Merge pull request #332 from Control-D-Inc/release-branch-v1.5.7

Release branch v1.5.7

.dockerignore

@@ -0,0 +1,2 @@
+Dockerfile
+.git/

.github/workflows/ci.yml

@@ -9,18 +9,18 @@ jobs:
       fail-fast: false
       matrix:
         os: ["windows-latest", "ubuntu-latest", "macOS-latest"]
-        go: ["1.20.x"]
+        go: ["1.26.x"]
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v3
         with:
           fetch-depth: 1
-      - uses: WillAbides/setup-go-faster@v1.8.0
+      - uses: actions/setup-go@v6
         with:
           go-version: ${{ matrix.go }}
       - run: "go test -race ./..."
-      - uses: dominikh/staticcheck-action@v1.2.0
+      - uses: dominikh/staticcheck-action@v1.4.1
         with:
-          version: "2023.1.2"
+          version: "2026.2"
           install-go: false
           cache-key: ${{ matrix.go }}

.gitignore

@@ -1,3 +1,16 @@
-
 dist/
 gon.hcl
+
+/Build
+.DS_Store
+
+# Release folder
+dist/
+
+# Binaries
+ctrld-*
+
+# generated file
+cmd/cli/rsrc_*.syso
+ctrld
+ctrld.exe

.goreleaser-darwin.yaml

@@ -9,6 +9,8 @@ builds:
       - -trimpath
     ldflags:
       - -s -w
+      - -X main.version={{.Version}}
+      - -X main.commit={{.Commit}}
     goos:
       - darwin
     goarch:

.goreleaser-qf.yaml

@@ -9,11 +9,15 @@ builds:
       - -trimpath
     ldflags:
       - -s -w
+      - -X main.version={{.Version}}
+      - -X main.commit={{.Commit}}
     goos:
       - darwin
       - linux
       - windows
     goarch:
+      - 386
+      - arm
       - amd64
       - arm64
     tags:

.goreleaser.yaml

@@ -9,6 +9,8 @@ builds:
       - -trimpath
     ldflags:
       - -s -w
+      - -X main.version={{.Version}}
+      - -X main.commit={{.Commit}}
     goos:
       - linux
       - freebsd
@@ -17,6 +19,7 @@ builds:
       - 386
       - arm
       - mips
+      - mipsle
       - amd64
       - arm64
     goarm:

README.md

@@ -4,11 +4,19 @@
 [![Go Reference](https://pkg.go.dev/badge/github.com/Control-D-Inc/ctrld.svg)](https://pkg.go.dev/github.com/Control-D-Inc/ctrld)
 [![Go Report Card](https://goreportcard.com/badge/github.com/Control-D-Inc/ctrld)](https://goreportcard.com/report/github.com/Control-D-Inc/ctrld)
 
+![ctrld splash image](/docs/ctrldsplash.png)
+
 A highly configurable DNS forwarding proxy with support for:
 - Multiple listeners for incoming queries
 - Multiple upstreams with fallbacks
-- Multiple network policy driven DNS query steering
+- Multiple network policy driven DNS query steering (via network cidr, MAC address or FQDN)
 - Policy driven domain based "split horizon" DNS with wildcard support
+- Integrations with common router vendors and firmware
+- LAN client discovery via DHCP, mDNS, ARP, NDP, hosts file parsing
+- Prometheus metrics exporter 
+
+## TLDR
+Proxy legacy DNS traffic to secure DNS upstreams in highly configurable ways. 
 
 All DNS protocols are supported, including:
 - `UDP 53`
@@ -17,34 +25,83 @@ All DNS protocols are supported, including:
 - `DNS-over-HTTP/3` (DOH3)
 - `DNS-over-QUIC`
 
-## Use Cases
+# Use Cases
 1. Use secure DNS protocols on networks and devices that don't natively support them (legacy routers, legacy OSes, TVs, smart toasters).
 2. Create source IP based DNS routing policies with variable secure DNS upstreams. Subnet 1 (admin) uses upstream resolver A, while Subnet 2 (employee) uses upstream resolver B.
 3. Create destination IP based DNS routing policies with variable secure DNS upstreams. Listener 1 uses upstream resolver C, while Listener 2 uses upstream resolver D.
 4. Create domain level "split horizon" DNS routing policies to send internal domains (*.company.int) to a local DNS server, while everything else goes to another upstream.
+5. Deploy on a router and create LAN client specific DNS routing policies from a web GUI (When using ControlD.com).
 
 
 ## OS Support
 - Windows (386, amd64, arm)
-- Mac (amd64, arm64)
+- Windows Server (386, amd64)
+- MacOS (amd64, arm64)
 - Linux (386, amd64, arm, mips)
+- FreeBSD (386, amd64, arm)
+- Common routers (See below)
 
-## Download
-Download pre-compiled binaries from the [Releases](https://github.com/Control-D-Inc/ctrld/releases) section.
 
-## Build
-`ctrld` requires `go1.19+`:
+### Supported Routers
+You can run `ctrld` on any supported router. The list of supported routers and firmware includes:
+- Asus Merlin
+- DD-WRT
+- Firewalla
+- FreshTomato
+- GL.iNet
+- OpenWRT
+- pfSense / OPNsense
+- Synology 
+- Ubiquiti (UniFi, EdgeOS)
+
+`ctrld` will attempt to interface with dnsmasq (or Windows Server) whenever possible and set itself as the upstream, while running on port 5354. On FreeBSD based OSes, `ctrld` will terminate dnsmasq and unbound in order to be able to listen on port 53 directly.  
+
+# Install
+There are several ways to download and install `ctrld`.
+
+## Quick Install
+The simplest way to download and install `ctrld` is to use the following installer command on any UNIX-like platform:
 
 ```shell
-$ go build ./cmd/ctrld
+sh -c 'sh -c "$(curl -sL https://api.controld.com/dl)"'
+```
+
+Windows user and prefer Powershell (who doesn't)? No problem, execute this command instead in administrative PowerShell:
+```shell
+(Invoke-WebRequest -Uri 'https://api.controld.com/dl/ps1' -UseBasicParsing).Content | Set-Content "$env:TEMPctrld_install.ps1"; Invoke-Expression "& '$env:TEMPctrld_install.ps1'"
+```
+
+Or you can pull and run a Docker container from [Docker Hub](https://hub.docker.com/r/controldns/ctrld)
+```shell
+docker run -d --name=ctrld -p 127.0.0.1:53:53/tcp -p 127.0.0.1:53:53/udp controldns/ctrld:latest
+```
+
+## Download Manually
+Alternatively, if you know what you're doing you can download pre-compiled binaries from the [Releases](https://github.com/Control-D-Inc/ctrld/releases) section for the appropriate platform. 
+
+## Build
+Lastly, you can build `ctrld` from source which requires `go1.21+`:
+
+```shell
+go build ./cmd/ctrld
 ```
 
 or
 
 ```shell
-$ go install github.com/Control-D-Inc/ctrld/cmd/ctrld@latest
+go install github.com/Control-D-Inc/ctrld/cmd/ctrld@latest
 ```
 
+or 
+
+```shell
+docker build -t controldns/ctrld . -f docker/Dockerfile
+```
+
+
+# Usage
+The cli is self documenting, so feel free to run `--help` on any sub-command to get specific usages. 
+
 ## Arguments
 ```
         __         .__       .___
@@ -59,101 +116,120 @@ Usage:
 
 Available Commands:
   run         Run the DNS proxy server
+  start       Quick start service and configure DNS on interface
+  stop        Quick stop service and remove DNS from interface
+  restart     Restart the ctrld service
+  reload      Reload the ctrld service
+  status      Show status of the ctrld service
+  uninstall   Stop and uninstall the ctrld service
   service     Manage ctrld service
-  start       Quick start service and configure DNS on default interface
-  stop        Quick stop service and remove DNS from default interface
+  clients     Manage clients
+  upgrade     Upgrading ctrld to latest version
+  log         Manage runtime debug logs
 
 Flags:
   -h, --help            help for ctrld
+  -s, --silent          do not write any log output
   -v, --verbose count   verbose log output, "-v" basic logging, "-vv" debug level logging
       --version         version for ctrld
 
 Use "ctrld [command] --help" for more information about a command.
 ```
 
-## Usage
-To start the server with default configuration, simply run: `./ctrld run`. This will create a generic `ctrld.toml` file in the **working directory** and start the application in foreground. 
-1. Start the server
-  ```
-  $ sudo ./ctrld run
+## Basic Run Mode
+This is the most basic way to run `ctrld`, in foreground mode. Unless you already have a config file, a default one will be generated. 
+
+### Command
+
+Windows (Admin Shell)
+  ```shell
+  ctrld.exe run
   ```
 
-2. Run a test query using a DNS client, for example, `dig`:
+Linux or Macos
+  ```shell
+  sudo ctrld run
+  ```
+
+You can then run a test query using a DNS client, for example, `dig`:
   ```
   $ dig verify.controld.com @127.0.0.1 +short
   api.controld.com.
   147.185.34.1
   ```
 
-If `verify.controld.com` resolves, you're successfully using the default Control D upstream.
+If `verify.controld.com` resolves, you're successfully using the default Control D upstream. From here, you can start editing the config file that was generated. To enforce a new config, restart the server. 
 
-### Service Mode
-To run the application in service mode, simply run: `./ctrld start` as system/root user. This will create a generic `ctrld.toml` file in the **user home** directory, start the system service, and configure the listener on the default interface. Service will start on OS boot.
+## Service Mode
+This mode will run the application as a background system service on any Windows, MacOS, Linux, FreeBSD distribution or supported router. This will create a generic `ctrld.toml` file in the **C:\ControlD** directory (on Windows) or `/etc/controld/` (almost everywhere else), start the system service, and **configure the listener on all physical network interface**. Service will start on OS boot.
 
-In order to stop the service, and restore your DNS to original state, simply run `./ctrld stop`.
+When Control D upstreams are used on a router type device, `ctrld` will [relay your network topology](https://docs.controld.com/docs/device-clients) to Control D (LAN IPs, MAC addresses, and hostnames), and you will be able to see your LAN devices in the web panel, view analytics and apply unique profiles to them. 
 
-For granular control of the service, run the `service` command. Each sub-command has its own help section so you can see what arguments you can supply.
+### Command
 
-```
-  Manage ctrld service
+Windows (Admin Shell)
+  ```shell
+  ctrld.exe start
+  ```
 
-  Usage:
-    ctrld service [command]
+Linux or Macos
+  ```
+  sudo ctrld start
+  ```
 
-  Available Commands:
-    interfaces  Manage network interfaces
-    restart     Restart the ctrld service
-    start       Start the ctrld service
-    status      Show status of the ctrld service
-    stop        Stop the ctrld service
-    uninstall   Uninstall the ctrld service
+If `ctrld` is not in your system path (you installed it manually), you will need to run the above commands from the directory where you installed `ctrld`. 
 
-  Flags:
-    -h, --help   help for service
+In order to stop the service, and restore your DNS to original state, simply run `ctrld stop`. If you wish to stop and uninstall the service permanently, run `ctrld uninstall`. 
 
-  Global Flags:
-    -v, --verbose count   verbose log output, "-v" basic logging, "-vv" debug level logging
+## Unmanaged Service Mode
+This mode functions similarly to the "Service Mode" above except it will simply start a system service and the config defined listeners, but **will not make any changes to any network interfaces**. You can then set the `ctrld` listener(s) IP on the desired network interfaces manually. 
 
-  Use "ctrld service [command] --help" for more information about a command.
-```
+### Command
 
-### Control D Auto Configuration
-Application can be started with a specific resolver config, instead of the default one. Simply supply your resolver ID with a `--cd` flag, when using the `run` (foreground) or `start` (service) modes. 
+Windows (Admin Shell)
+  ```shell
+  ctrld.exe service start
+  ```
 
-The following command will start the application in foreground mode, using the free "p2" resolver, which blocks Ads & Trackers. 
+Linux or Macos
+  ```shell
+  sudo ctrld service start
+  ```
 
+# Configuration
+`ctrld` can be configured in variety of different ways, which include: API, local config file or via cli launch args. 
+
+## API Based Auto Configuration
+Application can be started with a specific Control D resolver config, instead of the default one. Simply supply your Resolver ID with a `--cd` flag, when using the `start` (service) mode. In this mode, the application will automatically choose a non-conflicting IP and/or port and configure itself as the upstream to whatever process is running on port 53 (like dnsmasq or Windows DNS Server). This mode is used when the 1 liner installer command from the Control D onboarding guide is executed. 
+
+The following command will use your own personal Control D Device resolver, and start the application in service mode. Your resolver ID is displayed on the "Show Resolvers" screen for the relevant Control D Endpoint. 
+
+Windows (Admin Shell)
 ```shell
-./ctrld run --cd p2
+ctrld.exe start --cd abcd1234
 ```
 
-Alternatively, you can use your own personal Control D Device resolver, and start the application in service mode. Your resolver ID is the part after the slash of your DNS-over-HTTPS resolver. ie. https://dns.controld.com/abcd1234
-
+Linux or Macos
 ```shell
-./ctrld start --cd abcd1234
+sudo ctrld start --cd abcd1234
 ```
 
 Once you run the above command, the following things will happen:
 - You resolver configuration will be fetched from the API, and config file templated with the resolver data
-- Application will start as a service, and keep running (even after reboot) until you run the `stop` or `service uninstall` sub-commands
-- Your default network interface will be updated to use the listener started by the service
-- All OS DNS queries will be sent to the listener
+- Application will start as a service, and keep running (even after reboot) until you run the `stop` or `uninstall` sub-commands
+- All physical network interface will be updated to use the listener started by the service or dnsmasq upstream will be switched to `ctrld`
+- All DNS queries will be sent to the listener
 
-## Configuration
-See [Configuration Docs](docs/config.md).
+## Manual Configuration 
+`ctrld` is entirely config driven and can be configured in many different ways, please see [Configuration Docs](docs/config.md).
 
-### Example 
-- Start `listener.0` on 127.0.0.1:53
-- Accept queries from any source address
-- Send all queries to `upstream.0` via DoH protocol
-
-### Default Config
+### Example
 ```toml
 [listener]
 
   [listener.0]
-    ip = "127.0.0.1"
+    ip = '0.0.0.0'
     port = 53
-    restricted = false
 
 [network]
 
@@ -161,10 +237,6 @@ See [Configuration Docs](docs/config.md).
     cidrs = ["0.0.0.0/0"]
     name = "Network 0"
 
-[service]
-  log_level = "info"
-  log_path = ""
-
 [upstream]
 
