refactor(bootstrap): BTreeMap for overrides + simplify review

- Switch overrides from HashMap to BTreeMap — deterministic iteration by
  type, drops the manual sort when logging.
- Rename the flat_map closure's inner `ips` to `addrs` to stop shadowing
  the outer Vec<String>.
- Trim the Suite 8 TEST-NET-1 comment to keep the "why" and drop
  mechanism narration.
- Drop a redundant sleep 1 after wait — wait already blocks on exit.

.github/workflows/ci.yml

@@ -56,6 +56,8 @@ jobs:
     runs-on: windows-latest
     steps:
       - uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
       - uses: dtolnay/rust-toolchain@stable
       - uses: Swatinem/rust-cache@v2
       - name: build
@@ -69,3 +71,76 @@ jobs:
         with:
           name: numa-windows-x86_64
           path: target/debug/numa.exe
+
+  integration-linux:
+    needs: [check]
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: Swatinem/rust-cache@v2
+      - name: build
+        run: cargo build --release
+      - name: install / verify / re-install / uninstall
+        run: |
+          sudo ./target/release/numa install
+          sleep 2
+          curl -sf http://127.0.0.1:5380/health
+          dig @127.0.0.1 example.com +short +timeout=5 | grep -q '.'
+          user=$(ps -o user= -p "$(systemctl show -p MainPID --value numa)" | tr -d ' ')
+          echo "numa running as: $user"
+          test "$user" != "root"
+          sudo ./target/release/numa install
+          sleep 2
+          curl -sf http://127.0.0.1:5380/health
+          sudo ./target/release/numa uninstall
+          sleep 1
+          ! curl -sf http://127.0.0.1:5380/health 2>/dev/null
+      - name: diagnostics on failure
+        if: failure()
+        run: |
+          echo "=== systemctl status numa ==="
+          sudo systemctl status numa --no-pager -l || true
+          echo "=== journalctl -u numa (last 200) ==="
+          sudo journalctl -u numa --no-pager -n 200 || true
+          echo "=== ss -tulnp on 53/80/443/853/5380 ==="
+          sudo ss -tulnp 2>/dev/null | grep -E ':(53|80|443|853|5380)\b' || true
+          echo "=== systemctl is-active systemd-resolved ==="
+          systemctl is-active systemd-resolved || true
+      - name: cleanup
+        if: always()
+        run: |
+          sudo ./target/release/numa uninstall 2>/dev/null || true
+          # systemd-resolved has a ~40s DNS reconfiguration stall after
+          # restart (systemd issue #22521) that breaks the runner agent's
+          # connection to GitHub. Bridge it by replacing the stub-resolv
+          # symlink with a direct upstream — DNS works instantly and the
+          # runner can phone home for post-job steps.
+          sudo rm -f /etc/resolv.conf
+          echo "nameserver 8.8.8.8" | sudo tee /etc/resolv.conf > /dev/null
+          getent hosts github.com >/dev/null
+
+  integration-macos:
+    needs: [check-macos]
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: dtolnay/rust-toolchain@stable
+      - uses: Swatinem/rust-cache@v2
+      - name: build
+        run: cargo build --release
+      - name: install / verify / re-install / uninstall
+        run: |
+          sudo ./target/release/numa install
+          sleep 2
+          curl -sf http://127.0.0.1:5380/health
+          dig @127.0.0.1 example.com +short +timeout=5 | grep -q '.'
+          sudo ./target/release/numa install
+          sleep 2
+          curl -sf http://127.0.0.1:5380/health
+          sudo ./target/release/numa uninstall
+          sleep 1
+          ! curl -sf http://127.0.0.1:5380/health 2>/dev/null
+      - name: cleanup
+        if: always()
+        run: sudo ./target/release/numa uninstall 2>/dev/null || true

Cargo.lock

@@ -8,6 +8,41 @@ version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
 
+[[package]]
+name = "aead"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d122413f284cf2d62fb1b7db97e02edb8cda96d769b16e443a4f6195e35662b0"
+dependencies = [
+ "crypto-common",
+ "generic-array",
+]
+
+[[package]]
+name = "aes"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b169f7a6d4742236a0a00c541b845991d0ac43e546831af1249753ab4c3aa3a0"
+dependencies = [
+ "cfg-if",
+ "cipher",
+ "cpufeatures",
+]
+
+[[package]]
+name = "aes-gcm"
+version = "0.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "831010a0f742e1209b3bcea8fab6a8e149051ba6099432c8cb2cc117dec3ead1"
+dependencies = [
+ "aead",
+ "aes",
+ "cipher",
+ "ctr",
+ "ghash",
+ "subtle",
+]
+
 [[package]]
 name = "aho-corasick"
 version = "1.1.4"
@@ -109,7 +144,7 @@ dependencies = [
  "nom",
  "num-traits",
  "rusticata-macros",
- "thiserror",
+ "thiserror 2.0.18",
  "time",
 ]
 
@@ -257,6 +292,15 @@ version = "2.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "843867be96c8daad0d758b57df9392b6d8d271134fce549de6ce169ff98a92af"
 
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
 [[package]]
 name = "bumpalo"
 version = "3.20.2"
@@ -299,6 +343,30 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
+[[package]]
+name = "chacha20"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3613f74bd2eac03dad61bd53dbe620703d4371614fe0bc3b9f04dd36fe4e818"
+dependencies = [
+ "cfg-if",
+ "cipher",
+ "cpufeatures",
+]
+
+[[package]]
+name = "chacha20poly1305"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10cd79432192d1c0f4e1a0fef9527696cc039165d729fb41b3f4f4f354c2dc35"
+dependencies = [
+ "aead",
+ "chacha20",
+ "cipher",
+ "poly1305",
+ "zeroize",
+]
+
 [[package]]
 name = "ciborium"
 version = "0.2.2"
@@ -326,6 +394,17 @@ dependencies = [
  "half",
 ]
 
+[[package]]
+name = "cipher"
+version = "0.4.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "773f3b9af64447d2ce9850330c473515014aa235e6a783b02db81ff39e4a3dad"
+dependencies = [
+ "crypto-common",
+ "inout",
+ "zeroize",
+]
+
 [[package]]
 name = "clap"
 version = "4.6.0"
@@ -383,6 +462,15 @@ version = "0.4.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "75984efb6ed102a0d42db99afb6c1948f0380d1d91808d5529916e6c08b49d8d"
 
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -473,6 +561,51 @@ version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5"
 
+[[package]]
+name = "crypto-common"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
+dependencies = [
+ "generic-array",
+ "rand_core 0.6.4",
+ "typenum",
+]
+
+[[package]]
+name = "ctr"
+version = "0.9.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0369ee1ad671834580515889b80f2ea915f23b8be8d0daa4bbaf2ac5c7590835"
+dependencies = [
+ "cipher",
+]
+
+[[package]]
+name = "curve25519-dalek"
+version = "4.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97fb8b7c4503de7d6ae7b42ab72a5a59857b4c937ec27a3d4539dba95b5ab2be"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "curve25519-dalek-derive",
+ "fiat-crypto",
+ "rustc_version",
+ "subtle",
+]
+
+[[package]]
+name = "curve25519-dalek-derive"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f46882e17999c6cc590af592290432be3bce0428cb0d5f8b6715e4dc7b383eb3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "data-encoding"
 version = "2.10.0"
@@ -502,6 +635,17 @@ dependencies = [
  "powerfmt",
 ]
 
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+ "subtle",
+]
+
 [[package]]
 name = "displaydoc"
 version = "0.2.5"
@@ -576,6 +720,12 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "fiat-crypto"
+version = "0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28dea519a9695b9977216879a3ebfddf92f1c08c05d984f8996aecd6ecdc811d"
+
 [[package]]
 name = "find-msvc-tools"
 version = "0.1.9"
@@ -707,6 +857,16 @@ dependencies = [
  "slab",
 ]
 
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
 [[package]]
 name = "getrandom"
 version = "0.2.17"
@@ -747,6 +907,16 @@ dependencies = [
  "wasip3",
 ]
 
+[[package]]
+name = "ghash"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0d8a4362ccb29cb0b265253fb0a2728f592895ee6854fd9bc13f2ffda266ff1"
+dependencies = [
+ "opaque-debug",
+ "polyval",
+]
+
 [[package]]
 name = "h2"
 version = "0.4.13"
@@ -820,7 +990,7 @@ dependencies = [
  "rand",
  "ring",
  "rustls",
- "thiserror",
+ "thiserror 2.0.18",
  "tinyvec",
  "tokio",
  "tokio-rustls",
@@ -846,13 +1016,51 @@ dependencies = [
  "resolv-conf",
  "rustls",
  "smallvec",
- "thiserror",
+ "thiserror 2.0.18",
  "tokio",
  "tokio-rustls",
  "tracing",
  "webpki-roots 0.26.11",
 ]
 
+[[package]]
+name = "hkdf"
+version = "0.12.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7b5f8eb2ad728638ea2c7d47a21db23b7b58a72ed6a38256b8a1849f15fbbdf7"
+dependencies = [
+ "hmac",
+]
+
+[[package]]
+name = "hmac"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e"
+dependencies = [
+ "digest",
+]
+
+[[package]]
+name = "hpke"
+version = "0.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f65d16b699dd1a1fa2d851c970b0c971b388eeeb40f744252b8de48860980c8f"
+dependencies = [
+ "aead",
+ "aes-gcm",
+ "chacha20poly1305",
+ "digest",
+ "generic-array",
+ "hkdf",
+ "hmac",
+ "rand_core 0.9.5",
+ "sha2",
+ "subtle",
+ "x25519-dalek",
+ "zeroize",
+]
+
 [[package]]
 name = "http"
 version = "1.4.0"
@@ -1081,6 +1289,15 @@ dependencies = [
  "serde_core",
 ]
 
+[[package]]
+name = "inout"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "879f10e63c20629ecabbb64a8010319738c66a5cd0c29b02d63d272b03751d01"
+dependencies = [
+ "generic-array",
+]
+
 [[package]]
 name = "ipconfig"
 version = "0.3.4"
@@ -1330,7 +1547,7 @@ dependencies = [
 
 [[package]]
 name = "numa"
-version = "0.13.1"
+version = "0.14.1"
 dependencies = [
  "arc-swap",
  "axum",
@@ -1344,7 +1561,10 @@ dependencies = [
  "hyper",
  "hyper-util",
  "log",
+ "odoh-rs",
+ "psl",
  "qrcode",
+ "rand_core 0.9.5",
  "rcgen",
  "reqwest",
  "ring",
@@ -1359,9 +1579,23 @@ dependencies = [
  "toml",
  "tower",
  "webpki-roots 1.0.6",
+ "windows-service",
  "x509-parser",
 ]
 
+[[package]]
+name = "odoh-rs"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cbb89720b7dfdddc89bc7560669d41a0bb68eb64784a4aebd293308a489f3837"
+dependencies = [
+ "aes-gcm",
+ "bytes",
+ "hkdf",
+ "hpke",
+ "thiserror 1.0.69",
+]
+
 [[package]]
 name = "oid-registry"
 version = "0.8.1"
@@ -1393,6 +1627,12 @@ version = "11.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"
 
+[[package]]
+name = "opaque-debug"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08d65885ee38876c4f86fa503fb49d7b507c2b62552df7c70b2fce627e06381"
+
 [[package]]
 name = "page_size"
 version = "0.6.0"
@@ -1482,6 +1722,29 @@ dependencies = [
  "plotters-backend",
 ]
 
+[[package]]
+name = "poly1305"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8159bd90725d2df49889a078b54f4f79e87f1f8a8444194cdca81d38f5393abf"
+dependencies = [
+ "cpufeatures",
+ "opaque-debug",
+ "universal-hash",
+]
+
+[[package]]
+name = "polyval"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9d1fe60d06143b2430aa532c94cfe9e29783047f06c0d7fd359a9a51b729fa25"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "opaque-debug",
+ "universal-hash",
+]
+
 [[package]]
 name = "portable-atomic"
 version = "1.13.1"
@@ -1540,6 +1803,21 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "psl"
+version = "2.1.203"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "76c0777260d32b76a8c3c197646707085d37e79d63b5872a29192c8d4f60f50b"
+dependencies = [
+ "psl-types",
+]
+
+[[package]]
+name = "psl-types"
+version = "2.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33cb294fe86a74cbcf50d4445b37da762029549ebeea341421c7c70370f86cac"
+
 [[package]]
 name = "qrcode"
 version = "0.14.1"
@@ -1560,7 +1838,7 @@ dependencies = [
  "rustc-hash",
  "rustls",
  "socket2",
- "thiserror",
+ "thiserror 2.0.18",
  "tokio",
  "tracing",
  "web-time",
@@ -1581,7 +1859,7 @@ dependencies = [
  "rustls",
  "rustls-pki-types",
  "slab",
- "thiserror",
+ "thiserror 2.0.18",
  "tinyvec",
  "tracing",
  "web-time",
@@ -1629,7 +1907,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
 dependencies = [
  "rand_chacha",
- "rand_core",
+ "rand_core 0.9.5",
 ]
 
 [[package]]
@@ -1639,7 +1917,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
 dependencies = [
  "ppv-lite86",
- "rand_core",
+ "rand_core 0.9.5",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
+dependencies = [
+ "getrandom 0.2.17",
 ]
 
 [[package]]
@@ -1788,6 +2075,15 @@ version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d"
 
+[[package]]
+name = "rustc_version"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
+dependencies = [
+ "semver",
+]
+
 [[package]]
 name = "rusticata-macros"
 version = "4.1.0"
@@ -1834,9 +2130,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-webpki"
-version = "0.103.10"
+version = "0.103.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df33b2b81ac578cabaf06b89b0631153a3f416b0a886e8a7a1707fb51abbd1ef"
+checksum = "8279bb85272c9f10811ae6a6c547ff594d6a7f3c6c6b02ee9726d1d0dcfcdd06"
 dependencies = [
  "aws-lc-rs",
  "ring",
@@ -1952,6 +2248,17 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "sha2"
+version = "0.10.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
 [[package]]
 name = "shlex"
 version = "1.3.0"
@@ -2045,13 +2352,33 @@ version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7b2093cf4c8eb1e67749a6762251bc9cd836b6fc171623bd0a9d324d37af2417"
 
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 2.0.18",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
 ]
 
 [[package]]
@@ -2297,6 +2624,12 @@ version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
 
+[[package]]
+name = "typenum"
+version = "1.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "40ce102ab67701b8526c123c1bab5cbe42d7040ccfd0f64af1a385808d2f43de"
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.24"
@@ -2309,6 +2642,16 @@ version = "0.2.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
 
+[[package]]
+name = "universal-hash"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc1de2c688dc15305988b563c3854064043356019f97a4b46276fe734c4f07ea"
+dependencies = [
+ "crypto-common",
+ "subtle",
+]
+
 [[package]]
 name = "untrusted"
 version = "0.9.0"
@@ -2350,6 +2693,12 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
 [[package]]
 name = "walkdir"
 version = "2.5.0"
@@ -2583,6 +2932,17 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "windows-service"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d24d6bcc7f734a4091ecf8d7a64c5f7d7066f45585c1861eba06449909609c8a"
+dependencies = [
+ "bitflags",
+ "widestring",
+ "windows-sys 0.52.0",
+]
+
 [[package]]
 name = "windows-strings"
 version = "0.5.1"
@@ -2848,6 +3208,16 @@ version = "0.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
 
+[[package]]
+name = "x25519-dalek"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7e468321c81fb07fa7f4c636c3972b9100f0346e5b6a9f2bd0603a52f7ed277"
+dependencies = [
+ "curve25519-dalek",
+ "rand_core 0.6.4",
+]
+
 [[package]]
 name = "x509-parser"
 version = "0.18.1"
@@ -2862,7 +3232,7 @@ dependencies = [
  "oid-registry",
  "ring",
  "rusticata-macros",
- "thiserror",
+ "thiserror 2.0.18",
  "time",
 ]
 
@@ -2944,6 +3314,20 @@ name = "zeroize"
 version = "1.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
+dependencies = [
+ "zeroize_derive",
+]
+
+[[package]]
+name = "zeroize_derive"
+version = "1.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85a5b4158499876c763cb03bc4e49185d3cccbabb15b33c627f7884f43db852e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
 
 [[package]]
 name = "zerotrie"

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "numa"
-version = "0.13.1"
+version = "0.14.1"
 authors = ["razvandimescu <razvan@dimescu.com>"]
 edition = "2021"
 description = "Portable DNS resolver in Rust — .numa local domains, ad blocking, developer overrides, DNS-over-HTTPS"
@@ -29,10 +29,18 @@ rustls = "0.23"
 tokio-rustls = "0.26"
 arc-swap = "1"
 ring = "0.17"
+odoh-rs = "1"
+psl = "2"
+# rand_core 0.9 matches the version odoh-rs (via hpke 0.13) depends on, so we
+# share one RngCore trait and OsRng impl across the dep tree.
+rand_core = { version = "0.9", features = ["os_rng"] }
 rustls-pemfile = "2.2.0"
 qrcode = { version = "0.14", default-features = false, features = ["svg"] }
 webpki-roots = "1"
 
+[target.'cfg(windows)'.dependencies]
+windows-service = "0.7"
+
 [dev-dependencies]
 criterion = { version = "0.8", features = ["html_reports"] }
 tower = { version = "0.5", features = ["util"] }

README.md

@@ -6,9 +6,9 @@
 
 **DNS you own. Everywhere you go.** — [numa.rs](https://numa.rs)
 
-A portable DNS resolver in a single binary. Block ads on any network, name your local services (`frontend.numa`), and override any hostname with auto-revert — all from your laptop, no cloud account or Raspberry Pi required.
+A portable DNS resolver in a single binary. Block ads on any network, name your local services (`frontend.numa`), override any hostname with auto-revert, and seal every outbound query with **ODoH (RFC 9230)** so no single party sees both who you are and what you asked — all from your laptop, no cloud account or Raspberry Pi required.
 
-Built from scratch in Rust. Zero DNS libraries. RFC 1035 wire protocol parsed by hand. Caching, ad blocking, and local service domains out of the box. Optional recursive resolution from root nameservers with full DNSSEC chain-of-trust validation, plus a DNS-over-TLS listener for encrypted client connections (iOS Private DNS, systemd-resolved, etc.). One ~8MB binary, everything embedded.
+Built from scratch in Rust. Zero DNS libraries. Caching, ad blocking, and local service domains out of the box. Optional recursive resolution from root nameservers with full DNSSEC chain-of-trust validation, plus a DNS-over-TLS listener for encrypted client connections (iOS Private DNS, systemd-resolved, etc.). Run `numa relay` and the same binary becomes a public ODoH endpoint too — the curated DNSCrypt list currently has one surviving relay, so every Numa deploy materially expands the ecosystem. One ~8MB binary, everything embedded.
 
 ![Numa dashboard](assets/hero-demo.gif)
 

benches/recursive_compare.rs

@@ -383,7 +383,7 @@ fn run_default(rt: &tokio::runtime::Runtime) {
 
 /// Library-to-library: Numa forward_query_raw vs Hickory resolver.lookup.
 fn run_direct(rt: &tokio::runtime::Runtime) {
-    let upstream = numa::forward::parse_upstream(DOH_UPSTREAM, 443).expect("failed to parse");
+    let upstream = numa::forward::parse_upstream(DOH_UPSTREAM, 443, None).expect("failed to parse");
     let resolver = rt.block_on(build_hickory_resolver());
     let timeout = Duration::from_secs(10);
 
@@ -609,9 +609,11 @@ fn run_hedge_multi(rt: &tokio::runtime::Runtime, iterations: usize) {
         DOMAINS.len()
     );
 
-    let primary = numa::forward::parse_upstream(DOH_UPSTREAM, 443).expect("failed to parse");
+    let primary = numa::forward::parse_upstream(DOH_UPSTREAM, 443, None).expect("failed to parse");
-    let primary_dual = numa::forward::parse_upstream(DOH_UPSTREAM, 443).expect("failed to parse");
+    let primary_dual =
-    let secondary_dual = numa::forward::parse_upstream(DOH_UPSTREAM, 443).expect("failed to parse");
+        numa::forward::parse_upstream(DOH_UPSTREAM, 443, None).expect("failed to parse");
+    let secondary_dual =
+        numa::forward::parse_upstream(DOH_UPSTREAM, 443, None).expect("failed to parse");
     let resolver = rt.block_on(build_hickory_resolver());
 
     println!("Warming up...");
@@ -810,7 +812,7 @@ fn run_diag(rt: &tokio::runtime::Runtime) {
 fn run_diag_clients(rt: &tokio::runtime::Runtime) {
     println!("Client diagnostic: reqwest vs Hickory (20 queries to {DOH_UPSTREAM})\n");
 
-    let upstream = numa::forward::parse_upstream(DOH_UPSTREAM, 443).expect("failed to parse");
+    let upstream = numa::forward::parse_upstream(DOH_UPSTREAM, 443, None).expect("failed to parse");
     let resolver = rt.block_on(build_hickory_resolver());
     let timeout = Duration::from_secs(10);
 

build.rs

@@ -0,0 +1,48 @@
+fn main() {
+    // --long forces "TAG-N-gSHA[-dirty]" format even on exact tag matches,
+    // making parsing unambiguous for pre-release tags like v0.14.0-rc1.
+    let git_version = std::process::Command::new("git")
+        .args(["describe", "--tags", "--always", "--dirty", "--long"])
+        .output()
+        .ok()
+        .filter(|o| o.status.success())
+        .and_then(|o| String::from_utf8(o.stdout).ok())
+        .and_then(|raw| parse_git_describe(raw.trim()));
+
+    if let Some(v) = git_version {
+        println!("cargo:rustc-env=NUMA_BUILD_VERSION={}", v);
+    }
+
+    println!("cargo:rerun-if-changed=.git/HEAD");
+}
+
+/// Parse `git describe --long` output into a SemVer-compatible string.
+///   "v0.13.1-0-ga87f907"          → "0.13.1"
+///   "v0.13.1-9-ga87f907"          → "0.13.1+a87f907"
+///   "v0.14.0-rc1-0-ga87f907"      → "0.14.0-rc1"
+///   "v0.14.0-rc1-3-ga87f907-dirty" → "0.14.0-rc1+a87f907-dirty"
+///   "a87f907"                      → "0.0.0+a87f907"
+fn parse_git_describe(s: &str) -> Option<String> {
+    let s = s.strip_prefix('v').unwrap_or(s);
+    let dirty = s.ends_with("-dirty");
+    let s = s.strip_suffix("-dirty").unwrap_or(s);
+
+    // --long format: TAG-N-gSHA. Split from the right so tags with hyphens work.
+    let gpos = s.rfind("-g")?;
+    let sha = &s[gpos + 2..];
+    let rest = &s[..gpos];
+    let npos = rest.rfind('-')?;
+    let n: u32 = rest[npos + 1..].parse().ok()?;
+    let tag = &rest[..npos];
+
+    if tag.is_empty() {
+        return Some(format!("0.0.0+{}", sha));
+    }
+
+    Some(match (n, dirty) {
+        (0, false) => tag.to_string(),
+        (0, true) => format!("{}+{}-dirty", tag, sha),
+        (_, false) => format!("{}+{}", tag, sha),
+        (_, true) => format!("{}+{}-dirty", tag, sha),
+    })
+}

numa.service

@@ -8,6 +8,39 @@ Type=simple
 ExecStart={{exe_path}}
 Restart=always
 RestartSec=2
+
+# Transient system user per start; no PKGBUILD/sysusers setup required.
+# systemd remaps the StateDirectory ownership to the dynamic UID on each
+# launch, including legacy root-owned trees from pre-drop installs.
+DynamicUser=yes
+
+AmbientCapabilities=CAP_NET_BIND_SERVICE
+CapabilityBoundingSet=CAP_NET_BIND_SERVICE
+
+StateDirectory=numa
+StateDirectoryMode=0750
+ConfigurationDirectory=numa
+ConfigurationDirectoryMode=0755
+
+# Sandboxing — conservative set known to work with Rust network daemons.
+# Aggressive hardening (MemoryDenyWriteExecute, SystemCallFilter, seccomp
+# allow-lists) can be layered on once tested in isolation.
+NoNewPrivileges=true
+ProtectSystem=strict
+# DynamicUser= sets ProtectHome=read-only by default — leaves /home
+# readable so systemd can exec binaries installed under it (cargo install,
+# source builds), while blocking writes to user $HOMEs. Don't set =yes:
+# that hides /home entirely and fails with status=203/EXEC.
+PrivateTmp=true
+PrivateDevices=true
+ProtectKernelTunables=true
+ProtectKernelModules=true
+ProtectControlGroups=true
+RestrictRealtime=true
+RestrictSUIDSGID=true
+# AF_NETLINK for interface enumeration on network changes
+RestrictAddressFamilies=AF_INET AF_INET6 AF_UNIX AF_NETLINK
+
 StandardOutput=journal
 StandardError=journal
 SyslogIdentifier=numa

numa.toml

@@ -8,6 +8,16 @@ api_port = 5380
                               # %PROGRAMDATA%\numa on windows. Override for
                               # containerized deploys or tests that can't
                               # write to the system path.
+# filter_aaaa = true          # on IPv4-only networks, answer AAAA queries with
+                              # NODATA (NOERROR + empty answer) so Happy Eyeballs
+                              # clients don't wait on a v6 attempt that can't
+                              # succeed. Also strips `ipv6hint` from HTTPS/SVCB
+                              # records (RFC 9460) so modern browsers (Chrome
+                              # ≥103, Firefox, Safari) don't bypass the AAAA
+                              # filter via SVCB hints. Local zones, overrides,
+                              # and the .numa proxy are NOT filtered — you can
+                              # still configure v6 records for local services.
+                              # Default: false.
 
 # [upstream]
 # mode = "forward"                              # "forward" (default) — relay to upstream
@@ -66,6 +76,13 @@ api_port = 5380
 # [[forwarding]]                                    # DoH upstream: full https:// URL
 # suffix = "example.corp"
 # upstream = "https://dns.quad9.net/dns-query"
+#
+# [[forwarding]]                                    # array of upstreams → SRTT-aware failover
+# suffix = ["google.com", "goog"]                   # fastest-healthy first, dead one skipped
+# upstream = [
+#     "tls://9.9.9.9#dns.quad9.net",
+#     "tls://149.112.112.112#dns.quad9.net",
+# ]
 
 # [blocking]
 # enabled = true               # set to false to disable ad blocking

packaging/relay/Caddyfile

@@ -0,0 +1,15 @@
+odoh-relay.example.com {
+    handle /relay {
+        reverse_proxy numa-relay:8443
+    }
+    handle /health {
+        reverse_proxy numa-relay:8443
+    }
+    respond 404
+
+    # Per-request access logs defeat the point of an oblivious relay.
+    # Aggregate counters are exposed at /health on the relay itself.
+    log {
+        output discard
+    }
+}

packaging/relay/README.md

@@ -0,0 +1,48 @@
+# Numa ODoH Relay — Docker deploy
+
+Two-container deploy: Caddy terminates TLS (auto-provisioning a Let's Encrypt
+cert via ACME) and reverse-proxies to a Numa relay running on an internal
+Docker network. The relay never reads sealed payloads; Caddy never logs them.
+
+## Prerequisites
+
+- A host with public 80/443 reachable from the internet.
+- A DNS record (`A` or `AAAA`) pointing your chosen hostname at the host.
+- Docker + Docker Compose v2.
+
+## Configure
+
+Edit `Caddyfile` and replace `odoh-relay.example.com` with your hostname.
+That hostname is what ACME validates against and what ODoH clients will
+configure as their relay URL: `https://<hostname>/relay`.
+
+## Deploy
+
+```sh
+docker compose up -d
+docker compose logs -f caddy   # watch ACME provisioning
+```
+
+First boot takes a few seconds while Caddy obtains the cert. Subsequent
+restarts reuse the cached cert from the `caddy_data` volume.
+
+## Verify
+
+```sh
+curl https://<hostname>/health
+# ok
+# total 0
+# forwarded_ok 0
+# forwarded_err 0
+# rejected_bad_request 0
+```
+
+Then point any ODoH client at `https://<hostname>/relay` and watch the
+counters tick.
+
+## Listing on the public ecosystem
+
+DNSCrypt's [v3/odoh-relays.md](https://github.com/DNSCrypt/dnscrypt-resolvers/blob/master/v3/odoh-relays.md)
+is the canonical list. The pruned 2025-09-16 commit shows one public ODoH
+relay survived the cull — running this compose file doubles global supply.
+Open a PR there once your relay has been up for ~24 hours.

packaging/relay/docker-compose.yml

@@ -0,0 +1,26 @@
+services:
+  numa-relay:
+    image: ghcr.io/razvandimescu/numa:latest
+    command: ["relay", "8443", "0.0.0.0"]
+    restart: unless-stopped
+    networks: [internal]
+
+  caddy:
+    image: caddy:2
+    ports:
+      - "80:80"
+      - "443:443"
+    volumes:
+      - ./Caddyfile:/etc/caddy/Caddyfile:ro
+      - caddy_data:/data
+      - caddy_config:/config
+    restart: unless-stopped
+    depends_on: [numa-relay]
+    networks: [internal]
+
+networks:
+  internal:
+
+volumes:
+  caddy_data:
+  caddy_config:

site/dashboard.html

@@ -217,6 +217,7 @@ body {
   min-width: 2px;
 }
 .path-bar-fill.forward { background: var(--amber); }
+.path-bar-fill.upstream { background: var(--amber-dim); }
 .path-bar-fill.recursive { background: var(--cyan); }
 .path-bar-fill.cached { background: var(--teal); }
 .path-bar-fill.local { background: var(--violet); }
@@ -227,6 +228,7 @@ body {
 .path-bar-fill.tcp { background: var(--violet); }
 .path-bar-fill.dot { background: var(--emerald); }
 .path-bar-fill.doh { background: var(--teal); }
+.path-bar-fill.odoh { background: var(--violet-dim); }
 .path-pct {
   font-family: var(--font-mono);
   font-size: 0.75rem;
@@ -285,6 +287,7 @@ body {
   font-weight: 500;
 }
 .path-tag.FORWARD { background: rgba(192, 98, 58, 0.12); color: var(--amber-dim); }
+.path-tag.UPSTREAM { background: rgba(160, 120, 72, 0.12); color: var(--amber-dim); }
 .path-tag.RECURSIVE { background: rgba(74, 124, 138, 0.12); color: var(--cyan); }
 .path-tag.CACHED { background: rgba(107, 124, 78, 0.12); color: var(--teal-dim); }
 .path-tag.LOCAL { background: rgba(100, 116, 139, 0.12); color: var(--violet-dim); }
@@ -550,7 +553,11 @@ body {
 @media (max-width: 700px) {
   .stats-row { grid-template-columns: repeat(2, 1fr); }
   .dashboard { padding: 1rem; }
-  .header { padding: 1rem; }
+  .header { padding: 0.8rem 1rem; }
+  .logo { font-size: 1.4rem; }
+  .tagline { display: none; }
+  #headerVersion { display: none; }
+  #phoneSetup { display: none; }
 }
 </style>
 </head>
@@ -559,6 +566,7 @@ body {
 <div class="header">
   <div class="header-left">
     <div class="logo">Numa</div>
+    <span id="headerVersion" style="font-family:var(--font-mono);font-size:0.68rem;color:var(--text-dim);"></span>
     <div class="tagline">DNS that governs itself</div>
   </div>
   <div style="display:flex;align-items:center;gap:1.2rem;">
@@ -630,16 +638,26 @@ body {
     </div>
   </div>
 
-  <!-- Transport breakdown -->
+  <!-- Inbound wire (apps → numa) -->
   <div class="panel">
     <div class="panel-header">
-      <span class="panel-title">Transport</span>
+      <span class="panel-title">Inbound Wire <span style="color: var(--text-dim); font-weight: normal;">apps → numa</span></span>
       <span class="panel-title" id="transportEncrypted" style="color: var(--text-dim)"></span>
     </div>
     <div class="panel-body" id="transportBars">
     </div>
   </div>
 
+  <!-- Outbound wire (numa → internet) -->
+  <div class="panel">
+    <div class="panel-header">
+      <span class="panel-title">Outbound Wire <span style="color: var(--text-dim); font-weight: normal;">numa → internet</span></span>
+      <span class="panel-title" id="upstreamWireEncrypted" style="color: var(--text-dim)"></span>
+    </div>
+    <div class="panel-body" id="upstreamWireBars">
+    </div>
+  </div>
+
   <!-- Main grid: query log + sidebar -->
   <div class="main-grid">
     <!-- Query log -->
@@ -655,6 +673,7 @@ body {
             <option value="RECURSIVE">recursive</option>
             <option value="COALESCED">coalesced</option>
             <option value="FORWARD">forward</option>
+            <option value="UPSTREAM">upstream</option>
             <option value="CACHED">cached</option>
             <option value="BLOCKED">blocked</option>
             <option value="OVERRIDE">override</option>
@@ -936,10 +955,12 @@ function renderMemory(mem, stats) {
 
 function renderBarChart(containerId, defs, data, total) {
   total = total || 1;
-  document.getElementById(containerId).innerHTML = defs.map(d => {
+  document.getElementById(containerId).innerHTML = defs
-    const count = data[d.key] || 0;
+    .filter(d => (data[d.key] || 0) > 0)
-    const pct = ((count / total) * 100).toFixed(1);
+    .map(d => {
-    return `
+      const count = data[d.key] || 0;
+      const pct = ((count / total) * 100).toFixed(1);
+      return `
       <div class="path-bar-row">
         <span class="path-label">${d.label}</span>
         <div class="path-bar-track">
@@ -947,16 +968,19 @@ function renderBarChart(containerId, defs, data, total) {
         </div>
         <span class="path-pct">${pct}%</span>
       </div>`;
-  }).join('');
+    }).join('');
 }
 
-function encryptionPct(transport) {
+function encryptionPct(data, encryptedKeys, allKeys) {
-  const total = (transport.udp + transport.tcp + transport.dot + transport.doh) || 1;
+  const total = allKeys.reduce((s, k) => s + (data[k] || 0), 0);
-  return (((transport.dot + transport.doh) / total) * 100).toFixed(0);
+  if (total === 0) return 0;
+  const encrypted = encryptedKeys.reduce((s, k) => s + (data[k] || 0), 0);
+  return Math.round((encrypted / total) * 100);
 }
 
 const PATH_DEFS = [
   { key: 'forwarded', label: 'Forward', cls: 'forward' },
+  { key: 'upstream',  label: 'Upstream', cls: 'upstream' },
   { key: 'recursive', label: 'Recursive', cls: 'recursive' },
   { key: 'cached',    label: 'Cached',  cls: 'cached' },
   { key: 'local',     label: 'Local',   cls: 'local' },
@@ -979,9 +1003,25 @@ const TRANSPORT_DEFS = [
 function renderTransport(transport) {
   const total = (transport.udp + transport.tcp + transport.dot + transport.doh) || 1;
   renderBarChart('transportBars', TRANSPORT_DEFS, transport, total);
-  const encPct = encryptionPct(transport);
+  const encPct = encryptionPct(transport, ['dot', 'doh'], ['udp', 'tcp', 'dot', 'doh']);
   const el = document.getElementById('transportEncrypted');
-  el.textContent = `${encPct}% encrypted`;
+  el.textContent = `${encPct}% encrypted inbound`;
+  el.style.color = encPct >= 80 ? 'var(--emerald)' : encPct >= 50 ? 'var(--amber)' : 'var(--rose)';
+}
+
+const UPSTREAM_WIRE_DEFS = [
+  { key: 'udp',  label: 'UDP',  cls: 'udp' },
+  { key: 'doh',  label: 'DoH',  cls: 'doh' },
+  { key: 'dot',  label: 'DoT',  cls: 'dot' },
+  { key: 'odoh', label: 'ODoH', cls: 'odoh' },
+];
+
+function renderUpstreamWire(ut) {
+  const total = (ut.udp + ut.doh + ut.dot + ut.odoh) || 0;
+  renderBarChart('upstreamWireBars', UPSTREAM_WIRE_DEFS, ut, total || 1);
+  const encPct = encryptionPct(ut, ['doh', 'dot', 'odoh'], ['udp', 'doh', 'dot', 'odoh']);
+  const el = document.getElementById('upstreamWireEncrypted');
+  el.textContent = total > 0 ? `${encPct}% encrypted outbound` : '';
   el.style.color = encPct >= 80 ? 'var(--emerald)' : encPct >= 50 ? 'var(--amber)' : 'var(--rose)';
 }
 
@@ -1130,16 +1170,23 @@ async function refresh() {
     document.getElementById('totalQueries').textContent = formatNumber(q.total);
     document.getElementById('uptime').textContent = formatUptime(stats.uptime_secs);
     document.getElementById('uptimeSub').textContent = formatUptimeSub(stats.uptime_secs);
+    document.getElementById('headerVersion').textContent = stats.version ? 'v' + stats.version : '';
     document.getElementById('footerUpstream').textContent = stats.upstream || '';
     document.getElementById('footerConfig').textContent = stats.config_path || '';
     document.getElementById('footerData').textContent = stats.data_dir || '';
-    const modeEl = document.getElementById('footerMode');
-    modeEl.textContent = stats.mode || '—';
-    modeEl.style.color = stats.mode === 'recursive' ? 'var(--emerald)' : 'var(--amber)';
     document.getElementById('footerDnssec').textContent = stats.dnssec ? 'on' : 'off';
     document.getElementById('footerDnssec').style.color = stats.dnssec ? 'var(--emerald)' : 'var(--text-dim)';
     document.getElementById('footerSrtt').textContent = stats.srtt ? 'on' : 'off';
     document.getElementById('footerSrtt').style.color = stats.srtt ? 'var(--emerald)' : 'var(--text-dim)';
+    if (!document.getElementById('footerLogs').textContent) {
+      const isWin = stats.data_dir && stats.data_dir.includes(':\\');
+      const isMac = stats.data_dir && stats.data_dir.includes('/usr/local/');
+      const logsEl = document.getElementById('footerLogs');
+      logsEl.textContent = isWin
+        ? stats.data_dir + '\\numa.log'
+        : isMac ? '/usr/local/var/log/numa.log'
+        : 'journalctl -u numa -f';
+    }
 
     // LAN status indicator
     const lanEl = document.getElementById('lanToggle');
@@ -1197,7 +1244,7 @@ async function refresh() {
 
     // QPS calculation
     const now = Date.now();
-    const encPct = encryptionPct(stats.transport);
+    const encPct = encryptionPct(stats.transport, ['dot', 'doh'], ['udp', 'tcp', 'dot', 'doh']);
     if (prevTotal !== null && prevTime !== null) {
       const dt = (now - prevTime) / 1000;
       const dq = q.total - prevTotal;
@@ -1209,13 +1256,14 @@ async function refresh() {
     prevTime = now;
 
