re-sends the same network map far more often than it
-	// actually changes (account-wide updates, peer meta churn), and rebuilding
-	// every peer/route ACL and flushing the firewall on every such sync is the
-	// dominant client-side cost when nothing changed. Mirrors the same guard the
-	// DNS server already uses (previousConfigHash). Only the fields ApplyFiltering
-	// consumes participate in the hash, so an unrelated map change cannot mask a
-	// real ACL change.
-	hash, err := d.firewallConfigHash(networkMap, dnsRouteFeatureFlag)
-	if err != nil {
-		log.Errorf("unable to hash firewall configuration, applying unconditionally: %v", err)
-	} else if d.hasAppliedConfig && d.previousConfigHash == hash {
-		log.Debugf("not applying the firewall configuration update as there is nothing new (hash: %d)", hash)
-		return
-	}
-
 	start := time.Now()
 	defer func() {
 		total := 0
@@ -90,49 +70,13 @@ func (d *DefaultManager) ApplyFiltering(networkMap *mgmProto.NetworkMap, dnsRout
 
 	d.applyPeerACLs(networkMap)
 
-	routeErr := d.applyRouteACLs(networkMap.RoutesFirewallRules, dnsRouteFeatureFlag)
-	if routeErr != nil {
-		log.Errorf("Failed to apply route ACLs: %v", routeErr)
+	if err := d.applyRouteACLs(networkMap.RoutesFirewallRules, dnsRouteFeatureFlag); err != nil {
+		log.Errorf("Failed to apply route ACLs: %v", err)
 	}
 
-	flushErr := d.firewall.Flush()
-	if flushErr != nil {
-		log.Error("failed to flush firewall rules: ", flushErr)
+	if err := d.firewall.Flush(); err != nil {
+		log.Error("failed to flush firewall rules: ", err)
 	}
-
-	// Only remember the hash once the firewall actually reflects this config.
-	// If applying or flushing failed, leave the previous hash untouched so the
-	// next (possibly identical) update is not skipped and gets a chance to
-	// reconcile the firewall state.
-	if err == nil && routeErr == nil && flushErr == nil {
-		d.previousConfigHash = hash
-		d.hasAppliedConfig = true
-	} else {
-		d.hasAppliedConfig = false
-	}
-}
-
-// firewallConfigHash hashes exactly the inputs ApplyFiltering uses to build the
-// firewall state, so an identical hash means an identical resulting ruleset.
-func (d *DefaultManager) firewallConfigHash(networkMap *mgmProto.NetworkMap, dnsRouteFeatureFlag bool) (uint64, error) {
-	return hashstructure.Hash(struct {
-		PeerRules            []*mgmProto.FirewallRule
-		PeerRulesIsEmpty     bool
-		RouteRules           []*mgmProto.RouteFirewallRule
-		RouteRulesIsEmpty    bool
-		DNSRouteFeatureFlag  bool
-	}{
-		PeerRules:           networkMap.GetFirewallRules(),
-		PeerRulesIsEmpty:    networkMap.GetFirewallRulesIsEmpty(),
-		RouteRules:          networkMap.GetRoutesFirewallRules(),
-		RouteRulesIsEmpty:   networkMap.GetRoutesFirewallRulesIsEmpty(),
-		DNSRouteFeatureFlag: dnsRouteFeatureFlag,
-	}, hashstructure.FormatV2, &hashstructure.HashOptions{
-		ZeroNil:         true,
-		IgnoreZeroValue: true,
-		SlicesAsSets:    true,
-		UseStringer:     true,
-	})
 }
 
 func (d *DefaultManager) applyPeerACLs(networkMap *mgmProto.NetworkMap) {

client/internal/acl/manager_test.go

@@ -1,7 +1,6 @@
 package acl
 
 import (
-	"fmt"
 	"net/netip"
 	"testing"
 
@@ -486,149 +485,3 @@ func TestPortInfoEmpty(t *testing.T) {
 		})
 	}
 }
-
-// TestApplyFilteringSkipsUnchangedConfig verifies that an identical network map
-// re-applied is recognized as a no-op (hash unchanged), while a real change to
-// any firewall-relevant input forces a re-apply (hash changes). This is the
-// guard that prevents a full ruleset rebuild + flush on every redundant sync.
-func TestApplyFilteringSkipsUnchangedConfig(t *testing.T) {
-	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
-	t.Setenv(firewall.EnvForceUserspaceFirewall, "true")
-
-	ctrl := gomock.NewController(t)
-	defer ctrl.Finish()
-
-	ifaceMock := mocks.NewMockIFaceMapper(ctrl)
-	ifaceMock.EXPECT().IsUserspaceBind().Return(true).AnyTimes()
-	ifaceMock.EXPECT().SetFilter(gomock.Any())
-	network := netip.MustParsePrefix("172.0.0.1/32")
-	ifaceMock.EXPECT().Name().Return("lo").AnyTimes()
-	ifaceMock.EXPECT().Address().Return(wgaddr.Address{
-		IP:      network.Addr(),
-		Network: network,
-	}).AnyTimes()
-	ifaceMock.EXPECT().GetWGDevice().Return(nil).AnyTimes()
-
-	fw, err := firewall.NewFirewall(ifaceMock, nil, flowLogger, false, iface.DefaultMTU)
-	require.NoError(t, err)
-	defer func() {
-		require.NoError(t, fw.Close(nil))
-	}()
-
-	acl := NewDefaultManager(fw)
-
-	networkMap := &mgmProto.NetworkMap{
-		FirewallRules: []*mgmProto.FirewallRule{
-			{
-				PeerIP:    "10.93.0.1",
-				Direction: mgmProto.RuleDirection_IN,
-				Action:    mgmProto.RuleAction_ACCEPT,
-				Protocol:  mgmProto.RuleProtocol_TCP,
-				Port:      "22",
-			},
-		},
-		FirewallRulesIsEmpty: false,
-	}
-
-	acl.ApplyFiltering(networkMap, false)
-	require.True(t, acl.hasAppliedConfig, "config should be marked applied after first apply")
-	firstHash := acl.previousConfigHash
-	require.NotZero(t, firstHash)
-
-	// Re-applying the identical map must not change the recorded hash: the
-	// expensive rebuild path was skipped.
-	acl.ApplyFiltering(networkMap, false)
-	assert.Equal(t, firstHash, acl.previousConfigHash,
-		"identical re-apply must be a no-op (hash unchanged)")
-
-	// A real change must produce a different hash and re-apply.
-	networkMap.FirewallRules[0].Action = mgmProto.RuleAction_DROP
-	acl.ApplyFiltering(networkMap, false)
-	assert.NotEqual(t, firstHash, acl.previousConfigHash,
-		"changing a rule's action must force a re-apply (hash changed)")
-
-	// The dnsRouteFeatureFlag also participates in the hash.
-	changedHash := acl.previousConfigHash
-	acl.ApplyFiltering(networkMap, true)
-	assert.NotEqual(t, changedHash, acl.previousConfigHash,
-		"flipping dnsRouteFeatureFlag must force a re-apply (hash changed)")
-}
-
-func buildNetworkMap(peerRules, routeRules int) *mgmProto.NetworkMap {
-	nm := &mgmProto.NetworkMap{
-		FirewallRulesIsEmpty:      peerRules == 0,
-		RoutesFirewallRulesIsEmpty: routeRules == 0,
-	}
-	for i := range peerRules {
-		nm.FirewallRules = append(nm.FirewallRules, &mgmProto.FirewallRule{
-			PeerIP:    fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff),
-			Direction: mgmProto.RuleDirection_IN,
-			Action:    mgmProto.RuleAction_ACCEPT,
-			Protocol:  mgmProto.RuleProtocol_TCP,
-			Port:      fmt.Sprintf("%d", 1024+i%64511),
-		})
-	}
-	for i := range routeRules {
-		nm.RoutesFirewallRules = append(nm.RoutesFirewallRules, &mgmProto.RouteFirewallRule{
-			Destination:  fmt.Sprintf("192.168.%d.0/24", i%256),
-			SourceRanges: []string{fmt.Sprintf("10.0.%d.0/24", i%256)},
-			Action:       mgmProto.RuleAction_ACCEPT,
-			Protocol:     mgmProto.RuleProtocol_ALL,
-		})
-	}
-	return nm
-}
-
-func BenchmarkFirewallConfigHash_Small(b *testing.B) {
-	d := &DefaultManager{}
-	nm := buildNetworkMap(10, 5)
-	b.ResetTimer()
-	for b.Loop() {
-		_, _ = d.firewallConfigHash(nm, false)
-	}
-}
-
-func BenchmarkFirewallConfigHash_Medium(b *testing.B) {
-	d := &DefaultManager{}
-	nm := buildNetworkMap(100, 50)
-	b.ResetTimer()
-	for b.Loop() {
-		_, _ = d.firewallConfigHash(nm, false)
-	}
-}
-
-func BenchmarkFirewallConfigHash_Large(b *testing.B) {
-	d := &DefaultManager{}
-	nm := buildNetworkMap(1000, 200)
-	b.ResetTimer()
-	for b.Loop() {
-		_, _ = d.firewallConfigHash(nm, false)
-	}
-}
-
-// TestFirewallConfigHashDeterministic verifies the hash is stable for equal
-// inputs and order-independent for the rule slices (management does not
-// guarantee rule order).
-func TestFirewallConfigHashDeterministic(t *testing.T) {
-	d := &DefaultManager{}
-
-	nm1 := &mgmProto.NetworkMap{
-		FirewallRules: []*mgmProto.FirewallRule{
-			{PeerIP: "10.0.0.1", Direction: mgmProto.RuleDirection_IN, Action: mgmProto.RuleAction_ACCEPT, Protocol: mgmProto.RuleProtocol_TCP, Port: "22"},
-			{PeerIP: "10.0.0.2", Direction: mgmProto.RuleDirection_IN, Action: mgmProto.RuleAction_DROP, Protocol: mgmProto.RuleProtocol_TCP, Port: "80"},
-		},
-	}
-	// Same rules, reversed order.
-	nm2 := &mgmProto.NetworkMap{
-		FirewallRules: []*mgmProto.FirewallRule{
-			nm1.FirewallRules[1],
-			nm1.FirewallRules[0],
-		},
-	}
-
-	h1, err := d.firewallConfigHash(nm1, false)
-	require.NoError(t, err)
-	h2, err := d.firewallConfigHash(nm2, false)
-	require.NoError(t, err)
-	assert.Equal(t, h1, h2, "hash must be order-independent for rule slices")
-}

client/internal/auth/auth.go

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

client/internal/auth/device_flow.go

@@ -259,18 +259,12 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 	ticker := time.NewTicker(interval)
 	defer ticker.Stop()
 
-	log.Infof("device flow: waiting for user authorization, polling token endpoint every %s, code expires in %s", interval, timeout)
-
-	start := time.Now()
-	polls := 0
-
 	for {
 		select {
 		case <-waitCtx.Done():
 			return TokenInfo{}, waitCtx.Err()
 		case <-ticker.C:
 
-			polls++
 			tokenResponse, err := d.requestToken(info)
 			if err != nil {
 				return TokenInfo{}, fmt.Errorf("parsing token response failed with error: %v", err)
@@ -278,12 +272,10 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 
 			if tokenResponse.Error != "" {
 				if tokenResponse.Error == "authorization_pending" {
-					log.Tracef("device flow: authorization still pending after poll %d", polls)
 					continue
 				} else if tokenResponse.Error == "slow_down" {
 					interval += (3 * time.Second)
 					ticker.Reset(interval)
-					log.Infof("device flow: IdP requested slow_down, polling interval increased to %s", interval)
 					continue
 				}
 
@@ -299,12 +291,11 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 				UseIDToken:   d.providerConfig.UseIDToken,
 			}
 
-			err = validateTokenAudience(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
+			err = isValidAccessToken(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
 			if err != nil {
 				return TokenInfo{}, fmt.Errorf("validate access token failed with error: %v", err)
 			}
 
-			log.Infof("device flow: user authorization confirmed after %d polls in %s", polls, time.Since(start).Round(time.Second))
 			return tokenInfo, err
 		}
 	}

client/internal/auth/pkce_flow.go

@@ -188,8 +188,6 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
 	waitCtx, cancel := context.WithTimeout(ctx, timeout)
 	defer cancel()
 
-	log.Infof("pkce flow: waiting for authorization callback on %s, timeout %s", p.oAuthConfig.RedirectURL, timeout)
-
 	tokenChan := make(chan *oauth2.Token, 1)
 	errChan := make(chan error, 1)
 
@@ -223,7 +221,6 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
 func (p *PKCEAuthorizationFlow) startServer(server *http.Server, tokenChan chan<- *oauth2.Token, errChan chan<- error) {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/", func(w http.ResponseWriter, req *http.Request) {
-		log.Infof("pkce flow: received authorization callback from IdP")
 		cert := p.providerConfig.ClientCertPair
 		if cert != nil {
 			tr := &http.Transport{
@@ -274,18 +271,11 @@ func (p *PKCEAuthorizationFlow) handleRequest(req *http.Request) (*oauth2.Token,
 		return nil, fmt.Errorf("authentication failed: missing code")
 	}
 
-	exchangeStart := time.Now()
-	token, err := p.oAuthConfig.Exchange(
+	return p.oAuthConfig.Exchange(
 		req.Context(),
 		code,
 		oauth2.SetAuthURLParam("code_verifier", p.codeVerifier),
 	)
-	if err != nil {
-		return nil, err
-	}
-
-	log.Infof("pkce flow: authorization code exchanged for token in %s", time.Since(exchangeStart).Round(time.Millisecond))
-	return token, nil
 }
 
 func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo, error) {
@@ -306,7 +296,7 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
 		audience = p.providerConfig.ClientID
 	}
 
-	if err := validateTokenAudience(tokenInfo.GetTokenToUse(), audience); err != nil {
+	if err := isValidAccessToken(tokenInfo.GetTokenToUse(), audience); err != nil {
 		return TokenInfo{}, fmt.Errorf("authentication failed: invalid access token - %w", err)
 	}
 
@@ -320,11 +310,6 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
 	return tokenInfo, nil
 }
 
-// parseEmailFromIDToken extracts the email (or name) claim from an ID token
-// without verifying its signature. The value is best-effort and used only as a
-// UX convenience (login hint prefill and display); it never drives an
-// authorization decision. The authoritative identity is established server-side
-// from the signature-verified token.
 func parseEmailFromIDToken(token string) (string, error) {
 	parts := strings.Split(token, ".")
 	if len(parts) < 2 {

client/internal/auth/sessionwatch/watcher.go

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

client/internal/auth/sessionwatch/watcher_test.go

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

client/internal/auth/util.go

@@ -20,26 +20,14 @@ func randomBytesInHex(count int) (string, error) {
 	return hex.EncodeToString(buf), nil
 }
 
-// validateTokenAudience checks that the token is a well-formed JWT whose
-// audience claim matches the expected audience.
-//
-// It does NOT verify the token's cryptographic signature and therefore must not
-// be treated as an authenticity check. The token is obtained by the client
-// directly from the IdP token endpoint over TLS, and its signature is verified
-// server-side by the management server against the IdP's JWKS
-// (see shared/auth/jwt/validator.go). This function is only a client-side
-// sanity check that the returned token targets the expected audience.
-func validateTokenAudience(token string, audience string) error {
+// isValidAccessToken is a simple validation of the access token
+func isValidAccessToken(token string, audience string) error {
 	if token == "" {
 		return fmt.Errorf("token received is empty")
 	}
 