   [upstream.0]
@@ -173,27 +245,88 @@ See [Configuration Docs](docs/config.md).
     name = "Control D - Anti-Malware"
     timeout = 5000
     type = "doh"
-
-  [upstream.1]
-    bootstrap_ip = "76.76.2.11"
-    endpoint = "p2.freedns.controld.com"
-    name = "Control D - No Ads"
-    timeout = 3000
-    type = "doq"
-
 ```
 
-### Advanced
-The above is the most basic example, which will work out of the box. If you're looking to do advanced configurations using policies, see [Configuration Docs](docs/config.md) for complete documentation of the config file.
+The above basic config will:
+- Start listener on 0.0.0.0:53
+- Accept queries from any source address
+- Send all queries to `https://freedns.controld.com/p1` using DoH protocol
 
-You can also supply configuration via launch argeuments, in [Ephemeral Mode](docs/ephemeral_mode.md).
+## CLI Args
+If you're unable to use a config file, `ctrld` can be be supplied with basic configuration via launch arguments, in [Ephemeral Mode](docs/ephemeral_mode.md).
+
+### Example
+```
+ctrld run --listen=127.0.0.1:53 --primary_upstream=https://freedns.controld.com/p2 --secondary_upstream=10.0.10.1:53 --domains=*.company.int,very-secure.local --log /path/to/log.log
+```
+
+The above will start a foreground process and:
+- Listen on `127.0.0.1:53` for DNS queries
+- Forward all queries to `https://freedns.controld.com/p2` using DoH protocol, while...
+- Excluding `*.company.int` and `very-secure.local` matching queries, that are forwarded to `10.0.10.1:53`
+- Write a debug log to `/path/to/log.log`
+
+## DNS Intercept Mode
+When running `ctrld` alongside VPN software, DNS conflicts can cause intermittent failures, bypassed filtering, or configuration loops. DNS Intercept Mode prevents these issues by transparently capturing all DNS traffic on the system and routing it through `ctrld`, without modifying network adapter DNS settings.
+
+### When to Use
+Enable DNS Intercept Mode if you:
+- Use corporate VPN software (F5, Cisco AnyConnect, Palo Alto GlobalProtect, Zscaler)
+- Run overlay networks like Tailscale or WireGuard
+- Experience random DNS failures when VPN connects/disconnects
+- See gaps in your Control D analytics when VPN is active
+- Have endpoint security software that also manages DNS
+
+### Command
+
+Windows (Admin Shell)
+```shell
+ctrld.exe start --intercept-mode dns --cd RESOLVER_ID_HERE
+```
+
+macOS
+```shell
+sudo ctrld start --intercept-mode dns --cd RESOLVER_ID_HERE
+```
+
+`--intercept-mode dns` automatically detects VPN internal domains and routes them to the VPN's DNS server, while Control D handles everything else.
+
+To disable intercept mode on a service that already has it enabled:
+
+Windows (Admin Shell)
+```shell
+ctrld.exe start --intercept-mode off
+```
+
+macOS
+```shell
+sudo ctrld start --intercept-mode off
+```
+
+This removes the intercept rules and reverts to standard interface-based DNS configuration.
+
+### Platform Support
+| Platform | Supported | Mechanism |
+|----------|-----------|-----------|
+| Windows  | ✅        | NRPT (Name Resolution Policy Table) |
+| macOS    | ✅        | pf (packet filter) redirect |
+| Linux    | ❌        | Not currently supported |
+
+### Features
+- **VPN split routing** — VPN-specific domains are automatically detected and forwarded to the VPN's DNS server
+- **Captive portal recovery** — Wi-Fi login pages (hotels, airports, coffee shops) work automatically
+- **No network adapter changes** — DNS settings stay untouched, eliminating conflicts entirely
+- **Automatic port 53 conflict resolution** — if another process (e.g., `mDNSResponder` on macOS) is already using port 53, `ctrld` automatically listens on a different port. OS-level packet interception redirects all DNS traffic to `ctrld` transparently, so no manual configuration is needed. This only applies to intercept mode.
+
+### Tested VPN Software
+- F5 BIG-IP APM
+- Cisco AnyConnect
+- Palo Alto GlobalProtect
+- Tailscale (including Exit Nodes)
+- Windscribe
+- WireGuard
+
+For more details, see the [DNS Intercept Mode documentation](https://docs.controld.com/docs/dns-intercept).
 
 ## Contributing
-
 See [Contribution Guideline](./docs/contributing.md)
-
-## Roadmap
-The following functionality is on the roadmap and will be available in future releases. 
-- Router self-installation
-- Client hostname/MAC passthrough
-- Prometheus metrics exporter 

SPEC.md

@@ -0,0 +1,206 @@
+# SPEC: Stable customer-visible provisioning failure codes
+
+Issue: [#586](https://gitlab.int.windscribe.com/controld/clients/ctrld/-/issues/586)
+Requested by: Catt Garrod (@catt). Scope expanded by: Anthony Wong (@anthony).
+
+## 1. Objective
+
+Terminal provisioning failures in ctrld — bootstrap/API setup, listener
+binding, and service installation/startup — must produce a stable,
+support-facing failure identifier that survives process exit and reaches
+both manual CLI users and MDM-driven installs. A customer or admin reports
+one code; Support maps it to a scenario and a next action without asking
+for reruns or verbose logs.
+
+Motivating incident (v1.5.5, macOS): provisioning reached the Control D
+API, then died with only `FTL listener.0 could not find available listen
+ip and port`. The per-address UDP/TCP bind errors existed only at Info
+level in an in-memory logger and vanished on exit. The macOS pkg
+`postinstall` discards ctrld's stdout/stderr entirely and judges success
+by plist existence, so nothing useful reached the MDM log.
+
+**Users:** end customers and IT admins reporting failures; Support agents
+triaging them; MDM/RMM operators reading installer logs.
+
+### Failure contract (agreed design)
+
+Three surfaces, all carrying the same identifier:
+
+1. **Result file** — on terminal provisioning failure, ctrld writes a
+   small redacted JSON file (atomic write: temp + rename) in the ctrld
+   home directory (same base dir as the internal `ctrld.log`,
+   via `absHomeDir`). Removed/overwritten on later successful
+   provisioning so stale failures don't mislead. Schema:
+
+   ```json
+   {
+     "version": 1,
+     "timestamp": "2026-08-18T12:00:00Z",
+     "stage": "listener",
+     "code": "LISTENER_BIND_FAILED",
+     "exit_code": 41,
+     "message": "could not find available listen ip and port",
+     "detail": {
+       "attempts": [
+         {"addr": "127.0.0.1:53", "proto": "udp", "os_error": "address already in use"}
+       ]
+     }
+   }
+   ```
+
+   `detail` is bounded (cap recorded bind attempts; cap string lengths)
+   and redacted by construction: no provisioning tokens, resolver IDs,
+   config contents, or unrelated host data.
+
+2. **Exit code + final stderr line** — the installer-facing command
+   (`ctrld start`, and `ctrld run` when run manually in the foreground)
+   exits with a stage-scoped code and prints one final line containing
+   the string code and stage, e.g.
+   `provisioning failed: stage=listener code=LISTENER_BIND_FAILED (exit 41)`.
+
+3. **Installer log (MDM path)** — `scripts/pkg/postinstall` stops
+   discarding the signal: it captures `ctrld start`'s output to a
+   private temp file, extracts only the fixed-charset identifier line
+   (`stage=[a-z]* code=[A-Z_]* (exit [0-9]*)` — structurally unable to
+   carry the token), and echoes it with the exit code into the
+   installer log. The result file's `message`/`detail` fields are
+   deliberately never surfaced there. The plist-existence check remains
+   the final success gate.
+
+### Identifier format
+
+- **Primary identifier: stable string codes.** Initial set —
+  bootstrap: `API_UNREACHABLE`, `API_REJECTED`, `API_DEVICE_INVALID`;
+  listener: `LISTENER_BIND_FAILED`, `LISTENER_CONFIGURED_ADDR_UNAVAILABLE`;
+  service: `SERVICE_INSTALL_FAILED`, `SERVICE_START_FAILED`,
+  `SERVICE_SELFCHECK_FAILED`. Codes are append-only; renames are new
+  codes plus a deprecation note in the mapping doc.
+- **Secondary: stage-scoped process exit codes** as a coarse machine
+  signal: bootstrap 30–39, listener 40–49, service install/start 50–59.
+  Each string code owns one exit code. Existing contracts are untouched:
+  `ctrld status` 0–3, deactivation-pin 126, success 0.
+- One underlying failure maps to one code on every path (manual CLI and
+  MDM), on both branches.
+
+### Propagation (daemon → installer)
+
+The listener/bootstrap fatals fire inside the daemon process
+(`ctrld run` under launchd/systemd/SCM), not in `ctrld start`. The
+daemon writes the result file before exiting; the existing log-socket
+exit notification (`notifyExitToLogServer`) already unblocks `ctrld
+start`'s self-check. `ctrld start` then reads the result file, prints
+the identifier, and exits with the mapped stage exit code. The daemon's
+own exit-status semantics toward service managers are preserved —
+in particular the deliberate exit-0 on permanent API rejection that
+protects the restart-policy budget; the result file carries the failure
+identity in that case.
+
+### Support mapping
+
+`docs/provisioning-failure-codes.md` in this repo: one row per code —
+code, stage, exit code, failure scenario, next safe troubleshooting
+action or evidence request. Updated in the same MR whenever a code is
+added or changed.
+
+### Branch scope
+
+Full implementation on **both** `v1.0` (release line for v1.5.5) and
+`master`. The branches diverge heavily (`v1.0`: zerolog fork,
+`commands.go`, `service_status.go`, macOS pkg scripts; `master`: zap,
+inline commands, no pkg scripts), so this is one shared contract
+(codes, exit-code ranges, file schema, doc) implemented twice, as two
+MRs referencing #586.
+
+## 2. Commands
+
+- Build: `go build ./...`
+- Test: `go test ./cmd/cli/...` (full: `go test ./...`)
+- Vet: `go vet ./...`
+- Branch workflow: feature branch off `v1.0` for the v1.0 MR; separate
+  feature branch off `master` for the port MR. Rebase, never merge the
+  base branch in.
+
+## 3. Project structure
+
+New and touched files on `v1.0` (master port mirrors the same contract
+at its equivalent emission points in its `cli.go`):
+
+- `cmd/cli/provision_result.go` (new) — stage + code enums, exit-code
+  mapping, result-file schema, atomic write/read/clear helpers,
+  bounded/redacted detail builders. Pattern follows `service_status.go`
+  (small file: named constants + classifier + dedicated tests).
+- `cmd/cli/provision_result_test.go` (new).
+- `cmd/cli/cli.go` — emission points: `run()` bootstrap failure branches
+  (permanent rejection, invalid-device, fatal fetch), and
+  `tryUpdateListenerConfig` / `tryUpdateListenerConfigIntercept` fatals,
+  which now record per-attempt `{addr, proto, os_error}` bind detail.
+- `cmd/cli/commands.go` — `initStartCmd`: doTasks install/start failures
+  and the self-check failure branch read the result file, print the
+  identifier, and exit with the stage code (replacing bare `os.Exit(1)`
+  on those paths).
+- `scripts/pkg/postinstall` — propagate exit code + result-file contents
+  into the installer log (v1.0 only; master has no pkg scripts).
+- `docs/provisioning-failure-codes.md` (new) — support mapping.
+
+## 4. Code style
+
+- Per repo conventions and global rules: guard clauses, small functions,
+  descriptive names, explicit error handling — never weaken existing
+  handling (e.g. keep the permanent-rejection exit-0 rationale intact).
+- Comments only for non-obvious constraints (e.g. why the daemon must
+  still exit 0 on permanent rejection), simple-english, self-contained —
+  no issue/MR references in code.
+- Match each branch's logging idiom: zerolog fork on `v1.0`, zap on
+  `master`. No new dependencies.
+- Conventional Commits; MR titles in simple-english; both MRs reference
+  #586 (release-line MR carries `Closes #586`).
+
+## 5. Testing strategy
+
+Test-first where the harness allows. Coverage required by the issue:
+
+- **Code/mapping unit tests** — every string code maps to exactly one
+  stage and one in-range exit code; ranges don't collide with existing
+  contracts (0–3 status, 126 pin).
+- **Result file round-trip** — write/read/clear; atomic write; stale
+  file removed on success.
+- **Redaction** — serialize a result built from inputs containing a
+  provision token, resolver ID, and config content; assert none appear.
+- **Listener bind failure (regression test for the incident)** — occupy
+  a port, drive the listener-config path to exhaustion, assert the
+  result records `LISTENER_BIND_FAILED` with attempted address, UDP/TCP
+  operation, and OS error (`address already in use`-class).
+- **Bootstrap failures** — mock API: permanent 4xx → `API_REJECTED`;
+  invalid-device 40402 → `API_DEVICE_INVALID`; unreachable →
+  `API_UNREACHABLE`.
+- **Service install/start/self-check failures** — injected task
+  failures assert code selection and `ctrld start` exit code.
+- **MDM surface** — shell-level check of `postinstall` failure branch
+  (result file present → correct log line and exit), aligned with the
+  existing `test-scripts/` approach; manual pkg verification steps
+  documented in the MR.
+- Both branches: the shared contract tests exist on both; branch-specific
+  emission tests match each branch's structure.
+
+## 6. Boundaries
+
+**Always:**
+- Redact tokens, resolver IDs, config contents, host data from every
+  customer-visible surface (result file, stderr line, installer log).
+- Preserve existing exit-code contracts (`ctrld status` 0–3, pin 126)
+  and the daemon's service-manager-facing exit semantics.
+- Bound all recorded detail (attempt counts, string lengths).
+- Keep codes append-only once merged.
+
+**Ask first:**
+- Changing the daemon's (`ctrld run` under a service manager) exit codes
+  or restart-relevant behavior beyond writing the result file.
+- Adding any persisted file outside the ctrld home directory.
+- Expanding scope to runtime (post-provisioning) failures — this ticket
+  owns terminal provisioning failures only.
+
+**Never:**
+- Print or persist the provisioning token (the reason postinstall
+  discards output today — the replacement surface must stay token-free).
+- Auto-detect or kill conflicting processes (explicitly out of scope).
+- Break `ctrld status`'s documented exit-code contract.

client_info.go

@@ -0,0 +1,22 @@
+package ctrld
+
+// ClientInfoCtxKey is the context key to store client info.
+type ClientInfoCtxKey struct{}
+
+// ClientInfo represents ctrld's clients information.
+type ClientInfo struct {
+	Mac          string
+	IP           string
+	Hostname     string
+	Self         bool
+	ClientIDPref string
+}
+
+// LeaseFileFormat specifies the format of DHCP lease file.
+type LeaseFileFormat string
+
+const (
+	Dnsmasq  LeaseFileFormat = "dnsmasq"
+	IscDhcpd LeaseFileFormat = "isc-dhcpd"
+	KeaDHCP4 LeaseFileFormat = "kea-dhcp4"
+)

client_info_darwin.go

@@ -0,0 +1,4 @@
+package ctrld
+
+// SelfDiscover reports whether ctrld should only do self discover.
+func SelfDiscover() bool { return true }

client_info_others.go

@@ -0,0 +1,6 @@
+//go:build !windows && !darwin
+
+package ctrld
+
+// SelfDiscover reports whether ctrld should only do self discover.
+func SelfDiscover() bool { return false }

client_info_windows.go

@@ -0,0 +1,18 @@
+package ctrld
+
+import (
+	"golang.org/x/sys/windows"
+)
+
+// isWindowsWorkStation reports whether ctrld was run on a Windows workstation machine.
+func isWindowsWorkStation() bool {
+	// From https://learn.microsoft.com/en-us/windows/win32/api/winnt/ns-winnt-osversioninfoexa
+	const VER_NT_WORKSTATION = 0x0000001
+	osvi := windows.RtlGetVersion()
+	return osvi.ProductType == VER_NT_WORKSTATION
+}
+
+// SelfDiscover reports whether ctrld should only do self discover.
+func SelfDiscover() bool {
+	return isWindowsWorkStation()
+}

cmd/cli/ad_others.go

@@ -0,0 +1,15 @@
+//go:build !windows
+
+package cli
+
+import (
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// addExtraSplitDnsRule adds split DNS rule if present.
+func addExtraSplitDnsRule(_ *ctrld.Config) bool { return false }
+
+// getActiveDirectoryDomain returns AD domain name of this computer.
+func getActiveDirectoryDomain() (string, error) {
+	return "", nil
+}

cmd/cli/ad_windows.go

@@ -0,0 +1,74 @@
+package cli
+
+import (
+	"io"
+	"log"
+	"os"
+	"strings"
+
+	"github.com/microsoft/wmi/pkg/base/host"
+	hh "github.com/microsoft/wmi/pkg/hardware/host"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/system"
+)
+
+// addExtraSplitDnsRule adds split DNS rule for domain if it's part of active directory.
+func addExtraSplitDnsRule(cfg *ctrld.Config) bool {
+	domain, err := system.GetActiveDirectoryDomain()
+	if err != nil {
+		mainLog.Load().Debug().Msgf("unable to get active directory domain: %v", err)
+		return false
+	}
+	if domain == "" {
+		mainLog.Load().Debug().Msg("no active directory domain found")
+		return false
+	}
+	// Network rules are lowercase during toml config marshaling,
+	// lowercase the domain here too for consistency.
+	domain = strings.ToLower(domain)
+	domainRuleAdded := addSplitDnsRule(cfg, domain)
+	wildcardDomainRuleRuleAdded := addSplitDnsRule(cfg, "*."+strings.TrimPrefix(domain, "."))
+	return domainRuleAdded || wildcardDomainRuleRuleAdded
+}
+
+// addSplitDnsRule adds split-rule for given domain if there's no existed rule.
+// The return value indicates whether the split-rule was added or not.
+func addSplitDnsRule(cfg *ctrld.Config, domain string) bool {
+	for n, lc := range cfg.Listener {
+		if lc.Policy == nil {
+			lc.Policy = &ctrld.ListenerPolicyConfig{}
+		}
+		for _, rule := range lc.Policy.Rules {
+			if _, ok := rule[domain]; ok {
+				mainLog.Load().Debug().Msgf("split-rule %q already existed for listener.%s", domain, n)
+				return false
+			}
+		}
+		mainLog.Load().Debug().Msgf("adding split-rule %q for listener.%s", domain, n)
+		lc.Policy.Rules = append(lc.Policy.Rules, ctrld.Rule{domain: []string{}})
+	}
+	return true
+}
+
+// getActiveDirectoryDomain returns AD domain name of this computer.
+func getActiveDirectoryDomain() (string, error) {
+	log.SetOutput(io.Discard)
+	defer log.SetOutput(os.Stderr)
+	whost := host.NewWmiLocalHost()
+	cs, err := hh.GetComputerSystem(whost)
+	if cs != nil {
+		defer cs.Close()
+	}
+	if err != nil {
+		return "", err
+	}
+	pod, err := cs.GetPropertyPartOfDomain()
+	if err != nil {
+		return "", err
+	}
+	if pod {
+		return cs.GetPropertyDomain()
+	}
+	return "", nil
+}

cmd/cli/ad_windows_test.go

@@ -0,0 +1,73 @@
+package cli
+
+import (
+	"fmt"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/system"
+	"github.com/Control-D-Inc/ctrld/testhelper"
+)
+
+func Test_getActiveDirectoryDomain(t *testing.T) {
+	start := time.Now()
+	domain, err := system.GetActiveDirectoryDomain()
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Logf("Using Windows API takes: %d", time.Since(start).Milliseconds())
+
+	start = time.Now()
+	domainPowershell, err := getActiveDirectoryDomainPowershell()
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Logf("Using Powershell takes: %d", time.Since(start).Milliseconds())
+
+	if domain != domainPowershell {
+		t.Fatalf("result mismatch, want: %v, got: %v", domainPowershell, domain)
+	}
+}
+
+func getActiveDirectoryDomainPowershell() (string, error) {
+	cmd := "$obj = Get-WmiObject Win32_ComputerSystem; if ($obj.PartOfDomain) { $obj.Domain }"
+	output, err := powershell(cmd)
+	if err != nil {
+		return "", fmt.Errorf("failed to get domain name: %w, output:\n\n%s", err, string(output))
+	}
+	return string(output), nil
+}
+
+func Test_addSplitDnsRule(t *testing.T) {
+	newCfg := func(domains ...string) *ctrld.Config {
+		cfg := testhelper.SampleConfig(t)
+		lc := cfg.Listener["0"]
+		for _, domain := range domains {
+			lc.Policy.Rules = append(lc.Policy.Rules, ctrld.Rule{domain: []string{}})
+		}
+		return cfg
+	}
+	tests := []struct {
+		name   string
+		cfg    *ctrld.Config
+		domain string
+		added  bool
+	}{
+		{"added", newCfg(), "example.com", true},
+		{"TLD existed", newCfg("example.com"), "*.example.com", true},
+		{"wildcard existed", newCfg("*.example.com"), "example.com", true},
+		{"not added TLD", newCfg("example.com", "*.example.com"), "example.com", false},
+		{"not added wildcard", newCfg("example.com", "*.example.com"), "*.example.com", false},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			added := addSplitDnsRule(tc.cfg, tc.domain)
+			assert.Equal(t, tc.added, added)
+		})
+	}
+}

cmd/cli/cgo.go

@@ -0,0 +1,5 @@
+//go:build cgo
+
+package cli
+
+const cgoEnabled = true

cmd/cli/cli_intercept_listener_test.go

@@ -0,0 +1,116 @@
+package cli
+
+import (
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestIsExplicitInterceptListener(t *testing.T) {
+	tests := []struct {
+		name string
+		ip   string
+		port int
+		want bool
+	}{
+		{name: "empty", ip: "", port: 0, want: false},
+		{name: "wildcard", ip: "0.0.0.0", port: 53, want: false},
+		{name: "zero port", ip: "127.0.0.1", port: 0, want: false},
+		{name: "default intercept listener", ip: "127.0.0.1", port: 53, want: false},
+		{name: "fallback port explicit", ip: "127.0.0.1", port: 5354, want: true},
+		{name: "custom loopback explicit", ip: "127.0.0.2", port: 53, want: true},
+		{name: "custom address explicit", ip: "192.0.2.10", port: 53, want: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isExplicitInterceptListener(tt.ip, tt.port); got != tt.want {
+				t.Fatalf("isExplicitInterceptListener(%q, %d) = %v, want %v", tt.ip, tt.port, got, tt.want)
+			}
+		})
+	}
+}
+
+// TestPreserveBoundListeners is a regression test for #551: on reload, the on-disk
+// generated config still declares 127.0.0.1:53, but the running listener has fallen back
+// to 127.0.0.1:5354. preserveBoundListeners must keep the in-memory config on the actual
+// bound port so pf rdr rules and probes do not target the dead default port.
+func TestPreserveBoundListeners(t *testing.T) {
+	// cur = actual running listener (fell back to 5354); newCfg = freshly read from disk (53).
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("listener port after reload = %d, want 5354 (actual bound port)", got)
+	}
+	if got := newListeners["0"].IP; got != "127.0.0.1" {
+		t.Errorf("listener IP after reload = %q, want 127.0.0.1", got)
+	}
+}
+
+// TestPreserveBoundListeners_NoChange verifies that when the on-disk config matches the
+// running listener, the config is left untouched (a legitimate reload with the same port).
+func TestPreserveBoundListeners_NoChange(t *testing.T) {
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("listener port = %d, want 5354", got)
+	}
+}
+
+// TestPreserveBoundListeners_MissingCurrent verifies that a listener present on disk but not
+// in the current running set (e.g. newly added) is left as configured.
+func TestPreserveBoundListeners_MissingCurrent(t *testing.T) {
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{
+		"0": {IP: "127.0.0.1", Port: 53},
+		"1": {IP: "127.0.0.1", Port: 5355},
+	}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("listener 0 port = %d, want 5354 (preserved)", got)
+	}
+	if got := newListeners["1"].Port; got != 5355 {
+		t.Errorf("listener 1 port = %d, want 5355 (unchanged, no current binding)", got)
+	}
+}
+
+// TestPreserveBoundListeners_ExplicitChangeNotMasked verifies that an explicit, non-default
+// listener in the reloaded config is applied rather than reverted to the old bound listener.
+// Reverting an explicit change would make the control-server reload comparison return 200
+// instead of 201, silently dropping the new listener. Regression guard for #551 review.
+func TestPreserveBoundListeners_ExplicitChangeNotMasked(t *testing.T) {
+	// Running listener fell back to 5354; user reloads with an explicit new listener.
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.2", Port: 5399}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].IP; got != "127.0.0.2" {
+		t.Errorf("explicit listener IP = %q, want 127.0.0.2 (not reverted)", got)
+	}
+	if got := newListeners["0"].Port; got != 5399 {
+		t.Errorf("explicit listener port = %d, want 5399 (not reverted)", got)
+	}
+}
+
+// TestPreserveBoundListeners_ExplicitDefaultPreserved verifies that the default
+// 127.0.0.1:53 listener remains fallback-eligible: when it diverges from the running
+// fallback port it is still preserved (isExplicitInterceptListener treats :53 as non-explicit).
+func TestPreserveBoundListeners_ExplicitDefaultPreserved(t *testing.T) {
+	cur := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 5354}}
+	newListeners := map[string]*ctrld.ListenerConfig{"0": {IP: "127.0.0.1", Port: 53}}
+
+	preserveBoundListeners(newListeners, cur)
+
+	if got := newListeners["0"].Port; got != 5354 {
+		t.Errorf("default listener port = %d, want 5354 (preserved fallback)", got)
+	}
+}

cmd/cli/cli_preflight_test.go

@@ -0,0 +1,403 @@
+package cli
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+	"net/http"
+	"net/url"
+	"sync/atomic"
+	"syscall"
+	"testing"
+	"time"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/controld"
+)
+
+func TestContextFromStopCh(t *testing.T) {
+	t.Run("cancels when stopCh closes", func(t *testing.T) {
+		stopCh := make(chan struct{})
+		ctx, cancel := contextFromStopCh(stopCh)
+		defer cancel()
+
+		if ctx.Err() != nil {
+			t.Fatalf("context cancelled before the stop request: %v", ctx.Err())
+		}
+		close(stopCh)
+		select {
+		case <-ctx.Done():
+		case <-time.After(5 * time.Second):
+			t.Fatal("context was not cancelled after stopCh closed")
+		}
+		if !errors.Is(ctx.Err(), context.Canceled) {
+			t.Errorf("ctx.Err() = %v, want %v", ctx.Err(), context.Canceled)
+		}
+	})
+
+	t.Run("cancel releases the watcher", func(t *testing.T) {
+		// stopCh is never closed: cancel() must still end the goroutine watching it.
+		ctx, cancel := contextFromStopCh(make(chan struct{}))
+		cancel()
+		select {
+		case <-ctx.Done():
+		case <-time.After(5 * time.Second):
+			t.Fatal("context was not cancelled by cancel()")
+		}
+	})
+
+	t.Run("nil stopCh is usable", func(t *testing.T) {
+		// Mobile callers have no stop channel; preflight must still run.
+		ctx, cancel := contextFromStopCh(nil)
+		defer cancel()
+		if ctx.Err() != nil {
+			t.Fatalf("context cancelled immediately: %v", ctx.Err())
+		}
+	})
+}
+
+// retryableNetworkErr is the shape processCDFlags treats as "retry with bootstrap
+// DNS": a url.Error wrapping a network failure.
+func retryableNetworkErr() error {
+	return &url.Error{
+		Op:  "Post",
+		URL: "https://api.controld.com/utility",
+		Err: &net.OpError{Op: "dial", Net: "tcp", Err: syscall.ECONNREFUSED},
+	}
+}
+
+func TestProcessCDFlagsStopsWhenCancelled(t *testing.T) {
+	oldFetch := fetchResolverConfig
+	oldUID := cdUID
+	t.Cleanup(func() {
+		fetchResolverConfig = oldFetch
+		cdUID = oldUID
+	})
+	cdUID = "testuid"
+
+	var calls atomic.Int64
+	fetchResolverConfig = func(ctx context.Context, req *controld.ResolverConfigRequest, dev bool) (*controld.ResolverConfig, error) {
+		calls.Add(1)
+		return nil, retryableNetworkErr()
+	}
+
+	// A stop request arriving while the API is unreachable. Before this was
+	// cancellable, the retry loop kept running after the service reported itself
+	// stopped, which is what kept the incident's process alive and enforcing.
+	stopCh := make(chan struct{})
+	ctx, cancel := contextFromStopCh(stopCh)
+	defer cancel()
+
+	done := make(chan error, 1)
+	go func() {
+		cfg := ctrld.Config{}
+		_, err := processCDFlags(ctx, &cfg)
+		done <- err
+	}()
+
+	// Let it fail at least once and settle into backoff before stopping.
+	deadline := time.After(10 * time.Second)
+	for calls.Load() == 0 {
+		select {
+		case <-deadline:
+			t.Fatal("resolver config was never fetched")
+		case err := <-done:
+			t.Fatalf("processCDFlags returned before any fetch: %v", err)
+		default:
+			time.Sleep(5 * time.Millisecond)
+		}
+	}
+	close(stopCh)
+
+	select {
+	case err := <-done:
+		if !errors.Is(err, context.Canceled) {
+			t.Errorf("processCDFlags err = %v, want it to report %v", err, context.Canceled)
+		}
+	case <-time.After(30 * time.Second):
+		t.Fatal("processCDFlags did not return after the stop request")
+	}
+}
+
+func TestProcessCDFlagsReturnsImmediatelyWhenAlreadyCancelled(t *testing.T) {
+	oldFetch := fetchResolverConfig
+	oldUID := cdUID
+	t.Cleanup(func() {
+		fetchResolverConfig = oldFetch
+		cdUID = oldUID
+	})
+	cdUID = "testuid"
+
+	var calls atomic.Int64
+	fetchResolverConfig = func(ctx context.Context, req *controld.ResolverConfigRequest, dev bool) (*controld.ResolverConfig, error) {
+		calls.Add(1)
+		return nil, retryableNetworkErr()
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	cfg := ctrld.Config{}
+	_, err := processCDFlags(ctx, &cfg)
+	if !errors.Is(err, context.Canceled) {
+		t.Errorf("processCDFlags err = %v, want %v", err, context.Canceled)
+	}
+	// One attempt is made before the loop notices; it must not retry past that.
+	if got := calls.Load(); got > 1 {
+		t.Errorf("fetched %d times with a cancelled context, want at most 1", got)
+	}
+}
+
+// TestRunAPIPreflightClassification is the regression guard for classifying a preflight
+// failure as an operator stop.
+//
+// runAPIPreflight cancels the context it derived from stopCh. Sampling the stop state
+// from that context afterwards reports "stopped" unconditionally, because
+// context.CancelFunc sets ctx.Err() whether or not anyone asked to stop. run() then
+// takes the stop branch for every failure, which skips self-uninstalling a deleted
+// device, skips the mobile exit callback, and tells the service manager a failed start
+// was a clean exit.
+func TestRunAPIPreflightClassification(t *testing.T) {
+	oldFetch := fetchResolverConfig
+	oldUID := cdUID
+	t.Cleanup(func() {
+		fetchResolverConfig = oldFetch
+		cdUID = oldUID
+	})
+	cdUID = "testuid"
+
+	// A deleted ControlD device: non-retryable, so preflight returns promptly.
+	deletedDevice := func() error {
+		e := &controld.ErrorResponse{}
+		e.ErrorField.Code = controld.InvalidConfigCode
+		e.ErrorField.Message = "device does not exist"
+		return e
+	}
+
+	openCh := make(chan struct{})
+	closedCh := make(chan struct{})
+	close(closedCh)
+
+	tests := []struct {
+		name     string
+		stopCh   <-chan struct{}
+		fetchErr func() error
+		wantStop bool
+	}{
+		{
+			// The P1: no stop was requested, so this must reach the failure branch.
+			name:     "api error with no stop request",
+			stopCh:   openCh,
+			fetchErr: deletedDevice,
+		},
+		{
+			// Mobile passes no stop channel at all, so it could never have stopped.
+			name:     "api error with a nil stop channel",
+			stopCh:   nil,
+			fetchErr: deletedDevice,
+		},
+		{
+			name:     "stop requested during preflight",
+			stopCh:   closedCh,
+			fetchErr: func() error { return retryableNetworkErr() },
+			wantStop: true,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			fetchResolverConfig = func(context.Context, *controld.ResolverConfigRequest, bool) (*controld.ResolverConfig, error) {
+				return nil, tc.fetchErr()
+			}
+			cfg := ctrld.Config{}
+			pf := runAPIPreflight(tc.stopCh, &cfg)
+
+			if pf.err == nil {
+				t.Fatal("expected preflight to fail")
+			}
+			if pf.stopRequested != tc.wantStop {
+				t.Errorf("stopRequested = %v, want %v", pf.stopRequested, tc.wantStop)
+			}
+		})
+	}
+}
+
+// TestRunAPIPreflightPreservesAPIError verifies the error reaches the caller in a form
+// the failure branch can still act on: self-uninstall keys off an *ErrorResponse with
+// InvalidConfigCode, and it only runs if that error is both classified as a failure and
+// still unwrappable.
+func TestRunAPIPreflightPreservesAPIError(t *testing.T) {
+	oldFetch := fetchResolverConfig
+	oldUID := cdUID
+	t.Cleanup(func() {
+		fetchResolverConfig = oldFetch
+		cdUID = oldUID
+	})
+	cdUID = "testuid"
+
+	want := &controld.ErrorResponse{}
+	want.ErrorField.Code = controld.InvalidConfigCode
+	fetchResolverConfig = func(context.Context, *controld.ResolverConfigRequest, bool) (*controld.ResolverConfig, error) {
+		return nil, want
+	}
+
+	cfg := ctrld.Config{}
+	pf := runAPIPreflight(make(chan struct{}), &cfg)
+
+	if pf.stopRequested {
+		t.Error("a device-deleted failure must not be reported as an operator stop")
+	}
+	var got *controld.ErrorResponse
+	if !errors.As(pf.err, &got) {
+		t.Fatalf("error no longer unwraps to *controld.ErrorResponse: %v", pf.err)
+	}
+	if got.ErrorField.Code != controld.InvalidConfigCode {
+		t.Errorf("code = %d, want %d (self-uninstall would not trigger)", got.ErrorField.Code, controld.InvalidConfigCode)
+	}
+}
+
+// TestPermanentAPIRejectionNarrowsToClientErrors is the regression guard for the clean
+// exit added above.
+//
+// controld builds an *ErrorResponse for any non-200 whose body decodes, so the Go type
+// says nothing about whether the API's answer will change on a retry. Keying the clean
+// exit off the type alone meant a 502 from a load balancer, or an API having a bad ten
+// minutes, stopped ctrld on every affected host with no service-manager retry behind it -
+// worse than the abnormal exit it replaced, because a Fatal at least gets restarted.
+//
+// Only a client-error status may take that path.
+func TestPermanentAPIRejectionNarrowsToClientErrors(t *testing.T) {
+	rejection := func(status, code int) error {
+		e := &controld.ErrorResponse{StatusCode: status}
+		e.ErrorField.Code = code
+		e.ErrorField.Message = "api said no"
+		return e
+	}
+
+	tests := []struct {
+		name          string
+		err           error
+		wantPermanent bool
+	}{
+		{
+			// The case the clean exit exists for: the device is gone, and every restart
+			// will be told the same thing.
+			name:          "deleted device",
+			err:           rejection(http.StatusNotFound, controld.InvalidConfigCode),
+			wantPermanent: true,
+		},
+		{"revoked credentials", rejection(http.StatusUnauthorized, 0), true},
+		{"forbidden", rejection(http.StatusForbidden, 0), true},
+		{"malformed request", rejection(http.StatusBadRequest, 0), true},
+
+		// Server-side trouble. These must keep the abnormal exit so the service
+		// manager's recovery policy retries.
+		{"bad gateway", rejection(http.StatusBadGateway, 0), false},
+		{"internal error", rejection(http.StatusInternalServerError, 0), false},
+		{"service unavailable", rejection(http.StatusServiceUnavailable, 0), false},
+
+		// 4xx, but both are the API asking for a later attempt rather than refusing
+		// this configuration.
+		{"request timeout", rejection(http.StatusRequestTimeout, 0), false},
+		{"rate limited", rejection(http.StatusTooManyRequests, 0), false},
+
+		// An *ErrorResponse built without a recorded status carries no verdict. A
+		// hand-constructed one, or a decode path that forgets to record the status,
+		// must not silently gain the clean exit.
+		{"no recorded status", rejection(0, controld.InvalidConfigCode), false},
+
+		// Not an API answer at all: the incident's denied socket reaches Fatal.
+		{"network failure", retryableNetworkErr(), false},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			got, ok := permanentAPIRejection(tc.err)
+			if ok != tc.wantPermanent {
+				t.Errorf("permanentAPIRejection() = %v, want %v", ok, tc.wantPermanent)
+			}
+			if ok && got == nil {
+				t.Error("a permanent rejection must return the rejection for reporting")
+			}
+		})
+	}
+
+	// The wrapped form matters too: preflight composes the fetch error, and errors.As has
+	// to reach through that for either branch to be chosen correctly.
+	wrapped := fmt.Errorf("processCDFlags: %w", rejection(http.StatusNotFound, controld.InvalidConfigCode))
+	if _, ok := permanentAPIRejection(wrapped); !ok {
+		t.Error("a wrapped API rejection must still be recognised")
+	}
+	wrappedTransient := fmt.Errorf("processCDFlags: %w", rejection(http.StatusBadGateway, 0))
+	if _, ok := permanentAPIRejection(wrappedTransient); ok {
+		t.Error("a wrapped 502 must not be treated as a permanent rejection")
+	}
+}
+
+func TestStopRequested(t *testing.T) {
+	closedCh := make(chan struct{})
+	close(closedCh)
+
+	if stopRequested(nil) {
+		t.Error("a nil stop channel must read as no stop (mobile passes none)")
+	}
+	if stopRequested(make(chan struct{})) {
+		t.Error("an open stop channel must read as no stop")
+	}
+	if !stopRequested(closedCh) {
+		t.Error("a closed stop channel must read as a stop")
+	}
+}
+
+// TestReloadFetchIsBoundedByServiceLifetime covers the reload path's stop wiring.
+//
+// Reload fetches the ControlD config too, and it used to build the bounded context
+// itself. Nothing tested that: the wrong channel, or a dropped cancel, would have left a
+// reload retrying against an unreachable API after "service stopped" was logged, and no
+// test would have failed. Both paths now go through one bounded fetch, so this pins it.
+func TestReloadFetchIsBoundedByServiceLifetime(t *testing.T) {
+	original := processCDFlagsFn
+	t.Cleanup(func() { processCDFlagsFn = original })
+
+	t.Run("a stop request cancels the reload fetch", func(t *testing.T) {
+		stopCh := make(chan struct{})
+		close(stopCh)
+
+		var sawCancelled bool
+		processCDFlagsFn = func(ctx context.Context, _ *ctrld.Config) (*controld.ResolverConfig, error) {
+			select {
+			case <-ctx.Done():
+				sawCancelled = true
+			case <-time.After(2 * time.Second):
+			}
+			return nil, ctx.Err()
+		}
+
+		p := &prog{stopCh: stopCh}
+		if _, err := p.fetchCDConfigBoundedByLifetime(&ctrld.Config{}); !errors.Is(err, context.Canceled) {
+			t.Errorf("reload fetch err = %v, want %v", err, context.Canceled)
+		}
+		if !sawCancelled {
+			t.Error("the reload fetch did not observe the stop request: it is not bound to the service lifetime")
+		}
+	})
+
+	t.Run("the derived context is always released", func(t *testing.T) {
+		// stopCh stays open: the fetch's own cancel is what must end the watcher, or
+		// every reload leaks a goroutine.
+		var captured context.Context
+		processCDFlagsFn = func(ctx context.Context, _ *ctrld.Config) (*controld.ResolverConfig, error) {
+			captured = ctx
+			return nil, nil
+		}
+
+		p := &prog{stopCh: make(chan struct{})}
+		if _, err := p.fetchCDConfigBoundedByLifetime(&ctrld.Config{}); err != nil {
+			t.Fatalf("unexpected error: %v", err)
+		}
+		select {
+		case <-captured.Done():
+		case <-time.After(time.Second):
+			t.Error("the reload fetch left its context uncancelled")
+		}
+	})
+}

cmd/cli/cli_provision_test.go

@@ -0,0 +1,329 @@
+package cli
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"net/http"
+	"path/filepath"
+	"runtime"
+	"strconv"
+	"strings"
+	"testing"
+
+	"github.com/rs/zerolog"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/controld"
+)
+
+// TestApiFailureCode covers the preflight-error mapping: a deleted device
+// gets its own code (it drives self-uninstall), other permanent rejections
+// are generic, anything else is retryable reachability trouble.
+func TestApiFailureCode(t *testing.T) {
+	rejection := func(status, code int) error {
+		e := &controld.ErrorResponse{StatusCode: status}
+		e.ErrorField.Code = code
+		e.ErrorField.Message = "api said no"
+		return e
+	}
+
+	tests := []struct {
+		name     string
+		err      error
+		wantCode provisionFailureCode
+		wantOk   bool
+	}{
+		{name: "nil error", err: nil, wantCode: "", wantOk: false},
+		{
+			name:     "deleted device maps to device invalid",
+			err:      rejection(http.StatusNotFound, controld.InvalidConfigCode),
+			wantCode: provisionCodeAPIDeviceInvalid,
+			wantOk:   true,
+		},
+		{
+			name:     "revoked credentials map to rejected",
+			err:      rejection(http.StatusUnauthorized, 0),
+			wantCode: provisionCodeAPIRejected,
+			wantOk:   true,
+		},
+		{
+			name:     "server error maps to unreachable",
+			err:      rejection(http.StatusBadGateway, 0),
+			wantCode: provisionCodeAPIUnreachable,
+			wantOk:   true,
+		},
+		{
+			name:     "network failure maps to unreachable",
+			err:      retryableNetworkErr(),
+			wantCode: provisionCodeAPIUnreachable,
+			wantOk:   true,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			code, ok := apiFailureCode(tc.err)
+			if ok != tc.wantOk {
+				t.Fatalf("apiFailureCode() ok = %v, want %v", ok, tc.wantOk)
+			}
+			if code != tc.wantCode {
+				t.Errorf("apiFailureCode() code = %s, want %s", code, tc.wantCode)
+			}
+		})
+	}
+}
+
+func stubProvisionGlobals(t *testing.T) (exitCode *int, notified *bool) {
+	t.Helper()
+	oldCdUID, oldCdOrg := cdUID, cdOrg
+	oldExit, oldUninstall := provisionExit, uninstallInvalidCdUIDFn
+	t.Cleanup(func() {
+		cdUID, cdOrg = oldCdUID, oldCdOrg
+		provisionExit, uninstallInvalidCdUIDFn = oldExit, oldUninstall
+	})
+	overrideProvisionResultPath(t)
+	code := -1
+	provisionExit = func(c int) { code = c }
+	n := false
+	return &code, &n
+}
+
+func TestHandleAPIPreflightFailure(t *testing.T) {
+	deviceInvalid := func() error {
+		e := &controld.ErrorResponse{StatusCode: http.StatusNotFound}
+		e.ErrorField.Code = controld.InvalidConfigCode
+		e.ErrorField.Message = "device does not exist"
+		return e
+	}
+	rejected := func() error {
+		e := &controld.ErrorResponse{StatusCode: http.StatusUnauthorized}
+		e.ErrorField.Message = "bad token"
+		return e
+	}
+
+	t.Run("permanent rejection returns cleanly", func(t *testing.T) {
+		exitCode, notified := stubProvisionGlobals(t)
+		handleAPIPreflightFailure(&prog{}, rejected(), func() { *notified = true })
+		if *exitCode != -1 {
+			t.Errorf("provisionExit called with %d, want a clean return", *exitCode)
+		}
+		if !*notified {
+			t.Error("notify not called")
+		}
+		r, err := readProvisionResult()
+		if err != nil {
+			t.Fatal(err)
+		}
+		if r.Code != string(provisionCodeAPIRejected) {
+			t.Errorf("code = %q, want API_REJECTED", r.Code)
+		}
+	})
+
+	t.Run("deleted device self-uninstalls and returns cleanly", func(t *testing.T) {
+		exitCode, notified := stubProvisionGlobals(t)
+		uninstalled := false
+		uninstallInvalidCdUIDFn = func(_ *prog, _ zerolog.Logger, _ bool) bool {
+			uninstalled = true
+			return true
+		}
+		handleAPIPreflightFailure(&prog{}, deviceInvalid(), func() { *notified = true })
+		if *exitCode != -1 {
+			t.Errorf("provisionExit called with %d, want a clean return", *exitCode)
+		}
+		if !uninstalled {
+			t.Error("self-uninstall not attempted")
+		}
+		if !*notified {
+			t.Error("notify not called")
+		}
+		r, err := readProvisionResult()
+		if err != nil {
+			t.Fatal(err)
+		}
+		if r.Code != string(provisionCodeAPIDeviceInvalid) {
+			t.Errorf("code = %q, want API_DEVICE_INVALID", r.Code)
+		}
+	})
+
+	t.Run("unreachable exits nonzero", func(t *testing.T) {
+		exitCode, notified := stubProvisionGlobals(t)
+		handleAPIPreflightFailure(&prog{}, retryableNetworkErr(), func() { *notified = true })
+		if *exitCode != provisionExitCodeForCode[provisionCodeAPIUnreachable] {
+			t.Errorf("exit = %d, want %d", *exitCode, provisionExitCodeForCode[provisionCodeAPIUnreachable])
+		}
+		if !*notified {
+			t.Error("notify not called")
+		}
+		r, err := readProvisionResult()
+		if err != nil {
+			t.Fatal(err)
+		}
+		if r.Code != string(provisionCodeAPIUnreachable) {
+			t.Errorf("code = %q, want API_UNREACHABLE", r.Code)
+		}
+	})
+
+	t.Run("bare uid from a composite --cd value is redacted", func(t *testing.T) {
+		_, _ = stubProvisionGlobals(t)
+		cdUID = "deviceabc/clientxyz"
+		cdOrg = ""
+		err := fmt.Errorf("failed: api says deviceabc is unknown")
+		handleAPIPreflightFailure(&prog{}, err, func() {})
+		r, rerr := readProvisionResult()
+		if rerr != nil {
+			t.Fatal(rerr)
+		}
+		if strings.Contains(r.Message, "deviceabc") {
+			t.Errorf("bare uid leaked into message: %q", r.Message)
+		}
+	})
+}
+
+func TestCdUIDFromProvTokenFailureEmitsCode(t *testing.T) {
+	exitCode, _ := stubProvisionGlobals(t)
+	oldFetch, oldHostname := fetchResolverUIDFn, customHostname
+	t.Cleanup(func() { fetchResolverUIDFn, customHostname = oldFetch, oldHostname })
+	cdUID = ""
+	cdOrg = "org-secret-token-123"
+	customHostname = ""
+
+	rejected := &controld.ErrorResponse{StatusCode: http.StatusUnauthorized}
+	rejected.ErrorField.Message = "bad provision token org-secret-token-123"
+	fetchResolverUIDFn = func(context.Context, *controld.UtilityOrgRequest, string, bool) (*controld.ResolverConfig, error) {
+		return nil, rejected
+	}
+
+	if got := cdUIDFromProvToken(); got != "" {
+		t.Errorf("cdUIDFromProvToken() = %q, want empty on failure", got)
+	}
+	if *exitCode != provisionExitCodeForCode[provisionCodeAPIRejected] {
+		t.Errorf("exit = %d, want API_REJECTED exit %d", *exitCode, provisionExitCodeForCode[provisionCodeAPIRejected])
+	}
+	r, err := readProvisionResult()
+	if err != nil {
+		t.Fatalf("no provision result written: %v", err)
+	}
+	if r.Code != string(provisionCodeAPIRejected) {
+		t.Errorf("code = %q, want API_REJECTED", r.Code)
+	}
+	if strings.Contains(r.Message, cdOrg) {
+		t.Errorf("token leaked into result message: %q", r.Message)
+	}
+}
+
+// Regression test: an explicit ip:port that fails to bind used to die with a
+// bare fatal log automation could not tell apart from any other crash. It
+// must report a stable code through the provisioning result instead.
+func TestTryUpdateListenerConfigConfiguredAddrUnavailable(t *testing.T) {
+	// Occupy one localhost port on both udp and tcp, and hold both for the
+	// whole test so ctrld's own bind attempt is guaranteed to fail.
+	udpConn, err := net.ListenPacket("udp", "127.0.0.1:0")
+	if err != nil {
+		t.Fatalf("could not reserve a udp port: %v", err)
+	}
+	defer udpConn.Close()
+
+	host, portStr, err := net.SplitHostPort(udpConn.LocalAddr().String())
+	if err != nil {
+		t.Fatalf("could not parse reserved address: %v", err)
+	}
+	port, err := strconv.Atoi(portStr)
+	if err != nil {
+		t.Fatalf("could not parse reserved port: %v", err)
+	}
+
+	tcpLn, err := net.Listen("tcp", net.JoinHostPort(host, portStr))
+	if err != nil {
+		t.Fatalf("could not reserve the same port on tcp: %v", err)
+	}
+	defer tcpLn.Close()
+
+	oldCdUID, oldCdOrg, oldNextdns, oldIntercept := cdUID, cdOrg, nextdns, interceptMode