     // Cache hit rate
-    const answered = q.cached + q.forwarded + q.recursive + q.coalesced + q.local + q.overridden;
+    const answered = q.cached + q.forwarded + q.upstream + q.recursive + q.coalesced + q.local + q.overridden;
     const hitRate = answered > 0 ? ((q.cached / answered) * 100).toFixed(1) : '0.0';
     document.getElementById('cacheRate').textContent = hitRate + '%';
 
     // Panels
     renderPaths(q);
     renderTransport(stats.transport);
+    renderUpstreamWire(stats.upstream_transport || { udp: 0, doh: 0, dot: 0, odoh: 0 });
     renderQueryLog(logs);
     renderOverrides(overrides);
     renderCache(cache);
@@ -1225,6 +1273,7 @@ async function refresh() {
     renderMemory(stats.memory, stats);
 
   } catch (err) {
+    console.error('[numa dashboard] render failed:', err);
     document.getElementById('statusDot').className = 'status-dot error';
     document.getElementById('statusText').textContent = 'disconnected';
   }
@@ -1339,6 +1388,7 @@ function renderBlockingInfo(info) {
 }
 
 function renderAllowlist(entries) {
+  if (document.activeElement && document.activeElement.id === 'allowDomainInput') return;
   const el = document.getElementById('blockingAllowlist');
   const count = entries.length;
   el.innerHTML = `
@@ -1498,14 +1548,14 @@ refresh();
 setInterval(refresh, 2000);
 </script>
 
-<div style="text-align:center;padding:0.8rem;font-family:var(--font-mono);font-size:0.68rem;color:var(--text-dim);">
+<div style="text-align:center;padding:0.8rem 0.8rem 0.4rem;font-family:var(--font-mono);font-size:0.68rem;color:var(--text-dim);line-height:1.8;">
   Config: <span id="footerConfig" style="user-select:all;color:var(--emerald);"></span>
   · Data: <span id="footerData" style="user-select:all;color:var(--emerald);"></span>
-  · Upstream: <span id="footerUpstream" style="user-select:all;color:var(--emerald);"></span>
+  · Logs: <span id="footerLogs" style="user-select:all;color:var(--emerald);"></span>
-  · Mode: <span id="footerMode" style="color:var(--text-dim);">—</span>
+  <br>
+  Upstream: <span id="footerUpstream" style="user-select:all;color:var(--emerald);"></span>
   · DNSSEC: <span id="footerDnssec" style="color:var(--text-dim);">—</span>
   · SRTT: <span id="footerSrtt" style="color:var(--text-dim);">—</span>
-  · Logs: <span style="user-select:all;color:var(--emerald);">macOS: /usr/local/var/log/numa.log · Linux: journalctl -u numa -f</span>
   · <a href="https://github.com/razvandimescu/numa" target="_blank" rel="noopener" style="color:var(--amber);text-decoration:none;">GitHub</a>
 </div>
 

src/api.rs

@@ -160,6 +160,7 @@ struct QueryLogResponse {
 
 #[derive(Serialize)]
 struct StatsResponse {
+    version: &'static str,
     uptime_secs: u64,
     upstream: String,
     mode: &'static str, // "recursive" or "forward" — never "auto" at runtime
@@ -169,6 +170,7 @@ struct StatsResponse {
     srtt: bool,
     queries: QueriesStats,
     transport: TransportStats,
+    upstream_transport: UpstreamTransportStats,
     cache: CacheStats,
     overrides: OverrideStats,
     blocking: BlockingStatsResponse,
@@ -185,6 +187,14 @@ struct TransportStats {
     doh: u64,
 }
 
+#[derive(Serialize)]
+struct UpstreamTransportStats {
+    udp: u64,
+    doh: u64,
+    dot: u64,
+    odoh: u64,
+}
+
 #[derive(Serialize)]
 struct MobileStatsResponse {
     enabled: bool,
@@ -201,6 +211,7 @@ struct LanStatsResponse {
 struct QueriesStats {
     total: u64,
     forwarded: u64,
+    upstream: u64,
     recursive: u64,
     coalesced: u64,
     cached: u64,
@@ -538,6 +549,7 @@ async fn stats(State(ctx): State<Arc<ServerCtx>>) -> Json<StatsResponse> {
     };
 
     Json(StatsResponse {
+        version: crate::version(),
         uptime_secs: snap.uptime_secs,
         upstream,
         mode: ctx.upstream_mode.as_str(),
@@ -548,6 +560,7 @@ async fn stats(State(ctx): State<Arc<ServerCtx>>) -> Json<StatsResponse> {
         queries: QueriesStats {
             total: snap.total,
             forwarded: snap.forwarded,
+            upstream: snap.upstream,
             recursive: snap.recursive,
             coalesced: snap.coalesced,
             cached: snap.cached,
@@ -562,6 +575,12 @@ async fn stats(State(ctx): State<Arc<ServerCtx>>) -> Json<StatsResponse> {
             dot: snap.transport_dot,
             doh: snap.transport_doh,
         },
+        upstream_transport: UpstreamTransportStats {
+            udp: snap.upstream_transport_udp,
+            doh: snap.upstream_transport_doh,
+            dot: snap.upstream_transport_dot,
+            odoh: snap.upstream_transport_odoh,
+        },
         cache: CacheStats {
             entries: cache_len,
             max_entries: cache_max,

src/blocklist.rs

@@ -1,5 +1,5 @@
 use std::collections::HashSet;
-use std::time::Instant;
+use std::time::{Duration, Instant};
 
 use log::{info, warn};
 
@@ -355,27 +355,144 @@ mod tests {
     }
 }
 
-pub async fn download_blocklists(lists: &[String]) -> Vec<(String, String)> {
+const RETRY_DELAYS_SECS: &[u64] = &[2, 10, 30];
-    let client = reqwest::Client::builder()
-        .timeout(std::time::Duration::from_secs(30))
-        .gzip(true)
-        .build()
-        .unwrap_or_default();
 
-    let mut results = Vec::new();
+pub async fn download_blocklists(
+    lists: &[String],
+    resolver: Option<std::sync::Arc<crate::bootstrap_resolver::NumaResolver>>,
+) -> Vec<(String, String)> {
+    let mut builder = reqwest::Client::builder()
+        .timeout(Duration::from_secs(30))
+        .gzip(true);
+    if let Some(r) = resolver {
+        builder = builder.dns_resolver(r);
+    }
+    let client = builder.build().unwrap_or_default();
 
-    for url in lists {
+    let fetches = lists.iter().map(|url| {
-        match client.get(url).send().await {
+        let client = &client;
-            Ok(resp) => match resp.text().await {
+        async move {
-                Ok(text) => {
+            let text = fetch_with_retry(client, url).await?;
-                    info!("downloaded blocklist: {} ({} bytes)", url, text.len());
+            info!("downloaded blocklist: {} ({} bytes)", url, text.len());
-                    results.push((url.clone(), text));
+            Some((url.clone(), text))
-                }
+        }
-                Err(e) => warn!("failed to read blocklist body {}: {}", url, e),
+    });
-            },
+    futures::future::join_all(fetches)
-            Err(e) => warn!("failed to download blocklist {}: {}", url, e),
+        .await
+        .into_iter()
+        .flatten()
+        .collect()
+}
+
+async fn fetch_with_retry(client: &reqwest::Client, url: &str) -> Option<String> {
+    fetch_with_retry_delays(client, url, RETRY_DELAYS_SECS).await
+}
+
+async fn fetch_with_retry_delays(
+    client: &reqwest::Client,
+    url: &str,
+    delays: &[u64],
+) -> Option<String> {
+    let total = delays.len() + 1;
+    for attempt in 1..=total {
+        match fetch_once(client, url).await {
+            Ok(text) => return Some(text),
+            Err(msg) if attempt < total => {
+                let delay = delays[attempt - 1];
+                warn!(
+                    "blocklist {} attempt {}/{} failed: {} — retrying in {}s",
+                    url, attempt, total, msg, delay
+                );
+                tokio::time::sleep(Duration::from_secs(delay)).await;
+            }
+            Err(msg) => {
+                warn!(
+                    "blocklist {} attempt {}/{} failed: {} — giving up",
+                    url, attempt, total, msg
+                );
+            }
         }
     }
-
+    None
-    results
+}
+
+async fn fetch_once(client: &reqwest::Client, url: &str) -> Result<String, String> {
+    let resp = client
+        .get(url)
+        .send()
+        .await
+        .map_err(|e| format_error_chain(&e))?;
+    resp.text().await.map_err(|e| format_error_chain(&e))
+}
+
+fn format_error_chain(e: &(dyn std::error::Error + 'static)) -> String {
+    let mut parts = vec![e.to_string()];
+    let mut src = e.source();
+    while let Some(s) = src {
+        parts.push(s.to_string());
+        src = s.source();
+    }
+    parts.join(": ")
+}
+
+#[cfg(test)]
+mod retry_tests {
+    use super::*;
+    use std::net::SocketAddr;
+    use tokio::io::{AsyncReadExt, AsyncWriteExt};
+    use tokio::net::TcpListener;
+
+    async fn flaky_http_server(drop_first_n: usize, body: &'static str) -> SocketAddr {
+        let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+        let addr = listener.local_addr().unwrap();
+        tokio::spawn(async move {
+            for _ in 0..drop_first_n {
+                if let Ok((sock, _)) = listener.accept().await {
+                    drop(sock);
+                }
+            }
+            loop {
+                let Ok((mut sock, _)) = listener.accept().await else {
+                    return;
+                };
+                tokio::spawn(async move {
+                    let mut buf = [0u8; 2048];
+                    let _ = sock.read(&mut buf).await;
+                    let response = format!(
+                        "HTTP/1.1 200 OK\r\nContent-Length: {}\r\nContent-Type: text/plain\r\nConnection: close\r\n\r\n{}",
+                        body.len(),
+                        body,
+                    );
+                    let _ = sock.write_all(response.as_bytes()).await;
+                    let _ = sock.shutdown().await;
+                });
+            }
+        });
+        addr
+    }
+
+    fn zero_delays() -> Vec<u64> {
+        vec![0; RETRY_DELAYS_SECS.len()]
+    }
+
+    #[tokio::test]
+    async fn retry_succeeds_on_final_attempt() {
+        let body = "ads.example.com\ntracker.example.net\n";
+        let delays = zero_delays();
+        let addr = flaky_http_server(delays.len(), body).await;
+        let client = reqwest::Client::new();
+        let url = format!("http://{addr}/");
+        let result = fetch_with_retry_delays(&client, &url, &delays).await;
+        assert_eq!(result.as_deref(), Some(body));
+    }
+
+    #[tokio::test]
+    async fn retry_gives_up_when_all_attempts_fail() {
+        let delays = zero_delays();
+        let addr = flaky_http_server(delays.len() + 2, "unreachable").await;
+        let client = reqwest::Client::new();
+        let url = format!("http://{addr}/");
+        let result = fetch_with_retry_delays(&client, &url, &delays).await;
+        assert_eq!(result, None);
+    }
 }

src/bootstrap_resolver.rs

@@ -0,0 +1,235 @@
+//! `reqwest` DNS resolver used by numa-originated HTTPS (DoH upstream, ODoH
+//! relay/target, blocklist CDN). When numa is its own system resolver
+//! (`/etc/resolv.conf → 127.0.0.1`, HAOS add-on, Pi-hole-style container),
+//! the default `getaddrinfo` path loops back through numa before numa can
+//! answer — a chicken-and-egg that deadlocks cold boot. See issue #122 and
+//! `docs/implementation/bootstrap-resolver.md`.
+//!
+//! Resolution order per hostname:
+//! 1. Per-hostname overrides (e.g. ODoH `relay_ip` / `target_ip`) → return
+//!    immediately, no DNS query. Preserves ODoH's "zero plain-DNS leak"
+//!    property for configured endpoints.
+//! 2. Otherwise, query A + AAAA in parallel via UDP to IP-literal bootstrap
+//!    servers, with TCP fallback on UDP timeout (for networks that block
+//!    outbound UDP:53 — see memory: `project_network_udp_hostile.md`).
+
+use std::collections::BTreeMap;
+use std::net::{IpAddr, Ipv4Addr, SocketAddr};
+use std::time::Duration;
+
+use log::{debug, info, warn};
+use reqwest::dns::{Addrs, Name, Resolve, Resolving};
+
+use crate::forward::{forward_tcp, forward_udp};
+use crate::packet::DnsPacket;
+use crate::question::QueryType;
+use crate::record::DnsRecord;
+
+const UDP_TIMEOUT: Duration = Duration::from_millis(800);
+const TCP_TIMEOUT: Duration = Duration::from_millis(1500);
+const DEFAULT_BOOTSTRAP: &[SocketAddr] = &[
+    SocketAddr::new(IpAddr::V4(Ipv4Addr::new(9, 9, 9, 9)), 53),
+    SocketAddr::new(IpAddr::V4(Ipv4Addr::new(1, 1, 1, 1)), 53),
+];
+
+pub struct NumaResolver {
+    bootstrap: Vec<SocketAddr>,
+    overrides: BTreeMap<String, Vec<IpAddr>>,
+}
+
+impl NumaResolver {
+    /// Build a resolver from the configured `upstream.fallback` list and any
+    /// per-hostname overrides (e.g. ODoH's `relay_ip`/`target_ip`).
+    ///
+    /// `fallback` entries are filtered to IP literals only — hostnames would
+    /// re-introduce the self-loop inside the resolver itself. Empty or
+    /// unusable fallback yields the hardcoded default (Quad9 + Cloudflare).
+    pub fn new(fallback: &[String], overrides: BTreeMap<String, Vec<IpAddr>>) -> Self {
+        let mut bootstrap: Vec<SocketAddr> = Vec::with_capacity(fallback.len());
+        for entry in fallback {
+            match crate::forward::parse_upstream_addr(entry, 53) {
+                Ok(addr) => bootstrap.push(addr),
+                Err(_) => {
+                    warn!(
+                        "bootstrap_resolver: skipping non-IP fallback '{}' \
+                         (hostnames would re-enter the self-loop)",
+                        entry
+                    );
+                }
+            }
+        }
+        let source = if bootstrap.is_empty() {
+            bootstrap = DEFAULT_BOOTSTRAP.to_vec();
+            "default (no IP-literal in upstream.fallback)"
+        } else {
+            "upstream.fallback"
+        };
+        let ips: Vec<String> = bootstrap.iter().map(|s| s.ip().to_string()).collect();
+        info!(
+            "bootstrap resolver: {} via {} — used for numa-originated HTTPS hostname resolution",
+            ips.join(", "),
+            source
+        );
+        if !overrides.is_empty() {
+            let pairs: Vec<String> = overrides
+                .iter()
+                .flat_map(|(host, addrs)| addrs.iter().map(move |ip| format!("{}={}", host, ip)))
+                .collect();
+            info!(
+                "bootstrap resolver: host overrides (skip DNS, connect direct): {}",
+                pairs.join(", ")
+            );
+        }
+        Self {
+            bootstrap,
+            overrides,
+        }
+    }
+
+    #[cfg(test)]
+    pub fn bootstrap(&self) -> &[SocketAddr] {
+        &self.bootstrap
+    }
+}
+
+impl Resolve for NumaResolver {
+    fn resolve(&self, name: Name) -> Resolving {
+        let hostname = name.as_str().to_string();
+
+        if let Some(ips) = self.overrides.get(&hostname) {
+            let addrs: Vec<SocketAddr> = ips.iter().map(|ip| SocketAddr::new(*ip, 0)).collect();
+            debug!(
+                "bootstrap_resolver: override hit for {} → {:?}",
+                hostname, ips
+            );
+            return Box::pin(async move { Ok(Box::new(addrs.into_iter()) as Addrs) });
+        }
+
+        let bootstrap = self.bootstrap.clone();
+        Box::pin(async move {
+            let addrs = resolve_via_bootstrap(&hostname, &bootstrap).await?;
+            debug!(
+                "bootstrap_resolver: resolved {} → {} addr(s)",
+                hostname,
+                addrs.len()
+            );
+            Ok(Box::new(addrs.into_iter()) as Addrs)
+        })
+    }
+}
+
+async fn resolve_via_bootstrap(
+    hostname: &str,
+    bootstrap: &[SocketAddr],
+) -> Result<Vec<SocketAddr>, Box<dyn std::error::Error + Send + Sync>> {
+    let mut last_err: Option<String> = None;
+    for &server in bootstrap {
+        let q_a = DnsPacket::query(0xBEEF, hostname, QueryType::A);
+        let q_aaaa = DnsPacket::query(0xBEF0, hostname, QueryType::AAAA);
+        let (a_res, aaaa_res) = tokio::join!(
+            query_with_tcp_fallback(&q_a, server),
+            query_with_tcp_fallback(&q_aaaa, server),
+        );
+
+        let mut out = Vec::new();
+        match a_res {
+            Ok(pkt) => extract_addrs(&pkt, &mut out),
+            Err(e) => last_err = Some(format!("{} A failed: {}", server, e)),
+        }
+        match aaaa_res {
+            Ok(pkt) => extract_addrs(&pkt, &mut out),
+            // AAAA is optional — many hosts return NXDOMAIN/empty. Don't
+            // treat as the primary error if A succeeded.
+            Err(e) => debug!("bootstrap {} AAAA for {} failed: {}", server, hostname, e),
+        }
+        if !out.is_empty() {
+            return Ok(out);
+        }
+    }
+    Err(last_err
+        .unwrap_or_else(|| "no bootstrap servers reachable".into())
+        .into())
+}
+
+async fn query_with_tcp_fallback(
+    query: &DnsPacket,
+    server: SocketAddr,
+) -> crate::Result<DnsPacket> {
+    match forward_udp(query, server, UDP_TIMEOUT).await {
+        Ok(pkt) => Ok(pkt),
+        Err(e) => {
+            debug!(
+                "bootstrap UDP {} failed ({}), falling back to TCP",
+                server, e
+            );
+            forward_tcp(query, server, TCP_TIMEOUT).await
+        }
+    }
+}
+
+fn extract_addrs(pkt: &DnsPacket, out: &mut Vec<SocketAddr>) {
+    for r in &pkt.answers {
+        match r {
+            DnsRecord::A { addr, .. } => out.push(SocketAddr::new(IpAddr::V4(*addr), 0)),
+            DnsRecord::AAAA { addr, .. } => out.push(SocketAddr::new(IpAddr::V6(*addr), 0)),
+            _ => {}
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::net::{Ipv4Addr, Ipv6Addr};
+
+    #[test]
+    fn empty_fallback_uses_defaults() {
+        let r = NumaResolver::new(&[], BTreeMap::new());
+        let got: Vec<String> = r.bootstrap().iter().map(|s| s.to_string()).collect();
+        assert_eq!(got, vec!["9.9.9.9:53", "1.1.1.1:53"]);
+    }
+
+    #[test]
+    fn fallback_accepts_ip_literals_only() {
+        let fallback = vec![
+            "9.9.9.9".to_string(),
+            "dns.quad9.net".to_string(),
+            "1.1.1.1:5353".to_string(),
+        ];
+        let r = NumaResolver::new(&fallback, BTreeMap::new());
+        let got: Vec<String> = r.bootstrap().iter().map(|s| s.to_string()).collect();
+        assert_eq!(got, vec!["9.9.9.9:53", "1.1.1.1:5353"]);
+    }
+
+    #[test]
+    fn override_returns_configured_ips_without_dns() {
+        let mut overrides = BTreeMap::new();
+        overrides.insert(
+            "odoh-relay.example".to_string(),
+            vec![IpAddr::V4(Ipv4Addr::new(178, 104, 229, 30))],
+        );
+        let r = NumaResolver::new(&[], overrides);
+        let name: Name = "odoh-relay.example".parse().unwrap();
+        let fut = r.resolve(name);
+        let res = futures::executor::block_on(fut).unwrap();
+        let addrs: Vec<_> = res.collect();
+        assert_eq!(addrs.len(), 1);
+        assert_eq!(addrs[0].ip(), IpAddr::V4(Ipv4Addr::new(178, 104, 229, 30)));
+    }
+
+    #[test]
+    fn override_supports_multiple_ips_including_ipv6() {
+        let mut overrides = BTreeMap::new();
+        overrides.insert(
+            "dual.example".to_string(),
+            vec![
+                IpAddr::V4(Ipv4Addr::new(1, 2, 3, 4)),
+                IpAddr::V6(Ipv6Addr::LOCALHOST),
+            ],
+        );
+        let r = NumaResolver::new(&[], overrides);
+        let res = futures::executor::block_on(r.resolve("dual.example".parse().unwrap())).unwrap();
+        let addrs: Vec<_> = res.collect();
+        assert_eq!(addrs.len(), 2);
+    }
+}

src/config.rs

@@ -1,7 +1,7 @@
 use std::collections::HashMap;
-use std::net::Ipv4Addr;
+use std::net::{IpAddr, Ipv4Addr, Ipv6Addr, SocketAddr};
-use std::net::Ipv6Addr;
 use std::path::{Path, PathBuf};
+use std::time::Duration;
 
 use serde::Deserialize;
 
@@ -41,17 +41,30 @@ pub struct Config {
 pub struct ForwardingRuleConfig {
     #[serde(deserialize_with = "string_or_vec")]
     pub suffix: Vec<String>,
-    pub upstream: String,
+    #[serde(deserialize_with = "string_or_vec")]
+    pub upstream: Vec<String>,
 }
 
 impl ForwardingRuleConfig {
     fn to_runtime_rules(&self) -> Result<Vec<crate::system_dns::ForwardingRule>> {
-        let upstream = crate::forward::parse_upstream(&self.upstream, 53)
+        if self.upstream.is_empty() {
-            .map_err(|e| format!("forwarding rule for upstream '{}': {}", self.upstream, e))?;
+            return Err(format!(
+                "forwarding rule for suffix {:?}: upstream must not be empty",
+                self.suffix
+            )
+            .into());
+        }
+        let mut primary = Vec::with_capacity(self.upstream.len());
+        for s in &self.upstream {
+            let u = crate::forward::parse_upstream(s, 53, None)
+                .map_err(|e| format!("forwarding rule for upstream '{}': {}", s, e))?;
+            primary.push(u);
+        }
+        let pool = crate::forward::UpstreamPool::new(primary, vec![]);
         Ok(self
             .suffix
             .iter()
-            .map(|s| crate::system_dns::ForwardingRule::new(s.clone(), upstream.clone()))
+            .map(|s| crate::system_dns::ForwardingRule::new(s.clone(), pool.clone()))
             .collect())
     }
 }
@@ -80,6 +93,12 @@ pub struct ServerConfig {
     /// Defaults to `crate::data_dir()` (platform-specific system path) if unset.
     #[serde(default)]
     pub data_dir: Option<PathBuf>,
+    /// Synthesize NODATA (NOERROR + empty answer) for AAAA queries, and
+    /// strip `ipv6hint` from HTTPS/SVCB responses (RFC 9460). For IPv4-only
+    /// networks where Happy Eyeballs fallback adds latency. Local zones,
+    /// overrides, and the service proxy are not affected. Default false.
+    #[serde(default)]
+    pub filter_aaaa: bool,
 }
 
 impl Default for ServerConfig {
@@ -89,6 +108,7 @@ impl Default for ServerConfig {
             api_port: default_api_port(),
             api_bind_addr: default_api_bind_addr(),
             data_dir: None,
+            filter_aaaa: false,
         }
     }
 }
@@ -114,6 +134,7 @@ pub enum UpstreamMode {
     #[default]
     Forward,
     Recursive,
+    Odoh,
 }
 
 impl UpstreamMode {
@@ -122,6 +143,20 @@ impl UpstreamMode {
             UpstreamMode::Auto => "auto",
             UpstreamMode::Forward => "forward",
             UpstreamMode::Recursive => "recursive",
+            UpstreamMode::Odoh => "odoh",
+        }
+    }
+
+    /// Hedging duplicates the in-flight query against the same upstream to
+    /// rescue tail latency. Beneficial for UDP/DoH/DoT (cheap retransmit /
+    /// h2 stream multiplexing). For ODoH it doubles the relay's HPKE
+    /// seal/unseal load and the sealed-byte footprint a passive observer
+    /// can correlate, with no latency win — the relay hop dominates either
+    /// way. Force-zero in oblivious mode regardless of `hedge_ms`.
+    pub fn hedge_delay(self, hedge_ms: u64) -> Duration {
+        match self {
+            UpstreamMode::Odoh => Duration::ZERO,
+            _ => Duration::from_millis(hedge_ms),
         }
     }
 }
@@ -134,7 +169,7 @@ pub struct UpstreamConfig {
     pub address: Vec<String>,
     #[serde(default = "default_upstream_port")]
     pub port: u16,
-    #[serde(default)]
+    #[serde(default, deserialize_with = "string_or_vec")]
     pub fallback: Vec<String>,
     #[serde(default = "default_timeout_ms")]
     pub timeout_ms: u64,
@@ -146,6 +181,30 @@ pub struct UpstreamConfig {
     pub prime_tlds: Vec<String>,
     #[serde(default = "default_srtt")]
     pub srtt: bool,
+
+    /// Only used when `mode = "odoh"`. Full https:// URL of the relay
+    /// endpoint (including path, e.g. `https://odoh-relay.numa.rs/relay`).
+    #[serde(default)]
+    pub relay: Option<String>,
+    /// Only used when `mode = "odoh"`. Full https:// URL of the target
+    /// resolver (`https://odoh.cloudflare-dns.com/dns-query`).
+    #[serde(default)]
+    pub target: Option<String>,
+    /// Only used when `mode = "odoh"`. When true (the default), relay failure
+    /// returns SERVFAIL instead of downgrading to the `fallback` upstream —
+    /// a user who configured ODoH rarely wants a silent non-oblivious path.
+    #[serde(default)]
+    pub strict: Option<bool>,
+
+    /// Bootstrap IP for the relay host, used when numa is its own system
+    /// resolver (otherwise the ODoH HTTPS client loops resolving through
+    /// itself). TLS still validates the cert against `relay`'s hostname.
+    #[serde(default)]
+    pub relay_ip: Option<IpAddr>,
+
+    /// Same as `relay_ip` but for the target host.
+    #[serde(default)]
+    pub target_ip: Option<IpAddr>,
 }
 
 impl Default for UpstreamConfig {
@@ -160,10 +219,128 @@ impl Default for UpstreamConfig {
             root_hints: default_root_hints(),
             prime_tlds: default_prime_tlds(),
             srtt: default_srtt(),
+            relay: None,
+            target: None,
+            strict: None,
+            relay_ip: None,
+            target_ip: None,
         }
     }
 }
 
+/// Parsed ODoH config fields. `mode = "odoh"` requires both URLs to be
+/// present, to parse as `https://`, and to resolve to distinct hosts.
+#[derive(Debug)]
+pub struct OdohUpstream {
+    pub relay_url: String,
+    pub relay_host: String,
+    pub target_host: String,
+    pub target_path: String,
+    pub strict: bool,
+    pub relay_bootstrap: Option<SocketAddr>,
+    pub target_bootstrap: Option<SocketAddr>,
+}
+
+impl OdohUpstream {
+    /// Per-host IP overrides for the bootstrap resolver, lifted from
+    /// `relay_ip`/`target_ip`. Keeps the "zero plain-DNS leak for ODoH
+    /// endpoints" property when numa is its own system resolver.
+    pub fn host_ip_overrides(&self) -> std::collections::BTreeMap<String, Vec<std::net::IpAddr>> {
+        let mut out = std::collections::BTreeMap::new();
+        if let Some(addr) = self.relay_bootstrap {
+            out.entry(self.relay_host.clone())
+                .or_insert_with(Vec::new)
+                .push(addr.ip());
+        }
+        if let Some(addr) = self.target_bootstrap {
+            out.entry(self.target_host.clone())
+                .or_insert_with(Vec::new)
+                .push(addr.ip());
+        }
+        out
+    }
+}
+
+impl UpstreamConfig {
+    /// Validate and extract ODoH-specific fields. Called during `load_config`
+    /// so misconfigured ODoH fails fast at startup, the same care we take
+    /// with the DNSSEC strict boot check.
+    pub fn odoh_upstream(&self) -> Result<OdohUpstream> {
+        let relay = self
+            .relay
+            .as_deref()
+            .ok_or("mode = \"odoh\" requires upstream.relay")?;
+        let target = self
+            .target
+            .as_deref()
+            .ok_or("mode = \"odoh\" requires upstream.target")?;
+
+        let relay_url = reqwest::Url::parse(relay)
+            .map_err(|e| format!("upstream.relay invalid URL '{}': {}", relay, e))?;
+        let target_url = reqwest::Url::parse(target)
+            .map_err(|e| format!("upstream.target invalid URL '{}': {}", target, e))?;
+
+        if relay_url.scheme() != "https" || target_url.scheme() != "https" {
+            return Err("upstream.relay and upstream.target must both use https://".into());
+        }
+        let relay_host = relay_url
+            .host_str()
+            .ok_or("upstream.relay must include a host")?
+            .to_string();
+        let target_host = target_url
+            .host_str()
+            .ok_or("upstream.target must include a host")?
+            .to_string();
+
+        if relay_host == target_host {
+            return Err(format!(
+                "upstream.relay and upstream.target resolve to the same host ({}); the privacy property requires distinct operators",
+                relay_host
+            )
+            .into());
+        }
+        if let Some(shared) = shared_registrable_domain(&relay_host, &target_host) {
+            return Err(format!(
+                "upstream.relay ({}) and upstream.target ({}) share the registrable domain ({}); the privacy property requires distinct operators",
+                relay_host, target_host, shared
+            )
+            .into());
+        }
+        let target_path = if target_url.path().is_empty() {
+            "/".to_string()
+        } else {
+            target_url.path().to_string()
+        };
+
+        let relay_port = relay_url.port_or_known_default().unwrap_or(443);
+        let target_port = target_url.port_or_known_default().unwrap_or(443);
+
+        Ok(OdohUpstream {
+            relay_url: relay.to_string(),
+            relay_host,
+            target_host,
+            target_path,
+            strict: self.strict.unwrap_or(true),
+            relay_bootstrap: self.relay_ip.map(|ip| SocketAddr::new(ip, relay_port)),
+            target_bootstrap: self.target_ip.map(|ip| SocketAddr::new(ip, target_port)),
+        })
+    }
+}
+
+/// Returns the registrable domain (eTLD+1) shared by both hosts, if any.
+/// Fails open on hosts the PSL can't parse (IP literals, bare TLDs).
+fn shared_registrable_domain(relay_host: &str, target_host: &str) -> Option<String> {
+    let relay = psl::domain(relay_host.as_bytes())?;
+    let target = psl::domain(target_host.as_bytes())?;
+    if relay.as_bytes() == target.as_bytes() {
+        std::str::from_utf8(relay.as_bytes())
+            .ok()
+            .map(str::to_owned)
+    } else {
+        None
+    }
+}
+
 fn string_or_vec<'de, D>(deserializer: D) -> std::result::Result<Vec<String>, D::Error>
 where
     D: serde::Deserializer<'de>,
@@ -567,6 +744,17 @@ mod tests {
         assert!(config.lan.enabled);
     }
 
+    #[test]
+    fn filter_aaaa_defaults_false() {
+        assert!(!ServerConfig::default().filter_aaaa);
+    }
+
+    #[test]
+    fn filter_aaaa_parses_from_server_section() {
+        let config: Config = toml::from_str("[server]\nfilter_aaaa = true").unwrap();
+        assert!(config.server.filter_aaaa);
+    }
+
     #[test]
     fn custom_bind_addrs_parse() {
         let toml = r#"
@@ -612,12 +800,22 @@ mod tests {
     }
 
     #[test]
-    fn fallback_parses() {
+    fn fallback_array_parses() {
         let config: Config =
             toml::from_str("[upstream]\nfallback = [\"8.8.8.8\", \"1.1.1.1\"]").unwrap();
         assert_eq!(config.upstream.fallback, vec!["8.8.8.8", "1.1.1.1"]);
     }
 
+    #[test]
+    fn fallback_string_parses_as_singleton_vec() {
+        let config: Config =
+            toml::from_str("[upstream]\nfallback = \"tls://1.1.1.1#cloudflare-dns.com\"").unwrap();
+        assert_eq!(
+            config.upstream.fallback,
+            vec!["tls://1.1.1.1#cloudflare-dns.com"]
+        );
+    }
+
     #[test]
     fn empty_address_gives_empty_vec() {
         let config: Config = toml::from_str("").unwrap();
@@ -625,6 +823,222 @@ mod tests {
         assert!(config.upstream.fallback.is_empty());
     }
 
+    // ── [upstream] mode = "odoh" ────────────────────────────────────────
+
+    #[test]
+    fn odoh_config_parses_and_validates() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        assert!(matches!(config.upstream.mode, UpstreamMode::Odoh));
+        let odoh = config.upstream.odoh_upstream().unwrap();
+        assert_eq!(odoh.relay_url, "https://odoh-relay.numa.rs/relay");
+        assert_eq!(odoh.target_host, "odoh.cloudflare-dns.com");
+        assert_eq!(odoh.target_path, "/dns-query");
+        assert!(odoh.strict, "strict defaults to true under mode=odoh");
+    }
+
+    #[test]
+    fn odoh_strict_false_is_honoured() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+strict = false
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        assert!(!config.upstream.odoh_upstream().unwrap().strict);
+    }
+
+    #[test]
+    fn odoh_rejects_same_host_relay_and_target() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh.example.com/relay"
+target = "https://odoh.example.com/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let err = config.upstream.odoh_upstream().unwrap_err().to_string();
+        assert!(err.contains("same host"), "got: {err}");
+    }
+
+    #[test]
+    fn odoh_rejects_shared_registrable_domain() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://r.cloudflare.com/relay"
+target = "https://odoh.cloudflare.com/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let err = config.upstream.odoh_upstream().unwrap_err().to_string();
+        assert!(err.contains("registrable domain"), "got: {err}");
+        assert!(err.contains("cloudflare.com"), "got: {err}");
+    }
+
+    #[test]
+    fn odoh_rejects_shared_registrable_under_multi_label_suffix() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://a.foo.co.uk/relay"
+target = "https://b.foo.co.uk/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let err = config.upstream.odoh_upstream().unwrap_err().to_string();
+        assert!(err.contains("foo.co.uk"), "got: {err}");
+    }
+
+    #[test]
+    fn odoh_accepts_distinct_registrable_under_multi_label_suffix() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://relay.foo.co.uk/relay"
+target = "https://target.bar.co.uk/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        assert!(config.upstream.odoh_upstream().is_ok());
+    }
+
+    #[test]
+    fn odoh_accepts_distinct_private_psl_suffix_subdomains() {
+        // *.github.io is a public suffix, so foo.github.io and bar.github.io
+        // are independent registrable domains — accept.
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://foo.github.io/relay"
+target = "https://bar.github.io/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        assert!(config.upstream.odoh_upstream().is_ok());
+    }
+
+    #[test]
+    fn odoh_rejects_non_https() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "http://odoh-relay.numa.rs/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let err = config.upstream.odoh_upstream().unwrap_err().to_string();
+        assert!(err.contains("https"), "got: {err}");
+    }
+
+    #[test]
+    fn odoh_missing_relay_rejected() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let err = config.upstream.odoh_upstream().unwrap_err().to_string();
+        assert!(err.contains("upstream.relay"), "got: {err}");
+    }
+
+    #[test]
+    fn odoh_bootstrap_ips_parse_into_socket_addrs() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+relay_ip = "178.104.229.30"
+target_ip = "104.16.249.249"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let odoh = config.upstream.odoh_upstream().unwrap();
+        assert_eq!(odoh.relay_host, "odoh-relay.numa.rs");
+        assert_eq!(
+            odoh.relay_bootstrap.unwrap().to_string(),
+            "178.104.229.30:443"
+        );
+        assert_eq!(
+            odoh.target_bootstrap.unwrap().to_string(),
+            "104.16.249.249:443"
+        );
+    }
+
+    #[test]
+    fn odoh_bootstrap_ips_optional() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let odoh = config.upstream.odoh_upstream().unwrap();
+        assert!(odoh.relay_bootstrap.is_none());
+        assert!(odoh.target_bootstrap.is_none());
+    }
+
+    #[test]
+    fn odoh_bootstrap_ip_rejects_garbage() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+relay_ip = "not-an-ip"
+"#;
+        let err = toml::from_str::<Config>(toml).err().unwrap().to_string();
+        assert!(err.contains("relay_ip"), "got: {err}");
+    }
+
+    #[test]
+    fn odoh_bootstrap_uses_url_port_when_non_default() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs:8443/relay"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+relay_ip = "178.104.229.30"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let odoh = config.upstream.odoh_upstream().unwrap();
+        assert_eq!(
+            odoh.relay_bootstrap.unwrap().to_string(),
+            "178.104.229.30:8443"
+        );
+    }
+
+    #[test]
+    fn hedge_delay_zeroed_for_odoh_mode() {
+        assert_eq!(
+            UpstreamMode::Odoh.hedge_delay(50),
+            Duration::ZERO,
+            "ODoH mode must zero hedge regardless of configured hedge_ms"
+        );
+        assert_eq!(
+            UpstreamMode::Forward.hedge_delay(50),
+            Duration::from_millis(50),
+            "non-ODoH modes honour configured hedge_ms"
+        );
+    }
+
+    #[test]
+    fn odoh_missing_target_rejected() {
+        let toml = r#"
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.numa.rs/relay"
+"#;
+        let config: Config = toml::from_str(toml).unwrap();
+        let err = config.upstream.odoh_upstream().unwrap_err().to_string();
+        assert!(err.contains("upstream.target"), "got: {err}");
+    }
+
     // ── issue #82: [[forwarding]] config section ────────────────────────
 
     #[test]
@@ -643,7 +1057,7 @@ mod tests {
         let config: Config = toml::from_str(toml).unwrap();
         assert_eq!(config.forwarding.len(), 1);
         assert_eq!(config.forwarding[0].suffix, &["home.local"]);
-        assert_eq!(config.forwarding[0].upstream, "100.90.1.63:5361");
+        assert_eq!(config.forwarding[0].upstream, vec!["100.90.1.63:5361"]);
     }
 
     #[test]
@@ -671,7 +1085,7 @@ mod tests {
         "#;
         let config: Config = toml::from_str(toml).unwrap();
         assert_eq!(config.forwarding.len(), 2);
-        assert_eq!(config.forwarding[1].upstream, "10.0.0.1");
+        assert_eq!(config.forwarding[1].upstream, vec!["10.0.0.1"]);
     }
 