-	parts := strings.Split(token, ".")
-	if len(parts) != 3 {
-		return fmt.Errorf("token is not a well-formed JWT")
-	}
-
-	claimsString, err := base64.RawURLEncoding.DecodeString(parts[1])
+	encodedClaims := strings.Split(token, ".")[1]
+	claimsString, err := base64.RawURLEncoding.DecodeString(encodedClaims)
 	if err != nil {
 		return err
 	}

client/internal/auth/util_test.go

@@ -1,108 +0,0 @@
-package auth
-
-import (
-	"encoding/base64"
-	"encoding/json"
-	"testing"
-)
-
-// makeJWT builds an unsigned JWT-shaped string (header.payload.signature) with
-// the given claims payload. The signature part is arbitrary because
-// validateTokenAudience intentionally does not verify it.
-func makeJWT(t *testing.T, claims map[string]interface{}) string {
-	t.Helper()
-	header := base64.RawURLEncoding.EncodeToString([]byte(`{"alg":"RS256","typ":"JWT"}`))
-	payloadBytes, err := json.Marshal(claims)
-	if err != nil {
-		t.Fatalf("marshal claims: %v", err)
-	}
-	payload := base64.RawURLEncoding.EncodeToString(payloadBytes)
-	return header + "." + payload + ".unverified-signature"
-}
-
-func TestValidateTokenAudience(t *testing.T) {
-	tests := []struct {
-		name     string
-		token    string
-		audience string
-		wantErr  bool
-	}{
-		{
-			name:     "empty token",
-			token:    "",
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "not a JWT - no dots",
-			token:    "notajwt",
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "not a JWT - two parts only",
-			token:    "header.payload",
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "matching string audience",
-			token:    makeJWT(t, map[string]interface{}{"aud": "netbird"}),
-			audience: "netbird",
-			wantErr:  false,
-		},
-		{
-			name:     "mismatching string audience",
-			token:    makeJWT(t, map[string]interface{}{"aud": "other"}),
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "matching audience in array",
-			token:    makeJWT(t, map[string]interface{}{"aud": []interface{}{"other", "netbird"}}),
-			audience: "netbird",
-			wantErr:  false,
-		},
-		{
-			name:     "mismatching audience array",
-			token:    makeJWT(t, map[string]interface{}{"aud": []interface{}{"a", "b"}}),
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "missing audience claim",
-			token:    makeJWT(t, map[string]interface{}{"sub": "user"}),
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "invalid base64 payload",
-			token:    "header.!!!not-base64!!!.sig",
-			audience: "netbird",
-			wantErr:  true,
-		},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			err := validateTokenAudience(tc.token, tc.audience)
-			if tc.wantErr && err == nil {
-				t.Fatalf("expected error, got nil")
-			}
-			if !tc.wantErr && err != nil {
-				t.Fatalf("expected no error, got %v", err)
-			}
-		})
-	}
-}
-
-// TestValidateTokenAudienceNoPanic guards the regression where a non-empty
-// token without the JWT dot structure caused an index-out-of-range panic.
-func TestValidateTokenAudienceNoPanic(t *testing.T) {
-	inputs := []string{"a", ".", "a.", "aaaa", "no-dots-here"}
-	for _, in := range inputs {
-		if err := validateTokenAudience(in, "netbird"); err == nil {
-			t.Fatalf("expected error for malformed token %q, got nil", in)
-		}
-	}
-}

client/internal/conn_mgr.go

@@ -16,16 +16,6 @@ import (
 	"github.com/netbirdio/netbird/route"
 )
 
-// lazyForce is the resolved local decision for lazy connections, layered above the
-// management feature flag. lazyForceNone defers to management.
-type lazyForce int
-
-const (
-	lazyForceNone lazyForce = iota
-	lazyForceOn
-	lazyForceOff
-)
-
 // ConnMgr coordinates both lazy connections (established on-demand) and permanent peer connections.
 //
 // The connection manager is responsible for:
@@ -38,7 +28,7 @@ type ConnMgr struct {
 	peerStore        *peerstore.Store
 	statusRecorder   *peer.Status
 	iface            lazyconn.WGIface
-	force            lazyForce
+	enabledLocally   bool
 	rosenpassEnabled bool
 
 	lazyConnMgr *manager.Manager
@@ -53,34 +43,28 @@ func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerSto
 		peerStore:        peerStore,
 		statusRecorder:   statusRecorder,
 		iface:            iface,
-		force:            resolveLazyForce(engineConfig.LazyConnection),
 		rosenpassEnabled: engineConfig.RosenpassEnabled,
 	}
+	if engineConfig.LazyConnectionEnabled || lazyconn.IsLazyConnEnabledByEnv() {
+		e.enabledLocally = true
+	}
 	return e
 }
 
-// Start initializes the connection manager. It starts the lazy connection manager when a
-// local override forces it on; with no local override it waits for the management feature flag.
+// Start initializes the connection manager and starts the lazy connection manager if enabled by env var or cmd line option.
 func (e *ConnMgr) Start(ctx context.Context) {
 	if e.lazyConnMgr != nil {
 		log.Errorf("lazy connection manager is already started")
 		return
 	}
 
-	switch e.force {
-	case lazyForceOff:
-		log.Infof("lazy connection manager is disabled by local override (%s or MDM policy)", lazyconn.EnvLazyConn)
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	case lazyForceNone:
-		log.Infof("lazy connection manager is managed by the management feature flag")
-		e.statusRecorder.UpdateLazyConnection(false)
+	if !e.enabledLocally {
+		log.Infof("lazy connection manager is disabled")
 		return
 	}
 
 	if e.rosenpassEnabled {
 		log.Warnf("rosenpass connection manager is enabled, lazy connection manager will not be started")
-		e.statusRecorder.UpdateLazyConnection(false)
 		return
 	}
 
@@ -92,8 +76,8 @@ func (e *ConnMgr) Start(ctx context.Context) {
 // If enabled, it initializes the lazy connection manager and start it. Do not need to call Start() again.
 // If disabled, then it closes the lazy connection manager and open the connections to all peers.
 func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) error {
-	// a local override (NB_LAZY_CONN or local config) takes precedence over management
-	if e.force != lazyForceNone {
+	// do not disable lazy connection manager if it was enabled by env var
+	if e.enabledLocally {
 		return nil
 	}
 
@@ -105,17 +89,15 @@ func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) er
 
 		if e.rosenpassEnabled {
 			log.Infof("rosenpass connection manager is enabled, lazy connection manager will not be started")
-			e.statusRecorder.UpdateLazyConnection(false)
 			return nil
 		}
 
-		log.Infof("lazy connection manager is enabled by the management feature flag")
+		log.Warnf("lazy connection manager is enabled by management feature flag")
 		e.initLazyManager(ctx)
 		e.statusRecorder.UpdateLazyConnection(true)
 		return e.addPeersToLazyConnManager()
 	} else {
 		if e.lazyConnMgr == nil {
-			e.statusRecorder.UpdateLazyConnection(false)
 			return nil
 		}
 		log.Infof("lazy connection manager is disabled by management feature flag")
@@ -125,6 +107,37 @@ func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) er
 	}
 }
 
+// SetLocalLazyConn applies a local lazy connection override (UI / CLI / env).
+// While enabledLocally is true, UpdatedRemoteFeatureFlag (management sync) is a
+// no-op, so the local setting wins until it is turned off again.
+func (e *ConnMgr) SetLocalLazyConn(ctx context.Context, enabled bool) error {
+	e.enabledLocally = enabled
+
+	if enabled {
+		if e.lazyConnMgr != nil {
+			return nil
+		}
+
+		if e.rosenpassEnabled {
+			log.Warnf("rosenpass connection manager is enabled, lazy connection manager will not be started")
+			return nil
+		}
+
+		log.Infof("lazy connection manager is enabled locally")
+		e.initLazyManager(ctx)
+		e.statusRecorder.UpdateLazyConnection(true)
+		return e.addPeersToLazyConnManager()
+	}
+
+	if e.lazyConnMgr == nil {
+		return nil
+	}
+	log.Infof("lazy connection manager is disabled locally")
+	e.closeManager(ctx)
+	e.statusRecorder.UpdateLazyConnection(false)
+	return nil
+}
+
 // UpdateRouteHAMap updates the route HA mappings in the lazy connection manager
 func (e *ConnMgr) UpdateRouteHAMap(haMap route.HAMap) {
 	if !e.isStartedWithLazyMgr() {
@@ -327,25 +340,6 @@ func (e *ConnMgr) isStartedWithLazyMgr() bool {
 	return e.lazyConnMgr != nil && e.lazyCtxCancel != nil
 }
 
-// resolveLazyForce determines the local override. NB_LAZY_CONN takes precedence; when it
-// is unset the MDM policy override (mdmState) applies. Either wins in both directions over
-// the management feature flag; StateUnset for both defers to management.
-func resolveLazyForce(mdmState lazyconn.State) lazyForce {
-	state := lazyconn.EnvState()
-	if state == lazyconn.StateUnset {
-		state = mdmState
-	}
-
-	switch state {
-	case lazyconn.StateOn:
-		return lazyForceOn
-	case lazyconn.StateOff:
-		return lazyForceOff
-	default:
-		return lazyForceNone
-	}
-}
-
 func inactivityThresholdEnv() *time.Duration {
 	envValue := os.Getenv(lazyconn.EnvInactivityThreshold)
 	if envValue == "" {

client/internal/conn_mgr_test.go

@@ -1,40 +0,0 @@
-package internal
-
-import (
-	"os"
-	"testing"
-
-	"github.com/netbirdio/netbird/client/internal/lazyconn"
-)
-
-func TestResolveLazyForce(t *testing.T) {
-	tests := []struct {
-		name   string
-		env    string
-		envSet bool
-		mdm    lazyconn.State
-		want   lazyForce
-	}{
-		{name: "env unset, mdm unset -> defer to management", mdm: lazyconn.StateUnset, want: lazyForceNone},
-		{name: "env on -> force on", env: "on", envSet: true, mdm: lazyconn.StateUnset, want: lazyForceOn},
-		{name: "env off -> force off", env: "off", envSet: true, mdm: lazyconn.StateUnset, want: lazyForceOff},
-		{name: "env unset, mdm on -> force on", mdm: lazyconn.StateOn, want: lazyForceOn},
-		{name: "env unset, mdm off -> force off", mdm: lazyconn.StateOff, want: lazyForceOff},
-		{name: "env on beats mdm off", env: "on", envSet: true, mdm: lazyconn.StateOff, want: lazyForceOn},
-		{name: "env off beats mdm on", env: "off", envSet: true, mdm: lazyconn.StateOn, want: lazyForceOff},
-		{name: "unrecognized env, mdm on -> mdm wins", env: "auto", envSet: true, mdm: lazyconn.StateOn, want: lazyForceOn},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Setenv(lazyconn.EnvLazyConn, tt.env)
-			if !tt.envSet {
-				os.Unsetenv(lazyconn.EnvLazyConn)
-			}
-
-			if got := resolveLazyForce(tt.mdm); got != tt.want {
-				t.Fatalf("resolveLazyForce(%v) = %v, want %v", tt.mdm, got, tt.want)
-			}
-		})
-	}
-}

client/internal/connect.go

@@ -11,7 +11,6 @@ import (
 	"runtime/debug"
 	"strings"
 	"sync"
-	"sync/atomic"
 	"time"
 
 	"github.com/cenkalti/backoff/v4"
@@ -27,7 +26,6 @@ import (
 	"github.com/netbirdio/netbird/client/iface/device"
 	"github.com/netbirdio/netbird/client/iface/netstack"
 	"github.com/netbirdio/netbird/client/internal/dns"
-	"github.com/netbirdio/netbird/client/internal/lazyconn"
 	"github.com/netbirdio/netbird/client/internal/listener"
 	"github.com/netbirdio/netbird/client/internal/metrics"
 	"github.com/netbirdio/netbird/client/internal/peer"
@@ -56,10 +54,6 @@ var androidRunOverride func(c *ConnectClient, runningChan chan struct{}, logPath
 
 type ConnectClient struct {
 	ctx            context.Context
-	runCancel      context.CancelFunc
-	runExited      chan struct{}
-	runOnce        sync.Once
-	runStarted     atomic.Bool
 	config         *profilemanager.Config
 	statusRecorder *peer.Status
 
@@ -76,14 +70,8 @@ func NewConnectClient(
 	config *profilemanager.Config,
 	statusRecorder *peer.Status,
 ) *ConnectClient {
-	// Derive the run context here so Stop owns the cancel that unblocks the run
-	// loop. runCancel is set once at construction, so Stop can call it without
-	// racing the run loop's startup. Callers therefore need not cancel before Stop.
-	runCtx, runCancel := context.WithCancel(ctx)
 	return &ConnectClient{
-		ctx:            runCtx,
-		runCancel:      runCancel,
-		runExited:      make(chan struct{}),
+		ctx:            ctx,
 		config:         config,
 		statusRecorder: statusRecorder,
 		engineMutex:    sync.Mutex{},
@@ -147,11 +135,6 @@ func (c *ConnectClient) RunOniOS(
 }
 
 func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan struct{}, logPath string) error {
-	// Mark the loop as started and signal exit on return so Stop can wait for
-	// the loop to finish (and skip the wait if the loop never ran).
-	c.runStarted.Store(true)
-	defer c.runOnce.Do(func() { close(c.runExited) })
-
 	defer func() {
 		if r := recover(); r != nil {
 			rec := c.statusRecorder
@@ -257,10 +240,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		log.Errorf("failed to clean up temporary installer file: %v", err)
 	}
 
-	defer func() {
-		c.statusRecorder.SetSessionExpiresAt(time.Time{})
-		c.statusRecorder.ClientStop()
-	}()
+	defer c.statusRecorder.ClientStop()
 	operation := func() error {
 		// if context cancelled we not start new backoff cycle
 		if c.ctx.Err() != nil {
@@ -319,7 +299,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			log.Debug(err)
 			if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 				state.Set(StatusNeedsLogin)
-				c.runCancel()
+				_ = c.Stop()
 				return backoff.Permanent(wrapErr(err)) // unrecoverable error
 			}
 			return wrapErr(err)
@@ -327,10 +307,6 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		c.clientMetrics.RecordLoginDuration(engineCtx, time.Since(loginStarted), true)
 		c.statusRecorder.MarkManagementConnected()
 
-		if metricsConfig := loginResp.GetNetbirdConfig().GetMetrics(); metricsConfig != nil {
-			c.clientMetrics.UpdatePushFromMgm(c.ctx, metricsConfig.GetEnabled())
-		}
-
 		localPeerState := peer.LocalPeerState{
 			IP:              loginResp.GetPeerConfig().GetAddress(),
 			PubKey:          myPrivateKey.PublicKey().String(),
@@ -416,7 +392,6 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			StateManager:   stateManager,
 			UpdateManager:  c.updateManager,
 			ClientMetrics:  c.clientMetrics,
-			MetricsCtx:     c.ctx,
 		}, mobileDependency)
 		engine.SetSyncResponsePersistence(c.persistSyncResponse)
 		c.engine = engine
@@ -448,10 +423,14 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		c.engine = nil
 		c.engineMutex.Unlock()
 
-		log.Infof("ensuring wg interface is removed, Netbird engine context cancelled")
+		// todo: consider to remove this condition. Is not thread safe.
+		// We should always call Stop(), but we need to verify that it is idempotent
+		if engine.wgInterface != nil {
+			log.Infof("ensuring %s is removed, Netbird engine context cancelled", engine.wgInterface.Name())
 
-		if err := engine.Stop(); err != nil {
-			log.Errorf("Failed to stop engine: %v", err)
+			if err := engine.Stop(); err != nil {
+				log.Errorf("Failed to stop engine: %v", err)
+			}
 		}
 		c.statusRecorder.ClientTeardown()
 