+	oldPath, oldExit := provisionResultPath, provisionExit
+	t.Cleanup(func() {
+		cdUID, cdOrg, nextdns, interceptMode = oldCdUID, oldCdOrg, oldNextdns, oldIntercept
+		provisionResultPath, provisionExit = oldPath, oldExit
+	})
+	// Non-cd, non-nextdns mode with an explicit ip:port: no fallback checks,
+	// the path that used to reach the fatal exit directly.
+	cdUID = ""
+	cdOrg = ""
+	nextdns = ""
+	interceptMode = ""
+
+	tmpDir := t.TempDir()
+	provisionResultPath = func() string { return filepath.Join(tmpDir, "provision_result.json") }
+
+	var exitCode int
+	var exited bool
+	provisionExit = func(code int) { exitCode = code; exited = true }
+
+	cfg := &ctrld.Config{
+		Listener: map[string]*ctrld.ListenerConfig{
+			"0": {IP: host, Port: port},
+		},
+	}
+
+	notified := false
+	_, ok := tryUpdateListenerConfig(cfg, nil, func() { notified = true }, true)
+
+	if ok {
+		t.Error("tryUpdateListenerConfig ok = true, want false")
+	}
+	if !notified {
+		t.Error("expected notifyFunc to run before the recorded exit")
+	}
+	if !exited {
+		t.Fatal("expected provisionExit to be called")
+	}
+	if exitCode != 42 {
+		t.Errorf("exit code = %d, want 42 (LISTENER_CONFIGURED_ADDR_UNAVAILABLE)", exitCode)
+	}
+
+	result, err := readProvisionResult()
+	if err != nil {
+		t.Fatalf("could not read provision result: %v", err)
+	}
+	if result.Code != string(provisionCodeListenerAddrUnavail) {
+		t.Errorf("result code = %s, want %s", result.Code, provisionCodeListenerAddrUnavail)
+	}
+	if result.Stage != string(provisionStageListener) {
+		t.Errorf("result stage = %s, want %s", result.Stage, provisionStageListener)
+	}
+	if result.ExitCode != 42 {
+		t.Errorf("result exit code = %d, want 42", result.ExitCode)
+	}
+	if result.Detail == nil || len(result.Detail.Attempts) == 0 {
+		t.Fatal("expected the occupied address to appear as a recorded bind attempt")
+	}
+
+	occupiedAddr := net.JoinHostPort(host, portStr)
+	// Windows words WSAEADDRINUSE differently, so only require the canonical
+	// message on platforms that produce it.
+	requireInUseText := runtime.GOOS != "windows"
+	var sawUDP, sawTCP bool
+	for _, a := range result.Detail.Attempts {
+		if a.Addr != occupiedAddr || a.OSError == "" {
+			continue
+		}
+		if requireInUseText && !strings.Contains(strings.ToLower(a.OSError), "address already in use") {
+			continue
+		}
+		switch a.Proto {
+		case "udp":
+			sawUDP = true
+		case "tcp":
+			sawTCP = true
+		}
+	}
+	if !sawUDP {
+		t.Error("expected a udp attempt on the occupied address with a bind error")
+	}
+	if !sawTCP {
+		t.Error("expected a tcp attempt on the occupied address with a bind error")
+	}
+}
+
+// The exhaustion path (exit 41) is not covered: forcing every fallback,
+// including a freshly randomized ip/port, to fail has no deterministic seam,
+// so a test would race whatever ports are free on the host.

cmd/cli/cli_test.go

@@ -0,0 +1,46 @@
+package cli
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func Test_writeConfigFile(t *testing.T) {
+	tmpdir := t.TempDir()
+	// simulate --config CLI flag by setting configPath manually.
+	configPath = filepath.Join(tmpdir, "ctrld.toml")
+	_, err := os.Stat(configPath)
+	assert.True(t, os.IsNotExist(err))
+
+	assert.NoError(t, writeConfigFile(&cfg))
+
+	_, err = os.Stat(configPath)
+	require.NoError(t, err)
+}
+
+func Test_isStableVersion(t *testing.T) {
+	tests := []struct {
+		name     string
+		ver      string
+		isStable bool
+	}{
+		{"stable", "v1.3.5", true},
+		{"pre", "v1.3.5-next", false},
+		{"pre with commit hash", "v1.3.5-next-asdf", false},
+		{"dev", "dev", false},
+		{"empty", "dev", false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := isStableVersion(tc.ver); got != tc.isStable {
+				t.Errorf("unexpected result for %s, want: %v, got: %v", tc.ver, tc.isStable, got)
+			}
+		})
+	}
+}

cmd/cli/commands_start_test.go

@@ -0,0 +1,122 @@
+package cli
+
+import (
+	"testing"
+	"time"
+)
+
+func TestServiceStageFailureCode(t *testing.T) {
+	tests := []struct {
+		taskName string
+		wantCode provisionFailureCode
+		wantOK   bool
+	}{
+		{"Install", provisionCodeServiceInstall, true},
+		{"Start", provisionCodeServiceStartFailed, true},
+		{"Checking config", "", false},
+		{"", "", false},
+	}
+	for _, tc := range tests {
+		code, ok := serviceStageFailureCode(tc.taskName)
+		if code != tc.wantCode || ok != tc.wantOK {
+			t.Errorf("serviceStageFailureCode(%q) = (%q, %v), want (%q, %v)", tc.taskName, code, ok, tc.wantCode, tc.wantOK)
+		}
+	}
+}
+
+func stubProvisionExit(t *testing.T) *int {
+	t.Helper()
+	exitCode := -1
+	old := provisionExit
+	provisionExit = func(code int) { exitCode = code }
+	t.Cleanup(func() { provisionExit = old })
+	return &exitCode
+}
+
+func TestReportStartFailureUsesFreshDaemonResult(t *testing.T) {
+	overrideProvisionResultPath(t)
+	exitCode := stubProvisionExit(t)
+
+	startedAt := time.Now()
+	daemonResult := newProvisionResult(provisionCodeAPIUnreachable, "daemon could not reach the API", nil)
+	if err := writeProvisionResult(daemonResult); err != nil {
+		t.Fatal(err)
+	}
+
+	reportStartFailure(startedAt, "generic self-check failure")
+
+	if *exitCode != provisionExitCodeForCode[provisionCodeAPIUnreachable] {
+		t.Errorf("exit code = %d, want the daemon's own exit code %d", *exitCode, provisionExitCodeForCode[provisionCodeAPIUnreachable])
+	}
+	out, err := readProvisionResult()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if out.Code != string(provisionCodeAPIUnreachable) {
+		t.Errorf("persisted code = %q, want the daemon's own code untouched", out.Code)
+	}
+}
+
+func TestReportStartFailureFallsBackOnStaleDaemonResult(t *testing.T) {
+	overrideProvisionResultPath(t)
+	exitCode := stubProvisionExit(t)
+
+	stale := newProvisionResult(provisionCodeAPIUnreachable, "an old failure", nil)
+	stale.Timestamp = time.Now().Add(-1 * time.Hour).UTC().Format(time.RFC3339)
+	if err := writeProvisionResult(stale); err != nil {
+		t.Fatal(err)
+	}
+
+	startedAt := time.Now()
+	reportStartFailure(startedAt, "test query failed: timeout")
+
+	if *exitCode != provisionExitCodeForCode[provisionCodeServiceSelfCheck] {
+		t.Errorf("exit code = %d, want SERVICE_SELFCHECK_FAILED exit %d", *exitCode, provisionExitCodeForCode[provisionCodeServiceSelfCheck])
+	}
+	out, err := readProvisionResult()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if out.Code != string(provisionCodeServiceSelfCheck) {
+		t.Errorf("persisted code = %q, want %q", out.Code, provisionCodeServiceSelfCheck)
+	}
+	if out.Message != "test query failed: timeout" {
+		t.Errorf("persisted message = %q, want the fallback message", out.Message)
+	}
+}
+
+func TestReportStartFailureRejectsUntrustedFile(t *testing.T) {
+	overrideProvisionResultPath(t)
+	exitCode := stubProvisionExit(t)
+
+	planted := newProvisionResult(provisionCodeAPIUnreachable, "planted", nil)
+	planted.Code = "FAKE_CODE"
+	planted.ExitCode = 99
+	if err := writeProvisionResult(planted); err != nil {
+		t.Fatal(err)
+	}
+
+	reportStartFailure(time.Now().Add(-time.Minute), "self-check failed")
+
+	if *exitCode != provisionExitCodeForCode[provisionCodeServiceSelfCheck] {
+		t.Errorf("exit = %d, want the fallback %d, never the planted 99", *exitCode, provisionExitCodeForCode[provisionCodeServiceSelfCheck])
+	}
+}
+
+func TestReportStartFailureFallsBackWhenResultFileMissing(t *testing.T) {
+	overrideProvisionResultPath(t)
+	exitCode := stubProvisionExit(t)
+
+	reportStartFailure(time.Now(), "firewall hint")
+
+	if *exitCode != provisionExitCodeForCode[provisionCodeServiceSelfCheck] {
+		t.Errorf("exit code = %d, want SERVICE_SELFCHECK_FAILED exit %d", *exitCode, provisionExitCodeForCode[provisionCodeServiceSelfCheck])
+	}
+	out, err := readProvisionResult()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if out.Message != "firewall hint" {
+		t.Errorf("persisted message = %q, want the fallback message", out.Message)
+	}
+}

cmd/cli/conn.go

@@ -0,0 +1,51 @@
+package cli
+
+import (
+	"net"
+	"time"
+)
+
+// logConn wraps a net.Conn, override the Write behavior.
+// runCmd uses this wrapper, so as long as startCmd finished,
+// ctrld log won't be flushed with un-necessary write errors.
+type logConn struct {
+	conn net.Conn
+}
+
+func (lc *logConn) Read(b []byte) (n int, err error) {
+	return lc.conn.Read(b)
+}
+
+func (lc *logConn) Close() error {
+	return lc.conn.Close()
+}
+
+func (lc *logConn) LocalAddr() net.Addr {
+	return lc.conn.LocalAddr()
+}
+
+func (lc *logConn) RemoteAddr() net.Addr {
+	return lc.conn.RemoteAddr()
+}
+
+func (lc *logConn) SetDeadline(t time.Time) error {
+	return lc.conn.SetDeadline(t)
+}
+
+func (lc *logConn) SetReadDeadline(t time.Time) error {
+	return lc.conn.SetReadDeadline(t)
+}
+
+func (lc *logConn) SetWriteDeadline(t time.Time) error {
+	return lc.conn.SetWriteDeadline(t)
+}
+
+func (lc *logConn) Write(b []byte) (int, error) {
+	// Write performs writes with underlying net.Conn, ignore any errors happen.
+	// "ctrld run" command use this wrapper to report errors to "ctrld start".
+	// If no error occurred, "ctrld start" may finish before "ctrld run" attempt
+	// to close the connection, so ignore errors conservatively here, prevent
+	// un-necessary error "write to closed connection" flushed to ctrld log.
+	_, _ = lc.conn.Write(b)
+	return len(b), nil
+}

cmd/cli/control_client.go

@@ -0,0 +1,44 @@
+package cli
+
+import (
+	"context"
+	"io"
+	"net"
+	"net/http"
+	"time"
+)
+
+type controlClient struct {
+	c *http.Client
+}
+
+func newControlClient(addr string) *controlClient {
+	return &controlClient{c: &http.Client{
+		Transport: &http.Transport{
+			DialContext: func(ctx context.Context, _, _ string) (net.Conn, error) {
+				d := net.Dialer{}
+				return d.DialContext(ctx, "unix", addr)
+			},
+		},
+		Timeout: time.Second * 30,
+	}}
+}
+
+func (c *controlClient) post(path string, data io.Reader) (*http.Response, error) {
+	// for log/send, set the timeout to 5 minutes
+	if path == sendLogsPath {
+		c.c.Timeout = time.Minute * 5
+	}
+	return c.c.Post("http://unix"+path, contentTypeJson, data)
+}
+
+// postStream sends a POST request with no timeout, suitable for long-lived streaming connections.
+func (c *controlClient) postStream(path string, data io.Reader) (*http.Response, error) {
+	c.c.Timeout = 0
+	return c.c.Post("http://unix"+path, contentTypeJson, data)
+}
+
+// deactivationRequest represents request for validating deactivation pin.
+type deactivationRequest struct {
+	Pin int64 `json:"pin"`
+}

cmd/cli/control_server.go

@@ -0,0 +1,538 @@
+package cli
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"os"
+	"reflect"
+	"sort"
+	"strconv"
+	"time"
+
+	"github.com/kardianos/service"
+	dto "github.com/prometheus/client_model/go"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/controld"
+)
+
+const (
+	contentTypeJson  = "application/json"
+	listClientsPath  = "/clients"
+	startedPath      = "/started"
+	reloadPath       = "/reload"
+	deactivationPath = "/deactivation"
+	cdPath           = "/cd"
+	ifacePath        = "/iface"
+	viewLogsPath     = "/log/view"
+	sendLogsPath     = "/log/send"
+	tailLogsPath     = "/log/tail"
+)
+
+type ifaceResponse struct {
+	Name          string `json:"name"`
+	All           bool   `json:"all"`
+	OK            bool   `json:"ok"`
+	InterceptMode string `json:"intercept_mode,omitempty"` // "dns", "hard", or "" (not intercepting)
+}
+
+type controlServer struct {
+	server *http.Server
+	mux    *http.ServeMux
+	addr   string
+}
+
+func newControlServer(addr string) (*controlServer, error) {
+	mux := http.NewServeMux()
+	s := &controlServer{
+		server: &http.Server{Handler: mux},
+		mux:    mux,
+	}
+	s.addr = addr
+	return s, nil
+}
+
+func (s *controlServer) start() error {
+	_ = os.Remove(s.addr)
+	unixListener, err := net.Listen("unix", s.addr)
+	if err != nil {
+		return err
+	}
+	// Restrict socket permissions to owner-only (0600) so that only the
+	// process owner (typically root) can connect. Defense-in-depth since
+	// the control server endpoints carry no authentication of their own.
+	if err := os.Chmod(s.addr, 0600); err != nil {
+		return err
+	}
+	if l, ok := unixListener.(*net.UnixListener); ok {
+		l.SetUnlinkOnClose(true)
+	}
+	go s.server.Serve(unixListener)
+	return nil
+}
+
+func (s *controlServer) stop() error {
+	_ = os.Remove(s.addr)
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*2)
+	defer cancel()
+	return s.server.Shutdown(ctx)
+}
+
+func (s *controlServer) register(pattern string, handler http.Handler) {
+	s.mux.Handle(pattern, jsonResponse(handler))
+}
+
+func (p *prog) registerControlServerHandler() {
+	p.cs.register(listClientsPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		mainLog.Load().Debug().Msg("handling list clients request")
+
+		clients := p.ciTable.ListClients()
+		mainLog.Load().Debug().Int("client_count", len(clients)).Msg("retrieved clients list")
+
+		sort.Slice(clients, func(i, j int) bool {
+			return clients[i].IP.Less(clients[j].IP)
+		})
+		mainLog.Load().Debug().Msg("sorted clients by IP address")
+
+		if p.metricsQueryStats.Load() {
+			mainLog.Load().Debug().Msg("metrics query stats enabled, collecting query counts")
+
+			for idx, client := range clients {
+				mainLog.Load().Debug().
+					Int("index", idx).
+					Str("ip", client.IP.String()).
+					Str("mac", client.Mac).
+					Str("hostname", client.Hostname).
+					Msg("processing client metrics")
+
+				client.IncludeQueryCount = true
+				dm := &dto.Metric{}
+
+				if statsClientQueriesCount.MetricVec == nil {
+					mainLog.Load().Debug().
+						Str("client_ip", client.IP.String()).
+						Msg("skipping metrics collection: MetricVec is nil")
+					continue
+				}
+
+				m, err := statsClientQueriesCount.MetricVec.GetMetricWithLabelValues(
+					client.IP.String(),
+					client.Mac,
+					client.Hostname,
+				)
+				if err != nil {
+					mainLog.Load().Debug().
+						Err(err).
+						Str("client_ip", client.IP.String()).
+						Str("mac", client.Mac).
+						Str("hostname", client.Hostname).
+						Msg("failed to get metrics for client")
+					continue
+				}
+
+				if err := m.Write(dm); err == nil && dm.Counter != nil {
+					client.QueryCount = int64(dm.Counter.GetValue())
+					mainLog.Load().Debug().
+						Str("client_ip", client.IP.String()).
+						Int64("query_count", client.QueryCount).
+						Msg("successfully collected query count")
+				} else if err != nil {
+					mainLog.Load().Debug().
+						Err(err).
+						Str("client_ip", client.IP.String()).
+						Msg("failed to write metric")
+				}
+			}
+		} else {
+			mainLog.Load().Debug().Msg("metrics query stats disabled, skipping query counts")
+		}
+
+		if err := json.NewEncoder(w).Encode(&clients); err != nil {
+			mainLog.Load().Error().
+				Err(err).
+				Int("client_count", len(clients)).
+				Msg("failed to encode clients response")
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+			return
+		}
+
+		mainLog.Load().Debug().
+			Int("client_count", len(clients)).
+			Msg("successfully sent clients list response")
+	}))
+	p.cs.register(startedPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		select {
+		case <-p.onStartedDone:
+			w.WriteHeader(http.StatusOK)
+		case <-time.After(10 * time.Second):
+			w.WriteHeader(http.StatusRequestTimeout)
+		}
+	}))
+	p.cs.register(reloadPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		listeners := make(map[string]*ctrld.ListenerConfig)
+		p.mu.Lock()
+		for k, v := range p.cfg.Listener {
+			listeners[k] = &ctrld.ListenerConfig{
+				IP:   v.IP,
+				Port: v.Port,
+			}
+		}
+		oldSvc := p.cfg.Service
+		p.mu.Unlock()
+		if err := p.sendReloadSignal(); err != nil {
+			mainLog.Load().Err(err).Msg("could not send reload signal")
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+			return
+		}
+		select {
+		case <-p.reloadDoneCh:
+		case <-time.After(5 * time.Second):
+			http.Error(w, "timeout waiting for ctrld reload", http.StatusInternalServerError)
+			return
+		}
+
+		p.mu.Lock()
+		defer p.mu.Unlock()
+
+		// Checking for cases that we could not do a reload.
+
+		// 1. Listener config ip or port changes.
+		for k, v := range p.cfg.Listener {
+			l := listeners[k]
+			if l == nil || l.IP != v.IP || l.Port != v.Port {
+				w.WriteHeader(http.StatusCreated)
+				return
+			}
+		}
+
+		// 2. Service config changes.
+		if !reflect.DeepEqual(oldSvc, p.cfg.Service) {
+			w.WriteHeader(http.StatusCreated)
+			return
+		}
+
+		// Otherwise, reload is done.
+		w.WriteHeader(http.StatusOK)
+	}))
+	p.cs.register(deactivationPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		// Non-cd mode always allowing deactivation.
+		if cdUID == "" {
+			w.WriteHeader(http.StatusOK)
+			return
+		}
+
+		// Reject further attempts while locked out due to repeated wrong PINs.
+		if now := time.Now().Unix(); now < deactivationLockedUntil.Load() {
+			w.WriteHeader(http.StatusTooManyRequests)
+			return
+		}
+
+		// Re-fetch pin code from API.
+		rcReq := &controld.ResolverConfigRequest{
+			RawUID:   cdUID,
+			Version:  rootCmd.Version,
+			Metadata: ctrld.SystemMetadataRuntime(context.Background()),
+		}
+		if rc, err := controld.FetchResolverConfig(context.Background(), rcReq, cdDev); rc != nil {
+			if rc.DeactivationPin != nil {
+				cdDeactivationPin.Store(*rc.DeactivationPin)
+			} else {
+				cdDeactivationPin.Store(defaultDeactivationPin)
+			}
+		} else {
+			mainLog.Load().Warn().Err(err).Msg("could not re-fetch deactivation pin code")
+		}
+
+		// If pin code not set, allowing deactivation.
+		if !deactivationPinSet() {
+			w.WriteHeader(http.StatusOK)
+			return
+		}
+
+		var req deactivationRequest
+		if err := json.NewDecoder(request.Body).Decode(&req); err != nil {
+			w.WriteHeader(http.StatusPreconditionFailed)
+			mainLog.Load().Err(err).Msg("invalid deactivation request")
+			return
+		}
+
+		code := http.StatusForbidden
+		switch req.Pin {
+		case cdDeactivationPin.Load():
+			code = http.StatusOK
+			deactivationFailedAttempts.Store(0)
+			select {
+			case p.pinCodeValidCh <- struct{}{}:
+			default:
+			}
+		case defaultDeactivationPin:
+			// If the pin code was set, but users do not provide --pin, return proper code to client.
+			code = http.StatusBadRequest
+		default:
+			if deactivationFailedAttempts.Add(1) >= deactivationMaxFailedAttempts {
+				deactivationLockedUntil.Store(time.Now().Unix() + deactivationLockoutSeconds)
+				deactivationFailedAttempts.Store(0)
+			}
+		}
+		w.WriteHeader(code)
+	}))
+	p.cs.register(cdPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		if cdUID != "" {
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(cdUID))
+			return
+		}
+		w.WriteHeader(http.StatusBadRequest)
+	}))
+	p.cs.register(ifacePath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		res := &ifaceResponse{Name: iface}
+		// p.setDNS is only called when running as a service
+		if !service.Interactive() {
+			<-p.csSetDnsDone
+			if p.csSetDnsOk {
+				res.Name = p.runningIface
+				res.All = p.requiredMultiNICsConfig
+				res.OK = true
+				// Report intercept mode to the start command for proper log output.
+				if interceptMode == "dns" || interceptMode == "hard" {
+					res.InterceptMode = interceptMode
+				}
+			}
+		}
+		if err := json.NewEncoder(w).Encode(res); err != nil {
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+			http.Error(w, fmt.Sprintf("could not marshal iface data: %v", err), http.StatusInternalServerError)
+			return
+		}
+	}))
+	p.cs.register(viewLogsPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		lr, err := p.logReader()
+		if err != nil {
+			http.Error(w, err.Error(), http.StatusBadRequest)
+			return
+		}
+		defer lr.r.Close()
+		if lr.size == 0 {
+			w.WriteHeader(http.StatusMovedPermanently)
+			return
+		}
+		data, err := io.ReadAll(lr.r)
+		if err != nil {
+			http.Error(w, fmt.Sprintf("could not read log: %v", err), http.StatusInternalServerError)
+			return
+		}
+		if err := json.NewEncoder(w).Encode(&logViewResponse{Data: string(data)}); err != nil {
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+			http.Error(w, fmt.Sprintf("could not marshal log data: %v", err), http.StatusInternalServerError)
+			return
+		}
+	}))
+	p.cs.register(sendLogsPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		if time.Since(p.internalLogSent) < logWriterSentInterval {
+			w.WriteHeader(http.StatusServiceUnavailable)
+			return
+		}
+		r, err := p.logReader()
+		if err != nil {
+			http.Error(w, err.Error(), http.StatusBadRequest)
+			return
+		}
+		if r.size == 0 {
+			w.WriteHeader(http.StatusMovedPermanently)
+			return
+		}
+		req := &controld.LogsRequest{
+			UID:  cdUID,
+			Data: r.r,
+		}
+		mainLog.Load().Debug().Msg("sending log file to ControlD server")
+		resp := logSentResponse{Size: r.size}
+		if err := controld.SendLogs(context.Background(), req, cdDev); err != nil {
+			mainLog.Load().Error().Msgf("could not send log file to ControlD server: %v", err)
+			resp.Error = err.Error()
+			w.WriteHeader(http.StatusInternalServerError)
+		} else {
+			mainLog.Load().Debug().Msg("sending log file successfully")
+			w.WriteHeader(http.StatusOK)
+		}
+		if err := json.NewEncoder(w).Encode(&resp); err != nil {
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+		}
+		p.internalLogSent = time.Now()
+	}))
+	p.cs.register(tailLogsPath, http.HandlerFunc(func(w http.ResponseWriter, request *http.Request) {
+		flusher, ok := w.(http.Flusher)
+		if !ok {
+			http.Error(w, "streaming unsupported", http.StatusInternalServerError)
+			return
+		}
+
+		// Determine logging mode and validate before starting the stream.
+		var lw *logWriter
+		useInternalLog := p.needInternalLogging()
+		if useInternalLog {
+			p.mu.Lock()
+			lw = p.internalLogWriter
+			p.mu.Unlock()
+			if lw == nil {
+				w.WriteHeader(http.StatusMovedPermanently)
+				return
+			}
+		} else if p.cfg.Service.LogPath == "" {
+			// No logging configured at all.
+			w.WriteHeader(http.StatusMovedPermanently)
+			return
+		}
+
+		// Parse optional "lines" query param for initial context.
+		numLines := 10
+		if v := request.URL.Query().Get("lines"); v != "" {
+			if n, err := strconv.Atoi(v); err == nil && n >= 0 {
+				numLines = n
+			}
+		}
+
+		w.Header().Set("Content-Type", "text/plain; charset=utf-8")
+		w.Header().Set("Transfer-Encoding", "chunked")
+		w.Header().Set("X-Content-Type-Options", "nosniff")
+		w.WriteHeader(http.StatusOK)
+
+		if useInternalLog {
+			// Internal logging mode: subscribe to the logWriter.
+
+			// Send last N lines as initial context.
+			if numLines > 0 {
+				if tail := lw.tailLastLines(numLines); len(tail) > 0 {
+					w.Write(tail)
+					flusher.Flush()
+				}
+			}
+
+			ch, unsub := lw.Subscribe()
+			defer unsub()
+			for {
+				select {
+				case data, ok := <-ch:
+					if !ok {
+						return
+					}
+					if _, err := w.Write(data); err != nil {
+						return
+					}
+					flusher.Flush()
+				case <-request.Context().Done():
+					return
+				}
+			}
+		} else {
+			// File-based logging mode: tail the log file.
+			logFile := normalizeLogFilePath(p.cfg.Service.LogPath)
+			f, err := os.Open(logFile)
+			if err != nil {
+				// Already committed 200, just return.
+				return
+			}
+			defer f.Close()
+
+			// Seek to show last N lines.
+			if numLines > 0 {
+				if tail := tailFileLastLines(f, numLines); len(tail) > 0 {
+					w.Write(tail)
+					flusher.Flush()
+				}
+			} else {
+				// Seek to end.
+				f.Seek(0, io.SeekEnd)
+			}
+
+			// Poll for new data.
+			buf := make([]byte, 4096)
+			ticker := time.NewTicker(200 * time.Millisecond)
+			defer ticker.Stop()
+			for {
+				select {
+				case <-ticker.C:
+					n, err := f.Read(buf)
+					if n > 0 {
+						if _, werr := w.Write(buf[:n]); werr != nil {
+							return
+						}
+						flusher.Flush()
+					}
+					if err != nil && err != io.EOF {
+						return
+					}
+				case <-request.Context().Done():
+					return
+				}
+			}
+		}
+	}))
+}
+
+// tailFileLastLines reads the last n lines from a file and returns them.
+// The file position is left at the end of the file after this call.
+func tailFileLastLines(f *os.File, n int) []byte {
+	stat, err := f.Stat()
+	if err != nil || stat.Size() == 0 {
+		return nil
+	}
+
+	// Read from the end in chunks to find the last n lines.
+	const chunkSize = 4096
+	fileSize := stat.Size()
+	var lines []byte
+	offset := fileSize
+	count := 0
+
+	for offset > 0 && count <= n {
+		readSize := int64(chunkSize)
+		if readSize > offset {
+			readSize = offset
+		}
+		offset -= readSize
+		buf := make([]byte, readSize)
+		nRead, err := f.ReadAt(buf, offset)
+		if err != nil && err != io.EOF {
+			break
+		}
+		buf = buf[:nRead]
+		lines = append(buf, lines...)
+
+		// Count newlines in this chunk.
+		for _, b := range buf {
+			if b == '\n' {
+				count++
+			}
+		}
+	}
+
+	// Trim to last n lines.
+	idx := 0
+	nlCount := 0
+	for i := len(lines) - 1; i >= 0; i-- {
+		if lines[i] == '\n' {
+			nlCount++
+			if nlCount == n+1 {
+				idx = i + 1
+				break
+			}
+		}
+	}
+	lines = lines[idx:]
+
+	// Seek to end of file for subsequent reads.
+	f.Seek(0, io.SeekEnd)
+	return lines
+}
+
+func jsonResponse(next http.Handler) http.Handler {
+	return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		next.ServeHTTP(w, r)
+	})
+}

cmd/cli/control_server_test.go

@@ -0,0 +1,54 @@
+package cli
+
+import (
+	"bytes"
+	"io"
+	"net/http"
+	"os"
+	"testing"
+)
+
+func TestControlServer(t *testing.T) {
+	f, err := os.CreateTemp("", "")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer os.Remove(f.Name())
+	f.Close()
+
+	s, err := newControlServer(f.Name())
+	if err != nil {
+		t.Fatal(err)
+	}
+	pattern := "/ping"
+	respBody := []byte("pong")
+	s.register(pattern, http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_, _ = w.Write(respBody)
+	}))
+	if err := s.start(); err != nil {
+		t.Fatal(err)
+	}
+
+	c := newControlClient(f.Name())
+	resp, err := c.post(pattern, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != 200 {
+		t.Fatalf("unepxected response code: %d", resp.StatusCode)
+	}
+	if ct := resp.Header.Get("content-type"); ct != contentTypeJson {
+		t.Fatalf("unexpected content type: %s", ct)
+	}
+	buf, err := io.ReadAll(resp.Body)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if !bytes.Equal(buf, respBody) {
+		t.Errorf("unexpected response body, want: %q, got: %q", string(respBody), string(buf))
+	}
+	if err := s.stop(); err != nil {
+		t.Fatal(err)
+	}
+}

cmd/cli/dns.go

@@ -1,4 +1,4 @@
-package main
+package cli
 
 //lint:ignore U1000 use in os_linux.go
 type getDNS func(iface string) []string

cmd/cli/dns_intercept_ignored_change_windows_test.go

@@ -0,0 +1,20 @@
+//go:build windows
+
+package cli
+
+import (
+	"testing"
+	"time"
+)
+
+func TestDNSInterceptIgnoredChangeReconcileDueWindowsPreservesImmediateBehavior(t *testing.T) {
+	p := &prog{}
+	now := time.Now()
+
+	if !p.dnsInterceptIgnoredChangeReconcileDue(now) {
+		t.Fatal("first ignored Windows change must reconcile immediately")
+	}
+	if !p.dnsInterceptIgnoredChangeReconcileDue(now) {
+		t.Fatal("Windows ignored changes must not inherit the macOS pf rate limit")
+	}
+}

cmd/cli/dns_intercept_lifecycle_windows_test.go

@@ -0,0 +1,319 @@
+//go:build windows
+
+package cli
+
+import (
+	"runtime"
+	"testing"
+	"time"
+)
+
+// newInterceptTestProg returns a prog with a published intercept state, fake NRPT
+// operations already installed, and no WFP engine (engineHandle 0).
+//
+// The fake is installed here, before anything can inspect registry state, and it is the
+// safety boundary - not the empty wfpState. A zero-valued state has owner None, and
+// shutdown's None branch sweeps orphaned ctrld rules, so an unfaked stopDNSIntercept would
+// reach the production nrptCatchAllRuleExists / removeNRPTCatchAllRule / signalNRPTChange.
+// On a host that has ctrld's deterministic key - a developer box, or a CI runner where
+// ctrld is installed - that deletes live policy and forces a Group Policy refresh, a
+// Dnscache paramchange and a cache flush. A green run on a clean runner proves nothing
+// about that.
+func newInterceptTestProg(t *testing.T) (*prog, *wfpState, *fakeNRPTOps) {
+	t.Helper()
+	f := fakeNRPTOpsForTest(t)
+	// Prove the fake is in effect before anything can inspect registry state. Asserting
+	// zero side effects afterwards cannot do that: an uninstalled fake reports zero
+	// whether it was consulted or bypassed.
+	requireFakeNRPTOpsInstalled(t, f)
+	state := &wfpState{stopCh: make(chan struct{}), listenerIP: "127.0.0.1"}
+	p := &prog{}
+	p.dnsInterceptState = state
+	return p, state, f
+}
+
+// assertNoNRPTSideEffects fails when a lifecycle path wrote NRPT policy or signalled the
+// DNS Client. Every test in this file exercises a guard that is supposed to stand down, so
+// any registry write or signal here means the guard did not hold - and, without the fake,
+// would have hit the host's real policy.
+func assertNoNRPTSideEffects(t *testing.T, f *fakeNRPTOps) {
+	t.Helper()
+	add, remove, signal, _ := f.counts()
+	if add != 0 || remove != 0 || signal != 0 {
+		t.Errorf("addRule = %d, removeRule = %d, signal = %d, want 0/0/0: this path must not write NRPT policy",
+			add, remove, signal)
+	}
+	if flush := f.flushCount(); flush != 0 {
+		t.Errorf("flush calls = %d, want 0: this path must not flush the resolver cache", flush)
+	}
+}
+
+// TestStopDNSInterceptRevokesBeforeTeardown pins the ordering the shutdown/monitor race
+// depends on. Teardown deletes our WFP sublayer, and a missing sublayer is precisely what
+// the health monitor treats as "our filters were wiped, rebuild everything". Were the
+// state revoked only after teardown, a monitor tick inside that window would rebuild the
+// intercept during shutdown.
+func TestStopDNSInterceptRevokesBeforeTeardown(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+
+	if p.interceptStateRevoked(state) {
+		t.Fatal("a freshly published intercept state must not read as retired")
+	}
+	if err := p.stopDNSIntercept(); err != nil {
+		t.Fatalf("stopDNSIntercept() = %v", err)
+	}
+	if !p.interceptStateRevoked(state) {
+		t.Error("state still reads live after shutdown: the monitor and heal flows would keep writing host DNS state")
+	}
+	if p.dnsInterceptState != nil {
+		t.Error("dnsInterceptState survived shutdown")
+	}
+	if p.dnsInterceptStopRequested.Load() {
+		t.Error("stop-requested flag was left set; a later start would see a phantom shutdown")
+	}
+}
+
+// TestRebuildDNSInterceptRefusedAfterShutdown is the regression test for the reported
+// race: SCM stop runs resetDNS -> stopDNSIntercept while the health monitor is mid-tick,
+// and the monitor then reaches the rebuild path before the process exits. The rebuild
+// must refuse - completing it would re-add the NRPT catch-all and the WFP filters moments
+// before ctrld disappears, leaving Windows resolving through a listener that is gone.
+//
+// That refusal is also what keeps this test safe on a real Windows host: a rebuild that
+// did not refuse would run startDNSIntercept and write NRPT policy to the machine
+// running the tests.
+func TestRebuildDNSInterceptRefusedAfterShutdown(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+	if err := p.stopDNSIntercept(); err != nil {
+		t.Fatalf("stopDNSIntercept() = %v", err)
+	}
+
+	if got := p.rebuildDNSIntercept(state, "WFP sublayer missing during health check"); got != interceptRebuildRetired {
+		t.Fatalf("rebuildDNSIntercept() = %v, want interceptRebuildRetired - a post-shutdown rebuild resurrects DNS interception", got)
+	}
+	if p.dnsInterceptState != nil {
+		t.Error("rebuild published new intercept state after shutdown")
+	}
+}
+
+// TestRebuildDNSInterceptRefusedForReplacedState covers the other stale-owner case: an
+// earlier rebuild already replaced the state, so a goroutine still holding the old one
+// must not tear down its successor.
+func TestRebuildDNSInterceptRefusedForReplacedState(t *testing.T) {
+	p, old, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+	current := &wfpState{stopCh: make(chan struct{}), listenerIP: "127.0.0.1"}
+	p.dnsInterceptState = current
+
+	if got := p.rebuildDNSIntercept(old, "WFP sublayer missing during health check"); got != interceptRebuildRetired {
+		t.Fatalf("rebuildDNSIntercept() = %v, want interceptRebuildRetired for a superseded state", got)
+	}
+	if p.dnsInterceptState != any(current) {
+		t.Error("a superseded state's rebuild replaced the live intercept")
+	}
+	if p.interceptStateRevoked(current) {
+		t.Error("the live state was revoked by a superseded rebuild")
+	}
+}
+
+// TestRepairMissingWFPStandsDownAfterShutdown checks the monitor's entry point. It must
+// not even query WFP for a retired state - the sublayer it looks for is what teardown
+// just deleted - and it must tell the monitor goroutine to exit.
+func TestRepairMissingWFPStandsDownAfterShutdown(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+	if err := p.stopDNSIntercept(); err != nil {
+		t.Fatalf("stopDNSIntercept() = %v", err)
+	}
+	// Set the handle only after teardown. A fake handle proves the revocation check
+	// comes first, but must never reach the real WFP calls in cleanupWFPFilters.
+	state.engineHandle = 1
+
+	if !p.repairMissingWFP(state) {
+		t.Error("repairMissingWFP() = false after shutdown; the health monitor would keep running for a dead intercept")
+	}
+	if p.dnsInterceptState != nil {
+		t.Error("repairMissingWFP rebuilt the intercept after shutdown")
+	}
+}
+
+// TestPendingStopSignalsRevocation covers how a stop avoids waiting: while it is blocked
+// on the lifecycle lock it must already read as revoked, so an in-flight NRPT heal
+// abandons its probe backoff instead of making the service stop wait it out. A stop that
+// waits too long is killed by the Service Control Manager, which cleans up nothing.
+func TestPendingStopSignalsRevocation(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+
+	p.dnsInterceptMu.Lock()
+	stopped := make(chan struct{})
+	go func() {
+		defer close(stopped)
+		_ = p.stopDNSIntercept()
+	}()
+
+	// Wait for the stop to announce itself while it is blocked on the lock.
+	deadline := time.Now().Add(5 * time.Second)
+	for !p.dnsInterceptStopRequested.Load() {
+		if time.Now().After(deadline) {
+			p.dnsInterceptMu.Unlock()
+			<-stopped
+			t.Fatal("stop never announced itself before waiting for the lifecycle lock")
+		}
+		runtime.Gosched()
+	}
+	if !p.interceptStateRevoked(state) {
+		t.Error("a pending stop does not read as revoked; the heal flows would keep it waiting")
+	}
+	p.dnsInterceptMu.Unlock()
+	<-stopped
+
+	if p.dnsInterceptState != nil {
+		t.Error("the pending stop did not tear down the intercept once it acquired the lock")
+	}
+}
+
+// TestInterceptWaitAbandonsPromptlyOnPendingStop is the bound on how long a stop can be
+// delayed by a recovery flow: the heal sequence's waits add up to tens of seconds, and
+// each one must end as soon as a stop is pending.
+func TestInterceptWaitAbandonsPromptlyOnPendingStop(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+	p.dnsInterceptStopRequested.Store(true)
+
+	start := time.Now()
+	if p.interceptWait(state, 30*time.Second) {
+		t.Fatal("interceptWait() = true with a stop pending; the caller would carry on writing host DNS state")
+	}
+	if elapsed := time.Since(start); elapsed > 2*time.Second {
+		t.Errorf("interceptWait took %v to notice a pending stop; shutdown would inherit that delay", elapsed)
+	}
+}
+
+// TestInterceptWaitRunsToCompletionWhileLive guards the other direction: the cancellable
+// wait must still actually wait, or the recovery flows lose their backoff.
+func TestInterceptWaitRunsToCompletionWhileLive(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+
+	start := time.Now()
+	if !p.interceptWait(state, 250*time.Millisecond) {
+		t.Fatal("interceptWait() = false for a live intercept")
+	}
+	if elapsed := time.Since(start); elapsed < 250*time.Millisecond {
+		t.Errorf("interceptWait returned after %v, want at least 250ms", elapsed)
+	}
+}
+
+// TestNRPTNeedsCtrldActivation covers the recovery gap that left a machine unfiltered
+// until restart: a failed NRPT write clears ownership, and an owner-None tick used to do
+// nothing at all, so nothing ever retried the write.
+func TestNRPTNeedsCtrldActivation(t *testing.T) {
+	tests := []struct {
+		name       string
+		owner      nrptRuleOwner
+		ruleExists bool
+		want       bool
+	}{
+		{
+			// The reported hole: activation failed, ownership was cleared, and no
+			// other path re-arms it. In hard mode WFP keeps blocking DNS meanwhile.
+			name:  "no owner retries the failed write",
+			owner: nrptRuleOwnerNone,
+			want:  true,
+		},
+		{
+			name:       "no owner retries even if a rule is somehow present",
+			owner:      nrptRuleOwnerNone,
+			ruleExists: true,
+			want:       true,
+		},
+		{
+			name:  "ctrld-owned rule removed externally is re-added",
+			owner: nrptRuleOwnerCtrld,
+			want:  true,
+		},
+		{
+			name:       "healthy ctrld-owned rule is left alone",
+			owner:      nrptRuleOwnerCtrld,
+			ruleExists: true,
+			want:       false,
+		},
+		{
+			// Writing beside external policy would be ambiguous policy, not recovery.
+			name:  "external policy is never overwritten",
+			owner: nrptRuleOwnerGroupPolicy,
+			want:  false,
+		},
+		{
+			name:       "external policy is never overwritten even with a ctrld rule present",
+			owner:      nrptRuleOwnerGroupPolicy,
+			ruleExists: true,
+			want:       false,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := nrptNeedsCtrldActivation(tc.owner, tc.ruleExists); got != tc.want {
+				t.Errorf("nrptNeedsCtrldActivation(%v, %v) = %v, want %v", tc.owner, tc.ruleExists, got, tc.want)
+			}
+		})
+	}
+}
+
+// TestActivateCtrldNRPTFallbackRefusedAfterShutdown guards the worst leftover. A
+// catch-all re-added after shutdown points every DNS query on the machine at a listener
+// that no longer exists, so nothing resolves at all. Refusing early also keeps this test
+// from writing NRPT policy on the machine running it.
+func TestActivateCtrldNRPTFallbackRefusedAfterShutdown(t *testing.T) {
+	p, state, f := newInterceptTestProg(t)
+	defer assertNoNRPTSideEffects(t, f)
+	if err := p.stopDNSIntercept(); err != nil {
+		t.Fatalf("stopDNSIntercept() = %v", err)
+	}
+
+	if p.activateCtrldNRPTFallback(state, "ctrld-owned rule missing during health check") {
+		t.Error("activateCtrldNRPTFallback() = true after shutdown: the catch-all would outlive ctrld")
+	}
+	if owner, _ := state.nrptPolicyOwner(); owner != nrptRuleOwnerNone {
+		t.Errorf("NRPT owner = %v after a refused fallback, want nrptRuleOwnerNone", owner)
+	}
+}
+
+// TestAllowHandbackAttemptRateLimits covers the throttle on testing an external
+// catch-all. Each attempt takes ctrld's rule out of the way for a probe, so a rule that
+// never routes would cost a brief DNS outage on every 30s health tick without this - in
+// hard mode a window where WFP blocks DNS and nothing redirects it.
+func TestHandbackThrottleIsPerRule(t *testing.T) {
+	state := &wfpState{stopCh: make(chan struct{})}
+	now := time.Now()
+
+	if !state.handbackAllowed(now, "{GP-RULE}", nrptHandbackRetryInterval) {
+		t.Fatal("first handback attempt must be allowed")
+	}
+	// Checking alone must not spend the budget: a pre-probe can still abort the attempt
+	// without disturbing NRPT, and that must not cost the rule its next window.
+	if !state.handbackAllowed(now, "{GP-RULE}", nrptHandbackRetryInterval) {
+		t.Error("handbackAllowed must not consume the budget by itself")
+	}
+
+	state.recordHandbackAttempt(now, "{GP-RULE}", nrptHandbackRetryInterval)
+	if state.handbackAllowed(now.Add(nrptHandbackRetryInterval-time.Second), "{GP-RULE}", nrptHandbackRetryInterval) {
+		t.Error("re-testing the same rule inside the interval must be suppressed")
+	}
+	// Group Policy alternating between two names must not erase either one's memory:
+	// with a single slot every swap costs another removal of the live rule.
+	if !state.handbackAllowed(now.Add(time.Second), "{OTHER-RULE}", nrptHandbackRetryInterval) {
+		t.Error("a different rule name means the administrator changed policy: test it now")
+	}
+	state.recordHandbackAttempt(now.Add(time.Second), "{OTHER-RULE}", nrptHandbackRetryInterval)
+	if state.handbackAllowed(now.Add(2*time.Second), "{GP-RULE}", nrptHandbackRetryInterval) {
+		t.Error("testing another rule must not clear the first rule's throttle")
+	}
+
+	if !state.handbackAllowed(now.Add(2*nrptHandbackRetryInterval), "{GP-RULE}", nrptHandbackRetryInterval) {
+		t.Error("the same rule must be testable again after the interval")
+	}
+}

cmd/cli/dns_intercept_others.go

@@ -0,0 +1,51 @@
+//go:build !windows && !darwin
+
+package cli
+
+import (
+	"fmt"
+	"time"
+)
+
+// startDNSIntercept is not supported on this platform.
+// DNS intercept mode is only available on Windows (via WFP) and macOS (via pf).
+func (p *prog) startDNSIntercept() error {
+	return fmt.Errorf("dns intercept: not supported on this platform (only Windows and macOS)")
+}
+
+// stopDNSIntercept is a no-op on unsupported platforms.
+func (p *prog) stopDNSIntercept() error {
+	return nil
+}
+
+// skipInitialDNSReset is Windows-only; other platforms keep the normal reset.
+func (p *prog) skipInitialDNSReset() bool { return false }
+
+// exemptVPNDNSServers is a no-op on unsupported platforms.
+func (p *prog) exemptVPNDNSServers(exemptions []vpnDNSExemption) error {
+	return nil
+}
+
+// ensurePFAnchorActive is a no-op on unsupported platforms.
+func (p *prog) ensurePFAnchorActive() pfAnchorCheckResult {
+	return pfAnchorCheckSkipped
+}
+
+// checkTunnelInterfaceChanges is a no-op on unsupported platforms.
+func (p *prog) checkTunnelInterfaceChanges() bool {
+	return false
+}
+
+func (p *prog) dnsInterceptIgnoredChangeReconcileDue(time.Time) bool {
+	return false
+}
+
+// scheduleDelayedRechecks is a no-op on unsupported platforms.
+func (p *prog) scheduleDelayedRechecks() {}
+
+// pfInterceptMonitor is a no-op on unsupported platforms.
+func (p *prog) pfInterceptMonitor() {}
+
+// osHealthcheckSuppressed always returns false on non-Windows platforms —
+// WFP loopback protect (the trigger for suppression) is Windows-only.
+func (p *prog) osHealthcheckSuppressed() bool { return false }

cmd/cli/dns_intercept_settle.go

@@ -0,0 +1,38 @@
+package cli
+
+import "github.com/Control-D-Inc/ctrld"
+
+var initializeOsResolver = ctrld.InitializeOsResolver
+
+func (p *prog) refreshDNSAfterVPNSettle(reason string) (routes, domainlessServers, exemptions int) {
+	mainLog.Load().Info().Msgf("DNS intercept: refreshing OS/VPN DNS route state after VPN settle (%s)", reason)
+	ns := initializeOsResolver(true)
+	mainLog.Load().Debug().Msgf("DNS intercept: post-settle OS resolver nameservers: %v", ns)
+
+	if p.vpnDNS == nil {
+		mainLog.Load().Debug().Msg("DNS intercept: post-settle VPN DNS route refresh skipped — manager unavailable")
+		return 0, 0, 0
+	}
+
+	routes, domainlessServers, exemptions = p.vpnDNS.RefreshRoutesOnly()
+	mainLog.Load().Info().Msgf("DNS intercept: post-settle VPN DNS route refresh completed — %d routes, %d domainless servers, %d exemptions",
+		routes, domainlessServers, exemptions)
+	return routes, domainlessServers, exemptions
+}
+
+func vpnDNSExemptionsEqual(a, b []vpnDNSExemption) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	seen := make(map[vpnDNSExemption]int, len(a))
+	for _, ex := range a {
+		seen[ex]++
+	}
+	for _, ex := range b {
+		if seen[ex] == 0 {
+			return false
+		}
+		seen[ex]--
+	}
+	return true
+}

cmd/cli/dns_intercept_settle_test.go

@@ -0,0 +1,54 @@
+package cli
+
+import (
+	"context"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestRefreshDNSAfterVPNSettleRefreshesOSResolverAndVPNRoutes(t *testing.T) {
+	oldInitialize := initializeOsResolver
+	defer func() { initializeOsResolver = oldInitialize }()
+
+	var initialized []bool
+	initializeOsResolver = func(force bool) []string {
+		initialized = append(initialized, force)
+		return []string{"10.102.26.10:53"}
+	}
+
+	var exemptionUpdates [][]vpnDNSExemption
+	p := &prog{}
+	p.vpnDNS = newVPNDNSManager(func(exemptions []vpnDNSExemption) error {
+		exemptionUpdates = append(exemptionUpdates, append([]vpnDNSExemption{}, exemptions...))
+		return nil
+	})
+	p.vpnDNS.discoverVPNDNS = func(context.Context) []ctrld.VPNDNSConfig {
+		return []ctrld.VPNDNSConfig{{
+			InterfaceName: "utun4",
+			Servers:       []string{"10.102.26.10"},
+			Domains:       []string{"bmwgroup.net"},
+		}}
+	}
+
+	routes, domainlessServers, exemptions := p.refreshDNSAfterVPNSettle("test")
+
+	if routes != 1 || domainlessServers != 0 || exemptions != 1 {
+		t.Fatalf("expected 1 route, 0 domainless servers, 1 exemption, got routes=%d domainless=%d exemptions=%d",
+			routes, domainlessServers, exemptions)
+	}
+	if len(initialized) != 1 || !initialized[0] {
+		t.Fatalf("expected forced OS resolver refresh once, got %v", initialized)
+	}
+	if got := p.vpnDNS.UpstreamForDomain("jira.cc.bmwgroup.net."); len(got) != 1 || got[0] != "10.102.26.10" {
+		t.Fatalf("expected refreshed VPN DNS route, got %v", got)
+	}
+	if len(exemptionUpdates) != 1 || len(exemptionUpdates[0]) != 1 || exemptionUpdates[0][0].Server != "10.102.26.10" {
+		t.Fatalf("expected one serialized pf exemption update for the late VPN DNS server, got %+v", exemptionUpdates)
+	}
+
+	p.refreshDNSAfterVPNSettle("test-repeat")
+	if len(exemptionUpdates) != 1 {
+		t.Fatalf("unchanged post-settle VPN DNS state rewrote pf: %+v", exemptionUpdates)
+	}
+}

cmd/cli/dns_proxy_test.go

@@ -0,0 +1,513 @@
+package cli
+
+import (
+	"context"
+	"net"
+	"testing"
+	"time"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/Control-D-Inc/ctrld"
+	"github.com/Control-D-Inc/ctrld/internal/dnscache"
+	"github.com/Control-D-Inc/ctrld/testhelper"
+)
+
+func Test_wildcardMatches(t *testing.T) {
+	tests := []struct {
+		name     string
+		wildcard string
+		domain   string
+		match    bool
+	}{