     #[test]
@@ -693,28 +1107,29 @@ mod tests {
     fn forwarding_suffix_array_expands_to_multiple_runtime_rules() {
         let rule = ForwardingRuleConfig {
             suffix: vec!["168.192.in-addr.arpa".to_string(), "onsite".to_string()],
-            upstream: "192.168.88.1".to_string(),
+            upstream: vec!["192.168.88.1".to_string()],
         };
         let runtime = rule.to_runtime_rules().unwrap();
         assert_eq!(runtime.len(), 2);
         assert_eq!(runtime[0].suffix, "168.192.in-addr.arpa");
         assert_eq!(runtime[1].suffix, "onsite");
-        assert_eq!(runtime[0].upstream, runtime[1].upstream);
+        assert_eq!(
+            runtime[0].upstream.preferred(),
+            runtime[1].upstream.preferred()
+        );
     }
 
     #[test]
     fn forwarding_upstream_with_explicit_port() {
         let rule = ForwardingRuleConfig {
             suffix: vec!["home.local".to_string()],
-            upstream: "100.90.1.63:5361".to_string(),
+            upstream: vec!["100.90.1.63:5361".to_string()],
         };
         let runtime = rule.to_runtime_rules().unwrap();
         assert_eq!(runtime.len(), 1);
-        assert!(matches!(
+        let preferred = runtime[0].upstream.preferred().unwrap();
-            runtime[0].upstream,
+        assert!(matches!(preferred, crate::forward::Upstream::Udp(_)));
-            crate::forward::Upstream::Udp(_)
+        assert_eq!(preferred.to_string(), "100.90.1.63:5361");
-        ));
-        assert_eq!(runtime[0].upstream.to_string(), "100.90.1.63:5361");
         assert_eq!(runtime[0].suffix, "home.local");
     }
 
@@ -722,17 +1137,20 @@ mod tests {
     fn forwarding_upstream_defaults_to_port_53() {
         let rule = ForwardingRuleConfig {
             suffix: vec!["home.local".to_string()],
-            upstream: "100.90.1.63".to_string(),
+            upstream: vec!["100.90.1.63".to_string()],
         };
         let runtime = rule.to_runtime_rules().unwrap();
-        assert_eq!(runtime[0].upstream.to_string(), "100.90.1.63:53");
+        assert_eq!(
+            runtime[0].upstream.preferred().unwrap().to_string(),
+            "100.90.1.63:53"
+        );
     }
 
     #[test]
     fn forwarding_invalid_upstream_returns_error() {
         let rule = ForwardingRuleConfig {
             suffix: vec!["home.local".to_string()],
-            upstream: "not-a-valid-host".to_string(),
+            upstream: vec!["not-a-valid-host".to_string()],
         };
         assert!(rule.to_runtime_rules().is_err());
     }
@@ -741,14 +1159,14 @@ mod tests {
     fn forwarding_upstream_accepts_dot_scheme() {
         let rule = ForwardingRuleConfig {
             suffix: vec!["google.com".to_string()],
-            upstream: "tls://9.9.9.9#dns.quad9.net".to_string(),
+            upstream: vec!["tls://9.9.9.9#dns.quad9.net".to_string()],
         };
         let runtime = rule
             .to_runtime_rules()
             .expect("tls:// upstream should parse");
         assert_eq!(runtime.len(), 1);
         assert_eq!(
-            runtime[0].upstream.to_string(),
+            runtime[0].upstream.preferred().unwrap().to_string(),
             "tls://9.9.9.9:853#dns.quad9.net"
         );
     }
@@ -757,14 +1175,14 @@ mod tests {
     fn forwarding_upstream_accepts_doh_scheme() {
         let rule = ForwardingRuleConfig {
             suffix: vec!["goog".to_string()],
-            upstream: "https://dns.quad9.net/dns-query".to_string(),
+            upstream: vec!["https://dns.quad9.net/dns-query".to_string()],
         };
         let runtime = rule
             .to_runtime_rules()
             .expect("https:// upstream should parse");
         assert_eq!(runtime.len(), 1);
         assert_eq!(
-            runtime[0].upstream.to_string(),
+            runtime[0].upstream.preferred().unwrap().to_string(),
             "https://dns.quad9.net/dns-query"
         );
     }
@@ -773,44 +1191,90 @@ mod tests {
     fn forwarding_config_rules_take_precedence_over_discovered() {
         let config_rules = vec![ForwardingRuleConfig {
             suffix: vec!["home.local".to_string()],
-            upstream: "10.0.0.1:53".to_string(),
+            upstream: vec!["10.0.0.1:53".to_string()],
         }];
         let discovered = vec![crate::system_dns::ForwardingRule::new(
             "home.local".to_string(),
-            crate::forward::Upstream::Udp("192.168.1.1:53".parse().unwrap()),
+            crate::forward::UpstreamPool::new(
+                vec![crate::forward::Upstream::Udp(
+                    "192.168.1.1:53".parse().unwrap(),
+                )],
+                vec![],
+            ),
         )];
         let merged = merge_forwarding_rules(&config_rules, discovered).unwrap();
         let picked = crate::system_dns::match_forwarding_rule("host.home.local", &merged)
             .expect("rule should match");
-        assert_eq!(picked.to_string(), "10.0.0.1:53");
+        assert_eq!(picked.preferred().unwrap().to_string(), "10.0.0.1:53");
     }
 
     #[test]
     fn forwarding_merge_preserves_non_overlapping_discovered() {
         let config_rules = vec![ForwardingRuleConfig {
             suffix: vec!["home.local".to_string()],
-            upstream: "10.0.0.1:53".to_string(),
+            upstream: vec!["10.0.0.1:53".to_string()],
         }];
         let discovered = vec![crate::system_dns::ForwardingRule::new(
             "corp.example".to_string(),
-            crate::forward::Upstream::Udp("192.168.1.1:53".parse().unwrap()),
+            crate::forward::UpstreamPool::new(
+                vec![crate::forward::Upstream::Udp(
+                    "192.168.1.1:53".parse().unwrap(),
+                )],
+                vec![],
+            ),
         )];
         let merged = merge_forwarding_rules(&config_rules, discovered).unwrap();
         assert_eq!(merged.len(), 2);
         let picked = crate::system_dns::match_forwarding_rule("host.corp.example", &merged)
             .expect("discovered rule should still match");
-        assert_eq!(picked.to_string(), "192.168.1.1:53");
+        assert_eq!(picked.preferred().unwrap().to_string(), "192.168.1.1:53");
     }
 
     #[test]
     fn forwarding_merge_suffix_array_expands_to_multiple_rules() {
         let config_rules = vec![ForwardingRuleConfig {
             suffix: vec!["a.local".to_string(), "b.local".to_string()],
-            upstream: "10.0.0.1:53".to_string(),
+            upstream: vec!["10.0.0.1:53".to_string()],
         }];
         let merged = merge_forwarding_rules(&config_rules, vec![]).unwrap();
         assert_eq!(merged.len(), 2);
     }
+
+    #[test]
+    fn forwarding_parses_upstream_array() {
+        let toml = r#"
+            [[forwarding]]
+            suffix = "google.com"
+            upstream = ["tls://9.9.9.9#dns.quad9.net", "tls://149.112.112.112#dns.quad9.net"]
+        "#;
+        let config: Config = toml::from_str(toml).unwrap();
+        assert_eq!(config.forwarding.len(), 1);
+        assert_eq!(config.forwarding[0].upstream.len(), 2);
+    }
+
+    #[test]
+    fn forwarding_upstream_array_builds_pool_with_multiple_primaries() {
+        let rule = ForwardingRuleConfig {
+            suffix: vec!["google.com".to_string()],
+            upstream: vec![
+                "tls://9.9.9.9#dns.quad9.net".to_string(),
+                "tls://149.112.112.112#dns.quad9.net".to_string(),
+            ],
+        };
+        let runtime = rule.to_runtime_rules().unwrap();
+        assert_eq!(runtime.len(), 1);
+        let label = runtime[0].upstream.label();
+        assert!(label.contains("+1 more"), "label was: {}", label);
+    }
+
+    #[test]
+    fn forwarding_empty_upstream_array_errors() {
+        let rule = ForwardingRuleConfig {
+            suffix: vec!["home.local".to_string()],
+            upstream: vec![],
+        };
+        assert!(rule.to_runtime_rules().is_err());
+    }
 }
 
 pub struct ConfigLoad {

src/ctx.rs

@@ -16,7 +16,9 @@ use crate::blocklist::BlocklistStore;
 use crate::buffer::BytePacketBuffer;
 use crate::cache::{DnsCache, DnssecStatus};
 use crate::config::{UpstreamMode, ZoneMap};
-use crate::forward::{forward_query_raw, forward_with_failover_raw, Upstream, UpstreamPool};
+#[cfg(test)]
+use crate::forward::Upstream;
+use crate::forward::{forward_with_failover_raw, UpstreamPool};
 use crate::header::ResultCode;
 use crate::health::HealthMeta;
 use crate::lan::PeerStore;
@@ -75,6 +77,10 @@ pub struct ServerCtx {
     pub ca_pem: Option<String>,
     pub mobile_enabled: bool,
     pub mobile_port: u16,
+    /// When true, AAAA queries short-circuit with NODATA (NOERROR + empty
+    /// answer) instead of hitting cache/forwarding/upstream. Local data
+    /// (overrides, zones, .numa proxy, blocklist sinkhole) is unaffected.
+    pub filter_aaaa: bool,
 }
 
 /// Transport-agnostic DNS resolution. Runs the full pipeline (overrides, blocklist,
@@ -99,6 +105,7 @@ pub async fn resolve_query(
     // Pipeline: overrides -> .localhost -> local zones -> special-use (unless forwarded)
     //        -> .tld proxy -> blocklist -> cache -> forwarding -> recursive/upstream
     // Each lock is scoped to avoid holding MutexGuard across await points.
+    let mut upstream_transport: Option<crate::stats::UpstreamTransport> = None;
     let (response, path, dnssec) = {
         let override_record = ctx.overrides.read().unwrap().lookup(&qname);
         if let Some(record) = override_record {
@@ -170,6 +177,13 @@ pub async fn resolve_query(
                 60,
             ));
             (resp, QueryPath::Blocked, DnssecStatus::Indeterminate)
+        } else if qtype == QueryType::AAAA && ctx.filter_aaaa {
+            // RFC 2308 NODATA: NOERROR with empty answer section. Prevents
+            // Happy Eyeballs clients from waiting on an AAAA they'll never use
+            // on IPv4-only networks. NXDOMAIN would be wrong (it'd imply the
+            // name doesn't exist for A either).
+            let resp = DnsPacket::response_from(&query, ResultCode::NOERROR);
+            (resp, QueryPath::Local, DnssecStatus::Indeterminate)
         } else {
             let cached = ctx.cache.read().unwrap().lookup_with_status(&qname, qtype);
             if let Some((cached, cached_dnssec, freshness)) = cached {
@@ -190,84 +204,73 @@ pub async fn resolve_query(
                     resp.header.authed_data = true;
                 }
                 (resp, QueryPath::Cached, cached_dnssec)
-            } else if let Some(upstream) =
+            } else if let Some(pool) =
                 crate::system_dns::match_forwarding_rule(&qname, &ctx.forwarding_rules)
             {
                 // Conditional forwarding takes priority over recursive mode
                 // (e.g. Tailscale .ts.net, VPC private zones)
-                match forward_and_cache(raw_wire, upstream, ctx, &qname, qtype).await {
-                    Ok(resp) => (resp, QueryPath::Forwarded, DnssecStatus::Indeterminate),
-                    Err(e) => {
-                        error!(
-                            "{} | {:?} {} | FORWARD ERROR | {}",
-                            src_addr, qtype, qname, e
-                        );
-                        (
-                            DnsPacket::response_from(&query, ResultCode::SERVFAIL),
-                            QueryPath::UpstreamError,
-                            DnssecStatus::Indeterminate,
-                        )
-                    }
-                }
-            } else if ctx.upstream_mode == UpstreamMode::Recursive {
                 let key = (qname.clone(), qtype);
-                let (resp, path, err) = resolve_coalesced(&ctx.inflight, key, &query, || {
+                let (resp, path, err) =
-                    crate::recursive::resolve_recursive(
+                    resolve_coalesced(&ctx.inflight, key, &query, QueryPath::Forwarded, || async {
-                        &qname,
+                        let wire = forward_with_failover_raw(
-                        qtype,
+                            raw_wire,
-                        &ctx.cache,
+                            pool,
-                        &query,
+                            &ctx.srtt,
-                        &ctx.root_hints,
+                            ctx.timeout,
-                        &ctx.srtt,
+                            ctx.hedge_delay,
-                    )
+                        )
-                })
+                        .await?;
-                .await;
+                        cache_and_parse(ctx, &qname, qtype, &wire)
-                if path == QueryPath::Coalesced {
+                    })
-                    debug!("{} | {:?} {} | COALESCED", src_addr, qtype, qname);
+                    .await;
-                } else if path == QueryPath::UpstreamError {
+                log_coalesced_outcome(src_addr, qtype, &qname, path, err.as_deref(), "FORWARD");
-                    error!(
+                if path == QueryPath::Forwarded {
-                        "{} | {:?} {} | RECURSIVE ERROR | {}",
+                    upstream_transport = pool.preferred().map(|u| u.transport());
-                        src_addr,
+                }
-                        qtype,
+                (resp, path, DnssecStatus::Indeterminate)
-                        qname,
+            } else if ctx.upstream_mode == UpstreamMode::Recursive {
-                        err.as_deref().unwrap_or("leader failed")
+                // Recursive resolution makes UDP hops to roots/TLDs/auths;
-                    );
+                // tag as Udp so the dashboard can aggregate plaintext-wire
+                // egress honestly. Only mark on success — errors stay None.
+                let key = (qname.clone(), qtype);
+                let (resp, path, err) =
+                    resolve_coalesced(&ctx.inflight, key, &query, QueryPath::Recursive, || {
+                        crate::recursive::resolve_recursive(
+                            &qname,
+                            qtype,
+                            &ctx.cache,
+                            &query,
+                            &ctx.root_hints,
+                            &ctx.srtt,
+                        )
+                    })
+                    .await;
+                log_coalesced_outcome(src_addr, qtype, &qname, path, err.as_deref(), "RECURSIVE");
+                if path == QueryPath::Recursive {
+                    upstream_transport = Some(crate::stats::UpstreamTransport::Udp);
                 }
                 (resp, path, DnssecStatus::Indeterminate)
             } else {
                 let pool = ctx.upstream_pool.lock().unwrap().clone();
-                match forward_with_failover_raw(
+                let key = (qname.clone(), qtype);
-                    raw_wire,
+                let (resp, path, err) =
-                    &pool,
+                    resolve_coalesced(&ctx.inflight, key, &query, QueryPath::Upstream, || async {
-                    &ctx.srtt,
+                        let wire = forward_with_failover_raw(
-                    ctx.timeout,
+                            raw_wire,
-                    ctx.hedge_delay,
+                            &pool,
-                )
+                            &ctx.srtt,
-                .await
+                            ctx.timeout,
-                {
+                            ctx.hedge_delay,
-                    Ok(resp_wire) => match cache_and_parse(ctx, &qname, qtype, &resp_wire) {
-                        Ok(resp) => (resp, QueryPath::Forwarded, DnssecStatus::Indeterminate),
-                        Err(e) => {
-                            error!("{} | {:?} {} | PARSE ERROR | {}", src_addr, qtype, qname, e);
-                            (
-                                DnsPacket::response_from(&query, ResultCode::SERVFAIL),
-                                QueryPath::UpstreamError,
-                                DnssecStatus::Indeterminate,
-                            )
-                        }
-                    },
-                    Err(e) => {
-                        error!(
-                            "{} | {:?} {} | UPSTREAM ERROR | {}",
-                            src_addr, qtype, qname, e
-                        );
-                        (
-                            DnsPacket::response_from(&query, ResultCode::SERVFAIL),
-                            QueryPath::UpstreamError,
-                            DnssecStatus::Indeterminate,
                         )
-                    }
+                        .await?;
+                        cache_and_parse(ctx, &qname, qtype, &wire)
+                    })
+                    .await;
+                log_coalesced_outcome(src_addr, qtype, &qname, path, err.as_deref(), "UPSTREAM");
+                if path == QueryPath::Upstream {
+                    upstream_transport = pool.preferred().map(|u| u.transport());
                 }
+                (resp, path, DnssecStatus::Indeterminate)
             }
         }
     };
@@ -314,6 +317,15 @@ pub async fn resolve_query(
         strip_dnssec_records(&mut response);
     }
 
+    // filter_aaaa: also strip ipv6hint from HTTPS/SVCB answers so modern
+    // browsers (Chrome ≥103 etc.) don't receive v6 address hints via the
+    // HTTPS record path that bypasses AAAA entirely. Gated on !client_do
+    // because modifying rdata invalidates any accompanying RRSIG — a DO-bit
+    // validator downstream would reject the response as Bogus.
+    if ctx.filter_aaaa && !client_do {
+        strip_svcb_ipv6_hints(&mut response);
+    }
+
     // Echo EDNS back if client sent it
     if query.edns.is_some() {
         response.edns = Some(crate::packet::EdnsOpt {
@@ -357,7 +369,7 @@ pub async fn resolve_query(
     // Record stats and query log
     {
         let mut s = ctx.stats.lock().unwrap();
-        let total = s.record(path, transport);
+        let total = s.record(path, transport, upstream_transport);
         if total.is_multiple_of(1000) {
             s.log_summary();
         }
@@ -433,17 +445,6 @@ pub async fn refresh_entry(ctx: &ServerCtx, qname: &str, qtype: QueryType) {
     }
 }
 
-async fn forward_and_cache(
-    wire: &[u8],
-    upstream: &Upstream,
-    ctx: &ServerCtx,
-    qname: &str,
-    qtype: QueryType,
-) -> crate::Result<DnsPacket> {
-    let resp_wire = forward_query_raw(wire, upstream, ctx.timeout).await?;
-    cache_and_parse(ctx, qname, qtype, &resp_wire)
-}
-
 pub async fn handle_query(
     mut buffer: BytePacketBuffer,
     raw_len: usize,
@@ -482,6 +483,20 @@ fn strip_dnssec_records(pkt: &mut DnsPacket) {
     pkt.resources.retain(|r| !is_dnssec_record(r));
 }
 
+fn strip_svcb_ipv6_hints(pkt: &mut DnsPacket) {
+    let https_qtype = QueryType::HTTPS.to_num();
+    let svcb_qtype = QueryType::SVCB.to_num();
+    pkt.for_each_record_mut(|rec| {
+        if let DnsRecord::UNKNOWN { qtype, data, .. } = rec {
+            if *qtype == https_qtype || *qtype == svcb_qtype {
+                if let Some(new_data) = crate::svcb::strip_ipv6hint(data) {
+                    *data = new_data;
+                }
+            }
+        }
+    });
+}
+
 fn is_special_use_domain(qname: &str) -> bool {
     if qname.ends_with(".in-addr.arpa") {
         // RFC 6303: private + loopback + link-local reverse DNS
@@ -558,11 +573,15 @@ fn acquire_inflight(inflight: &Mutex<InflightMap>, key: (String, QueryType)) ->
 
 /// Run a resolve function with in-flight coalescing. Multiple concurrent calls
 /// for the same key share a single resolution — the first caller (leader)
-/// executes `resolve_fn`, and followers wait for the broadcast result.
+/// executes `resolve_fn`, and followers wait for the broadcast result. The
+/// leader's successful path is tagged with `leader_path` so callers that
+/// share this helper (recursive, forwarded-rule, forward-upstream) keep their
+/// own observability without duplicating the inflight map.
 async fn resolve_coalesced<F, Fut>(
     inflight: &Mutex<InflightMap>,
     key: (String, QueryType),
     query: &DnsPacket,
+    leader_path: QueryPath,
     resolve_fn: F,
 ) -> (DnsPacket, QueryPath, Option<String>)
 where
@@ -591,7 +610,7 @@ where
             match result {
                 Ok(resp) => {
                     let _ = tx.send(Some(resp.clone()));
-                    (resp, QueryPath::Recursive, None)
+                    (resp, leader_path, None)
                 }
                 Err(e) => {
                     let _ = tx.send(None);
@@ -618,6 +637,33 @@ impl Drop for InflightGuard<'_> {
     }
 }
 
+/// Emit the log lines shared by the three upstream branches (Forwarded,
+/// Recursive, Upstream) after `resolve_coalesced` returns. Leader-success
+/// and transport-tagging stay at the call site since they diverge per
+/// branch, but the Coalesced debug and UpstreamError error are identical
+/// except for the label.
+fn log_coalesced_outcome(
+    src_addr: SocketAddr,
+    qtype: QueryType,
+    qname: &str,
+    path: QueryPath,
+    err: Option<&str>,
+    label: &str,
+) {
+    match path {
+        QueryPath::Coalesced => debug!("{} | {:?} {} | COALESCED", src_addr, qtype, qname),
+        QueryPath::UpstreamError => error!(
+            "{} | {:?} {} | {} ERROR | {}",
+            src_addr,
+            qtype,
+            qname,
+            label,
+            err.unwrap_or("leader failed")
+        ),
+        _ => {}
+    }
+}
+
 fn special_use_response(query: &DnsPacket, qname: &str, qtype: QueryType) -> DnsPacket {
     use std::net::{Ipv4Addr, Ipv6Addr};
     if qname == "ipv4only.arpa" {
@@ -856,7 +902,7 @@ mod tests {
             let key = ("coalesce.test".to_string(), QueryType::A);
             let query = DnsPacket::query(100 + i, "coalesce.test", QueryType::A);
             handles.push(tokio::spawn(async move {
-                resolve_coalesced(&inf, key, &query, || async {
+                resolve_coalesced(&inf, key, &query, QueryPath::Recursive, || async {
                     count.fetch_add(1, std::sync::atomic::Ordering::Relaxed);
                     tokio::time::sleep(Duration::from_millis(200)).await;
                     Ok(mock_response("coalesce.test"))
@@ -900,6 +946,7 @@ mod tests {
                 &inf1,
                 ("same.domain".to_string(), QueryType::A),
                 &query_a,
+                QueryPath::Recursive,
                 || async {
                     count1.fetch_add(1, std::sync::atomic::Ordering::Relaxed);
                     tokio::time::sleep(Duration::from_millis(100)).await;
@@ -913,6 +960,7 @@ mod tests {
                 &inf2,
                 ("same.domain".to_string(), QueryType::AAAA),
                 &query_aaaa,
+                QueryPath::Recursive,
                 || async {
                     count2.fetch_add(1, std::sync::atomic::Ordering::Relaxed);
                     tokio::time::sleep(Duration::from_millis(100)).await;
@@ -942,6 +990,7 @@ mod tests {
             &inflight,
             ("will-fail.test".to_string(), QueryType::A),
             &query,
+            QueryPath::Recursive,
             || async { Err::<DnsPacket, _>("upstream timeout".into()) },
         )
         .await;
@@ -963,6 +1012,7 @@ mod tests {
                     &inf,
                     ("fail.test".to_string(), QueryType::A),
                     &query,
+                    QueryPath::Recursive,
                     || async {
                         tokio::time::sleep(Duration::from_millis(200)).await;
                         Err::<DnsPacket, _>("upstream error".into())
@@ -1003,6 +1053,7 @@ mod tests {
             &inflight,
             ("question.test".to_string(), QueryType::A),
             &query,
+            QueryPath::Recursive,
             || async { Err::<DnsPacket, _>("fail".into()) },
         )
         .await;
@@ -1027,6 +1078,7 @@ mod tests {
             &inflight,
             ("err-msg.test".to_string(), QueryType::A),
             &query,
+            QueryPath::Recursive,
             || async { Err::<DnsPacket, _>("connection refused by upstream".into()) },
         )
         .await;
@@ -1082,7 +1134,7 @@ mod tests {
         let mut ctx = crate::testutil::test_ctx().await;
         ctx.forwarding_rules = vec![ForwardingRule::new(
             "168.192.in-addr.arpa".to_string(),
-            Upstream::Udp(upstream_addr),
+            UpstreamPool::new(vec![Upstream::Udp(upstream_addr)], vec![]),
         )];
         let ctx = Arc::new(ctx);
 
@@ -1178,6 +1230,201 @@ mod tests {
         }
     }
 
+    #[tokio::test]
+    async fn pipeline_filter_aaaa_returns_nodata() {
+        let mut ctx = crate::testutil::test_ctx().await;
+        ctx.filter_aaaa = true;
+        let ctx = Arc::new(ctx);
+
+        let (resp, path) = resolve_in_test(&ctx, "example.com", QueryType::AAAA).await;
+        assert_eq!(path, QueryPath::Local);
+        assert_eq!(resp.header.rescode, ResultCode::NOERROR);
+        assert!(resp.answers.is_empty(), "AAAA must be filtered to NODATA");
+    }
+
+    #[tokio::test]
+    async fn pipeline_filter_aaaa_leaves_a_queries_alone() {
+        let mut upstream_resp = DnsPacket::new();
+        upstream_resp.header.response = true;
+        upstream_resp.header.rescode = ResultCode::NOERROR;
+        upstream_resp.answers.push(DnsRecord::A {
+            domain: "example.com".to_string(),
+            addr: Ipv4Addr::new(93, 184, 216, 34),
+            ttl: 300,
+        });
+        let upstream_addr = crate::testutil::mock_upstream(upstream_resp).await;
+
+        let mut ctx = crate::testutil::test_ctx().await;
+        ctx.filter_aaaa = true;
+        ctx.upstream_pool
+            .lock()
+            .unwrap()
+            .set_primary(vec![Upstream::Udp(upstream_addr)]);
+        let ctx = Arc::new(ctx);
+
+        let (resp, path) = resolve_in_test(&ctx, "example.com", QueryType::A).await;
+        assert_eq!(path, QueryPath::Upstream);
+        assert_eq!(resp.answers.len(), 1);
+    }
+
+    #[tokio::test]
+    async fn pipeline_filter_aaaa_respects_override() {
+        let mut ctx = crate::testutil::test_ctx().await;
+        ctx.filter_aaaa = true;
+        ctx.overrides
+            .write()
+            .unwrap()
+            .insert("v6.test", "2001:db8::1", 60, None)
+            .unwrap();
+        let ctx = Arc::new(ctx);
+
+        let (resp, path) = resolve_in_test(&ctx, "v6.test", QueryType::AAAA).await;
+        assert_eq!(path, QueryPath::Overridden);
+        assert_eq!(resp.answers.len(), 1, "override must win over filter");
+    }
+
+    #[tokio::test]
+    async fn pipeline_filter_aaaa_strips_ipv6hint_from_https_and_svcb() {
+        let rdata = crate::svcb::build_rdata(
+            1,
+            &[],
+            &[
+                (1, vec![0x02, b'h', b'3']),
+                (
+                    6,
+                    vec![
+                        0x26, 0x06, 0x47, 0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x01,
+                    ],
+                ),
+            ],
+        );
+
+        let mut pkt = DnsPacket::new();
+        pkt.header.response = true;
+        pkt.header.rescode = ResultCode::NOERROR;
+        pkt.questions.push(crate::question::DnsQuestion {
+            name: "hints.test".to_string(),
+            qtype: QueryType::HTTPS,
+        });
+        pkt.answers.push(DnsRecord::UNKNOWN {
+            domain: "hints.test".to_string(),
+            qtype: 65,
+            data: rdata.clone(),
+            ttl: 300,
+        });
+
+        let mut svcb_pkt = pkt.clone();
+        svcb_pkt.questions[0].name = "svc.test".to_string();
+        svcb_pkt.questions[0].qtype = QueryType::SVCB;
+        if let DnsRecord::UNKNOWN { domain, qtype, .. } = &mut svcb_pkt.answers[0] {
+            *domain = "svc.test".to_string();
+            *qtype = 64;
+        }
+
+        let mut ctx = crate::testutil::test_ctx().await;
+        ctx.filter_aaaa = true;
+        ctx.cache
+            .write()
+            .unwrap()
+            .insert("hints.test", QueryType::HTTPS, &pkt);
+        ctx.cache
+            .write()
+            .unwrap()
+            .insert("svc.test", QueryType::SVCB, &svcb_pkt);
+        let ctx = Arc::new(ctx);
+
+        for (name, qtype, label) in [
+            ("hints.test", QueryType::HTTPS, "HTTPS"),
+            ("svc.test", QueryType::SVCB, "SVCB"),
+        ] {
+            let (resp, path) = resolve_in_test(&ctx, name, qtype).await;
+            assert_eq!(path, QueryPath::Cached, "{label}");
+            assert_eq!(resp.answers.len(), 1, "{label}");
+            match &resp.answers[0] {
+                DnsRecord::UNKNOWN { data, .. } => {
+                    assert!(
+                        data.len() < rdata.len(),
+                        "{label}: ipv6hint (20 bytes) must be removed"
+                    );
+                    // Bytes for key=6 must not appear at any 4-byte boundary in the
+                    // params section — cheap structural check.
+                    assert!(
+                        !data.windows(4).any(|w| w == [0, 6, 0, 16]),
+                        "{label}: ipv6hint TLV header must be absent"
+                    );
+                }
+                other => panic!("{label}: expected UNKNOWN record, got {other:?}"),
+            }
+        }
+    }
+
+    #[tokio::test]
+    async fn pipeline_filter_aaaa_preserves_ipv6hint_for_dnssec_clients() {
+        // Regression guard for the DO-bit gate in resolve_query: modifying
+        // HTTPS rdata invalidates any accompanying RRSIG, so a DO=1 client
+        // must receive the record untouched even when filter_aaaa is on.
+        let rdata = crate::svcb::build_rdata(
+            1,
+            &[],
+            &[(
+                6,
+                vec![
+                    0x26, 0x06, 0x47, 0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x01,
+                ],
+            )],
+        );
+
+        let mut pkt = DnsPacket::new();
+        pkt.header.response = true;
+        pkt.header.rescode = ResultCode::NOERROR;
+        pkt.questions.push(crate::question::DnsQuestion {
+            name: "hints.test".to_string(),
+            qtype: QueryType::HTTPS,
+        });
+        pkt.answers.push(DnsRecord::UNKNOWN {
+            domain: "hints.test".to_string(),
+            qtype: 65,
+            data: rdata.clone(),
+            ttl: 300,
+        });
+
+        let mut ctx = crate::testutil::test_ctx().await;
+        ctx.filter_aaaa = true;
+        ctx.cache
+            .write()
+            .unwrap()
+            .insert("hints.test", QueryType::HTTPS, &pkt);
+        let ctx = Arc::new(ctx);
+
+        // Build a query with EDNS DO bit set — can't use resolve_in_test
+        // because it constructs a plain query without EDNS.
+        let mut query = DnsPacket::query(0xBEEF, "hints.test", QueryType::HTTPS);
+        query.edns = Some(crate::packet::EdnsOpt {
+            do_bit: true,
+            ..Default::default()
+        });
+        let mut buf = BytePacketBuffer::new();
+        query.write(&mut buf).unwrap();
+        let raw = &buf.buf[..buf.pos];
+        let src: SocketAddr = "127.0.0.1:1234".parse().unwrap();
+
+        let (resp_buf, _) = resolve_query(query, raw, src, &ctx, Transport::Udp)
+            .await
+            .unwrap();
+        let mut resp_parse_buf = BytePacketBuffer::from_bytes(resp_buf.filled());
+        let resp = DnsPacket::from_buffer(&mut resp_parse_buf).unwrap();
+
+        match &resp.answers[0] {
+            DnsRecord::UNKNOWN { data, .. } => {
+                assert_eq!(
+                    data, &rdata,
+                    "ipv6hint must be preserved for DO-bit clients"
+                );
+            }
+            other => panic!("expected UNKNOWN record, got {:?}", other),
+        }
+    }
+
     #[tokio::test]
     async fn pipeline_blocklist_sinkhole() {
         let ctx = crate::testutil::test_ctx().await;
@@ -1237,7 +1484,7 @@ mod tests {
         let mut ctx = crate::testutil::test_ctx().await;
         ctx.forwarding_rules = vec![ForwardingRule::new(
             "corp".to_string(),
-            Upstream::Udp(upstream_addr),
+            UpstreamPool::new(vec![Upstream::Udp(upstream_addr)], vec![]),
         )];
         let ctx = Arc::new(ctx);
 
@@ -1253,4 +1500,60 @@ mod tests {
             other => panic!("expected A record, got {:?}", other),
         }
     }
+
+    #[tokio::test]
+    async fn pipeline_forwarding_fails_over_to_second_upstream() {
+        let dead = crate::testutil::blackhole_upstream();
+
+        let mut live_resp = DnsPacket::new();
+        live_resp.header.response = true;
+        live_resp.header.rescode = ResultCode::NOERROR;
+        live_resp.answers.push(DnsRecord::A {
+            domain: "internal.corp".to_string(),
+            addr: Ipv4Addr::new(10, 9, 9, 9),
+            ttl: 600,
+        });
+        let live = crate::testutil::mock_upstream(live_resp).await;
+
+        let mut ctx = crate::testutil::test_ctx().await;
+        ctx.forwarding_rules = vec![ForwardingRule::new(
+            "corp".to_string(),
+            UpstreamPool::new(vec![Upstream::Udp(dead), Upstream::Udp(live)], vec![]),
+        )];
+        let ctx = Arc::new(ctx);
+
+        let (resp, path) = resolve_in_test(&ctx, "internal.corp", QueryType::A).await;
+        assert_eq!(path, QueryPath::Forwarded);
+        assert_eq!(resp.header.rescode, ResultCode::NOERROR);
+        assert_eq!(resp.answers.len(), 1);
+        match &resp.answers[0] {
+            DnsRecord::A { addr, .. } => assert_eq!(*addr, Ipv4Addr::new(10, 9, 9, 9)),
+            other => panic!("expected A record, got {:?}", other),
+        }
+    }
+
+    #[tokio::test]
+    async fn pipeline_default_pool_reports_upstream_path() {
+        let mut upstream_resp = DnsPacket::new();
+        upstream_resp.header.response = true;
+        upstream_resp.header.rescode = ResultCode::NOERROR;
+        upstream_resp.answers.push(DnsRecord::A {
+            domain: "example.com".to_string(),
+            addr: Ipv4Addr::new(93, 184, 216, 34),
+            ttl: 300,
+        });
+        let upstream_addr = crate::testutil::mock_upstream(upstream_resp).await;
+
+        let ctx = crate::testutil::test_ctx().await;
+        ctx.upstream_pool
+            .lock()
+            .unwrap()
+            .set_primary(vec![Upstream::Udp(upstream_addr)]);
+        let ctx = Arc::new(ctx);
+
+        let (resp, path) = resolve_in_test(&ctx, "example.com", QueryType::A).await;
+        assert_eq!(path, QueryPath::Upstream);
+        assert_eq!(resp.header.rescode, ResultCode::NOERROR);
+        assert_eq!(resp.answers.len(), 1);
+    }
 }

src/forward.rs

@@ -1,14 +1,16 @@
 use std::fmt;
 use std::net::{IpAddr, SocketAddr};
-use std::sync::RwLock;
+use std::sync::{Arc, RwLock};
 use std::time::{Duration, Instant};
 
 use tokio::net::UdpSocket;
 use tokio::time::timeout;
 
 use crate::buffer::BytePacketBuffer;
+use crate::odoh::{query_through_relay, OdohConfigCache};
 use crate::packet::DnsPacket;
 use crate::srtt::SrttCache;
+use crate::stats::UpstreamTransport;
 use crate::Result;
 
 #[derive(Clone)]
@@ -23,6 +25,36 @@ pub enum Upstream {
         tls_name: Option<String>,
         connector: tokio_rustls::TlsConnector,
     },
+    /// Oblivious DNS-over-HTTPS (RFC 9230). Queries are HPKE-sealed to the
+    /// target and forwarded through an independent relay. Target host lives
+    /// on `target_config` (single source of truth — the cache keys on it).
+    Odoh {
+        relay_url: String,
+        target_path: String,
+        client: reqwest::Client,
+        target_config: Arc<OdohConfigCache>,
+    },
+}
+
+impl Upstream {
+    /// IP address to key SRTT tracking on, if the upstream has a stable one.
+    /// `Doh` and `Odoh` route through a URL + connection pool, so there's no
+    /// single IP to track; SRTT is skipped for them.
+    pub fn tracked_ip(&self) -> Option<IpAddr> {
+        match self {
+            Upstream::Udp(addr) | Upstream::Dot { addr, .. } => Some(addr.ip()),
+            Upstream::Doh { .. } | Upstream::Odoh { .. } => None,
+        }
+    }
+
+    pub fn transport(&self) -> UpstreamTransport {
+        match self {
+            Upstream::Udp(_) => UpstreamTransport::Udp,
+            Upstream::Doh { .. } => UpstreamTransport::Doh,
+            Upstream::Dot { .. } => UpstreamTransport::Dot,
+            Upstream::Odoh { .. } => UpstreamTransport::Odoh,
+        }
+    }
 }
 
 impl PartialEq for Upstream {
@@ -31,6 +63,20 @@ impl PartialEq for Upstream {
             (Self::Udp(a), Self::Udp(b)) => a == b,
             (Self::Doh { url: a, .. }, Self::Doh { url: b, .. }) => a == b,
             (Self::Dot { addr: a, .. }, Self::Dot { addr: b, .. }) => a == b,
+            (
+                Self::Odoh {
+                    relay_url: ra,
+                    target_path: pa,
+                    target_config: ca,
+                    ..
+                },
+                Self::Odoh {
+                    relay_url: rb,
+                    target_path: pb,
+                    target_config: cb,
+                    ..
+                },
+            ) => ra == rb && pa == pb && ca.target_host() == cb.target_host(),
             _ => false,
         }
     }
@@ -51,14 +97,23 @@ impl fmt::Display for Upstream {
                 Some(name) => write!(f, "tls://{}#{}", addr, name),
                 None => write!(f, "tls://{}", addr),
             },
+            Upstream::Odoh {
+                relay_url,
+                target_path,
+                target_config,
+                ..
+            } => write!(
+                f,
+                "odoh://{}{} via {}",
+                target_config.target_host(),
+                target_path,
+                relay_url
+            ),
         }
     }
 }
 
-pub(crate) fn parse_upstream_addr(
+pub fn parse_upstream_addr(s: &str, default_port: u16) -> std::result::Result<SocketAddr, String> {
-    s: &str,
-    default_port: u16,
-) -> std::result::Result<SocketAddr, String> {
     // Try full socket addr first: "1.2.3.4:5353" or "[::1]:5353"
     if let Ok(addr) = s.parse::<SocketAddr>() {
         return Ok(addr);
@@ -70,22 +125,29 @@ pub(crate) fn parse_upstream_addr(
     Err(format!("invalid upstream address: {}", s))
 }
 