@@ -476,7 +455,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 			state.Set(StatusNeedsLogin)
-			c.runCancel()
+			_ = c.Stop()
 		}
 		return err
 	}
@@ -554,9 +533,11 @@ func (c *ConnectClient) Status() StatusType {
 }
 
 func (c *ConnectClient) Stop() error {
-	c.runCancel()
-	if c.runStarted.Load() {
-		<-c.runExited
+	engine := c.Engine()
+	if engine != nil {
+		if err := engine.Stop(); err != nil {
+			return fmt.Errorf("stop engine: %w", err)
+		}
 	}
 	return nil
 }
@@ -622,7 +603,7 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
 		BlockInbound:        config.BlockInbound,
 		DisableIPv6:         config.DisableIPv6,
 
-		LazyConnection: lazyconn.ParseState(config.LazyConnection),
+		LazyConnectionEnabled: config.LazyConnectionEnabled,
 
 		MTU:     selectMTU(config.MTU, peerConfig.Mtu),
 		LogPath: logPath,
@@ -696,6 +677,7 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
 		config.BlockLANAccess,
 		config.BlockInbound,
 		config.DisableIPv6,
+		config.LazyConnectionEnabled,
 		config.EnableSSHRoot,
 		config.EnableSSHSFTP,
 		config.EnableSSHLocalPortForwarding,

client/internal/debug/debug.go

@@ -480,6 +480,7 @@ func (g *BundleGenerator) addStatus() error {
 
 		fullStatus := g.statusRecorder.GetFullStatus()
 		protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
+		protoFullStatus.Events = g.statusRecorder.GetEventHistory()
 		overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
 			Anonymize:     g.anonymize,
 			ProfileName:   profName,
@@ -694,7 +695,7 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder)
 		configContent.WriteString(fmt.Sprintf("ClientCertKeyPath: %s\n", g.internalConfig.ClientCertKeyPath))
 	}
 
-	configContent.WriteString(fmt.Sprintf("LazyConnection: %q\n", g.internalConfig.LazyConnection))
+	configContent.WriteString(fmt.Sprintf("LazyConnectionEnabled: %v\n", g.internalConfig.LazyConnectionEnabled))
 	configContent.WriteString(fmt.Sprintf("MTU: %d\n", g.internalConfig.MTU))
 }
 

client/internal/debug/debug_test.go

@@ -885,7 +885,7 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		DNSRouteInterval:              5 * time.Second,
 		ClientCertPath:                "/tmp/cert",
 		ClientCertKeyPath:             "/tmp/key",
-		LazyConnection:                "on",
+		LazyConnectionEnabled:         true,
 		MTU:                           1280,
 	}
 

client/internal/dns/mgmt/mgmt.go

@@ -51,20 +51,13 @@ type cachedRecord struct {
 }
 
 // Resolver caches critical NetBird infrastructure domains.
-// records, refreshing, failedResolves, mgmtDomain and serverDomains are all
-// guarded by mutex.
+// records, refreshing, mgmtDomain and serverDomains are all guarded by mutex.
 type Resolver struct {
 	records       map[dns.Question]*cachedRecord
 	mgmtDomain    *domain.Domain
 	serverDomains *dnsconfig.ServerDomains
 	mutex         sync.RWMutex
 
-	// failedResolves records the last failed initial resolve per domain so a
-	// domain that never resolves isn't retried on every server-domains update
-	// until refreshBackoff elapses. Entries are cleared on success and pruned
-	// to the current server-domains set.
-	failedResolves map[domain.Domain]time.Time
-
 	chain            ChainResolver
 	chainMaxPriority int
 	refreshGroup     singleflight.Group
@@ -83,10 +76,9 @@ type Resolver struct {
 // NewResolver creates a new management domains cache resolver.
 func NewResolver() *Resolver {
 	return &Resolver{
-		records:        make(map[dns.Question]*cachedRecord),
-		refreshing:     make(map[dns.Question]*atomic.Bool),
-		failedResolves: make(map[domain.Domain]time.Time),
-		cacheTTL:       resolveCacheTTL(),
+		records:    make(map[dns.Question]*cachedRecord),
+		refreshing: make(map[dns.Question]*atomic.Bool),
+		cacheTTL:   resolveCacheTTL(),
 	}
 }
 
@@ -181,9 +173,7 @@ func (m *Resolver) continueToNext(w dns.ResponseWriter, r *dns.Msg) {
 
 // AddDomain resolves a domain and stores its A/AAAA records in the cache.
 // A family that resolves NODATA (nil err, zero records) evicts any stale
-// entry for that qtype. When one family hard-errors while the other succeeds,
-// the resolved family is still cached but AddDomain returns an error so the
-// caller retries the incomplete resolve rather than treating it as complete.
+// entry for that qtype.
 func (m *Resolver) AddDomain(ctx context.Context, d domain.Domain) error {
 	dnsName := strings.ToLower(dns.Fqdn(d.PunycodeString()))
 
@@ -213,10 +203,6 @@ func (m *Resolver) AddDomain(ctx context.Context, d domain.Domain) error {
 	log.Debugf("added/updated domain=%s with %d A records and %d AAAA records",
 		d.SafeString(), len(aRecords), len(aaaaRecords))
 
-	if errA != nil || errAAAA != nil {
-		return fmt.Errorf("resolve %s: incomplete, a family failed: %w", d.SafeString(), errors.Join(errA, errAAAA))
-	}
-
 	return nil
 }
 
@@ -476,7 +462,6 @@ func (m *Resolver) RemoveDomain(d domain.Domain) error {
 	delete(m.records, qAAAA)
 	delete(m.refreshing, qA)
 	delete(m.refreshing, qAAAA)
-	delete(m.failedResolves, d)
 
 	log.Debugf("removed domain=%s from cache", d.SafeString())
 	return nil
@@ -520,7 +505,6 @@ func (m *Resolver) UpdateFromServerDomains(ctx context.Context, serverDomains dn
 		allDomains := m.extractDomainsFromServerDomains(updatedServerDomains)
 		currentDomains := m.GetCachedDomains()
 		removedDomains = m.removeStaleDomains(currentDomains, allDomains)
-		m.pruneFailedResolves(allDomains)
 	}
 
 	m.addNewDomains(ctx, newDomains)
@@ -593,85 +577,13 @@ func (m *Resolver) isManagementDomain(domain domain.Domain) bool {
 	return m.mgmtDomain != nil && domain == *m.mgmtDomain
 }
 
-// addNewDomains resolves and caches domains that are not yet in the cache,
-// running the lookups concurrently. Domains already cached are skipped and left
-// to the stale-while-revalidate refresh path, so a sync never re-resolves them
-// synchronously: once NetBird owns the OS resolver the resolve runs through the
-// handler chain and would otherwise dial the managed upstreams under the engine
-// sync lock on every update.
+// addNewDomains resolves and caches all domains from the update
 func (m *Resolver) addNewDomains(ctx context.Context, newDomains domain.List) {
-	var wg sync.WaitGroup
-	seen := make(map[domain.Domain]struct{}, len(newDomains))
 	for _, newDomain := range newDomains {
-		if _, dup := seen[newDomain]; dup {
-			continue
-		}
-		seen[newDomain] = struct{}{}
-
-		if !m.needsResolve(newDomain) {
-			continue
-		}
-
-		wg.Add(1)
-		go func(d domain.Domain) {
-			defer wg.Done()
-			if err := m.AddDomain(ctx, d); err != nil {
-				m.markResolveFailed(d)
-				log.Warnf("failed to add/update domain=%s: %v", d.SafeString(), err)
-				return
-			}
-			m.clearResolveFailed(d)
-			log.Debugf("added/updated management cache domain=%s", d.SafeString())
-		}(newDomain)
-	}
-	wg.Wait()
-}
-
-// needsResolve reports whether d should be resolved now. A recent failed or
-// incomplete resolve gates retries on the backoff even when one family is
-// already cached, so a transiently-failed family is retried instead of being
-// treated as fully resolved. Otherwise a domain with any cached record is left
-// to the stale-while-revalidate refresh path.
-func (m *Resolver) needsResolve(d domain.Domain) bool {
-	dnsName := strings.ToLower(dns.Fqdn(d.PunycodeString()))
-
-	m.mutex.RLock()
-	defer m.mutex.RUnlock()
-
-	if failedAt, ok := m.failedResolves[d]; ok {
-		return time.Since(failedAt) >= refreshBackoff
-	}
-
-	for _, qtype := range []uint16{dns.TypeA, dns.TypeAAAA} {
-		q := dns.Question{Name: dnsName, Qtype: qtype, Qclass: dns.ClassINET}
-		if _, ok := m.records[q]; ok {
-			return false
-		}
-	}
-	return true
-}
-
-func (m *Resolver) markResolveFailed(d domain.Domain) {
-	m.mutex.Lock()
-	m.failedResolves[d] = time.Now()
-	m.mutex.Unlock()
-}
-
-func (m *Resolver) clearResolveFailed(d domain.Domain) {
-	m.mutex.Lock()
-	delete(m.failedResolves, d)
-	m.mutex.Unlock()
-}
-
-// pruneFailedResolves drops failure markers for domains no longer present in
-// the server-domains set, keeping the map bounded to the current set (a
-// failed-only domain has no cached record, so RemoveDomain never sees it).
-func (m *Resolver) pruneFailedResolves(domains domain.List) {
-	m.mutex.Lock()
-	defer m.mutex.Unlock()
-	for d := range m.failedResolves {
-		if !slices.Contains(domains, d) {
-			delete(m.failedResolves, d)
+		if err := m.AddDomain(ctx, newDomain); err != nil {
+			log.Warnf("failed to add/update domain=%s: %v", newDomain.SafeString(), err)
+		} else {
+			log.Debugf("added/updated management cache domain=%s", newDomain.SafeString())
 		}
 	}
 }

client/internal/dns/mgmt/mgmt_refresh_test.go

@@ -21,7 +21,6 @@ type fakeChain struct {
 	mu       sync.Mutex
 	calls    map[string]int
 	answers  map[string][]dns.RR
-	qErr     map[string]error
 	err      error
 	hasRoot  bool
 	onLookup func()
@@ -31,7 +30,6 @@ func newFakeChain() *fakeChain {
 	return &fakeChain{
 		calls:   map[string]int{},
 		answers: map[string][]dns.RR{},
-		qErr:    map[string]error{},
 		hasRoot: true,
 	}
 }
@@ -49,9 +47,6 @@ func (f *fakeChain) ResolveInternal(ctx context.Context, msg *dns.Msg, maxPriori
 	f.calls[key]++
 	answers := f.answers[key]
 	err := f.err
-	if err == nil {
-		err = f.qErr[key]
-	}
 	onLookup := f.onLookup
 	f.mu.Unlock()
 
@@ -80,12 +75,6 @@ func (f *fakeChain) setAnswer(name string, qtype uint16, ip string) {
 	}
 }
 
-func (f *fakeChain) setErr(name string, qtype uint16, err error) {
-	f.mu.Lock()
-	defer f.mu.Unlock()
-	f.qErr[name+"|"+dns.TypeToString[qtype]] = err
-}
-
 func (f *fakeChain) callCount(name string, qtype uint16) int {
 	f.mu.Lock()
 	defer f.mu.Unlock()

client/internal/dns/mgmt/mgmt_resolve_test.go

@@ -1,183 +0,0 @@
-package mgmt
-
-import (
-	"context"
-	"errors"
-	"sync/atomic"
-	"testing"
-	"time"
-
-	"github.com/miekg/dns"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
-	"github.com/netbirdio/netbird/shared/management/domain"
-)
-
-// A domain already in the cache must not be re-resolved on a subsequent server
-// domains update; it is left to the stale-while-revalidate refresh path.
-func TestResolver_UpdateFromServerDomains_SkipsCached(t *testing.T) {
-	r := NewResolver()
-	chain := newFakeChain()
-	chain.setAnswer("signal.example.com.", dns.TypeA, "10.0.0.2")
-	r.SetChainResolver(chain, 50)
-
-	sd := dnsconfig.ServerDomains{Signal: domain.Domain("signal.example.com")}
-
-	_, err := r.UpdateFromServerDomains(context.Background(), sd)
-	require.NoError(t, err)
-	require.Equal(t, 1, chain.callCount("signal.example.com.", dns.TypeA),
-		"first update must resolve the domain")
-
-	_, err = r.UpdateFromServerDomains(context.Background(), sd)
-	require.NoError(t, err)
-	assert.Equal(t, 1, chain.callCount("signal.example.com.", dns.TypeA),
-		"cached domain must not be re-resolved on a subsequent update")
-}
-
-// New domains in a single update must resolve concurrently rather than serially.
-func TestResolver_AddNewDomains_ResolvesConcurrently(t *testing.T) {
-	r := NewResolver()
-	chain := newFakeChain()
-
-	var inflight, maxInflight atomic.Int32
-	chain.onLookup = func() {
-		n := inflight.Add(1)
-		for {
-			old := maxInflight.Load()
-			if n <= old || maxInflight.CompareAndSwap(old, n) {
-				break
-			}
-		}
-		time.Sleep(50 * time.Millisecond)
-		inflight.Add(-1)
-	}
-
-	relays := []domain.Domain{"a.example.com", "b.example.com", "c.example.com", "d.example.com"}
-	for _, d := range relays {
-		chain.setAnswer(dns.Fqdn(string(d)), dns.TypeA, "10.0.0.2")
-	}
-	r.SetChainResolver(chain, 50)
-
-	start := time.Now()
-	_, err := r.UpdateFromServerDomains(context.Background(), dnsconfig.ServerDomains{Relay: relays})
-	require.NoError(t, err)
-	elapsed := time.Since(start)
-
-	assert.GreaterOrEqual(t, int(maxInflight.Load()), 2, "domains must resolve concurrently")
-	// Serial resolution of 4 domains would take at least 4*50ms; concurrent is far less.
-	assert.Less(t, elapsed, 300*time.Millisecond, "resolution should not be serial")
-}
-
-// A domain that fails to resolve must not be retried on every update; the
-// failure backoff suppresses re-resolution until it expires.
-func TestResolver_UpdateFromServerDomains_BacksOffFailures(t *testing.T) {
-	r := NewResolver()
-	chain := newFakeChain()
-	chain.err = errors.New("resolve boom")
-	r.SetChainResolver(chain, 50)
-
-	sd := dnsconfig.ServerDomains{Signal: domain.Domain("signal.example.com")}
-
-	_, err := r.UpdateFromServerDomains(context.Background(), sd)
-	require.NoError(t, err)
-	require.Equal(t, 1, chain.callCount("signal.example.com.", dns.TypeA),
-		"first update must attempt the resolve")
-
-	_, err = r.UpdateFromServerDomains(context.Background(), sd)
-	require.NoError(t, err)
-	assert.Equal(t, 1, chain.callCount("signal.example.com.", dns.TypeA),
-		"failed resolve must back off and not retry on the next update")
-}
-
-// A domain listed under more than one server-domain type (e.g. STUN and TURN on
-// the same host) must be resolved once per update, not once per occurrence.
-func TestResolver_AddNewDomains_DedupesDuplicateDomains(t *testing.T) {
-	r := NewResolver()
-	chain := newFakeChain()
-	chain.setAnswer("dup.example.com.", dns.TypeA, "10.0.0.9")
-	r.SetChainResolver(chain, 50)
-
-	sd := dnsconfig.ServerDomains{
-		Stuns: []domain.Domain{"dup.example.com"},
-		Turns: []domain.Domain{"dup.example.com"},
-	}
-
-	_, err := r.UpdateFromServerDomains(context.Background(), sd)
-	require.NoError(t, err)
-	assert.Equal(t, 1, chain.callCount("dup.example.com.", dns.TypeA),
-		"a domain appearing under multiple server-domain types must resolve once")
-}
-
-// A failure marker must be dropped once its domain leaves the server-domains set
-// so the map stays bounded to the current set.
-func TestResolver_UpdateFromServerDomains_PrunesFailedResolves(t *testing.T) {
-	r := NewResolver()
-	chain := newFakeChain()
-	chain.err = errors.New("resolve boom")
-	r.SetChainResolver(chain, 50)
-
-	_, err := r.UpdateFromServerDomains(context.Background(), dnsconfig.ServerDomains{Signal: domain.Domain("gone.example.com")})
-	require.NoError(t, err)
-	r.mutex.RLock()
-	_, marked := r.failedResolves[domain.Domain("gone.example.com")]
-	r.mutex.RUnlock()
-	require.True(t, marked, "failed resolve must be recorded")
-
-	_, err = r.UpdateFromServerDomains(context.Background(), dnsconfig.ServerDomains{Signal: domain.Domain("other.example.com")})
-	require.NoError(t, err)
-	r.mutex.RLock()
-	_, stillMarked := r.failedResolves[domain.Domain("gone.example.com")]
-	r.mutex.RUnlock()
-	assert.False(t, stillMarked, "failure marker for a domain no longer in the set must be pruned")
-}
-
-// When one family hard-errors while the other resolves, the domain is cached
-// for the working family but recorded as incomplete so the failed family is
-// retried under backoff instead of being treated as fully resolved forever.
-func TestResolver_AddNewDomains_RetriesPartialFamilyFailure(t *testing.T) {
-	d := domain.Domain("relay.example.com")
-	r := NewResolver()
-	chain := newFakeChain()
-	chain.setAnswer("relay.example.com.", dns.TypeA, "10.0.0.2")
-	chain.setErr("relay.example.com.", dns.TypeAAAA, errors.New("servfail"))
-	r.SetChainResolver(chain, 50)
-
-	_, err := r.UpdateFromServerDomains(context.Background(), dnsconfig.ServerDomains{Relay: []domain.Domain{d}})
-	require.NoError(t, err)
-
-	r.mutex.RLock()
-	_, aCached := r.records[dns.Question{Name: "relay.example.com.", Qtype: dns.TypeA, Qclass: dns.ClassINET}]
-	_, marked := r.failedResolves[d]
-	r.mutex.RUnlock()
-	require.True(t, aCached, "the working family must still be cached")
-	require.True(t, marked, "a partial failure must be recorded so the failed family is retried")
-
-	assert.False(t, r.needsResolve(d), "within the backoff window the domain is not retried")
-
-	r.mutex.Lock()
-	r.failedResolves[d] = time.Now().Add(-2 * refreshBackoff)
-	r.mutex.Unlock()
-	assert.True(t, r.needsResolve(d), "after the backoff elapses the domain is retried to pick up the missing family")
-}
-
-// A family that returns NODATA (legitimately absent, e.g. an IPv4-only host) is
-// not a failure: the domain must not be marked for retry, otherwise it would be
-// re-resolved on every sync.
-func TestResolver_AddNewDomains_NodataIsNotFailure(t *testing.T) {
-	d := domain.Domain("v4only.example.com")
-	r := NewResolver()
-	chain := newFakeChain()
-	chain.setAnswer("v4only.example.com.", dns.TypeA, "10.0.0.2")
-	r.SetChainResolver(chain, 50)
-
-	_, err := r.UpdateFromServerDomains(context.Background(), dnsconfig.ServerDomains{Relay: []domain.Domain{d}})
-	require.NoError(t, err)
-
-	r.mutex.RLock()
-	_, marked := r.failedResolves[d]
-	r.mutex.RUnlock()
-	assert.False(t, marked, "a NODATA family must not be recorded as a failure")
-	assert.False(t, r.needsResolve(d), "an IPv4-only host must not be re-resolved on later syncs")
-}