+		{"domain - prefix parent should not match", "*.example.com", "example.com", false},
+		{"domain - prefix", "*.example.com", "anything.example.com", true},
+		{"domain - prefix not match other s", "*.example.com", "other.org", false},
+		{"domain - prefix not match s in name", "*.example.com", "eexample.com", false},
+		{"domain - suffix", "suffix.*", "suffix.example.com", true},
+		{"domain - suffix not match other", "suffix.*", "suffix1.example.com", false},
+		{"domain - both", "suffix.*.example.com", "suffix.anything.example.com", true},
+		{"domain - both not match", "suffix.*.example.com", "suffix1.suffix.example.com", false},
+		{"domain - case-insensitive", "*.EXAMPLE.com", "anything.example.com", true},
+		{"mac - prefix", "*:98:05:b4:2b", "d4:67:98:05:b4:2b", true},
+		{"mac - prefix not match other s", "*:98:05:b4:2b", "0d:ba:54:09:94:2c", false},
+		{"mac - prefix not match s in name", "*:98:05:b4:2b", "e4:67:97:05:b4:2b", false},
+		{"mac - suffix", "d4:67:98:*", "d4:67:98:05:b4:2b", true},
+		{"mac - suffix not match other", "d4:67:98:*", "d4:67:97:15:b4:2b", false},
+		{"mac - both", "d4:67:98:*:b4:2b", "d4:67:98:05:b4:2b", true},
+		{"mac - both not match", "d4:67:98:*:b4:2b", "d4:67:97:05:c4:2b", false},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := wildcardMatches(tc.wildcard, tc.domain); got != tc.match {
+				t.Errorf("unexpected result, wildcard: %s, domain: %s, want: %v, got: %v", tc.wildcard, tc.domain, tc.match, got)
+			}
+		})
+	}
+}
+
+func Test_canonicalName(t *testing.T) {
+	tests := []struct {
+		name      string
+		domain    string
+		canonical string
+	}{
+		{"fqdn to canonical", "example.com.", "example.com"},
+		{"already canonical", "example.com", "example.com"},
+		{"case insensitive", "Example.Com.", "example.com"},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := canonicalName(tc.domain); got != tc.canonical {
+				t.Errorf("unexpected result, want: %s, got: %s", tc.canonical, got)
+			}
+		})
+	}
+}
+
+func Test_prog_upstreamFor(t *testing.T) {
+	cfg := testhelper.SampleConfig(t)
+	cfg.Service.LeakOnUpstreamFailure = func(v bool) *bool { return &v }(false)
+	p := &prog{cfg: cfg}
+	p.um = newUpstreamMonitor(p.cfg)
+	p.lanLoopGuard = newLoopGuard()
+	p.ptrLoopGuard = newLoopGuard()
+	for _, nc := range p.cfg.Network {
+		for _, cidr := range nc.Cidrs {
+			_, ipNet, err := net.ParseCIDR(cidr)
+			if err != nil {
+				t.Fatal(err)
+			}
+			nc.IPNets = append(nc.IPNets, ipNet)
+		}
+	}
+
+	tests := []struct {
+		name               string
+		ip                 string
+		mac                string
+		defaultUpstreamNum string
+		lc                 *ctrld.ListenerConfig
+		domain             string
+		upstreams          []string
+		matched            bool
+		testLogMsg         string
+	}{
+		{"Policy map matches", "192.168.0.1:0", "", "0", p.cfg.Listener["0"], "abc.xyz", []string{"upstream.1", "upstream.0"}, true, ""},
+		{"Policy split matches", "192.168.0.1:0", "", "0", p.cfg.Listener["0"], "abc.ru", []string{"upstream.1"}, true, ""},
+		{"Policy map for other network matches", "192.168.1.2:0", "", "0", p.cfg.Listener["0"], "abc.xyz", []string{"upstream.0"}, true, ""},
+		{"No policy map for listener", "192.168.1.2:0", "", "1", p.cfg.Listener["1"], "abc.ru", []string{"upstream.1"}, false, ""},
+		{"unenforced loging", "192.168.1.2:0", "", "0", p.cfg.Listener["0"], "abc.ru", []string{"upstream.1"}, true, "My Policy, network.1 (unenforced), *.ru -> [upstream.1]"},
+		{"Policy Macs matches upper", "192.168.0.1:0", "14:45:A0:67:83:0A", "0", p.cfg.Listener["0"], "abc.xyz", []string{"upstream.2"}, true, "14:45:a0:67:83:0a"},
+		{"Policy Macs matches lower", "192.168.0.1:0", "14:54:4a:8e:08:2d", "0", p.cfg.Listener["0"], "abc.xyz", []string{"upstream.2"}, true, "14:54:4a:8e:08:2d"},
+		{"Policy Macs matches case-insensitive", "192.168.0.1:0", "14:54:4A:8E:08:2D", "0", p.cfg.Listener["0"], "abc.xyz", []string{"upstream.2"}, true, "14:54:4a:8e:08:2d"},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			for _, network := range []string{"udp", "tcp"} {
+				var (
+					addr net.Addr
+					err  error
+				)
+				switch network {
+				case "udp":
+					addr, err = net.ResolveUDPAddr(network, tc.ip)
+				case "tcp":
+					addr, err = net.ResolveTCPAddr(network, tc.ip)
+				}
+				require.NoError(t, err)
+				require.NotNil(t, addr)
+				ctx := context.WithValue(context.Background(), ctrld.ReqIdCtxKey{}, requestID())
+				ufr := p.upstreamFor(ctx, tc.defaultUpstreamNum, tc.lc, addr, tc.mac, tc.domain)
+				p.proxy(ctx, &proxyRequest{
+					msg: newDnsMsgWithHostname("foo", dns.TypeA),
+					ufr: ufr,
+				})
+				assert.Equal(t, tc.matched, ufr.matched)
+				assert.Equal(t, tc.upstreams, ufr.upstreams)
+				if tc.testLogMsg != "" {
+					assert.Contains(t, logOutput.String(), tc.testLogMsg)
+				}
+			}
+		})
+	}
+}
+
+func TestCache(t *testing.T) {
+	cfg := testhelper.SampleConfig(t)
+	prog := &prog{cfg: cfg}
+	for _, nc := range prog.cfg.Network {
+		for _, cidr := range nc.Cidrs {
+			_, ipNet, err := net.ParseCIDR(cidr)
+			if err != nil {
+				t.Fatal(err)
+			}
+			nc.IPNets = append(nc.IPNets, ipNet)
+		}
+	}
+	cacher, err := dnscache.NewLRUCache(4096)
+	require.NoError(t, err)
+	prog.cache = cacher
+
+	msg := new(dns.Msg)
+	msg.SetQuestion("example.com", dns.TypeA)
+	msg.MsgHdr.RecursionDesired = true
+	answer1 := new(dns.Msg)
+	answer1.SetRcode(msg, dns.RcodeSuccess)
+
+	prog.cache.Add(dnscache.NewKey(msg, "upstream.1"), dnscache.NewValue(answer1, time.Now().Add(time.Minute)))
+	answer2 := new(dns.Msg)
+	answer2.SetRcode(msg, dns.RcodeRefused)
+	prog.cache.Add(dnscache.NewKey(msg, "upstream.0"), dnscache.NewValue(answer2, time.Now().Add(time.Minute)))
+
+	req1 := &proxyRequest{
+		msg:            msg,
+		ci:             nil,
+		failoverRcodes: nil,
+		ufr: &upstreamForResult{
+			upstreams:      []string{"upstream.1"},
+			matchedPolicy:  "",
+			matchedNetwork: "",
+			matchedRule:    "",
+			matched:        false,
+		},
+	}
+	req2 := &proxyRequest{
+		msg:            msg,
+		ci:             nil,
+		failoverRcodes: nil,
+		ufr: &upstreamForResult{
+			upstreams:      []string{"upstream.0"},
+			matchedPolicy:  "",
+			matchedNetwork: "",
+			matchedRule:    "",
+			matched:        false,
+		},
+	}
+	got1 := prog.proxy(context.Background(), req1)
+	got2 := prog.proxy(context.Background(), req2)
+	assert.NotSame(t, got1, got2)
+	assert.Equal(t, answer1.Rcode, got1.answer.Rcode)
+	assert.Equal(t, answer2.Rcode, got2.answer.Rcode)
+}
+
+func Test_ipAndMacFromMsg(t *testing.T) {
+	tests := []struct {
+		name    string
+		ip      string
+		wantIp  bool
+		mac     string
+		wantMac bool
+	}{
+		{"has ip v4 and mac", "1.2.3.4", true, "4c:20:b8:ab:87:1b", true},
+		{"has ip v6 and mac", "2606:1a40:3::1", true, "4c:20:b8:ab:87:1b", true},
+		{"no ip", "1.2.3.4", false, "4c:20:b8:ab:87:1b", false},
+		{"no mac", "1.2.3.4", false, "4c:20:b8:ab:87:1b", false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			ip := net.ParseIP(tc.ip)
+			if ip == nil {
+				t.Fatal("missing IP")
+			}
+			hw, err := net.ParseMAC(tc.mac)
+			if err != nil {
+				t.Fatal(err)
+			}
+			m := new(dns.Msg)
+			m.SetQuestion("example.com.", dns.TypeA)
+			o := &dns.OPT{Hdr: dns.RR_Header{Name: ".", Rrtype: dns.TypeOPT}}
+			if tc.wantMac {
+				ec1 := &dns.EDNS0_LOCAL{Code: EDNS0_OPTION_MAC, Data: hw}
+				o.Option = append(o.Option, ec1)
+			}
+			if tc.wantIp {
+				ec2 := &dns.EDNS0_SUBNET{Address: ip}
+				o.Option = append(o.Option, ec2)
+			}
+			m.Extra = append(m.Extra, o)
+			gotIP, gotMac := ipAndMacFromMsg(m)
+			if tc.wantMac && gotMac != tc.mac {
+				t.Errorf("mismatch, want: %q, got: %q", tc.mac, gotMac)
+			}
+			if !tc.wantMac && gotMac != "" {
+				t.Errorf("unexpected mac: %q", gotMac)
+			}
+			if tc.wantIp && gotIP != tc.ip {
+				t.Errorf("mismatch, want: %q, got: %q", tc.ip, gotIP)
+			}
+			if !tc.wantIp && gotIP != "" {
+				t.Errorf("unexpected ip: %q", gotIP)
+			}
+		})
+	}
+}
+
+func Test_remoteAddrFromMsg(t *testing.T) {
+	loopbackIP := net.ParseIP("127.0.0.1")
+	tests := []struct {
+		name string
+		addr net.Addr
+		ci   *ctrld.ClientInfo
+		want string
+	}{
+		{"tcp", &net.TCPAddr{IP: loopbackIP, Port: 12345}, &ctrld.ClientInfo{IP: "192.168.1.10"}, "192.168.1.10:12345"},
+		{"udp", &net.UDPAddr{IP: loopbackIP, Port: 12345}, &ctrld.ClientInfo{IP: "192.168.1.11"}, "192.168.1.11:12345"},
+		{"nil client info", &net.UDPAddr{IP: loopbackIP, Port: 12345}, nil, "127.0.0.1:12345"},
+		{"empty ip", &net.UDPAddr{IP: loopbackIP, Port: 12345}, &ctrld.ClientInfo{}, "127.0.0.1:12345"},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			addr := spoofRemoteAddr(tc.addr, tc.ci)
+			if addr.String() != tc.want {
+				t.Errorf("unexpected result, want: %q, got: %q", tc.want, addr.String())
+			}
+		})
+	}
+}
+
+func Test_ipFromARPA(t *testing.T) {
+	tests := []struct {
+		IP   string
+		ARPA string
+	}{
+		{"1.2.3.4", "4.3.2.1.in-addr.arpa."},
+		{"245.110.36.114", "114.36.110.245.in-addr.arpa."},
+		{"::ffff:12.34.56.78", "78.56.34.12.in-addr.arpa."},
+		{"::1", "1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.ip6.arpa."},
+		{"1::", "0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.1.0.0.0.ip6.arpa."},
+		{"1234:567::89a:bcde", "e.d.c.b.a.9.8.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.7.6.5.0.4.3.2.1.ip6.arpa."},
+		{"1234:567:fefe:bcbc:adad:9e4a:89a:bcde", "e.d.c.b.a.9.8.0.a.4.e.9.d.a.d.a.c.b.c.b.e.f.e.f.7.6.5.0.4.3.2.1.ip6.arpa."},
+		{"", "asd.in-addr.arpa."},
+		{"", "asd.ip6.arpa."},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.IP, func(t *testing.T) {
+			t.Parallel()
+			if got := ipFromARPA(tc.ARPA); !got.Equal(net.ParseIP(tc.IP)) {
+				t.Errorf("unexpected ip, want: %s, got: %s", tc.IP, got)
+			}
+		})
+	}
+}
+
+func newDnsMsgWithClientIP(ip string) *dns.Msg {
+	m := new(dns.Msg)
+	m.SetQuestion("example.com.", dns.TypeA)
+	o := &dns.OPT{Hdr: dns.RR_Header{Name: ".", Rrtype: dns.TypeOPT}}
+	o.Option = append(o.Option, &dns.EDNS0_SUBNET{Address: net.ParseIP(ip)})
+	m.Extra = append(m.Extra, o)
+	return m
+}
+
+func Test_stripClientSubnet(t *testing.T) {
+	tests := []struct {
+		name       string
+		msg        *dns.Msg
+		wantSubnet bool
+	}{
+		{"no edns0", new(dns.Msg), false},
+		{"loopback IP v4", newDnsMsgWithClientIP("127.0.0.1"), false},
+		{"loopback IP v6", newDnsMsgWithClientIP("::1"), false},
+		{"private IP v4", newDnsMsgWithClientIP("192.168.1.123"), false},
+		{"private IP v6", newDnsMsgWithClientIP("fd12:3456:789a:1::1"), false},
+		{"public IP", newDnsMsgWithClientIP("1.1.1.1"), true},
+		{"invalid IP", newDnsMsgWithClientIP(""), true},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			stripClientSubnet(tc.msg)
+			hasSubnet := false
+			if opt := tc.msg.IsEdns0(); opt != nil {
+				for _, s := range opt.Option {
+					if _, ok := s.(*dns.EDNS0_SUBNET); ok {
+						hasSubnet = true
+					}
+				}
+			}
+			if tc.wantSubnet != hasSubnet {
+				t.Errorf("unexpected result, want: %v, got: %v", tc.wantSubnet, hasSubnet)
+			}
+		})
+	}
+}
+
+func newDnsMsgWithHostname(hostname string, typ uint16) *dns.Msg {
+	m := new(dns.Msg)
+	m.SetQuestion(hostname, typ)
+	return m
+}
+
+func Test_isLanHostnameQuery(t *testing.T) {
+	tests := []struct {
+		name               string
+		msg                *dns.Msg
+		isLanHostnameQuery bool
+	}{
+		{"A", newDnsMsgWithHostname("foo", dns.TypeA), true},
+		{"AAAA", newDnsMsgWithHostname("foo", dns.TypeAAAA), true},
+		{"A not LAN", newDnsMsgWithHostname("example.com", dns.TypeA), false},
+		{"AAAA not LAN", newDnsMsgWithHostname("example.com", dns.TypeAAAA), false},
+		{"Not A or AAAA", newDnsMsgWithHostname("foo", dns.TypeTXT), false},
+		{".domain", newDnsMsgWithHostname("foo.domain", dns.TypeA), true},
+		{".lan", newDnsMsgWithHostname("foo.lan", dns.TypeA), true},
+		{".local", newDnsMsgWithHostname("foo.local", dns.TypeA), true},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := isLanHostnameQuery(tc.msg); tc.isLanHostnameQuery != got {
+				t.Errorf("unexpected result, want: %v, got: %v", tc.isLanHostnameQuery, got)
+			}
+		})
+	}
+}
+
+func newDnsMsgPtr(ip string, t *testing.T) *dns.Msg {
+	t.Helper()
+	m := new(dns.Msg)
+	ptr, err := dns.ReverseAddr(ip)
+	if err != nil {
+		t.Fatal(err)
+	}
+	m.SetQuestion(ptr, dns.TypePTR)
+	return m
+}
+
+func Test_isPrivatePtrLookup(t *testing.T) {
+	tests := []struct {
+		name               string
+		msg                *dns.Msg
+		isPrivatePtrLookup bool
+	}{
+		// RFC 1918 allocates 10.0.0.0/8, 172.16.0.0/12, and 192.168.0.0/16 as
+		{"10.0.0.0/8", newDnsMsgPtr("10.0.0.123", t), true},
+		{"172.16.0.0/12", newDnsMsgPtr("172.16.0.123", t), true},
+		{"192.168.0.0/16", newDnsMsgPtr("192.168.1.123", t), true},
+		{"CGNAT", newDnsMsgPtr("100.66.27.28", t), true},
+		{"Loopback", newDnsMsgPtr("127.0.0.1", t), true},
+		{"Link Local Unicast", newDnsMsgPtr("fe80::69f6:e16e:8bdb:433f", t), true},
+		// RFC 7335 IPv4 Service Continuity Prefix (464XLAT/DS-Lite CLAT), see #552.
+		{"464XLAT CLAT host", newDnsMsgPtr("192.0.0.2", t), true},
+		{"Public IP", newDnsMsgPtr("8.8.8.8", t), false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := isPrivatePtrLookup(tc.msg); tc.isPrivatePtrLookup != got {
+				t.Errorf("unexpected result, want: %v, got: %v", tc.isPrivatePtrLookup, got)
+			}
+		})
+	}
+}
+
+func Test_isSrvLanLookup(t *testing.T) {
+	tests := []struct {
+		name        string
+		msg         *dns.Msg
+		isSrvLookup bool
+	}{
+		{"SRV LAN", newDnsMsgWithHostname("foo", dns.TypeSRV), true},
+		{"Not SRV", newDnsMsgWithHostname("foo", dns.TypeNone), false},
+		{"Not SRV LAN", newDnsMsgWithHostname("controld.com", dns.TypeSRV), false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := isSrvLanLookup(tc.msg); tc.isSrvLookup != got {
+				t.Errorf("unexpected result, want: %v, got: %v", tc.isSrvLookup, got)
+			}
+		})
+	}
+}
+
+func Test_isWanClient(t *testing.T) {
+	tests := []struct {
+		name        string
+		addr        net.Addr
+		isWanClient bool
+	}{
+		// RFC 1918 allocates 10.0.0.0/8, 172.16.0.0/12, and 192.168.0.0/16 as
+		{"10.0.0.0/8", &net.UDPAddr{IP: net.ParseIP("10.0.0.123")}, false},
+		{"172.16.0.0/12", &net.UDPAddr{IP: net.ParseIP("172.16.0.123")}, false},
+		{"192.168.0.0/16", &net.UDPAddr{IP: net.ParseIP("192.168.1.123")}, false},
+		{"CGNAT", &net.UDPAddr{IP: net.ParseIP("100.66.27.28")}, false},
+		{"Loopback", &net.UDPAddr{IP: net.ParseIP("127.0.0.1")}, false},
+		{"Link Local Unicast", &net.UDPAddr{IP: net.ParseIP("fe80::69f6:e16e:8bdb:433f")}, false},
+		// RFC 7335 IPv4 Service Continuity Prefix (464XLAT/DS-Lite CLAT), see #552.
+		{"464XLAT PLAT side", &net.UDPAddr{IP: net.ParseIP("192.0.0.1")}, false},
+		{"464XLAT CLAT host", &net.UDPAddr{IP: net.ParseIP("192.0.0.2")}, false},
+		// Outside the /29 but inside 192.0.0.0/24: still WAN (fix is scoped to /29).
+		{"192.0.0.0/24 outside /29", &net.UDPAddr{IP: net.ParseIP("192.0.0.100")}, true},
+		{"Public", &net.UDPAddr{IP: net.ParseIP("8.8.8.8")}, true},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			t.Parallel()
+			if got := isWanClient(tc.addr); tc.isWanClient != got {
+				t.Errorf("unexpected result, want: %v, got: %v", tc.isWanClient, got)
+			}
+		})
+	}
+}
+
+func Test_prog_queryFromSelf(t *testing.T) {
+	p := &prog{}
+	require.NotPanics(t, func() {
+		p.queryFromSelf("")
+	})
+	require.NotPanics(t, func() {
+		p.queryFromSelf("foo")
+	})
+}
+
+func Test_sameQuestion(t *testing.T) {
+	mk := func(name string, qtype uint16) *dns.Msg {
+		m := new(dns.Msg)
+		m.SetQuestion(name, qtype)
+		return m
+	}
+	tests := []struct {
+		name   string
+		req    *dns.Msg
+		answer *dns.Msg
+		want   bool
+	}{
+		{"identical", mk("example.com.", dns.TypeA), mk("example.com.", dns.TypeA), true},
+		{"case insensitive", mk("Example.COM.", dns.TypeA), mk("example.com.", dns.TypeA), true},
+		{"different name", mk("victim.example.", dns.TypeA), mk("attacker.example.", dns.TypeA), false},
+		{"different type", mk("example.com.", dns.TypeA), mk("example.com.", dns.TypeAAAA), false},
+		{"nil req", nil, mk("example.com.", dns.TypeA), false},
+		{"nil answer", mk("example.com.", dns.TypeA), nil, false},
+		{"empty answer question", mk("example.com.", dns.TypeA), new(dns.Msg), false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			if got := sameQuestion(tc.req, tc.answer); got != tc.want {
+				t.Errorf("sameQuestion() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}

cmd/cli/dns_target.go

@@ -0,0 +1,116 @@
+package cli
+
+import "net"
+
+// interceptDNSRdrTarget is the loopback address used as the macOS service
+// DNS value when ctrld's listener is NOT reachable at <listener IP>:53
+// directly (non-53 port, e.g. 127.0.0.1:5354 when mDNSResponder holds *:53).
+//
+// macOS resolvers always send DNS to port 53, so a direct-hit value is
+// impossible in that case; delivery must go through the pf rdr rule
+// ("rdr on lo0 ... to ! <listenerIP> port 53 -> <listenerIP> port <port>").
+// The value therefore must be a loopback address DIFFERENT from the listener
+// IP so the rdr's "! <listenerIP>" matches. Any 127/8 address routes via lo0
+// on macOS.
+const interceptDNSRdrTarget = "127.0.0.53"
+
+// interceptDNSTargetValue returns the nameserver value to set on a DNS-less
+// macOS service so the OS emits DNS queries that reach ctrld, respecting the
+// configured listener. The listener IP/port derivation mirrors
+// buildPFAnchorRulesForTunnels so the value and the pf rules always agree.
+//
+//   - listener on port 53: return the effective listener IP — queries hit the
+//     listener directly, no pf dependency for this leg.
+//   - listener on another port: return interceptDNSRdrTarget so the lo0 rdr
+//     rule fires and rewrites to the real listener address.
+func (p *prog) interceptDNSTargetValue() string {
+	listenerIP := "127.0.0.1"
+	listenerPort := 53
+	// FirstListener panics when no listener is configured; guard like the
+	// startup paths do.
+	if p.cfg != nil && len(p.cfg.Listener) > 0 {
+		if lc := p.cfg.FirstListener(); lc != nil {
+			if lc.IP != "" && lc.IP != "0.0.0.0" && lc.IP != "::" {
+				listenerIP = lc.IP
+			}
+			if lc.Port != 0 {
+				listenerPort = lc.Port
+			}
+		}
+	}
+	if listenerPort == 53 {
+		return listenerIP
+	}
+	if listenerIP == interceptDNSRdrTarget {
+		// Pathological config: the listener itself sits on the rdr target
+		// address (with a non-53 port). Pick a different loopback so the
+		// rdr's "! <listenerIP>" still matches.
+		return "127.0.0.54"
+	}
+	return interceptDNSRdrTarget
+}
+
+// hasIPv4DNS reports whether any of the given nameserver strings (bare IPs or
+// host:port) is an IPv4 address. Loopback counts: an existing local resolver
+// is treated conservatively as an intentional emittable DNS target; ctrld does
+// not probe or replace another resolver's ownership.
+func hasIPv4DNS(nameservers []string) bool {
+	for _, s := range nameservers {
+		host := s
+		if h, _, err := net.SplitHostPort(s); err == nil {
+			host = h
+		}
+		ip := net.ParseIP(host)
+		if ip == nil {
+			continue
+		}
+		if ip.To4() != nil {
+			return true
+		}
+	}
+	return false
+}
+
+// needsInterceptDNSTarget reports whether the OS is left without any usable
+// IPv4 DNS target: neither the default-route service's static DNS nor the
+// discovered (DHCP/scutil) nameservers contain an IPv4 address.
+//
+// IPv6-only DNS is not usable under DNS intercept mode on macOS: the pf
+// ruleset blocks all outbound IPv6 port-53 traffic (IPv6 interception is not
+// supported, see issues #507/#533), and with no IPv4 DNS configured
+// mDNSResponder emits no DNS packets at all — leaving pf nothing to
+// intercept despite a healthy upstream. Observed in production on IPv6-only
+// iPhone tethering with 464XLAT (issue #533).
+func needsInterceptDNSTarget(staticDNS, discovered []string) bool {
+	return !hasIPv4DNS(staticDNS) && !hasIPv4DNS(discovered)
+}
+
+// isInterceptDNSTargetOnly reports whether the given static DNS list is
+// exactly the entry ctrld set via ensureInterceptDNSTarget (recorded in
+// target), meaning it is safe for ctrld to remove.
+func isInterceptDNSTargetOnly(nameservers []string, target string) bool {
+	return target != "" && len(nameservers) == 1 && nameservers[0] == target
+}
+
+// filterOwnTarget returns nameservers with ctrld's own recorded target
+// removed. A previously-set target must never be mistaken for user/network
+// IPv4 DNS when judging whether the network still needs one — otherwise the
+// second recovery on the same DNS-less network would see "IPv4 DNS present"
+// and remove the entry, and the third would re-add it, oscillating on every
+// recovery.
+func filterOwnTarget(nameservers []string, target string) []string {
+	if target == "" {
+		return nameservers
+	}
+	out := nameservers[:0:0]
+	for _, s := range nameservers {
+		host := s
+		if h, _, err := net.SplitHostPort(s); err == nil {
+			host = h
+		}
+		if host != target {
+			out = append(out, s)
+		}
+	}
+	return out
+}

cmd/cli/dns_target_darwin.go

@@ -0,0 +1,234 @@
+//go:build darwin
+
+package cli
+
+import (
+	"encoding/json"
+	"net"
+	"os"
+
+	"tailscale.com/net/netmon"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// interceptDNSTargetStateFile persists which service/value ctrld set, so a
+// daemon restart (crash, upgrade, plain restart) does not orphan the entry:
+// without it a restarted daemon would not know the entry is ctrld's own and
+// could neither remove it on shutdown nor keep its bookkeeping consistent.
+const interceptDNSTargetStateFile = ".intercept_dns_target"
+
+var (
+	interceptDNSTargetStatePathFn          = func() string { return absHomeDir(interceptDNSTargetStateFile) }
+	interceptDefaultRouteInterfaceFn       = netmon.DefaultRouteInterface
+	interceptInterfaceByNameFn             = net.InterfaceByName
+	interceptPatchNetIfaceNameFn           = patchNetIfaceName
+	interceptCurrentStaticDNSFn            = currentStaticDNS
+	interceptSaveCurrentStaticDNSFn        = saveCurrentStaticDNS
+	interceptSetDNSFn                      = setDNS
+	interceptSavedStaticNameserversFn      = savedStaticNameservers
+	interceptResetDNSIgnoreUnusableIfaceFn = resetDnsIgnoreUnusableInterface
+	interceptDHCPNameserversForInterfaceFn = ctrld.DHCPNameserversForInterface
+)
+
+type interceptDNSTargetState struct {
+	Service string `json:"service"`
+	Value   string `json:"value"`
+}
+
+// loadInterceptDNSTargetStateLocked hydrates in-memory tracking from the
+// state file once (only when memory is empty). Callers must hold
+// interceptDNSTargetMu.
+func (p *prog) loadInterceptDNSTargetStateLocked() {
+	if p.interceptDNSTargetService != "" || p.interceptDNSTargetLoaded {
+		return
+	}
+	p.interceptDNSTargetLoaded = true
+	data, err := os.ReadFile(interceptDNSTargetStatePathFn())
+	if err != nil {
+		return
+	}
+	var st interceptDNSTargetState
+	if err := json.Unmarshal(data, &st); err != nil || st.Service == "" || st.Value == "" {
+		return
+	}
+	p.interceptDNSTargetService = st.Service
+	p.interceptDNSTargetSetValue = st.Value
+	mainLog.Load().Debug().Msgf("intercept DNS target: restored tracking of %s on %q from previous run", st.Value, st.Service)
+}
+
+// persistInterceptDNSTargetStateLocked writes (or clears) the state file to
+// match in-memory tracking. Callers must hold interceptDNSTargetMu.
+func (p *prog) persistInterceptDNSTargetStateLocked() {
+	file := interceptDNSTargetStatePathFn()
+	if p.interceptDNSTargetService == "" {
+		_ = os.Remove(file)
+		return
+	}
+	data, err := json.Marshal(interceptDNSTargetState{Service: p.interceptDNSTargetService, Value: p.interceptDNSTargetSetValue})
+	if err != nil {
+		return
+	}
+	if err := os.WriteFile(file, data, 0600); err != nil {
+		mainLog.Load().Debug().Err(err).Msg("intercept DNS target: could not persist state file")
+	}
+}
+
+// ensureInterceptDNSTarget guarantees macOS always has an emittable DNS
+// target while DNS intercept mode is active.
+//
+// Intercept mode deliberately never manages interface DNS: pf redirects DNS
+// packets in flight. But pf can only redirect packets macOS actually sends,
+// and mDNSResponder emits none when the active network service has no DNS
+// configured. IPv6-only networks (e.g. iPhone tethering with 464XLAT) supply
+// no IPv4 DNS, and the pf ruleset blocks all outbound IPv6 port 53, so such
+// networks otherwise end in a total DNS outage with a healthy upstream
+// (issue #533).
+//
+// Only when the default-route service has no usable IPv4 DNS at all does
+// ctrld set a loopback DNS value on it — chosen by interceptDNSTargetValue to
+// respect the configured listener: the listener IP directly when it serves
+// port 53, else a distinct loopback address so the pf lo0 rdr rule rewrites
+// to the listener's real port. The entry is removed when the network regains
+// IPv4 DNS and on intercept shutdown. Networks that provide IPv4 DNS are
+// never modified.
+//
+// Callers pass a non-nil raw system discovery result to prove discovery ran;
+// an empty slice is a valid DNS-less result. The decision itself uses static
+// DNS plus DHCP option 6 from the default-route interface, so resolvers on a
+// second physical interface cannot suppress the target. Invoked during
+// startup, debounced network recovery, and periodic pf watchdog reconciliation.
+func (p *prog) ensureInterceptDNSTarget(systemDiscovery []string) {
+	if !dnsIntercept || p.dnsInterceptState == nil {
+		return
+	}
+	if systemDiscovery == nil {
+		mainLog.Load().Debug().Msg("intercept DNS target: system DNS discovery was not performed; not changing DNS")
+		return
+	}
+	p.interceptDNSTargetMu.Lock()
+	defer p.interceptDNSTargetMu.Unlock()
+	p.loadInterceptDNSTargetStateLocked()
+
+	drIfaceName, err := interceptDefaultRouteInterfaceFn()
+	if err != nil || drIfaceName == "" {
+		// Mid-transition with no default route; the next recovery decides.
+		return
+	}
+	iface, err := interceptInterfaceByNameFn(drIfaceName)
+	if err != nil || iface == nil {
+		return
+	}
+	// Resolve the network service name (e.g. en5 -> "iPhone USB") so
+	// networksetup operates on the right service.
+	if _, err := interceptPatchNetIfaceNameFn(iface); err != nil {
+		mainLog.Load().Debug().Err(err).Msgf("intercept DNS target: could not resolve network service for %s", drIfaceName)
+		return
+	}
+
+	staticDNS, err := interceptCurrentStaticDNSFn(iface)
+	if err != nil {
+		// Interfaces without a network service (utun/VPN tunnels) land here:
+		// networksetup cannot address them, ctrld never writes to them, and
+		// any target set on the underlying physical service stays in place —
+		// still correct while ctrld runs.
+		mainLog.Load().Debug().Err(err).Msgf("intercept DNS target: could not read static DNS for %q", iface.Name)
+		return
+	}
+	// Never count ctrld's own previously-set entry as network-provided DNS,
+	// or the next recovery on the same DNS-less network would remove it and
+	// the one after re-add it.
+	if p.interceptDNSTargetService == iface.Name {
+		staticDNS = filterOwnTarget(staticDNS, p.interceptDNSTargetSetValue)
+	}
+	if hasIPv4DNS(staticDNS) {
+		p.removeInterceptDNSTargetLocked("network has usable static IPv4 DNS")
+		return
+	}
+
+	routeDHCPDNS, err := interceptDHCPNameserversForInterfaceFn(drIfaceName)
+	if err != nil {
+		mainLog.Load().Debug().Err(err).Msgf("intercept DNS target: could not read DHCP DNS for default-route service %q", iface.Name)
+		return
+	}
+	if hasIPv4DNS(routeDHCPDNS) {
+		// The default-route service regained DHCP option 6. Remove a target
+		// previously set on this or another service.
+		p.removeInterceptDNSTargetLocked("network has usable DHCP IPv4 DNS")
+		return
+	}
+
+	target := p.interceptDNSTargetValue()
+	if p.interceptDNSTargetService == iface.Name && p.interceptDNSTargetSetValue == target {
+		return // already set on this service
+	}
+	// Default route moved to a different DNS-less service (or the listener
+	// config changed): clear the stale entry first.
+	p.removeInterceptDNSTargetLocked("default route service changed")
+
+	// Preserve any existing (IPv6-only) static entries for later restore.
+	// saveCurrentStaticDNS filters loopback on write, and
+	// savedStaticNameservers filters loopback on read, so ctrld's own
+	// loopback target can never be recorded or restored as user DNS.
+	if err := interceptSaveCurrentStaticDNSFn(iface); err != nil {
+		mainLog.Load().Debug().Err(err).Msgf("intercept DNS target: could not save static DNS for %q", iface.Name)
+	}
+	if err := interceptSetDNSFn(iface, []string{target}); err != nil {
+		mainLog.Load().Warn().Err(err).Msgf("intercept DNS target: could not set %s on %q", target, iface.Name)
+		return
+	}
+	p.interceptDNSTargetService = iface.Name
+	p.interceptDNSTargetSetValue = target
+	p.persistInterceptDNSTargetStateLocked()
+	mainLog.Load().Warn().Msgf("intercept DNS target: service %q provides no usable IPv4 DNS; set %s so macOS can emit DNS queries (removed automatically when the network provides IPv4 DNS)", iface.Name, target)
+}
+
+// removeInterceptDNSTarget removes a previously set intercept DNS target,
+// restoring the service's saved static DNS (or empty). Safe no-op when no
+// target was set.
+func (p *prog) removeInterceptDNSTarget(reason string) {
+	p.interceptDNSTargetMu.Lock()
+	defer p.interceptDNSTargetMu.Unlock()
+	p.loadInterceptDNSTargetStateLocked()
+	p.removeInterceptDNSTargetLocked(reason)
+}
+
+// removeInterceptDNSTargetLocked is removeInterceptDNSTarget without locking;
+// callers must hold interceptDNSTargetMu.
+func (p *prog) removeInterceptDNSTargetLocked(reason string) {
+	svc := p.interceptDNSTargetService
+	val := p.interceptDNSTargetSetValue
+	if svc == "" {
+		return
+	}
+	iface := &net.Interface{Name: svc}
+	// Only remove what ctrld set. If the service's DNS changed externally,
+	// leave that value alone and discard our stale ownership record.
+	cur, err := interceptCurrentStaticDNSFn(iface)
+	if err != nil {
+		mainLog.Load().Debug().Err(err).Msgf("intercept DNS target: could not read %q DNS; retaining cleanup state (%s)", svc, reason)
+		return
+	}
+	if !isInterceptDNSTargetOnly(cur, val) {
+		mainLog.Load().Debug().Msgf("intercept DNS target: %q DNS changed externally; not removing (%s)", svc, reason)
+		p.clearInterceptDNSTargetStateLocked()
+		return
+	}
+	if saved := interceptSavedStaticNameserversFn(iface); len(saved) > 0 {
+		if err := interceptSetDNSFn(iface, saved); err != nil {
+			mainLog.Load().Warn().Err(err).Msgf("intercept DNS target: could not restore saved DNS on %q; retaining cleanup state", svc)
+			return
+		}
+	} else if err := interceptResetDNSIgnoreUnusableIfaceFn(iface); err != nil {
+		mainLog.Load().Warn().Err(err).Msgf("intercept DNS target: could not reset DNS on %q; retaining cleanup state", svc)
+		return
+	}
+	p.clearInterceptDNSTargetStateLocked()
+	mainLog.Load().Info().Msgf("intercept DNS target: removed %s from %q (%s)", val, svc, reason)
+}
+
+func (p *prog) clearInterceptDNSTargetStateLocked() {
+	p.interceptDNSTargetService = ""
+	p.interceptDNSTargetSetValue = ""
+	p.persistInterceptDNSTargetStateLocked()
+}

cmd/cli/dns_target_darwin_test.go

@@ -0,0 +1,248 @@
+//go:build darwin
+
+package cli
+
+import (
+	"errors"
+	"net"
+	"os"
+	"path/filepath"
+	"slices"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+type interceptTargetHarness struct {
+	dns          map[string][]string
+	saved        map[string][]string
+	serviceByDev map[string]string
+	dhcp         []string
+	dhcpErr      error
+	readErr      error
+	setErr       error
+	resetErr     error
+	setCalls     []string
+	resetCalls   []string
+	statePath    string
+}
+
+func newInterceptTargetHarness(t *testing.T) *interceptTargetHarness {
+	t.Helper()
+	h := &interceptTargetHarness{
+		dns:          make(map[string][]string),
+		saved:        make(map[string][]string),
+		serviceByDev: map[string]string{"en1": "Wi-Fi"},
+		statePath:    filepath.Join(t.TempDir(), interceptDNSTargetStateFile),
+	}
+
+	origPath := interceptDNSTargetStatePathFn
+	origRoute := interceptDefaultRouteInterfaceFn
+	origIface := interceptInterfaceByNameFn
+	origPatch := interceptPatchNetIfaceNameFn
+	origCurrent := interceptCurrentStaticDNSFn
+	origSave := interceptSaveCurrentStaticDNSFn
+	origSet := interceptSetDNSFn
+	origSaved := interceptSavedStaticNameserversFn
+	origReset := interceptResetDNSIgnoreUnusableIfaceFn
+	origDHCP := interceptDHCPNameserversForInterfaceFn
+	origIntercept := dnsIntercept
+	t.Cleanup(func() {
+		interceptDNSTargetStatePathFn = origPath
+		interceptDefaultRouteInterfaceFn = origRoute
+		interceptInterfaceByNameFn = origIface
+		interceptPatchNetIfaceNameFn = origPatch
+		interceptCurrentStaticDNSFn = origCurrent
+		interceptSaveCurrentStaticDNSFn = origSave
+		interceptSetDNSFn = origSet
+		interceptSavedStaticNameserversFn = origSaved
+		interceptResetDNSIgnoreUnusableIfaceFn = origReset
+		interceptDHCPNameserversForInterfaceFn = origDHCP
+		dnsIntercept = origIntercept
+	})
+
+	dnsIntercept = true
+	interceptDNSTargetStatePathFn = func() string { return h.statePath }
+	interceptDefaultRouteInterfaceFn = func() (string, error) { return "en1", nil }
+	interceptInterfaceByNameFn = func(name string) (*net.Interface, error) { return &net.Interface{Name: name}, nil }
+	interceptPatchNetIfaceNameFn = func(iface *net.Interface) (bool, error) {
+		service, ok := h.serviceByDev[iface.Name]
+		if !ok {
+			return false, errors.New("unknown network service")
+		}
+		iface.Name = service
+		return true, nil
+	}
+	interceptCurrentStaticDNSFn = func(iface *net.Interface) ([]string, error) {
+		if h.readErr != nil {
+			return nil, h.readErr
+		}
+		return slices.Clone(h.dns[iface.Name]), nil
+	}
+	interceptSaveCurrentStaticDNSFn = func(iface *net.Interface) error {
+		h.saved[iface.Name] = slices.Clone(h.dns[iface.Name])
+		return nil
+	}
+	interceptSetDNSFn = func(iface *net.Interface, nameservers []string) error {
+		h.setCalls = append(h.setCalls, iface.Name)
+		if h.setErr != nil {
+			return h.setErr
+		}
+		h.dns[iface.Name] = slices.Clone(nameservers)
+		return nil
+	}
+	interceptSavedStaticNameserversFn = func(iface *net.Interface) []string {
+		return slices.Clone(h.saved[iface.Name])
+	}
+	interceptResetDNSIgnoreUnusableIfaceFn = func(iface *net.Interface) error {
+		h.resetCalls = append(h.resetCalls, iface.Name)
+		if h.resetErr != nil {
+			return h.resetErr
+		}
+		h.dns[iface.Name] = nil
+		return nil
+	}
+	interceptDHCPNameserversForInterfaceFn = func(iface string) ([]string, error) {
+		if iface != "en1" {
+			return nil, errors.New("DHCP lookup used a non-default interface")
+		}
+		return slices.Clone(h.dhcp), h.dhcpErr
+	}
+	return h
+}
+
+func newInterceptTargetProg() *prog {
+	return &prog{
+		cfg: &ctrld.Config{Listener: map[string]*ctrld.ListenerConfig{
+			"0": {IP: "127.0.0.1", Port: 5354},
+		}},
+		dnsInterceptState: &interceptStateStub{},
+	}
+}
+
+func persistInterceptTargetForTest(t *testing.T, p *prog, service, value string) {
+	t.Helper()
+	p.interceptDNSTargetMu.Lock()
+	defer p.interceptDNSTargetMu.Unlock()
+	p.interceptDNSTargetLoaded = true
+	p.interceptDNSTargetService = service
+	p.interceptDNSTargetSetValue = value
+	p.persistInterceptDNSTargetStateLocked()
+}
+
+func TestEnsureInterceptDNSTargetRequiresCompletedDiscovery(t *testing.T) {
+	h := newInterceptTargetHarness(t)
+	p := newInterceptTargetProg()
+	p.ensureInterceptDNSTarget(nil)
+	if len(h.setCalls) != 0 || len(h.resetCalls) != 0 {
+		t.Fatal("nil system discovery changed service DNS")
+	}
+}
+
+func TestEnsureInterceptDNSTargetMigratesService(t *testing.T) {
+	h := newInterceptTargetHarness(t)
+	p := newInterceptTargetProg()
+	persistInterceptTargetForTest(t, p, "iPhone USB", "127.0.0.53")
+	h.dns["iPhone USB"] = []string{"127.0.0.53"}
+	h.dns["Wi-Fi"] = nil
+
+	p.ensureInterceptDNSTarget([]string{})
+
+	if len(h.dns["iPhone USB"]) != 0 {
+		t.Fatalf("old service DNS = %v, want empty", h.dns["iPhone USB"])
+	}
+	if got := h.dns["Wi-Fi"]; !slices.Equal(got, []string{"127.0.0.53"}) {
+		t.Fatalf("new service DNS = %v, want [127.0.0.53]", got)
+	}
+	if p.interceptDNSTargetService != "Wi-Fi" || p.interceptDNSTargetSetValue != "127.0.0.53" {
+		t.Fatalf("tracking = %q/%q, want Wi-Fi/127.0.0.53", p.interceptDNSTargetService, p.interceptDNSTargetSetValue)
+	}
+}
+
+func TestEnsureInterceptDNSTargetUsesDefaultRouteDHCPOnly(t *testing.T) {
+	t.Run("other interface IPv4 does not suppress target", func(t *testing.T) {
+		h := newInterceptTargetHarness(t)
+		p := newInterceptTargetProg()
+		p.ensureInterceptDNSTarget([]string{"10.10.10.1"})
+		if got := h.dns["Wi-Fi"]; !slices.Equal(got, []string{"127.0.0.53"}) {
+			t.Fatalf("other interface DNS suppressed target: %v", got)
+		}
+	})
+
+	t.Run("returned default route DHCP removes target", func(t *testing.T) {
+		h := newInterceptTargetHarness(t)
+		p := newInterceptTargetProg()
+		persistInterceptTargetForTest(t, p, "Wi-Fi", "127.0.0.53")
+		h.dns["Wi-Fi"] = []string{"127.0.0.53"}
+		h.dhcp = []string{"192.168.10.1"}
+
+		p.ensureInterceptDNSTarget([]string{"10.10.10.1"})
+
+		if len(h.dns["Wi-Fi"]) != 0 || p.interceptDNSTargetService != "" {
+			t.Fatalf("returned default-route DHCP DNS did not remove target: dns=%v service=%q", h.dns["Wi-Fi"], p.interceptDNSTargetService)
+		}
+	})
+}
+
+func TestRemoveInterceptDNSTargetRestoresStateFileAfterRestart(t *testing.T) {
+	h := newInterceptTargetHarness(t)
+	h.dns["iPhone USB"] = []string{"127.0.0.53"}
+	if err := os.WriteFile(h.statePath, []byte(`{"service":"iPhone USB","value":"127.0.0.53"}`), 0600); err != nil {
+		t.Fatal(err)
+	}
+	p := newInterceptTargetProg()
+
+	p.removeInterceptDNSTarget("intercept mode inactive")
+
+	if len(h.dns["iPhone USB"]) != 0 || p.interceptDNSTargetService != "" {
+		t.Fatalf("restart cleanup failed: dns=%v service=%q", h.dns["iPhone USB"], p.interceptDNSTargetService)
+	}
+	if _, err := os.Stat(h.statePath); !os.IsNotExist(err) {
+		t.Fatalf("state file still exists after cleanup: %v", err)
+	}
+}
+
+func TestRemoveInterceptDNSTargetKeepsExternalDNS(t *testing.T) {
+	h := newInterceptTargetHarness(t)
+	p := newInterceptTargetProg()
+	persistInterceptTargetForTest(t, p, "Wi-Fi", "127.0.0.53")
+	h.dns["Wi-Fi"] = []string{"8.8.8.8"}
+
+	p.removeInterceptDNSTarget("test")
+
+	if !slices.Equal(h.dns["Wi-Fi"], []string{"8.8.8.8"}) || len(h.setCalls) != 0 || len(h.resetCalls) != 0 {
+		t.Fatalf("external DNS was changed: dns=%v set=%v reset=%v", h.dns["Wi-Fi"], h.setCalls, h.resetCalls)
+	}
+	if p.interceptDNSTargetService != "" {
+		t.Fatal("external change left stale ownership tracking")
+	}
+}
+
+func TestRemoveInterceptDNSTargetRetainsStateOnFailure(t *testing.T) {
+	for _, tc := range []struct {
+		name     string
+		readErr  error
+		resetErr error
+	}{
+		{"read failure", errors.New("networksetup read failed"), nil},
+		{"restore failure", nil, errors.New("networksetup reset failed")},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			h := newInterceptTargetHarness(t)
+			p := newInterceptTargetProg()
+			persistInterceptTargetForTest(t, p, "Wi-Fi", "127.0.0.53")
+			h.dns["Wi-Fi"] = []string{"127.0.0.53"}
+			h.readErr = tc.readErr
+			h.resetErr = tc.resetErr
+
+			p.removeInterceptDNSTarget("test")
+
+			if p.interceptDNSTargetService != "Wi-Fi" || p.interceptDNSTargetSetValue != "127.0.0.53" {
+				t.Fatal("failed cleanup discarded retry state")
+			}
+			if _, err := os.Stat(h.statePath); err != nil {
+				t.Fatalf("failed cleanup removed persisted retry state: %v", err)
+			}
+		})
+	}
+}

cmd/cli/dns_target_filter_test.go

@@ -0,0 +1,57 @@
+package cli
+
+import "testing"
+
+func TestFilterOwnTarget(t *testing.T) {
+	tests := []struct {
+		name    string
+		in      []string
+		target  string
+		wantLen int
+	}{
+		// The oscillation guard (MR !997 review): the second recovery on the
+		// same DNS-less network must not count ctrld's own entry as
+		// network-provided IPv4 DNS.
+		{"removes own entry", []string{"127.0.0.1"}, "127.0.0.1", 0},
+		{"removes own entry with resolver port", []string{"127.0.0.53:53"}, "127.0.0.53", 0},
+		{"keeps user entries", []string{"127.0.0.1", "1.1.1.1"}, "127.0.0.1", 1},
+		{"empty target keeps all", []string{"127.0.0.1"}, "", 1},
+		{"no match keeps all", []string{"1.1.1.1"}, "127.0.0.53", 1},
+		{"nil input", nil, "127.0.0.1", 0},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			got := filterOwnTarget(tc.in, tc.target)
+			if len(got) != tc.wantLen {
+				t.Errorf("filterOwnTarget(%v, %q) = %v, want len %d", tc.in, tc.target, got, tc.wantLen)
+			}
+			for _, s := range got {
+				if tc.target != "" && s == tc.target {
+					t.Errorf("filterOwnTarget(%v, %q) retained the target entry", tc.in, tc.target)
+				}
+			}
+		})
+	}
+}
+
+// TestFilterOwnTargetStability pins the recovery-cycle contract: on a
+// DNS-less network where ctrld already set its target, needsInterceptDNSTarget
+// over the filtered list must still report true (entry kept, no oscillation),
+// while a genuine user-added IPv4 server must report false (entry removed).
+func TestFilterOwnTargetStability(t *testing.T) {
+	target := "127.0.0.1"
+
+	// Second recovery, same tether: only our own entry present. The OS resolver
+	// reports it with :53, while networksetup reports the bare address.
+	static := filterOwnTarget([]string{target}, target)
+	discovered := filterOwnTarget([]string{target + ":53"}, target)
+	if !needsInterceptDNSTarget(static, discovered) {
+		t.Error("second recovery on the same DNS-less network would remove the target (oscillation)")
+	}
+
+	// User manually added a public server meanwhile: target no longer needed.
+	static = filterOwnTarget([]string{target, "1.1.1.1"}, target)
+	if needsInterceptDNSTarget(static, nil) {
+		t.Error("user-added IPv4 DNS not recognized; target would be kept unnecessarily")
+	}
+}

cmd/cli/dns_target_stub.go

@@ -0,0 +1,14 @@
+//go:build !darwin
+
+package cli
+
+// ensureInterceptDNSTarget is a no-op on non-Darwin platforms: the DNS-less
+// network problem it solves is specific to macOS pf interception blocking
+// IPv6 port 53 with no IPv4 fallback (issue #533). Windows intercept mode
+// uses NRPT, which routes queries regardless of adapter DNS configuration.
+func (p *prog) ensureInterceptDNSTarget(_ []string) {}
+
+// removeInterceptDNSTarget is a no-op on non-Darwin platforms.
+//
+//lint:ignore U1000 called from Darwin-only intercept shutdown; kept for API symmetry.
+func (p *prog) removeInterceptDNSTarget(_ string) {}

cmd/cli/dns_target_test.go

@@ -0,0 +1,113 @@
+package cli
+
+import (
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestHasIPv4DNS(t *testing.T) {
+	tests := []struct {
+		name string
+		in   []string
+		want bool
+	}{
+		{"empty", nil, false},
+		{"ipv4", []string{"8.8.8.8"}, true},
+		{"ipv4 with port", []string{"192.168.1.1:53"}, true},
+		{"loopback counts", []string{"127.0.0.1"}, true},
+		{"ipv6 only", []string{"2001:4860:4860::8888"}, false},
+		{"ipv6 with port", []string{"[2001:4860:4860::8888]:53"}, false},
+		{"mixed", []string{"2001:4860:4860::8888", "9.9.9.9"}, true},
+		{"garbage ignored", []string{"not-an-ip", ""}, false},
+		{"garbage plus v4", []string{"not-an-ip", "1.1.1.1"}, true},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := hasIPv4DNS(tc.in); got != tc.want {
+				t.Errorf("hasIPv4DNS(%v) = %v, want %v", tc.in, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestNeedsInterceptDNSTarget(t *testing.T) {
+	tests := []struct {
+		name               string
+		static, discovered []string
+		want               bool
+	}{
+		{"no dns at all", nil, nil, true},
+		{"ipv6-only tether (464XLAT, issue #533)", nil, []string{"2605:8d80::1"}, true},
+		{"static v4 present", []string{"1.1.1.1"}, nil, false},
+		{"discovered v4 present", nil, []string{"192.168.1.1:53"}, false},
+		{"existing ctrld target satisfies", []string{"127.0.0.1"}, nil, false},
+		{"ipv6 static, v4 discovered", []string{"2001:db8::1"}, []string{"10.0.0.1"}, false},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := needsInterceptDNSTarget(tc.static, tc.discovered); got != tc.want {
+				t.Errorf("needsInterceptDNSTarget(%v, %v) = %v, want %v", tc.static, tc.discovered, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestIsInterceptDNSTargetOnly(t *testing.T) {
+	tests := []struct {
+		name   string
+		in     []string
+		target string
+		want   bool
+	}{
+		{"exactly ours (direct listener)", []string{"127.0.0.1"}, "127.0.0.1", true},
+		{"exactly ours (rdr target)", []string{"127.0.0.53"}, "127.0.0.53", true},
+		{"empty list", nil, "127.0.0.1", false},
+		{"empty target never matches", []string{"127.0.0.1"}, "", false},
+		{"ours plus user entry", []string{"127.0.0.1", "1.1.1.1"}, "127.0.0.1", false},
+		{"user entry only", []string{"1.1.1.1"}, "127.0.0.1", false},
+		{"different loopback than ours", []string{"127.0.0.53"}, "127.0.0.1", false},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := isInterceptDNSTargetOnly(tc.in, tc.target); got != tc.want {
+				t.Errorf("isInterceptDNSTargetOnly(%v, %q) = %v, want %v", tc.in, tc.target, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestInterceptDNSTargetValue(t *testing.T) {
+	tests := []struct {
+		name string
+		ip   string
+		port int
+		want string
+	}{
+		{"default direct listener :53", "127.0.0.1", 53, "127.0.0.1"},
+		{"custom loopback listener :53", "127.0.0.2", 53, "127.0.0.2"},
+		{"non-53 port uses rdr target", "127.0.0.1", 5354, "127.0.0.53"},
+		{"listener on rdr target with non-53 port", "127.0.0.53", 5354, "127.0.0.54"},
+		{"wildcard ip :53 falls back to loopback", "0.0.0.0", 53, "127.0.0.1"},
+		{"wildcard ip non-53 uses rdr target", "0.0.0.0", 5354, "127.0.0.53"},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			p := &prog{cfg: &ctrld.Config{
+				Listener: map[string]*ctrld.ListenerConfig{
+					"0": {IP: tc.ip, Port: tc.port},
+				},
+			}}
+			if got := p.interceptDNSTargetValue(); got != tc.want {