-pub fn parse_upstream(s: &str, default_port: u16) -> Result<Upstream> {
+/// Parse a slice of upstream address strings into `Upstream` values, failing
+/// on the first invalid entry. DoH entries use `resolver` (when provided) as
+/// their hostname resolver.
+pub fn parse_upstream_list(
+    addrs: &[String],
+    default_port: u16,
+    resolver: Option<Arc<crate::bootstrap_resolver::NumaResolver>>,
+) -> Result<Vec<Upstream>> {
+    addrs
+        .iter()
+        .map(|s| parse_upstream(s, default_port, resolver.clone()))
+        .collect()
+}
+
+pub fn parse_upstream(
+    s: &str,
+    default_port: u16,
+    resolver: Option<Arc<crate::bootstrap_resolver::NumaResolver>>,
+) -> Result<Upstream> {
     if s.starts_with("https://") {
-        let client = reqwest::Client::builder()
-            .use_rustls_tls()
-            .http2_initial_stream_window_size(65_535)
-            .http2_initial_connection_window_size(65_535)
-            .http2_keep_alive_interval(Duration::from_secs(15))
-            .http2_keep_alive_while_idle(true)
-            .http2_keep_alive_timeout(Duration::from_secs(10))
-            .pool_idle_timeout(Duration::from_secs(300))
-            .pool_max_idle_per_host(1)
-            .build()
-            .unwrap_or_default();
         return Ok(Upstream::Doh {
             url: s.to_string(),
-            client,
+            client: build_https_client_with_resolver(1, resolver),
         });
     }
     // tls://IP:PORT#hostname  or  tls://IP#hostname  (default port 853)
@@ -106,6 +168,52 @@ pub fn parse_upstream(s: &str, default_port: u16) -> Result<Upstream> {
     Ok(Upstream::Udp(addr))
 }
 
+/// HTTP/2 client tuned for DoH/ODoH: small windows for low latency, long-lived
+/// keep-alive. Pool defaults to one idle conn per host — good for resolvers
+/// that talk to a single upstream; relays that fan out to many targets
+/// should use [`build_https_client_with_pool`].
+///
+/// Uses the system resolver. Callers running inside `serve::run` pass the
+/// shared [`crate::bootstrap_resolver::NumaResolver`] via
+/// [`build_https_client_with_resolver`] to avoid the self-loop documented
+/// in `docs/implementation/bootstrap-resolver.md`.
+pub fn build_https_client() -> reqwest::Client {
+    build_https_client_with_resolver(1, None)
+}
+
+/// Same shape as [`build_https_client`], but caller picks
+/// `pool_max_idle_per_host`. Relay workloads hit many distinct target hosts
+/// and benefit from a larger pool so warm connections survive concurrent
+/// fan-out.
+pub fn build_https_client_with_pool(pool_max_idle_per_host: usize) -> reqwest::Client {
+    build_https_client_with_resolver(pool_max_idle_per_host, None)
+}
+
+/// [`build_https_client`] with an optional custom DNS resolver. Numa wires
+/// [`crate::bootstrap_resolver::NumaResolver`] here.
+pub fn build_https_client_with_resolver(
+    pool_max_idle_per_host: usize,
+    resolver: Option<Arc<crate::bootstrap_resolver::NumaResolver>>,
+) -> reqwest::Client {
+    let mut builder = https_client_builder(pool_max_idle_per_host);
+    if let Some(r) = resolver {
+        builder = builder.dns_resolver(r);
+    }
+    builder.build().unwrap_or_default()
+}
+
+fn https_client_builder(pool_max_idle_per_host: usize) -> reqwest::ClientBuilder {
+    reqwest::Client::builder()
+        .use_rustls_tls()
+        .http2_initial_stream_window_size(65_535)
+        .http2_initial_connection_window_size(65_535)
+        .http2_keep_alive_interval(Duration::from_secs(15))
+        .http2_keep_alive_while_idle(true)
+        .http2_keep_alive_timeout(Duration::from_secs(10))
+        .pool_idle_timeout(Duration::from_secs(300))
+        .pool_max_idle_per_host(pool_max_idle_per_host)
+}
+
 fn build_dot_connector() -> Result<tokio_rustls::TlsConnector> {
     let _ = rustls::crypto::ring::default_provider().install_default();
     let mut root_store = rustls::RootCertStore::empty();
@@ -270,6 +378,22 @@ pub async fn forward_query_raw(
             tls_name,
             connector,
         } => forward_dot_raw(wire, *addr, tls_name, connector, timeout_duration).await,
+        Upstream::Odoh {
+            relay_url,
+            target_path,
+            client,
+            target_config,
+        } => {
+            query_through_relay(
+                wire,
+                relay_url,
+                target_path,
+                client,
+                target_config,
+                timeout_duration,
+            )
+            .await
+        }
     }
 }
 
@@ -345,18 +469,17 @@ pub async fn forward_with_failover_raw(
     timeout_duration: Duration,
     hedge_delay: Duration,
 ) -> Result<Vec<u8>> {
-    let mut candidates: Vec<(usize, u64)> = pool
+    let mut candidates: Vec<(usize, u64)> = {
-        .primary
+        let srtt_read = srtt.read().unwrap();
-        .iter()
+        pool.primary
-        .enumerate()
+            .iter()
-        .map(|(i, u)| {
+            .enumerate()
-            let rtt = match u {
+            .map(|(i, u)| {
-                Upstream::Udp(addr) => srtt.read().unwrap().get(addr.ip()),
+                let rtt = u.tracked_ip().map(|ip| srtt_read.get(ip)).unwrap_or(0);
-                _ => 0,
+                (i, rtt)
-            };
+            })
-            (i, rtt)
+            .collect()
-        })
+    };
-        .collect();
     candidates.sort_by_key(|&(_, rtt)| rtt);
 
     let all_upstreams: Vec<&Upstream> = candidates
@@ -380,15 +503,15 @@ pub async fn forward_with_failover_raw(
         };
         match result {
             Ok(resp) => {
-                if let Upstream::Udp(addr) = upstream {
+                if let Some(ip) = upstream.tracked_ip() {
                     let rtt_ms = start.elapsed().as_millis() as u64;
-                    srtt.write().unwrap().record_rtt(addr.ip(), rtt_ms, false);
+                    srtt.write().unwrap().record_rtt(ip, rtt_ms, false);
                 }
                 return Ok(resp);
             }
             Err(e) => {
-                if let Upstream::Udp(addr) = upstream {
+                if let Some(ip) = upstream.tracked_ip() {
-                    srtt.write().unwrap().record_failure(addr.ip());
+                    srtt.write().unwrap().record_failure(ip);
                 }
                 log::debug!("upstream {} failed: {}", upstream, e);
                 last_err = Some(e);
@@ -438,6 +561,9 @@ async fn forward_doh_raw(
 
 /// Send a lightweight keepalive query to a DoH upstream to prevent
 /// the HTTP/2 + TLS connection from going idle and being torn down.
+/// The first call doubles as a startup warm-up: bootstrap-resolver failures
+/// (unreachable Quad9/Cloudflare defaults, misconfigured hostname upstream)
+/// surface here rather than on the first client query.
 pub async fn keepalive_doh(upstream: &Upstream) {
     if let Upstream::Doh { url, client } = upstream {
         // Query for . NS — minimal, always succeeds, response is small
@@ -450,7 +576,9 @@ pub async fn keepalive_doh(upstream: &Upstream) {
             0x00, 0x02, // type NS
             0x00, 0x01, // class IN
         ];
-        let _ = forward_doh_raw(wire, url, client, Duration::from_secs(5)).await;
+        if let Err(e) = forward_doh_raw(wire, url, client, Duration::from_secs(5)).await {
+            log::warn!("DoH keepalive to {} failed: {}", url, e);
+        }
     }
 }
 
@@ -707,4 +835,62 @@ mod tests {
         assert!(!pool.maybe_update_primary("not-an-ip", 53));
         assert_eq!(pool.preferred().unwrap().to_string(), "1.2.3.4:53");
     }
+
+    fn tcp_closed_port() -> SocketAddr {
+        // Bind a TCP listener, grab the port, drop → kernel returns RST on connect.
+        let listener = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
+        let addr = listener.local_addr().unwrap();
+        drop(listener);
+        addr
+    }
+
+    #[tokio::test]
+    async fn udp_failure_records_in_srtt() {
+        let blackhole = crate::testutil::blackhole_upstream();
+        let pool = UpstreamPool::new(vec![Upstream::Udp(blackhole)], vec![]);
+        let srtt = RwLock::new(SrttCache::new(true));
+        let _ = forward_with_failover_raw(
+            &[0u8; 12],
+            &pool,
+            &srtt,
+            Duration::from_millis(100),
+            Duration::ZERO,
+        )
+        .await;
+        assert!(srtt.read().unwrap().is_known(blackhole.ip()));
+    }
+
+    #[tokio::test]
+    async fn dot_failure_records_in_srtt() {
+        let dead1 = tcp_closed_port();
+        let dead2 = tcp_closed_port();
+        let connector = build_dot_connector().unwrap();
+        let pool = UpstreamPool::new(
+            vec![
+                Upstream::Dot {
+                    addr: dead1,
+                    tls_name: Some("dns.quad9.net".to_string()),
+                    connector: connector.clone(),
+                },
+                Upstream::Dot {
+                    addr: dead2,
+                    tls_name: Some("dns.quad9.net".to_string()),
+                    connector,
+                },
+            ],
+            vec![],
+        );
+        let srtt = RwLock::new(SrttCache::new(true));
+        let _ = forward_with_failover_raw(
+            &[0u8; 12],
+            &pool,
+            &srtt,
+            Duration::from_millis(500),
+            Duration::ZERO,
+        )
+        .await;
+        let cache = srtt.read().unwrap();
+        assert!(cache.is_known(dead1.ip()));
+        assert!(cache.is_known(dead2.ip()));
+    }
 }

src/health.rs

@@ -43,7 +43,7 @@ impl HealthMeta {
     #[cfg(test)]
     pub fn test_fixture() -> Self {
         HealthMeta {
-            version: env!("CARGO_PKG_VERSION"),
+            version: crate::version(),
             hostname: "test-host".to_string(),
             sni: "numa.numa".to_string(),
             dot_enabled: false,
@@ -99,7 +99,7 @@ impl HealthMeta {
         }
 
         HealthMeta {
-            version: env!("CARGO_PKG_VERSION"),
+            version: crate::version(),
             hostname: crate::hostname(),
             sni: "numa.numa".to_string(),
             dot_enabled,

src/lib.rs

@@ -1,5 +1,6 @@
 pub mod api;
 pub mod blocklist;
+pub mod bootstrap_resolver;
 pub mod buffer;
 pub mod cache;
 pub mod config;
@@ -13,6 +14,7 @@ pub mod health;
 pub mod lan;
 pub mod mobile_api;
 pub mod mobileconfig;
+pub mod odoh;
 pub mod override_store;
 pub mod packet;
 pub mod proxy;
@@ -20,20 +22,34 @@ pub mod query_log;
 pub mod question;
 pub mod record;
 pub mod recursive;
+pub mod relay;
+pub mod serve;
 pub mod service_store;
 pub mod setup_phone;
 pub mod srtt;
 pub mod stats;
+pub mod svcb;
 pub mod system_dns;
 pub mod tls;
 pub mod wire;
 
+#[cfg(windows)]
+pub mod windows_service;
+
 #[cfg(test)]
 pub(crate) mod testutil;
 
 pub type Error = Box<dyn std::error::Error + Send + Sync>;
 pub type Result<T> = std::result::Result<T, Error>;
 
+/// Build version string. On tagged releases: `0.13.1`. On commits ahead
+/// of a tag: `0.13.1+a87f907`. With uncommitted changes: `0.13.1+a87f907-dirty`.
+/// Falls back to `CARGO_PKG_VERSION` when built outside a git repo (e.g.
+/// from a source tarball).
+pub fn version() -> &'static str {
+    option_env!("NUMA_BUILD_VERSION").unwrap_or(env!("CARGO_PKG_VERSION"))
+}
+
 /// Detect the machine hostname via the `hostname` command. Returns the
 /// full hostname (e.g., `macbook-pro.local`), or `"numa"` if the command
 /// fails. Call sites that need the short form (e.g., mDNS instance
@@ -89,14 +105,11 @@ where
 /// Linux root daemon: /var/lib/numa (FHS) — falls back to /usr/local/var/numa
 ///                    if a pre-v0.10.1 install already lives there.
 /// macOS root daemon: /usr/local/var/numa (Homebrew prefix)
-/// Windows: %APPDATA%\numa
+/// Windows: %PROGRAMDATA%\numa (same as data_dir — no per-user config on Windows)
 pub fn config_dir() -> std::path::PathBuf {
     #[cfg(windows)]
     {
-        std::path::PathBuf::from(
+        data_dir()
-            std::env::var("APPDATA").unwrap_or_else(|_| "C:\\ProgramData".into()),
-        )
-        .join("numa")
     }
     #[cfg(not(windows))]
     {

src/main.rs

@@ -1,36 +1,34 @@
-use std::net::SocketAddr;
-use std::sync::{Arc, Mutex, RwLock};
-use std::time::Duration;
-
-use arc_swap::ArcSwap;
-use log::{error, info};
-use tokio::net::UdpSocket;
-
-use numa::blocklist::{download_blocklists, parse_blocklist, BlocklistStore};
-use numa::buffer::BytePacketBuffer;
-use numa::cache::DnsCache;
-use numa::config::{build_zone_map, load_config, ConfigLoad};
-use numa::ctx::{handle_query, ServerCtx};
-use numa::forward::{parse_upstream, Upstream, UpstreamPool};
-use numa::override_store::OverrideStore;
-use numa::query_log::QueryLog;
-use numa::service_store::ServiceStore;
-use numa::stats::{ServerStats, Transport};
 use numa::system_dns::{
-    discover_system_dns, install_service, restart_service, service_status, uninstall_service,
+    install_service, restart_service, service_status, start_service, stop_service,
+    uninstall_service,
 };
 
-const QUAD9_IP: &str = "9.9.9.9";
+fn main() -> numa::Result<()> {
-const DOH_FALLBACK: &str = "https://9.9.9.9/dns-query";
+    // Handle CLI subcommands
+    let arg1 = std::env::args().nth(1).unwrap_or_default();
+
+    #[cfg(windows)]
+    if arg1 == "--service" {
+        // Running under SCM — stderr goes nowhere. Redirect logs to a file.
+        let log_path = numa::data_dir().join("numa.log");
+        let log_file = std::fs::OpenOptions::new()
+            .create(true)
+            .append(true)
+            .open(&log_path)
+            .expect("failed to open log file");
+        env_logger::Builder::from_env(env_logger::Env::default().default_filter_or("info"))
+            .format_timestamp_millis()
+            .target(env_logger::Target::Pipe(Box::new(log_file)))
+            .init();
+        numa::windows_service::run_as_service()
+            .map_err(|e| format!("windows service dispatcher failed: {}", e))?;
+        return Ok(());
+    }
 
-#[tokio::main]
-async fn main() -> numa::Result<()> {
     env_logger::Builder::from_env(env_logger::Env::default().default_filter_or("info"))
         .format_timestamp_millis()
         .init();
 
-    // Handle CLI subcommands
-    let arg1 = std::env::args().nth(1).unwrap_or_default();
     match arg1.as_str() {
         "install" => {
             eprintln!("\x1b[1;38;2;192;98;58mNuma\x1b[0m — installing\n");
@@ -44,8 +42,8 @@ async fn main() -> numa::Result<()> {
             let sub = std::env::args().nth(2).unwrap_or_default();
             eprintln!("\x1b[1;38;2;192;98;58mNuma\x1b[0m — service management\n");
             return match sub.as_str() {
-                "start" => install_service().map_err(|e| e.into()),
+                "start" => start_service().map_err(|e| e.into()),
-                "stop" => uninstall_service().map_err(|e| e.into()),
+                "stop" => stop_service().map_err(|e| e.into()),
                 "restart" => restart_service().map_err(|e| e.into()),
                 "status" => service_status().map_err(|e| e.into()),
                 _ => {
@@ -55,7 +53,38 @@ async fn main() -> numa::Result<()> {
             };
         }
         "setup-phone" => {
-            return numa::setup_phone::run().await.map_err(|e| e.into());
+            let runtime = tokio::runtime::Builder::new_current_thread()
+                .enable_all()
+                .build()?;
+            return runtime
+                .block_on(numa::setup_phone::run())
+                .map_err(|e| e.into());
+        }
+        "relay" => {
+            let port: u16 = std::env::args()
+                .nth(2)
+                .as_deref()
+                .and_then(|s| s.parse().ok())
+                .unwrap_or(8443);
+            let bind: std::net::IpAddr = std::env::args()
+                .nth(3)
+                .as_deref()
+                .map(|s| {
+                    s.parse().unwrap_or_else(|e| {
+                        eprintln!("invalid bind address '{}': {}", s, e);
+                        std::process::exit(1);
+                    })
+                })
+                .unwrap_or(std::net::IpAddr::V4(std::net::Ipv4Addr::LOCALHOST));
+            let addr = std::net::SocketAddr::new(bind, port);
+            eprintln!(
+                "\x1b[1;38;2;192;98;58mNuma\x1b[0m — ODoH relay on {}\n",
+                addr
+            );
+            let runtime = tokio::runtime::Builder::new_multi_thread()
+                .enable_all()
+                .build()?;
+            return runtime.block_on(numa::relay::run(addr));
         }
         "lan" => {
             let sub = std::env::args().nth(2).unwrap_or_default();
@@ -88,6 +117,8 @@ async fn main() -> numa::Result<()> {
             eprintln!("  service status  Check if the service is running");
             eprintln!("  lan on          Enable LAN service discovery (mDNS)");
             eprintln!("  lan off         Disable LAN service discovery");
+            eprintln!("  relay [PORT] [BIND]");
+            eprintln!("                  Run as an ODoH relay (RFC 9230, default 127.0.0.1:8443)");
             eprintln!("  setup-phone     Generate a QR code to install Numa DoT on a phone");
             eprintln!("  help            Show this help");
             eprintln!();
@@ -118,552 +149,11 @@ async fn main() -> numa::Result<()> {
     } else {
         arg1 // treat as config path for backwards compatibility
     };
-    let ConfigLoad {
-        config,
-        path: resolved_config_path,
-        found: config_found,
-    } = load_config(&config_path)?;
 
-    // Discover system DNS in a single pass (upstream + forwarding rules)
+    let runtime = tokio::runtime::Builder::new_multi_thread()
-    let system_dns = discover_system_dns();
+        .enable_all()
-
+        .build()?;
-    let root_hints = numa::recursive::parse_root_hints(&config.upstream.root_hints);
+    runtime.block_on(numa::serve::run(config_path))
-
-    let recursive_pool = || {
-        let dummy = UpstreamPool::new(vec![Upstream::Udp("0.0.0.0:0".parse().unwrap())], vec![]);
-        (dummy, "recursive (root hints)".to_string())
-    };
-
-    let (resolved_mode, upstream_auto, pool, upstream_label) = match config.upstream.mode {
-        numa::config::UpstreamMode::Auto => {
-            info!("auto mode: probing recursive resolution...");
-            if numa::recursive::probe_recursive(&root_hints).await {
-                info!("recursive probe succeeded — self-sovereign mode");
-                let (pool, label) = recursive_pool();
-                (numa::config::UpstreamMode::Recursive, false, pool, label)
-            } else {
-                log::warn!("recursive probe failed — falling back to Quad9 DoH");
-                let client = reqwest::Client::builder()
-                    .use_rustls_tls()
-                    .build()
-                    .unwrap_or_default();
-                let url = DOH_FALLBACK.to_string();
-                let label = url.clone();
-                let pool = UpstreamPool::new(vec![Upstream::Doh { url, client }], vec![]);
-                (numa::config::UpstreamMode::Forward, false, pool, label)
-            }
-        }
-        numa::config::UpstreamMode::Recursive => {
-            let (pool, label) = recursive_pool();
-            (numa::config::UpstreamMode::Recursive, false, pool, label)
-        }
-        numa::config::UpstreamMode::Forward => {
-            let addrs = if config.upstream.address.is_empty() {
-                let detected = system_dns
-                    .default_upstream
-                    .or_else(numa::system_dns::detect_dhcp_dns)
-                    .unwrap_or_else(|| {
-                        info!("could not detect system DNS, falling back to Quad9 DoH");
-                        DOH_FALLBACK.to_string()
-                    });
-                vec![detected]
-            } else {
-                config.upstream.address.clone()
-            };
-
-            let primary: Vec<Upstream> = addrs
-                .iter()
-                .map(|s| parse_upstream(s, config.upstream.port))
-                .collect::<numa::Result<Vec<_>>>()?;
-            let fallback: Vec<Upstream> = config
-                .upstream
-                .fallback
-                .iter()
-                .map(|s| parse_upstream(s, config.upstream.port))
-                .collect::<numa::Result<Vec<_>>>()?;
-
-            let pool = UpstreamPool::new(primary, fallback);
-            let label = pool.label();
-            (
-                numa::config::UpstreamMode::Forward,
-                config.upstream.address.is_empty(),
-                pool,
-                label,
-            )
-        }
-    };
-    let api_port = config.server.api_port;
-
-    let mut blocklist = BlocklistStore::new();
-    for domain in &config.blocking.allowlist {
-        blocklist.add_to_allowlist(domain);
-    }
-    if !config.blocking.enabled {
-        blocklist.set_enabled(false);
-    }
-
-    // Build service store: config services + persisted user services
-    let mut service_store = ServiceStore::new();
-    service_store.insert_from_config("numa", config.server.api_port, Vec::new());
-    for svc in &config.services {
-        service_store.insert_from_config(&svc.name, svc.target_port, svc.routes.clone());
-    }
-    service_store.load_persisted();
-
-    for fwd in &config.forwarding {
-        for suffix in &fwd.suffix {
-            info!("forwarding .{} to {} (config rule)", suffix, fwd.upstream);
-        }
-    }
-    let forwarding_rules =
-        numa::config::merge_forwarding_rules(&config.forwarding, system_dns.forwarding_rules)?;
-
-    // Resolve data_dir from config, falling back to the platform default.
-    // Used for TLS CA storage below and stored on ServerCtx for runtime use.
-    let resolved_data_dir = config
-        .server
-        .data_dir
-        .clone()
-        .unwrap_or_else(numa::data_dir);
-
-    // Build initial TLS config before ServerCtx (so ArcSwap is ready at construction)
-    let initial_tls = if config.proxy.enabled && config.proxy.tls_port > 0 {
-        let service_names = service_store.names();
-        match numa::tls::build_tls_config(
-            &config.proxy.tld,
-            &service_names,
-            Vec::new(),
-            &resolved_data_dir,
-        ) {
-            Ok(tls_config) => Some(ArcSwap::from(tls_config)),
-            Err(e) => {
-                if let Some(advisory) = numa::tls::try_data_dir_advisory(&e, &resolved_data_dir) {
-                    eprint!("{}", advisory);
-                } else {
-                    log::warn!("TLS setup failed, HTTPS proxy disabled: {}", e);
-                }
-                None
-            }
-        }
-    } else {
-        None
-    };
-
-    let doh_enabled = initial_tls.is_some();
-    let health_meta = numa::health::HealthMeta::build(
-        &resolved_data_dir,
-        config.dot.enabled,
-        config.dot.port,
-        config.mobile.port,
-        config.dnssec.enabled,
-        resolved_mode == numa::config::UpstreamMode::Recursive,
-        config.lan.enabled,
-        config.blocking.enabled,
-        doh_enabled,
-    );
-
-    let ca_pem = std::fs::read_to_string(resolved_data_dir.join("ca.pem")).ok();
-
-    let socket = match UdpSocket::bind(&config.server.bind_addr).await {
-        Ok(s) => s,
-        Err(e) => {
-            if let Some(advisory) =
-                numa::system_dns::try_port53_advisory(&config.server.bind_addr, &e)
-            {
-                eprint!("{}", advisory);
-                std::process::exit(1);
-            }
-            return Err(e.into());
-        }
-    };
-
-    let ctx = Arc::new(ServerCtx {
-        socket,
-        zone_map: build_zone_map(&config.zones)?,
-        cache: RwLock::new(DnsCache::new(
-            config.cache.max_entries,
-            config.cache.min_ttl,
-            config.cache.max_ttl,
-        )),
-        refreshing: Mutex::new(std::collections::HashSet::new()),
-        stats: Mutex::new(ServerStats::new()),
-        overrides: RwLock::new(OverrideStore::new()),
-        blocklist: RwLock::new(blocklist),
-        query_log: Mutex::new(QueryLog::new(1000)),
-        services: Mutex::new(service_store),
-        lan_peers: Mutex::new(numa::lan::PeerStore::new(config.lan.peer_timeout_secs)),
-        forwarding_rules,
-        upstream_pool: Mutex::new(pool),
-        upstream_auto,
-        upstream_port: config.upstream.port,
-        lan_ip: Mutex::new(numa::lan::detect_lan_ip().unwrap_or(std::net::Ipv4Addr::LOCALHOST)),
-        timeout: Duration::from_millis(config.upstream.timeout_ms),
-        hedge_delay: Duration::from_millis(config.upstream.hedge_ms),
-        proxy_tld_suffix: if config.proxy.tld.is_empty() {
-            String::new()
-        } else {
-            format!(".{}", config.proxy.tld)
-        },
-        proxy_tld: config.proxy.tld.clone(),
-        lan_enabled: config.lan.enabled,
-        config_path: resolved_config_path,
-        config_found,
-        config_dir: numa::config_dir(),
-        data_dir: resolved_data_dir,
-        tls_config: initial_tls,
-        upstream_mode: resolved_mode,
-        root_hints,
-        srtt: std::sync::RwLock::new(numa::srtt::SrttCache::new(config.upstream.srtt)),
-        inflight: std::sync::Mutex::new(std::collections::HashMap::new()),
-        dnssec_enabled: config.dnssec.enabled,
-        dnssec_strict: config.dnssec.strict,
-        health_meta,
-        ca_pem,
-        mobile_enabled: config.mobile.enabled,
-        mobile_port: config.mobile.port,
-    });
-
-    let zone_count: usize = ctx.zone_map.values().map(|m| m.len()).sum();
-    // Build banner rows, then size the box to fit the longest value
-    let api_url = format!("http://localhost:{}", api_port);
-    let proxy_label = if config.proxy.enabled {
-        if config.proxy.tls_port > 0 {
-            Some(format!(
-                "http://:{} https://:{}",
-                config.proxy.port, config.proxy.tls_port
-            ))
-        } else {
-            Some(format!(
-                "http://*.{} on :{}",
-                config.proxy.tld, config.proxy.port
-            ))
-        }
-    } else {
-        None
-    };
-    let config_label = if ctx.config_found {
-        ctx.config_path.clone()
-    } else {
-        format!("{} (defaults)", ctx.config_path)
-    };
-    let data_label = ctx.data_dir.display().to_string();
-    let services_label = ctx.config_dir.join("services.json").display().to_string();
-
-    // label (10) + value + padding (2) = inner width; minimum 40 for the title row
-    let val_w = [
-        config.server.bind_addr.len(),
-        api_url.len(),
-        upstream_label.len(),
-        config_label.len(),
-        data_label.len(),
-        services_label.len(),
-    ]
-    .into_iter()
-    .chain(proxy_label.as_ref().map(|s| s.len()))
-    .max()
-    .unwrap_or(30);
-    let w = (val_w + 12).max(42); // 10 label + 2 padding, min 42 for title
-
-    let o = "\x1b[38;2;192;98;58m"; // orange
-    let g = "\x1b[38;2;107;124;78m"; // green
-    let d = "\x1b[38;2;163;152;136m"; // dim
-    let r = "\x1b[0m"; // reset
-    let b = "\x1b[1;38;2;192;98;58m"; // bold orange
-    let it = "\x1b[3;38;2;163;152;136m"; // italic dim
-
-    let bar_top = "═".repeat(w);
-    let bar_mid = "─".repeat(w);
-    let row = |label: &str, color: &str, value: &str| {
-        eprintln!(
-            "{o}  ║{r}  {color}{:<9}{r} {:<vw$}{o}║{r}",
-            label,
-            value,
-            vw = w - 12
-        );
-    };
-
-    // Title row: center within the box
-    let title = format!(
-        "{b}NUMA{r}  {it}DNS that governs itself{r}  {d}v{}{r}",
-        env!("CARGO_PKG_VERSION")
-    );
-    // The title contains ANSI codes; visible length is ~38 chars. Pad to fill the box.
-    let title_visible_len = 4 + 2 + 24 + 2 + 1 + env!("CARGO_PKG_VERSION").len() + 1;
-    let title_pad = w.saturating_sub(title_visible_len);
-    eprintln!("\n{o}  ╔{bar_top}╗{r}");
-    eprint!("{o}  ║{r} {title}");
-    eprintln!("{}{o}║{r}", " ".repeat(title_pad));
-    eprintln!("{o}  ╠{bar_top}╣{r}");
-    row("DNS", g, &config.server.bind_addr);
-    row("API", g, &api_url);
-    row("Dashboard", g, &api_url);
-    row(
-        "Upstream",
-        g,
-        if ctx.upstream_mode == numa::config::UpstreamMode::Recursive {
-            "recursive (root hints)"
-        } else {
-            &upstream_label
-        },
-    );
-    row("Zones", g, &format!("{} records", zone_count));
-    row(
-        "Cache",
-        g,
-        &format!("max {} entries", config.cache.max_entries),
-    );
-    if !config.cache.warm.is_empty() {
-        row("Warm", g, &format!("{} domains", config.cache.warm.len()));
-    }
-    row(
-        "Blocking",
-        g,
-        &if config.blocking.enabled {
-            format!("{} lists", config.blocking.lists.len())
-        } else {
-            "disabled".to_string()
-        },
-    );
-    if let Some(ref label) = proxy_label {
-        row("Proxy", g, label);
-        if config.proxy.bind_addr == "127.0.0.1" {
-            let y = "\x1b[38;2;204;176;59m"; // yellow
-            row(
-                "",
-                y,
-                &format!(
-                    "⚠ proxy on 127.0.0.1 — .{} not LAN reachable",
-                    config.proxy.tld
-                ),
-            );
-        }
-    }
-    if config.dot.enabled {
-        row("DoT", g, &format!("tls://:{}", config.dot.port));
-    }
-    if doh_enabled {
-        row(
-            "DoH",
-            g,
-            &format!("https://:{}/dns-query", config.proxy.tls_port),
-        );
-    }
-    if config.lan.enabled {
-        row("LAN", g, "mDNS (_numa._tcp.local)");
-    }
-    if !ctx.forwarding_rules.is_empty() {
-        row(
-            "Routing",
-            g,
-            &format!("{} conditional rules", ctx.forwarding_rules.len()),
-        );
-    }
-    eprintln!("{o}  ╠{bar_mid}╣{r}");
-    row("Config", d, &config_label);
-    row("Data", d, &data_label);
-    row("Services", d, &services_label);
-    eprintln!("{o}  ╚{bar_top}╝{r}\n");
-
-    info!(
-        "numa listening on {}, upstream {}, {} zone records, cache max {}, API on port {}",
-        config.server.bind_addr, upstream_label, zone_count, config.cache.max_entries, api_port,
-    );
-
-    // Download blocklists on startup
-    let blocklist_lists = config.blocking.lists.clone();
-    let refresh_hours = config.blocking.refresh_hours;
-    if config.blocking.enabled && !blocklist_lists.is_empty() {
-        let bl_ctx = Arc::clone(&ctx);
-        let bl_lists = blocklist_lists.clone();
-        tokio::spawn(async move {
-            load_blocklists(&bl_ctx, &bl_lists).await;
-
-            // Periodic refresh
-            let mut interval = tokio::time::interval(Duration::from_secs(refresh_hours * 3600));
-            interval.tick().await; // skip immediate tick
-            loop {
-                interval.tick().await;
-                info!("refreshing blocklists...");
-                load_blocklists(&bl_ctx, &bl_lists).await;
-            }
-        });
-    }
-
-    // Prime TLD cache (recursive mode only)
-    if ctx.upstream_mode == numa::config::UpstreamMode::Recursive {
-        let prime_ctx = Arc::clone(&ctx);
-        let prime_tlds = config.upstream.prime_tlds;
-        tokio::spawn(async move {
-            numa::recursive::prime_tld_cache(
-                &prime_ctx.cache,
-                &prime_ctx.root_hints,
-                &prime_tlds,
-                &prime_ctx.srtt,
-            )
-            .await;
-        });
-    }
-
-    // Spawn cache warming for user-configured domains
-    if !config.cache.warm.is_empty() {
-        let warm_ctx = Arc::clone(&ctx);
-        let warm_domains = config.cache.warm.clone();
-        tokio::spawn(async move {
-            cache_warm_loop(warm_ctx, warm_domains).await;
-        });
-    }
-
-    // Spawn DoH connection keepalive — prevents idle TLS teardown
-    {
-        let keepalive_ctx = Arc::clone(&ctx);
-        tokio::spawn(async move {
-            doh_keepalive_loop(keepalive_ctx).await;
-        });
-    }
-
-    // Spawn HTTP API server
-    let api_ctx = Arc::clone(&ctx);
-    let api_addr: SocketAddr = format!("{}:{}", config.server.api_bind_addr, api_port).parse()?;
-    tokio::spawn(async move {
-        let app = numa::api::router(api_ctx);
-        let listener = tokio::net::TcpListener::bind(api_addr).await.unwrap();
-        info!("HTTP API listening on {}", api_addr);
-        axum::serve(listener, app).await.unwrap();
-    });
-
-    // Spawn Mobile API listener (read-only subset for iOS/Android companion
-    // apps, LAN-bound by default so phones can reach it). Only idempotent
-    // GETs; no state-mutating routes are exposed here regardless of
-    // the main API's bind address.
-    if config.mobile.enabled {
-        let mobile_ctx = Arc::clone(&ctx);
-        let mobile_bind = config.mobile.bind_addr.clone();
-        let mobile_port = config.mobile.port;
-        tokio::spawn(async move {
-            if let Err(e) = numa::mobile_api::start(mobile_ctx, mobile_bind, mobile_port).await {
-                log::warn!("Mobile API listener failed: {}", e);
-            }
-        });
-    }
-
-    let proxy_bind: std::net::Ipv4Addr = config
-        .proxy
-        .bind_addr
-        .parse()
-        .unwrap_or(std::net::Ipv4Addr::LOCALHOST);
-
-    // Spawn HTTP reverse proxy for .numa domains
-    if config.proxy.enabled {
-        let proxy_ctx = Arc::clone(&ctx);
-        let proxy_port = config.proxy.port;
-        tokio::spawn(async move {
-            numa::proxy::start_proxy(proxy_ctx, proxy_port, proxy_bind).await;
-        });
-    }
-
-    // Spawn HTTPS reverse proxy with TLS termination
-    if config.proxy.enabled && config.proxy.tls_port > 0 && ctx.tls_config.is_some() {
-        let proxy_ctx = Arc::clone(&ctx);
-        let tls_port = config.proxy.tls_port;
-        tokio::spawn(async move {
-            numa::proxy::start_proxy_tls(proxy_ctx, tls_port, proxy_bind).await;
-        });
-    }
-
-    // Spawn network change watcher (upstream re-detection, LAN IP update, peer flush)
-    {
-        let watch_ctx = Arc::clone(&ctx);
-        tokio::spawn(async move {
-            network_watch_loop(watch_ctx).await;
-        });
-    }
-
-    // Spawn LAN service discovery
-    if config.lan.enabled {
-        let lan_ctx = Arc::clone(&ctx);
-        let lan_config = config.lan.clone();
-        tokio::spawn(async move {
-            numa::lan::start_lan_discovery(lan_ctx, &lan_config).await;
-        });
-    }
-
-    // Spawn DNS-over-TLS listener (RFC 7858)
-    if config.dot.enabled {
-        let dot_ctx = Arc::clone(&ctx);
-        let dot_config = config.dot.clone();
-        tokio::spawn(async move {
-            numa::dot::start_dot(dot_ctx, &dot_config).await;
-        });
-    }
-
-    // UDP DNS listener
-    #[allow(clippy::infinite_loop)]
-    loop {
-        let mut buffer = BytePacketBuffer::new();
-        let (len, src_addr) = match ctx.socket.recv_from(&mut buffer.buf).await {
-            Ok(r) => r,
-            Err(e) if e.kind() == std::io::ErrorKind::ConnectionReset => {
-                // Windows delivers ICMP port-unreachable as ConnectionReset on UDP sockets
-                continue;
-            }
-            Err(e) => return Err(e.into()),
-        };
-        let ctx = Arc::clone(&ctx);
-        tokio::spawn(async move {
-            if let Err(e) = handle_query(buffer, len, src_addr, &ctx, Transport::Udp).await {
-                error!("{} | HANDLER ERROR | {}", src_addr, e);
-            }
-        });
-    }
-}
-
-async fn network_watch_loop(ctx: Arc<numa::ctx::ServerCtx>) {
-    let mut tick: u64 = 0;
-
-    let mut interval = tokio::time::interval(Duration::from_secs(5));
-    interval.tick().await; // skip immediate tick
-
-    loop {
-        interval.tick().await;
-        tick += 1;
-        let mut changed = false;
-
-        // Check LAN IP change (every 5s — cheap, one UDP socket call)
-        if let Some(new_ip) = numa::lan::detect_lan_ip() {
-            let mut current_ip = ctx.lan_ip.lock().unwrap();
-            if new_ip != *current_ip {
-                info!("LAN IP changed: {} → {}", current_ip, new_ip);
-                *current_ip = new_ip;
-                changed = true;
-                numa::recursive::reset_udp_state();
-            }
-        }
-
-        // Re-detect upstream every 30s or on LAN IP change (auto-detect only)
-        if ctx.upstream_auto && (changed || tick.is_multiple_of(6)) {
-            let dns_info = numa::system_dns::discover_system_dns();
-            let new_addr = dns_info
-                .default_upstream
-                .or_else(numa::system_dns::detect_dhcp_dns)
-                .unwrap_or_else(|| QUAD9_IP.to_string());
-            let mut pool = ctx.upstream_pool.lock().unwrap();
-            if pool.maybe_update_primary(&new_addr, ctx.upstream_port) {
-                info!("upstream changed → {}", pool.label());
-                changed = true;
-            }
-        }
-
-        // Flush stale LAN peers on any network change
-        if changed {
-            ctx.lan_peers.lock().unwrap().clear();
-            info!("flushed LAN peers after network change");
-        }
-
-        // Re-probe UDP every 5 minutes when disabled
-        if tick.is_multiple_of(60) {
-            numa::recursive::probe_udp(&ctx.root_hints).await;
-        }
-    }
 }
 