client/internal/dns/resutil/resolve.go

@@ -8,7 +8,6 @@ import (
 	"errors"
 	"net"
 	"net/netip"
-	"slices"
 	"strings"
 
 	"github.com/miekg/dns"
@@ -168,10 +167,7 @@ func getRcodeForNotFound(ctx context.Context, r resolver, domain string, origina
 	case dns.TypeA:
 		alternativeNetwork = "ip6"
 	default:
-		// Non-address types reach LookupIP only unexpectedly; without an
-		// address pair to probe we cannot prove the name is absent, so answer
-		// NODATA rather than a poisoning NXDOMAIN.
-		return dns.RcodeSuccess
+		return dns.RcodeNameError
 	}
 
 	if _, err := r.LookupNetIP(ctx, alternativeNetwork, domain); err != nil {
@@ -188,230 +184,6 @@ func getRcodeForNotFound(ctx context.Context, r resolver, domain string, origina
 	return dns.RcodeSuccess
 }
 
-// RecordResolver is the host resolver surface used to forward non-address
-// record queries. net.DefaultResolver satisfies it.
-type RecordResolver interface {
-	LookupMX(ctx context.Context, name string) ([]*net.MX, error)
-	LookupTXT(ctx context.Context, name string) ([]string, error)
-	LookupNS(ctx context.Context, name string) ([]*net.NS, error)
-	LookupSRV(ctx context.Context, service, proto, name string) (string, []*net.SRV, error)
-	LookupCNAME(ctx context.Context, host string) (string, error)
-	LookupAddr(ctx context.Context, addr string) ([]string, error)
-}
-
-// LookupRecords resolves a non-address DNS record type through the host
-// resolver and returns the resource records and the DNS rcode. Types the host
-// resolver cannot answer (anything not covered by the net.Resolver Lookup*
-// methods) yield NODATA so that a routed name is never poisoned with NXDOMAIN
-// for an unsupported type.
-func LookupRecords(ctx context.Context, r RecordResolver, name string, qtype uint16, ttl uint32) ([]dns.RR, int) {
-	fqdn := dns.Fqdn(name)
-
-	switch qtype {
-	case dns.TypeMX:
-		return lookupMX(ctx, r, name, fqdn, ttl)
-	case dns.TypeTXT:
-		return lookupTXT(ctx, r, name, fqdn, ttl)
-	case dns.TypeNS:
-		return lookupNS(ctx, r, name, fqdn, ttl)
-	case dns.TypeSRV:
-		return lookupSRV(ctx, r, name, fqdn, ttl)
-	case dns.TypeCNAME:
-		return lookupCNAME(ctx, r, name, fqdn, ttl)
-	case dns.TypePTR:
-		return lookupPTR(ctx, r, name, fqdn, ttl)
-	default:
-		return nil, dns.RcodeSuccess
-	}
-}
-
-func recordHeader(fqdn string, rrtype uint16, ttl uint32) dns.RR_Header {
-	return dns.RR_Header{Name: fqdn, Rrtype: rrtype, Class: dns.ClassINET, Ttl: ttl}
-}
-
-func lookupMX(ctx context.Context, r RecordResolver, name, fqdn string, ttl uint32) ([]dns.RR, int) {
-	recs, err := r.LookupMX(ctx, name)
-	if err != nil {
-		return nil, rcodeForRecordError(err)
-	}
-	rrs := make([]dns.RR, 0, len(recs))
-	for _, mx := range recs {
-		rrs = append(rrs, &dns.MX{
-			Hdr:        recordHeader(fqdn, dns.TypeMX, ttl),
-			Preference: mx.Pref,
-			Mx:         dns.Fqdn(mx.Host),
-		})
-	}
-	return rrs, dns.RcodeSuccess
-}
-
-func lookupTXT(ctx context.Context, r RecordResolver, name, fqdn string, ttl uint32) ([]dns.RR, int) {
-	recs, err := r.LookupTXT(ctx, name)
-	if err != nil {
-		return nil, rcodeForRecordError(err)
-	}
-	rrs := make([]dns.RR, 0, len(recs))
-	for _, txt := range recs {
-		rrs = append(rrs, &dns.TXT{
-			Hdr: recordHeader(fqdn, dns.TypeTXT, ttl),
-			Txt: chunkTXT(txt),
-		})
-	}
-	return rrs, dns.RcodeSuccess
-}
-
-func lookupNS(ctx context.Context, r RecordResolver, name, fqdn string, ttl uint32) ([]dns.RR, int) {
-	recs, err := r.LookupNS(ctx, name)
-	if err != nil {
-		return nil, rcodeForRecordError(err)
-	}
-	rrs := make([]dns.RR, 0, len(recs))
-	for _, ns := range recs {
-		rrs = append(rrs, &dns.NS{
-			Hdr: recordHeader(fqdn, dns.TypeNS, ttl),
-			Ns:  dns.Fqdn(ns.Host),
-		})
-	}
-	return rrs, dns.RcodeSuccess
-}
-
-func lookupSRV(ctx context.Context, r RecordResolver, name, fqdn string, ttl uint32) ([]dns.RR, int) {
-	_, recs, err := r.LookupSRV(ctx, "", "", name)
-	if err != nil {
-		return nil, rcodeForRecordError(err)
-	}
-	rrs := make([]dns.RR, 0, len(recs))
-	for _, srv := range recs {
-		rrs = append(rrs, &dns.SRV{
-			Hdr:      recordHeader(fqdn, dns.TypeSRV, ttl),
-			Priority: srv.Priority,
-			Weight:   srv.Weight,
-			Port:     srv.Port,
-			Target:   dns.Fqdn(srv.Target),
-		})
-	}
-	return rrs, dns.RcodeSuccess
-}
-
-func lookupCNAME(ctx context.Context, r RecordResolver, name, fqdn string, ttl uint32) ([]dns.RR, int) {
-	cname, err := r.LookupCNAME(ctx, name)
-	if err != nil {
-		return nil, rcodeForRecordError(err)
-	}
-	// LookupCNAME returns the queried name itself when the name resolves but
-	// has no CNAME record; that is a NODATA result, not a CNAME.
-	if strings.EqualFold(dns.Fqdn(cname), fqdn) {
-		return nil, dns.RcodeSuccess
-	}
-	return []dns.RR{&dns.CNAME{
-		Hdr:    recordHeader(fqdn, dns.TypeCNAME, ttl),
-		Target: dns.Fqdn(cname),
-	}}, dns.RcodeSuccess
-}
-
-func lookupPTR(ctx context.Context, r RecordResolver, name, fqdn string, ttl uint32) ([]dns.RR, int) {
-	addr, ok := ptrQueryAddr(name)
-	if !ok {
-		return nil, dns.RcodeSuccess
-	}
-	names, err := r.LookupAddr(ctx, addr)
-	if err != nil {
-		return nil, rcodeForRecordError(err)
-	}
-	rrs := make([]dns.RR, 0, len(names))
-	for _, n := range names {
-		rrs = append(rrs, &dns.PTR{
-			Hdr: recordHeader(fqdn, dns.TypePTR, ttl),
-			Ptr: dns.Fqdn(n),
-		})
-	}
-	return rrs, dns.RcodeSuccess
-}
-
-// ptrQueryAddr converts a reverse-DNS query name (in-addr.arpa or ip6.arpa)
-// into the address string expected by net.Resolver.LookupAddr. It reports false
-// when the name is not a well-formed reverse name.
-func ptrQueryAddr(qname string) (string, bool) {
-	name := strings.TrimSuffix(strings.ToLower(dns.Fqdn(qname)), ".")
-
-	switch {
-	case strings.HasSuffix(name, ".in-addr.arpa"):
-		return parseInAddrArpa(strings.TrimSuffix(name, ".in-addr.arpa"))
-	case strings.HasSuffix(name, ".ip6.arpa"):
-		return parseIP6Arpa(strings.TrimSuffix(name, ".ip6.arpa"))
-	default:
-		return "", false
-	}
-}
-
-// parseInAddrArpa turns the label portion of an in-addr.arpa name into an IPv4
-// address string, reporting false when it is not a well-formed reverse name.
-func parseInAddrArpa(labelPart string) (string, bool) {
-	labels := strings.Split(labelPart, ".")
-	if len(labels) != 4 {
-		return "", false
-	}
-	slices.Reverse(labels)
-	addr, err := netip.ParseAddr(strings.Join(labels, "."))
-	if err != nil || !addr.Is4() {
-		return "", false
-	}
-	return addr.String(), true
-}
-
-// parseIP6Arpa turns the nibble portion of an ip6.arpa name into an IPv6
-// address string, reporting false when it is not a well-formed reverse name.
-func parseIP6Arpa(nibblePart string) (string, bool) {
-	nibbles := strings.Split(nibblePart, ".")
-	if len(nibbles) != 32 {
-		return "", false
-	}
-	slices.Reverse(nibbles)
-	var sb strings.Builder
-	for i, n := range nibbles {
-		if i > 0 && i%4 == 0 {
-			sb.WriteByte(':')
-		}
-		sb.WriteString(n)
-	}
-	addr, err := netip.ParseAddr(sb.String())
-	if err != nil || !addr.Is6() {
-		return "", false
-	}
-	return addr.String(), true
-}
-
-// rcodeForRecordError maps a non-address lookup error to a DNS rcode. A
-// not-found result becomes NODATA rather than NXDOMAIN: net.DNSError.IsNotFound
-// does not distinguish a missing name from a name that exists only with records
-// of other types, so the name cannot be proven absent and must not be poisoned.
-func rcodeForRecordError(err error) int {
-	var dnsErr *net.DNSError
-	if errors.As(err, &dnsErr) && dnsErr.IsNotFound {
-		return dns.RcodeSuccess
-	}
-	return dns.RcodeServerFailure
-}
-
-// chunkTXT splits a TXT string into character-strings no longer than 255 bytes
-// so the record can be packed. The chunks form one TXT resource record.
-func chunkTXT(s string) []string {
-	const maxLen = 255
-	if len(s) <= maxLen {
-		return []string{s}
-	}
-
-	var chunks []string
-	for len(s) > maxLen {
-		chunks = append(chunks, s[:maxLen])
-		s = s[maxLen:]
-	}
-	if len(s) > 0 {
-		chunks = append(chunks, s)
-	}
-	return chunks
-}
-
 // FormatAnswers formats DNS resource records for logging.
 func FormatAnswers(answers []dns.RR) string {
 	if len(answers) == 0 {
@@ -435,35 +207,3 @@ func FormatAnswers(answers []dns.RR) string {
 	}
 	return "[" + strings.Join(parts, ", ") + "]"
 }
-
-// StripOPT removes any OPT pseudo-RRs from the message's Extra section. Per
-// RFC 6891 a responder must not include an OPT RR toward a client that did not
-// advertise EDNS0.
-func StripOPT(msg *dns.Msg) {
-	if len(msg.Extra) == 0 {
-		return
-	}
-	out := msg.Extra[:0]
-	for _, rr := range msg.Extra {
-		if _, ok := rr.(*dns.OPT); ok {
-			continue
-		}
-		out = append(out, rr)
-	}
-	msg.Extra = out
-}
-
-// ExtractEDE returns the first Extended DNS Error (RFC 8914) option carried in
-// the message, if present.
-func ExtractEDE(msg *dns.Msg) (*dns.EDNS0_EDE, bool) {
-	opt := msg.IsEdns0()
-	if opt == nil {
-		return nil, false
-	}
-	for _, o := range opt.Option {
-		if ede, ok := o.(*dns.EDNS0_EDE); ok {
-			return ede, true
-		}
-	}
-	return nil, false
-}

client/internal/dns/resutil/resolve_test.go

@@ -5,7 +5,6 @@ import (
 	"errors"
 	"net"
 	"net/netip"
-	"strings"
 	"testing"
 