+				t.Errorf("interceptDNSTargetValue() with listener %s:%d = %q, want %q", tc.ip, tc.port, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestInterceptDNSTargetValue_NoListener(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{}}
+	if got := p.interceptDNSTargetValue(); got != "127.0.0.1" {
+		t.Errorf("interceptDNSTargetValue() with no listener = %q, want 127.0.0.1", got)
+	}
+}

cmd/cli/hostname.go

@@ -0,0 +1,14 @@
+package cli
+
+import "regexp"
+
+// validHostname reports whether hostname is a valid hostname.
+// A valid hostname contains 3 -> 64 characters and conform to RFC1123.
+func validHostname(hostname string) bool {
+	hostnameLen := len(hostname)
+	if hostnameLen < 3 || hostnameLen > 64 {
+		return false
+	}
+	validHostnameRfc1123 := regexp.MustCompile(`^(([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.)*([A-Za-z0-9]|[A-Za-z0-9][A-Za-z0-9\-]*[A-Za-z0-9])$`)
+	return validHostnameRfc1123.MatchString(hostname)
+}

cmd/cli/hostname_test.go

@@ -0,0 +1,35 @@
+package cli
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func Test_validHostname(t *testing.T) {
+	tests := []struct {
+		name     string
+		hostname string
+		valid    bool
+	}{
+		{"localhost", "localhost", true},
+		{"localdomain", "localhost.localdomain", true},
+		{"localhost6", "localhost6.localdomain6", true},
+		{"ip6", "ip6-localhost", true},
+		{"non-domain", "controld", true},
+		{"domain", "controld.com", true},
+		{"empty", "", false},
+		{"min length", "fo", false},
+		{"max length", strings.Repeat("a", 65), false},
+		{"special char", "foo!", false},
+		{"non-ascii", "fooΩ", false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.hostname, func(t *testing.T) {
+			t.Parallel()
+			assert.True(t, validHostname(tc.hostname) == tc.valid)
+		})
+	}
+}

cmd/cli/intercept_mode_config_test.go

@@ -0,0 +1,65 @@
+package cli
+
+import (
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestUpdateConfigInterceptMode(t *testing.T) {
+	tests := []struct {
+		name        string
+		current     string
+		mode        string
+		want        string
+		wantUpdated bool
+	}{
+		{name: "empty flag preserves config", current: "dns", mode: "", want: "dns"},
+		{name: "dns is persisted", mode: "dns", want: "dns", wantUpdated: true},
+		{name: "hard is persisted", current: "dns", mode: "hard", want: "hard", wantUpdated: true},
+		{name: "off clears persisted mode", current: "dns", mode: "off", want: "", wantUpdated: true},
+		{name: "off is idempotent", mode: "off", want: ""},
+		{name: "invalid flag preserves config", current: "hard", mode: "invalid", want: "hard"},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			cfg := &ctrld.Config{}
+			cfg.Service.InterceptMode = tc.current
+			updated := updateConfigInterceptMode(cfg, tc.mode)
+			if updated != tc.wantUpdated {
+				t.Fatalf("updateConfigInterceptMode() updated = %v, want %v", updated, tc.wantUpdated)
+			}
+			if cfg.Service.InterceptMode != tc.want {
+				t.Fatalf("service.intercept_mode = %q, want %q", cfg.Service.InterceptMode, tc.want)
+			}
+		})
+	}
+}
+
+func TestConfiguredInterceptMode(t *testing.T) {
+	oldInterceptMode := interceptMode
+	t.Cleanup(func() { interceptMode = oldInterceptMode })
+
+	p := &prog{cfg: &ctrld.Config{}}
+	p.cfg.Service.InterceptMode = "dns"
+
+	tests := []struct {
+		name string
+		flag string
+		want string
+	}{
+		{name: "empty flag falls back to config", flag: "", want: "dns"},
+		{name: "explicit off is final", flag: "off", want: "off"},
+		{name: "explicit hard wins over config", flag: "hard", want: "hard"},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			interceptMode = tc.flag
+			if got := p.configuredInterceptMode(); got != tc.want {
+				t.Fatalf("configuredInterceptMode() = %q, want %q", got, tc.want)
+			}
+		})
+	}
+}

cmd/cli/intercept_probe.go

@@ -0,0 +1,68 @@
+package cli
+
+// Interception probe registry.
+//
+// A probe sends a DNS query for a unique synthetic domain through the OS resolver and
+// waits for ctrld's own handler to receive it. That is the only way to tell "the rules are
+// present" from "the rules are actually redirecting packets", and both the macOS pf path
+// and the Windows NRPT path use it.
+//
+// Each attempt registers its own domain, so overlapping probes cannot cancel each other,
+// and deregistration only removes the entry it owns.
+
+// registerInterceptProbe registers domain and returns the channel it will be signalled on
+// plus the function that removes the registration.
+//
+//lint:ignore U1000 used on darwin (pf probes) and windows (NRPT probes)
+func (p *prog) registerInterceptProbe(domain string) (<-chan struct{}, func()) {
+	ch := make(chan struct{}, 1)
+
+	p.interceptProbeMu.Lock()
+	current, _ := p.interceptProbes.Load().(map[string]chan struct{})
+	next := make(map[string]chan struct{}, len(current)+1)
+	for k, v := range current {
+		next[k] = v
+	}
+	next[domain] = ch
+	p.interceptProbes.Store(next)
+	p.interceptProbeMu.Unlock()
+
+	return ch, func() {
+		p.interceptProbeMu.Lock()
+		defer p.interceptProbeMu.Unlock()
+		current, _ := p.interceptProbes.Load().(map[string]chan struct{})
+		// Only drop the entry while it is still this attempt's channel. A later probe
+		// that reused the domain owns the slot now, and clearing it would make that one
+		// wait out its timeout for a query it already received.
+		if existing, ok := current[domain]; !ok || existing != ch {
+			return
+		}
+		next := make(map[string]chan struct{}, len(current))
+		for k, v := range current {
+			if k != domain {
+				next[k] = v
+			}
+		}
+		p.interceptProbes.Store(next)
+	}
+}
+
+// signalInterceptProbe reports whether domain is a pending probe, signalling its waiter
+// when it is. Called from the DNS handler for every query, so the common case is a nil or
+// empty map and no allocation.
+func (p *prog) signalInterceptProbe(domain string) bool {
+	probes, _ := p.interceptProbes.Load().(map[string]chan struct{})
+	if len(probes) == 0 {
+		return false
+	}
+	ch, ok := probes[domain]
+	if !ok {
+		return false
+	}
+	select {
+	case ch <- struct{}{}:
+	default:
+		// Buffered channel already holds a signal: the waiter has what it needs.
+	}
+	return true
+}

cmd/cli/library.go

@@ -0,0 +1,106 @@
+package cli
+
+import (
+	"fmt"
+	"net"
+	"net/http"
+	"time"
+)
+
+// AppCallback provides hooks for injecting certain functionalities
+// from mobile platforms to main ctrld cli.
+type AppCallback struct {
+	HostName   func() string
+	LanIp      func() string
+	MacAddress func() string
+	Exit       func(error string)
+}
+
+// AppConfig allows overwriting ctrld cli flags from mobile platforms.
+type AppConfig struct {
+	CdUID          string
+	ProvisionID    string
+	CustomHostname string
+	HomeDir        string
+	UpstreamProto  string
+	Verbose        int
+	LogPath        string
+}
+
+const (
+	defaultHTTPTimeout = 30 * time.Second
+	defaultMaxRetries  = 3
+	downloadServerIp   = "23.171.240.151"
+)
+
+// httpClientWithFallback returns an HTTP client configured with timeout and IPv4 fallback
+func httpClientWithFallback(timeout time.Duration) *http.Client {
+	return &http.Client{
+		Timeout: timeout,
+		Transport: &http.Transport{
+			// Prefer IPv4 over IPv6
+			DialContext: (&net.Dialer{
+				Timeout:       10 * time.Second,
+				KeepAlive:     30 * time.Second,
+				FallbackDelay: 1 * time.Millisecond, // Very small delay to prefer IPv4
+			}).DialContext,
+		},
+	}
+}
+
+// doWithRetry performs an HTTP request with retries
+func doWithRetry(req *http.Request, maxRetries int, ip string) (*http.Response, error) {
+	return doWithRetryClient(httpClientWithFallback(defaultHTTPTimeout), req, maxRetries, ip)
+}
+
+// doWithRetryClient is doWithRetry with an injectable client, so the retry and
+// error-composition behaviour can be tested without real network access.
+func doWithRetryClient(client *http.Client, req *http.Request, maxRetries int, ip string) (*http.Response, error) {
+	var lastErr error
+	var ipReq *http.Request
+	if ip != "" {
+		ipReq = req.Clone(req.Context())
+		ipReq.Host = ip
+		ipReq.URL.Host = ip
+	}
+	for attempt := 0; attempt < maxRetries; attempt++ {
+		if attempt > 0 {
+			time.Sleep(time.Second * time.Duration(attempt+1)) // Exponential backoff
+		}
+
+		resp, err := client.Do(req)
+		if err == nil {
+			return resp, nil
+		}
+		// Keep the hostname attempt's error: it carries the diagnosis (on Windows,
+		// a local firewall denying the socket shows up here as WSAEACCES), while the
+		// direct-IP fallback often fails for an unrelated reason such as an
+		// unreachable IPv6 route.
+		attemptErr := err
+		if ipReq != nil {
+			mainLog.Load().Warn().Err(err).Msgf("dial to %q failed", req.Host)
+			mainLog.Load().Warn().Msgf("fallback to direct IP to download prod version: %q", ip)
+			resp, fallbackErr := client.Do(ipReq)
+			if fallbackErr == nil {
+				return resp, nil
+			}
+			attemptErr = fmt.Errorf("%w; fallback to direct ip %s failed: %w", attemptErr, ip, fallbackErr)
+		}
+
+		lastErr = attemptErr
+		mainLog.Load().Debug().Err(attemptErr).
+			Str("method", req.Method).
+			Str("url", req.URL.String()).
+			Msgf("HTTP request attempt %d/%d failed", attempt+1, maxRetries)
+	}
+	return nil, fmt.Errorf("failed after %d attempts to %s %s: %w", maxRetries, req.Method, req.URL, lastErr)
+}
+
+// Helper for making GET requests with retries
+func getWithRetry(url string, ip string) (*http.Response, error) {
+	req, err := http.NewRequest(http.MethodGet, url, nil)
+	if err != nil {
+		return nil, err
+	}
+	return doWithRetry(req, defaultMaxRetries, ip)
+}

cmd/cli/library_retry_test.go

@@ -0,0 +1,241 @@
+package cli
+
+import (
+	"errors"
+	"fmt"
+	"net"
+	"net/http"
+	"net/url"
+	"syscall"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld/internal/controld"
+)
+
+// wsaEACCES is WSAEACCES (10013): "An attempt was made to access a socket in a way
+// forbidden by its access permissions." This is what Windows reports when a WFP
+// filter denies the connect. Used as a plain errno so the test runs everywhere.
+const wsaEACCES = syscall.Errno(10013)
+
+// denyingRoundTripper denies the hostname attempt with firstErr and the direct-ip
+// attempt with fbErr, the shape seen during the Firewall Mode incident: the
+// hostname attempt was denied by ctrld's own stale block-all filters, while the
+// direct-ip fallback failed on an unreachable IPv6 route.
+type denyingRoundTripper struct {
+	hostname string
+	firstErr error
+	fbErr    error
+}
+
+func (rt *denyingRoundTripper) RoundTrip(req *http.Request) (*http.Response, error) {
+	if req.URL.Host == rt.hostname {
+		return nil, &net.OpError{Op: "dial", Net: "tcp4", Err: rt.firstErr}
+	}
+	return nil, &net.OpError{Op: "dial", Net: "tcp6", Err: rt.fbErr}
+}
+
+func TestDoWithRetryPreservesHostnameError(t *testing.T) {
+	const hostname = "dl.controld.dev"
+	req, err := http.NewRequest(http.MethodGet, "https://"+hostname+"/v2/windows-amd64/ctrld.exe", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	rt := &denyingRoundTripper{
+		hostname: hostname,
+		firstErr: wsaEACCES,
+		fbErr:    syscall.EHOSTUNREACH,
+	}
+
+	_, err = doWithRetryClient(&http.Client{Transport: rt}, req, 1, "23.171.240.151")
+	if err == nil {
+		t.Fatal("expected doWithRetry to fail when both attempts are denied")
+	}
+	if !errors.Is(err, wsaEACCES) {
+		t.Errorf("hostname-attempt error (WSAEACCES) was lost, got: %v", err)
+	}
+	if !errors.Is(err, syscall.EHOSTUNREACH) {
+		t.Errorf("fallback error was lost, got: %v", err)
+	}
+}
+
+// composedAttemptErrors builds the error shape the two-attempt paths return: each
+// attempt's *url.Error (as produced by http.Client.Do) wrapped by a single fmt.Errorf
+// with two %w verbs, hostname attempt first. Mirrors doWithFallback in
+// internal/controld and doWithRetryClient above.
+func composedAttemptErrors(first, fallback error) error {
+	attempt := func(network string, cause error) error {
+		return &url.Error{
+			Op:  "Post",
+			URL: "https://api.controld.com/utility",
+			Err: &net.OpError{Op: "dial", Net: network, Err: cause},
+		}
+	}
+	return fmt.Errorf("request failed: %w; fallback to direct ip %s failed: %w",
+		attempt("tcp4", first), "147.185.34.1", attempt("tcp6", fallback))
+}
+
+// TestComposedFallbackErrorRetryClassification pins which attempt decides whether
+// preflight keeps retrying.
+//
+// Reporting both attempt errors is not purely diagnostic: processCDFlags decides
+// retryability with errUrlNetworkError, which uses errors.As, and errors.As is
+// order-sensitive - it returns the *first* matching error in the tree. Composing the
+// hostname attempt first therefore hands the retry predicate the hostname failure,
+// where previously only the fallback's error survived to be classified.
+//
+// The consequence is deliberate: a locally denied socket (WSAEACCES, a firewall
+// blocking ctrld) is no longer treated as a transient network error, so preflight fails
+// fast and reports instead of backing off - the incident logged 256 retry cycles
+// against filters that were never going to clear on their own. The boot case that
+// justifies the indefinite retry, a network unreachable on both attempts, is preserved.
+//
+// If the wrap order is ever reversed, this test fails rather than silently restoring
+// indefinite retries against a host that is actively refusing.
+func TestComposedFallbackErrorRetryClassification(t *testing.T) {
+	tests := []struct {
+		name          string
+		hostname      error
+		fallback      error
+		wantRetryable bool
+	}{
+		{
+			// The incident's pair: denied locally, IPv6 route unusable.
+			name:          "denied socket then unreachable fallback fails fast",
+			hostname:      wsaEACCES,
+			fallback:      syscall.EHOSTUNREACH,
+			wantRetryable: false,
+		},
+		{
+			// Boot with no network yet: must still retry indefinitely.
+			name:          "network unreachable on both attempts still retries",
+			hostname:      syscall.ENETUNREACH,
+			fallback:      syscall.ENETUNREACH,
+			wantRetryable: true,
+		},
+		{
+			name:          "connection refused still retries",
+			hostname:      syscall.ECONNREFUSED,
+			fallback:      syscall.EHOSTUNREACH,
+			wantRetryable: true,
+		},
+		{
+			name:          "permission denied on both attempts fails fast",
+			hostname:      syscall.EACCES,
+			fallback:      syscall.EACCES,
+			wantRetryable: false,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			err := composedAttemptErrors(tc.hostname, tc.fallback)
+			if got := errUrlNetworkError(err); got != tc.wantRetryable {
+				t.Errorf("errUrlNetworkError() = %v, want %v", got, tc.wantRetryable)
+			}
+			// Both attempts remain reportable regardless of classification.
+			if !errors.Is(err, tc.hostname) {
+				t.Error("hostname attempt error was lost")
+			}
+			if !errors.Is(err, tc.fallback) {
+				t.Error("fallback attempt error was lost")
+			}
+		})
+	}
+}
+
+// TestUnresolvedHostnameDefersToFallbackAttempt covers the asymmetric pair.
+//
+// Only the hostname attempt resolves DNS, and Go marks a *net.DNSError as temporary only
+// for socket failures that reached the server - so a SERVFAIL or "no such host" answer is
+// not temporary. At boot behind a captive portal, or before a router's forwarder is up,
+// that is exactly how the hostname attempt fails while the network is merely not ready.
+// Before the composed error existed only the fallback decided, so this pair retried;
+// classifying the hostname attempt alone would fail it fast and reach Fatal.
+//
+// A name-resolution failure therefore carries no verdict: the fallback attempt decides.
+// The locally-denied case above still fails fast, because a denied socket is definitive.
+func TestUnresolvedHostnameDefersToFallbackAttempt(t *testing.T) {
+	dnsFailure := &url.Error{
+		Op:  "Post",
+		URL: "https://api.controld.com/utility",
+		Err: &net.DNSError{Err: "server misbehaving", Name: "api.controld.com", IsTemporary: false},
+	}
+	attempt := func(cause error) error {
+		return &url.Error{
+			Op:  "Post",
+			URL: "https://api.controld.com/utility",
+			Err: &net.OpError{Op: "dial", Net: "tcp6", Err: cause},
+		}
+	}
+
+	retryable := fmt.Errorf("request failed: %w; fallback to direct ip %s failed: %w",
+		dnsFailure, "147.185.34.1", attempt(syscall.ECONNREFUSED))
+	if !errUrlNetworkError(retryable) {
+		t.Error("an unresolved hostname with a retryable fallback must keep retrying: at boot the network is simply not up yet")
+	}
+
+	denied := fmt.Errorf("request failed: %w; fallback to direct ip %s failed: %w",
+		dnsFailure, "147.185.34.1", attempt(wsaEACCES))
+	if errUrlNetworkError(denied) {
+		t.Error("an unresolved hostname with a denied fallback must fail fast: nothing here clears on its own")
+	}
+
+	// A resolution failure alone still says nothing, so it must not be read as retryable.
+	if errUrlNetworkError(dnsFailure) {
+		t.Error("a bare name-resolution failure must not be classified as retryable")
+	}
+}
+
+// TestDoWithFallbackClassificationEndToEnd drives the real composition in
+// internal/controld through the real predicate, instead of asserting a hand-written copy
+// of its error shape against another hand-written copy. A change to either side's format
+// string or wrap order is caught here.
+func TestDoWithFallbackClassificationEndToEnd(t *testing.T) {
+	const hostname = "api.controld.com"
+	req, err := http.NewRequest(http.MethodPost, "https://"+hostname+"/utility", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	rt := &denyingRoundTripper{
+		hostname: hostname,
+		firstErr: wsaEACCES,
+		fbErr:    syscall.EHOSTUNREACH,
+	}
+
+	_, gotErr := controld.DoWithFallbackForTest(&http.Client{Transport: rt}, req, "147.185.34.1")
+	if gotErr == nil {
+		t.Fatal("expected both attempts to fail")
+	}
+	if errUrlNetworkError(gotErr) {
+		t.Errorf("the real composed error was classified as retryable: %v", gotErr)
+	}
+	if !errors.Is(gotErr, wsaEACCES) || !errors.Is(gotErr, syscall.EHOSTUNREACH) {
+		t.Errorf("the real composed error lost an attempt: %v", gotErr)
+	}
+}
+
+// TestDoWithRetryComposesHostnameAttemptFirst anchors the ordering assumption above to
+// the real composition, so a reordering of the wrap in doWithRetryClient is caught here
+// and not only in the hand-built shape.
+func TestDoWithRetryComposesHostnameAttemptFirst(t *testing.T) {
+	const hostname = "dl.controld.dev"
+	req, err := http.NewRequest(http.MethodGet, "https://"+hostname+"/v2/windows-amd64/ctrld.exe", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	rt := &denyingRoundTripper{hostname: hostname, firstErr: wsaEACCES, fbErr: syscall.EHOSTUNREACH}
+
+	_, gotErr := doWithRetryClient(&http.Client{Transport: rt}, req, 1, "23.171.240.151")
+	if gotErr == nil {
+		t.Fatal("expected both attempts to fail")
+	}
+
+	// errors.As must reach the hostname attempt first: that is what the retry
+	// predicate classifies.
+	var opErr *net.OpError
+	if !errors.As(gotErr, &opErr) {
+		t.Fatalf("no net.OpError in the chain: %v", gotErr)
+	}
+	if !errors.Is(opErr.Err, wsaEACCES) {
+		t.Errorf("first OpError in the chain is %v, want the hostname attempt (%v)", opErr.Err, wsaEACCES)
+	}
+}

cmd/cli/listener_intercept_mode_test.go

@@ -0,0 +1,34 @@
+package cli
+
+import (
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestListenerInterceptModeExplicitOff(t *testing.T) {
+	oldIntercept := interceptMode
+	t.Cleanup(func() { interceptMode = oldIntercept })
+
+	cfg := &ctrld.Config{}
+	cfg.Service.InterceptMode = "dns"
+
+	tests := []struct {
+		name string
+		flag string
+		want string
+	}{
+		{name: "explicit off is final", flag: "off", want: "off"},
+		{name: "empty flag falls back to config", flag: "", want: "dns"},
+		{name: "explicit dns wins over config", flag: "dns", want: "dns"},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			interceptMode = tc.flag
+			if got := listenerInterceptMode(cfg); got != tc.want {
+				t.Fatalf("listenerInterceptMode() = %q, want %q", got, tc.want)
+			}
+		})
+	}
+}

cmd/cli/log_tail_test.go

@@ -0,0 +1,339 @@
+package cli
+
+import (
+	"io"
+	"os"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+)
+
+// =============================================================================
+// logWriter.tailLastLines tests
+// =============================================================================
+
+func Test_logWriter_tailLastLines_Empty(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	if got := lw.tailLastLines(10); got != nil {
+		t.Fatalf("expected nil for empty buffer, got %q", got)
+	}
+}
+
+func Test_logWriter_tailLastLines_ZeroLines(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("line1\nline2\n"))
+	if got := lw.tailLastLines(0); got != nil {
+		t.Fatalf("expected nil for n=0, got %q", got)
+	}
+}
+
+func Test_logWriter_tailLastLines_NegativeLines(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("line1\nline2\n"))
+	if got := lw.tailLastLines(-1); got != nil {
+		t.Fatalf("expected nil for n=-1, got %q", got)
+	}
+}
+
+func Test_logWriter_tailLastLines_FewerThanN(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("line1\nline2\n"))
+	got := string(lw.tailLastLines(10))
+	want := "line1\nline2\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_logWriter_tailLastLines_ExactN(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("line1\nline2\nline3\n"))
+	got := string(lw.tailLastLines(3))
+	want := "line1\nline2\nline3\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_logWriter_tailLastLines_MoreThanN(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("line1\nline2\nline3\nline4\nline5\n"))
+	got := string(lw.tailLastLines(2))
+	want := "line4\nline5\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_logWriter_tailLastLines_NoTrailingNewline(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("line1\nline2\nline3"))
+	// Without trailing newline, "line3" is a partial line.
+	// Asking for 1 line returns the last newline-terminated line plus the partial.
+	got := string(lw.tailLastLines(1))
+	want := "line2\nline3"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_logWriter_tailLastLines_SingleLineNoNewline(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("only line"))
+	got := string(lw.tailLastLines(5))
+	want := "only line"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_logWriter_tailLastLines_SingleLineWithNewline(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	lw.Write([]byte("only line\n"))
+	got := string(lw.tailLastLines(1))
+	want := "only line\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+// =============================================================================
+// logWriter.Subscribe tests
+// =============================================================================
+
+func Test_logWriter_Subscribe_Basic(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	ch, unsub := lw.Subscribe()
+	defer unsub()
+
+	msg := []byte("hello world\n")
+	lw.Write(msg)
+
+	select {
+	case got := <-ch:
+		if string(got) != string(msg) {
+			t.Fatalf("got %q, want %q", got, msg)
+		}
+	case <-time.After(time.Second):
+		t.Fatal("timed out waiting for subscriber data")
+	}
+}
+
+func Test_logWriter_Subscribe_MultipleSubscribers(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	ch1, unsub1 := lw.Subscribe()
+	defer unsub1()
+	ch2, unsub2 := lw.Subscribe()
+	defer unsub2()
+
+	msg := []byte("broadcast\n")
+	lw.Write(msg)
+
+	for i, ch := range []<-chan []byte{ch1, ch2} {
+		select {
+		case got := <-ch:
+			if string(got) != string(msg) {
+				t.Fatalf("subscriber %d: got %q, want %q", i, got, msg)
+			}
+		case <-time.After(time.Second):
+			t.Fatalf("subscriber %d: timed out", i)
+		}
+	}
+}
+
+func Test_logWriter_Subscribe_Unsubscribe(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	ch, unsub := lw.Subscribe()
+
+	// Verify subscribed.
+	lw.Write([]byte("before unsub\n"))
+	select {
+	case <-ch:
+	case <-time.After(time.Second):
+		t.Fatal("timed out before unsub")
+	}
+
+	unsub()
+
+	// Channel should be closed after unsub.
+	if _, ok := <-ch; ok {
+		t.Fatal("channel should be closed after unsubscribe")
+	}
+
+	// Verify subscriber list is empty.
+	lw.mu.Lock()
+	count := len(lw.subscribers)
+	lw.mu.Unlock()
+	if count != 0 {
+		t.Fatalf("expected 0 subscribers after unsub, got %d", count)
+	}
+}
+
+func Test_logWriter_Subscribe_UnsubscribeIdempotent(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	_, unsub := lw.Subscribe()
+	unsub()
+	// Second unsub should not panic.
+	unsub()
+}
+
+func Test_logWriter_Subscribe_SlowSubscriberDropped(t *testing.T) {
+	lw := newLogWriterWithSize(4096)
+	ch, unsub := lw.Subscribe()
+	defer unsub()
+
+	// Fill the subscriber channel (buffer size is 256).
+	for i := 0; i < 300; i++ {
+		lw.Write([]byte("msg\n"))
+	}
+
+	// Should have 256 buffered messages, rest dropped.
+	count := 0
+	for {
+		select {
+		case <-ch:
+			count++
+		default:
+			goto done
+		}
+	}
+done:
+	if count != 256 {
+		t.Fatalf("expected 256 buffered messages, got %d", count)
+	}
+}
+
+func Test_logWriter_Subscribe_ConcurrentWriteAndRead(t *testing.T) {
+	lw := newLogWriterWithSize(64 * 1024)
+	ch, unsub := lw.Subscribe()
+	defer unsub()
+
+	const numWrites = 100
+	var wg sync.WaitGroup
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		for i := 0; i < numWrites; i++ {
+			lw.Write([]byte("concurrent write\n"))
+		}
+	}()
+
+	received := 0
+	timeout := time.After(5 * time.Second)
+	for received < numWrites {
+		select {
+		case <-ch:
+			received++
+		case <-timeout:
+			t.Fatalf("timed out after receiving %d/%d messages", received, numWrites)
+		}
+	}
+	wg.Wait()
+}
+
+// =============================================================================
+// tailFileLastLines tests
+// =============================================================================
+
+func writeTempFile(t *testing.T, content string) *os.File {
+	t.Helper()
+	f, err := os.CreateTemp(t.TempDir(), "tail-test-*")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := f.WriteString(content); err != nil {
+		t.Fatal(err)
+	}
+	return f
+}
+
+func Test_tailFileLastLines_Empty(t *testing.T) {
+	f := writeTempFile(t, "")
+	defer f.Close()
+	if got := tailFileLastLines(f, 10); got != nil {
+		t.Fatalf("expected nil for empty file, got %q", got)
+	}
+}
+
+func Test_tailFileLastLines_FewerThanN(t *testing.T) {
+	f := writeTempFile(t, "line1\nline2\n")
+	defer f.Close()
+	got := string(tailFileLastLines(f, 10))
+	want := "line1\nline2\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_tailFileLastLines_ExactN(t *testing.T) {
+	f := writeTempFile(t, "a\nb\nc\n")
+	defer f.Close()
+	got := string(tailFileLastLines(f, 3))
+	want := "a\nb\nc\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_tailFileLastLines_MoreThanN(t *testing.T) {
+	f := writeTempFile(t, "line1\nline2\nline3\nline4\nline5\n")
+	defer f.Close()
+	got := string(tailFileLastLines(f, 2))
+	want := "line4\nline5\n"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_tailFileLastLines_NoTrailingNewline(t *testing.T) {
+	f := writeTempFile(t, "line1\nline2\nline3")
+	defer f.Close()
+	// Without trailing newline, partial last line comes with the previous line.
+	got := string(tailFileLastLines(f, 1))
+	want := "line2\nline3"
+	if got != want {
+		t.Fatalf("got %q, want %q", got, want)
+	}
+}
+
+func Test_tailFileLastLines_LargerThanChunk(t *testing.T) {
+	// Build content larger than the 4096 chunk size to exercise multi-chunk reads.
+	var sb strings.Builder
+	for i := 0; i < 200; i++ {
+		sb.WriteString(strings.Repeat("x", 50))
+		sb.WriteByte('\n')
+	}
+	f := writeTempFile(t, sb.String())
+	defer f.Close()
+	got := string(tailFileLastLines(f, 3))
+	lines := strings.Split(strings.TrimRight(got, "\n"), "\n")
+	if len(lines) != 3 {
+		t.Fatalf("expected 3 lines, got %d: %q", len(lines), got)
+	}
+	expectedLine := strings.Repeat("x", 50)
+	for _, line := range lines {
+		if line != expectedLine {
+			t.Fatalf("unexpected line content: %q", line)
+		}
+	}
+}
+
+func Test_tailFileLastLines_SeeksToEnd(t *testing.T) {
+	f := writeTempFile(t, "line1\nline2\nline3\n")
+	defer f.Close()
+	tailFileLastLines(f, 1)
+
+	// After tailFileLastLines, file position should be at the end.
+	pos, err := f.Seek(0, io.SeekCurrent)
+	if err != nil {
+		t.Fatal(err)
+	}
+	stat, err := f.Stat()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if pos != stat.Size() {
+		t.Fatalf("expected file position at end (%d), got %d", stat.Size(), pos)
+	}
+}

cmd/cli/log_writer.go

@@ -0,0 +1,473 @@
+package cli
+
+import (
+	"bytes"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/rs/zerolog"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+const (
+	logWriterSize          = 1024 * 1024 * 5 // 5 MB
+	logWriterSmallSize     = 1024 * 1024 * 1 // 1 MB
+	logWriterInitialSize   = 32 * 1024       // 32 KB
+	logWriterSentInterval  = time.Minute
+	logWriterInitEndMarker = "\n\n=== INIT_END ===\n\n"
+	logWriterLogEndMarker  = "\n\n=== LOG_END ===\n\n"
+
+	logFileName    = "ctrld.log"
+	logFileMaxSize = 1024 * 1024 * 5 // 5 MB
+)
+
+type logViewResponse struct {
+	Data string `json:"data"`
+}
+
+type logSentResponse struct {
+	Size  int64  `json:"size"`
+	Error string `json:"error"`
+}
+
+type logReader struct {
+	r    io.ReadCloser
+	size int64
+}
+
+// logSubscriber represents a subscriber to live log output.
+type logSubscriber struct {
+	ch chan []byte
+}
+
+// logWriter is an internal buffer to keep track of runtime log when no logging is enabled.
+// When a file path is configured via setLogFile, writes are also persisted to
+// a rotated file on disk (max logFileMaxSize, 1 backup) so logs survive restarts.
+type logWriter struct {
+	mu          sync.Mutex
+	buf         bytes.Buffer
+	size        int
+	subscribers []*logSubscriber
+
+	// File persistence fields.
+	logFile     *os.File
+	logFilePath string
+	logFileSize int64
+}
+
+// newLogWriter creates an internal log writer.
+func newLogWriter() *logWriter {
+	return newLogWriterWithSize(logWriterSize)
+}
+
+// newSmallLogWriter creates an internal log writer with small buffer size.
+func newSmallLogWriter() *logWriter {
+	return newLogWriterWithSize(logWriterSmallSize)
+}
+
+// newLogWriterWithSize creates an internal log writer with a given buffer size.
+func newLogWriterWithSize(size int) *logWriter {
+	lw := &logWriter{size: size}
+	return lw
+}
+
+// setLogFile configures file-backed persistence for the log writer.
+// The directory is created if it does not exist. An existing file is
+// opened in append mode and its current size is tracked for rotation.
+func (lw *logWriter) setLogFile(path string) error {
+	dir := filepath.Dir(path)
+	if err := os.MkdirAll(dir, 0750); err != nil {
+		return fmt.Errorf("creating log directory: %w", err)
+	}
+	f, err := os.OpenFile(path, os.O_CREATE|os.O_RDWR|os.O_APPEND, 0600)
+	if err != nil {
+		return fmt.Errorf("opening log file: %w", err)
+	}
+	st, err := f.Stat()
+	if err != nil {
+		f.Close()
+		return fmt.Errorf("stat log file: %w", err)
+	}
+	lw.mu.Lock()
+	defer lw.mu.Unlock()
+	lw.logFile = f
+	lw.logFilePath = path
+	lw.logFileSize = st.Size()
+	return nil
+}
+
+// rotateLogFile rotates the current log file to a .1 backup.
+// It returns true if lw.logFile is usable after the call, false otherwise.
+// Must be called with lw.mu held.
+func (lw *logWriter) rotateLogFile() bool {
+	if lw.logFile == nil {
+		return false
+	}
+	lw.logFile.Close()
+	backupPath := lw.logFilePath + ".1"
+	// Best effort: rename current to backup (overwrites old backup).
+	os.Rename(lw.logFilePath, backupPath)
+	f, err := os.OpenFile(lw.logFilePath, os.O_CREATE|os.O_RDWR|os.O_TRUNC, 0600)
+	if err != nil {
+		// If we can't reopen, disable file logging.
+		lw.logFile = nil
+		lw.logFileSize = 0
+		return false
+	}
+	lw.logFile = f
+	lw.logFileSize = 0
+	return true
+}
+
+// closeLogFile closes the backing file if open.
+func (lw *logWriter) closeLogFile() {
+	lw.mu.Lock()
+	defer lw.mu.Unlock()
+	if lw.logFile != nil {
+		lw.logFile.Close()
+		lw.logFile = nil
+	}
+}
+
+// logFilePaths returns the paths to the current log file and its backup
+// (if they exist) for inclusion in log send payloads.
+func (lw *logWriter) logFilePaths() (current, backup string) {
+	lw.mu.Lock()
+	defer lw.mu.Unlock()
+	if lw.logFilePath == "" {
+		return "", ""
+	}
+	current = lw.logFilePath
+	bp := lw.logFilePath + ".1"
+	if _, err := os.Stat(bp); err == nil {
+		backup = bp
+	}
+	return current, backup
+}
+
+// Subscribe returns a channel that receives new log data as it's written,
+// and an unsubscribe function to clean up when done.
+func (lw *logWriter) Subscribe() (<-chan []byte, func()) {
+	lw.mu.Lock()
+	defer lw.mu.Unlock()
+	sub := &logSubscriber{ch: make(chan []byte, 256)}
+	lw.subscribers = append(lw.subscribers, sub)
+	unsub := func() {
+		lw.mu.Lock()
+		defer lw.mu.Unlock()
+		for i, s := range lw.subscribers {
+			if s == sub {
+				lw.subscribers = append(lw.subscribers[:i], lw.subscribers[i+1:]...)
+				close(sub.ch)
+				break
+			}
+		}
+	}
+	return sub.ch, unsub
+}
+
+// tailLastLines returns the last n lines from the current buffer.
+func (lw *logWriter) tailLastLines(n int) []byte {
+	lw.mu.Lock()
+	defer lw.mu.Unlock()
+	data := lw.buf.Bytes()
+	if n <= 0 || len(data) == 0 {
+		return nil
+	}
+	// Find the last n newlines from the end.
+	count := 0
+	pos := len(data)
+	for pos > 0 {
+		pos--
+		if data[pos] == '\n' {
+			count++
+			if count == n+1 {
+				pos++ // move past this newline
+				break
+			}
+		}
+	}
+	result := make([]byte, len(data)-pos)
+	copy(result, data[pos:])
+	return result
+}
+
+func (lw *logWriter) Write(p []byte) (int, error) {
+	lw.mu.Lock()
+	defer lw.mu.Unlock()
+
+	// Fan-out to subscribers (non-blocking).
+	if len(lw.subscribers) > 0 {
+		cp := make([]byte, len(p))
+		copy(cp, p)
+		for _, sub := range lw.subscribers {
+			select {
+			case sub.ch <- cp:
+			default:
+				// Drop if subscriber is slow to avoid blocking the logger.
+			}
+		}
+	}
+
+	// Write to backing file if configured.
+	if lw.logFile != nil {
+		needsRotation := lw.logFileSize+int64(len(p)) > logFileMaxSize
+		if !needsRotation || lw.rotateLogFile() {
+			if n, err := lw.logFile.Write(p); err == nil {
+				lw.logFileSize += int64(n)
+			}
+		}
+	}
+
+	// If writing p causes overflows, discard old data.
+	if lw.buf.Len()+len(p) > lw.size {
+		buf := lw.buf.Bytes()
+		haveEndMarker := false
+		// If there's init end marker already, preserve the data til the marker.
+		if idx := bytes.LastIndex(buf, []byte(logWriterInitEndMarker)); idx >= 0 {
+			buf = buf[:idx+len(logWriterInitEndMarker)]
+			haveEndMarker = true
+		} else {
+			// Otherwise, preserve the initial size data.
+			buf = buf[:logWriterInitialSize]
+			if idx := bytes.LastIndex(buf, []byte("\n")); idx != -1 {
+				buf = buf[:idx]
+			}
+		}
+		lw.buf.Reset()
+		lw.buf.Write(buf)
+		if !haveEndMarker {
+			lw.buf.WriteString(logWriterInitEndMarker) // indicate that the log was truncated.
+		}
+	}
+	// If p is bigger than buffer size, truncate p by half until its size is smaller.
+	for len(p)+lw.buf.Len() > lw.size {
+		p = p[len(p)/2:]
+	}
+	return lw.buf.Write(p)
+}
+
+// initLogging initializes global logging setup.
+func (p *prog) initLogging(backup bool) {
+	zerolog.TimeFieldFormat = time.RFC3339 + ".000"
+	logWriters := initLoggingWithBackup(backup)
+
+	// Initializing internal logging after global logging.
+	p.initInternalLogging(logWriters)
+}
+
+// internalLogFilePath returns the path for persisted internal logs.
+// The file lives in the ctrld home directory alongside other runtime state.
+func internalLogFilePath() string {
+	return absHomeDir(logFileName)
+}
+
+// initInternalLogging performs internal logging if there's no log enabled.
+func (p *prog) initInternalLogging(writers []io.Writer) {
+	if !p.needInternalLogging() {
+		return
+	}
+	p.initInternalLogWriterOnce.Do(func() {
+		mainLog.Load().Notice().Msg("internal logging enabled")
+		p.internalLogWriter = newLogWriter()
+		p.internalLogSent = time.Now().Add(-logWriterSentInterval)
+		p.internalWarnLogWriter = newSmallLogWriter()
+		// Persist internal logs to disk so they survive restarts.
+		if path := internalLogFilePath(); path != "" {
+			if err := p.internalLogWriter.setLogFile(path); err != nil {
+				mainLog.Load().Warn().Err(err).Msg("could not enable persistent internal logging")
+			} else {
+				mainLog.Load().Notice().Msgf("internal log file: %s", path)
+			}
+		}
+	})
+	p.mu.Lock()
+	lw := p.internalLogWriter
+	wlw := p.internalWarnLogWriter
+	p.mu.Unlock()
+	// If ctrld was run without explicit verbose level,
+	// run the internal logging at debug level, so we could
+	// have enough information for troubleshooting.
+	if verbose == 0 {
+		for i := range writers {
+			w := &zerolog.FilteredLevelWriter{
+				Writer: zerolog.LevelWriterAdapter{Writer: writers[i]},
+				Level:  zerolog.NoticeLevel,
+			}
+			writers[i] = w
+		}
+		zerolog.SetGlobalLevel(zerolog.DebugLevel)
+	}
+	writers = append(writers, lw)
+	writers = append(writers, &zerolog.FilteredLevelWriter{
+		Writer: zerolog.LevelWriterAdapter{Writer: wlw},
+		Level:  zerolog.WarnLevel,
+	})
+	multi := zerolog.MultiLevelWriter(writers...)
+	l := mainLog.Load().Output(multi).With().Logger()
+	mainLog.Store(&l)
+	ctrld.ProxyLogger.Store(&l)
+}
+
+// needInternalLogging reports whether prog needs to run internal logging.
+func (p *prog) needInternalLogging() bool {
+	// Do not run in silent mode: the user explicitly asked for no logging, so
+	// ctrld must not create or write the persisted internal log file (nor reset
+	// the global level back to debug). See https://github.com/Control-D-Inc/ctrld/issues/320.
+	if silent {
+		return false
+	}
+	// Do not run in non-cd mode.
+	if cdUID == "" {
+		return false
+	}
+	// Do not run if there's already log file.
+	if p.cfg.Service.LogPath != "" {
+		return false
+	}
+	return true
+}
+
+func (p *prog) logReader() (*logReader, error) {
+	if p.needInternalLogging() {
+		p.mu.Lock()
+		lw := p.internalLogWriter
+		wlw := p.internalWarnLogWriter
+		p.mu.Unlock()
+		if lw == nil {
+			return nil, errors.New("nil internal log writer")
+		}
+		if wlw == nil {
+			return nil, errors.New("nil internal warn log writer")
+		}
+
+		// If we have a persisted log file, read from disk (includes data
+		// from previous runs that the in-memory buffer wouldn't have).
+		current, backup := lw.logFilePaths()
+		if current != "" {
+			return p.logReaderFromFiles(current, backup, wlw)
+		}
+
+		// Fall back to in-memory buffer.
+		lw.mu.Lock()
+		lwReader := bytes.NewReader(lw.buf.Bytes())
+		lwSize := lw.buf.Len()
+		lw.mu.Unlock()
+		// Warn log content.
+		wlw.mu.Lock()
+		wlwReader := bytes.NewReader(wlw.buf.Bytes())
+		wlwSize := wlw.buf.Len()
+		wlw.mu.Unlock()
+		reader := io.MultiReader(lwReader, bytes.NewReader([]byte(logWriterLogEndMarker)), wlwReader)
+		lr := &logReader{r: io.NopCloser(reader)}
+		lr.size = int64(lwSize + wlwSize)
+		if lr.size == 0 {
+			return nil, errors.New("internal log is empty")
+		}
+		return lr, nil
+	}
+	if p.cfg.Service.LogPath == "" {
+		return &logReader{r: io.NopCloser(strings.NewReader(""))}, nil
+	}
+	f, err := os.Open(normalizeLogFilePath(p.cfg.Service.LogPath))
+	if err != nil {
+		return nil, err
+	}
+	lr := &logReader{r: f}
+	if st, err := f.Stat(); err == nil {
+		lr.size = st.Size()
+	} else {
+		return nil, fmt.Errorf("f.Stat: %w", err)
+	}
+	if lr.size == 0 {
+		return nil, errors.New("log file is empty")
+	}
+	return lr, nil
+}
+
+// logReaderFromFiles builds a logReader that concatenates the backup file
+// (if it exists), the current log file, and the in-memory warn log buffer.
+func (p *prog) logReaderFromFiles(current, backup string, wlw *logWriter) (*logReader, error) {
+	var rcs []io.ReadCloser
+	var totalSize int64
+
+	closeAll := func() {
+		for _, rc := range rcs {
+			rc.Close()
+		}
+	}
+
+	// Read backup file first (older entries).
+	if backup != "" {
+		if bf, err := os.Open(backup); err == nil {
+			if st, err := bf.Stat(); err == nil {
+				totalSize += st.Size()
+			}
+			rcs = append(rcs, bf)
+		}
+	}
+
+	// Read current file.
+	cf, err := os.Open(current)
+	if err != nil {
+		closeAll()
+		return nil, fmt.Errorf("opening current log file: %w", err)
+	}
+	if st, err := cf.Stat(); err == nil {
+		totalSize += st.Size()
+	}
+	rcs = append(rcs, cf)
+
+	// Append warn log content from memory.
+	wlw.mu.Lock()
+	warnData := make([]byte, wlw.buf.Len())
+	copy(warnData, wlw.buf.Bytes())
+	wlw.mu.Unlock()
+
+	if len(warnData) > 0 {
+		rcs = append(rcs, io.NopCloser(bytes.NewReader([]byte(logWriterLogEndMarker))))
+		rcs = append(rcs, io.NopCloser(bytes.NewReader(warnData)))
+		totalSize += int64(len(logWriterLogEndMarker) + len(warnData))
+	}
+
+	if totalSize == 0 {
+		closeAll()
+		return nil, errors.New("internal log is empty")
+	}
+
+	readers := make([]io.Reader, len(rcs))
+	closers := make([]io.Closer, len(rcs))
+	for i, rc := range rcs {
+		readers[i] = rc
+		closers[i] = rc
+	}
+	combined := io.MultiReader(readers...)
+	lr := &logReader{
+		r:    &multiCloser{Reader: combined, closers: closers},
+		size: totalSize,
+	}
+	return lr, nil
+}
+
+// multiCloser wraps an io.Reader and closes multiple underlying closers.
+type multiCloser struct {
+	io.Reader
+	closers []io.Closer
+}
+
+func (mc *multiCloser) Close() error {
+	var firstErr error
+	for _, c := range mc.closers {
+		if err := c.Close(); err != nil && firstErr == nil {
+			firstErr = err
+		}
+	}
+	return firstErr
+}

cmd/cli/log_writer_silent_test.go

@@ -0,0 +1,66 @@
+package cli
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// Test_needInternalLogging_silent is a regression test for
+// https://github.com/Control-D-Inc/ctrld/issues/320: running with --silent must
+// not enable internal logging, otherwise ctrld creates and writes
+// <homedir>/ctrld.log (and, when verbose==0, resets the global level back to
+// debug) despite the user asking for silence.
+func Test_needInternalLogging_silent(t *testing.T) {
+	origSilent, origCdUID := silent, cdUID
+	t.Cleanup(func() { silent, cdUID = origSilent, origCdUID })
+
+	tests := []struct {
+		name    string
+		silent  bool
+		cdUID   string
+		logPath string
+		want    bool
+	}{
+		{"silent suppresses internal logging in cd mode", true, "test-uid", "", false},
+		{"cd mode enables internal logging", false, "test-uid", "", true},
+		{"non-cd mode disabled", false, "", "", false},
+		{"explicit log path disables internal logging", false, "test-uid", "/var/log/ctrld.log", false},
+	}
+	for _, tt := range tests {
+		tt := tt
+		t.Run(tt.name, func(t *testing.T) {
+			silent = tt.silent
+			cdUID = tt.cdUID
+			p := &prog{cfg: &ctrld.Config{}}
+			p.cfg.Service.LogPath = tt.logPath
+			if got := p.needInternalLogging(); got != tt.want {
+				t.Fatalf("needInternalLogging() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+// Test_initInternalLogging_silentCreatesNoFile drives the real initInternalLogging
+// path and asserts that a --silent --cd run does not create <homedir>/ctrld.log,
+// which is the observable failure reported in
+// https://github.com/Control-D-Inc/ctrld/issues/320.
+func Test_initInternalLogging_silentCreatesNoFile(t *testing.T) {
+	origSilent, origCdUID, origHomedir := silent, cdUID, homedir
+	t.Cleanup(func() { silent, cdUID, homedir = origSilent, origCdUID, origHomedir })
+
+	dir := t.TempDir()
+	homedir = dir
+	cdUID = "test-uid" // cd mode, which would otherwise enable internal logging
+	silent = true
+
+	p := &prog{cfg: &ctrld.Config{}}
+	p.initInternalLogging(nil)
+
+	logPath := filepath.Join(dir, logFileName)
+	if _, err := os.Stat(logPath); !os.IsNotExist(err) {
+		t.Fatalf("silent mode must not create %s (stat err = %v)", logPath, err)
+	}
+}

cmd/cli/log_writer_test.go

@@ -0,0 +1,210 @@
+package cli
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+)
+
+func Test_logWriter_Write(t *testing.T) {
+	size := 64 * 1024
+	lw := &logWriter{size: size}
+	lw.buf.Grow(lw.size)
+	data := strings.Repeat("A", size)
+	lw.Write([]byte(data))
+	if lw.buf.String() != data {
+		t.Fatalf("unexpected buf content: %v", lw.buf.String())
+	}
+	newData := "B"
+	halfData := strings.Repeat("A", len(data)/2) + logWriterInitEndMarker
+	lw.Write([]byte(newData))
+	if lw.buf.String() != halfData+newData {
+		t.Fatalf("unexpected new buf content: %v", lw.buf.String())
+	}
+
+	bigData := strings.Repeat("B", 256*1024)
+	expected := halfData + strings.Repeat("B", 16*1024)
+	lw.Write([]byte(bigData))
+	if lw.buf.String() != expected {
+		t.Fatalf("unexpected big buf content: %v", lw.buf.String())
+	}
+}
+
+func Test_logWriter_ConcurrentWrite(t *testing.T) {
+	size := 64 * 1024
+	lw := &logWriter{size: size}
+	n := 10
+	var wg sync.WaitGroup
+	wg.Add(n)
+	for i := 0; i < n; i++ {
+		go func() {
+			defer wg.Done()
+			lw.Write([]byte(strings.Repeat("A", i)))
+		}()
+	}
+	wg.Wait()
+	if lw.buf.Len() > lw.size {
+		t.Fatalf("unexpected buf size: %v, content: %q", lw.buf.Len(), lw.buf.String())
+	}
+}
+
+func Test_logWriter_MarkerInitEnd(t *testing.T) {
+	size := 64 * 1024
+	lw := &logWriter{size: size}
+	lw.buf.Grow(lw.size)
+
+	paddingSize := 10
+	// Writing half of the size, minus len(end marker) and padding size.
+	dataSize := size/2 - len(logWriterInitEndMarker) - paddingSize
+	data := strings.Repeat("A", dataSize)
+	// Inserting newline for making partial init data
+	data += "\n"
+	// Filling left over buffer to make the log full.
+	// The data length: len(end marker) + padding size - 1 (for newline above) + size/2
+	data += strings.Repeat("A", len(logWriterInitEndMarker)+paddingSize-1+(size/2))
+	lw.Write([]byte(data))
+	if lw.buf.String() != data {
+		t.Fatalf("unexpected buf content: %v", lw.buf.String())
+	}
+	lw.Write([]byte("B"))
+	lw.Write([]byte(strings.Repeat("B", 256*1024)))
+	firstIdx := strings.Index(lw.buf.String(), logWriterInitEndMarker)
+	lastIdx := strings.LastIndex(lw.buf.String(), logWriterInitEndMarker)
+	// Check if init end marker present.