 fn set_lan_enabled(enabled: bool, path: &str) -> numa::Result<()> {
@@ -730,71 +220,3 @@ fn print_lan_status(enabled: bool) {
         eprintln!("  Restart Numa to start mDNS discovery");
     }
 }
-
-async fn load_blocklists(ctx: &ServerCtx, lists: &[String]) {
-    let downloaded = download_blocklists(lists).await;
-
-    // Parse outside the lock to avoid blocking DNS queries during parse (~100ms)
-    let mut all_domains = std::collections::HashSet::new();
-    let mut sources = Vec::new();
-    for (source, text) in &downloaded {
-        let domains = parse_blocklist(text);
-        info!("blocklist: {} domains from {}", domains.len(), source);
-        all_domains.extend(domains);
-        sources.push(source.clone());
-    }
-    let total = all_domains.len();
-
-    // Swap under lock — sub-microsecond
-    ctx.blocklist
-        .write()
-        .unwrap()
-        .swap_domains(all_domains, sources);
-    info!(
-        "blocking enabled: {} unique domains from {} lists",
-        total,
-        downloaded.len()
-    );
-}
-
-async fn warm_domain(ctx: &ServerCtx, domain: &str) {
-    for qtype in [
-        numa::question::QueryType::A,
-        numa::question::QueryType::AAAA,
-    ] {
-        numa::ctx::refresh_entry(ctx, domain, qtype).await;
-    }
-}
-
-async fn doh_keepalive_loop(ctx: Arc<ServerCtx>) {
-    let mut interval = tokio::time::interval(Duration::from_secs(25));
-    interval.tick().await; // skip first immediate tick
-    loop {
-        interval.tick().await;
-        let pool = ctx.upstream_pool.lock().unwrap().clone();
-        if let Some(upstream) = pool.preferred() {
-            numa::forward::keepalive_doh(upstream).await;
-        }
-    }
-}
-
-async fn cache_warm_loop(ctx: Arc<ServerCtx>, domains: Vec<String>) {
-    tokio::time::sleep(Duration::from_secs(2)).await;
-
-    for domain in &domains {
-        warm_domain(&ctx, domain).await;
-    }
-    info!("cache warm: {} domains resolved at startup", domains.len());
-
-    let mut interval = tokio::time::interval(Duration::from_secs(30));
-    interval.tick().await;
-    loop {
-        interval.tick().await;
-        for domain in &domains {
-            let refresh = ctx.cache.read().unwrap().needs_warm(domain);
-            if refresh {
-                warm_domain(&ctx, domain).await;
-            }
-        }
-    }
-}

src/odoh.rs

@@ -0,0 +1,489 @@
+//! ODoH target-config fetcher and TTL cache (RFC 9230 §6).
+//!
+//! ## Ciphersuite policy
+//! `odoh-rs` deserialization rejects any config whose KEM/KDF/AEAD triple is
+//! not the mandatory `(X25519, HKDF-SHA256, AES-128-GCM)` (see
+//! `ObliviousDoHConfigContents::deserialize`). This is stricter than the
+//! plan's "pick the mandatory suite if mixed": a response containing *any*
+//! non-mandatory config fails parse entirely. Real-world targets publish a
+//! single mandatory config, so this is fine in practice; revisit if a target
+//! that matters starts mixing suites.
+
+use std::sync::Arc;
+use std::time::{Duration, Instant};
+
+use arc_swap::ArcSwapOption;
+use odoh_rs::{
+    ObliviousDoHConfigContents, ObliviousDoHConfigs, ObliviousDoHMessage,
+    ObliviousDoHMessagePlaintext,
+};
+use rand_core::{OsRng, TryRngCore};
+use reqwest::header::HeaderMap;
+use tokio::sync::Mutex;
+use tokio::time::timeout;
+
+use crate::Result;
+
+/// MIME type used for both directions of the ODoH exchange (RFC 9230 §4).
+pub(crate) const ODOH_CONTENT_TYPE: &str = "application/oblivious-dns-message";
+
+/// Cap on the response body we read into memory when the relay returns
+/// non-success. Protects against a hostile relay streaming a huge body on
+/// the error path; keeps enough room to carry a human-readable reason.
+const ERROR_BODY_PREVIEW_BYTES: usize = 1024;
+
+/// Fallback TTL when the target's response lacks a usable `Cache-Control`
+/// directive. RFC 9230 §6.2 places no hard floor; 24 h matches what Cloudflare
+/// publishes in practice.
+const DEFAULT_CONFIG_TTL: Duration = Duration::from_secs(24 * 60 * 60);
+
+/// Cap on any TTL we'll honour, regardless of what the target advertises.
+/// Keeps a misconfigured server from pinning an old key indefinitely.
+const MAX_CONFIG_TTL: Duration = Duration::from_secs(7 * 24 * 60 * 60);
+
+/// After a failed `/.well-known/odohconfigs` fetch, refuse to refetch again
+/// within this window — a target that is genuinely broken would otherwise
+/// receive one request per query. Queries that arrive during the backoff
+/// return the cached error immediately.
+const REFRESH_BACKOFF: Duration = Duration::from_secs(60);
+
+/// Parsed ODoH target config plus the freshness metadata needed to age it out.
+#[derive(Debug)]
+pub struct OdohTargetConfig {
+    pub contents: ObliviousDoHConfigContents,
+    pub key_id: Vec<u8>,
+    expires_at: Instant,
+}
+
+impl OdohTargetConfig {
+    pub fn is_expired(&self) -> bool {
+        Instant::now() >= self.expires_at
+    }
+}
+
+struct FailedRefresh {
+    at: Instant,
+    err: String,
+}
+
+/// TTL-gated cache of a single target's HPKE config.
+///
+/// Reads go through `ArcSwapOption` (lock-free hot path). Refreshes serialize
+/// on an async mutex so a burst of simultaneous misses produces a single
+/// outbound fetch, and a failed refresh blocks subsequent refetches for
+/// [`REFRESH_BACKOFF`] to prevent hot-looping against a broken target.
+pub struct OdohConfigCache {
+    target_host: String,
+    configs_url: String,
+    client: reqwest::Client,
+    current: ArcSwapOption<OdohTargetConfig>,
+    last_failure: ArcSwapOption<FailedRefresh>,
+    refresh_lock: Mutex<()>,
+}
+
+impl OdohConfigCache {
+    pub fn new(target_host: String, client: reqwest::Client) -> Self {
+        let configs_url = format!("https://{}/.well-known/odohconfigs", target_host);
+        Self {
+            target_host,
+            configs_url,
+            client,
+            current: ArcSwapOption::from(None),
+            last_failure: ArcSwapOption::from(None),
+            refresh_lock: Mutex::new(()),
+        }
+    }
+
+    pub fn target_host(&self) -> &str {
+        &self.target_host
+    }
+
+    /// Return a valid config, refetching when the cache is cold or expired.
+    /// Within [`REFRESH_BACKOFF`] of a failed refresh, returns the cached
+    /// error without issuing another fetch.
+    pub async fn get(&self) -> Result<Arc<OdohTargetConfig>> {
+        if let Some(cfg) = self.current.load_full() {
+            if !cfg.is_expired() {
+                return Ok(cfg);
+            }
+        }
+
+        if let Some(err) = self.backoff_error() {
+            return Err(err);
+        }
+
+        let _guard = self.refresh_lock.lock().await;
+
+        // Another task may have refreshed or failed while we waited.
+        if let Some(cfg) = self.current.load_full() {
+            if !cfg.is_expired() {
+                return Ok(cfg);
+            }
+        }
+        if let Some(err) = self.backoff_error() {
+            return Err(err);
+        }
+
+        match fetch_odoh_config(&self.client, &self.configs_url).await {
+            Ok(fresh) => {
+                let fresh = Arc::new(fresh);
+                self.current.store(Some(fresh.clone()));
+                self.last_failure.store(None);
+                Ok(fresh)
+            }
+            Err(e) => {
+                let msg = format!("ODoH config fetch failed: {e}");
+                self.last_failure.store(Some(Arc::new(FailedRefresh {
+                    at: Instant::now(),
+                    err: msg.clone(),
+                })));
+                Err(msg.into())
+            }
+        }
+    }
+
+    /// Drop the cached config. Called after the target rejects ciphertext
+    /// (key rotation race) so the next `get()` refetches.
+    pub fn invalidate(&self) {
+        self.current.store(None);
+    }
+
+    fn backoff_error(&self) -> Option<crate::Error> {
+        let fail = self.last_failure.load_full()?;
+        if fail.at.elapsed() < REFRESH_BACKOFF {
+            Some(format!("{} (backoff active)", fail.err).into())
+        } else {
+            None
+        }
+    }
+}
+
+/// Fetch `/.well-known/odohconfigs` from `configs_url` and parse it into an
+/// [`OdohTargetConfig`]. The TTL is taken from the response's
+/// `Cache-Control: max-age=`, clamped to [`DEFAULT_CONFIG_TTL`,
+/// [`MAX_CONFIG_TTL`]] when absent or obviously wrong.
+pub async fn fetch_odoh_config(
+    client: &reqwest::Client,
+    configs_url: &str,
+) -> Result<OdohTargetConfig> {
+    let resp = client.get(configs_url).send().await?.error_for_status()?;
+    let ttl = cache_control_ttl(resp.headers()).unwrap_or(DEFAULT_CONFIG_TTL);
+    let body = resp.bytes().await?;
+    parse_odoh_config(&body, ttl)
+}
+
+fn parse_odoh_config(body: &[u8], ttl: Duration) -> Result<OdohTargetConfig> {
+    let mut buf = body;
+    let configs: ObliviousDoHConfigs = odoh_rs::parse(&mut buf)
+        .map_err(|e| format!("failed to parse ObliviousDoHConfigs: {e}"))?;
+    let first = configs
+        .into_iter()
+        .next()
+        .ok_or("target published no ODoH configs with a supported version + ciphersuite")?;
+    let contents: ObliviousDoHConfigContents = first.into();
+    let key_id = contents
+        .identifier()
+        .map_err(|e| format!("failed to derive key_id from ODoH config: {e}"))?;
+    Ok(OdohTargetConfig {
+        contents,
+        key_id,
+        expires_at: Instant::now() + ttl.min(MAX_CONFIG_TTL),
+    })
+}
+
+/// Send a DNS wire query through an ODoH relay to a target and return the
+/// plaintext DNS wire response.
+///
+/// Flow: fetch the target's HPKE config (cached), seal the query, POST to the
+/// relay with `Targethost`/`Targetpath` headers, then unseal the response.
+/// On seal/unseal failure we invalidate the cache and retry once — this
+/// handles the benign race where the target rotated its key between our
+/// cached config and the POST.
+pub async fn query_through_relay(
+    wire: &[u8],
+    relay_url: &str,
+    target_path: &str,
+    client: &reqwest::Client,
+    cache: &OdohConfigCache,
+    timeout_duration: Duration,
+) -> Result<Vec<u8>> {
+    let req = OdohRequest {
+        wire,
+        relay_url,
+        target_path,
+        client,
+        cache,
+        timeout: timeout_duration,
+    };
+    match attempt_query(&req).await {
+        Ok(v) => Ok(v),
+        Err(AttemptError::KeyRotation(_)) => {
+            cache.invalidate();
+            attempt_query(&req).await.map_err(AttemptError::into_error)
+        }
+        Err(e) => Err(e.into_error()),
+    }
+}
+
+struct OdohRequest<'a> {
+    wire: &'a [u8],
+    relay_url: &'a str,
+    target_path: &'a str,
+    client: &'a reqwest::Client,
+    cache: &'a OdohConfigCache,
+    timeout: Duration,
+}
+
+/// Classification used only by the retry path in [`query_through_relay`].
+enum AttemptError {
+    /// Target signalled the config we used is stale (key rotation race).
+    /// Callers should invalidate the cache and retry exactly once.
+    KeyRotation(String),
+    /// Any other failure — transport, timeout, malformed response.
+    Other(crate::Error),
+}
+
+impl AttemptError {
+    fn into_error(self) -> crate::Error {
+        match self {
+            AttemptError::KeyRotation(m) => format!("ODoH key rotation race: {m}").into(),
+            AttemptError::Other(e) => e,
+        }
+    }
+}
+
+async fn attempt_query(req: &OdohRequest<'_>) -> std::result::Result<Vec<u8>, AttemptError> {
+    let cfg = req.cache.get().await.map_err(AttemptError::Other)?;
+
+    let plaintext = ObliviousDoHMessagePlaintext::new(req.wire, 0);
+    // rand_core 0.9's OsRng is fallible-only; wrap for the infallible bound.
+    let mut os = OsRng;
+    let mut rng = os.unwrap_mut();
+    let (encrypted_query, client_secret) =
+        odoh_rs::encrypt_query(&plaintext, &cfg.contents, &mut rng)
+            .map_err(|e| AttemptError::Other(format!("ODoH encrypt failed: {e}").into()))?;
+    let body = odoh_rs::compose(&encrypted_query)
+        .map_err(|e| AttemptError::Other(format!("ODoH compose failed: {e}").into()))?
+        .freeze();
+
+    // RFC 9230 §5 and the reference client use URL query parameters, not
+    // HTTP headers, to carry the target routing. `Targethost`/`Targetpath`
+    // headers cause relays to treat the request as an unspecified-target and
+    // reject it.
+    let (status, resp_body) = timeout(req.timeout, async {
+        let resp = req
+            .client
+            .post(req.relay_url)
+            .header(reqwest::header::CONTENT_TYPE, ODOH_CONTENT_TYPE)
+            .header(reqwest::header::ACCEPT, ODOH_CONTENT_TYPE)
+            .header(reqwest::header::CACHE_CONTROL, "no-cache, no-store")
+            .query(&[
+                ("targethost", req.cache.target_host()),
+                ("targetpath", req.target_path),
+            ])
+            .body(body)
+            .send()
+            .await?;
+        let status = resp.status();
+        let body = resp.bytes().await?;
+        Ok::<_, reqwest::Error>((status, body))
+    })
+    .await
+    .map_err(|_| AttemptError::Other("ODoH relay request timed out".into()))?
+    .map_err(|e| AttemptError::Other(format!("ODoH relay request failed: {e}").into()))?;
+
+    // RFC 9230 §4.3 expects a target that can't decrypt to reply with a DNS
+    // error in a sealed 200 response; a 401 from the relay/target is the
+    // practical signal that our cached HPKE key is stale. Treat 400 as a
+    // client-side bug (malformed ODoH envelope) — retrying would loop-fail.
+    if !status.is_success() {
+        let preview_len = resp_body.len().min(ERROR_BODY_PREVIEW_BYTES);
+        let body_preview = String::from_utf8_lossy(&resp_body[..preview_len]);
+        let msg = format!("ODoH relay returned {status}: {}", body_preview.trim());
+        return Err(if status.as_u16() == 401 {
+            AttemptError::KeyRotation(msg)
+        } else {
+            AttemptError::Other(msg.into())
+        });
+    }
+
+    let mut buf = resp_body;
+    let encrypted_response: ObliviousDoHMessage = odoh_rs::parse(&mut buf)
+        .map_err(|e| AttemptError::Other(format!("ODoH response parse failed: {e}").into()))?;
+    let plaintext_response =
+        odoh_rs::decrypt_response(&plaintext, &encrypted_response, client_secret)
+            .map_err(|e| AttemptError::KeyRotation(format!("ODoH decrypt failed: {e}")))?;
+
+    Ok(plaintext_response.into_msg().to_vec())
+}
+
+fn cache_control_ttl(headers: &HeaderMap) -> Option<Duration> {
+    let cc = headers.get(reqwest::header::CACHE_CONTROL)?.to_str().ok()?;
+    for directive in cc.split(',') {
+        let directive = directive.trim();
+        if let Some(rest) = directive.strip_prefix("max-age=") {
+            if let Ok(secs) = rest.trim().parse::<u64>() {
+                if secs > 0 {
+                    return Some(Duration::from_secs(secs));
+                }
+            }
+        }
+    }
+    None
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use odoh_rs::{ObliviousDoHConfig, ObliviousDoHKeyPair};
+
+    // RFC 9180 HPKE IDs for the sole ODoH mandatory suite:
+    // KEM = X25519, KDF = HKDF-SHA256, AEAD = AES-128-GCM.
+    const KEM_X25519: u16 = 0x0020;
+    const KDF_SHA256: u16 = 0x0001;
+    const AEAD_AES128GCM: u16 = 0x0001;
+
+    fn synth_configs_bytes() -> Vec<u8> {
+        let kp = ObliviousDoHKeyPair::from_parameters(
+            KEM_X25519,
+            KDF_SHA256,
+            AEAD_AES128GCM,
+            &[0u8; 32],
+        );
+        let pk = kp.public().clone();
+        let configs: ObliviousDoHConfigs = vec![ObliviousDoHConfig::from(pk)].into();
+        odoh_rs::compose(&configs).unwrap().to_vec()
+    }
+
+    #[test]
+    fn parse_accepts_well_formed_config() {
+        let bytes = synth_configs_bytes();
+        let cfg = parse_odoh_config(&bytes, Duration::from_secs(3600)).unwrap();
+        assert!(!cfg.key_id.is_empty());
+        assert!(!cfg.is_expired());
+    }
+
+    #[test]
+    fn parse_rejects_garbage() {
+        let bytes = [0xffu8; 16];
+        assert!(parse_odoh_config(&bytes, Duration::from_secs(3600)).is_err());
+    }
+
+    #[test]
+    fn parse_rejects_empty() {
+        assert!(parse_odoh_config(&[], Duration::from_secs(3600)).is_err());
+    }
+
+    #[test]
+    fn ttl_capped_at_max() {
+        let bytes = synth_configs_bytes();
+        let cfg = parse_odoh_config(&bytes, Duration::from_secs(100 * 24 * 60 * 60)).unwrap();
+        let remaining = cfg.expires_at.saturating_duration_since(Instant::now());
+        assert!(remaining <= MAX_CONFIG_TTL);
+        assert!(remaining >= MAX_CONFIG_TTL - Duration::from_secs(1));
+    }
+
+    #[test]
+    fn cache_control_parses_max_age() {
+        let mut h = HeaderMap::new();
+        h.insert("cache-control", "public, max-age=86400".parse().unwrap());
+        assert_eq!(cache_control_ttl(&h), Some(Duration::from_secs(86400)));
+    }
+
+    #[test]
+    fn cache_control_ignores_max_age_zero() {
+        let mut h = HeaderMap::new();
+        h.insert("cache-control", "max-age=0, no-store".parse().unwrap());
+        assert_eq!(cache_control_ttl(&h), None);
+    }
+
+    #[test]
+    fn cache_control_missing_falls_back() {
+        let h = HeaderMap::new();
+        assert_eq!(cache_control_ttl(&h), None);
+    }
+
+    #[test]
+    fn is_expired_tracks_ttl() {
+        let bytes = synth_configs_bytes();
+        let mut cfg = parse_odoh_config(&bytes, Duration::from_secs(3600)).unwrap();
+        assert!(!cfg.is_expired());
+        cfg.expires_at = Instant::now() - Duration::from_secs(1);
+        assert!(cfg.is_expired());
+    }
+
+    #[tokio::test]
+    async fn cache_backoff_blocks_refetch_after_failure() {
+        // Point the cache at a host that does not exist so the fetch fails
+        // deterministically; this exercises the backoff wiring without a
+        // network round-trip succeeding.
+        let cache = OdohConfigCache::new(
+            "odoh-target.invalid".to_string(),
+            reqwest::Client::builder()
+                .timeout(Duration::from_millis(200))
+                .build()
+                .unwrap(),
+        );
+
+        let first = cache.get().await;
+        assert!(first.is_err(), "first fetch must fail against invalid host");
+
+        // Within the backoff window, the cached error is returned immediately.
+        let second = cache.get().await.unwrap_err().to_string();
+        assert!(
+            second.contains("backoff active"),
+            "expected backoff hint, got: {second}"
+        );
+
+        // Reaching past the backoff window allows a fresh attempt — simulate
+        // by rewinding the recorded failure timestamp.
+        cache.last_failure.store(Some(Arc::new(FailedRefresh {
+            at: Instant::now() - (REFRESH_BACKOFF + Duration::from_secs(1)),
+            err: "prior".to_string(),
+        })));
+        let third = cache.get().await.unwrap_err().to_string();
+        assert!(
+            !third.contains("backoff active"),
+            "expected fresh fetch attempt, got: {third}"
+        );
+    }
+
+    /// Round-trip the HPKE seal/unseal path in isolation from HTTP, using the
+    /// odoh-rs primitives that `query_through_relay` wires together. Guards
+    /// against silently breaking the crypto glue if we refactor that path.
+    #[test]
+    fn seal_unseal_round_trip() {
+        use odoh_rs::{decrypt_query, encrypt_response, ResponseNonce};
+
+        let kp = ObliviousDoHKeyPair::from_parameters(
+            KEM_X25519,
+            KDF_SHA256,
+            AEAD_AES128GCM,
+            &[0u8; 32],
+        );
+
+        let query_wire = b"\x12\x34\x01\x00\x00\x01\x00\x00\x00\x00\x00\x00\x07example\x03com\x00\x00\x01\x00\x01";
+        let query_pt = ObliviousDoHMessagePlaintext::new(query_wire, 0);
+        let mut os = OsRng;
+        let mut rng = os.unwrap_mut();
+        let (query_enc, client_secret) =
+            odoh_rs::encrypt_query(&query_pt, kp.public(), &mut rng).unwrap();
+
+        let (query_back, server_secret) = decrypt_query(&query_enc, &kp).unwrap();
+        assert_eq!(query_back.into_msg().as_ref(), query_wire);
+
+        let response_wire = b"\x12\x34\x81\x80\x00\x01\x00\x01\x00\x00\x00\x00";
+        let response_pt = ObliviousDoHMessagePlaintext::new(response_wire, 0);
+        let response_enc = encrypt_response(
+            &query_pt,
+            &response_pt,
+            server_secret,
+            ResponseNonce::default(),
+        )
+        .unwrap();
+
+        let response_back =
+            odoh_rs::decrypt_response(&query_pt, &response_enc, client_secret).unwrap();
+        assert_eq!(response_back.into_msg().as_ref(), response_wire);
+    }
+}

src/packet.rs

@@ -85,6 +85,14 @@ impl DnsPacket {
             + self.edns.as_ref().map_or(0, |e| e.options.capacity())
     }
 
+    /// Apply `f` to every record in the three RR sections (answers,
+    /// authorities, resources). Does not touch questions or edns.
+    pub fn for_each_record_mut(&mut self, mut f: impl FnMut(&mut DnsRecord)) {
+        self.answers.iter_mut().for_each(&mut f);
+        self.authorities.iter_mut().for_each(&mut f);
+        self.resources.iter_mut().for_each(&mut f);
+    }
+
     pub fn response_from(query: &DnsPacket, rescode: crate::header::ResultCode) -> DnsPacket {
         let mut resp = DnsPacket::new();
         resp.header.id = query.header.id;

src/question.rs

@@ -1,114 +1,66 @@
 use crate::buffer::BytePacketBuffer;
 use crate::Result;
 
-#[derive(PartialEq, Eq, Debug, Clone, Hash, Copy)]
+macro_rules! define_qtypes {
-pub enum QueryType {
+    ( $( $variant:ident = $num:literal, $str:literal ),* $(,)? ) => {
-    UNKNOWN(u16),
+        #[derive(PartialEq, Eq, Debug, Clone, Hash, Copy)]
-    A,      // 1
+        pub enum QueryType {
-    NS,     // 2
+            UNKNOWN(u16),
-    CNAME,  // 5
+            $( $variant, )*
-    SOA,    // 6
+        }
-    PTR,    // 12
+
-    MX,     // 15
+        impl QueryType {
-    TXT,    // 16
+            pub fn to_num(&self) -> u16 {
-    AAAA,   // 28
+                match *self {
-    SRV,    // 33
+                    QueryType::UNKNOWN(x) => x,
-    DS,     // 43
+                    $( QueryType::$variant => $num, )*
-    RRSIG,  // 46
+                }
-    NSEC,   // 47
+            }
-    DNSKEY, // 48
+
-    NSEC3,  // 50
+            pub fn from_num(num: u16) -> QueryType {
-    OPT,    // 41 (EDNS0 pseudo-type)
+                match num {
-    HTTPS,  // 65
+                    $( $num => QueryType::$variant, )*
+                    _ => QueryType::UNKNOWN(num),
+                }
+            }
+
+            pub fn as_str(&self) -> &'static str {
+                match self {
+                    QueryType::UNKNOWN(_) => "UNKNOWN",
+                    $( QueryType::$variant => $str, )*
+                }
+            }
+
+            pub fn parse_str(s: &str) -> Option<QueryType> {
+                match s.to_ascii_uppercase().as_str() {
+                    $( $str => Some(QueryType::$variant), )*
+                    _ => None,
+                }
+            }
+        }
+    };
 }
 
-impl QueryType {
+define_qtypes! {
-    pub fn to_num(&self) -> u16 {
+    A      = 1,  "A",
-        match *self {
+    NS     = 2,  "NS",
-            QueryType::UNKNOWN(x) => x,
+    CNAME  = 5,  "CNAME",
-            QueryType::A => 1,
+    SOA    = 6,  "SOA",
-            QueryType::NS => 2,
+    PTR    = 12, "PTR",
-            QueryType::CNAME => 5,
+    MX     = 15, "MX",
-            QueryType::SOA => 6,
+    TXT    = 16, "TXT",
-            QueryType::PTR => 12,
+    AAAA   = 28, "AAAA",
-            QueryType::MX => 15,
+    LOC    = 29, "LOC",
-            QueryType::TXT => 16,
+    SRV    = 33, "SRV",
-            QueryType::AAAA => 28,
+    NAPTR  = 35, "NAPTR",
-            QueryType::SRV => 33,
+    OPT    = 41, "OPT",
-            QueryType::OPT => 41,
+    DS     = 43, "DS",
-            QueryType::DS => 43,
+    RRSIG  = 46, "RRSIG",
-            QueryType::RRSIG => 46,
+    NSEC   = 47, "NSEC",
-            QueryType::NSEC => 47,
+    DNSKEY = 48, "DNSKEY",
-            QueryType::DNSKEY => 48,
+    NSEC3  = 50, "NSEC3",
-            QueryType::NSEC3 => 50,
+    SVCB   = 64, "SVCB",
-            QueryType::HTTPS => 65,
+    HTTPS  = 65, "HTTPS",
-        }
-    }
-
-    pub fn from_num(num: u16) -> QueryType {
-        match num {
-            1 => QueryType::A,
-            2 => QueryType::NS,
-            5 => QueryType::CNAME,
-            6 => QueryType::SOA,
-            12 => QueryType::PTR,
-            15 => QueryType::MX,
-            16 => QueryType::TXT,
-            28 => QueryType::AAAA,
-            33 => QueryType::SRV,
-            41 => QueryType::OPT,
-            43 => QueryType::DS,
-            46 => QueryType::RRSIG,
-            47 => QueryType::NSEC,
-            48 => QueryType::DNSKEY,
-            50 => QueryType::NSEC3,
-            65 => QueryType::HTTPS,
-            _ => QueryType::UNKNOWN(num),
-        }
-    }
-
-    pub fn as_str(&self) -> &'static str {
-        match self {
-            QueryType::A => "A",
-            QueryType::NS => "NS",
-            QueryType::CNAME => "CNAME",
-            QueryType::SOA => "SOA",
-            QueryType::PTR => "PTR",
-            QueryType::MX => "MX",
-            QueryType::TXT => "TXT",
-            QueryType::AAAA => "AAAA",
-            QueryType::SRV => "SRV",
-            QueryType::OPT => "OPT",
-            QueryType::DS => "DS",
-            QueryType::RRSIG => "RRSIG",
-            QueryType::NSEC => "NSEC",
-            QueryType::DNSKEY => "DNSKEY",
-            QueryType::NSEC3 => "NSEC3",
-            QueryType::HTTPS => "HTTPS",
-            QueryType::UNKNOWN(_) => "UNKNOWN",
-        }
-    }
-
-    pub fn parse_str(s: &str) -> Option<QueryType> {
-        match s.to_ascii_uppercase().as_str() {
-            "A" => Some(QueryType::A),
-            "NS" => Some(QueryType::NS),
-            "CNAME" => Some(QueryType::CNAME),
-            "SOA" => Some(QueryType::SOA),
-            "PTR" => Some(QueryType::PTR),
-            "MX" => Some(QueryType::MX),
-            "TXT" => Some(QueryType::TXT),
-            "AAAA" => Some(QueryType::AAAA),
-            "SRV" => Some(QueryType::SRV),
-            "DS" => Some(QueryType::DS),
-            "RRSIG" => Some(QueryType::RRSIG),
-            "DNSKEY" => Some(QueryType::DNSKEY),
-            "NSEC" => Some(QueryType::NSEC),
-            "NSEC3" => Some(QueryType::NSEC3),
-            "HTTPS" => Some(QueryType::HTTPS),
-            _ => None,
-        }
-    }
 }
 
 #[derive(Debug, Clone, PartialEq, Eq)]

src/relay.rs

@@ -0,0 +1,342 @@
+//! ODoH relay (RFC 9230 §5) — the forward-without-reading half of the
+//! protocol. Runs `numa relay`; skips all resolver initialisation (no port
+//! 53, no cache, no recursion, no dashboard). The relay never reads the
+//! HPKE-sealed payload and keeps no per-request logs — only aggregate
+//! counters.
+
+use std::net::SocketAddr;
+use std::sync::atomic::{AtomicU64, Ordering};
+use std::sync::Arc;
+use std::time::Duration;
+
+use axum::body::Bytes;
+use axum::extract::{DefaultBodyLimit, Query, State};
+use axum::http::{header, StatusCode};
+use axum::response::{IntoResponse, Response};
+use axum::routing::{get, post};
+use axum::Router;
+use log::{error, info};
+use serde::Deserialize;
+use tokio::net::TcpListener;
+
+use crate::forward::build_https_client_with_pool;
+use crate::odoh::ODOH_CONTENT_TYPE;
+use crate::Result;
+
+/// Cap on the opaque body we accept from a client. ODoH envelopes are
+/// ~100–300 bytes in practice; anything larger is malformed or hostile.
+const MAX_BODY_BYTES: usize = 4 * 1024;
+
+/// Cap on the body we read back from the target before streaming to client.
+/// Slightly larger: target responses carry DNS answers plus HPKE overhead.
+const MAX_TARGET_RESPONSE_BYTES: usize = 8 * 1024;
+
+/// Covers the whole client-to-target round trip — not just `.send()` — so a
+/// slow-drip target can't hang a worker indefinitely after headers arrive.
+const TARGET_REQUEST_TIMEOUT: Duration = Duration::from_secs(5);
+
+/// The relay hits many distinct target hosts on behalf of clients. A
+/// per-host idle pool of 4 keeps warm TLS connections available for concurrent
+/// fan-out without blowing up memory on a small VPS.
+const RELAY_POOL_PER_HOST: usize = 4;
+
+#[derive(Deserialize)]
+struct RelayParams {
+    targethost: String,
+    targetpath: String,
+}
+
+struct RelayState {
+    client: reqwest::Client,
+    total_requests: AtomicU64,
+    forwarded_ok: AtomicU64,
+    forwarded_err: AtomicU64,
+    rejected_bad_request: AtomicU64,
+}
+
+impl RelayState {
+    fn new() -> Arc<Self> {
+        Arc::new(RelayState {
+            client: build_https_client_with_pool(RELAY_POOL_PER_HOST),
+            total_requests: AtomicU64::new(0),
+            forwarded_ok: AtomicU64::new(0),
+            forwarded_err: AtomicU64::new(0),
+            rejected_bad_request: AtomicU64::new(0),
+        })
+    }
+}
+
+/// `DefaultBodyLimit` overrides axum's 2 MiB default so hostile clients
+/// can't force the relay to buffer multi-MB bodies before our own cap.
+fn build_app(state: Arc<RelayState>) -> Router {
+    Router::new()
+        .route("/relay", post(handle_relay))
+        .layer(DefaultBodyLimit::max(MAX_BODY_BYTES))
+        .route("/health", get(handle_health))
+        .with_state(state)
+}
+
+pub async fn run(addr: SocketAddr) -> Result<()> {
+    let app = build_app(RelayState::new());
+    let listener = TcpListener::bind(addr).await?;
+    info!("ODoH relay listening on {}", addr);
+    axum::serve(listener, app).await?;
+    Ok(())
+}
+
+async fn handle_health(State(state): State<Arc<RelayState>>) -> impl IntoResponse {
+    let body = format!(
+        "ok\ntotal {}\nforwarded_ok {}\nforwarded_err {}\nrejected_bad_request {}\n",
+        state.total_requests.load(Ordering::Relaxed),
+        state.forwarded_ok.load(Ordering::Relaxed),
+        state.forwarded_err.load(Ordering::Relaxed),
+        state.rejected_bad_request.load(Ordering::Relaxed),
+    );
+    (
+        StatusCode::OK,
+        [(header::CONTENT_TYPE, "text/plain; charset=utf-8")],
+        body,
+    )
+}
+
+async fn handle_relay(
+    State(state): State<Arc<RelayState>>,
+    Query(params): Query<RelayParams>,
+    headers: axum::http::HeaderMap,
+    body: Bytes,
+) -> Response {
+    state.total_requests.fetch_add(1, Ordering::Relaxed);
+
+    if !content_type_matches(&headers, ODOH_CONTENT_TYPE) {
+        state.rejected_bad_request.fetch_add(1, Ordering::Relaxed);
+        return (
+            StatusCode::UNSUPPORTED_MEDIA_TYPE,
+            "expected application/oblivious-dns-message",
+        )
+            .into_response();
+    }
+
+    if body.len() > MAX_BODY_BYTES {
+        state.rejected_bad_request.fetch_add(1, Ordering::Relaxed);
+        return (StatusCode::PAYLOAD_TOO_LARGE, "body exceeds 4 KiB cap").into_response();
+    }
+
+    if !is_valid_hostname(&params.targethost) || !params.targetpath.starts_with('/') {
+        state.rejected_bad_request.fetch_add(1, Ordering::Relaxed);
+        return (StatusCode::BAD_REQUEST, "invalid targethost or targetpath").into_response();
+    }
+
+    let target_url = format!("https://{}{}", params.targethost, params.targetpath);
+    match forward_to_target(&state.client, &target_url, body).await {
+        Ok((status, resp_body)) => {
+            state.forwarded_ok.fetch_add(1, Ordering::Relaxed);
+            (
+                status,
+                [(header::CONTENT_TYPE, ODOH_CONTENT_TYPE)],
+                resp_body,
+            )
+                .into_response()
+        }
+        Err(e) => {
+            // Log the underlying reason for operators; don't leak reqwest
+            // internals (which can reveal the target's TLS config, IP, etc.)
+            // back to arbitrary clients.
+            error!("relay forward to {} failed: {}", target_url, e);
+            state.forwarded_err.fetch_add(1, Ordering::Relaxed);
+            (StatusCode::BAD_GATEWAY, "target unreachable").into_response()
+        }
+    }
+}
+
+async fn forward_to_target(
+    client: &reqwest::Client,
+    url: &str,
+    body: Bytes,
+) -> Result<(StatusCode, Bytes)> {
+    let response = tokio::time::timeout(TARGET_REQUEST_TIMEOUT, async {
+        let resp = client
+            .post(url)
+            .header(header::CONTENT_TYPE, ODOH_CONTENT_TYPE)
+            .header(header::ACCEPT, ODOH_CONTENT_TYPE)
+            .body(body)
+            .send()
+            .await?;
+        let status = StatusCode::from_u16(resp.status().as_u16())?;
+        let resp_body = resp.bytes().await?;
+        Ok::<_, crate::Error>((status, resp_body))
+    })
+    .await
+    .map_err(|_| "timed out talking to target")??;
+
+    if response.1.len() > MAX_TARGET_RESPONSE_BYTES {
+        return Err("target response exceeds cap".into());
+    }
+    Ok(response)
+}
+
+fn content_type_matches(headers: &axum::http::HeaderMap, expected: &str) -> bool {
+    headers
+        .get(header::CONTENT_TYPE)
+        .and_then(|v| v.to_str().ok())
+        .map(|ct| ct.split(';').next().unwrap_or("").trim() == expected)
+        .unwrap_or(false)
+}
+
+/// Strict DNS-hostname validator, aimed at closing the SSRF surface a naive
+/// `contains('.')` check leaves open (e.g. `example.com@internal.host`,
+/// `evil.com/../admin`). Requires ASCII letters/digits/dot/dash, at least
+/// one dot, no leading dot or dash, length ≤ 253 per RFC 1035.
+fn is_valid_hostname(h: &str) -> bool {
+    if h.is_empty() || h.len() > 253 || !h.contains('.') {
+        return false;
+    }
+    if h.starts_with('.') || h.starts_with('-') || h.ends_with('.') || h.ends_with('-') {
+        return false;
+    }
+    h.chars()
+        .all(|c| c.is_ascii_alphanumeric() || c == '.' || c == '-')
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    async fn spawn_relay() -> (SocketAddr, Arc<RelayState>) {
+        let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
+        let addr = listener.local_addr().unwrap();
+
+        let state = RelayState::new();
+        let app = build_app(state.clone());
+
+        tokio::spawn(async move {
+            let _ = axum::serve(listener, app).await;
+        });
+        (addr, state)
+    }
+
+    #[tokio::test]
+    async fn rejects_missing_content_type() {
+        let (addr, state) = spawn_relay().await;
+        let client = reqwest::Client::new();
+        let resp = client
+            .post(format!(
+                "http://{}/relay?targethost=odoh.example.com&targetpath=/dns-query",
+                addr
+            ))
+            .body("body")
+            .send()
+            .await
+            .unwrap();
+        assert_eq!(resp.status(), reqwest::StatusCode::UNSUPPORTED_MEDIA_TYPE);
+        assert_eq!(state.rejected_bad_request.load(Ordering::Relaxed), 1);
+    }
+
+    #[tokio::test]
+    async fn rejects_oversized_body() {
+        let (addr, _state) = spawn_relay().await;
+        let big = vec![0u8; MAX_BODY_BYTES + 1];
+        let client = reqwest::Client::new();
+        let resp = client
+            .post(format!(
+                "http://{}/relay?targethost=odoh.example.com&targetpath=/dns-query",
+                addr
+            ))
+            .header(header::CONTENT_TYPE, ODOH_CONTENT_TYPE)
+            .body(big)
+            .send()
+            .await
+            .unwrap();
+        // axum's DefaultBodyLimit rejects before our handler runs, so the
+        // counter doesn't increment — but the status code proves the layer
+        // enforced the cap. Either status is acceptable evidence.
+        assert!(matches!(
+            resp.status(),
+            reqwest::StatusCode::PAYLOAD_TOO_LARGE | reqwest::StatusCode::BAD_REQUEST
+        ));
+    }
+
+    #[tokio::test]
+    async fn rejects_targethost_without_dot() {
+        let (addr, state) = spawn_relay().await;
+        let client = reqwest::Client::new();
+        let resp = client
+            .post(format!(
+                "http://{}/relay?targethost=localhost&targetpath=/dns-query",
+                addr
+            ))
+            .header(header::CONTENT_TYPE, ODOH_CONTENT_TYPE)
+            .body("body")
+            .send()
+            .await
+            .unwrap();
+        assert_eq!(resp.status(), reqwest::StatusCode::BAD_REQUEST);
+        assert_eq!(state.rejected_bad_request.load(Ordering::Relaxed), 1);
+    }
+
+    #[tokio::test]
+    async fn rejects_userinfo_ssrf_attempt() {
+        let (addr, state) = spawn_relay().await;
+        let client = reqwest::Client::new();
+        // The naive contains('.') check would let this through and reqwest
+        // would route to `internal.host` using `evil.com` as userinfo.
+        let resp = client
+            .post(format!(
+                "http://{}/relay?targethost=evil.com@internal.host&targetpath=/dns-query",
+                addr
+            ))
+            .header(header::CONTENT_TYPE, ODOH_CONTENT_TYPE)
+            .body("body")
+            .send()
+            .await
+            .unwrap();
+        assert_eq!(resp.status(), reqwest::StatusCode::BAD_REQUEST);
+        assert_eq!(state.rejected_bad_request.load(Ordering::Relaxed), 1);
+    }
+
+    #[tokio::test]
+    async fn rejects_targetpath_without_leading_slash() {
+        let (addr, state) = spawn_relay().await;
+        let client = reqwest::Client::new();
+        let resp = client
+            .post(format!(
+                "http://{}/relay?targethost=odoh.example.com&targetpath=dns-query",
+                addr
+            ))
+            .header(header::CONTENT_TYPE, ODOH_CONTENT_TYPE)
+            .body("body")
+            .send()
+            .await
+            .unwrap();
+        assert_eq!(resp.status(), reqwest::StatusCode::BAD_REQUEST);
+        assert_eq!(state.rejected_bad_request.load(Ordering::Relaxed), 1);
+    }
+
+    #[tokio::test]
+    async fn health_endpoint_reports_counters() {
+        let (addr, _state) = spawn_relay().await;
+        let client = reqwest::Client::new();
+        let resp = client
+            .get(format!("http://{}/health", addr))
+            .send()
+            .await
+            .unwrap();
+        assert_eq!(resp.status(), reqwest::StatusCode::OK);
+        let body = resp.text().await.unwrap();
+        assert!(body.contains("ok\n"));
+        assert!(body.contains("forwarded_ok 0"));
+    }
+
+    #[test]
+    fn hostname_validator_accepts_and_rejects() {
+        assert!(is_valid_hostname("odoh.cloudflare-dns.com"));
+        assert!(is_valid_hostname("a.b"));
+        assert!(!is_valid_hostname(""));
+        assert!(!is_valid_hostname("localhost"));
+        assert!(!is_valid_hostname(".leading.dot"));
+        assert!(!is_valid_hostname("trailing.dot."));
+        assert!(!is_valid_hostname("-leading.dash"));
+        assert!(!is_valid_hostname("evil.com@internal.host"));
+        assert!(!is_valid_hostname("evil.com/../admin"));
+        assert!(!is_valid_hostname(&"a".repeat(254)));
+    }
+}