 	"github.com/miekg/dns"
@@ -121,200 +120,3 @@ func TestLookupIP_DNSErrorNotIsNotFound(t *testing.T) {
 
 	assert.Equal(t, dns.RcodeServerFailure, result.Rcode, "upstream failure should map to SERVFAIL")
 }
-
-func TestPtrQueryAddr(t *testing.T) {
-	tests := []struct {
-		name   string
-		qname  string
-		want   string
-		wantOK bool
-	}{
-		{name: "ipv4", qname: "4.3.2.1.in-addr.arpa.", want: "1.2.3.4", wantOK: true},
-		{name: "ipv4 no trailing dot", qname: "1.0.0.127.in-addr.arpa", want: "127.0.0.1", wantOK: true},
-		{
-			name:   "ipv6",
-			qname:  "1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.8.b.d.0.1.0.0.2.ip6.arpa.",
-			want:   "2001:db8::1",
-			wantOK: true,
-		},
-		{name: "ipv4 wrong label count", qname: "2.1.in-addr.arpa.", wantOK: false},
-		{name: "ipv6 wrong nibble count", qname: "1.0.ip6.arpa.", wantOK: false},
-		{name: "not a reverse name", qname: "example.com.", wantOK: false},
-		{name: "ipv4 bad octet", qname: "4.3.2.999.in-addr.arpa.", wantOK: false},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			got, ok := ptrQueryAddr(tt.qname)
-			assert.Equal(t, tt.wantOK, ok, "parse success mismatch")
-			if tt.wantOK {
-				assert.Equal(t, tt.want, got, "parsed address mismatch")
-			}
-		})
-	}
-}
-
-type mockRecordResolver struct {
-	mx    []*net.MX
-	txt   []string
-	ns    []*net.NS
-	srv   []*net.SRV
-	cname string
-	ptr   []string
-	err   error
-}
-
-func (m *mockRecordResolver) LookupMX(context.Context, string) ([]*net.MX, error) {
-	return m.mx, m.err
-}
-func (m *mockRecordResolver) LookupTXT(context.Context, string) ([]string, error) {
-	return m.txt, m.err
-}
-func (m *mockRecordResolver) LookupNS(context.Context, string) ([]*net.NS, error) {
-	return m.ns, m.err
-}
-func (m *mockRecordResolver) LookupSRV(context.Context, string, string, string) (string, []*net.SRV, error) {
-	return "", m.srv, m.err
-}
-func (m *mockRecordResolver) LookupCNAME(context.Context, string) (string, error) {
-	return m.cname, m.err
-}
-func (m *mockRecordResolver) LookupAddr(context.Context, string) ([]string, error) {
-	return m.ptr, m.err
-}
-
-func TestLookupRecords(t *testing.T) {
-	notFound := &net.DNSError{IsNotFound: true, Name: "example.com."}
-
-	t.Run("MX success", func(t *testing.T) {
-		r := &mockRecordResolver{mx: []*net.MX{{Host: "mail.example.com.", Pref: 10}}}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeMX, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		assert.Equal(t, "mail.example.com.", rrs[0].(*dns.MX).Mx)
-	})
-
-	t.Run("TXT short string is one character-string", func(t *testing.T) {
-		r := &mockRecordResolver{txt: []string{"v=spf1 -all"}}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeTXT, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		assert.Equal(t, []string{"v=spf1 -all"}, rrs[0].(*dns.TXT).Txt)
-	})
-
-	t.Run("TXT chunks long strings", func(t *testing.T) {
-		long := strings.Repeat("a", 300)
-		r := &mockRecordResolver{txt: []string{long}}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeTXT, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		txt := rrs[0].(*dns.TXT).Txt
-		require.Len(t, txt, 2, "300-byte string should split into two character-strings")
-		assert.Equal(t, 255, len(txt[0]))
-		assert.Equal(t, 45, len(txt[1]))
-	})
-
-	t.Run("NS success", func(t *testing.T) {
-		r := &mockRecordResolver{ns: []*net.NS{{Host: "ns1.example.com."}}}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeNS, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		assert.Equal(t, "ns1.example.com.", rrs[0].(*dns.NS).Ns)
-	})
-
-	t.Run("SRV success", func(t *testing.T) {
-		r := &mockRecordResolver{srv: []*net.SRV{{Target: "sip.example.com.", Port: 5060}}}
-		rrs, rcode := LookupRecords(context.Background(), r, "_sip._tcp.example.com.", dns.TypeSRV, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		assert.Equal(t, uint16(5060), rrs[0].(*dns.SRV).Port)
-	})
-
-	t.Run("CNAME success", func(t *testing.T) {
-		r := &mockRecordResolver{cname: "target.example.com."}
-		rrs, rcode := LookupRecords(context.Background(), r, "www.example.com.", dns.TypeCNAME, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		assert.Equal(t, "target.example.com.", rrs[0].(*dns.CNAME).Target)
-	})
-
-	t.Run("CNAME equal to name is NODATA", func(t *testing.T) {
-		r := &mockRecordResolver{cname: "example.com."}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeCNAME, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		assert.Empty(t, rrs, "self-referential CNAME is NODATA")
-	})
-
-	t.Run("PTR success", func(t *testing.T) {
-		r := &mockRecordResolver{ptr: []string{"host.example.com."}}
-		rrs, rcode := LookupRecords(context.Background(), r, "4.3.2.1.in-addr.arpa.", dns.TypePTR, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		require.Len(t, rrs, 1)
-		assert.Equal(t, "host.example.com.", rrs[0].(*dns.PTR).Ptr)
-	})
-
-	t.Run("PTR malformed name is NODATA", func(t *testing.T) {
-		r := &mockRecordResolver{}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypePTR, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		assert.Empty(t, rrs)
-	})
-
-	t.Run("not found is NODATA never NXDOMAIN", func(t *testing.T) {
-		r := &mockRecordResolver{err: notFound}
-		_, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeMX, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode, "missing record must not poison the name")
-	})
-
-	t.Run("server failure maps to SERVFAIL", func(t *testing.T) {
-		r := &mockRecordResolver{err: &net.DNSError{Err: "server misbehaving", IsTemporary: true}}
-		_, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeMX, 300)
-		assert.Equal(t, dns.RcodeServerFailure, rcode)
-	})
-
-	t.Run("unsupported type is NODATA", func(t *testing.T) {
-		r := &mockRecordResolver{}
-		rrs, rcode := LookupRecords(context.Background(), r, "example.com.", dns.TypeCAA, 300)
-		assert.Equal(t, dns.RcodeSuccess, rcode)
-		assert.Empty(t, rrs)
-	})
-}
-
-func TestStripOPT(t *testing.T) {
-	rm := &dns.Msg{
-		Extra: []dns.RR{
-			&dns.OPT{Hdr: dns.RR_Header{Name: ".", Rrtype: dns.TypeOPT}},
-			&dns.A{Hdr: dns.RR_Header{Name: "x.", Rrtype: dns.TypeA}, A: net.IPv4(1, 2, 3, 4)},
-		},
-	}
-	StripOPT(rm)
-	assert.Len(t, rm.Extra, 1, "OPT should be removed, A kept")
-	_, isOPT := rm.Extra[0].(*dns.OPT)
-	assert.False(t, isOPT, "remaining record must not be OPT")
-}
-
-func TestExtractEDE(t *testing.T) {
-	t.Run("no edns", func(t *testing.T) {
-		_, ok := ExtractEDE(&dns.Msg{})
-		assert.False(t, ok, "message without OPT has no EDE")
-	})
-
-	t.Run("edns without ede", func(t *testing.T) {
-		rm := &dns.Msg{}
-		rm.SetEdns0(4096, false)
-		_, ok := ExtractEDE(rm)
-		assert.False(t, ok, "OPT without EDE option returns false")
-	})
-
-	t.Run("with ede", func(t *testing.T) {
-		rm := &dns.Msg{}
-		opt := &dns.OPT{Hdr: dns.RR_Header{Name: ".", Rrtype: dns.TypeOPT}}
-		opt.Option = append(opt.Option, &dns.EDNS0_EDE{InfoCode: 49152, ExtraText: "upstream timeout"})
-		rm.Extra = append(rm.Extra, opt)
-
-		ede, ok := ExtractEDE(rm)
-		assert.True(t, ok, "EDE option should be found")
-		assert.Equal(t, uint16(49152), ede.InfoCode)
-		assert.Equal(t, "upstream timeout", ede.ExtraText)
-	})
-}

client/internal/dns/server.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"net/netip"
 	"net/url"
-	"os"
 	"slices"
 	"strings"
 	"sync"
@@ -39,15 +38,11 @@ const (
 	// defaultWarningDelayBase is the starting grace window before a
 	// "Nameserver group unreachable" event fires for a group that's
 	// never been healthy and only has overlay upstreams with no
-	// Connected peer. Per-server and overridable via envWarningDelay;
-	// see warningDelay.
-	defaultWarningDelayBase = 60 * time.Second
+	// Connected peer. Per-server and overridable; see warningDelayFor.
+	defaultWarningDelayBase = 30 * time.Second
 	// warningDelayBonusCap caps the route-count bonus added to the
-	// base grace window. See warningDelay.
+	// base grace window. See warningDelayFor.
 	warningDelayBonusCap = 30 * time.Second
-	// envWarningDelay overrides defaultWarningDelayBase with a Go duration
-	// string (e.g. "90s", "2m"). Invalid or non-positive values are ignored.
-	envWarningDelay = "NB_DNS_HEALTH_WARNING_DELAY"
 )
 
 // errNoUsableNameservers signals that a merged-domain group has no usable
@@ -140,7 +135,7 @@ type DefaultServer struct {
 	disableSys         bool
 	mux                sync.Mutex
 	service            service
-	dnsMuxHandlers     []handlerWrapper
+	dnsMuxMap          registeredHandlerMap
 	localResolver      *local.Resolver
 	wgInterface        WGIface
 	hostManager        hostManager
@@ -204,6 +199,8 @@ type handlerWrapper struct {
 	priority int
 }
 
+type registeredHandlerMap map[types.HandlerID]handlerWrapper
+
 // DefaultServerConfig holds configuration parameters for NewDefaultServer
 type DefaultServerConfig struct {
 	WgInterface    WGIface
@@ -292,6 +289,7 @@ func newDefaultServer(
 		service:           dnsService,
 		handlerChain:      handlerChain,
 		extraDomains:      make(map[domain.Domain]int),
+		dnsMuxMap:         make(registeredHandlerMap),
 		localResolver:     local.NewResolver(),
 		wgInterface:       wgInterface,
 		statusRecorder:    statusRecorder,
@@ -300,7 +298,7 @@ func newDefaultServer(
 		hostManager:       &noopHostConfigurator{},
 		mgmtCacheResolver: mgmtCacheResolver,
 		currentConfigHash: ^uint64(0), // Initialize to max uint64 to ensure first config is always applied
-		warningDelayBase:  warningDelayBaseFromEnv(),
+		warningDelayBase:  defaultWarningDelayBase,
 		healthRefresh:     make(chan struct{}, 1),
 	}
 	// Wire the local resolver against the peer status recorder so it can
@@ -330,7 +328,7 @@ func (s *DefaultServer) SetRouteSources(selected, active func() route.HAMap) {
 	type routeSettable interface {
 		setSelectedRoutes(func() route.HAMap)
 	}
-	for _, entry := range s.dnsMuxHandlers {
+	for _, entry := range s.dnsMuxMap {
 		if h, ok := entry.handler.(routeSettable); ok {
 			h.setSelectedRoutes(selected)
 		}
@@ -980,23 +978,19 @@ func (s *DefaultServer) usableNameServers(nameServers []nbdns.NameServer) []neti
 
 func (s *DefaultServer) updateMux(muxUpdates []handlerWrapper) {
 	// this will introduce a short period of time when the server is not able to handle DNS requests
-	for _, existing := range s.dnsMuxHandlers {
+	for _, existing := range s.dnsMuxMap {
 		s.deregisterHandler([]string{existing.domain}, existing.priority)
-		// The local resolver is a persistent singleton shared by every custom
-		// zone and reused across config updates. Its chain registrations are
-		// per-config and must be deregistered, but Stop() cancels its lookup
-		// context (breaking external CNAME-target resolution) and clears its
-		// records, so it must not be torn down here.
-		if existing.handler != s.localResolver {
-			existing.handler.Stop()
-		}
+		existing.handler.Stop()
 	}
 
+	muxUpdateMap := make(registeredHandlerMap)
+
 	for _, update := range muxUpdates {
 		s.registerHandler([]string{update.domain}, update.handler, update.priority)
+		muxUpdateMap[update.handler.ID()] = update
 	}
 
-	s.dnsMuxHandlers = muxUpdates
+	s.dnsMuxMap = muxUpdateMap
 }
 
 // updateNSGroupStates records the new group set and pokes the refresher.
@@ -1160,26 +1154,6 @@ func (s *DefaultServer) projectUnhealthy(p *nsGroupProj, servers []netip.AddrPor
 	return false
 }
 
-// warningDelayBaseFromEnv returns the base grace window, honoring
-// envWarningDelay when it holds a valid positive Go duration. Invalid or
-// non-positive values fall back to defaultWarningDelayBase.
-func warningDelayBaseFromEnv() time.Duration {
-	val := os.Getenv(envWarningDelay)
-	if val == "" {
-		return defaultWarningDelayBase
-	}
-	d, err := time.ParseDuration(val)
-	if err != nil {
-		log.Warnf("invalid %s value %q, using default %v: %v", envWarningDelay, val, defaultWarningDelayBase, err)
-		return defaultWarningDelayBase
-	}
-	if d <= 0 {
-		log.Warnf("%s must be positive, got %v, using default %v", envWarningDelay, d, defaultWarningDelayBase)
-		return defaultWarningDelayBase
-	}
-	return d
-}
-
 // warningDelay returns the grace window for the given selected-route
 // count. Scales gently: +1s per 100 routes, capped by
 // warningDelayBonusCap. Parallel handshakes mean handshake time grows
@@ -1230,7 +1204,7 @@ func (s *DefaultServer) groupHasImmediateUpstream(servers []netip.AddrPort, snap
 // in more than one handler.
 func (s *DefaultServer) collectUpstreamHealth() map[netip.AddrPort]UpstreamHealth {
 	merged := make(map[netip.AddrPort]UpstreamHealth)
-	for _, entry := range s.dnsMuxHandlers {
+	for _, entry := range s.dnsMuxMap {
 		reporter, ok := entry.handler.(upstreamHealthReporter)
 		if !ok {
 			continue