+	if firstIdx == -1 || lastIdx == -1 {
+		t.Fatalf("missing init end marker: %s", lw.buf.String())
+	}
+	// Check if init end marker appears only once.
+	if firstIdx != lastIdx {
+		t.Fatalf("log init end marker appears more than once: %s", lw.buf.String())
+	}
+	// Ensure that we have the correct init log data.
+	if !strings.Contains(lw.buf.String(), strings.Repeat("A", dataSize)+logWriterInitEndMarker) {
+		t.Fatalf("unexpected log content: %s", lw.buf.String())
+	}
+}
+
+func Test_logWriter_SetLogFile(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.log")
+	lw := newLogWriterWithSize(logWriterSize)
+	if err := lw.setLogFile(path); err != nil {
+		t.Fatalf("setLogFile: %v", err)
+	}
+	defer lw.closeLogFile()
+
+	msg := "hello file\n"
+	lw.Write([]byte(msg))
+
+	// Verify data in memory buffer.
+	if lw.buf.String() != msg {
+		t.Fatalf("buffer: got %q, want %q", lw.buf.String(), msg)
+	}
+	// Verify data on disk.
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("ReadFile: %v", err)
+	}
+	if string(data) != msg {
+		t.Fatalf("file: got %q, want %q", data, msg)
+	}
+}
+
+func Test_logWriter_FileRotation(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.log")
+	// Use a tiny max size to trigger rotation quickly.
+	lw := newLogWriterWithSize(logWriterSize)
+	if err := lw.setLogFile(path); err != nil {
+		t.Fatalf("setLogFile: %v", err)
+	}
+	defer lw.closeLogFile()
+
+	// Write enough to exceed logFileMaxSize.
+	chunk := strings.Repeat("X", 1024) + "\n"
+	written := 0
+	for written < logFileMaxSize+1024 {
+		lw.Write([]byte(chunk))
+		written += len(chunk)
+	}
+
+	// Backup file should exist.
+	backupPath := path + ".1"
+	if _, err := os.Stat(backupPath); os.IsNotExist(err) {
+		t.Fatal("expected backup file to exist after rotation")
+	}
+
+	// Current file should be smaller than max (it was rotated).
+	st, err := os.Stat(path)
+	if err != nil {
+		t.Fatalf("stat current: %v", err)
+	}
+	if st.Size() > logFileMaxSize {
+		t.Fatalf("current file too large after rotation: %d", st.Size())
+	}
+}
+
+func Test_logWriter_FilePaths(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.log")
+	lw := newLogWriterWithSize(logWriterSize)
+
+	// No file configured.
+	c, b := lw.logFilePaths()
+	if c != "" || b != "" {
+		t.Fatalf("expected empty paths, got %q %q", c, b)
+	}
+
+	if err := lw.setLogFile(path); err != nil {
+		t.Fatalf("setLogFile: %v", err)
+	}
+	defer lw.closeLogFile()
+
+	// Current exists, no backup yet.
+	c, b = lw.logFilePaths()
+	if c != path {
+		t.Fatalf("current: got %q, want %q", c, path)
+	}
+	if b != "" {
+		t.Fatalf("backup should be empty, got %q", b)
+	}
+
+	// Create a backup file manually.
+	os.WriteFile(path+".1", []byte("old"), 0600)
+	_, b = lw.logFilePaths()
+	if b != path+".1" {
+		t.Fatalf("backup: got %q, want %q", b, path+".1")
+	}
+}
+
+func Test_logWriter_FileAppendOnRestart(t *testing.T) {
+	dir := t.TempDir()
+	path := filepath.Join(dir, "test.log")
+
+	// Simulate first run.
+	lw1 := newLogWriterWithSize(logWriterSize)
+	if err := lw1.setLogFile(path); err != nil {
+		t.Fatalf("setLogFile: %v", err)
+	}
+	lw1.Write([]byte("run1\n"))
+	lw1.closeLogFile()
+
+	// Simulate second run (restart) — file should be appended.
+	lw2 := newLogWriterWithSize(logWriterSize)
+	if err := lw2.setLogFile(path); err != nil {
+		t.Fatalf("setLogFile: %v", err)
+	}
+	lw2.Write([]byte("run2\n"))
+	lw2.closeLogFile()
+
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("ReadFile: %v", err)
+	}
+	want := "run1\nrun2\n"
+	if string(data) != want {
+		t.Fatalf("file: got %q, want %q", data, want)
+	}
+}

cmd/cli/loop.go

@@ -0,0 +1,145 @@
+package cli
+
+import (
+	"context"
+	"strings"
+	"sync"
+	"time"
+
+	"github.com/miekg/dns"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+const (
+	loopTestDomain = ".test"
+	loopTestQtype  = dns.TypeTXT
+)
+
+// newLoopGuard returns new loopGuard.
+func newLoopGuard() *loopGuard {
+	return &loopGuard{inflight: make(map[string]struct{})}
+}
+
+// loopGuard guards against DNS loop, ensuring only one query
+// for a given domain is processed at a time.
+type loopGuard struct {
+	mu       sync.Mutex
+	inflight map[string]struct{}
+}
+
+// TryLock marks the domain as being processed.
+func (lg *loopGuard) TryLock(domain string) bool {
+	lg.mu.Lock()
+	defer lg.mu.Unlock()
+	if _, inflight := lg.inflight[domain]; !inflight {
+		lg.inflight[domain] = struct{}{}
+		return true
+	}
+	return false
+}
+
+// Unlock marks the domain as being done.
+func (lg *loopGuard) Unlock(domain string) {
+	lg.mu.Lock()
+	defer lg.mu.Unlock()
+	delete(lg.inflight, domain)
+}
+
+// isLoop reports whether the given upstream config is detected as having DNS loop.
+func (p *prog) isLoop(uc *ctrld.UpstreamConfig) bool {
+	p.loopMu.Lock()
+	defer p.loopMu.Unlock()
+	return p.loop[uc.UID()]
+}
+
+// detectLoop checks if the given DNS message is initialized sent by ctrld.
+// If yes, marking the corresponding upstream as loop, prevent infinite DNS
+// forwarding loop.
+//
+// See p.checkDnsLoop for more details how it works.
+func (p *prog) detectLoop(msg *dns.Msg) {
+	if len(msg.Question) != 1 {
+		return
+	}
+	q := msg.Question[0]
+	if q.Qtype != loopTestQtype {
+		return
+	}
+	unFQDNname := strings.TrimSuffix(q.Name, ".")
+	uid := strings.TrimSuffix(unFQDNname, loopTestDomain)
+	p.loopMu.Lock()
+	if _, loop := p.loop[uid]; loop {
+		p.loop[uid] = loop
+	}
+	p.loopMu.Unlock()
+}
+
+// checkDnsLoop sends a message to check if there's any DNS forwarding loop
+// with all the upstreams. The way it works based on dnsmasq --dns-loop-detect.
+//
+// - Generating a TXT test query and sending it to all upstream.
+// - The test query is formed by upstream UID and test domain: <uid>.test
+// - If the test query returns to ctrld, mark the corresponding upstream as loop (see p.detectLoop).
+//
+// See: https://thekelleys.org.uk/dnsmasq/docs/dnsmasq-man.html
+func (p *prog) checkDnsLoop() {
+	mainLog.Load().Debug().Msg("start checking DNS loop")
+	upstream := make(map[string]*ctrld.UpstreamConfig)
+	p.loopMu.Lock()
+	for n, uc := range p.cfg.Upstream {
+		if p.um.isDown("upstream." + n) {
+			continue
+		}
+		// Do not send test query to external upstream.
+		if !canBeLocalUpstream(uc.Domain) {
+			mainLog.Load().Debug().Msgf("skipping external: upstream.%s", n)
+			continue
+		}
+		uid := uc.UID()
+		p.loop[uid] = false
+		upstream[uid] = uc
+	}
+	p.loopMu.Unlock()
+
+	for uid := range p.loop {
+		msg := loopTestMsg(uid)
+		uc := upstream[uid]
+		// Skipping upstream which is being marked as down.
+		if uc == nil {
+			continue
+		}
+		resolver, err := ctrld.NewResolver(uc)
+		if err != nil {
+			mainLog.Load().Warn().Err(err).Msgf("could not perform loop check for upstream: %q, endpoint: %q", uc.Name, uc.Endpoint)
+			continue
+		}
+		if _, err := resolver.Resolve(context.Background(), msg); err != nil {
+			mainLog.Load().Warn().Err(err).Msgf("could not send DNS loop check query for upstream: %q, endpoint: %q", uc.Name, uc.Endpoint)
+		}
+	}
+	mainLog.Load().Debug().Msg("end checking DNS loop")
+}
+
+// checkDnsLoopTicker performs p.checkDnsLoop every minute.
+func (p *prog) checkDnsLoopTicker(ctx context.Context) {
+	timer := time.NewTicker(time.Minute)
+	defer timer.Stop()
+	for {
+		select {
+		case <-p.stopCh:
+			return
+		case <-ctx.Done():
+			return
+		case <-timer.C:
+			p.checkDnsLoop()
+		}
+	}
+}
+
+// loopTestMsg generates DNS message for checking loop.
+func loopTestMsg(uid string) *dns.Msg {
+	msg := new(dns.Msg)
+	msg.SetQuestion(dns.Fqdn(uid+loopTestDomain), loopTestQtype)
+	return msg
+}

cmd/cli/loop_test.go

@@ -0,0 +1,42 @@
+package cli
+
+import (
+	"sync"
+	"sync/atomic"
+	"testing"
+)
+
+func Test_loopGuard(t *testing.T) {
+	lg := newLoopGuard()
+	key := "foo"
+
+	var i atomic.Int64
+	var started atomic.Int64
+	n := 1000
+	do := func() {
+		locked := lg.TryLock(key)
+		defer lg.Unlock(key)
+		started.Add(1)
+		for started.Load() < 2 {
+			// Wait until at least 2 goroutines started, otherwise, on system with heavy load,
+			// or having only 1 CPU, all goroutines can be scheduled to run consequently.
+		}
+		if locked {
+			i.Add(1)
+		}
+	}
+
+	var wg sync.WaitGroup
+	wg.Add(n)
+	for i := 0; i < n; i++ {
+		go func() {
+			defer wg.Done()
+			do()
+		}()
+	}
+	wg.Wait()
+
+	if i.Load() == int64(n) {
+		t.Fatalf("i must not be increased %d times", n)
+	}
+}

cmd/cli/main.go

@@ -0,0 +1,231 @@
+package cli
+
+import (
+	"encoding/hex"
+	"io"
+	"net"
+	"os"
+	"path/filepath"
+	"sync/atomic"
+	"time"
+
+	"github.com/kardianos/service"
+	"github.com/rs/zerolog"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+var (
+	configPath        string
+	configBase64      string
+	daemon            bool
+	listenAddress     string
+	primaryUpstream   string
+	secondaryUpstream string
+	domains           []string
+	logPath           string
+	homedir           string
+	cacheSize         int
+	cfg               ctrld.Config
+	verbose           int
+	silent            bool
+	cdUID             string
+	cdOrg             string
+	customHostname    string
+	cdDev             bool
+	iface             string
+	ifaceStartStop    string
+	nextdns           string
+	cdUpstreamProto   string
+	deactivationPin   int64
+	skipSelfChecks    bool
+	cleanup           bool
+	startOnly         bool
+	rfc1918           bool
+	interceptMode     string // "", "off", "dns", or "hard" — set via --intercept-mode flag or config
+	dnsIntercept      bool   // derived: interceptMode == "dns" || interceptMode == "hard"
+	hardIntercept     bool   // derived: interceptMode == "hard"
+
+	mainLog       atomic.Pointer[zerolog.Logger]
+	consoleWriter zerolog.ConsoleWriter
+	noConfigStart bool
+)
+
+const (
+	cdUidFlagName          = "cd"
+	cdOrgFlagName          = "cd-org"
+	customHostnameFlagName = "custom-hostname"
+	nextdnsFlagName        = "nextdns"
+
+	// autoIface is the sentinel --iface value meaning "use the default gateway interface".
+	autoIface = "auto"
+)
+
+func init() {
+	l := zerolog.New(io.Discard)
+	mainLog.Store(&l)
+}
+
+func Main() {
+	// Fast path for pf interception probe subprocess. This runs before cobra
+	// initialization to minimize startup time. The parent process spawns us with
+	// "pf-probe-send <host> <hex-dns-packet>" and a non-_ctrld GID so pf
+	// intercepts the DNS query. If pf rdr is working, the query reaches ctrld's
+	// listener; if not, it goes to the real DNS server and ctrld detects the miss.
+	if len(os.Args) >= 4 && os.Args[1] == "pf-probe-send" {
+		pfProbeSend(os.Args[2], os.Args[3])
+		return
+	}
+
+	ctrld.InitConfig(v, "ctrld")
+	initCLI()
+	if err := rootCmd.Execute(); err != nil {
+		mainLog.Load().Error().Msg(err.Error())
+		os.Exit(1)
+	}
+}
+
+func normalizeLogFilePath(logFilePath string) string {
+	if logFilePath == "" || filepath.IsAbs(logFilePath) || service.Interactive() {
+		return logFilePath
+	}
+	if homedir != "" {
+		return filepath.Join(homedir, logFilePath)
+	}
+	dir, _ := userHomeDir()
+	if dir == "" {
+		return logFilePath
+	}
+	return filepath.Join(dir, logFilePath)
+}
+
+// initConsoleLogging initializes console logging, then storing to mainLog.
+func initConsoleLogging() {
+	consoleWriter = zerolog.NewConsoleWriter(func(w *zerolog.ConsoleWriter) {
+		w.TimeFormat = time.StampMilli
+	})
+	multi := zerolog.MultiLevelWriter(consoleWriter)
+	l := mainLog.Load().Output(multi).With().Timestamp().Logger()
+	mainLog.Store(&l)
+
+	switch {
+	case silent:
+		zerolog.SetGlobalLevel(zerolog.NoLevel)
+	case verbose == 1:
+		ctrld.ProxyLogger.Store(&l)
+		zerolog.SetGlobalLevel(zerolog.InfoLevel)
+	case verbose > 1:
+		ctrld.ProxyLogger.Store(&l)
+		zerolog.SetGlobalLevel(zerolog.DebugLevel)
+	default:
+		zerolog.SetGlobalLevel(zerolog.NoticeLevel)
+	}
+}
+
+// initInteractiveLogging is like initLogging, but the ProxyLogger is discarded
+// to be used for all interactive commands.
+//
+// Current log file config will also be ignored.
+func initInteractiveLogging() {
+	old := cfg.Service.LogPath
+	cfg.Service.LogPath = ""
+	zerolog.TimeFieldFormat = time.RFC3339 + ".000"
+	initLoggingWithBackup(false)
+	cfg.Service.LogPath = old
+	l := zerolog.New(io.Discard)
+	ctrld.ProxyLogger.Store(&l)
+}
+
+// initLoggingWithBackup initializes log setup base on current config.
+// If doBackup is true, backup old log file with ".1" suffix.
+//
+// This is only used in runCmd for special handling in case of logging config
+// change in cd mode. Without special reason, the caller should use initLogging
+// wrapper instead of calling this function directly.
+func initLoggingWithBackup(doBackup bool) []io.Writer {
+	var writers []io.Writer
+	if logFilePath := normalizeLogFilePath(cfg.Service.LogPath); logFilePath != "" {
+		// Create parent directory if necessary.
+		if err := os.MkdirAll(filepath.Dir(logFilePath), 0750); err != nil {
+			mainLog.Load().Error().Msgf("failed to create log path: %v", err)
+			os.Exit(1)
+		}
+
+		// Default open log file in append mode.
+		flags := os.O_CREATE | os.O_RDWR | os.O_APPEND
+		if doBackup {
+			// Backup old log file with .1 suffix.
+			if err := os.Rename(logFilePath, logFilePath+oldLogSuffix); err != nil && !os.IsNotExist(err) {
+				mainLog.Load().Error().Msgf("could not backup old log file: %v", err)
+			} else {
+				// Backup was created, set flags for truncating old log file.
+				flags = os.O_CREATE | os.O_RDWR
+			}
+		}
+		logFile, err := openLogFile(logFilePath, flags)
+		if err != nil {
+			mainLog.Load().Error().Msgf("failed to create log file: %v", err)
+			os.Exit(1)
+		}
+		writers = append(writers, logFile)
+	}
+	writers = append(writers, consoleWriter)
+	multi := zerolog.MultiLevelWriter(writers...)
+	l := mainLog.Load().Output(multi).With().Logger()
+	mainLog.Store(&l)
+	// TODO: find a better way.
+	ctrld.ProxyLogger.Store(&l)
+
+	zerolog.SetGlobalLevel(zerolog.NoticeLevel)
+	logLevel := cfg.Service.LogLevel
+	switch {
+	case silent:
+		zerolog.SetGlobalLevel(zerolog.NoLevel)
+		return writers
+	case verbose == 1:
+		logLevel = "info"
+	case verbose > 1:
+		logLevel = "debug"
+	}
+	if logLevel == "" {
+		return writers
+	}
+	level, err := zerolog.ParseLevel(logLevel)
+	if err != nil {
+		mainLog.Load().Warn().Err(err).Msg("could not set log level")
+		return writers
+	}
+	zerolog.SetGlobalLevel(level)
+	return writers
+}
+
+func initCache() {
+	if !cfg.Service.CacheEnable {
+		return
+	}
+	if cfg.Service.CacheSize == 0 {
+		cfg.Service.CacheSize = 4096
+	}
+}
+
+// pfProbeSend is a minimal subprocess that sends a pre-built DNS query packet
+// to the specified host on port 53. It's invoked by probePFIntercept() with a
+// non-_ctrld GID so pf interception applies to the query.
+//
+// Usage: ctrld pf-probe-send <host> <hex-encoded-dns-packet>
+func pfProbeSend(host, hexPacket string) {
+	packet, err := hex.DecodeString(hexPacket)
+	if err != nil {
+		os.Exit(1)
+	}
+	conn, err := net.DialTimeout("udp", net.JoinHostPort(host, "53"), time.Second)
+	if err != nil {
+		os.Exit(1)
+	}
+	defer conn.Close()
+	conn.SetDeadline(time.Now().Add(time.Second))
+	_, _ = conn.Write(packet)
+	// Read response (don't care about result, just need the send to happen)
+	buf := make([]byte, 512)
+	_, _ = conn.Read(buf)
+}

cmd/cli/main_test.go

@@ -0,0 +1,76 @@
+package cli
+
+import (
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+	"sync"
+	"testing"
+
+	"github.com/rs/zerolog"
+)
+
+// logOutput is the log sink for the whole test binary. Tests share it with any
+// background goroutine the code under test starts (watchdogs, timers), so it
+// must tolerate concurrent writes.
+var logOutput syncBuffer
+
+// syncBuffer is a strings.Builder guarded by a mutex.
+type syncBuffer struct {
+	mu sync.Mutex
+	sb strings.Builder
+}
+
+func (b *syncBuffer) Write(p []byte) (int, error) {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return b.sb.Write(p)
+}
+
+func (b *syncBuffer) String() string {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return b.sb.String()
+}
+
+// envFakeVersionOutput makes this test binary impersonate a ctrld executable: when
+// set, the process writes the value to stdout and exits without running any test, so
+// binaryVersion() can be exercised on every platform without building or shipping a
+// fixture binary. The value envFakeVersionSilent produces no output at all, which
+// reproduces a ctrld.exe_previous that exists but reports no version.
+//
+// This must be handled before m.Run(), which is what parses the test flags: the child
+// is invoked as "<binary> --version" and would otherwise die on an unknown flag.
+const (
+	envFakeVersionOutput = "CTRLD_TEST_FAKE_VERSION_OUTPUT"
+	envFakeVersionSilent = "<silent>"
+)
+
+func TestMain(m *testing.M) {
+	if out := os.Getenv(envFakeVersionOutput); out != "" {
+		if out != envFakeVersionSilent {
+			fmt.Println(out)
+		}
+		os.Exit(0)
+	}
+
+	l := zerolog.New(&logOutput)
+	mainLog.Store(&l)
+
+	// Stub the self-upgrade command builder for the whole test binary. The real
+	// builder execs os.Executable() — which under `go test` IS this test binary
+	// — with positional args ("upgrade", ...). `go test` stops flag parsing at
+	// the first positional arg and ignores the rest, so the child just re-runs
+	// the entire suite, hits the upgrade tests again, and spawns more children:
+	// a fork bomb of detached processes that stalls the host and (on Windows)
+	// holds the test binary's image locked, breaking CI artifact cleanup.
+	// Point it at the test binary with a no-match -test.run so any test that
+	// reaches performUpgrade still exercises the cmd.Start() success path while
+	// the child exits immediately without recursing.
+	newUpgradeCmd = func(exe string) *exec.Cmd {
+		return exec.Command(exe, "-test.run=^$")
+	}
+
+	os.Exit(m.Run())
+}

cmd/cli/metrics.go

@@ -0,0 +1,166 @@
+package cli
+
+import (
+	"context"
+	"encoding/json"
+	"net"
+	"net/http"
+	"runtime"
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/collectors"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+	"github.com/prometheus/prom2json"
+)
+
+// metricsServer represents a server to expose Prometheus metrics via HTTP.
+type metricsServer struct {
+	server  *http.Server
+	mux     *http.ServeMux
+	reg     *prometheus.Registry
+	addr    string
+	started bool
+}
+
+// newMetricsServer returns new metrics server.
+func newMetricsServer(addr string, reg *prometheus.Registry) (*metricsServer, error) {
+	mux := http.NewServeMux()
+	ms := &metricsServer{
+		server: &http.Server{Handler: mux},
+		mux:    mux,
+		reg:    reg,
+	}
+	ms.addr = addr
+	ms.registerMetricsServerHandler()
+	return ms, nil
+}
+
+// register adds handlers for given pattern.
+func (ms *metricsServer) register(pattern string, handler http.Handler) {
+	ms.mux.Handle(pattern, handler)
+}
+
+// registerMetricsServerHandler adds handlers for metrics server.
+func (ms *metricsServer) registerMetricsServerHandler() {
+	ms.register("/metrics", promhttp.HandlerFor(
+		ms.reg,
+		promhttp.HandlerOpts{
+			EnableOpenMetrics: true,
+			Timeout:           10 * time.Second,
+		},
+	))
+	ms.register("/metrics/json", jsonResponse(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		g := prometheus.ToTransactionalGatherer(ms.reg)
+		mfs, done, err := g.Gather()
+		defer done()
+		if err != nil {
+			msg := "could not gather metrics"
+			mainLog.Load().Warn().Err(err).Msg(msg)
+			http.Error(w, msg, http.StatusInternalServerError)
+			return
+		}
+		result := make([]*prom2json.Family, 0, len(mfs))
+		for _, mf := range mfs {
+			result = append(result, prom2json.NewFamily(mf))
+		}
+		if err := json.NewEncoder(w).Encode(result); err != nil {
+			msg := "could not marshal metrics result"
+			mainLog.Load().Warn().Err(err).Msg(msg)
+			http.Error(w, msg, http.StatusInternalServerError)
+			return
+		}
+	})))
+}
+
+// start runs the metricsServer.
+func (ms *metricsServer) start() error {
+	listener, err := net.Listen("tcp", ms.addr)
+	if err != nil {
+		return err
+	}
+	go ms.server.Serve(listener)
+	ms.started = true
+	return nil
+}
+
+// stop shutdowns the metricsServer within 2 seconds timeout.
+func (ms *metricsServer) stop() error {
+	if !ms.started {
+		return nil
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*1)
+	defer cancel()
+	return ms.server.Shutdown(ctx)
+}
+
+// runMetricsServer initializes metrics stats and runs the metrics server if enabled.
+func (p *prog) runMetricsServer(ctx context.Context, reloadCh chan struct{}) {
+	if !p.metricsEnabled() {
+		return
+	}
+
+	// Reset all stats.
+	statsVersion.Reset()
+	statsQueriesCount.Reset()
+	statsClientQueriesCount.Reset()
+
+	reg := prometheus.NewRegistry()
+	// Register queries count stats if enabled.
+	if p.metricsQueryStats.Load() {
+		reg.MustRegister(statsQueriesCount)
+		reg.MustRegister(statsClientQueriesCount)
+	}
+
+	addr := p.cfg.Service.MetricsListener
+	if addr != "" {
+		host, port, err := net.SplitHostPort(addr)
+		if err != nil {
+			mainLog.Load().Warn().Err(err).Msgf("Invalid metrics listener address (%s); expected host:port", addr)
+		} else {
+			if host == "" {
+				host = "127.0.0.1"
+				addr = net.JoinHostPort(host, port)
+			}
+			ip := net.ParseIP(host)
+			if (ip != nil && !ip.IsLoopback()) || (ip == nil && host != "localhost") {
+				mainLog.Load().Warn().Msgf("Metrics server is bound to a non-loopback address (%s). This exposes sensitive data without authentication.", addr)
+			}
+		}
+	}
+
+	ms, err := newMetricsServer(addr, reg)
+	if err != nil {
+		mainLog.Load().Warn().Err(err).Msg("could not create new metrics server")
+		return
+	}
+	// Only start listener address if defined.
+	if addr != "" {
+		// Go runtime stats.
+		reg.MustRegister(collectors.NewBuildInfoCollector())
+		reg.MustRegister(collectors.NewGoCollector(
+			collectors.WithGoCollectorRuntimeMetrics(collectors.MetricsAll),
+		))
+		// ctrld stats.
+		reg.MustRegister(statsVersion)
+		statsVersion.WithLabelValues(commit, runtime.Version(), curVersion()).Inc()
+		reg.MustRegister(statsTimeStart)
+		statsTimeStart.Set(float64(time.Now().Unix()))
+		mainLog.Load().Debug().Msgf("starting metrics server on: %s", addr)
+		if err := ms.start(); err != nil {
+			mainLog.Load().Warn().Err(err).Msg("could not start metrics server")
+			return
+		}
+	}
+
+	select {
+	case <-p.stopCh:
+	case <-ctx.Done():
+	case <-reloadCh:
+	}
+
+	if err := ms.stop(); err != nil {
+		mainLog.Load().Warn().Err(err).Msg("could not stop metrics server")
+		return
+	}
+}

cmd/cli/net_darwin.go

@@ -0,0 +1,76 @@
+package cli
+
+import (
+	"bufio"
+	"bytes"
+	"io"
+	"net"
+	"os/exec"
+	"strings"
+)
+
+func patchNetIfaceName(iface *net.Interface) (bool, error) {
+	b, err := exec.Command("networksetup", "-listnetworkserviceorder").Output()
+	if err != nil {
+		return false, err
+	}
+
+	patched := false
+	if name := networkServiceName(iface.Name, bytes.NewReader(b)); name != "" {
+		patched = true
+		iface.Name = name
+	}
+	return patched, nil
+}
+
+func networkServiceName(ifaceName string, r io.Reader) string {
+	scanner := bufio.NewScanner(r)
+	prevLine := ""
+	for scanner.Scan() {
+		line := scanner.Text()
+		if strings.Contains(line, "*") {
+			// Network services is disabled.
+			continue
+		}
+		if !strings.Contains(line, "Device: "+ifaceName) {
+			prevLine = line
+			continue
+		}
+		parts := strings.SplitN(prevLine, " ", 2)
+		if len(parts) == 2 {
+			return strings.TrimSpace(parts[1])
+		}
+	}
+	return ""
+}
+
+// validInterface reports whether the *net.Interface is a valid one.
+func validInterface(iface *net.Interface, validIfacesMap map[string]struct{}) bool {
+	_, ok := validIfacesMap[iface.Name]
+	return ok
+}
+
+// validInterfacesMap returns a set of all valid hardware ports.
+func validInterfacesMap() map[string]struct{} {
+	b, err := exec.Command("networksetup", "-listallhardwareports").Output()
+	if err != nil {
+		return nil
+	}
+	return parseListAllHardwarePorts(bytes.NewReader(b))
+}
+
+// parseListAllHardwarePorts parses output of "networksetup -listallhardwareports"
+// and returns map presents all hardware ports.
+func parseListAllHardwarePorts(r io.Reader) map[string]struct{} {
+	m := make(map[string]struct{})
+	scanner := bufio.NewScanner(r)
+	for scanner.Scan() {
+		line := scanner.Text()
+		after, ok := strings.CutPrefix(line, "Device: ")
+		if !ok {
+			continue
+		}
+		m[after] = struct{}{}
+	}
+	return m
+}

cmd/cli/net_linux.go

@@ -0,0 +1,52 @@
+package cli
+
+import (
+	"net"
+	"net/netip"
+	"os"
+	"strings"
+
+	"tailscale.com/net/netmon"
+)
+
+func patchNetIfaceName(iface *net.Interface) (bool, error) { return true, nil }
+
+// validInterface reports whether the *net.Interface is a valid one.
+// Only non-virtual interfaces are considered valid.
+func validInterface(iface *net.Interface, validIfacesMap map[string]struct{}) bool {
+	_, ok := validIfacesMap[iface.Name]
+	return ok
+}
+
+// validInterfacesMap returns a set containing non virtual interfaces.
+func validInterfacesMap() map[string]struct{} {
+	m := make(map[string]struct{})
+	vis := virtualInterfaces()
+	netmon.ForeachInterface(func(i netmon.Interface, prefixes []netip.Prefix) {
+		if _, existed := vis[i.Name]; existed {
+			return
+		}
+		m[i.Name] = struct{}{}
+	})
+	// Fallback to default route interface if found nothing.
+	if len(m) == 0 {
+		defaultRoute, err := netmon.DefaultRoute()
+		if err != nil {
+			return m
+		}
+		m[defaultRoute.InterfaceName] = struct{}{}
+	}
+	return m
+}
+
+// virtualInterfaces returns a map of virtual interfaces on current machine.
+func virtualInterfaces() map[string]struct{} {
+	s := make(map[string]struct{})
+	entries, _ := os.ReadDir("/sys/devices/virtual/net")
+	for _, entry := range entries {
+		if entry.IsDir() {
+			s[strings.TrimSpace(entry.Name())] = struct{}{}
+		}
+	}
+	return s
+}

cmd/cli/net_others.go

@@ -0,0 +1,22 @@
+//go:build !darwin && !windows && !linux
+
+package cli
+
+import (
+	"net"
+
+	"tailscale.com/net/netmon"
+)
+
+func patchNetIfaceName(iface *net.Interface) (bool, error) { return true, nil }
+
+func validInterface(iface *net.Interface, validIfacesMap map[string]struct{}) bool { return true }
+
+// validInterfacesMap returns a set containing only default route interfaces.
+func validInterfacesMap() map[string]struct{} {
+	defaultRoute, err := netmon.DefaultRoute()
+	if err != nil {
+		return nil
+	}
+	return map[string]struct{}{defaultRoute.InterfaceName: {}}
+}

cmd/cli/net_windows.go

@@ -0,0 +1,93 @@
+package cli
+
+import (
+	"io"
+	"log"
+	"net"
+	"os"
+
+	"github.com/microsoft/wmi/pkg/base/host"
+	"github.com/microsoft/wmi/pkg/base/instance"
+	"github.com/microsoft/wmi/pkg/base/query"
+	"github.com/microsoft/wmi/pkg/constant"
+	"github.com/microsoft/wmi/pkg/hardware/network/netadapter"
+)
+
+func patchNetIfaceName(iface *net.Interface) (bool, error) {
+	return true, nil
+}
+
+// validInterface reports whether the *net.Interface is a valid one.
+// On Windows, only physical interfaces are considered valid.
+func validInterface(iface *net.Interface, validIfacesMap map[string]struct{}) bool {
+	_, ok := validIfacesMap[iface.Name]
+	return ok
+}
+
+// validInterfacesMap returns a set of all physical interfaces.
+func validInterfacesMap() map[string]struct{} {
+	m := make(map[string]struct{})
+	for _, ifaceName := range validInterfaces() {
+		m[ifaceName] = struct{}{}
+	}
+	return m
+}
+
+// validInterfaces returns a list of all physical interfaces.
+func validInterfaces() []string {
+	log.SetOutput(io.Discard)
+	defer log.SetOutput(os.Stderr)
+	whost := host.NewWmiLocalHost()
+	q := query.NewWmiQuery("MSFT_NetAdapter")
+	instances, err := instance.GetWmiInstancesFromHost(whost, string(constant.StadardCimV2), q)
+	if instances != nil {
+		defer instances.Close()
+	}
+	if err != nil {
+		mainLog.Load().Warn().Err(err).Msg("failed to get wmi network adapter")
+		return nil
+	}
+	var adapters []string
+	for _, i := range instances {
+		adapter, err := netadapter.NewNetworkAdapter(i)
+		if err != nil {
+			mainLog.Load().Warn().Err(err).Msg("failed to get network adapter")
+			continue
+		}
+
+		name, err := adapter.GetPropertyName()
+		if err != nil {
+			mainLog.Load().Warn().Err(err).Msg("failed to get interface name")
+			continue
+		}
+
+		// From: https://learn.microsoft.com/en-us/previous-versions/windows/desktop/legacy/hh968170(v=vs.85)
+		//
+		// "Indicates if a connector is present on the network adapter. This value is set to TRUE
+		// if this is a physical adapter or FALSE if this is not a physical adapter."
+		physical, err := adapter.GetPropertyConnectorPresent()
+		if err != nil {
+			mainLog.Load().Debug().Str("method", "validInterfaces").Str("interface", name).Msg("failed to get network adapter connector present property")
+			continue
+		}
+		if !physical {
+			mainLog.Load().Debug().Str("method", "validInterfaces").Str("interface", name).Msg("skipping non-physical adapter")
+			continue
+		}
+
+		// Check if it's a hardware interface. Checking only for connector present is not enough
+		// because some interfaces are not physical but have a connector.
+		hardware, err := adapter.GetPropertyHardwareInterface()
+		if err != nil {
+			mainLog.Load().Debug().Str("method", "validInterfaces").Str("interface", name).Msg("failed to get network adapter hardware interface property")
+			continue
+		}
+		if !hardware {
+			mainLog.Load().Debug().Str("method", "validInterfaces").Str("interface", name).Msg("skipping non-hardware interface")
+			continue
+		}
+
+		adapters = append(adapters, name)
+	}
+	return adapters
+}

cmd/cli/net_windows_test.go

@@ -0,0 +1,42 @@
+package cli
+
+import (
+	"bufio"
+	"bytes"
+	"slices"
+	"strings"
+	"testing"
+	"time"
+)
+
+func Test_validInterfaces(t *testing.T) {
+	verbose = 3
+	initConsoleLogging()
+	start := time.Now()
+	ifaces := validInterfaces()
+	t.Logf("Using Windows API takes: %d", time.Since(start).Milliseconds())
+
+	start = time.Now()
+	ifacesPowershell := validInterfacesPowershell()
+	t.Logf("Using Powershell takes: %d", time.Since(start).Milliseconds())
+
+	slices.Sort(ifaces)
+	slices.Sort(ifacesPowershell)
+	if !slices.Equal(ifaces, ifacesPowershell) {
+		t.Fatalf("result mismatch, want: %v, got: %v", ifacesPowershell, ifaces)
+	}
+}
+
+func validInterfacesPowershell() []string {
+	out, err := powershell("Get-NetAdapter -Physical | Select-Object -ExpandProperty Name")
+	if err != nil {
+		return nil
+	}
+	var res []string
+	scanner := bufio.NewScanner(bytes.NewReader(out))
+	for scanner.Scan() {
+		ifaceName := strings.TrimSpace(scanner.Text())
+		res = append(res, ifaceName)
+	}
+	return res
+}

cmd/cli/network_manager_linux.go

@@ -1,8 +1,9 @@
-package main
+package cli
 
 import (
 	"context"
 	"os"
+	"os/exec"
 	"path/filepath"
 	"time"
 
@@ -16,45 +17,56 @@ const (
 dns=none
 systemd-resolved=false
 `
-	nmSystemdUnitName   = "NetworkManager.service"
-	systemdEnabledState = "enabled"
+	nmSystemdUnitName = "NetworkManager.service"
 )
 
 var networkManagerCtrldConfFile = filepath.Join(nmConfDir, nmCtrldConfFilename)
 
+// hasNetworkManager reports whether NetworkManager executable found.
+func hasNetworkManager() bool {
+	exe, _ := exec.LookPath("NetworkManager")
+	return exe != ""
+}
+
 func setupNetworkManager() error {
+	if !hasNetworkManager() {
+		return nil
+	}
 	if content, _ := os.ReadFile(nmCtrldConfContent); string(content) == nmCtrldConfContent {
-		mainLog.Debug().Msg("NetworkManager already setup, nothing to do")
+		mainLog.Load().Debug().Msg("NetworkManager already setup, nothing to do")
 		return nil
 	}
 	err := os.WriteFile(networkManagerCtrldConfFile, []byte(nmCtrldConfContent), os.FileMode(0644))
 	if os.IsNotExist(err) {
-		mainLog.Debug().Msg("NetworkManager is not available")
+		mainLog.Load().Debug().Msg("NetworkManager is not available")
 		return nil
 	}
 	if err != nil {
-		mainLog.Debug().Err(err).Msg("could not write NetworkManager ctrld config file")
+		mainLog.Load().Debug().Err(err).Msg("could not write NetworkManager ctrld config file")
 		return err
 	}
 
 	reloadNetworkManager()
-	mainLog.Debug().Msg("setup NetworkManager done")
+	mainLog.Load().Debug().Msg("setup NetworkManager done")
 	return nil
 }
 
 func restoreNetworkManager() error {
+	if !hasNetworkManager() {
+		return nil
+	}
 	err := os.Remove(networkManagerCtrldConfFile)
 	if os.IsNotExist(err) {
-		mainLog.Debug().Msg("NetworkManager is not available")
+		mainLog.Load().Debug().Msg("NetworkManager is not available")
 		return nil
 	}
 	if err != nil {
-		mainLog.Debug().Err(err).Msg("could not remove NetworkManager ctrld config file")
+		mainLog.Load().Debug().Err(err).Msg("could not remove NetworkManager ctrld config file")
 		return err
 	}
 
 	reloadNetworkManager()
-	mainLog.Debug().Msg("restore NetworkManager done")
+	mainLog.Load().Debug().Msg("restore NetworkManager done")
 	return nil
 }
 
@@ -63,14 +75,15 @@ func reloadNetworkManager() {
 	defer cancel()
 	conn, err := dbus.NewSystemConnectionContext(ctx)
 	if err != nil {
-		mainLog.Error().Err(err).Msg("could not create new system connection")
+		mainLog.Load().Error().Err(err).Msg("could not create new system connection")
 		return
 	}
 	defer conn.Close()
 
 	waitCh := make(chan string)
 	if _, err := conn.ReloadUnitContext(ctx, nmSystemdUnitName, "ignore-dependencies", waitCh); err != nil {
-		mainLog.Debug().Err(err).Msg("could not reload NetworkManager")
+		mainLog.Load().Debug().Err(err).Msg("could not reload NetworkManager")
+		return
 	}
 	<-waitCh
 }

cmd/cli/network_manager_others.go

@@ -1,6 +1,6 @@
 //go:build !linux
 
-package main
+package cli
 
 func setupNetworkManager() error {
 	reloadNetworkManager()

cmd/cli/nextdns.go

@@ -0,0 +1,31 @@
+package cli
+
+import (
+	"fmt"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+const nextdnsURL = "https://dns.nextdns.io"
+
+func generateNextDNSConfig(uid string) {
+	if uid == "" {
+		return
+	}
+	mainLog.Load().Info().Msg("generating ctrld config for NextDNS resolver")
+	cfg = ctrld.Config{
+		Listener: map[string]*ctrld.ListenerConfig{
+			"0": {
+				IP:   "0.0.0.0",
+				Port: 53,
+			},
+		},
+		Upstream: map[string]*ctrld.UpstreamConfig{
+			"0": {
+				Type:     ctrld.ResolverTypeDOH3,
+				Endpoint: fmt.Sprintf("%s/%s", nextdnsURL, uid),
+				Timeout:  5000,
+			},
+		},
+	}
+}

cmd/cli/nocgo.go

@@ -0,0 +1,5 @@
+//go:build !cgo
+
+package cli
+
+const cgoEnabled = false

cmd/cli/nrpt_external_gp.go

@@ -0,0 +1,63 @@
+package cli
+
+import (
+	"errors"
+	"net/netip"
+	"strings"
+)
+
+const nrptRuleName = `CtrldCatchAll`
+
+// errGPNRPTVerified marks an intercept startup failure that happened while an externally
+// managed (Group Policy) NRPT catch-all was proved - by probe, not by registry shape
+// alone - to be routing DNS to this listener. It is the difference between "intercept
+// failed but DNS still reaches ctrld" and "intercept failed and nothing is filtering",
+// which is what decides whether the interface-DNS fallback must run.
+//
+// Only the Windows path produces it, but setDNS is shared, so the sentinel and its
+// predicate live here with the other platform-neutral NRPT helpers.
+var errGPNRPTVerified = errors.New("GP-managed NRPT verified routing to ctrld")
+
+// errGPNRPTIneffective marks a startup that ends with externally managed NRPT owning the
+// namespace while no probe has proved it routes to ctrld. DNS is not reaching ctrld, but
+// adapter DNS was deliberately preserved and no ctrld rule may be written beside an
+// administrator's catch-all - so this is a failed start that must not take the
+// interface-DNS fallback either.
+var errGPNRPTIneffective = errors.New("GP-managed NRPT owns the namespace but no probe reached ctrld")
+
+// interceptFailedWithVerifiedExternalDNS reports whether an intercept startup failure
+// happened while externally managed DNS policy was verified to be routing to ctrld.
+func interceptFailedWithVerifiedExternalDNS(err error) bool {
+	return errors.Is(err, errGPNRPTVerified)
+}
+
+// interceptFailedUnderExternalDNSPolicy reports whether an intercept startup failure
+// happened while externally managed DNS policy owned the namespace, whether or not it was
+// proved to route. Either way the interface-DNS fallback must not run: adapter DNS was
+// preserved on purpose, and rewriting it would violate the policy ctrld just deferred to.
+// Only the verified case is a successful start.
+func interceptFailedUnderExternalDNSPolicy(err error) bool {
+	return errors.Is(err, errGPNRPTVerified) || errors.Is(err, errGPNRPTIneffective)
+}
+
+// isExternalGPCatchAll recognizes only a single catch-all namespace that is not
+// ctrld's deterministic GP key. Registry access stays in the Windows file; this
+// pure classifier is shared with host-runnable tests.
+func isExternalGPCatchAll(ruleName string, namespaces []string) bool {
+	return ruleName != "" && !strings.EqualFold(ruleName, nrptRuleName) && len(namespaces) == 1 && strings.TrimSpace(namespaces[0]) == "."
+}
+
+func isMatchingGPNRPTRule(ruleName string, namespaces []string, dnsServers, listenerIP string) bool {
+	if !isExternalGPCatchAll(ruleName, namespaces) {
+		return false
+	}
+	server, err := netip.ParseAddr(strings.TrimSpace(dnsServers))
+	if err != nil {
+		return false
+	}
+	listener, err := netip.ParseAddr(strings.TrimSpace(listenerIP))
+	if err != nil {
+		return false
+	}
+	return server.Unmap() == listener.Unmap()
+}

cmd/cli/nrpt_external_gp_test.go

@@ -0,0 +1,129 @@
+package cli
+
+import (
+	"errors"
+	"fmt"
+	"testing"
+)
+
+func TestIsMatchingGPNRPTRule(t *testing.T) {
+	tests := []struct {
+		name       string
+		ruleName   string
+		namespaces []string
+		servers    string
+		listener   string
+		want       bool
+	}{
+		{
+			name:       "exact IPv4 catch-all",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{"."},
+			servers:    "127.0.0.1",
+			listener:   "127.0.0.1",
+			want:       true,
+		},
+		{
+			name:       "normalized IPv4-mapped listener",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{"."},
+			servers:    "::ffff:127.0.0.1",
+			listener:   "127.0.0.1",
+			want:       true,
+		},
+		{
+			name:       "ctrld GP key is not external",
+			ruleName:   "ctrldcatchall",
+			namespaces: []string{"."},
+			servers:    "127.0.0.1",
+			listener:   "127.0.0.1",
+		},
+		{
+			name:       "partial namespace",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{"corp.example"},
+			servers:    "127.0.0.1",
+			listener:   "127.0.0.1",
+		},
+		{
+			name:       "multiple namespaces",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{".", "corp.example"},
+			servers:    "127.0.0.1",
+			listener:   "127.0.0.1",
+		},
+		{
+			name:       "wrong listener",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{"."},
+			servers:    "127.0.0.2",
+			listener:   "127.0.0.1",
+		},
+		{
+			name:       "multiple nameservers",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{"."},
+			servers:    "127.0.0.1;127.0.0.2",
+			listener:   "127.0.0.1",
+		},
+		{
+			name:       "malformed nameserver",
+			ruleName:   "{A1B2C3D4}",
+			namespaces: []string{"."},
+			servers:    "localhost",
+			listener:   "127.0.0.1",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isMatchingGPNRPTRule(tt.ruleName, tt.namespaces, tt.servers, tt.listener); got != tt.want {
+				t.Fatalf("isMatchingGPNRPTRule() = %t, want %t", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestIsExternalGPCatchAll(t *testing.T) {
+	tests := []struct {
+		name       string
+		ruleName   string
+		namespaces []string
+		want       bool
+	}{
+		{name: "external catch-all", ruleName: "{GP-RULE}", namespaces: []string{"."}, want: true},
+		{name: "ctrld key", ruleName: nrptRuleName, namespaces: []string{"."}},
+		{name: "partial namespace", ruleName: "{GP-RULE}", namespaces: []string{"corp.example"}},
+		{name: "multiple namespaces", ruleName: "{GP-RULE}", namespaces: []string{".", "corp.example"}},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isExternalGPCatchAll(tt.ruleName, tt.namespaces); got != tt.want {
+				t.Fatalf("isExternalGPCatchAll() = %t, want %t", got, tt.want)
+			}
+		})
+	}
+}
+
+// TestInterceptFailedWithVerifiedExternalDNS covers the distinction the interface-DNS
+// fallback turns on. "A GP rule exists" is not enough: if it is not actually routing and
+// intercept failed too, skipping the fallback leaves the machine with no NRPT, no WFP and
+// no adapter DNS - that is, unfiltered. Only a probe-verified route earns the skip.
+func TestInterceptFailedWithVerifiedExternalDNS(t *testing.T) {
+	wfpErr := errors.New("FwpmEngineOpen0 failed: HRESULT 0x5")
+
+	verified := fmt.Errorf("dns intercept: WFP setup failed: %w: %w", wfpErr, errGPNRPTVerified)
+	if !interceptFailedWithVerifiedExternalDNS(verified) {
+		t.Error("a failure carrying errGPNRPTVerified must skip the interface-DNS fallback")
+	}
+	if !errors.Is(verified, wfpErr) {
+		t.Error("the underlying cause must stay inspectable for logs and callers")
+	}
+
+	if interceptFailedWithVerifiedExternalDNS(fmt.Errorf("dns intercept: WFP setup failed: %w", wfpErr)) {
+		t.Error("an unverified failure must take the interface-DNS fallback rather than leave the machine unfiltered")
+	}
+	if interceptFailedWithVerifiedExternalDNS(nil) {
+		t.Error("no error must not read as a verified external route")
+	}
+}

cmd/cli/nrpt_external_gp_windows_test.go

@@ -0,0 +1,20 @@
+//go:build windows
+
+package cli
+
+import "testing"
+
+func TestWFPStateNRPTPolicyOwner(t *testing.T) {
+	state := &wfpState{}
+	state.setNRPTPolicyOwner(nrptRuleOwnerGroupPolicy, "{GP-RULE}")
+	owner, ruleName := state.nrptPolicyOwner()
+	if owner != nrptRuleOwnerGroupPolicy || ruleName != "{GP-RULE}" {
+		t.Fatalf("owner = %v, rule = %q", owner, ruleName)
+	}
+
+	state.setNRPTPolicyOwner(nrptRuleOwnerCtrld, "")
+	owner, ruleName = state.nrptPolicyOwner()
+	if owner != nrptRuleOwnerCtrld || ruleName != "" {
+		t.Fatalf("owner = %v, rule = %q", owner, ruleName)
+	}
+}

cmd/cli/nrpt_recovery_limiter_windows.go

@@ -0,0 +1,101 @@
+//go:build windows
+
+package cli
+
+import (
+	"sync"
+	"time"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+const (
+	// Default to current behavior: keep recovering indefinitely unless configured.
+	defaultNRPTRecoveryMaxAttempts = 0
+	defaultNRPTRecoveryCooldown    = 30 * time.Minute
+
+	// Require more than one good health tick before clearing the circuit. A probe can
+	// pass briefly after delete/re-add even when another agent recreates broken NRPT state.
+	nrptRecoveryStableSuccessesToReset = 2
+)
+
+type nrptRecoveryLimiter struct {
+	mu              sync.Mutex
+	attempts        int
+	stableSuccesses int
+	cooldownUntil   time.Time
+	lastSkipLog     time.Time
+}
+
+func nrptRecoveryMaxAttempts(cfg *ctrld.Config) int {
+	if cfg != nil && cfg.Service.NRPTRecoveryMaxAttempts != nil {
+		return *cfg.Service.NRPTRecoveryMaxAttempts
+	}
+	return defaultNRPTRecoveryMaxAttempts
+}
+
+func nrptRecoveryCooldown(cfg *ctrld.Config) time.Duration {
+	if cfg != nil && cfg.Service.NRPTRecoveryCooldown != nil {
+		return *cfg.Service.NRPTRecoveryCooldown
+	}
+	return defaultNRPTRecoveryCooldown
+}
+
+func (l *nrptRecoveryLimiter) allow(now time.Time, cfg *ctrld.Config) (bool, time.Duration) {
+	maxAttempts := nrptRecoveryMaxAttempts(cfg)
+	if maxAttempts <= 0 {
+		return true, 0
+	}
+
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	if now.Before(l.cooldownUntil) {
+		return false, l.cooldownUntil.Sub(now)
+	}
+	return true, 0
+}
+
+func (l *nrptRecoveryLimiter) recordRecoveryFlow(now time.Time, cfg *ctrld.Config) {
+	maxAttempts := nrptRecoveryMaxAttempts(cfg)
+	if maxAttempts <= 0 {
+		return
+	}
+
+	cooldown := nrptRecoveryCooldown(cfg)
+	if cooldown <= 0 {
+		cooldown = defaultNRPTRecoveryCooldown
+	}
+
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	l.stableSuccesses = 0
+	l.attempts++
+	if l.attempts >= maxAttempts {
+		l.cooldownUntil = now.Add(cooldown)
+	}
+}
+
+func (l *nrptRecoveryLimiter) recordStableSuccess() {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	l.stableSuccesses++
+	if l.stableSuccesses >= nrptRecoveryStableSuccessesToReset {
+		l.attempts = 0
+		l.cooldownUntil = time.Time{}
+		l.lastSkipLog = time.Time{}
+	}
+}
+
+func (l *nrptRecoveryLimiter) shouldLogSkip(now time.Time) bool {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+
+	if l.lastSkipLog.IsZero() || now.Sub(l.lastSkipLog) >= 5*time.Minute {
+		l.lastSkipLog = now
+		return true
+	}
+	return false
+}

cmd/cli/nrpt_recovery_limiter_windows_test.go

@@ -0,0 +1,74 @@
+//go:build windows
+
+package cli
+
+import (
+	"testing"
+	"time"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestNRPTRecoveryLimiterCooldownAndStableReset(t *testing.T) {
+	maxAttempts := 2
+	cooldown := 10 * time.Minute
+	cfg := &ctrld.Config{}
+	cfg.Service.NRPTRecoveryMaxAttempts = &maxAttempts
+	cfg.Service.NRPTRecoveryCooldown = &cooldown
+
+	limiter := &nrptRecoveryLimiter{}
+	now := time.Unix(100, 0)
+
+	if ok, wait := limiter.allow(now, cfg); !ok || wait != 0 {
+		t.Fatalf("initial allow = %v, %v; want true, 0", ok, wait)
+	}
+
+	limiter.recordRecoveryFlow(now, cfg)
+	if ok, wait := limiter.allow(now.Add(time.Second), cfg); !ok || wait != 0 {
+		t.Fatalf("allow after first flow = %v, %v; want true, 0", ok, wait)
+	}
+
+	limiter.recordRecoveryFlow(now.Add(2*time.Second), cfg)
+	if ok, wait := limiter.allow(now.Add(3*time.Second), cfg); ok || wait <= 0 {
+		t.Fatalf("allow after max flows = %v, %v; want false, positive wait", ok, wait)
+	}
+
+	limiter.recordStableSuccess()
+	if ok, _ := limiter.allow(now.Add(4*time.Second), cfg); ok {
+		t.Fatal("one stable success cleared cooldown; want cooldown to remain")
+	}
+
+	limiter.recordStableSuccess()
+	if ok, wait := limiter.allow(now.Add(5*time.Second), cfg); !ok || wait != 0 {
+		t.Fatalf("allow after stable reset = %v, %v; want true, 0", ok, wait)
+	}
+}
+
+func TestNRPTRecoveryLimiterDefaultIsUnlimited(t *testing.T) {
+	cfg := &ctrld.Config{}
+	limiter := &nrptRecoveryLimiter{}