src/serve.rs

@@ -0,0 +1,698 @@
+//! The main DNS-server runtime.
+//!
+//! Extracted from `main.rs` so both the interactive CLI entry and the
+//! Windows service dispatcher (`windows_service` module) can drive the
+//! same startup/serve loop.
+
+use std::net::SocketAddr;
+use std::sync::{Arc, Mutex, RwLock};
+use std::time::Duration;
+
+use arc_swap::ArcSwap;
+use log::{error, info};
+use tokio::net::UdpSocket;
+
+use crate::blocklist::{download_blocklists, parse_blocklist, BlocklistStore};
+use crate::bootstrap_resolver::NumaResolver;
+use crate::buffer::BytePacketBuffer;
+use crate::cache::DnsCache;
+use crate::config::{build_zone_map, load_config, ConfigLoad};
+use crate::ctx::{handle_query, ServerCtx};
+use crate::forward::{
+    build_https_client_with_resolver, parse_upstream_list, Upstream, UpstreamPool,
+};
+use crate::odoh::OdohConfigCache;
+use crate::override_store::OverrideStore;
+use crate::query_log::QueryLog;
+use crate::service_store::ServiceStore;
+use crate::stats::{ServerStats, Transport};
+use crate::system_dns::discover_system_dns;
+
+const QUAD9_IP: &str = "9.9.9.9";
+const DOH_FALLBACK: &str = "https://9.9.9.9/dns-query";
+
+/// Boot the DNS server and run until the UDP listener errors out.
+pub async fn run(config_path: String) -> crate::Result<()> {
+    let ConfigLoad {
+        config,
+        path: resolved_config_path,
+        found: config_found,
+    } = load_config(&config_path)?;
+
+    // Discover system DNS in a single pass (upstream + forwarding rules)
+    let system_dns = discover_system_dns();
+
+    let root_hints = crate::recursive::parse_root_hints(&config.upstream.root_hints);
+
+    let recursive_pool = || {
+        let dummy = UpstreamPool::new(vec![Upstream::Udp("0.0.0.0:0".parse().unwrap())], vec![]);
+        (dummy, "recursive (root hints)".to_string())
+    };
+
+    // Routes numa-originated HTTPS (DoH upstream, ODoH relay/target, blocklist
+    // CDN) away from the system resolver so lookups don't loop back through
+    // numa when it's its own system DNS.
+    // See `docs/implementation/bootstrap-resolver.md`.
+    let resolver_overrides = match config.upstream.mode {
+        crate::config::UpstreamMode::Odoh => config
+            .upstream
+            .odoh_upstream()
+            .map(|o| o.host_ip_overrides())
+            .unwrap_or_default(),
+        _ => std::collections::BTreeMap::new(),
+    };
+    let bootstrap_resolver: Arc<NumaResolver> = Arc::new(NumaResolver::new(
+        &config.upstream.fallback,
+        resolver_overrides,
+    ));
+
+    let (resolved_mode, upstream_auto, pool, upstream_label) = match config.upstream.mode {
+        crate::config::UpstreamMode::Auto => {
+            info!("auto mode: probing recursive resolution...");
+            if crate::recursive::probe_recursive(&root_hints).await {
+                info!("recursive probe succeeded — self-sovereign mode");
+                let (pool, label) = recursive_pool();
+                (crate::config::UpstreamMode::Recursive, false, pool, label)
+            } else {
+                log::warn!("recursive probe failed — falling back to Quad9 DoH");
+                let client = build_https_client_with_resolver(1, Some(bootstrap_resolver.clone()));
+                let url = DOH_FALLBACK.to_string();
+                let label = url.clone();
+                let pool = UpstreamPool::new(vec![Upstream::Doh { url, client }], vec![]);
+                (crate::config::UpstreamMode::Forward, false, pool, label)
+            }
+        }
+        crate::config::UpstreamMode::Recursive => {
+            let (pool, label) = recursive_pool();
+            (crate::config::UpstreamMode::Recursive, false, pool, label)
+        }
+        crate::config::UpstreamMode::Forward => {
+            let addrs = if config.upstream.address.is_empty() {
+                let detected = system_dns
+                    .default_upstream
+                    .or_else(crate::system_dns::detect_dhcp_dns)
+                    .unwrap_or_else(|| {
+                        info!("could not detect system DNS, falling back to Quad9 DoH");
+                        DOH_FALLBACK.to_string()
+                    });
+                vec![detected]
+            } else {
+                config.upstream.address.clone()
+            };
+
+            let primary = parse_upstream_list(
+                &addrs,
+                config.upstream.port,
+                Some(bootstrap_resolver.clone()),
+            )?;
+            let fallback = parse_upstream_list(
+                &config.upstream.fallback,
+                config.upstream.port,
+                Some(bootstrap_resolver.clone()),
+            )?;
+
+            let pool = UpstreamPool::new(primary, fallback);
+            let label = pool.label();
+            (
+                crate::config::UpstreamMode::Forward,
+                config.upstream.address.is_empty(),
+                pool,
+                label,
+            )
+        }
+        crate::config::UpstreamMode::Odoh => {
+            let odoh = config.upstream.odoh_upstream()?;
+            let client = build_https_client_with_resolver(1, Some(bootstrap_resolver.clone()));
+            let target_config = Arc::new(OdohConfigCache::new(
+                odoh.target_host.clone(),
+                client.clone(),
+            ));
+            let primary = vec![Upstream::Odoh {
+                relay_url: odoh.relay_url,
+                target_path: odoh.target_path,
+                client,
+                target_config,
+            }];
+            let fallback = if odoh.strict {
+                Vec::new()
+            } else {
+                parse_upstream_list(
+                    &config.upstream.fallback,
+                    config.upstream.port,
+                    Some(bootstrap_resolver.clone()),
+                )?
+            };
+            let pool = UpstreamPool::new(primary, fallback);
+            let label = pool.label();
+            (crate::config::UpstreamMode::Odoh, false, pool, label)
+        }
+    };
+    let api_port = config.server.api_port;
+
+    let mut blocklist = BlocklistStore::new();
+    for domain in &config.blocking.allowlist {
+        blocklist.add_to_allowlist(domain);
+    }
+    if !config.blocking.enabled {
+        blocklist.set_enabled(false);
+    }
+
+    // Build service store: config services + persisted user services
+    let mut service_store = ServiceStore::new();
+    service_store.insert_from_config("numa", config.server.api_port, Vec::new());
+    for svc in &config.services {
+        service_store.insert_from_config(&svc.name, svc.target_port, svc.routes.clone());
+    }
+    service_store.load_persisted();
+
+    for fwd in &config.forwarding {
+        for suffix in &fwd.suffix {
+            info!(
+                "forwarding .{} to {} (config rule)",
+                suffix,
+                fwd.upstream.join(", ")
+            );
+        }
+    }
+    let forwarding_rules =
+        crate::config::merge_forwarding_rules(&config.forwarding, system_dns.forwarding_rules)?;
+
+    // Resolve data_dir from config, falling back to the platform default.
+    // Used for TLS CA storage below and stored on ServerCtx for runtime use.
+    let resolved_data_dir = config
+        .server
+        .data_dir
+        .clone()
+        .unwrap_or_else(crate::data_dir);
+
+    // Build initial TLS config before ServerCtx (so ArcSwap is ready at construction)
+    let initial_tls = if config.proxy.enabled && config.proxy.tls_port > 0 {
+        let service_names = service_store.names();
+        match crate::tls::build_tls_config(
+            &config.proxy.tld,
+            &service_names,
+            Vec::new(),
+            &resolved_data_dir,
+        ) {
+            Ok(tls_config) => Some(ArcSwap::from(tls_config)),
+            Err(e) => {
+                if let Some(advisory) = crate::tls::try_data_dir_advisory(&e, &resolved_data_dir) {
+                    eprint!("{}", advisory);
+                } else {
+                    log::warn!("TLS setup failed, HTTPS proxy disabled: {}", e);
+                }
+                None
+            }
+        }
+    } else {
+        None
+    };
+
+    let doh_enabled = initial_tls.is_some();
+    let health_meta = crate::health::HealthMeta::build(
+        &resolved_data_dir,
+        config.dot.enabled,
+        config.dot.port,
+        config.mobile.port,
+        config.dnssec.enabled,
+        resolved_mode == crate::config::UpstreamMode::Recursive,
+        config.lan.enabled,
+        config.blocking.enabled,
+        doh_enabled,
+    );
+
+    let ca_pem = std::fs::read_to_string(resolved_data_dir.join("ca.pem")).ok();
+
+    let socket = match UdpSocket::bind(&config.server.bind_addr).await {
+        Ok(s) => s,
+        Err(e) => {
+            if let Some(advisory) =
+                crate::system_dns::try_port53_advisory(&config.server.bind_addr, &e)
+            {
+                eprint!("{}", advisory);
+                std::process::exit(1);
+            }
+            return Err(e.into());
+        }
+    };
+
+    let ctx = Arc::new(ServerCtx {
+        socket,
+        zone_map: build_zone_map(&config.zones)?,
+        cache: RwLock::new(DnsCache::new(
+            config.cache.max_entries,
+            config.cache.min_ttl,
+            config.cache.max_ttl,
+        )),
+        refreshing: Mutex::new(std::collections::HashSet::new()),
+        stats: Mutex::new(ServerStats::new()),
+        overrides: RwLock::new(OverrideStore::new()),
+        blocklist: RwLock::new(blocklist),
+        query_log: Mutex::new(QueryLog::new(1000)),
+        services: Mutex::new(service_store),
+        lan_peers: Mutex::new(crate::lan::PeerStore::new(config.lan.peer_timeout_secs)),
+        forwarding_rules,
+        upstream_pool: Mutex::new(pool),
+        upstream_auto,
+        upstream_port: config.upstream.port,
+        lan_ip: Mutex::new(crate::lan::detect_lan_ip().unwrap_or(std::net::Ipv4Addr::LOCALHOST)),
+        timeout: Duration::from_millis(config.upstream.timeout_ms),
+        hedge_delay: resolved_mode.hedge_delay(config.upstream.hedge_ms),
+        proxy_tld_suffix: if config.proxy.tld.is_empty() {
+            String::new()
+        } else {
+            format!(".{}", config.proxy.tld)
+        },
+        proxy_tld: config.proxy.tld.clone(),
+        lan_enabled: config.lan.enabled,
+        config_path: resolved_config_path,
+        config_found,
+        config_dir: crate::config_dir(),
+        data_dir: resolved_data_dir,
+        tls_config: initial_tls,
+        upstream_mode: resolved_mode,
+        root_hints,
+        srtt: std::sync::RwLock::new(crate::srtt::SrttCache::new(config.upstream.srtt)),
+        inflight: std::sync::Mutex::new(std::collections::HashMap::new()),
+        dnssec_enabled: config.dnssec.enabled,
+        dnssec_strict: config.dnssec.strict,
+        health_meta,
+        ca_pem,
+        mobile_enabled: config.mobile.enabled,
+        mobile_port: config.mobile.port,
+        filter_aaaa: config.server.filter_aaaa,
+    });
+
+    let zone_count: usize = ctx.zone_map.values().map(|m| m.len()).sum();
+    // Build banner rows, then size the box to fit the longest value
+    let api_url = format!("http://localhost:{}", api_port);
+    let proxy_label = if config.proxy.enabled {
+        if config.proxy.tls_port > 0 {
+            Some(format!(
+                "http://:{} https://:{}",
+                config.proxy.port, config.proxy.tls_port
+            ))
+        } else {
+            Some(format!(
+                "http://*.{} on :{}",
+                config.proxy.tld, config.proxy.port
+            ))
+        }
+    } else {
+        None
+    };
+    let config_label = if ctx.config_found {
+        ctx.config_path.clone()
+    } else {
+        format!("{} (defaults)", ctx.config_path)
+    };
+    let data_label = ctx.data_dir.display().to_string();
+    let services_label = ctx.config_dir.join("services.json").display().to_string();
+
+    // label (10) + value + padding (2) = inner width; minimum 40 for the title row
+    let val_w = [
+        config.server.bind_addr.len(),
+        api_url.len(),
+        upstream_label.len(),
+        config_label.len(),
+        data_label.len(),
+        services_label.len(),
+    ]
+    .into_iter()
+    .chain(proxy_label.as_ref().map(|s| s.len()))
+    .max()
+    .unwrap_or(30);
+    let w = (val_w + 12).max(42); // 10 label + 2 padding, min 42 for title
+
+    let o = "\x1b[38;2;192;98;58m"; // orange
+    let g = "\x1b[38;2;107;124;78m"; // green
+    let d = "\x1b[38;2;163;152;136m"; // dim
+    let r = "\x1b[0m"; // reset
+    let b = "\x1b[1;38;2;192;98;58m"; // bold orange
+    let it = "\x1b[3;38;2;163;152;136m"; // italic dim
+
+    let bar_top = "═".repeat(w);
+    let bar_mid = "─".repeat(w);
+    let row = |label: &str, color: &str, value: &str| {
+        eprintln!(
+            "{o}  ║{r}  {color}{:<9}{r} {:<vw$}{o}║{r}",
+            label,
+            value,
+            vw = w - 12
+        );
+    };
+
+    // Title row: center within the box
+    let title = format!(
+        "{b}NUMA{r}  {it}DNS that governs itself{r}  {d}v{}{r}",
+        env!("CARGO_PKG_VERSION")
+    );
+    // The title contains ANSI codes; visible length is ~38 chars. Pad to fill the box.
+    let title_visible_len = 4 + 2 + 24 + 2 + 1 + env!("CARGO_PKG_VERSION").len() + 1;
+    let title_pad = w.saturating_sub(title_visible_len);
+    eprintln!("\n{o}  ╔{bar_top}╗{r}");
+    eprint!("{o}  ║{r} {title}");
+    eprintln!("{}{o}║{r}", " ".repeat(title_pad));
+    eprintln!("{o}  ╠{bar_top}╣{r}");
+    row("DNS", g, &config.server.bind_addr);
+    row("API", g, &api_url);
+    row("Dashboard", g, &api_url);
+    row(
+        "Upstream",
+        g,
+        if ctx.upstream_mode == crate::config::UpstreamMode::Recursive {
+            "recursive (root hints)"
+        } else {
+            &upstream_label
+        },
+    );
+    row("Zones", g, &format!("{} records", zone_count));
+    row(
+        "Cache",
+        g,
+        &format!("max {} entries", config.cache.max_entries),
+    );
+    if !config.cache.warm.is_empty() {
+        row("Warm", g, &format!("{} domains", config.cache.warm.len()));
+    }
+    row(
+        "Blocking",
+        g,
+        &if config.blocking.enabled {
+            format!("{} lists", config.blocking.lists.len())
+        } else {
+            "disabled".to_string()
+        },
+    );
+    if let Some(ref label) = proxy_label {
+        row("Proxy", g, label);
+        if config.proxy.bind_addr == "127.0.0.1" {
+            let y = "\x1b[38;2;204;176;59m"; // yellow
+            row(
+                "",
+                y,
+                &format!(
+                    "⚠ proxy on 127.0.0.1 — .{} not LAN reachable",
+                    config.proxy.tld
+                ),
+            );
+        }
+    }
+    if config.dot.enabled {
+        row("DoT", g, &format!("tls://:{}", config.dot.port));
+    }
+    if doh_enabled {
+        row(
+            "DoH",
+            g,
+            &format!("https://:{}/dns-query", config.proxy.tls_port),
+        );
+    }
+    if config.lan.enabled {
+        row("LAN", g, "mDNS (_numa._tcp.local)");
+    }
+    if !ctx.forwarding_rules.is_empty() {
+        row(
+            "Routing",
+            g,
+            &format!("{} conditional rules", ctx.forwarding_rules.len()),
+        );
+    }
+    eprintln!("{o}  ╠{bar_mid}╣{r}");
+    row("Config", d, &config_label);
+    row("Data", d, &data_label);
+    row("Services", d, &services_label);
+    eprintln!("{o}  ╚{bar_top}╝{r}\n");
+
+    info!(
+        "numa listening on {}, upstream {}, {} zone records, cache max {}, API on port {}",
+        config.server.bind_addr, upstream_label, zone_count, config.cache.max_entries, api_port,
+    );
+
+    // Download blocklists on startup
+    let blocklist_lists = config.blocking.lists.clone();
+    let refresh_hours = config.blocking.refresh_hours;
+    if config.blocking.enabled && !blocklist_lists.is_empty() {
+        let bl_ctx = Arc::clone(&ctx);
+        let bl_lists = blocklist_lists.clone();
+        let bl_resolver = bootstrap_resolver.clone();
+        tokio::spawn(async move {
+            load_blocklists(&bl_ctx, &bl_lists, Some(bl_resolver.clone())).await;
+
+            // Periodic refresh
+            let mut interval = tokio::time::interval(Duration::from_secs(refresh_hours * 3600));
+            interval.tick().await; // skip immediate tick
+            loop {
+                interval.tick().await;
+                info!("refreshing blocklists...");
+                load_blocklists(&bl_ctx, &bl_lists, Some(bl_resolver.clone())).await;
+            }
+        });
+    }
+
+    // Prime TLD cache (recursive mode only)
+    if ctx.upstream_mode == crate::config::UpstreamMode::Recursive {
+        let prime_ctx = Arc::clone(&ctx);
+        let prime_tlds = config.upstream.prime_tlds;
+        tokio::spawn(async move {
+            crate::recursive::prime_tld_cache(
+                &prime_ctx.cache,
+                &prime_ctx.root_hints,
+                &prime_tlds,
+                &prime_ctx.srtt,
+            )
+            .await;
+        });
+    }
+
+    // Spawn cache warming for user-configured domains
+    if !config.cache.warm.is_empty() {
+        let warm_ctx = Arc::clone(&ctx);
+        let warm_domains = config.cache.warm.clone();
+        tokio::spawn(async move {
+            cache_warm_loop(warm_ctx, warm_domains).await;
+        });
+    }
+
+    // Spawn DoH connection keepalive — prevents idle TLS teardown
+    {
+        let keepalive_ctx = Arc::clone(&ctx);
+        tokio::spawn(async move {
+            doh_keepalive_loop(keepalive_ctx).await;
+        });
+    }
+
+    // Spawn HTTP API server
+    let api_ctx = Arc::clone(&ctx);
+    let api_addr: SocketAddr = format!("{}:{}", config.server.api_bind_addr, api_port).parse()?;
+    tokio::spawn(async move {
+        let app = crate::api::router(api_ctx);
+        let listener = tokio::net::TcpListener::bind(api_addr).await.unwrap();
+        info!("HTTP API listening on {}", api_addr);
+        axum::serve(listener, app).await.unwrap();
+    });
+
+    // Spawn Mobile API listener (read-only subset for iOS/Android companion
+    // apps, LAN-bound by default so phones can reach it). Only idempotent
+    // GETs; no state-mutating routes are exposed here regardless of
+    // the main API's bind address.
+    if config.mobile.enabled {
+        let mobile_ctx = Arc::clone(&ctx);
+        let mobile_bind = config.mobile.bind_addr.clone();
+        let mobile_port = config.mobile.port;
+        tokio::spawn(async move {
+            if let Err(e) = crate::mobile_api::start(mobile_ctx, mobile_bind, mobile_port).await {
+                log::warn!("Mobile API listener failed: {}", e);
+            }
+        });
+    }
+
+    let proxy_bind: std::net::Ipv4Addr = config
+        .proxy
+        .bind_addr
+        .parse()
+        .unwrap_or(std::net::Ipv4Addr::LOCALHOST);
+
+    // Spawn HTTP reverse proxy for .numa domains
+    if config.proxy.enabled {
+        let proxy_ctx = Arc::clone(&ctx);
+        let proxy_port = config.proxy.port;
+        tokio::spawn(async move {
+            crate::proxy::start_proxy(proxy_ctx, proxy_port, proxy_bind).await;
+        });
+    }
+
+    // Spawn HTTPS reverse proxy with TLS termination
+    if config.proxy.enabled && config.proxy.tls_port > 0 && ctx.tls_config.is_some() {
+        let proxy_ctx = Arc::clone(&ctx);
+        let tls_port = config.proxy.tls_port;
+        tokio::spawn(async move {
+            crate::proxy::start_proxy_tls(proxy_ctx, tls_port, proxy_bind).await;
+        });
+    }
+
+    // Spawn network change watcher (upstream re-detection, LAN IP update, peer flush)
+    {
+        let watch_ctx = Arc::clone(&ctx);
+        tokio::spawn(async move {
+            network_watch_loop(watch_ctx).await;
+        });
+    }
+
+    // Spawn LAN service discovery
+    if config.lan.enabled {
+        let lan_ctx = Arc::clone(&ctx);
+        let lan_config = config.lan.clone();
+        tokio::spawn(async move {
+            crate::lan::start_lan_discovery(lan_ctx, &lan_config).await;
+        });
+    }
+
+    // Spawn DNS-over-TLS listener (RFC 7858)
+    if config.dot.enabled {
+        let dot_ctx = Arc::clone(&ctx);
+        let dot_config = config.dot.clone();
+        tokio::spawn(async move {
+            crate::dot::start_dot(dot_ctx, &dot_config).await;
+        });
+    }
+
+    // UDP DNS listener
+    #[allow(clippy::infinite_loop)]
+    loop {
+        let mut buffer = BytePacketBuffer::new();
+        let (len, src_addr) = match ctx.socket.recv_from(&mut buffer.buf).await {
+            Ok(r) => r,
+            Err(e) if e.kind() == std::io::ErrorKind::ConnectionReset => {
+                // Windows delivers ICMP port-unreachable as ConnectionReset on UDP sockets
+                continue;
+            }
+            Err(e) => return Err(e.into()),
+        };
+        let ctx = Arc::clone(&ctx);
+        tokio::spawn(async move {
+            if let Err(e) = handle_query(buffer, len, src_addr, &ctx, Transport::Udp).await {
+                error!("{} | HANDLER ERROR | {}", src_addr, e);
+            }
+        });
+    }
+}
+
+async fn network_watch_loop(ctx: Arc<ServerCtx>) {
+    let mut tick: u64 = 0;
+
+    let mut interval = tokio::time::interval(Duration::from_secs(5));
+    interval.tick().await; // skip immediate tick
+
+    loop {
+        interval.tick().await;
+        tick += 1;
+        let mut changed = false;
+
+        // Check LAN IP change (every 5s — cheap, one UDP socket call)
+        if let Some(new_ip) = crate::lan::detect_lan_ip() {
+            let mut current_ip = ctx.lan_ip.lock().unwrap();
+            if new_ip != *current_ip {
+                info!("LAN IP changed: {} → {}", current_ip, new_ip);
+                *current_ip = new_ip;
+                changed = true;
+                crate::recursive::reset_udp_state();
+            }
+        }
+
+        // Re-detect upstream every 30s or on LAN IP change (auto-detect only)
+        if ctx.upstream_auto && (changed || tick.is_multiple_of(6)) {
+            let dns_info = crate::system_dns::discover_system_dns();
+            let new_addr = dns_info
+                .default_upstream
+                .or_else(crate::system_dns::detect_dhcp_dns)
+                .unwrap_or_else(|| QUAD9_IP.to_string());
+            let mut pool = ctx.upstream_pool.lock().unwrap();
+            if pool.maybe_update_primary(&new_addr, ctx.upstream_port) {
+                info!("upstream changed → {}", pool.label());
+                changed = true;
+            }
+        }
+
+        // Flush stale LAN peers on any network change
+        if changed {
+            ctx.lan_peers.lock().unwrap().clear();
+            info!("flushed LAN peers after network change");
+        }
+
+        // Re-probe UDP every 5 minutes when disabled
+        if tick.is_multiple_of(60) {
+            crate::recursive::probe_udp(&ctx.root_hints).await;
+        }
+    }
+}
+
+async fn load_blocklists(ctx: &ServerCtx, lists: &[String], resolver: Option<Arc<NumaResolver>>) {
+    let downloaded = download_blocklists(lists, resolver).await;
+
+    // Parse outside the lock to avoid blocking DNS queries during parse (~100ms)
+    let mut all_domains = std::collections::HashSet::new();
+    let mut sources = Vec::new();
+    for (source, text) in &downloaded {
+        let domains = parse_blocklist(text);
+        info!("blocklist: {} domains from {}", domains.len(), source);
+        all_domains.extend(domains);
+        sources.push(source.clone());
+    }
+    let total = all_domains.len();
+
+    // Swap under lock — sub-microsecond
+    ctx.blocklist
+        .write()
+        .unwrap()
+        .swap_domains(all_domains, sources);
+    info!(
+        "blocking enabled: {} unique domains from {} lists",
+        total,
+        downloaded.len()
+    );
+}
+
+async fn warm_domain(ctx: &ServerCtx, domain: &str) {
+    for qtype in [
+        crate::question::QueryType::A,
+        crate::question::QueryType::AAAA,
+    ] {
+        crate::ctx::refresh_entry(ctx, domain, qtype).await;
+    }
+}
+
+async fn doh_keepalive_loop(ctx: Arc<ServerCtx>) {
+    // First tick fires immediately so we surface bootstrap-resolver failures
+    // (unreachable Quad9/Cloudflare, blocked :53, bad upstream hostname) in
+    // the startup logs instead of on the first client query.
+    let mut interval = tokio::time::interval(Duration::from_secs(25));
+    loop {
+        interval.tick().await;
+        let pool = ctx.upstream_pool.lock().unwrap().clone();
+        if let Some(upstream) = pool.preferred() {
+            crate::forward::keepalive_doh(upstream).await;
+        }
+    }
+}
+
+async fn cache_warm_loop(ctx: Arc<ServerCtx>, domains: Vec<String>) {
+    tokio::time::sleep(Duration::from_secs(2)).await;
+
+    for domain in &domains {
+        warm_domain(&ctx, domain).await;
+    }
+    info!("cache warm: {} domains resolved at startup", domains.len());
+
+    let mut interval = tokio::time::interval(Duration::from_secs(30));
+    interval.tick().await;
+    loop {
+        interval.tick().await;
+        for domain in &domains {
+            let refresh = ctx.cache.read().unwrap().needs_warm(domain);
+            if refresh {
+                warm_domain(&ctx, domain).await;
+            }
+        }
+    }
+}

src/stats.rs

@@ -90,6 +90,7 @@ fn linux_rss() -> usize {
 pub struct ServerStats {
     queries_total: u64,
     queries_forwarded: u64,
+    queries_upstream: u64,
     queries_recursive: u64,
     queries_coalesced: u64,
     queries_cached: u64,
@@ -101,6 +102,10 @@ pub struct ServerStats {
     transport_tcp: u64,
     transport_dot: u64,
     transport_doh: u64,
+    upstream_transport_udp: u64,
+    upstream_transport_doh: u64,
+    upstream_transport_dot: u64,
+    upstream_transport_odoh: u64,
     started_at: Instant,
 }
 
@@ -123,11 +128,39 @@ impl Transport {
     }
 }
 
+/// Wire protocol used for a forwarded upstream call. Orthogonal to
+/// `QueryPath`: the path answers "where the answer came from"; this answers
+/// "over what wire we spoke to the forwarder." Callers pass
+/// `Option<UpstreamTransport>` — `None` for resolutions that never touched
+/// a forwarder (cache/local/blocked) or for recursive mode, which has its
+/// own counter via `QueryPath::Recursive`.
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum UpstreamTransport {
+    Udp,
+    Doh,
+    Dot,
+    Odoh,
+}
+
+impl UpstreamTransport {
+    pub fn as_str(&self) -> &'static str {
+        match self {
+            UpstreamTransport::Udp => "UDP",
+            UpstreamTransport::Doh => "DOH",
+            UpstreamTransport::Dot => "DOT",
+            UpstreamTransport::Odoh => "ODOH",
+        }
+    }
+}
+
 #[derive(Clone, Copy, Debug, PartialEq, Eq)]
 pub enum QueryPath {
     Local,
     Cached,
+    /// Matched a `[[forwarding]]` suffix rule.
     Forwarded,
+    /// Resolved via the default `[upstream]` pool (no suffix match).
+    Upstream,
     Recursive,
     Coalesced,
     Blocked,
@@ -141,6 +174,7 @@ impl QueryPath {
             QueryPath::Local => "LOCAL",
             QueryPath::Cached => "CACHED",
             QueryPath::Forwarded => "FORWARD",
+            QueryPath::Upstream => "UPSTREAM",
             QueryPath::Recursive => "RECURSIVE",
             QueryPath::Coalesced => "COALESCED",
             QueryPath::Blocked => "BLOCKED",
@@ -156,6 +190,8 @@ impl QueryPath {
             Some(QueryPath::Cached)
         } else if s.eq_ignore_ascii_case("FORWARD") {
             Some(QueryPath::Forwarded)
+        } else if s.eq_ignore_ascii_case("UPSTREAM") {
+            Some(QueryPath::Upstream)
         } else if s.eq_ignore_ascii_case("RECURSIVE") {
             Some(QueryPath::Recursive)
         } else if s.eq_ignore_ascii_case("COALESCED") {
@@ -183,6 +219,7 @@ impl ServerStats {
         ServerStats {
             queries_total: 0,
             queries_forwarded: 0,
+            queries_upstream: 0,
             queries_recursive: 0,
             queries_coalesced: 0,
             queries_cached: 0,
@@ -194,16 +231,26 @@ impl ServerStats {
             transport_tcp: 0,
             transport_dot: 0,
             transport_doh: 0,
+            upstream_transport_udp: 0,
+            upstream_transport_doh: 0,
+            upstream_transport_dot: 0,
+            upstream_transport_odoh: 0,
             started_at: Instant::now(),
         }
     }
 
-    pub fn record(&mut self, path: QueryPath, transport: Transport) -> u64 {
+    pub fn record(
+        &mut self,
+        path: QueryPath,
+        transport: Transport,
+        upstream_transport: Option<UpstreamTransport>,
+    ) -> u64 {
         self.queries_total += 1;
         match path {
             QueryPath::Local => self.queries_local += 1,
             QueryPath::Cached => self.queries_cached += 1,
             QueryPath::Forwarded => self.queries_forwarded += 1,
+            QueryPath::Upstream => self.queries_upstream += 1,
             QueryPath::Recursive => self.queries_recursive += 1,
             QueryPath::Coalesced => self.queries_coalesced += 1,
             QueryPath::Blocked => self.queries_blocked += 1,
@@ -216,6 +263,14 @@ impl ServerStats {
             Transport::Dot => self.transport_dot += 1,
             Transport::Doh => self.transport_doh += 1,
         }
+        if let Some(ut) = upstream_transport {
+            match ut {
+                UpstreamTransport::Udp => self.upstream_transport_udp += 1,
+                UpstreamTransport::Doh => self.upstream_transport_doh += 1,
+                UpstreamTransport::Dot => self.upstream_transport_dot += 1,
+                UpstreamTransport::Odoh => self.upstream_transport_odoh += 1,
+            }
+        }
         self.queries_total
     }
 
@@ -232,6 +287,7 @@ impl ServerStats {
             uptime_secs: self.uptime_secs(),
             total: self.queries_total,
             forwarded: self.queries_forwarded,
+            upstream: self.queries_upstream,
             recursive: self.queries_recursive,
             coalesced: self.queries_coalesced,
             cached: self.queries_cached,
@@ -243,6 +299,10 @@ impl ServerStats {
             transport_tcp: self.transport_tcp,
             transport_dot: self.transport_dot,
             transport_doh: self.transport_doh,
+            upstream_transport_udp: self.upstream_transport_udp,
+            upstream_transport_doh: self.upstream_transport_doh,
+            upstream_transport_dot: self.upstream_transport_dot,
+            upstream_transport_odoh: self.upstream_transport_odoh,
         }
     }
 