client/internal/dns/server_privileged_test.go

@@ -1,485 +0,0 @@
-//go:build privileged
-
-package dns
-
-import (
-	"context"
-	"fmt"
-	"net/netip"
-	"os"
-	"testing"
-
-	"github.com/golang/mock/gomock"
-	"github.com/miekg/dns"
-	"github.com/stretchr/testify/assert"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-
-	"github.com/netbirdio/netbird/client/iface"
-	pfmock "github.com/netbirdio/netbird/client/iface/mocks"
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
-	"github.com/netbirdio/netbird/client/internal/dns/local"
-	"github.com/netbirdio/netbird/client/internal/dns/test"
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/stdnet"
-	nbdns "github.com/netbirdio/netbird/dns"
-)
-
-func TestUpdateDNSServer(t *testing.T) {
-
-	nameServers := []nbdns.NameServer{
-		{
-			IP:     netip.MustParseAddr("8.8.8.8"),
-			NSType: nbdns.UDPNameServerType,
-			Port:   53,
-		},
-		{
-			IP:     netip.MustParseAddr("8.8.4.4"),
-			NSType: nbdns.UDPNameServerType,
-			Port:   53,
-		},
-	}
-
-	testCases := []struct {
-		name                string
-		initUpstreamMap     []handlerWrapper
-		initLocalZones      []nbdns.CustomZone
-		initSerial          uint64
-		inputSerial         uint64
-		inputUpdate         nbdns.Config
-		shouldFail          bool
-		expectedUpstreamMap []handlerWrapper
-		expectedLocalQs     []dns.Question
-	}{
-		{
-			name:            "Initial Config Should Succeed",
-			initUpstreamMap: nil,
-			initSerial:      0,
-			inputSerial:     1,
-			inputUpdate: nbdns.Config{
-				ServiceEnable: true,
-				CustomZones: []nbdns.CustomZone{
-					{
-						Domain:  "netbird.cloud",
-						Records: zoneRecords,
-					},
-				},
-				NameServerGroups: []*nbdns.NameServerGroup{
-					{
-						Domains:     []string{"netbird.io"},
-						NameServers: nameServers,
-					},
-					{
-						NameServers: nameServers,
-						Primary:     true,
-					},
-				},
-			},
-			expectedUpstreamMap: []handlerWrapper{
-				{
-					domain:   "netbird.io",
-					priority: PriorityUpstream,
-				},
-				{
-					domain:   "netbird.cloud",
-					priority: PriorityLocal,
-				},
-				{
-					domain:   nbdns.RootZone,
-					priority: PriorityDefault,
-				},
-			},
-			expectedLocalQs: []dns.Question{{Name: "peera.netbird.cloud.", Qtype: dns.TypeA, Qclass: dns.ClassINET}},
-		},
-		{
-			name:           "New Config Should Succeed",
-			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
-			initUpstreamMap: []handlerWrapper{
-				{
-					domain:   "netbird.cloud",
-					handler:  &mockHandler{},
-					priority: PriorityUpstream,
-				},
-			},
-			initSerial:  0,
-			inputSerial: 1,
-			inputUpdate: nbdns.Config{
-				ServiceEnable: true,
-				CustomZones: []nbdns.CustomZone{
-					{
-						Domain:  "netbird.cloud",
-						Records: zoneRecords,
-					},
-				},
-				NameServerGroups: []*nbdns.NameServerGroup{
-					{
-						Domains:     []string{"netbird.io"},
-						NameServers: nameServers,
-					},
-				},
-			},
-			expectedUpstreamMap: []handlerWrapper{
-				{
-					domain:   "netbird.io",
-					priority: PriorityUpstream,
-				},
-				{
-					domain:   "netbird.cloud",
-					priority: PriorityLocal,
-				},
-			},
-			expectedLocalQs: []dns.Question{{Name: zoneRecords[0].Name, Qtype: 1, Qclass: 1}},
-		},
-		{
-			name:            "Smaller Config Serial Should Be Skipped",
-			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: nil,
-			initSerial:      2,
-			inputSerial:     1,
-			shouldFail:      true,
-		},
-		{
-			name:            "Empty NS Group Domain Or Not Primary Element Should Fail",
-			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: nil,
-			initSerial:      0,
-			inputSerial:     1,
-			inputUpdate: nbdns.Config{
-				ServiceEnable: true,
-				CustomZones: []nbdns.CustomZone{
-					{
-						Domain:  "netbird.cloud",
-						Records: zoneRecords,
-					},
-				},
-				NameServerGroups: []*nbdns.NameServerGroup{
-					{
-						NameServers: nameServers,
-					},
-				},
-			},
-			shouldFail: true,
-		},
-		{
-			name:            "Invalid NS Group Nameservers list Should Fail",
-			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: nil,
-			initSerial:      0,
-			inputSerial:     1,
-			inputUpdate: nbdns.Config{
-				ServiceEnable: true,
-				CustomZones: []nbdns.CustomZone{
-					{
-						Domain:  "netbird.cloud",
-						Records: zoneRecords,
-					},
-				},
-				NameServerGroups: []*nbdns.NameServerGroup{
-					{
-						NameServers: nameServers,
-					},
-				},
-			},
-			shouldFail: true,
-		},
-		{
-			name:            "Invalid Custom Zone Records list Should Skip",
-			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: nil,
-			initSerial:      0,
-			inputSerial:     1,
-			inputUpdate: nbdns.Config{
-				ServiceEnable: true,
-				CustomZones: []nbdns.CustomZone{
-					{
-						Domain: "netbird.cloud",
-					},
-				},
-				NameServerGroups: []*nbdns.NameServerGroup{
-					{
-						NameServers: nameServers,
-						Primary:     true,
-					},
-				},
-			},
-			expectedUpstreamMap: []handlerWrapper{{
-				domain:   ".",
-				priority: PriorityDefault,
-			}},
-		},
-		{
-			name:           "Empty Config Should Succeed and Clean Maps",
-			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
-			initUpstreamMap: []handlerWrapper{
-				{
-					domain:   zoneRecords[0].Name,
-					handler:  &mockHandler{},
-					priority: PriorityUpstream,
-				},
-			},
-			initSerial:          0,
-			inputSerial:         1,
-			inputUpdate:         nbdns.Config{ServiceEnable: true},
-			expectedUpstreamMap: nil,
-			expectedLocalQs:     []dns.Question{},
-		},
-		{
-			name:           "Disabled Service Should clean map",
-			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
-			initUpstreamMap: []handlerWrapper{
-				{
-					domain:   zoneRecords[0].Name,
-					handler:  &mockHandler{},
-					priority: PriorityUpstream,
-				},
-			},
-			initSerial:          0,
-			inputSerial:         1,
-			inputUpdate:         nbdns.Config{ServiceEnable: false},
-			expectedUpstreamMap: nil,
-			expectedLocalQs:     []dns.Question{},
-		},
-	}
-
-	for n, testCase := range testCases {
-		t.Run(testCase.name, func(t *testing.T) {
-			privKey, _ := wgtypes.GenerateKey()
-			newNet, err := stdnet.NewNet(context.Background(), nil)
-			if err != nil {
-				t.Fatal(err)
-			}
-
-			opts := iface.WGIFaceOpts{
-				IFaceName:    fmt.Sprintf("utun230%d", n),
-				Address:      wgaddr.MustParseWGAddress(fmt.Sprintf("100.66.100.%d/32", n+1)),
-				WGPort:       33100,
-				WGPrivKey:    privKey.String(),
-				MTU:          iface.DefaultMTU,
-				TransportNet: newNet,
-			}
-
-			wgIface, err := iface.NewWGIFace(opts)
-			if err != nil {
-				t.Fatal(err)
-			}
-			err = wgIface.Create()
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer func() {
-				err = wgIface.Close()
-				if err != nil {
-					t.Log(err)
-				}
-			}()
-			dnsServer, err := NewDefaultServer(context.Background(), DefaultServerConfig{
-				WgInterface:    wgIface,
-				CustomAddress:  "",
-				StatusRecorder: peer.NewRecorder("mgm"),
-				StateManager:   nil,
-				DisableSys:     false,
-			})
-			if err != nil {
-				t.Fatal(err)
-			}
-			err = dnsServer.Initialize()
-			if err != nil {
-				t.Fatal(err)
-			}
-			defer func() {
-				err = dnsServer.hostManager.restoreHostDNS()
-				if err != nil {
-					t.Log(err)
-				}
-			}()
-
-			dnsServer.dnsMuxHandlers = testCase.initUpstreamMap
-			dnsServer.localResolver.Update(testCase.initLocalZones)
-			dnsServer.updateSerial = testCase.initSerial
-
-			err = dnsServer.UpdateDNSServer(testCase.inputSerial, testCase.inputUpdate)
-			if err != nil {
-				if testCase.shouldFail {
-					return
-				}
-				t.Fatalf("update dns server should not fail, got error: %v", err)
-			}
-
-			if len(dnsServer.dnsMuxHandlers) != len(testCase.expectedUpstreamMap) {
-				t.Fatalf("update upstream failed, map size is different than expected, want %d, got %d", len(testCase.expectedUpstreamMap), len(dnsServer.dnsMuxHandlers))
-			}
-
-			for _, expected := range testCase.expectedUpstreamMap {
-				found := false
-				for _, got := range dnsServer.dnsMuxHandlers {
-					if got.domain == expected.domain && got.priority == expected.priority {
-						found = true
-						break
-					}
-				}
-				if !found {
-					t.Fatalf("update upstream failed, handler for domain=%s priority=%d not found in dnsMuxHandlers: %#v", expected.domain, expected.priority, dnsServer.dnsMuxHandlers)
-				}
-			}
-
-			var responseMSG *dns.Msg
-			responseWriter := &test.MockResponseWriter{
-				WriteMsgFunc: func(m *dns.Msg) error {
-					responseMSG = m
-					return nil
-				},
-			}
-			for _, q := range testCase.expectedLocalQs {
-				dnsServer.localResolver.ServeDNS(responseWriter, &dns.Msg{
-					Question: []dns.Question{q},
-				})
-			}
-
-			if len(testCase.expectedLocalQs) > 0 {
-				assert.NotNil(t, responseMSG, "response message should not be nil")
-				assert.Equal(t, dns.RcodeSuccess, responseMSG.Rcode, "response code should be success")
-				assert.NotEmpty(t, responseMSG.Answer, "response message should have answers")
-			}
-		})
-	}
-}
-
-func TestDNSFakeResolverHandleUpdates(t *testing.T) {
-	ov := os.Getenv("NB_WG_KERNEL_DISABLED")
-	defer t.Setenv("NB_WG_KERNEL_DISABLED", ov)
-
-	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
-	newNet, err := stdnet.NewNet(context.Background(), []string{"utun2301"})
-	if err != nil {
-		t.Errorf("create stdnet: %v", err)
-		return
-	}
-
-	privKey, _ := wgtypes.GeneratePrivateKey()
-	opts := iface.WGIFaceOpts{
-		IFaceName:    "utun2301",
-		Address:      wgaddr.MustParseWGAddress("100.66.100.1/32"),
-		WGPort:       33100,
-		WGPrivKey:    privKey.String(),
-		MTU:          iface.DefaultMTU,
-		TransportNet: newNet,
-	}
-	wgIface, err := iface.NewWGIFace(opts)
-	if err != nil {
-		t.Errorf("build interface wireguard: %v", err)
-		return
-	}
-
-	err = wgIface.Create()
-	if err != nil {
-		t.Errorf("create and init wireguard interface: %v", err)
-		return
-	}
-	defer func() {
-		if err = wgIface.Close(); err != nil {
-			t.Logf("close wireguard interface: %v", err)
-		}
-	}()
-
-	ctrl := gomock.NewController(t)
-	defer ctrl.Finish()
-
-	packetfilter := pfmock.NewMockPacketFilter(ctrl)
-	packetfilter.EXPECT().FilterOutbound(gomock.Any(), gomock.Any()).AnyTimes()
-	packetfilter.EXPECT().SetUDPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-	packetfilter.EXPECT().SetTCPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-
-	if err := wgIface.SetFilter(packetfilter); err != nil {
-		t.Errorf("set packet filter: %v", err)
-		return
-	}
-
-	dnsServer, err := NewDefaultServer(context.Background(), DefaultServerConfig{
-		WgInterface:    wgIface,
-		CustomAddress:  "",
-		StatusRecorder: peer.NewRecorder("mgm"),
-		StateManager:   nil,
-		DisableSys:     false,
-	})
-	if err != nil {
-		t.Errorf("create DNS server: %v", err)
-		return
-	}
-
-	err = dnsServer.Initialize()
-	if err != nil {
-		t.Errorf("run DNS server: %v", err)
-		return
-	}
-	defer func() {
-		if err = dnsServer.hostManager.restoreHostDNS(); err != nil {
-			t.Logf("restore DNS settings on the host: %v", err)
-			return
-		}
-	}()
-
-	dnsServer.dnsMuxHandlers = []handlerWrapper{
-		{
-			domain:   zoneRecords[0].Name,
-			handler:  &local.Resolver{},
-			priority: PriorityUpstream,
-		},
-	}
-	dnsServer.localResolver.Update([]nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}})
-	dnsServer.updateSerial = 0
-
-	nameServers := []nbdns.NameServer{
-		{
-			IP:     netip.MustParseAddr("8.8.8.8"),
-			NSType: nbdns.UDPNameServerType,
-			Port:   53,
-		},
-		{
-			IP:     netip.MustParseAddr("8.8.4.4"),
-			NSType: nbdns.UDPNameServerType,
-			Port:   53,
-		},
-	}
-
-	update := nbdns.Config{
-		ServiceEnable: true,
-		CustomZones: []nbdns.CustomZone{
-			{
-				Domain:  "netbird.cloud",
-				Records: zoneRecords,
-			},
-		},
-		NameServerGroups: []*nbdns.NameServerGroup{
-			{
-				Domains:     []string{"netbird.io"},
-				NameServers: nameServers,
-			},
-			{
-				NameServers: nameServers,
-				Primary:     true,
-			},
-		},
-	}
-
-	// Start the server with regular configuration
-	if err := dnsServer.UpdateDNSServer(1, update); err != nil {
-		t.Fatalf("update dns server should not fail, got error: %v", err)
-		return
-	}
-
-	update2 := update
-	update2.ServiceEnable = false
-	// Disable the server, stop the listener
-	if err := dnsServer.UpdateDNSServer(2, update2); err != nil {
-		t.Fatalf("update dns server should not fail, got error: %v", err)
-		return
-	}
-
-	update3 := update2
-	update3.NameServerGroups = update3.NameServerGroups[:1]
-	// But service still get updates and we checking that we handle
-	// internal state in the right way
-	if err := dnsServer.UpdateDNSServer(3, update3); err != nil {
-		t.Fatalf("update dns server should not fail, got error: %v", err)
-		return
-	}
-}

client/internal/dns/server_test.go

@@ -10,6 +10,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/golang/mock/gomock"
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
@@ -22,6 +23,7 @@ import (
 	"github.com/netbirdio/netbird/client/iface"
 	"github.com/netbirdio/netbird/client/iface/configurer"
 	"github.com/netbirdio/netbird/client/iface/device"
+	pfmock "github.com/netbirdio/netbird/client/iface/mocks"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/dns/local"
 	"github.com/netbirdio/netbird/client/internal/dns/test"
@@ -102,6 +104,481 @@ func init() {
 	formatter.SetTextFormatter(log.StandardLogger())
 }
 