+	now := time.Unix(100, 0)
+
+	for i := 0; i < 10; i++ {
+		limiter.recordRecoveryFlow(now.Add(time.Duration(i)*time.Second), cfg)
+	}
+	if ok, wait := limiter.allow(now.Add(time.Hour), cfg); !ok || wait != 0 {
+		t.Fatalf("default allow after recovery flows = %v, %v; want true, 0", ok, wait)
+	}
+}
+
+func TestNRPTRecoveryLimiterUnlimited(t *testing.T) {
+	maxAttempts := 0
+	cfg := &ctrld.Config{}
+	cfg.Service.NRPTRecoveryMaxAttempts = &maxAttempts
+
+	limiter := &nrptRecoveryLimiter{}
+	now := time.Unix(100, 0)
+
+	for i := 0; i < 10; i++ {
+		limiter.recordRecoveryFlow(now.Add(time.Duration(i)*time.Second), cfg)
+	}
+	if ok, wait := limiter.allow(now.Add(time.Hour), cfg); !ok || wait != 0 {
+		t.Fatalf("unlimited allow = %v, %v; want true, 0", ok, wait)
+	}
+}

cmd/cli/os_darwin.go

@@ -0,0 +1,114 @@
+package cli
+
+import (
+	"bufio"
+	"bytes"
+	"fmt"
+	"net"
+	"os/exec"
+	"strings"
+
+	"github.com/Control-D-Inc/ctrld/internal/resolvconffile"
+)
+
+// allocate loopback ip
+// sudo ifconfig lo0 alias 127.0.0.2 up
+func allocateIP(ip string) error {
+	cmd := exec.Command("ifconfig", "lo0", "alias", ip, "up")
+	if err := cmd.Run(); err != nil {
+		mainLog.Load().Error().Err(err).Msg("allocateIP failed")
+		return err
+	}
+	return nil
+}
+
+func deAllocateIP(ip string) error {
+	cmd := exec.Command("ifconfig", "lo0", "-alias", ip)
+	if err := cmd.Run(); err != nil {
+		mainLog.Load().Error().Err(err).Msg("deAllocateIP failed")
+		return err
+	}
+	return nil
+}
+
+// setDnsIgnoreUnusableInterface likes setDNS, but return a nil error if the interface is not usable.
+func setDnsIgnoreUnusableInterface(iface *net.Interface, nameservers []string) error {
+	if err := setDNS(iface, nameservers); err != nil {
+		// TODO: investiate whether we can detect this without relying on error message.
+		if strings.Contains(err.Error(), " is not a recognized network service") {
+			return nil
+		}
+		return err
+	}
+	return nil
+}
+
+// set the dns server for the provided network interface
+// networksetup -setdnsservers Wi-Fi 8.8.8.8 1.1.1.1
+// TODO(cuonglm): use system API
+func setDNS(iface *net.Interface, nameservers []string) error {
+	// Note that networksetup won't modify search domains settings,
+	// This assignment is just a placeholder to silent linter.
+	_ = searchDomains
+	cmd := "networksetup"
+	args := []string{"-setdnsservers", iface.Name}
+	args = append(args, nameservers...)
+	if out, err := exec.Command(cmd, args...).CombinedOutput(); err != nil {
+		return fmt.Errorf("%v: %w", string(out), err)
+	}
+	return nil
+}
+
+// resetDnsIgnoreUnusableInterface likes resetDNS, but return a nil error if the interface is not usable.
+func resetDnsIgnoreUnusableInterface(iface *net.Interface) error {
+	if err := resetDNS(iface); err != nil {
+		// TODO: investiate whether we can detect this without relying on error message.
+		if strings.Contains(err.Error(), " is not a recognized network service") {
+			return nil
+		}
+		return err
+	}
+	return nil
+}
+
+// TODO(cuonglm): use system API
+func resetDNS(iface *net.Interface) error {
+	cmd := "networksetup"
+	args := []string{"-setdnsservers", iface.Name, "empty"}
+	if out, err := exec.Command(cmd, args...).CombinedOutput(); err != nil {
+		return fmt.Errorf("%v: %w", string(out), err)
+	}
+	return nil
+}
+
+// restoreDNS restores the DNS settings of the given interface.
+// this should only be executed upon turning off the ctrld service.
+func restoreDNS(iface *net.Interface) (err error) {
+	if ns := savedStaticNameservers(iface); len(ns) > 0 {
+		err = setDNS(iface, ns)
+	}
+	return err
+}
+
+func currentDNS(_ *net.Interface) []string {
+	return resolvconffile.NameServers()
+}
+
+// currentStaticDNS returns the current static DNS settings of given interface.
+func currentStaticDNS(iface *net.Interface) ([]string, error) {
+	cmd := "networksetup"
+	args := []string{"-getdnsservers", iface.Name}
+	out, err := exec.Command(cmd, args...).Output()
+	if err != nil {
+		return nil, err
+	}
+	scanner := bufio.NewScanner(bytes.NewReader(out))
+	var ns []string
+	for scanner.Scan() {
+		line := scanner.Text()
+		if ip := net.ParseIP(line); ip != nil {
+			ns = append(ns, ip.String())
+		}
+	}
+	return ns, nil
+}

cmd/cli/os_freebsd.go

@@ -0,0 +1,103 @@
+package cli
+
+import (
+	"net"
+	"net/netip"
+	"os/exec"
+
+	"tailscale.com/control/controlknobs"
+	"tailscale.com/health"
+	"tailscale.com/util/dnsname"
+
+	"github.com/Control-D-Inc/ctrld/internal/dns"
+	"github.com/Control-D-Inc/ctrld/internal/resolvconffile"
+)
+
+// allocate loopback ip
+// sudo ifconfig lo0 127.0.0.53 alias
+func allocateIP(ip string) error {
+	cmd := exec.Command("ifconfig", "lo0", ip, "alias")
+	if err := cmd.Run(); err != nil {
+		mainLog.Load().Error().Err(err).Msg("allocateIP failed")
+		return err
+	}
+	return nil
+}
+
+func deAllocateIP(ip string) error {
+	cmd := exec.Command("ifconfig", "lo0", ip, "-alias")
+	if err := cmd.Run(); err != nil {
+		mainLog.Load().Error().Err(err).Msg("deAllocateIP failed")
+		return err
+	}
+	return nil
+}
+
+// setDnsIgnoreUnusableInterface likes setDNS, but return a nil error if the interface is not usable.
+func setDnsIgnoreUnusableInterface(iface *net.Interface, nameservers []string) error {
+	return setDNS(iface, nameservers)
+}
+
+// set the dns server for the provided network interface
+func setDNS(iface *net.Interface, nameservers []string) error {
+	r, err := dns.NewOSConfigurator(logf, &health.Tracker{}, &controlknobs.Knobs{}, iface.Name)
+	if err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to create DNS OS configurator")
+		return err
+	}
+
+	ns := make([]netip.Addr, 0, len(nameservers))
+	for _, nameserver := range nameservers {
+		ns = append(ns, netip.MustParseAddr(nameserver))
+	}
+
+	osConfig := dns.OSConfig{
+		Nameservers:   ns,
+		SearchDomains: []dnsname.FQDN{},
+	}
+	if sds, err := searchDomains(); err == nil {
+		osConfig.SearchDomains = sds
+	} else {
+		mainLog.Load().Debug().Err(err).Msg("failed to get search domains list")
+	}
+
+	if err := r.SetDNS(osConfig); err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to set DNS")
+		return err
+	}
+	return nil
+}
+
+// resetDnsIgnoreUnusableInterface likes resetDNS, but return a nil error if the interface is not usable.
+func resetDnsIgnoreUnusableInterface(iface *net.Interface) error {
+	return resetDNS(iface)
+}
+
+func resetDNS(iface *net.Interface) error {
+	r, err := dns.NewOSConfigurator(logf, &health.Tracker{}, &controlknobs.Knobs{}, iface.Name)
+	if err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to create DNS OS configurator")
+		return err
+	}
+
+	if err := r.Close(); err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to rollback DNS setting")
+		return err
+	}
+	return nil
+}
+
+// restoreDNS restores the DNS settings of the given interface.
+// this should only be executed upon turning off the ctrld service.
+func restoreDNS(iface *net.Interface) (err error) {
+	return err
+}
+
+func currentDNS(_ *net.Interface) []string {
+	return resolvconffile.NameServers()
+}
+
+// currentStaticDNS returns the current static DNS settings of given interface.
+func currentStaticDNS(iface *net.Interface) ([]string, error) {
+	return currentDNS(iface), nil
+}

cmd/cli/os_linux.go

@@ -0,0 +1,314 @@
+package cli
+
+import (
+	"bufio"
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"net"
+	"net/netip"
+	"os/exec"
+	"slices"
+	"strings"
+	"syscall"
+	"time"
+
+	"github.com/insomniacslk/dhcp/dhcpv4/nclient4"
+	"github.com/insomniacslk/dhcp/dhcpv6"
+	"github.com/insomniacslk/dhcp/dhcpv6/client6"
+	"tailscale.com/control/controlknobs"
+	"tailscale.com/health"
+	"tailscale.com/util/dnsname"
+
+	"github.com/Control-D-Inc/ctrld/internal/dns"
+	ctrldnet "github.com/Control-D-Inc/ctrld/internal/net"
+	"github.com/Control-D-Inc/ctrld/internal/resolvconffile"
+)
+
+const resolvConfBackupFailedMsg = "open /etc/resolv.pre-ctrld-backup.conf: read-only file system"
+
+// allocate loopback ip
+// sudo ip a add 127.0.0.2/24 dev lo
+func allocateIP(ip string) error {
+	cmd := exec.Command("ip", "a", "add", ip+"/24", "dev", "lo")
+	if out, err := cmd.CombinedOutput(); err != nil {
+		mainLog.Load().Error().Err(err).Msgf("allocateIP failed: %s", string(out))
+		return err
+	}
+	return nil
+}
+
+func deAllocateIP(ip string) error {
+	cmd := exec.Command("ip", "a", "del", ip+"/24", "dev", "lo")
+	if err := cmd.Run(); err != nil {
+		mainLog.Load().Error().Err(err).Msg("deAllocateIP failed")
+		return err
+	}
+	return nil
+}
+
+const maxSetDNSAttempts = 5
+
+// setDnsIgnoreUnusableInterface likes setDNS, but return a nil error if the interface is not usable.
+func setDnsIgnoreUnusableInterface(iface *net.Interface, nameservers []string) error {
+	return setDNS(iface, nameservers)
+}
+
+func setDNS(iface *net.Interface, nameservers []string) error {
+	r, err := dns.NewOSConfigurator(logf, &health.Tracker{}, &controlknobs.Knobs{}, iface.Name)
+	if err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to create DNS OS configurator")
+		return err
+	}
+
+	ns := make([]netip.Addr, 0, len(nameservers))
+	for _, nameserver := range nameservers {
+		ns = append(ns, netip.MustParseAddr(nameserver))
+	}
+
+	osConfig := dns.OSConfig{
+		Nameservers:   ns,
+		SearchDomains: []dnsname.FQDN{},
+	}
+	if sds, err := searchDomains(); err == nil {
+		// Filter the root domain, since it's not allowed by systemd.
+		// See https://github.com/systemd/systemd/issues/9515
+		filteredSds := slices.DeleteFunc(sds, func(s dnsname.FQDN) bool {
+			return s == "" || s == "."
+		})
+		if len(filteredSds) != len(sds) {
+			mainLog.Load().Debug().Msg(`Removed root domain "." from search domains list`)
+		}
+		osConfig.SearchDomains = filteredSds
+	} else {
+		mainLog.Load().Debug().Err(err).Msg("failed to get search domains list")
+	}
+	trySystemdResolve := false
+	if err := r.SetDNS(osConfig); err != nil {
+		if strings.Contains(err.Error(), "Rejected send message") &&
+			strings.Contains(err.Error(), "org.freedesktop.network1.Manager") {
+			mainLog.Load().Warn().Msg("Interfaces are managed by systemd-networkd, switch to systemd-resolve for setting DNS")
+			trySystemdResolve = true
+			goto systemdResolve
+		}
+		// This error happens on read-only file system, which causes ctrld failed to create backup
+		// for /etc/resolv.conf file. It is ok, because the DNS is still set anyway, and restore
+		// DNS will fallback to use DHCP if there's no backup /etc/resolv.conf file.
+		// The error format is controlled by us, so checking for error string is fine.
+		// See: ../../internal/dns/direct.go:L278
+		if r.Mode() == "direct" && strings.Contains(err.Error(), resolvConfBackupFailedMsg) {
+			return nil
+		}
+		return err
+	}
+
+systemdResolve:
+	if trySystemdResolve {
+		// Stop systemd-networkd and retry setting DNS.
+		if out, err := exec.Command("systemctl", "stop", "systemd-networkd").CombinedOutput(); err != nil {
+			return fmt.Errorf("%s: %w", string(out), err)
+		}
+		args := []string{"--interface=" + iface.Name, "--set-domain=~"}
+		for _, nameserver := range nameservers {
+			args = append(args, "--set-dns="+nameserver)
+		}
+		for i := 0; i < maxSetDNSAttempts; i++ {
+			if out, err := exec.Command("systemd-resolve", args...).CombinedOutput(); err != nil {
+				return fmt.Errorf("%s: %w", string(out), err)
+			}
+			currentNS := currentDNS(iface)
+			if isSubSet(nameservers, currentNS) {
+				return nil
+			}
+			time.Sleep(time.Second)
+		}
+		mainLog.Load().Debug().Msg("DNS was not set for some reason")
+	}
+	return nil
+}
+
+// resetDnsIgnoreUnusableInterface likes resetDNS, but return a nil error if the interface is not usable.
+func resetDnsIgnoreUnusableInterface(iface *net.Interface) error {
+	return resetDNS(iface)
+}
+
+func resetDNS(iface *net.Interface) (err error) {
+	defer func() {
+		if err == nil {
+			return
+		}
+		// Start systemd-networkd if present.
+		if exe, _ := exec.LookPath("/lib/systemd/systemd-networkd"); exe != "" {
+			_ = exec.Command("systemctl", "start", "systemd-networkd").Run()
+		}
+		if r, oerr := dns.NewOSConfigurator(logf, &health.Tracker{}, &controlknobs.Knobs{}, iface.Name); oerr == nil {
+			_ = r.SetDNS(dns.OSConfig{})
+			if err := r.Close(); err != nil {
+				mainLog.Load().Error().Err(err).Msg("failed to rollback DNS setting")
+				return
+			}
+			err = nil
+		}
+	}()
+
+	var ns []string
+	c, err := nclient4.New(iface.Name)
+	if err != nil {
+		return fmt.Errorf("nclient4.New: %w", err)
+	}
+	defer c.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second*5)
+	defer cancel()
+	lease, err := c.Request(ctx)
+	if err != nil {
+		return fmt.Errorf("nclient4.Request: %w", err)
+	}
+	for _, nameserver := range lease.ACK.DNS() {
+		if nameserver.Equal(net.IPv4zero) {
+			continue
+		}
+		ns = append(ns, nameserver.String())
+	}
+
+	// TODO(cuonglm): handle DHCPv6 properly.
+	mainLog.Load().Debug().Msg("checking for IPv6 availability")
+	if ctrldnet.IPv6Available(ctx) {
+		c := client6.NewClient()
+		conversation, err := c.Exchange(iface.Name)
+		if err != nil && !errAddrInUse(err) {
+			mainLog.Load().Debug().Err(err).Msg("could not exchange DHCPv6")
+		}
+		for _, packet := range conversation {
+			if packet.Type() == dhcpv6.MessageTypeReply {
+				msg, err := packet.GetInnerMessage()
+				if err != nil {
+					mainLog.Load().Debug().Err(err).Msg("could not get inner DHCPv6 message")
+					return nil
+				}
+				nameservers := msg.Options.DNS()
+				for _, nameserver := range nameservers {
+					ns = append(ns, nameserver.String())
+				}
+			}
+		}
+	} else {
+		mainLog.Load().Debug().Msg("IPv6 is not available")
+	}
+
+	return ignoringEINTR(func() error {
+		return setDNS(iface, ns)
+	})
+}
+
+// restoreDNS restores the DNS settings of the given interface.
+// this should only be executed upon turning off the ctrld service.
+func restoreDNS(iface *net.Interface) (err error) {
+	return err
+}
+
+func currentDNS(iface *net.Interface) []string {
+	resolvconfFunc := func(_ string) []string { return resolvconffile.NameServers() }
+	for _, fn := range []getDNS{getDNSByResolvectl, getDNSBySystemdResolved, getDNSByNmcli, resolvconfFunc} {
+		if ns := fn(iface.Name); len(ns) > 0 {
+			return ns
+		}
+	}
+	return nil
+}
+
+// currentStaticDNS returns the current static DNS settings of given interface.
+func currentStaticDNS(iface *net.Interface) ([]string, error) {
+	return currentDNS(iface), nil
+}
+
+func getDNSByResolvectl(iface string) []string {
+	b, err := exec.Command("resolvectl", "dns", "-i", iface).Output()
+	if err != nil {
+		return nil
+	}
+
+	parts := strings.Fields(strings.SplitN(string(b), "%", 2)[0])
+	if len(parts) > 2 {
+		return parts[3:]
+	}
+	return nil
+}
+
+func getDNSBySystemdResolved(iface string) []string {
+	b, err := exec.Command("systemd-resolve", "--status", iface).Output()
+	if err != nil {
+		return nil
+	}
+	return getDNSBySystemdResolvedFromReader(bytes.NewReader(b))
+}
+
+func getDNSBySystemdResolvedFromReader(r io.Reader) []string {
+	scanner := bufio.NewScanner(r)
+	var ret []string
+	for scanner.Scan() {
+		line := strings.TrimSpace(scanner.Text())
+		if len(ret) > 0 {
+			if net.ParseIP(line) != nil {
+				ret = append(ret, line)
+			}
+			continue
+		}
+		after, found := strings.CutPrefix(line, "DNS Servers: ")
+		if !found {
+			continue
+		}
+		if net.ParseIP(after) != nil {
+			ret = append(ret, after)
+		}
+	}
+	return ret
+}
+
+func getDNSByNmcli(iface string) []string {
+	b, err := exec.Command("nmcli", "dev", "show", iface).Output()
+	if err != nil {
+		return nil
+	}
+	s := bufio.NewScanner(bytes.NewReader(b))
+	var dns []string
+	do := func(line string) {
+		parts := strings.SplitN(line, ":", 2)
+		if len(parts) > 1 {
+			dns = append(dns, strings.TrimSpace(parts[1]))
+		}
+	}
+	for s.Scan() {
+		line := s.Text()
+		switch {
+		case strings.HasPrefix(line, "IP4.DNS"):
+			fallthrough
+		case strings.HasPrefix(line, "IP6.DNS"):
+			do(line)
+		}
+	}
+	return dns
+}
+
+func ignoringEINTR(fn func() error) error {
+	for {
+		err := fn()
+		if err != syscall.EINTR {
+			return err
+		}
+	}
+}
+
+// isSubSet reports whether s2 contains all elements of s1.
+func isSubSet(s1, s2 []string) bool {
+	ok := true
+	for _, ns := range s1 {
+		if slices.Contains(s2, ns) {
+			continue
+		}
+		ok = false
+		break
+	}
+	return ok
+}

cmd/cli/os_linux_test.go

@@ -0,0 +1,23 @@
+package cli
+
+import (
+	"reflect"
+	"strings"
+	"testing"
+)
+
+func Test_getDNSBySystemdResolvedFromReader(t *testing.T) {
+	r := strings.NewReader(`Link 2 (eth0)
+      Current Scopes: DNS
+       LLMNR setting: yes
+MulticastDNS setting: no
+      DNSSEC setting: no
+    DNSSEC supported: no
+         DNS Servers: 8.8.8.8
+                      8.8.4.4`)
+	want := []string{"8.8.8.8", "8.8.4.4"}
+	ns := getDNSBySystemdResolvedFromReader(r)
+	if !reflect.DeepEqual(ns, want) {
+		t.Logf("unexpected result, want: %v, got: %v", want, ns)
+	}
+}

cmd/cli/os_others.go

@@ -1,6 +1,6 @@
 //go:build !linux && !darwin && !freebsd
 
-package main
+package cli
 
 // TODO(cuonglm): implement.
 func allocateIP(ip string) error {

cmd/cli/os_windows.go

@@ -0,0 +1,332 @@
+package cli
+
+import (
+	"bytes"
+	"errors"
+	"fmt"
+	"net"
+	"net/netip"
+	"os"
+	"os/exec"
+	"slices"
+	"strings"
+	"sync"
+
+	"golang.org/x/sys/windows"
+	"golang.org/x/sys/windows/registry"
+	"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
+
+	ctrldnet "github.com/Control-D-Inc/ctrld/internal/net"
+)
+
+const (
+	v4InterfaceKeyPathFormat = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\`
+	v6InterfaceKeyPathFormat = `SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces\`
+)
+
+var (
+	setDNSOnce   sync.Once
+	resetDNSOnce sync.Once
+)
+
+// setDnsIgnoreUnusableInterface likes setDNS, but return a nil error if the interface is not usable.
+func setDnsIgnoreUnusableInterface(iface *net.Interface, nameservers []string) error {
+	return setDNS(iface, nameservers)
+}
+
+// setDNS sets the dns server for the provided network interface
+func setDNS(iface *net.Interface, nameservers []string) error {
+	if len(nameservers) == 0 {
+		return errors.New("empty DNS nameservers")
+	}
+	setDNSOnce.Do(func() {
+		// If there's a Dns server running, that means we are on AD with Dns feature enabled.
+		// Configuring the Dns server to forward queries to ctrld instead.
+		if hasLocalDnsServerRunning() {
+			mainLog.Load().Debug().Msg("Local DNS server detected, configuring forwarders")
+
+			file := absHomeDir(windowsForwardersFilename)
+			mainLog.Load().Debug().Msgf("Using forwarders file: %s", file)
+
+			oldForwardersContent, err := os.ReadFile(file)
+			if err != nil {
+				mainLog.Load().Debug().Err(err).Msg("Could not read existing forwarders file")
+			} else {
+				mainLog.Load().Debug().Msgf("Existing forwarders content: %s", string(oldForwardersContent))
+			}
+
+			hasLocalIPv6Listener := needLocalIPv6Listener(interceptMode)
+			mainLog.Load().Debug().Bool("has_ipv6_listener", hasLocalIPv6Listener).Msg("IPv6 listener status")
+
+			forwarders := slices.DeleteFunc(slices.Clone(nameservers), func(s string) bool {
+				if !hasLocalIPv6Listener {
+					return false
+				}
+				return s == "::1"
+			})
+			mainLog.Load().Debug().Strs("forwarders", forwarders).Msg("Filtered forwarders list")
+
+			if err := os.WriteFile(file, []byte(strings.Join(forwarders, ",")), 0600); err != nil {
+				mainLog.Load().Warn().Err(err).Msg("could not save forwarders settings")
+			} else {
+				mainLog.Load().Debug().Msg("Successfully wrote new forwarders file")
+			}
+
+			oldForwarders := strings.Split(string(oldForwardersContent), ",")
+			mainLog.Load().Debug().Strs("old_forwarders", oldForwarders).Msg("Previous forwarders")
+
+			if err := addDnsServerForwarders(forwarders, oldForwarders); err != nil {
+				mainLog.Load().Warn().Err(err).Msg("could not set forwarders settings")
+			} else {
+				mainLog.Load().Debug().Msg("Successfully configured DNS server forwarders")
+			}
+		}
+	})
+	luid, err := winipcfg.LUIDFromIndex(uint32(iface.Index))
+	if err != nil {
+		return fmt.Errorf("setDNS: %w", err)
+	}
+	var (
+		serversV4 []netip.Addr
+		serversV6 []netip.Addr
+	)
+	for _, ns := range nameservers {
+		if addr, err := netip.ParseAddr(ns); err == nil {
+			if addr.Is4() {
+				serversV4 = append(serversV4, addr)
+			} else {
+				serversV6 = append(serversV6, addr)
+			}
+		}
+	}
+
+	// Note that Windows won't modify the current search domains if passing nil to luid.SetDNS function.
+	// searchDomains is still implemented for Windows just in case Windows API changes in future versions.
+	_ = searchDomains
+
+	if len(serversV4) == 0 && len(serversV6) == 0 {
+		return errors.New("invalid DNS nameservers")
+	}
+	if len(serversV4) > 0 {
+		if err := luid.SetDNS(windows.AF_INET, serversV4, nil); err != nil {
+			return fmt.Errorf("could not set DNS ipv4: %w", err)
+		}
+	}
+	if len(serversV6) > 0 {
+		if err := luid.SetDNS(windows.AF_INET6, serversV6, nil); err != nil {
+			return fmt.Errorf("could not set DNS ipv6: %w", err)
+		}
+	}
+	return nil
+}
+
+// resetDnsIgnoreUnusableInterface likes resetDNS, but return a nil error if the interface is not usable.
+func resetDnsIgnoreUnusableInterface(iface *net.Interface) error {
+	return resetDNS(iface)
+}
+
+// TODO(cuonglm): should we use system API?
+func resetDNS(iface *net.Interface) error {
+	resetDNSOnce.Do(func() {
+		// See corresponding comment in setDNS.
+		if hasLocalDnsServerRunning() {
+			file := absHomeDir(windowsForwardersFilename)
+			content, err := os.ReadFile(file)
+			if err != nil {
+				mainLog.Load().Error().Err(err).Msg("could not read forwarders settings")
+				return
+			}
+			nameservers := strings.Split(string(content), ",")
+			if err := removeDnsServerForwarders(nameservers); err != nil {
+				mainLog.Load().Error().Err(err).Msg("could not remove forwarders settings")
+				return
+			}
+		}
+	})
+
+	luid, err := winipcfg.LUIDFromIndex(uint32(iface.Index))
+	if err != nil {
+		return fmt.Errorf("resetDNS: %w", err)
+	}
+	// Restoring DHCP settings.
+	if err := luid.SetDNS(windows.AF_INET, nil, nil); err != nil {
+		return fmt.Errorf("could not reset DNS ipv4: %w", err)
+	}
+	if err := luid.SetDNS(windows.AF_INET6, nil, nil); err != nil {
+		return fmt.Errorf("could not reset DNS ipv6: %w", err)
+	}
+	return nil
+}
+
+// restoreDNS restores the DNS settings of the given interface.
+// this should only be executed upon turning off the ctrld service.
+func restoreDNS(iface *net.Interface) (err error) {
+	if nss := savedStaticNameservers(iface); len(nss) > 0 {
+		v4ns := make([]string, 0, 2)
+		v6ns := make([]string, 0, 2)
+		for _, ns := range nss {
+			if ctrldnet.IsIPv6(ns) {
+				v6ns = append(v6ns, ns)
+			} else {
+				v4ns = append(v4ns, ns)
+			}
+		}
+
+		luid, err := winipcfg.LUIDFromIndex(uint32(iface.Index))
+		if err != nil {
+			return fmt.Errorf("restoreDNS: %w", err)
+		}
+
+		if len(v4ns) > 0 {
+			mainLog.Load().Debug().Msgf("restoring IPv4 static DNS for interface %q: %v", iface.Name, v4ns)
+			if err := setDNS(iface, v4ns); err != nil {
+				return fmt.Errorf("restoreDNS (IPv4): %w", err)
+			}
+		} else {
+			mainLog.Load().Debug().Msgf("restoring IPv4 DHCP for interface %q", iface.Name)
+			if err := luid.SetDNS(windows.AF_INET, nil, nil); err != nil {
+				return fmt.Errorf("restoreDNS (IPv4 clear): %w", err)
+			}
+		}
+
+		if len(v6ns) > 0 {
+			mainLog.Load().Debug().Msgf("restoring IPv6 static DNS for interface %q: %v", iface.Name, v6ns)
+			if err := setDNS(iface, v6ns); err != nil {
+				return fmt.Errorf("restoreDNS (IPv6): %w", err)
+			}
+		} else {
+			mainLog.Load().Debug().Msgf("restoring IPv6 DHCP for interface %q", iface.Name)
+			if err := luid.SetDNS(windows.AF_INET6, nil, nil); err != nil {
+				return fmt.Errorf("restoreDNS (IPv6 clear): %w", err)
+			}
+		}
+	}
+	return err
+}
+
+func currentDNS(iface *net.Interface) []string {
+	luid, err := winipcfg.LUIDFromIndex(uint32(iface.Index))
+	if err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to get interface LUID")
+		return nil
+	}
+	nameservers, err := luid.DNS()
+	if err != nil {
+		mainLog.Load().Error().Err(err).Msg("failed to get interface DNS")
+		return nil
+	}
+	ns := make([]string, 0, len(nameservers))
+	for _, nameserver := range nameservers {
+		ns = append(ns, nameserver.String())
+	}
+	return ns
+}
+
+// currentStaticDNS checks both the IPv4 and IPv6 paths for static DNS values using keys
+// like "NameServer" and "ProfileNameServer".
+func currentStaticDNS(iface *net.Interface) ([]string, error) {
+	luid, err := winipcfg.LUIDFromIndex(uint32(iface.Index))
+	if err != nil {
+		return nil, fmt.Errorf("fallback winipcfg.LUIDFromIndex: %w", err)
+	}
+	guid, err := luid.GUID()
+	if err != nil {
+		return nil, fmt.Errorf("fallback luid.GUID: %w", err)
+	}
+
+	var ns []string
+	keyPaths := []string{v4InterfaceKeyPathFormat, v6InterfaceKeyPathFormat}
+	for _, path := range keyPaths {
+		interfaceKeyPath := path + guid.String()
+		k, err := registry.OpenKey(registry.LOCAL_MACHINE, interfaceKeyPath, registry.QUERY_VALUE)
+		if err != nil {
+			mainLog.Load().Debug().Err(err).Msgf("failed to open registry key %q for interface %q; trying next key", interfaceKeyPath, iface.Name)
+			continue
+		}
+		func() {
+			defer k.Close()
+			for _, keyName := range []string{"NameServer", "ProfileNameServer"} {
+				value, _, err := k.GetStringValue(keyName)
+				if err != nil && !errors.Is(err, registry.ErrNotExist) {
+					mainLog.Load().Debug().Err(err).Msgf("error reading %s registry key", keyName)
+					continue
+				}
+				if len(value) > 0 {
+					mainLog.Load().Debug().Msgf("found static DNS for interface %q: %s", iface.Name, value)
+					parsed := parseDNSServers(value)
+					for _, pns := range parsed {
+						if !slices.Contains(ns, pns) {
+							ns = append(ns, pns)
+						}
+					}
+				}
+			}
+		}()
+	}
+	if len(ns) == 0 {
+		mainLog.Load().Debug().Msgf("no static DNS values found for interface %q", iface.Name)
+	}
+	return ns, nil
+}
+
+// parseDNSServers splits a DNS server string that may be comma- or space-separated,
+// and trims any extraneous whitespace or null characters.
+func parseDNSServers(val string) []string {
+	fields := strings.FieldsFunc(val, func(r rune) bool {
+		return r == ' ' || r == ','
+	})
+	var servers []string
+	for _, f := range fields {
+		trimmed := strings.TrimSpace(f)
+		if len(trimmed) > 0 {
+			servers = append(servers, trimmed)
+		}
+	}
+	return servers
+}
+
+// addDnsServerForwarders adds given nameservers to DNS server forwarders list,
+// and also removing old forwarders if provided.
+func addDnsServerForwarders(nameservers, old []string) error {
+	newForwardersMap := make(map[string]struct{})
+	newForwarders := make([]string, len(nameservers))
+	for i := range nameservers {
+		newForwardersMap[nameservers[i]] = struct{}{}
+		newForwarders[i] = fmt.Sprintf("%q", nameservers[i])
+	}
+	oldForwarders := old[:0]
+	for _, fwd := range old {
+		if _, ok := newForwardersMap[fwd]; !ok {
+			oldForwarders = append(oldForwarders, fwd)
+		}
+	}
+	// NOTE: It is important to add new forwarder before removing old one.
+	//       Testing on Windows Server 2022 shows that removing forwarder1
+	//       then adding forwarder2 sometimes ends up adding both of them
+	//       to the forwarders list.
+	cmd := fmt.Sprintf("Add-DnsServerForwarder -IPAddress %s", strings.Join(newForwarders, ","))
+	if len(oldForwarders) > 0 {
+		cmd = fmt.Sprintf("%s ; Remove-DnsServerForwarder -IPAddress %s -Force", cmd, strings.Join(oldForwarders, ","))
+	}
+	if out, err := powershell(cmd); err != nil {
+		return fmt.Errorf("%w: %s", err, string(out))
+	}
+	return nil
+}
+
+// removeDnsServerForwarders removes given nameservers from DNS server forwarders list.
+func removeDnsServerForwarders(nameservers []string) error {
+	for _, ns := range nameservers {
+		cmd := fmt.Sprintf("Remove-DnsServerForwarder -IPAddress %s -Force", ns)
+		if out, err := powershell(cmd); err != nil {
+			return fmt.Errorf("%w: %s", err, string(out))
+		}
+	}
+	return nil
+}
+
+// powershell runs the given powershell command.
+func powershell(cmd string) ([]byte, error) {
+	out, err := exec.Command("powershell", "-Command", cmd).CombinedOutput()
+	return bytes.TrimSpace(out), err
+}

cmd/cli/os_windows_test.go

@@ -0,0 +1,68 @@
+package cli
+
+import (
+	"fmt"
+	"net"
+	"slices"
+	"strings"
+	"testing"
+	"time"
+
+	"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
+)
+
+func Test_currentStaticDNS(t *testing.T) {
+	iface, err := net.InterfaceByName(defaultIfaceName())
+	if err != nil {
+		t.Fatal(err)
+	}
+	start := time.Now()
+	staticDns, err := currentStaticDNS(iface)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Logf("Using Windows API takes: %d", time.Since(start).Milliseconds())
+
+	start = time.Now()
+	staticDnsPowershell, err := currentStaticDnsPowershell(iface)
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Logf("Using Powershell takes: %d", time.Since(start).Milliseconds())
+
+	slices.Sort(staticDns)
+	slices.Sort(staticDnsPowershell)
+	if !slices.Equal(staticDns, staticDnsPowershell) {
+		t.Fatalf("result mismatch, want: %v, got: %v", staticDnsPowershell, staticDns)
+	}
+}
+
+func currentStaticDnsPowershell(iface *net.Interface) ([]string, error) {
+	luid, err := winipcfg.LUIDFromIndex(uint32(iface.Index))
+	if err != nil {
+		return nil, err
+	}
+	guid, err := luid.GUID()
+	if err != nil {
+		return nil, err
+	}
+	var ns []string
+	for _, path := range []string{"HKLM:\\" + v4InterfaceKeyPathFormat, "HKLM:\\" + v6InterfaceKeyPathFormat} {
+		interfaceKeyPath := path + guid.String()
+		found := false
+		for _, key := range []string{"NameServer", "ProfileNameServer"} {
+			if found {
+				continue
+			}
+			cmd := fmt.Sprintf(`Get-ItemPropertyValue -Path "%s" -Name "%s"`, interfaceKeyPath, key)
+			out, err := powershell(cmd)
+			if err == nil && len(out) > 0 {
+				found = true
+				for _, e := range strings.Split(string(out), ",") {
+					ns = append(ns, strings.TrimRight(e, "\x00"))
+				}
+			}
+		}
+	}
+	return ns, nil
+}

cmd/cli/pf_ruleset.go

@@ -0,0 +1,79 @@
+package cli
+
+import (
+	"fmt"
+	"strings"
+)
+
+// pfNoRulesMarker is what pfctl prints for a ruleset that contains nothing.
+const pfNoRulesMarker = "(no rules)"
+
+// pfFilterRuleLines reduces pfctl output to the lines that are actually pf rules.
+//
+// It exists because every pfctl reader here uses CombinedOutput, and pfctl on macOS
+// writes "No ALTQ support in kernel" and "ALTQ related functions disabled" to stderr on
+// essentially every show command, so raw output is never a clean rule list. An empty
+// ruleset can also report "(no rules)", which is a status line rather than a rule.
+//
+// Two consequences follow from getting this wrong, and both have bitten this file:
+// callers that test the output for emptiness can never see empty, and callers that feed
+// the lines back into "pfctl -f -" would splice non-rule text into a ruleset and have
+// the reload rejected.
+//
+// Registry access and platform specifics stay elsewhere; this is pure string handling
+// so it can be tested on any host.
+func pfFilterRuleLines(output string) []string {
+	var rules []string
+	for _, line := range strings.Split(output, "\n") {
+		line = strings.TrimSpace(line)
+		if line == "" {
+			continue
+		}
+		// pfctl stderr warnings, merged in by CombinedOutput.
+		if strings.Contains(line, "ALTQ") {
+			continue
+		}
+		// Status line for an empty ruleset, not a rule.
+		if line == pfNoRulesMarker {
+			continue
+		}
+		rules = append(rules, line)
+	}
+	return rules
+}
+
+// pfRulesetEmpty reports whether pfctl output describes a ruleset with no rules.
+//
+// Use this rather than testing the raw output for emptiness: the merged stderr warnings
+// described above mean a raw test is always false, so the condition it guards - an
+// anchor whose contents were flushed - would never be detected.
+func pfRulesetEmpty(output string) bool {
+	return len(pfFilterRuleLines(output)) == 0
+}
+
+// pfContainsRule checks if any line in the slice contains the given rule string.
+// Uses substring matching because pfctl may append extra tokens like " all" to rules
+// (e.g., `rdr-anchor "com.controld.ctrld" all`), which would fail exact matching.
+func pfContainsRule(lines []string, rule string) bool {
+	for _, line := range lines {
+		if strings.Contains(line, rule) {
+			return true
+		}
+	}
+	return false
+}
+
+// pfAnchorReferencesPresent reports whether ctrld's anchor references appear in the
+// running ruleset, given the output of "pfctl -sn" and "pfctl -sr".
+//
+// Removing the references means reloading the entire main ruleset, and that reload
+// carries no options section - so it resets system-wide pf options, including any
+// third-party "set skip" directives. Doing that when there is nothing of ours to
+// remove is pure collateral damage, which is what a startup rollback would otherwise
+// cause after failing before the references were ever added.
+func pfAnchorReferencesPresent(natOutput, filterOutput, anchorName string) bool {
+	rdrAnchorRef := fmt.Sprintf("rdr-anchor %q", anchorName)
+	anchorRef := fmt.Sprintf("anchor %q", anchorName)
+	return pfContainsRule(pfFilterRuleLines(natOutput), rdrAnchorRef) ||
+		pfContainsRule(pfFilterRuleLines(filterOutput), anchorRef)
+}

cmd/cli/pf_ruleset_test.go

@@ -0,0 +1,157 @@
+package cli
+
+import "testing"
+
+// altqNoise is what macOS pfctl writes to stderr on show commands. Because every
+// pfctl reader here uses CombinedOutput, it lands in the middle of the data being
+// parsed — which is why these helpers exist.
+const altqNoise = "No ALTQ support in kernel\nALTQ related functions disabled\n"
+
+// TestPFRulesetEmpty is the regression guard for a flushed anchor being undetectable.
+//
+// The anchor-content checks in verifyPFState and ensurePFAnchorActive decide whether pf
+// still has ctrld's rules. Testing the raw pfctl output for emptiness can never be true
+// on macOS, because the merged ALTQ warnings are always present — so a genuinely flushed
+// anchor reads as healthy and neither the startup gate nor the watchdog restore fires.
+func TestPFRulesetEmpty(t *testing.T) {
+	tests := []struct {
+		name   string
+		output string
+		want   bool
+	}{
+		{
+			// The case that was broken: nothing but merged stderr.
+			name:   "only ALTQ warnings",
+			output: altqNoise,
+			want:   true,
+		},
+		{
+			// As captured on macOS 26.6 from "pfctl -sn -a com.controld.ctrld".
+			name:   "ALTQ warnings plus the empty-ruleset marker",
+			output: altqNoise + "(no rules)\n",
+			want:   true,
+		},
+		{
+			name:   "empty output",
+			output: "",
+			want:   true,
+		},
+		{
+			name:   "whitespace only",
+			output: "\n  \n\t\n",
+			want:   true,
+		},
+		{
+			name:   "a real rdr rule behind the warnings",
+			output: altqNoise + "rdr on lo0 inet proto udp from any to ! 127.0.0.1 port = 53 -> 127.0.0.1 port 5354\n",
+			want:   false,
+		},
+		{
+			name:   "a real filter rule behind the warnings",
+			output: altqNoise + "pass in quick on lo0 reply-to lo0 inet proto udp from any to 127.0.0.1 port = 5354\n",
+			want:   false,
+		},
+		{
+			name:   "rule with no warnings at all",
+			output: "anchor \"com.controld.ctrld\" all\n",
+			want:   false,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := pfRulesetEmpty(tc.output); got != tc.want {
+				t.Errorf("pfRulesetEmpty() = %v, want %v\noutput:\n%s", got, tc.want, tc.output)
+			}
+		})
+	}
+}
+
+// TestPFFilterRuleLines checks what survives filtering, since these lines are fed back
+// into "pfctl -f -" by the ruleset-rebuild paths. Splicing a warning or the
+// empty-ruleset marker into a ruleset would have the reload rejected outright.
+func TestPFFilterRuleLines(t *testing.T) {
+	got := pfFilterRuleLines(altqNoise + "(no rules)\nrdr-anchor \"com.controld.ctrld\" all\n\nanchor \"com.controld.ctrld\" all\n")
+	want := []string{
+		`rdr-anchor "com.controld.ctrld" all`,
+		`anchor "com.controld.ctrld" all`,
+	}
+	if len(got) != len(want) {
+		t.Fatalf("got %d lines %q, want %d %q", len(got), got, len(want), want)
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("line %d = %q, want %q", i, got[i], want[i])
+		}
+	}
+
+	if lines := pfFilterRuleLines(altqNoise); lines != nil {
+		t.Errorf("warnings alone must yield no rule lines, got %q", lines)
+	}
+}
+
+// TestPFAnchorReferencesPresent guards when the main ruleset may be rewritten.
+//
+// Removing our anchor references means reloading the whole main ruleset, and that
+// reload carries no options section — so it resets system-wide pf options, including
+// third-party "set skip" directives. Startup rollback runs after failures that happen
+// before the references were ever added, so without this check it would reset another
+// application's pf options while removing nothing of ours.
+func TestPFAnchorReferencesPresent(t *testing.T) {
+	const anchor = "com.controld.ctrld"
+	const otherAppRules = "scrub-anchor \"com.apple/*\" all fragment reassemble\nanchor \"com.vendor.vpn\" all\n"
+
+	tests := []struct {
+		name   string
+		nat    string
+		filter string
+		want   bool
+	}{
+		{
+			name:   "both references present",
+			nat:    altqNoise + "rdr-anchor \"com.controld.ctrld\" all\n",
+			filter: altqNoise + "anchor \"com.controld.ctrld\" all\n",
+			want:   true,
+		},
+		{
+			// pfctl appends tokens like " all", so matching is substring-based.
+			name:   "rdr reference only",
+			nat:    altqNoise + "rdr-anchor \"com.controld.ctrld\" all\n",
+			filter: altqNoise + otherAppRules,
+			want:   true,
+		},
+		{
+			name:   "filter reference only",
+			nat:    altqNoise,
+			filter: altqNoise + "anchor \"com.controld.ctrld\"\n",
+			want:   true,
+		},
+		{
+			// The rollback case: we failed before adding anything, and another
+			// application owns the ruleset. Rewriting it would be pure collateral.
+			name:   "someone else's ruleset, none of ours",
+			nat:    altqNoise,
+			filter: altqNoise + otherAppRules,
+			want:   false,
+		},
+		{
+			name:   "empty ruleset",
+			nat:    altqNoise + "(no rules)\n",
+			filter: altqNoise + "(no rules)\n",
+			want:   false,
+		},
+		{
+			// A different anchor whose name merely contains ours must not count.
+			name:   "another anchor with a similar name",
+			nat:    altqNoise,
+			filter: altqNoise + "anchor \"com.vendor.controld-shim\" all\n",
+			want:   false,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := pfAnchorReferencesPresent(tc.nat, tc.filter, anchor); got != tc.want {
+				t.Errorf("pfAnchorReferencesPresent() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}

cmd/cli/prog_darwin.go

@@ -0,0 +1,11 @@
+package cli
+
+import (
+	"github.com/kardianos/service"
+)
+
+func setDependencies(svc *service.Config) {}
+
+func setWorkingDirectory(svc *service.Config, dir string) {
+	svc.WorkingDirectory = dir
+}

cmd/cli/prog_freebsd.go

@@ -1,4 +1,4 @@
-package main
+package cli
 
 import (
 	"os"
@@ -6,12 +6,6 @@ import (
 	"github.com/kardianos/service"
 )
 
-func (p *prog) preRun() {
-	if !service.Interactive() {
-		p.setDNS()
-	}
-}
-
 func setDependencies(svc *service.Config) {
 	// TODO(cuonglm): remove once https://github.com/kardianos/service/issues/359 fixed.
 	_ = os.MkdirAll("/usr/local/etc/rc.d", 0755)

cmd/cli/prog_intercept_fallback_test.go

@@ -0,0 +1,275 @@
+package cli
+
+import (
+	"errors"
+	"fmt"
+	"net"
+	"slices"
+	"strings"
+	"testing"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+// TestInterfaceDNSFallbackViable covers when the interface-DNS fallback may be used
+// after DNS intercept fails to start.
+//
+// The fallback names a resolver by IP with no port, so it can only reach a listener on
+// :53. Taking it with the listener on a redirect-dependent port produced a total DNS
+// outage on macOS: the interface points at 127.0.0.1, mDNSResponder answers there, and
+// its upstream is ctrld's own address - a resolution loop with a healthy ctrld listener
+// nothing can reach. Intercept startup refuses the fallback in that case rather than
+// creating it.
+func TestInterfaceDNSFallbackViable(t *testing.T) {
+	tests := []struct {
+		name          string
+		lc            *ctrld.ListenerConfig
+		localResolver string
+		want          bool
+	}{
+		{
+			name: "listener on 53 can be reached by interface DNS",
+			lc:   &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 53},
+			want: true,
+		},
+		{
+			// The reported outage: no local resolver, so the :5354 fallback port
+			// cannot be expressed by interface DNS.
+			name: "listener on the fallback port cannot",
+			lc:   &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 5354},
+			want: false,
+		},
+		{
+			name: "any other non-53 port cannot",
+			lc:   &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 5300},
+			want: false,
+		},
+		{
+			// Router platforms with their own dnsmasq: it owns :53 and forwards to
+			// ctrld's port, so interface DNS reaches the listener through it.
+			// Refusing here would break a working EdgeOS/Firewalla setup.
+			name:          "non-53 listener behind a forwarding local resolver",
+			lc:            &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 5354},
+			localResolver: "192.168.1.1",
+			want:          true,
+		},
+		{
+			// Port is resolved elsewhere and defaults to 53; nothing to refuse yet.
+			name: "unset port is not refused",
+			lc:   &ctrld.ListenerConfig{IP: "127.0.0.1"},
+			want: true,
+		},
+		{
+			name: "no listener is not refused",
+			lc:   nil,
+			want: true,
+		},
+		{
+			// A non-loopback listener on 53 is still reachable by IP.
+			name: "non-loopback listener on 53",
+			lc:   &ctrld.ListenerConfig{IP: "192.168.1.10", Port: 53},
+			want: true,
+		},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			if got := interfaceDNSFallbackViable(tc.lc, tc.localResolver); got != tc.want {
+				t.Errorf("interfaceDNSFallbackViable() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}
+
+// interceptFallbackHarness drives setDNS() through the intercept-start failure path and
+// records the side effects that decide whether the host ends up with a working
+// resolver.
+//
+// Every host-touching step is stubbed, including the intercept start itself: this test
+// runs untagged on Linux, macOS and Windows runners, where the real startDNSIntercept
+// would set up pf or install an NRPT rule on the machine running the tests. Stubbing it
+// also makes the precondition deterministic - the failure under test is injected rather
+// than depending on the runner denying a privileged operation.
+type interceptFallbackHarness struct {
+	interceptCalls       int
+	ensureTargetCalls    int
+	ensuredNameservers   []string
+	installedNameservers []string
+	installCalls         int
+	resetCalls           int
+	removeTargetCalls    int
+	refusals             []string
+}
+
+func newInterceptFallbackHarness(t *testing.T, lc *ctrld.ListenerConfig) *interceptFallbackHarness {
+	t.Helper()
+	h := &interceptFallbackHarness{}
+
+	origStart, origEnsure, origRemove, origInstall := startDNSInterceptFn, ensureInterceptDNSTargetFn, removeInterceptDNSTargetFn, setDnsForRunningIfaceFn
+	origReset, origFatal := resetDNSFn, refuseFallbackFatal
+	origResolver := localResolverIPFn
+	origCfg, origMode, origIntercept, origHard := cfg, interceptMode, dnsIntercept, hardIntercept
+	t.Cleanup(func() {
+		startDNSInterceptFn, ensureInterceptDNSTargetFn, removeInterceptDNSTargetFn, setDnsForRunningIfaceFn = origStart, origEnsure, origRemove, origInstall
+		resetDNSFn, refuseFallbackFatal = origReset, origFatal
+		localResolverIPFn = origResolver
+		cfg, interceptMode, dnsIntercept, hardIntercept = origCfg, origMode, origIntercept, origHard
+	})
+
+	// Default to no local resolver: the desktop case. Router cases set it per test.
+	localResolverIPFn = func() string { return "" }
+
+	// Never reach the real interceptor: it would configure pf on macOS and NRPT on
+	// Windows, on the machine running the tests.
+	startDNSInterceptFn = func(_ *prog) error {
+		h.interceptCalls++
+		return errors.New("dns intercept: injected start failure")
+	}
+	ensureInterceptDNSTargetFn = func(_ *prog, nameservers []string) {
+		h.ensureTargetCalls++
+		h.ensuredNameservers = slices.Clone(nameservers)
+	}
+	removeInterceptDNSTargetFn = func(_ *prog, _ string) { h.removeTargetCalls++ }
+	setDnsForRunningIfaceFn = func(_ *prog, nameservers []string) *net.Interface {
+		h.installCalls++
+		h.installedNameservers = nameservers
+		return nil
+	}
+	resetDNSFn = func(_ *prog, _ bool, _ bool) { h.resetCalls++ }
+	refuseFallbackFatal = func(format string, v ...any) {
+		h.refusals = append(h.refusals, fmt.Sprintf(format, v...))
+	}
+
+	cfg = ctrld.Config{}
+	cfg.Service.InterceptMode = "dns"
+	cfg.Listener = map[string]*ctrld.ListenerConfig{"0": lc}
+	watchdogOff := false
+	cfg.Service.DnsWatchdogEnabled = &watchdogOff
+	interceptMode, dnsIntercept, hardIntercept = "dns", false, false
+	return h
+}
+
+func (h *interceptFallbackHarness) run(t *testing.T) {
+	t.Helper()
+	p := &prog{cfg: &cfg}
+	p.setDNS(nil)
+}
+
+func TestSetDNSEnsuresInterceptTargetAfterSuccessfulStart(t *testing.T) {
+	h := newInterceptFallbackHarness(t, &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 5354})
+	startDNSInterceptFn = func(_ *prog) error {
+		h.interceptCalls++
+		return nil
+	}
+	want := []string{"fe80::1"}
+	p := &prog{cfg: &cfg}
+	p.setDNS(want)
+
+	if h.interceptCalls != 1 {
+		t.Fatalf("intercept start called %d time(s), want 1", h.interceptCalls)
+	}
+	if h.ensureTargetCalls != 1 {
+		t.Fatalf("intercept DNS target ensured %d time(s), want 1 after successful start", h.ensureTargetCalls)
+	}
+	if !slices.Equal(h.ensuredNameservers, want) {
+		t.Fatalf("system nameservers = %v, want %v", h.ensuredNameservers, want)
+	}
+	if h.installCalls != 0 {
+		t.Fatalf("interface-DNS fallback installed %d time(s) after successful intercept start", h.installCalls)