@@ -253,10 +313,11 @@ impl ServerStats {
         let secs = uptime.as_secs() % 60;
 
         log::info!(
-            "STATS | uptime {}h{}m{}s | total {} | fwd {} | recursive {} | coalesced {} | cached {} | local {} | override {} | blocked {} | errors {}",
+            "STATS | uptime {}h{}m{}s | total {} | fwd {} | upstream {} | recursive {} | coalesced {} | cached {} | local {} | override {} | blocked {} | errors {} | up-udp {} | up-doh {} | up-dot {} | up-odoh {}",
             hours, mins, secs,
             self.queries_total,
             self.queries_forwarded,
+            self.queries_upstream,
             self.queries_recursive,
             self.queries_coalesced,
             self.queries_cached,
@@ -264,6 +325,10 @@ impl ServerStats {
             self.queries_overridden,
             self.queries_blocked,
             self.upstream_errors,
+            self.upstream_transport_udp,
+            self.upstream_transport_doh,
+            self.upstream_transport_dot,
+            self.upstream_transport_odoh,
         );
     }
 }
@@ -272,6 +337,7 @@ pub struct StatsSnapshot {
     pub uptime_secs: u64,
     pub total: u64,
     pub forwarded: u64,
+    pub upstream: u64,
     pub recursive: u64,
     pub coalesced: u64,
     pub cached: u64,
@@ -283,4 +349,8 @@ pub struct StatsSnapshot {
     pub transport_tcp: u64,
     pub transport_dot: u64,
     pub transport_doh: u64,
+    pub upstream_transport_udp: u64,
+    pub upstream_transport_doh: u64,
+    pub upstream_transport_dot: u64,
+    pub upstream_transport_odoh: u64,
 }

src/svcb.rs

@@ -0,0 +1,179 @@
+//! Minimal SVCB/HTTPS (RFC 9460) RDATA parser — just enough to strip
+//! the `ipv6hint` SvcParam. Used by the `filter_aaaa` feature so
+//! HTTPS-record-aware clients (Chrome ≥103, Firefox, Safari) don't
+//! receive v6 address hints on IPv4-only networks.
+
+/// SvcParamKey = 6 (RFC 9460 §14.3.2).
+const IPV6_HINT_KEY: u16 = 6;
+
+/// Strip the `ipv6hint` SvcParam from an HTTPS/SVCB RDATA blob.
+///
+/// Returns `Some(new_rdata)` if `ipv6hint` was present and removed.
+/// Returns `None` if the record had no `ipv6hint`, or if the RDATA
+/// couldn't be parsed — in both cases the caller should keep the
+/// original bytes untouched.
+///
+/// SVCB RDATA (RFC 9460 §2.2):
+///   SvcPriority (u16)
+///   TargetName  (uncompressed DNS name — labels terminated by 0 octet)
+///   SvcParams   (series of {u16 key, u16 len, opaque[len] value}, sorted by key)
+pub fn strip_ipv6hint(rdata: &[u8]) -> Option<Vec<u8>> {
+    if rdata.len() < 2 {
+        return None;
+    }
+    let mut pos = 2;
+
+    // TargetName — uncompressed per RFC 9460 §2.2
+    loop {
+        let len = *rdata.get(pos)? as usize;
+        pos += 1;
+        if len == 0 {
+            break;
+        }
+        if len & 0xC0 != 0 {
+            // Pointer: forbidden in SVCB but defend against a broken upstream.
+            return None;
+        }
+        pos = pos.checked_add(len)?;
+        if pos > rdata.len() {
+            return None;
+        }
+    }
+
+    // Scan params once to decide whether we need to rebuild.
+    let params_start = pos;
+    let mut scan = pos;
+    let mut has_ipv6hint = false;
+    while scan < rdata.len() {
+        if scan + 4 > rdata.len() {
+            return None;
+        }
+        let key = u16::from_be_bytes([rdata[scan], rdata[scan + 1]]);
+        let vlen = u16::from_be_bytes([rdata[scan + 2], rdata[scan + 3]]) as usize;
+        let end = scan.checked_add(4)?.checked_add(vlen)?;
+        if end > rdata.len() {
+            return None;
+        }
+        if key == IPV6_HINT_KEY {
+            has_ipv6hint = true;
+        }
+        scan = end;
+    }
+    if scan != rdata.len() || !has_ipv6hint {
+        return None;
+    }
+
+    // Rebuild without ipv6hint, preserving param order (RFC 9460 requires
+    // ascending key order, which we preserve by filtering in place).
+    let mut out = Vec::with_capacity(rdata.len());
+    out.extend_from_slice(&rdata[..params_start]);
+    let mut pos = params_start;
+    while pos < rdata.len() {
+        let key = u16::from_be_bytes([rdata[pos], rdata[pos + 1]]);
+        let vlen = u16::from_be_bytes([rdata[pos + 2], rdata[pos + 3]]) as usize;
+        let end = pos + 4 + vlen;
+        if key != IPV6_HINT_KEY {
+            out.extend_from_slice(&rdata[pos..end]);
+        }
+        pos = end;
+    }
+    Some(out)
+}
+
+/// Build an SVCB RDATA blob from a priority, target labels, and
+/// (key, value) param pairs. Shared by `svcb` unit tests and `ctx`
+/// pipeline tests that need to seed the cache with a synthetic HTTPS RR.
+#[cfg(test)]
+pub(crate) fn build_rdata(priority: u16, target: &[&str], params: &[(u16, Vec<u8>)]) -> Vec<u8> {
+    let mut out = Vec::new();
+    out.extend_from_slice(&priority.to_be_bytes());
+    for label in target {
+        out.push(label.len() as u8);
+        out.extend_from_slice(label.as_bytes());
+    }
+    out.push(0);
+    for (key, value) in params {
+        out.extend_from_slice(&key.to_be_bytes());
+        out.extend_from_slice(&(value.len() as u16).to_be_bytes());
+        out.extend_from_slice(value);
+    }
+    out
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn alpn_h3() -> (u16, Vec<u8>) {
+        // alpn = ["h3"]: one length-prefixed ALPN id
+        (1, vec![0x02, b'h', b'3'])
+    }
+
+    fn ipv4hint_single() -> (u16, Vec<u8>) {
+        (4, vec![93, 184, 216, 34])
+    }
+
+    fn ipv6hint_single() -> (u16, Vec<u8>) {
+        // 2606:4700::1
+        (
+            6,
+            vec![
+                0x26, 0x06, 0x47, 0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x01,
+            ],
+        )
+    }
+
+    #[test]
+    fn strips_ipv6hint_and_keeps_other_params() {
+        let rdata = build_rdata(1, &[], &[alpn_h3(), ipv4hint_single(), ipv6hint_single()]);
+        let stripped = strip_ipv6hint(&rdata).expect("ipv6hint present → stripped");
+        let expected = build_rdata(1, &[], &[alpn_h3(), ipv4hint_single()]);
+        assert_eq!(stripped, expected);
+    }
+
+    #[test]
+    fn no_ipv6hint_returns_none() {
+        let rdata = build_rdata(1, &[], &[alpn_h3(), ipv4hint_single()]);
+        assert!(strip_ipv6hint(&rdata).is_none());
+    }
+
+    #[test]
+    fn alias_mode_empty_params_returns_none() {
+        let rdata = build_rdata(0, &["example", "com"], &[]);
+        assert!(strip_ipv6hint(&rdata).is_none());
+    }
+
+    #[test]
+    fn only_ipv6hint_yields_empty_param_section() {
+        let rdata = build_rdata(1, &[], &[ipv6hint_single()]);
+        let stripped = strip_ipv6hint(&rdata).expect("ipv6hint present → stripped");
+        let expected = build_rdata(1, &[], &[]);
+        assert_eq!(stripped, expected);
+    }
+
+    #[test]
+    fn preserves_target_name() {
+        let rdata = build_rdata(1, &["svc", "example", "net"], &[ipv6hint_single()]);
+        let stripped = strip_ipv6hint(&rdata).unwrap();
+        assert!(stripped.starts_with(&[0x00, 0x01])); // priority
+        assert_eq!(&stripped[2..6], b"\x03svc");
+    }
+
+    #[test]
+    fn truncated_rdata_returns_none() {
+        // Priority only, no target terminator.
+        assert!(strip_ipv6hint(&[0, 1, 3, b'c', b'o', b'm']).is_none());
+    }
+
+    #[test]
+    fn empty_input_returns_none() {
+        assert!(strip_ipv6hint(&[]).is_none());
+    }
+
+    #[test]
+    fn param_length_overflow_returns_none() {
+        // key=6, length=0xFFFF but value is short — malformed.
+        let rdata = vec![0, 1, 0, 0, 6, 0xFF, 0xFF, 0, 1, 2];
+        assert!(strip_ipv6hint(&rdata).is_none());
+    }
+}

src/system_dns.rs

@@ -2,7 +2,9 @@ use std::net::SocketAddr;
 
 use log::info;
 
+#[cfg(any(target_os = "macos", target_os = "linux"))]
 use crate::forward::Upstream;
+use crate::forward::UpstreamPool;
 
 fn print_recursive_hint() {
     let is_recursive = crate::config::load_config("numa.toml")
@@ -20,15 +22,15 @@ fn is_loopback_or_stub(addr: &str) -> bool {
 }
 
 /// A conditional forwarding rule: domains matching `suffix` are forwarded to `upstream`.
-#[derive(Debug, Clone)]
+#[derive(Clone)]
 pub struct ForwardingRule {
     pub suffix: String,
     dot_suffix: String, // pre-computed ".suffix" for zero-alloc matching
-    pub upstream: Upstream,
+    pub upstream: UpstreamPool,
 }
 
 impl ForwardingRule {
-    pub fn new(suffix: String, upstream: Upstream) -> Self {
+    pub fn new(suffix: String, upstream: UpstreamPool) -> Self {
         let dot_suffix = format!(".{}", suffix);
         Self {
             suffix,
@@ -211,12 +213,13 @@ fn discover_macos() -> SystemDnsInfo {
     }
 
     // Sort longest suffix first for most-specific matching
-    rules.sort_by(|a, b| b.suffix.len().cmp(&a.suffix.len()));
+    rules.sort_by_key(|r| std::cmp::Reverse(r.suffix.len()));
 
     for rule in &rules {
         info!(
             "auto-discovered forwarding: *.{} -> {}",
-            rule.suffix, rule.upstream
+            rule.suffix,
+            rule.upstream.label()
         );
     }
     if rules.is_empty() {
@@ -235,7 +238,8 @@ fn discover_macos() -> SystemDnsInfo {
 #[cfg(any(target_os = "macos", target_os = "linux"))]
 fn make_rule(domain: &str, nameserver: &str) -> Option<ForwardingRule> {
     let addr = crate::forward::parse_upstream_addr(nameserver, 53).ok()?;
-    Some(ForwardingRule::new(domain.to_string(), Upstream::Udp(addr)))
+    let pool = UpstreamPool::new(vec![Upstream::Udp(addr)], vec![]);
+    Some(ForwardingRule::new(domain.to_string(), pool))
 }
 
 #[cfg(target_os = "linux")]
@@ -572,7 +576,7 @@ fn windows_backup_path() -> std::path::PathBuf {
 
 #[cfg(windows)]
 fn disable_dnscache() -> Result<bool, String> {
-    // Check if Dnscache is running (it holds port 53 at kernel level)
+    // Check if Dnscache is running (it can hold port 53)
     let output = std::process::Command::new("sc")
         .args(["query", "Dnscache"])
         .output()
@@ -603,8 +607,16 @@ fn disable_dnscache() -> Result<bool, String> {
         return Err("failed to disable Dnscache via registry (run as Administrator?)".into());
     }
 
-    eprintln!("  Dnscache disabled. A reboot is required to free port 53.");
+    // Dnscache is disabled for next boot. Check whether port 53 is
-    Ok(true)
+    // actually blocked right now — on many Windows configurations
+    // Dnscache doesn't bind port 53 even while running.
+    let port_blocked = std::net::UdpSocket::bind("127.0.0.1:53").is_err();
+    if port_blocked {
+        eprintln!("  Dnscache disabled. A reboot is required to free port 53.");
+    } else {
+        eprintln!("  Dnscache disabled. Port 53 is free.");
+    }
+    Ok(port_blocked)
 }
 
 #[cfg(windows)]
@@ -671,6 +683,83 @@ fn install_windows() -> Result<(), String> {
         std::fs::write(&path, json).map_err(|e| format!("failed to write backup: {}", e))?;
     }
 
+    // On re-install, stop the running service first so the binary can be
+    // overwritten and port 53 is released for the Dnscache probe.
+    if is_service_registered() {
+        eprintln!("  Stopping existing service...");
+        stop_service_scm();
+    }
+
+    let needs_reboot = disable_dnscache()?;
+
+    // Copy the binary to a stable path under ProgramData and register it
+    // as a real Windows service (SCM-managed, boot-time, auto-restart).
+    let service_exe = install_service_binary()?;
+    register_service_scm(&service_exe)?;
+
+    if needs_reboot {
+        // Dnscache still holds port 53 until reboot. Do NOT redirect DNS
+        // yet — nothing is listening on 127.0.0.1:53, so redirecting now
+        // would kill DNS. The service will call redirect_dns_to_localhost()
+        // on its first startup after reboot.
+    } else {
+        redirect_dns_with_interfaces(&interfaces)?;
+
+        match start_service_scm() {
+            Ok(_) => eprintln!("  Service started."),
+            Err(e) => eprintln!(
+                "  warning: service registered but could not start now: {}",
+                e
+            ),
+        }
+    }
+
+    eprintln!();
+    if !has_useful_existing {
+        eprintln!("  Original DNS saved to {}", path.display());
+    }
+    eprintln!("  Run 'numa uninstall' to restore.\n");
+    if needs_reboot {
+        eprintln!("  *** Reboot required. Numa will start automatically. ***\n");
+    } else {
+        eprintln!("  Numa is running.\n");
+    }
+    print_recursive_hint();
+    Ok(())
+}
+
+/// Stable install location for the service binary. SCM keeps a handle to
+/// this path; the user's Downloads folder (where `current_exe()` points at
+/// install time) is not durable.
+#[cfg(windows)]
+fn windows_service_exe_path() -> std::path::PathBuf {
+    crate::data_dir().join("bin").join("numa.exe")
+}
+
+/// Run `sc.exe` with the given args and return its merged stdout/stderr on
+/// failure. `sc` emits errors on stdout (not stderr) on Windows, so the
+/// caller reads stdout to format a useful error.
+#[cfg(windows)]
+fn run_sc(args: &[&str]) -> Result<std::process::Output, String> {
+    let out = std::process::Command::new("sc")
+        .args(args)
+        .output()
+        .map_err(|e| format!("failed to run sc {}: {}", args.first().unwrap_or(&""), e))?;
+    Ok(out)
+}
+
+/// Point all active network interfaces at 127.0.0.1 so Numa handles DNS.
+/// Called from the service on first boot after a reboot that freed Dnscache.
+#[cfg(windows)]
+pub fn redirect_dns_to_localhost() -> Result<(), String> {
+    let interfaces = get_windows_interfaces()?;
+    redirect_dns_with_interfaces(&interfaces)
+}
+
+#[cfg(windows)]
+fn redirect_dns_with_interfaces(
+    interfaces: &std::collections::HashMap<String, WindowsInterfaceDns>,
+) -> Result<(), String> {
     for name in interfaces.keys() {
         let status = std::process::Command::new("netsh")
             .args([
@@ -695,63 +784,184 @@ fn install_windows() -> Result<(), String> {
             );
         }
     }
-
-    let needs_reboot = disable_dnscache()?;
-    register_autostart();
-
-    eprintln!();
-    if !has_useful_existing {
-        eprintln!("  Original DNS saved to {}", path.display());
-    }
-    eprintln!("  Run 'numa uninstall' to restore.\n");
-    if needs_reboot {
-        eprintln!("  *** Reboot required. Numa will start automatically. ***\n");
-    } else {
-        eprintln!("  Numa will start automatically on next boot.\n");
-    }
-    print_recursive_hint();
     Ok(())
 }
 
-/// Register numa to auto-start on boot via registry Run key.
+/// Copy the currently-running binary to the service install location. SCM
+/// keeps a handle to this path, so it must be stable across user sessions.
 #[cfg(windows)]
-fn register_autostart() {
+fn install_service_binary() -> Result<std::path::PathBuf, String> {
-    let exe = std::env::current_exe()
+    let src = std::env::current_exe().map_err(|e| format!("current_exe(): {}", e))?;
-        .map(|p| p.to_string_lossy().to_string())
+    let dst = windows_service_exe_path();
-        .unwrap_or_else(|_| "numa".into());
+    if let Some(parent) = dst.parent() {
-    let _ = std::process::Command::new("reg")
+        std::fs::create_dir_all(parent)
-        .args([
+            .map_err(|e| format!("failed to create {}: {}", parent.display(), e))?;
-            "add",
+    }
-            "HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Run",
+    // Copy only if source and destination differ; running the binary from
-            "/v",
+    // its install location is a supported (re-install) case.
-            "Numa",
+    if src != dst {
-            "/t",
+        std::fs::copy(&src, &dst).map_err(|e| {
-            "REG_SZ",
+            format!(
-            "/d",
+                "failed to copy {} -> {}: {}",
-            &exe,
+                src.display(),
-            "/f",
+                dst.display(),
-        ])
+                e
-        .status();
+            )
-    eprintln!("  Registered auto-start on boot.");
+        })?;
+    }
+    Ok(dst)
 }
 
-/// Remove numa auto-start registry key.
+/// Remove the service binary on uninstall. Ignore failures — the service
+/// is already deleted; a leftover file in ProgramData is not a hard error.
 #[cfg(windows)]
-fn remove_autostart() {
+fn remove_service_binary() {
-    let _ = std::process::Command::new("reg")
+    let _ = std::fs::remove_file(windows_service_exe_path());
-        .args([
+}
-            "delete",
+
-            "HKLM\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Run",
+/// Register numa with the Service Control Manager, boot-time auto-start,
-            "/v",
+/// LocalSystem context, with a failure policy of restart-after-5s.
-            "Numa",
+#[cfg(windows)]
-            "/f",
+fn register_service_scm(exe: &std::path::Path) -> Result<(), String> {
-        ])
+    let bin_path = format!("\"{}\" --service", exe.display());
-        .status();
+    let name = crate::windows_service::SERVICE_NAME;
+
+    // sc.exe uses a leading space as its `name= value` delimiter; the space
+    // after `=` is mandatory.
+    let create = run_sc(&[
+        "create",
+        name,
+        "binPath=",
+        &bin_path,
+        "DisplayName=",
+        "Numa DNS",
+        "start=",
+        "auto",
+        "obj=",
+        "LocalSystem",
+    ])?;
+    if !create.status.success() {
+        let out = String::from_utf8_lossy(&create.stdout);
+        // "service already exists" is 1073 — treat as idempotent success.
+        if !out.contains("1073") {
+            return Err(format!("sc create failed: {}", out.trim()));
+        }
+    }
+
+    let _ = run_sc(&[
+        "description",
+        name,
+        "Self-sovereign DNS resolver (ad blocking, DoH/DoT, local zones).",
+    ]);
+
+    // Restart on crash: 5s, 5s, 10s; reset failure counter after 60s.
+    let _ = run_sc(&[
+        "failure",
+        name,
+        "reset=",
+        "60",
+        "actions=",
+        "restart/5000/restart/5000/restart/10000",
+    ]);
+
+    eprintln!("  Registered service '{}' (boot-time).", name);
+    Ok(())
+}
+
+/// Start the service. Safe to call on a freshly-registered service — SCM
+/// will fail with 1056 ("already running") or 1058 ("disabled") and we
+/// return the underlying error string rather than masking it.
+#[cfg(windows)]
+fn start_service_scm() -> Result<(), String> {
+    let out = run_sc(&["start", crate::windows_service::SERVICE_NAME])?;
+    if !out.status.success() {
+        let text = String::from_utf8_lossy(&out.stdout);
+        if text.contains("1056") {
+            return Ok(()); // already running
+        }
+        return Err(format!("sc start failed: {}", text.trim()));
+    }
+    Ok(())
+}
+
+/// Stop the service and wait for it to fully exit. Idempotent —
+/// already-stopped or missing service is not an error.
+#[cfg(windows)]
+fn stop_service_scm() {
+    let name = crate::windows_service::SERVICE_NAME;
+    let _ = run_sc(&["stop", name]);
+    // Wait up to 10s for the service to reach STOPPED state so the
+    // binary file handle is released before we try to overwrite it.
+    for _ in 0..20 {
+        if let Ok(out) = run_sc(&["query", name]) {
+            let text = String::from_utf8_lossy(&out.stdout);
+            if text.contains("STOPPED") || text.contains("1060") {
+                return;
+            }
+        }
+        std::thread::sleep(std::time::Duration::from_millis(500));
+    }
+    eprintln!("  warning: service did not stop within 10s");
+}
+
+/// Remove the service from SCM. Idempotent — see `stop_service_scm`.
+#[cfg(windows)]
+fn delete_service_scm() {
+    if let Err(e) = run_sc(&["delete", crate::windows_service::SERVICE_NAME]) {
+        log::warn!("sc delete failed: {}", e);
+    }
+}
+
+/// Check whether the service is registered with SCM (regardless of state).
+#[cfg(windows)]
+fn is_service_registered() -> bool {
+    run_sc(&["query", crate::windows_service::SERVICE_NAME])
+        .map(|o| parse_sc_registered(o.status.success(), &String::from_utf8_lossy(&o.stdout)))
+        .unwrap_or(false)
+}
+
+/// Parse `sc query` output to determine if a service is registered.
+/// Extracted for testability — the actual `sc` call is in `is_service_registered`.
+#[cfg(any(windows, test))]
+fn parse_sc_registered(exit_success: bool, stdout: &str) -> bool {
+    if exit_success {
+        return true;
+    }
+    // Error 1060 = "The specified service does not exist as an installed service."
+    !stdout.contains("1060")
+}
+
+/// Print service state from SCM.
+#[cfg(windows)]
+fn service_status_windows() -> Result<(), String> {
+    let out = run_sc(&["query", crate::windows_service::SERVICE_NAME])?;
+    let text = String::from_utf8_lossy(&out.stdout);
+    let display = parse_sc_state(&text);
+    eprintln!("  {}\n", display);
+    Ok(())
+}
+
+/// Parse the STATE line from `sc query` output. Returns a human-readable
+/// string like "STATE : 4 RUNNING" or "Service is not installed."
+#[cfg(any(windows, test))]
+fn parse_sc_state(sc_output: &str) -> String {
+    if sc_output.contains("1060") {
+        return "Service is not installed.".to_string();
+    }
+    sc_output
+        .lines()
+        .find(|l| l.contains("STATE"))
+        .map(|l| l.trim().to_string())
+        .unwrap_or_else(|| "unknown".to_string())
 }
 
 #[cfg(windows)]
 fn uninstall_windows() -> Result<(), String> {
-    remove_autostart();
+    // Stop + remove the service before touching DNS, so port 53 is released
+    // cleanly and the failure-restart policy doesn't resurrect it.
+    stop_service_scm();
+    delete_service_scm();
+    remove_service_binary();
     let path = windows_backup_path();
     let json = std::fs::read_to_string(&path)
         .map_err(|e| format!("no backup found at {}: {}", path.display(), e))?;
@@ -827,7 +1037,7 @@ fn uninstall_windows() -> Result<(), String> {
 pub fn match_forwarding_rule<'a>(
     domain: &str,
     rules: &'a [ForwardingRule],
-) -> Option<&'a Upstream> {
+) -> Option<&'a UpstreamPool> {
     for rule in rules {
         if domain == rule.suffix || domain.ends_with(&rule.dot_suffix) {
             return Some(&rule.upstream);
@@ -1048,6 +1258,62 @@ pub fn install_service() -> Result<(), String> {
     result
 }
 
+/// Start the service. If already installed, just starts it via the platform
+/// service manager. If not installed, falls through to a full install.
+pub fn start_service() -> Result<(), String> {
+    #[cfg(target_os = "macos")]
+    {
+        install_service()
+    }
+    #[cfg(target_os = "linux")]
+    {
+        install_service()
+    }
+    #[cfg(windows)]
+    {
+        if is_service_registered() {
+            start_service_scm()?;
+            eprintln!("  Service started.\n");
+            Ok(())
+        } else {
+            install_service()
+        }
+    }
+    #[cfg(not(any(target_os = "macos", target_os = "linux", windows)))]
+    {
+        Err("service start not supported on this OS".to_string())
+    }
+}
+
+/// Stop the service without uninstalling it.
+pub fn stop_service() -> Result<(), String> {
+    #[cfg(target_os = "macos")]
+    {
+        uninstall_service()
+    }
+    #[cfg(target_os = "linux")]
+    {
+        uninstall_service()
+    }
+    #[cfg(windows)]
+    {
+        let out = run_sc(&["stop", crate::windows_service::SERVICE_NAME])?;
+        if !out.status.success() {
+            let text = String::from_utf8_lossy(&out.stdout);
+            // 1062 = not started, 1060 = does not exist
+            if !text.contains("1062") && !text.contains("1060") {
+                return Err(format!("sc stop failed: {}", text.trim()));
+            }
+        }
+        eprintln!("  Service stopped.\n");
+        Ok(())
+    }
+    #[cfg(not(any(target_os = "macos", target_os = "linux", windows)))]
+    {
+        Err("service stop not supported on this OS".to_string())
+    }
+}
+
 /// Uninstall the Numa system service.
 pub fn uninstall_service() -> Result<(), String> {
     let _ = untrust_ca();
@@ -1117,7 +1383,14 @@ pub fn restart_service() -> Result<(), String> {
         eprintln!("  Service restarted → {}\n", version);
         Ok(())
     }
-    #[cfg(not(any(target_os = "macos", target_os = "linux")))]
+    #[cfg(windows)]
+    {
+        stop_service_scm();
+        start_service_scm()?;
+        eprintln!("  Service restarted.\n");
+        Ok(())
+    }
+    #[cfg(not(any(target_os = "macos", target_os = "linux", windows)))]
     {
         Err("service restart not supported on this OS".to_string())
     }
@@ -1133,13 +1406,17 @@ pub fn service_status() -> Result<(), String> {
     {
         service_status_linux()
     }
-    #[cfg(not(any(target_os = "macos", target_os = "linux")))]
+    #[cfg(windows)]
+    {
+        service_status_windows()
+    }
+    #[cfg(not(any(target_os = "macos", target_os = "linux", windows)))]
     {
         Err("service status not supported on this OS".to_string())
     }
 }
 
-#[cfg(any(target_os = "macos", target_os = "linux"))]
+#[cfg(target_os = "macos")]
 fn replace_exe_path(service: &str) -> Result<String, String> {
     let exe_path =
         std::env::current_exe().map_err(|e| format!("failed to get current exe: {}", e))?;
@@ -1387,10 +1664,78 @@ fn uninstall_linux() -> Result<(), String> {
     Ok(())
 }
 
+/// Fallback install location when current_exe() sits on a path the
+/// dynamic user cannot traverse (e.g. `/home/<user>/` mode 0700).
+#[cfg(target_os = "linux")]
+fn linux_service_exe_path() -> std::path::PathBuf {
+    std::path::PathBuf::from("/usr/local/bin/numa")
+}
+
+/// True iff every ancestor of `p` (excluding `/`) grants world-execute —
+/// i.e. the `DynamicUser=yes` service account can traverse the path and
+/// exec the binary without being in any group. Linuxbrew's
+/// `/home/linuxbrew` is 0755 (traversable, keep brew's path, upgrades
+/// via `brew` propagate). A build tree under `/home/<user>/` (0700) or
+/// `~/.cargo/bin/` is not (copy to /usr/local/bin so systemd can reach it).
+#[cfg(target_os = "linux")]
+fn path_world_traversable_linux(p: &std::path::Path) -> bool {
+    use std::os::unix::fs::PermissionsExt;
+    let mut current = p;
+    while let Some(parent) = current.parent() {
+        if parent.as_os_str().is_empty() || parent == std::path::Path::new("/") {
+            break;
+        }
+        match std::fs::metadata(parent) {
+            Ok(m) if m.permissions().mode() & 0o001 != 0 => {}
+            _ => return false,
+        }
+        current = parent;
+    }
+    true
+}
+
+#[cfg(target_os = "linux")]
+fn install_service_binary_linux() -> Result<std::path::PathBuf, String> {
+    let src = std::env::current_exe().map_err(|e| format!("current_exe(): {}", e))?;
+    if path_world_traversable_linux(&src) {
+        return Ok(src);
+    }
+    let dst = linux_service_exe_path();
+    if src == dst {
+        return Ok(dst);
+    }
+    if let Some(parent) = dst.parent() {
+        std::fs::create_dir_all(parent)
+            .map_err(|e| format!("failed to create {}: {}", parent.display(), e))?;
+    }
+    // Atomic replace via temp + rename. Plain copy fails with ETXTBSY when
+    // re-installing while the service is running the previous binary —
+    // rename swaps the path while the running process keeps the old inode.
+    let tmp = dst.with_extension("new");
+    std::fs::copy(&src, &tmp).map_err(|e| {
+        format!(
+            "failed to copy {} -> {}: {}",
+            src.display(),
+            tmp.display(),
+            e
+        )
+    })?;
+    std::fs::rename(&tmp, &dst).map_err(|e| {
+        let _ = std::fs::remove_file(&tmp);
+        format!(
+            "failed to rename {} -> {}: {}",
+            tmp.display(),
+            dst.display(),
+            e
+        )
+    })?;
+    Ok(dst)
+}
+
 #[cfg(target_os = "linux")]
 fn install_service_linux() -> Result<(), String> {
-    let unit = include_str!("../numa.service");
+    let exe = install_service_binary_linux()?;
-    let unit = replace_exe_path(unit)?;
+    let unit = include_str!("../numa.service").replace("{{exe_path}}", &exe.to_string_lossy());
     std::fs::write(SYSTEMD_UNIT, unit)
         .map_err(|e| format!("failed to write {}: {}", SYSTEMD_UNIT, e))?;
 
@@ -1402,7 +1747,9 @@ fn install_service_linux() -> Result<(), String> {
         eprintln!("  warning: failed to configure system DNS: {}", e);
     }
 
-    run_systemctl(&["start", "numa"])?;
+    // restart, not start: on re-install the service is already running
+    // the previous binary; restart picks up the new one.
+    run_systemctl(&["restart", "numa"])?;
 
     eprintln!("  Service installed and started.");
     eprintln!("  Numa will auto-start on boot and restart if killed.");
@@ -1718,22 +2065,25 @@ Wireless LAN adapter Wi-Fi:
     }
 
     #[test]
-    #[cfg(any(target_os = "macos", target_os = "linux"))]
+    fn install_templates_contain_exe_path_placeholder() {
-    fn replace_exe_path_substitutes_template() {
+        // Both files are substituted at install time — plist via
+        // replace_exe_path on macOS, numa.service via inline .replace
+        // in install_service_linux. Catch placeholder removal early.
         let plist = include_str!("../com.numa.dns.plist");
         let unit = include_str!("../numa.service");
-
         assert!(plist.contains("{{exe_path}}"), "plist missing placeholder");
         assert!(
             unit.contains("{{exe_path}}"),
             "unit file missing placeholder"
         );
+    }
 
+    #[test]
+    #[cfg(target_os = "macos")]
+    fn replace_exe_path_substitutes_template() {
+        let plist = include_str!("../com.numa.dns.plist");
         let result = replace_exe_path(plist).expect("replace_exe_path failed for plist");
         assert!(!result.contains("{{exe_path}}"));
-
-        let result = replace_exe_path(unit).expect("replace_exe_path failed for unit");
-        assert!(!result.contains("{{exe_path}}"));
     }
 
     #[test]
@@ -1867,4 +2217,57 @@ Wireless LAN adapter Wi-Fi:
         let err = std::io::Error::from(std::io::ErrorKind::AddrInUse);
         assert!(try_port53_advisory("not-an-address", &err).is_none());
     }
+
+    #[test]
+    fn sc_query_running_service_is_registered() {
+        assert!(parse_sc_registered(true, ""));
+    }
+
+    #[test]
+    fn sc_query_stopped_service_is_registered() {
+        let output = "SERVICE_NAME: Numa\n        TYPE: 10  WIN32_OWN\n        STATE: 1  STOPPED\n";
+        assert!(parse_sc_registered(true, output));
+    }
+
+    #[test]
+    fn sc_query_missing_service_not_registered() {
+        let output = "[SC] EnumQueryServicesStatus:OpenService FAILED 1060:\n\nThe specified service does not exist as an installed service.\n";
+        assert!(!parse_sc_registered(false, output));
+    }
+
+    #[test]
+    fn sc_query_other_error_assumes_registered() {
+        // Permission denied or other errors — don't assume unregistered.
+        let output = "[SC] OpenService FAILED 5:\n\nAccess is denied.\n";
+        assert!(parse_sc_registered(false, output));
+    }
+
+    #[test]
+    fn parse_sc_state_running() {
+        let output = "SERVICE_NAME: Numa\n        TYPE               : 10  WIN32_OWN_PROCESS\n        STATE              : 4  RUNNING\n        WIN32_EXIT_CODE    : 0\n";
+        assert!(parse_sc_state(output).contains("RUNNING"));
+    }
+
+    #[test]
+    fn parse_sc_state_stopped() {
+        let output = "SERVICE_NAME: Numa\n        TYPE               : 10  WIN32_OWN_PROCESS\n        STATE              : 1  STOPPED\n";
+        assert!(parse_sc_state(output).contains("STOPPED"));
+    }
+
+    #[test]
+    fn parse_sc_state_not_installed() {
+        let output = "[SC] EnumQueryServicesStatus:OpenService FAILED 1060:\n\n";
+        assert_eq!(parse_sc_state(output), "Service is not installed.");
+    }
+
+    #[test]
+    fn parse_sc_state_empty_output() {
+        assert_eq!(parse_sc_state(""), "unknown");
+    }
+
+    #[cfg(windows)]
+    #[test]
+    fn windows_config_dir_equals_data_dir() {
+        assert_eq!(crate::config_dir(), crate::data_dir());
+    }
 }

src/testutil.rs

@@ -63,6 +63,7 @@ pub async fn test_ctx() -> ServerCtx {
         ca_pem: None,
         mobile_enabled: false,
         mobile_port: 8765,
+        filter_aaaa: false,
     }
 }
 

src/windows_service.rs

@@ -0,0 +1,147 @@
+//! Windows service wrapper.
+//!
+//! Lets the `numa.exe` binary act as a real Windows service registered with
+//! the Service Control Manager (SCM). Invoked via `numa.exe --service` (the
+//! form that `sc create … binPath=` uses).
+//!
+//! Interactive runs (`numa.exe`, `numa.exe run`, `numa.exe install`) do not
+//! go through this module — they keep their existing console-attached
+//! behaviour.
+
+use std::ffi::OsString;
+use std::sync::mpsc;
+use std::time::Duration;
+
+use windows_service::service::{
+    ServiceControl, ServiceControlAccept, ServiceExitCode, ServiceState, ServiceStatus, ServiceType,
+};
+use windows_service::service_control_handler::{self, ServiceControlHandlerResult};
+use windows_service::{define_windows_service, service_dispatcher};
+
+pub const SERVICE_NAME: &str = "Numa";
+
+define_windows_service!(ffi_service_main, service_main);
+
+/// Entry point the SCM hands control to after `StartServiceCtrlDispatcherW`.
+/// Any panic here vanishes silently into the service host — log instead of
+/// unwrapping.
+fn service_main(_arguments: Vec<OsString>) {
+    if let Err(e) = run_service() {
+        log::error!("numa service exited with error: {:?}", e);
+    }
+}
+
+fn run_service() -> windows_service::Result<()> {
+    let (shutdown_tx, shutdown_rx) = mpsc::channel::<()>();
+
+    let event_handler = move |control_event| -> ServiceControlHandlerResult {
+        match control_event {
+            ServiceControl::Stop | ServiceControl::Shutdown => {
+                let _ = shutdown_tx.send(());
+                ServiceControlHandlerResult::NoError
+            }
+            ServiceControl::Interrogate => ServiceControlHandlerResult::NoError,
+            _ => ServiceControlHandlerResult::NotImplemented,
+        }
+    };
+
+    let status_handle = service_control_handler::register(SERVICE_NAME, event_handler)?;
+
+    status_handle.set_service_status(ServiceStatus {
+        service_type: ServiceType::OWN_PROCESS,
+        current_state: ServiceState::Running,
+        controls_accepted: ServiceControlAccept::STOP | ServiceControlAccept::SHUTDOWN,
+        exit_code: ServiceExitCode::Win32(0),
+        checkpoint: 0,
+        wait_hint: Duration::default(),
+        process_id: None,
+    })?;
+
+    // Spin up a multi-threaded tokio runtime and run the server on it. A
+    // dedicated thread runs the runtime so this function can return cleanly
+    // once the SCM tells us to stop — we can't block the dispatcher thread
+    // forever without preventing graceful shutdown.
+    let config_path = service_config_path();
+    let (server_done_tx, server_done_rx) = mpsc::channel::<()>();
+
+    let server_thread = std::thread::spawn(move || {
+        let runtime = match tokio::runtime::Builder::new_multi_thread()
+            .enable_all()
+            .build()
+        {
+            Ok(rt) => rt,
+            Err(e) => {
+                log::error!("failed to build tokio runtime: {}", e);
+                let _ = server_done_tx.send(());
+                return;
+            }
+        };
+
+        if let Err(e) = runtime.block_on(crate::serve::run(config_path)) {
+            log::error!("numa serve exited with error: {}", e);
+        }
+        let _ = server_done_tx.send(());
+    });
+
+    // Wait for the API to be ready, then ensure DNS points at localhost.
+    // On first boot after install (Dnscache was disabled, reboot freed
+    // port 53), the installer deferred the DNS redirect — do it now.
+    let api_up = (0..20).any(|i| {
+        if i > 0 {
+            std::thread::sleep(Duration::from_millis(500));
+        }
+        std::net::TcpStream::connect(("127.0.0.1", crate::config::DEFAULT_API_PORT)).is_ok()
+    });
+    if api_up {
+        if let Err(e) = crate::system_dns::redirect_dns_to_localhost() {
+            log::warn!("could not redirect DNS to localhost: {}", e);
+        }
+    } else {
+        log::error!("numa API did not start within 10s — DNS not redirected");
+    }
+
+    // Wait for either SCM stop or server termination.
+    loop {
+        if shutdown_rx.recv_timeout(Duration::from_millis(500)).is_ok() {
+            break;
+        }
+        if server_done_rx.try_recv().is_ok() {
+            break;
+        }
+    }
+
+    // The server's tokio runtime runs detached inside server_thread. Abandon
+    // it — the process is about to report Stopped and the SCM will terminate
+    // us if we linger. Future work: plumb a cancellation signal into
+    // serve::run() for a clean teardown of listeners and in-flight queries.
+    drop(server_thread);
+
+    status_handle.set_service_status(ServiceStatus {
+        service_type: ServiceType::OWN_PROCESS,
+        current_state: ServiceState::Stopped,
+        controls_accepted: ServiceControlAccept::empty(),
+        exit_code: ServiceExitCode::Win32(0),
+        checkpoint: 0,
+        wait_hint: Duration::default(),
+        process_id: None,
+    })?;
+
+    Ok(())
+}
+
+/// Hand control to the SCM dispatcher. Blocks until the service stops.
+/// Call only from the `--service` command path — interactive invocations
+/// will hang here waiting for an SCM that isn't talking to them.
+pub fn run_as_service() -> windows_service::Result<()> {
+    service_dispatcher::start(SERVICE_NAME, ffi_service_main)
+}
+
+/// Path to the config file used when running under SCM. SCM launches the
+/// service with SYSTEM's working directory (usually `C:\Windows\System32`),
+/// so a relative `numa.toml` lookup won't find anything meaningful.
+fn service_config_path() -> String {
+    crate::data_dir()
+        .join("numa.toml")
+        .to_string_lossy()
+        .into_owned()
+}