+func generateDummyHandler(d string, servers []nbdns.NameServer) *upstreamResolverBase {
+	var srvs []netip.AddrPort
+	for _, srv := range servers {
+		srvs = append(srvs, srv.AddrPort())
+	}
+	u := &upstreamResolverBase{
+		domain: domain.Domain(d),
+		cancel: func() {},
+	}
+	u.addRace(srvs)
+	return u
+}
+
+func TestUpdateDNSServer(t *testing.T) {
+
+	nameServers := []nbdns.NameServer{
+		{
+			IP:     netip.MustParseAddr("8.8.8.8"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+		{
+			IP:     netip.MustParseAddr("8.8.4.4"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+	}
+
+	dummyHandler := local.NewResolver()
+
+	testCases := []struct {
+		name                string
+		initUpstreamMap     registeredHandlerMap
+		initLocalZones      []nbdns.CustomZone
+		initSerial          uint64
+		inputSerial         uint64
+		inputUpdate         nbdns.Config
+		shouldFail          bool
+		expectedUpstreamMap registeredHandlerMap
+		expectedLocalQs     []dns.Question
+	}{
+		{
+			name:            "Initial Config Should Succeed",
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						Domains:     []string{"netbird.io"},
+						NameServers: nameServers,
+					},
+					{
+						NameServers: nameServers,
+						Primary:     true,
+					},
+				},
+			},
+			expectedUpstreamMap: registeredHandlerMap{
+				generateDummyHandler("netbird.io", nameServers).ID(): handlerWrapper{
+					domain:   "netbird.io",
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+				dummyHandler.ID(): handlerWrapper{
+					domain:   "netbird.cloud",
+					handler:  dummyHandler,
+					priority: PriorityLocal,
+				},
+				generateDummyHandler(".", nameServers).ID(): handlerWrapper{
+					domain:   nbdns.RootZone,
+					handler:  dummyHandler,
+					priority: PriorityDefault,
+				},
+			},
+			expectedLocalQs: []dns.Question{{Name: "peera.netbird.cloud.", Qtype: dns.TypeA, Qclass: dns.ClassINET}},
+		},
+		{
+			name:           "New Config Should Succeed",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
+			initUpstreamMap: registeredHandlerMap{
+				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+					domain:   "netbird.cloud",
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+			},
+			initSerial:  0,
+			inputSerial: 1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						Domains:     []string{"netbird.io"},
+						NameServers: nameServers,
+					},
+				},
+			},
+			expectedUpstreamMap: registeredHandlerMap{
+				generateDummyHandler("netbird.io", nameServers).ID(): handlerWrapper{
+					domain:   "netbird.io",
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+				"local-resolver": handlerWrapper{
+					domain:   "netbird.cloud",
+					handler:  dummyHandler,
+					priority: PriorityLocal,
+				},
+			},
+			expectedLocalQs: []dns.Question{{Name: zoneRecords[0].Name, Qtype: 1, Qclass: 1}},
+		},
+		{
+			name:            "Smaller Config Serial Should Be Skipped",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      2,
+			inputSerial:     1,
+			shouldFail:      true,
+		},
+		{
+			name:            "Empty NS Group Domain Or Not Primary Element Should Fail",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						NameServers: nameServers,
+					},
+				},
+			},
+			shouldFail: true,
+		},
+		{
+			name:            "Invalid NS Group Nameservers list Should Fail",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain:  "netbird.cloud",
+						Records: zoneRecords,
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						NameServers: nameServers,
+					},
+				},
+			},
+			shouldFail: true,
+		},
+		{
+			name:            "Invalid Custom Zone Records list Should Skip",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
+			inputUpdate: nbdns.Config{
+				ServiceEnable: true,
+				CustomZones: []nbdns.CustomZone{
+					{
+						Domain: "netbird.cloud",
+					},
+				},
+				NameServerGroups: []*nbdns.NameServerGroup{
+					{
+						NameServers: nameServers,
+						Primary:     true,
+					},
+				},
+			},
+			expectedUpstreamMap: registeredHandlerMap{generateDummyHandler(".", nameServers).ID(): handlerWrapper{
+				domain:   ".",
+				handler:  dummyHandler,
+				priority: PriorityDefault,
+			}},
+		},
+		{
+			name:           "Empty Config Should Succeed and Clean Maps",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
+			initUpstreamMap: registeredHandlerMap{
+				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+					domain:   zoneRecords[0].Name,
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+			},
+			initSerial:          0,
+			inputSerial:         1,
+			inputUpdate:         nbdns.Config{ServiceEnable: true},
+			expectedUpstreamMap: make(registeredHandlerMap),
+			expectedLocalQs:     []dns.Question{},
+		},
+		{
+			name:           "Disabled Service Should clean map",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
+			initUpstreamMap: registeredHandlerMap{
+				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+					domain:   zoneRecords[0].Name,
+					handler:  dummyHandler,
+					priority: PriorityUpstream,
+				},
+			},
+			initSerial:          0,
+			inputSerial:         1,
+			inputUpdate:         nbdns.Config{ServiceEnable: false},
+			expectedUpstreamMap: make(registeredHandlerMap),
+			expectedLocalQs:     []dns.Question{},
+		},
+	}
+
+	for n, testCase := range testCases {
+		t.Run(testCase.name, func(t *testing.T) {
+			privKey, _ := wgtypes.GenerateKey()
+			newNet, err := stdnet.NewNet(context.Background(), nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			opts := iface.WGIFaceOpts{
+				IFaceName:    fmt.Sprintf("utun230%d", n),
+				Address:      wgaddr.MustParseWGAddress(fmt.Sprintf("100.66.100.%d/32", n+1)),
+				WGPort:       33100,
+				WGPrivKey:    privKey.String(),
+				MTU:          iface.DefaultMTU,
+				TransportNet: newNet,
+			}
+
+			wgIface, err := iface.NewWGIFace(opts)
+			if err != nil {
+				t.Fatal(err)
+			}
+			err = wgIface.Create()
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer func() {
+				err = wgIface.Close()
+				if err != nil {
+					t.Log(err)
+				}
+			}()
+			dnsServer, err := NewDefaultServer(context.Background(), DefaultServerConfig{
+				WgInterface:    wgIface,
+				CustomAddress:  "",
+				StatusRecorder: peer.NewRecorder("mgm"),
+				StateManager:   nil,
+				DisableSys:     false,
+			})
+			if err != nil {
+				t.Fatal(err)
+			}
+			err = dnsServer.Initialize()
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer func() {
+				err = dnsServer.hostManager.restoreHostDNS()
+				if err != nil {
+					t.Log(err)
+				}
+			}()
+
+			dnsServer.dnsMuxMap = testCase.initUpstreamMap
+			dnsServer.localResolver.Update(testCase.initLocalZones)
+			dnsServer.updateSerial = testCase.initSerial
+
+			err = dnsServer.UpdateDNSServer(testCase.inputSerial, testCase.inputUpdate)
+			if err != nil {
+				if testCase.shouldFail {
+					return
+				}
+				t.Fatalf("update dns server should not fail, got error: %v", err)
+			}
+
+			if len(dnsServer.dnsMuxMap) != len(testCase.expectedUpstreamMap) {
+				t.Fatalf("update upstream failed, map size is different than expected, want %d, got %d", len(testCase.expectedUpstreamMap), len(dnsServer.dnsMuxMap))
+			}
+
+			for key := range testCase.expectedUpstreamMap {
+				_, found := dnsServer.dnsMuxMap[key]
+				if !found {
+					t.Fatalf("update upstream failed, key %s was not found in the dnsMuxMap: %#v", key, dnsServer.dnsMuxMap)
+				}
+			}
+
+			var responseMSG *dns.Msg
+			responseWriter := &test.MockResponseWriter{
+				WriteMsgFunc: func(m *dns.Msg) error {
+					responseMSG = m
+					return nil
+				},
+			}
+			for _, q := range testCase.expectedLocalQs {
+				dnsServer.localResolver.ServeDNS(responseWriter, &dns.Msg{
+					Question: []dns.Question{q},
+				})
+			}
+
+			if len(testCase.expectedLocalQs) > 0 {
+				assert.NotNil(t, responseMSG, "response message should not be nil")
+				assert.Equal(t, dns.RcodeSuccess, responseMSG.Rcode, "response code should be success")
+				assert.NotEmpty(t, responseMSG.Answer, "response message should have answers")
+			}
+		})
+	}
+}
+
+func TestDNSFakeResolverHandleUpdates(t *testing.T) {
+	ov := os.Getenv("NB_WG_KERNEL_DISABLED")
+	defer t.Setenv("NB_WG_KERNEL_DISABLED", ov)
+
+	t.Setenv("NB_WG_KERNEL_DISABLED", "true")
+	newNet, err := stdnet.NewNet(context.Background(), []string{"utun2301"})
+	if err != nil {
+		t.Errorf("create stdnet: %v", err)
+		return
+	}
+
+	privKey, _ := wgtypes.GeneratePrivateKey()
+	opts := iface.WGIFaceOpts{
+		IFaceName:    "utun2301",
+		Address:      wgaddr.MustParseWGAddress("100.66.100.1/32"),
+		WGPort:       33100,
+		WGPrivKey:    privKey.String(),
+		MTU:          iface.DefaultMTU,
+		TransportNet: newNet,
+	}
+	wgIface, err := iface.NewWGIFace(opts)
+	if err != nil {
+		t.Errorf("build interface wireguard: %v", err)
+		return
+	}
+
+	err = wgIface.Create()
+	if err != nil {
+		t.Errorf("create and init wireguard interface: %v", err)
+		return
+	}
+	defer func() {
+		if err = wgIface.Close(); err != nil {
+			t.Logf("close wireguard interface: %v", err)
+		}
+	}()
+
+	ctrl := gomock.NewController(t)
+	defer ctrl.Finish()
+
+	packetfilter := pfmock.NewMockPacketFilter(ctrl)
+	packetfilter.EXPECT().FilterOutbound(gomock.Any(), gomock.Any()).AnyTimes()
+	packetfilter.EXPECT().SetUDPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
+	packetfilter.EXPECT().SetTCPPacketHook(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
+
+	if err := wgIface.SetFilter(packetfilter); err != nil {
+		t.Errorf("set packet filter: %v", err)
+		return
+	}
+
+	dnsServer, err := NewDefaultServer(context.Background(), DefaultServerConfig{
+		WgInterface:    wgIface,
+		CustomAddress:  "",
+		StatusRecorder: peer.NewRecorder("mgm"),
+		StateManager:   nil,
+		DisableSys:     false,
+	})
+	if err != nil {
+		t.Errorf("create DNS server: %v", err)
+		return
+	}
+
+	err = dnsServer.Initialize()
+	if err != nil {
+		t.Errorf("run DNS server: %v", err)
+		return
+	}
+	defer func() {
+		if err = dnsServer.hostManager.restoreHostDNS(); err != nil {
+			t.Logf("restore DNS settings on the host: %v", err)
+			return
+		}
+	}()
+
+	dnsServer.dnsMuxMap = registeredHandlerMap{
+		"id1": handlerWrapper{
+			domain:   zoneRecords[0].Name,
+			handler:  &local.Resolver{},
+			priority: PriorityUpstream,
+		},
+	}
+	dnsServer.localResolver.Update([]nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}})
+	dnsServer.updateSerial = 0
+
+	nameServers := []nbdns.NameServer{
+		{
+			IP:     netip.MustParseAddr("8.8.8.8"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+		{
+			IP:     netip.MustParseAddr("8.8.4.4"),
+			NSType: nbdns.UDPNameServerType,
+			Port:   53,
+		},
+	}
+
+	update := nbdns.Config{
+		ServiceEnable: true,
+		CustomZones: []nbdns.CustomZone{
+			{
+				Domain:  "netbird.cloud",
+				Records: zoneRecords,
+			},
+		},
+		NameServerGroups: []*nbdns.NameServerGroup{
+			{
+				Domains:     []string{"netbird.io"},
+				NameServers: nameServers,
+			},
+			{
+				NameServers: nameServers,
+				Primary:     true,
+			},
+		},
+	}
+
+	// Start the server with regular configuration
+	if err := dnsServer.UpdateDNSServer(1, update); err != nil {
+		t.Fatalf("update dns server should not fail, got error: %v", err)
+		return
+	}
+
+	update2 := update
+	update2.ServiceEnable = false
+	// Disable the server, stop the listener
+	if err := dnsServer.UpdateDNSServer(2, update2); err != nil {
+		t.Fatalf("update dns server should not fail, got error: %v", err)
+		return
+	}
+
+	update3 := update2
+	update3.NameServerGroups = update3.NameServerGroups[:1]
+	// But service still get updates and we checking that we handle
+	// internal state in the right way
+	if err := dnsServer.UpdateDNSServer(3, update3); err != nil {
+		t.Fatalf("update dns server should not fail, got error: %v", err)
+		return
+	}
+}
+
 func TestDNSServerStartStop(t *testing.T) {
 	testCases := []struct {
 		name     string
@@ -552,15 +1029,15 @@ func (m *mockService) RegisterMux(string, dns.Handler) {}
 func (m *mockService) DeregisterMux(string)            {}
 
 func TestDefaultServer_UpdateMux(t *testing.T) {
-	baseMatchHandlers := []handlerWrapper{
-		{
+	baseMatchHandlers := registeredHandlerMap{
+		"upstream-group1": {
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group1",
 			},
 			priority: PriorityUpstream,
 		},
-		{
+		"upstream-group2": {
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group2",
@@ -569,15 +1046,15 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 		},
 	}
 
-	baseRootHandlers := []handlerWrapper{
-		{
+	baseRootHandlers := registeredHandlerMap{
+		"upstream-root1": {
 			domain: ".",
 			handler: &mockHandler{
 				Id: "upstream-root1",
 			},
 			priority: PriorityDefault,
 		},
-		{
+		"upstream-root2": {
 			domain: ".",
 			handler: &mockHandler{
 				Id: "upstream-root2",
@@ -586,22 +1063,22 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 		},
 	}
 
-	baseMixedHandlers := []handlerWrapper{
-		{
+	baseMixedHandlers := registeredHandlerMap{
+		"upstream-group1": {
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group1",
 			},
 			priority: PriorityUpstream,
 		},
-		{
+		"upstream-group2": {
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group2",
 			},
 			priority: PriorityUpstream - 1,
 		},
-		{
+		"upstream-other": {
 			domain: "other.com",
 			handler: &mockHandler{
 				Id: "upstream-other",
@@ -612,7 +1089,7 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 
 	tests := []struct {
 		name             string
-		initialHandlers  []handlerWrapper
+		initialHandlers  registeredHandlerMap
 		updates          []handlerWrapper
 		expectedHandlers map[string]string // map[HandlerID]domain
 		description      string
@@ -896,38 +1373,32 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			server := &DefaultServer{
-				dnsMuxHandlers: tt.initialHandlers,
-				handlerChain:   NewHandlerChain(),
-				service:        &mockService{},
+				dnsMuxMap:    tt.initialHandlers,
+				handlerChain: NewHandlerChain(),
+				service:      &mockService{},
 			}
 
 			// Perform the update
 			server.updateMux(tt.updates)
 
 			// Verify the results
-			assert.Equal(t, len(tt.expectedHandlers), len(server.dnsMuxHandlers),
+			assert.Equal(t, len(tt.expectedHandlers), len(server.dnsMuxMap),
 				"Number of handlers after update doesn't match expected")
 
 			// Check each expected handler
 			for id, expectedDomain := range tt.expectedHandlers {
-				var found *handlerWrapper
-				for i := range server.dnsMuxHandlers {
-					if server.dnsMuxHandlers[i].handler.ID() == types.HandlerID(id) {
-						found = &server.dnsMuxHandlers[i]
-						break
-					}
-				}
-				assert.NotNil(t, found, "Expected handler %s not found", id)
-				if found != nil {
-					assert.Equal(t, expectedDomain, found.domain,
+				handler, exists := server.dnsMuxMap[types.HandlerID(id)]
+				assert.True(t, exists, "Expected handler %s not found", id)
+				if exists {
+					assert.Equal(t, expectedDomain, handler.domain,
 						"Domain mismatch for handler %s", id)
 				}
 			}
 
 			// Verify no unexpected handlers exist
-			for _, entry := range server.dnsMuxHandlers {
-				_, expected := tt.expectedHandlers[string(entry.handler.ID())]
-				assert.True(t, expected, "Unexpected handler found: %s", entry.handler.ID())
+			for HandlerID := range server.dnsMuxMap {
+				_, expected := tt.expectedHandlers[string(HandlerID)]
+				assert.True(t, expected, "Unexpected handler found: %s", HandlerID)
 			}
 
 			// Verify the handlerChain state and order
@@ -942,7 +1413,7 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 
 				// Verify handler exists in mux
 				foundInMux := false
-				for _, muxEntry := range server.dnsMuxHandlers {
+				for _, muxEntry := range server.dnsMuxMap {
 					if chainEntry.Handler == muxEntry.handler &&
 						chainEntry.Priority == muxEntry.priority &&
 						chainEntry.Pattern == dns.Fqdn(muxEntry.domain) {
@@ -951,108 +1422,12 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 					}
 				}
 				assert.True(t, foundInMux,
-					"Handler in chain not found in dnsMuxHandlers")
+					"Handler in chain not found in dnsMuxMap")
 			}
 		})
 	}
 }
 