+	}
+}
+
+func TestSetDNSExplicitOffOverridesConfig(t *testing.T) {
+	h := newInterceptFallbackHarness(t, &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 53})
+	interceptMode = "off"
+	dnsIntercept = false
+	hardIntercept = false
+
+	h.run(t)
+
+	if h.interceptCalls != 0 {
+		t.Fatalf("intercept start called %d time(s), want 0: explicit off must override service.intercept_mode", h.interceptCalls)
+	}
+	if h.installCalls != 1 {
+		t.Fatalf("interface DNS installed %d time(s), want 1", h.installCalls)
+	}
+	if h.removeTargetCalls != 1 {
+		t.Fatalf("stale intercept DNS target cleanup called %d time(s), want 1", h.removeTargetCalls)
+	}
+}
+
+// TestSetDNSRefusesUnreachableFallback is the behaviour test for the reported outage: it
+// drives the real setDNS() lifecycle rather than the classification helper alone.
+//
+// Deleting or bypassing the guard in setDNS makes the first case fail, because interface
+// DNS then gets installed pointing at a listener that cannot answer on :53 - which is
+// the resolution loop this refuses to create.
+func TestSetDNSRefusesUnreachableFallback(t *testing.T) {
+	t.Run("non-53 listener refuses the fallback and restores DNS", func(t *testing.T) {
+		h := newInterceptFallbackHarness(t, &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 5354})
+		h.run(t)
+
+		if h.interceptCalls != 1 {
+			t.Fatalf("intercept start called %d time(s) through the seam, want 1 — the real platform interceptor must never run here", h.interceptCalls)
+		}
+		if h.installCalls != 0 {
+			t.Errorf("interface DNS was installed %d time(s) for a listener on :5354 — that is the resolver loop", h.installCalls)
+		}
+		if h.resetCalls == 0 {
+			t.Error("host DNS was not restored before refusing, leaving the interface pointed at a ctrld that is not serving")
+		}
+		if h.removeTargetCalls != 1 {
+			t.Errorf("stale intercept DNS target cleanup called %d time(s), want 1 after intercept failure", h.removeTargetCalls)
+		}
+		if len(h.refusals) == 0 {
+			t.Fatal("refusal was not surfaced: startup must fail loudly rather than silently skip the fallback")
+		}
+		if !strings.Contains(h.refusals[0], "5354") {
+			t.Errorf("refusal does not name the unreachable port: %q", h.refusals[0])
+		}
+	})
+
+	t.Run("non-53 listener behind a local resolver still falls back", func(t *testing.T) {
+		// EdgeOS/Firewalla: dnsmasq owns :53 and forwards to ctrld's port, so the
+		// fallback works and must not be refused. setDNS points the interface at the
+		// resolver rather than at the listener.
+		h := newInterceptFallbackHarness(t, &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 5354})
+		localResolverIPFn = func() string { return "192.168.1.1" }
+		h.run(t)
+
+		if h.installCalls != 1 {
+			t.Errorf("interface DNS installed %d time(s), want 1: a forwarding local resolver makes the fallback usable", h.installCalls)
+		}
+		if len(h.refusals) != 0 {
+			t.Errorf("refused a fallback that a local resolver can serve: %v", h.refusals)
+		}
+		// Assert on membership, not on the exact set: setDNS appends platform-dependent
+		// entries beside the chosen nameserver - "::1" on Windows for the local IPv6
+		// listener, the RFC1918 addresses where those listeners are needed. What matters
+		// is that the interface points at the resolver and not at the listener IP, whose
+		// port the interface cannot express.
+		if !slices.Contains(h.installedNameservers, "192.168.1.1") {
+			t.Errorf("nameservers = %v, want the local resolver among them so queries reach ctrld through it", h.installedNameservers)
+		}
+		if slices.Contains(h.installedNameservers, "127.0.0.1") {
+			t.Errorf("nameservers = %v, must not name the listener IP: interface DNS cannot reach it on :5354", h.installedNameservers)
+		}
+	})
+
+	t.Run("listener on 53 still reaches the interface-DNS fallback", func(t *testing.T) {
+		h := newInterceptFallbackHarness(t, &ctrld.ListenerConfig{IP: "127.0.0.1", Port: 53})
+		h.run(t)
+
+		if h.interceptCalls != 1 {
+			t.Fatalf("intercept start called %d time(s) through the seam, want 1", h.interceptCalls)
+		}
+		if h.installCalls != 1 {
+			t.Errorf("interface DNS installed %d time(s), want 1: a listener on :53 is reachable, so the fallback must still apply", h.installCalls)
+		}
+		if len(h.refusals) != 0 {
+			t.Errorf("unexpected refusal for a reachable listener: %v", h.refusals)
+		}
+		if len(h.installedNameservers) == 0 {
+			t.Error("fallback installed no nameservers")
+		}
+	})
+}

cmd/cli/prog_linux.go

@@ -0,0 +1,68 @@
+package cli
+
+import (
+	"bufio"
+	"bytes"
+	"io"
+	"os"
+	"os/exec"
+	"strings"
+
+	"github.com/kardianos/service"
+
+	"github.com/Control-D-Inc/ctrld/internal/router"
+)
+
+func init() {
+	if isAndroid() {
+		return
+	}
+	if r, err := newLoopbackOSConfigurator(); err == nil {
+		useSystemdResolved = r.Mode() == "systemd-resolved"
+	}
+	// Disable quic-go's ECN support by default, see https://github.com/quic-go/quic-go/issues/3911
+	if os.Getenv("QUIC_GO_DISABLE_ECN") == "" {
+		os.Setenv("QUIC_GO_DISABLE_ECN", "true")
+	}
+}
+
+func setDependencies(svc *service.Config) {
+	svc.Dependencies = []string{
+		"Wants=network-online.target",
+		"After=network-online.target",
+		"Wants=NetworkManager-wait-online.service",
+		"After=NetworkManager-wait-online.service",
+		"Wants=nss-lookup.target",
+		"After=nss-lookup.target",
+	}
+	if out, _ := exec.Command("networkctl", "--no-pager").CombinedOutput(); len(out) > 0 {
+		if wantsSystemDNetworkdWaitOnline(bytes.NewReader(out)) {
+			svc.Dependencies = append(svc.Dependencies, "Wants=systemd-networkd-wait-online.service")
+		}
+	}
+	if routerDeps := router.ServiceDependencies(); len(routerDeps) > 0 {
+		svc.Dependencies = append(svc.Dependencies, routerDeps...)
+	}
+}
+
+func setWorkingDirectory(svc *service.Config, dir string) {
+	svc.WorkingDirectory = dir
+}
+
+// wantsSystemDNetworkdWaitOnline reports whether "systemd-networkd-wait-online" service
+// is required to be added to ctrld dependencies services.
+// The input reader r is the output of "networkctl --no-pager" command.
+func wantsSystemDNetworkdWaitOnline(r io.Reader) bool {
+	scanner := bufio.NewScanner(r)
+	// Skip header
+	scanner.Scan()
+	configured := false
+	for scanner.Scan() {
+		fields := strings.Fields(scanner.Text())
+		if len(fields) > 0 && fields[len(fields)-1] == "configured" {
+			configured = true
+			break
+		}
+	}
+	return configured
+}

cmd/cli/prog_linux_test.go

@@ -0,0 +1,48 @@
+package cli
+
+import (
+	"io"
+	"strings"
+	"testing"
+)
+
+const (
+	networkctlUnmanagedOutput = `IDX LINK            TYPE     OPERATIONAL SETUP    
+  1 lo              loopback carrier     unmanaged
+  2 wlp0s20f3       wlan     routable    unmanaged
+  3 tailscale0      none     routable    unmanaged
+  4 br-9ac33145e060 bridge   no-carrier  unmanaged
+  5 docker0         bridge   no-carrier  unmanaged
+
+5 links listed.
+`
+	networkctlManagedOutput = `IDX LINK            TYPE     OPERATIONAL SETUP    
+  1 lo              loopback carrier     unmanaged
+  2 wlp0s20f3       wlan     routable    configured
+  3 tailscale0      none     routable    unmanaged
+  4 br-9ac33145e060 bridge   no-carrier  unmanaged
+  5 docker0         bridge   no-carrier  unmanaged
+
+5 links listed.
+`
+)
+
+func Test_wantsSystemDNetworkdWaitOnline(t *testing.T) {
+	tests := []struct {
+		name     string
+		r        io.Reader
+		required bool
+	}{
+		{"unmanaged", strings.NewReader(networkctlUnmanagedOutput), false},
+		{"managed", strings.NewReader(networkctlManagedOutput), true},
+		{"empty", strings.NewReader(""), false},
+	}
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			if required := wantsSystemDNetworkdWaitOnline(tc.r); required != tc.required {
+				t.Errorf("wants %v got %v", tc.required, required)
+			}
+		})
+	}
+}

cmd/cli/prog_others.go

@@ -1,11 +1,9 @@
-//go:build !linux && !freebsd
+//go:build !linux && !freebsd && !darwin && !windows
 
-package main
+package cli
 
 import "github.com/kardianos/service"
 
-func (p *prog) preRun() {}
-
 func setDependencies(svc *service.Config) {}
 
 func setWorkingDirectory(svc *service.Config, dir string) {

cmd/cli/prog_test.go

@@ -0,0 +1,305 @@
+package cli
+
+import (
+	"context"
+	"net"
+	"net/url"
+	"runtime"
+	"syscall"
+	"testing"
+	"time"
+
+	"github.com/Masterminds/semver/v3"
+	"github.com/rs/zerolog"
+	"github.com/stretchr/testify/assert"
+
+	"github.com/Control-D-Inc/ctrld"
+)
+
+func TestErrNetworkErrorTreatsNoRouteAsNetworkError(t *testing.T) {
+	err := &net.OpError{Op: "dial", Net: "tcp", Err: syscall.EHOSTUNREACH}
+	assert.True(t, errNetworkError(err))
+	assert.True(t, errUrlNetworkError(&url.Error{Op: "Get", URL: "https://dns.controld.com", Err: err}))
+}
+
+func TestSleepWithContext(t *testing.T) {
+	assert.True(t, sleepWithContext(context.Background(), time.Millisecond))
+
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	start := time.Now()
+	assert.False(t, sleepWithContext(ctx, time.Minute))
+	assert.Less(t, time.Since(start), 100*time.Millisecond)
+}
+
+func TestUnreachableRecoveryBackoff(t *testing.T) {
+	// Streak starts at the base cadence and doubles each attempt, capped at the max.
+	assert.Equal(t, checkUpstreamBackoffSleep, unreachableRecoveryBackoff(0))
+	assert.Equal(t, checkUpstreamBackoffSleep, unreachableRecoveryBackoff(1))
+	assert.Equal(t, 2*checkUpstreamBackoffSleep, unreachableRecoveryBackoff(2))
+	assert.Equal(t, 4*checkUpstreamBackoffSleep, unreachableRecoveryBackoff(3))
+	assert.Equal(t, checkUpstreamUnreachableBackoffMax, unreachableRecoveryBackoff(100))
+}
+
+func Test_prog_dnsWatchdogEnabled(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{}}
+
+	// Default value is true.
+	assert.True(t, p.dnsWatchdogEnabled())
+
+	tests := []struct {
+		name    string
+		enabled bool
+	}{
+		{"enabled", true},
+		{"disabled", false},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			p.cfg.Service.DnsWatchdogEnabled = &tc.enabled
+			assert.Equal(t, tc.enabled, p.dnsWatchdogEnabled())
+		})
+	}
+}
+
+func Test_prog_dnsWatchdogInterval(t *testing.T) {
+	p := &prog{cfg: &ctrld.Config{}}
+
+	// Default value is 20s.
+	assert.Equal(t, dnsWatchdogDefaultInterval, p.dnsWatchdogDuration())
+
+	tests := []struct {
+		name     string
+		duration time.Duration
+		expected time.Duration
+	}{
+		{"valid", time.Minute, time.Minute},
+		{"zero", 0, dnsWatchdogDefaultInterval},
+		{"nagative", time.Duration(-1 * time.Minute), dnsWatchdogDefaultInterval},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			p.cfg.Service.DnsWatchdogInvterval = &tc.duration
+			assert.Equal(t, tc.expected, p.dnsWatchdogDuration())
+		})
+	}
+}
+
+func Test_shouldUpgrade(t *testing.T) {
+	// Helper function to create a version
+	makeVersion := func(v string) *semver.Version {
+		ver, err := semver.NewVersion(v)
+		if err != nil {
+			t.Fatalf("failed to create version %s: %v", v, err)
+		}
+		return ver
+	}
+
+	tests := []struct {
+		name           string
+		versionTarget  string
+		currentVersion *semver.Version
+		shouldUpgrade  bool
+		description    string
+	}{
+		{
+			name:           "empty version target",
+			versionTarget:  "",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when version target is empty",
+		},
+		{
+			name:           "invalid version target",
+			versionTarget:  "invalid-version",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when version target is invalid",
+		},
+		{
+			name:           "same version",
+			versionTarget:  "v1.0.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when target version equals current version",
+		},
+		{
+			name:           "older version",
+			versionTarget:  "v1.0.0",
+			currentVersion: makeVersion("v1.1.0"),
+			shouldUpgrade:  false,
+			description:    "should skip upgrade when target version is older than current version",
+		},
+		{
+			name:           "patch upgrade allowed",
+			versionTarget:  "v1.0.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow patch version upgrade within same major version",
+		},
+		{
+			name:           "minor upgrade allowed",
+			versionTarget:  "v1.1.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow minor version upgrade within same major version",
+		},
+		{
+			name:           "major upgrade blocked",
+			versionTarget:  "v2.0.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block major version upgrade",
+		},
+		{
+			name:           "major downgrade blocked",
+			versionTarget:  "v1.0.0",
+			currentVersion: makeVersion("v2.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block major version downgrade",
+		},
+		{
+			name:           "version without v prefix",
+			versionTarget:  "1.0.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should handle version target without v prefix",
+		},
+		{
+			name:           "complex version upgrade allowed",
+			versionTarget:  "v1.5.3",
+			currentVersion: makeVersion("v1.4.2"),
+			shouldUpgrade:  true,
+			description:    "should allow complex version upgrade within same major version",
+		},
+		{
+			name:           "complex major upgrade blocked",
+			versionTarget:  "v3.1.0",
+			currentVersion: makeVersion("v2.5.3"),
+			shouldUpgrade:  false,
+			description:    "should block complex major version upgrade",
+		},
+		{
+			name:           "pre-release version upgrade allowed",
+			versionTarget:  "v1.0.1-beta.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow pre-release version upgrade within same major version",
+		},
+		{
+			name:           "pre-release major upgrade blocked",
+			versionTarget:  "v2.0.0-alpha.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block pre-release major version upgrade",
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			// Create test logger
+			testLogger := zerolog.New(zerolog.NewTestWriter(t)).With().Logger()
+
+			// Call the function and capture the result
+			result := shouldUpgrade(tc.versionTarget, tc.currentVersion, &testLogger)
+
+			// Assert the expected result
+			assert.Equal(t, tc.shouldUpgrade, result, tc.description)
+		})
+	}
+}
+
+func Test_selfUpgradeCheck(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("skipped due to Windows file locking issue on Github Action runners")
+	}
+
+	// Helper function to create a version
+	makeVersion := func(v string) *semver.Version {
+		ver, err := semver.NewVersion(v)
+		if err != nil {
+			t.Fatalf("failed to create version %s: %v", v, err)
+		}
+		return ver
+	}
+
+	tests := []struct {
+		name           string
+		versionTarget  string
+		currentVersion *semver.Version
+		shouldUpgrade  bool
+		description    string
+	}{
+		{
+			name:           "upgrade allowed",
+			versionTarget:  "v1.0.1",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  true,
+			description:    "should allow upgrade and attempt to perform it",
+		},
+		{
+			name:           "upgrade blocked",
+			versionTarget:  "v2.0.0",
+			currentVersion: makeVersion("v1.0.0"),
+			shouldUpgrade:  false,
+			description:    "should block upgrade and not attempt to perform it",
+		},
+	}
+
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			// Create test logger
+			testLogger := zerolog.New(zerolog.NewTestWriter(t)).With().Logger()
+
+			// Call the function and capture the result
+			result := selfUpgradeCheck(tc.versionTarget, tc.currentVersion, &testLogger)
+
+			// Assert the expected result
+			assert.Equal(t, tc.shouldUpgrade, result, tc.description)
+		})
+	}
+}
+
+func Test_performUpgrade(t *testing.T) {
+	if runtime.GOOS == "windows" {
+		t.Skip("skipped due to Windows file locking issue on Github Action runners")
+	}
+
+	tests := []struct {
+		name           string
+		versionTarget  string
+		expectedResult bool
+		description    string
+	}{
+		{
+			name:           "valid version target",
+			versionTarget:  "v1.0.1",
+			expectedResult: true,
+			description:    "should attempt to perform upgrade with valid version target",
+		},
+		{
+			name:           "empty version target",
+			versionTarget:  "",
+			expectedResult: true,
+			description:    "should attempt to perform upgrade even with empty version target",
+		},
+	}
+
+	// newUpgradeCmd is stubbed in TestMain so performUpgrade does not re-exec
+	// (and fork-bomb) the test binary; see the comment there.
+	for _, tc := range tests {
+		tc := tc
+		t.Run(tc.name, func(t *testing.T) {
+			// Call the function and capture the result
+			result := performUpgrade(tc.versionTarget)
+			assert.Equal(t, tc.expectedResult, result, tc.description)
+		})
+	}
+}

cmd/cli/prog_windows.go

@@ -0,0 +1,14 @@
+package cli
+
+import "github.com/kardianos/service"
+
+func setDependencies(svc *service.Config) {
+	if hasLocalDnsServerRunning() {
+		svc.Dependencies = []string{"DNS"}
+	}
+}
+
+func setWorkingDirectory(svc *service.Config, dir string) {
+	// WorkingDirectory is not supported on Windows.
+	svc.WorkingDirectory = dir
+}

cmd/cli/prometheus.go

@@ -0,0 +1,57 @@
+package cli
+
+import "github.com/prometheus/client_golang/prometheus"
+
+const (
+	metricsLabelListener       = "listener"
+	metricsLabelClientSourceIP = "client_source_ip"
+	metricsLabelClientMac      = "client_mac"
+	metricsLabelClientHostname = "client_hostname"
+	metricsLabelUpstream       = "upstream"
+	metricsLabelRRType         = "rr_type"
+	metricsLabelRCode          = "rcode"
+)
+
+// statsVersion represent ctrld version.
+var statsVersion = prometheus.NewCounterVec(prometheus.CounterOpts{
+	Name: "ctrld_build_info",
+	Help: "Version of ctrld process.",
+}, []string{"gitref", "goversion", "version"})
+
+// statsTimeStart represents start time of ctrld service.
+var statsTimeStart = prometheus.NewGauge(prometheus.GaugeOpts{
+	Name: "ctrld_time_seconds",
+	Help: "Start time of the ctrld process since unix epoch in seconds.",
+})
+
+var statsQueriesCountLabels = []string{
+	metricsLabelListener,
+	metricsLabelClientSourceIP,
+	metricsLabelClientMac,
+	metricsLabelClientHostname,
+	metricsLabelUpstream,
+	metricsLabelRRType,
+	metricsLabelRCode,
+}
+
+// statsQueriesCount counts total number of queries.
+var statsQueriesCount = prometheus.NewCounterVec(prometheus.CounterOpts{
+	Name: "ctrld_queries_count",
+	Help: "Total number of queries.",
+}, statsQueriesCountLabels)
+
+// statsClientQueriesCount counts total number of queries of a client.
+//
+// The labels "client_source_ip", "client_mac", "client_hostname" are unbounded,
+// thus this stat is highly inefficient if there are many devices.
+var statsClientQueriesCount = prometheus.NewCounterVec(prometheus.CounterOpts{
+	Name: "ctrld_client_queries_count",
+	Help: "Total number queries of a client.",
+}, []string{metricsLabelClientSourceIP, metricsLabelClientMac, metricsLabelClientHostname})
+
+// WithLabelValuesInc increases prometheus counter by 1 if query stats is enabled.
+func (p *prog) WithLabelValuesInc(c *prometheus.CounterVec, lvs ...string) {
+	if p.metricsQueryStats.Load() {
+		c.WithLabelValues(lvs...).Inc()
+	}
+}

cmd/cli/provision_result.go

@@ -0,0 +1,247 @@
+package cli
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+	"unicode/utf8"
+)
+
+// A terminal provisioning failure reports the same stable code on three
+// surfaces: a persisted result file, one fixed-format output line, and a
+// stage-scoped process exit code. docs/provisioning-failure-codes.md maps
+// each code to its scenario and must stay in sync with the constants below.
+// Codes are append-only once released; renaming or reusing one breaks the
+// support contract.
+
+type provisionStage string
+
+const (
+	provisionStageBootstrap provisionStage = "bootstrap"
+	provisionStageListener  provisionStage = "listener"
+	provisionStageService   provisionStage = "service"
+)
+
+type provisionFailureCode string
+
+const (
+	provisionCodeAPIUnreachable      provisionFailureCode = "API_UNREACHABLE"
+	provisionCodeAPIRejected         provisionFailureCode = "API_REJECTED"
+	provisionCodeAPIDeviceInvalid    provisionFailureCode = "API_DEVICE_INVALID"
+	provisionCodeListenerBindFailed  provisionFailureCode = "LISTENER_BIND_FAILED"
+	provisionCodeListenerAddrUnavail provisionFailureCode = "LISTENER_CONFIGURED_ADDR_UNAVAILABLE"
+	provisionCodeServiceInstall      provisionFailureCode = "SERVICE_INSTALL_FAILED"
+	provisionCodeServiceStartFailed  provisionFailureCode = "SERVICE_START_FAILED"
+	provisionCodeServiceSelfCheck    provisionFailureCode = "SERVICE_SELFCHECK_FAILED"
+)
+
+var allProvisionFailureCodes = []provisionFailureCode{
+	provisionCodeAPIUnreachable,
+	provisionCodeAPIRejected,
+	provisionCodeAPIDeviceInvalid,
+	provisionCodeListenerBindFailed,
+	provisionCodeListenerAddrUnavail,
+	provisionCodeServiceInstall,
+	provisionCodeServiceStartFailed,
+	provisionCodeServiceSelfCheck,
+}
+
+var provisionStageForCode = map[provisionFailureCode]provisionStage{
+	provisionCodeAPIUnreachable:      provisionStageBootstrap,
+	provisionCodeAPIRejected:         provisionStageBootstrap,
+	provisionCodeAPIDeviceInvalid:    provisionStageBootstrap,
+	provisionCodeListenerBindFailed:  provisionStageListener,
+	provisionCodeListenerAddrUnavail: provisionStageListener,
+	provisionCodeServiceInstall:      provisionStageService,
+	provisionCodeServiceStartFailed:  provisionStageService,
+	provisionCodeServiceSelfCheck:    provisionStageService,
+}
+
+// Exit codes are grouped by stage (bootstrap 30-39, listener 40-49, service
+// 50-59) so the exit code alone names the failed stage. 0-3 belong to
+// "ctrld status" and 126 to the deactivation pin check; never reuse those.
+var provisionExitCodeForCode = map[provisionFailureCode]int{
+	provisionCodeAPIUnreachable:      30,
+	provisionCodeAPIRejected:         31,
+	provisionCodeAPIDeviceInvalid:    32,
+	provisionCodeListenerBindFailed:  41,
+	provisionCodeListenerAddrUnavail: 42,
+	provisionCodeServiceInstall:      51,
+	provisionCodeServiceStartFailed:  52,
+	provisionCodeServiceSelfCheck:    53,
+}
+
+const (
+	provisionResultFileName = "provision_result.json"
+	// Detail identifies a failure, it is not a log. Caps keep the artifact
+	// small and predictable.
+	maxProvisionBindAttempts = 12
+	maxProvisionStringLen    = 256
+)
+
+type provisionBindAttempt struct {
+	Addr    string `json:"addr"`
+	Proto   string `json:"proto"`
+	OSError string `json:"os_error"`
+}
+
+type provisionDetail struct {
+	Attempts []provisionBindAttempt `json:"attempts,omitempty"`
+}
+
+type provisionResult struct {
+	Version   int              `json:"version"`
+	Timestamp string           `json:"timestamp"`
+	Stage     string           `json:"stage"`
+	Code      string           `json:"code"`
+	ExitCode  int              `json:"exit_code"`
+	Message   string           `json:"message"`
+	Detail    *provisionDetail `json:"detail,omitempty"`
+}
+
+// provisionResultPath is a var so tests can point it at a temp dir.
+var provisionResultPath = func() string {
+	return absHomeDir(provisionResultFileName)
+}
+
+// provisionExit is a var so tests can observe the exit code instead of dying.
+var provisionExit = os.Exit
+
+// newProvisionResult builds a result with every field bounded and the given
+// secrets stripped. The artifact reaches installer logs and support tickets,
+// so callers pass every secret in scope (provision token, cd UID).
+func newProvisionResult(code provisionFailureCode, message string, attempts []provisionBindAttempt, secrets ...string) *provisionResult {
+	sanitize := func(s string) string {
+		s = redactSecrets(s, secrets...)
+		if len(s) > maxProvisionStringLen {
+			// Cut on a rune boundary so a localized OS error does not end in
+			// a broken multi-byte sequence.
+			cut := maxProvisionStringLen
+			for cut > 0 && !utf8.RuneStart(s[cut]) {
+				cut--
+			}
+			s = s[:cut]
+		}
+		return s
+	}
+	r := &provisionResult{
+		Version:   1,
+		Timestamp: time.Now().UTC().Format(time.RFC3339),
+		Stage:     string(provisionStageForCode[code]),
+		Code:      string(code),
+		ExitCode:  provisionExitCodeForCode[code],
+		Message:   sanitize(message),
+	}
+	if len(attempts) > 0 {
+		if len(attempts) > maxProvisionBindAttempts {
+			attempts = attempts[:maxProvisionBindAttempts]
+		}
+		detail := &provisionDetail{Attempts: make([]provisionBindAttempt, 0, len(attempts))}
+		for _, a := range attempts {
+			detail.Attempts = append(detail.Attempts, provisionBindAttempt{
+				Addr:    sanitize(a.Addr),
+				Proto:   sanitize(a.Proto),
+				OSError: sanitize(a.OSError),
+			})
+		}
+		r.Detail = detail
+	}
+	return r
+}
+
+// redactSecrets removes every non-empty secret from s.
+func redactSecrets(s string, secrets ...string) string {
+	for _, secret := range secrets {
+		if secret == "" {
+			continue
+		}
+		s = strings.ReplaceAll(s, secret, "[redacted]")
+	}
+	return s
+}
+
+// provisionResultTrusted rejects a result whose code, stage, or exit code is
+// not part of the known contract, so a corrupt or planted file cannot drive
+// what "ctrld start" logs and exits with.
+func provisionResultTrusted(r *provisionResult) bool {
+	code := provisionFailureCode(r.Code)
+	stage, ok := provisionStageForCode[code]
+	if !ok {
+		return false
+	}
+	return r.Stage == string(stage) && r.ExitCode == provisionExitCodeForCode[code]
+}
+
+func (r *provisionResult) failureLine() string {
+	return fmt.Sprintf("provisioning failed: stage=%s code=%s (exit %d)", r.Stage, r.Code, r.ExitCode)
+}
+
+// writeProvisionResult persists the result atomically (temp file + rename in
+// the same directory) so a reader never sees a partial file.
+func writeProvisionResult(r *provisionResult) error {
+	path := provisionResultPath()
+	buf, err := json.MarshalIndent(r, "", "  ")
+	if err != nil {
+		return err
+	}
+	tmp, err := os.CreateTemp(filepath.Dir(path), provisionResultFileName+".tmp*")
+	if err != nil {
+		return err
+	}
+	tmpName := tmp.Name()
+	if _, err := tmp.Write(buf); err != nil {
+		_ = tmp.Close()
+		_ = os.Remove(tmpName)
+		return err
+	}
+	if err := tmp.Close(); err != nil {
+		_ = os.Remove(tmpName)
+		return err
+	}
+	if err := os.Chmod(tmpName, 0o600); err != nil {
+		_ = os.Remove(tmpName)
+		return err
+	}
+	if err := os.Rename(tmpName, path); err != nil {
+		_ = os.Remove(tmpName)
+		return err
+	}
+	return nil
+}
+
+func readProvisionResult() (*provisionResult, error) {
+	buf, err := os.ReadFile(provisionResultPath())
+	if err != nil {
+		return nil, err
+	}
+	r := &provisionResult{}
+	if err := json.Unmarshal(buf, r); err != nil {
+		return nil, err
+	}
+	return r, nil
+}
+
+// clearProvisionResult removes a stale result once provisioning succeeds, so
+// support never diagnoses a healthy install from an old failure.
+func clearProvisionResult() {
+	if err := os.Remove(provisionResultPath()); err != nil && !os.IsNotExist(err) {
+		mainLog.Load().Debug().Err(err).Msg("could not remove provision result file")
+	}
+}
+
+// failProvision persists the result, prints the identifier line, unblocks a
+// waiting "ctrld start" via notify, then exits with the stage code. The write
+// comes first so the file survives even if logging or notify misbehaves.
+func failProvision(r *provisionResult, notify func()) {
+	if err := writeProvisionResult(r); err != nil {
+		mainLog.Load().Warn().Err(err).Msg("could not persist provision result")
+	}
+	mainLog.Load().Error().Msg(r.failureLine())
+	if notify != nil {
+		notify()
+	}
+	provisionExit(r.ExitCode)
+}

cmd/cli/provision_result_test.go

@@ -0,0 +1,278 @@
+package cli
+
+import (
+	"encoding/json"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"testing"
+	"time"
+	"unicode/utf8"
+)
+
+func overrideProvisionResultPath(t *testing.T) string {
+	t.Helper()
+	path := filepath.Join(t.TempDir(), provisionResultFileName)
+	old := provisionResultPath
+	provisionResultPath = func() string { return path }
+	t.Cleanup(func() { provisionResultPath = old })
+	return path
+}
+
+func TestProvisionCodesMapToOneStageAndInRangeExit(t *testing.T) {
+	stageRanges := map[provisionStage][2]int{
+		provisionStageBootstrap: {30, 39},
+		provisionStageListener:  {40, 49},
+		provisionStageService:   {50, 59},
+	}
+	reservedExits := map[int]string{
+		statusExitRunning:              "ctrld status running",
+		statusExitStopped:              "ctrld status stopped",
+		statusExitUnknown:              "ctrld status unknown",
+		statusExitNotReady:             "ctrld status not ready",
+		deactivationPinInvalidExitCode: "deactivation pin invalid",
+	}
+	seenExits := make(map[int]provisionFailureCode)
+	for _, code := range allProvisionFailureCodes {
+		stage, ok := provisionStageForCode[code]
+		if !ok {
+			t.Fatalf("code %s has no stage", code)
+		}
+		exit, ok := provisionExitCodeForCode[code]
+		if !ok {
+			t.Fatalf("code %s has no exit code", code)
+		}
+		r := stageRanges[stage]
+		if exit < r[0] || exit > r[1] {
+			t.Errorf("code %s exit %d outside stage %s range %v", code, exit, stage, r)
+		}
+		if owner, ok := reservedExits[exit]; ok {
+			t.Errorf("code %s exit %d collides with %s", code, exit, owner)
+		}
+		if prev, dup := seenExits[exit]; dup {
+			t.Errorf("codes %s and %s share exit %d", prev, code, exit)
+		}
+		seenExits[exit] = code
+	}
+	if len(allProvisionFailureCodes) != 8 {
+		t.Errorf("expected 8 codes, got %d", len(allProvisionFailureCodes))
+	}
+}
+
+func TestNewProvisionResultRedactsSecrets(t *testing.T) {
+	token := "org-secret-token-12345"
+	cdUIDValue := "abcdef123456"
+	attempts := []provisionBindAttempt{
+		{Addr: "127.0.0.1:53", Proto: "udp", OSError: "bind failed for " + token},
+	}
+	r := newProvisionResult(
+		provisionCodeListenerBindFailed,
+		"could not bind, token="+token+" uid="+cdUIDValue,
+		attempts,
+		token, cdUIDValue,
+	)
+	raw, err := json.Marshal(r)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, secret := range []string{token, cdUIDValue} {
+		if strings.Contains(string(raw), secret) {
+			t.Errorf("serialized result contains secret %q: %s", secret, raw)
+		}
+	}
+}
+
+func TestNewProvisionResultBoundsDetail(t *testing.T) {
+	long := strings.Repeat("x", 1000)
+	var attempts []provisionBindAttempt
+	for i := 0; i < 50; i++ {
+		attempts = append(attempts, provisionBindAttempt{Addr: long, Proto: "udp", OSError: long})
+	}
+	r := newProvisionResult(provisionCodeListenerBindFailed, long, attempts)
+	if got := len(r.Detail.Attempts); got > maxProvisionBindAttempts {
+		t.Errorf("attempts not capped: %d > %d", got, maxProvisionBindAttempts)
+	}
+	if len(r.Message) > maxProvisionStringLen {
+		t.Errorf("message not capped: %d", len(r.Message))
+	}
+	for _, a := range r.Detail.Attempts {
+		if len(a.Addr) > maxProvisionStringLen || len(a.OSError) > maxProvisionStringLen {
+			t.Error("attempt fields not capped")
+		}
+	}
+}
+
+func TestProvisionResultFields(t *testing.T) {
+	r := newProvisionResult(provisionCodeAPIRejected, "the API rejected this configuration", nil)
+	if r.Version != 1 {
+		t.Errorf("version = %d, want 1", r.Version)
+	}
+	if r.Stage != string(provisionStageBootstrap) {
+		t.Errorf("stage = %q, want bootstrap", r.Stage)
+	}
+	if r.ExitCode != provisionExitCodeForCode[provisionCodeAPIRejected] {
+		t.Errorf("exit = %d", r.ExitCode)
+	}
+	if _, err := time.Parse(time.RFC3339, r.Timestamp); err != nil {
+		t.Errorf("timestamp %q not RFC3339: %v", r.Timestamp, err)
+	}
+	if r.Detail != nil {
+		t.Error("nil attempts should give nil detail")
+	}
+}
+
+func TestProvisionResultTrusted(t *testing.T) {
+	good := newProvisionResult(provisionCodeListenerBindFailed, "x", nil)
+	if !provisionResultTrusted(good) {
+		t.Error("constructor-built result must be trusted")
+	}
+	bogusCode := newProvisionResult(provisionCodeListenerBindFailed, "x", nil)
+	bogusCode.Code = "TOTALLY_MADE_UP"
+	if provisionResultTrusted(bogusCode) {
+		t.Error("unknown code must not be trusted")
+	}
+	wrongExit := newProvisionResult(provisionCodeListenerBindFailed, "x", nil)
+	wrongExit.ExitCode = 126
+	if provisionResultTrusted(wrongExit) {
+		t.Error("exit code not matching the contract must not be trusted")
+	}
+	wrongStage := newProvisionResult(provisionCodeListenerBindFailed, "x", nil)
+	wrongStage.Stage = string(provisionStageService)
+	if provisionResultTrusted(wrongStage) {
+		t.Error("stage not matching the code must not be trusted")
+	}
+}
+
+func TestNewProvisionResultTruncatesOnRuneBoundary(t *testing.T) {
+	msg := strings.Repeat("é", maxProvisionStringLen) // 2 bytes per rune
+	r := newProvisionResult(provisionCodeListenerBindFailed, msg, nil)
+	if len(r.Message) > maxProvisionStringLen {
+		t.Errorf("message not capped: %d bytes", len(r.Message))
+	}
+	if !utf8.ValidString(r.Message) {
+		t.Error("truncation split a multi-byte rune")
+	}
+}
+
+func TestFailureCodeDocTableMatchesConstants(t *testing.T) {
+	buf, err := os.ReadFile(filepath.Join("..", "..", "docs", "provisioning-failure-codes.md"))
+	if os.IsNotExist(err) {
+		// The Windows CI runner executes prebuilt test binaries outside the
+		// repo; the sync guarantee is still enforced on runners with a checkout.
+		t.Skip("failure-code doc not available in this test environment")
+	}
+	if err != nil {
+		t.Fatalf("could not read the failure-code doc: %v", err)
+	}
+	doc := string(buf)
+	rows := 0
+	for _, line := range strings.Split(doc, "\n") {
+		if strings.HasPrefix(line, "| `") {
+			rows++
+		}
+	}
+	if rows != len(allProvisionFailureCodes) {
+		t.Errorf("doc table has %d code rows, want %d", rows, len(allProvisionFailureCodes))
+	}
+	for _, code := range allProvisionFailureCodes {
+		row := "| `" + string(code) + "` | " + string(provisionStageForCode[code]) + " | " + strconv.Itoa(provisionExitCodeForCode[code]) + " |"
+		if !strings.Contains(doc, row) {
+			t.Errorf("doc table missing row for %s (want prefix %q)", code, row)
+		}
+	}
+}
+
+func TestProvisionFailureLineFormat(t *testing.T) {
+	r := newProvisionResult(provisionCodeListenerBindFailed, "could not find available listen ip and port", nil)
+	want := "provisioning failed: stage=listener code=LISTENER_BIND_FAILED (exit 41)"
+	if got := r.failureLine(); got != want {
+		t.Errorf("failureLine() = %q, want %q", got, want)
+	}
+}
+
+func TestProvisionResultRoundTrip(t *testing.T) {
+	overrideProvisionResultPath(t)
+	in := newProvisionResult(provisionCodeServiceStartFailed, "service failed to start", nil)
+	if err := writeProvisionResult(in); err != nil {
+		t.Fatal(err)
+	}
+	out, err := readProvisionResult()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if out.Code != in.Code || out.Stage != in.Stage || out.ExitCode != in.ExitCode || out.Message != in.Message {
+		t.Errorf("round trip mismatch: in=%+v out=%+v", in, out)
+	}
+}
+
+func TestWriteProvisionResultOverwritesAtomically(t *testing.T) {
+	path := overrideProvisionResultPath(t)
+	first := newProvisionResult(provisionCodeAPIUnreachable, "first", nil)
+	if err := writeProvisionResult(first); err != nil {
+		t.Fatal(err)
+	}
+	second := newProvisionResult(provisionCodeListenerBindFailed, "second", nil)
+	if err := writeProvisionResult(second); err != nil {
+		t.Fatal(err)
+	}
+	out, err := readProvisionResult()
+	if err != nil {
+		t.Fatal(err)
+	}
+	if out.Code != string(provisionCodeListenerBindFailed) || out.Message != "second" {
+		t.Errorf("overwrite failed: %+v", out)
+	}
+	entries, err := os.ReadDir(filepath.Dir(path))
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(entries) != 1 {
+		t.Errorf("temp files left behind: %v", entries)
+	}
+}
+
+func TestClearProvisionResult(t *testing.T) {
+	path := overrideProvisionResultPath(t)
+	clearProvisionResult() // missing file must not panic or error loudly
+	if err := writeProvisionResult(newProvisionResult(provisionCodeAPIUnreachable, "x", nil)); err != nil {
+		t.Fatal(err)
+	}
+	clearProvisionResult()
+	if _, err := os.Stat(path); !os.IsNotExist(err) {
+		t.Errorf("result file still present after clear: %v", err)
+	}
+}
+
+func TestReadProvisionResultMissing(t *testing.T) {
+	overrideProvisionResultPath(t)
+	if _, err := readProvisionResult(); err == nil {
+		t.Error("expected error reading missing result file")
+	}
+}
+
+func TestFailProvisionWritesLogsNotifiesAndExits(t *testing.T) {
+	overrideProvisionResultPath(t)
+	exitCode := -1
+	oldExit := provisionExit
+	provisionExit = func(code int) { exitCode = code }
+	t.Cleanup(func() { provisionExit = oldExit })
+
+	notified := false
+	r := newProvisionResult(provisionCodeListenerBindFailed, "no listen addr", nil)
+	failProvision(r, func() { notified = true })
+
+	if !notified {
+		t.Error("notify func not called")
+	}
+	if exitCode != provisionExitCodeForCode[provisionCodeListenerBindFailed] {
+		t.Errorf("exit code = %d", exitCode)
+	}
+	out, err := readProvisionResult()
+	if err != nil {
+		t.Fatalf("result not persisted: %v", err)
+	}
+	if out.Code != string(provisionCodeListenerBindFailed) {
+		t.Errorf("persisted code = %q", out.Code)
+	}
+}

cmd/cli/recovery_state.go

@@ -0,0 +1,75 @@
+package cli
+
+import "context"
+
+// beginRecovery atomically transfers ownership of shared recovery state. A
+// network change cancels and replaces the current owner without exposing a nil
+// recoveryCancel gap; other triggers are coalesced while an owner exists.
+func (p *prog) beginRecovery(reason RecoveryReason) (ctx context.Context, gen uint64, intercept bool, ok bool) {
+	p.recoveryCancelMu.Lock()
+	defer p.recoveryCancelMu.Unlock()
+
+	if reason != RecoveryReasonNetworkChange && p.recoveryCancel != nil {
+		return nil, 0, false, false
+	}
+	if p.recoveryCancel != nil {
+		p.recoveryCancel()
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	gen = p.recoveryGen.Add(1)
+	intercept = dnsIntercept && p.dnsInterceptState != nil
+	p.recoveryCancel = cancel
+	p.recoveryRunning.Store(true)
+	p.recoveryBypass.Store(intercept)
+	return ctx, gen, intercept, true
+}
+
+func (p *prog) recoveryOwnsState(gen uint64) bool {
+	p.recoveryCancelMu.Lock()
+	defer p.recoveryCancelMu.Unlock()
+	return p.recoveryGen.Load() == gen && p.recoveryCancel != nil
+}
+
+func systemNameserversForInterceptRetry() []string {
+	_, system := initializeOsResolverWithSystemNameserversFn(true)
+	if system == nil {
+		return []string{}
+	}
+	return system
+}
+
+// completeRecovery releases shared state only if gen still owns it. The bypass
+// reset is unconditional because live intercept state can disappear while a
+// recovery is running, but a stale true flag still affects proxy routing.
+func (p *prog) completeRecovery(gen uint64) bool {
+	p.recoveryCancelMu.Lock()
+	defer p.recoveryCancelMu.Unlock()
+	if p.recoveryGen.Load() != gen || p.recoveryCancel == nil {
+		return false
+	}
+	p.recoveryBypass.Store(false)
+	p.recoveryRunning.Store(false)
+	p.recoveryCancel = nil
+	return true
+}
+
+// recoveryCanceledCleanup resets shared recovery state after a canceled or
+// failed recovery, but only when the recovery identified by gen was NOT
+// superseded by a newer one (issue #597).
+//
+// A network-change cancellation is normally followed immediately by a new
+// handleRecovery that owns recoveryBypass/recoveryRunning/recoveryCancel;
+// clearing them here would disable the successor's bypass mid-flight and
+// make it uncancellable. But when the canceled recovery is the LAST one
+// (e.g. the tail of a network flap burst), nothing else will ever clear the
+// flags: the daemon would stay in recovery bypass forever — every query
+// detouring to the OS resolver — and the DNS-settings watchdog would stay
+// permanently disabled.
+func (p *prog) recoveryCanceledCleanup(gen uint64) {
+	if !p.completeRecovery(gen) {
+		// Superseded: the newer recovery owns the shared state.
+		return
+	}
+	mainLog.Load().Info().Msg("Recovery canceled with no successor; cleared recovery state and DHCP bypass")
+}

cmd/cli/recovery_state_test.go

@@ -0,0 +1,161 @@
+package cli
+
+import (
+	"testing"
+	"time"
+)
+
+// interceptStateStub stands in for the platform pfState/wfpState; the
+// recovery cleanup path only checks dnsInterceptState != nil.
+type interceptStateStub struct{}
+
+// setupInterceptRecovery puts p into "intercept-mode recovery in flight"
+// state and restores the package-level dnsIntercept flag on cleanup.
+func setupInterceptRecovery(t *testing.T, p *prog) {
+	t.Helper()
+	oldIntercept := dnsIntercept
+	dnsIntercept = true
+	t.Cleanup(func() { dnsIntercept = oldIntercept })
+	p.dnsInterceptState = &interceptStateStub{}
+	p.recoveryBypass.Store(true)
+	p.recoveryRunning.Store(true)
+	p.recoveryCancel = func() {}
+}
+
+// TestRecoveryCanceledCleanup_LastRecoveryResetsState pins issue #597: a
+// canceled recovery with no successor must clear recoveryBypass and
+// recoveryRunning, or the daemon stays in bypass forever (every query
+// detours to the OS resolver) and the DNS watchdog stays disabled.
+func TestRecoveryCanceledCleanup_LastRecoveryResetsState(t *testing.T) {
+	p := &prog{}
+	setupInterceptRecovery(t, p)
+	gen := p.recoveryGen.Add(1)
+
+	p.recoveryCanceledCleanup(gen)
+
+	if p.recoveryBypass.Load() {
+		t.Error("recoveryBypass still set after canceled recovery with no successor")
+	}
+	if p.recoveryRunning.Load() {
+		t.Error("recoveryRunning still set after canceled recovery with no successor")
+	}
+	p.recoveryCancelMu.Lock()
+	cancelCleared := p.recoveryCancel == nil
+	p.recoveryCancelMu.Unlock()
+	if !cancelCleared {
+		t.Error("recoveryCancel not cleared after canceled recovery with no successor")
+	}
+}
+
+// TestRecoveryCanceledCleanup_SupersededKeepsSuccessorState pins the
+// captive-portal/network-flap contract: when a newer recovery superseded the
+// canceled one, the canceled recovery must NOT clear shared state — the
+// successor owns bypass for its own duration.
+func TestRecoveryCanceledCleanup_SupersededKeepsSuccessorState(t *testing.T) {
+	p := &prog{}
+	setupInterceptRecovery(t, p)
+	gen := p.recoveryGen.Add(1)
+	// A successor recovery started.
+	p.recoveryGen.Add(1)
+
+	p.recoveryCanceledCleanup(gen)
+
+	if !p.recoveryBypass.Load() {
+		t.Error("superseded canceled recovery cleared recoveryBypass owned by its successor")
+	}
+	if !p.recoveryRunning.Load() {
+		t.Error("superseded canceled recovery cleared recoveryRunning owned by its successor")
+	}
+	p.recoveryCancelMu.Lock()
+	cancelKept := p.recoveryCancel != nil
+	p.recoveryCancelMu.Unlock()
+	if !cancelKept {
+		t.Error("superseded canceled recovery cleared the successor's recoveryCancel")
+	}
+}
+
+// TestRecoveryCanceledCleanup_NonInterceptResetsRunning covers traditional
+// (non-intercept) mode: recoveryRunning must still be reset so watchdogs
+// resume, while bypass is untouched (it is never set in that mode).
+func TestRecoveryCanceledCleanup_NonInterceptResetsRunning(t *testing.T) {
+	oldIntercept := dnsIntercept
+	dnsIntercept = false
+	t.Cleanup(func() { dnsIntercept = oldIntercept })
+
+	p := &prog{}
+	p.recoveryRunning.Store(true)
+	p.recoveryCancel = func() {}
+	gen := p.recoveryGen.Add(1)
+
+	p.recoveryCanceledCleanup(gen)
+
+	if p.recoveryRunning.Load() {
+		t.Error("recoveryRunning still set after canceled non-intercept recovery")
+	}
+}
+
+func TestBeginRecoveryTransfersOwnershipAtomically(t *testing.T) {
+	oldIntercept := dnsIntercept
+	dnsIntercept = true
+	t.Cleanup(func() { dnsIntercept = oldIntercept })
+
+	p := &prog{dnsInterceptState: &interceptStateStub{}}
+	firstCtx, firstGen, _, ok := p.beginRecovery(RecoveryReasonRegularFailure)
+	if !ok {
+		t.Fatal("first recovery did not acquire ownership")
+	}
+	if _, _, _, ok := p.beginRecovery(RecoveryReasonRegularFailure); ok {
+		t.Fatal("duplicate upstream recovery acquired ownership")
+	}
+
+	_, successorGen, intercept, ok := p.beginRecovery(RecoveryReasonNetworkChange)
+	if !ok || !intercept || successorGen <= firstGen {
+		t.Fatalf("network recovery did not replace owner: first=%d successor=%d intercept=%v ok=%v", firstGen, successorGen, intercept, ok)
+	}
+	select {
+	case <-firstCtx.Done():
+	case <-time.After(time.Second):
+		t.Fatal("successor did not cancel the previous recovery")
+	}
+
+	p.recoveryCanceledCleanup(firstGen)
+	if !p.recoveryRunning.Load() || !p.recoveryBypass.Load() || !p.recoveryOwnsState(successorGen) {
+		t.Fatal("stale cleanup changed successor-owned recovery state")
+	}
+	if !p.completeRecovery(successorGen) {
+		t.Fatal("successor could not complete its own recovery state")
+	}
+}
+
+func TestRecoveryCleanupClearsBypassAfterInterceptStateDisappears(t *testing.T) {
+	p := &prog{}
+	p.recoveryBypass.Store(true)
+	p.recoveryRunning.Store(true)
+	p.recoveryCancel = func() {}
+	gen := p.recoveryGen.Add(1)
+
+	p.recoveryCanceledCleanup(gen)
+	if p.recoveryBypass.Load() || p.recoveryRunning.Load() {
+		t.Fatal("cleanup retained recovery flags after intercept state disappeared")
+	}
+}
+
+func TestSystemNameserversForInterceptRetryNormalizesEmptyDiscovery(t *testing.T) {
+	original := initializeOsResolverWithSystemNameserversFn
+	called := false
+	initializeOsResolverWithSystemNameserversFn = func(guard bool) ([]string, []string) {
+		called = true
+		if !guard {
+			t.Error("intercept retry discovery did not guard the existing resolver")
+		}
+		return nil, nil
+	}
+	t.Cleanup(func() { initializeOsResolverWithSystemNameserversFn = original })
+
+	if got := systemNameserversForInterceptRetry(); got == nil || len(got) != 0 {
+		t.Fatalf("system discovery = %#v, want non-nil empty slice", got)
+	}
+	if !called {
+		t.Fatal("system discovery was not called")
+	}
+}

cmd/cli/reload_others.go

@@ -0,0 +1,17 @@
+//go:build !windows
+
+package cli
+
+import (
+	"os"
+	"os/signal"
+	"syscall"
+)
+
+func notifyReloadSigCh(ch chan os.Signal) {
+	signal.Notify(ch, syscall.SIGUSR1)
+}
+
+func (p *prog) sendReloadSignal() error {
+	return syscall.Kill(syscall.Getpid(), syscall.SIGUSR1)
+}

cmd/cli/reload_windows.go

@@ -0,0 +1,18 @@
+package cli
+
+import (
+	"errors"
+	"os"
+	"time"
+)
+
+func notifyReloadSigCh(ch chan os.Signal) {}
+
+func (p *prog) sendReloadSignal() error {
+	select {
+	case p.reloadCh <- struct{}{}:
+		return nil
+	case <-time.After(5 * time.Second):
+	}
+	return errors.New("timeout while sending reload signal")
+}