tests/docker/install-systemd.sh

@@ -0,0 +1,288 @@
+#!/usr/bin/env bash
+#
+# Systemd service install verification for the DynamicUser-based Linux
+# service unit. Stands up a privileged ubuntu:24.04 container with systemd
+# as PID 1, builds numa inside, runs three scenarios that CI does not:
+#
+#   A. Fresh install — every advertised port is not just bound but
+#      functional (DNS resolves on :53, TLS handshake validates against
+#      numa's CA on :853/:443, HTTP responds on :80, API on :5380).
+#   B. Upgrade from pre-drop layout (root-owned /var/lib/numa) preserves
+#      the CA fingerprint — users' browser-installed CA trust survives.
+#   C. Install from a 0700 source directory stages the binary under
+#      /usr/local/bin/numa and the service starts from there.
+#
+# First run is slow (~5-10 min): image pull + apt + cold cargo build.
+# Subsequent runs reuse cached docker volumes for cargo + target (~30s).
+#
+# Requirements: docker
+# Usage:        ./tests/docker/install-systemd.sh
+
+set -u
+set -o pipefail
+
+GREEN="\033[32m"; RED="\033[31m"; RESET="\033[0m"
+
+pass() { printf "  ${GREEN}PASS${RESET}: %s\n" "$*"; }
+fail() { printf "  ${RED}FAIL${RESET}: %s\n" "$*"; FAIL=1; }
+
+# ============================================================
+# Mode B: running inside the systemd container — run scenarios
+# ============================================================
+if [ "${NUMA_INSIDE:-}" = "1" ]; then
+    set +e  # assertions report pass/fail, don't abort
+    FAIL=0
+    NUMA=/work/target/release/numa
+
+    reset_state() {
+        "$NUMA" uninstall >/dev/null 2>&1 || true
+        systemctl reset-failed numa 2>/dev/null || true
+        rm -rf /var/lib/numa /var/lib/private/numa /etc/numa /home/builder /usr/local/bin/numa
+        systemctl daemon-reload 2>/dev/null || true
+    }
+
+    main_pid_user() {
+        local pid
+        pid=$(systemctl show -p MainPID --value numa)
+        [ "$pid" != "0" ] || { echo ""; return; }
+        ps -o user= -p "$pid" 2>/dev/null | tr -d ' '
+    }
+
+    # MainPID + user briefly stabilize after a fresh restart. Retry so we
+    # don't race the moment systemd flips the service to "active" vs when
+    # the forked numa process actually owns MainPID.
+    assert_nonroot() {
+        local pid user comm n=0
+        while [ $n -lt 20 ]; do
+            pid=$(systemctl show -p MainPID --value numa)
+            if [ "$pid" != "0" ]; then
+                comm=$(ps -o comm= -p "$pid" 2>/dev/null | tr -d ' ')
+                user=$(ps -o user= -p "$pid" 2>/dev/null | tr -d ' ')
+                if [ "$comm" = "numa" ]; then
+                    if [ "$user" = "root" ]; then
+                        fail "daemon runs as root (expected transient UID)"
+                    else
+                        pass "daemon runs as $user (non-root)"
+                    fi
+                    return
+                fi
+            fi
+            sleep 0.2
+            n=$((n + 1))
+        done
+        fail "numa MainPID did not settle (last: pid=${pid:-?} comm=${comm:-?} user=${user:-?})"
+    }
+
+    # Functional DNS check: just "port 53 bound" isn't enough — systemd-resolved
+    # listens on 127.0.0.53 and would satisfy a bind test. Retries for ~15s
+    # to tolerate cold-start upstream / blocklist warmup.
+    assert_dns_works() {
+        local n=0
+        while [ $n -lt 15 ]; do
+            if dig @127.0.0.1 -p 53 example.com +short +timeout=2 +tries=1 2>/dev/null \
+                 | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$'; then
+                pass "DNS resolves on :53 (A record returned)"
+                return
+            fi
+            sleep 1
+            n=$((n + 1))
+        done
+        fail "DNS did not return an A record on :53 within 15s"
+    }
+
+    # TLS handshake: cert must validate against numa's CA when connecting
+    # to a .numa SNI. Catches port-not-bound, wrong cert, missing CA file.
+    assert_tls_handshake() {
+        local port=$1 sni=${2:-numa.numa} out
+        if out=$(openssl s_client -connect "127.0.0.1:${port}" \
+                    -servername "$sni" \
+                    -CAfile /var/lib/numa/ca.pem \
+                    -verify_return_error </dev/null 2>&1); then
+            if echo "$out" | grep -q 'Verify return code: 0 (ok)'; then
+                pass "TLS handshake + cert chain verified on :${port}"
+            else
+                fail "TLS handshake on :${port} did not report 'Verify return code: 0'"
+            fi
+        else
+            fail "openssl s_client failed connecting to :${port}"
+        fi
+    }
+
+    assert_http_responds() {
+        local code
+        code=$(curl -s -o /dev/null -w "%{http_code}" --max-time 3 http://127.0.0.1/ || echo 000)
+        if [ "$code" != "000" ]; then
+            pass "HTTP responds on :80 (status $code)"
+        else
+            fail "HTTP :80 connection failed"
+        fi
+    }
+
+    assert_api_healthy() {
+        if curl -sf --max-time 3 http://127.0.0.1:5380/health >/dev/null; then
+            pass "API /health OK on :5380"
+        else
+            fail "API /health failed on :5380"
+        fi
+    }
+
+    ca_fingerprint() {
+        openssl x509 -in /var/lib/numa/ca.pem -noout -fingerprint -sha256 2>/dev/null \
+            | sed 's/.*=//'
+    }
+
+    wait_active() {
+        local n=0
+        while [ $n -lt 20 ]; do
+            systemctl is-active --quiet numa && return 0
+            sleep 0.5
+            n=$((n + 1))
+        done
+        fail "service did not become active within 10s"
+        systemctl status numa --no-pager -l 2>&1 | head -20 || true
+        return 1
+    }
+
+    # ---- Scenario A ----
+    printf "\n=== Scenario A: fresh install — every advertised port is functional ===\n"
+    reset_state
+    "$NUMA" install >/tmp/installA.log 2>&1 || { fail "install failed"; tail -20 /tmp/installA.log; }
+    wait_active || true
+    assert_nonroot
+    assert_dns_works
+    assert_tls_handshake 853
+    assert_tls_handshake 443
+    assert_http_responds
+    assert_api_healthy
+
+    # ---- Scenario B ----
+    # Pre-drop installs left /var/lib/numa as a plain root-owned tree.
+    # Flattening the current DynamicUser layout back into that shape
+    # simulates the upgrade path without needing an actual old binary.
+    printf "\n=== Scenario B: CA fingerprint survives upgrade from pre-drop layout ===\n"
+    fp_before=$(ca_fingerprint)
+    if [ -z "$fp_before" ]; then
+        fail "could not read initial CA fingerprint (skipping scenario B)"
+    else
+        echo "  CA fingerprint before: $fp_before"
+        "$NUMA" uninstall >/dev/null 2>&1 || true
+        tmp=$(mktemp -d)
+        cp -a /var/lib/private/numa/. "$tmp"/ 2>/dev/null || true
+        rm -rf /var/lib/numa /var/lib/private/numa
+        mv "$tmp" /var/lib/numa
+        chown -R root:root /var/lib/numa
+        chmod 755 /var/lib/numa
+        [ -f /var/lib/numa/ca.pem ] || fail "ca.pem missing from seeded legacy tree"
+
+        "$NUMA" install >/tmp/installB.log 2>&1 || { fail "upgrade install failed"; tail -20 /tmp/installB.log; }
+        wait_active || true
+        assert_nonroot
+        fp_after=$(ca_fingerprint)
+        if [ -z "$fp_after" ]; then
+            fail "could not read CA fingerprint after upgrade"
+        elif [ "$fp_before" = "$fp_after" ]; then
+            pass "CA fingerprint preserved across upgrade"
+        else
+            fail "CA fingerprint changed: before=$fp_before after=$fp_after"
+        fi
+        assert_dns_works
+    fi
+
+    # ---- Scenario C ----
+    printf "\n=== Scenario C: install from unreachable source stages binary to /usr/local/bin ===\n"
+    reset_state
+    mkdir -p /home/builder
+    chmod 700 /home/builder
+    cp "$NUMA" /home/builder/numa
+    chmod 755 /home/builder/numa
+    /home/builder/numa install >/tmp/installC.log 2>&1 || { fail "install failed"; tail -20 /tmp/installC.log; }
+    wait_active || true
+    if [ -x /usr/local/bin/numa ]; then
+        pass "binary staged to /usr/local/bin/numa"
+    else
+        fail "/usr/local/bin/numa missing after install from 0700 source"
+    fi
+    exec_line=$(grep '^ExecStart=' /etc/systemd/system/numa.service 2>/dev/null || echo "ExecStart=<unit missing>")
+    if echo "$exec_line" | grep -q '/usr/local/bin/numa'; then
+        pass "unit ExecStart points to staged path"
+    else
+        fail "unit ExecStart wrong: $exec_line"
+    fi
+    assert_nonroot
+    assert_dns_works
+
+    reset_state
+    rm -rf /home/builder
+    echo
+    if [ "$FAIL" -eq 0 ]; then
+        printf "${GREEN}── all scenarios passed ──${RESET}\n"
+        exit 0
+    else
+        printf "${RED}── some scenarios failed ──${RESET}\n"
+        exit 1
+    fi
+fi
+
+# ============================================================
+# Mode A: host-side bootstrap
+# ============================================================
+set -e
+cd "$(dirname "$0")/../.."
+
+IMAGE=numa-install-systemd:local
+CONTAINER="numa-install-systemd-$$"
+trap 'docker rm -f "$CONTAINER" >/dev/null 2>&1 || true' EXIT
+
+echo "── building systemd-in-container image (cached after first run) ──"
+docker build --quiet -t "$IMAGE" -f - . <<'DOCKERFILE' >/dev/null
+FROM ubuntu:24.04
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update -qq && apt-get install -y -qq \
+      systemd systemd-sysv systemd-resolved \
+      ca-certificates curl build-essential \
+      pkg-config libssl-dev cmake make perl \
+      dnsutils iproute2 openssl \
+    && rm -rf /var/lib/apt/lists/* \
+    && for u in dev-hugepages.mount sys-fs-fuse-connections.mount \
+                systemd-logind.service getty.target console-getty.service; do \
+         systemctl mask $u; \
+       done
+STOPSIGNAL SIGRTMIN+3
+CMD ["/lib/systemd/systemd"]
+DOCKERFILE
+
+echo "── starting systemd container ──"
+docker run -d --name "$CONTAINER" \
+    --privileged --cgroupns=host \
+    --tmpfs /run --tmpfs /run/lock --tmpfs /tmp:exec \
+    -v "$PWD:/src:ro" \
+    -v numa-install-systemd-cargo:/root/.cargo \
+    -v numa-install-systemd-work:/work \
+    "$IMAGE" >/dev/null
+
+# Wait for systemd to be up
+for _ in $(seq 1 30); do
+    state=$(docker exec "$CONTAINER" systemctl is-system-running 2>&1 || true)
+    case "$state" in running|degraded) break ;; esac
+    sleep 0.5
+done
+
+echo "── copying source into /work (writable) ──"
+docker exec "$CONTAINER" bash -c '
+mkdir -p /work
+tar -C /src --exclude=./target --exclude=./.git --exclude=./.claude -cf - . | tar -C /work -xf -
+'
+
+echo "── rustup + cargo build --release --locked ──"
+docker exec "$CONTAINER" bash -c '
+set -e
+if ! command -v cargo &>/dev/null; then
+    curl -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal --quiet
+fi
+. "$HOME/.cargo/env"
+cd /work
+cargo build --release --locked 2>&1 | tail -5
+'
+
+echo "── running scenarios ──"
+docker exec -e NUMA_INSIDE=1 "$CONTAINER" bash /src/tests/docker/install-systemd.sh

tests/docker/self-resolver-loop.sh

@@ -0,0 +1,155 @@
+#!/usr/bin/env bash
+#
+# Reproducer for issue #122 — chicken-and-egg when numa is its own system
+# resolver (HAOS add-on, Pi-hole-style container, laptop with
+# resolv.conf → 127.0.0.1).
+#
+# Topology:
+#   container /etc/resolv.conf  →  nameserver 127.0.0.1
+#   numa bound on :53           →  upstream DoH by hostname (quad9)
+#   numa boots → spawns blocklist download
+#   reqwest::get → getaddrinfo("cdn.jsdelivr.net")
+#     → loopback UDP :53 → numa → cache miss → DoH upstream
+#     → getaddrinfo("dns.quad9.net") → same loop → glibc EAI_AGAIN
+#
+# Expected on master: both assertions FAIL (bug reproduced).
+# Expected after bootstrap-IP fix: both assertions PASS.
+#
+# Requirements: docker (with internet access for external lists/DoH)
+# Usage:        ./tests/docker/self-resolver-loop.sh
+
+set -euo pipefail
+
+cd "$(dirname "$0")/../.."
+
+GREEN="\033[32m"; RED="\033[31m"; RESET="\033[0m"
+
+pass() { printf "  ${GREEN}✓${RESET} %s\n" "$1"; }
+fail() { printf "  ${RED}✗${RESET} %s\n" "$1"; printf "    %s\n" "$2"; FAILED=$((FAILED+1)); }
+FAILED=0
+
+OUT=/tmp/numa-self-resolver.out
+
+echo "── self-resolver-loop: building + reproducing on debian:bookworm ──"
+echo "  (first run is slow: image pull + cold cargo build, ~5-8 min)"
+echo
+
+docker run --rm \
+    -v "$PWD:/src:ro" \
+    -v numa-self-resolver-cargo:/root/.cargo \
+    -v numa-self-resolver-target:/work/target \
+    debian:bookworm bash -c '
+set -e
+
+# Phase 1: install deps + build with the container DNS as given by Docker
+# (resolves deb.debian.org, static.rust-lang.org, crates.io).
+apt-get update -qq && apt-get install -y -qq curl build-essential dnsutils 2>&1 | tail -3
+
+if ! command -v cargo &>/dev/null; then
+    curl -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal --quiet
+fi
+. "$HOME/.cargo/env"
+
+mkdir -p /work
+tar -C /src --exclude=./target --exclude=./.git -cf - . | tar -C /work -xf -
+cd /work
+
+echo "── cargo build --release --locked ──"
+cargo build --release --locked 2>&1 | tail -5
+echo
+
+# Phase 2: flip system DNS to numa itself — this is the pathological
+# topology from issue #122 (HAOS add-on, resolv.conf → 127.0.0.1).
+# Everything after this point, any getaddrinfo call inside numa loops
+# back through :53.
+echo "nameserver 127.0.0.1" > /etc/resolv.conf
+echo "── /etc/resolv.conf inside container (post-flip) ──"
+cat /etc/resolv.conf
+echo
+
+cat > /tmp/numa.toml <<CONF
+[server]
+bind_addr = "0.0.0.0:53"
+api_port = 5380
+api_bind_addr = "127.0.0.1"
+data_dir = "/tmp/numa-data"
+
+[upstream]
+mode = "forward"
+address = ["https://dns.quad9.net/dns-query"]
+timeout_ms = 3000
+
+[blocking]
+enabled = true
+lists = ["https://cdn.jsdelivr.net/gh/hagezi/dns-blocklists@latest/hosts/pro.txt"]
+CONF
+
+mkdir -p /tmp/numa-data
+
+echo "── starting numa ──"
+RUST_LOG=info ./target/release/numa /tmp/numa.toml > /tmp/numa.log 2>&1 &
+NUMA_PID=$!
+
+# Wait up to 120s for blocklist to populate.
+# Retry delays 2+10+30s = 42s, plus ~4 × ~10s getaddrinfo timeouts under
+# self-loop = ~82s worst case. 120s leaves headroom.
+LOADED=0
+for i in $(seq 1 120); do
+    LOADED=$(curl -sf http://127.0.0.1:5380/blocking/stats 2>/dev/null \
+        | grep -o "\"domains_loaded\":[0-9]*" | cut -d: -f2 || echo 0)
+    [ "${LOADED:-0}" -gt 100 ] && break
+    sleep 1
+done
+
+# First cold DoH query — time it.
+START=$(date +%s%N)
+dig @127.0.0.1 example.com A +time=15 +tries=1 > /tmp/dig.out 2>&1 || true
+END=$(date +%s%N)
+LATENCY_MS=$(( (END - START) / 1000000 ))
+STATUS=$(grep -oE "status: [A-Z]+" /tmp/dig.out | head -1 || echo "status: TIMEOUT")
+
+kill $NUMA_PID 2>/dev/null || true
+wait $NUMA_PID 2>/dev/null || true
+
+echo
+echo "=== RESULT ==="
+echo "domains_loaded=$LOADED"
+echo "first_query_latency_ms=$LATENCY_MS"
+echo "first_query_${STATUS// /_}"
+echo
+echo "=== numa.log (tail 40) ==="
+tail -40 /tmp/numa.log
+echo
+echo "=== dig.out ==="
+cat /tmp/dig.out
+' 2>&1 | tee "$OUT"
+
+echo
+echo "── assertions ──"
+
+LOADED=$(grep '^domains_loaded=' "$OUT" | tail -1 | cut -d= -f2 || echo 0)
+LATENCY=$(grep '^first_query_latency_ms=' "$OUT" | tail -1 | cut -d= -f2 || echo 999999)
+STATUS_LINE=$(grep '^first_query_status_' "$OUT" | tail -1 || echo "first_query_status_TIMEOUT")
+
+if [ "${LOADED:-0}" -gt 100 ]; then
+    pass "blocklist downloaded (domains_loaded=$LOADED)"
+else
+    fail "blocklist downloaded (got domains_loaded=${LOADED:-0}, expected >100)" \
+         "chicken-and-egg: blocklist HTTPS client has no DNS bootstrap; getaddrinfo loops through numa"
+fi
+
+if [ "${LATENCY:-999999}" -lt 2000 ]; then
+    pass "first DoH query under 2s (latency=${LATENCY}ms, $STATUS_LINE)"
+else
+    fail "first DoH query under 2s (got ${LATENCY}ms, $STATUS_LINE)" \
+         "self-loop on getaddrinfo(upstream_host); plain DoH needs bootstrap-IP symmetry with ODoH"
+fi
+
+echo
+if [ "$FAILED" -eq 0 ]; then
+    printf "${GREEN}── self-resolver-loop passed (fix is in place) ──${RESET}\n"
+    exit 0
+else
+    printf "${RED}── self-resolver-loop failed ($FAILED assertion(s)) — bug #122 reproduced ──${RESET}\n"
+    exit 1
+fi

tests/integration.sh

@@ -1,7 +1,10 @@
 #!/usr/bin/env bash
 # Integration test suite for Numa
 # Runs a test instance on port 5354, validates all features, exits with status.
-# Usage: ./tests/integration.sh [release|debug]
+# Usage:
+#   ./tests/integration.sh [release|debug]       # all suites
+#   SUITES=7 ./tests/integration.sh              # only Suite 7
+#   SUITES=1,3,7 ./tests/integration.sh          # Suites 1, 3, and 7
 
 set -euo pipefail
 
@@ -14,6 +17,14 @@ LOG="/tmp/numa-integration-test.log"
 PASSED=0
 FAILED=0
 
+# Suite filter: empty runs all; comma list runs a subset.
+SUITES="${SUITES:-}"
+should_run_suite() {
+    [ -z "$SUITES" ] && return 0
+    case ",$SUITES," in *",$1,"*) return 0;; esac
+    return 1
+}
+
 # Colors
 GREEN="\033[32m"
 RED="\033[31m"
@@ -166,6 +177,7 @@ CONF
 }
 
 # ---- Suite 1: Recursive mode + DNSSEC ----
+if should_run_suite 1; then
 echo ""
 echo "╔══════════════════════════════════════════╗"
 echo "║  Suite 1: Recursive + DNSSEC + Blocking  ║"
@@ -234,7 +246,10 @@ kill "$NUMA_PID" 2>/dev/null || true
 wait "$NUMA_PID" 2>/dev/null || true
 sleep 1
 
+fi  # end Suite 1
+
 # ---- Suite 2: Forward mode (backward compat) ----
+if should_run_suite 2; then
 echo ""
 echo "╔══════════════════════════════════════════╗"
 echo "║  Suite 2: Forward (DoH) + Blocking       ║"
@@ -261,7 +276,10 @@ enabled = true
 enabled = false
 "
 
+fi  # end Suite 2
+
 # ---- Suite 3: Forward UDP (plain, no DoH) ----
+if should_run_suite 3; then
 echo ""
 echo "╔══════════════════════════════════════════╗"
 echo "║  Suite 3: Forward (UDP) + No Blocking    ║"
@@ -307,7 +325,10 @@ kill "$NUMA_PID" 2>/dev/null || true
 wait "$NUMA_PID" 2>/dev/null || true
 sleep 1
 
+fi  # end Suite 3
+
 # ---- Suite 4: Local zones + Overrides API ----
+if should_run_suite 4; then
 echo ""
 echo "╔══════════════════════════════════════════╗"
 echo "║  Suite 4: Local Zones + Overrides API    ║"
@@ -416,7 +437,10 @@ kill "$NUMA_PID" 2>/dev/null || true
 wait "$NUMA_PID" 2>/dev/null || true
 sleep 1
 
+fi  # end Suite 4
+
 # ---- Suite 5: DNS-over-TLS (RFC 7858) ----
+if should_run_suite 5; then
 echo ""
 echo "╔══════════════════════════════════════════╗"
 echo "║  Suite 5: DNS-over-TLS (RFC 7858)        ║"
@@ -538,7 +562,10 @@ CONF
 fi
 sleep 1
 
+fi  # end Suite 5
+
 # ---- Suite 6: Proxy + DoT coexistence ----
+if should_run_suite 6; then
 echo ""
 echo "╔══════════════════════════════════════════╗"
 echo "║  Suite 6: Proxy + DoT Coexistence        ║"
@@ -698,6 +725,376 @@ CONF
     rm -rf "$NUMA_DATA"
 fi
 
+fi  # end Suite 6
+
+# ---- Suite 7: filter_aaaa (IPv4-only networks) ----
+if should_run_suite 7; then
+echo ""
+echo "╔══════════════════════════════════════════╗"
+echo "║  Suite 7: filter_aaaa                    ║"
+echo "╚══════════════════════════════════════════╝"
+
+# Config A — filter on, with a local AAAA zone to prove local data bypass.
+cat > "$CONFIG" << 'CONF'
+[server]
+bind_addr = "127.0.0.1:5354"
+api_port = 5381
+filter_aaaa = true
+
+[upstream]
+mode = "forward"
+address = "9.9.9.9"
+port = 53
+
+[cache]
+max_entries = 10000
+
+[blocking]
+enabled = false
+
+[proxy]
+enabled = false
+
+[[zones]]
+domain = "v6.test"
+record_type = "AAAA"
+value = "2001:db8::1"
+ttl = 60
+CONF
+
+RUST_LOG=info "$BINARY" "$CONFIG" > "$LOG" 2>&1 &
+NUMA_PID=$!
+sleep 3
+
+DIG="dig @127.0.0.1 -p $PORT +time=5 +tries=1"
+
+echo ""
+echo "=== filter_aaaa = true ==="
+
+# A queries must be untouched.
+check "A record resolves under filter_aaaa" \
+    "." \
+    "$($DIG google.com A +short | head -1)"
+
+# AAAA must be NOERROR (NODATA), not NXDOMAIN, not SERVFAIL.
+check "AAAA returns NOERROR (not NXDOMAIN)" \
+    "status: NOERROR" \
+    "$($DIG google.com AAAA 2>&1 | grep 'status:')"
+
+check "AAAA returns zero answers (NODATA shape)" \
+    "ANSWER: 0" \
+    "$($DIG google.com AAAA 2>&1 | grep -oE 'ANSWER: [0-9]+' | head -1)"
+
+# Local zone AAAA must survive the filter (PR claim: local data bypasses).
+check "Local [[zones]] AAAA bypasses filter" \
+    "2001:db8::1" \
+    "$($DIG v6.test AAAA +short)"
+
+# HTTPS RR: ipv6hint (SvcParamKey 6) must be stripped. Query as `type65`
+# because dig 9.10.6 (macOS) misparses `HTTPS` as a domain name; `type65`
+# works on both 9.10.6 and 9.18. Assert on the raw rdata hex (RFC 3597
+# generic format), since dig 9.10.6 doesn't pretty-print HTTPS params.
+# cloudflare.com's ipv6hint values sit under the 2606:4700 prefix —
+# checking that `26064700` is absent from the rdata hex is a precise,
+# upstream-stable signal that the TLV was stripped.
+HTTPS_OUT=$($DIG cloudflare.com type65 2>&1)
+if echo "$HTTPS_OUT" | grep -qE "cloudflare\.com\..*IN[[:space:]]+TYPE65"; then
+    HTTPS_HEX=$(echo "$HTTPS_OUT" | grep -A5 "IN[[:space:]]*TYPE65" | tr -d " \t\n")
+    if echo "$HTTPS_HEX" | grep -qi "26064700"; then
+        check "HTTPS ipv6hint stripped (2606:4700 absent from rdata)" "absent" "present"
+    else
+        check "HTTPS ipv6hint stripped (2606:4700 absent from rdata)" "absent" "absent"
+    fi
+else
+    # Upstream didn't return an HTTPS record — skip rather than false-pass.
+    printf "  ${DIM}~ HTTPS ipv6hint stripped (skipped: no HTTPS RR returned by upstream)${RESET}\n"
+fi
+
+kill "$NUMA_PID" 2>/dev/null || true
+wait "$NUMA_PID" 2>/dev/null || true
+sleep 1
+
+# Config B — filter off. Regression guard: prove AAAA answers come back
+# when the flag isn't set, so a network failure in Config A can't silently
+# pass as "filter working".
+cat > "$CONFIG" << 'CONF'
+[server]
+bind_addr = "127.0.0.1:5354"
+api_port = 5381
+
+[upstream]
+mode = "forward"
+address = "9.9.9.9"
+port = 53
+
+[cache]
+max_entries = 10000
+
+[blocking]
+enabled = false
+
+[proxy]
+enabled = false
+CONF
+
+RUST_LOG=info "$BINARY" "$CONFIG" > "$LOG" 2>&1 &
+NUMA_PID=$!
+sleep 3
+
+echo ""
+echo "=== filter_aaaa unset (regression guard) ==="
+
+check "AAAA returns real answers with filter off" \
+    ":" \
+    "$($DIG google.com AAAA +short | head -1)"
+
+kill "$NUMA_PID" 2>/dev/null || true
+wait "$NUMA_PID" 2>/dev/null || true
+sleep 1
+
+fi  # end Suite 7
+
+# ---- Suite 8: ODoH (Oblivious DoH via public relay + target) ----
+# Exercises the full client pipeline: /.well-known/odohconfigs fetch,
+# HPKE seal/unseal, URL-query target routing (RFC 9230 §5), dashboard
+# QueryPath::Odoh counter. Depends on the public ecosystem being up —
+# the probe-odoh-ecosystem.sh script guards against flaky runs.
+if should_run_suite 8; then
+echo ""
+echo "╔══════════════════════════════════════════╗"
+echo "║  Suite 8: ODoH (Anonymous DNS)           ║"
+echo "╚══════════════════════════════════════════╝"
+
+run_test_suite "ODoH via edgecompute.app relay → Cloudflare target" "
+[server]
+bind_addr = \"127.0.0.1:5354\"
+api_port = 5381
+
+[upstream]
+mode = \"odoh\"
+relay = \"https://odoh-relay.edgecompute.app/proxy\"
+target = \"https://odoh.cloudflare-dns.com/dns-query\"
+
+[cache]
+max_entries = 10000
+min_ttl = 60
+max_ttl = 86400
+
+[blocking]
+enabled = false
+
+[proxy]
+enabled = false
+"
+
+# Re-start briefly to assert ODoH-specific observability: the odoh counter
+# has to tick above zero after a query, and the stats label has to reflect
+# the oblivious path. These guard against silent regressions in the
+# QueryPath::Odoh tagging and the /stats serialisation.
+RUST_LOG=info "$BINARY" "$CONFIG" > "$LOG" 2>&1 &
+NUMA_PID=$!
+for _ in $(seq 1 30); do
+    curl -sf "http://127.0.0.1:$API_PORT/health" >/dev/null 2>&1 && break
+    sleep 0.1
+done
+
+$DIG example.com A +short > /dev/null 2>&1 || true
+sleep 1
+
+STATS=$(curl -sf http://127.0.0.1:$API_PORT/stats 2>/dev/null)
+# upstream_transport.odoh lives inside the upstream_transport object.
+ODOH_COUNT=$(echo "$STATS" | grep -o '"upstream_transport":{[^}]*}' \
+    | grep -o '"odoh":[0-9]*' | cut -d: -f2)
+check "upstream_transport.odoh > 0 after a query" "[1-9]" "${ODOH_COUNT:-0}"
+
+check "Upstream label advertises odoh://" \
+    "odoh://" \
+    "$(echo "$STATS" | grep -o '"upstream":"[^"]*"')"
+
+check "Stats mode field is 'odoh'" \
+    '"mode":"odoh"' \
+    "$(echo "$STATS" | grep -o '"mode":"odoh"')"
+
+# Strict-mode failure path: a clearly-unreachable relay must produce
+# SERVFAIL without silent downgrade. We hijack the config to point at
+# an .invalid host so we don't rely on external uptime.
+kill "$NUMA_PID" 2>/dev/null || true
+wait "$NUMA_PID" 2>/dev/null || true
+sleep 1
+
+cat > "$CONFIG" << 'CONF'
+[server]
+bind_addr = "127.0.0.1:5354"
+api_port = 5381
+
+[upstream]
+mode = "odoh"
+relay = "https://relay.invalid/proxy"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+strict = true
+
+[cache]
+max_entries = 10000
+
+[blocking]
+enabled = false
+
+[proxy]
+enabled = false
+CONF
+
+RUST_LOG=info "$BINARY" "$CONFIG" > "$LOG" 2>&1 &
+NUMA_PID=$!
+for _ in $(seq 1 30); do
+    curl -sf "http://127.0.0.1:$API_PORT/health" >/dev/null 2>&1 && break
+    sleep 0.1
+done
+
+check "Strict-mode relay outage returns SERVFAIL" \
+    "SERVFAIL" \
+    "$($DIG example.com A 2>&1 | grep 'status:')"
+
+kill "$NUMA_PID" 2>/dev/null || true
+wait "$NUMA_PID" 2>/dev/null || true
+sleep 1
+
+# Negative: relay and target on the same host must be rejected at startup.
+cat > "$CONFIG" << 'CONF'
+[server]
+bind_addr = "127.0.0.1:5354"
+api_port = 5381
+
+[upstream]
+mode = "odoh"
+relay = "https://odoh.cloudflare-dns.com/proxy"
+target = "https://odoh.cloudflare-dns.com/dns-query"
+CONF
+
+STARTUP_OUT=$("$BINARY" "$CONFIG" 2>&1 || true)
+check "Same-host relay+target rejected at startup" \
+    "same host" \
+    "$STARTUP_OUT"
+
+# Guards ODoH's zero-plain-DNS-leak property: relay_ip / target_ip must
+# land in the bootstrap resolver's override map so reqwest connects direct
+# to the configured IPs instead of resolving the hostnames via plain DNS.
+# RFC 5737 TEST-NET-1 IPs (unroutable).
+cat > "$CONFIG" << 'CONF'
+[server]
+bind_addr = "127.0.0.1:5354"
+api_port = 5381
+
+[upstream]
+mode = "odoh"
+relay = "https://odoh-relay.example.com/proxy"
+target = "https://odoh-target.example.org/dns-query"
+relay_ip = "192.0.2.1"
+target_ip = "192.0.2.2"
+
+[cache]
+max_entries = 10000
+
+[blocking]
+enabled = false
+
+[proxy]
+enabled = false
+CONF
+
+RUST_LOG=info "$BINARY" "$CONFIG" > "$LOG" 2>&1 &
+NUMA_PID=$!
+for _ in $(seq 1 30); do
+    curl -sf "http://127.0.0.1:$API_PORT/health" >/dev/null 2>&1 && break
+    sleep 0.1
+done
+
+OVERRIDE_LOG=$(grep 'bootstrap resolver: host overrides' "$LOG" || true)
+check "relay_ip wired into bootstrap override map" \
+    "odoh-relay.example.com=192.0.2.1" \
+    "$OVERRIDE_LOG"
+check "target_ip wired into bootstrap override map" \
+    "odoh-target.example.org=192.0.2.2" \
+    "$OVERRIDE_LOG"
+
+kill "$NUMA_PID" 2>/dev/null || true
+wait "$NUMA_PID" 2>/dev/null || true
+
+fi  # end Suite 8
+
+# ---- Suite 9: Numa's own ODoH relay (--relay-mode) ----
+# Exercises `numa relay PORT` as a forwarding proxy to a real ODoH target.
+# Validates the RFC 9230 §5 relay behaviour: URL-query routing, content-type
+# gating, body-size cap, and /health observability.
+if should_run_suite 9; then
+echo ""
+echo "╔══════════════════════════════════════════╗"
+echo "║  Suite 9: Numa ODoH Relay (own)          ║"
+echo "╚══════════════════════════════════════════╝"
+
+RELAY_PORT=18443
+"$BINARY" relay $RELAY_PORT > "$LOG" 2>&1 &
+NUMA_PID=$!
+for _ in $(seq 1 30); do
+    curl -sf "http://127.0.0.1:$RELAY_PORT/health" >/dev/null 2>&1 && break
+    sleep 0.1
+done
+
+echo ""
+echo "=== Relay Endpoints ==="
+
+check "Health endpoint returns ok" \
+    "ok" \
+    "$(curl -sf http://127.0.0.1:$RELAY_PORT/health | head -1)"
+
+# Happy path: forwards arbitrary body to Cloudflare's ODoH target. The
+# target will reject the garbage envelope with HTTP 400 — which is exactly
+# what proves our relay faithfully forwarded (otherwise we'd see our own
+# 4xx from the relay itself).
+HAPPY_STATUS=$(curl -sS -o /dev/null -w "%{http_code}" -X POST \
+    -H "Content-Type: application/oblivious-dns-message" \
+    --data-binary "garbage-forwarded-end-to-end" \
+    "http://127.0.0.1:$RELAY_PORT/relay?targethost=odoh.cloudflare-dns.com&targetpath=/dns-query")
+check "Relay forwards to target (target rejects garbage → 400)" \
+    "400" \
+    "$HAPPY_STATUS"
+
+echo ""
+echo "=== Guards ==="
+
+check "Missing content-type → 415" \
+    "415" \
+    "$(curl -sS -o /dev/null -w '%{http_code}' -X POST --data-binary 'x' \
+        'http://127.0.0.1:'$RELAY_PORT'/relay?targethost=odoh.cloudflare-dns.com&targetpath=/dns-query')"
+
+check "Oversized body (>4 KiB) → 413" \
+    "413" \
+    "$(head -c 5000 /dev/urandom | curl -sS -o /dev/null -w '%{http_code}' -X POST \
+        -H 'Content-Type: application/oblivious-dns-message' --data-binary @- \
+        'http://127.0.0.1:'$RELAY_PORT'/relay?targethost=odoh.cloudflare-dns.com&targetpath=/dns-query')"
+
+check "Invalid targethost (no dot) → 400" \
+    "400" \
+    "$(curl -sS -o /dev/null -w '%{http_code}' -X POST \
+        -H 'Content-Type: application/oblivious-dns-message' --data-binary 'x' \
+        'http://127.0.0.1:'$RELAY_PORT'/relay?targethost=invalid&targetpath=/dns-query')"
+
+echo ""
+echo "=== Counters ==="
+
+HEALTH=$(curl -sf "http://127.0.0.1:$RELAY_PORT/health")
+check "Relay counted at least one forwarded_ok" \
+    "[1-9]" \
+    "$(echo "$HEALTH" | grep 'forwarded_ok' | awk '{print $2}')"
+check "Relay counted at least one rejected_bad_request" \
+    "[1-9]" \
+    "$(echo "$HEALTH" | grep 'rejected_bad_request' | awk '{print $2}')"
+
+kill "$NUMA_PID" 2>/dev/null || true
+wait "$NUMA_PID" 2>/dev/null || true
+sleep 1
+
+fi  # end Suite 9
+
 # Summary
 echo ""
 TOTAL=$((PASSED + FAILED))

tests/probe-odoh-ecosystem.sh

@@ -0,0 +1,101 @@
+#!/usr/bin/env bash
+# Probe the public ODoH ecosystem.
+#
+# Source of truth: DNSCrypt's curated list at
+#   https://github.com/DNSCrypt/dnscrypt-resolvers/tree/master/v3
+#   - v3/odoh-servers.md  (ODoH targets)
+#   - v3/odoh-relays.md   (ODoH relays)
+#
+# As of commit 2025-09-16 ("odohrelay-crypto-sx seems to be the only ODoH
+# relay left"), the full public ecosystem is 4 targets + 1 relay. Re-run this
+# script against the upstream list before making any "only N public relays"
+# claim publicly.
+#
+# Usage: ./tests/probe-odoh-ecosystem.sh
+
+set -uo pipefail
+
+GREEN="\033[32m"
+RED="\033[31m"
+YELLOW="\033[33m"
+DIM="\033[90m"
+RESET="\033[0m"
+
+UP=0
+DOWN=0
+
+probe_target() {
+    local name="$1"
+    local host="$2"
+    local url="https://${host}/.well-known/odohconfigs"
+    local start=$(date +%s%N)
+    local headers
+    headers=$(curl -sS -o /tmp/odoh-probe-body -D - --max-time 5 -A "numa-odoh-probe/0.1" "$url" 2>&1) || {
+        DOWN=$((DOWN + 1))
+        printf "  ${RED}✗${RESET} %-25s ${DIM}unreachable${RESET}\n" "$name"
+        return
+    }
+    local elapsed_ms=$((($(date +%s%N) - start) / 1000000))
+    local status
+    status=$(echo "$headers" | head -1 | awk '{print $2}')
+    local ctype
+    ctype=$(echo "$headers" | grep -i '^content-type:' | head -1 | tr -d '\r')
+    local size
+    size=$(stat -f%z /tmp/odoh-probe-body 2>/dev/null || stat -c%s /tmp/odoh-probe-body 2>/dev/null || echo 0)
+
+    if [[ "$status" == "200" ]] && [[ "$size" -gt 0 ]]; then
+        UP=$((UP + 1))
+        printf "  ${GREEN}✓${RESET} %-25s ${DIM}%4dms  %s bytes  %s${RESET}\n" "$name" "$elapsed_ms" "$size" "$ctype"
+    else
+        DOWN=$((DOWN + 1))
+        printf "  ${RED}✗${RESET} %-25s ${DIM}status=%s size=%s${RESET}\n" "$name" "$status" "$size"
+    fi
+    rm -f /tmp/odoh-probe-body
+}
+
+probe_relay() {
+    # Relays don't expose /.well-known/odohconfigs — we just verify TLS reachability
+    # and that the endpoint responds to a malformed POST with an HTTP error
+    # (indicating the relay path exists). A real ODoH validation requires HPKE.
+    local name="$1"
+    local url="$2"
+    local start=$(date +%s%N)
+    local status
+    status=$(curl -sS -o /dev/null -w "%{http_code}" --max-time 5 -A "numa-odoh-probe/0.1" \
+        -X POST -H "Content-Type: application/oblivious-dns-message" \
+        --data-binary "" "$url" 2>&1) || {
+        DOWN=$((DOWN + 1))
+        printf "  ${RED}✗${RESET} %-25s ${DIM}unreachable${RESET}\n" "$name"
+        return
+    }
+    local elapsed_ms=$((($(date +%s%N) - start) / 1000000))
+    # Any 2xx or 4xx means the endpoint is live (TLS works, HTTP responded).
+    # 5xx or 000 (curl failure) means broken.
+    if [[ "$status" =~ ^[24] ]]; then
+        UP=$((UP + 1))
+        printf "  ${GREEN}✓${RESET} %-25s ${DIM}%4dms  status=%s (endpoint live)${RESET}\n" "$name" "$elapsed_ms" "$status"
+    else
+        DOWN=$((DOWN + 1))
+        printf "  ${RED}✗${RESET} %-25s ${DIM}status=%s${RESET}\n" "$name" "$status"
+    fi
+}
+
+echo "ODoH targets:"
+probe_target "Cloudflare"   "odoh.cloudflare-dns.com"
+probe_target "crypto.sx"    "odoh.crypto.sx"
+probe_target "Snowstorm"    "dope.snowstorm.love"
+probe_target "Tiarap"       "doh.tiarap.org"
+
+echo
+echo "ODoH relays:"
+probe_relay  "Frank Denis (Fastly)" "https://odoh-relay.edgecompute.app/proxy"
+
+echo
+TOTAL=$((UP + DOWN))
+if [[ "$DOWN" -eq 0 ]]; then
+    printf "${GREEN}All %d endpoints up${RESET}\n" "$TOTAL"
+    exit 0
+else
+    printf "${YELLOW}%d/%d up, %d down${RESET}\n" "$UP" "$TOTAL" "$DOWN"
+    exit 1
+fi