-// chainHasPattern reports whether the handler chain holds an entry registered
-// for the given fqdn pattern at the given priority.
-func chainHasPattern(s *DefaultServer, pattern string, priority int) bool {
-	for _, h := range s.handlerChain.handlers {
-		if h.OrigPattern == pattern && h.Priority == priority {
-			return true
-		}
-	}
-	return false
-}
-
-// TestDefaultServer_UpdateMux_SharedHandlerZoneRemoval verifies that updateMux
-// tracks each (handler, domain) registration independently when one handler
-// serves multiple zones. Every custom zone is served by the same handler
-// instance (the local resolver, whose ID is the constant "local-resolver"), so
-// removing one zone must deregister exactly that zone's chain entry and leave
-// the others in place. Tracking registrations by handler ID alone collapses all
-// zones onto one entry, leaving removed zones in the chain to answer
-// authoritatively with no records.
-func TestDefaultServer_UpdateMux_SharedHandlerZoneRemoval(t *testing.T) {
-	// One handler serves every custom zone, mirroring s.localResolver.
-	shared := &mockHandler{Id: "local-resolver"}
-
-	server := &DefaultServer{
-		handlerChain: NewHandlerChain(),
-		service:      &mockService{},
-	}
-
-	// Two custom zones under the same handler. The surviving zone is registered
-	// last, mirroring the management emission order.
-	server.updateMux([]handlerWrapper{
-		{domain: "userzone.test", handler: shared, priority: PriorityLocal},
-		{domain: "peerzone.test", handler: shared, priority: PriorityLocal},
-	})
-
-	require.True(t, chainHasPattern(server, "userzone.test.", PriorityLocal),
-		"userzone.test should be registered after the first update")
-	require.True(t, chainHasPattern(server, "peerzone.test.", PriorityLocal),
-		"peerzone.test should be registered after the first update")
-
-	// Remove one zone, keep the other.
-	server.updateMux([]handlerWrapper{
-		{domain: "peerzone.test", handler: shared, priority: PriorityLocal},
-	})
-
-	assert.True(t, chainHasPattern(server, "peerzone.test.", PriorityLocal),
-		"peerzone.test should remain after removing userzone.test")
-	assert.False(t, chainHasPattern(server, "userzone.test.", PriorityLocal),
-		"userzone.test handler must be deregistered, not leaked in the chain")
-}
-
-// TestDefaultServer_UpdateMux_PreservesLocalResolver verifies that updateMux
-// does not tear down the shared local resolver during reconfiguration. The
-// resolver is a process-lifetime singleton reused across config updates;
-// Stop() cancels its lookup context (breaking external CNAME-target
-// resolution) and clears its records. updateMux must deregister its chain
-// entries without stopping it. Records surviving a teardown update is the
-// observable proxy: Stop() would have cleared them.
-func TestDefaultServer_UpdateMux_PreservesLocalResolver(t *testing.T) {
-	resolver := local.NewResolver()
-	require.NoError(t, resolver.RegisterRecord(nbdns.SimpleRecord{
-		Name:  "peer.netbird.cloud.",
-		Type:  int(dns.TypeA),
-		Class: nbdns.DefaultClass,
-		TTL:   300,
-		RData: "10.0.0.1",
-	}))
-
-	server := &DefaultServer{
-		handlerChain:  NewHandlerChain(),
-		service:       &mockService{},
-		localResolver: resolver,
-	}
-
-	server.updateMux([]handlerWrapper{
-		{domain: "netbird.cloud", handler: resolver, priority: PriorityLocal},
-	})
-
-	// Remove the zone. The resolver must survive so its records and lookup
-	// context stay intact for the next registration.
-	server.updateMux(nil)
-
-	var response *dns.Msg
-	resolver.ServeDNS(&test.MockResponseWriter{
-		WriteMsgFunc: func(m *dns.Msg) error {
-			response = m
-			return nil
-		},
-	}, &dns.Msg{Question: []dns.Question{{Name: "peer.netbird.cloud.", Qtype: dns.TypeA, Qclass: dns.ClassINET}}})
-
-	require.NotNil(t, response, "local resolver should answer after teardown")
-	assert.Equal(t, dns.RcodeSuccess, response.Rcode,
-		"local resolver records must survive teardown; updateMux must not Stop() the shared resolver")
-	assert.NotEmpty(t, response.Answer, "answer should contain the surviving record")
-}
-
 func TestExtraDomains(t *testing.T) {
 	tests := []struct {
 		name                string
@@ -1674,6 +2049,7 @@ func TestBuildUpstreamHandler_MergesGroupsPerDomain(t *testing.T) {
 		localResolver: local.NewResolver(),
 		handlerChain:  NewHandlerChain(),
 		hostManager:   &noopHostConfigurator{},
+		dnsMuxMap:     make(registeredHandlerMap),
 	}
 
 	groups := []*nbdns.NameServerGroup{
@@ -1831,7 +2207,7 @@ func TestEvaluateNSGroupHealth(t *testing.T) {
 	}
 }
 
-// healthStubHandler is a minimal dnsMuxHandlers entry that exposes a fixed
+// healthStubHandler is a minimal dnsMuxMap entry that exposes a fixed
 // UpstreamHealth snapshot, letting tests drive recomputeNSGroupStates
 // without spinning up real handlers.
 type healthStubHandler struct {
@@ -1907,11 +2283,12 @@ func newProjTestFixture(t *testing.T) *projTestFixture {
 		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.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: fx.stub, priority: PriorityUpstream}}
+	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})
@@ -2018,6 +2395,7 @@ func TestProjection_OverlayAddrNoRouteDelaysWarning(t *testing.T) {
 		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,
@@ -2029,7 +2407,7 @@ func TestProjection_OverlayAddrNoRouteDelaysWarning(t *testing.T) {
 	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{
 		overlayPeer: {LastFail: time.Now(), LastErr: "timeout"},
 	}}
-	server.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: stub, priority: PriorityUpstream}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
 
 	server.mux.Lock()
 	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
@@ -2066,6 +2444,7 @@ func TestProjection_StopClearsHealthState(t *testing.T) {
 		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 },
@@ -2080,7 +2459,7 @@ func TestProjection_StopClearsHealthState(t *testing.T) {
 		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.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: stub, priority: PriorityUpstream}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
 
 	server.mux.Lock()
 	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
@@ -2105,32 +2484,6 @@ func TestProjection_StopClearsHealthState(t *testing.T) {
 // 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 TestWarningDelayBaseFromEnv(t *testing.T) {
-	tests := []struct {
-		name string
-		set  bool
-		val  string
-		want time.Duration
-	}{
-		{name: "unset uses default", set: false, want: defaultWarningDelayBase},
-		{name: "valid override", set: true, val: "90s", want: 90 * time.Second},
-		{name: "valid minutes", set: true, val: "2m", want: 2 * time.Minute},
-		{name: "invalid falls back", set: true, val: "notaduration", want: defaultWarningDelayBase},
-		{name: "zero falls back", set: true, val: "0s", want: defaultWarningDelayBase},
-		{name: "negative falls back", set: true, val: "-30s", want: defaultWarningDelayBase},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(envWarningDelay, tc.val)
-			if !tc.set {
-				os.Unsetenv(envWarningDelay)
-			}
-			assert.Equal(t, tc.want, warningDelayBaseFromEnv(), "grace window base")
-		})
-	}
-}
-
 func TestProjection_OverlayRecoversDuringGrace(t *testing.T) {
 	fx := newProjTestFixture(t)
 	fx.server.warningDelayBase = 200 * time.Millisecond
@@ -2242,6 +2595,7 @@ func TestProjection_MixedGroupEmitsImmediately(t *testing.T) {
 	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,
@@ -2259,7 +2613,7 @@ func TestProjection_MixedGroupEmitsImmediately(t *testing.T) {
 			overlay: {LastFail: time.Now(), LastErr: "timeout"},
 		},
 	}
-	server.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: stub, priority: PriorityUpstream}}
+	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
 
 	server.mux.Lock()
 	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
@@ -2286,6 +2640,7 @@ func TestDNSLoopPrevention(t *testing.T) {
 		localResolver: local.NewResolver(),
 		handlerChain:  NewHandlerChain(),
 		hostManager:   &noopHostConfigurator{},
+		dnsMuxMap:     make(registeredHandlerMap),
 	}
 
 	tests := []struct {

client/internal/dns/service_listener.go

@@ -292,16 +292,18 @@ func (s *serviceViaListener) generateFreePort() (uint16, error) {
 		return customPort, nil
 	}
 
-	probeListener, err := net.ListenUDP("udp4", &net.UDPAddr{})
+	udpAddr := net.UDPAddrFromAddrPort(netip.MustParseAddrPort("0.0.0.0:0"))
+	probeListener, err := net.ListenUDP("udp", udpAddr)
 	if err != nil {
 		log.Debugf("failed to bind random port for DNS: %s", err)
 		return 0, err
 	}
 
-	port := uint16(probeListener.LocalAddr().(*net.UDPAddr).Port)
-	if err = probeListener.Close(); err != nil {
+	addrPort := netip.MustParseAddrPort(probeListener.LocalAddr().String()) // might panic if address is incorrect
+	err = probeListener.Close()
+	if err != nil {
 		log.Debugf("failed to free up DNS port: %s", err)
 		return 0, err
 	}
-	return port, nil
+	return addrPort.Port(), nil
 }

client/internal/dns/upstream.go

@@ -443,32 +443,29 @@ func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, r *dns.M
 		return raceResult{}, &upstreamFailure{upstream: upstream, reason: "no response"}
 	}
 
-	// A valid response means the upstream is reachable, whatever the Rcode.
-	u.markUpstreamOk(upstream)
-
 	proto := ""
 	if upstreamProto != nil {
 		proto = upstreamProto.protocol
 	}
 
 	if rm.Rcode == dns.RcodeServerFailure || rm.Rcode == dns.RcodeRefused {
-		// SERVFAIL and REFUSED are per-question outcomes (DNSSEC-bogus names,
-		// refused zones, transient recursion errors), not reachability
-		// problems: fail over for a better answer but keep the upstream healthy.
 		if code, ok := nonRetryableEDE(rm); ok {
 			if !hadEdns {
-				resutil.StripOPT(rm)
+				stripOPT(rm)
 			}
+			u.markUpstreamOk(upstream)
 			return raceResult{msg: rm, upstream: upstream, protocol: proto, ede: edeName(code)}, nil
 		}
 		reason := dns.RcodeToString[rm.Rcode]
+		u.markUpstreamFail(upstream, reason)
 		return raceResult{}, &upstreamFailure{upstream: upstream, reason: reason}
 	}
 
 	if !hadEdns {
-		resutil.StripOPT(rm)
+		stripOPT(rm)
 	}
 
+	u.markUpstreamOk(upstream)
 	return raceResult{msg: rm, upstream: upstream, protocol: proto}, nil
 }
 
@@ -523,6 +520,22 @@ func upstreamUDPSize() uint16 {
 	return dns.MinMsgSize
 }
 
+// stripOPT removes any OPT pseudo-RRs from the response's Extra section so
+// the response complies with RFC 6891 when the client did not advertise EDNS0.
+func stripOPT(rm *dns.Msg) {
+	if len(rm.Extra) == 0 {
+		return
+	}
+	out := rm.Extra[:0]
+	for _, rr := range rm.Extra {
+		if _, ok := rr.(*dns.OPT); ok {
+			continue
+		}
+		out = append(out, rr)
+	}
+	rm.Extra = out
+}
+
 func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.AddrPort, startTime time.Time) *upstreamFailure {
 	if !errors.Is(err, context.DeadlineExceeded) && !isTimeout(err) {
 		return &upstreamFailure{upstream: upstream, reason: err.Error()}

client/internal/dns/upstream_test.go

@@ -517,78 +517,6 @@ func TestUpstreamResolver_HealthTracking(t *testing.T) {
 	assert.NotContains(t, health, bad, "sibling upstream should not be queried when primary answers")
 }
 
-// TestUpstreamResolver_HealthTracking_ResponseMeansReachable verifies that an
-// upstream which answers with SERVFAIL or REFUSED is recorded as healthy:
-// those are per-question outcomes from a reachable server and must not mark
-// the upstream unhealthy. Only transport failures (timeouts) do.
-func TestUpstreamResolver_HealthTracking_ResponseMeansReachable(t *testing.T) {
-	a := netip.MustParseAddrPort("192.0.2.10:53")
-	b := netip.MustParseAddrPort("192.0.2.11:53")
-	timeoutErr := &net.OpError{Op: "read", Err: fmt.Errorf("i/o timeout")}
-
-	tests := []struct {
-		name        string
-		respA       mockUpstreamResponse
-		respB       mockUpstreamResponse
-		wantHealthy bool
-	}{
-		{
-			name:        "both SERVFAIL are reachable",
-			respA:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
-			respB:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
-			wantHealthy: true,
-		},
-		{
-			name:        "both REFUSED are reachable",
-			respA:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeRefused, "")},
-			respB:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeRefused, "")},
-			wantHealthy: true,
-		},
-		{
-			name:        "timeout marks unhealthy",
-			respA:       mockUpstreamResponse{err: timeoutErr},
-			respB:       mockUpstreamResponse{err: timeoutErr},
-			wantHealthy: false,
-		},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			mockClient := &mockUpstreamResolverPerServer{
-				responses: map[string]mockUpstreamResponse{
-					a.String(): tc.respA,
-					b.String(): tc.respB,
-				},
-				rtt: time.Millisecond,
-			}
-
-			ctx, cancel := context.WithCancel(context.Background())
-			defer cancel()
-
-			resolver := &upstreamResolverBase{
-				ctx:             ctx,
-				upstreamClient:  mockClient,
-				upstreamTimeout: UpstreamTimeout,
-			}
-			resolver.addRace([]netip.AddrPort{a, b})
-
-			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, a, "primary upstream should have a health record")
-			if tc.wantHealthy {
-				assert.False(t, health[a].LastOk.IsZero(), "responding upstream should have LastOk set")
-				assert.True(t, health[a].LastFail.IsZero(), "responding upstream should not be marked failed")
-				assert.Empty(t, health[a].LastErr, "responding upstream should have no error")
-			} else {
-				assert.False(t, health[a].LastFail.IsZero(), "timed-out upstream should be marked failed")
-				assert.NotEmpty(t, health[a].LastErr, "timed-out upstream should record an error")
-			}
-		})
-	}
-}
-
 func TestFormatFailures(t *testing.T) {
 	testCases := []struct {
 		name     string
@@ -985,6 +913,19 @@ func TestEDEName(t *testing.T) {
 	assert.Equal(t, "EDE 9999", edeName(9999), "unknown code falls back to numeric")
 }
 
+func TestStripOPT(t *testing.T) {
+	rm := &dns.Msg{
+		Extra: []dns.RR{
+			&dns.OPT{Hdr: dns.RR_Header{Name: ".", Rrtype: dns.TypeOPT}},
+			&dns.A{Hdr: dns.RR_Header{Name: "x.", Rrtype: dns.TypeA}, A: net.IPv4(1, 2, 3, 4)},
+		},
+	}
+	stripOPT(rm)
+	assert.Len(t, rm.Extra, 1, "OPT should be removed, A kept")
+	_, isOPT := rm.Extra[0].(*dns.OPT)
+	assert.False(t, isOPT, "remaining record must not be OPT")
+}
+
 func TestUpstreamResolver_NonRetryableEDEShortCircuits(t *testing.T) {
 	upstream1 := netip.MustParseAddrPort("192.0.2.1:53")
 	upstream2 := netip.MustParseAddrPort("192.0.2.2:53")